diff --git a/Makefile.am b/Makefile.am index b287fca3f2..b61b06bfb0 100644 --- a/Makefile.am +++ b/Makefile.am @@ -84,7 +84,6 @@ CORE_CFLAGS = $(AM_LIBAPR_CFLAGS) $(AM_LIBAPR_CPPFLAGS) CORE_CFLAGS += $(AM_LIBAPU_CPPFLAGS) CORE_CFLAGS += -I$(switch_srcdir)/libs/libtpl-1.5/src CORE_CFLAGS += -I$(switch_builddir)/libs/sqlite -CORE_CFLAGS += -I$(switch_srcdir)/libs/pcre CORE_CFLAGS += -I$(switch_srcdir)/libs/speex/include -Ilibs/speex/include CORE_CFLAGS += -I$(switch_srcdir)/libs/srtp/include CORE_CFLAGS += -I$(switch_srcdir)/libs/srtp/crypto/include -Ilibs/srtp/crypto/include @@ -93,7 +92,7 @@ CORE_CFLAGS += -I$(switch_builddir)/libs/tiff-4.0.2/libtiff -I$(switch_srcdir)/l APR_LIBS = $(AM_LIBAPU_LIBS) $(AM_LIBAPR_LIBS) CORE_LIBS = libs/apr-util/libaprutil-1.la libs/apr/libapr-1.la -CORE_LIBS += libs/sqlite/libsqlite3.la libs/pcre/libpcre.la libs/speex/libspeex/libspeexdsp.la libs/speex/libspeex/libspeex.la +CORE_LIBS += libs/sqlite/libsqlite3.la libs/speex/libspeex/libspeexdsp.la libs/speex/libspeex/libspeex.la if ENABLE_SRTP CORE_CFLAGS += -DENABLE_SRTP @@ -125,9 +124,9 @@ libfreeswitch_spandsp_la_SOURCES = libs/spandsp/src/plc.c libs/spandsp/src/alloc libfreeswitch_spandsp_la_CFLAGS = -Ilibs/spandsp/src $(CORE_CFLAGS) $(AM_CFLAGS) CORE_LIBS+=libfreeswitch_spandsp.la lib_LTLIBRARIES = libfreeswitch.la -libfreeswitch_la_CFLAGS = $(CORE_CFLAGS) $(AM_CFLAGS) +libfreeswitch_la_CFLAGS = $(CORE_CFLAGS) $(PCRE_CFLAGS) $(AM_CFLAGS) libfreeswitch_la_LDFLAGS = -version-info 1:0:0 $(AM_LDFLAGS) $(PLATFORM_CORE_LDFLAGS) -shared -no-undefined -libfreeswitch_la_LIBADD = $(CORE_LIBS) $(APR_LIBS) $(PLATFORM_CORE_LIBS) +libfreeswitch_la_LIBADD = $(CORE_LIBS) $(APR_LIBS) $(PCRE_LIBS) $(PLATFORM_CORE_LIBS) libfreeswitch_la_DEPENDENCIES = $(BUILT_SOURCES) if CURL_BUILTIN @@ -482,11 +481,6 @@ libs/sqlite/Makefile: libs/sqlite/configure.ac cd libs/sqlite && ./config.status @$(TOUCH_TARGET) -libs/pcre/libpcre.la: libs/pcre libs/pcre/.update - touch $(switch_srcdir)/src/include/switch.h - @cd libs/pcre && $(MAKE) - @$(TOUCH_TARGET) - SRTP_SRC = libs/srtp/srtp/srtp.c libs/srtp/srtp/ekt.c libs/srtp/crypto/cipher/cipher.c libs/srtp/crypto/cipher/null_cipher.c \ libs/srtp/crypto/cipher/aes.c libs/srtp/crypto/cipher/aes_icm.c \ libs/srtp/crypto/cipher/aes_cbc.c \ diff --git a/configure.ac b/configure.ac index 524955f8b1..cc7d480404 100644 --- a/configure.ac +++ b/configure.ac @@ -1102,6 +1102,7 @@ AM_CONDITIONAL([CURL_BUILTIN],[test "${ac_cv_use_system_curl}" != "yes"]) AC_SUBST(LIBCURL_DEPS) +PKG_CHECK_MODULES([PCRE], [libpcre >= 7.9]) AC_ARG_ENABLE(core-libedit-support, [AS_HELP_STRING([--disable-core-libedit-support], [Compile without libedit Support])], [enable_core_libedit_support="$enableval"], [enable_core_libedit_support="yes"]) @@ -1492,7 +1493,6 @@ if test "$enable_core_libedit_support" = "yes" ; then AC_CONFIG_SUBDIRS([libs/libedit]) fi -AC_CONFIG_SUBDIRS([libs/pcre]) AC_CONFIG_SUBDIRS([libs/apr]) AC_CONFIG_SUBDIRS([libs/apr-util]) AC_CONFIG_SUBDIRS([libs/ilbc]) diff --git a/debian/bootstrap.sh b/debian/bootstrap.sh index fdeda221a9..325a23b528 100755 --- a/debian/bootstrap.sh +++ b/debian/bootstrap.sh @@ -283,6 +283,7 @@ Build-Depends: # core build dpkg-dev (>= 1.15.8.12), gcc (>= 4:4.4.5), g++ (>= 4:4.4.5), libc6-dev (>= 2.11.3), make (>= 3.81), + libpcre3-dev, wget, pkg-config, # core codecs libogg-dev, diff --git a/debian/copyright b/debian/copyright index 46826f5561..48c16826ea 100644 --- a/debian/copyright +++ b/debian/copyright @@ -1821,14 +1821,6 @@ Copyright: 2008-2010, Eric des Courtis Benbria. License: MPL-1.1 -Files: libs/pcre/* -Copyright: 1997-2009 University of Cambridge - 2003 and onwards Google Inc. - 2005-2006, Google Inc - 2001 Alexander Tokarev - 2001 Peter S. Voronov aka Chem O'Dun -License: BSD-3-clause - Files: libs/silk/* Copyright: 2006-2011, Skype Limited. License: BSD-2-clause diff --git a/docs/Doxygen.conf b/docs/Doxygen.conf index c7fc40ee73..d161223268 100644 --- a/docs/Doxygen.conf +++ b/docs/Doxygen.conf @@ -1243,7 +1243,7 @@ SEARCH_INCLUDES = YES INCLUDE_PATH =../libs/apr ../libs/apr-util ../libs/curl \ ../libs/iksemel ../libs/ilbc ../libs/js \ ../libs/libedit ../libs/libg722_1 ../libs/libnatpmp \ - ../libs/libsndfile ../libs/miniupnpc ../libs/pcre \ + ../libs/libsndfile ../libs/miniupnpc \ ../libs/portaudio ../libs/sofia-sip ../libs/spandsp \ ../libs/speex ../libs/sqlite ../libs/srtp \ ../libs/tiff-4.0.2 ../libs/udns \ diff --git a/libs/.gitignore b/libs/.gitignore index 46bc93e3e0..64e09ccd9c 100644 --- a/libs/.gitignore +++ b/libs/.gitignore @@ -408,20 +408,6 @@ opal /openzap/INSTALL /openzap/Makefile.in /opus-*/ -/pcre/config.h -/pcre/Makefile -/pcre/Makefile.in -/pcre/pcre_chartables.c -/pcre/pcre-config -/pcre/pcrecpparg.h -/pcre/pcrecpp_unittest -/pcre/pcregrep -/pcre/pcre_scanner_unittest -/pcre/pcre_stringpiece.h -/pcre/pcre_stringpiece_unittest -/pcre/pcretest -/pcre/stamp-h1 -/pcre-*/ /pocketsphinx-*/ /portaudio/bin/ /portaudio/bin-stamp @@ -1012,7 +998,6 @@ opal !/libdingaling/missing !/libg722_1/config/depcomp !/libg722_1/config/missing -!/pcre/depcomp !/portaudio/bindings/cpp/build/gnu/aclocal.m4 !/portaudio/bindings/cpp/build/gnu/config.guess !/portaudio/bindings/cpp/build/gnu/config.sub diff --git a/libs/pcre/.update b/libs/pcre/.update deleted file mode 100644 index 399fbd8863..0000000000 --- a/libs/pcre/.update +++ /dev/null @@ -1 +0,0 @@ -Mon Jun 8 19:51:53 EDT 2009 diff --git a/libs/pcre/132html b/libs/pcre/132html deleted file mode 100755 index 43d1358172..0000000000 --- a/libs/pcre/132html +++ /dev/null @@ -1,296 +0,0 @@ -#! /usr/bin/perl -w - -# Script to turn PCRE man pages into HTML - - -# Subroutine to handle font changes and other escapes - -sub do_line { -my($s) = $_[0]; - -$s =~ s/ -$s =~ s/>/>/g; -$s =~ s"\\fI(.*?)\\f[RP]"$1"g; -$s =~ s"\\fB(.*?)\\f[RP]"$1"g; -$s =~ s"\\e"\\"g; -$s =~ s/(?<=Copyright )\(c\)/©/g; -$s; -} - -# Subroutine to ensure not in a paragraph - -sub end_para { -if ($inpara) - { - print TEMP "\n" if ($inpre); - print TEMP "

\n"; - } -$inpara = $inpre = 0; -$wrotetext = 0; -} - -# Subroutine to start a new paragraph - -sub new_para { -&end_para(); -print TEMP "

\n"; -$inpara = 1; -} - - -# Main program - -$innf = 0; -$inpara = 0; -$inpre = 0; -$wrotetext = 0; -$toc = 0; -$ref = 1; - -while ($#ARGV >= 0 && $ARGV[0] =~ /^-/) - { - $toc = 1 if $ARGV[0] eq "-toc"; - shift; - } - -# Initial output to STDOUT - -print < - -$ARGV[0] specification - - -

$ARGV[0] man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-End - -print "

    \n" if ($toc); - -open(TEMP, ">/tmp/$$") || die "Can't open /tmp/$$ for output\n"; - -while () - { - # Handle lines beginning with a dot - - if (/^\./) - { - # Some of the PCRE man pages used to contain instances of .br. However, - # they should have all been removed because they cause trouble in some - # (other) automated systems that translate man pages to HTML. Complain if - # we find .br or .in (another macro that is deprecated). - - if (/^\.br/ || /^\.in/) - { - print STDERR "\n*** Deprecated macro encountered - rewrite needed\n"; - print STDERR "*** $_\n"; - die "*** Processing abandoned\n"; - } - - # Instead of .br, relevent "literal" sections are enclosed in .nf/.fi. - - elsif (/^\.nf/) - { - $innf = 1; - } - - elsif (/^\.fi/) - { - $innf = 0; - } - - # Handling .sp is subtle. If it is inside a literal section, do nothing if - # the next line is a non literal text line; similarly, if not inside a - # literal section, do nothing if a literal follows. The point being that - # the 
     and
    that delimit literal sections will do the spacing. - # Always skip if no previous output. - - elsif (/^\.sp/) - { - if ($wrotetext) - { - $_ = ; - if ($inpre) - { - print TEMP "\n" if (/^[\s.]/); - } - else - { - print TEMP "
    \n
    \n" if (!/^[\s.]/); - } - redo; # Now process the lookahead line we just read - } - } - elsif (/^\.TP/ || /^\.PP/ || /^\.P/) - { - &new_para(); - } - elsif (/^\.SH\s*("?)(.*)\1/) - { - # Ignore the NAME section - if ($2 =~ /^NAME\b/) - { - ; - next; - } - - &end_para(); - my($title) = &do_line($2); - if ($toc) - { - printf("
  • $title\n", - $ref, $ref); - printf TEMP ("
    $title
    \n", - $ref, $ref); - $ref++; - } - else - { - print TEMP "
    \n$title\n
    \n"; - } - } - elsif (/^\.SS\s*("?)(.*)\1/) - { - &end_para(); - my($title) = &do_line($2); - print TEMP "
    \n$title\n
    \n"; - } - elsif (/^\.B\s*(.*)/) - { - &new_para() if (!$inpara); - $_ = &do_line($1); - s/"(.*?)"/$1/g; - print TEMP "$_\n"; - $wrotetext = 1; - } - elsif (/^\.I\s*(.*)/) - { - &new_para() if (!$inpara); - $_ = &do_line($1); - s/"(.*?)"/$1/g; - print TEMP "$_\n"; - $wrotetext = 1; - } - - # A comment that starts "HREF" takes the next line as a name that - # is turned into a hyperlink, using the text given, which might be - # in a special font. If it ends in () or (digits) or punctuation, they - # aren't part of the link. - - elsif (/^\.\\"\s*HREF/) - { - $_=; - chomp; - $_ = &do_line($_); - $_ =~ s/\s+$//; - $_ =~ /^(?:<.>)?([^<(]+)(?:\(\))?(?:<\/.>)?(?:\(\d+\))?[.,;:]?$/; - print TEMP "$_\n"; - } - - # A comment that starts "HTML" inserts literal HTML - - elsif (/^\.\\"\s*HTML\s*(.*)/) - { - print TEMP $1; - } - - # A comment that starts < inserts that HTML at the end of the - # *next* input line - so as not to get a newline between them. - - elsif (/^\.\\"\s*(<.*>)/) - { - my($markup) = $1; - $_=; - chomp; - $_ = &do_line($_); - $_ =~ s/\s+$//; - print TEMP "$_$markup\n"; - } - - # A comment that starts JOIN joins the next two lines together, with one - # space between them. Then that line is processed. This is used in some - # displays where two lines are needed for the "man" version. JOINSH works - # the same, except that it assumes this is a shell command, so removes - # continuation backslashes. - - elsif (/^\.\\"\s*JOIN(SH)?/) - { - my($one,$two); - $one = ; - $two = ; - $one =~ s/\s*\\e\s*$// if (defined($1)); - chomp($one); - $two =~ s/^\s+//; - $_ = "$one $two"; - redo; # Process the joined lines - } - - # Ignore anything not recognized - - next; - } - - # Line does not begin with a dot. Replace blank lines with new paragraphs - - if (/^\s*$/) - { - &end_para() if ($wrotetext); - next; - } - - # Convert fonts changes and output an ordinary line. Ensure that indented - # lines are marked as literal. - - $_ = &do_line($_); - &new_para() if (!$inpara); - - if (/^\s/) - { - if (!$inpre) - { - print TEMP "
    \n";
-      $inpre = 1;
-      }
-    }
-  elsif ($inpre)
-    {
-    print TEMP "
    \n"; - $inpre = 0; - } - - # Add
    to the end of a non-literal line if we are within .nf/.fi - - $_ .= "
    \n" if (!$inpre && $innf); - - print TEMP; - $wrotetext = 1; - } - -# The TOC, if present, will have been written - terminate it - -print "
\n" if ($toc); - -# Copy the remainder to the standard output - -close(TEMP); -open(TEMP, "/tmp/$$") || die "Can't open /tmp/$$ for input\n"; - -print while (); - -print < -Return to the PCRE index page. -

-End - -close(TEMP); -unlink("/tmp/$$"); - -# End diff --git a/libs/pcre/AUTHORS b/libs/pcre/AUTHORS deleted file mode 100644 index 44ff433d8d..0000000000 --- a/libs/pcre/AUTHORS +++ /dev/null @@ -1,23 +0,0 @@ -THE MAIN PCRE LIBRARY ---------------------- - -Written by: Philip Hazel -Email local part: ph10 -Email domain: cam.ac.uk - -University of Cambridge Computing Service, -Cambridge, England. - -Copyright (c) 1997-2009 University of Cambridge -All rights reserved - - -THE C++ WRAPPER LIBRARY ------------------------ - -Written by: Google Inc. - -Copyright (c) 2007-2008 Google Inc -All rights reserved - -#### diff --git a/libs/pcre/CMakeLists.txt b/libs/pcre/CMakeLists.txt deleted file mode 100644 index 344fb0f571..0000000000 --- a/libs/pcre/CMakeLists.txt +++ /dev/null @@ -1,578 +0,0 @@ -# CMakeLists.txt -# -# -# This file allows building PCRE with the CMake configuration and build -# tool. Download CMake in source or binary form from http://www.cmake.org/ -# -# Original listfile by Christian Ehrlicher -# Refined and expanded by Daniel Richard G. -# 2007-09-14 mod by Sheri so 7.4 supported configuration options can be entered -# 2007-09-19 Adjusted by PH to retain previous default settings -# 2007-12-26 (a) On UNIX, use names libpcre instead of just pcre -# (b) Ensure pcretest and pcregrep link with the local library, -# not a previously-installed one. -# (c) Add PCRE_SUPPORT_LIBREADLINE, PCRE_SUPPORT_LIBZ, and -# PCRE_SUPPORT_LIBBZ2. -# 2008-01-20 Brought up to date to include several new features by Christian -# Ehrlicher. -# 2008-01-22 Sheri added options for backward compatibility of library names -# when building with minGW: -# if "ON", NON_STANDARD_LIB_PREFIX causes shared libraries to -# be built without "lib" as prefix. (The libraries will be named -# pcre.dll, pcreposix.dll and pcrecpp.dll). -# if "ON", NON_STANDARD_LIB_SUFFIX causes shared libraries to -# be built with suffix of "-0.dll". (The libraries will be named -# libpcre-0.dll, libpcreposix-0.dll and libpcrecpp-0.dll - same names -# built by default with Configure and Make. -# 2008-01-23 PH removed the automatic build of pcredemo. -# 2008-04-22 PH modified READLINE support so it finds NCURSES when needed. -# 2008-07-03 PH updated for revised UCP property support (change of files) -# 2009-03-23 PH applied Steven Van Ingelgem's patch to change the name -# CMAKE_BINARY_DIR to PROJECT_BINARY_DIR so that it works when PCRE -# is included within another project. -# 2009-03-23 PH applied a modified version of Steven Van Ingelgem's patches to -# add options to stop the building of pcregrep and the tests, and -# to disable the final configuration report. -# 2009-04-11 PH applied Christian Ehrlicher's patch to show compiler flags that -# are set by specifying a release type. - -PROJECT(PCRE C CXX) - -CMAKE_MINIMUM_REQUIRED(VERSION 2.4.6) - -SET(CMAKE_MODULE_PATH ${PROJECT_SOURCE_DIR}/cmake) # for FindReadline.cmake - -# external packages -FIND_PACKAGE( BZip2 ) -FIND_PACKAGE( ZLIB ) -FIND_PACKAGE( Readline ) - -# Configuration checks - -INCLUDE(CheckIncludeFile) -INCLUDE(CheckIncludeFileCXX) -INCLUDE(CheckFunctionExists) -INCLUDE(CheckTypeSize) - -CHECK_INCLUDE_FILE(dirent.h HAVE_DIRENT_H) -CHECK_INCLUDE_FILE(sys/stat.h HAVE_SYS_STAT_H) -CHECK_INCLUDE_FILE(sys/types.h HAVE_SYS_TYPES_H) -CHECK_INCLUDE_FILE(unistd.h HAVE_UNISTD_H) -CHECK_INCLUDE_FILE(windows.h HAVE_WINDOWS_H) - -CHECK_INCLUDE_FILE_CXX(type_traits.h HAVE_TYPE_TRAITS_H) -CHECK_INCLUDE_FILE_CXX(bits/type_traits.h HAVE_BITS_TYPE_TRAITS_H) - -CHECK_FUNCTION_EXISTS(bcopy HAVE_BCOPY) -CHECK_FUNCTION_EXISTS(memmove HAVE_MEMMOVE) -CHECK_FUNCTION_EXISTS(strerror HAVE_STRERROR) -CHECK_FUNCTION_EXISTS(strtoll HAVE_STRTOLL) -CHECK_FUNCTION_EXISTS(strtoq HAVE_STRTOQ) -CHECK_FUNCTION_EXISTS(_strtoi64 HAVE__STRTOI64) - -CHECK_TYPE_SIZE("long long" LONG_LONG) -CHECK_TYPE_SIZE("unsigned long long" UNSIGNED_LONG_LONG) - -# User-configurable options -# -# (Note: CMakeSetup displays these in alphabetical order, regardless of -# the order we use here) - -SET(BUILD_SHARED_LIBS OFF CACHE BOOL - "Build shared libraries instead of static ones.") - -OPTION(PCRE_BUILD_PCRECPP "Build the PCRE C++ library (pcrecpp)." ON) - -SET(PCRE_EBCDIC OFF CACHE BOOL - "Use EBCDIC coding instead of ASCII. (This is rarely used outside of mainframe systems)") - -SET(PCRE_LINK_SIZE "2" CACHE STRING - "Internal link size (2, 3 or 4 allowed). See LINK_SIZE in config.h.in for details.") - -SET(PCRE_MATCH_LIMIT "10000000" CACHE STRING - "Default limit on internal looping. See MATCH_LIMIT in config.h.in for details.") - -SET(PCRE_MATCH_LIMIT_RECURSION "MATCH_LIMIT" CACHE STRING - "Default limit on internal recursion. See MATCH_LIMIT_RECURSION in config.h.in for details.") - -SET(PCRE_NEWLINE "LF" CACHE STRING - "What to recognize as a newline (one of CR, LF, CRLF, ANY, ANYCRLF).") - -SET(PCRE_NO_RECURSE OFF CACHE BOOL - "If ON, then don't use stack recursion when matching. See NO_RECURSE in config.h.in for details.") - -SET(PCRE_POSIX_MALLOC_THRESHOLD "10" CACHE STRING - "Threshold for malloc() usage. See POSIX_MALLOC_THRESHOLD in config.h.in for details.") - -SET(PCRE_SUPPORT_UNICODE_PROPERTIES OFF CACHE BOOL - "Enable support for Unicode properties. (If set, UTF-8 support will be enabled as well)") - -SET(PCRE_SUPPORT_UTF8 OFF CACHE BOOL - "Enable support for the Unicode UTF-8 encoding.") - -SET(PCRE_SUPPORT_BSR_ANYCRLF OFF CACHE BOOL - "ON=Backslash-R matches only LF CR and CRLF, OFF=Backslash-R matches all Unicode Linebreaks") - -OPTION(PCRE_SHOW_REPORT "Show the final configuration report" ON) -OPTION(PCRE_BUILD_PCREGREP "Build pcregrep" ON) -OPTION(PCRE_BUILD_TESTS "Build the tests" ON) - -IF (PCRE_BUILD_TESTS) - IF (NOT PCRE_BUILD_PCREGREP) - MESSAGE(STATUS "** Building tests requires pcregrep: PCRE_BUILD_PCREGREP forced ON") - SET(PCRE_BUILD_PCREGREP ON) - ENDIF(NOT PCRE_BUILD_PCREGREP) -ENDIF(PCRE_BUILD_TESTS) - -IF (MINGW) - OPTION(NON_STANDARD_LIB_PREFIX - "ON=Shared libraries built in mingw will be named pcre.dll, etc., instead of libpcre.dll, etc." - OFF) - - OPTION(NON_STANDARD_LIB_SUFFIX - "ON=Shared libraries built in mingw will be named libpcre-0.dll, etc., instead of libpcre.dll, etc." - OFF) -ENDIF(MINGW) - -# bzip2 lib -IF(BZIP2_FOUND) - OPTION (PCRE_SUPPORT_LIBBZ2 "Enable support for linking pcregrep with libbz2." ON) -ENDIF(BZIP2_FOUND) -IF(PCRE_SUPPORT_LIBBZ2) - INCLUDE_DIRECTORIES(${BZIP2_INCLUDE_DIR}) -ENDIF(PCRE_SUPPORT_LIBBZ2) - -# zlib -IF(ZLIB_FOUND) - OPTION (PCRE_SUPPORT_LIBZ "Enable support for linking pcregrep with libz." ON) -ENDIF(ZLIB_FOUND) -IF(PCRE_SUPPORT_LIBZ) - INCLUDE_DIRECTORIES(${ZLIB_INCLUDE_DIR}) -ENDIF(PCRE_SUPPORT_LIBZ) - -# readline lib -IF(READLINE_FOUND) - OPTION (PCRE_SUPPORT_LIBREADLINE "Enable support for linking pcretest with libreadline." ON) -ENDIF(READLINE_FOUND) -IF(PCRE_SUPPORT_LIBREADLINE) - INCLUDE_DIRECTORIES(${READLINE_INCLUDE_DIR}) -ENDIF(PCRE_SUPPORT_LIBREADLINE) - -# Prepare build configuration - -SET(pcre_have_type_traits 0) -SET(pcre_have_bits_type_traits 0) - -IF(HAVE_TYPE_TRAITS_H) - SET(pcre_have_type_traits 1) -ENDIF(HAVE_TYPE_TRAITS_H) - -IF(HAVE_BITS_TYPE_TRAITS_H) - SET(pcre_have_bits_type_traits 1) -ENDIF(HAVE_BITS_TYPE_TRAITS_H) - -SET(pcre_have_long_long 0) -SET(pcre_have_ulong_long 0) - -IF(HAVE_LONG_LONG) - SET(pcre_have_long_long 1) -ENDIF(HAVE_LONG_LONG) - -IF(HAVE_UNSIGNED_LONG_LONG) - SET(pcre_have_ulong_long 1) -ENDIF(HAVE_UNSIGNED_LONG_LONG) - -IF(NOT BUILD_SHARED_LIBS) - SET(PCRE_STATIC 1) -ENDIF(NOT BUILD_SHARED_LIBS) - -IF(PCRE_SUPPORT_BSR_ANYCRLF) - SET(BSR_ANYCRLF 1) -ENDIF(PCRE_SUPPORT_BSR_ANYCRLF) - -IF(PCRE_SUPPORT_UTF8 OR PCRE_SUPPORT_UNICODE_PROPERTIES) - SET(SUPPORT_UTF8 1) -ENDIF(PCRE_SUPPORT_UTF8 OR PCRE_SUPPORT_UNICODE_PROPERTIES) - -IF(PCRE_SUPPORT_UNICODE_PROPERTIES) - SET(SUPPORT_UCP 1) -ENDIF(PCRE_SUPPORT_UNICODE_PROPERTIES) - -# This next one used to contain -# SET(PCRETEST_LIBS ${READLINE_LIBRARY}) -# but I was advised to add the NCURSES test as well, along with -# some modifications to cmake/FindReadline.cmake which should -# make it possible to override the default if necessary. PH - -IF(PCRE_SUPPORT_LIBREADLINE) - SET(SUPPORT_LIBREADLINE 1) - SET(PCRETEST_LIBS ${READLINE_LIBRARY} ${NCURSES_LIBRARY}) -ENDIF(PCRE_SUPPORT_LIBREADLINE) - -IF(PCRE_SUPPORT_LIBZ) - SET(SUPPORT_LIBZ 1) - SET(PCREGREP_LIBS ${PCREGREP_LIBS} ${ZLIB_LIBRARIES}) -ENDIF(PCRE_SUPPORT_LIBZ) - -IF(PCRE_SUPPORT_LIBBZ2) - SET(SUPPORT_LIBBZ2 1) - SET(PCREGREP_LIBS ${PCREGREP_LIBS} ${BZIP2_LIBRARIES}) -ENDIF(PCRE_SUPPORT_LIBBZ2) - -SET(NEWLINE "") - -IF(PCRE_NEWLINE STREQUAL "LF") - SET(NEWLINE "10") -ENDIF(PCRE_NEWLINE STREQUAL "LF") -IF(PCRE_NEWLINE STREQUAL "CR") - SET(NEWLINE "13") -ENDIF(PCRE_NEWLINE STREQUAL "CR") -IF(PCRE_NEWLINE STREQUAL "CRLF") - SET(NEWLINE "3338") -ENDIF(PCRE_NEWLINE STREQUAL "CRLF") -IF(PCRE_NEWLINE STREQUAL "ANY") - SET(NEWLINE "-1") -ENDIF(PCRE_NEWLINE STREQUAL "ANY") -IF(PCRE_NEWLINE STREQUAL "ANYCRLF") - SET(NEWLINE "-2") -ENDIF(PCRE_NEWLINE STREQUAL "ANYCRLF") - -IF(NEWLINE STREQUAL "") - MESSAGE(FATAL_ERROR "The PCRE_NEWLINE variable must be set to one of the following values: \"LF\", \"CR\", \"CRLF\", \"ANY\", \"ANYCRLF\".") -ENDIF(NEWLINE STREQUAL "") - -IF(PCRE_EBCDIC) - SET(EBCDIC 1) -ENDIF(PCRE_EBCDIC) - -IF(PCRE_NO_RECURSE) - SET(NO_RECURSE 1) -ENDIF(PCRE_NO_RECURSE) - -# Output files -CONFIGURE_FILE(config-cmake.h.in - ${PROJECT_BINARY_DIR}/config.h - @ONLY) - -CONFIGURE_FILE(pcre.h.generic - ${PROJECT_BINARY_DIR}/pcre.h - COPYONLY) - -# What about pcre-config and libpcre.pc? - -IF(PCRE_BUILD_PCRECPP) - CONFIGURE_FILE(pcre_stringpiece.h.in - ${PROJECT_BINARY_DIR}/pcre_stringpiece.h - @ONLY) - - CONFIGURE_FILE(pcrecpparg.h.in - ${PROJECT_BINARY_DIR}/pcrecpparg.h - @ONLY) -ENDIF(PCRE_BUILD_PCRECPP) - -# Character table generation - -OPTION(PCRE_REBUILD_CHARTABLES "Rebuild char tables" OFF) -IF(PCRE_REBUILD_CHARTABLES) - ADD_EXECUTABLE(dftables dftables.c) - - GET_TARGET_PROPERTY(DFTABLES_EXE dftables LOCATION) - - ADD_CUSTOM_COMMAND( - COMMENT "Generating character tables (pcre_chartables.c) for current locale" - DEPENDS dftables - COMMAND ${DFTABLES_EXE} - ARGS ${PROJECT_BINARY_DIR}/pcre_chartables.c - OUTPUT ${PROJECT_BINARY_DIR}/pcre_chartables.c - ) -ELSE(PCRE_REBUILD_CHARTABLES) - CONFIGURE_FILE(${PROJECT_SOURCE_DIR}/pcre_chartables.c.dist - ${PROJECT_BINARY_DIR}/pcre_chartables.c - COPYONLY) -ENDIF(PCRE_REBUILD_CHARTABLES) - -# Source code - -SET(PCRE_HEADERS ${PROJECT_BINARY_DIR}/pcre.h) - -SET(PCRE_SOURCES - ${PROJECT_BINARY_DIR}/pcre_chartables.c - pcre_compile.c - pcre_config.c - pcre_dfa_exec.c - pcre_exec.c - pcre_fullinfo.c - pcre_get.c - pcre_globals.c - pcre_info.c - pcre_newline.c - pcre_maketables.c - pcre_ord2utf8.c - pcre_refcount.c - pcre_study.c - pcre_tables.c - pcre_try_flipped.c - pcre_ucd.c - pcre_valid_utf8.c - pcre_version.c - pcre_xclass.c -) - -SET(PCREPOSIX_HEADERS pcreposix.h) - -SET(PCREPOSIX_SOURCES pcreposix.c) - -SET(PCRECPP_HEADERS - pcrecpp.h - pcre_scanner.h - ${PROJECT_BINARY_DIR}/pcrecpparg.h - ${PROJECT_BINARY_DIR}/pcre_stringpiece.h -) - -SET(PCRECPP_SOURCES - pcrecpp.cc - pcre_scanner.cc - pcre_stringpiece.cc -) - -# Build setup - -ADD_DEFINITIONS(-DHAVE_CONFIG_H) - -IF(MSVC) - ADD_DEFINITIONS(-D_CRT_SECURE_NO_DEPRECATE) -ENDIF(MSVC) - -SET(CMAKE_INCLUDE_CURRENT_DIR 1) -# needed to make sure to not link debug libs -# against release libs and vice versa -IF(WIN32) - SET(CMAKE_DEBUG_POSTFIX "d") -ENDIF(WIN32) - -SET(targets) - -# Libraries -# pcre -ADD_LIBRARY(pcre ${PCRE_HEADERS} ${PCRE_SOURCES} ${PROJECT_BINARY_DIR}/config.h) -SET(targets ${targets} pcre) -ADD_LIBRARY(pcreposix ${PCREPOSIX_HEADERS} ${PCREPOSIX_SOURCES}) -SET(targets ${targets} pcreposix) -TARGET_LINK_LIBRARIES(pcreposix pcre) -IF(MINGW AND NOT PCRE_STATIC) - IF(NON_STANDARD_LIB_PREFIX) - SET_TARGET_PROPERTIES(pcre pcreposix - PROPERTIES PREFIX "" - ) - ENDIF(NON_STANDARD_LIB_PREFIX) - - IF(NON_STANDARD_LIB_SUFFIX) - SET_TARGET_PROPERTIES(pcre pcreposix - PROPERTIES SUFFIX "-0.dll" - ) - ENDIF(NON_STANDARD_LIB_SUFFIX) -ENDIF(MINGW AND NOT PCRE_STATIC) - - -# pcrecpp -IF(PCRE_BUILD_PCRECPP) - ADD_LIBRARY(pcrecpp ${PCRECPP_HEADERS} ${PCRECPP_SOURCES}) -SET(targets ${targets} pcrecpp) - TARGET_LINK_LIBRARIES(pcrecpp pcre) - - IF(MINGW AND NOT PCRE_STATIC) - IF(NON_STANDARD_LIB_PREFIX) - SET_TARGET_PROPERTIES(pcrecpp - PROPERTIES PREFIX "" - ) - ENDIF(NON_STANDARD_LIB_PREFIX) - - IF(NON_STANDARD_LIB_SUFFIX) - SET_TARGET_PROPERTIES(pcrecpp - PROPERTIES SUFFIX "-0.dll" - ) - ENDIF(NON_STANDARD_LIB_SUFFIX) - ENDIF(MINGW AND NOT PCRE_STATIC) -ENDIF(PCRE_BUILD_PCRECPP) - - -# Executables - -# Removed by PH (2008-01-23) because pcredemo shouldn't really be built -# automatically, and it gave trouble in some environments anyway. -# ADD_EXECUTABLE(pcredemo pcredemo.c) -# TARGET_LINK_LIBRARIES(pcredemo pcreposix) -# IF(NOT BUILD_SHARED_LIBS) -# # make sure to not use declspec(dllimport) in static mode on windows -# SET_TARGET_PROPERTIES(pcredemo PROPERTIES COMPILE_FLAGS "-DPCRE_STATIC") -# ENDIF(NOT BUILD_SHARED_LIBS) - -IF(PCRE_BUILD_PCREGREP) - ADD_EXECUTABLE(pcregrep pcregrep.c) - SET(targets ${targets} pcregrep) - TARGET_LINK_LIBRARIES(pcregrep pcreposix ${PCREGREP_LIBS}) -ENDIF(PCRE_BUILD_PCREGREP) - - -# Testing -IF(PCRE_BUILD_TESTS) - ENABLE_TESTING() - - ADD_EXECUTABLE(pcretest pcretest.c) - SET(targets ${targets} pcretest) - TARGET_LINK_LIBRARIES(pcretest pcreposix ${PCRETEST_LIBS}) - - IF(PCRE_BUILD_PCRECPP) - ADD_EXECUTABLE(pcrecpp_unittest pcrecpp_unittest.cc) - SET(targets ${targets} pcrecpp_unittest) - TARGET_LINK_LIBRARIES(pcrecpp_unittest pcrecpp) - IF(MINGW AND NON_STANDARD_LIB_NAMES AND NOT PCRE_STATIC) - SET_TARGET_PROPERTIES(pcrecpp - PROPERTIES PREFIX "" - ) - ENDIF(MINGW AND NON_STANDARD_LIB_NAMES AND NOT PCRE_STATIC) - - - ADD_EXECUTABLE(pcre_scanner_unittest pcre_scanner_unittest.cc) - SET(targets ${targets} pcre_scanner_unittest) - TARGET_LINK_LIBRARIES(pcre_scanner_unittest pcrecpp) - - ADD_EXECUTABLE(pcre_stringpiece_unittest pcre_stringpiece_unittest.cc) - SET(targets ${targets} pcre_stringpiece_unittest) - TARGET_LINK_LIBRARIES(pcre_stringpiece_unittest pcrecpp) - ENDIF(PCRE_BUILD_PCRECPP) - - GET_TARGET_PROPERTY(PCREGREP_EXE pcregrep DEBUG_LOCATION) - GET_TARGET_PROPERTY(PCRETEST_EXE pcretest DEBUG_LOCATION) - - # Write out a CTest configuration file that sets some needed environment - # variables for the test scripts. - # - FILE(WRITE ${PROJECT_BINARY_DIR}/CTestCustom.ctest - "# This is a generated file. - SET(ENV{srcdir} ${PROJECT_SOURCE_DIR}) - SET(ENV{pcregrep} ${PCREGREP_EXE}) - SET(ENV{pcretest} ${PCRETEST_EXE}) - ") - - IF(UNIX) - ADD_TEST(pcre_test ${PROJECT_SOURCE_DIR}/RunTest) - ADD_TEST(pcre_grep_test ${PROJECT_SOURCE_DIR}/RunGrepTest) - ENDIF(UNIX) - IF(WIN32) - ADD_TEST(pcre_test cmd /C ${PROJECT_SOURCE_DIR}/RunTest.bat) - ENDIF(WIN32) - - GET_TARGET_PROPERTY(PCRECPP_UNITTEST_EXE - pcrecpp_unittest - DEBUG_LOCATION) - - GET_TARGET_PROPERTY(PCRE_SCANNER_UNITTEST_EXE - pcre_scanner_unittest - DEBUG_LOCATION) - - GET_TARGET_PROPERTY(PCRE_STRINGPIECE_UNITTEST_EXE - pcre_stringpiece_unittest - DEBUG_LOCATION) - - ADD_TEST(pcrecpp_test ${PCRECPP_UNITTEST_EXE}) - ADD_TEST(pcre_scanner_test ${PCRE_SCANNER_UNITTEST_EXE}) - ADD_TEST(pcre_stringpiece_test ${PCRE_STRINGPIECE_UNITTEST_EXE}) -ENDIF(PCRE_BUILD_TESTS) - -# Installation -SET(CMAKE_INSTALL_ALWAYS 1) - -INSTALL(TARGETS ${targets} - RUNTIME DESTINATION bin - LIBRARY DESTINATION lib - ARCHIVE DESTINATION lib) - -INSTALL(FILES ${PCRE_HEADERS} ${PCREPOSIX_HEADERS} DESTINATION include) - -FILE(GLOB html ${PROJECT_SOURCE_DIR}/doc/html/*.html) -FILE(GLOB man1 ${PROJECT_SOURCE_DIR}/doc/*.1) -FILE(GLOB man3 ${PROJECT_SOURCE_DIR}/doc/*.3) - -IF(PCRE_BUILD_PCRECPP) - INSTALL(FILES ${PCRECPP_HEADERS} DESTINATION include) -ELSE(PCRE_BUILD_PCRECPP) - # Remove pcrecpp.3 - FOREACH(man ${man3}) - GET_FILENAME_COMPONENT(man_tmp ${man} NAME) - IF(NOT man_tmp STREQUAL "pcrecpp.3") - SET(man3_new ${man3} ${man}) - ENDIF(NOT man_tmp STREQUAL "pcrecpp.3") - ENDFOREACH(man ${man3}) - SET(man3 ${man3_new}) -ENDIF(PCRE_BUILD_PCRECPP) - - -INSTALL(FILES ${man1} DESTINATION man/man1) -INSTALL(FILES ${man3} DESTINATION man/man3) -INSTALL(FILES ${html} DESTINATION share/doc/pcre/html) - -# help, only for nice output -IF(BUILD_SHARED_LIBS) - SET(BUILD_STATIC_LIBS OFF) -ELSE(BUILD_SHARED_LIBS) - SET(BUILD_STATIC_LIBS ON) -ENDIF(BUILD_SHARED_LIBS) - -IF(PCRE_SHOW_REPORT) - STRING(TOUPPER "${CMAKE_BUILD_TYPE}" buildtype) - IF (CMAKE_C_FLAGS) - SET(cfsp " ") - ENDIF(CMAKE_C_FLAGS) - IF (CMAKE_CXX_FLAGS) - SET(cxxfsp " ") - ENDIF(CMAKE_CXX_FLAGS) - MESSAGE(STATUS "") - MESSAGE(STATUS "") - MESSAGE(STATUS "PCRE configuration summary:") - MESSAGE(STATUS "") - MESSAGE(STATUS " Install prefix .................. : ${CMAKE_INSTALL_PREFIX}") - MESSAGE(STATUS " C compiler ...................... : ${CMAKE_C_COMPILER}") - MESSAGE(STATUS " C++ compiler .................... : ${CMAKE_CXX_COMPILER}") - MESSAGE(STATUS " C compiler flags ................ : ${CMAKE_C_FLAGS}${cfsp}${CMAKE_C_FLAGS_${buildtype}}") - MESSAGE(STATUS " C++ compiler flags .............. : ${CMAKE_CXX_FLAGS}${cxxfsp}${CMAKE_CXX_FLAGS_${buildtype}}") - MESSAGE(STATUS "") - MESSAGE(STATUS " Build C++ library ............... : ${PCRE_BUILD_PCRECPP}") - MESSAGE(STATUS " Enable UTF-8 support ............ : ${PCRE_SUPPORT_UNICODE_PROPERTIES}") - MESSAGE(STATUS " Unicode properties .............. : ${PCRE_SUPPORT_UNICODE_PROPERTIES}") - MESSAGE(STATUS " Newline char/sequence ........... : ${PCRE_NEWLINE}") - MESSAGE(STATUS " \\R matches only ANYCRLF ......... : ${PCRE_SUPPORT_BSR_ANYCRLF}") - MESSAGE(STATUS " EBCDIC coding ................... : ${PCRE_EBCDIC}") - MESSAGE(STATUS " Rebuild char tables ............. : ${PCRE_REBUILD_CHARTABLES}") - MESSAGE(STATUS " No stack recursion .............. : ${PCRE_NO_RECURSE}") - MESSAGE(STATUS " POSIX mem threshold ............. : ${PCRE_POSIX_MALLOC_THRESHOLD}") - MESSAGE(STATUS " Internal link size .............. : ${PCRE_LINK_SIZE}") - MESSAGE(STATUS " Match limit ..................... : ${PCRE_MATCH_LIMIT}") - MESSAGE(STATUS " Match limit recursion ........... : ${PCRE_MATCH_LIMIT_RECURSION}") - MESSAGE(STATUS " Build shared libs ............... : ${BUILD_SHARED_LIBS}") - MESSAGE(STATUS " Build static libs ............... : ${BUILD_STATIC_LIBS}") - MESSAGE(STATUS " Build pcregrep .................. : ${PCRE_BUILD_PCREGREP}") - MESSAGE(STATUS " Build tests (implies pcretest) .. : ${PCRE_BUILD_TESTS}") - IF(ZLIB_FOUND) - MESSAGE(STATUS " Link pcregrep with libz ......... : ${PCRE_SUPPORT_LIBZ}") - ELSE(ZLIB_FOUND) - MESSAGE(STATUS " Link pcregrep with libz ......... : None" ) - ENDIF(ZLIB_FOUND) - IF(BZIP2_FOUND) - MESSAGE(STATUS " Link pcregrep with libbz2 ....... : ${PCRE_SUPPORT_LIBBZ2}") - ELSE(BZIP2_FOUND) - MESSAGE(STATUS " Link pcregrep with libbz2 ....... : None" ) - ENDIF(BZIP2_FOUND) - IF(NOT PCRE_SUPPORT_LIBREADLINE) - MESSAGE(STATUS " Link pcretest with libreadline .. : None" ) - ELSE(NOT PCRE_SUPPORT_LIBREADLINE) - MESSAGE(STATUS " Link pcretest with libreadline .. : ${PCRE_SUPPORT_LIBREADLINE}") - ENDIF(NOT PCRE_SUPPORT_LIBREADLINE) - IF(MINGW AND NOT PCRE_STATIC) - MESSAGE(STATUS " Non-standard dll names (prefix) . : ${NON_STANDARD_LIB_PREFIX}") - MESSAGE(STATUS " Non-standard dll names (suffix) . : ${NON_STANDARD_LIB_SUFFIX}") - ENDIF(MINGW AND NOT PCRE_STATIC) - MESSAGE(STATUS "") -ENDIF(PCRE_SHOW_REPORT) - -# end CMakeLists.txt diff --git a/libs/pcre/COPYING b/libs/pcre/COPYING deleted file mode 100644 index 58eed01b61..0000000000 --- a/libs/pcre/COPYING +++ /dev/null @@ -1,5 +0,0 @@ -PCRE LICENCE - -Please see the file LICENCE in the PCRE distribution for licensing details. - -End diff --git a/libs/pcre/ChangeLog b/libs/pcre/ChangeLog deleted file mode 100644 index 93a5415ee7..0000000000 --- a/libs/pcre/ChangeLog +++ /dev/null @@ -1,3508 +0,0 @@ -ChangeLog for PCRE ------------------- - -Version 7.9 11-Apr-09 ---------------------- - -1. When building with support for bzlib/zlib (pcregrep) and/or readline - (pcretest), all targets were linked against these libraries. This included - libpcre, libpcreposix, and libpcrecpp, even though they do not use these - libraries. This caused unwanted dependencies to be created. This problem - has been fixed, and now only pcregrep is linked with bzlib/zlib and only - pcretest is linked with readline. - -2. The "typedef int BOOL" in pcre_internal.h that was included inside the - "#ifndef FALSE" condition by an earlier change (probably 7.8/18) has been - moved outside it again, because FALSE and TRUE are already defined in AIX, - but BOOL is not. - -3. The pcre_config() function was treating the PCRE_MATCH_LIMIT and - PCRE_MATCH_LIMIT_RECURSION values as ints, when they should be long ints. - -4. The pcregrep documentation said spaces were inserted as well as colons (or - hyphens) following file names and line numbers when outputting matching - lines. This is not true; no spaces are inserted. I have also clarified the - wording for the --colour (or --color) option. - -5. In pcregrep, when --colour was used with -o, the list of matching strings - was not coloured; this is different to GNU grep, so I have changed it to be - the same. - -6. When --colo(u)r was used in pcregrep, only the first matching substring in - each matching line was coloured. Now it goes on to look for further matches - of any of the test patterns, which is the same behaviour as GNU grep. - -7. A pattern that could match an empty string could cause pcregrep to loop; it - doesn't make sense to accept an empty string match in pcregrep, so I have - locked it out (using PCRE's PCRE_NOTEMPTY option). By experiment, this - seems to be how GNU grep behaves. - -8. The pattern (?(?=.*b)b|^) was incorrectly compiled as "match must be at - start or after a newline", because the conditional assertion was not being - correctly handled. The rule now is that both the assertion and what follows - in the first alternative must satisfy the test. - -9. If auto-callout was enabled in a pattern with a conditional group whose - condition was an assertion, PCRE could crash during matching, both with - pcre_exec() and pcre_dfa_exec(). - -10. The PCRE_DOLLAR_ENDONLY option was not working when pcre_dfa_exec() was - used for matching. - -11. Unicode property support in character classes was not working for - characters (bytes) greater than 127 when not in UTF-8 mode. - -12. Added the -M command line option to pcretest. - -14. Added the non-standard REG_NOTEMPTY option to the POSIX interface. - -15. Added the PCRE_NO_START_OPTIMIZE match-time option. - -16. Added comments and documentation about mis-use of no_arg in the C++ - wrapper. - -17. Implemented support for UTF-8 encoding in EBCDIC environments, a patch - from Martin Jerabek that uses macro names for all relevant character and - string constants. - -18. Added to pcre_internal.h two configuration checks: (a) If both EBCDIC and - SUPPORT_UTF8 are set, give an error; (b) If SUPPORT_UCP is set without - SUPPORT_UTF8, define SUPPORT_UTF8. The "configure" script handles both of - these, but not everybody uses configure. - -19. A conditional group that had only one branch was not being correctly - recognized as an item that could match an empty string. This meant that an - enclosing group might also not be so recognized, causing infinite looping - (and probably a segfault) for patterns such as ^"((?(?=[a])[^"])|b)*"$ - with the subject "ab", where knowledge that the repeated group can match - nothing is needed in order to break the loop. - -20. If a pattern that was compiled with callouts was matched using pcre_dfa_ - exec(), but without supplying a callout function, matching went wrong. - -21. If PCRE_ERROR_MATCHLIMIT occurred during a recursion, there was a memory - leak if the size of the offset vector was greater than 30. When the vector - is smaller, the saved offsets during recursion go onto a local stack - vector, but for larger vectors malloc() is used. It was failing to free - when the recursion yielded PCRE_ERROR_MATCH_LIMIT (or any other "abnormal" - error, in fact). - -22. There was a missing #ifdef SUPPORT_UTF8 round one of the variables in the - heapframe that is used only when UTF-8 support is enabled. This caused no - problem, but was untidy. - -23. Steven Van Ingelgem's patch to CMakeLists.txt to change the name - CMAKE_BINARY_DIR to PROJECT_BINARY_DIR so that it works when PCRE is - included within another project. - -24. Steven Van Ingelgem's patches to add more options to the CMake support, - slightly modified by me: - - (a) PCRE_BUILD_TESTS can be set OFF not to build the tests, including - not building pcregrep. - - (b) PCRE_BUILD_PCREGREP can be see OFF not to build pcregrep, but only - if PCRE_BUILD_TESTS is also set OFF, because the tests use pcregrep. - -25. Forward references, both numeric and by name, in patterns that made use of - duplicate group numbers, could behave incorrectly or give incorrect errors, - because when scanning forward to find the reference group, PCRE was not - taking into account the duplicate group numbers. A pattern such as - ^X(?3)(a)(?|(b)|(q))(Y) is an example. - -26. Changed a few more instances of "const unsigned char *" to USPTR, making - the feature of a custom pointer more persuasive (as requested by a user). - -27. Wrapped the definitions of fileno and isatty for Windows, which appear in - pcretest.c, inside #ifndefs, because it seems they are sometimes already - pre-defined. - -28. Added support for (*UTF8) at the start of a pattern. - -29. Arrange for flags added by the "release type" setting in CMake to be shown - in the configuration summary. - - -Version 7.8 05-Sep-08 ---------------------- - -1. Replaced UCP searching code with optimized version as implemented for Ad - Muncher (http://www.admuncher.com/) by Peter Kankowski. This uses a two- - stage table and inline lookup instead of a function, giving speed ups of 2 - to 5 times on some simple patterns that I tested. Permission was given to - distribute the MultiStage2.py script that generates the tables (it's not in - the tarball, but is in the Subversion repository). - -2. Updated the Unicode datatables to Unicode 5.1.0. This adds yet more - scripts. - -3. Change 12 for 7.7 introduced a bug in pcre_study() when a pattern contained - a group with a zero qualifier. The result of the study could be incorrect, - or the function might crash, depending on the pattern. - -4. Caseless matching was not working for non-ASCII characters in back - references. For example, /(\x{de})\1/8i was not matching \x{de}\x{fe}. - It now works when Unicode Property Support is available. - -5. In pcretest, an escape such as \x{de} in the data was always generating - a UTF-8 string, even in non-UTF-8 mode. Now it generates a single byte in - non-UTF-8 mode. If the value is greater than 255, it gives a warning about - truncation. - -6. Minor bugfix in pcrecpp.cc (change "" == ... to NULL == ...). - -7. Added two (int) casts to pcregrep when printing the difference of two - pointers, in case they are 64-bit values. - -8. Added comments about Mac OS X stack usage to the pcrestack man page and to - test 2 if it fails. - -9. Added PCRE_CALL_CONVENTION just before the names of all exported functions, - and a #define of that name to empty if it is not externally set. This is to - allow users of MSVC to set it if necessary. - -10. The PCRE_EXP_DEFN macro which precedes exported functions was missing from - the convenience functions in the pcre_get.c source file. - -11. An option change at the start of a pattern that had top-level alternatives - could cause overwriting and/or a crash. This command provoked a crash in - some environments: - - printf "/(?i)[\xc3\xa9\xc3\xbd]|[\xc3\xa9\xc3\xbdA]/8\n" | pcretest - - This potential security problem was recorded as CVE-2008-2371. - -12. For a pattern where the match had to start at the beginning or immediately - after a newline (e.g /.*anything/ without the DOTALL flag), pcre_exec() and - pcre_dfa_exec() could read past the end of the passed subject if there was - no match. To help with detecting such bugs (e.g. with valgrind), I modified - pcretest so that it places the subject at the end of its malloc-ed buffer. - -13. The change to pcretest in 12 above threw up a couple more cases when pcre_ - exec() might read past the end of the data buffer in UTF-8 mode. - -14. A similar bug to 7.3/2 existed when the PCRE_FIRSTLINE option was set and - the data contained the byte 0x85 as part of a UTF-8 character within its - first line. This applied both to normal and DFA matching. - -15. Lazy qualifiers were not working in some cases in UTF-8 mode. For example, - /^[^d]*?$/8 failed to match "abc". - -16. Added a missing copyright notice to pcrecpp_internal.h. - -17. Make it more clear in the documentation that values returned from - pcre_exec() in ovector are byte offsets, not character counts. - -18. Tidied a few places to stop certain compilers from issuing warnings. - -19. Updated the Virtual Pascal + BCC files to compile the latest v7.7, as - supplied by Stefan Weber. I made a further small update for 7.8 because - there is a change of source arrangements: the pcre_searchfuncs.c module is - replaced by pcre_ucd.c. - - -Version 7.7 07-May-08 ---------------------- - -1. Applied Craig's patch to sort out a long long problem: "If we can't convert - a string to a long long, pretend we don't even have a long long." This is - done by checking for the strtoq, strtoll, and _strtoi64 functions. - -2. Applied Craig's patch to pcrecpp.cc to restore ABI compatibility with - pre-7.6 versions, which defined a global no_arg variable instead of putting - it in the RE class. (See also #8 below.) - -3. Remove a line of dead code, identified by coverity and reported by Nuno - Lopes. - -4. Fixed two related pcregrep bugs involving -r with --include or --exclude: - - (1) The include/exclude patterns were being applied to the whole pathnames - of files, instead of just to the final components. - - (2) If there was more than one level of directory, the subdirectories were - skipped unless they satisfied the include/exclude conditions. This is - inconsistent with GNU grep (and could even be seen as contrary to the - pcregrep specification - which I improved to make it absolutely clear). - The action now is always to scan all levels of directory, and just - apply the include/exclude patterns to regular files. - -5. Added the --include_dir and --exclude_dir patterns to pcregrep, and used - --exclude_dir in the tests to avoid scanning .svn directories. - -6. Applied Craig's patch to the QuoteMeta function so that it escapes the - NUL character as backslash + 0 rather than backslash + NUL, because PCRE - doesn't support NULs in patterns. - -7. Added some missing "const"s to declarations of static tables in - pcre_compile.c and pcre_dfa_exec.c. - -8. Applied Craig's patch to pcrecpp.cc to fix a problem in OS X that was - caused by fix #2 above. (Subsequently also a second patch to fix the - first patch. And a third patch - this was a messy problem.) - -9. Applied Craig's patch to remove the use of push_back(). - -10. Applied Alan Lehotsky's patch to add REG_STARTEND support to the POSIX - matching function regexec(). - -11. Added support for the Oniguruma syntax \g, \g, \g'name', \g'n', - which, however, unlike Perl's \g{...}, are subroutine calls, not back - references. PCRE supports relative numbers with this syntax (I don't think - Oniguruma does). - -12. Previously, a group with a zero repeat such as (...){0} was completely - omitted from the compiled regex. However, this means that if the group - was called as a subroutine from elsewhere in the pattern, things went wrong - (an internal error was given). Such groups are now left in the compiled - pattern, with a new opcode that causes them to be skipped at execution - time. - -13. Added the PCRE_JAVASCRIPT_COMPAT option. This makes the following changes - to the way PCRE behaves: - - (a) A lone ] character is dis-allowed (Perl treats it as data). - - (b) A back reference to an unmatched subpattern matches an empty string - (Perl fails the current match path). - - (c) A data ] in a character class must be notated as \] because if the - first data character in a class is ], it defines an empty class. (In - Perl it is not possible to have an empty class.) The empty class [] - never matches; it forces failure and is equivalent to (*FAIL) or (?!). - The negative empty class [^] matches any one character, independently - of the DOTALL setting. - -14. A pattern such as /(?2)[]a()b](abc)/ which had a forward reference to a - non-existent subpattern following a character class starting with ']' and - containing () gave an internal compiling error instead of "reference to - non-existent subpattern". Fortunately, when the pattern did exist, the - compiled code was correct. (When scanning forwards to check for the - existencd of the subpattern, it was treating the data ']' as terminating - the class, so got the count wrong. When actually compiling, the reference - was subsequently set up correctly.) - -15. The "always fail" assertion (?!) is optimzed to (*FAIL) by pcre_compile; - it was being rejected as not supported by pcre_dfa_exec(), even though - other assertions are supported. I have made pcre_dfa_exec() support - (*FAIL). - -16. The implementation of 13c above involved the invention of a new opcode, - OP_ALLANY, which is like OP_ANY but doesn't check the /s flag. Since /s - cannot be changed at match time, I realized I could make a small - improvement to matching performance by compiling OP_ALLANY instead of - OP_ANY for "." when DOTALL was set, and then removing the runtime tests - on the OP_ANY path. - -17. Compiling pcretest on Windows with readline support failed without the - following two fixes: (1) Make the unistd.h include conditional on - HAVE_UNISTD_H; (2) #define isatty and fileno as _isatty and _fileno. - -18. Changed CMakeLists.txt and cmake/FindReadline.cmake to arrange for the - ncurses library to be included for pcretest when ReadLine support is - requested, but also to allow for it to be overridden. This patch came from - Daniel Bergström. - -19. There was a typo in the file ucpinternal.h where f0_rangeflag was defined - as 0x00f00000 instead of 0x00800000. Luckily, this would not have caused - any errors with the current Unicode tables. Thanks to Peter Kankowski for - spotting this. - - -Version 7.6 28-Jan-08 ---------------------- - -1. A character class containing a very large number of characters with - codepoints greater than 255 (in UTF-8 mode, of course) caused a buffer - overflow. - -2. Patch to cut out the "long long" test in pcrecpp_unittest when - HAVE_LONG_LONG is not defined. - -3. Applied Christian Ehrlicher's patch to update the CMake build files to - bring them up to date and include new features. This patch includes: - - - Fixed PH's badly added libz and libbz2 support. - - Fixed a problem with static linking. - - Added pcredemo. [But later removed - see 7 below.] - - Fixed dftables problem and added an option. - - Added a number of HAVE_XXX tests, including HAVE_WINDOWS_H and - HAVE_LONG_LONG. - - Added readline support for pcretest. - - Added an listing of the option settings after cmake has run. - -4. A user submitted a patch to Makefile that makes it easy to create - "pcre.dll" under mingw when using Configure/Make. I added stuff to - Makefile.am that cause it to include this special target, without - affecting anything else. Note that the same mingw target plus all - the other distribution libraries and programs are now supported - when configuring with CMake (see 6 below) instead of with - Configure/Make. - -5. Applied Craig's patch that moves no_arg into the RE class in the C++ code. - This is an attempt to solve the reported problem "pcrecpp::no_arg is not - exported in the Windows port". It has not yet been confirmed that the patch - solves the problem, but it does no harm. - -6. Applied Sheri's patch to CMakeLists.txt to add NON_STANDARD_LIB_PREFIX and - NON_STANDARD_LIB_SUFFIX for dll names built with mingw when configured - with CMake, and also correct the comment about stack recursion. - -7. Remove the automatic building of pcredemo from the ./configure system and - from CMakeLists.txt. The whole idea of pcredemo.c is that it is an example - of a program that users should build themselves after PCRE is installed, so - building it automatically is not really right. What is more, it gave - trouble in some build environments. - -8. Further tidies to CMakeLists.txt from Sheri and Christian. - - -Version 7.5 10-Jan-08 ---------------------- - -1. Applied a patch from Craig: "This patch makes it possible to 'ignore' - values in parens when parsing an RE using the C++ wrapper." - -2. Negative specials like \S did not work in character classes in UTF-8 mode. - Characters greater than 255 were excluded from the class instead of being - included. - -3. The same bug as (2) above applied to negated POSIX classes such as - [:^space:]. - -4. PCRECPP_STATIC was referenced in pcrecpp_internal.h, but nowhere was it - defined or documented. It seems to have been a typo for PCRE_STATIC, so - I have changed it. - -5. The construct (?&) was not diagnosed as a syntax error (it referenced the - first named subpattern) and a construct such as (?&a) would reference the - first named subpattern whose name started with "a" (in other words, the - length check was missing). Both these problems are fixed. "Subpattern name - expected" is now given for (?&) (a zero-length name), and this patch also - makes it give the same error for \k'' (previously it complained that that - was a reference to a non-existent subpattern). - -6. The erroneous patterns (?+-a) and (?-+a) give different error messages; - this is right because (?- can be followed by option settings as well as by - digits. I have, however, made the messages clearer. - -7. Patterns such as (?(1)a|b) (a pattern that contains fewer subpatterns - than the number used in the conditional) now cause a compile-time error. - This is actually not compatible with Perl, which accepts such patterns, but - treats the conditional as always being FALSE (as PCRE used to), but it - seems to me that giving a diagnostic is better. - -8. Change "alphameric" to the more common word "alphanumeric" in comments - and messages. - -9. Fix two occurrences of "backslash" in comments that should have been - "backspace". - -10. Remove two redundant lines of code that can never be obeyed (their function - was moved elsewhere). - -11. The program that makes PCRE's Unicode character property table had a bug - which caused it to generate incorrect table entries for sequences of - characters that have the same character type, but are in different scripts. - It amalgamated them into a single range, with the script of the first of - them. In other words, some characters were in the wrong script. There were - thirteen such cases, affecting characters in the following ranges: - - U+002b0 - U+002c1 - U+0060c - U+0060d - U+0061e - U+00612 - U+0064b - U+0065e - U+0074d - U+0076d - U+01800 - U+01805 - U+01d00 - U+01d77 - U+01d9b - U+01dbf - U+0200b - U+0200f - U+030fc - U+030fe - U+03260 - U+0327f - U+0fb46 - U+0fbb1 - U+10450 - U+1049d - -12. The -o option (show only the matching part of a line) for pcregrep was not - compatible with GNU grep in that, if there was more than one match in a - line, it showed only the first of them. It now behaves in the same way as - GNU grep. - -13. If the -o and -v options were combined for pcregrep, it printed a blank - line for every non-matching line. GNU grep prints nothing, and pcregrep now - does the same. The return code can be used to tell if there were any - non-matching lines. - -14. Added --file-offsets and --line-offsets to pcregrep. - -15. The pattern (?=something)(?R) was not being diagnosed as a potentially - infinitely looping recursion. The bug was that positive lookaheads were not - being skipped when checking for a possible empty match (negative lookaheads - and both kinds of lookbehind were skipped). - -16. Fixed two typos in the Windows-only code in pcregrep.c, and moved the - inclusion of to before rather than after the definition of - INVALID_FILE_ATTRIBUTES (patch from David Byron). - -17. Specifying a possessive quantifier with a specific limit for a Unicode - character property caused pcre_compile() to compile bad code, which led at - runtime to PCRE_ERROR_INTERNAL (-14). Examples of patterns that caused this - are: /\p{Zl}{2,3}+/8 and /\p{Cc}{2}+/8. It was the possessive "+" that - caused the error; without that there was no problem. - -18. Added --enable-pcregrep-libz and --enable-pcregrep-libbz2. - -19. Added --enable-pcretest-libreadline. - -20. In pcrecpp.cc, the variable 'count' was incremented twice in - RE::GlobalReplace(). As a result, the number of replacements returned was - double what it should be. I removed one of the increments, but Craig sent a - later patch that removed the other one (the right fix) and added unit tests - that check the return values (which was not done before). - -21. Several CMake things: - - (1) Arranged that, when cmake is used on Unix, the libraries end up with - the names libpcre and libpcreposix, not just pcre and pcreposix. - - (2) The above change means that pcretest and pcregrep are now correctly - linked with the newly-built libraries, not previously installed ones. - - (3) Added PCRE_SUPPORT_LIBREADLINE, PCRE_SUPPORT_LIBZ, PCRE_SUPPORT_LIBBZ2. - -22. In UTF-8 mode, with newline set to "any", a pattern such as .*a.*=.b.* - crashed when matching a string such as a\x{2029}b (note that \x{2029} is a - UTF-8 newline character). The key issue is that the pattern starts .*; - this means that the match must be either at the beginning, or after a - newline. The bug was in the code for advancing after a failed match and - checking that the new position followed a newline. It was not taking - account of UTF-8 characters correctly. - -23. PCRE was behaving differently from Perl in the way it recognized POSIX - character classes. PCRE was not treating the sequence [:...:] as a - character class unless the ... were all letters. Perl, however, seems to - allow any characters between [: and :], though of course it rejects as - unknown any "names" that contain non-letters, because all the known class - names consist only of letters. Thus, Perl gives an error for [[:1234:]], - for example, whereas PCRE did not - it did not recognize a POSIX character - class. This seemed a bit dangerous, so the code has been changed to be - closer to Perl. The behaviour is not identical to Perl, because PCRE will - diagnose an unknown class for, for example, [[:l\ower:]] where Perl will - treat it as [[:lower:]]. However, PCRE does now give "unknown" errors where - Perl does, and where it didn't before. - -24. Rewrite so as to remove the single use of %n from pcregrep because in some - Windows environments %n is disabled by default. - - -Version 7.4 21-Sep-07 ---------------------- - -1. Change 7.3/28 was implemented for classes by looking at the bitmap. This - means that a class such as [\s] counted as "explicit reference to CR or - LF". That isn't really right - the whole point of the change was to try to - help when there was an actual mention of one of the two characters. So now - the change happens only if \r or \n (or a literal CR or LF) character is - encountered. - -2. The 32-bit options word was also used for 6 internal flags, but the numbers - of both had grown to the point where there were only 3 bits left. - Fortunately, there was spare space in the data structure, and so I have - moved the internal flags into a new 16-bit field to free up more option - bits. - -3. The appearance of (?J) at the start of a pattern set the DUPNAMES option, - but did not set the internal JCHANGED flag - either of these is enough to - control the way the "get" function works - but the PCRE_INFO_JCHANGED - facility is supposed to tell if (?J) was ever used, so now (?J) at the - start sets both bits. - -4. Added options (at build time, compile time, exec time) to change \R from - matching any Unicode line ending sequence to just matching CR, LF, or CRLF. - -5. doc/pcresyntax.html was missing from the distribution. - -6. Put back the definition of PCRE_ERROR_NULLWSLIMIT, for backward - compatibility, even though it is no longer used. - -7. Added macro for snprintf to pcrecpp_unittest.cc and also for strtoll and - strtoull to pcrecpp.cc to select the available functions in WIN32 when the - windows.h file is present (where different names are used). [This was - reversed later after testing - see 16 below.] - -8. Changed all #include to #include "config.h". There were also - some further cases that I changed to "pcre.h". - -9. When pcregrep was used with the --colour option, it missed the line ending - sequence off the lines that it output. - -10. It was pointed out to me that arrays of string pointers cause lots of - relocations when a shared library is dynamically loaded. A technique of - using a single long string with a table of offsets can drastically reduce - these. I have refactored PCRE in four places to do this. The result is - dramatic: - - Originally: 290 - After changing UCP table: 187 - After changing error message table: 43 - After changing table of "verbs" 36 - After changing table of Posix names 22 - - Thanks to the folks working on Gregex for glib for this insight. - -11. --disable-stack-for-recursion caused compiling to fail unless -enable- - unicode-properties was also set. - -12. Updated the tests so that they work when \R is defaulted to ANYCRLF. - -13. Added checks for ANY and ANYCRLF to pcrecpp.cc where it previously - checked only for CRLF. - -14. Added casts to pcretest.c to avoid compiler warnings. - -15. Added Craig's patch to various pcrecpp modules to avoid compiler warnings. - -16. Added Craig's patch to remove the WINDOWS_H tests, that were not working, - and instead check for _strtoi64 explicitly, and avoid the use of snprintf() - entirely. This removes changes made in 7 above. - -17. The CMake files have been updated, and there is now more information about - building with CMake in the NON-UNIX-USE document. - - -Version 7.3 28-Aug-07 ---------------------- - - 1. In the rejigging of the build system that eventually resulted in 7.1, the - line "#include " was included in pcre_internal.h. The use of angle - brackets there is not right, since it causes compilers to look for an - installed pcre.h, not the version that is in the source that is being - compiled (which of course may be different). I have changed it back to: - - #include "pcre.h" - - I have a vague recollection that the change was concerned with compiling in - different directories, but in the new build system, that is taken care of - by the VPATH setting the Makefile. - - 2. The pattern .*$ when run in not-DOTALL UTF-8 mode with newline=any failed - when the subject happened to end in the byte 0x85 (e.g. if the last - character was \x{1ec5}). *Character* 0x85 is one of the "any" newline - characters but of course it shouldn't be taken as a newline when it is part - of another character. The bug was that, for an unlimited repeat of . in - not-DOTALL UTF-8 mode, PCRE was advancing by bytes rather than by - characters when looking for a newline. - - 3. A small performance improvement in the DOTALL UTF-8 mode .* case. - - 4. Debugging: adjusted the names of opcodes for different kinds of parentheses - in debug output. - - 5. Arrange to use "%I64d" instead of "%lld" and "%I64u" instead of "%llu" for - long printing in the pcrecpp unittest when running under MinGW. - - 6. ESC_K was left out of the EBCDIC table. - - 7. Change 7.0/38 introduced a new limit on the number of nested non-capturing - parentheses; I made it 1000, which seemed large enough. Unfortunately, the - limit also applies to "virtual nesting" when a pattern is recursive, and in - this case 1000 isn't so big. I have been able to remove this limit at the - expense of backing off one optimization in certain circumstances. Normally, - when pcre_exec() would call its internal match() function recursively and - immediately return the result unconditionally, it uses a "tail recursion" - feature to save stack. However, when a subpattern that can match an empty - string has an unlimited repetition quantifier, it no longer makes this - optimization. That gives it a stack frame in which to save the data for - checking that an empty string has been matched. Previously this was taken - from the 1000-entry workspace that had been reserved. So now there is no - explicit limit, but more stack is used. - - 8. Applied Daniel's patches to solve problems with the import/export magic - syntax that is required for Windows, and which was going wrong for the - pcreposix and pcrecpp parts of the library. These were overlooked when this - problem was solved for the main library. - - 9. There were some crude static tests to avoid integer overflow when computing - the size of patterns that contain repeated groups with explicit upper - limits. As the maximum quantifier is 65535, the maximum group length was - set at 30,000 so that the product of these two numbers did not overflow a - 32-bit integer. However, it turns out that people want to use groups that - are longer than 30,000 bytes (though not repeat them that many times). - Change 7.0/17 (the refactoring of the way the pattern size is computed) has - made it possible to implement the integer overflow checks in a much more - dynamic way, which I have now done. The artificial limitation on group - length has been removed - we now have only the limit on the total length of - the compiled pattern, which depends on the LINK_SIZE setting. - -10. Fixed a bug in the documentation for get/copy named substring when - duplicate names are permitted. If none of the named substrings are set, the - functions return PCRE_ERROR_NOSUBSTRING (7); the doc said they returned an - empty string. - -11. Because Perl interprets \Q...\E at a high level, and ignores orphan \E - instances, patterns such as [\Q\E] or [\E] or even [^\E] cause an error, - because the ] is interpreted as the first data character and the - terminating ] is not found. PCRE has been made compatible with Perl in this - regard. Previously, it interpreted [\Q\E] as an empty class, and [\E] could - cause memory overwriting. - -10. Like Perl, PCRE automatically breaks an unlimited repeat after an empty - string has been matched (to stop an infinite loop). It was not recognizing - a conditional subpattern that could match an empty string if that - subpattern was within another subpattern. For example, it looped when - trying to match (((?(1)X|))*) but it was OK with ((?(1)X|)*) where the - condition was not nested. This bug has been fixed. - -12. A pattern like \X?\d or \P{L}?\d in non-UTF-8 mode could cause a backtrack - past the start of the subject in the presence of bytes with the top bit - set, for example "\x8aBCD". - -13. Added Perl 5.10 experimental backtracking controls (*FAIL), (*F), (*PRUNE), - (*SKIP), (*THEN), (*COMMIT), and (*ACCEPT). - -14. Optimized (?!) to (*FAIL). - -15. Updated the test for a valid UTF-8 string to conform to the later RFC 3629. - This restricts code points to be within the range 0 to 0x10FFFF, excluding - the "low surrogate" sequence 0xD800 to 0xDFFF. Previously, PCRE allowed the - full range 0 to 0x7FFFFFFF, as defined by RFC 2279. Internally, it still - does: it's just the validity check that is more restrictive. - -16. Inserted checks for integer overflows during escape sequence (backslash) - processing, and also fixed erroneous offset values for syntax errors during - backslash processing. - -17. Fixed another case of looking too far back in non-UTF-8 mode (cf 12 above) - for patterns like [\PPP\x8a]{1,}\x80 with the subject "A\x80". - -18. An unterminated class in a pattern like (?1)\c[ with a "forward reference" - caused an overrun. - -19. A pattern like (?:[\PPa*]*){8,} which had an "extended class" (one with - something other than just ASCII characters) inside a group that had an - unlimited repeat caused a loop at compile time (while checking to see - whether the group could match an empty string). - -20. Debugging a pattern containing \p or \P could cause a crash. For example, - [\P{Any}] did so. (Error in the code for printing property names.) - -21. An orphan \E inside a character class could cause a crash. - -22. A repeated capturing bracket such as (A)? could cause a wild memory - reference during compilation. - -23. There are several functions in pcre_compile() that scan along a compiled - expression for various reasons (e.g. to see if it's fixed length for look - behind). There were bugs in these functions when a repeated \p or \P was - present in the pattern. These operators have additional parameters compared - with \d, etc, and these were not being taken into account when moving along - the compiled data. Specifically: - - (a) A item such as \p{Yi}{3} in a lookbehind was not treated as fixed - length. - - (b) An item such as \pL+ within a repeated group could cause crashes or - loops. - - (c) A pattern such as \p{Yi}+(\P{Yi}+)(?1) could give an incorrect - "reference to non-existent subpattern" error. - - (d) A pattern like (\P{Yi}{2}\277)? could loop at compile time. - -24. A repeated \S or \W in UTF-8 mode could give wrong answers when multibyte - characters were involved (for example /\S{2}/8g with "A\x{a3}BC"). - -25. Using pcregrep in multiline, inverted mode (-Mv) caused it to loop. - -26. Patterns such as [\P{Yi}A] which include \p or \P and just one other - character were causing crashes (broken optimization). - -27. Patterns such as (\P{Yi}*\277)* (group with possible zero repeat containing - \p or \P) caused a compile-time loop. - -28. More problems have arisen in unanchored patterns when CRLF is a valid line - break. For example, the unstudied pattern [\r\n]A does not match the string - "\r\nA" because change 7.0/46 below moves the current point on by two - characters after failing to match at the start. However, the pattern \nA - *does* match, because it doesn't start till \n, and if [\r\n]A is studied, - the same is true. There doesn't seem any very clean way out of this, but - what I have chosen to do makes the common cases work: PCRE now takes note - of whether there can be an explicit match for \r or \n anywhere in the - pattern, and if so, 7.0/46 no longer applies. As part of this change, - there's a new PCRE_INFO_HASCRORLF option for finding out whether a compiled - pattern has explicit CR or LF references. - -29. Added (*CR) etc for changing newline setting at start of pattern. - - -Version 7.2 19-Jun-07 ---------------------- - - 1. If the fr_FR locale cannot be found for test 3, try the "french" locale, - which is apparently normally available under Windows. - - 2. Re-jig the pcregrep tests with different newline settings in an attempt - to make them independent of the local environment's newline setting. - - 3. Add code to configure.ac to remove -g from the CFLAGS default settings. - - 4. Some of the "internals" tests were previously cut out when the link size - was not 2, because the output contained actual offsets. The recent new - "Z" feature of pcretest means that these can be cut out, making the tests - usable with all link sizes. - - 5. Implemented Stan Switzer's goto replacement for longjmp() when not using - stack recursion. This gives a massive performance boost under BSD, but just - a small improvement under Linux. However, it saves one field in the frame - in all cases. - - 6. Added more features from the forthcoming Perl 5.10: - - (a) (?-n) (where n is a string of digits) is a relative subroutine or - recursion call. It refers to the nth most recently opened parentheses. - - (b) (?+n) is also a relative subroutine call; it refers to the nth next - to be opened parentheses. - - (c) Conditions that refer to capturing parentheses can be specified - relatively, for example, (?(-2)... or (?(+3)... - - (d) \K resets the start of the current match so that everything before - is not part of it. - - (e) \k{name} is synonymous with \k and \k'name' (.NET compatible). - - (f) \g{name} is another synonym - part of Perl 5.10's unification of - reference syntax. - - (g) (?| introduces a group in which the numbering of parentheses in each - alternative starts with the same number. - - (h) \h, \H, \v, and \V match horizontal and vertical whitespace. - - 7. Added two new calls to pcre_fullinfo(): PCRE_INFO_OKPARTIAL and - PCRE_INFO_JCHANGED. - - 8. A pattern such as (.*(.)?)* caused pcre_exec() to fail by either not - terminating or by crashing. Diagnosed by Viktor Griph; it was in the code - for detecting groups that can match an empty string. - - 9. A pattern with a very large number of alternatives (more than several - hundred) was running out of internal workspace during the pre-compile - phase, where pcre_compile() figures out how much memory will be needed. A - bit of new cunning has reduced the workspace needed for groups with - alternatives. The 1000-alternative test pattern now uses 12 bytes of - workspace instead of running out of the 4096 that are available. - -10. Inserted some missing (unsigned int) casts to get rid of compiler warnings. - -11. Applied patch from Google to remove an optimization that didn't quite work. - The report of the bug said: - - pcrecpp::RE("a*").FullMatch("aaa") matches, while - pcrecpp::RE("a*?").FullMatch("aaa") does not, and - pcrecpp::RE("a*?\\z").FullMatch("aaa") does again. - -12. If \p or \P was used in non-UTF-8 mode on a character greater than 127 - it matched the wrong number of bytes. - - -Version 7.1 24-Apr-07 ---------------------- - - 1. Applied Bob Rossi and Daniel G's patches to convert the build system to one - that is more "standard", making use of automake and other Autotools. There - is some re-arrangement of the files and adjustment of comments consequent - on this. - - 2. Part of the patch fixed a problem with the pcregrep tests. The test of -r - for recursive directory scanning broke on some systems because the files - are not scanned in any specific order and on different systems the order - was different. A call to "sort" has been inserted into RunGrepTest for the - approprate test as a short-term fix. In the longer term there may be an - alternative. - - 3. I had an email from Eric Raymond about problems translating some of PCRE's - man pages to HTML (despite the fact that I distribute HTML pages, some - people do their own conversions for various reasons). The problems - concerned the use of low-level troff macros .br and .in. I have therefore - removed all such uses from the man pages (some were redundant, some could - be replaced by .nf/.fi pairs). The 132html script that I use to generate - HTML has been updated to handle .nf/.fi and to complain if it encounters - .br or .in. - - 4. Updated comments in configure.ac that get placed in config.h.in and also - arranged for config.h to be included in the distribution, with the name - config.h.generic, for the benefit of those who have to compile without - Autotools (compare pcre.h, which is now distributed as pcre.h.generic). - - 5. Updated the support (such as it is) for Virtual Pascal, thanks to Stefan - Weber: (1) pcre_internal.h was missing some function renames; (2) updated - makevp.bat for the current PCRE, using the additional files - makevp_c.txt, makevp_l.txt, and pcregexp.pas. - - 6. A Windows user reported a minor discrepancy with test 2, which turned out - to be caused by a trailing space on an input line that had got lost in his - copy. The trailing space was an accident, so I've just removed it. - - 7. Add -Wl,-R... flags in pcre-config.in for *BSD* systems, as I'm told - that is needed. - - 8. Mark ucp_table (in ucptable.h) and ucp_gentype (in pcre_ucp_searchfuncs.c) - as "const" (a) because they are and (b) because it helps the PHP - maintainers who have recently made a script to detect big data structures - in the php code that should be moved to the .rodata section. I remembered - to update Builducptable as well, so it won't revert if ucptable.h is ever - re-created. - - 9. Added some extra #ifdef SUPPORT_UTF8 conditionals into pcretest.c, - pcre_printint.src, pcre_compile.c, pcre_study.c, and pcre_tables.c, in - order to be able to cut out the UTF-8 tables in the latter when UTF-8 - support is not required. This saves 1.5-2K of code, which is important in - some applications. - - Later: more #ifdefs are needed in pcre_ord2utf8.c and pcre_valid_utf8.c - so as not to refer to the tables, even though these functions will never be - called when UTF-8 support is disabled. Otherwise there are problems with a - shared library. - -10. Fixed two bugs in the emulated memmove() function in pcre_internal.h: - - (a) It was defining its arguments as char * instead of void *. - - (b) It was assuming that all moves were upwards in memory; this was true - a long time ago when I wrote it, but is no longer the case. - - The emulated memove() is provided for those environments that have neither - memmove() nor bcopy(). I didn't think anyone used it these days, but that - is clearly not the case, as these two bugs were recently reported. - -11. The script PrepareRelease is now distributed: it calls 132html, CleanTxt, - and Detrail to create the HTML documentation, the .txt form of the man - pages, and it removes trailing spaces from listed files. It also creates - pcre.h.generic and config.h.generic from pcre.h and config.h. In the latter - case, it wraps all the #defines with #ifndefs. This script should be run - before "make dist". - -12. Fixed two fairly obscure bugs concerned with quantified caseless matching - with Unicode property support. - - (a) For a maximizing quantifier, if the two different cases of the - character were of different lengths in their UTF-8 codings (there are - some cases like this - I found 11), and the matching function had to - back up over a mixture of the two cases, it incorrectly assumed they - were both the same length. - - (b) When PCRE was configured to use the heap rather than the stack for - recursion during matching, it was not correctly preserving the data for - the other case of a UTF-8 character when checking ahead for a match - while processing a minimizing repeat. If the check also involved - matching a wide character, but failed, corruption could cause an - erroneous result when trying to check for a repeat of the original - character. - -13. Some tidying changes to the testing mechanism: - - (a) The RunTest script now detects the internal link size and whether there - is UTF-8 and UCP support by running ./pcretest -C instead of relying on - values substituted by "configure". (The RunGrepTest script already did - this for UTF-8.) The configure.ac script no longer substitutes the - relevant variables. - - (b) The debugging options /B and /D in pcretest show the compiled bytecode - with length and offset values. This means that the output is different - for different internal link sizes. Test 2 is skipped for link sizes - other than 2 because of this, bypassing the problem. Unfortunately, - there was also a test in test 3 (the locale tests) that used /B and - failed for link sizes other than 2. Rather than cut the whole test out, - I have added a new /Z option to pcretest that replaces the length and - offset values with spaces. This is now used to make test 3 independent - of link size. (Test 2 will be tidied up later.) - -14. If erroroffset was passed as NULL to pcre_compile, it provoked a - segmentation fault instead of returning the appropriate error message. - -15. In multiline mode when the newline sequence was set to "any", the pattern - ^$ would give a match between the \r and \n of a subject such as "A\r\nB". - This doesn't seem right; it now treats the CRLF combination as the line - ending, and so does not match in that case. It's only a pattern such as ^$ - that would hit this one: something like ^ABC$ would have failed after \r - and then tried again after \r\n. - -16. Changed the comparison command for RunGrepTest from "diff -u" to "diff -ub" - in an attempt to make files that differ only in their line terminators - compare equal. This works on Linux. - -17. Under certain error circumstances pcregrep might try to free random memory - as it exited. This is now fixed, thanks to valgrind. - -19. In pcretest, if the pattern /(?m)^$/g was matched against the string - "abc\r\n\r\n", it found an unwanted second match after the second \r. This - was because its rules for how to advance for /g after matching an empty - string at the end of a line did not allow for this case. They now check for - it specially. - -20. pcretest is supposed to handle patterns and data of any length, by - extending its buffers when necessary. It was getting this wrong when the - buffer for a data line had to be extended. - -21. Added PCRE_NEWLINE_ANYCRLF which is like ANY, but matches only CR, LF, or - CRLF as a newline sequence. - -22. Code for handling Unicode properties in pcre_dfa_exec() wasn't being cut - out by #ifdef SUPPORT_UCP. This did no harm, as it could never be used, but - I have nevertheless tidied it up. - -23. Added some casts to kill warnings from HP-UX ia64 compiler. - -24. Added a man page for pcre-config. - - -Version 7.0 19-Dec-06 ---------------------- - - 1. Fixed a signed/unsigned compiler warning in pcre_compile.c, shown up by - moving to gcc 4.1.1. - - 2. The -S option for pcretest uses setrlimit(); I had omitted to #include - sys/time.h, which is documented as needed for this function. It doesn't - seem to matter on Linux, but it showed up on some releases of OS X. - - 3. It seems that there are systems where bytes whose values are greater than - 127 match isprint() in the "C" locale. The "C" locale should be the - default when a C program starts up. In most systems, only ASCII printing - characters match isprint(). This difference caused the output from pcretest - to vary, making some of the tests fail. I have changed pcretest so that: - - (a) When it is outputting text in the compiled version of a pattern, bytes - other than 32-126 are always shown as hex escapes. - - (b) When it is outputting text that is a matched part of a subject string, - it does the same, unless a different locale has been set for the match - (using the /L modifier). In this case, it uses isprint() to decide. - - 4. Fixed a major bug that caused incorrect computation of the amount of memory - required for a compiled pattern when options that changed within the - pattern affected the logic of the preliminary scan that determines the - length. The relevant options are -x, and -i in UTF-8 mode. The result was - that the computed length was too small. The symptoms of this bug were - either the PCRE error "internal error: code overflow" from pcre_compile(), - or a glibc crash with a message such as "pcretest: free(): invalid next - size (fast)". Examples of patterns that provoked this bug (shown in - pcretest format) are: - - /(?-x: )/x - /(?x)(?-x: \s*#\s*)/ - /((?i)[\x{c0}])/8 - /(?i:[\x{c0}])/8 - - HOWEVER: Change 17 below makes this fix obsolete as the memory computation - is now done differently. - - 5. Applied patches from Google to: (a) add a QuoteMeta function to the C++ - wrapper classes; (b) implement a new function in the C++ scanner that is - more efficient than the old way of doing things because it avoids levels of - recursion in the regex matching; (c) add a paragraph to the documentation - for the FullMatch() function. - - 6. The escape sequence \n was being treated as whatever was defined as - "newline". Not only was this contrary to the documentation, which states - that \n is character 10 (hex 0A), but it also went horribly wrong when - "newline" was defined as CRLF. This has been fixed. - - 7. In pcre_dfa_exec.c the value of an unsigned integer (the variable called c) - was being set to -1 for the "end of line" case (supposedly a value that no - character can have). Though this value is never used (the check for end of - line is "zero bytes in current character"), it caused compiler complaints. - I've changed it to 0xffffffff. - - 8. In pcre_version.c, the version string was being built by a sequence of - C macros that, in the event of PCRE_PRERELEASE being defined as an empty - string (as it is for production releases) called a macro with an empty - argument. The C standard says the result of this is undefined. The gcc - compiler treats it as an empty string (which was what was wanted) but it is - reported that Visual C gives an error. The source has been hacked around to - avoid this problem. - - 9. On the advice of a Windows user, included and in Windows - builds of pcretest, and changed the call to _setmode() to use _O_BINARY - instead of 0x8000. Made all the #ifdefs test both _WIN32 and WIN32 (not all - of them did). - -10. Originally, pcretest opened its input and output without "b"; then I was - told that "b" was needed in some environments, so it was added for release - 5.0 to both the input and output. (It makes no difference on Unix-like - systems.) Later I was told that it is wrong for the input on Windows. I've - now abstracted the modes into two macros, to make it easier to fiddle with - them, and removed "b" from the input mode under Windows. - -11. Added pkgconfig support for the C++ wrapper library, libpcrecpp. - -12. Added -help and --help to pcretest as an official way of being reminded - of the options. - -13. Removed some redundant semicolons after macro calls in pcrecpparg.h.in - and pcrecpp.cc because they annoy compilers at high warning levels. - -14. A bit of tidying/refactoring in pcre_exec.c in the main bumpalong loop. - -15. Fixed an occurrence of == in configure.ac that should have been = (shell - scripts are not C programs :-) and which was not noticed because it works - on Linux. - -16. pcretest is supposed to handle any length of pattern and data line (as one - line or as a continued sequence of lines) by extending its input buffer if - necessary. This feature was broken for very long pattern lines, leading to - a string of junk being passed to pcre_compile() if the pattern was longer - than about 50K. - -17. I have done a major re-factoring of the way pcre_compile() computes the - amount of memory needed for a compiled pattern. Previously, there was code - that made a preliminary scan of the pattern in order to do this. That was - OK when PCRE was new, but as the facilities have expanded, it has become - harder and harder to keep it in step with the real compile phase, and there - have been a number of bugs (see for example, 4 above). I have now found a - cunning way of running the real compile function in a "fake" mode that - enables it to compute how much memory it would need, while actually only - ever using a few hundred bytes of working memory and without too many - tests of the mode. This should make future maintenance and development - easier. A side effect of this work is that the limit of 200 on the nesting - depth of parentheses has been removed (though this was never a serious - limitation, I suspect). However, there is a downside: pcre_compile() now - runs more slowly than before (30% or more, depending on the pattern). I - hope this isn't a big issue. There is no effect on runtime performance. - -18. Fixed a minor bug in pcretest: if a pattern line was not terminated by a - newline (only possible for the last line of a file) and it was a - pattern that set a locale (followed by /Lsomething), pcretest crashed. - -19. Added additional timing features to pcretest. (1) The -tm option now times - matching only, not compiling. (2) Both -t and -tm can be followed, as a - separate command line item, by a number that specifies the number of - repeats to use when timing. The default is 50000; this gives better - precision, but takes uncomfortably long for very large patterns. - -20. Extended pcre_study() to be more clever in cases where a branch of a - subpattern has no definite first character. For example, (a*|b*)[cd] would - previously give no result from pcre_study(). Now it recognizes that the - first character must be a, b, c, or d. - -21. There was an incorrect error "recursive call could loop indefinitely" if - a subpattern (or the entire pattern) that was being tested for matching an - empty string contained only one non-empty item after a nested subpattern. - For example, the pattern (?>\x{100}*)\d(?R) provoked this error - incorrectly, because the \d was being skipped in the check. - -22. The pcretest program now has a new pattern option /B and a command line - option -b, which is equivalent to adding /B to every pattern. This causes - it to show the compiled bytecode, without the additional information that - -d shows. The effect of -d is now the same as -b with -i (and similarly, /D - is the same as /B/I). - -23. A new optimization is now able automatically to treat some sequences such - as a*b as a*+b. More specifically, if something simple (such as a character - or a simple class like \d) has an unlimited quantifier, and is followed by - something that cannot possibly match the quantified thing, the quantifier - is automatically "possessified". - -24. A recursive reference to a subpattern whose number was greater than 39 - went wrong under certain circumstances in UTF-8 mode. This bug could also - have affected the operation of pcre_study(). - -25. Realized that a little bit of performance could be had by replacing - (c & 0xc0) == 0xc0 with c >= 0xc0 when processing UTF-8 characters. - -26. Timing data from pcretest is now shown to 4 decimal places instead of 3. - -27. Possessive quantifiers such as a++ were previously implemented by turning - them into atomic groups such as ($>a+). Now they have their own opcodes, - which improves performance. This includes the automatically created ones - from 23 above. - -28. A pattern such as (?=(\w+))\1: which simulates an atomic group using a - lookahead was broken if it was not anchored. PCRE was mistakenly expecting - the first matched character to be a colon. This applied both to named and - numbered groups. - -29. The ucpinternal.h header file was missing its idempotency #ifdef. - -30. I was sent a "project" file called libpcre.a.dev which I understand makes - building PCRE on Windows easier, so I have included it in the distribution. - -31. There is now a check in pcretest against a ridiculously large number being - returned by pcre_exec() or pcre_dfa_exec(). If this happens in a /g or /G - loop, the loop is abandoned. - -32. Forward references to subpatterns in conditions such as (?(2)...) where - subpattern 2 is defined later cause pcre_compile() to search forwards in - the pattern for the relevant set of parentheses. This search went wrong - when there were unescaped parentheses in a character class, parentheses - escaped with \Q...\E, or parentheses in a #-comment in /x mode. - -33. "Subroutine" calls and backreferences were previously restricted to - referencing subpatterns earlier in the regex. This restriction has now - been removed. - -34. Added a number of extra features that are going to be in Perl 5.10. On the - whole, these are just syntactic alternatives for features that PCRE had - previously implemented using the Python syntax or my own invention. The - other formats are all retained for compatibility. - - (a) Named groups can now be defined as (?...) or (?'name'...) as well - as (?P...). The new forms, as well as being in Perl 5.10, are - also .NET compatible. - - (b) A recursion or subroutine call to a named group can now be defined as - (?&name) as well as (?P>name). - - (c) A backreference to a named group can now be defined as \k or - \k'name' as well as (?P=name). The new forms, as well as being in Perl - 5.10, are also .NET compatible. - - (d) A conditional reference to a named group can now use the syntax - (?() or (?('name') as well as (?(name). - - (e) A "conditional group" of the form (?(DEFINE)...) can be used to define - groups (named and numbered) that are never evaluated inline, but can be - called as "subroutines" from elsewhere. In effect, the DEFINE condition - is always false. There may be only one alternative in such a group. - - (f) A test for recursion can be given as (?(R1).. or (?(R&name)... as well - as the simple (?(R). The condition is true only if the most recent - recursion is that of the given number or name. It does not search out - through the entire recursion stack. - - (g) The escape \gN or \g{N} has been added, where N is a positive or - negative number, specifying an absolute or relative reference. - -35. Tidied to get rid of some further signed/unsigned compiler warnings and - some "unreachable code" warnings. - -36. Updated the Unicode property tables to Unicode version 5.0.0. Amongst other - things, this adds five new scripts. - -37. Perl ignores orphaned \E escapes completely. PCRE now does the same. - There were also incompatibilities regarding the handling of \Q..\E inside - character classes, for example with patterns like [\Qa\E-\Qz\E] where the - hyphen was adjacent to \Q or \E. I hope I've cleared all this up now. - -38. Like Perl, PCRE detects when an indefinitely repeated parenthesized group - matches an empty string, and forcibly breaks the loop. There were bugs in - this code in non-simple cases. For a pattern such as ^(a()*)* matched - against aaaa the result was just "a" rather than "aaaa", for example. Two - separate and independent bugs (that affected different cases) have been - fixed. - -39. Refactored the code to abolish the use of different opcodes for small - capturing bracket numbers. This is a tidy that I avoided doing when I - removed the limit on the number of capturing brackets for 3.5 back in 2001. - The new approach is not only tidier, it makes it possible to reduce the - memory needed to fix the previous bug (38). - -40. Implemented PCRE_NEWLINE_ANY to recognize any of the Unicode newline - sequences (http://unicode.org/unicode/reports/tr18/) as "newline" when - processing dot, circumflex, or dollar metacharacters, or #-comments in /x - mode. - -41. Add \R to match any Unicode newline sequence, as suggested in the Unicode - report. - -42. Applied patch, originally from Ari Pollak, modified by Google, to allow - copy construction and assignment in the C++ wrapper. - -43. Updated pcregrep to support "--newline=any". In the process, I fixed a - couple of bugs that could have given wrong results in the "--newline=crlf" - case. - -44. Added a number of casts and did some reorganization of signed/unsigned int - variables following suggestions from Dair Grant. Also renamed the variable - "this" as "item" because it is a C++ keyword. - -45. Arranged for dftables to add - - #include "pcre_internal.h" - - to pcre_chartables.c because without it, gcc 4.x may remove the array - definition from the final binary if PCRE is built into a static library and - dead code stripping is activated. - -46. For an unanchored pattern, if a match attempt fails at the start of a - newline sequence, and the newline setting is CRLF or ANY, and the next two - characters are CRLF, advance by two characters instead of one. - - -Version 6.7 04-Jul-06 ---------------------- - - 1. In order to handle tests when input lines are enormously long, pcretest has - been re-factored so that it automatically extends its buffers when - necessary. The code is crude, but this _is_ just a test program. The - default size has been increased from 32K to 50K. - - 2. The code in pcre_study() was using the value of the re argument before - testing it for NULL. (Of course, in any sensible call of the function, it - won't be NULL.) - - 3. The memmove() emulation function in pcre_internal.h, which is used on - systems that lack both memmove() and bcopy() - that is, hardly ever - - was missing a "static" storage class specifier. - - 4. When UTF-8 mode was not set, PCRE looped when compiling certain patterns - containing an extended class (one that cannot be represented by a bitmap - because it contains high-valued characters or Unicode property items, e.g. - [\pZ]). Almost always one would set UTF-8 mode when processing such a - pattern, but PCRE should not loop if you do not (it no longer does). - [Detail: two cases were found: (a) a repeated subpattern containing an - extended class; (b) a recursive reference to a subpattern that followed a - previous extended class. It wasn't skipping over the extended class - correctly when UTF-8 mode was not set.] - - 5. A negated single-character class was not being recognized as fixed-length - in lookbehind assertions such as (?<=[^f]), leading to an incorrect - compile error "lookbehind assertion is not fixed length". - - 6. The RunPerlTest auxiliary script was showing an unexpected difference - between PCRE and Perl for UTF-8 tests. It turns out that it is hard to - write a Perl script that can interpret lines of an input file either as - byte characters or as UTF-8, which is what "perltest" was being required to - do for the non-UTF-8 and UTF-8 tests, respectively. Essentially what you - can't do is switch easily at run time between having the "use utf8;" pragma - or not. In the end, I fudged it by using the RunPerlTest script to insert - "use utf8;" explicitly for the UTF-8 tests. - - 7. In multiline (/m) mode, PCRE was matching ^ after a terminating newline at - the end of the subject string, contrary to the documentation and to what - Perl does. This was true of both matching functions. Now it matches only at - the start of the subject and immediately after *internal* newlines. - - 8. A call of pcre_fullinfo() from pcretest to get the option bits was passing - a pointer to an int instead of a pointer to an unsigned long int. This - caused problems on 64-bit systems. - - 9. Applied a patch from the folks at Google to pcrecpp.cc, to fix "another - instance of the 'standard' template library not being so standard". - -10. There was no check on the number of named subpatterns nor the maximum - length of a subpattern name. The product of these values is used to compute - the size of the memory block for a compiled pattern. By supplying a very - long subpattern name and a large number of named subpatterns, the size - computation could be caused to overflow. This is now prevented by limiting - the length of names to 32 characters, and the number of named subpatterns - to 10,000. - -11. Subpatterns that are repeated with specific counts have to be replicated in - the compiled pattern. The size of memory for this was computed from the - length of the subpattern and the repeat count. The latter is limited to - 65535, but there was no limit on the former, meaning that integer overflow - could in principle occur. The compiled length of a repeated subpattern is - now limited to 30,000 bytes in order to prevent this. - -12. Added the optional facility to have named substrings with the same name. - -13. Added the ability to use a named substring as a condition, using the - Python syntax: (?(name)yes|no). This overloads (?(R)... and names that - are numbers (not recommended). Forward references are permitted. - -14. Added forward references in named backreferences (if you see what I mean). - -15. In UTF-8 mode, with the PCRE_DOTALL option set, a quantified dot in the - pattern could run off the end of the subject. For example, the pattern - "(?s)(.{1,5})"8 did this with the subject "ab". - -16. If PCRE_DOTALL or PCRE_MULTILINE were set, pcre_dfa_exec() behaved as if - PCRE_CASELESS was set when matching characters that were quantified with ? - or *. - -17. A character class other than a single negated character that had a minimum - but no maximum quantifier - for example [ab]{6,} - was not handled - correctly by pce_dfa_exec(). It would match only one character. - -18. A valid (though odd) pattern that looked like a POSIX character - class but used an invalid character after [ (for example [[,abc,]]) caused - pcre_compile() to give the error "Failed: internal error: code overflow" or - in some cases to crash with a glibc free() error. This could even happen if - the pattern terminated after [[ but there just happened to be a sequence of - letters, a binary zero, and a closing ] in the memory that followed. - -19. Perl's treatment of octal escapes in the range \400 to \777 has changed - over the years. Originally (before any Unicode support), just the bottom 8 - bits were taken. Thus, for example, \500 really meant \100. Nowadays the - output from "man perlunicode" includes this: - - The regular expression compiler produces polymorphic opcodes. That - is, the pattern adapts to the data and automatically switches to - the Unicode character scheme when presented with Unicode data--or - instead uses a traditional byte scheme when presented with byte - data. - - Sadly, a wide octal escape does not cause a switch, and in a string with - no other multibyte characters, these octal escapes are treated as before. - Thus, in Perl, the pattern /\500/ actually matches \100 but the pattern - /\500|\x{1ff}/ matches \500 or \777 because the whole thing is treated as a - Unicode string. - - I have not perpetrated such confusion in PCRE. Up till now, it took just - the bottom 8 bits, as in old Perl. I have now made octal escapes with - values greater than \377 illegal in non-UTF-8 mode. In UTF-8 mode they - translate to the appropriate multibyte character. - -29. Applied some refactoring to reduce the number of warnings from Microsoft - and Borland compilers. This has included removing the fudge introduced - seven years ago for the OS/2 compiler (see 2.02/2 below) because it caused - a warning about an unused variable. - -21. PCRE has not included VT (character 0x0b) in the set of whitespace - characters since release 4.0, because Perl (from release 5.004) does not. - [Or at least, is documented not to: some releases seem to be in conflict - with the documentation.] However, when a pattern was studied with - pcre_study() and all its branches started with \s, PCRE still included VT - as a possible starting character. Of course, this did no harm; it just - caused an unnecessary match attempt. - -22. Removed a now-redundant internal flag bit that recorded the fact that case - dependency changed within the pattern. This was once needed for "required - byte" processing, but is no longer used. This recovers a now-scarce options - bit. Also moved the least significant internal flag bit to the most- - significant bit of the word, which was not previously used (hangover from - the days when it was an int rather than a uint) to free up another bit for - the future. - -23. Added support for CRLF line endings as well as CR and LF. As well as the - default being selectable at build time, it can now be changed at runtime - via the PCRE_NEWLINE_xxx flags. There are now options for pcregrep to - specify that it is scanning data with non-default line endings. - -24. Changed the definition of CXXLINK to make it agree with the definition of - LINK in the Makefile, by replacing LDFLAGS to CXXFLAGS. - -25. Applied Ian Taylor's patches to avoid using another stack frame for tail - recursions. This makes a big different to stack usage for some patterns. - -26. If a subpattern containing a named recursion or subroutine reference such - as (?P>B) was quantified, for example (xxx(?P>B)){3}, the calculation of - the space required for the compiled pattern went wrong and gave too small a - value. Depending on the environment, this could lead to "Failed: internal - error: code overflow at offset 49" or "glibc detected double free or - corruption" errors. - -27. Applied patches from Google (a) to support the new newline modes and (b) to - advance over multibyte UTF-8 characters in GlobalReplace. - -28. Change free() to pcre_free() in pcredemo.c. Apparently this makes a - difference for some implementation of PCRE in some Windows version. - -29. Added some extra testing facilities to pcretest: - - \q in a data line sets the "match limit" value - \Q in a data line sets the "match recursion limt" value - -S sets the stack size, where is in megabytes - - The -S option isn't available for Windows. - - -Version 6.6 06-Feb-06 ---------------------- - - 1. Change 16(a) for 6.5 broke things, because PCRE_DATA_SCOPE was not defined - in pcreposix.h. I have copied the definition from pcre.h. - - 2. Change 25 for 6.5 broke compilation in a build directory out-of-tree - because pcre.h is no longer a built file. - - 3. Added Jeff Friedl's additional debugging patches to pcregrep. These are - not normally included in the compiled code. - - -Version 6.5 01-Feb-06 ---------------------- - - 1. When using the partial match feature with pcre_dfa_exec(), it was not - anchoring the second and subsequent partial matches at the new starting - point. This could lead to incorrect results. For example, with the pattern - /1234/, partially matching against "123" and then "a4" gave a match. - - 2. Changes to pcregrep: - - (a) All non-match returns from pcre_exec() were being treated as failures - to match the line. Now, unless the error is PCRE_ERROR_NOMATCH, an - error message is output. Some extra information is given for the - PCRE_ERROR_MATCHLIMIT and PCRE_ERROR_RECURSIONLIMIT errors, which are - probably the only errors that are likely to be caused by users (by - specifying a regex that has nested indefinite repeats, for instance). - If there are more than 20 of these errors, pcregrep is abandoned. - - (b) A binary zero was treated as data while matching, but terminated the - output line if it was written out. This has been fixed: binary zeroes - are now no different to any other data bytes. - - (c) Whichever of the LC_ALL or LC_CTYPE environment variables is set is - used to set a locale for matching. The --locale=xxxx long option has - been added (no short equivalent) to specify a locale explicitly on the - pcregrep command, overriding the environment variables. - - (d) When -B was used with -n, some line numbers in the output were one less - than they should have been. - - (e) Added the -o (--only-matching) option. - - (f) If -A or -C was used with -c (count only), some lines of context were - accidentally printed for the final match. - - (g) Added the -H (--with-filename) option. - - (h) The combination of options -rh failed to suppress file names for files - that were found from directory arguments. - - (i) Added the -D (--devices) and -d (--directories) options. - - (j) Added the -F (--fixed-strings) option. - - (k) Allow "-" to be used as a file name for -f as well as for a data file. - - (l) Added the --colo(u)r option. - - (m) Added Jeffrey Friedl's -S testing option, but within #ifdefs so that it - is not present by default. - - 3. A nasty bug was discovered in the handling of recursive patterns, that is, - items such as (?R) or (?1), when the recursion could match a number of - alternatives. If it matched one of the alternatives, but subsequently, - outside the recursion, there was a failure, the code tried to back up into - the recursion. However, because of the way PCRE is implemented, this is not - possible, and the result was an incorrect result from the match. - - In order to prevent this happening, the specification of recursion has - been changed so that all such subpatterns are automatically treated as - atomic groups. Thus, for example, (?R) is treated as if it were (?>(?R)). - - 4. I had overlooked the fact that, in some locales, there are characters for - which isalpha() is true but neither isupper() nor islower() are true. In - the fr_FR locale, for instance, the \xAA and \xBA characters (ordmasculine - and ordfeminine) are like this. This affected the treatment of \w and \W - when they appeared in character classes, but not when they appeared outside - a character class. The bit map for "word" characters is now created - separately from the results of isalnum() instead of just taking it from the - upper, lower, and digit maps. (Plus the underscore character, of course.) - - 5. The above bug also affected the handling of POSIX character classes such as - [[:alpha:]] and [[:alnum:]]. These do not have their own bit maps in PCRE's - permanent tables. Instead, the bit maps for such a class were previously - created as the appropriate unions of the upper, lower, and digit bitmaps. - Now they are created by subtraction from the [[:word:]] class, which has - its own bitmap. - - 6. The [[:blank:]] character class matches horizontal, but not vertical space. - It is created by subtracting the vertical space characters (\x09, \x0a, - \x0b, \x0c) from the [[:space:]] bitmap. Previously, however, the - subtraction was done in the overall bitmap for a character class, meaning - that a class such as [\x0c[:blank:]] was incorrect because \x0c would not - be recognized. This bug has been fixed. - - 7. Patches from the folks at Google: - - (a) pcrecpp.cc: "to handle a corner case that may or may not happen in - real life, but is still worth protecting against". - - (b) pcrecpp.cc: "corrects a bug when negative radixes are used with - regular expressions". - - (c) pcre_scanner.cc: avoid use of std::count() because not all systems - have it. - - (d) Split off pcrecpparg.h from pcrecpp.h and had the former built by - "configure" and the latter not, in order to fix a problem somebody had - with compiling the Arg class on HP-UX. - - (e) Improve the error-handling of the C++ wrapper a little bit. - - (f) New tests for checking recursion limiting. - - 8. The pcre_memmove() function, which is used only if the environment does not - have a standard memmove() function (and is therefore rarely compiled), - contained two bugs: (a) use of int instead of size_t, and (b) it was not - returning a result (though PCRE never actually uses the result). - - 9. In the POSIX regexec() interface, if nmatch is specified as a ridiculously - large number - greater than INT_MAX/(3*sizeof(int)) - REG_ESPACE is - returned instead of calling malloc() with an overflowing number that would - most likely cause subsequent chaos. - -10. The debugging option of pcretest was not showing the NO_AUTO_CAPTURE flag. - -11. The POSIX flag REG_NOSUB is now supported. When a pattern that was compiled - with this option is matched, the nmatch and pmatch options of regexec() are - ignored. - -12. Added REG_UTF8 to the POSIX interface. This is not defined by POSIX, but is - provided in case anyone wants to the the POSIX interface with UTF-8 - strings. - -13. Added CXXLDFLAGS to the Makefile parameters to provide settings only on the - C++ linking (needed for some HP-UX environments). - -14. Avoid compiler warnings in get_ucpname() when compiled without UCP support - (unused parameter) and in the pcre_printint() function (omitted "default" - switch label when the default is to do nothing). - -15. Added some code to make it possible, when PCRE is compiled as a C++ - library, to replace subject pointers for pcre_exec() with a smart pointer - class, thus making it possible to process discontinuous strings. - -16. The two macros PCRE_EXPORT and PCRE_DATA_SCOPE are confusing, and perform - much the same function. They were added by different people who were trying - to make PCRE easy to compile on non-Unix systems. It has been suggested - that PCRE_EXPORT be abolished now that there is more automatic apparatus - for compiling on Windows systems. I have therefore replaced it with - PCRE_DATA_SCOPE. This is set automatically for Windows; if not set it - defaults to "extern" for C or "extern C" for C++, which works fine on - Unix-like systems. It is now possible to override the value of PCRE_DATA_ - SCOPE with something explicit in config.h. In addition: - - (a) pcreposix.h still had just "extern" instead of either of these macros; - I have replaced it with PCRE_DATA_SCOPE. - - (b) Functions such as _pcre_xclass(), which are internal to the library, - but external in the C sense, all had PCRE_EXPORT in their definitions. - This is apparently wrong for the Windows case, so I have removed it. - (It makes no difference on Unix-like systems.) - -17. Added a new limit, MATCH_LIMIT_RECURSION, which limits the depth of nesting - of recursive calls to match(). This is different to MATCH_LIMIT because - that limits the total number of calls to match(), not all of which increase - the depth of recursion. Limiting the recursion depth limits the amount of - stack (or heap if NO_RECURSE is set) that is used. The default can be set - when PCRE is compiled, and changed at run time. A patch from Google adds - this functionality to the C++ interface. - -18. Changes to the handling of Unicode character properties: - - (a) Updated the table to Unicode 4.1.0. - - (b) Recognize characters that are not in the table as "Cn" (undefined). - - (c) I revised the way the table is implemented to a much improved format - which includes recognition of ranges. It now supports the ranges that - are defined in UnicodeData.txt, and it also amalgamates other - characters into ranges. This has reduced the number of entries in the - table from around 16,000 to around 3,000, thus reducing its size - considerably. I realized I did not need to use a tree structure after - all - a binary chop search is just as efficient. Having reduced the - number of entries, I extended their size from 6 bytes to 8 bytes to - allow for more data. - - (d) Added support for Unicode script names via properties such as \p{Han}. - -19. In UTF-8 mode, a backslash followed by a non-Ascii character was not - matching that character. - -20. When matching a repeated Unicode property with a minimum greater than zero, - (for example \pL{2,}), PCRE could look past the end of the subject if it - reached it while seeking the minimum number of characters. This could - happen only if some of the characters were more than one byte long, because - there is a check for at least the minimum number of bytes. - -21. Refactored the implementation of \p and \P so as to be more general, to - allow for more different types of property in future. This has changed the - compiled form incompatibly. Anybody with saved compiled patterns that use - \p or \P will have to recompile them. - -22. Added "Any" and "L&" to the supported property types. - -23. Recognize \x{...} as a code point specifier, even when not in UTF-8 mode, - but give a compile time error if the value is greater than 0xff. - -24. The man pages for pcrepartial, pcreprecompile, and pcre_compile2 were - accidentally not being installed or uninstalled. - -25. The pcre.h file was built from pcre.h.in, but the only changes that were - made were to insert the current release number. This seemed silly, because - it made things harder for people building PCRE on systems that don't run - "configure". I have turned pcre.h into a distributed file, no longer built - by "configure", with the version identification directly included. There is - no longer a pcre.h.in file. - - However, this change necessitated a change to the pcre-config script as - well. It is built from pcre-config.in, and one of the substitutions was the - release number. I have updated configure.ac so that ./configure now finds - the release number by grepping pcre.h. - -26. Added the ability to run the tests under valgrind. - - -Version 6.4 05-Sep-05 ---------------------- - - 1. Change 6.0/10/(l) to pcregrep introduced a bug that caused separator lines - "--" to be printed when multiple files were scanned, even when none of the - -A, -B, or -C options were used. This is not compatible with Gnu grep, so I - consider it to be a bug, and have restored the previous behaviour. - - 2. A couple of code tidies to get rid of compiler warnings. - - 3. The pcretest program used to cheat by referring to symbols in the library - whose names begin with _pcre_. These are internal symbols that are not - really supposed to be visible externally, and in some environments it is - possible to suppress them. The cheating is now confined to including - certain files from the library's source, which is a bit cleaner. - - 4. Renamed pcre.in as pcre.h.in to go with pcrecpp.h.in; it also makes the - file's purpose clearer. - - 5. Reorganized pcre_ucp_findchar(). - - -Version 6.3 15-Aug-05 ---------------------- - - 1. The file libpcre.pc.in did not have general read permission in the tarball. - - 2. There were some problems when building without C++ support: - - (a) If C++ support was not built, "make install" and "make test" still - tried to test it. - - (b) There were problems when the value of CXX was explicitly set. Some - changes have been made to try to fix these, and ... - - (c) --disable-cpp can now be used to explicitly disable C++ support. - - (d) The use of @CPP_OBJ@ directly caused a blank line preceded by a - backslash in a target when C++ was disabled. This confuses some - versions of "make", apparently. Using an intermediate variable solves - this. (Same for CPP_LOBJ.) - - 3. $(LINK_FOR_BUILD) now includes $(CFLAGS_FOR_BUILD) and $(LINK) - (non-Windows) now includes $(CFLAGS) because these flags are sometimes - necessary on certain architectures. - - 4. Added a setting of -export-symbols-regex to the link command to remove - those symbols that are exported in the C sense, but actually are local - within the library, and not documented. Their names all begin with - "_pcre_". This is not a perfect job, because (a) we have to except some - symbols that pcretest ("illegally") uses, and (b) the facility isn't always - available (and never for static libraries). I have made a note to try to - find a way round (a) in the future. - - -Version 6.2 01-Aug-05 ---------------------- - - 1. There was no test for integer overflow of quantifier values. A construction - such as {1111111111111111} would give undefined results. What is worse, if - a minimum quantifier for a parenthesized subpattern overflowed and became - negative, the calculation of the memory size went wrong. This could have - led to memory overwriting. - - 2. Building PCRE using VPATH was broken. Hopefully it is now fixed. - - 3. Added "b" to the 2nd argument of fopen() in dftables.c, for non-Unix-like - operating environments where this matters. - - 4. Applied Giuseppe Maxia's patch to add additional features for controlling - PCRE options from within the C++ wrapper. - - 5. Named capturing subpatterns were not being correctly counted when a pattern - was compiled. This caused two problems: (a) If there were more than 100 - such subpatterns, the calculation of the memory needed for the whole - compiled pattern went wrong, leading to an overflow error. (b) Numerical - back references of the form \12, where the number was greater than 9, were - not recognized as back references, even though there were sufficient - previous subpatterns. - - 6. Two minor patches to pcrecpp.cc in order to allow it to compile on older - versions of gcc, e.g. 2.95.4. - - -Version 6.1 21-Jun-05 ---------------------- - - 1. There was one reference to the variable "posix" in pcretest.c that was not - surrounded by "#if !defined NOPOSIX". - - 2. Make it possible to compile pcretest without DFA support, UTF8 support, or - the cross-check on the old pcre_info() function, for the benefit of the - cut-down version of PCRE that is currently imported into Exim. - - 3. A (silly) pattern starting with (?i)(?-i) caused an internal space - allocation error. I've done the easy fix, which wastes 2 bytes for sensible - patterns that start (?i) but I don't think that matters. The use of (?i) is - just an example; this all applies to the other options as well. - - 4. Since libtool seems to echo the compile commands it is issuing, the output - from "make" can be reduced a bit by putting "@" in front of each libtool - compile command. - - 5. Patch from the folks at Google for configure.in to be a bit more thorough - in checking for a suitable C++ installation before trying to compile the - C++ stuff. This should fix a reported problem when a compiler was present, - but no suitable headers. - - 6. The man pages all had just "PCRE" as their title. I have changed them to - be the relevant file name. I have also arranged that these names are - retained in the file doc/pcre.txt, which is a concatenation in text format - of all the man pages except the little individual ones for each function. - - 7. The NON-UNIX-USE file had not been updated for the different set of source - files that come with release 6. I also added a few comments about the C++ - wrapper. - - -Version 6.0 07-Jun-05 ---------------------- - - 1. Some minor internal re-organization to help with my DFA experiments. - - 2. Some missing #ifdef SUPPORT_UCP conditionals in pcretest and printint that - didn't matter for the library itself when fully configured, but did matter - when compiling without UCP support, or within Exim, where the ucp files are - not imported. - - 3. Refactoring of the library code to split up the various functions into - different source modules. The addition of the new DFA matching code (see - below) to a single monolithic source would have made it really too - unwieldy, quite apart from causing all the code to be include in a - statically linked application, when only some functions are used. This is - relevant even without the DFA addition now that patterns can be compiled in - one application and matched in another. - - The downside of splitting up is that there have to be some external - functions and data tables that are used internally in different modules of - the library but which are not part of the API. These have all had their - names changed to start with "_pcre_" so that they are unlikely to clash - with other external names. - - 4. Added an alternate matching function, pcre_dfa_exec(), which matches using - a different (DFA) algorithm. Although it is slower than the original - function, it does have some advantages for certain types of matching - problem. - - 5. Upgrades to pcretest in order to test the features of pcre_dfa_exec(), - including restarting after a partial match. - - 6. A patch for pcregrep that defines INVALID_FILE_ATTRIBUTES if it is not - defined when compiling for Windows was sent to me. I have put it into the - code, though I have no means of testing or verifying it. - - 7. Added the pcre_refcount() auxiliary function. - - 8. Added the PCRE_FIRSTLINE option. This constrains an unanchored pattern to - match before or at the first newline in the subject string. In pcretest, - the /f option on a pattern can be used to set this. - - 9. A repeated \w when used in UTF-8 mode with characters greater than 256 - would behave wrongly. This has been present in PCRE since release 4.0. - -10. A number of changes to the pcregrep command: - - (a) Refactored how -x works; insert ^(...)$ instead of setting - PCRE_ANCHORED and checking the length, in preparation for adding - something similar for -w. - - (b) Added the -w (match as a word) option. - - (c) Refactored the way lines are read and buffered so as to have more - than one at a time available. - - (d) Implemented a pcregrep test script. - - (e) Added the -M (multiline match) option. This allows patterns to match - over several lines of the subject. The buffering ensures that at least - 8K, or the rest of the document (whichever is the shorter) is available - for matching (and similarly the previous 8K for lookbehind assertions). - - (f) Changed the --help output so that it now says - - -w, --word-regex(p) - - instead of two lines, one with "regex" and the other with "regexp" - because that confused at least one person since the short forms are the - same. (This required a bit of code, as the output is generated - automatically from a table. It wasn't just a text change.) - - (g) -- can be used to terminate pcregrep options if the next thing isn't an - option but starts with a hyphen. Could be a pattern or a path name - starting with a hyphen, for instance. - - (h) "-" can be given as a file name to represent stdin. - - (i) When file names are being printed, "(standard input)" is used for - the standard input, for compatibility with GNU grep. Previously - "" was used. - - (j) The option --label=xxx can be used to supply a name to be used for - stdin when file names are being printed. There is no short form. - - (k) Re-factored the options decoding logic because we are going to add - two more options that take data. Such options can now be given in four - different ways, e.g. "-fname", "-f name", "--file=name", "--file name". - - (l) Added the -A, -B, and -C options for requesting that lines of context - around matches be printed. - - (m) Added the -L option to print the names of files that do not contain - any matching lines, that is, the complement of -l. - - (n) The return code is 2 if any file cannot be opened, but pcregrep does - continue to scan other files. - - (o) The -s option was incorrectly implemented. For compatibility with other - greps, it now suppresses the error message for a non-existent or non- - accessible file (but not the return code). There is a new option called - -q that suppresses the output of matching lines, which was what -s was - previously doing. - - (p) Added --include and --exclude options to specify files for inclusion - and exclusion when recursing. - -11. The Makefile was not using the Autoconf-supported LDFLAGS macro properly. - Hopefully, it now does. - -12. Missing cast in pcre_study(). - -13. Added an "uninstall" target to the makefile. - -14. Replaced "extern" in the function prototypes in Makefile.in with - "PCRE_DATA_SCOPE", which defaults to 'extern' or 'extern "C"' in the Unix - world, but is set differently for Windows. - -15. Added a second compiling function called pcre_compile2(). The only - difference is that it has an extra argument, which is a pointer to an - integer error code. When there is a compile-time failure, this is set - non-zero, in addition to the error test pointer being set to point to an - error message. The new argument may be NULL if no error number is required - (but then you may as well call pcre_compile(), which is now just a - wrapper). This facility is provided because some applications need a - numeric error indication, but it has also enabled me to tidy up the way - compile-time errors are handled in the POSIX wrapper. - -16. Added VPATH=.libs to the makefile; this should help when building with one - prefix path and installing with another. (Or so I'm told by someone who - knows more about this stuff than I do.) - -17. Added a new option, REG_DOTALL, to the POSIX function regcomp(). This - passes PCRE_DOTALL to the pcre_compile() function, making the "." character - match everything, including newlines. This is not POSIX-compatible, but - somebody wanted the feature. From pcretest it can be activated by using - both the P and the s flags. - -18. AC_PROG_LIBTOOL appeared twice in Makefile.in. Removed one. - -19. libpcre.pc was being incorrectly installed as executable. - -20. A couple of places in pcretest check for end-of-line by looking for '\n'; - it now also looks for '\r' so that it will work unmodified on Windows. - -21. Added Google's contributed C++ wrapper to the distribution. - -22. Added some untidy missing memory free() calls in pcretest, to keep - Electric Fence happy when testing. - - - -Version 5.0 13-Sep-04 ---------------------- - - 1. Internal change: literal characters are no longer packed up into items - containing multiple characters in a single byte-string. Each character - is now matched using a separate opcode. However, there may be more than one - byte in the character in UTF-8 mode. - - 2. The pcre_callout_block structure has two new fields: pattern_position and - next_item_length. These contain the offset in the pattern to the next match - item, and its length, respectively. - - 3. The PCRE_AUTO_CALLOUT option for pcre_compile() requests the automatic - insertion of callouts before each pattern item. Added the /C option to - pcretest to make use of this. - - 4. On the advice of a Windows user, the lines - - #if defined(_WIN32) || defined(WIN32) - _setmode( _fileno( stdout ), 0x8000 ); - #endif /* defined(_WIN32) || defined(WIN32) */ - - have been added to the source of pcretest. This apparently does useful - magic in relation to line terminators. - - 5. Changed "r" and "w" in the calls to fopen() in pcretest to "rb" and "wb" - for the benefit of those environments where the "b" makes a difference. - - 6. The icc compiler has the same options as gcc, but "configure" doesn't seem - to know about it. I have put a hack into configure.in that adds in code - to set GCC=yes if CC=icc. This seems to end up at a point in the - generated configure script that is early enough to affect the setting of - compiler options, which is what is needed, but I have no means of testing - whether it really works. (The user who reported this had patched the - generated configure script, which of course I cannot do.) - - LATER: After change 22 below (new libtool files), the configure script - seems to know about icc (and also ecc). Therefore, I have commented out - this hack in configure.in. - - 7. Added support for pkg-config (2 patches were sent in). - - 8. Negated POSIX character classes that used a combination of internal tables - were completely broken. These were [[:^alpha:]], [[:^alnum:]], and - [[:^ascii]]. Typically, they would match almost any characters. The other - POSIX classes were not broken in this way. - - 9. Matching the pattern "\b.*?" against "ab cd", starting at offset 1, failed - to find the match, as PCRE was deluded into thinking that the match had to - start at the start point or following a newline. The same bug applied to - patterns with negative forward assertions or any backward assertions - preceding ".*" at the start, unless the pattern required a fixed first - character. This was a failing pattern: "(?!.bcd).*". The bug is now fixed. - -10. In UTF-8 mode, when moving forwards in the subject after a failed match - starting at the last subject character, bytes beyond the end of the subject - string were read. - -11. Renamed the variable "class" as "classbits" to make life easier for C++ - users. (Previously there was a macro definition, but it apparently wasn't - enough.) - -12. Added the new field "tables" to the extra data so that tables can be passed - in at exec time, or the internal tables can be re-selected. This allows - a compiled regex to be saved and re-used at a later time by a different - program that might have everything at different addresses. - -13. Modified the pcre-config script so that, when run on Solaris, it shows a - -R library as well as a -L library. - -14. The debugging options of pcretest (-d on the command line or D on a - pattern) showed incorrect output for anything following an extended class - that contained multibyte characters and which was followed by a quantifier. - -15. Added optional support for general category Unicode character properties - via the \p, \P, and \X escapes. Unicode property support implies UTF-8 - support. It adds about 90K to the size of the library. The meanings of the - inbuilt class escapes such as \d and \s have NOT been changed. - -16. Updated pcredemo.c to include calls to free() to release the memory for the - compiled pattern. - -17. The generated file chartables.c was being created in the source directory - instead of in the building directory. This caused the build to fail if the - source directory was different from the building directory, and was - read-only. - -18. Added some sample Win commands from Mark Tetrode into the NON-UNIX-USE - file. No doubt somebody will tell me if they don't make sense... Also added - Dan Mooney's comments about building on OpenVMS. - -19. Added support for partial matching via the PCRE_PARTIAL option for - pcre_exec() and the \P data escape in pcretest. - -20. Extended pcretest with 3 new pattern features: - - (i) A pattern option of the form ">rest-of-line" causes pcretest to - write the compiled pattern to the file whose name is "rest-of-line". - This is a straight binary dump of the data, with the saved pointer to - the character tables forced to be NULL. The study data, if any, is - written too. After writing, pcretest reads a new pattern. - - (ii) If, instead of a pattern, ": new target - : new target - : use native compiler - : use native linker - : handle Windows platform correctly - : ditto - : ditto - copy DLL to top builddir before testing - - As part of these changes, -no-undefined was removed again. This was reported - to give trouble on HP-UX 11.0, so getting rid of it seems like a good idea - in any case. - -3. Some tidies to get rid of compiler warnings: - - . In the match_data structure, match_limit was an unsigned long int, whereas - match_call_count was an int. I've made them both unsigned long ints. - - . In pcretest the fact that a const uschar * doesn't automatically cast to - a void * provoked a warning. - - . Turning on some more compiler warnings threw up some "shadow" variables - and a few more missing casts. - -4. If PCRE was complied with UTF-8 support, but called without the PCRE_UTF8 - option, a class that contained a single character with a value between 128 - and 255 (e.g. /[\xFF]/) caused PCRE to crash. - -5. If PCRE was compiled with UTF-8 support, but called without the PCRE_UTF8 - option, a class that contained several characters, but with at least one - whose value was between 128 and 255 caused PCRE to crash. - - -Version 4.1 12-Mar-03 ---------------------- - -1. Compiling with gcc -pedantic found a couple of places where casts were -needed, and a string in dftables.c that was longer than standard compilers are -required to support. - -2. Compiling with Sun's compiler found a few more places where the code could -be tidied up in order to avoid warnings. - -3. The variables for cross-compiling were called HOST_CC and HOST_CFLAGS; the -first of these names is deprecated in the latest Autoconf in favour of the name -CC_FOR_BUILD, because "host" is typically used to mean the system on which the -compiled code will be run. I can't find a reference for HOST_CFLAGS, but by -analogy I have changed it to CFLAGS_FOR_BUILD. - -4. Added -no-undefined to the linking command in the Makefile, because this is -apparently helpful for Windows. To make it work, also added "-L. -lpcre" to the -linking step for the pcreposix library. - -5. PCRE was failing to diagnose the case of two named groups with the same -name. - -6. A problem with one of PCRE's optimizations was discovered. PCRE remembers a -literal character that is needed in the subject for a match, and scans along to -ensure that it is present before embarking on the full matching process. This -saves time in cases of nested unlimited repeats that are never going to match. -Problem: the scan can take a lot of time if the subject is very long (e.g. -megabytes), thus penalizing straightforward matches. It is now done only if the -amount of subject to be scanned is less than 1000 bytes. - -7. A lesser problem with the same optimization is that it was recording the -first character of an anchored pattern as "needed", thus provoking a search -right along the subject, even when the first match of the pattern was going to -fail. The "needed" character is now not set for anchored patterns, unless it -follows something in the pattern that is of non-fixed length. Thus, it still -fulfils its original purpose of finding quick non-matches in cases of nested -unlimited repeats, but isn't used for simple anchored patterns such as /^abc/. - - -Version 4.0 17-Feb-03 ---------------------- - -1. If a comment in an extended regex that started immediately after a meta-item -extended to the end of string, PCRE compiled incorrect data. This could lead to -all kinds of weird effects. Example: /#/ was bad; /()#/ was bad; /a#/ was not. - -2. Moved to autoconf 2.53 and libtool 1.4.2. - -3. Perl 5.8 no longer needs "use utf8" for doing UTF-8 things. Consequently, -the special perltest8 script is no longer needed - all the tests can be run -from a single perltest script. - -4. From 5.004, Perl has not included the VT character (0x0b) in the set defined -by \s. It has now been removed in PCRE. This means it isn't recognized as -whitespace in /x regexes too, which is the same as Perl. Note that the POSIX -class [:space:] *does* include VT, thereby creating a mess. - -5. Added the class [:blank:] (a GNU extension from Perl 5.8) to match only -space and tab. - -6. Perl 5.005 was a long time ago. It's time to amalgamate the tests that use -its new features into the main test script, reducing the number of scripts. - -7. Perl 5.8 has changed the meaning of patterns like /a(?i)b/. Earlier versions -were backward compatible, and made the (?i) apply to the whole pattern, as if -/i were given. Now it behaves more logically, and applies the option setting -only to what follows. PCRE has been changed to follow suit. However, if it -finds options settings right at the start of the pattern, it extracts them into -the global options, as before. Thus, they show up in the info data. - -8. Added support for the \Q...\E escape sequence. Characters in between are -treated as literals. This is slightly different from Perl in that $ and @ are -also handled as literals inside the quotes. In Perl, they will cause variable -interpolation. Note the following examples: - - Pattern PCRE matches Perl matches - - \Qabc$xyz\E abc$xyz abc followed by the contents of $xyz - \Qabc\$xyz\E abc\$xyz abc\$xyz - \Qabc\E\$\Qxyz\E abc$xyz abc$xyz - -For compatibility with Perl, \Q...\E sequences are recognized inside character -classes as well as outside them. - -9. Re-organized 3 code statements in pcretest to avoid "overflow in -floating-point constant arithmetic" warnings from a Microsoft compiler. Added a -(size_t) cast to one statement in pcretest and one in pcreposix to avoid -signed/unsigned warnings. - -10. SunOS4 doesn't have strtoul(). This was used only for unpicking the -o -option for pcretest, so I've replaced it by a simple function that does just -that job. - -11. pcregrep was ending with code 0 instead of 2 for the commands "pcregrep" or -"pcregrep -". - -12. Added "possessive quantifiers" ?+, *+, ++, and {,}+ which come from Sun's -Java package. This provides some syntactic sugar for simple cases of what my -documentation calls "once-only subpatterns". A pattern such as x*+ is the same -as (?>x*). In other words, if what is inside (?>...) is just a single repeated -item, you can use this simplified notation. Note that only makes sense with -greedy quantifiers. Consequently, the use of the possessive quantifier forces -greediness, whatever the setting of the PCRE_UNGREEDY option. - -13. A change of greediness default within a pattern was not taking effect at -the current level for patterns like /(b+(?U)a+)/. It did apply to parenthesized -subpatterns that followed. Patterns like /b+(?U)a+/ worked because the option -was abstracted outside. - -14. PCRE now supports the \G assertion. It is true when the current matching -position is at the start point of the match. This differs from \A when the -starting offset is non-zero. Used with the /g option of pcretest (or similar -code), it works in the same way as it does for Perl's /g option. If all -alternatives of a regex begin with \G, the expression is anchored to the start -match position, and the "anchored" flag is set in the compiled expression. - -15. Some bugs concerning the handling of certain option changes within patterns -have been fixed. These applied to options other than (?ims). For example, -"a(?x: b c )d" did not match "XabcdY" but did match "Xa b c dY". It should have -been the other way round. Some of this was related to change 7 above. - -16. PCRE now gives errors for /[.x.]/ and /[=x=]/ as unsupported POSIX -features, as Perl does. Previously, PCRE gave the warnings only for /[[.x.]]/ -and /[[=x=]]/. PCRE now also gives an error for /[:name:]/ because it supports -POSIX classes only within a class (e.g. /[[:alpha:]]/). - -17. Added support for Perl's \C escape. This matches one byte, even in UTF8 -mode. Unlike ".", it always matches newline, whatever the setting of -PCRE_DOTALL. However, PCRE does not permit \C to appear in lookbehind -assertions. Perl allows it, but it doesn't (in general) work because it can't -calculate the length of the lookbehind. At least, that's the case for Perl -5.8.0 - I've been told they are going to document that it doesn't work in -future. - -18. Added an error diagnosis for escapes that PCRE does not support: these are -\L, \l, \N, \P, \p, \U, \u, and \X. - -19. Although correctly diagnosing a missing ']' in a character class, PCRE was -reading past the end of the pattern in cases such as /[abcd/. - -20. PCRE was getting more memory than necessary for patterns with classes that -contained both POSIX named classes and other characters, e.g. /[[:space:]abc/. - -21. Added some code, conditional on #ifdef VPCOMPAT, to make life easier for -compiling PCRE for use with Virtual Pascal. - -22. Small fix to the Makefile to make it work properly if the build is done -outside the source tree. - -23. Added a new extension: a condition to go with recursion. If a conditional -subpattern starts with (?(R) the "true" branch is used if recursion has -happened, whereas the "false" branch is used only at the top level. - -24. When there was a very long string of literal characters (over 255 bytes -without UTF support, over 250 bytes with UTF support), the computation of how -much memory was required could be incorrect, leading to segfaults or other -strange effects. - -25. PCRE was incorrectly assuming anchoring (either to start of subject or to -start of line for a non-DOTALL pattern) when a pattern started with (.*) and -there was a subsequent back reference to those brackets. This meant that, for -example, /(.*)\d+\1/ failed to match "abc123bc". Unfortunately, it isn't -possible to check for precisely this case. All we can do is abandon the -optimization if .* occurs inside capturing brackets when there are any back -references whatsoever. (See below for a better fix that came later.) - -26. The handling of the optimization for finding the first character of a -non-anchored pattern, and for finding a character that is required later in the -match were failing in some cases. This didn't break the matching; it just -failed to optimize when it could. The way this is done has been re-implemented. - -27. Fixed typo in error message for invalid (?R item (it said "(?p"). - -28. Added a new feature that provides some of the functionality that Perl -provides with (?{...}). The facility is termed a "callout". The way it is done -in PCRE is for the caller to provide an optional function, by setting -pcre_callout to its entry point. Like pcre_malloc and pcre_free, this is a -global variable. By default it is unset, which disables all calling out. To get -the function called, the regex must include (?C) at appropriate points. This -is, in fact, equivalent to (?C0), and any number <= 255 may be given with (?C). -This provides a means of identifying different callout points. When PCRE -reaches such a point in the regex, if pcre_callout has been set, the external -function is called. It is provided with data in a structure called -pcre_callout_block, which is defined in pcre.h. If the function returns 0, -matching continues; if it returns a non-zero value, the match at the current -point fails. However, backtracking will occur if possible. [This was changed -later and other features added - see item 49 below.] - -29. pcretest is upgraded to test the callout functionality. It provides a -callout function that displays information. By default, it shows the start of -the match and the current position in the text. There are some new data escapes -to vary what happens: - - \C+ in addition, show current contents of captured substrings - \C- do not supply a callout function - \C!n return 1 when callout number n is reached - \C!n!m return 1 when callout number n is reached for the mth time - -30. If pcregrep was called with the -l option and just a single file name, it -output "" if a match was found, instead of the file name. - -31. Improve the efficiency of the POSIX API to PCRE. If the number of capturing -slots is less than POSIX_MALLOC_THRESHOLD, use a block on the stack to pass to -pcre_exec(). This saves a malloc/free per call. The default value of -POSIX_MALLOC_THRESHOLD is 10; it can be changed by --with-posix-malloc-threshold -when configuring. - -32. The default maximum size of a compiled pattern is 64K. There have been a -few cases of people hitting this limit. The code now uses macros to handle the -storing of links as offsets within the compiled pattern. It defaults to 2-byte -links, but this can be changed to 3 or 4 bytes by --with-link-size when -configuring. Tests 2 and 5 work only with 2-byte links because they output -debugging information about compiled patterns. - -33. Internal code re-arrangements: - -(a) Moved the debugging function for printing out a compiled regex into - its own source file (printint.c) and used #include to pull it into - pcretest.c and, when DEBUG is defined, into pcre.c, instead of having two - separate copies. - -(b) Defined the list of op-code names for debugging as a macro in - internal.h so that it is next to the definition of the opcodes. - -(c) Defined a table of op-code lengths for simpler skipping along compiled - code. This is again a macro in internal.h so that it is next to the - definition of the opcodes. - -34. Added support for recursive calls to individual subpatterns, along the -lines of Robin Houston's patch (but implemented somewhat differently). - -35. Further mods to the Makefile to help Win32. Also, added code to pcregrep to -allow it to read and process whole directories in Win32. This code was -contributed by Lionel Fourquaux; it has not been tested by me. - -36. Added support for named subpatterns. The Python syntax (?P...) is -used to name a group. Names consist of alphanumerics and underscores, and must -be unique. Back references use the syntax (?P=name) and recursive calls use -(?P>name) which is a PCRE extension to the Python extension. Groups still have -numbers. The function pcre_fullinfo() can be used after compilation to extract -a name/number map. There are three relevant calls: - - PCRE_INFO_NAMEENTRYSIZE yields the size of each entry in the map - PCRE_INFO_NAMECOUNT yields the number of entries - PCRE_INFO_NAMETABLE yields a pointer to the map. - -The map is a vector of fixed-size entries. The size of each entry depends on -the length of the longest name used. The first two bytes of each entry are the -group number, most significant byte first. There follows the corresponding -name, zero terminated. The names are in alphabetical order. - -37. Make the maximum literal string in the compiled code 250 for the non-UTF-8 -case instead of 255. Making it the same both with and without UTF-8 support -means that the same test output works with both. - -38. There was a case of malloc(0) in the POSIX testing code in pcretest. Avoid -calling malloc() with a zero argument. - -39. Change 25 above had to resort to a heavy-handed test for the .* anchoring -optimization. I've improved things by keeping a bitmap of backreferences with -numbers 1-31 so that if .* occurs inside capturing brackets that are not in -fact referenced, the optimization can be applied. It is unlikely that a -relevant occurrence of .* (i.e. one which might indicate anchoring or forcing -the match to follow \n) will appear inside brackets with a number greater than -31, but if it does, any back reference > 31 suppresses the optimization. - -40. Added a new compile-time option PCRE_NO_AUTO_CAPTURE. This has the effect -of disabling numbered capturing parentheses. Any opening parenthesis that is -not followed by ? behaves as if it were followed by ?: but named parentheses -can still be used for capturing (and they will acquire numbers in the usual -way). - -41. Redesigned the return codes from the match() function into yes/no/error so -that errors can be passed back from deep inside the nested calls. A malloc -failure while inside a recursive subpattern call now causes the -PCRE_ERROR_NOMEMORY return instead of quietly going wrong. - -42. It is now possible to set a limit on the number of times the match() -function is called in a call to pcre_exec(). This facility makes it possible to -limit the amount of recursion and backtracking, though not in a directly -obvious way, because the match() function is used in a number of different -circumstances. The count starts from zero for each position in the subject -string (for non-anchored patterns). The default limit is, for compatibility, a -large number, namely 10 000 000. You can change this in two ways: - -(a) When configuring PCRE before making, you can use --with-match-limit=n - to set a default value for the compiled library. - -(b) For each call to pcre_exec(), you can pass a pcre_extra block in which - a different value is set. See 45 below. - -If the limit is exceeded, pcre_exec() returns PCRE_ERROR_MATCHLIMIT. - -43. Added a new function pcre_config(int, void *) to enable run-time extraction -of things that can be changed at compile time. The first argument specifies -what is wanted and the second points to where the information is to be placed. -The current list of available information is: - - PCRE_CONFIG_UTF8 - -The output is an integer that is set to one if UTF-8 support is available; -otherwise it is set to zero. - - PCRE_CONFIG_NEWLINE - -The output is an integer that it set to the value of the code that is used for -newline. It is either LF (10) or CR (13). - - PCRE_CONFIG_LINK_SIZE - -The output is an integer that contains the number of bytes used for internal -linkage in compiled expressions. The value is 2, 3, or 4. See item 32 above. - - PCRE_CONFIG_POSIX_MALLOC_THRESHOLD - -The output is an integer that contains the threshold above which the POSIX -interface uses malloc() for output vectors. See item 31 above. - - PCRE_CONFIG_MATCH_LIMIT - -The output is an unsigned integer that contains the default limit of the number -of match() calls in a pcre_exec() execution. See 42 above. - -44. pcretest has been upgraded by the addition of the -C option. This causes it -to extract all the available output from the new pcre_config() function, and to -output it. The program then exits immediately. - -45. A need has arisen to pass over additional data with calls to pcre_exec() in -order to support additional features. One way would have been to define -pcre_exec2() (for example) with extra arguments, but this would not have been -extensible, and would also have required all calls to the original function to -be mapped to the new one. Instead, I have chosen to extend the mechanism that -is used for passing in "extra" data from pcre_study(). - -The pcre_extra structure is now exposed and defined in pcre.h. It currently -contains the following fields: - - flags a bitmap indicating which of the following fields are set - study_data opaque data from pcre_study() - match_limit a way of specifying a limit on match() calls for a specific - call to pcre_exec() - callout_data data for callouts (see 49 below) - -The flag bits are also defined in pcre.h, and are - - PCRE_EXTRA_STUDY_DATA - PCRE_EXTRA_MATCH_LIMIT - PCRE_EXTRA_CALLOUT_DATA - -The pcre_study() function now returns one of these new pcre_extra blocks, with -the actual study data pointed to by the study_data field, and the -PCRE_EXTRA_STUDY_DATA flag set. This can be passed directly to pcre_exec() as -before. That is, this change is entirely upwards-compatible and requires no -change to existing code. - -If you want to pass in additional data to pcre_exec(), you can either place it -in a pcre_extra block provided by pcre_study(), or create your own pcre_extra -block. - -46. pcretest has been extended to test the PCRE_EXTRA_MATCH_LIMIT feature. If a -data string contains the escape sequence \M, pcretest calls pcre_exec() several -times with different match limits, until it finds the minimum value needed for -pcre_exec() to complete. The value is then output. This can be instructive; for -most simple matches the number is quite small, but for pathological cases it -gets very large very quickly. - -47. There's a new option for pcre_fullinfo() called PCRE_INFO_STUDYSIZE. It -returns the size of the data block pointed to by the study_data field in a -pcre_extra block, that is, the value that was passed as the argument to -pcre_malloc() when PCRE was getting memory in which to place the information -created by pcre_study(). The fourth argument should point to a size_t variable. -pcretest has been extended so that this information is shown after a successful -pcre_study() call when information about the compiled regex is being displayed. - -48. Cosmetic change to Makefile: there's no need to have / after $(DESTDIR) -because what follows is always an absolute path. (Later: it turns out that this -is more than cosmetic for MinGW, because it doesn't like empty path -components.) - -49. Some changes have been made to the callout feature (see 28 above): - -(i) A callout function now has three choices for what it returns: - - 0 => success, carry on matching - > 0 => failure at this point, but backtrack if possible - < 0 => serious error, return this value from pcre_exec() - - Negative values should normally be chosen from the set of PCRE_ERROR_xxx - values. In particular, returning PCRE_ERROR_NOMATCH forces a standard - "match failed" error. The error number PCRE_ERROR_CALLOUT is reserved for - use by callout functions. It will never be used by PCRE itself. - -(ii) The pcre_extra structure (see 45 above) has a void * field called - callout_data, with corresponding flag bit PCRE_EXTRA_CALLOUT_DATA. The - pcre_callout_block structure has a field of the same name. The contents of - the field passed in the pcre_extra structure are passed to the callout - function in the corresponding field in the callout block. This makes it - easier to use the same callout-containing regex from multiple threads. For - testing, the pcretest program has a new data escape - - \C*n pass the number n (may be negative) as callout_data - - If the callout function in pcretest receives a non-zero value as - callout_data, it returns that value. - -50. Makefile wasn't handling CFLAGS properly when compiling dftables. Also, -there were some redundant $(CFLAGS) in commands that are now specified as -$(LINK), which already includes $(CFLAGS). - -51. Extensions to UTF-8 support are listed below. These all apply when (a) PCRE -has been compiled with UTF-8 support *and* pcre_compile() has been compiled -with the PCRE_UTF8 flag. Patterns that are compiled without that flag assume -one-byte characters throughout. Note that case-insensitive matching applies -only to characters whose values are less than 256. PCRE doesn't support the -notion of cases for higher-valued characters. - -(i) A character class whose characters are all within 0-255 is handled as - a bit map, and the map is inverted for negative classes. Previously, a - character > 255 always failed to match such a class; however it should - match if the class was a negative one (e.g. [^ab]). This has been fixed. - -(ii) A negated character class with a single character < 255 is coded as - "not this character" (OP_NOT). This wasn't working properly when the test - character was multibyte, either singly or repeated. - -(iii) Repeats of multibyte characters are now handled correctly in UTF-8 - mode, for example: \x{100}{2,3}. - -(iv) The character escapes \b, \B, \d, \D, \s, \S, \w, and \W (either - singly or repeated) now correctly test multibyte characters. However, - PCRE doesn't recognize any characters with values greater than 255 as - digits, spaces, or word characters. Such characters always match \D, \S, - and \W, and never match \d, \s, or \w. - -(v) Classes may now contain characters and character ranges with values - greater than 255. For example: [ab\x{100}-\x{400}]. - -(vi) pcregrep now has a --utf-8 option (synonym -u) which makes it call - PCRE in UTF-8 mode. - -52. The info request value PCRE_INFO_FIRSTCHAR has been renamed -PCRE_INFO_FIRSTBYTE because it is a byte value. However, the old name is -retained for backwards compatibility. (Note that LASTLITERAL is also a byte -value.) - -53. The single man page has become too large. I have therefore split it up into -a number of separate man pages. These also give rise to individual HTML pages; -these are now put in a separate directory, and there is an index.html page that -lists them all. Some hyperlinking between the pages has been installed. - -54. Added convenience functions for handling named capturing parentheses. - -55. Unknown escapes inside character classes (e.g. [\M]) and escapes that -aren't interpreted therein (e.g. [\C]) are literals in Perl. This is now also -true in PCRE, except when the PCRE_EXTENDED option is set, in which case they -are faulted. - -56. Introduced HOST_CC and HOST_CFLAGS which can be set in the environment when -calling configure. These values are used when compiling the dftables.c program -which is run to generate the source of the default character tables. They -default to the values of CC and CFLAGS. If you are cross-compiling PCRE, -you will need to set these values. - -57. Updated the building process for Windows DLL, as provided by Fred Cox. - - -Version 3.9 02-Jan-02 ---------------------- - -1. A bit of extraneous text had somehow crept into the pcregrep documentation. - -2. If --disable-static was given, the building process failed when trying to -build pcretest and pcregrep. (For some reason it was using libtool to compile -them, which is not right, as they aren't part of the library.) - - -Version 3.8 18-Dec-01 ---------------------- - -1. The experimental UTF-8 code was completely screwed up. It was packing the -bytes in the wrong order. How dumb can you get? - - -Version 3.7 29-Oct-01 ---------------------- - -1. In updating pcretest to check change 1 of version 3.6, I screwed up. -This caused pcretest, when used on the test data, to segfault. Unfortunately, -this didn't happen under Solaris 8, where I normally test things. - -2. The Makefile had to be changed to make it work on BSD systems, where 'make' -doesn't seem to recognize that ./xxx and xxx are the same file. (This entry -isn't in ChangeLog distributed with 3.7 because I forgot when I hastily made -this fix an hour or so after the initial 3.7 release.) - - -Version 3.6 23-Oct-01 ---------------------- - -1. Crashed with /(sens|respons)e and \1ibility/ and "sense and sensibility" if -offsets passed as NULL with zero offset count. - -2. The config.guess and config.sub files had not been updated when I moved to -the latest autoconf. - - -Version 3.5 15-Aug-01 ---------------------- - -1. Added some missing #if !defined NOPOSIX conditionals in pcretest.c that -had been forgotten. - -2. By using declared but undefined structures, we can avoid using "void" -definitions in pcre.h while keeping the internal definitions of the structures -private. - -3. The distribution is now built using autoconf 2.50 and libtool 1.4. From a -user point of view, this means that both static and shared libraries are built -by default, but this can be individually controlled. More of the work of -handling this static/shared cases is now inside libtool instead of PCRE's make -file. - -4. The pcretest utility is now installed along with pcregrep because it is -useful for users (to test regexs) and by doing this, it automatically gets -relinked by libtool. The documentation has been turned into a man page, so -there are now .1, .txt, and .html versions in /doc. - -5. Upgrades to pcregrep: - (i) Added long-form option names like gnu grep. - (ii) Added --help to list all options with an explanatory phrase. - (iii) Added -r, --recursive to recurse into sub-directories. - (iv) Added -f, --file to read patterns from a file. - -6. pcre_exec() was referring to its "code" argument before testing that -argument for NULL (and giving an error if it was NULL). - -7. Upgraded Makefile.in to allow for compiling in a different directory from -the source directory. - -8. Tiny buglet in pcretest: when pcre_fullinfo() was called to retrieve the -options bits, the pointer it was passed was to an int instead of to an unsigned -long int. This mattered only on 64-bit systems. - -9. Fixed typo (3.4/1) in pcre.h again. Sigh. I had changed pcre.h (which is -generated) instead of pcre.in, which it its source. Also made the same change -in several of the .c files. - -10. A new release of gcc defines printf() as a macro, which broke pcretest -because it had an ifdef in the middle of a string argument for printf(). Fixed -by using separate calls to printf(). - -11. Added --enable-newline-is-cr and --enable-newline-is-lf to the configure -script, to force use of CR or LF instead of \n in the source. On non-Unix -systems, the value can be set in config.h. - -12. The limit of 200 on non-capturing parentheses is a _nesting_ limit, not an -absolute limit. Changed the text of the error message to make this clear, and -likewise updated the man page. - -13. The limit of 99 on the number of capturing subpatterns has been removed. -The new limit is 65535, which I hope will not be a "real" limit. - - -Version 3.4 22-Aug-00 ---------------------- - -1. Fixed typo in pcre.h: unsigned const char * changed to const unsigned char *. - -2. Diagnose condition (?(0) as an error instead of crashing on matching. - - -Version 3.3 01-Aug-00 ---------------------- - -1. If an octal character was given, but the value was greater than \377, it -was not getting masked to the least significant bits, as documented. This could -lead to crashes in some systems. - -2. Perl 5.6 (if not earlier versions) accepts classes like [a-\d] and treats -the hyphen as a literal. PCRE used to give an error; it now behaves like Perl. - -3. Added the functions pcre_free_substring() and pcre_free_substring_list(). -These just pass their arguments on to (pcre_free)(), but they are provided -because some uses of PCRE bind it to non-C systems that can call its functions, -but cannot call free() or pcre_free() directly. - -4. Add "make test" as a synonym for "make check". Corrected some comments in -the Makefile. - -5. Add $(DESTDIR)/ in front of all the paths in the "install" target in the -Makefile. - -6. Changed the name of pgrep to pcregrep, because Solaris has introduced a -command called pgrep for grepping around the active processes. - -7. Added the beginnings of support for UTF-8 character strings. - -8. Arranged for the Makefile to pass over the settings of CC, CFLAGS, and -RANLIB to ./ltconfig so that they are used by libtool. I think these are all -the relevant ones. (AR is not passed because ./ltconfig does its own figuring -out for the ar command.) - - -Version 3.2 12-May-00 ---------------------- - -This is purely a bug fixing release. - -1. If the pattern /((Z)+|A)*/ was matched agained ZABCDEFG it matched Z instead -of ZA. This was just one example of several cases that could provoke this bug, -which was introduced by change 9 of version 2.00. The code for breaking -infinite loops after an iteration that matches an empty string was't working -correctly. - -2. The pcretest program was not imitating Perl correctly for the pattern /a*/g -when matched against abbab (for example). After matching an empty string, it -wasn't forcing anchoring when setting PCRE_NOTEMPTY for the next attempt; this -caused it to match further down the string than it should. - -3. The code contained an inclusion of sys/types.h. It isn't clear why this -was there because it doesn't seem to be needed, and it causes trouble on some -systems, as it is not a Standard C header. It has been removed. - -4. Made 4 silly changes to the source to avoid stupid compiler warnings that -were reported on the Macintosh. The changes were from - - while ((c = *(++ptr)) != 0 && c != '\n'); -to - while ((c = *(++ptr)) != 0 && c != '\n') ; - -Totally extraordinary, but if that's what it takes... - -5. PCRE is being used in one environment where neither memmove() nor bcopy() is -available. Added HAVE_BCOPY and an autoconf test for it; if neither -HAVE_MEMMOVE nor HAVE_BCOPY is set, use a built-in emulation function which -assumes the way PCRE uses memmove() (always moving upwards). - -6. PCRE is being used in one environment where strchr() is not available. There -was only one use in pcre.c, and writing it out to avoid strchr() probably gives -faster code anyway. - - -Version 3.1 09-Feb-00 ---------------------- - -The only change in this release is the fixing of some bugs in Makefile.in for -the "install" target: - -(1) It was failing to install pcreposix.h. - -(2) It was overwriting the pcre.3 man page with the pcreposix.3 man page. - - -Version 3.0 01-Feb-00 ---------------------- - -1. Add support for the /+ modifier to perltest (to output $` like it does in -pcretest). - -2. Add support for the /g modifier to perltest. - -3. Fix pcretest so that it behaves even more like Perl for /g when the pattern -matches null strings. - -4. Fix perltest so that it doesn't do unwanted things when fed an empty -pattern. Perl treats empty patterns specially - it reuses the most recent -pattern, which is not what we want. Replace // by /(?#)/ in order to avoid this -effect. - -5. The POSIX interface was broken in that it was just handing over the POSIX -captured string vector to pcre_exec(), but (since release 2.00) PCRE has -required a bigger vector, with some working space on the end. This means that -the POSIX wrapper now has to get and free some memory, and copy the results. - -6. Added some simple autoconf support, placing the test data and the -documentation in separate directories, re-organizing some of the -information files, and making it build pcre-config (a GNU standard). Also added -libtool support for building PCRE as a shared library, which is now the -default. - -7. Got rid of the leading zero in the definition of PCRE_MINOR because 08 and -09 are not valid octal constants. Single digits will be used for minor values -less than 10. - -8. Defined REG_EXTENDED and REG_NOSUB as zero in the POSIX header, so that -existing programs that set these in the POSIX interface can use PCRE without -modification. - -9. Added a new function, pcre_fullinfo() with an extensible interface. It can -return all that pcre_info() returns, plus additional data. The pcre_info() -function is retained for compatibility, but is considered to be obsolete. - -10. Added experimental recursion feature (?R) to handle one common case that -Perl 5.6 will be able to do with (?p{...}). - -11. Added support for POSIX character classes like [:alpha:], which Perl is -adopting. - - -Version 2.08 31-Aug-99 ----------------------- - -1. When startoffset was not zero and the pattern began with ".*", PCRE was not -trying to match at the startoffset position, but instead was moving forward to -the next newline as if a previous match had failed. - -2. pcretest was not making use of PCRE_NOTEMPTY when repeating for /g and /G, -and could get into a loop if a null string was matched other than at the start -of the subject. - -3. Added definitions of PCRE_MAJOR and PCRE_MINOR to pcre.h so the version can -be distinguished at compile time, and for completeness also added PCRE_DATE. - -5. Added Paul Sokolovsky's minor changes to make it easy to compile a Win32 DLL -in GnuWin32 environments. - - -Version 2.07 29-Jul-99 ----------------------- - -1. The documentation is now supplied in plain text form and HTML as well as in -the form of man page sources. - -2. C++ compilers don't like assigning (void *) values to other pointer types. -In particular this affects malloc(). Although there is no problem in Standard -C, I've put in casts to keep C++ compilers happy. - -3. Typo on pcretest.c; a cast of (unsigned char *) in the POSIX regexec() call -should be (const char *). - -4. If NOPOSIX is defined, pcretest.c compiles without POSIX support. This may -be useful for non-Unix systems who don't want to bother with the POSIX stuff. -However, I haven't made this a standard facility. The documentation doesn't -mention it, and the Makefile doesn't support it. - -5. The Makefile now contains an "install" target, with editable destinations at -the top of the file. The pcretest program is not installed. - -6. pgrep -V now gives the PCRE version number and date. - -7. Fixed bug: a zero repetition after a literal string (e.g. /abcde{0}/) was -causing the entire string to be ignored, instead of just the last character. - -8. If a pattern like /"([^\\"]+|\\.)*"/ is applied in the normal way to a -non-matching string, it can take a very, very long time, even for strings of -quite modest length, because of the nested recursion. PCRE now does better in -some of these cases. It does this by remembering the last required literal -character in the pattern, and pre-searching the subject to ensure it is present -before running the real match. In other words, it applies a heuristic to detect -some types of certain failure quickly, and in the above example, if presented -with a string that has no trailing " it gives "no match" very quickly. - -9. A new runtime option PCRE_NOTEMPTY causes null string matches to be ignored; -other alternatives are tried instead. - - -Version 2.06 09-Jun-99 ----------------------- - -1. Change pcretest's output for amount of store used to show just the code -space, because the remainder (the data block) varies in size between 32-bit and -64-bit systems. - -2. Added an extra argument to pcre_exec() to supply an offset in the subject to -start matching at. This allows lookbehinds to work when searching for multiple -occurrences in a string. - -3. Added additional options to pcretest for testing multiple occurrences: - - /+ outputs the rest of the string that follows a match - /g loops for multiple occurrences, using the new startoffset argument - /G loops for multiple occurrences by passing an incremented pointer - -4. PCRE wasn't doing the "first character" optimization for patterns starting -with \b or \B, though it was doing it for other lookbehind assertions. That is, -it wasn't noticing that a match for a pattern such as /\bxyz/ has to start with -the letter 'x'. On long subject strings, this gives a significant speed-up. - - -Version 2.05 21-Apr-99 ----------------------- - -1. Changed the type of magic_number from int to long int so that it works -properly on 16-bit systems. - -2. Fixed a bug which caused patterns starting with .* not to work correctly -when the subject string contained newline characters. PCRE was assuming -anchoring for such patterns in all cases, which is not correct because .* will -not pass a newline unless PCRE_DOTALL is set. It now assumes anchoring only if -DOTALL is set at top level; otherwise it knows that patterns starting with .* -must be retried after every newline in the subject. - - -Version 2.04 18-Feb-99 ----------------------- - -1. For parenthesized subpatterns with repeats whose minimum was zero, the -computation of the store needed to hold the pattern was incorrect (too large). -If such patterns were nested a few deep, this could multiply and become a real -problem. - -2. Added /M option to pcretest to show the memory requirement of a specific -pattern. Made -m a synonym of -s (which does this globally) for compatibility. - -3. Subpatterns of the form (regex){n,m} (i.e. limited maximum) were being -compiled in such a way that the backtracking after subsequent failure was -pessimal. Something like (a){0,3} was compiled as (a)?(a)?(a)? instead of -((a)((a)(a)?)?)? with disastrous performance if the maximum was of any size. - - -Version 2.03 02-Feb-99 ----------------------- - -1. Fixed typo and small mistake in man page. - -2. Added 4th condition (GPL supersedes if conflict) and created separate -LICENCE file containing the conditions. - -3. Updated pcretest so that patterns such as /abc\/def/ work like they do in -Perl, that is the internal \ allows the delimiter to be included in the -pattern. Locked out the use of \ as a delimiter. If \ immediately follows -the final delimiter, add \ to the end of the pattern (to test the error). - -4. Added the convenience functions for extracting substrings after a successful -match. Updated pcretest to make it able to test these functions. - - -Version 2.02 14-Jan-99 ----------------------- - -1. Initialized the working variables associated with each extraction so that -their saving and restoring doesn't refer to uninitialized store. - -2. Put dummy code into study.c in order to trick the optimizer of the IBM C -compiler for OS/2 into generating correct code. Apparently IBM isn't going to -fix the problem. - -3. Pcretest: the timing code wasn't using LOOPREPEAT for timing execution -calls, and wasn't printing the correct value for compiling calls. Increased the -default value of LOOPREPEAT, and the number of significant figures in the -times. - -4. Changed "/bin/rm" in the Makefile to "-rm" so it works on Windows NT. - -5. Renamed "deftables" as "dftables" to get it down to 8 characters, to avoid -a building problem on Windows NT with a FAT file system. - - -Version 2.01 21-Oct-98 ----------------------- - -1. Changed the API for pcre_compile() to allow for the provision of a pointer -to character tables built by pcre_maketables() in the current locale. If NULL -is passed, the default tables are used. - - -Version 2.00 24-Sep-98 ----------------------- - -1. Since the (>?) facility is in Perl 5.005, don't require PCRE_EXTRA to enable -it any more. - -2. Allow quantification of (?>) groups, and make it work correctly. - -3. The first character computation wasn't working for (?>) groups. - -4. Correct the implementation of \Z (it is permitted to match on the \n at the -end of the subject) and add 5.005's \z, which really does match only at the -very end of the subject. - -5. Remove the \X "cut" facility; Perl doesn't have it, and (?> is neater. - -6. Remove the ability to specify CASELESS, MULTILINE, DOTALL, and -DOLLAR_END_ONLY at runtime, to make it possible to implement the Perl 5.005 -localized options. All options to pcre_study() were also removed. - -7. Add other new features from 5.005: - - $(?<= positive lookbehind - $(?a*))*/ (a PCRE_EXTRA facility). - - -Version 1.00 18-Nov-97 ----------------------- - -1. Added compile-time macros to support systems such as SunOS4 which don't have -memmove() or strerror() but have other things that can be used instead. - -2. Arranged that "make clean" removes the executables. - - -Version 0.99 27-Oct-97 ----------------------- - -1. Fixed bug in code for optimizing classes with only one character. It was -initializing a 32-byte map regardless, which could cause it to run off the end -of the memory it had got. - -2. Added, conditional on PCRE_EXTRA, the proposed (?>REGEX) construction. - - -Version 0.98 22-Oct-97 ----------------------- - -1. Fixed bug in code for handling temporary memory usage when there are more -back references than supplied space in the ovector. This could cause segfaults. - - -Version 0.97 21-Oct-97 ----------------------- - -1. Added the \X "cut" facility, conditional on PCRE_EXTRA. - -2. Optimized negated single characters not to use a bit map. - -3. Brought error texts together as macro definitions; clarified some of them; -fixed one that was wrong - it said "range out of order" when it meant "invalid -escape sequence". - -4. Changed some char * arguments to const char *. - -5. Added PCRE_NOTBOL and PCRE_NOTEOL (from POSIX). - -6. Added the POSIX-style API wrapper in pcreposix.a and testing facilities in -pcretest. - - -Version 0.96 16-Oct-97 ----------------------- - -1. Added a simple "pgrep" utility to the distribution. - -2. Fixed an incompatibility with Perl: "{" is now treated as a normal character -unless it appears in one of the precise forms "{ddd}", "{ddd,}", or "{ddd,ddd}" -where "ddd" means "one or more decimal digits". - -3. Fixed serious bug. If a pattern had a back reference, but the call to -pcre_exec() didn't supply a large enough ovector to record the related -identifying subpattern, the match always failed. PCRE now remembers the number -of the largest back reference, and gets some temporary memory in which to save -the offsets during matching if necessary, in order to ensure that -backreferences always work. - -4. Increased the compatibility with Perl in a number of ways: - - (a) . no longer matches \n by default; an option PCRE_DOTALL is provided - to request this handling. The option can be set at compile or exec time. - - (b) $ matches before a terminating newline by default; an option - PCRE_DOLLAR_ENDONLY is provided to override this (but not in multiline - mode). The option can be set at compile or exec time. - - (c) The handling of \ followed by a digit other than 0 is now supposed to be - the same as Perl's. If the decimal number it represents is less than 10 - or there aren't that many previous left capturing parentheses, an octal - escape is read. Inside a character class, it's always an octal escape, - even if it is a single digit. - - (d) An escaped but undefined alphabetic character is taken as a literal, - unless PCRE_EXTRA is set. Currently this just reserves the remaining - escapes. - - (e) {0} is now permitted. (The previous item is removed from the compiled - pattern). - -5. Changed all the names of code files so that the basic parts are no longer -than 10 characters, and abolished the teeny "globals.c" file. - -6. Changed the handling of character classes; they are now done with a 32-byte -bit map always. - -7. Added the -d and /D options to pcretest to make it possible to look at the -internals of compilation without having to recompile pcre. - - -Version 0.95 23-Sep-97 ----------------------- - -1. Fixed bug in pre-pass concerning escaped "normal" characters such as \x5c or -\x20 at the start of a run of normal characters. These were being treated as -real characters, instead of the source characters being re-checked. - - -Version 0.94 18-Sep-97 ----------------------- - -1. The functions are now thread-safe, with the caveat that the global variables -containing pointers to malloc() and free() or alternative functions are the -same for all threads. - -2. Get pcre_study() to generate a bitmap of initial characters for non- -anchored patterns when this is possible, and use it if passed to pcre_exec(). - - -Version 0.93 15-Sep-97 ----------------------- - -1. /(b)|(:+)/ was computing an incorrect first character. - -2. Add pcre_study() to the API and the passing of pcre_extra to pcre_exec(), -but not actually doing anything yet. - -3. Treat "-" characters in classes that cannot be part of ranges as literals, -as Perl does (e.g. [-az] or [az-]). - -4. Set the anchored flag if a branch starts with .* or .*? because that tests -all possible positions. - -5. Split up into different modules to avoid including unneeded functions in a -compiled binary. However, compile and exec are still in one module. The "study" -function is split off. - -6. The character tables are now in a separate module whose source is generated -by an auxiliary program - but can then be edited by hand if required. There are -now no calls to isalnum(), isspace(), isdigit(), isxdigit(), tolower() or -toupper() in the code. - -7. Turn the malloc/free funtions variables into pcre_malloc and pcre_free and -make them global. Abolish the function for setting them, as the caller can now -set them directly. - - -Version 0.92 11-Sep-97 ----------------------- - -1. A repeat with a fixed maximum and a minimum of 1 for an ordinary character -(e.g. /a{1,3}/) was broken (I mis-optimized it). - -2. Caseless matching was not working in character classes if the characters in -the pattern were in upper case. - -3. Make ranges like [W-c] work in the same way as Perl for caseless matching. - -4. Make PCRE_ANCHORED public and accept as a compile option. - -5. Add an options word to pcre_exec() and accept PCRE_ANCHORED and -PCRE_CASELESS at run time. Add escapes \A and \I to pcretest to cause it to -pass them. - -6. Give an error if bad option bits passed at compile or run time. - -7. Add PCRE_MULTILINE at compile and exec time, and (?m) as well. Add \M to -pcretest to cause it to pass that flag. - -8. Add pcre_info(), to get the number of identifying subpatterns, the stored -options, and the first character, if set. - -9. Recognize C+ or C{n,m} where n >= 1 as providing a fixed starting character. - - -Version 0.91 10-Sep-97 ----------------------- - -1. PCRE was failing to diagnose unlimited repeats of subpatterns that could -match the empty string as in /(a*)*/. It was looping and ultimately crashing. - -2. PCRE was looping on encountering an indefinitely repeated back reference to -a subpattern that had matched an empty string, e.g. /(a|)\1*/. It now does what -Perl does - treats the match as successful. - -**** diff --git a/libs/pcre/CleanTxt b/libs/pcre/CleanTxt deleted file mode 100755 index 1f42519c8d..0000000000 --- a/libs/pcre/CleanTxt +++ /dev/null @@ -1,113 +0,0 @@ -#! /usr/bin/perl -w - -# Script to take the output of nroff -man and remove all the backspacing and -# the page footers and the screen commands etc so that it is more usefully -# readable online. In fact, in the latest nroff, intermediate footers don't -# seem to be generated any more. - -$blankcount = 0; -$lastwascut = 0; -$firstheader = 1; - -# Input on STDIN; output to STDOUT. - -while () - { - s/\x1b\[\d+m//g; # Remove screen controls "ESC [ number m" - s/.\x8//g; # Remove "char, backspace" - - # Handle header lines. Retain only the first one we encounter, but remove - # the blank line that follows. Any others (e.g. at end of document) and the - # following blank line are dropped. - - if (/^PCRE(\w*)\(([13])\)\s+PCRE\1\(\2\)$/) - { - if ($firstheader) - { - $firstheader = 0; - print; - $lastprinted = $_; - $lastwascut = 0; - } - $_=; # Remove a blank that follows - next; - } - - # Count runs of empty lines - - if (/^\s*$/) - { - $blankcount++; - $lastwascut = 0; - next; - } - - # If a chunk of lines has been cut out (page footer) and the next line - # has a different indentation, put back one blank line. - - if ($lastwascut && $blankcount < 1 && defined($lastprinted)) - { - ($a) = $lastprinted =~ /^(\s*)/; - ($b) = $_ =~ /^(\s*)/; - $blankcount++ if ($a ne $b); - } - - # We get here only when we have a non-blank line in hand. If it was preceded - # by 3 or more blank lines, read the next 3 lines and see if they are blank. - # If so, remove all 7 lines, and remember that we have just done a cut. - - if ($blankcount >= 3) - { - for ($i = 0; $i < 3; $i++) - { - $next[$i] = ; - $next[$i] = "" if !defined $next[$i]; - $next[$i] =~ s/\x1b\[\d+m//g; # Remove screen controls "ESC [ number m" - $next[$i] =~ s/.\x8//g; # Remove "char, backspace" - } - - # Cut out chunks of the form <3 blanks><3 blanks> - - if ($next[0] =~ /^\s*$/ && - $next[1] =~ /^\s*$/ && - $next[2] =~ /^\s*$/) - { - $blankcount -= 3; - $lastwascut = 1; - } - - # Otherwise output the saved blanks, the current, and the next three - # lines. Remember the last printed line. - - else - { - for ($i = 0; $i < $blankcount; $i++) { print "\n"; } - print; - for ($i = 0; $i < 3; $i++) - { - $next[$i] =~ s/.\x8//g; - print $next[$i]; - $lastprinted = $_; - } - $lastwascut = 0; - $blankcount = 0; - } - } - - # This non-blank line is not preceded by 3 or more blank lines. Output - # any blanks there are, and the line. Remember it. Force two blank lines - # before headings. - - else - { - $blankcount = 2 if /^\S/ && !/^Last updated/ && !/^Copyright/ && - defined($lastprinted); - for ($i = 0; $i < $blankcount; $i++) { print "\n"; } - print; - $lastprinted = $_; - $lastwascut = 0; - $blankcount = 0; - } - } - -# End diff --git a/libs/pcre/Detrail b/libs/pcre/Detrail deleted file mode 100755 index 1c5c7e9cae..0000000000 --- a/libs/pcre/Detrail +++ /dev/null @@ -1,35 +0,0 @@ -#!/usr/bin/perl - -# This is a script for removing trailing whitespace from lines in files that -# are listed on the command line. - -# This subroutine does the work for one file. - -sub detrail { -my($file) = $_[0]; -my($changed) = 0; -open(IN, "$file") || die "Can't open $file for input"; -@lines = ; -close(IN); -foreach (@lines) - { - if (/\s+\n$/) - { - s/\s+\n$/\n/; - $changed = 1; - } - } -if ($changed) - { - open(OUT, ">$file") || die "Can't open $file for output"; - print OUT @lines; - close(OUT); - } -} - -# This is the main program - -$, = ""; # Output field separator -for ($i = 0; $i < @ARGV; $i++) { &detrail($ARGV[$i]); } - -# End diff --git a/libs/pcre/HACKING b/libs/pcre/HACKING deleted file mode 100644 index 1f30d4c487..0000000000 --- a/libs/pcre/HACKING +++ /dev/null @@ -1,418 +0,0 @@ -Technical Notes about PCRE --------------------------- - -These are very rough technical notes that record potentially useful information -about PCRE internals. - -Historical note 1 ------------------ - -Many years ago I implemented some regular expression functions to an algorithm -suggested by Martin Richards. These were not Unix-like in form, and were quite -restricted in what they could do by comparison with Perl. The interesting part -about the algorithm was that the amount of space required to hold the compiled -form of an expression was known in advance. The code to apply an expression did -not operate by backtracking, as the original Henry Spencer code and current -Perl code does, but instead checked all possibilities simultaneously by keeping -a list of current states and checking all of them as it advanced through the -subject string. In the terminology of Jeffrey Friedl's book, it was a "DFA -algorithm", though it was not a traditional Finite State Machine (FSM). When -the pattern was all used up, all remaining states were possible matches, and -the one matching the longest subset of the subject string was chosen. This did -not necessarily maximize the individual wild portions of the pattern, as is -expected in Unix and Perl-style regular expressions. - -Historical note 2 ------------------ - -By contrast, the code originally written by Henry Spencer (which was -subsequently heavily modified for Perl) compiles the expression twice: once in -a dummy mode in order to find out how much store will be needed, and then for -real. (The Perl version probably doesn't do this any more; I'm talking about -the original library.) The execution function operates by backtracking and -maximizing (or, optionally, minimizing in Perl) the amount of the subject that -matches individual wild portions of the pattern. This is an "NFA algorithm" in -Friedl's terminology. - -OK, here's the real stuff -------------------------- - -For the set of functions that form the "basic" PCRE library (which are -unrelated to those mentioned above), I tried at first to invent an algorithm -that used an amount of store bounded by a multiple of the number of characters -in the pattern, to save on compiling time. However, because of the greater -complexity in Perl regular expressions, I couldn't do this. In any case, a -first pass through the pattern is helpful for other reasons. - -Computing the memory requirement: how it was --------------------------------------------- - -Up to and including release 6.7, PCRE worked by running a very degenerate first -pass to calculate a maximum store size, and then a second pass to do the real -compile - which might use a bit less than the predicted amount of memory. The -idea was that this would turn out faster than the Henry Spencer code because -the first pass is degenerate and the second pass can just store stuff straight -into the vector, which it knows is big enough. - -Computing the memory requirement: how it is -------------------------------------------- - -By the time I was working on a potential 6.8 release, the degenerate first pass -had become very complicated and hard to maintain. Indeed one of the early -things I did for 6.8 was to fix Yet Another Bug in the memory computation. Then -I had a flash of inspiration as to how I could run the real compile function in -a "fake" mode that enables it to compute how much memory it would need, while -actually only ever using a few hundred bytes of working memory, and without too -many tests of the mode that might slow it down. So I re-factored the compiling -functions to work this way. This got rid of about 600 lines of source. It -should make future maintenance and development easier. As this was such a major -change, I never released 6.8, instead upping the number to 7.0 (other quite -major changes are also present in the 7.0 release). - -A side effect of this work is that the previous limit of 200 on the nesting -depth of parentheses was removed. However, there is a downside: pcre_compile() -runs more slowly than before (30% or more, depending on the pattern) because it -is doing a full analysis of the pattern. My hope is that this is not a big -issue. - -Traditional matching function ------------------------------ - -The "traditional", and original, matching function is called pcre_exec(), and -it implements an NFA algorithm, similar to the original Henry Spencer algorithm -and the way that Perl works. Not surprising, since it is intended to be as -compatible with Perl as possible. This is the function most users of PCRE will -use most of the time. - -Supplementary matching function -------------------------------- - -From PCRE 6.0, there is also a supplementary matching function called -pcre_dfa_exec(). This implements a DFA matching algorithm that searches -simultaneously for all possible matches that start at one point in the subject -string. (Going back to my roots: see Historical Note 1 above.) This function -intreprets the same compiled pattern data as pcre_exec(); however, not all the -facilities are available, and those that are do not always work in quite the -same way. See the user documentation for details. - -The algorithm that is used for pcre_dfa_exec() is not a traditional FSM, -because it may have a number of states active at one time. More work would be -needed at compile time to produce a traditional FSM where only one state is -ever active at once. I believe some other regex matchers work this way. - - -Format of compiled patterns ---------------------------- - -The compiled form of a pattern is a vector of bytes, containing items of -variable length. The first byte in an item is an opcode, and the length of the -item is either implicit in the opcode or contained in the data bytes that -follow it. - -In many cases below LINK_SIZE data values are specified for offsets within the -compiled pattern. The default value for LINK_SIZE is 2, but PCRE can be -compiled to use 3-byte or 4-byte values for these offsets (impairing the -performance). This is necessary only when patterns whose compiled length is -greater than 64K are going to be processed. In this description, we assume the -"normal" compilation options. Data values that are counts (e.g. for -quantifiers) are always just two bytes long. - -A list of the opcodes follows: - -Opcodes with no following data ------------------------------- - -These items are all just one byte long - - OP_END end of pattern - OP_ANY match any one character other than newline - OP_ALLANY match any one character, including newline - OP_ANYBYTE match any single byte, even in UTF-8 mode - OP_SOD match start of data: \A - OP_SOM, start of match (subject + offset): \G - OP_SET_SOM, set start of match (\K) - OP_CIRC ^ (start of data, or after \n in multiline) - OP_NOT_WORD_BOUNDARY \W - OP_WORD_BOUNDARY \w - OP_NOT_DIGIT \D - OP_DIGIT \d - OP_NOT_HSPACE \H - OP_HSPACE \h - OP_NOT_WHITESPACE \S - OP_WHITESPACE \s - OP_NOT_VSPACE \V - OP_VSPACE \v - OP_NOT_WORDCHAR \W - OP_WORDCHAR \w - OP_EODN match end of data or \n at end: \Z - OP_EOD match end of data: \z - OP_DOLL $ (end of data, or before \n in multiline) - OP_EXTUNI match an extended Unicode character - OP_ANYNL match any Unicode newline sequence - - OP_ACCEPT ) - OP_COMMIT ) - OP_FAIL ) These are Perl 5.10's "backtracking - OP_PRUNE ) control verbs". - OP_SKIP ) - OP_THEN ) - - -Repeating single characters ---------------------------- - -The common repeats (*, +, ?) when applied to a single character use the -following opcodes: - - OP_STAR - OP_MINSTAR - OP_POSSTAR - OP_PLUS - OP_MINPLUS - OP_POSPLUS - OP_QUERY - OP_MINQUERY - OP_POSQUERY - -In ASCII mode, these are two-byte items; in UTF-8 mode, the length is variable. -Those with "MIN" in their name are the minimizing versions. Those with "POS" in -their names are possessive versions. Each is followed by the character that is -to be repeated. Other repeats make use of - - OP_UPTO - OP_MINUPTO - OP_POSUPTO - OP_EXACT - -which are followed by a two-byte count (most significant first) and the -repeated character. OP_UPTO matches from 0 to the given number. A repeat with a -non-zero minimum and a fixed maximum is coded as an OP_EXACT followed by an -OP_UPTO (or OP_MINUPTO or OPT_POSUPTO). - - -Repeating character types -------------------------- - -Repeats of things like \d are done exactly as for single characters, except -that instead of a character, the opcode for the type is stored in the data -byte. The opcodes are: - - OP_TYPESTAR - OP_TYPEMINSTAR - OP_TYPEPOSSTAR - OP_TYPEPLUS - OP_TYPEMINPLUS - OP_TYPEPOSPLUS - OP_TYPEQUERY - OP_TYPEMINQUERY - OP_TYPEPOSQUERY - OP_TYPEUPTO - OP_TYPEMINUPTO - OP_TYPEPOSUPTO - OP_TYPEEXACT - - -Match by Unicode property -------------------------- - -OP_PROP and OP_NOTPROP are used for positive and negative matches of a -character by testing its Unicode property (the \p and \P escape sequences). -Each is followed by two bytes that encode the desired property as a type and a -value. - -Repeats of these items use the OP_TYPESTAR etc. set of opcodes, followed by -three bytes: OP_PROP or OP_NOTPROP and then the desired property type and -value. - - -Matching literal characters ---------------------------- - -The OP_CHAR opcode is followed by a single character that is to be matched -casefully. For caseless matching, OP_CHARNC is used. In UTF-8 mode, the -character may be more than one byte long. (Earlier versions of PCRE used -multi-character strings, but this was changed to allow some new features to be -added.) - - -Character classes ------------------ - -If there is only one character, OP_CHAR or OP_CHARNC is used for a positive -class, and OP_NOT for a negative one (that is, for something like [^a]). -However, in UTF-8 mode, the use of OP_NOT applies only to characters with -values < 128, because OP_NOT is confined to single bytes. - -Another set of repeating opcodes (OP_NOTSTAR etc.) are used for a repeated, -negated, single-character class. The normal ones (OP_STAR etc.) are used for a -repeated positive single-character class. - -When there's more than one character in a class and all the characters are less -than 256, OP_CLASS is used for a positive class, and OP_NCLASS for a negative -one. In either case, the opcode is followed by a 32-byte bit map containing a 1 -bit for every character that is acceptable. The bits are counted from the least -significant end of each byte. - -The reason for having both OP_CLASS and OP_NCLASS is so that, in UTF-8 mode, -subject characters with values greater than 256 can be handled correctly. For -OP_CLASS they don't match, whereas for OP_NCLASS they do. - -For classes containing characters with values > 255, OP_XCLASS is used. It -optionally uses a bit map (if any characters lie within it), followed by a list -of pairs and single characters. There is a flag character than indicates -whether it's a positive or a negative class. - - -Back references ---------------- - -OP_REF is followed by two bytes containing the reference number. - - -Repeating character classes and back references ------------------------------------------------ - -Single-character classes are handled specially (see above). This section -applies to OP_CLASS and OP_REF. In both cases, the repeat information follows -the base item. The matching code looks at the following opcode to see if it is -one of - - OP_CRSTAR - OP_CRMINSTAR - OP_CRPLUS - OP_CRMINPLUS - OP_CRQUERY - OP_CRMINQUERY - OP_CRRANGE - OP_CRMINRANGE - -All but the last two are just single-byte items. The others are followed by -four bytes of data, comprising the minimum and maximum repeat counts. There are -no special possessive opcodes for these repeats; a possessive repeat is -compiled into an atomic group. - - -Brackets and alternation ------------------------- - -A pair of non-capturing (round) brackets is wrapped round each expression at -compile time, so alternation always happens in the context of brackets. - -[Note for North Americans: "bracket" to some English speakers, including -myself, can be round, square, curly, or pointy. Hence this usage.] - -Non-capturing brackets use the opcode OP_BRA. Originally PCRE was limited to 99 -capturing brackets and it used a different opcode for each one. From release -3.5, the limit was removed by putting the bracket number into the data for -higher-numbered brackets. From release 7.0 all capturing brackets are handled -this way, using the single opcode OP_CBRA. - -A bracket opcode is followed by LINK_SIZE bytes which give the offset to the -next alternative OP_ALT or, if there aren't any branches, to the matching -OP_KET opcode. Each OP_ALT is followed by LINK_SIZE bytes giving the offset to -the next one, or to the OP_KET opcode. For capturing brackets, the bracket -number immediately follows the offset, always as a 2-byte item. - -OP_KET is used for subpatterns that do not repeat indefinitely, while -OP_KETRMIN and OP_KETRMAX are used for indefinite repetitions, minimally or -maximally respectively. All three are followed by LINK_SIZE bytes giving (as a -positive number) the offset back to the matching bracket opcode. - -If a subpattern is quantified such that it is permitted to match zero times, it -is preceded by one of OP_BRAZERO, OP_BRAMINZERO, or OP_SKIPZERO. These are -single-byte opcodes that tell the matcher that skipping the following -subpattern entirely is a valid branch. In the case of the first two, not -skipping the pattern is also valid (greedy and non-greedy). The third is used -when a pattern has the quantifier {0,0}. It cannot be entirely discarded, -because it may be called as a subroutine from elsewhere in the regex. - -A subpattern with an indefinite maximum repetition is replicated in the -compiled data its minimum number of times (or once with OP_BRAZERO if the -minimum is zero), with the final copy terminating with OP_KETRMIN or OP_KETRMAX -as appropriate. - -A subpattern with a bounded maximum repetition is replicated in a nested -fashion up to the maximum number of times, with OP_BRAZERO or OP_BRAMINZERO -before each replication after the minimum, so that, for example, (abc){2,5} is -compiled as (abc)(abc)((abc)((abc)(abc)?)?)?, except that each bracketed group -has the same number. - -When a repeated subpattern has an unbounded upper limit, it is checked to see -whether it could match an empty string. If this is the case, the opcode in the -final replication is changed to OP_SBRA or OP_SCBRA. This tells the matcher -that it needs to check for matching an empty string when it hits OP_KETRMIN or -OP_KETRMAX, and if so, to break the loop. - - -Assertions ----------- - -Forward assertions are just like other subpatterns, but starting with one of -the opcodes OP_ASSERT or OP_ASSERT_NOT. Backward assertions use the opcodes -OP_ASSERTBACK and OP_ASSERTBACK_NOT, and the first opcode inside the assertion -is OP_REVERSE, followed by a two byte count of the number of characters to move -back the pointer in the subject string. When operating in UTF-8 mode, the count -is a character count rather than a byte count. A separate count is present in -each alternative of a lookbehind assertion, allowing them to have different -fixed lengths. - - -Once-only (atomic) subpatterns ------------------------------- - -These are also just like other subpatterns, but they start with the opcode -OP_ONCE. The check for matching an empty string in an unbounded repeat is -handled entirely at runtime, so there is just this one opcode. - - -Conditional subpatterns ------------------------ - -These are like other subpatterns, but they start with the opcode OP_COND, or -OP_SCOND for one that might match an empty string in an unbounded repeat. If -the condition is a back reference, this is stored at the start of the -subpattern using the opcode OP_CREF followed by two bytes containing the -reference number. If the condition is "in recursion" (coded as "(?(R)"), or "in -recursion of group x" (coded as "(?(Rx)"), the group number is stored at the -start of the subpattern using the opcode OP_RREF, and a value of zero for "the -whole pattern". For a DEFINE condition, just the single byte OP_DEF is used (it -has no associated data). Otherwise, a conditional subpattern always starts with -one of the assertions. - - -Recursion ---------- - -Recursion either matches the current regex, or some subexpression. The opcode -OP_RECURSE is followed by an value which is the offset to the starting bracket -from the start of the whole pattern. From release 6.5, OP_RECURSE is -automatically wrapped inside OP_ONCE brackets (because otherwise some patterns -broke it). OP_RECURSE is also used for "subroutine" calls, even though they -are not strictly a recursion. - - -Callout -------- - -OP_CALLOUT is followed by one byte of data that holds a callout number in the -range 0 to 254 for manual callouts, or 255 for an automatic callout. In both -cases there follows a two-byte value giving the offset in the pattern to the -start of the following item, and another two-byte item giving the length of the -next item. - - -Changing options ----------------- - -If any of the /i, /m, or /s options are changed within a pattern, an OP_OPT -opcode is compiled, followed by one byte containing the new settings of these -flags. If there are several alternatives, there is an occurrence of OP_OPT at -the start of all those following the first options change, to set appropriate -options for the start of the alternative. Immediately after the end of the -group there is another such item to reset the flags to their previous values. A -change of flag right at the very start of the pattern can be handled entirely -at compile time, and so does not cause anything to be put into the compiled -data. - -Philip Hazel -April 2008 diff --git a/libs/pcre/INSTALL b/libs/pcre/INSTALL deleted file mode 100644 index 8b82ade08e..0000000000 --- a/libs/pcre/INSTALL +++ /dev/null @@ -1,291 +0,0 @@ -Installation Instructions -************************* - -Copyright (C) 1994, 1995, 1996, 1999, 2000, 2001, 2002, 2004, 2005, -2006, 2007, 2008 Free Software Foundation, Inc. - - This file is free documentation; the Free Software Foundation gives -unlimited permission to copy, distribute and modify it. - -Basic Installation -================== - - Briefly, the shell commands `./configure; make; make install' should -configure, build, and install this package. The following -more-detailed instructions are generic; see the `README' file for -instructions specific to this package. - - The `configure' shell script attempts to guess correct values for -various system-dependent variables used during compilation. It uses -those values to create a `Makefile' in each directory of the package. -It may also create one or more `.h' files containing system-dependent -definitions. Finally, it creates a shell script `config.status' that -you can run in the future to recreate the current configuration, and a -file `config.log' containing compiler output (useful mainly for -debugging `configure'). - - It can also use an optional file (typically called `config.cache' -and enabled with `--cache-file=config.cache' or simply `-C') that saves -the results of its tests to speed up reconfiguring. Caching is -disabled by default to prevent problems with accidental use of stale -cache files. - - If you need to do unusual things to compile the package, please try -to figure out how `configure' could check whether to do them, and mail -diffs or instructions to the address given in the `README' so they can -be considered for the next release. If you are using the cache, and at -some point `config.cache' contains results you don't want to keep, you -may remove or edit it. - - The file `configure.ac' (or `configure.in') is used to create -`configure' by a program called `autoconf'. You need `configure.ac' if -you want to change it or regenerate `configure' using a newer version -of `autoconf'. - -The simplest way to compile this package is: - - 1. `cd' to the directory containing the package's source code and type - `./configure' to configure the package for your system. - - Running `configure' might take a while. While running, it prints - some messages telling which features it is checking for. - - 2. Type `make' to compile the package. - - 3. Optionally, type `make check' to run any self-tests that come with - the package. - - 4. Type `make install' to install the programs and any data files and - documentation. - - 5. You can remove the program binaries and object files from the - source code directory by typing `make clean'. To also remove the - files that `configure' created (so you can compile the package for - a different kind of computer), type `make distclean'. There is - also a `make maintainer-clean' target, but that is intended mainly - for the package's developers. If you use it, you may have to get - all sorts of other programs in order to regenerate files that came - with the distribution. - - 6. Often, you can also type `make uninstall' to remove the installed - files again. - -Compilers and Options -===================== - - Some systems require unusual options for compilation or linking that -the `configure' script does not know about. Run `./configure --help' -for details on some of the pertinent environment variables. - - You can give `configure' initial values for configuration parameters -by setting variables in the command line or in the environment. Here -is an example: - - ./configure CC=c99 CFLAGS=-g LIBS=-lposix - - *Note Defining Variables::, for more details. - -Compiling For Multiple Architectures -==================================== - - You can compile the package for more than one kind of computer at the -same time, by placing the object files for each architecture in their -own directory. To do this, you can use GNU `make'. `cd' to the -directory where you want the object files and executables to go and run -the `configure' script. `configure' automatically checks for the -source code in the directory that `configure' is in and in `..'. - - With a non-GNU `make', it is safer to compile the package for one -architecture at a time in the source code directory. After you have -installed the package for one architecture, use `make distclean' before -reconfiguring for another architecture. - - On MacOS X 10.5 and later systems, you can create libraries and -executables that work on multiple system types--known as "fat" or -"universal" binaries--by specifying multiple `-arch' options to the -compiler but only a single `-arch' option to the preprocessor. Like -this: - - ./configure CC="gcc -arch i386 -arch x86_64 -arch ppc -arch ppc64" \ - CXX="g++ -arch i386 -arch x86_64 -arch ppc -arch ppc64" \ - CPP="gcc -E" CXXCPP="g++ -E" - - This is not guaranteed to produce working output in all cases, you -may have to build one architecture at a time and combine the results -using the `lipo' tool if you have problems. - -Installation Names -================== - - By default, `make install' installs the package's commands under -`/usr/local/bin', include files under `/usr/local/include', etc. You -can specify an installation prefix other than `/usr/local' by giving -`configure' the option `--prefix=PREFIX'. - - You can specify separate installation prefixes for -architecture-specific files and architecture-independent files. If you -pass the option `--exec-prefix=PREFIX' to `configure', the package uses -PREFIX as the prefix for installing programs and libraries. -Documentation and other data files still use the regular prefix. - - In addition, if you use an unusual directory layout you can give -options like `--bindir=DIR' to specify different values for particular -kinds of files. Run `configure --help' for a list of the directories -you can set and what kinds of files go in them. - - If the package supports it, you can cause programs to be installed -with an extra prefix or suffix on their names by giving `configure' the -option `--program-prefix=PREFIX' or `--program-suffix=SUFFIX'. - -Optional Features -================= - - Some packages pay attention to `--enable-FEATURE' options to -`configure', where FEATURE indicates an optional part of the package. -They may also pay attention to `--with-PACKAGE' options, where PACKAGE -is something like `gnu-as' or `x' (for the X Window System). The -`README' should mention any `--enable-' and `--with-' options that the -package recognizes. - - For packages that use the X Window System, `configure' can usually -find the X include and library files automatically, but if it doesn't, -you can use the `configure' options `--x-includes=DIR' and -`--x-libraries=DIR' to specify their locations. - -Particular systems -================== - - On HP-UX, the default C compiler is not ANSI C compatible. If GNU -CC is not installed, it is recommended to use the following options in -order to use an ANSI C compiler: - - ./configure CC="cc -Ae" - -and if that doesn't work, install pre-built binaries of GCC for HP-UX. - - On OSF/1 a.k.a. Tru64, some versions of the default C compiler cannot -parse its `' header file. The option `-nodtk' can be used as -a workaround. If GNU CC is not installed, it is therefore recommended -to try - - ./configure CC="cc" - -and if that doesn't work, try - - ./configure CC="cc -nodtk" - -Specifying the System Type -========================== - - There may be some features `configure' cannot figure out -automatically, but needs to determine by the type of machine the package -will run on. Usually, assuming the package is built to be run on the -_same_ architectures, `configure' can figure that out, but if it prints -a message saying it cannot guess the machine type, give it the -`--build=TYPE' option. TYPE can either be a short name for the system -type, such as `sun4', or a canonical name which has the form: - - CPU-COMPANY-SYSTEM - -where SYSTEM can have one of these forms: - - OS KERNEL-OS - - See the file `config.sub' for the possible values of each field. If -`config.sub' isn't included in this package, then this package doesn't -need to know the machine type. - - If you are _building_ compiler tools for cross-compiling, you should -use the option `--target=TYPE' to select the type of system they will -produce code for. - - If you want to _use_ a cross compiler, that generates code for a -platform different from the build platform, you should specify the -"host" platform (i.e., that on which the generated programs will -eventually be run) with `--host=TYPE'. - -Sharing Defaults -================ - - If you want to set default values for `configure' scripts to share, -you can create a site shell script called `config.site' that gives -default values for variables like `CC', `cache_file', and `prefix'. -`configure' looks for `PREFIX/share/config.site' if it exists, then -`PREFIX/etc/config.site' if it exists. Or, you can set the -`CONFIG_SITE' environment variable to the location of the site script. -A warning: not all `configure' scripts look for a site script. - -Defining Variables -================== - - Variables not defined in a site shell script can be set in the -environment passed to `configure'. However, some packages may run -configure again during the build, and the customized values of these -variables may be lost. In order to avoid this problem, you should set -them in the `configure' command line, using `VAR=value'. For example: - - ./configure CC=/usr/local2/bin/gcc - -causes the specified `gcc' to be used as the C compiler (unless it is -overridden in the site shell script). - -Unfortunately, this technique does not work for `CONFIG_SHELL' due to -an Autoconf bug. Until the bug is fixed you can use this workaround: - - CONFIG_SHELL=/bin/bash /bin/bash ./configure CONFIG_SHELL=/bin/bash - -`configure' Invocation -====================== - - `configure' recognizes the following options to control how it -operates. - -`--help' -`-h' - Print a summary of all of the options to `configure', and exit. - -`--help=short' -`--help=recursive' - Print a summary of the options unique to this package's - `configure', and exit. The `short' variant lists options used - only in the top level, while the `recursive' variant lists options - also present in any nested packages. - -`--version' -`-V' - Print the version of Autoconf used to generate the `configure' - script, and exit. - -`--cache-file=FILE' - Enable the cache: use and save the results of the tests in FILE, - traditionally `config.cache'. FILE defaults to `/dev/null' to - disable caching. - -`--config-cache' -`-C' - Alias for `--cache-file=config.cache'. - -`--quiet' -`--silent' -`-q' - Do not print messages saying which checks are being made. To - suppress all normal output, redirect it to `/dev/null' (any error - messages will still be shown). - -`--srcdir=DIR' - Look for the package's source code in directory DIR. Usually - `configure' can determine that directory automatically. - -`--prefix=DIR' - Use DIR as the installation prefix. *Note Installation Names:: - for more details, including other options available for fine-tuning - the installation locations. - -`--no-create' -`-n' - Run the configure checks, but stop before creating any output - files. - -`configure' also accepts some other, not widely useful, options. Run -`configure --help' for more details. - diff --git a/libs/pcre/LICENCE b/libs/pcre/LICENCE deleted file mode 100644 index ff443a929c..0000000000 --- a/libs/pcre/LICENCE +++ /dev/null @@ -1,68 +0,0 @@ -PCRE LICENCE ------------- - -PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - -Release 7 of PCRE is distributed under the terms of the "BSD" licence, as -specified below. The documentation for PCRE, supplied in the "doc" -directory, is distributed under the same terms as the software itself. - -The basic library functions are written in C and are freestanding. Also -included in the distribution is a set of C++ wrapper functions. - - -THE BASIC LIBRARY FUNCTIONS ---------------------------- - -Written by: Philip Hazel -Email local part: ph10 -Email domain: cam.ac.uk - -University of Cambridge Computing Service, -Cambridge, England. - -Copyright (c) 1997-2009 University of Cambridge -All rights reserved. - - -THE C++ WRAPPER FUNCTIONS -------------------------- - -Contributed by: Google Inc. - -Copyright (c) 2007-2008, Google Inc. -All rights reserved. - - -THE "BSD" LICENCE ------------------ - -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the name of Google - Inc. nor the names of their contributors may be used to endorse or - promote products derived from this software without specific prior - written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. - -End diff --git a/libs/pcre/Makefile.am b/libs/pcre/Makefile.am deleted file mode 100644 index 0d84062f2b..0000000000 --- a/libs/pcre/Makefile.am +++ /dev/null @@ -1,334 +0,0 @@ -## Process this file with automake to produce Makefile.in. - -pcrecpp_html = doc/html/pcrecpp.html -dist_noinst_DATA = $(pcrecpp_html) - -# The Libtool libraries to install. We'll add to this later. -lib_LTLIBRARIES = - -# Unit tests you want to run when people type 'make check'. -# TESTS is for binary unit tests, check_SCRIPTS for script-based tests -TESTS = -check_SCRIPTS = -dist_noinst_SCRIPTS = - -# Some of the binaries we make are to be installed, and others are -# (non-user-visible) helper programs needed to build libpcre. -bin_PROGRAMS = -noinst_PROGRAMS = - -# Additional files to delete on 'make clean' and 'make maintainer-clean'. -CLEANFILES = -MAINTAINERCLEANFILES = - -# Additional files to bundle with the distribution, over and above what -# the Autotools include by default. -EXTRA_DIST = - -# These files contain maintenance information -EXTRA_DIST += \ - doc/perltest.txt \ - NON-UNIX-USE \ - HACKING - -# These files are used in the preparation of a release -EXTRA_DIST += \ - PrepareRelease \ - CleanTxt \ - Detrail \ - 132html \ - doc/index.html.src - -# These files are to do with building for Virtual Pascal -EXTRA_DIST += \ - makevp.bat \ - makevp_c.txt \ - makevp_l.txt \ - pcregexp.pas - -# These files are usable versions of pcre.h and config.h that are distributed -# for the benefit of people who are building PCRE manually, without the -# Autotools support. -EXTRA_DIST += \ - pcre.h.generic \ - config.h.generic - -pcre.h.generic: configure.ac - rm -f $@ - cp -p pcre.h $@ - -MAINTAINERCLEANFILES += pcre.h.generic - -# These are the header files we'll install. We do not distribute pcre.h because -# it is generated from pcre.h.in. -nodist_include_HEADERS = \ - pcre.h -include_HEADERS = \ - pcreposix.h - -# These additional headers will be be installed if C++ support is enabled. We -# do not distribute pcrecpparg.h or pcre_stringpiece.h, as these are generated -# from corresponding .h.in files (which we do distribute). -if WITH_PCRE_CPP -nodist_include_HEADERS += \ - pcrecpparg.h \ - pcre_stringpiece.h -include_HEADERS += \ - pcrecpp.h \ - pcre_scanner.h -endif # WITH_PCRE_CPP - -bin_SCRIPTS = pcre-config - -## --------------------------------------------------------------- -## The dftables program is used to rebuild character tables before compiling -## PCRE, if --enable-rebuild-chartables is specified. It is not a user-visible -## program. The default (when --enable-rebuild-chartables is not specified) is -## to copy a distributed set of tables that are defined for ASCII code. In this -## case, dftables is not needed. - -if WITH_REBUILD_CHARTABLES - -noinst_PROGRAMS += dftables -dftables_SOURCES = dftables.c - -pcre_chartables.c: dftables$(EXEEXT) - ./dftables$(EXEEXT) $@ -else - -pcre_chartables.c: $(srcdir)/pcre_chartables.c.dist - rm -f $@ - $(LN_S) $(srcdir)/pcre_chartables.c.dist $@ - -endif # WITH_REBUILD_CHARTABLES - - -## The main pcre library -lib_LTLIBRARIES += libpcre.la -libpcre_la_SOURCES = \ - pcre_compile.c \ - pcre_config.c \ - pcre_dfa_exec.c \ - pcre_exec.c \ - pcre_fullinfo.c \ - pcre_get.c \ - pcre_globals.c \ - pcre_info.c \ - pcre_internal.h \ - pcre_maketables.c \ - pcre_newline.c \ - pcre_ord2utf8.c \ - pcre_refcount.c \ - pcre_study.c \ - pcre_tables.c \ - pcre_try_flipped.c \ - pcre_ucd.c \ - pcre_valid_utf8.c \ - pcre_version.c \ - pcre_xclass.c \ - ucp.h - -## This file is generated as part of the building process, so don't distribute. -nodist_libpcre_la_SOURCES = \ - pcre_chartables.c - -# The pcre_printint.src file is #included by some source files, so it must be -# distributed. The pcre_chartables.c.dist file is the default version of -# pcre_chartables.c, used unless --enable-rebuild-chartables is specified. -EXTRA_DIST += pcre_printint.src pcre_chartables.c.dist - -libpcre_la_LDFLAGS = $(EXTRA_LIBPCRE_LDFLAGS) - -CLEANFILES += pcre_chartables.c - -## A version of the main pcre library that has a posix re API. -lib_LTLIBRARIES += libpcreposix.la -libpcreposix_la_SOURCES = \ - pcreposix.c -libpcreposix_la_LDFLAGS = $(EXTRA_LIBPCREPOSIX_LDFLAGS) -libpcreposix_la_LIBADD = libpcre.la - -## There's a C++ library as well. -if WITH_PCRE_CPP - -lib_LTLIBRARIES += libpcrecpp.la -libpcrecpp_la_SOURCES = \ - pcrecpp_internal.h \ - pcrecpp.cc \ - pcre_scanner.cc \ - pcre_stringpiece.cc -libpcrecpp_la_LDFLAGS = $(EXTRA_LIBPCRECPP_LDFLAGS) -libpcrecpp_la_LIBADD = libpcre.la - -TESTS += pcrecpp_unittest -noinst_PROGRAMS += pcrecpp_unittest -pcrecpp_unittest_SOURCES = pcrecpp_unittest.cc -pcrecpp_unittest_LDADD = libpcrecpp.la - -TESTS += pcre_scanner_unittest -noinst_PROGRAMS += pcre_scanner_unittest -pcre_scanner_unittest_SOURCES = pcre_scanner_unittest.cc -pcre_scanner_unittest_LDADD = libpcrecpp.la - -TESTS += pcre_stringpiece_unittest -noinst_PROGRAMS += pcre_stringpiece_unittest -pcre_stringpiece_unittest_SOURCES = pcre_stringpiece_unittest.cc -pcre_stringpiece_unittest_LDADD = libpcrecpp.la - -endif # WITH_PCRE_CPP - -## The main unit tests - -# Each unit test is a binary plus a script that runs that binary in various -# ways. We install these test binaries in case folks find it helpful. - -TESTS += RunTest -dist_noinst_SCRIPTS += RunTest -EXTRA_DIST += RunTest.bat -bin_PROGRAMS += pcretest -pcretest_SOURCES = pcretest.c -pcretest_LDADD = libpcreposix.la $(LIBREADLINE) - -TESTS += RunGrepTest -dist_noinst_SCRIPTS += RunGrepTest -bin_PROGRAMS += pcregrep -pcregrep_SOURCES = pcregrep.c -pcregrep_LDADD = libpcreposix.la $(LIBZ) $(LIBBZ2) - -EXTRA_DIST += \ - testdata/grepinput \ - testdata/grepinput8 \ - testdata/grepinputv \ - testdata/grepinputx \ - testdata/greplist \ - testdata/grepoutput \ - testdata/grepoutput8 \ - testdata/grepoutputN \ - testdata/testinput1 \ - testdata/testinput2 \ - testdata/testinput3 \ - testdata/testinput4 \ - testdata/testinput5 \ - testdata/testinput6 \ - testdata/testinput7 \ - testdata/testinput8 \ - testdata/testinput9 \ - testdata/testinput10 \ - testdata/testoutput1 \ - testdata/testoutput2 \ - testdata/testoutput3 \ - testdata/testoutput4 \ - testdata/testoutput5 \ - testdata/testoutput6 \ - testdata/testoutput7 \ - testdata/testoutput8 \ - testdata/testoutput9 \ - testdata/testoutput10 \ - testdata/wintestinput3 \ - testdata/wintestoutput3 \ - perltest.pl - -CLEANFILES += \ - testsavedregex \ - teststderr \ - testtry \ - testNinput - - -# PCRE demonstration program. No longer built automatcally. The point is that -# the users should build it themselves. So just distribute the source. -# noinst_PROGRAMS += pcredemo -# pcredemo_SOURCES = pcredemo.c -# pcredemo_LDADD = libpcre.la - -EXTRA_DIST += pcredemo.c - - -## Utility rules, documentation, etc. - -# A compatibility line, the old build system worked with 'make test' -test: check ; - - -# A PCRE user submitted the following addition, saying that it "will allow -# anyone using the 'mingw32' compiler to simply type 'make pcre.dll' and get a -# nice DLL for Windows use". (It is used by the pcre.dll target.) -DLL_OBJS= pcre_compile.o pcre_config.o \ - pcre_dfa_exec.o pcre_exec.o pcre_fullinfo.o pcre_get.o \ - pcre_globals.o pcre_info.o pcre_maketables.o \ - pcre_newline.o pcre_ord2utf8.o pcre_refcount.o \ - pcre_study.o pcre_tables.o pcre_try_flipped.o \ - pcre_ucd.o pcre_valid_utf8.o pcre_version.o \ - pcre_chartables.o \ - pcre_xclass.o - -# A PCRE user submitted the following addition, saying that it "will allow -# anyone using the 'mingw32' compiler to simply type 'make pcre.dll' and get a -# nice DLL for Windows use". -pcre.dll: $(DLL_OBJS) - $(CC) -shared -o pcre.dll -Wl,"--strip-all" -Wl,"--export-all-symbols" $(DLL_OBJS) - - -# We have .pc files for pkg-config users. -pkgconfigdir = $(libdir)/pkgconfig -pkgconfig_DATA = libpcre.pc -if WITH_PCRE_CPP -pkgconfig_DATA += libpcrecpp.pc -endif - -dist_man_MANS = \ - doc/pcre.3 \ - doc/pcre-config.1 \ - doc/pcre_compile.3 \ - doc/pcre_compile2.3 \ - doc/pcre_config.3 \ - doc/pcre_copy_named_substring.3 \ - doc/pcre_copy_substring.3 \ - doc/pcre_dfa_exec.3 \ - doc/pcre_exec.3 \ - doc/pcre_free_substring.3 \ - doc/pcre_free_substring_list.3 \ - doc/pcre_fullinfo.3 \ - doc/pcre_get_named_substring.3 \ - doc/pcre_get_stringnumber.3 \ - doc/pcre_get_stringtable_entries.3 \ - doc/pcre_get_substring.3 \ - doc/pcre_get_substring_list.3 \ - doc/pcre_info.3 \ - doc/pcre_maketables.3 \ - doc/pcre_refcount.3 \ - doc/pcre_study.3 \ - doc/pcre_version.3 \ - doc/pcreapi.3 \ - doc/pcrebuild.3 \ - doc/pcrecallout.3 \ - doc/pcrecompat.3 \ - doc/pcregrep.1 \ - doc/pcrematching.3 \ - doc/pcrepartial.3 \ - doc/pcrepattern.3 \ - doc/pcreperform.3 \ - doc/pcreposix.3 \ - doc/pcreprecompile.3 \ - doc/pcresample.3 \ - doc/pcrestack.3 \ - doc/pcresyntax.3 \ - doc/pcretest.1 - -pcrecpp_man = doc/pcrecpp.3 -EXTRA_DIST += $(pcrecpp_man) - -if WITH_PCRE_CPP -man_MANS = $(pcrecpp_man) -endif - -## CMake support - -EXTRA_DIST += \ - cmake/COPYING-CMAKE-SCRIPTS \ - cmake/FindPackageHandleStandardArgs.cmake \ - cmake/FindReadline.cmake \ - CMakeLists.txt \ - config-cmake.h.in - -## end Makefile.am diff --git a/libs/pcre/NEWS b/libs/pcre/NEWS deleted file mode 100644 index 2b26fccf51..0000000000 --- a/libs/pcre/NEWS +++ /dev/null @@ -1,428 +0,0 @@ -News about PCRE releases ------------------------- - -Release 7.9 11-Apr-09 ---------------------- - -Mostly bugfixes and tidies with just a couple of minor functional additions. - - -Release 7.8 05-Sep-08 ---------------------- - -More bug fixes, plus a performance improvement in Unicode character property -lookup. - - -Release 7.7 07-May-08 ---------------------- - -This is once again mainly a bug-fix release, but there are a couple of new -features. - - -Release 7.6 28-Jan-08 ---------------------- - -The main reason for having this release so soon after 7.5 is because it fixes a -potential buffer overflow problem in pcre_compile() when run in UTF-8 mode. In -addition, the CMake configuration files have been brought up to date. - - -Release 7.5 10-Jan-08 ---------------------- - -This is mainly a bug-fix release. However the ability to link pcregrep with -libz or libbz2 and the ability to link pcretest with libreadline have been -added. Also the --line-offsets and --file-offsets options were added to -pcregrep. - - -Release 7.4 21-Sep-07 ---------------------- - -The only change of specification is the addition of options to control whether -\R matches any Unicode line ending (the default) or just CR, LF, and CRLF. -Otherwise, the changes are bug fixes and a refactoring to reduce the number of -relocations needed in a shared library. There have also been some documentation -updates, in particular, some more information about using CMake to build PCRE -has been added to the NON-UNIX-USE file. - - -Release 7.3 28-Aug-07 ---------------------- - -Most changes are bug fixes. Some that are not: - -1. There is some support for Perl 5.10's experimental "backtracking control - verbs" such as (*PRUNE). - -2. UTF-8 checking is now as per RFC 3629 instead of RFC 2279; this is more - restrictive in the strings it accepts. - -3. Checking for potential integer overflow has been made more dynamic, and as a - consequence there is no longer a hard limit on the size of a subpattern that - has a limited repeat count. - -4. When CRLF is a valid line-ending sequence, pcre_exec() and pcre_dfa_exec() - no longer advance by two characters instead of one when an unanchored match - fails at CRLF if there are explicit CR or LF matches within the pattern. - This gets rid of some anomalous effects that previously occurred. - -5. Some PCRE-specific settings for varying the newline options at the start of - a pattern have been added. - - -Release 7.2 19-Jun-07 ---------------------- - -WARNING: saved patterns that were compiled by earlier versions of PCRE must be -recompiled for use with 7.2 (necessitated by the addition of \K, \h, \H, \v, -and \V). - -Correction to the notes for 7.1: the note about shared libraries for Windows is -wrong. Previously, three libraries were built, but each could function -independently. For example, the pcreposix library also included all the -functions from the basic pcre library. The change is that the three libraries -are no longer independent. They are like the Unix libraries. To use the -pcreposix functions, for example, you need to link with both the pcreposix and -the basic pcre library. - -Some more features from Perl 5.10 have been added: - - (?-n) and (?+n) relative references for recursion and subroutines. - - (?(-n) and (?(+n) relative references as conditions. - - \k{name} and \g{name} are synonyms for \k. - - \K to reset the start of the matched string; for example, (foo)\Kbar - matches bar preceded by foo, but only sets bar as the matched string. - - (?| introduces a group where the capturing parentheses in each alternative - start from the same number; for example, (?|(abc)|(xyz)) sets capturing - parentheses number 1 in both cases. - - \h, \H, \v, \V match horizontal and vertical whitespace, respectively. - - -Release 7.1 24-Apr-07 ---------------------- - -There is only one new feature in this release: a linebreak setting of -PCRE_NEWLINE_ANYCRLF. It is a cut-down version of PCRE_NEWLINE_ANY, which -recognizes only CRLF, CR, and LF as linebreaks. - -A few bugs are fixed (see ChangeLog for details), but the major change is a -complete re-implementation of the build system. This now has full Autotools -support and so is now "standard" in some sense. It should help with compiling -PCRE in a wide variety of environments. - -NOTE: when building shared libraries for Windows, three dlls are now built, -called libpcre, libpcreposix, and libpcrecpp. Previously, everything was -included in a single dll. - -Another important change is that the dftables auxiliary program is no longer -compiled and run at "make" time by default. Instead, a default set of character -tables (assuming ASCII coding) is used. If you want to use dftables to generate -the character tables as previously, add --enable-rebuild-chartables to the -"configure" command. You must do this if you are compiling PCRE to run on a -system that uses EBCDIC code. - -There is a discussion about character tables in the README file. The default is -not to use dftables so that that there is no problem when cross-compiling. - - -Release 7.0 19-Dec-06 ---------------------- - -This release has a new major number because there have been some internal -upheavals to facilitate the addition of new optimizations and other facilities, -and to make subsequent maintenance and extension easier. Compilation is likely -to be a bit slower, but there should be no major effect on runtime performance. -Previously compiled patterns are NOT upwards compatible with this release. If -you have saved compiled patterns from a previous release, you will have to -re-compile them. Important changes that are visible to users are: - -1. The Unicode property tables have been updated to Unicode 5.0.0, which adds - some more scripts. - -2. The option PCRE_NEWLINE_ANY causes PCRE to recognize any Unicode newline - sequence as a newline. - -3. The \R escape matches a single Unicode newline sequence as a single unit. - -4. New features that will appear in Perl 5.10 are now in PCRE. These include - alternative Perl syntax for named parentheses, and Perl syntax for - recursion. - -5. The C++ wrapper interface has been extended by the addition of a - QuoteMeta function and the ability to allow copy construction and - assignment. - -For a complete list of changes, see the ChangeLog file. - - -Release 6.7 04-Jul-06 ---------------------- - -The main additions to this release are the ability to use the same name for -multiple sets of parentheses, and support for CRLF line endings in both the -library and pcregrep (and in pcretest for testing). - -Thanks to Ian Taylor, the stack usage for many kinds of pattern has been -significantly reduced for certain subject strings. - - -Release 6.5 01-Feb-06 ---------------------- - -Important changes in this release: - -1. A number of new features have been added to pcregrep. - -2. The Unicode property tables have been updated to Unicode 4.1.0, and the - supported properties have been extended with script names such as "Arabic", - and the derived properties "Any" and "L&". This has necessitated a change to - the interal format of compiled patterns. Any saved compiled patterns that - use \p or \P must be recompiled. - -3. The specification of recursion in patterns has been changed so that all - recursive subpatterns are automatically treated as atomic groups. Thus, for - example, (?R) is treated as if it were (?>(?R)). This is necessary because - otherwise there are situations where recursion does not work. - -See the ChangeLog for a complete list of changes, which include a number of bug -fixes and tidies. - - -Release 6.0 07-Jun-05 ---------------------- - -The release number has been increased to 6.0 because of the addition of several -major new pieces of functionality. - -A new function, pcre_dfa_exec(), which implements pattern matching using a DFA -algorithm, has been added. This has a number of advantages for certain cases, -though it does run more slowly, and lacks the ability to capture substrings. On -the other hand, it does find all matches, not just the first, and it works -better for partial matching. The pcrematching man page discusses the -differences. - -The pcretest program has been enhanced so that it can make use of the new -pcre_dfa_exec() matching function and the extra features it provides. - -The distribution now includes a C++ wrapper library. This is built -automatically if a C++ compiler is found. The pcrecpp man page discusses this -interface. - -The code itself has been re-organized into many more files, one for each -function, so it no longer requires everything to be linked in when static -linkage is used. As a consequence, some internal functions have had to have -their names exposed. These functions all have names starting with _pcre_. They -are undocumented, and are not intended for use by outside callers. - -The pcregrep program has been enhanced with new functionality such as -multiline-matching and options for output more matching context. See the -ChangeLog for a complete list of changes to the library and the utility -programs. - - -Release 5.0 13-Sep-04 ---------------------- - -The licence under which PCRE is released has been changed to the more -conventional "BSD" licence. - -In the code, some bugs have been fixed, and there are also some major changes -in this release (which is why I've increased the number to 5.0). Some changes -are internal rearrangements, and some provide a number of new facilities. The -new features are: - -1. There's an "automatic callout" feature that inserts callouts before every - item in the regex, and there's a new callout field that gives the position - in the pattern - useful for debugging and tracing. - -2. The extra_data structure can now be used to pass in a set of character - tables at exec time. This is useful if compiled regex are saved and re-used - at a later time when the tables may not be at the same address. If the - default internal tables are used, the pointer saved with the compiled - pattern is now set to NULL, which means that you don't need to do anything - special unless you are using custom tables. - -3. It is possible, with some restrictions on the content of the regex, to - request "partial" matching. A special return code is given if all of the - subject string matched part of the regex. This could be useful for testing - an input field as it is being typed. - -4. There is now some optional support for Unicode character properties, which - means that the patterns items such as \p{Lu} and \X can now be used. Only - the general category properties are supported. If PCRE is compiled with this - support, an additional 90K data structure is include, which increases the - size of the library dramatically. - -5. There is support for saving compiled patterns and re-using them later. - -6. There is support for running regular expressions that were compiled on a - different host with the opposite endianness. - -7. The pcretest program has been extended to accommodate the new features. - -The main internal rearrangement is that sequences of literal characters are no -longer handled as strings. Instead, each character is handled on its own. This -makes some UTF-8 handling easier, and makes the support of partial matching -possible. Compiled patterns containing long literal strings will be larger as a -result of this change; I hope that performance will not be much affected. - - -Release 4.5 01-Dec-03 ---------------------- - -Again mainly a bug-fix and tidying release, with only a couple of new features: - -1. It's possible now to compile PCRE so that it does not use recursive -function calls when matching. Instead it gets memory from the heap. This slows -things down, but may be necessary on systems with limited stacks. - -2. UTF-8 string checking has been tightened to reject overlong sequences and to -check that a starting offset points to the start of a character. Failure of the -latter returns a new error code: PCRE_ERROR_BADUTF8_OFFSET. - -3. PCRE can now be compiled for systems that use EBCDIC code. - - -Release 4.4 21-Aug-03 ---------------------- - -This is mainly a bug-fix and tidying release. The only new feature is that PCRE -checks UTF-8 strings for validity by default. There is an option to suppress -this, just in case anybody wants that teeny extra bit of performance. - - -Releases 4.1 - 4.3 ------------------- - -Sorry, I forgot about updating the NEWS file for these releases. Please take a -look at ChangeLog. - - -Release 4.0 17-Feb-03 ---------------------- - -There have been a lot of changes for the 4.0 release, adding additional -functionality and mending bugs. Below is a list of the highlights of the new -functionality. For full details of these features, please consult the -documentation. For a complete list of changes, see the ChangeLog file. - -1. Support for Perl's \Q...\E escapes. - -2. "Possessive quantifiers" ?+, *+, ++, and {,}+ which come from Sun's Java -package. They provide some syntactic sugar for simple cases of "atomic -grouping". - -3. Support for the \G assertion. It is true when the current matching position -is at the start point of the match. - -4. A new feature that provides some of the functionality that Perl provides -with (?{...}). The facility is termed a "callout". The way it is done in PCRE -is for the caller to provide an optional function, by setting pcre_callout to -its entry point. To get the function called, the regex must include (?C) at -appropriate points. - -5. Support for recursive calls to individual subpatterns. This makes it really -easy to get totally confused. - -6. Support for named subpatterns. The Python syntax (?P...) is used to -name a group. - -7. Several extensions to UTF-8 support; it is now fairly complete. There is an -option for pcregrep to make it operate in UTF-8 mode. - -8. The single man page has been split into a number of separate man pages. -These also give rise to individual HTML pages which are put in a separate -directory. There is an index.html page that lists them all. Some hyperlinking -between the pages has been installed. - - -Release 3.5 15-Aug-01 ---------------------- - -1. The configuring system has been upgraded to use later versions of autoconf -and libtool. By default it builds both a shared and a static library if the OS -supports it. You can use --disable-shared or --disable-static on the configure -command if you want only one of them. - -2. The pcretest utility is now installed along with pcregrep because it is -useful for users (to test regexs) and by doing this, it automatically gets -relinked by libtool. The documentation has been turned into a man page, so -there are now .1, .txt, and .html versions in /doc. - -3. Upgrades to pcregrep: - (i) Added long-form option names like gnu grep. - (ii) Added --help to list all options with an explanatory phrase. - (iii) Added -r, --recursive to recurse into sub-directories. - (iv) Added -f, --file to read patterns from a file. - -4. Added --enable-newline-is-cr and --enable-newline-is-lf to the configure -script, to force use of CR or LF instead of \n in the source. On non-Unix -systems, the value can be set in config.h. - -5. The limit of 200 on non-capturing parentheses is a _nesting_ limit, not an -absolute limit. Changed the text of the error message to make this clear, and -likewise updated the man page. - -6. The limit of 99 on the number of capturing subpatterns has been removed. -The new limit is 65535, which I hope will not be a "real" limit. - - -Release 3.3 01-Aug-00 ---------------------- - -There is some support for UTF-8 character strings. This is incomplete and -experimental. The documentation describes what is and what is not implemented. -Otherwise, this is just a bug-fixing release. - - -Release 3.0 01-Feb-00 ---------------------- - -1. A "configure" script is now used to configure PCRE for Unix systems. It -builds a Makefile, a config.h file, and the pcre-config script. - -2. PCRE is built as a shared library by default. - -3. There is support for POSIX classes such as [:alpha:]. - -5. There is an experimental recursion feature. - ----------------------------------------------------------------------------- - IMPORTANT FOR THOSE UPGRADING FROM VERSIONS BEFORE 2.00 - -Please note that there has been a change in the API such that a larger -ovector is required at matching time, to provide some additional workspace. -The new man page has details. This change was necessary in order to support -some of the new functionality in Perl 5.005. - - IMPORTANT FOR THOSE UPGRADING FROM VERSION 2.00 - -Another (I hope this is the last!) change has been made to the API for the -pcre_compile() function. An additional argument has been added to make it -possible to pass over a pointer to character tables built in the current -locale by pcre_maketables(). To use the default tables, this new arguement -should be passed as NULL. - - IMPORTANT FOR THOSE UPGRADING FROM VERSION 2.05 - -Yet another (and again I hope this really is the last) change has been made -to the API for the pcre_exec() function. An additional argument has been -added to make it possible to start the match other than at the start of the -subject string. This is important if there are lookbehinds. The new man -page has the details, but you just want to convert existing programs, all -you need to do is to stick in a new fifth argument to pcre_exec(), with a -value of zero. For example, change - - pcre_exec(pattern, extra, subject, length, options, ovec, ovecsize) -to - pcre_exec(pattern, extra, subject, length, 0, options, ovec, ovecsize) - -**** diff --git a/libs/pcre/NON-UNIX-USE b/libs/pcre/NON-UNIX-USE deleted file mode 100644 index 803e73e98b..0000000000 --- a/libs/pcre/NON-UNIX-USE +++ /dev/null @@ -1,448 +0,0 @@ -Compiling PCRE on non-Unix systems ----------------------------------- - -This document contains the following sections: - - General - Generic instructions for the PCRE C library - The C++ wrapper functions - Building for virtual Pascal - Stack size in Windows environments - Linking programs in Windows environments - Comments about Win32 builds - Building PCRE on Windows with CMake - Use of relative paths with CMake on Windows - Testing with runtest.bat - Building under Windows with BCC5.5 - Building PCRE on OpenVMS - - -GENERAL - -I (Philip Hazel) have no experience of Windows or VMS sytems and how their -libraries work. The items in the PCRE distribution and Makefile that relate to -anything other than Unix-like systems are untested by me. - -There are some other comments and files (including some documentation in CHM -format) in the Contrib directory on the FTP site: - - ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/Contrib - -If you want to compile PCRE for a non-Unix system (especially for a system that -does not support "configure" and "make" files), note that the basic PCRE -library consists entirely of code written in Standard C, and so should compile -successfully on any system that has a Standard C compiler and library. The C++ -wrapper functions are a separate issue (see below). - -The PCRE distribution includes a "configure" file for use by the Configure/Make -build system, as found in many Unix-like environments. There is also support -support for CMake, which some users prefer, in particular in Windows -environments. There are some instructions for CMake under Windows in the -section entitled "Building PCRE with CMake" below. CMake can also be used to -build PCRE in Unix-like systems. - - -GENERIC INSTRUCTIONS FOR THE PCRE C LIBRARY - -The following are generic comments about building the PCRE C library "by hand". - - (1) Copy or rename the file config.h.generic as config.h, and edit the macro - settings that it contains to whatever is appropriate for your environment. - In particular, if you want to force a specific value for newline, you can - define the NEWLINE macro. When you compile any of the PCRE modules, you - must specify -DHAVE_CONFIG_H to your compiler so that config.h is included - in the sources. - - An alternative approach is not to edit config.h, but to use -D on the - compiler command line to make any changes that you need to the - configuration options. In this case -DHAVE_CONFIG_H must not be set. - - NOTE: There have been occasions when the way in which certain parameters - in config.h are used has changed between releases. (In the configure/make - world, this is handled automatically.) When upgrading to a new release, - you are strongly advised to review config.h.generic before re-using what - you had previously. - - (2) Copy or rename the file pcre.h.generic as pcre.h. - - (3) EITHER: - Copy or rename file pcre_chartables.c.dist as pcre_chartables.c. - - OR: - Compile dftables.c as a stand-alone program (using -DHAVE_CONFIG_H if - you have set up config.h), and then run it with the single argument - "pcre_chartables.c". This generates a set of standard character tables - and writes them to that file. The tables are generated using the default - C locale for your system. If you want to use a locale that is specified - by LC_xxx environment variables, add the -L option to the dftables - command. You must use this method if you are building on a system that - uses EBCDIC code. - - The tables in pcre_chartables.c are defaults. The caller of PCRE can - specify alternative tables at run time. - - (4) Ensure that you have the following header files: - - pcre_internal.h - ucp.h - - (5) Also ensure that you have the following file, which is #included as source - when building a debugging version of PCRE, and is also used by pcretest. - - pcre_printint.src - - (6) Compile the following source files, setting -DHAVE_CONFIG_H as a compiler - option if you have set up config.h with your configuration, or else use - other -D settings to change the configuration as required. - - pcre_chartables.c - pcre_compile.c - pcre_config.c - pcre_dfa_exec.c - pcre_exec.c - pcre_fullinfo.c - pcre_get.c - pcre_globals.c - pcre_info.c - pcre_maketables.c - pcre_newline.c - pcre_ord2utf8.c - pcre_refcount.c - pcre_study.c - pcre_tables.c - pcre_try_flipped.c - pcre_ucd.c - pcre_valid_utf8.c - pcre_version.c - pcre_xclass.c - - Make sure that you include -I. in the compiler command (or equivalent for - an unusual compiler) so that all included PCRE header files are first - sought in the current directory. Otherwise you run the risk of picking up - a previously-installed file from somewhere else. - - (7) Now link all the compiled code into an object library in whichever form - your system keeps such libraries. This is the basic PCRE C library. If - your system has static and shared libraries, you may have to do this once - for each type. - - (8) Similarly, compile pcreposix.c (remembering -DHAVE_CONFIG_H if necessary) - and link the result (on its own) as the pcreposix library. - - (9) Compile the test program pcretest.c (again, don't forget -DHAVE_CONFIG_H). - This needs the functions in the pcre and pcreposix libraries when linking. - It also needs the pcre_printint.src source file, which it #includes. - -(10) Run pcretest on the testinput files in the testdata directory, and check - that the output matches the corresponding testoutput files. Note that the - supplied files are in Unix format, with just LF characters as line - terminators. You may need to edit them to change this if your system uses - a different convention. If you are using Windows, you probably should use - the wintestinput3 file instead of testinput3 (and the corresponding output - file). This is a locale test; wintestinput3 sets the locale to "french" - rather than "fr_FR", and there some minor output differences. - -(11) If you want to use the pcregrep command, compile and link pcregrep.c; it - uses only the basic PCRE library (it does not need the pcreposix library). - - -THE C++ WRAPPER FUNCTIONS - -The PCRE distribution also contains some C++ wrapper functions and tests, -contributed by Google Inc. On a system that can use "configure" and "make", -the functions are automatically built into a library called pcrecpp. It should -be straightforward to compile the .cc files manually on other systems. The -files called xxx_unittest.cc are test programs for each of the corresponding -xxx.cc files. - - -BUILDING FOR VIRTUAL PASCAL - -A script for building PCRE using Borland's C++ compiler for use with VPASCAL -was contributed by Alexander Tokarev. Stefan Weber updated the script and added -additional files. The following files in the distribution are for building PCRE -for use with VP/Borland: makevp_c.txt, makevp_l.txt, makevp.bat, pcregexp.pas. - - -STACK SIZE IN WINDOWS ENVIRONMENTS - -The default processor stack size of 1Mb in some Windows environments is too -small for matching patterns that need much recursion. In particular, test 2 may -fail because of this. Normally, running out of stack causes a crash, but there -have been cases where the test program has just died silently. See your linker -documentation for how to increase stack size if you experience problems. The -Linux default of 8Mb is a reasonable choice for the stack, though even that can -be too small for some pattern/subject combinations. - -PCRE has a compile configuration option to disable the use of stack for -recursion so that heap is used instead. However, pattern matching is -significantly slower when this is done. There is more about stack usage in the -"pcrestack" documentation. - - -LINKING PROGRAMS IN WINDOWS ENVIRONMENTS - -If you want to statically link a program against a PCRE library in the form of -a non-dll .a file, you must define PCRE_STATIC before including pcre.h, -otherwise the pcre_malloc() and pcre_free() exported functions will be declared -__declspec(dllimport), with unwanted results. - - -CALLING CONVENTIONS IN WINDOWS ENVIRONMENTS - -It is possible to compile programs to use different calling conventions using -MSVC. Search the web for "calling conventions" for more information. To make it -easier to change the calling convention for the exported functions in the -PCRE library, the macro PCRE_CALL_CONVENTION is present in all the external -definitions. It can be set externally when compiling (e.g. in CFLAGS). If it is -not set, it defaults to empty; the default calling convention is then used -(which is what is wanted most of the time). - - -COMMENTS ABOUT WIN32 BUILDS (see also "BUILDING PCRE WITH CMAKE" below) - -There are two ways of building PCRE using the "configure, make, make install" -paradigm on Windows systems: using MinGW or using Cygwin. These are not at all -the same thing; they are completely different from each other. There is also -support for building using CMake, which some users find a more straightforward -way of building PCRE under Windows. However, the tests are not run -automatically when CMake is used. - -The MinGW home page (http://www.mingw.org/) says this: - - MinGW: A collection of freely available and freely distributable Windows - specific header files and import libraries combined with GNU toolsets that - allow one to produce native Windows programs that do not rely on any - 3rd-party C runtime DLLs. - -The Cygwin home page (http://www.cygwin.com/) says this: - - Cygwin is a Linux-like environment for Windows. It consists of two parts: - - . A DLL (cygwin1.dll) which acts as a Linux API emulation layer providing - substantial Linux API functionality - - . A collection of tools which provide Linux look and feel. - - The Cygwin DLL currently works with all recent, commercially released x86 32 - bit and 64 bit versions of Windows, with the exception of Windows CE. - -On both MinGW and Cygwin, PCRE should build correctly using: - - ./configure && make && make install - -This should create two libraries called libpcre and libpcreposix, and, if you -have enabled building the C++ wrapper, a third one called libpcrecpp. These are -independent libraries: when you like with libpcreposix or libpcrecpp you must -also link with libpcre, which contains the basic functions. (Some earlier -releases of PCRE included the basic libpcre functions in libpcreposix. This no -longer happens.) - -A user submitted a special-purpose patch that makes it easy to create -"pcre.dll" under mingw32 using the "msys" environment. It provides "pcre.dll" -as a special target. If you use this target, no other files are built, and in -particular, the pcretest and pcregrep programs are not built. An example of how -this might be used is: - - ./configure --enable-utf --disable-cpp CFLAGS="-03 -s"; make pcre.dll - -Using Cygwin's compiler generates libraries and executables that depend on -cygwin1.dll. If a library that is generated this way is distributed, -cygwin1.dll has to be distributed as well. Since cygwin1.dll is under the GPL -licence, this forces not only PCRE to be under the GPL, but also the entire -application. A distributor who wants to keep their own code proprietary must -purchase an appropriate Cygwin licence. - -MinGW has no such restrictions. The MinGW compiler generates a library or -executable that can run standalone on Windows without any third party dll or -licensing issues. - -But there is more complication: - -If a Cygwin user uses the -mno-cygwin Cygwin gcc flag, what that really does is -to tell Cygwin's gcc to use the MinGW gcc. Cygwin's gcc is only acting as a -front end to MinGW's gcc (if you install Cygwin's gcc, you get both Cygwin's -gcc and MinGW's gcc). So, a user can: - -. Build native binaries by using MinGW or by getting Cygwin and using - -mno-cygwin. - -. Build binaries that depend on cygwin1.dll by using Cygwin with the normal - compiler flags. - -The test files that are supplied with PCRE are in Unix format, with LF -characters as line terminators. It may be necessary to change the line -terminators in order to get some of the tests to work. We hope to improve -things in this area in future. - - -BUILDING PCRE ON WINDOWS WITH CMAKE - -CMake is an alternative build facility that can be used instead of the -traditional Unix "configure". CMake version 2.4.7 supports Borland makefiles, -MinGW makefiles, MSYS makefiles, NMake makefiles, UNIX makefiles, Visual Studio -6, Visual Studio 7, Visual Studio 8, and Watcom W8. The following instructions -were contributed by a PCRE user. - -1. Download CMake 2.4.7 or above from http://www.cmake.org/, install and ensure - that cmake\bin is on your path. - -2. Unzip (retaining folder structure) the PCRE source tree into a source - directory such as C:\pcre. - -3. Create a new, empty build directory: C:\pcre\build\ - -4. Run CMakeSetup from the Shell envirornment of your build tool, e.g., Msys - for Msys/MinGW or Visual Studio Command Prompt for VC/VC++ - -5. Enter C:\pcre\pcre-xx and C:\pcre\build for the source and build - directories, respectively - -6. Hit the "Configure" button. - -7. Select the particular IDE / build tool that you are using (Visual Studio, - MSYS makefiles, MinGW makefiles, etc.) - -8. The GUI will then list several configuration options. This is where you can - enable UTF-8 support, etc. - -9. Hit "Configure" again. The adjacent "OK" button should now be active. - -10. Hit "OK". - -11. The build directory should now contain a usable build system, be it a - solution file for Visual Studio, makefiles for MinGW, etc. - - -USE OF RELATIVE PATHS WITH CMAKE ON WINDOWS - -A PCRE user comments as follows: - -I thought that others may want to know the current state of -CMAKE_USE_RELATIVE_PATHS support on Windows. - -Here it is: --- AdditionalIncludeDirectories is only partially modified (only the -first path - see below) --- Only some of the contained file paths are modified - shown below for -pcre.vcproj --- It properly modifies - -I am sure CMake people can fix that if they want to. Until then one will -need to replace existing absolute paths in project files with relative -paths manually (e.g. from VS) - relative to project file location. I did -just that before being told to try CMAKE_USE_RELATIVE_PATHS. Not a big -deal. - -AdditionalIncludeDirectories="E:\builds\pcre\build;E:\builds\pcre\pcre-7.5;" -AdditionalIncludeDirectories=".;E:\builds\pcre\pcre-7.5;" - -RelativePath="pcre.h"> -RelativePath="pcre_chartables.c"> -RelativePath="pcre_chartables.c.rule"> - - -TESTING WITH RUNTEST.BAT - -1. Copy RunTest.bat into the directory where pcretest.exe has been created. - -2. Edit RunTest.bat and insert a line that indentifies the relative location of - the pcre source, e.g.: - - set srcdir=..\pcre-7.4-RC3 - -3. Run RunTest.bat from a command shell environment. Test outputs will - automatically be compared to expected results, and discrepancies will - identified in the console output. - -4. To test pcrecpp, run pcrecpp_unittest.exe, pcre_stringpiece_unittest.exe and - pcre_scanner_unittest.exe. - - -BUILDING UNDER WINDOWS WITH BCC5.5 - -Michael Roy sent these comments about building PCRE under Windows with BCC5.5: - - Some of the core BCC libraries have a version of PCRE from 1998 built in, - which can lead to pcre_exec() giving an erroneous PCRE_ERROR_NULL from a - version mismatch. I'm including an easy workaround below, if you'd like to - include it in the non-unix instructions: - - When linking a project with BCC5.5, pcre.lib must be included before any of - the libraries cw32.lib, cw32i.lib, cw32mt.lib, and cw32mti.lib on the command - line. - - -BUILDING UNDER WINDOWS CE WITH VISUAL STUDIO 200x - -Vincent Richomme sent a zip archive of files to help with this process. They -can be found in the file "pcre-vsbuild.zip" in the Contrib directory of the FTP -site. - - -BUILDING PCRE ON OPENVMS - -Dan Mooney sent the following comments about building PCRE on OpenVMS. They -relate to an older version of PCRE that used fewer source files, so the exact -commands will need changing. See the current list of source files above. - -"It was quite easy to compile and link the library. I don't have a formal -make file but the attached file [reproduced below] contains the OpenVMS DCL -commands I used to build the library. I had to add #define -POSIX_MALLOC_THRESHOLD 10 to pcre.h since it was not defined anywhere. - -The library was built on: -O/S: HP OpenVMS v7.3-1 -Compiler: Compaq C v6.5-001-48BCD -Linker: vA13-01 - -The test results did not match 100% due to the issues you mention in your -documentation regarding isprint(), iscntrl(), isgraph() and ispunct(). I -modified some of the character tables temporarily and was able to get the -results to match. Tests using the fr locale did not match since I don't have -that locale loaded. The study size was always reported to be 3 less than the -value in the standard test output files." - -========================= -$! This DCL procedure builds PCRE on OpenVMS -$! -$! I followed the instructions in the non-unix-use file in the distribution. -$! -$ COMPILE == "CC/LIST/NOMEMBER_ALIGNMENT/PREFIX_LIBRARY_ENTRIES=ALL_ENTRIES -$ COMPILE DFTABLES.C -$ LINK/EXE=DFTABLES.EXE DFTABLES.OBJ -$ RUN DFTABLES.EXE/OUTPUT=CHARTABLES.C -$ COMPILE MAKETABLES.C -$ COMPILE GET.C -$ COMPILE STUDY.C -$! I had to set POSIX_MALLOC_THRESHOLD to 10 in PCRE.H since the symbol -$! did not seem to be defined anywhere. -$! I edited pcre.h and added #DEFINE SUPPORT_UTF8 to enable UTF8 support. -$ COMPILE PCRE.C -$ LIB/CREATE PCRE MAKETABLES.OBJ, GET.OBJ, STUDY.OBJ, PCRE.OBJ -$! I had to set POSIX_MALLOC_THRESHOLD to 10 in PCRE.H since the symbol -$! did not seem to be defined anywhere. -$ COMPILE PCREPOSIX.C -$ LIB/CREATE PCREPOSIX PCREPOSIX.OBJ -$ COMPILE PCRETEST.C -$ LINK/EXE=PCRETEST.EXE PCRETEST.OBJ, PCRE/LIB, PCREPOSIX/LIB -$! C programs that want access to command line arguments must be -$! defined as a symbol -$ PCRETEST :== "$ SYS$ROADSUSERS:[DMOONEY.REGEXP]PCRETEST.EXE" -$! Arguments must be enclosed in quotes. -$ PCRETEST "-C" -$! Test results: -$! -$! The test results did not match 100%. The functions isprint(), iscntrl(), -$! isgraph() and ispunct() on OpenVMS must not produce the same results -$! as the system that built the test output files provided with the -$! distribution. -$! -$! The study size did not match and was always 3 less on OpenVMS. -$! -$! Locale could not be set to fr -$! -========================= - -Last Updated: 17 March 2009 -**** diff --git a/libs/pcre/PrepareRelease b/libs/pcre/PrepareRelease deleted file mode 100755 index 79b139fe9a..0000000000 --- a/libs/pcre/PrepareRelease +++ /dev/null @@ -1,214 +0,0 @@ -#/bin/sh - -# Script to prepare the files for building a PCRE release. It does some -# processing of the documentation, detrails files, and creates pcre.h.generic -# and config.h.generic (for use by builders who can't run ./configure). - -# You must run this script before runnning "make dist". It makes use of the -# following files: - -# 132html A Perl script that converts a .1 or .3 man page into HTML. It -# is called from MakeRelease. It "knows" the relevant troff -# constructs that are used in the PCRE man pages. - -# CleanTxt A Perl script that cleans up the output of "nroff -man" by -# removing backspaces and other redundant text so as to produce -# a readable .txt file. - -# Detrail A Perl script that removes trailing spaces from files. - -# doc/index.html.src -# A file that is copied as index.html into the doc/html directory -# when the HTML documentation is built. It works like this so that -# doc/html can be deleted and re-created from scratch. - - -# First, sort out the documentation - -cd doc -echo Processing documentation - -# Make Text form of the documentation. It needs some mangling to make it -# tidy for online reading. Concatenate all the .3 stuff, but omit the -# individual function pages. - -cat <pcre.txt ------------------------------------------------------------------------------ -This file contains a concatenation of the PCRE man pages, converted to plain -text format for ease of searching with a text editor, or for use on systems -that do not have a man page processor. The small individual files that give -synopses of each function in the library have not been included. There are -separate text files for the pcregrep and pcretest commands. ------------------------------------------------------------------------------ - - -End - -echo "Making pcre.txt" -for file in pcre pcrebuild pcrematching pcreapi pcrecallout pcrecompat \ - pcrepattern pcresyntax pcrepartial pcreprecompile \ - pcreperform pcreposix pcrecpp pcresample pcrestack ; do - echo " Processing $file.3" - nroff -c -man $file.3 >$file.rawtxt - ../CleanTxt <$file.rawtxt >>pcre.txt - /bin/rm $file.rawtxt - echo "------------------------------------------------------------------------------" >>pcre.txt - if [ "$file" != "pcresample" ] ; then - echo " " >>pcre.txt - echo " " >>pcre.txt - fi -done - -# The three commands -for file in pcretest pcregrep pcre-config ; do - echo Making $file.txt - nroff -c -man $file.1 >$file.rawtxt - ../CleanTxt <$file.rawtxt >$file.txt - /bin/rm $file.rawtxt -done - - -# Make HTML form of the documentation. - -echo "Making HTML documentation" -/bin/rm html/* -cp index.html.src html/index.html - -for file in *.1 ; do - base=`basename $file .1` - echo " Making $base.html" - ../132html -toc $base <$file >html/$base.html -done - -# Exclude table of contents for function summaries. It seems that expr -# forces an anchored regex. Also exclude them for small pages that have -# only one section. -for file in *.3 ; do - base=`basename $file .3` - toc=-toc - if [ `expr $base : '.*_'` -ne 0 ] ; then toc="" ; fi - if [ "$base" = "pcresample" ] || \ - [ "$base" = "pcrestack" ] || \ - [ "$base" = "pcrecompat" ] || \ - [ "$base" = "pcreperform" ] ; then - toc="" - fi - echo " Making $base.html" - ../132html $toc $base <$file >html/$base.html - if [ $? != 0 ] ; then exit 1; fi -done - -# End of documentation processing - -cd .. -echo Documentation done - -# These files are detrailed; do not detrail the test data because there may be -# significant trailing spaces. The configure files are also omitted from the -# detrailing. - -files="\ - Makefile.am \ - Makefile.in \ - configure.ac \ - README \ - LICENCE \ - COPYING \ - AUTHORS \ - NEWS \ - NON-UNIX-USE \ - INSTALL \ - 132html \ - CleanTxt \ - Detrail \ - ChangeLog \ - CMakeLists.txt \ - RunGrepTest \ - RunTest \ - RunTest.bat \ - pcre-config.in \ - libpcre.pc.in \ - libpcrecpp.pc.in \ - config.h.in \ - pcre_printint.src \ - pcre_chartables.c.dist \ - pcredemo.c \ - pcregrep.c \ - pcretest.c \ - dftables.c \ - pcreposix.c \ - pcreposix.h \ - pcre.h.in \ - pcre_internal.h - pcre_compile.c \ - pcre_config.c \ - pcre_dfa_exec.c \ - pcre_exec.c \ - pcre_fullinfo.c \ - pcre_get.c \ - pcre_globals.c \ - pcre_info.c \ - pcre_maketables.c \ - pcre_newline.c \ - pcre_ord2utf8.c \ - pcre_refcount.c \ - pcre_study.c \ - pcre_tables.c \ - pcre_try_flipped.c \ - pcre_ucp_searchfuncs.c \ - pcre_valid_utf8.c \ - pcre_version.c \ - pcre_xclass.c \ - pcre_scanner.cc \ - pcre_scanner.h \ - pcre_scanner_unittest.cc \ - pcrecpp.cc \ - pcrecpp.h \ - pcrecpparg.h.in \ - pcrecpp_unittest.cc \ - pcre_stringpiece.cc \ - pcre_stringpiece.h.in \ - pcre_stringpiece_unittest.cc \ - perltest.pl \ - ucp.h \ - ucpinternal.h \ - ucptable.h \ - makevp.bat \ - pcre.def \ - libpcre.def \ - libpcreposix.def" - -echo Detrailing -./Detrail $files doc/p* doc/html/* - -echo Doing basic configure to get default pcre.h and config.h -# This is in case the caller has set aliases (as I do - PH) -unset cp ls mv rm -./configure >/dev/null - -echo Converting pcre.h and config.h to generic forms -cp -f pcre.h pcre.h.generic - -perl <<'END' - open(IN, "config.h.generic") || die "Can't open config.h.generic: $!\n"; - while () - { - if (/^#define\s(?!PACKAGE)(\w+)/) - { - print OUT "#ifndef $1\n"; - print OUT; - print OUT "#endif\n"; - } - else - { - print OUT; - } - } - close IN; - close OUT; -END - -echo Done - -#End diff --git a/libs/pcre/README b/libs/pcre/README deleted file mode 100644 index 6b7c83fed3..0000000000 --- a/libs/pcre/README +++ /dev/null @@ -1,767 +0,0 @@ -README file for PCRE (Perl-compatible regular expression library) ------------------------------------------------------------------ - -The latest release of PCRE is always available in three alternative formats -from: - - ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.tar.gz - ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.tar.bz2 - ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.zip - -There is a mailing list for discussion about the development of PCRE at - - pcre-dev@exim.org - -Please read the NEWS file if you are upgrading from a previous release. -The contents of this README file are: - - The PCRE APIs - Documentation for PCRE - Contributions by users of PCRE - Building PCRE on non-Unix systems - Building PCRE on Unix-like systems - Retrieving configuration information on Unix-like systems - Shared libraries on Unix-like systems - Cross-compiling on Unix-like systems - Using HP's ANSI C++ compiler (aCC) - Making new tarballs - Testing PCRE - Character tables - File manifest - - -The PCRE APIs -------------- - -PCRE is written in C, and it has its own API. The distribution also includes a -set of C++ wrapper functions (see the pcrecpp man page for details), courtesy -of Google Inc. - -In addition, there is a set of C wrapper functions that are based on the POSIX -regular expression API (see the pcreposix man page). These end up in the -library called libpcreposix. Note that this just provides a POSIX calling -interface to PCRE; the regular expressions themselves still follow Perl syntax -and semantics. The POSIX API is restricted, and does not give full access to -all of PCRE's facilities. - -The header file for the POSIX-style functions is called pcreposix.h. The -official POSIX name is regex.h, but I did not want to risk possible problems -with existing files of that name by distributing it that way. To use PCRE with -an existing program that uses the POSIX API, pcreposix.h will have to be -renamed or pointed at by a link. - -If you are using the POSIX interface to PCRE and there is already a POSIX regex -library installed on your system, as well as worrying about the regex.h header -file (as mentioned above), you must also take care when linking programs to -ensure that they link with PCRE's libpcreposix library. Otherwise they may pick -up the POSIX functions of the same name from the other library. - -One way of avoiding this confusion is to compile PCRE with the addition of --Dregcomp=PCREregcomp (and similarly for the other POSIX functions) to the -compiler flags (CFLAGS if you are using "configure" -- see below). This has the -effect of renaming the functions so that the names no longer clash. Of course, -you have to do the same thing for your applications, or write them using the -new names. - - -Documentation for PCRE ----------------------- - -If you install PCRE in the normal way on a Unix-like system, you will end up -with a set of man pages whose names all start with "pcre". The one that is just -called "pcre" lists all the others. In addition to these man pages, the PCRE -documentation is supplied in two other forms: - - 1. There are files called doc/pcre.txt, doc/pcregrep.txt, and - doc/pcretest.txt in the source distribution. The first of these is a - concatenation of the text forms of all the section 3 man pages except - those that summarize individual functions. The other two are the text - forms of the section 1 man pages for the pcregrep and pcretest commands. - These text forms are provided for ease of scanning with text editors or - similar tools. They are installed in /share/doc/pcre, where - is the installation prefix (defaulting to /usr/local). - - 2. A set of files containing all the documentation in HTML form, hyperlinked - in various ways, and rooted in a file called index.html, is distributed in - doc/html and installed in /share/doc/pcre/html. - -Users of PCRE have contributed files containing the documentation for various -releases in CHM format. These can be found in the Contrib directory of the FTP -site (see next section). - - -Contributions by users of PCRE ------------------------------- - -You can find contributions from PCRE users in the directory - - ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/Contrib - -There is a README file giving brief descriptions of what they are. Some are -complete in themselves; others are pointers to URLs containing relevant files. -Some of this material is likely to be well out-of-date. Several of the earlier -contributions provided support for compiling PCRE on various flavours of -Windows (I myself do not use Windows). Nowadays there is more Windows support -in the standard distribution, so these contibutions have been archived. - - -Building PCRE on non-Unix systems ---------------------------------- - -For a non-Unix system, please read the comments in the file NON-UNIX-USE, -though if your system supports the use of "configure" and "make" you may be -able to build PCRE in the same way as for Unix-like systems. PCRE can also be -configured in many platform environments using the GUI facility of CMake's -CMakeSetup. It creates Makefiles, solution files, etc. - -PCRE has been compiled on many different operating systems. It should be -straightforward to build PCRE on any system that has a Standard C compiler and -library, because it uses only Standard C functions. - - -Building PCRE on Unix-like systems ----------------------------------- - -If you are using HP's ANSI C++ compiler (aCC), please see the special note -in the section entitled "Using HP's ANSI C++ compiler (aCC)" below. - -The following instructions assume the use of the widely used "configure, make, -make install" process. There is also support for CMake in the PCRE -distribution; there are some comments about using CMake in the NON-UNIX-USE -file, though it can also be used in Unix-like systems. - -To build PCRE on a Unix-like system, first run the "configure" command from the -PCRE distribution directory, with your current directory set to the directory -where you want the files to be created. This command is a standard GNU -"autoconf" configuration script, for which generic instructions are supplied in -the file INSTALL. - -Most commonly, people build PCRE within its own distribution directory, and in -this case, on many systems, just running "./configure" is sufficient. However, -the usual methods of changing standard defaults are available. For example: - -CFLAGS='-O2 -Wall' ./configure --prefix=/opt/local - -specifies that the C compiler should be run with the flags '-O2 -Wall' instead -of the default, and that "make install" should install PCRE under /opt/local -instead of the default /usr/local. - -If you want to build in a different directory, just run "configure" with that -directory as current. For example, suppose you have unpacked the PCRE source -into /source/pcre/pcre-xxx, but you want to build it in /build/pcre/pcre-xxx: - -cd /build/pcre/pcre-xxx -/source/pcre/pcre-xxx/configure - -PCRE is written in C and is normally compiled as a C library. However, it is -possible to build it as a C++ library, though the provided building apparatus -does not have any features to support this. - -There are some optional features that can be included or omitted from the PCRE -library. You can read more about them in the pcrebuild man page. - -. If you want to suppress the building of the C++ wrapper library, you can add - --disable-cpp to the "configure" command. Otherwise, when "configure" is run, - it will try to find a C++ compiler and C++ header files, and if it succeeds, - it will try to build the C++ wrapper. - -. If you want to make use of the support for UTF-8 Unicode character strings in - PCRE, you must add --enable-utf8 to the "configure" command. Without it, the - code for handling UTF-8 is not included in the library. Even when included, - it still has to be enabled by an option at run time. When PCRE is compiled - with this option, its input can only either be ASCII or UTF-8, even when - running on EBCDIC platforms. It is not possible to use both --enable-utf8 and - --enable-ebcdic at the same time. - -. If, in addition to support for UTF-8 character strings, you want to include - support for the \P, \p, and \X sequences that recognize Unicode character - properties, you must add --enable-unicode-properties to the "configure" - command. This adds about 30K to the size of the library (in the form of a - property table); only the basic two-letter properties such as Lu are - supported. - -. You can build PCRE to recognize either CR or LF or the sequence CRLF or any - of the preceding, or any of the Unicode newline sequences as indicating the - end of a line. Whatever you specify at build time is the default; the caller - of PCRE can change the selection at run time. The default newline indicator - is a single LF character (the Unix standard). You can specify the default - newline indicator by adding --enable-newline-is-cr or --enable-newline-is-lf - or --enable-newline-is-crlf or --enable-newline-is-anycrlf or - --enable-newline-is-any to the "configure" command, respectively. - - If you specify --enable-newline-is-cr or --enable-newline-is-crlf, some of - the standard tests will fail, because the lines in the test files end with - LF. Even if the files are edited to change the line endings, there are likely - to be some failures. With --enable-newline-is-anycrlf or - --enable-newline-is-any, many tests should succeed, but there may be some - failures. - -. By default, the sequence \R in a pattern matches any Unicode line ending - sequence. This is independent of the option specifying what PCRE considers to - be the end of a line (see above). However, the caller of PCRE can restrict \R - to match only CR, LF, or CRLF. You can make this the default by adding - --enable-bsr-anycrlf to the "configure" command (bsr = "backslash R"). - -. When called via the POSIX interface, PCRE uses malloc() to get additional - storage for processing capturing parentheses if there are more than 10 of - them in a pattern. You can increase this threshold by setting, for example, - - --with-posix-malloc-threshold=20 - - on the "configure" command. - -. PCRE has a counter that can be set to limit the amount of resources it uses. - If the limit is exceeded during a match, the match fails. The default is ten - million. You can change the default by setting, for example, - - --with-match-limit=500000 - - on the "configure" command. This is just the default; individual calls to - pcre_exec() can supply their own value. There is more discussion on the - pcreapi man page. - -. There is a separate counter that limits the depth of recursive function calls - during a matching process. This also has a default of ten million, which is - essentially "unlimited". You can change the default by setting, for example, - - --with-match-limit-recursion=500000 - - Recursive function calls use up the runtime stack; running out of stack can - cause programs to crash in strange ways. There is a discussion about stack - sizes in the pcrestack man page. - -. The default maximum compiled pattern size is around 64K. You can increase - this by adding --with-link-size=3 to the "configure" command. You can - increase it even more by setting --with-link-size=4, but this is unlikely - ever to be necessary. Increasing the internal link size will reduce - performance. - -. You can build PCRE so that its internal match() function that is called from - pcre_exec() does not call itself recursively. Instead, it uses memory blocks - obtained from the heap via the special functions pcre_stack_malloc() and - pcre_stack_free() to save data that would otherwise be saved on the stack. To - build PCRE like this, use - - --disable-stack-for-recursion - - on the "configure" command. PCRE runs more slowly in this mode, but it may be - necessary in environments with limited stack sizes. This applies only to the - pcre_exec() function; it does not apply to pcre_dfa_exec(), which does not - use deeply nested recursion. There is a discussion about stack sizes in the - pcrestack man page. - -. For speed, PCRE uses four tables for manipulating and identifying characters - whose code point values are less than 256. By default, it uses a set of - tables for ASCII encoding that is part of the distribution. If you specify - - --enable-rebuild-chartables - - a program called dftables is compiled and run in the default C locale when - you obey "make". It builds a source file called pcre_chartables.c. If you do - not specify this option, pcre_chartables.c is created as a copy of - pcre_chartables.c.dist. See "Character tables" below for further information. - -. It is possible to compile PCRE for use on systems that use EBCDIC as their - character code (as opposed to ASCII) by specifying - - --enable-ebcdic - - This automatically implies --enable-rebuild-chartables (see above). However, - when PCRE is built this way, it always operates in EBCDIC. It cannot support - both EBCDIC and UTF-8. - -. It is possible to compile pcregrep to use libz and/or libbz2, in order to - read .gz and .bz2 files (respectively), by specifying one or both of - - --enable-pcregrep-libz - --enable-pcregrep-libbz2 - - Of course, the relevant libraries must be installed on your system. - -. It is possible to compile pcretest so that it links with the libreadline - library, by specifying - - --enable-pcretest-libreadline - - If this is done, when pcretest's input is from a terminal, it reads it using - the readline() function. This provides line-editing and history facilities. - Note that libreadline is GPL-licenced, so if you distribute a binary of - pcretest linked in this way, there may be licensing issues. - - Setting this option causes the -lreadline option to be added to the pcretest - build. In many operating environments with a sytem-installed readline - library this is sufficient. However, in some environments (e.g. if an - unmodified distribution version of readline is in use), it may be necessary - to specify something like LIBS="-lncurses" as well. This is because, to quote - the readline INSTALL, "Readline uses the termcap functions, but does not link - with the termcap or curses library itself, allowing applications which link - with readline the to choose an appropriate library." If you get error - messages about missing functions tgetstr, tgetent, tputs, tgetflag, or tgoto, - this is the problem, and linking with the ncurses library should fix it. - -The "configure" script builds the following files for the basic C library: - -. Makefile is the makefile that builds the library -. config.h contains build-time configuration options for the library -. pcre.h is the public PCRE header file -. pcre-config is a script that shows the settings of "configure" options -. libpcre.pc is data for the pkg-config command -. libtool is a script that builds shared and/or static libraries -. RunTest is a script for running tests on the basic C library -. RunGrepTest is a script for running tests on the pcregrep command - -Versions of config.h and pcre.h are distributed in the PCRE tarballs under -the names config.h.generic and pcre.h.generic. These are provided for the -benefit of those who have to built PCRE without the benefit of "configure". If -you use "configure", the .generic versions are not used. - -If a C++ compiler is found, the following files are also built: - -. libpcrecpp.pc is data for the pkg-config command -. pcrecpparg.h is a header file for programs that call PCRE via the C++ wrapper -. pcre_stringpiece.h is the header for the C++ "stringpiece" functions - -The "configure" script also creates config.status, which is an executable -script that can be run to recreate the configuration, and config.log, which -contains compiler output from tests that "configure" runs. - -Once "configure" has run, you can run "make". It builds two libraries, called -libpcre and libpcreposix, a test program called pcretest, and the pcregrep -command. If a C++ compiler was found on your system, "make" also builds the C++ -wrapper library, which is called libpcrecpp, and some test programs called -pcrecpp_unittest, pcre_scanner_unittest, and pcre_stringpiece_unittest. -Building the C++ wrapper can be disabled by adding --disable-cpp to the -"configure" command. - -The command "make check" runs all the appropriate tests. Details of the PCRE -tests are given below in a separate section of this document. - -You can use "make install" to install PCRE into live directories on your -system. The following are installed (file names are all relative to the - that is set when "configure" is run): - - Commands (bin): - pcretest - pcregrep - pcre-config - - Libraries (lib): - libpcre - libpcreposix - libpcrecpp (if C++ support is enabled) - - Configuration information (lib/pkgconfig): - libpcre.pc - libpcrecpp.pc (if C++ support is enabled) - - Header files (include): - pcre.h - pcreposix.h - pcre_scanner.h ) - pcre_stringpiece.h ) if C++ support is enabled - pcrecpp.h ) - pcrecpparg.h ) - - Man pages (share/man/man{1,3}): - pcregrep.1 - pcretest.1 - pcre.3 - pcre*.3 (lots more pages, all starting "pcre") - - HTML documentation (share/doc/pcre/html): - index.html - *.html (lots more pages, hyperlinked from index.html) - - Text file documentation (share/doc/pcre): - AUTHORS - COPYING - ChangeLog - LICENCE - NEWS - README - pcre.txt (a concatenation of the man(3) pages) - pcretest.txt the pcretest man page - pcregrep.txt the pcregrep man page - -If you want to remove PCRE from your system, you can run "make uninstall". -This removes all the files that "make install" installed. However, it does not -remove any directories, because these are often shared with other programs. - - -Retrieving configuration information on Unix-like systems ---------------------------------------------------------- - -Running "make install" installs the command pcre-config, which can be used to -recall information about the PCRE configuration and installation. For example: - - pcre-config --version - -prints the version number, and - - pcre-config --libs - -outputs information about where the library is installed. This command can be -included in makefiles for programs that use PCRE, saving the programmer from -having to remember too many details. - -The pkg-config command is another system for saving and retrieving information -about installed libraries. Instead of separate commands for each library, a -single command is used. For example: - - pkg-config --cflags pcre - -The data is held in *.pc files that are installed in a directory called -/lib/pkgconfig. - - -Shared libraries on Unix-like systems -------------------------------------- - -The default distribution builds PCRE as shared libraries and static libraries, -as long as the operating system supports shared libraries. Shared library -support relies on the "libtool" script which is built as part of the -"configure" process. - -The libtool script is used to compile and link both shared and static -libraries. They are placed in a subdirectory called .libs when they are newly -built. The programs pcretest and pcregrep are built to use these uninstalled -libraries (by means of wrapper scripts in the case of shared libraries). When -you use "make install" to install shared libraries, pcregrep and pcretest are -automatically re-built to use the newly installed shared libraries before being -installed themselves. However, the versions left in the build directory still -use the uninstalled libraries. - -To build PCRE using static libraries only you must use --disable-shared when -configuring it. For example: - -./configure --prefix=/usr/gnu --disable-shared - -Then run "make" in the usual way. Similarly, you can use --disable-static to -build only shared libraries. - - -Cross-compiling on Unix-like systems ------------------------------------- - -You can specify CC and CFLAGS in the normal way to the "configure" command, in -order to cross-compile PCRE for some other host. However, you should NOT -specify --enable-rebuild-chartables, because if you do, the dftables.c source -file is compiled and run on the local host, in order to generate the inbuilt -character tables (the pcre_chartables.c file). This will probably not work, -because dftables.c needs to be compiled with the local compiler, not the cross -compiler. - -When --enable-rebuild-chartables is not specified, pcre_chartables.c is created -by making a copy of pcre_chartables.c.dist, which is a default set of tables -that assumes ASCII code. Cross-compiling with the default tables should not be -a problem. - -If you need to modify the character tables when cross-compiling, you should -move pcre_chartables.c.dist out of the way, then compile dftables.c by hand and -run it on the local host to make a new version of pcre_chartables.c.dist. -Then when you cross-compile PCRE this new version of the tables will be used. - - -Using HP's ANSI C++ compiler (aCC) ----------------------------------- - -Unless C++ support is disabled by specifying the "--disable-cpp" option of the -"configure" script, you must include the "-AA" option in the CXXFLAGS -environment variable in order for the C++ components to compile correctly. - -Also, note that the aCC compiler on PA-RISC platforms may have a defect whereby -needed libraries fail to get included when specifying the "-AA" compiler -option. If you experience unresolved symbols when linking the C++ programs, -use the workaround of specifying the following environment variable prior to -running the "configure" script: - - CXXLDFLAGS="-lstd_v2 -lCsup_v2" - - -Making new tarballs -------------------- - -The command "make dist" creates three PCRE tarballs, in tar.gz, tar.bz2, and -zip formats. The command "make distcheck" does the same, but then does a trial -build of the new distribution to ensure that it works. - -If you have modified any of the man page sources in the doc directory, you -should first run the PrepareRelease script before making a distribution. This -script creates the .txt and HTML forms of the documentation from the man pages. - - -Testing PCRE ------------- - -To test the basic PCRE library on a Unix system, run the RunTest script that is -created by the configuring process. There is also a script called RunGrepTest -that tests the options of the pcregrep command. If the C++ wrapper library is -built, three test programs called pcrecpp_unittest, pcre_scanner_unittest, and -pcre_stringpiece_unittest are also built. - -Both the scripts and all the program tests are run if you obey "make check" or -"make test". For other systems, see the instructions in NON-UNIX-USE. - -The RunTest script runs the pcretest test program (which is documented in its -own man page) on each of the testinput files in the testdata directory in -turn, and compares the output with the contents of the corresponding testoutput -files. A file called testtry is used to hold the main output from pcretest -(testsavedregex is also used as a working file). To run pcretest on just one of -the test files, give its number as an argument to RunTest, for example: - - RunTest 2 - -The first test file can also be fed directly into the perltest.pl script to -check that Perl gives the same results. The only difference you should see is -in the first few lines, where the Perl version is given instead of the PCRE -version. - -The second set of tests check pcre_fullinfo(), pcre_info(), pcre_study(), -pcre_copy_substring(), pcre_get_substring(), pcre_get_substring_list(), error -detection, and run-time flags that are specific to PCRE, as well as the POSIX -wrapper API. It also uses the debugging flags to check some of the internals of -pcre_compile(). - -If you build PCRE with a locale setting that is not the standard C locale, the -character tables may be different (see next paragraph). In some cases, this may -cause failures in the second set of tests. For example, in a locale where the -isprint() function yields TRUE for characters in the range 128-255, the use of -[:isascii:] inside a character class defines a different set of characters, and -this shows up in this test as a difference in the compiled code, which is being -listed for checking. Where the comparison test output contains [\x00-\x7f] the -test will contain [\x00-\xff], and similarly in some other cases. This is not a -bug in PCRE. - -The third set of tests checks pcre_maketables(), the facility for building a -set of character tables for a specific locale and using them instead of the -default tables. The tests make use of the "fr_FR" (French) locale. Before -running the test, the script checks for the presence of this locale by running -the "locale" command. If that command fails, or if it doesn't include "fr_FR" -in the list of available locales, the third test cannot be run, and a comment -is output to say why. If running this test produces instances of the error - - ** Failed to set locale "fr_FR" - -in the comparison output, it means that locale is not available on your system, -despite being listed by "locale". This does not mean that PCRE is broken. - -[If you are trying to run this test on Windows, you may be able to get it to -work by changing "fr_FR" to "french" everywhere it occurs. Alternatively, use -RunTest.bat. The version of RunTest.bat included with PCRE 7.4 and above uses -Windows versions of test 2. More info on using RunTest.bat is included in the -document entitled NON-UNIX-USE.] - -The fourth test checks the UTF-8 support. It is not run automatically unless -PCRE is built with UTF-8 support. To do this you must set --enable-utf8 when -running "configure". This file can be also fed directly to the perltest script, -provided you are running Perl 5.8 or higher. (For Perl 5.6, a small patch, -commented in the script, can be be used.) - -The fifth test checks error handling with UTF-8 encoding, and internal UTF-8 -features of PCRE that are not relevant to Perl. - -The sixth test checks the support for Unicode character properties. It it not -run automatically unless PCRE is built with Unicode property support. To to -this you must set --enable-unicode-properties when running "configure". - -The seventh, eighth, and ninth tests check the pcre_dfa_exec() alternative -matching function, in non-UTF-8 mode, UTF-8 mode, and UTF-8 mode with Unicode -property support, respectively. The eighth and ninth tests are not run -automatically unless PCRE is build with the relevant support. - - -Character tables ----------------- - -For speed, PCRE uses four tables for manipulating and identifying characters -whose code point values are less than 256. The final argument of the -pcre_compile() function is a pointer to a block of memory containing the -concatenated tables. A call to pcre_maketables() can be used to generate a set -of tables in the current locale. If the final argument for pcre_compile() is -passed as NULL, a set of default tables that is built into the binary is used. - -The source file called pcre_chartables.c contains the default set of tables. By -default, this is created as a copy of pcre_chartables.c.dist, which contains -tables for ASCII coding. However, if --enable-rebuild-chartables is specified -for ./configure, a different version of pcre_chartables.c is built by the -program dftables (compiled from dftables.c), which uses the ANSI C character -handling functions such as isalnum(), isalpha(), isupper(), islower(), etc. to -build the table sources. This means that the default C locale which is set for -your system will control the contents of these default tables. You can change -the default tables by editing pcre_chartables.c and then re-building PCRE. If -you do this, you should take care to ensure that the file does not get -automatically re-generated. The best way to do this is to move -pcre_chartables.c.dist out of the way and replace it with your customized -tables. - -When the dftables program is run as a result of --enable-rebuild-chartables, -it uses the default C locale that is set on your system. It does not pay -attention to the LC_xxx environment variables. In other words, it uses the -system's default locale rather than whatever the compiling user happens to have -set. If you really do want to build a source set of character tables in a -locale that is specified by the LC_xxx variables, you can run the dftables -program by hand with the -L option. For example: - - ./dftables -L pcre_chartables.c.special - -The first two 256-byte tables provide lower casing and case flipping functions, -respectively. The next table consists of three 32-byte bit maps which identify -digits, "word" characters, and white space, respectively. These are used when -building 32-byte bit maps that represent character classes for code points less -than 256. - -The final 256-byte table has bits indicating various character types, as -follows: - - 1 white space character - 2 letter - 4 decimal digit - 8 hexadecimal digit - 16 alphanumeric or '_' - 128 regular expression metacharacter or binary zero - -You should not alter the set of characters that contain the 128 bit, as that -will cause PCRE to malfunction. - - -File manifest -------------- - -The distribution should contain the following files: - -(A) Source files of the PCRE library functions and their headers: - - dftables.c auxiliary program for building pcre_chartables.c - when --enable-rebuild-chartables is specified - - pcre_chartables.c.dist a default set of character tables that assume ASCII - coding; used, unless --enable-rebuild-chartables is - specified, by copying to pcre_chartables.c - - pcreposix.c ) - pcre_compile.c ) - pcre_config.c ) - pcre_dfa_exec.c ) - pcre_exec.c ) - pcre_fullinfo.c ) - pcre_get.c ) sources for the functions in the library, - pcre_globals.c ) and some internal functions that they use - pcre_info.c ) - pcre_maketables.c ) - pcre_newline.c ) - pcre_ord2utf8.c ) - pcre_refcount.c ) - pcre_study.c ) - pcre_tables.c ) - pcre_try_flipped.c ) - pcre_ucd.c ) - pcre_valid_utf8.c ) - pcre_version.c ) - pcre_xclass.c ) - pcre_printint.src ) debugging function that is #included in pcretest, - ) and can also be #included in pcre_compile() - pcre.h.in template for pcre.h when built by "configure" - pcreposix.h header for the external POSIX wrapper API - pcre_internal.h header for internal use - ucp.h header for Unicode property handling - - config.h.in template for config.h, which is built by "configure" - - pcrecpp.h public header file for the C++ wrapper - pcrecpparg.h.in template for another C++ header file - pcre_scanner.h public header file for C++ scanner functions - pcrecpp.cc ) - pcre_scanner.cc ) source for the C++ wrapper library - - pcre_stringpiece.h.in template for pcre_stringpiece.h, the header for the - C++ stringpiece functions - pcre_stringpiece.cc source for the C++ stringpiece functions - -(B) Source files for programs that use PCRE: - - pcredemo.c simple demonstration of coding calls to PCRE - pcregrep.c source of a grep utility that uses PCRE - pcretest.c comprehensive test program - -(C) Auxiliary files: - - 132html script to turn "man" pages into HTML - AUTHORS information about the author of PCRE - ChangeLog log of changes to the code - CleanTxt script to clean nroff output for txt man pages - Detrail script to remove trailing spaces - HACKING some notes about the internals of PCRE - INSTALL generic installation instructions - LICENCE conditions for the use of PCRE - COPYING the same, using GNU's standard name - Makefile.in ) template for Unix Makefile, which is built by - ) "configure" - Makefile.am ) the automake input that was used to create - ) Makefile.in - NEWS important changes in this release - NON-UNIX-USE notes on building PCRE on non-Unix systems - PrepareRelease script to make preparations for "make dist" - README this file - RunTest a Unix shell script for running tests - RunGrepTest a Unix shell script for pcregrep tests - aclocal.m4 m4 macros (generated by "aclocal") - config.guess ) files used by libtool, - config.sub ) used only when building a shared library - configure a configuring shell script (built by autoconf) - configure.ac ) the autoconf input that was used to build - ) "configure" and config.h - depcomp ) script to find program dependencies, generated by - ) automake - doc/*.3 man page sources for the PCRE functions - doc/*.1 man page sources for pcregrep and pcretest - doc/index.html.src the base HTML page - doc/html/* HTML documentation - doc/pcre.txt plain text version of the man pages - doc/pcretest.txt plain text documentation of test program - doc/perltest.txt plain text documentation of Perl test program - install-sh a shell script for installing files - libpcre.pc.in template for libpcre.pc for pkg-config - libpcrecpp.pc.in template for libpcrecpp.pc for pkg-config - ltmain.sh file used to build a libtool script - missing ) common stub for a few missing GNU programs while - ) installing, generated by automake - mkinstalldirs script for making install directories - perltest.pl Perl test program - pcre-config.in source of script which retains PCRE information - pcrecpp_unittest.cc ) - pcre_scanner_unittest.cc ) test programs for the C++ wrapper - pcre_stringpiece_unittest.cc ) - testdata/testinput* test data for main library tests - testdata/testoutput* expected test results - testdata/grep* input and output for pcregrep tests - -(D) Auxiliary files for cmake support - - cmake/COPYING-CMAKE-SCRIPTS - cmake/FindPackageHandleStandardArgs.cmake - cmake/FindReadline.cmake - CMakeLists.txt - config-cmake.h.in - -(E) Auxiliary files for VPASCAL - - makevp.bat - makevp_c.txt - makevp_l.txt - pcregexp.pas - -(F) Auxiliary files for building PCRE "by hand" - - pcre.h.generic ) a version of the public PCRE header file - ) for use in non-"configure" environments - config.h.generic ) a version of config.h for use in non-"configure" - ) environments - -(F) Miscellaneous - - RunTest.bat a script for running tests under Windows - -Philip Hazel -Email local part: ph10 -Email domain: cam.ac.uk -Last updated: 21 March 2009 diff --git a/libs/pcre/RunGrepTest b/libs/pcre/RunGrepTest deleted file mode 100755 index ed28ee3085..0000000000 --- a/libs/pcre/RunGrepTest +++ /dev/null @@ -1,280 +0,0 @@ -#! /bin/sh - -# Run pcregrep tests. The assumption is that the PCRE tests check the library -# itself. What we are checking here is the file handling and options that are -# supported by pcregrep. - -# Set the C locale, so that sort(1) behaves predictably. -LC_ALL=C -export LC_ALL - -pcregrep=`pwd`/pcregrep - -echo " " -echo "Testing pcregrep" -$pcregrep -V - -cf="diff -ub" -valgrind= - -while [ $# -gt 0 ] ; do - case $1 in - valgrind) valgrind="valgrind -q --leak-check=no";; - *) echo "Unknown argument $1"; exit 1;; - esac - shift -done - -# If PCRE has been built in a directory other than the source directory, and -# this test is being run from "make check" as usual, then $(srcdir) will be -# set. If not, set it to the current directory. We then arrange to run the -# pcregrep command in the source directory so that the file names that appear -# in the output are always the same. - -if [ -z "$srcdir" -o ! -d "$srcdir/testdata" ] ; then - srcdir=. -fi - -# Check for the availability of UTF-8 support - -./pcretest -C | ./pcregrep "No UTF-8 support" >/dev/null -utf8=$? - -echo "---------------------------- Test 1 ------------------------------" >testtry -(cd $srcdir; $valgrind $pcregrep PATTERN ./testdata/grepinput) >>testtry - -echo "---------------------------- Test 2 ------------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep '^PATTERN' ./testdata/grepinput) >>testtry - -echo "---------------------------- Test 3 ------------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -in PATTERN ./testdata/grepinput) >>testtry - -echo "---------------------------- Test 4 ------------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -ic PATTERN ./testdata/grepinput) >>testtry - -echo "---------------------------- Test 5 ------------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -in PATTERN ./testdata/grepinput ./testdata/grepinputx) >>testtry - -echo "---------------------------- Test 6 ------------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -inh PATTERN ./testdata/grepinput ./testdata/grepinputx) >>testtry - -echo "---------------------------- Test 7 ------------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -il PATTERN ./testdata/grepinput ./testdata/grepinputx) >>testtry - -echo "---------------------------- Test 8 ------------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -l PATTERN ./testdata/grepinput ./testdata/grepinputx) >>testtry - -echo "---------------------------- Test 9 ------------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -q PATTERN ./testdata/grepinput ./testdata/grepinputx) >>testtry -echo "RC=$?" >>testtry - -echo "---------------------------- Test 10 -----------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -q NEVER-PATTERN ./testdata/grepinput ./testdata/grepinputx) >>testtry -echo "RC=$?" >>testtry - -echo "---------------------------- Test 11 -----------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -vn pattern ./testdata/grepinputx) >>testtry - -echo "---------------------------- Test 12 -----------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -ix pattern ./testdata/grepinputx) >>testtry - -echo "---------------------------- Test 13 -----------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -f./testdata/greplist ./testdata/grepinputx) >>testtry - -echo "---------------------------- Test 14 -----------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -w pat ./testdata/grepinput ./testdata/grepinputx) >>testtry - -echo "---------------------------- Test 15 -----------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep 'abc^*' ./testdata/grepinput) 2>>testtry >>testtry - -echo "---------------------------- Test 16 -----------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep abc ./testdata/grepinput ./testdata/nonexistfile) 2>>testtry >>testtry - -echo "---------------------------- Test 17 -----------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -M 'the\noutput' ./testdata/grepinput) >>testtry - -echo "---------------------------- Test 18 -----------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -Mn '(the\noutput|dog\.\n--)' ./testdata/grepinput) >>testtry - -echo "---------------------------- Test 19 -----------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -Mix 'Pattern' ./testdata/grepinputx) >>testtry - -echo "---------------------------- Test 20 -----------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -Mixn 'complete pair\nof lines' ./testdata/grepinputx) >>testtry - -echo "---------------------------- Test 21 -----------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -nA3 'four' ./testdata/grepinputx) >>testtry - -echo "---------------------------- Test 22 -----------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -nB3 'four' ./testdata/grepinputx) >>testtry - -echo "---------------------------- Test 23 -----------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -C3 'four' ./testdata/grepinputx) >>testtry - -echo "---------------------------- Test 24 -----------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -A9 'four' ./testdata/grepinputx) >>testtry - -echo "---------------------------- Test 25 -----------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -nB9 'four' ./testdata/grepinputx) >>testtry - -echo "---------------------------- Test 26 -----------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -A9 -B9 'four' ./testdata/grepinputx) >>testtry - -echo "---------------------------- Test 27 -----------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -A10 'four' ./testdata/grepinputx) >>testtry - -echo "---------------------------- Test 28 -----------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -nB10 'four' ./testdata/grepinputx) >>testtry - -echo "---------------------------- Test 29 -----------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -C12 -B10 'four' ./testdata/grepinputx) >>testtry - -echo "---------------------------- Test 30 -----------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -inB3 'pattern' ./testdata/grepinput ./testdata/grepinputx) >>testtry - -echo "---------------------------- Test 31 -----------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -inA3 'pattern' ./testdata/grepinput ./testdata/grepinputx) >>testtry - -echo "---------------------------- Test 32 -----------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -L 'fox' ./testdata/grepinput ./testdata/grepinputx) >>testtry - -echo "---------------------------- Test 33 -----------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep 'fox' ./testdata/grepnonexist) >>testtry 2>&1 -echo "RC=$?" >>testtry - -echo "---------------------------- Test 34 -----------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -s 'fox' ./testdata/grepnonexist) >>testtry 2>&1 -echo "RC=$?" >>testtry - -echo "---------------------------- Test 35 -----------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -L -r --include=grepinputx --exclude_dir='^\.' 'fox' ./testdata) >>testtry -echo "RC=$?" >>testtry - -echo "---------------------------- Test 36 -----------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -L -r --include=grepinput --exclude 'grepinput$' --exclude_dir='^\.' 'fox' ./testdata | sort) >>testtry -echo "RC=$?" >>testtry - -echo "---------------------------- Test 37 -----------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep '^(a+)*\d' ./testdata/grepinput) >>testtry 2>teststderr -echo "RC=$?" >>testtry -echo "======== STDERR ========" >>testtry -cat teststderr >>testtry - -echo "---------------------------- Test 38 ------------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep '>\x00<' ./testdata/grepinput) >>testtry - -echo "---------------------------- Test 39 ------------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -A1 'before the binary zero' ./testdata/grepinput) >>testtry - -echo "---------------------------- Test 40 ------------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -B1 'after the binary zero' ./testdata/grepinput) >>testtry - -echo "---------------------------- Test 41 ------------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -B1 -o '\w+ the binary zero' ./testdata/grepinput) >>testtry - -echo "---------------------------- Test 41 ------------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -B1 -onH '\w+ the binary zero' ./testdata/grepinput) >>testtry - -echo "---------------------------- Test 42 ------------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -on 'before|zero|after' ./testdata/grepinput) >>testtry - -echo "---------------------------- Test 43 ------------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -on -e before -e zero -e after ./testdata/grepinput) >>testtry - -echo "---------------------------- Test 44 ------------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -on -f ./testdata/greplist -e binary ./testdata/grepinput) >>testtry - -echo "---------------------------- Test 45 ------------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -e abc -e '(unclosed' ./testdata/grepinput) 2>>testtry >>testtry - -echo "---------------------------- Test 46 ------------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -Fx "AB.VE -elephant" ./testdata/grepinput) >>testtry - -echo "---------------------------- Test 47 ------------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -F "AB.VE -elephant" ./testdata/grepinput) >>testtry - -echo "---------------------------- Test 48 ------------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -F -e DATA -e "AB.VE -elephant" ./testdata/grepinput) >>testtry - -echo "---------------------------- Test 49 ------------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep "^(abc|def|ghi|jkl)" ./testdata/grepinputx) >>testtry - -echo "---------------------------- Test 50 ------------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -Mv "brown\sfox" ./testdata/grepinputv) >>testtry - -echo "---------------------------- Test 51 ------------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep --colour=always jumps ./testdata/grepinputv) >>testtry - -echo "---------------------------- Test 52 ------------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep --file-offsets 'before|zero|after' ./testdata/grepinput) >>testtry - -echo "---------------------------- Test 53 ------------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep --line-offsets 'before|zero|after' ./testdata/grepinput) >>testtry - -echo "---------------------------- Test 54 -----------------------------" >>testtry -(cd $srcdir; $valgrind $pcregrep -f./testdata/greplist --color=always ./testdata/grepinputx) >>testtry - -# Now compare the results. - -$cf $srcdir/testdata/grepoutput testtry -if [ $? != 0 ] ; then exit 1; fi - - -# These tests require UTF-8 support - -if [ $utf8 -ne 0 ] ; then - echo "Testing pcregrep UTF-8 features" - - echo "---------------------------- Test U1 ------------------------------" >testtry - (cd $srcdir; $valgrind $pcregrep -n -u --newline=any "^X" ./testdata/grepinput8) >>testtry - - echo "---------------------------- Test U2 ------------------------------" >>testtry - (cd $srcdir; $valgrind $pcregrep -n -u -C 3 --newline=any "Match" ./testdata/grepinput8) >>testtry - - $cf $srcdir/testdata/grepoutput8 testtry - if [ $? != 0 ] ; then exit 1; fi - -else - echo "Skipping pcregrep UTF-8 tests: no UTF-8 support in PCRE library" -fi - - -# We go to some contortions to try to ensure that the tests for the various -# newline settings will work in environments where the normal newline sequence -# is not \n. Do not use exported files, whose line endings might be changed. -# Instead, create an input file using printf so that its contents are exactly -# what we want. Note the messy fudge to get printf to write a string that -# starts with a hyphen. - -echo "Testing pcregrep newline settings" -printf "abc\rdef\r\nghi\njkl" >testNinput - -printf "%c--------------------------- Test N1 ------------------------------\r\n" - >testtry -$valgrind $pcregrep -n -N CR "^(abc|def|ghi|jkl)" testNinput >>testtry - -printf "%c--------------------------- Test N2 ------------------------------\r\n" - >>testtry -$valgrind $pcregrep -n --newline=crlf "^(abc|def|ghi|jkl)" testNinput >>testtry - -printf "%c--------------------------- Test N3 ------------------------------\r\n" - >>testtry -pattern=`printf 'def\rjkl'` -$valgrind $pcregrep -n --newline=cr -F "$pattern" testNinput >>testtry - -printf "%c--------------------------- Test N4 ------------------------------\r\n" - >>testtry -pattern=`printf 'xxx\r\njkl'` -$valgrind $pcregrep -n --newline=crlf -F "$pattern" testNinput >>testtry - -printf "%c--------------------------- Test N5 ------------------------------\r\n" - >>testtry -$valgrind $pcregrep -n --newline=any "^(abc|def|ghi|jkl)" testNinput >>testtry - -printf "%c--------------------------- Test N6 ------------------------------\r\n" - >>testtry -$valgrind $pcregrep -n --newline=anycrlf "^(abc|def|ghi|jkl)" testNinput >>testtry - -$cf $srcdir/testdata/grepoutputN testtry -if [ $? != 0 ] ; then exit 1; fi - -exit 0 - -# End diff --git a/libs/pcre/RunGrepTest.in b/libs/pcre/RunGrepTest.in deleted file mode 100644 index 86ada8dbf4..0000000000 --- a/libs/pcre/RunGrepTest.in +++ /dev/null @@ -1,208 +0,0 @@ -#! /bin/sh - -# This file is generated by configure from RunGrepTest.in. Make any changes -# to that file. - -echo "Testing pcregrep" -./pcregrep -V - -# Run pcregrep tests. The assumption is that the PCRE tests check the library -# itself. What we are checking here is the file handling and options that are -# supported by pcregrep. - -cf=diff -valgrind= -if [ ! -d testdata ] ; then - ln -s @top_srcdir@/testdata testdata -fi -testdata=./testdata - -while [ $# -gt 0 ] ; do - case $1 in - valgrind) valgrind="valgrind -q --leak-check=no";; - *) echo "Unknown argument $1"; exit 1;; - esac - shift -done - -echo "---------------------------- Test 1 ------------------------------" >testtry -$valgrind ./pcregrep PATTERN $testdata/grepinput >>testtry - -echo "---------------------------- Test 2 ------------------------------" >>testtry -$valgrind ./pcregrep '^PATTERN' $testdata/grepinput >>testtry - -echo "---------------------------- Test 3 ------------------------------" >>testtry -$valgrind ./pcregrep -in PATTERN $testdata/grepinput >>testtry - -echo "---------------------------- Test 4 ------------------------------" >>testtry -$valgrind ./pcregrep -ic PATTERN $testdata/grepinput >>testtry - -echo "---------------------------- Test 5 ------------------------------" >>testtry -$valgrind ./pcregrep -in PATTERN $testdata/grepinput $testdata/grepinputx >>testtry - -echo "---------------------------- Test 6 ------------------------------" >>testtry -$valgrind ./pcregrep -inh PATTERN $testdata/grepinput $testdata/grepinputx >>testtry - -echo "---------------------------- Test 7 ------------------------------" >>testtry -$valgrind ./pcregrep -il PATTERN $testdata/grepinput $testdata/grepinputx >>testtry - -echo "---------------------------- Test 8 ------------------------------" >>testtry -$valgrind ./pcregrep -l PATTERN $testdata/grepinput $testdata/grepinputx >>testtry - -echo "---------------------------- Test 9 ------------------------------" >>testtry -$valgrind ./pcregrep -q PATTERN $testdata/grepinput $testdata/grepinputx >>testtry -echo "RC=$?" >>testtry - -echo "---------------------------- Test 10 -----------------------------" >>testtry -$valgrind ./pcregrep -q NEVER-PATTERN $testdata/grepinput $testdata/grepinputx >>testtry -echo "RC=$?" >>testtry - -echo "---------------------------- Test 11 -----------------------------" >>testtry -$valgrind ./pcregrep -vn pattern $testdata/grepinputx >>testtry - -echo "---------------------------- Test 12 -----------------------------" >>testtry -$valgrind ./pcregrep -ix pattern $testdata/grepinputx >>testtry - -echo "---------------------------- Test 13 -----------------------------" >>testtry -$valgrind ./pcregrep -f$testdata/greplist $testdata/grepinputx >>testtry - -echo "---------------------------- Test 14 -----------------------------" >>testtry -$valgrind ./pcregrep -w pat $testdata/grepinput $testdata/grepinputx >>testtry - -echo "---------------------------- Test 15 -----------------------------" >>testtry -$valgrind ./pcregrep 'abc^*' $testdata/grepinput 2>>testtry >>testtry - -echo "---------------------------- Test 16 -----------------------------" >>testtry -$valgrind ./pcregrep abc $testdata/grepinput $testdata/nonexistfile 2>>testtry >>testtry - -echo "---------------------------- Test 17 -----------------------------" >>testtry -$valgrind ./pcregrep -M 'the\noutput' $testdata/grepinput >>testtry - -echo "---------------------------- Test 18 -----------------------------" >>testtry -$valgrind ./pcregrep -Mn '(the\noutput|dog\.\n--)' $testdata/grepinput >>testtry - -echo "---------------------------- Test 19 -----------------------------" >>testtry -$valgrind ./pcregrep -Mix 'Pattern' $testdata/grepinputx >>testtry - -echo "---------------------------- Test 20 -----------------------------" >>testtry -$valgrind ./pcregrep -Mixn 'complete pair\nof lines' $testdata/grepinputx >>testtry - -echo "---------------------------- Test 21 -----------------------------" >>testtry -$valgrind ./pcregrep -nA3 'four' $testdata/grepinputx >>testtry - -echo "---------------------------- Test 22 -----------------------------" >>testtry -$valgrind ./pcregrep -nB3 'four' $testdata/grepinputx >>testtry - -echo "---------------------------- Test 23 -----------------------------" >>testtry -$valgrind ./pcregrep -C3 'four' $testdata/grepinputx >>testtry - -echo "---------------------------- Test 24 -----------------------------" >>testtry -$valgrind ./pcregrep -A9 'four' $testdata/grepinputx >>testtry - -echo "---------------------------- Test 25 -----------------------------" >>testtry -$valgrind ./pcregrep -nB9 'four' $testdata/grepinputx >>testtry - -echo "---------------------------- Test 26 -----------------------------" >>testtry -$valgrind ./pcregrep -A9 -B9 'four' $testdata/grepinputx >>testtry - -echo "---------------------------- Test 27 -----------------------------" >>testtry -$valgrind ./pcregrep -A10 'four' $testdata/grepinputx >>testtry - -echo "---------------------------- Test 28 -----------------------------" >>testtry -$valgrind ./pcregrep -nB10 'four' $testdata/grepinputx >>testtry - -echo "---------------------------- Test 29 -----------------------------" >>testtry -$valgrind ./pcregrep -C12 -B10 'four' $testdata/grepinputx >>testtry - -echo "---------------------------- Test 30 -----------------------------" >>testtry -$valgrind ./pcregrep -inB3 'pattern' $testdata/grepinput $testdata/grepinputx >>testtry - -echo "---------------------------- Test 31 -----------------------------" >>testtry -$valgrind ./pcregrep -inA3 'pattern' $testdata/grepinput $testdata/grepinputx >>testtry - -echo "---------------------------- Test 32 -----------------------------" >>testtry -$valgrind ./pcregrep -L 'fox' $testdata/grepinput $testdata/grepinputx >>testtry - -echo "---------------------------- Test 33 -----------------------------" >>testtry -$valgrind ./pcregrep 'fox' $testdata/grepnonexist >>testtry 2>&1 -echo "RC=$?" >>testtry - -echo "---------------------------- Test 34 -----------------------------" >>testtry -$valgrind ./pcregrep -s 'fox' $testdata/grepnonexist >>testtry 2>&1 -echo "RC=$?" >>testtry - -echo "---------------------------- Test 35 -----------------------------" >>testtry -$valgrind ./pcregrep -L -r --include=grepinputx 'fox' $testdata >>testtry -echo "RC=$?" >>testtry - -echo "---------------------------- Test 36 -----------------------------" >>testtry -$valgrind ./pcregrep -L -r --include=grepinput --exclude 'grepinput$' 'fox' $testdata >>testtry -echo "RC=$?" >>testtry - -echo "---------------------------- Test 37 -----------------------------" >>testtry -$valgrind ./pcregrep '^(a+)*\d' $testdata/grepinput >>testtry 2>teststderr -echo "RC=$?" >>testtry -echo "======== STDERR ========" >>testtry -cat teststderr >>testtry - -echo "---------------------------- Test 38 ------------------------------" >>testtry -$valgrind ./pcregrep '>\x00<' $testdata/grepinput >>testtry - -echo "---------------------------- Test 39 ------------------------------" >>testtry -$valgrind ./pcregrep -A1 'before the binary zero' $testdata/grepinput >>testtry - -echo "---------------------------- Test 40 ------------------------------" >>testtry -$valgrind ./pcregrep -B1 'after the binary zero' $testdata/grepinput >>testtry - -echo "---------------------------- Test 41 ------------------------------" >>testtry -$valgrind ./pcregrep -B1 -o '\w+ the binary zero' $testdata/grepinput >>testtry - -echo "---------------------------- Test 41 ------------------------------" >>testtry -$valgrind ./pcregrep -B1 -onH '\w+ the binary zero' $testdata/grepinput >>testtry - -echo "---------------------------- Test 42 ------------------------------" >>testtry -$valgrind ./pcregrep -on 'before|zero|after' $testdata/grepinput >>testtry - -echo "---------------------------- Test 43 ------------------------------" >>testtry -$valgrind ./pcregrep -on -e before -e zero -e after $testdata/grepinput >>testtry - -echo "---------------------------- Test 44 ------------------------------" >>testtry -$valgrind ./pcregrep -on -f $testdata/greplist -e binary $testdata/grepinput >>testtry - -echo "---------------------------- Test 45 ------------------------------" >>testtry -$valgrind ./pcregrep -e abc -e '(unclosed' $testdata/grepinput 2>>testtry >>testtry - -echo "---------------------------- Test 46 ------------------------------" >>testtry -$valgrind ./pcregrep -Fx "AB.VE -elephant" $testdata/grepinput >>testtry - -echo "---------------------------- Test 47 ------------------------------" >>testtry -$valgrind ./pcregrep -F "AB.VE -elephant" $testdata/grepinput >>testtry - -echo "---------------------------- Test 48 ------------------------------" >>testtry -$valgrind ./pcregrep -F -e DATA -e "AB.VE -elephant" $testdata/grepinput >>testtry - -echo "---------------------------- Test 49 ------------------------------" >>testtry -$valgrind ./pcregrep "^(abc|def|ghi|jkl)" $testdata/grepinputx >>testtry - -echo "---------------------------- Test 50 ------------------------------" >>testtry -$valgrind ./pcregrep -N CR "^(abc|def|ghi|jkl)" $testdata/grepinputx >>testtry - -echo "---------------------------- Test 51 ------------------------------" >>testtry -$valgrind ./pcregrep --newline=crlf "^(abc|def|ghi|jkl)" $testdata/grepinputx >>testtry - -echo "---------------------------- Test 52 ------------------------------" >>testtry -$valgrind ./pcregrep --newline=cr -F "def jkl" $testdata/grepinputx >>testtry - -echo "---------------------------- Test 53 ------------------------------" >>testtry -$valgrind ./pcregrep --newline=crlf -F "xxx -jkl" $testdata/grepinputx >>testtry - -# Now compare the results. - -$cf testtry $testdata/grepoutput -if [ $? != 0 ] ; then exit 1; else exit 0; fi - -# End diff --git a/libs/pcre/RunTest b/libs/pcre/RunTest deleted file mode 100755 index 514bb79e34..0000000000 --- a/libs/pcre/RunTest +++ /dev/null @@ -1,292 +0,0 @@ -#! /bin/sh - -# Run PCRE tests. - -valgrind= - -# Set up a suitable "diff" command for comparison. Some systems -# have a diff that lacks a -u option. Try to deal with this. - -if diff -u /dev/null /dev/null; then cf="diff -u"; else cf="diff"; fi - -# Find the test data - -testdata=testdata -if [ -n "$srcdir" -a -d "$srcdir" ] ; then - testdata="$srcdir/testdata" -fi - -# Find which optional facilities are available - -case `./pcretest -C | ./pcregrep 'Internal link size'` in - *2) link_size=2;; - *3) link_size=3;; - *4) link_size=4;; - *) echo "Failed to find internal link size"; exit 1;; -esac - -./pcretest -C | ./pcregrep 'No UTF-8 support' >/dev/null -utf8=$? - -./pcretest -C | ./pcregrep 'No Unicode properties support' >/dev/null -ucp=$? - -# Select which tests to run; for those that are explicitly requested, check -# that the necessary optional facilities are available. - -do1=no -do2=no -do3=no -do4=no -do5=no -do6=no -do7=no -do8=no -do9=no -do10=no - -while [ $# -gt 0 ] ; do - case $1 in - 1) do1=yes;; - 2) do2=yes;; - 3) do3=yes;; - 4) do4=yes;; - 5) do5=yes;; - 6) do6=yes;; - 7) do7=yes;; - 8) do8=yes;; - 9) do9=yes;; - 10) do10=yes;; - valgrind) valgrind="valgrind -q";; - *) echo "Unknown test number $1"; exit 1;; - esac - shift -done - -if [ $utf8 -eq 0 ] ; then - if [ $do4 = yes ] ; then - echo "Can't run test 4 because UTF-8 support is not configured" - exit 1 - fi - if [ $do5 = yes ] ; then - echo "Can't run test 5 because UTF-8 support is not configured" - exit 1 - fi - if [ $do8 = yes ] ; then - echo "Can't run test 8 because UTF-8 support is not configured" - exit 1 - fi -fi - -if [ $ucp -eq 0 ] ; then - if [ $do6 = yes ] ; then - echo "Can't run test 6 because Unicode property support is not configured" - exit 1 - fi - if [ $do9 = yes ] ; then - echo "Can't run test 9 because Unicode property support is not configured" - exit 1 - fi - if [ $do10 = yes ] ; then - echo "Can't run test 10 because Unicode property support is not configured" - exit 1 - fi -fi - -if [ $link_size -ne 2 ] ; then - if [ $do10 = yes ] ; then - echo "Can't run test 10 because the link size ($link_size) is not 2" - exit 1 - fi -fi - -# If no specific tests were requested, select all that are relevant. - -if [ $do1 = no -a $do2 = no -a $do3 = no -a $do4 = no -a \ - $do5 = no -a $do6 = no -a $do7 = no -a $do8 = no -a \ - $do9 = no -a $do10 = no ] ; then - do1=yes - do2=yes - do3=yes - if [ $utf8 -ne 0 ] ; then do4=yes; fi - if [ $utf8 -ne 0 ] ; then do5=yes; fi - if [ $utf8 -ne 0 -a $ucp -ne 0 ] ; then do6=yes; fi - do7=yes - if [ $utf8 -ne 0 ] ; then do8=yes; fi - if [ $utf8 -ne 0 -a $ucp -ne 0 ] ; then do9=yes; fi - if [ $link_size -eq 2 -a $ucp -ne 0 ] ; then do10=yes; fi -fi - -# Show which release - -echo "" -echo PCRE C library tests -./pcretest /dev/null - -# Primary test, Perl-compatible - -if [ $do1 = yes ] ; then - echo "Test 1: main functionality (Perl compatible)" - $valgrind ./pcretest -q $testdata/testinput1 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput1 testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - echo "OK" -fi - -# PCRE tests that are not Perl-compatible - API & error tests, mostly - -if [ $do2 = yes ] ; then - echo "Test 2: API and error handling (not Perl compatible)" - $valgrind ./pcretest -q $testdata/testinput2 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput2 testtry - if [ $? != 0 ] ; then exit 1; fi - else - echo " " - echo "** Test 2 requires a lot of stack. If it has crashed with a" - echo "** segmentation fault, it may be that you do not have enough" - echo "** stack available by default. Please see the 'pcrestack' man" - echo "** page for a discussion of PCRE's stack usage." - echo " " - exit 1 - fi - echo "OK" -fi - -# Locale-specific tests, provided that either the "fr_FR" or the "french" -# locale is available. The former is the Unix-like standard; the latter is -# for Windows. - -if [ $do3 = yes ] ; then - locale -a | grep '^fr_FR$' >/dev/null - if [ $? -eq 0 ] ; then - locale=fr_FR - infile=$testdata/testinput3 - outfile=$testdata/testoutput3 - else - locale -a | grep '^french$' >/dev/null - if [ $? -eq 0 ] ; then - locale=french - sed 's/fr_FR/french/' $testdata/testinput3 >test3input - sed 's/fr_FR/french/' $testdata/testoutput3 >test3output - infile=test3input - outfile=test3output - else - locale= - fi - fi - - if [ "$locale" != "" ] ; then - echo "Test 3: locale-specific features (using '$locale' locale)" - $valgrind ./pcretest -q $infile testtry - if [ $? = 0 ] ; then - $cf $outfile testtry - if [ $? != 0 ] ; then - echo " " - echo "Locale test did not run entirely successfully." - echo "This usually means that there is a problem with the locale" - echo "settings rather than a bug in PCRE." - else - echo "OK" - fi - else exit 1 - fi - else - echo "Cannot test locale-specific features - neither the 'fr_FR' nor the" - echo "'french' locale exists, or the \"locale\" command is not available" - echo "to check for them." - echo " " - fi -fi - -# Additional tests for UTF8 support - -if [ $do4 = yes ] ; then - echo "Test 4: UTF-8 support (Perl compatible)" - $valgrind ./pcretest -q $testdata/testinput4 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput4 testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - echo "OK" -fi - -if [ $do5 = yes ] ; then - echo "Test 5: API and internals for UTF-8 support (not Perl compatible)" - $valgrind ./pcretest -q $testdata/testinput5 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput5 testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - echo "OK" -fi - -if [ $do6 = yes ] ; then - echo "Test 6: Unicode property support" - $valgrind ./pcretest -q $testdata/testinput6 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput6 testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - echo "OK" -fi - -# Tests for DFA matching support - -if [ $do7 = yes ] ; then - echo "Test 7: DFA matching" - $valgrind ./pcretest -q -dfa $testdata/testinput7 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput7 testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - echo "OK" -fi - -if [ $do8 = yes ] ; then - echo "Test 8: DFA matching with UTF-8" - $valgrind ./pcretest -q -dfa $testdata/testinput8 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput8 testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - echo "OK" -fi - -if [ $do9 = yes ] ; then - echo "Test 9: DFA matching with Unicode properties" - $valgrind ./pcretest -q -dfa $testdata/testinput9 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput9 testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - echo "OK" -fi - -# Test of internal offsets and code sizes. This test is run only when there -# is Unicode property support and the link size is 2. The actual tests are -# mostly the same as in some of the above, but in this test we inspect some -# offsets and sizes that require a known link size. This is a doublecheck for -# the maintainer, just in case something changes unexpectely. - -if [ $do10 = yes ] ; then - echo "Test 10: Internal offsets and code size tests" - $valgrind ./pcretest -q $testdata/testinput10 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput10 testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - echo "OK" -fi - -# End diff --git a/libs/pcre/RunTest.bat b/libs/pcre/RunTest.bat deleted file mode 100644 index 70517d09ee..0000000000 --- a/libs/pcre/RunTest.bat +++ /dev/null @@ -1,39 +0,0 @@ -@rem This file was contributed by Ralf Junker, and touched up by -@rem Daniel Richard G. Test 10 added by Philip H. -@rem Philip H also changed test 3 to use "wintest" files. -@rem -@rem MS Windows batch file to run pcretest on testfiles with the correct -@rem options. -@rem -@rem Output is written to a newly created subfolder named "testdata". - -setlocal - -if [%srcdir%]==[] set srcdir=. -if [%pcretest%]==[] set pcretest=pcretest - -if not exist testout md testout - -%pcretest% -q %srcdir%\testdata\testinput1 > testout\testoutput1 -%pcretest% -q %srcdir%\testdata\testinput2 > testout\testoutput2 -@rem %pcretest% -q %srcdir%\testdata\testinput3 > testout\testoutput3 -%pcretest% -q %srcdir%\testdata\wintestinput3 > testout\wintestoutput3 -%pcretest% -q %srcdir%\testdata\testinput4 > testout\testoutput4 -%pcretest% -q %srcdir%\testdata\testinput5 > testout\testoutput5 -%pcretest% -q %srcdir%\testdata\testinput6 > testout\testoutput6 -%pcretest% -q -dfa %srcdir%\testdata\testinput7 > testout\testoutput7 -%pcretest% -q -dfa %srcdir%\testdata\testinput8 > testout\testoutput8 -%pcretest% -q -dfa %srcdir%\testdata\testinput9 > testout\testoutput9 -%pcretest% -q %srcdir%\testdata\testinput10 > testout\testoutput10 - -fc /n %srcdir%\testdata\testoutput1 testout\testoutput1 -fc /n %srcdir%\testdata\testoutput2 testout\testoutput2 -rem fc /n %srcdir%\testdata\testoutput3 testout\testoutput3 -fc /n %srcdir%\testdata\wintestoutput3 testout\wintestoutput3 -fc /n %srcdir%\testdata\testoutput4 testout\testoutput4 -fc /n %srcdir%\testdata\testoutput5 testout\testoutput5 -fc /n %srcdir%\testdata\testoutput6 testout\testoutput6 -fc /n %srcdir%\testdata\testoutput7 testout\testoutput7 -fc /n %srcdir%\testdata\testoutput8 testout\testoutput8 -fc /n %srcdir%\testdata\testoutput9 testout\testoutput9 -fc /n %srcdir%\testdata\testoutput10 testout\testoutput10 diff --git a/libs/pcre/RunTest.in b/libs/pcre/RunTest.in deleted file mode 100755 index f6518ed57e..0000000000 --- a/libs/pcre/RunTest.in +++ /dev/null @@ -1,258 +0,0 @@ -#! /bin/sh - -# This file is generated by configure from RunTest.in. Make any changes -# to that file. - -# Run PCRE tests - -cf=diff -valgrind= -if [ ! -d testdata ] ; then - ln -s @top_srcdir@/testdata testdata -fi -testdata=./testdata - - -# Select which tests to run; if no selection, run all - -do1=no -do2=no -do3=no -do4=no -do5=no -do6=no -do7=no -do8=no -do9=no - -while [ $# -gt 0 ] ; do - case $1 in - 1) do1=yes;; - 2) do2=yes;; - 3) do3=yes;; - 4) do4=yes;; - 5) do5=yes;; - 6) do6=yes;; - 7) do7=yes;; - 8) do8=yes;; - 9) do9=yes;; - valgrind) valgrind="valgrind -q";; - *) echo "Unknown test number $1"; exit 1;; - esac - shift -done - -if [ "@LINK_SIZE@" != "" -a "@LINK_SIZE@" != "-DLINK_SIZE=2" ] ; then - if [ $do2 = yes ] ; then - echo "Can't run test 2 with an internal link size other than 2" - exit 1 - fi - if [ $do5 = yes ] ; then - echo "Can't run test 5 with an internal link size other than 2" - exit 1 - fi - if [ $do6 = yes ] ; then - echo "Can't run test 6 with an internal link size other than 2" - exit 1 - fi -fi - -if [ "@UTF8@" = "" ] ; then - if [ $do4 = yes ] ; then - echo "Can't run test 4 because UTF-8 support is not configured" - exit 1 - fi - if [ $do5 = yes ] ; then - echo "Can't run test 5 because UTF-8 support is not configured" - exit 1 - fi - if [ $do6 = yes ] ; then - echo "Can't run test 6 because UTF-8 support is not configured" - exit 1 - fi - if [ $do8 = yes ] ; then - echo "Can't run test 8 because UTF-8 support is not configured" - exit 1 - fi - if [ $do9 = yes ] ; then - echo "Can't run test 9 because UTF-8 support is not configured" - exit 1 - fi -fi - -if [ "@UCP@" = "" ] ; then - if [ $do6 = yes ] ; then - echo "Can't run test 6 because Unicode property support is not configured" - exit 1 - fi - if [ $do9 = yes ] ; then - echo "Can't run test 9 because Unicode property support is not configured" - exit 1 - fi -fi - -if [ $do1 = no -a $do2 = no -a $do3 = no -a $do4 = no -a \ - $do5 = no -a $do6 = no -a $do7 = no -a $do8 = no -a \ - $do9 = no ] ; then - do1=yes - do2=yes - do3=yes - if [ "@UTF8@" != "" ] ; then do4=yes; fi - if [ "@UTF8@" != "" ] ; then do5=yes; fi - if [ "@UTF8@" != "" -a "@UCP@" != "" ] ; then do6=yes; fi - do7=yes - if [ "@UTF8@" != "" ] ; then do8=yes; fi - if [ "@UTF8@" != "" -a "@UCP@" != "" ] ; then do9=yes; fi -fi - -# Show which release - -./pcretest /dev/null - -# Primary test, Perl-compatible - -if [ $do1 = yes ] ; then - echo "Test 1: main functionality (Perl compatible)" - $valgrind ./pcretest -q $testdata/testinput1 testtry - if [ $? = 0 ] ; then - $cf testtry $testdata/testoutput1 - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - echo "OK" - echo " " -fi - -# PCRE tests that are not Perl-compatible - API & error tests, mostly - -if [ $do2 = yes ] ; then - if [ "@LINK_SIZE@" = "" -o "@LINK_SIZE@" = "-DLINK_SIZE=2" ] ; then - echo "Test 2: API and error handling (not Perl compatible)" - $valgrind ./pcretest -q -i $testdata/testinput2 testtry - if [ $? = 0 ] ; then - $cf testtry $testdata/testoutput2 - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - echo "OK" - echo " " - else - echo Test 2 skipped for link size other than 2 \(@LINK_SIZE@\) - echo " " - fi -fi - -# Locale-specific tests, provided the "fr_FR" locale is available - -if [ $do3 = yes ] ; then - locale -a | grep '^fr_FR$' >/dev/null - if [ $? -eq 0 ] ; then - echo "Test 3: locale-specific features (using 'fr_FR' locale)" - $valgrind ./pcretest -q $testdata/testinput3 testtry - if [ $? = 0 ] ; then - $cf testtry $testdata/testoutput3 - if [ $? != 0 ] ; then - echo " " - echo "Locale test did not run entirely successfully." - echo "This usually means that there is a problem with the locale" - echo "settings rather than a bug in PCRE." - else - echo "OK" - fi - echo " " - else exit 1 - fi - else - echo "Cannot test locale-specific features - 'fr_FR' locale not found," - echo "or the \"locale\" command is not available to check for it." - echo " " - fi -fi - -# Additional tests for UTF8 support - -if [ $do4 = yes ] ; then - echo "Test 4: UTF-8 support (Perl compatible)" - $valgrind ./pcretest -q $testdata/testinput4 testtry - if [ $? = 0 ] ; then - $cf testtry $testdata/testoutput4 - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - echo "OK" - echo " " -fi - -if [ $do5 = yes ] ; then - if [ "@LINK_SIZE@" = "" -o "@LINK_SIZE@" = "-DLINK_SIZE=2" ] ; then - echo "Test 5: API and internals for UTF-8 support (not Perl compatible)" - $valgrind ./pcretest -q $testdata/testinput5 testtry - if [ $? = 0 ] ; then - $cf testtry $testdata/testoutput5 - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - echo "OK" - echo " " - else - echo Test 5 skipped for link size other than 2 \(@LINK_SIZE@\) - echo " " - fi -fi - -if [ $do6 = yes ] ; then - if [ "@LINK_SIZE@" = "" -o "@LINK_SIZE@" = "-DLINK_SIZE=2" ] ; then - echo "Test 6: Unicode property support" - $valgrind ./pcretest -q $testdata/testinput6 testtry - if [ $? = 0 ] ; then - $cf testtry $testdata/testoutput6 - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - echo "OK" - echo " " - else - echo Test 6 skipped for link size other than 2 \(@LINK_SIZE@\) - echo " " - fi -fi - -# Tests for DFA matching support - -if [ $do7 = yes ] ; then - echo "Test 7: DFA matching" - $valgrind ./pcretest -q -dfa $testdata/testinput7 testtry - if [ $? = 0 ] ; then - $cf testtry $testdata/testoutput7 - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - echo "OK" - echo " " -fi - -if [ $do8 = yes ] ; then - echo "Test 8: DFA matching with UTF-8" - $valgrind ./pcretest -q -dfa $testdata/testinput8 testtry - if [ $? = 0 ] ; then - $cf testtry $testdata/testoutput8 - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - echo "OK" - echo " " -fi - -if [ $do9 = yes ] ; then - echo "Test 9: DFA matching with Unicode properties" - $valgrind ./pcretest -q -dfa $testdata/testinput9 testtry - if [ $? = 0 ] ; then - $cf testtry $testdata/testoutput9 - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - echo "OK" - echo " " -fi - -# End diff --git a/libs/pcre/cmake/COPYING-CMAKE-SCRIPTS b/libs/pcre/cmake/COPYING-CMAKE-SCRIPTS deleted file mode 100644 index 4b417765f3..0000000000 --- a/libs/pcre/cmake/COPYING-CMAKE-SCRIPTS +++ /dev/null @@ -1,22 +0,0 @@ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions -are met: - -1. Redistributions of source code must retain the copyright - notice, this list of conditions and the following disclaimer. -2. Redistributions in binary form must reproduce the copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. -3. The name of the author may not be used to endorse or promote products - derived from this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR -IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES -OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. -IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, -INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT -NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, -DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY -THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT -(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF -THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. diff --git a/libs/pcre/cmake/FindPackageHandleStandardArgs.cmake b/libs/pcre/cmake/FindPackageHandleStandardArgs.cmake deleted file mode 100644 index 151d812503..0000000000 --- a/libs/pcre/cmake/FindPackageHandleStandardArgs.cmake +++ /dev/null @@ -1,58 +0,0 @@ -# FIND_PACKAGE_HANDLE_STANDARD_ARGS(NAME (DEFAULT_MSG|"Custom failure message") VAR1 ... ) -# This macro is intended to be used in FindXXX.cmake modules files. -# It handles the REQUIRED and QUIET argument to FIND_PACKAGE() and -# it also sets the _FOUND variable. -# The package is found if all variables listed are TRUE. -# Example: -# -# FIND_PACKAGE_HANDLE_STANDARD_ARGS(LibXml2 DEFAULT_MSG LIBXML2_LIBRARIES LIBXML2_INCLUDE_DIR) -# -# LibXml2 is considered to be found, if both LIBXML2_LIBRARIES and -# LIBXML2_INCLUDE_DIR are valid. Then also LIBXML2_FOUND is set to TRUE. -# If it is not found and REQUIRED was used, it fails with FATAL_ERROR, -# independent whether QUIET was used or not. -# If it is found, the location is reported using the VAR1 argument, so -# here a message "Found LibXml2: /usr/lib/libxml2.so" will be printed out. -# If the second argument is DEFAULT_MSG, the message in the failure case will -# be "Could NOT find LibXml2", if you don't like this message you can specify -# your own custom failure message there. - -MACRO(FIND_PACKAGE_HANDLE_STANDARD_ARGS _NAME _FAIL_MSG _VAR1 ) - - IF("${_FAIL_MSG}" STREQUAL "DEFAULT_MSG") - IF (${_NAME}_FIND_REQUIRED) - SET(_FAIL_MESSAGE "Could not find REQUIRED package ${_NAME}") - ELSE (${_NAME}_FIND_REQUIRED) - SET(_FAIL_MESSAGE "Could not find OPTIONAL package ${_NAME}") - ENDIF (${_NAME}_FIND_REQUIRED) - ELSE("${_FAIL_MSG}" STREQUAL "DEFAULT_MSG") - SET(_FAIL_MESSAGE "${_FAIL_MSG}") - ENDIF("${_FAIL_MSG}" STREQUAL "DEFAULT_MSG") - - STRING(TOUPPER ${_NAME} _NAME_UPPER) - - SET(${_NAME_UPPER}_FOUND TRUE) - IF(NOT ${_VAR1}) - SET(${_NAME_UPPER}_FOUND FALSE) - ENDIF(NOT ${_VAR1}) - - FOREACH(_CURRENT_VAR ${ARGN}) - IF(NOT ${_CURRENT_VAR}) - SET(${_NAME_UPPER}_FOUND FALSE) - ENDIF(NOT ${_CURRENT_VAR}) - ENDFOREACH(_CURRENT_VAR) - - IF (${_NAME_UPPER}_FOUND) - IF (NOT ${_NAME}_FIND_QUIETLY) - MESSAGE(STATUS "Found ${_NAME}: ${${_VAR1}}") - ENDIF (NOT ${_NAME}_FIND_QUIETLY) - ELSE (${_NAME_UPPER}_FOUND) - IF (${_NAME}_FIND_REQUIRED) - MESSAGE(FATAL_ERROR "${_FAIL_MESSAGE}") - ELSE (${_NAME}_FIND_REQUIRED) - IF (NOT ${_NAME}_FIND_QUIETLY) - MESSAGE(STATUS "${_FAIL_MESSAGE}") - ENDIF (NOT ${_NAME}_FIND_QUIETLY) - ENDIF (${_NAME}_FIND_REQUIRED) - ENDIF (${_NAME_UPPER}_FOUND) -ENDMACRO(FIND_PACKAGE_HANDLE_STANDARD_ARGS) diff --git a/libs/pcre/cmake/FindReadline.cmake b/libs/pcre/cmake/FindReadline.cmake deleted file mode 100644 index 1d4cc55843..0000000000 --- a/libs/pcre/cmake/FindReadline.cmake +++ /dev/null @@ -1,29 +0,0 @@ -# from http://websvn.kde.org/trunk/KDE/kdeedu/cmake/modules/FindReadline.cmake -# http://websvn.kde.org/trunk/KDE/kdeedu/cmake/modules/COPYING-CMAKE-SCRIPTS -# --> BSD licensed -# -# GNU Readline library finder -if(READLINE_INCLUDE_DIR AND READLINE_LIBRARY AND NCURSES_LIBRARY) - set(READLINE_FOUND TRUE) -else(READLINE_INCLUDE_DIR AND READLINE_LIBRARY AND NCURSES_LIBRARY) - FIND_PATH(READLINE_INCLUDE_DIR readline/readline.h - /usr/include/readline - ) - -# 2008-04-22 The next clause used to read like this: -# -# FIND_LIBRARY(READLINE_LIBRARY NAMES readline) -# FIND_LIBRARY(NCURSES_LIBRARY NAMES ncurses ) -# include(FindPackageHandleStandardArgs) -# FIND_PACKAGE_HANDLE_STANDARD_ARGS(Readline DEFAULT_MSG NCURSES_LIBRARY READLINE_INCLUDE_DIR READLINE_LIBRARY ) -# -# I was advised to modify it such that it will find an ncurses library if -# required, but not if one was explicitly given, that is, it allows the -# default to be overridden. PH - - FIND_LIBRARY(READLINE_LIBRARY NAMES readline) - include(FindPackageHandleStandardArgs) - FIND_PACKAGE_HANDLE_STANDARD_ARGS(Readline DEFAULT_MSG READLINE_INCLUDE_DIR READLINE_LIBRARY ) - - MARK_AS_ADVANCED(READLINE_INCLUDE_DIR READLINE_LIBRARY) -endif(READLINE_INCLUDE_DIR AND READLINE_LIBRARY AND NCURSES_LIBRARY) diff --git a/libs/pcre/config-cmake.h.in b/libs/pcre/config-cmake.h.in deleted file mode 100644 index 5951af7441..0000000000 --- a/libs/pcre/config-cmake.h.in +++ /dev/null @@ -1,44 +0,0 @@ -/* config.h for CMake builds */ - -#cmakedefine HAVE_DIRENT_H 1 -#cmakedefine HAVE_SYS_STAT_H 1 -#cmakedefine HAVE_SYS_TYPES_H 1 -#cmakedefine HAVE_UNISTD_H 1 -#cmakedefine HAVE_WINDOWS_H 1 - -#cmakedefine HAVE_TYPE_TRAITS_H 1 -#cmakedefine HAVE_BITS_TYPE_TRAITS_H 1 - -#cmakedefine HAVE_BCOPY 1 -#cmakedefine HAVE_MEMMOVE 1 -#cmakedefine HAVE_STRERROR 1 -#cmakedefine HAVE_STRTOLL 1 -#cmakedefine HAVE_STRTOQ 1 -#cmakedefine HAVE__STRTOI64 1 - -#cmakedefine PCRE_STATIC 1 - -#cmakedefine SUPPORT_UTF8 1 -#cmakedefine SUPPORT_UCP 1 -#cmakedefine EBCDIC 1 -#cmakedefine BSR_ANYCRLF 1 -#cmakedefine NO_RECURSE 1 - -#cmakedefine HAVE_LONG_LONG 1 -#cmakedefine HAVE_UNSIGNED_LONG_LONG 1 - -#cmakedefine SUPPORT_LIBBZ2 1 -#cmakedefine SUPPORT_LIBZ 1 -#cmakedefine SUPPORT_LIBREADLINE 1 - -#define NEWLINE @NEWLINE@ -#define POSIX_MALLOC_THRESHOLD @PCRE_POSIX_MALLOC_THRESHOLD@ -#define LINK_SIZE @PCRE_LINK_SIZE@ -#define MATCH_LIMIT @PCRE_MATCH_LIMIT@ -#define MATCH_LIMIT_RECURSION @PCRE_MATCH_LIMIT_RECURSION@ - - -#define MAX_NAME_SIZE 32 -#define MAX_NAME_COUNT 10000 - -/* end config.h for CMake builds */ diff --git a/libs/pcre/config.h.generic b/libs/pcre/config.h.generic deleted file mode 100644 index 7bfcdb858c..0000000000 --- a/libs/pcre/config.h.generic +++ /dev/null @@ -1,313 +0,0 @@ -/* config.h. Generated from config.h.in by configure. */ -/* config.h.in. Generated from configure.ac by autoheader. */ - - -/* On Unix-like systems config.h.in is converted by "configure" into config.h. -Some other environments also support the use of "configure". PCRE is written in -Standard C, but there are a few non-standard things it can cope with, allowing -it to run on SunOS4 and other "close to standard" systems. - -If you are going to build PCRE "by hand" on a system without "configure" you -should copy the distributed config.h.generic to config.h, and then set up the -macro definitions the way you need them. You must then add -DHAVE_CONFIG_H to -all of your compile commands, so that config.h is included at the start of -every source. - -Alternatively, you can avoid editing by using -D on the compiler command line -to set the macro values. In this case, you do not have to set -DHAVE_CONFIG_H. - -PCRE uses memmove() if HAVE_MEMMOVE is set to 1; otherwise it uses bcopy() if -HAVE_BCOPY is set to 1. If your system has neither bcopy() nor memmove(), set -them both to 0; an emulation function will be used. */ - -/* By default, the \R escape sequence matches any Unicode line ending - character or sequence of characters. If BSR_ANYCRLF is defined, this is - changed so that backslash-R matches only CR, LF, or CRLF. The build- time - default can be overridden by the user of PCRE at runtime. On systems that - support it, "configure" can be used to override the default. */ -/* #undef BSR_ANYCRLF */ - -/* If you are compiling for a system that uses EBCDIC instead of ASCII - character codes, define this macro as 1. On systems that can use - "configure", this can be done via --enable-ebcdic. PCRE will then assume - that all input strings are in EBCDIC. If you do not define this macro, PCRE - will assume input strings are ASCII or UTF-8 Unicode. It is not possible to - build a version of PCRE that supports both EBCDIC and UTF-8. */ -/* #undef EBCDIC */ - -/* Define to 1 if you have the `bcopy' function. */ -#ifndef HAVE_BCOPY -#define HAVE_BCOPY 1 -#endif - -/* Define to 1 if you have the header file. */ -/* #undef HAVE_BITS_TYPE_TRAITS_H */ - -/* Define to 1 if you have the header file. */ -#ifndef HAVE_BZLIB_H -#define HAVE_BZLIB_H 1 -#endif - -/* Define to 1 if you have the header file. */ -#ifndef HAVE_DIRENT_H -#define HAVE_DIRENT_H 1 -#endif - -/* Define to 1 if you have the header file. */ -#ifndef HAVE_DLFCN_H -#define HAVE_DLFCN_H 1 -#endif - -/* Define to 1 if you have the header file. */ -#ifndef HAVE_INTTYPES_H -#define HAVE_INTTYPES_H 1 -#endif - -/* Define to 1 if you have the header file. */ -#ifndef HAVE_LIMITS_H -#define HAVE_LIMITS_H 1 -#endif - -/* Define to 1 if the system has the type `long long'. */ -#ifndef HAVE_LONG_LONG -#define HAVE_LONG_LONG 1 -#endif - -/* Define to 1 if you have the `memmove' function. */ -#ifndef HAVE_MEMMOVE -#define HAVE_MEMMOVE 1 -#endif - -/* Define to 1 if you have the header file. */ -#ifndef HAVE_MEMORY_H -#define HAVE_MEMORY_H 1 -#endif - -/* Define to 1 if you have the header file. */ -#ifndef HAVE_READLINE_HISTORY_H -#define HAVE_READLINE_HISTORY_H 1 -#endif - -/* Define to 1 if you have the header file. */ -#ifndef HAVE_READLINE_READLINE_H -#define HAVE_READLINE_READLINE_H 1 -#endif - -/* Define to 1 if you have the header file. */ -#ifndef HAVE_STDINT_H -#define HAVE_STDINT_H 1 -#endif - -/* Define to 1 if you have the header file. */ -#ifndef HAVE_STDLIB_H -#define HAVE_STDLIB_H 1 -#endif - -/* Define to 1 if you have the `strerror' function. */ -#ifndef HAVE_STRERROR -#define HAVE_STRERROR 1 -#endif - -/* Define to 1 if you have the header file. */ -#ifndef HAVE_STRING -#define HAVE_STRING 1 -#endif - -/* Define to 1 if you have the header file. */ -#ifndef HAVE_STRINGS_H -#define HAVE_STRINGS_H 1 -#endif - -/* Define to 1 if you have the header file. */ -#ifndef HAVE_STRING_H -#define HAVE_STRING_H 1 -#endif - -/* Define to 1 if you have the `strtoll' function. */ -/* #undef HAVE_STRTOLL */ - -/* Define to 1 if you have the `strtoq' function. */ -#ifndef HAVE_STRTOQ -#define HAVE_STRTOQ 1 -#endif - -/* Define to 1 if you have the header file. */ -#ifndef HAVE_SYS_STAT_H -#define HAVE_SYS_STAT_H 1 -#endif - -/* Define to 1 if you have the header file. */ -#ifndef HAVE_SYS_TYPES_H -#define HAVE_SYS_TYPES_H 1 -#endif - -/* Define to 1 if you have the header file. */ -/* #undef HAVE_TYPE_TRAITS_H */ - -/* Define to 1 if you have the header file. */ -#ifndef HAVE_UNISTD_H -#define HAVE_UNISTD_H 1 -#endif - -/* Define to 1 if the system has the type `unsigned long long'. */ -#ifndef HAVE_UNSIGNED_LONG_LONG -#define HAVE_UNSIGNED_LONG_LONG 1 -#endif - -/* Define to 1 if you have the header file. */ -/* #undef HAVE_WINDOWS_H */ - -/* Define to 1 if you have the header file. */ -#ifndef HAVE_ZLIB_H -#define HAVE_ZLIB_H 1 -#endif - -/* Define to 1 if you have the `_strtoi64' function. */ -/* #undef HAVE__STRTOI64 */ - -/* The value of LINK_SIZE determines the number of bytes used to store links - as offsets within the compiled regex. The default is 2, which allows for - compiled patterns up to 64K long. This covers the vast majority of cases. - However, PCRE can also be compiled to use 3 or 4 bytes instead. This allows - for longer patterns in extreme cases. On systems that support it, - "configure" can be used to override this default. */ -#ifndef LINK_SIZE -#define LINK_SIZE 2 -#endif - -/* The value of MATCH_LIMIT determines the default number of times the - internal match() function can be called during a single execution of - pcre_exec(). There is a runtime interface for setting a different limit. - The limit exists in order to catch runaway regular expressions that take - for ever to determine that they do not match. The default is set very large - so that it does not accidentally catch legitimate cases. On systems that - support it, "configure" can be used to override this default default. */ -#ifndef MATCH_LIMIT -#define MATCH_LIMIT 10000000 -#endif - -/* The above limit applies to all calls of match(), whether or not they - increase the recursion depth. In some environments it is desirable to limit - the depth of recursive calls of match() more strictly, in order to restrict - the maximum amount of stack (or heap, if NO_RECURSE is defined) that is - used. The value of MATCH_LIMIT_RECURSION applies only to recursive calls of - match(). To have any useful effect, it must be less than the value of - MATCH_LIMIT. The default is to use the same value as MATCH_LIMIT. There is - a runtime method for setting a different limit. On systems that support it, - "configure" can be used to override the default. */ -#ifndef MATCH_LIMIT_RECURSION -#define MATCH_LIMIT_RECURSION MATCH_LIMIT -#endif - -/* This limit is parameterized just in case anybody ever wants to change it. - Care must be taken if it is increased, because it guards against integer - overflow caused by enormously large patterns. */ -#ifndef MAX_NAME_COUNT -#define MAX_NAME_COUNT 10000 -#endif - -/* This limit is parameterized just in case anybody ever wants to change it. - Care must be taken if it is increased, because it guards against integer - overflow caused by enormously large patterns. */ -#ifndef MAX_NAME_SIZE -#define MAX_NAME_SIZE 32 -#endif - -/* The value of NEWLINE determines the newline character sequence. On systems - that support it, "configure" can be used to override the default, which is - 10. The possible values are 10 (LF), 13 (CR), 3338 (CRLF), -1 (ANY), or -2 - (ANYCRLF). */ -#ifndef NEWLINE -#define NEWLINE 10 -#endif - -/* PCRE uses recursive function calls to handle backtracking while matching. - This can sometimes be a problem on systems that have stacks of limited - size. Define NO_RECURSE to get a version that doesn't use recursion in the - match() function; instead it creates its own stack by steam using - pcre_recurse_malloc() to obtain memory from the heap. For more detail, see - the comments and other stuff just above the match() function. On systems - that support it, "configure" can be used to set this in the Makefile (use - --disable-stack-for-recursion). */ -/* #undef NO_RECURSE */ - -/* Name of package */ -#define PACKAGE "pcre" - -/* Define to the address where bug reports for this package should be sent. */ -#define PACKAGE_BUGREPORT "" - -/* Define to the full name of this package. */ -#define PACKAGE_NAME "PCRE" - -/* Define to the full name and version of this package. */ -#define PACKAGE_STRING "PCRE 7.9" - -/* Define to the one symbol short name of this package. */ -#define PACKAGE_TARNAME "pcre" - -/* Define to the version of this package. */ -#define PACKAGE_VERSION "7.9" - - -/* If you are compiling for a system other than a Unix-like system or - Win32, and it needs some magic to be inserted before the definition - of a function that is exported by the library, define this macro to - contain the relevant magic. If you do not define this macro, it - defaults to "extern" for a C compiler and "extern C" for a C++ - compiler on non-Win32 systems. This macro apears at the start of - every exported function that is part of the external API. It does - not appear on functions that are "external" in the C sense, but - which are internal to the library. */ -/* #undef PCRE_EXP_DEFN */ - -/* Define if linking statically (TODO: make nice with Libtool) */ -/* #undef PCRE_STATIC */ - -/* When calling PCRE via the POSIX interface, additional working storage is - required for holding the pointers to capturing substrings because PCRE - requires three integers per substring, whereas the POSIX interface provides - only two. If the number of expected substrings is small, the wrapper - function uses space on the stack, because this is faster than using - malloc() for each call. The threshold above which the stack is no longer - used is defined by POSIX_MALLOC_THRESHOLD. On systems that support it, - "configure" can be used to override this default. */ -#ifndef POSIX_MALLOC_THRESHOLD -#define POSIX_MALLOC_THRESHOLD 10 -#endif - -/* Define to 1 if you have the ANSI C header files. */ -#ifndef STDC_HEADERS -#define STDC_HEADERS 1 -#endif - -/* Define to allow pcregrep to be linked with libbz2, so that it is able to - handle .bz2 files. */ -/* #undef SUPPORT_LIBBZ2 */ - -/* Define to allow pcretest to be linked with libreadline. */ -/* #undef SUPPORT_LIBREADLINE */ - -/* Define to allow pcregrep to be linked with libz, so that it is able to - handle .gz files. */ -/* #undef SUPPORT_LIBZ */ - -/* Define to enable support for Unicode properties */ -/* #undef SUPPORT_UCP */ - -/* Define to enable support for the UTF-8 Unicode encoding. This will work - even in an EBCDIC environment, but it is incompatible with the EBCDIC - macro. That is, PCRE can support *either* EBCDIC code *or* ASCII/UTF-8, but - not both at once. */ -/* #undef SUPPORT_UTF8 */ - -/* Version number of package */ -#ifndef VERSION -#define VERSION "7.9" -#endif - -/* Define to empty if `const' does not conform to ANSI C. */ -/* #undef const */ - -/* Define to `unsigned int' if does not define. */ -/* #undef size_t */ diff --git a/libs/pcre/configure.ac b/libs/pcre/configure.ac deleted file mode 100644 index cc01267b4d..0000000000 --- a/libs/pcre/configure.ac +++ /dev/null @@ -1,691 +0,0 @@ -dnl Process this file with autoconf to produce a configure script. - -dnl NOTE FOR MAINTAINERS: Do not use major or minor version numbers with -dnl leading zeros, because they may be treated as octal constants. The -dnl PCRE_PRERELEASE feature is for identifying release candidates. It might -dnl be defined as -RC2, for example. For real releases, it should be defined -dnl empty. - -m4_define(pcre_major, [7]) -m4_define(pcre_minor, [9]) -m4_define(pcre_prerelease, []) -m4_define(pcre_date, [2009-04-11]) - -# Libtool shared library interface versions (current:revision:age) -m4_define(libpcre_version, [0:1:0]) -m4_define(libpcreposix_version, [0:0:0]) -m4_define(libpcrecpp_version, [0:0:0]) - -AC_PREREQ(2.57) -AC_INIT(PCRE, pcre_major.pcre_minor[]pcre_prerelease, , pcre) -AC_CONFIG_SRCDIR([pcre.h.in]) -AM_INIT_AUTOMAKE([dist-bzip2 dist-zip]) -AC_CONFIG_HEADERS(config.h) - -CFLAGS="$CFLAGS $CONFIGURE_CFLAGS" -CXXFLAGS="$CXXFLAGS $CONFIGURE_CXXFLAGS" -LDFLAGS="$LDFLAGS $CONFIGURE_LDFLAGS" - -# The default CFLAGS and CXXFLAGS in Autoconf are "-g -O2" for gcc and just -# "-g" for any other compiler. There doesn't seem to be a standard way of -# getting rid of the -g (which I don't think is needed for a production -# library). This fudge seems to achieve the necessary. First, we remember the -# externally set values of CFLAGS and CXXFLAGS. Then call the AC_PROG_CC and -# AC_PROG_CXX macros to find the compilers - if CFLAGS and CXXFLAGS are not -# set, they will be set to Autoconf's defaults. Afterwards, if the original -# values were not set, remove the -g from the Autoconf defaults. -# (PH 02-May-07) - -remember_set_CFLAGS="$CFLAGS" -remember_set_CXXFLAGS="$CXXFLAGS" - -AC_PROG_CC -AC_PROG_CXX - -if test "x$remember_set_CFLAGS" = "x" -then - if test "$CFLAGS" = "-g -O2" - then - CFLAGS="-O2" - elif test "$CFLAGS" = "-g" - then - CFLAGS="" - fi -fi - -if test "x$remember_set_CXXFLAGS" = "x" -then - if test "$CXXFLAGS" = "-g -O2" - then - CXXFLAGS="-O2" - elif test "$CXXFLAGS" = "-g" - then - CXXFLAGS="" - fi -fi - -# AC_PROG_CXX will return "g++" even if no c++ compiler is installed. -# Check for that case, and just disable c++ code if g++ doesn't run. -AC_LANG_PUSH(C++) -AC_COMPILE_IFELSE([AC_LANG_PROGRAM([[]],[[]])],, CXX=""; CXXCP=""; CXXFLAGS="") -AC_LANG_POP - -AC_PROG_INSTALL -AC_LIBTOOL_WIN32_DLL -AC_PROG_LIBTOOL -AC_PROG_LN_S - -PCRE_MAJOR="pcre_major" -PCRE_MINOR="pcre_minor" -PCRE_PRERELEASE="pcre_prerelease" -PCRE_DATE="pcre_date" - -AC_SUBST(PCRE_MAJOR) -AC_SUBST(PCRE_MINOR) -AC_SUBST(PCRE_PRERELEASE) -AC_SUBST(PCRE_DATE) - -# Set a more sensible default value for $(htmldir). -if test "x$htmldir" = 'x${docdir}' -then - htmldir='${docdir}/html' -fi - -# Handle --disable-cpp -AC_ARG_ENABLE(cpp, - AS_HELP_STRING([--disable-cpp], - [disable C++ support]), - , enable_cpp=yes) - -# Handle --enable-rebuild-chartables -AC_ARG_ENABLE(rebuild-chartables, - AS_HELP_STRING([--enable-rebuild-chartables], - [rebuild character tables in current locale]), - , enable_rebuild_chartables=no) - -# Handle --enable-utf8 (disabled by default) -AC_ARG_ENABLE(utf8, - AS_HELP_STRING([--enable-utf8], - [enable UTF-8 support (incompatible with --enable-ebcdic)]), - , enable_utf8=unset) - -# Handle --enable-unicode-properties -AC_ARG_ENABLE(unicode-properties, - AS_HELP_STRING([--enable-unicode-properties], - [enable Unicode properties support (implies --enable-utf8)]), - , enable_unicode_properties=no) - -# Handle --enable-newline=NL -dnl AC_ARG_ENABLE(newline, -dnl AS_HELP_STRING([--enable-newline=NL], -dnl [use NL as newline (lf, cr, crlf, anycrlf, any; default=lf)]), -dnl , enable_newline=lf) - -# Separate newline options -ac_pcre_newline=lf -AC_ARG_ENABLE(newline-is-cr, - AS_HELP_STRING([--enable-newline-is-cr], - [use CR as newline character]), - ac_pcre_newline=cr) -AC_ARG_ENABLE(newline-is-lf, - AS_HELP_STRING([--enable-newline-is-lf], - [use LF as newline character (default)]), - ac_pcre_newline=lf) -AC_ARG_ENABLE(newline-is-crlf, - AS_HELP_STRING([--enable-newline-is-crlf], - [use CRLF as newline sequence]), - ac_pcre_newline=crlf) -AC_ARG_ENABLE(newline-is-anycrlf, - AS_HELP_STRING([--enable-newline-is-anycrlf], - [use CR, LF, or CRLF as newline sequence]), - ac_pcre_newline=anycrlf) -AC_ARG_ENABLE(newline-is-any, - AS_HELP_STRING([--enable-newline-is-any], - [use any valid Unicode newline sequence]), - ac_pcre_newline=any) -enable_newline="$ac_pcre_newline" - -# Handle --enable-bsr-anycrlf -AC_ARG_ENABLE(bsr-anycrlf, - AS_HELP_STRING([--enable-bsr-anycrlf], - [\R matches only CR, LF, CRLF by default]), - , enable_bsr_anycrlf=no) - -# Handle --enable-ebcdic -AC_ARG_ENABLE(ebcdic, - AS_HELP_STRING([--enable-ebcdic], - [assume EBCDIC coding rather than ASCII; incompatible with --enable-utf8; use only in (uncommon) EBCDIC environments; it implies --enable-rebuild-chartables]), - , enable_ebcdic=no) - -# Handle --disable-stack-for-recursion -AC_ARG_ENABLE(stack-for-recursion, - AS_HELP_STRING([--disable-stack-for-recursion], - [don't use stack recursion when matching]), - , enable_stack_for_recursion=yes) - -# Handle --enable-pcregrep-libz -AC_ARG_ENABLE(pcregrep-libz, - AS_HELP_STRING([--enable-pcregrep-libz], - [link pcregrep with libz to handle .gz files]), - , enable_pcregrep_libz=no) - -# Handle --enable-pcregrep-libbz2 -AC_ARG_ENABLE(pcregrep-libbz2, - AS_HELP_STRING([--enable-pcregrep-libbz2], - [link pcregrep with libbz2 to handle .bz2 files]), - , enable_pcregrep_libbz2=no) - -# Handle --enable-pcretest-libreadline -AC_ARG_ENABLE(pcretest-libreadline, - AS_HELP_STRING([--enable-pcretest-libreadline], - [link pcretest with libreadline]), - , enable_pcretest_libreadline=no) - -# Handle --with-posix-malloc-threshold=NBYTES -AC_ARG_WITH(posix-malloc-threshold, - AS_HELP_STRING([--with-posix-malloc-threshold=NBYTES], - [threshold for POSIX malloc usage (default=10)]), - , with_posix_malloc_threshold=10) - -# Handle --with-link-size=N -AC_ARG_WITH(link-size, - AS_HELP_STRING([--with-link-size=N], - [internal link size (2, 3, or 4 allowed; default=2)]), - , with_link_size=2) - -# Handle --with-match-limit=N -AC_ARG_WITH(match-limit, - AS_HELP_STRING([--with-match-limit=N], - [default limit on internal looping (default=10000000)]), - , with_match_limit=10000000) - -# Handle --with-match-limit_recursion=N -# -# Note: In config.h, the default is to define MATCH_LIMIT_RECURSION -# symbolically as MATCH_LIMIT, which in turn is defined to be some numeric -# value (e.g. 10000000). MATCH_LIMIT_RECURSION can otherwise be set to some -# different numeric value (or even the same numeric value as MATCH_LIMIT, -# though no longer defined in terms of the latter). -# -AC_ARG_WITH(match-limit-recursion, - AS_HELP_STRING([--with-match-limit-recursion=N], - [default limit on internal recursion (default=MATCH_LIMIT)]), - , with_match_limit_recursion=MATCH_LIMIT) - -# Make sure that if enable_unicode_properties was set, that UTF-8 support -# is enabled. -# -if test "x$enable_unicode_properties" = "xyes" -then - if test "x$enable_utf8" = "xno" - then - AC_MSG_ERROR([support for Unicode properties requires UTF-8 support]) - fi - enable_utf8=yes -fi - -if test "x$enable_utf8" = "xunset" -then - enable_utf8=no -fi - -# Make sure that if enable_ebcdic is set, rebuild_chartables is also enabled. -# Also check that UTF-8 support is not requested, because PCRE cannot handle -# EBCDIC and UTF-8 in the same build. To do so it would need to use different -# character constants depending on the mode. -# -if test "x$enable_ebcdic" = "xyes" -then - enable_rebuild_chartables=yes - if test "x$enable_utf8" = "xyes" - then - AC_MSG_ERROR([support for EBCDIC and UTF-8 cannot be enabled at the same time]) - fi -fi - -# Convert the newline identifier into the appropriate integer value. -case "$enable_newline" in - lf) ac_pcre_newline_value=10 ;; - cr) ac_pcre_newline_value=13 ;; - crlf) ac_pcre_newline_value=3338 ;; - anycrlf) ac_pcre_newline_value=-2 ;; - any) ac_pcre_newline_value=-1 ;; - *) - AC_MSG_ERROR([invalid argument \"$enable_newline\" to --enable-newline option]) - ;; -esac - -# Check argument to --with-link-size -case "$with_link_size" in - 2|3|4) ;; - *) - AC_MSG_ERROR([invalid argument \"$with_link_size\" to --with-link-size option]) - ;; -esac - -AH_TOP([ -/* On Unix-like systems config.h.in is converted by "configure" into config.h. -Some other environments also support the use of "configure". PCRE is written in -Standard C, but there are a few non-standard things it can cope with, allowing -it to run on SunOS4 and other "close to standard" systems. - -If you are going to build PCRE "by hand" on a system without "configure" you -should copy the distributed config.h.generic to config.h, and then set up the -macro definitions the way you need them. You must then add -DHAVE_CONFIG_H to -all of your compile commands, so that config.h is included at the start of -every source. - -Alternatively, you can avoid editing by using -D on the compiler command line -to set the macro values. In this case, you do not have to set -DHAVE_CONFIG_H. - -PCRE uses memmove() if HAVE_MEMMOVE is set to 1; otherwise it uses bcopy() if -HAVE_BCOPY is set to 1. If your system has neither bcopy() nor memmove(), set -them both to 0; an emulation function will be used. */]) - -AC_DEFUN([AX_COMPILER_VENDOR], -[ -AC_CACHE_CHECK([for _AC_LANG compiler vendor], ax_cv_[]_AC_LANG_ABBREV[]_compiler_vendor, - [ax_cv_[]_AC_LANG_ABBREV[]_compiler_vendor=unknown - # note: don't check for gcc first since some other compilers define __GNUC__ - for ventest in intel:__ICC,__ECC,__INTEL_COMPILER ibm:__xlc__,__xlC__,__IBMC__,__IBMCPP__ gnu:__GNUC__ sun:__SUNPRO_C,__SUNPRO_CC hp:__HP_cc,__HP_aCC dec:__DECC,__DECCXX,__DECC_VER,__DECCXX_VER borland:__BORLANDC__,__TURBOC__ comeau:__COMO__ cray:_CRAYC kai:__KCC lcc:__LCC__ metrowerks:__MWERKS__ sgi:__sgi,sgi microsoft:_MSC_VER watcom:__WATCOMC__ portland:__PGI; do - vencpp="defined("`echo $ventest | cut -d: -f2 | sed 's/,/) || defined(/g'`")" - AC_COMPILE_IFELSE([AC_LANG_PROGRAM(,[ -#if !($vencpp) - thisisanerror; -#endif -])], [ax_cv_]_AC_LANG_ABBREV[_compiler_vendor=`echo $ventest | cut -d: -f1`; break]) - done - ]) -]) - -AX_COMPILER_VENDOR - -# Enable 64 bit build -AC_ARG_ENABLE(64, -[AC_HELP_STRING([--enable-64],[build with 64 bit support])],[enable_64="$enable_64"],[enable_64="no"]) - -if test "x${ax_cv_c_compiler_vendor}" = "xsun" ; then - if test "${enable_64}" = "yes"; then - CFLAGS="$CFLAGS -m64" - CXXFLAGS="$CXXFLAGS -m64" - fi -fi - -# Checks for header files. -AC_HEADER_STDC -AC_CHECK_HEADERS(limits.h sys/types.h sys/stat.h dirent.h windows.h) - -# The files below are C++ header files. -pcre_have_type_traits="0" -pcre_have_bits_type_traits="0" -if test "x$enable_cpp" = "xyes" -a -n "$CXX" -then -AC_LANG_PUSH(C++) - -# Older versions of pcre defined pcrecpp::no_arg, but in new versions -# it's called pcrecpp::RE::no_arg. For backwards ABI compatibility, -# we want to make one an alias for the other. Different systems do -# this in different ways. Some systems, for instance, can do it via -# a linker flag: -alias (for os x 10.5) or -i (for os x <=10.4). -OLD_LDFLAGS="$LDFLAGS" -for flag in "-alias,__ZN7pcrecpp2RE6no_argE,__ZN7pcrecpp6no_argE" \ - "-i__ZN7pcrecpp6no_argE:__ZN7pcrecpp2RE6no_argE"; do - AC_MSG_CHECKING([for alias support in the linker]) - LDFLAGS="$OLD_LDFLAGS -Wl,$flag" - # We try to run the linker with this new ld flag. If the link fails, - # we give up and remove the new flag from LDFLAGS. - AC_LINK_IFELSE([AC_LANG_PROGRAM([[namespace pcrecpp { - class RE { static int no_arg; }; - int RE::no_arg; - }]], - [[]])], - [AC_MSG_RESULT([yes]); - EXTRA_LIBPCRECPP_LDFLAGS="$EXTRA_LIBPCRECPP_LDFLAGS -Wl,$flag"; - break;], - AC_MSG_RESULT([no])) -done -LDFLAGS="$OLD_LDFLAGS" - -# We could be more clever here, given we're doing AC_SUBST with this -# (eg set a var to be the name of the include file we want). But we're not -# so it's easy to change back to 'regular' autoconf vars if we needed to. -AC_CHECK_HEADERS(string, [pcre_have_cpp_headers="1"], - [pcre_have_cpp_headers="0"]) -AC_CHECK_HEADERS(bits/type_traits.h, [pcre_have_bits_type_traits="1"], - [pcre_have_bits_type_traits="0"]) -AC_CHECK_HEADERS(type_traits.h, [pcre_have_type_traits="1"], - [pcre_have_type_traits="0"]) - -AC_LANG_POP -fi -# Using AC_SUBST eliminates the need to include config.h in a public .h file -AC_SUBST(pcre_have_type_traits) -AC_SUBST(pcre_have_bits_type_traits) - -# Conditional compilation -AM_CONDITIONAL(WITH_PCRE_CPP, test "x$enable_cpp" = "xyes") -AM_CONDITIONAL(WITH_REBUILD_CHARTABLES, test "x$enable_rebuild_chartables" = "xyes") - -# Checks for typedefs, structures, and compiler characteristics. - -AC_C_CONST -AC_TYPE_SIZE_T - -pcre_have_strotolonglong=0 -AC_CHECK_FUNCS(strtoq strtoll _strtoi64, [pcre_have_strotolonglong="1"; break]) -# If we can't convert a string to a long long, pretend we don't even -# have a long long. -if test $pcre_have_strotolonglong = "0"; then - pcre_have_long_long="0" - pcre_have_ulong_long="0" -else - AC_CHECK_TYPES([long long], - [pcre_have_long_long="1"], - [pcre_have_long_long="0"]) - AC_CHECK_TYPES([unsigned long long], - [pcre_have_ulong_long="1"], - [pcre_have_ulong_long="0"]) -fi -AC_SUBST(pcre_have_long_long) -AC_SUBST(pcre_have_ulong_long) - -# Checks for library functions. - -AC_CHECK_FUNCS(bcopy memmove strerror) - -# Check for the availability of libz (aka zlib) - -AC_CHECK_HEADERS([zlib.h], [HAVE_ZLIB_H=1]) -AC_CHECK_LIB([z], [gzopen], [HAVE_LIBZ=1]) - -# Check for the availability of libbz2 - -AC_CHECK_HEADERS([bzlib.h], [HAVE_BZLIB_H=1]) -AC_CHECK_LIB([bz2], [BZ2_bzopen], [HAVE_LIBBZ2=1]) - -# Check for the availabiity of libreadline - -AC_CHECK_HEADERS([readline/readline.h], [HAVE_READLINE_H=1]) -AC_CHECK_HEADERS([readline/history.h], [HAVE_HISTORY_H=1]) -AC_CHECK_LIB([readline], [readline], [HAVE_LIB_READLINE=1]) - -# This facilitates -ansi builds under Linux -dnl AC_DEFINE([_GNU_SOURCE], [], [Enable GNU extensions in glibc]) - -if test "x$enable_shared" = "xno" ; then - AC_DEFINE([PCRE_STATIC], [1], [ - Define if linking statically (TODO: make nice with Libtool)]) -fi - -# Here is where pcre specific defines are handled - -if test "$enable_utf8" = "yes"; then - AC_DEFINE([SUPPORT_UTF8], [], [ - Define to enable support for the UTF-8 Unicode encoding. This will - work even in an EBCDIC environment, but it is incompatible with - the EBCDIC macro. That is, PCRE can support *either* EBCDIC code - *or* ASCII/UTF-8, but not both at once.]) -fi - -if test "$enable_unicode_properties" = "yes"; then - AC_DEFINE([SUPPORT_UCP], [], [ - Define to enable support for Unicode properties]) -fi - -if test "$enable_stack_for_recursion" = "no"; then - AC_DEFINE([NO_RECURSE], [], [ - PCRE uses recursive function calls to handle backtracking while - matching. This can sometimes be a problem on systems that have - stacks of limited size. Define NO_RECURSE to get a version that - doesn't use recursion in the match() function; instead it creates - its own stack by steam using pcre_recurse_malloc() to obtain memory - from the heap. For more detail, see the comments and other stuff - just above the match() function. On systems that support it, - "configure" can be used to set this in the Makefile - (use --disable-stack-for-recursion).]) -fi - -if test "$enable_pcregrep_libz" = "yes"; then - AC_DEFINE([SUPPORT_LIBZ], [], [ - Define to allow pcregrep to be linked with libz, so that it is - able to handle .gz files.]) -fi - -if test "$enable_pcregrep_libbz2" = "yes"; then - AC_DEFINE([SUPPORT_LIBBZ2], [], [ - Define to allow pcregrep to be linked with libbz2, so that it is - able to handle .bz2 files.]) -fi - -if test "$enable_pcretest_libreadline" = "yes"; then - AC_DEFINE([SUPPORT_LIBREADLINE], [], [ - Define to allow pcretest to be linked with libreadline.]) -fi - -AC_DEFINE_UNQUOTED([NEWLINE], [$ac_pcre_newline_value], [ - The value of NEWLINE determines the newline character sequence. On - systems that support it, "configure" can be used to override the - default, which is 10. The possible values are 10 (LF), 13 (CR), - 3338 (CRLF), -1 (ANY), or -2 (ANYCRLF).]) - -if test "$enable_bsr_anycrlf" = "yes"; then - AC_DEFINE([BSR_ANYCRLF], [], [ - By default, the \R escape sequence matches any Unicode line ending - character or sequence of characters. If BSR_ANYCRLF is defined, this is - changed so that backslash-R matches only CR, LF, or CRLF. The build- - time default can be overridden by the user of PCRE at runtime. On - systems that support it, "configure" can be used to override the - default.]) -fi - -AC_DEFINE_UNQUOTED([LINK_SIZE], [$with_link_size], [ - The value of LINK_SIZE determines the number of bytes used to store - links as offsets within the compiled regex. The default is 2, which - allows for compiled patterns up to 64K long. This covers the vast - majority of cases. However, PCRE can also be compiled to use 3 or 4 - bytes instead. This allows for longer patterns in extreme cases. On - systems that support it, "configure" can be used to override this default.]) - -AC_DEFINE_UNQUOTED([POSIX_MALLOC_THRESHOLD], [$with_posix_malloc_threshold], [ - When calling PCRE via the POSIX interface, additional working storage - is required for holding the pointers to capturing substrings because - PCRE requires three integers per substring, whereas the POSIX - interface provides only two. If the number of expected substrings is - small, the wrapper function uses space on the stack, because this is - faster than using malloc() for each call. The threshold above which - the stack is no longer used is defined by POSIX_MALLOC_THRESHOLD. On - systems that support it, "configure" can be used to override this - default.]) - -AC_DEFINE_UNQUOTED([MATCH_LIMIT], [$with_match_limit], [ - The value of MATCH_LIMIT determines the default number of times the - internal match() function can be called during a single execution of - pcre_exec(). There is a runtime interface for setting a different - limit. The limit exists in order to catch runaway regular - expressions that take for ever to determine that they do not match. - The default is set very large so that it does not accidentally catch - legitimate cases. On systems that support it, "configure" can be - used to override this default default.]) - -AC_DEFINE_UNQUOTED([MATCH_LIMIT_RECURSION], [$with_match_limit_recursion], [ - The above limit applies to all calls of match(), whether or not they - increase the recursion depth. In some environments it is desirable - to limit the depth of recursive calls of match() more strictly, in - order to restrict the maximum amount of stack (or heap, if - NO_RECURSE is defined) that is used. The value of - MATCH_LIMIT_RECURSION applies only to recursive calls of match(). To - have any useful effect, it must be less than the value of - MATCH_LIMIT. The default is to use the same value as MATCH_LIMIT. - There is a runtime method for setting a different limit. On systems - that support it, "configure" can be used to override the default.]) - -AC_DEFINE([MAX_NAME_SIZE], [32], [ - This limit is parameterized just in case anybody ever wants to - change it. Care must be taken if it is increased, because it guards - against integer overflow caused by enormously large patterns.]) - -AC_DEFINE([MAX_NAME_COUNT], [10000], [ - This limit is parameterized just in case anybody ever wants to - change it. Care must be taken if it is increased, because it guards - against integer overflow caused by enormously large patterns.]) - -AH_VERBATIM([PCRE_EXP_DEFN], [ -/* If you are compiling for a system other than a Unix-like system or - Win32, and it needs some magic to be inserted before the definition - of a function that is exported by the library, define this macro to - contain the relevant magic. If you do not define this macro, it - defaults to "extern" for a C compiler and "extern C" for a C++ - compiler on non-Win32 systems. This macro apears at the start of - every exported function that is part of the external API. It does - not appear on functions that are "external" in the C sense, but - which are internal to the library. */ -#undef PCRE_EXP_DEFN]) - -if test "$enable_ebcdic" = "yes"; then - AC_DEFINE_UNQUOTED([EBCDIC], [], [ - If you are compiling for a system that uses EBCDIC instead of ASCII - character codes, define this macro as 1. On systems that can use - "configure", this can be done via --enable-ebcdic. PCRE will then - assume that all input strings are in EBCDIC. If you do not define - this macro, PCRE will assume input strings are ASCII or UTF-8 Unicode. - It is not possible to build a version of PCRE that supports both - EBCDIC and UTF-8.]) -fi - -# Platform specific issues -NO_UNDEFINED= -EXPORT_ALL_SYMBOLS= -case $host_os in - cygwin* | mingw* ) - if test X"$enable_shared" = Xyes; then - NO_UNDEFINED="-no-undefined" - EXPORT_ALL_SYMBOLS="-Wl,--export-all-symbols" - fi - ;; -esac - -# The extra LDFLAGS for each particular library -# (Note: The libpcre*_version bits are m4 variables, assigned above) - -EXTRA_LIBPCRE_LDFLAGS="$EXTRA_LIBPCRE_LDFLAGS \ - $NO_UNDEFINED -version-info libpcre_version" - -EXTRA_LIBPCREPOSIX_LDFLAGS="$EXTRA_LIBPCREPOSIX_LDFLAGS \ - $NO_UNDEFINED -version-info libpcreposix_version" - -EXTRA_LIBPCRECPP_LDFLAGS="$EXTRA_LIBPCRECPP_LDFLAGS \ - $NO_UNDEFINED -version-info libpcrecpp_version \ - $EXPORT_ALL_SYMBOLS" - -AC_SUBST(EXTRA_LIBPCRE_LDFLAGS) -AC_SUBST(EXTRA_LIBPCREPOSIX_LDFLAGS) -AC_SUBST(EXTRA_LIBPCRECPP_LDFLAGS) - -# When we run 'make distcheck', use these arguments. -DISTCHECK_CONFIGURE_FLAGS="--enable-cpp --enable-unicode-properties" -AC_SUBST(DISTCHECK_CONFIGURE_FLAGS) - -# Check that, if --enable-pcregrep-libz or --enable-pcregrep-libbz2 is -# specified, the relevant library is available. - -if test "$enable_pcregrep_libz" = "yes"; then - if test "$HAVE_ZLIB_H" != "1"; then - echo "** Cannot --enable-pcregrep-libz because zlib.h was not found" - exit 1 - fi - if test "$HAVE_LIBZ" != "1"; then - echo "** Cannot --enable-pcregrep-libz because libz was not found" - exit 1 - fi - LIBZ="-lz" -fi -AC_SUBST(LIBZ) - -if test "$enable_pcregrep_libbz2" = "yes"; then - if test "$HAVE_BZLIB_H" != "1"; then - echo "** Cannot --enable-pcregrep-libbz2 because bzlib.h was not found" - exit 1 - fi - if test "$HAVE_LIBBZ2" != "1"; then - echo "** Cannot --enable-pcregrep-libbz2 because libbz2 was not found" - exit 1 - fi - LIBBZ2="-lbz2" -fi -AC_SUBST(LIBBZ2) - -# Similarly for --enable-pcretest-readline - -if test "$enable_pcretest_libreadline" = "yes"; then - if test "$HAVE_READLINE_H" != "1"; then - echo "** Cannot --enable-pcretest-readline because readline/readline.h was not found." - exit 1 - fi - if test "$HAVE_HISTORY_H" != "1"; then - echo "** Cannot --enable-pcretest-readline because readline/history.h was not found." - exit 1 - fi - LIBREADLINE="-lreadline" -fi -AC_SUBST(LIBREADLINE) - -# Produce these files, in addition to config.h. -AC_CONFIG_FILES( - Makefile - libpcre.pc - libpcrecpp.pc - pcre-config - pcre.h - pcre_stringpiece.h - pcrecpparg.h -) - -# Make the generated script files executable. -AC_CONFIG_COMMANDS([script-chmod], [chmod a+x pcre-config]) - -# Make sure that pcre_chartables.c is removed in case the method for -# creating it was changed by reconfiguration. -AC_CONFIG_COMMANDS([delete-old-chartables], [rm -f pcre_chartables.c]) - -AC_OUTPUT - -# Print out a nice little message after configure is run displaying your -# chosen options. - -cat </dev/null ) || srcpath="." -$srcpath/configure "$@" --disable-shared --with-pic --disable-cpp - diff --git a/libs/pcre/depcomp b/libs/pcre/depcomp deleted file mode 100755 index e5f9736c72..0000000000 --- a/libs/pcre/depcomp +++ /dev/null @@ -1,589 +0,0 @@ -#! /bin/sh -# depcomp - compile a program generating dependencies as side-effects - -scriptversion=2007-03-29.01 - -# Copyright (C) 1999, 2000, 2003, 2004, 2005, 2006, 2007 Free Software -# Foundation, Inc. - -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License as published by -# the Free Software Foundation; either version 2, or (at your option) -# any later version. - -# This program is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -# GNU General Public License for more details. - -# You should have received a copy of the GNU General Public License -# along with this program; if not, write to the Free Software -# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA -# 02110-1301, USA. - -# As a special exception to the GNU General Public License, if you -# distribute this file as part of a program that contains a -# configuration script generated by Autoconf, you may include it under -# the same distribution terms that you use for the rest of that program. - -# Originally written by Alexandre Oliva . - -case $1 in - '') - echo "$0: No command. Try \`$0 --help' for more information." 1>&2 - exit 1; - ;; - -h | --h*) - cat <<\EOF -Usage: depcomp [--help] [--version] PROGRAM [ARGS] - -Run PROGRAMS ARGS to compile a file, generating dependencies -as side-effects. - -Environment variables: - depmode Dependency tracking mode. - source Source file read by `PROGRAMS ARGS'. - object Object file output by `PROGRAMS ARGS'. - DEPDIR directory where to store dependencies. - depfile Dependency file to output. - tmpdepfile Temporary file to use when outputing dependencies. - libtool Whether libtool is used (yes/no). - -Report bugs to . -EOF - exit $? - ;; - -v | --v*) - echo "depcomp $scriptversion" - exit $? - ;; -esac - -if test -z "$depmode" || test -z "$source" || test -z "$object"; then - echo "depcomp: Variables source, object and depmode must be set" 1>&2 - exit 1 -fi - -# Dependencies for sub/bar.o or sub/bar.obj go into sub/.deps/bar.Po. -depfile=${depfile-`echo "$object" | - sed 's|[^\\/]*$|'${DEPDIR-.deps}'/&|;s|\.\([^.]*\)$|.P\1|;s|Pobj$|Po|'`} -tmpdepfile=${tmpdepfile-`echo "$depfile" | sed 's/\.\([^.]*\)$/.T\1/'`} - -rm -f "$tmpdepfile" - -# Some modes work just like other modes, but use different flags. We -# parameterize here, but still list the modes in the big case below, -# to make depend.m4 easier to write. Note that we *cannot* use a case -# here, because this file can only contain one case statement. -if test "$depmode" = hp; then - # HP compiler uses -M and no extra arg. - gccflag=-M - depmode=gcc -fi - -if test "$depmode" = dashXmstdout; then - # This is just like dashmstdout with a different argument. - dashmflag=-xM - depmode=dashmstdout -fi - -case "$depmode" in -gcc3) -## gcc 3 implements dependency tracking that does exactly what -## we want. Yay! Note: for some reason libtool 1.4 doesn't like -## it if -MD -MP comes after the -MF stuff. Hmm. -## Unfortunately, FreeBSD c89 acceptance of flags depends upon -## the command line argument order; so add the flags where they -## appear in depend2.am. Note that the slowdown incurred here -## affects only configure: in makefiles, %FASTDEP% shortcuts this. - for arg - do - case $arg in - -c) set fnord "$@" -MT "$object" -MD -MP -MF "$tmpdepfile" "$arg" ;; - *) set fnord "$@" "$arg" ;; - esac - shift # fnord - shift # $arg - done - "$@" - stat=$? - if test $stat -eq 0; then : - else - rm -f "$tmpdepfile" - exit $stat - fi - mv "$tmpdepfile" "$depfile" - ;; - -gcc) -## There are various ways to get dependency output from gcc. Here's -## why we pick this rather obscure method: -## - Don't want to use -MD because we'd like the dependencies to end -## up in a subdir. Having to rename by hand is ugly. -## (We might end up doing this anyway to support other compilers.) -## - The DEPENDENCIES_OUTPUT environment variable makes gcc act like -## -MM, not -M (despite what the docs say). -## - Using -M directly means running the compiler twice (even worse -## than renaming). - if test -z "$gccflag"; then - gccflag=-MD, - fi - "$@" -Wp,"$gccflag$tmpdepfile" - stat=$? - if test $stat -eq 0; then : - else - rm -f "$tmpdepfile" - exit $stat - fi - rm -f "$depfile" - echo "$object : \\" > "$depfile" - alpha=ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz -## The second -e expression handles DOS-style file names with drive letters. - sed -e 's/^[^:]*: / /' \ - -e 's/^['$alpha']:\/[^:]*: / /' < "$tmpdepfile" >> "$depfile" -## This next piece of magic avoids the `deleted header file' problem. -## The problem is that when a header file which appears in a .P file -## is deleted, the dependency causes make to die (because there is -## typically no way to rebuild the header). We avoid this by adding -## dummy dependencies for each header file. Too bad gcc doesn't do -## this for us directly. - tr ' ' ' -' < "$tmpdepfile" | -## Some versions of gcc put a space before the `:'. On the theory -## that the space means something, we add a space to the output as -## well. -## Some versions of the HPUX 10.20 sed can't process this invocation -## correctly. Breaking it into two sed invocations is a workaround. - sed -e 's/^\\$//' -e '/^$/d' -e '/:$/d' | sed -e 's/$/ :/' >> "$depfile" - rm -f "$tmpdepfile" - ;; - -hp) - # This case exists only to let depend.m4 do its work. It works by - # looking at the text of this script. This case will never be run, - # since it is checked for above. - exit 1 - ;; - -sgi) - if test "$libtool" = yes; then - "$@" "-Wp,-MDupdate,$tmpdepfile" - else - "$@" -MDupdate "$tmpdepfile" - fi - stat=$? - if test $stat -eq 0; then : - else - rm -f "$tmpdepfile" - exit $stat - fi - rm -f "$depfile" - - if test -f "$tmpdepfile"; then # yes, the sourcefile depend on other files - echo "$object : \\" > "$depfile" - - # Clip off the initial element (the dependent). Don't try to be - # clever and replace this with sed code, as IRIX sed won't handle - # lines with more than a fixed number of characters (4096 in - # IRIX 6.2 sed, 8192 in IRIX 6.5). We also remove comment lines; - # the IRIX cc adds comments like `#:fec' to the end of the - # dependency line. - tr ' ' ' -' < "$tmpdepfile" \ - | sed -e 's/^.*\.o://' -e 's/#.*$//' -e '/^$/ d' | \ - tr ' -' ' ' >> $depfile - echo >> $depfile - - # The second pass generates a dummy entry for each header file. - tr ' ' ' -' < "$tmpdepfile" \ - | sed -e 's/^.*\.o://' -e 's/#.*$//' -e '/^$/ d' -e 's/$/:/' \ - >> $depfile - else - # The sourcefile does not contain any dependencies, so just - # store a dummy comment line, to avoid errors with the Makefile - # "include basename.Plo" scheme. - echo "#dummy" > "$depfile" - fi - rm -f "$tmpdepfile" - ;; - -aix) - # The C for AIX Compiler uses -M and outputs the dependencies - # in a .u file. In older versions, this file always lives in the - # current directory. Also, the AIX compiler puts `$object:' at the - # start of each line; $object doesn't have directory information. - # Version 6 uses the directory in both cases. - dir=`echo "$object" | sed -e 's|/[^/]*$|/|'` - test "x$dir" = "x$object" && dir= - base=`echo "$object" | sed -e 's|^.*/||' -e 's/\.o$//' -e 's/\.lo$//'` - if test "$libtool" = yes; then - tmpdepfile1=$dir$base.u - tmpdepfile2=$base.u - tmpdepfile3=$dir.libs/$base.u - "$@" -Wc,-M - else - tmpdepfile1=$dir$base.u - tmpdepfile2=$dir$base.u - tmpdepfile3=$dir$base.u - "$@" -M - fi - stat=$? - - if test $stat -eq 0; then : - else - rm -f "$tmpdepfile1" "$tmpdepfile2" "$tmpdepfile3" - exit $stat - fi - - for tmpdepfile in "$tmpdepfile1" "$tmpdepfile2" "$tmpdepfile3" - do - test -f "$tmpdepfile" && break - done - if test -f "$tmpdepfile"; then - # Each line is of the form `foo.o: dependent.h'. - # Do two passes, one to just change these to - # `$object: dependent.h' and one to simply `dependent.h:'. - sed -e "s,^.*\.[a-z]*:,$object:," < "$tmpdepfile" > "$depfile" - # That's a tab and a space in the []. - sed -e 's,^.*\.[a-z]*:[ ]*,,' -e 's,$,:,' < "$tmpdepfile" >> "$depfile" - else - # The sourcefile does not contain any dependencies, so just - # store a dummy comment line, to avoid errors with the Makefile - # "include basename.Plo" scheme. - echo "#dummy" > "$depfile" - fi - rm -f "$tmpdepfile" - ;; - -icc) - # Intel's C compiler understands `-MD -MF file'. However on - # icc -MD -MF foo.d -c -o sub/foo.o sub/foo.c - # ICC 7.0 will fill foo.d with something like - # foo.o: sub/foo.c - # foo.o: sub/foo.h - # which is wrong. We want: - # sub/foo.o: sub/foo.c - # sub/foo.o: sub/foo.h - # sub/foo.c: - # sub/foo.h: - # ICC 7.1 will output - # foo.o: sub/foo.c sub/foo.h - # and will wrap long lines using \ : - # foo.o: sub/foo.c ... \ - # sub/foo.h ... \ - # ... - - "$@" -MD -MF "$tmpdepfile" - stat=$? - if test $stat -eq 0; then : - else - rm -f "$tmpdepfile" - exit $stat - fi - rm -f "$depfile" - # Each line is of the form `foo.o: dependent.h', - # or `foo.o: dep1.h dep2.h \', or ` dep3.h dep4.h \'. - # Do two passes, one to just change these to - # `$object: dependent.h' and one to simply `dependent.h:'. - sed "s,^[^:]*:,$object :," < "$tmpdepfile" > "$depfile" - # Some versions of the HPUX 10.20 sed can't process this invocation - # correctly. Breaking it into two sed invocations is a workaround. - sed 's,^[^:]*: \(.*\)$,\1,;s/^\\$//;/^$/d;/:$/d' < "$tmpdepfile" | - sed -e 's/$/ :/' >> "$depfile" - rm -f "$tmpdepfile" - ;; - -hp2) - # The "hp" stanza above does not work with aCC (C++) and HP's ia64 - # compilers, which have integrated preprocessors. The correct option - # to use with these is +Maked; it writes dependencies to a file named - # 'foo.d', which lands next to the object file, wherever that - # happens to be. - # Much of this is similar to the tru64 case; see comments there. - dir=`echo "$object" | sed -e 's|/[^/]*$|/|'` - test "x$dir" = "x$object" && dir= - base=`echo "$object" | sed -e 's|^.*/||' -e 's/\.o$//' -e 's/\.lo$//'` - if test "$libtool" = yes; then - tmpdepfile1=$dir$base.d - tmpdepfile2=$dir.libs/$base.d - "$@" -Wc,+Maked - else - tmpdepfile1=$dir$base.d - tmpdepfile2=$dir$base.d - "$@" +Maked - fi - stat=$? - if test $stat -eq 0; then : - else - rm -f "$tmpdepfile1" "$tmpdepfile2" - exit $stat - fi - - for tmpdepfile in "$tmpdepfile1" "$tmpdepfile2" - do - test -f "$tmpdepfile" && break - done - if test -f "$tmpdepfile"; then - sed -e "s,^.*\.[a-z]*:,$object:," "$tmpdepfile" > "$depfile" - # Add `dependent.h:' lines. - sed -ne '2,${; s/^ *//; s/ \\*$//; s/$/:/; p;}' "$tmpdepfile" >> "$depfile" - else - echo "#dummy" > "$depfile" - fi - rm -f "$tmpdepfile" "$tmpdepfile2" - ;; - -tru64) - # The Tru64 compiler uses -MD to generate dependencies as a side - # effect. `cc -MD -o foo.o ...' puts the dependencies into `foo.o.d'. - # At least on Alpha/Redhat 6.1, Compaq CCC V6.2-504 seems to put - # dependencies in `foo.d' instead, so we check for that too. - # Subdirectories are respected. - dir=`echo "$object" | sed -e 's|/[^/]*$|/|'` - test "x$dir" = "x$object" && dir= - base=`echo "$object" | sed -e 's|^.*/||' -e 's/\.o$//' -e 's/\.lo$//'` - - if test "$libtool" = yes; then - # With Tru64 cc, shared objects can also be used to make a - # static library. This mechanism is used in libtool 1.4 series to - # handle both shared and static libraries in a single compilation. - # With libtool 1.4, dependencies were output in $dir.libs/$base.lo.d. - # - # With libtool 1.5 this exception was removed, and libtool now - # generates 2 separate objects for the 2 libraries. These two - # compilations output dependencies in $dir.libs/$base.o.d and - # in $dir$base.o.d. We have to check for both files, because - # one of the two compilations can be disabled. We should prefer - # $dir$base.o.d over $dir.libs/$base.o.d because the latter is - # automatically cleaned when .libs/ is deleted, while ignoring - # the former would cause a distcleancheck panic. - tmpdepfile1=$dir.libs/$base.lo.d # libtool 1.4 - tmpdepfile2=$dir$base.o.d # libtool 1.5 - tmpdepfile3=$dir.libs/$base.o.d # libtool 1.5 - tmpdepfile4=$dir.libs/$base.d # Compaq CCC V6.2-504 - "$@" -Wc,-MD - else - tmpdepfile1=$dir$base.o.d - tmpdepfile2=$dir$base.d - tmpdepfile3=$dir$base.d - tmpdepfile4=$dir$base.d - "$@" -MD - fi - - stat=$? - if test $stat -eq 0; then : - else - rm -f "$tmpdepfile1" "$tmpdepfile2" "$tmpdepfile3" "$tmpdepfile4" - exit $stat - fi - - for tmpdepfile in "$tmpdepfile1" "$tmpdepfile2" "$tmpdepfile3" "$tmpdepfile4" - do - test -f "$tmpdepfile" && break - done - if test -f "$tmpdepfile"; then - sed -e "s,^.*\.[a-z]*:,$object:," < "$tmpdepfile" > "$depfile" - # That's a tab and a space in the []. - sed -e 's,^.*\.[a-z]*:[ ]*,,' -e 's,$,:,' < "$tmpdepfile" >> "$depfile" - else - echo "#dummy" > "$depfile" - fi - rm -f "$tmpdepfile" - ;; - -#nosideeffect) - # This comment above is used by automake to tell side-effect - # dependency tracking mechanisms from slower ones. - -dashmstdout) - # Important note: in order to support this mode, a compiler *must* - # always write the preprocessed file to stdout, regardless of -o. - "$@" || exit $? - - # Remove the call to Libtool. - if test "$libtool" = yes; then - while test $1 != '--mode=compile'; do - shift - done - shift - fi - - # Remove `-o $object'. - IFS=" " - for arg - do - case $arg in - -o) - shift - ;; - $object) - shift - ;; - *) - set fnord "$@" "$arg" - shift # fnord - shift # $arg - ;; - esac - done - - test -z "$dashmflag" && dashmflag=-M - # Require at least two characters before searching for `:' - # in the target name. This is to cope with DOS-style filenames: - # a dependency such as `c:/foo/bar' could be seen as target `c' otherwise. - "$@" $dashmflag | - sed 's:^[ ]*[^: ][^:][^:]*\:[ ]*:'"$object"'\: :' > "$tmpdepfile" - rm -f "$depfile" - cat < "$tmpdepfile" > "$depfile" - tr ' ' ' -' < "$tmpdepfile" | \ -## Some versions of the HPUX 10.20 sed can't process this invocation -## correctly. Breaking it into two sed invocations is a workaround. - sed -e 's/^\\$//' -e '/^$/d' -e '/:$/d' | sed -e 's/$/ :/' >> "$depfile" - rm -f "$tmpdepfile" - ;; - -dashXmstdout) - # This case only exists to satisfy depend.m4. It is never actually - # run, as this mode is specially recognized in the preamble. - exit 1 - ;; - -makedepend) - "$@" || exit $? - # Remove any Libtool call - if test "$libtool" = yes; then - while test $1 != '--mode=compile'; do - shift - done - shift - fi - # X makedepend - shift - cleared=no - for arg in "$@"; do - case $cleared in - no) - set ""; shift - cleared=yes ;; - esac - case "$arg" in - -D*|-I*) - set fnord "$@" "$arg"; shift ;; - # Strip any option that makedepend may not understand. Remove - # the object too, otherwise makedepend will parse it as a source file. - -*|$object) - ;; - *) - set fnord "$@" "$arg"; shift ;; - esac - done - obj_suffix="`echo $object | sed 's/^.*\././'`" - touch "$tmpdepfile" - ${MAKEDEPEND-makedepend} -o"$obj_suffix" -f"$tmpdepfile" "$@" - rm -f "$depfile" - cat < "$tmpdepfile" > "$depfile" - sed '1,2d' "$tmpdepfile" | tr ' ' ' -' | \ -## Some versions of the HPUX 10.20 sed can't process this invocation -## correctly. Breaking it into two sed invocations is a workaround. - sed -e 's/^\\$//' -e '/^$/d' -e '/:$/d' | sed -e 's/$/ :/' >> "$depfile" - rm -f "$tmpdepfile" "$tmpdepfile".bak - ;; - -cpp) - # Important note: in order to support this mode, a compiler *must* - # always write the preprocessed file to stdout. - "$@" || exit $? - - # Remove the call to Libtool. - if test "$libtool" = yes; then - while test $1 != '--mode=compile'; do - shift - done - shift - fi - - # Remove `-o $object'. - IFS=" " - for arg - do - case $arg in - -o) - shift - ;; - $object) - shift - ;; - *) - set fnord "$@" "$arg" - shift # fnord - shift # $arg - ;; - esac - done - - "$@" -E | - sed -n -e '/^# [0-9][0-9]* "\([^"]*\)".*/ s:: \1 \\:p' \ - -e '/^#line [0-9][0-9]* "\([^"]*\)".*/ s:: \1 \\:p' | - sed '$ s: \\$::' > "$tmpdepfile" - rm -f "$depfile" - echo "$object : \\" > "$depfile" - cat < "$tmpdepfile" >> "$depfile" - sed < "$tmpdepfile" '/^$/d;s/^ //;s/ \\$//;s/$/ :/' >> "$depfile" - rm -f "$tmpdepfile" - ;; - -msvisualcpp) - # Important note: in order to support this mode, a compiler *must* - # always write the preprocessed file to stdout, regardless of -o, - # because we must use -o when running libtool. - "$@" || exit $? - IFS=" " - for arg - do - case "$arg" in - "-Gm"|"/Gm"|"-Gi"|"/Gi"|"-ZI"|"/ZI") - set fnord "$@" - shift - shift - ;; - *) - set fnord "$@" "$arg" - shift - shift - ;; - esac - done - "$@" -E | - sed -n '/^#line [0-9][0-9]* "\([^"]*\)"/ s::echo "`cygpath -u \\"\1\\"`":p' | sort | uniq > "$tmpdepfile" - rm -f "$depfile" - echo "$object : \\" > "$depfile" - . "$tmpdepfile" | sed 's% %\\ %g' | sed -n '/^\(.*\)$/ s:: \1 \\:p' >> "$depfile" - echo " " >> "$depfile" - . "$tmpdepfile" | sed 's% %\\ %g' | sed -n '/^\(.*\)$/ s::\1\::p' >> "$depfile" - rm -f "$tmpdepfile" - ;; - -none) - exec "$@" - ;; - -*) - echo "Unknown depmode $depmode" 1>&2 - exit 1 - ;; -esac - -exit 0 - -# Local Variables: -# mode: shell-script -# sh-indentation: 2 -# eval: (add-hook 'write-file-hooks 'time-stamp) -# time-stamp-start: "scriptversion=" -# time-stamp-format: "%:y-%02m-%02d.%02H" -# time-stamp-end: "$" -# End: diff --git a/libs/pcre/dftables.c b/libs/pcre/dftables.c deleted file mode 100644 index 12e1af1489..0000000000 --- a/libs/pcre/dftables.c +++ /dev/null @@ -1,199 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2008 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This is a freestanding support program to generate a file containing -character tables for PCRE. The tables are built according to the current -locale. Now that pcre_maketables is a function visible to the outside world, we -make use of its code from here in order to be consistent. */ - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include -#include -#include -#include - -#include "pcre_internal.h" - -#define DFTABLES /* pcre_maketables.c notices this */ -#include "pcre_maketables.c" - - -int main(int argc, char **argv) -{ -FILE *f; -int i = 1; -const unsigned char *tables; -const unsigned char *base_of_tables; - -/* By default, the default C locale is used rather than what the building user -happens to have set. However, if the -L option is given, set the locale from -the LC_xxx environment variables. */ - -if (argc > 1 && strcmp(argv[1], "-L") == 0) - { - setlocale(LC_ALL, ""); /* Set from environment variables */ - i++; - } - -if (argc < i + 1) - { - fprintf(stderr, "dftables: one filename argument is required\n"); - return 1; - } - -tables = pcre_maketables(); -base_of_tables = tables; - -f = fopen(argv[i], "wb"); -if (f == NULL) - { - fprintf(stderr, "dftables: failed to open %s for writing\n", argv[1]); - return 1; - } - -/* There are several fprintf() calls here, because gcc in pedantic mode -complains about the very long string otherwise. */ - -fprintf(f, - "/*************************************************\n" - "* Perl-Compatible Regular Expressions *\n" - "*************************************************/\n\n" - "/* This file was automatically written by the dftables auxiliary\n" - "program. It contains character tables that are used when no external\n" - "tables are passed to PCRE by the application that calls it. The tables\n" - "are used only for characters whose code values are less than 256.\n\n"); -fprintf(f, - "The following #includes are present because without them gcc 4.x may remove\n" - "the array definition from the final binary if PCRE is built into a static\n" - "library and dead code stripping is activated. This leads to link errors.\n" - "Pulling in the header ensures that the array gets flagged as \"someone\n" - "outside this compilation unit might reference this\" and so it will always\n" - "be supplied to the linker. */\n\n" - "#ifdef HAVE_CONFIG_H\n" - "#include \"config.h\"\n" - "#endif\n\n" - "#include \"pcre_internal.h\"\n\n"); -fprintf(f, - "const unsigned char _pcre_default_tables[] = {\n\n" - "/* This table is a lower casing table. */\n\n"); - -fprintf(f, " "); -for (i = 0; i < 256; i++) - { - if ((i & 7) == 0 && i != 0) fprintf(f, "\n "); - fprintf(f, "%3d", *tables++); - if (i != 255) fprintf(f, ","); - } -fprintf(f, ",\n\n"); - -fprintf(f, "/* This table is a case flipping table. */\n\n"); - -fprintf(f, " "); -for (i = 0; i < 256; i++) - { - if ((i & 7) == 0 && i != 0) fprintf(f, "\n "); - fprintf(f, "%3d", *tables++); - if (i != 255) fprintf(f, ","); - } -fprintf(f, ",\n\n"); - -fprintf(f, - "/* This table contains bit maps for various character classes.\n" - "Each map is 32 bytes long and the bits run from the least\n" - "significant end of each byte. The classes that have their own\n" - "maps are: space, xdigit, digit, upper, lower, word, graph\n" - "print, punct, and cntrl. Other classes are built from combinations. */\n\n"); - -fprintf(f, " "); -for (i = 0; i < cbit_length; i++) - { - if ((i & 7) == 0 && i != 0) - { - if ((i & 31) == 0) fprintf(f, "\n"); - fprintf(f, "\n "); - } - fprintf(f, "0x%02x", *tables++); - if (i != cbit_length - 1) fprintf(f, ","); - } -fprintf(f, ",\n\n"); - -fprintf(f, - "/* This table identifies various classes of character by individual bits:\n" - " 0x%02x white space character\n" - " 0x%02x letter\n" - " 0x%02x decimal digit\n" - " 0x%02x hexadecimal digit\n" - " 0x%02x alphanumeric or '_'\n" - " 0x%02x regular expression metacharacter or binary zero\n*/\n\n", - ctype_space, ctype_letter, ctype_digit, ctype_xdigit, ctype_word, - ctype_meta); - -fprintf(f, " "); -for (i = 0; i < 256; i++) - { - if ((i & 7) == 0 && i != 0) - { - fprintf(f, " /* "); - if (isprint(i-8)) fprintf(f, " %c -", i-8); - else fprintf(f, "%3d-", i-8); - if (isprint(i-1)) fprintf(f, " %c ", i-1); - else fprintf(f, "%3d", i-1); - fprintf(f, " */\n "); - } - fprintf(f, "0x%02x", *tables++); - if (i != 255) fprintf(f, ","); - } - -fprintf(f, "};/* "); -if (isprint(i-8)) fprintf(f, " %c -", i-8); - else fprintf(f, "%3d-", i-8); -if (isprint(i-1)) fprintf(f, " %c ", i-1); - else fprintf(f, "%3d", i-1); -fprintf(f, " */\n\n/* End of pcre_chartables.c */\n"); - -fclose(f); -free((void *)base_of_tables); -return 0; -} - -/* End of dftables.c */ diff --git a/libs/pcre/doc/Tech.Notes b/libs/pcre/doc/Tech.Notes deleted file mode 100644 index 21dbe1f9b5..0000000000 --- a/libs/pcre/doc/Tech.Notes +++ /dev/null @@ -1,348 +0,0 @@ -Technical Notes about PCRE --------------------------- - -These are very rough technical notes that record potentially useful information -about PCRE internals. - -Historical note 1 ------------------ - -Many years ago I implemented some regular expression functions to an algorithm -suggested by Martin Richards. These were not Unix-like in form, and were quite -restricted in what they could do by comparison with Perl. The interesting part -about the algorithm was that the amount of space required to hold the compiled -form of an expression was known in advance. The code to apply an expression did -not operate by backtracking, as the original Henry Spencer code and current -Perl code does, but instead checked all possibilities simultaneously by keeping -a list of current states and checking all of them as it advanced through the -subject string. In the terminology of Jeffrey Friedl's book, it was a "DFA -algorithm". When the pattern was all used up, all remaining states were -possible matches, and the one matching the longest subset of the subject string -was chosen. This did not necessarily maximize the individual wild portions of -the pattern, as is expected in Unix and Perl-style regular expressions. - -Historical note 2 ------------------ - -By contrast, the code originally written by Henry Spencer (which was -subsequently heavily modified for Perl) compiles the expression twice: once in -a dummy mode in order to find out how much store will be needed, and then for -real. (The Perl version probably doesn't do this any more; I'm talking about -the original library.) The execution function operates by backtracking and -maximizing (or, optionally, minimizing in Perl) the amount of the subject that -matches individual wild portions of the pattern. This is an "NFA algorithm" in -Friedl's terminology. - -OK, here's the real stuff -------------------------- - -For the set of functions that form the "basic" PCRE library (which are -unrelated to those mentioned above), I tried at first to invent an algorithm -that used an amount of store bounded by a multiple of the number of characters -in the pattern, to save on compiling time. However, because of the greater -complexity in Perl regular expressions, I couldn't do this. In any case, a -first pass through the pattern is needed, for a number of reasons. PCRE works -by running a very degenerate first pass to calculate a maximum store size, and -then a second pass to do the real compile - which may use a bit less than the -predicted amount of store. The idea is that this is going to turn out faster -because the first pass is degenerate and the second pass can just store stuff -straight into the vector, which it knows is big enough. It does make the -compiling functions bigger, of course, but they have become quite big anyway to -handle all the Perl stuff. - -Traditional matching function ------------------------------ - -The "traditional", and original, matching function is called pcre_exec(), and -it implements an NFA algorithm, similar to the original Henry Spencer algorithm -and the way that Perl works. Not surprising, since it is intended to be as -compatible with Perl as possible. This is the function most users of PCRE will -use most of the time. - -Supplementary matching function -------------------------------- - -From PCRE 6.0, there is also a supplementary matching function called -pcre_dfa_exec(). This implements a DFA matching algorithm that searches -simultaneously for all possible matches that start at one point in the subject -string. (Going back to my roots: see Historical Note 1 above.) This function -intreprets the same compiled pattern data as pcre_exec(); however, not all the -facilities are available, and those that are do not always work in quite the -same way. See the user documentation for details. - -Format of compiled patterns ---------------------------- - -The compiled form of a pattern is a vector of bytes, containing items of -variable length. The first byte in an item is an opcode, and the length of the -item is either implicit in the opcode or contained in the data bytes that -follow it. - -In many cases below "two-byte" data values are specified. This is in fact just -a default. PCRE can be compiled to use 3-byte or 4-byte values (impairing the -performance). This is necessary only when patterns whose compiled length is -greater than 64K are going to be processed. In this description, we assume the -"normal" compilation options. - -A list of all the opcodes follows: - -Opcodes with no following data ------------------------------- - -These items are all just one byte long - - OP_END end of pattern - OP_ANY match any character - OP_ANYBYTE match any single byte, even in UTF-8 mode - OP_SOD match start of data: \A - OP_SOM, start of match (subject + offset): \G - OP_CIRC ^ (start of data, or after \n in multiline) - OP_NOT_WORD_BOUNDARY \W - OP_WORD_BOUNDARY \w - OP_NOT_DIGIT \D - OP_DIGIT \d - OP_NOT_WHITESPACE \S - OP_WHITESPACE \s - OP_NOT_WORDCHAR \W - OP_WORDCHAR \w - OP_EODN match end of data or \n at end: \Z - OP_EOD match end of data: \z - OP_DOLL $ (end of data, or before \n in multiline) - OP_EXTUNI match an extended Unicode character - - -Repeating single characters ---------------------------- - -The common repeats (*, +, ?) when applied to a single character use the -following opcodes: - - OP_STAR - OP_MINSTAR - OP_PLUS - OP_MINPLUS - OP_QUERY - OP_MINQUERY - -In ASCII mode, these are two-byte items; in UTF-8 mode, the length is variable. -Those with "MIN" in their name are the minimizing versions. Each is followed by -the character that is to be repeated. Other repeats make use of - - OP_UPTO - OP_MINUPTO - OP_EXACT - -which are followed by a two-byte count (most significant first) and the -repeated character. OP_UPTO matches from 0 to the given number. A repeat with a -non-zero minimum and a fixed maximum is coded as an OP_EXACT followed by an -OP_UPTO (or OP_MINUPTO). - - -Repeating character types -------------------------- - -Repeats of things like \d are done exactly as for single characters, except -that instead of a character, the opcode for the type is stored in the data -byte. The opcodes are: - - OP_TYPESTAR - OP_TYPEMINSTAR - OP_TYPEPLUS - OP_TYPEMINPLUS - OP_TYPEQUERY - OP_TYPEMINQUERY - OP_TYPEUPTO - OP_TYPEMINUPTO - OP_TYPEEXACT - - -Match by Unicode property -------------------------- - -OP_PROP and OP_NOTPROP are used for positive and negative matches of a -character by testing its Unicode property (the \p and \P escape sequences). -Each is followed by two bytes that encode the desired property as a type and a -value. - -Repeats of these items use the OP_TYPESTAR etc. set of opcodes, followed by -three bytes: OP_PROP or OP_NOTPROP and then the desired property type and -value. - - -Matching literal characters ---------------------------- - -The OP_CHAR opcode is followed by a single character that is to be matched -casefully. For caseless matching, OP_CHARNC is used. In UTF-8 mode, the -character may be more than one byte long. (Earlier versions of PCRE used -multi-character strings, but this was changed to allow some new features to be -added.) - - -Character classes ------------------ - -If there is only one character, OP_CHAR or OP_CHARNC is used for a positive -class, and OP_NOT for a negative one (that is, for something like [^a]). -However, in UTF-8 mode, the use of OP_NOT applies only to characters with -values < 128, because OP_NOT is confined to single bytes. - -Another set of repeating opcodes (OP_NOTSTAR etc.) are used for a repeated, -negated, single-character class. The normal ones (OP_STAR etc.) are used for a -repeated positive single-character class. - -When there's more than one character in a class and all the characters are less -than 256, OP_CLASS is used for a positive class, and OP_NCLASS for a negative -one. In either case, the opcode is followed by a 32-byte bit map containing a 1 -bit for every character that is acceptable. The bits are counted from the least -significant end of each byte. - -The reason for having both OP_CLASS and OP_NCLASS is so that, in UTF-8 mode, -subject characters with values greater than 256 can be handled correctly. For -OP_CLASS they don't match, whereas for OP_NCLASS they do. - -For classes containing characters with values > 255, OP_XCLASS is used. It -optionally uses a bit map (if any characters lie within it), followed by a list -of pairs and single characters. There is a flag character than indicates -whether it's a positive or a negative class. - - -Back references ---------------- - -OP_REF is followed by two bytes containing the reference number. - - -Repeating character classes and back references ------------------------------------------------ - -Single-character classes are handled specially (see above). This applies to -OP_CLASS and OP_REF. In both cases, the repeat information follows the base -item. The matching code looks at the following opcode to see if it is one of - - OP_CRSTAR - OP_CRMINSTAR - OP_CRPLUS - OP_CRMINPLUS - OP_CRQUERY - OP_CRMINQUERY - OP_CRRANGE - OP_CRMINRANGE - -All but the last two are just single-byte items. The others are followed by -four bytes of data, comprising the minimum and maximum repeat counts. - - -Brackets and alternation ------------------------- - -A pair of non-capturing (round) brackets is wrapped round each expression at -compile time, so alternation always happens in the context of brackets. - -Non-capturing brackets use the opcode OP_BRA, while capturing brackets use -OP_BRA+1, OP_BRA+2, etc. [Note for North Americans: "bracket" to some English -speakers, including myself, can be round, square, curly, or pointy. Hence this -usage.] - -Originally PCRE was limited to 99 capturing brackets (so as not to use up all -the opcodes). From release 3.5, there is no limit. What happens is that the -first ones, up to EXTRACT_BASIC_MAX are handled with separate opcodes, as -above. If there are more, the opcode is set to EXTRACT_BASIC_MAX+1, and the -first operation in the bracket is OP_BRANUMBER, followed by a 2-byte bracket -number. This opcode is ignored while matching, but is fished out when handling -the bracket itself. (They could have all been done like this, but I was making -minimal changes.) - -A bracket opcode is followed by LINK_SIZE bytes which give the offset to the -next alternative OP_ALT or, if there aren't any branches, to the matching -OP_KET opcode. Each OP_ALT is followed by LINK_SIZE bytes giving the offset to -the next one, or to the OP_KET opcode. - -OP_KET is used for subpatterns that do not repeat indefinitely, while -OP_KETRMIN and OP_KETRMAX are used for indefinite repetitions, minimally or -maximally respectively. All three are followed by LINK_SIZE bytes giving (as a -positive number) the offset back to the matching OP_BRA opcode. - -If a subpattern is quantified such that it is permitted to match zero times, it -is preceded by one of OP_BRAZERO or OP_BRAMINZERO. These are single-byte -opcodes which tell the matcher that skipping this subpattern entirely is a -valid branch. - -A subpattern with an indefinite maximum repetition is replicated in the -compiled data its minimum number of times (or once with OP_BRAZERO if the -minimum is zero), with the final copy terminating with OP_KETRMIN or OP_KETRMAX -as appropriate. - -A subpattern with a bounded maximum repetition is replicated in a nested -fashion up to the maximum number of times, with OP_BRAZERO or OP_BRAMINZERO -before each replication after the minimum, so that, for example, (abc){2,5} is -compiled as (abc)(abc)((abc)((abc)(abc)?)?)?. - - -Assertions ----------- - -Forward assertions are just like other subpatterns, but starting with one of -the opcodes OP_ASSERT or OP_ASSERT_NOT. Backward assertions use the opcodes -OP_ASSERTBACK and OP_ASSERTBACK_NOT, and the first opcode inside the assertion -is OP_REVERSE, followed by a two byte count of the number of characters to move -back the pointer in the subject string. When operating in UTF-8 mode, the count -is a character count rather than a byte count. A separate count is present in -each alternative of a lookbehind assertion, allowing them to have different -fixed lengths. - - -Once-only subpatterns ---------------------- - -These are also just like other subpatterns, but they start with the opcode -OP_ONCE. - - -Conditional subpatterns ------------------------ - -These are like other subpatterns, but they start with the opcode OP_COND. If -the condition is a back reference, this is stored at the start of the -subpattern using the opcode OP_CREF followed by two bytes containing the -reference number. If the condition is "in recursion" (coded as "(?(R)"), the -same scheme is used, with a "reference number" of 0xffff. Otherwise, a -conditional subpattern always starts with one of the assertions. - - -Recursion ---------- - -Recursion either matches the current regex, or some subexpression. The opcode -OP_RECURSE is followed by an value which is the offset to the starting bracket -from the start of the whole pattern. From release 6.5, OP_RECURSE is -automatically wrapped inside OP_ONCE brackets (because otherwise some patterns -broke it). OP_RECURSE is also used for "subroutine" calls, even though they -are not strictly a recursion. - - -Callout -------- - -OP_CALLOUT is followed by one byte of data that holds a callout number in the -range 0 to 254 for manual callouts, or 255 for an automatic callout. In both -cases there follows a two-byte value giving the offset in the pattern to the -start of the following item, and another two-byte item giving the length of the -next item. - - -Changing options ----------------- - -If any of the /i, /m, or /s options are changed within a pattern, an OP_OPT -opcode is compiled, followed by one byte containing the new settings of these -flags. If there are several alternatives, there is an occurrence of OP_OPT at -the start of all those following the first options change, to set appropriate -options for the start of the alternative. Immediately after the end of the -group there is another such item to reset the flags to their previous values. A -change of flag right at the very start of the pattern can be handled entirely -at compile time, and so does not cause anything to be put into the compiled -data. - -Philip Hazel -June 2006 diff --git a/libs/pcre/doc/html/index.html b/libs/pcre/doc/html/index.html deleted file mode 100644 index 8a7174e6ca..0000000000 --- a/libs/pcre/doc/html/index.html +++ /dev/null @@ -1,140 +0,0 @@ - - - -PCRE specification - - -

Perl-compatible Regular Expressions (PCRE)

-

-The HTML documentation for PCRE comprises the following pages: -

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
pcre  Introductory page
pcre-config  Information about the installation configuration
pcreapi  PCRE's native API
pcrebuild  Options for building PCRE
pcrecallout  The callout facility
pcrecompat  Compability with Perl
pcrecpp  The C++ wrapper for the PCRE library
pcregrep  The pcregrep command
pcrematching  Discussion of the two matching algorithms
pcrepartial  Using PCRE for partial matching
pcrepattern  Specification of the regular expressions supported by PCRE
pcreperform  Some comments on performance
pcreposix  The POSIX API to the PCRE library
pcreprecompile  How to save and re-use compiled patterns
pcresample  Description of the sample program
pcrestack  Discussion of PCRE's stack usage
pcresyntax  Syntax quick-reference summary
pcretest  The pcretest command for testing PCRE
- -

-There are also individual pages that summarize the interface for each function -in the library: -

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
pcre_compile  Compile a regular expression
pcre_compile2  Compile a regular expression (alternate interface)
pcre_config  Show build-time configuration options
pcre_copy_named_substring  Extract named substring into given buffer
pcre_copy_substring  Extract numbered substring into given buffer
pcre_dfa_exec  Match a compiled pattern to a subject string - (DFA algorithm; not Perl compatible)
pcre_exec  Match a compiled pattern to a subject string - (Perl compatible)
pcre_free_substring  Free extracted substring
pcre_free_substring_list  Free list of extracted substrings
pcre_fullinfo  Extract information about a pattern
pcre_get_named_substring  Extract named substring into new memory
pcre_get_stringnumber  Convert captured string name to number
pcre_get_substring  Extract numbered substring into new memory
pcre_get_substring_list  Extract all substrings into new memory
pcre_info  Obsolete information extraction function
pcre_maketables  Build character tables in current locale
pcre_refcount  Maintain reference count in compiled pattern
pcre_study  Study a compiled pattern
pcre_version  Return PCRE version and release date
- - diff --git a/libs/pcre/doc/html/pcre-config.html b/libs/pcre/doc/html/pcre-config.html deleted file mode 100644 index 09877456fd..0000000000 --- a/libs/pcre/doc/html/pcre-config.html +++ /dev/null @@ -1,88 +0,0 @@ - - -pcre-config specification - - -

pcre-config man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-

-
SYNOPSIS
-

-pcre-config [--prefix] [--exec-prefix] [--version] [--libs] -[--libs-posix] [--cflags] [--cflags-posix] -

-
DESCRIPTION
-

-pcre-config returns the configuration of the installed PCRE -libraries and the options required to compile a program to use them. -

-
OPTIONS
-

---prefix -Writes the directory prefix used in the PCRE installation for architecture -independent files (/usr on many systems, /usr/local on some -systems) to the standard output. -

-

---exec-prefix -Writes the directory prefix used in the PCRE installation for architecture -dependent files (normally the same as --prefix) to the standard output. -

-

---version -Writes the version number of the installed PCRE libraries to the standard -output. -

-

---libs -Writes to the standard output the command line options required to link -with PCRE (-lpcre on many systems). -

-

---libs-posix -Writes to the standard output the command line options required to link with -the PCRE posix emulation library (-lpcreposix -lpcre on many -systems). -

-

---cflags -Writes to the standard output the command line options required to compile -files that use PCRE (this may include some -I options, but is blank on -many systems). -

-

---cflags-posix -Writes to the standard output the command line options required to compile -files that use the PCRE posix emulation library (this may include some -I -options, but is blank on many systems). -

-
SEE ALSO
-

-pcre(3) -

-
AUTHOR
-

-This manual page was originally written by Mark Baker for the Debian GNU/Linux -system. It has been slightly revised as a generic PCRE man page. -

-
REVISION
-

-Last updated: 18 April 2007 -
-

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcre.html b/libs/pcre/doc/html/pcre.html deleted file mode 100644 index 5e2a036397..0000000000 --- a/libs/pcre/doc/html/pcre.html +++ /dev/null @@ -1,306 +0,0 @@ - - -pcre specification - - -

pcre man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-

-
INTRODUCTION
-

-The PCRE library is a set of functions that implement regular expression -pattern matching using the same syntax and semantics as Perl, with just a few -differences. Certain features that appeared in Python and PCRE before they -appeared in Perl are also available using the Python syntax. There is also some -support for certain .NET and Oniguruma syntax items, and there is an option for -requesting some minor changes that give better JavaScript compatibility. -

-

-The current implementation of PCRE (release 7.x) corresponds approximately with -Perl 5.10, including support for UTF-8 encoded strings and Unicode general -category properties. However, UTF-8 and Unicode support has to be explicitly -enabled; it is not the default. The Unicode tables correspond to Unicode -release 5.1. -

-

-In addition to the Perl-compatible matching function, PCRE contains an -alternative matching function that matches the same compiled patterns in a -different way. In certain circumstances, the alternative function has some -advantages. For a discussion of the two matching algorithms, see the -pcrematching -page. -

-

-PCRE is written in C and released as a C library. A number of people have -written wrappers and interfaces of various kinds. In particular, Google Inc. -have provided a comprehensive C++ wrapper. This is now included as part of the -PCRE distribution. The -pcrecpp -page has details of this interface. Other people's contributions can be found -in the Contrib directory at the primary FTP site, which is: -ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre -

-

-Details of exactly which Perl regular expression features are and are not -supported by PCRE are given in separate documents. See the -pcrepattern -and -pcrecompat -pages. There is a syntax summary in the -pcresyntax -page. -

-

-Some features of PCRE can be included, excluded, or changed when the library is -built. The -pcre_config() -function makes it possible for a client to discover which features are -available. The features themselves are described in the -pcrebuild -page. Documentation about building PCRE for various operating systems can be -found in the README file in the source distribution. -

-

-The library contains a number of undocumented internal functions and data -tables that are used by more than one of the exported external functions, but -which are not intended for use by external callers. Their names all begin with -"_pcre_", which hopefully will not provoke any name clashes. In some -environments, it is possible to control which external symbols are exported -when a shared library is built, and in these cases the undocumented symbols are -not exported. -

-
USER DOCUMENTATION
-

-The user documentation for PCRE comprises a number of different sections. In -the "man" format, each of these is a separate "man page". In the HTML format, -each is a separate page, linked from the index page. In the plain text format, -all the sections are concatenated, for ease of searching. The sections are as -follows: -

-  pcre              this document
-  pcre-config       show PCRE installation configuration information
-  pcreapi           details of PCRE's native C API
-  pcrebuild         options for building PCRE
-  pcrecallout       details of the callout feature
-  pcrecompat        discussion of Perl compatibility
-  pcrecpp           details of the C++ wrapper
-  pcregrep          description of the pcregrep command
-  pcrematching      discussion of the two matching algorithms
-  pcrepartial       details of the partial matching facility
-  pcrepattern       syntax and semantics of supported regular expressions
-  pcresyntax        quick syntax reference
-  pcreperform       discussion of performance issues
-  pcreposix         the POSIX-compatible C API
-  pcreprecompile    details of saving and re-using precompiled patterns
-  pcresample        discussion of the sample program
-  pcrestack         discussion of stack usage
-  pcretest          description of the pcretest testing command
-
-In addition, in the "man" and HTML formats, there is a short page for each -C library function, listing its arguments and results. -

-
LIMITATIONS
-

-There are some size limitations in PCRE but it is hoped that they will never in -practice be relevant. -

-

-The maximum length of a compiled pattern is 65539 (sic) bytes if PCRE is -compiled with the default internal linkage size of 2. If you want to process -regular expressions that are truly enormous, you can compile PCRE with an -internal linkage size of 3 or 4 (see the README file in the source -distribution and the -pcrebuild -documentation for details). In these cases the limit is substantially larger. -However, the speed of execution is slower. -

-

-All values in repeating quantifiers must be less than 65536. -

-

-There is no limit to the number of parenthesized subpatterns, but there can be -no more than 65535 capturing subpatterns. -

-

-The maximum length of name for a named subpattern is 32 characters, and the -maximum number of named subpatterns is 10000. -

-

-The maximum length of a subject string is the largest positive number that an -integer variable can hold. However, when using the traditional matching -function, PCRE uses recursion to handle subpatterns and indefinite repetition. -This means that the available stack space may limit the size of a subject -string that can be processed by certain patterns. For a discussion of stack -issues, see the -pcrestack -documentation. -

-
UTF-8 AND UNICODE PROPERTY SUPPORT
-

-From release 3.3, PCRE has had some support for character strings encoded in -the UTF-8 format. For release 4.0 this was greatly extended to cover most -common requirements, and in release 5.0 additional support for Unicode general -category properties was added. -

-

-In order process UTF-8 strings, you must build PCRE to include UTF-8 support in -the code, and, in addition, you must call -pcre_compile() -with the PCRE_UTF8 option flag, or the pattern must start with the sequence -(*UTF8). When either of these is the case, both the pattern and any subject -strings that are matched against it are treated as UTF-8 strings instead of -just strings of bytes. -

-

-If you compile PCRE with UTF-8 support, but do not use it at run time, the -library will be a bit bigger, but the additional run time overhead is limited -to testing the PCRE_UTF8 flag occasionally, so should not be very big. -

-

-If PCRE is built with Unicode character property support (which implies UTF-8 -support), the escape sequences \p{..}, \P{..}, and \X are supported. -The available properties that can be tested are limited to the general -category properties such as Lu for an upper case letter or Nd for a decimal -number, the Unicode script names such as Arabic or Han, and the derived -properties Any and L&. A full list is given in the -pcrepattern -documentation. Only the short names for properties are supported. For example, -\p{L} matches a letter. Its Perl synonym, \p{Letter}, is not supported. -Furthermore, in Perl, many properties may optionally be prefixed by "Is", for -compatibility with Perl 5.6. PCRE does not support this. -

-
-Validity of UTF-8 strings -
-

-When you set the PCRE_UTF8 flag, the strings passed as patterns and subjects -are (by default) checked for validity on entry to the relevant functions. From -release 7.3 of PCRE, the check is according the rules of RFC 3629, which are -themselves derived from the Unicode specification. Earlier releases of PCRE -followed the rules of RFC 2279, which allows the full range of 31-bit values (0 -to 0x7FFFFFFF). The current check allows only values in the range U+0 to -U+10FFFF, excluding U+D800 to U+DFFF. -

-

-The excluded code points are the "Low Surrogate Area" of Unicode, of which the -Unicode Standard says this: "The Low Surrogate Area does not contain any -character assignments, consequently no character code charts or namelists are -provided for this area. Surrogates are reserved for use with UTF-16 and then -must be used in pairs." The code points that are encoded by UTF-16 pairs are -available as independent code points in the UTF-8 encoding. (In other words, -the whole surrogate thing is a fudge for UTF-16 which unfortunately messes up -UTF-8.) -

-

-If an invalid UTF-8 string is passed to PCRE, an error return -(PCRE_ERROR_BADUTF8) is given. In some situations, you may already know that -your strings are valid, and therefore want to skip these checks in order to -improve performance. If you set the PCRE_NO_UTF8_CHECK flag at compile time or -at run time, PCRE assumes that the pattern or subject it is given -(respectively) contains only valid UTF-8 codes. In this case, it does not -diagnose an invalid UTF-8 string. -

-

-If you pass an invalid UTF-8 string when PCRE_NO_UTF8_CHECK is set, what -happens depends on why the string is invalid. If the string conforms to the -"old" definition of UTF-8 (RFC 2279), it is processed as a string of characters -in the range 0 to 0x7FFFFFFF. In other words, apart from the initial validity -test, PCRE (when in UTF-8 mode) handles strings according to the more liberal -rules of RFC 2279. However, if the string does not even conform to RFC 2279, -the result is undefined. Your program may crash. -

-

-If you want to process strings of values in the full range 0 to 0x7FFFFFFF, -encoded in a UTF-8-like manner as per the old RFC, you can set -PCRE_NO_UTF8_CHECK to bypass the more restrictive test. However, in this -situation, you will have to apply your own validity check. -

-
-General comments about UTF-8 mode -
-

-1. An unbraced hexadecimal escape sequence (such as \xb3) matches a two-byte -UTF-8 character if the value is greater than 127. -

-

-2. Octal numbers up to \777 are recognized, and match two-byte UTF-8 -characters for values greater than \177. -

-

-3. Repeat quantifiers apply to complete UTF-8 characters, not to individual -bytes, for example: \x{100}{3}. -

-

-4. The dot metacharacter matches one UTF-8 character instead of a single byte. -

-

-5. The escape sequence \C can be used to match a single byte in UTF-8 mode, -but its use can lead to some strange effects. This facility is not available in -the alternative matching function, pcre_dfa_exec(). -

-

-6. The character escapes \b, \B, \d, \D, \s, \S, \w, and \W correctly -test characters of any code value, but the characters that PCRE recognizes as -digits, spaces, or word characters remain the same set as before, all with -values less than 256. This remains true even when PCRE includes Unicode -property support, because to do otherwise would slow down PCRE in many common -cases. If you really want to test for a wider sense of, say, "digit", you -must use Unicode property tests such as \p{Nd}. Note that this also applies to -\b, because it is defined in terms of \w and \W. -

-

-7. Similarly, characters that match the POSIX named character classes are all -low-valued characters. -

-

-8. However, the Perl 5.10 horizontal and vertical whitespace matching escapes -(\h, \H, \v, and \V) do match all the appropriate Unicode characters. -

-

-9. Case-insensitive matching applies only to characters whose values are less -than 128, unless PCRE is built with Unicode property support. Even when Unicode -property support is available, PCRE still uses its own character tables when -checking the case of low-valued characters, so as not to degrade performance. -The Unicode property information is used only for characters with higher -values. Even when Unicode property support is available, PCRE supports -case-insensitive matching only when there is a one-to-one mapping between a -letter's cases. There are a small number of many-to-one mappings in Unicode; -these are not supported by PCRE. -

-
AUTHOR
-

-Philip Hazel -
-University Computing Service -
-Cambridge CB2 3QH, England. -
-

-

-Putting an actual email address here seems to have been a spam magnet, so I've -taken it away. If you want to email me, use my two initials, followed by the -two digits 10, at the domain cam.ac.uk. -

-
REVISION
-

-Last updated: 11 April 2009 -
-Copyright © 1997-2009 University of Cambridge. -
-

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcre_compile.html b/libs/pcre/doc/html/pcre_compile.html deleted file mode 100644 index 396a5fbdb4..0000000000 --- a/libs/pcre/doc/html/pcre_compile.html +++ /dev/null @@ -1,89 +0,0 @@ - - -pcre_compile specification - - -

pcre_compile man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-
-SYNOPSIS -
-

-#include <pcre.h> -

-

-pcre *pcre_compile(const char *pattern, int options, -const char **errptr, int *erroffset, -const unsigned char *tableptr); -

-
-DESCRIPTION -
-

-This function compiles a regular expression into an internal form. It is the -same as pcre_compile2(), except for the absence of the errorcodeptr -argument. Its arguments are: -

-  pattern       A zero-terminated string containing the
-                  regular expression to be compiled
-  options       Zero or more option bits
-  errptr        Where to put an error message
-  erroffset     Offset in pattern where error was found
-  tableptr      Pointer to character tables, or NULL to
-                  use the built-in default
-
-The option bits are: -
-  PCRE_ANCHORED           Force pattern anchoring
-  PCRE_AUTO_CALLOUT       Compile automatic callouts
-  PCRE_BSR_ANYCRLF        \R matches only CR, LF, or CRLF
-  PCRE_BSR_UNICODE        \R matches all Unicode line endings
-  PCRE_CASELESS           Do caseless matching
-  PCRE_DOLLAR_ENDONLY     $ not to match newline at end
-  PCRE_DOTALL             . matches anything including NL
-  PCRE_DUPNAMES           Allow duplicate names for subpatterns
-  PCRE_EXTENDED           Ignore whitespace and # comments
-  PCRE_EXTRA              PCRE extra features
-                            (not much use currently)
-  PCRE_FIRSTLINE          Force matching to be before newline
-  PCRE_JAVASCRIPT_COMPAT  JavaScript compatibility
-  PCRE_MULTILINE          ^ and $ match newlines within data
-  PCRE_NEWLINE_ANY        Recognize any Unicode newline sequence
-  PCRE_NEWLINE_ANYCRLF    Recognize CR, LF, and CRLF as newline
-                            sequences
-  PCRE_NEWLINE_CR         Set CR as the newline sequence
-  PCRE_NEWLINE_CRLF       Set CRLF as the newline sequence
-  PCRE_NEWLINE_LF         Set LF as the newline sequence
-  PCRE_NO_AUTO_CAPTURE    Disable numbered capturing paren-
-                            theses (named ones available)
-  PCRE_UNGREEDY           Invert greediness of quantifiers
-  PCRE_UTF8               Run in UTF-8 mode
-  PCRE_NO_UTF8_CHECK      Do not check the pattern for UTF-8
-                            validity (only relevant if
-                            PCRE_UTF8 is set)
-
-PCRE must be built with UTF-8 support in order to use PCRE_UTF8 and -PCRE_NO_UTF8_CHECK. -

-

-The yield of the function is a pointer to a private data structure that -contains the compiled pattern, or NULL if an error was detected. Note that -compiling regular expressions with one version of PCRE for use with a different -version is not guaranteed to work and may cause crashes. -

-

-There is a complete description of the PCRE native API in the -pcreapi -page and a description of the POSIX API in the -pcreposix -page. -

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcre_compile2.html b/libs/pcre/doc/html/pcre_compile2.html deleted file mode 100644 index 8d743c10e5..0000000000 --- a/libs/pcre/doc/html/pcre_compile2.html +++ /dev/null @@ -1,89 +0,0 @@ - - -pcre_compile2 specification - - -

pcre_compile2 man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-
-SYNOPSIS -
-

-#include <pcre.h> -

-

-pcre *pcre_compile2(const char *pattern, int options, -int *errorcodeptr, -const char **errptr, int *erroffset, -const unsigned char *tableptr); -

-
-DESCRIPTION -
-

-This function compiles a regular expression into an internal form. It is the -same as pcre_compile(), except for the addition of the errorcodeptr -argument. The arguments are: -

-

-

-  pattern       A zero-terminated string containing the
-                  regular expression to be compiled
-  options       Zero or more option bits
-  errorcodeptr  Where to put an error code
-  errptr        Where to put an error message
-  erroffset     Offset in pattern where error was found
-  tableptr      Pointer to character tables, or NULL to
-                  use the built-in default
-
-The option bits are: -
-  PCRE_ANCHORED         Force pattern anchoring
-  PCRE_AUTO_CALLOUT     Compile automatic callouts
-  PCRE_CASELESS         Do caseless matching
-  PCRE_DOLLAR_ENDONLY   $ not to match newline at end
-  PCRE_DOTALL           . matches anything including NL
-  PCRE_DUPNAMES         Allow duplicate names for subpatterns
-  PCRE_EXTENDED         Ignore whitespace and # comments
-  PCRE_EXTRA            PCRE extra features
-                          (not much use currently)
-  PCRE_FIRSTLINE        Force matching to be before newline
-  PCRE_MULTILINE        ^ and $ match newlines within data
-  PCRE_NEWLINE_ANY      Recognize any Unicode newline sequence
-  PCRE_NEWLINE_ANYCRLF  Recognize CR, LF, and CRLF as newline sequences
-  PCRE_NEWLINE_CR       Set CR as the newline sequence
-  PCRE_NEWLINE_CRLF     Set CRLF as the newline sequence
-  PCRE_NEWLINE_LF       Set LF as the newline sequence
-  PCRE_NO_AUTO_CAPTURE  Disable numbered capturing paren-
-                          theses (named ones available)
-  PCRE_UNGREEDY         Invert greediness of quantifiers
-  PCRE_UTF8             Run in UTF-8 mode
-  PCRE_NO_UTF8_CHECK    Do not check the pattern for UTF-8
-                          validity (only relevant if
-                          PCRE_UTF8 is set)
-
-PCRE must be built with UTF-8 support in order to use PCRE_UTF8 and -PCRE_NO_UTF8_CHECK. -

-

-The yield of the function is a pointer to a private data structure that -contains the compiled pattern, or NULL if an error was detected. Note that -compiling regular expressions with one version of PCRE for use with a different -version is not guaranteed to work and may cause crashes. -

-

-There is a complete description of the PCRE native API in the -pcreapi -page and a description of the POSIX API in the -pcreposix -page. -

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcre_config.html b/libs/pcre/doc/html/pcre_config.html deleted file mode 100644 index 40dee37db7..0000000000 --- a/libs/pcre/doc/html/pcre_config.html +++ /dev/null @@ -1,70 +0,0 @@ - - -pcre_config specification - - -

pcre_config man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-
-SYNOPSIS -
-

-#include <pcre.h> -

-

-int pcre_config(int what, void *where); -

-
-DESCRIPTION -
-

-This function makes it possible for a client program to find out which optional -features are available in the version of the PCRE library it is using. Its -arguments are as follows: -

-  what     A code specifying what information is required
-  where    Points to where to put the data
-
-The available codes are: -
-  PCRE_CONFIG_LINK_SIZE     Internal link size: 2, 3, or 4
-  PCRE_CONFIG_MATCH_LIMIT   Internal resource limit
-  PCRE_CONFIG_MATCH_LIMIT_RECURSION
-                            Internal recursion depth limit
-  PCRE_CONFIG_NEWLINE       Value of the default newline sequence:
-                                13 (0x000d)    for CR
-                                10 (0x000a)    for LF
-                              3338 (0x0d0a)    for CRLF
-                                -2             for ANYCRLF
-                                -1             for ANY
-  PCRE_CONFIG_BSR           Indicates what \R matches by default:
-                                 0             all Unicode line endings
-                                 1             CR, LF, or CRLF only
-  PCRE_CONFIG_POSIX_MALLOC_THRESHOLD
-                            Threshold of return slots, above
-                              which malloc() is used by
-                              the POSIX API
-  PCRE_CONFIG_STACKRECURSE  Recursion implementation (1=stack 0=heap)
-  PCRE_CONFIG_UTF8          Availability of UTF-8 support (1=yes 0=no)
-  PCRE_CONFIG_UNICODE_PROPERTIES
-                            Availability of Unicode property support
-                              (1=yes 0=no)
-
-The function yields 0 on success or PCRE_ERROR_BADOPTION otherwise. -

-

-There is a complete description of the PCRE native API in the -pcreapi -page and a description of the POSIX API in the -pcreposix -page. -

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcre_copy_named_substring.html b/libs/pcre/doc/html/pcre_copy_named_substring.html deleted file mode 100644 index 2185518c8a..0000000000 --- a/libs/pcre/doc/html/pcre_copy_named_substring.html +++ /dev/null @@ -1,53 +0,0 @@ - - -pcre_copy_named_substring specification - - -

pcre_copy_named_substring man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-
-SYNOPSIS -
-

-#include <pcre.h> -

-

-int pcre_copy_named_substring(const pcre *code, -const char *subject, int *ovector, -int stringcount, const char *stringname, -char *buffer, int buffersize); -

-
-DESCRIPTION -
-

-This is a convenience function for extracting a captured substring, identified -by name, into a given buffer. The arguments are: -

-  code          Pattern that was successfully matched
-  subject       Subject that has been successfully matched
-  ovector       Offset vector that pcre_exec() used
-  stringcount   Value returned by pcre_exec()
-  stringname    Name of the required substring
-  buffer        Buffer to receive the string
-  buffersize    Size of buffer
-
-The yield is the length of the substring, PCRE_ERROR_NOMEMORY if the buffer was -too small, or PCRE_ERROR_NOSUBSTRING if the string name is invalid. -

-

-There is a complete description of the PCRE native API in the -pcreapi -page and a description of the POSIX API in the -pcreposix -page. -

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcre_copy_substring.html b/libs/pcre/doc/html/pcre_copy_substring.html deleted file mode 100644 index b7d23417d7..0000000000 --- a/libs/pcre/doc/html/pcre_copy_substring.html +++ /dev/null @@ -1,51 +0,0 @@ - - -pcre_copy_substring specification - - -

pcre_copy_substring man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-
-SYNOPSIS -
-

-#include <pcre.h> -

-

-int pcre_copy_substring(const char *subject, int *ovector, -int stringcount, int stringnumber, char *buffer, -int buffersize); -

-
-DESCRIPTION -
-

-This is a convenience function for extracting a captured substring into a given -buffer. The arguments are: -

-  subject       Subject that has been successfully matched
-  ovector       Offset vector that pcre_exec() used
-  stringcount   Value returned by pcre_exec()
-  stringnumber  Number of the required substring
-  buffer        Buffer to receive the string
-  buffersize    Size of buffer
-
-The yield is the length of the string, PCRE_ERROR_NOMEMORY if the buffer was -too small, or PCRE_ERROR_NOSUBSTRING if the string number is invalid. -

-

-There is a complete description of the PCRE native API in the -pcreapi -page and a description of the POSIX API in the -pcreposix -page. -

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcre_dfa_exec.html b/libs/pcre/doc/html/pcre_dfa_exec.html deleted file mode 100644 index a243ee8175..0000000000 --- a/libs/pcre/doc/html/pcre_dfa_exec.html +++ /dev/null @@ -1,98 +0,0 @@ - - -pcre_dfa_exec specification - - -

pcre_dfa_exec man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-
-SYNOPSIS -
-

-#include <pcre.h> -

-

-int pcre_dfa_exec(const pcre *code, const pcre_extra *extra, -const char *subject, int length, int startoffset, -int options, int *ovector, int ovecsize, -int *workspace, int wscount); -

-
-DESCRIPTION -
-

-This function matches a compiled regular expression against a given subject -string, using an alternative matching algorithm that scans the subject string -just once (not Perl-compatible). Note that the main, Perl-compatible, -matching function is pcre_exec(). The arguments for this function are: -

-  code         Points to the compiled pattern
-  extra        Points to an associated pcre_extra structure,
-                 or is NULL
-  subject      Points to the subject string
-  length       Length of the subject string, in bytes
-  startoffset  Offset in bytes in the subject at which to
-                 start matching
-  options      Option bits
-  ovector      Points to a vector of ints for result offsets
-  ovecsize     Number of elements in the vector
-  workspace    Points to a vector of ints used as working space
-  wscount      Number of elements in the vector
-
-The options are: -
-  PCRE_ANCHORED      Match only at the first position
-  PCRE_BSR_ANYCRLF   \R matches only CR, LF, or CRLF
-  PCRE_BSR_UNICODE   \R matches all Unicode line endings
-  PCRE_NEWLINE_ANY   Recognize any Unicode newline sequence
-  PCRE_NEWLINE_ANYCRLF  Recognize CR, LF, and CRLF as newline sequences
-  PCRE_NEWLINE_CR    Set CR as the newline sequence
-  PCRE_NEWLINE_CRLF  Set CRLF as the newline sequence
-  PCRE_NEWLINE_LF    Set LF as the newline sequence
-  PCRE_NOTBOL        Subject is not the beginning of a line
-  PCRE_NOTEOL        Subject is not the end of a line
-  PCRE_NOTEMPTY      An empty string is not a valid match
-  PCRE_NO_START_OPTIMIZE  Do not do "start-match" optimizations
-  PCRE_NO_UTF8_CHECK Do not check the subject for UTF-8
-                       validity (only relevant if PCRE_UTF8
-                       was set at compile time)
-  PCRE_PARTIAL       Return PCRE_ERROR_PARTIAL for a partial match
-  PCRE_DFA_SHORTEST  Return only the shortest match
-  PCRE_DFA_RESTART   This is a restart after a partial match
-
-There are restrictions on what may appear in a pattern when using this matching -function. Details are given in the -pcrematching -documentation. -

-

-A pcre_extra structure contains the following fields: -

-  flags        Bits indicating which fields are set
-  study_data   Opaque data from pcre_study()
-  match_limit  Limit on internal resource use
-  match_limit_recursion  Limit on internal recursion depth
-  callout_data Opaque data passed back to callouts
-  tables       Points to character tables or is NULL
-
-The flag bits are PCRE_EXTRA_STUDY_DATA, PCRE_EXTRA_MATCH_LIMIT, -PCRE_EXTRA_MATCH_LIMIT_RECURSION, PCRE_EXTRA_CALLOUT_DATA, and -PCRE_EXTRA_TABLES. For this matching function, the match_limit and -match_limit_recursion fields are not used, and must not be set. -

-

-There is a complete description of the PCRE native API in the -pcreapi -page and a description of the POSIX API in the -pcreposix -page. -

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcre_exec.html b/libs/pcre/doc/html/pcre_exec.html deleted file mode 100644 index ef43830dfc..0000000000 --- a/libs/pcre/doc/html/pcre_exec.html +++ /dev/null @@ -1,91 +0,0 @@ - - -pcre_exec specification - - -

pcre_exec man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-
-SYNOPSIS -
-

-#include <pcre.h> -

-

-int pcre_exec(const pcre *code, const pcre_extra *extra, -const char *subject, int length, int startoffset, -int options, int *ovector, int ovecsize); -

-
-DESCRIPTION -
-

-This function matches a compiled regular expression against a given subject -string, using a matching algorithm that is similar to Perl's. It returns -offsets to captured substrings. Its arguments are: -

-  code         Points to the compiled pattern
-  extra        Points to an associated pcre_extra structure,
-                 or is NULL
-  subject      Points to the subject string
-  length       Length of the subject string, in bytes
-  startoffset  Offset in bytes in the subject at which to
-                 start matching
-  options      Option bits
-  ovector      Points to a vector of ints for result offsets
-  ovecsize     Number of elements in the vector (a multiple of 3)
-
-The options are: -
-  PCRE_ANCHORED      Match only at the first position
-  PCRE_BSR_ANYCRLF   \R matches only CR, LF, or CRLF
-  PCRE_BSR_UNICODE   \R matches all Unicode line endings
-  PCRE_NEWLINE_ANY   Recognize any Unicode newline sequence
-  PCRE_NEWLINE_ANYCRLF  Recognize CR, LF, and CRLF as newline sequences
-  PCRE_NEWLINE_CR    Set CR as the newline sequence
-  PCRE_NEWLINE_CRLF  Set CRLF as the newline sequence
-  PCRE_NEWLINE_LF    Set LF as the newline sequence
-  PCRE_NOTBOL        Subject is not the beginning of a line
-  PCRE_NOTEOL        Subject is not the end of a line
-  PCRE_NOTEMPTY      An empty string is not a valid match
-  PCRE_NO_START_OPTIMIZE  Do not do "start-match" optimizations
-  PCRE_NO_UTF8_CHECK Do not check the subject for UTF-8
-                       validity (only relevant if PCRE_UTF8
-                       was set at compile time)
-  PCRE_PARTIAL       Return PCRE_ERROR_PARTIAL for a partial match
-
-There are restrictions on what may appear in a pattern when partial matching is -requested. For details, see the -pcrepartial -page. -

-

-A pcre_extra structure contains the following fields: -

-  flags        Bits indicating which fields are set
-  study_data   Opaque data from pcre_study()
-  match_limit  Limit on internal resource use
-  match_limit_recursion  Limit on internal recursion depth
-  callout_data Opaque data passed back to callouts
-  tables       Points to character tables or is NULL
-
-The flag bits are PCRE_EXTRA_STUDY_DATA, PCRE_EXTRA_MATCH_LIMIT, -PCRE_EXTRA_MATCH_LIMIT_RECURSION, PCRE_EXTRA_CALLOUT_DATA, and -PCRE_EXTRA_TABLES. -

-

-There is a complete description of the PCRE native API in the -pcreapi -page and a description of the POSIX API in the -pcreposix -page. -

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcre_free_substring.html b/libs/pcre/doc/html/pcre_free_substring.html deleted file mode 100644 index fe6261474c..0000000000 --- a/libs/pcre/doc/html/pcre_free_substring.html +++ /dev/null @@ -1,40 +0,0 @@ - - -pcre_free_substring specification - - -

pcre_free_substring man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-
-SYNOPSIS -
-

-#include <pcre.h> -

-

-void pcre_free_substring(const char *stringptr); -

-
-DESCRIPTION -
-

-This is a convenience function for freeing the store obtained by a previous -call to pcre_get_substring() or pcre_get_named_substring(). Its -only argument is a pointer to the string. -

-

-There is a complete description of the PCRE native API in the -pcreapi -page and a description of the POSIX API in the -pcreposix -page. -

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcre_free_substring_list.html b/libs/pcre/doc/html/pcre_free_substring_list.html deleted file mode 100644 index a92c9603f0..0000000000 --- a/libs/pcre/doc/html/pcre_free_substring_list.html +++ /dev/null @@ -1,40 +0,0 @@ - - -pcre_free_substring_list specification - - -

pcre_free_substring_list man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-
-SYNOPSIS -
-

-#include <pcre.h> -

-

-void pcre_free_substring_list(const char **stringptr); -

-
-DESCRIPTION -
-

-This is a convenience function for freeing the store obtained by a previous -call to pcre_get_substring_list(). Its only argument is a pointer to the -list of string pointers. -

-

-There is a complete description of the PCRE native API in the -pcreapi -page and a description of the POSIX API in the -pcreposix -page. -

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcre_fullinfo.html b/libs/pcre/doc/html/pcre_fullinfo.html deleted file mode 100644 index 48fddf5c2b..0000000000 --- a/libs/pcre/doc/html/pcre_fullinfo.html +++ /dev/null @@ -1,72 +0,0 @@ - - -pcre_fullinfo specification - - -

pcre_fullinfo man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-
-SYNOPSIS -
-

-#include <pcre.h> -

-

-int pcre_fullinfo(const pcre *code, const pcre_extra *extra, -int what, void *where); -

-
-DESCRIPTION -
-

-This function returns information about a compiled pattern. Its arguments are: -

-  code                      Compiled regular expression
-  extra                     Result of pcre_study() or NULL
-  what                      What information is required
-  where                     Where to put the information
-
-The following information is available: -
-  PCRE_INFO_BACKREFMAX      Number of highest back reference
-  PCRE_INFO_CAPTURECOUNT    Number of capturing subpatterns
-  PCRE_INFO_DEFAULT_TABLES  Pointer to default tables
-  PCRE_INFO_FIRSTBYTE       Fixed first byte for a match, or
-                              -1 for start of string
-                                 or after newline, or
-                              -2 otherwise
-  PCRE_INFO_FIRSTTABLE      Table of first bytes (after studying)
-  PCRE_INFO_JCHANGED        Return 1 if (?J) or (?-J) was used
-  PCRE_INFO_LASTLITERAL     Literal last byte required
-  PCRE_INFO_NAMECOUNT       Number of named subpatterns
-  PCRE_INFO_NAMEENTRYSIZE   Size of name table entry
-  PCRE_INFO_NAMETABLE       Pointer to name table
-  PCRE_INFO_OKPARTIAL       Return 1 if partial matching can be tried
-  PCRE_INFO_OPTIONS         Option bits used for compilation
-  PCRE_INFO_SIZE            Size of compiled pattern
-  PCRE_INFO_STUDYSIZE       Size of study data
-
-The yield of the function is zero on success or: -
-  PCRE_ERROR_NULL           the argument code was NULL
-                            the argument where was NULL
-  PCRE_ERROR_BADMAGIC       the "magic number" was not found
-  PCRE_ERROR_BADOPTION      the value of what was invalid
-
-

-

-There is a complete description of the PCRE native API in the -pcreapi -page and a description of the POSIX API in the -pcreposix -page. -

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcre_get_named_substring.html b/libs/pcre/doc/html/pcre_get_named_substring.html deleted file mode 100644 index 24dc058260..0000000000 --- a/libs/pcre/doc/html/pcre_get_named_substring.html +++ /dev/null @@ -1,55 +0,0 @@ - - -pcre_get_named_substring specification - - -

pcre_get_named_substring man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-
-SYNOPSIS -
-

-#include <pcre.h> -

-

-int pcre_get_named_substring(const pcre *code, -const char *subject, int *ovector, -int stringcount, const char *stringname, -const char **stringptr); -

-
-DESCRIPTION -
-

-This is a convenience function for extracting a captured substring by name. The -arguments are: -

-  code          Compiled pattern
-  subject       Subject that has been successfully matched
-  ovector       Offset vector that pcre_exec() used
-  stringcount   Value returned by pcre_exec()
-  stringname    Name of the required substring
-  stringptr     Where to put the string pointer
-
-The memory in which the substring is placed is obtained by calling -pcre_malloc(). The convenience function pcre_free_substring() can -be used to free it when it is no longer needed. The yield of the function is -the length of the extracted substring, PCRE_ERROR_NOMEMORY if sufficient memory -could not be obtained, or PCRE_ERROR_NOSUBSTRING if the string name is invalid. -

-

-There is a complete description of the PCRE native API in the -pcreapi -page and a description of the POSIX API in the -pcreposix -page. -

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcre_get_stringnumber.html b/libs/pcre/doc/html/pcre_get_stringnumber.html deleted file mode 100644 index 43af3aaed8..0000000000 --- a/libs/pcre/doc/html/pcre_get_stringnumber.html +++ /dev/null @@ -1,49 +0,0 @@ - - -pcre_get_stringnumber specification - - -

pcre_get_stringnumber man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-
-SYNOPSIS -
-

-#include <pcre.h> -

-

-int pcre_get_stringnumber(const pcre *code, -const char *name); -

-
-DESCRIPTION -
-

-This convenience function finds the number of a named substring capturing -parenthesis in a compiled pattern. Its arguments are: -

-  code    Compiled regular expression
-  name    Name whose number is required
-
-The yield of the function is the number of the parenthesis if the name is -found, or PCRE_ERROR_NOSUBSTRING otherwise. When duplicate names are allowed -(PCRE_DUPNAMES is set), it is not defined which of the numbers is returned by -pcre_get_stringnumber(). You can obtain the complete list by calling -pcre_get_stringtable_entries(). -

-

-There is a complete description of the PCRE native API in the -pcreapi -page and a description of the POSIX API in the -pcreposix -page. -

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcre_get_stringtable_entries.html b/libs/pcre/doc/html/pcre_get_stringtable_entries.html deleted file mode 100644 index dc20ffd22c..0000000000 --- a/libs/pcre/doc/html/pcre_get_stringtable_entries.html +++ /dev/null @@ -1,52 +0,0 @@ - - -pcre_get_stringtable_entries specification - - -

pcre_get_stringtable_entries man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-
-SYNOPSIS -
-

-#include <pcre.h> -

-

-int pcre_get_stringtable_entries(const pcre *code, -const char *name, char **first, char **last); -

-
-DESCRIPTION -
-

-This convenience function finds, for a compiled pattern, the first and last -entries for a given name in the table that translates capturing parenthesis -names into numbers. When names are required to be unique (PCRE_DUPNAMES is -not set), it is usually easier to use pcre_get_stringnumber() -instead. -

-  code    Compiled regular expression
-  name    Name whose entries required
-  first   Where to return a pointer to the first entry
-  last    Where to return a pointer to the last entry
-
-The yield of the function is the length of each entry, or -PCRE_ERROR_NOSUBSTRING if none are found. -

-

-There is a complete description of the PCRE native API, including the format of -the table entries, in the -pcreapi -page, and a description of the POSIX API in the -pcreposix -page. -

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcre_get_substring.html b/libs/pcre/doc/html/pcre_get_substring.html deleted file mode 100644 index 9b40e4dfed..0000000000 --- a/libs/pcre/doc/html/pcre_get_substring.html +++ /dev/null @@ -1,53 +0,0 @@ - - -pcre_get_substring specification - - -

pcre_get_substring man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-
-SYNOPSIS -
-

-#include <pcre.h> -

-

-int pcre_get_substring(const char *subject, int *ovector, -int stringcount, int stringnumber, -const char **stringptr); -

-
-DESCRIPTION -
-

-This is a convenience function for extracting a captured substring. The -arguments are: -

-  subject       Subject that has been successfully matched
-  ovector       Offset vector that pcre_exec() used
-  stringcount   Value returned by pcre_exec()
-  stringnumber  Number of the required substring
-  stringptr     Where to put the string pointer
-
-The memory in which the substring is placed is obtained by calling -pcre_malloc(). The convenience function pcre_free_substring() can -be used to free it when it is no longer needed. The yield of the function is -the length of the substring, PCRE_ERROR_NOMEMORY if sufficient memory could not -be obtained, or PCRE_ERROR_NOSUBSTRING if the string number is invalid. -

-

-There is a complete description of the PCRE native API in the -pcreapi -page and a description of the POSIX API in the -pcreposix -page. -

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcre_get_substring_list.html b/libs/pcre/doc/html/pcre_get_substring_list.html deleted file mode 100644 index 617a3151d3..0000000000 --- a/libs/pcre/doc/html/pcre_get_substring_list.html +++ /dev/null @@ -1,53 +0,0 @@ - - -pcre_get_substring_list specification - - -

pcre_get_substring_list man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-
-SYNOPSIS -
-

-#include <pcre.h> -

-

-int pcre_get_substring_list(const char *subject, -int *ovector, int stringcount, const char ***listptr); -

-
-DESCRIPTION -
-

-This is a convenience function for extracting a list of all the captured -substrings. The arguments are: -

-  subject       Subject that has been successfully matched
-  ovector       Offset vector that pcre_exec used
-  stringcount   Value returned by pcre_exec
-  listptr       Where to put a pointer to the list
-
-The memory in which the substrings and the list are placed is obtained by -calling pcre_malloc(). The convenience function -pcre_free_substring_list() can be used to free it when it is no longer -needed. A pointer to a list of pointers is put in the variable whose address is -in listptr. The list is terminated by a NULL pointer. The yield of the -function is zero on success or PCRE_ERROR_NOMEMORY if sufficient memory could -not be obtained. -

-

-There is a complete description of the PCRE native API in the -pcreapi -page and a description of the POSIX API in the -pcreposix -page. -

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcre_info.html b/libs/pcre/doc/html/pcre_info.html deleted file mode 100644 index 6693ffee6c..0000000000 --- a/libs/pcre/doc/html/pcre_info.html +++ /dev/null @@ -1,39 +0,0 @@ - - -pcre_info specification - - -

pcre_info man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-
-SYNOPSIS -
-

-#include <pcre.h> -

-

-int pcre_info(const pcre *code, int *optptr, int -*firstcharptr); -

-
-DESCRIPTION -
-

-This function is obsolete. You should be using pcre_fullinfo() instead. -

-

-There is a complete description of the PCRE native API in the -pcreapi -page and a description of the POSIX API in the -pcreposix -page. -

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcre_maketables.html b/libs/pcre/doc/html/pcre_maketables.html deleted file mode 100644 index cf8d69ecfd..0000000000 --- a/libs/pcre/doc/html/pcre_maketables.html +++ /dev/null @@ -1,42 +0,0 @@ - - -pcre_maketables specification - - -

pcre_maketables man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-
-SYNOPSIS -
-

-#include <pcre.h> -

-

-const unsigned char *pcre_maketables(void); -

-
-DESCRIPTION -
-

-This function builds a set of character tables for character values less than -256. These can be passed to pcre_compile() to override PCRE's internal, -built-in tables (which were made by pcre_maketables() when PCRE was -compiled). You might want to do this if you are using a non-standard locale. -The function yields a pointer to the tables. -

-

-There is a complete description of the PCRE native API in the -pcreapi -page and a description of the POSIX API in the -pcreposix -page. -

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcre_refcount.html b/libs/pcre/doc/html/pcre_refcount.html deleted file mode 100644 index b748df2f1d..0000000000 --- a/libs/pcre/doc/html/pcre_refcount.html +++ /dev/null @@ -1,45 +0,0 @@ - - -pcre_refcount specification - - -

pcre_refcount man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-
-SYNOPSIS -
-

-#include <pcre.h> -

-

-int pcre_refcount(pcre *code, int adjust); -

-
-DESCRIPTION -
-

-This function is used to maintain a reference count inside a data block that -contains a compiled pattern. Its arguments are: -

-  code                      Compiled regular expression
-  adjust                    Adjustment to reference value
-
-The yield of the function is the adjusted reference value, which is constrained -to lie between 0 and 65535. -

-

-There is a complete description of the PCRE native API in the -pcreapi -page and a description of the POSIX API in the -pcreposix -page. -

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcre_study.html b/libs/pcre/doc/html/pcre_study.html deleted file mode 100644 index d290420e54..0000000000 --- a/libs/pcre/doc/html/pcre_study.html +++ /dev/null @@ -1,56 +0,0 @@ - - -pcre_study specification - - -

pcre_study man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-
-SYNOPSIS -
-

-#include <pcre.h> -

-

-pcre_extra *pcre_study(const pcre *code, int options, -const char **errptr); -

-
-DESCRIPTION -
-

-This function studies a compiled pattern, to see if additional information can -be extracted that might speed up matching. Its arguments are: -

-  code       A compiled regular expression
-  options    Options for pcre_study()
-  errptr     Where to put an error message
-
-If the function succeeds, it returns a value that can be passed to -pcre_exec() via its extra argument. -

-

-If the function returns NULL, either it could not find any additional -information, or there was an error. You can tell the difference by looking at -the error value. It is NULL in first case. -

-

-There are currently no options defined; the value of the second argument should -always be zero. -

-

-There is a complete description of the PCRE native API in the -pcreapi -page and a description of the POSIX API in the -pcreposix -page. -

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcre_version.html b/libs/pcre/doc/html/pcre_version.html deleted file mode 100644 index 7bc8f8653e..0000000000 --- a/libs/pcre/doc/html/pcre_version.html +++ /dev/null @@ -1,39 +0,0 @@ - - -pcre_version specification - - -

pcre_version man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-
-SYNOPSIS -
-

-#include <pcre.h> -

-

-char *pcre_version(void); -

-
-DESCRIPTION -
-

-This function returns a character string that gives the version number of the -PCRE library and the date of its release. -

-

-There is a complete description of the PCRE native API in the -pcreapi -page and a description of the POSIX API in the -pcreposix -page. -

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcreapi.html b/libs/pcre/doc/html/pcreapi.html deleted file mode 100644 index 91273de2e2..0000000000 --- a/libs/pcre/doc/html/pcreapi.html +++ /dev/null @@ -1,2005 +0,0 @@ - - -pcreapi specification - - -

pcreapi man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-

-
PCRE NATIVE API
-

-#include <pcre.h> -

-

-pcre *pcre_compile(const char *pattern, int options, -const char **errptr, int *erroffset, -const unsigned char *tableptr); -

-

-pcre *pcre_compile2(const char *pattern, int options, -int *errorcodeptr, -const char **errptr, int *erroffset, -const unsigned char *tableptr); -

-

-pcre_extra *pcre_study(const pcre *code, int options, -const char **errptr); -

-

-int pcre_exec(const pcre *code, const pcre_extra *extra, -const char *subject, int length, int startoffset, -int options, int *ovector, int ovecsize); -

-

-int pcre_dfa_exec(const pcre *code, const pcre_extra *extra, -const char *subject, int length, int startoffset, -int options, int *ovector, int ovecsize, -int *workspace, int wscount); -

-

-int pcre_copy_named_substring(const pcre *code, -const char *subject, int *ovector, -int stringcount, const char *stringname, -char *buffer, int buffersize); -

-

-int pcre_copy_substring(const char *subject, int *ovector, -int stringcount, int stringnumber, char *buffer, -int buffersize); -

-

-int pcre_get_named_substring(const pcre *code, -const char *subject, int *ovector, -int stringcount, const char *stringname, -const char **stringptr); -

-

-int pcre_get_stringnumber(const pcre *code, -const char *name); -

-

-int pcre_get_stringtable_entries(const pcre *code, -const char *name, char **first, char **last); -

-

-int pcre_get_substring(const char *subject, int *ovector, -int stringcount, int stringnumber, -const char **stringptr); -

-

-int pcre_get_substring_list(const char *subject, -int *ovector, int stringcount, const char ***listptr); -

-

-void pcre_free_substring(const char *stringptr); -

-

-void pcre_free_substring_list(const char **stringptr); -

-

-const unsigned char *pcre_maketables(void); -

-

-int pcre_fullinfo(const pcre *code, const pcre_extra *extra, -int what, void *where); -

-

-int pcre_info(const pcre *code, int *optptr, int -*firstcharptr); -

-

-int pcre_refcount(pcre *code, int adjust); -

-

-int pcre_config(int what, void *where); -

-

-char *pcre_version(void); -

-

-void *(*pcre_malloc)(size_t); -

-

-void (*pcre_free)(void *); -

-

-void *(*pcre_stack_malloc)(size_t); -

-

-void (*pcre_stack_free)(void *); -

-

-int (*pcre_callout)(pcre_callout_block *); -

-
PCRE API OVERVIEW
-

-PCRE has its own native API, which is described in this document. There are -also some wrapper functions that correspond to the POSIX regular expression -API. These are described in the -pcreposix -documentation. Both of these APIs define a set of C function calls. A C++ -wrapper is distributed with PCRE. It is documented in the -pcrecpp -page. -

-

-The native API C function prototypes are defined in the header file -pcre.h, and on Unix systems the library itself is called libpcre. -It can normally be accessed by adding -lpcre to the command for linking -an application that uses PCRE. The header file defines the macros PCRE_MAJOR -and PCRE_MINOR to contain the major and minor release numbers for the library. -Applications can use these to include support for different releases of PCRE. -

-

-The functions pcre_compile(), pcre_compile2(), pcre_study(), -and pcre_exec() are used for compiling and matching regular expressions -in a Perl-compatible manner. A sample program that demonstrates the simplest -way of using them is provided in the file called pcredemo.c in the source -distribution. The -pcresample -documentation describes how to compile and run it. -

-

-A second matching function, pcre_dfa_exec(), which is not -Perl-compatible, is also provided. This uses a different algorithm for the -matching. The alternative algorithm finds all possible matches (at a given -point in the subject), and scans the subject just once. However, this algorithm -does not return captured substrings. A description of the two matching -algorithms and their advantages and disadvantages is given in the -pcrematching -documentation. -

-

-In addition to the main compiling and matching functions, there are convenience -functions for extracting captured substrings from a subject string that is -matched by pcre_exec(). They are: -

-  pcre_copy_substring()
-  pcre_copy_named_substring()
-  pcre_get_substring()
-  pcre_get_named_substring()
-  pcre_get_substring_list()
-  pcre_get_stringnumber()
-  pcre_get_stringtable_entries()
-
-pcre_free_substring() and pcre_free_substring_list() are also -provided, to free the memory used for extracted strings. -

-

-The function pcre_maketables() is used to build a set of character tables -in the current locale for passing to pcre_compile(), pcre_exec(), -or pcre_dfa_exec(). This is an optional facility that is provided for -specialist use. Most commonly, no special tables are passed, in which case -internal tables that are generated when PCRE is built are used. -

-

-The function pcre_fullinfo() is used to find out information about a -compiled pattern; pcre_info() is an obsolete version that returns only -some of the available information, but is retained for backwards compatibility. -The function pcre_version() returns a pointer to a string containing the -version of PCRE and its date of release. -

-

-The function pcre_refcount() maintains a reference count in a data block -containing a compiled pattern. This is provided for the benefit of -object-oriented applications. -

-

-The global variables pcre_malloc and pcre_free initially contain -the entry points of the standard malloc() and free() functions, -respectively. PCRE calls the memory management functions via these variables, -so a calling program can replace them if it wishes to intercept the calls. This -should be done before calling any PCRE functions. -

-

-The global variables pcre_stack_malloc and pcre_stack_free are also -indirections to memory management functions. These special functions are used -only when PCRE is compiled to use the heap for remembering data, instead of -recursive function calls, when running the pcre_exec() function. See the -pcrebuild -documentation for details of how to do this. It is a non-standard way of -building PCRE, for use in environments that have limited stacks. Because of the -greater use of memory management, it runs more slowly. Separate functions are -provided so that special-purpose external code can be used for this case. When -used, these functions are always called in a stack-like manner (last obtained, -first freed), and always for memory blocks of the same size. There is a -discussion about PCRE's stack usage in the -pcrestack -documentation. -

-

-The global variable pcre_callout initially contains NULL. It can be set -by the caller to a "callout" function, which PCRE will then call at specified -points during a matching operation. Details are given in the -pcrecallout -documentation. -

-
NEWLINES
-

-PCRE supports five different conventions for indicating line breaks in -strings: a single CR (carriage return) character, a single LF (linefeed) -character, the two-character sequence CRLF, any of the three preceding, or any -Unicode newline sequence. The Unicode newline sequences are the three just -mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed, -U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS -(paragraph separator, U+2029). -

-

-Each of the first three conventions is used by at least one operating system as -its standard newline sequence. When PCRE is built, a default can be specified. -The default default is LF, which is the Unix standard. When PCRE is run, the -default can be overridden, either when a pattern is compiled, or when it is -matched. -

-

-At compile time, the newline convention can be specified by the options -argument of pcre_compile(), or it can be specified by special text at the -start of the pattern itself; this overrides any other settings. See the -pcrepattern -page for details of the special character sequences. -

-

-In the PCRE documentation the word "newline" is used to mean "the character or -pair of characters that indicate a line break". The choice of newline -convention affects the handling of the dot, circumflex, and dollar -metacharacters, the handling of #-comments in /x mode, and, when CRLF is a -recognized line ending sequence, the match position advancement for a -non-anchored pattern. There is more detail about this in the -section on pcre_exec() options -below. -

-

-The choice of newline convention does not affect the interpretation of -the \n or \r escape sequences, nor does it affect what \R matches, which is -controlled in a similar way, but by separate options. -

-
MULTITHREADING
-

-The PCRE functions can be used in multi-threading applications, with the -proviso that the memory management functions pointed to by pcre_malloc, -pcre_free, pcre_stack_malloc, and pcre_stack_free, and the -callout function pointed to by pcre_callout, are shared by all threads. -

-

-The compiled form of a regular expression is not altered during matching, so -the same compiled pattern can safely be used by several threads at once. -

-
SAVING PRECOMPILED PATTERNS FOR LATER USE
-

-The compiled form of a regular expression can be saved and re-used at a later -time, possibly by a different program, and even on a host other than the one on -which it was compiled. Details are given in the -pcreprecompile -documentation. However, compiling a regular expression with one version of PCRE -for use with a different version is not guaranteed to work and may cause -crashes. -

-
CHECKING BUILD-TIME OPTIONS
-

-int pcre_config(int what, void *where); -

-

-The function pcre_config() makes it possible for a PCRE client to -discover which optional features have been compiled into the PCRE library. The -pcrebuild -documentation has more details about these optional features. -

-

-The first argument for pcre_config() is an integer, specifying which -information is required; the second argument is a pointer to a variable into -which the information is placed. The following information is available: -

-  PCRE_CONFIG_UTF8
-
-The output is an integer that is set to one if UTF-8 support is available; -otherwise it is set to zero. -
-  PCRE_CONFIG_UNICODE_PROPERTIES
-
-The output is an integer that is set to one if support for Unicode character -properties is available; otherwise it is set to zero. -
-  PCRE_CONFIG_NEWLINE
-
-The output is an integer whose value specifies the default character sequence -that is recognized as meaning "newline". The four values that are supported -are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, and -1 for ANY. -Though they are derived from ASCII, the same values are returned in EBCDIC -environments. The default should normally correspond to the standard sequence -for your operating system. -
-  PCRE_CONFIG_BSR
-
-The output is an integer whose value indicates what character sequences the \R -escape sequence matches by default. A value of 0 means that \R matches any -Unicode line ending sequence; a value of 1 means that \R matches only CR, LF, -or CRLF. The default can be overridden when a pattern is compiled or matched. -
-  PCRE_CONFIG_LINK_SIZE
-
-The output is an integer that contains the number of bytes used for internal -linkage in compiled regular expressions. The value is 2, 3, or 4. Larger values -allow larger regular expressions to be compiled, at the expense of slower -matching. The default value of 2 is sufficient for all but the most massive -patterns, since it allows the compiled pattern to be up to 64K in size. -
-  PCRE_CONFIG_POSIX_MALLOC_THRESHOLD
-
-The output is an integer that contains the threshold above which the POSIX -interface uses malloc() for output vectors. Further details are given in -the -pcreposix -documentation. -
-  PCRE_CONFIG_MATCH_LIMIT
-
-The output is a long integer that gives the default limit for the number of -internal matching function calls in a pcre_exec() execution. Further -details are given with pcre_exec() below. -
-  PCRE_CONFIG_MATCH_LIMIT_RECURSION
-
-The output is a long integer that gives the default limit for the depth of -recursion when calling the internal matching function in a pcre_exec() -execution. Further details are given with pcre_exec() below. -
-  PCRE_CONFIG_STACKRECURSE
-
-The output is an integer that is set to one if internal recursion when running -pcre_exec() is implemented by recursive function calls that use the stack -to remember their state. This is the usual way that PCRE is compiled. The -output is zero if PCRE was compiled to use blocks of data on the heap instead -of recursive function calls. In this case, pcre_stack_malloc and -pcre_stack_free are called to manage memory blocks on the heap, thus -avoiding the use of the stack. -

-
COMPILING A PATTERN
-

-pcre *pcre_compile(const char *pattern, int options, -const char **errptr, int *erroffset, -const unsigned char *tableptr); -pcre *pcre_compile2(const char *pattern, int options, -int *errorcodeptr, -const char **errptr, int *erroffset, -const unsigned char *tableptr); -

-

-Either of the functions pcre_compile() or pcre_compile2() can be -called to compile a pattern into an internal form. The only difference between -the two interfaces is that pcre_compile2() has an additional argument, -errorcodeptr, via which a numerical error code can be returned. -

-

-The pattern is a C string terminated by a binary zero, and is passed in the -pattern argument. A pointer to a single block of memory that is obtained -via pcre_malloc is returned. This contains the compiled code and related -data. The pcre type is defined for the returned block; this is a typedef -for a structure whose contents are not externally defined. It is up to the -caller to free the memory (via pcre_free) when it is no longer required. -

-

-Although the compiled code of a PCRE regex is relocatable, that is, it does not -depend on memory location, the complete pcre data block is not -fully relocatable, because it may contain a copy of the tableptr -argument, which is an address (see below). -

-

-The options argument contains various bit settings that affect the -compilation. It should be zero if no options are required. The available -options are described below. Some of them (in particular, those that are -compatible with Perl, but also some others) can also be set and unset from -within the pattern (see the detailed description in the -pcrepattern -documentation). For those options that can be different in different parts of -the pattern, the contents of the options argument specifies their initial -settings at the start of compilation and execution. The PCRE_ANCHORED and -PCRE_NEWLINE_xxx options can be set at the time of matching as well as at -compile time. -

-

-If errptr is NULL, pcre_compile() returns NULL immediately. -Otherwise, if compilation of a pattern fails, pcre_compile() returns -NULL, and sets the variable pointed to by errptr to point to a textual -error message. This is a static string that is part of the library. You must -not try to free it. The offset from the start of the pattern to the character -where the error was discovered is placed in the variable pointed to by -erroffset, which must not be NULL. If it is, an immediate error is given. -

-

-If pcre_compile2() is used instead of pcre_compile(), and the -errorcodeptr argument is not NULL, a non-zero error code number is -returned via this argument in the event of an error. This is in addition to the -textual error message. Error codes and messages are listed below. -

-

-If the final argument, tableptr, is NULL, PCRE uses a default set of -character tables that are built when PCRE is compiled, using the default C -locale. Otherwise, tableptr must be an address that is the result of a -call to pcre_maketables(). This value is stored with the compiled -pattern, and used again by pcre_exec(), unless another table pointer is -passed to it. For more discussion, see the section on locale support below. -

-

-This code fragment shows a typical straightforward call to pcre_compile(): -

-  pcre *re;
-  const char *error;
-  int erroffset;
-  re = pcre_compile(
-    "^A.*Z",          /* the pattern */
-    0,                /* default options */
-    &error,           /* for error message */
-    &erroffset,       /* for error offset */
-    NULL);            /* use default character tables */
-
-The following names for option bits are defined in the pcre.h header -file: -
-  PCRE_ANCHORED
-
-If this bit is set, the pattern is forced to be "anchored", that is, it is -constrained to match only at the first matching point in the string that is -being searched (the "subject string"). This effect can also be achieved by -appropriate constructs in the pattern itself, which is the only way to do it in -Perl. -
-  PCRE_AUTO_CALLOUT
-
-If this bit is set, pcre_compile() automatically inserts callout items, -all with number 255, before each pattern item. For discussion of the callout -facility, see the -pcrecallout -documentation. -
-  PCRE_BSR_ANYCRLF
-  PCRE_BSR_UNICODE
-
-These options (which are mutually exclusive) control what the \R escape -sequence matches. The choice is either to match only CR, LF, or CRLF, or to -match any Unicode newline sequence. The default is specified when PCRE is -built. It can be overridden from within the pattern, or by setting an option -when a compiled pattern is matched. -
-  PCRE_CASELESS
-
-If this bit is set, letters in the pattern match both upper and lower case -letters. It is equivalent to Perl's /i option, and it can be changed within a -pattern by a (?i) option setting. In UTF-8 mode, PCRE always understands the -concept of case for characters whose values are less than 128, so caseless -matching is always possible. For characters with higher values, the concept of -case is supported if PCRE is compiled with Unicode property support, but not -otherwise. If you want to use caseless matching for characters 128 and above, -you must ensure that PCRE is compiled with Unicode property support as well as -with UTF-8 support. -
-  PCRE_DOLLAR_ENDONLY
-
-If this bit is set, a dollar metacharacter in the pattern matches only at the -end of the subject string. Without this option, a dollar also matches -immediately before a newline at the end of the string (but not before any other -newlines). The PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is set. -There is no equivalent to this option in Perl, and no way to set it within a -pattern. -
-  PCRE_DOTALL
-
-If this bit is set, a dot metacharater in the pattern matches all characters, -including those that indicate newline. Without it, a dot does not match when -the current position is at a newline. This option is equivalent to Perl's /s -option, and it can be changed within a pattern by a (?s) option setting. A -negative class such as [^a] always matches newline characters, independent of -the setting of this option. -
-  PCRE_DUPNAMES
-
-If this bit is set, names used to identify capturing subpatterns need not be -unique. This can be helpful for certain types of pattern when it is known that -only one instance of the named subpattern can ever be matched. There are more -details of named subpatterns below; see also the -pcrepattern -documentation. -
-  PCRE_EXTENDED
-
-If this bit is set, whitespace data characters in the pattern are totally -ignored except when escaped or inside a character class. Whitespace does not -include the VT character (code 11). In addition, characters between an -unescaped # outside a character class and the next newline, inclusive, are also -ignored. This is equivalent to Perl's /x option, and it can be changed within a -pattern by a (?x) option setting. -

-

-This option makes it possible to include comments inside complicated patterns. -Note, however, that this applies only to data characters. Whitespace characters -may never appear within special character sequences in a pattern, for example -within the sequence (?( which introduces a conditional subpattern. -

-  PCRE_EXTRA
-
-This option was invented in order to turn on additional functionality of PCRE -that is incompatible with Perl, but it is currently of very little use. When -set, any backslash in a pattern that is followed by a letter that has no -special meaning causes an error, thus reserving these combinations for future -expansion. By default, as in Perl, a backslash followed by a letter with no -special meaning is treated as a literal. (Perl can, however, be persuaded to -give a warning for this.) There are at present no other features controlled by -this option. It can also be set by a (?X) option setting within a pattern. -
-  PCRE_FIRSTLINE
-
-If this option is set, an unanchored pattern is required to match before or at -the first newline in the subject string, though the matched text may continue -over the newline. -
-  PCRE_JAVASCRIPT_COMPAT
-
-If this option is set, PCRE's behaviour is changed in some ways so that it is -compatible with JavaScript rather than Perl. The changes are as follows: -

-

-(1) A lone closing square bracket in a pattern causes a compile-time error, -because this is illegal in JavaScript (by default it is treated as a data -character). Thus, the pattern AB]CD becomes illegal when this option is set. -

-

-(2) At run time, a back reference to an unset subpattern group matches an empty -string (by default this causes the current matching alternative to fail). A -pattern such as (\1)(a) succeeds when this option is set (assuming it can find -an "a" in the subject), whereas it fails by default, for Perl compatibility. -

-  PCRE_MULTILINE
-
-By default, PCRE treats the subject string as consisting of a single line of -characters (even if it actually contains newlines). The "start of line" -metacharacter (^) matches only at the start of the string, while the "end of -line" metacharacter ($) matches only at the end of the string, or before a -terminating newline (unless PCRE_DOLLAR_ENDONLY is set). This is the same as -Perl. -

-

-When PCRE_MULTILINE it is set, the "start of line" and "end of line" constructs -match immediately following or immediately before internal newlines in the -subject string, respectively, as well as at the very start and end. This is -equivalent to Perl's /m option, and it can be changed within a pattern by a -(?m) option setting. If there are no newlines in a subject string, or no -occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect. -

-  PCRE_NEWLINE_CR
-  PCRE_NEWLINE_LF
-  PCRE_NEWLINE_CRLF
-  PCRE_NEWLINE_ANYCRLF
-  PCRE_NEWLINE_ANY
-
-These options override the default newline definition that was chosen when PCRE -was built. Setting the first or the second specifies that a newline is -indicated by a single character (CR or LF, respectively). Setting -PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character -CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three -preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies -that any Unicode newline sequence should be recognized. The Unicode newline -sequences are the three just mentioned, plus the single characters VT (vertical -tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line -separator, U+2028), and PS (paragraph separator, U+2029). The last two are -recognized only in UTF-8 mode. -

-

-The newline setting in the options word uses three bits that are treated -as a number, giving eight possibilities. Currently only six are used (default -plus the five values above). This means that if you set more than one newline -option, the combination may or may not be sensible. For example, -PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but -other combinations may yield unused numbers and cause an error. -

-

-The only time that a line break is specially recognized when compiling a -pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character -class is encountered. This indicates a comment that lasts until after the next -line break sequence. In other circumstances, line break sequences are treated -as literal data, except that in PCRE_EXTENDED mode, both CR and LF are treated -as whitespace characters and are therefore ignored. -

-

-The newline option that is set at compile time becomes the default that is used -for pcre_exec() and pcre_dfa_exec(), but it can be overridden. -

-  PCRE_NO_AUTO_CAPTURE
-
-If this option is set, it disables the use of numbered capturing parentheses in -the pattern. Any opening parenthesis that is not followed by ? behaves as if it -were followed by ?: but named parentheses can still be used for capturing (and -they acquire numbers in the usual way). There is no equivalent of this option -in Perl. -
-  PCRE_UNGREEDY
-
-This option inverts the "greediness" of the quantifiers so that they are not -greedy by default, but become greedy if followed by "?". It is not compatible -with Perl. It can also be set by a (?U) option setting within the pattern. -
-  PCRE_UTF8
-
-This option causes PCRE to regard both the pattern and the subject as strings -of UTF-8 characters instead of single-byte character strings. However, it is -available only when PCRE is built to include UTF-8 support. If not, the use -of this option provokes an error. Details of how this option changes the -behaviour of PCRE are given in the -section on UTF-8 support -in the main -pcre -page. -
-  PCRE_NO_UTF8_CHECK
-
-When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is -automatically checked. There is a discussion about the -validity of UTF-8 strings -in the main -pcre -page. If an invalid UTF-8 sequence of bytes is found, pcre_compile() -returns an error. If you already know that your pattern is valid, and you want -to skip this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK -option. When it is set, the effect of passing an invalid UTF-8 string as a -pattern is undefined. It may cause your program to crash. Note that this option -can also be passed to pcre_exec() and pcre_dfa_exec(), to suppress -the UTF-8 validity checking of subject strings. -

-
COMPILATION ERROR CODES
-

-The following table lists the error codes than may be returned by -pcre_compile2(), along with the error messages that may be returned by -both compiling functions. As PCRE has developed, some error codes have fallen -out of use. To avoid confusion, they have not been re-used. -

-   0  no error
-   1  \ at end of pattern
-   2  \c at end of pattern
-   3  unrecognized character follows \
-   4  numbers out of order in {} quantifier
-   5  number too big in {} quantifier
-   6  missing terminating ] for character class
-   7  invalid escape sequence in character class
-   8  range out of order in character class
-   9  nothing to repeat
-  10  [this code is not in use]
-  11  internal error: unexpected repeat
-  12  unrecognized character after (? or (?-
-  13  POSIX named classes are supported only within a class
-  14  missing )
-  15  reference to non-existent subpattern
-  16  erroffset passed as NULL
-  17  unknown option bit(s) set
-  18  missing ) after comment
-  19  [this code is not in use]
-  20  regular expression is too large
-  21  failed to get memory
-  22  unmatched parentheses
-  23  internal error: code overflow
-  24  unrecognized character after (?<
-  25  lookbehind assertion is not fixed length
-  26  malformed number or name after (?(
-  27  conditional group contains more than two branches
-  28  assertion expected after (?(
-  29  (?R or (?[+-]digits must be followed by )
-  30  unknown POSIX class name
-  31  POSIX collating elements are not supported
-  32  this version of PCRE is not compiled with PCRE_UTF8 support
-  33  [this code is not in use]
-  34  character value in \x{...} sequence is too large
-  35  invalid condition (?(0)
-  36  \C not allowed in lookbehind assertion
-  37  PCRE does not support \L, \l, \N, \U, or \u
-  38  number after (?C is > 255
-  39  closing ) for (?C expected
-  40  recursive call could loop indefinitely
-  41  unrecognized character after (?P
-  42  syntax error in subpattern name (missing terminator)
-  43  two named subpatterns have the same name
-  44  invalid UTF-8 string
-  45  support for \P, \p, and \X has not been compiled
-  46  malformed \P or \p sequence
-  47  unknown property name after \P or \p
-  48  subpattern name is too long (maximum 32 characters)
-  49  too many named subpatterns (maximum 10000)
-  50  [this code is not in use]
-  51  octal value is greater than \377 (not in UTF-8 mode)
-  52  internal error: overran compiling workspace
-  53  internal error: previously-checked referenced subpattern not found
-  54  DEFINE group contains more than one branch
-  55  repeating a DEFINE group is not allowed
-  56  inconsistent NEWLINE options
-  57  \g is not followed by a braced, angle-bracketed, or quoted
-        name/number or by a plain number
-  58  a numbered reference must not be zero
-  59  (*VERB) with an argument is not supported
-  60  (*VERB) not recognized
-  61  number is too big
-  62  subpattern name expected
-  63  digit expected after (?+
-  64  ] is an invalid data character in JavaScript compatibility mode
-
-The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may -be used if the limits were changed when PCRE was built. -

-
STUDYING A PATTERN
-

-pcre_extra *pcre_study(const pcre *code, int options -const char **errptr); -

-

-If a compiled pattern is going to be used several times, it is worth spending -more time analyzing it in order to speed up the time taken for matching. The -function pcre_study() takes a pointer to a compiled pattern as its first -argument. If studying the pattern produces additional information that will -help speed up matching, pcre_study() returns a pointer to a -pcre_extra block, in which the study_data field points to the -results of the study. -

-

-The returned value from pcre_study() can be passed directly to -pcre_exec(). However, a pcre_extra block also contains other -fields that can be set by the caller before the block is passed; these are -described -below -in the section on matching a pattern. -

-

-If studying the pattern does not produce any additional information -pcre_study() returns NULL. In that circumstance, if the calling program -wants to pass any of the other fields to pcre_exec(), it must set up its -own pcre_extra block. -

-

-The second argument of pcre_study() contains option bits. At present, no -options are defined, and this argument should always be zero. -

-

-The third argument for pcre_study() is a pointer for an error message. If -studying succeeds (even if no data is returned), the variable it points to is -set to NULL. Otherwise it is set to point to a textual error message. This is a -static string that is part of the library. You must not try to free it. You -should test the error pointer for NULL after calling pcre_study(), to be -sure that it has run successfully. -

-

-This is a typical call to pcre_study(): -

-  pcre_extra *pe;
-  pe = pcre_study(
-    re,             /* result of pcre_compile() */
-    0,              /* no options exist */
-    &error);        /* set to NULL or points to a message */
-
-At present, studying a pattern is useful only for non-anchored patterns that do -not have a single fixed starting character. A bitmap of possible starting -bytes is created. -

-
LOCALE SUPPORT
-

-PCRE handles caseless matching, and determines whether characters are letters, -digits, or whatever, by reference to a set of tables, indexed by character -value. When running in UTF-8 mode, this applies only to characters with codes -less than 128. Higher-valued codes never match escapes such as \w or \d, but -can be tested with \p if PCRE is built with Unicode character property -support. The use of locales with Unicode is discouraged. If you are handling -characters with codes greater than 128, you should either use UTF-8 and -Unicode, or use locales, but not try to mix the two. -

-

-PCRE contains an internal set of tables that are used when the final argument -of pcre_compile() is NULL. These are sufficient for many applications. -Normally, the internal tables recognize only ASCII characters. However, when -PCRE is built, it is possible to cause the internal tables to be rebuilt in the -default "C" locale of the local system, which may cause them to be different. -

-

-The internal tables can always be overridden by tables supplied by the -application that calls PCRE. These may be created in a different locale from -the default. As more and more applications change to using Unicode, the need -for this locale support is expected to die away. -

-

-External tables are built by calling the pcre_maketables() function, -which has no arguments, in the relevant locale. The result can then be passed -to pcre_compile() or pcre_exec() as often as necessary. For -example, to build and use tables that are appropriate for the French locale -(where accented characters with values greater than 128 are treated as letters), -the following code could be used: -

-  setlocale(LC_CTYPE, "fr_FR");
-  tables = pcre_maketables();
-  re = pcre_compile(..., tables);
-
-The locale name "fr_FR" is used on Linux and other Unix-like systems; if you -are using Windows, the name for the French locale is "french". -

-

-When pcre_maketables() runs, the tables are built in memory that is -obtained via pcre_malloc. It is the caller's responsibility to ensure -that the memory containing the tables remains available for as long as it is -needed. -

-

-The pointer that is passed to pcre_compile() is saved with the compiled -pattern, and the same tables are used via this pointer by pcre_study() -and normally also by pcre_exec(). Thus, by default, for any single -pattern, compilation, studying and matching all happen in the same locale, but -different patterns can be compiled in different locales. -

-

-It is possible to pass a table pointer or NULL (indicating the use of the -internal tables) to pcre_exec(). Although not intended for this purpose, -this facility could be used to match a pattern in a different locale from the -one in which it was compiled. Passing table pointers at run time is discussed -below in the section on matching a pattern. -

-
INFORMATION ABOUT A PATTERN
-

-int pcre_fullinfo(const pcre *code, const pcre_extra *extra, -int what, void *where); -

-

-The pcre_fullinfo() function returns information about a compiled -pattern. It replaces the obsolete pcre_info() function, which is -nevertheless retained for backwards compability (and is documented below). -

-

-The first argument for pcre_fullinfo() is a pointer to the compiled -pattern. The second argument is the result of pcre_study(), or NULL if -the pattern was not studied. The third argument specifies which piece of -information is required, and the fourth argument is a pointer to a variable -to receive the data. The yield of the function is zero for success, or one of -the following negative numbers: -

-  PCRE_ERROR_NULL       the argument code was NULL
-                        the argument where was NULL
-  PCRE_ERROR_BADMAGIC   the "magic number" was not found
-  PCRE_ERROR_BADOPTION  the value of what was invalid
-
-The "magic number" is placed at the start of each compiled pattern as an simple -check against passing an arbitrary memory pointer. Here is a typical call of -pcre_fullinfo(), to obtain the length of the compiled pattern: -
-  int rc;
-  size_t length;
-  rc = pcre_fullinfo(
-    re,               /* result of pcre_compile() */
-    pe,               /* result of pcre_study(), or NULL */
-    PCRE_INFO_SIZE,   /* what is required */
-    &length);         /* where to put the data */
-
-The possible values for the third argument are defined in pcre.h, and are -as follows: -
-  PCRE_INFO_BACKREFMAX
-
-Return the number of the highest back reference in the pattern. The fourth -argument should point to an int variable. Zero is returned if there are -no back references. -
-  PCRE_INFO_CAPTURECOUNT
-
-Return the number of capturing subpatterns in the pattern. The fourth argument -should point to an int variable. -
-  PCRE_INFO_DEFAULT_TABLES
-
-Return a pointer to the internal default character tables within PCRE. The -fourth argument should point to an unsigned char * variable. This -information call is provided for internal use by the pcre_study() -function. External callers can cause PCRE to use its internal tables by passing -a NULL table pointer. -
-  PCRE_INFO_FIRSTBYTE
-
-Return information about the first byte of any matched string, for a -non-anchored pattern. The fourth argument should point to an int -variable. (This option used to be called PCRE_INFO_FIRSTCHAR; the old name is -still recognized for backwards compatibility.) -

-

-If there is a fixed first byte, for example, from a pattern such as -(cat|cow|coyote), its value is returned. Otherwise, if either -
-
-(a) the pattern was compiled with the PCRE_MULTILINE option, and every branch -starts with "^", or -
-
-(b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set -(if it were set, the pattern would be anchored), -
-
--1 is returned, indicating that the pattern matches only at the start of a -subject string or after any newline within the string. Otherwise -2 is -returned. For anchored patterns, -2 is returned. -

-  PCRE_INFO_FIRSTTABLE
-
-If the pattern was studied, and this resulted in the construction of a 256-bit -table indicating a fixed set of bytes for the first byte in any matching -string, a pointer to the table is returned. Otherwise NULL is returned. The -fourth argument should point to an unsigned char * variable. -
-  PCRE_INFO_HASCRORLF
-
-Return 1 if the pattern contains any explicit matches for CR or LF characters, -otherwise 0. The fourth argument should point to an int variable. An -explicit match is either a literal CR or LF character, or \r or \n. -
-  PCRE_INFO_JCHANGED
-
-Return 1 if the (?J) or (?-J) option setting is used in the pattern, otherwise -0. The fourth argument should point to an int variable. (?J) and -(?-J) set and unset the local PCRE_DUPNAMES option, respectively. -
-  PCRE_INFO_LASTLITERAL
-
-Return the value of the rightmost literal byte that must exist in any matched -string, other than at its start, if such a byte has been recorded. The fourth -argument should point to an int variable. If there is no such byte, -1 is -returned. For anchored patterns, a last literal byte is recorded only if it -follows something of variable length. For example, for the pattern -/^a\d+z\d+/ the returned value is "z", but for /^a\dz\d/ the returned value -is -1. -
-  PCRE_INFO_NAMECOUNT
-  PCRE_INFO_NAMEENTRYSIZE
-  PCRE_INFO_NAMETABLE
-
-PCRE supports the use of named as well as numbered capturing parentheses. The -names are just an additional way of identifying the parentheses, which still -acquire numbers. Several convenience functions such as -pcre_get_named_substring() are provided for extracting captured -substrings by name. It is also possible to extract the data directly, by first -converting the name to a number in order to access the correct pointers in the -output vector (described with pcre_exec() below). To do the conversion, -you need to use the name-to-number map, which is described by these three -values. -

-

-The map consists of a number of fixed-size entries. PCRE_INFO_NAMECOUNT gives -the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size of each -entry; both of these return an int value. The entry size depends on the -length of the longest name. PCRE_INFO_NAMETABLE returns a pointer to the first -entry of the table (a pointer to char). The first two bytes of each entry -are the number of the capturing parenthesis, most significant byte first. The -rest of the entry is the corresponding name, zero terminated. The names are in -alphabetical order. When PCRE_DUPNAMES is set, duplicate names are in order of -their parentheses numbers. For example, consider the following pattern (assume -PCRE_EXTENDED is set, so white space - including newlines - is ignored): -

-  (?<date> (?<year>(\d\d)?\d\d) - (?<month>\d\d) - (?<day>\d\d) )
-
-There are four named subpatterns, so the table has four entries, and each entry -in the table is eight bytes long. The table is as follows, with non-printing -bytes shows in hexadecimal, and undefined bytes shown as ??: -
-  00 01 d  a  t  e  00 ??
-  00 05 d  a  y  00 ?? ??
-  00 04 m  o  n  t  h  00
-  00 02 y  e  a  r  00 ??
-
-When writing code to extract data from named subpatterns using the -name-to-number map, remember that the length of the entries is likely to be -different for each compiled pattern. -
-  PCRE_INFO_OKPARTIAL
-
-Return 1 if the pattern can be used for partial matching, otherwise 0. The -fourth argument should point to an int variable. The -pcrepartial -documentation lists the restrictions that apply to patterns when partial -matching is used. -
-  PCRE_INFO_OPTIONS
-
-Return a copy of the options with which the pattern was compiled. The fourth -argument should point to an unsigned long int variable. These option bits -are those specified in the call to pcre_compile(), modified by any -top-level option settings at the start of the pattern itself. In other words, -they are the options that will be in force when matching starts. For example, -if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the -result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED. -

-

-A pattern is automatically anchored by PCRE if all of its top-level -alternatives begin with one of the following: -

-  ^     unless PCRE_MULTILINE is set
-  \A    always
-  \G    always
-  .*    if PCRE_DOTALL is set and there are no back references to the subpattern in which .* appears
-
-For such patterns, the PCRE_ANCHORED bit is set in the options returned by -pcre_fullinfo(). -
-  PCRE_INFO_SIZE
-
-Return the size of the compiled pattern, that is, the value that was passed as -the argument to pcre_malloc() when PCRE was getting memory in which to -place the compiled data. The fourth argument should point to a size_t -variable. -
-  PCRE_INFO_STUDYSIZE
-
-Return the size of the data block pointed to by the study_data field in -a pcre_extra block. That is, it is the value that was passed to -pcre_malloc() when PCRE was getting memory into which to place the data -created by pcre_study(). The fourth argument should point to a -size_t variable. -

-
OBSOLETE INFO FUNCTION
-

-int pcre_info(const pcre *code, int *optptr, int -*firstcharptr); -

-

-The pcre_info() function is now obsolete because its interface is too -restrictive to return all the available data about a compiled pattern. New -programs should use pcre_fullinfo() instead. The yield of -pcre_info() is the number of capturing subpatterns, or one of the -following negative numbers: -

-  PCRE_ERROR_NULL       the argument code was NULL
-  PCRE_ERROR_BADMAGIC   the "magic number" was not found
-
-If the optptr argument is not NULL, a copy of the options with which the -pattern was compiled is placed in the integer it points to (see -PCRE_INFO_OPTIONS above). -

-

-If the pattern is not anchored and the firstcharptr argument is not NULL, -it is used to pass back information about the first character of any matched -string (see PCRE_INFO_FIRSTBYTE above). -

-
REFERENCE COUNTS
-

-int pcre_refcount(pcre *code, int adjust); -

-

-The pcre_refcount() function is used to maintain a reference count in the -data block that contains a compiled pattern. It is provided for the benefit of -applications that operate in an object-oriented manner, where different parts -of the application may be using the same compiled pattern, but you want to free -the block when they are all done. -

-

-When a pattern is compiled, the reference count field is initialized to zero. -It is changed only by calling this function, whose action is to add the -adjust value (which may be positive or negative) to it. The yield of the -function is the new value. However, the value of the count is constrained to -lie between 0 and 65535, inclusive. If the new value is outside these limits, -it is forced to the appropriate limit value. -

-

-Except when it is zero, the reference count is not correctly preserved if a -pattern is compiled on one host and then transferred to a host whose byte-order -is different. (This seems a highly unlikely scenario.) -

-
MATCHING A PATTERN: THE TRADITIONAL FUNCTION
-

-int pcre_exec(const pcre *code, const pcre_extra *extra, -const char *subject, int length, int startoffset, -int options, int *ovector, int ovecsize); -

-

-The function pcre_exec() is called to match a subject string against a -compiled pattern, which is passed in the code argument. If the -pattern has been studied, the result of the study should be passed in the -extra argument. This function is the main matching facility of the -library, and it operates in a Perl-like manner. For specialist use there is -also an alternative matching function, which is described -below -in the section about the pcre_dfa_exec() function. -

-

-In most applications, the pattern will have been compiled (and optionally -studied) in the same process that calls pcre_exec(). However, it is -possible to save compiled patterns and study data, and then use them later -in different processes, possibly even on different hosts. For a discussion -about this, see the -pcreprecompile -documentation. -

-

-Here is an example of a simple call to pcre_exec(): -

-  int rc;
-  int ovector[30];
-  rc = pcre_exec(
-    re,             /* result of pcre_compile() */
-    NULL,           /* we didn't study the pattern */
-    "some string",  /* the subject string */
-    11,             /* the length of the subject string */
-    0,              /* start at offset 0 in the subject */
-    0,              /* default options */
-    ovector,        /* vector of integers for substring information */
-    30);            /* number of elements (NOT size in bytes) */
-
-

-
-Extra data for pcre_exec() -
-

-If the extra argument is not NULL, it must point to a pcre_extra -data block. The pcre_study() function returns such a block (when it -doesn't return NULL), but you can also create one for yourself, and pass -additional information in it. The pcre_extra block contains the following -fields (not necessarily in this order): -

-  unsigned long int flags;
-  void *study_data;
-  unsigned long int match_limit;
-  unsigned long int match_limit_recursion;
-  void *callout_data;
-  const unsigned char *tables;
-
-The flags field is a bitmap that specifies which of the other fields -are set. The flag bits are: -
-  PCRE_EXTRA_STUDY_DATA
-  PCRE_EXTRA_MATCH_LIMIT
-  PCRE_EXTRA_MATCH_LIMIT_RECURSION
-  PCRE_EXTRA_CALLOUT_DATA
-  PCRE_EXTRA_TABLES
-
-Other flag bits should be set to zero. The study_data field is set in the -pcre_extra block that is returned by pcre_study(), together with -the appropriate flag bit. You should not set this yourself, but you may add to -the block by setting the other fields and their corresponding flag bits. -

-

-The match_limit field provides a means of preventing PCRE from using up a -vast amount of resources when running patterns that are not going to match, -but which have a very large number of possibilities in their search trees. The -classic example is the use of nested unlimited repeats. -

-

-Internally, PCRE uses a function called match() which it calls repeatedly -(sometimes recursively). The limit set by match_limit is imposed on the -number of times this function is called during a match, which has the effect of -limiting the amount of backtracking that can take place. For patterns that are -not anchored, the count restarts from zero for each position in the subject -string. -

-

-The default value for the limit can be set when PCRE is built; the default -default is 10 million, which handles all but the most extreme cases. You can -override the default by suppling pcre_exec() with a pcre_extra -block in which match_limit is set, and PCRE_EXTRA_MATCH_LIMIT is set in -the flags field. If the limit is exceeded, pcre_exec() returns -PCRE_ERROR_MATCHLIMIT. -

-

-The match_limit_recursion field is similar to match_limit, but -instead of limiting the total number of times that match() is called, it -limits the depth of recursion. The recursion depth is a smaller number than the -total number of calls, because not all calls to match() are recursive. -This limit is of use only if it is set smaller than match_limit. -

-

-Limiting the recursion depth limits the amount of stack that can be used, or, -when PCRE has been compiled to use memory on the heap instead of the stack, the -amount of heap memory that can be used. -

-

-The default value for match_limit_recursion can be set when PCRE is -built; the default default is the same value as the default for -match_limit. You can override the default by suppling pcre_exec() -with a pcre_extra block in which match_limit_recursion is set, and -PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the flags field. If the limit -is exceeded, pcre_exec() returns PCRE_ERROR_RECURSIONLIMIT. -

-

-The pcre_callout field is used in conjunction with the "callout" feature, -which is described in the -pcrecallout -documentation. -

-

-The tables field is used to pass a character tables pointer to -pcre_exec(); this overrides the value that is stored with the compiled -pattern. A non-NULL value is stored with the compiled pattern only if custom -tables were supplied to pcre_compile() via its tableptr argument. -If NULL is passed to pcre_exec() using this mechanism, it forces PCRE's -internal tables to be used. This facility is helpful when re-using patterns -that have been saved after compiling with an external set of tables, because -the external tables might be at a different address when pcre_exec() is -called. See the -pcreprecompile -documentation for a discussion of saving compiled patterns for later use. -

-
-Option bits for pcre_exec() -
-

-The unused bits of the options argument for pcre_exec() must be -zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_xxx, -PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_START_OPTIMIZE, -PCRE_NO_UTF8_CHECK and PCRE_PARTIAL. -

-  PCRE_ANCHORED
-
-The PCRE_ANCHORED option limits pcre_exec() to matching at the first -matching position. If a pattern was compiled with PCRE_ANCHORED, or turned out -to be anchored by virtue of its contents, it cannot be made unachored at -matching time. -
-  PCRE_BSR_ANYCRLF
-  PCRE_BSR_UNICODE
-
-These options (which are mutually exclusive) control what the \R escape -sequence matches. The choice is either to match only CR, LF, or CRLF, or to -match any Unicode newline sequence. These options override the choice that was -made or defaulted when the pattern was compiled. -
-  PCRE_NEWLINE_CR
-  PCRE_NEWLINE_LF
-  PCRE_NEWLINE_CRLF
-  PCRE_NEWLINE_ANYCRLF
-  PCRE_NEWLINE_ANY
-
-These options override the newline definition that was chosen or defaulted when -the pattern was compiled. For details, see the description of -pcre_compile() above. During matching, the newline choice affects the -behaviour of the dot, circumflex, and dollar metacharacters. It may also alter -the way the match position is advanced after a match failure for an unanchored -pattern. -

-

-When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is set, and a -match attempt for an unanchored pattern fails when the current position is at a -CRLF sequence, and the pattern contains no explicit matches for CR or LF -characters, the match position is advanced by two characters instead of one, in -other words, to after the CRLF. -

-

-The above rule is a compromise that makes the most common cases work as -expected. For example, if the pattern is .+A (and the PCRE_DOTALL option is not -set), it does not match the string "\r\nA" because, after failing at the -start, it skips both the CR and the LF before retrying. However, the pattern -[\r\n]A does match that string, because it contains an explicit CR or LF -reference, and so advances only by one character after the first failure. -

-

-An explicit match for CR of LF is either a literal appearance of one of those -characters, or one of the \r or \n escape sequences. Implicit matches such as -[^X] do not count, nor does \s (which includes CR and LF in the characters -that it matches). -

-

-Notwithstanding the above, anomalous effects may still occur when CRLF is a -valid newline sequence and explicit \r or \n escapes appear in the pattern. -

-  PCRE_NOTBOL
-
-This option specifies that first character of the subject string is not the -beginning of a line, so the circumflex metacharacter should not match before -it. Setting this without PCRE_MULTILINE (at compile time) causes circumflex -never to match. This option affects only the behaviour of the circumflex -metacharacter. It does not affect \A. -
-  PCRE_NOTEOL
-
-This option specifies that the end of the subject string is not the end of a -line, so the dollar metacharacter should not match it nor (except in multiline -mode) a newline immediately before it. Setting this without PCRE_MULTILINE (at -compile time) causes dollar never to match. This option affects only the -behaviour of the dollar metacharacter. It does not affect \Z or \z. -
-  PCRE_NOTEMPTY
-
-An empty string is not considered to be a valid match if this option is set. If -there are alternatives in the pattern, they are tried. If all the alternatives -match the empty string, the entire match fails. For example, if the pattern -
-  a?b?
-
-is applied to a string not beginning with "a" or "b", it matches the empty -string at the start of the subject. With PCRE_NOTEMPTY set, this match is not -valid, so PCRE searches further into the string for occurrences of "a" or "b". -

-

-Perl has no direct equivalent of PCRE_NOTEMPTY, but it does make a special case -of a pattern match of the empty string within its split() function, and -when using the /g modifier. It is possible to emulate Perl's behaviour after -matching a null string by first trying the match again at the same offset with -PCRE_NOTEMPTY and PCRE_ANCHORED, and then if that fails by advancing the -starting offset (see below) and trying an ordinary match again. There is some -code that demonstrates how to do this in the pcredemo.c sample program. -

-  PCRE_NO_START_OPTIMIZE
-
-There are a number of optimizations that pcre_exec() uses at the start of -a match, in order to speed up the process. For example, if it is known that a -match must start with a specific character, it searches the subject for that -character, and fails immediately if it cannot find it, without actually running -the main matching function. When callouts are in use, these optimizations can -cause them to be skipped. This option disables the "start-up" optimizations, -causing performance to suffer, but ensuring that the callouts do occur. -
-  PCRE_NO_UTF8_CHECK
-
-When PCRE_UTF8 is set at compile time, the validity of the subject as a UTF-8 -string is automatically checked when pcre_exec() is subsequently called. -The value of startoffset is also checked to ensure that it points to the -start of a UTF-8 character. There is a discussion about the validity of UTF-8 -strings in the -section on UTF-8 support -in the main -pcre -page. If an invalid UTF-8 sequence of bytes is found, pcre_exec() returns -the error PCRE_ERROR_BADUTF8. If startoffset contains an invalid value, -PCRE_ERROR_BADUTF8_OFFSET is returned. -

-

-If you already know that your subject is valid, and you want to skip these -checks for performance reasons, you can set the PCRE_NO_UTF8_CHECK option when -calling pcre_exec(). You might want to do this for the second and -subsequent calls to pcre_exec() if you are making repeated calls to find -all the matches in a single subject string. However, you should be sure that -the value of startoffset points to the start of a UTF-8 character. When -PCRE_NO_UTF8_CHECK is set, the effect of passing an invalid UTF-8 string as a -subject, or a value of startoffset that does not point to the start of a -UTF-8 character, is undefined. Your program may crash. -

-  PCRE_PARTIAL
-
-This option turns on the partial matching feature. If the subject string fails -to match the pattern, but at some point during the matching process the end of -the subject was reached (that is, the subject partially matches the pattern and -the failure to match occurred only because there were not enough subject -characters), pcre_exec() returns PCRE_ERROR_PARTIAL instead of -PCRE_ERROR_NOMATCH. When PCRE_PARTIAL is used, there are restrictions on what -may appear in the pattern. These are discussed in the -pcrepartial -documentation. -

-
-The string to be matched by pcre_exec() -
-

-The subject string is passed to pcre_exec() as a pointer in -subject, a length (in bytes) in length, and a starting byte offset -in startoffset. In UTF-8 mode, the byte offset must point to the start of -a UTF-8 character. Unlike the pattern string, the subject may contain binary -zero bytes. When the starting offset is zero, the search for a match starts at -the beginning of the subject, and this is by far the most common case. -

-

-A non-zero starting offset is useful when searching for another match in the -same subject by calling pcre_exec() again after a previous success. -Setting startoffset differs from just passing over a shortened string and -setting PCRE_NOTBOL in the case of a pattern that begins with any kind of -lookbehind. For example, consider the pattern -

-  \Biss\B
-
-which finds occurrences of "iss" in the middle of words. (\B matches only if -the current position in the subject is not a word boundary.) When applied to -the string "Mississipi" the first call to pcre_exec() finds the first -occurrence. If pcre_exec() is called again with just the remainder of the -subject, namely "issipi", it does not match, because \B is always false at the -start of the subject, which is deemed to be a word boundary. However, if -pcre_exec() is passed the entire string again, but with startoffset -set to 4, it finds the second occurrence of "iss" because it is able to look -behind the starting point to discover that it is preceded by a letter. -

-

-If a non-zero starting offset is passed when the pattern is anchored, one -attempt to match at the given offset is made. This can only succeed if the -pattern does not require the match to be at the start of the subject. -

-
-How pcre_exec() returns captured substrings -
-

-In general, a pattern matches a certain portion of the subject, and in -addition, further substrings from the subject may be picked out by parts of the -pattern. Following the usage in Jeffrey Friedl's book, this is called -"capturing" in what follows, and the phrase "capturing subpattern" is used for -a fragment of a pattern that picks out a substring. PCRE supports several other -kinds of parenthesized subpattern that do not cause substrings to be captured. -

-

-Captured substrings are returned to the caller via a vector of integers whose -address is passed in ovector. The number of elements in the vector is -passed in ovecsize, which must be a non-negative number. Note: this -argument is NOT the size of ovector in bytes. -

-

-The first two-thirds of the vector is used to pass back captured substrings, -each substring using a pair of integers. The remaining third of the vector is -used as workspace by pcre_exec() while matching capturing subpatterns, -and is not available for passing back information. The number passed in -ovecsize should always be a multiple of three. If it is not, it is -rounded down. -

-

-When a match is successful, information about captured substrings is returned -in pairs of integers, starting at the beginning of ovector, and -continuing up to two-thirds of its length at the most. The first element of -each pair is set to the byte offset of the first character in a substring, and -the second is set to the byte offset of the first character after the end of a -substring. Note: these values are always byte offsets, even in UTF-8 -mode. They are not character counts. -

-

-The first pair of integers, ovector[0] and ovector[1], identify the -portion of the subject string matched by the entire pattern. The next pair is -used for the first capturing subpattern, and so on. The value returned by -pcre_exec() is one more than the highest numbered pair that has been set. -For example, if two substrings have been captured, the returned value is 3. If -there are no capturing subpatterns, the return value from a successful match is -1, indicating that just the first pair of offsets has been set. -

-

-If a capturing subpattern is matched repeatedly, it is the last portion of the -string that it matched that is returned. -

-

-If the vector is too small to hold all the captured substring offsets, it is -used as far as possible (up to two-thirds of its length), and the function -returns a value of zero. If the substring offsets are not of interest, -pcre_exec() may be called with ovector passed as NULL and -ovecsize as zero. However, if the pattern contains back references and -the ovector is not big enough to remember the related substrings, PCRE -has to get additional memory for use during matching. Thus it is usually -advisable to supply an ovector. -

-

-The pcre_info() function can be used to find out how many capturing -subpatterns there are in a compiled pattern. The smallest size for -ovector that will allow for n captured substrings, in addition to -the offsets of the substring matched by the whole pattern, is (n+1)*3. -

-

-It is possible for capturing subpattern number n+1 to match some part of -the subject when subpattern n has not been used at all. For example, if -the string "abc" is matched against the pattern (a|(z))(bc) the return from the -function is 4, and subpatterns 1 and 3 are matched, but 2 is not. When this -happens, both values in the offset pairs corresponding to unused subpatterns -are set to -1. -

-

-Offset values that correspond to unused subpatterns at the end of the -expression are also set to -1. For example, if the string "abc" is matched -against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The -return from the function is 2, because the highest used capturing subpattern -number is 1. However, you can refer to the offsets for the second and third -capturing subpatterns if you wish (assuming the vector is large enough, of -course). -

-

-Some convenience functions are provided for extracting the captured substrings -as separate strings. These are described below. -

-
-Error return values from pcre_exec() -
-

-If pcre_exec() fails, it returns a negative number. The following are -defined in the header file: -

-  PCRE_ERROR_NOMATCH        (-1)
-
-The subject string did not match the pattern. -
-  PCRE_ERROR_NULL           (-2)
-
-Either code or subject was passed as NULL, or ovector was -NULL and ovecsize was not zero. -
-  PCRE_ERROR_BADOPTION      (-3)
-
-An unrecognized bit was set in the options argument. -
-  PCRE_ERROR_BADMAGIC       (-4)
-
-PCRE stores a 4-byte "magic number" at the start of the compiled code, to catch -the case when it is passed a junk pointer and to detect when a pattern that was -compiled in an environment of one endianness is run in an environment with the -other endianness. This is the error that PCRE gives when the magic number is -not present. -
-  PCRE_ERROR_UNKNOWN_OPCODE (-5)
-
-While running the pattern match, an unknown item was encountered in the -compiled pattern. This error could be caused by a bug in PCRE or by overwriting -of the compiled pattern. -
-  PCRE_ERROR_NOMEMORY       (-6)
-
-If a pattern contains back references, but the ovector that is passed to -pcre_exec() is not big enough to remember the referenced substrings, PCRE -gets a block of memory at the start of matching to use for this purpose. If the -call via pcre_malloc() fails, this error is given. The memory is -automatically freed at the end of matching. -
-  PCRE_ERROR_NOSUBSTRING    (-7)
-
-This error is used by the pcre_copy_substring(), -pcre_get_substring(), and pcre_get_substring_list() functions (see -below). It is never returned by pcre_exec(). -
-  PCRE_ERROR_MATCHLIMIT     (-8)
-
-The backtracking limit, as specified by the match_limit field in a -pcre_extra structure (or defaulted) was reached. See the description -above. -
-  PCRE_ERROR_CALLOUT        (-9)
-
-This error is never generated by pcre_exec() itself. It is provided for -use by callout functions that want to yield a distinctive error code. See the -pcrecallout -documentation for details. -
-  PCRE_ERROR_BADUTF8        (-10)
-
-A string that contains an invalid UTF-8 byte sequence was passed as a subject. -
-  PCRE_ERROR_BADUTF8_OFFSET (-11)
-
-The UTF-8 byte sequence that was passed as a subject was valid, but the value -of startoffset did not point to the beginning of a UTF-8 character. -
-  PCRE_ERROR_PARTIAL        (-12)
-
-The subject string did not match, but it did match partially. See the -pcrepartial -documentation for details of partial matching. -
-  PCRE_ERROR_BADPARTIAL     (-13)
-
-The PCRE_PARTIAL option was used with a compiled pattern containing items that -are not supported for partial matching. See the -pcrepartial -documentation for details of partial matching. -
-  PCRE_ERROR_INTERNAL       (-14)
-
-An unexpected internal error has occurred. This error could be caused by a bug -in PCRE or by overwriting of the compiled pattern. -
-  PCRE_ERROR_BADCOUNT       (-15)
-
-This error is given if the value of the ovecsize argument is negative. -
-  PCRE_ERROR_RECURSIONLIMIT (-21)
-
-The internal recursion limit, as specified by the match_limit_recursion -field in a pcre_extra structure (or defaulted) was reached. See the -description above. -
-  PCRE_ERROR_BADNEWLINE     (-23)
-
-An invalid combination of PCRE_NEWLINE_xxx options was given. -

-

-Error numbers -16 to -20 and -22 are not used by pcre_exec(). -

-
EXTRACTING CAPTURED SUBSTRINGS BY NUMBER
-

-int pcre_copy_substring(const char *subject, int *ovector, -int stringcount, int stringnumber, char *buffer, -int buffersize); -

-

-int pcre_get_substring(const char *subject, int *ovector, -int stringcount, int stringnumber, -const char **stringptr); -

-

-int pcre_get_substring_list(const char *subject, -int *ovector, int stringcount, const char ***listptr); -

-

-Captured substrings can be accessed directly by using the offsets returned by -pcre_exec() in ovector. For convenience, the functions -pcre_copy_substring(), pcre_get_substring(), and -pcre_get_substring_list() are provided for extracting captured substrings -as new, separate, zero-terminated strings. These functions identify substrings -by number. The next section describes functions for extracting named -substrings. -

-

-A substring that contains a binary zero is correctly extracted and has a -further zero added on the end, but the result is not, of course, a C string. -However, you can process such a string by referring to the length that is -returned by pcre_copy_substring() and pcre_get_substring(). -Unfortunately, the interface to pcre_get_substring_list() is not adequate -for handling strings containing binary zeros, because the end of the final -string is not independently indicated. -

-

-The first three arguments are the same for all three of these functions: -subject is the subject string that has just been successfully matched, -ovector is a pointer to the vector of integer offsets that was passed to -pcre_exec(), and stringcount is the number of substrings that were -captured by the match, including the substring that matched the entire regular -expression. This is the value returned by pcre_exec() if it is greater -than zero. If pcre_exec() returned zero, indicating that it ran out of -space in ovector, the value passed as stringcount should be the -number of elements in the vector divided by three. -

-

-The functions pcre_copy_substring() and pcre_get_substring() -extract a single substring, whose number is given as stringnumber. A -value of zero extracts the substring that matched the entire pattern, whereas -higher values extract the captured substrings. For pcre_copy_substring(), -the string is placed in buffer, whose length is given by -buffersize, while for pcre_get_substring() a new block of memory is -obtained via pcre_malloc, and its address is returned via -stringptr. The yield of the function is the length of the string, not -including the terminating zero, or one of these error codes: -

-  PCRE_ERROR_NOMEMORY       (-6)
-
-The buffer was too small for pcre_copy_substring(), or the attempt to get -memory failed for pcre_get_substring(). -
-  PCRE_ERROR_NOSUBSTRING    (-7)
-
-There is no substring whose number is stringnumber. -

-

-The pcre_get_substring_list() function extracts all available substrings -and builds a list of pointers to them. All this is done in a single block of -memory that is obtained via pcre_malloc. The address of the memory block -is returned via listptr, which is also the start of the list of string -pointers. The end of the list is marked by a NULL pointer. The yield of the -function is zero if all went well, or the error code -

-  PCRE_ERROR_NOMEMORY       (-6)
-
-if the attempt to get the memory block failed. -

-

-When any of these functions encounter a substring that is unset, which can -happen when capturing subpattern number n+1 matches some part of the -subject, but subpattern n has not been used at all, they return an empty -string. This can be distinguished from a genuine zero-length substring by -inspecting the appropriate offset in ovector, which is negative for unset -substrings. -

-

-The two convenience functions pcre_free_substring() and -pcre_free_substring_list() can be used to free the memory returned by -a previous call of pcre_get_substring() or -pcre_get_substring_list(), respectively. They do nothing more than call -the function pointed to by pcre_free, which of course could be called -directly from a C program. However, PCRE is used in some situations where it is -linked via a special interface to another programming language that cannot use -pcre_free directly; it is for these cases that the functions are -provided. -

-
EXTRACTING CAPTURED SUBSTRINGS BY NAME
-

-int pcre_get_stringnumber(const pcre *code, -const char *name); -

-

-int pcre_copy_named_substring(const pcre *code, -const char *subject, int *ovector, -int stringcount, const char *stringname, -char *buffer, int buffersize); -

-

-int pcre_get_named_substring(const pcre *code, -const char *subject, int *ovector, -int stringcount, const char *stringname, -const char **stringptr); -

-

-To extract a substring by name, you first have to find associated number. -For example, for this pattern -

-  (a+)b(?<xxx>\d+)...
-
-the number of the subpattern called "xxx" is 2. If the name is known to be -unique (PCRE_DUPNAMES was not set), you can find the number from the name by -calling pcre_get_stringnumber(). The first argument is the compiled -pattern, and the second is the name. The yield of the function is the -subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no subpattern of -that name. -

-

-Given the number, you can extract the substring directly, or use one of the -functions described in the previous section. For convenience, there are also -two functions that do the whole job. -

-

-Most of the arguments of pcre_copy_named_substring() and -pcre_get_named_substring() are the same as those for the similarly named -functions that extract by number. As these are described in the previous -section, they are not re-described here. There are just two differences: -

-

-First, instead of a substring number, a substring name is given. Second, there -is an extra argument, given at the start, which is a pointer to the compiled -pattern. This is needed in order to gain access to the name-to-number -translation table. -

-

-These functions call pcre_get_stringnumber(), and if it succeeds, they -then call pcre_copy_substring() or pcre_get_substring(), as -appropriate. NOTE: If PCRE_DUPNAMES is set and there are duplicate names, -the behaviour may not be what you want (see the next section). -

-

-Warning: If the pattern uses the "(?|" feature to set up multiple -subpatterns with the same number, you cannot use names to distinguish them, -because names are not included in the compiled code. The matching process uses -only numbers. -

-
DUPLICATE SUBPATTERN NAMES
-

-int pcre_get_stringtable_entries(const pcre *code, -const char *name, char **first, char **last); -

-

-When a pattern is compiled with the PCRE_DUPNAMES option, names for subpatterns -are not required to be unique. Normally, patterns with duplicate names are such -that in any one match, only one of the named subpatterns participates. An -example is shown in the -pcrepattern -documentation. -

-

-When duplicates are present, pcre_copy_named_substring() and -pcre_get_named_substring() return the first substring corresponding to -the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING (-7) is -returned; no data is returned. The pcre_get_stringnumber() function -returns one of the numbers that are associated with the name, but it is not -defined which it is. -

-

-If you want to get full details of all captured substrings for a given name, -you must use the pcre_get_stringtable_entries() function. The first -argument is the compiled pattern, and the second is the name. The third and -fourth are pointers to variables which are updated by the function. After it -has run, they point to the first and last entries in the name-to-number table -for the given name. The function itself returns the length of each entry, or -PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is -described above in the section entitled Information about a pattern. -Given all the relevant entries for the name, you can extract each of their -numbers, and hence the captured data, if any. -

-
FINDING ALL POSSIBLE MATCHES
-

-The traditional matching function uses a similar algorithm to Perl, which stops -when it finds the first match, starting at a given point in the subject. If you -want to find all possible matches, or the longest possible match, consider -using the alternative matching function (see below) instead. If you cannot use -the alternative function, but still need to find all possible matches, you -can kludge it up by making use of the callout facility, which is described in -the -pcrecallout -documentation. -

-

-What you have to do is to insert a callout right at the end of the pattern. -When your callout function is called, extract and save the current matched -substring. Then return 1, which forces pcre_exec() to backtrack and try -other alternatives. Ultimately, when it runs out of matches, pcre_exec() -will yield PCRE_ERROR_NOMATCH. -

-
MATCHING A PATTERN: THE ALTERNATIVE FUNCTION
-

-int pcre_dfa_exec(const pcre *code, const pcre_extra *extra, -const char *subject, int length, int startoffset, -int options, int *ovector, int ovecsize, -int *workspace, int wscount); -

-

-The function pcre_dfa_exec() is called to match a subject string against -a compiled pattern, using a matching algorithm that scans the subject string -just once, and does not backtrack. This has different characteristics to the -normal algorithm, and is not compatible with Perl. Some of the features of PCRE -patterns are not supported. Nevertheless, there are times when this kind of -matching can be useful. For a discussion of the two matching algorithms, see -the -pcrematching -documentation. -

-

-The arguments for the pcre_dfa_exec() function are the same as for -pcre_exec(), plus two extras. The ovector argument is used in a -different way, and this is described below. The other common arguments are used -in the same way as for pcre_exec(), so their description is not repeated -here. -

-

-The two additional arguments provide workspace for the function. The workspace -vector should contain at least 20 elements. It is used for keeping track of -multiple paths through the pattern tree. More workspace will be needed for -patterns and subjects where there are a lot of potential matches. -

-

-Here is an example of a simple call to pcre_dfa_exec(): -

-  int rc;
-  int ovector[10];
-  int wspace[20];
-  rc = pcre_dfa_exec(
-    re,             /* result of pcre_compile() */
-    NULL,           /* we didn't study the pattern */
-    "some string",  /* the subject string */
-    11,             /* the length of the subject string */
-    0,              /* start at offset 0 in the subject */
-    0,              /* default options */
-    ovector,        /* vector of integers for substring information */
-    10,             /* number of elements (NOT size in bytes) */
-    wspace,         /* working space vector */
-    20);            /* number of elements (NOT size in bytes) */
-
-

-
-Option bits for pcre_dfa_exec() -
-

-The unused bits of the options argument for pcre_dfa_exec() must be -zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_xxx, -PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL, -PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last three of these are -the same as for pcre_exec(), so their description is not repeated here. -

-  PCRE_PARTIAL
-
-This has the same general effect as it does for pcre_exec(), but the -details are slightly different. When PCRE_PARTIAL is set for -pcre_dfa_exec(), the return code PCRE_ERROR_NOMATCH is converted into -PCRE_ERROR_PARTIAL if the end of the subject is reached, there have been no -complete matches, but there is still at least one matching possibility. The -portion of the string that provided the partial match is set as the first -matching string. -
-  PCRE_DFA_SHORTEST
-
-Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to stop as -soon as it has found one match. Because of the way the alternative algorithm -works, this is necessarily the shortest possible match at the first possible -matching point in the subject string. -
-  PCRE_DFA_RESTART
-
-When pcre_dfa_exec() is called with the PCRE_PARTIAL option, and returns -a partial match, it is possible to call it again, with additional subject -characters, and have it continue with the same match. The PCRE_DFA_RESTART -option requests this action; when it is set, the workspace and -wscount options must reference the same vector as before because data -about the match so far is left in them after a partial match. There is more -discussion of this facility in the -pcrepartial -documentation. -

-
-Successful returns from pcre_dfa_exec() -
-

-When pcre_dfa_exec() succeeds, it may have matched more than one -substring in the subject. Note, however, that all the matches from one run of -the function start at the same point in the subject. The shorter matches are -all initial substrings of the longer matches. For example, if the pattern -

-  <.*>
-
-is matched against the string -
-  This is <something> <something else> <something further> no more
-
-the three matched strings are -
-  <something>
-  <something> <something else>
-  <something> <something else> <something further>
-
-On success, the yield of the function is a number greater than zero, which is -the number of matched substrings. The substrings themselves are returned in -ovector. Each string uses two elements; the first is the offset to the -start, and the second is the offset to the end. In fact, all the strings have -the same start offset. (Space could have been saved by giving this only once, -but it was decided to retain some compatibility with the way pcre_exec() -returns data, even though the meaning of the strings is different.) -

-

-The strings are returned in reverse order of length; that is, the longest -matching string is given first. If there were too many matches to fit into -ovector, the yield of the function is zero, and the vector is filled with -the longest matches. -

-
-Error returns from pcre_dfa_exec() -
-

-The pcre_dfa_exec() function returns a negative number when it fails. -Many of the errors are the same as for pcre_exec(), and these are -described -above. -There are in addition the following errors that are specific to -pcre_dfa_exec(): -

-  PCRE_ERROR_DFA_UITEM      (-16)
-
-This return is given if pcre_dfa_exec() encounters an item in the pattern -that it does not support, for instance, the use of \C or a back reference. -
-  PCRE_ERROR_DFA_UCOND      (-17)
-
-This return is given if pcre_dfa_exec() encounters a condition item that -uses a back reference for the condition, or a test for recursion in a specific -group. These are not supported. -
-  PCRE_ERROR_DFA_UMLIMIT    (-18)
-
-This return is given if pcre_dfa_exec() is called with an extra -block that contains a setting of the match_limit field. This is not -supported (it is meaningless). -
-  PCRE_ERROR_DFA_WSSIZE     (-19)
-
-This return is given if pcre_dfa_exec() runs out of space in the -workspace vector. -
-  PCRE_ERROR_DFA_RECURSE    (-20)
-
-When a recursive subpattern is processed, the matching function calls itself -recursively, using private vectors for ovector and workspace. This -error is given if the output vector is not large enough. This should be -extremely rare, as a vector of size 1000 is used. -

-
SEE ALSO
-

-pcrebuild(3), pcrecallout(3), pcrecpp(3)(3), -pcrematching(3), pcrepartial(3), pcreposix(3), -pcreprecompile(3), pcresample(3), pcrestack(3). -

-
AUTHOR
-

-Philip Hazel -
-University Computing Service -
-Cambridge CB2 3QH, England. -
-

-
REVISION
-

-Last updated: 11 April 2009 -
-Copyright © 1997-2009 University of Cambridge. -
-

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcrebuild.html b/libs/pcre/doc/html/pcrebuild.html deleted file mode 100644 index 7f06250660..0000000000 --- a/libs/pcre/doc/html/pcrebuild.html +++ /dev/null @@ -1,348 +0,0 @@ - - -pcrebuild specification - - -

pcrebuild man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-

-
PCRE BUILD-TIME OPTIONS
-

-This document describes the optional features of PCRE that can be selected when -the library is compiled. It assumes use of the configure script, where -the optional features are selected or deselected by providing options to -configure before running the make command. However, the same -options can be selected in both Unix-like and non-Unix-like environments using -the GUI facility of CMakeSetup if you are using CMake instead of -configure to build PCRE. -

-

-The complete list of options for configure (which includes the standard -ones such as the selection of the installation directory) can be obtained by -running -

-  ./configure --help
-
-The following sections include descriptions of options whose names begin with ---enable or --disable. These settings specify changes to the defaults for the -configure command. Because of the way that configure works, ---enable and --disable always come in pairs, so the complementary option always -exists as well, but as it specifies the default, it is not described. -

-
C++ SUPPORT
-

-By default, the configure script will search for a C++ compiler and C++ -header files. If it finds them, it automatically builds the C++ wrapper library -for PCRE. You can disable this by adding -

-  --disable-cpp
-
-to the configure command. -

-
UTF-8 SUPPORT
-

-To build PCRE with support for UTF-8 Unicode character strings, add -

-  --enable-utf8
-
-to the configure command. Of itself, this does not make PCRE treat -strings as UTF-8. As well as compiling PCRE with this option, you also have -have to set the PCRE_UTF8 option when you call the pcre_compile() -function. -

-

-If you set --enable-utf8 when compiling in an EBCDIC environment, PCRE expects -its input to be either ASCII or UTF-8 (depending on the runtime option). It is -not possible to support both EBCDIC and UTF-8 codes in the same version of the -library. Consequently, --enable-utf8 and --enable-ebcdic are mutually -exclusive. -

-
UNICODE CHARACTER PROPERTY SUPPORT
-

-UTF-8 support allows PCRE to process character values greater than 255 in the -strings that it handles. On its own, however, it does not provide any -facilities for accessing the properties of such characters. If you want to be -able to use the pattern escapes \P, \p, and \X, which refer to Unicode -character properties, you must add -

-  --enable-unicode-properties
-
-to the configure command. This implies UTF-8 support, even if you have -not explicitly requested it. -

-

-Including Unicode property support adds around 30K of tables to the PCRE -library. Only the general category properties such as Lu and Nd are -supported. Details are given in the -pcrepattern -documentation. -

-
CODE VALUE OF NEWLINE
-

-By default, PCRE interprets the linefeed (LF) character as indicating the end -of a line. This is the normal newline character on Unix-like systems. You can -compile PCRE to use carriage return (CR) instead, by adding -

-  --enable-newline-is-cr
-
-to the configure command. There is also a --enable-newline-is-lf option, -which explicitly specifies linefeed as the newline character. -
-
-Alternatively, you can specify that line endings are to be indicated by the two -character sequence CRLF. If you want this, add -
-  --enable-newline-is-crlf
-
-to the configure command. There is a fourth option, specified by -
-  --enable-newline-is-anycrlf
-
-which causes PCRE to recognize any of the three sequences CR, LF, or CRLF as -indicating a line ending. Finally, a fifth option, specified by -
-  --enable-newline-is-any
-
-causes PCRE to recognize any Unicode newline sequence. -

-

-Whatever line ending convention is selected when PCRE is built can be -overridden when the library functions are called. At build time it is -conventional to use the standard for your operating system. -

-
WHAT \R MATCHES
-

-By default, the sequence \R in a pattern matches any Unicode newline sequence, -whatever has been selected as the line ending sequence. If you specify -

-  --enable-bsr-anycrlf
-
-the default is changed so that \R matches only CR, LF, or CRLF. Whatever is -selected when PCRE is built can be overridden when the library functions are -called. -

-
BUILDING SHARED AND STATIC LIBRARIES
-

-The PCRE building process uses libtool to build both shared and static -Unix libraries by default. You can suppress one of these by adding one of -

-  --disable-shared
-  --disable-static
-
-to the configure command, as required. -

-
POSIX MALLOC USAGE
-

-When PCRE is called through the POSIX interface (see the -pcreposix -documentation), additional working storage is required for holding the pointers -to capturing substrings, because PCRE requires three integers per substring, -whereas the POSIX interface provides only two. If the number of expected -substrings is small, the wrapper function uses space on the stack, because this -is faster than using malloc() for each call. The default threshold above -which the stack is no longer used is 10; it can be changed by adding a setting -such as -

-  --with-posix-malloc-threshold=20
-
-to the configure command. -

-
HANDLING VERY LARGE PATTERNS
-

-Within a compiled pattern, offset values are used to point from one part to -another (for example, from an opening parenthesis to an alternation -metacharacter). By default, two-byte values are used for these offsets, leading -to a maximum size for a compiled pattern of around 64K. This is sufficient to -handle all but the most gigantic patterns. Nevertheless, some people do want to -process enormous patterns, so it is possible to compile PCRE to use three-byte -or four-byte offsets by adding a setting such as -

-  --with-link-size=3
-
-to the configure command. The value given must be 2, 3, or 4. Using -longer offsets slows down the operation of PCRE because it has to load -additional bytes when handling them. -

-
AVOIDING EXCESSIVE STACK USAGE
-

-When matching with the pcre_exec() function, PCRE implements backtracking -by making recursive calls to an internal function called match(). In -environments where the size of the stack is limited, this can severely limit -PCRE's operation. (The Unix environment does not usually suffer from this -problem, but it may sometimes be necessary to increase the maximum stack size. -There is a discussion in the -pcrestack -documentation.) An alternative approach to recursion that uses memory from the -heap to remember data, instead of using recursive function calls, has been -implemented to work round the problem of limited stack size. If you want to -build a version of PCRE that works this way, add -

-  --disable-stack-for-recursion
-
-to the configure command. With this configuration, PCRE will use the -pcre_stack_malloc and pcre_stack_free variables to call memory -management functions. By default these point to malloc() and -free(), but you can replace the pointers so that your own functions are -used. -

-

-Separate functions are provided rather than using pcre_malloc and -pcre_free because the usage is very predictable: the block sizes -requested are always the same, and the blocks are always freed in reverse -order. A calling program might be able to implement optimized functions that -perform better than malloc() and free(). PCRE runs noticeably more -slowly when built in this way. This option affects only the pcre_exec() -function; it is not relevant for the the pcre_dfa_exec() function. -

-
LIMITING PCRE RESOURCE USAGE
-

-Internally, PCRE has a function called match(), which it calls repeatedly -(sometimes recursively) when matching a pattern with the pcre_exec() -function. By controlling the maximum number of times this function may be -called during a single matching operation, a limit can be placed on the -resources used by a single call to pcre_exec(). The limit can be changed -at run time, as described in the -pcreapi -documentation. The default is 10 million, but this can be changed by adding a -setting such as -

-  --with-match-limit=500000
-
-to the configure command. This setting has no effect on the -pcre_dfa_exec() matching function. -

-

-In some environments it is desirable to limit the depth of recursive calls of -match() more strictly than the total number of calls, in order to -restrict the maximum amount of stack (or heap, if --disable-stack-for-recursion -is specified) that is used. A second limit controls this; it defaults to the -value that is set for --with-match-limit, which imposes no additional -constraints. However, you can set a lower limit by adding, for example, -

-  --with-match-limit-recursion=10000
-
-to the configure command. This value can also be overridden at run time. -

-
CREATING CHARACTER TABLES AT BUILD TIME
-

-PCRE uses fixed tables for processing characters whose code values are less -than 256. By default, PCRE is built with a set of tables that are distributed -in the file pcre_chartables.c.dist. These tables are for ASCII codes -only. If you add -

-  --enable-rebuild-chartables
-
-to the configure command, the distributed tables are no longer used. -Instead, a program called dftables is compiled and run. This outputs the -source for new set of tables, created in the default locale of your C runtime -system. (This method of replacing the tables does not work if you are cross -compiling, because dftables is run on the local host. If you need to -create alternative tables when cross compiling, you will have to do so "by -hand".) -

-
USING EBCDIC CODE
-

-PCRE assumes by default that it will run in an environment where the character -code is ASCII (or Unicode, which is a superset of ASCII). This is the case for -most computer operating systems. PCRE can, however, be compiled to run in an -EBCDIC environment by adding -

-  --enable-ebcdic
-
-to the configure command. This setting implies ---enable-rebuild-chartables. You should only use it if you know that you are in -an EBCDIC environment (for example, an IBM mainframe operating system). The ---enable-ebcdic option is incompatible with --enable-utf8. -

-
PCREGREP OPTIONS FOR COMPRESSED FILE SUPPORT
-

-By default, pcregrep reads all files as plain text. You can build it so -that it recognizes files whose names end in .gz or .bz2, and reads -them with libz or libbz2, respectively, by adding one or both of -

-  --enable-pcregrep-libz
-  --enable-pcregrep-libbz2
-
-to the configure command. These options naturally require that the -relevant libraries are installed on your system. Configuration will fail if -they are not. -

-
PCRETEST OPTION FOR LIBREADLINE SUPPORT
-

-If you add -

-  --enable-pcretest-libreadline
-
-to the configure command, pcretest is linked with the -libreadline library, and when its input is from a terminal, it reads it -using the readline() function. This provides line-editing and history -facilities. Note that libreadline is GPL-licenced, so if you distribute a -binary of pcretest linked in this way, there may be licensing issues. -

-

-Setting this option causes the -lreadline option to be added to the -pcretest build. In many operating environments with a sytem-installed -libreadline this is sufficient. However, in some environments (e.g. -if an unmodified distribution version of readline is in use), some extra -configuration may be necessary. The INSTALL file for libreadline says -this: -

-  "Readline uses the termcap functions, but does not link with the
-  termcap or curses library itself, allowing applications which link
-  with readline the to choose an appropriate library."
-
-If your environment has not been set up so that an appropriate library is -automatically included, you may need to add something like -
-  LIBS="-ncurses"
-
-immediately before the configure command. -

-
SEE ALSO
-

-pcreapi(3), pcre_config(3). -

-
AUTHOR
-

-Philip Hazel -
-University Computing Service -
-Cambridge CB2 3QH, England. -
-

-
REVISION
-

-Last updated: 17 March 2009 -
-Copyright © 1997-2009 University of Cambridge. -
-

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcrecallout.html b/libs/pcre/doc/html/pcrecallout.html deleted file mode 100644 index 217764e7b5..0000000000 --- a/libs/pcre/doc/html/pcrecallout.html +++ /dev/null @@ -1,208 +0,0 @@ - - -pcrecallout specification - - -

pcrecallout man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-

-
PCRE CALLOUTS
-

-int (*pcre_callout)(pcre_callout_block *); -

-

-PCRE provides a feature called "callout", which is a means of temporarily -passing control to the caller of PCRE in the middle of pattern matching. The -caller of PCRE provides an external function by putting its entry point in the -global variable pcre_callout. By default, this variable contains NULL, -which disables all calling out. -

-

-Within a regular expression, (?C) indicates the points at which the external -function is to be called. Different callout points can be identified by putting -a number less than 256 after the letter C. The default value is zero. -For example, this pattern has two callout points: -

-  (?C1)abc(?C2)def
-
-If the PCRE_AUTO_CALLOUT option bit is set when pcre_compile() is called, -PCRE automatically inserts callouts, all with number 255, before each item in -the pattern. For example, if PCRE_AUTO_CALLOUT is used with the pattern -
-  A(\d{2}|--)
-
-it is processed as if it were -
-
-(?C255)A(?C255)((?C255)\d{2}(?C255)|(?C255)-(?C255)-(?C255))(?C255) -
-
-Notice that there is a callout before and after each parenthesis and -alternation bar. Automatic callouts can be used for tracking the progress of -pattern matching. The -pcretest -command has an option that sets automatic callouts; when it is used, the output -indicates how the pattern is matched. This is useful information when you are -trying to optimize the performance of a particular pattern. -

-
MISSING CALLOUTS
-

-You should be aware that, because of optimizations in the way PCRE matches -patterns by default, callouts sometimes do not happen. For example, if the -pattern is -

-  ab(?C4)cd
-
-PCRE knows that any matching string must contain the letter "d". If the subject -string is "abyz", the lack of "d" means that matching doesn't ever start, and -the callout is never reached. However, with "abyd", though the result is still -no match, the callout is obeyed. -

-

-You can disable these optimizations by passing the PCRE_NO_START_OPTIMIZE -option to pcre_exec() or pcre_dfa_exec(). This slows down the -matching process, but does ensure that callouts such as the example above are -obeyed. -

-
THE CALLOUT INTERFACE
-

-During matching, when PCRE reaches a callout point, the external function -defined by pcre_callout is called (if it is set). This applies to both -the pcre_exec() and the pcre_dfa_exec() matching functions. The -only argument to the callout function is a pointer to a pcre_callout -block. This structure contains the following fields: -

-  int          version;
-  int          callout_number;
-  int         *offset_vector;
-  const char  *subject;
-  int          subject_length;
-  int          start_match;
-  int          current_position;
-  int          capture_top;
-  int          capture_last;
-  void        *callout_data;
-  int          pattern_position;
-  int          next_item_length;
-
-The version field is an integer containing the version number of the -block format. The initial version was 0; the current version is 1. The version -number will change again in future if additional fields are added, but the -intention is never to remove any of the existing fields. -

-

-The callout_number field contains the number of the callout, as compiled -into the pattern (that is, the number after ?C for manual callouts, and 255 for -automatically generated callouts). -

-

-The offset_vector field is a pointer to the vector of offsets that was -passed by the caller to pcre_exec() or pcre_dfa_exec(). When -pcre_exec() is used, the contents can be inspected in order to extract -substrings that have been matched so far, in the same way as for extracting -substrings after a match has completed. For pcre_dfa_exec() this field is -not useful. -

-

-The subject and subject_length fields contain copies of the values -that were passed to pcre_exec(). -

-

-The start_match field normally contains the offset within the subject at -which the current match attempt started. However, if the escape sequence \K -has been encountered, this value is changed to reflect the modified starting -point. If the pattern is not anchored, the callout function may be called -several times from the same point in the pattern for different starting points -in the subject. -

-

-The current_position field contains the offset within the subject of the -current match pointer. -

-

-When the pcre_exec() function is used, the capture_top field -contains one more than the number of the highest numbered captured substring so -far. If no substrings have been captured, the value of capture_top is -one. This is always the case when pcre_dfa_exec() is used, because it -does not support captured substrings. -

-

-The capture_last field contains the number of the most recently captured -substring. If no substrings have been captured, its value is -1. This is always -the case when pcre_dfa_exec() is used. -

-

-The callout_data field contains a value that is passed to -pcre_exec() or pcre_dfa_exec() specifically so that it can be -passed back in callouts. It is passed in the pcre_callout field of the -pcre_extra data structure. If no such data was passed, the value of -callout_data in a pcre_callout block is NULL. There is a -description of the pcre_extra structure in the -pcreapi -documentation. -

-

-The pattern_position field is present from version 1 of the -pcre_callout structure. It contains the offset to the next item to be -matched in the pattern string. -

-

-The next_item_length field is present from version 1 of the -pcre_callout structure. It contains the length of the next item to be -matched in the pattern string. When the callout immediately precedes an -alternation bar, a closing parenthesis, or the end of the pattern, the length -is zero. When the callout precedes an opening parenthesis, the length is that -of the entire subpattern. -

-

-The pattern_position and next_item_length fields are intended to -help in distinguishing between different automatic callouts, which all have the -same callout number. However, they are set for all callouts. -

-
RETURN VALUES
-

-The external callout function returns an integer to PCRE. If the value is zero, -matching proceeds as normal. If the value is greater than zero, matching fails -at the current point, but the testing of other matching possibilities goes -ahead, just as if a lookahead assertion had failed. If the value is less than -zero, the match is abandoned, and pcre_exec() (or pcre_dfa_exec()) -returns the negative value. -

-

-Negative values should normally be chosen from the set of PCRE_ERROR_xxx -values. In particular, PCRE_ERROR_NOMATCH forces a standard "no match" failure. -The error number PCRE_ERROR_CALLOUT is reserved for use by callout functions; -it will never be used by PCRE itself. -

-
AUTHOR
-

-Philip Hazel -
-University Computing Service -
-Cambridge CB2 3QH, England. -
-

-
REVISION
-

-Last updated: 15 March 2009 -
-Copyright © 1997-2009 University of Cambridge. -
-

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcrecompat.html b/libs/pcre/doc/html/pcrecompat.html deleted file mode 100644 index d1b93d043d..0000000000 --- a/libs/pcre/doc/html/pcrecompat.html +++ /dev/null @@ -1,179 +0,0 @@ - - -pcrecompat specification - - -

pcrecompat man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-
-DIFFERENCES BETWEEN PCRE AND PERL -
-

-This document describes the differences in the ways that PCRE and Perl handle -regular expressions. The differences described here are mainly with respect to -Perl 5.8, though PCRE versions 7.0 and later contain some features that are -expected to be in the forthcoming Perl 5.10. -

-

-1. PCRE has only a subset of Perl's UTF-8 and Unicode support. Details of what -it does have are given in the -section on UTF-8 support -in the main -pcre -page. -

-

-2. PCRE does not allow repeat quantifiers on lookahead assertions. Perl permits -them, but they do not mean what you might think. For example, (?!a){3} does -not assert that the next three characters are not "a". It just asserts that the -next character is not "a" three times. -

-

-3. Capturing subpatterns that occur inside negative lookahead assertions are -counted, but their entries in the offsets vector are never set. Perl sets its -numerical variables from any such patterns that are matched before the -assertion fails to match something (thereby succeeding), but only if the -negative lookahead assertion contains just one branch. -

-

-4. Though binary zero characters are supported in the subject string, they are -not allowed in a pattern string because it is passed as a normal C string, -terminated by zero. The escape sequence \0 can be used in the pattern to -represent a binary zero. -

-

-5. The following Perl escape sequences are not supported: \l, \u, \L, -\U, and \N. In fact these are implemented by Perl's general string-handling -and are not part of its pattern matching engine. If any of these are -encountered by PCRE, an error is generated. -

-

-6. The Perl escape sequences \p, \P, and \X are supported only if PCRE is -built with Unicode character property support. The properties that can be -tested with \p and \P are limited to the general category properties such as -Lu and Nd, script names such as Greek or Han, and the derived properties Any -and L&. -

-

-7. PCRE does support the \Q...\E escape for quoting substrings. Characters in -between are treated as literals. This is slightly different from Perl in that $ -and @ are also handled as literals inside the quotes. In Perl, they cause -variable interpolation (but of course PCRE does not have variables). Note the -following examples: -

-    Pattern            PCRE matches      Perl matches
-
-    \Qabc$xyz\E        abc$xyz           abc followed by the contents of $xyz
-    \Qabc\$xyz\E       abc\$xyz          abc\$xyz
-    \Qabc\E\$\Qxyz\E   abc$xyz           abc$xyz
-
-The \Q...\E sequence is recognized both inside and outside character classes. -

-

-8. Fairly obviously, PCRE does not support the (?{code}) and (??{code}) -constructions. However, there is support for recursive patterns. This is not -available in Perl 5.8, but will be in Perl 5.10. Also, the PCRE "callout" -feature allows an external function to be called during pattern matching. See -the -pcrecallout -documentation for details. -

-

-9. Subpatterns that are called recursively or as "subroutines" are always -treated as atomic groups in PCRE. This is like Python, but unlike Perl. -

-

-10. There are some differences that are concerned with the settings of captured -strings when part of a pattern is repeated. For example, matching "aba" against -the pattern /^(a(b)?)+$/ in Perl leaves $2 unset, but in PCRE it is set to "b". -

-

-11. PCRE does support Perl 5.10's backtracking verbs (*ACCEPT), (*FAIL), (*F), -(*COMMIT), (*PRUNE), (*SKIP), and (*THEN), but only in the forms without an -argument. PCRE does not support (*MARK). If (*ACCEPT) is within capturing -parentheses, PCRE does not set that capture group; this is different to Perl. -

-

-12. PCRE provides some extensions to the Perl regular expression facilities. -Perl 5.10 will include new features that are not in earlier versions, some of -which (such as named parentheses) have been in PCRE for some time. This list is -with respect to Perl 5.10: -
-
-(a) Although lookbehind assertions must match fixed length strings, each -alternative branch of a lookbehind assertion can match a different length of -string. Perl requires them all to have the same length. -
-
-(b) If PCRE_DOLLAR_ENDONLY is set and PCRE_MULTILINE is not set, the $ -meta-character matches only at the very end of the string. -
-
-(c) If PCRE_EXTRA is set, a backslash followed by a letter with no special -meaning is faulted. Otherwise, like Perl, the backslash is quietly ignored. -(Perl can be made to issue a warning.) -
-
-(d) If PCRE_UNGREEDY is set, the greediness of the repetition quantifiers is -inverted, that is, by default they are not greedy, but if followed by a -question mark they are. -
-
-(e) PCRE_ANCHORED can be used at matching time to force a pattern to be tried -only at the first matching position in the subject string. -
-
-(f) The PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, and PCRE_NO_AUTO_CAPTURE -options for pcre_exec() have no Perl equivalents. -
-
-(g) The \R escape sequence can be restricted to match only CR, LF, or CRLF -by the PCRE_BSR_ANYCRLF option. -
-
-(h) The callout facility is PCRE-specific. -
-
-(i) The partial matching facility is PCRE-specific. -
-
-(j) Patterns compiled by PCRE can be saved and re-used at a later time, even on -different hosts that have the other endianness. -
-
-(k) The alternative matching function (pcre_dfa_exec()) matches in a -different way and is not Perl-compatible. -
-
-(l) PCRE recognizes some special sequences such as (*CR) at the start of -a pattern that set overall options that cannot be changed within the pattern. -

-
-AUTHOR -
-

-Philip Hazel -
-University Computing Service -
-Cambridge CB2 3QH, England. -
-

-
-REVISION -
-

-Last updated: 11 September 2007 -
-Copyright © 1997-2007 University of Cambridge. -
-

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcrecpp.html b/libs/pcre/doc/html/pcrecpp.html deleted file mode 100644 index 7b52d92fda..0000000000 --- a/libs/pcre/doc/html/pcrecpp.html +++ /dev/null @@ -1,370 +0,0 @@ - - -pcrecpp specification - - -

pcrecpp man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-

-
SYNOPSIS OF C++ WRAPPER
-

-#include <pcrecpp.h> -

-
DESCRIPTION
-

-The C++ wrapper for PCRE was provided by Google Inc. Some additional -functionality was added by Giuseppe Maxia. This brief man page was constructed -from the notes in the pcrecpp.h file, which should be consulted for -further details. -

-
MATCHING INTERFACE
-

-The "FullMatch" operation checks that supplied text matches a supplied pattern -exactly. If pointer arguments are supplied, it copies matched sub-strings that -match sub-patterns into them. -

-  Example: successful match
-     pcrecpp::RE re("h.*o");
-     re.FullMatch("hello");
-
-  Example: unsuccessful match (requires full match):
-     pcrecpp::RE re("e");
-     !re.FullMatch("hello");
-
-  Example: creating a temporary RE object:
-     pcrecpp::RE("h.*o").FullMatch("hello");
-
-You can pass in a "const char*" or a "string" for "text". The examples below -tend to use a const char*. You can, as in the different examples above, store -the RE object explicitly in a variable or use a temporary RE object. The -examples below use one mode or the other arbitrarily. Either could correctly be -used for any of these examples. -

-

-You must supply extra pointer arguments to extract matched subpieces. -

-  Example: extracts "ruby" into "s" and 1234 into "i"
-     int i;
-     string s;
-     pcrecpp::RE re("(\\w+):(\\d+)");
-     re.FullMatch("ruby:1234", &s, &i);
-
-  Example: does not try to extract any extra sub-patterns
-     re.FullMatch("ruby:1234", &s);
-
-  Example: does not try to extract into NULL
-     re.FullMatch("ruby:1234", NULL, &i);
-
-  Example: integer overflow causes failure
-     !re.FullMatch("ruby:1234567891234", NULL, &i);
-
-  Example: fails because there aren't enough sub-patterns:
-     !pcrecpp::RE("\\w+:\\d+").FullMatch("ruby:1234", &s);
-
-  Example: fails because string cannot be stored in integer
-     !pcrecpp::RE("(.*)").FullMatch("ruby", &i);
-
-The provided pointer arguments can be pointers to any scalar numeric -type, or one of: -
-   string        (matched piece is copied to string)
-   StringPiece   (StringPiece is mutated to point to matched piece)
-   T             (where "bool T::ParseFrom(const char*, int)" exists)
-   NULL          (the corresponding matched sub-pattern is not copied)
-
-The function returns true iff all of the following conditions are satisfied: -
-  a. "text" matches "pattern" exactly;
-
-  b. The number of matched sub-patterns is >= number of supplied
-     pointers;
-
-  c. The "i"th argument has a suitable type for holding the
-     string captured as the "i"th sub-pattern. If you pass in
-     void * NULL for the "i"th argument, or a non-void * NULL
-     of the correct type, or pass fewer arguments than the
-     number of sub-patterns, "i"th captured sub-pattern is
-     ignored.
-
-CAVEAT: An optional sub-pattern that does not exist in the matched -string is assigned the empty string. Therefore, the following will -return false (because the empty string is not a valid number): -
-   int number;
-   pcrecpp::RE::FullMatch("abc", "[a-z]+(\\d+)?", &number);
-
-The matching interface supports at most 16 arguments per call. -If you need more, consider using the more general interface -pcrecpp::RE::DoMatch. See pcrecpp.h for the signature for -DoMatch. -

-

-NOTE: Do not use no_arg, which is used internally to mark the end of a -list of optional arguments, as a placeholder for missing arguments, as this can -lead to segfaults. -

-
QUOTING METACHARACTERS
-

-You can use the "QuoteMeta" operation to insert backslashes before all -potentially meaningful characters in a string. The returned string, used as a -regular expression, will exactly match the original string. -

-  Example:
-     string quoted = RE::QuoteMeta(unquoted);
-
-Note that it's legal to escape a character even if it has no special meaning in -a regular expression -- so this function does that. (This also makes it -identical to the perl function of the same name; see "perldoc -f quotemeta".) -For example, "1.5-2.0?" becomes "1\.5\-2\.0\?". -

-
PARTIAL MATCHES
-

-You can use the "PartialMatch" operation when you want the pattern -to match any substring of the text. -

-  Example: simple search for a string:
-     pcrecpp::RE("ell").PartialMatch("hello");
-
-  Example: find first number in a string:
-     int number;
-     pcrecpp::RE re("(\\d+)");
-     re.PartialMatch("x*100 + 20", &number);
-     assert(number == 100);
-
-

-
UTF-8 AND THE MATCHING INTERFACE
-

-By default, pattern and text are plain text, one byte per character. The UTF8 -flag, passed to the constructor, causes both pattern and string to be treated -as UTF-8 text, still a byte stream but potentially multiple bytes per -character. In practice, the text is likelier to be UTF-8 than the pattern, but -the match returned may depend on the UTF8 flag, so always use it when matching -UTF8 text. For example, "." will match one byte normally but with UTF8 set may -match up to three bytes of a multi-byte character. -

-  Example:
-     pcrecpp::RE_Options options;
-     options.set_utf8();
-     pcrecpp::RE re(utf8_pattern, options);
-     re.FullMatch(utf8_string);
-
-  Example: using the convenience function UTF8():
-     pcrecpp::RE re(utf8_pattern, pcrecpp::UTF8());
-     re.FullMatch(utf8_string);
-
-NOTE: The UTF8 flag is ignored if pcre was not configured with the -
-      --enable-utf8 flag.
-
-

-
PASSING MODIFIERS TO THE REGULAR EXPRESSION ENGINE
-

-PCRE defines some modifiers to change the behavior of the regular expression -engine. The C++ wrapper defines an auxiliary class, RE_Options, as a vehicle to -pass such modifiers to a RE class. Currently, the following modifiers are -supported: -

-   modifier              description               Perl corresponding
-
-   PCRE_CASELESS         case insensitive match      /i
-   PCRE_MULTILINE        multiple lines match        /m
-   PCRE_DOTALL           dot matches newlines        /s
-   PCRE_DOLLAR_ENDONLY   $ matches only at end       N/A
-   PCRE_EXTRA            strict escape parsing       N/A
-   PCRE_EXTENDED         ignore whitespaces          /x
-   PCRE_UTF8             handles UTF8 chars          built-in
-   PCRE_UNGREEDY         reverses * and *?           N/A
-   PCRE_NO_AUTO_CAPTURE  disables capturing parens   N/A (*)
-
-(*) Both Perl and PCRE allow non capturing parentheses by means of the -"?:" modifier within the pattern itself. e.g. (?:ab|cd) does not -capture, while (ab|cd) does. -

-

-For a full account on how each modifier works, please check the -PCRE API reference page. -

-

-For each modifier, there are two member functions whose name is made -out of the modifier in lowercase, without the "PCRE_" prefix. For -instance, PCRE_CASELESS is handled by -

-  bool caseless()
-
-which returns true if the modifier is set, and -
-  RE_Options & set_caseless(bool)
-
-which sets or unsets the modifier. Moreover, PCRE_EXTRA_MATCH_LIMIT can be -accessed through the set_match_limit() and match_limit() member -functions. Setting match_limit to a non-zero value will limit the -execution of pcre to keep it from doing bad things like blowing the stack or -taking an eternity to return a result. A value of 5000 is good enough to stop -stack blowup in a 2MB thread stack. Setting match_limit to zero disables -match limiting. Alternatively, you can call match_limit_recursion() -which uses PCRE_EXTRA_MATCH_LIMIT_RECURSION to limit how much PCRE -recurses. match_limit() limits the number of matches PCRE does; -match_limit_recursion() limits the depth of internal recursion, and -therefore the amount of stack that is used. -

-

-Normally, to pass one or more modifiers to a RE class, you declare -a RE_Options object, set the appropriate options, and pass this -object to a RE constructor. Example: -

-   RE_options opt;
-   opt.set_caseless(true);
-   if (RE("HELLO", opt).PartialMatch("hello world")) ...
-
-RE_options has two constructors. The default constructor takes no arguments and -creates a set of flags that are off by default. The optional parameter -option_flags is to facilitate transfer of legacy code from C programs. -This lets you do -
-   RE(pattern,
-     RE_Options(PCRE_CASELESS|PCRE_MULTILINE)).PartialMatch(str);
-
-However, new code is better off doing -
-   RE(pattern,
-     RE_Options().set_caseless(true).set_multiline(true))
-       .PartialMatch(str);
-
-If you are going to pass one of the most used modifiers, there are some -convenience functions that return a RE_Options class with the -appropriate modifier already set: CASELESS(), UTF8(), -MULTILINE(), DOTALL(), and EXTENDED(). -

-

-If you need to set several options at once, and you don't want to go through -the pains of declaring a RE_Options object and setting several options, there -is a parallel method that give you such ability on the fly. You can concatenate -several set_xxxxx() member functions, since each of them returns a -reference to its class object. For example, to pass PCRE_CASELESS, -PCRE_EXTENDED, and PCRE_MULTILINE to a RE with one statement, you may write: -

-   RE(" ^ xyz \\s+ .* blah$",
-     RE_Options()
-       .set_caseless(true)
-       .set_extended(true)
-       .set_multiline(true)).PartialMatch(sometext);
-
-
-

-
SCANNING TEXT INCREMENTALLY
-

-The "Consume" operation may be useful if you want to repeatedly -match regular expressions at the front of a string and skip over -them as they match. This requires use of the "StringPiece" type, -which represents a sub-range of a real string. Like RE, StringPiece -is defined in the pcrecpp namespace. -

-  Example: read lines of the form "var = value" from a string.
-     string contents = ...;                 // Fill string somehow
-     pcrecpp::StringPiece input(contents);  // Wrap in a StringPiece
-
-

-

-

-     string var;
-     int value;
-     pcrecpp::RE re("(\\w+) = (\\d+)\n");
-     while (re.Consume(&input, &var, &value)) {
-       ...;
-     }
-
-Each successful call to "Consume" will set "var/value", and also -advance "input" so it points past the matched text. -

-

-The "FindAndConsume" operation is similar to "Consume" but does not -anchor your match at the beginning of the string. For example, you -could extract all words from a string by repeatedly calling -

-  pcrecpp::RE("(\\w+)").FindAndConsume(&input, &word)
-
-

-
PARSING HEX/OCTAL/C-RADIX NUMBERS
-

-By default, if you pass a pointer to a numeric value, the -corresponding text is interpreted as a base-10 number. You can -instead wrap the pointer with a call to one of the operators Hex(), -Octal(), or CRadix() to interpret the text in another base. The -CRadix operator interprets C-style "0" (base-8) and "0x" (base-16) -prefixes, but defaults to base-10. -

-  Example:
-    int a, b, c, d;
-    pcrecpp::RE re("(.*) (.*) (.*) (.*)");
-    re.FullMatch("100 40 0100 0x40",
-                 pcrecpp::Octal(&a), pcrecpp::Hex(&b),
-                 pcrecpp::CRadix(&c), pcrecpp::CRadix(&d));
-
-will leave 64 in a, b, c, and d. -

-
REPLACING PARTS OF STRINGS
-

-You can replace the first match of "pattern" in "str" with "rewrite". -Within "rewrite", backslash-escaped digits (\1 to \9) can be -used to insert text matching corresponding parenthesized group -from the pattern. \0 in "rewrite" refers to the entire matching -text. For example: -

-  string s = "yabba dabba doo";
-  pcrecpp::RE("b+").Replace("d", &s);
-
-will leave "s" containing "yada dabba doo". The result is true if the pattern -matches and a replacement occurs, false otherwise. -

-

-GlobalReplace is like Replace except that it replaces all -occurrences of the pattern in the string with the rewrite. Replacements are -not subject to re-matching. For example: -

-  string s = "yabba dabba doo";
-  pcrecpp::RE("b+").GlobalReplace("d", &s);
-
-will leave "s" containing "yada dada doo". It returns the number of -replacements made. -

-

-Extract is like Replace, except that if the pattern matches, -"rewrite" is copied into "out" (an additional argument) with substitutions. -The non-matching portions of "text" are ignored. Returns true iff a match -occurred and the extraction happened successfully; if no match occurs, the -string is left unaffected. -

-
AUTHOR
-

-The C++ wrapper was contributed by Google Inc. -
-Copyright © 2007 Google Inc. -
-

-
REVISION
-

-Last updated: 17 March 2009 -
-

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcregrep.html b/libs/pcre/doc/html/pcregrep.html deleted file mode 100644 index 13e45d90ae..0000000000 --- a/libs/pcre/doc/html/pcregrep.html +++ /dev/null @@ -1,533 +0,0 @@ - - -pcregrep specification - - -

pcregrep man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-

-
SYNOPSIS
-

-pcregrep [options] [long options] [pattern] [path1 path2 ...] -

-
DESCRIPTION
-

-pcregrep searches files for character patterns, in the same way as other -grep commands do, but it uses the PCRE regular expression library to support -patterns that are compatible with the regular expressions of Perl 5. See -pcrepattern(3) -for a full description of syntax and semantics of the regular expressions -that PCRE supports. -

-

-Patterns, whether supplied on the command line or in a separate file, are given -without delimiters. For example: -

-  pcregrep Thursday /etc/motd
-
-If you attempt to use delimiters (for example, by surrounding a pattern with -slashes, as is common in Perl scripts), they are interpreted as part of the -pattern. Quotes can of course be used to delimit patterns on the command line -because they are interpreted by the shell, and indeed they are required if a -pattern contains white space or shell metacharacters. -

-

-The first argument that follows any option settings is treated as the single -pattern to be matched when neither -e nor -f is present. -Conversely, when one or both of these options are used to specify patterns, all -arguments are treated as path names. At least one of -e, -f, or an -argument pattern must be provided. -

-

-If no files are specified, pcregrep reads the standard input. The -standard input can also be referenced by a name consisting of a single hyphen. -For example: -

-  pcregrep some-pattern /file1 - /file3
-
-By default, each line that matches a pattern is copied to the standard -output, and if there is more than one file, the file name is output at the -start of each line, followed by a colon. However, there are options that can -change how pcregrep behaves. In particular, the -M option makes it -possible to search for patterns that span line boundaries. What defines a line -boundary is controlled by the -N (--newline) option. -

-

-Patterns are limited to 8K or BUFSIZ characters, whichever is the greater. -BUFSIZ is defined in <stdio.h>. When there is more than one pattern -(specified by the use of -e and/or -f), each pattern is applied to -each line in the order in which they are defined, except that all the -e -patterns are tried before the -f patterns. -

-

-By default, as soon as one pattern matches (or fails to match when -v is -used), no further patterns are considered. However, if --colour (or ---color) is used to colour the matching substrings, or if ---only-matching, --file-offsets, or --line-offsets is used to -output only the part of the line that matched (either shown literally, or as an -offset), scanning resumes immediately following the match, so that further -matches on the same line can be found. If there are multiple patterns, they are -all tried on the remainder of the line, but patterns that follow the one that -matched are not tried on the earlier part of the line. -

-

-This is the same behaviour as GNU grep, but it does mean that the order in -which multiple patterns are specified can affect the output when one of the -above options is used. -

-

-Patterns that can match an empty string are accepted, but empty string -matches are not recognized. An example is the pattern "(super)?(man)?", in -which all components are optional. This pattern finds all occurrences of both -"super" and "man"; the output differs from matching with "super|man" when only -the matching substrings are being shown. -

-

-If the LC_ALL or LC_CTYPE environment variable is set, -pcregrep uses the value to set a locale when calling the PCRE library. -The --locale option can be used to override this. -

-
SUPPORT FOR COMPRESSED FILES
-

-It is possible to compile pcregrep so that it uses libz or -libbz2 to read files whose names end in .gz or .bz2, -respectively. You can find out whether your binary has support for one or both -of these file types by running it with the --help option. If the -appropriate support is not present, files are treated as plain text. The -standard input is always so treated. -

-
OPTIONS
-

--- -This terminate the list of options. It is useful if the next item on the -command line starts with a hyphen but is not an option. This allows for the -processing of patterns and filenames that start with hyphens. -

-

--A number, --after-context=number -Output number lines of context after each matching line. If filenames -and/or line numbers are being output, a hyphen separator is used instead of a -colon for the context lines. A line containing "--" is output between each -group of lines, unless they are in fact contiguous in the input file. The value -of number is expected to be relatively small. However, pcregrep -guarantees to have up to 8K of following text available for context output. -

-

--B number, --before-context=number -Output number lines of context before each matching line. If filenames -and/or line numbers are being output, a hyphen separator is used instead of a -colon for the context lines. A line containing "--" is output between each -group of lines, unless they are in fact contiguous in the input file. The value -of number is expected to be relatively small. However, pcregrep -guarantees to have up to 8K of preceding text available for context output. -

-

--C number, --context=number -Output number lines of context both before and after each matching line. -This is equivalent to setting both -A and -B to the same value. -

-

--c, --count -Do not output individual lines; instead just output a count of the number of -lines that would otherwise have been output. If several files are given, a -count is output for each of them. In this mode, the -A, -B, and --C options are ignored. -

-

---colour, --color -If this option is given without any data, it is equivalent to "--colour=auto". -If data is required, it must be given in the same shell item, separated by an -equals sign. -

-

---colour=value, --color=value -This option specifies under what circumstances the parts of a line that matched -a pattern should be coloured in the output. By default, the output is not -coloured. The value (which is optional, see above) may be "never", "always", or -"auto". In the latter case, colouring happens only if the standard output is -connected to a terminal. More resources are used when colouring is enabled, -because pcregrep has to search for all possible matches in a line, not -just one, in order to colour them all. -

-

-The colour that is used can be specified by setting the environment variable -PCREGREP_COLOUR or PCREGREP_COLOR. The value of this variable should be a -string of two numbers, separated by a semicolon. They are copied directly into -the control string for setting colour on a terminal, so it is your -responsibility to ensure that they make sense. If neither of the environment -variables is set, the default is "1;31", which gives red. -

-

--D action, --devices=action -If an input path is not a regular file or a directory, "action" specifies how -it is to be processed. Valid values are "read" (the default) or "skip" -(silently skip the path). -

-

--d action, --directories=action -If an input path is a directory, "action" specifies how it is to be processed. -Valid values are "read" (the default), "recurse" (equivalent to the -r -option), or "skip" (silently skip the path). In the default case, directories -are read as if they were ordinary files. In some operating systems the effect -of reading a directory like this is an immediate end-of-file. -

-

--e pattern, --regex=pattern, --regexp=pattern -Specify a pattern to be matched. This option can be used multiple times in -order to specify several patterns. It can also be used as a way of specifying a -single pattern that starts with a hyphen. When -e is used, no argument -pattern is taken from the command line; all arguments are treated as file -names. There is an overall maximum of 100 patterns. They are applied to each -line in the order in which they are defined until one matches (or fails to -match if -v is used). If -f is used with -e, the command line -patterns are matched first, followed by the patterns from the file, independent -of the order in which these options are specified. Note that multiple use of --e is not the same as a single pattern with alternatives. For example, -X|Y finds the first character in a line that is X or Y, whereas if the two -patterns are given separately, pcregrep finds X if it is present, even if -it follows Y in the line. It finds Y only if there is no X in the line. This -really matters only if you are using -o to show the part(s) of the line -that matched. -

-

---exclude=pattern -When pcregrep is searching the files in a directory as a consequence of -the -r (recursive search) option, any regular files whose names match the -pattern are excluded. Subdirectories are not excluded by this option; they are -searched recursively, subject to the --exclude_dir and ---include_dir options. The pattern is a PCRE regular expression, and is -matched against the final component of the file name (not the entire path). If -a file name matches both --include and --exclude, it is excluded. -There is no short form for this option. -

-

---exclude_dir=pattern -When pcregrep is searching the contents of a directory as a consequence -of the -r (recursive search) option, any subdirectories whose names match -the pattern are excluded. (Note that the \fP--exclude\fP option does not affect -subdirectories.) The pattern is a PCRE regular expression, and is matched -against the final component of the name (not the entire path). If a -subdirectory name matches both --include_dir and --exclude_dir, it -is excluded. There is no short form for this option. -

-

--F, --fixed-strings -Interpret each pattern as a list of fixed strings, separated by newlines, -instead of as a regular expression. The -w (match as a word) and -x -(match whole line) options can be used with -F. They apply to each of the -fixed strings. A line is selected if any of the fixed strings are found in it -(subject to -w or -x, if present). -

-

--f filename, --file=filename -Read a number of patterns from the file, one per line, and match them against -each line of input. A data line is output if any of the patterns match it. The -filename can be given as "-" to refer to the standard input. When -f is -used, patterns specified on the command line using -e may also be -present; they are tested before the file's patterns. However, no other pattern -is taken from the command line; all arguments are treated as file names. There -is an overall maximum of 100 patterns. Trailing white space is removed from -each line, and blank lines are ignored. An empty file contains no patterns and -therefore matches nothing. See also the comments about multiple patterns versus -a single pattern with alternatives in the description of -e above. -

-

---file-offsets -Instead of showing lines or parts of lines that match, show each match as an -offset from the start of the file and a length, separated by a comma. In this -mode, no context is shown. That is, the -A, -B, and -C -options are ignored. If there is more than one match in a line, each of them is -shown separately. This option is mutually exclusive with --line-offsets -and --only-matching. -

-

--H, --with-filename -Force the inclusion of the filename at the start of output lines when searching -a single file. By default, the filename is not shown in this case. For matching -lines, the filename is followed by a colon; for context lines, a hyphen -separator is used. If a line number is also being output, it follows the file -name. -

-

--h, --no-filename -Suppress the output filenames when searching multiple files. By default, -filenames are shown when multiple files are searched. For matching lines, the -filename is followed by a colon; for context lines, a hyphen separator is used. -If a line number is also being output, it follows the file name. -

-

---help -Output a help message, giving brief details of the command options and file -type support, and then exit. -

-

--i, --ignore-case -Ignore upper/lower case distinctions during comparisons. -

-

---include=pattern -When pcregrep is searching the files in a directory as a consequence of -the -r (recursive search) option, only those regular files whose names -match the pattern are included. Subdirectories are always included and searched -recursively, subject to the \fP--include_dir\fP and --exclude_dir -options. The pattern is a PCRE regular expression, and is matched against the -final component of the file name (not the entire path). If a file name matches -both --include and --exclude, it is excluded. There is no short -form for this option. -

-

---include_dir=pattern -When pcregrep is searching the contents of a directory as a consequence -of the -r (recursive search) option, only those subdirectories whose -names match the pattern are included. (Note that the --include option -does not affect subdirectories.) The pattern is a PCRE regular expression, and -is matched against the final component of the name (not the entire path). If a -subdirectory name matches both --include_dir and --exclude_dir, it -is excluded. There is no short form for this option. -

-

--L, --files-without-match -Instead of outputting lines from the files, just output the names of the files -that do not contain any lines that would have been output. Each file name is -output once, on a separate line. -

-

--l, --files-with-matches -Instead of outputting lines from the files, just output the names of the files -containing lines that would have been output. Each file name is output -once, on a separate line. Searching stops as soon as a matching line is found -in a file. -

-

---label=name -This option supplies a name to be used for the standard input when file names -are being output. If not supplied, "(standard input)" is used. There is no -short form for this option. -

-

---line-offsets -Instead of showing lines or parts of lines that match, show each match as a -line number, the offset from the start of the line, and a length. The line -number is terminated by a colon (as usual; see the -n option), and the -offset and length are separated by a comma. In this mode, no context is shown. -That is, the -A, -B, and -C options are ignored. If there is -more than one match in a line, each of them is shown separately. This option is -mutually exclusive with --file-offsets and --only-matching. -

-

---locale=locale-name -This option specifies a locale to be used for pattern matching. It overrides -the value in the LC_ALL or LC_CTYPE environment variables. If no -locale is specified, the PCRE library's default (usually the "C" locale) is -used. There is no short form for this option. -

-

--M, --multiline -Allow patterns to match more than one line. When this option is given, patterns -may usefully contain literal newline characters and internal occurrences of ^ -and $ characters. The output for any one match may consist of more than one -line. When this option is set, the PCRE library is called in "multiline" mode. -There is a limit to the number of lines that can be matched, imposed by the way -that pcregrep buffers the input file as it scans it. However, -pcregrep ensures that at least 8K characters or the rest of the document -(whichever is the shorter) are available for forward matching, and similarly -the previous 8K characters (or all the previous characters, if fewer than 8K) -are guaranteed to be available for lookbehind assertions. -

-

--N newline-type, --newline=newline-type -The PCRE library supports five different conventions for indicating -the ends of lines. They are the single-character sequences CR (carriage return) -and LF (linefeed), the two-character sequence CRLF, an "anycrlf" convention, -which recognizes any of the preceding three types, and an "any" convention, in -which any Unicode line ending sequence is assumed to end a line. The Unicode -sequences are the three just mentioned, plus VT (vertical tab, U+000B), FF -(formfeed, U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and -PS (paragraph separator, U+2029). -
-
-When the PCRE library is built, a default line-ending sequence is specified. -This is normally the standard sequence for the operating system. Unless -otherwise specified by this option, pcregrep uses the library's default. -The possible values for this option are CR, LF, CRLF, ANYCRLF, or ANY. This -makes it possible to use pcregrep on files that have come from other -environments without having to modify their line endings. If the data that is -being scanned does not agree with the convention set by this option, -pcregrep may behave in strange ways. -

-

--n, --line-number -Precede each output line by its line number in the file, followed by a colon -for matching lines or a hyphen for context lines. If the filename is also being -output, it precedes the line number. This option is forced if ---line-offsets is used. -

-

--o, --only-matching -Show only the part of the line that matched a pattern. In this mode, no -context is shown. That is, the -A, -B, and -C options are -ignored. If there is more than one match in a line, each of them is shown -separately. If -o is combined with -v (invert the sense of the -match to find non-matching lines), no output is generated, but the return code -is set appropriately. This option is mutually exclusive with ---file-offsets and --line-offsets. -

-

--q, --quiet -Work quietly, that is, display nothing except error messages. The exit -status indicates whether or not any matches were found. -

-

--r, --recursive -If any given path is a directory, recursively scan the files it contains, -taking note of any --include and --exclude settings. By default, a -directory is read as a normal file; in some operating systems this gives an -immediate end-of-file. This option is a shorthand for setting the -d -option to "recurse". -

-

--s, --no-messages -Suppress error messages about non-existent or unreadable files. Such files are -quietly skipped. However, the return code is still 2, even if matches were -found in other files. -

-

--u, --utf-8 -Operate in UTF-8 mode. This option is available only if PCRE has been compiled -with UTF-8 support. Both patterns and subject lines must be valid strings of -UTF-8 characters. -

-

--V, --version -Write the version numbers of pcregrep and the PCRE library that is being -used to the standard error stream. -

-

--v, --invert-match -Invert the sense of the match, so that lines which do not match any of -the patterns are the ones that are found. -

-

--w, --word-regex, --word-regexp -Force the patterns to match only whole words. This is equivalent to having \b -at the start and end of the pattern. -

-

--x, --line-regex, --line-regexp -Force the patterns to be anchored (each must start matching at the beginning of -a line) and in addition, require them to match entire lines. This is -equivalent to having ^ and $ characters at the start and end of each -alternative branch in every pattern. -

-
ENVIRONMENT VARIABLES
-

-The environment variables LC_ALL and LC_CTYPE are examined, in that -order, for a locale. The first one that is set is used. This can be overridden -by the --locale option. If no locale is set, the PCRE library's default -(usually the "C" locale) is used. -

-
NEWLINES
-

-The -N (--newline) option allows pcregrep to scan files with -different newline conventions from the default. However, the setting of this -option does not affect the way in which pcregrep writes information to -the standard error and output streams. It uses the string "\n" in C -printf() calls to indicate newlines, relying on the C I/O library to -convert this to an appropriate sequence if the output is sent to a file. -

-
OPTIONS COMPATIBILITY
-

-The majority of short and long forms of pcregrep's options are the same -as in the GNU grep program. Any long option of the form ---xxx-regexp (GNU terminology) is also available as --xxx-regex -(PCRE terminology). However, the --locale, -M, --multiline, --u, and --utf-8 options are specific to pcregrep. -

-
OPTIONS WITH DATA
-

-There are four different ways in which an option with data can be specified. -If a short form option is used, the data may follow immediately, or in the next -command line item. For example: -

-  -f/some/file
-  -f /some/file
-
-If a long form option is used, the data may appear in the same command line -item, separated by an equals character, or (with one exception) it may appear -in the next command line item. For example: -
-  --file=/some/file
-  --file /some/file
-
-Note, however, that if you want to supply a file name beginning with ~ as data -in a shell command, and have the shell expand ~ to a home directory, you must -separate the file name from the option, because the shell does not treat ~ -specially unless it is at the start of an item. -

-

-The exception to the above is the --colour (or --color) option, -for which the data is optional. If this option does have data, it must be given -in the first form, using an equals character. Otherwise it will be assumed that -it has no data. -

-
MATCHING ERRORS
-

-It is possible to supply a regular expression that takes a very long time to -fail to match certain lines. Such patterns normally involve nested indefinite -repeats, for example: (a+)*\d when matched against a line of a's with no final -digit. The PCRE matching function has a resource limit that causes it to abort -in these circumstances. If this happens, pcregrep outputs an error -message and the line that caused the problem to the standard error stream. If -there are more than 20 such errors, pcregrep gives up. -

-
DIAGNOSTICS
-

-Exit status is 0 if any matches were found, 1 if no matches were found, and 2 -for syntax errors and non-existent or inacessible files (even if matches were -found in other files) or too many matching errors. Using the -s option to -suppress error messages about inaccessble files does not affect the return -code. -

-
SEE ALSO
-

-pcrepattern(3), pcretest(1). -

-
AUTHOR
-

-Philip Hazel -
-University Computing Service -
-Cambridge CB2 3QH, England. -
-

-
REVISION
-

-Last updated: 01 March 2009 -
-Copyright © 1997-2009 University of Cambridge. -
-

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcrematching.html b/libs/pcre/doc/html/pcrematching.html deleted file mode 100644 index 2cad88b061..0000000000 --- a/libs/pcre/doc/html/pcrematching.html +++ /dev/null @@ -1,224 +0,0 @@ - - -pcrematching specification - - -

pcrematching man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-

-
PCRE MATCHING ALGORITHMS
-

-This document describes the two different algorithms that are available in PCRE -for matching a compiled regular expression against a given subject string. The -"standard" algorithm is the one provided by the pcre_exec() function. -This works in the same was as Perl's matching function, and provides a -Perl-compatible matching operation. -

-

-An alternative algorithm is provided by the pcre_dfa_exec() function; -this operates in a different way, and is not Perl-compatible. It has advantages -and disadvantages compared with the standard algorithm, and these are described -below. -

-

-When there is only one possible way in which a given subject string can match a -pattern, the two algorithms give the same answer. A difference arises, however, -when there are multiple possibilities. For example, if the pattern -

-  ^<.*>
-
-is matched against the string -
-  <something> <something else> <something further>
-
-there are three possible answers. The standard algorithm finds only one of -them, whereas the alternative algorithm finds all three. -

-
REGULAR EXPRESSIONS AS TREES
-

-The set of strings that are matched by a regular expression can be represented -as a tree structure. An unlimited repetition in the pattern makes the tree of -infinite size, but it is still a tree. Matching the pattern to a given subject -string (from a given starting point) can be thought of as a search of the tree. -There are two ways to search a tree: depth-first and breadth-first, and these -correspond to the two matching algorithms provided by PCRE. -

-
THE STANDARD MATCHING ALGORITHM
-

-In the terminology of Jeffrey Friedl's book "Mastering Regular -Expressions", the standard algorithm is an "NFA algorithm". It conducts a -depth-first search of the pattern tree. That is, it proceeds along a single -path through the tree, checking that the subject matches what is required. When -there is a mismatch, the algorithm tries any alternatives at the current point, -and if they all fail, it backs up to the previous branch point in the tree, and -tries the next alternative branch at that level. This often involves backing up -(moving to the left) in the subject string as well. The order in which -repetition branches are tried is controlled by the greedy or ungreedy nature of -the quantifier. -

-

-If a leaf node is reached, a matching string has been found, and at that point -the algorithm stops. Thus, if there is more than one possible match, this -algorithm returns the first one that it finds. Whether this is the shortest, -the longest, or some intermediate length depends on the way the greedy and -ungreedy repetition quantifiers are specified in the pattern. -

-

-Because it ends up with a single path through the tree, it is relatively -straightforward for this algorithm to keep track of the substrings that are -matched by portions of the pattern in parentheses. This provides support for -capturing parentheses and back references. -

-
THE ALTERNATIVE MATCHING ALGORITHM
-

-This algorithm conducts a breadth-first search of the tree. Starting from the -first matching point in the subject, it scans the subject string from left to -right, once, character by character, and as it does this, it remembers all the -paths through the tree that represent valid matches. In Friedl's terminology, -this is a kind of "DFA algorithm", though it is not implemented as a -traditional finite state machine (it keeps multiple states active -simultaneously). -

-

-The scan continues until either the end of the subject is reached, or there are -no more unterminated paths. At this point, terminated paths represent the -different matching possibilities (if there are none, the match has failed). -Thus, if there is more than one possible match, this algorithm finds all of -them, and in particular, it finds the longest. In PCRE, there is an option to -stop the algorithm after the first match (which is necessarily the shortest) -has been found. -

-

-Note that all the matches that are found start at the same point in the -subject. If the pattern -

-  cat(er(pillar)?)
-
-is matched against the string "the caterpillar catchment", the result will be -the three strings "cat", "cater", and "caterpillar" that start at the fourth -character of the subject. The algorithm does not automatically move on to find -matches that start at later positions. -

-

-There are a number of features of PCRE regular expressions that are not -supported by the alternative matching algorithm. They are as follows: -

-

-1. Because the algorithm finds all possible matches, the greedy or ungreedy -nature of repetition quantifiers is not relevant. Greedy and ungreedy -quantifiers are treated in exactly the same way. However, possessive -quantifiers can make a difference when what follows could also match what is -quantified, for example in a pattern like this: -

-  ^a++\w!
-
-This pattern matches "aaab!" but not "aaa!", which would be matched by a -non-possessive quantifier. Similarly, if an atomic group is present, it is -matched as if it were a standalone pattern at the current point, and the -longest match is then "locked in" for the rest of the overall pattern. -

-

-2. When dealing with multiple paths through the tree simultaneously, it is not -straightforward to keep track of captured substrings for the different matching -possibilities, and PCRE's implementation of this algorithm does not attempt to -do this. This means that no captured substrings are available. -

-

-3. Because no substrings are captured, back references within the pattern are -not supported, and cause errors if encountered. -

-

-4. For the same reason, conditional expressions that use a backreference as the -condition or test for a specific group recursion are not supported. -

-

-5. Because many paths through the tree may be active, the \K escape sequence, -which resets the start of the match when encountered (but may be on some paths -and not on others), is not supported. It causes an error if encountered. -

-

-6. Callouts are supported, but the value of the capture_top field is -always 1, and the value of the capture_last field is always -1. -

-

-7. The \C escape sequence, which (in the standard algorithm) matches a single -byte, even in UTF-8 mode, is not supported because the alternative algorithm -moves through the subject string one character at a time, for all active paths -through the tree. -

-

-8. Except for (*FAIL), the backtracking control verbs such as (*PRUNE) are not -supported. (*FAIL) is supported, and behaves like a failing negative assertion. -

-
ADVANTAGES OF THE ALTERNATIVE ALGORITHM
-

-Using the alternative matching algorithm provides the following advantages: -

-

-1. All possible matches (at a single point in the subject) are automatically -found, and in particular, the longest match is found. To find more than one -match using the standard algorithm, you have to do kludgy things with -callouts. -

-

-2. There is much better support for partial matching. The restrictions on the -content of the pattern that apply when using the standard algorithm for partial -matching do not apply to the alternative algorithm. For non-anchored patterns, -the starting position of a partial match is available. -

-

-3. Because the alternative algorithm scans the subject string just once, and -never needs to backtrack, it is possible to pass very long subject strings to -the matching function in several pieces, checking for partial matching each -time. -

-
DISADVANTAGES OF THE ALTERNATIVE ALGORITHM
-

-The alternative algorithm suffers from a number of disadvantages: -

-

-1. It is substantially slower than the standard algorithm. This is partly -because it has to search for all possible matches, but is also because it is -less susceptible to optimization. -

-

-2. Capturing parentheses and back references are not supported. -

-

-3. Although atomic groups are supported, their use does not provide the -performance advantage that it does for the standard algorithm. -

-
AUTHOR
-

-Philip Hazel -
-University Computing Service -
-Cambridge CB2 3QH, England. -
-

-
REVISION
-

-Last updated: 19 April 2008 -
-Copyright © 1997-2008 University of Cambridge. -
-

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcrepartial.html b/libs/pcre/doc/html/pcrepartial.html deleted file mode 100644 index 1fab23c771..0000000000 --- a/libs/pcre/doc/html/pcrepartial.html +++ /dev/null @@ -1,242 +0,0 @@ - - -pcrepartial specification - - -

pcrepartial man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-

-
PARTIAL MATCHING IN PCRE
-

-In normal use of PCRE, if the subject string that is passed to -pcre_exec() or pcre_dfa_exec() matches as far as it goes, but is -too short to match the entire pattern, PCRE_ERROR_NOMATCH is returned. There -are circumstances where it might be helpful to distinguish this case from other -cases in which there is no match. -

-

-Consider, for example, an application where a human is required to type in data -for a field with specific formatting requirements. An example might be a date -in the form ddmmmyy, defined by this pattern: -

-  ^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$
-
-If the application sees the user's keystrokes one by one, and can check that -what has been typed so far is potentially valid, it is able to raise an error -as soon as a mistake is made, possibly beeping and not reflecting the -character that has been typed. This immediate feedback is likely to be a better -user interface than a check that is delayed until the entire string has been -entered. -

-

-PCRE supports the concept of partial matching by means of the PCRE_PARTIAL -option, which can be set when calling pcre_exec() or -pcre_dfa_exec(). When this flag is set for pcre_exec(), the return -code PCRE_ERROR_NOMATCH is converted into PCRE_ERROR_PARTIAL if at any time -during the matching process the last part of the subject string matched part of -the pattern. Unfortunately, for non-anchored matching, it is not possible to -obtain the position of the start of the partial match. No captured data is set -when PCRE_ERROR_PARTIAL is returned. -

-

-When PCRE_PARTIAL is set for pcre_dfa_exec(), the return code -PCRE_ERROR_NOMATCH is converted into PCRE_ERROR_PARTIAL if the end of the -subject is reached, there have been no complete matches, but there is still at -least one matching possibility. The portion of the string that provided the -partial match is set as the first matching string. -

-

-Using PCRE_PARTIAL disables one of PCRE's optimizations. PCRE remembers the -last literal byte in a pattern, and abandons matching immediately if such a -byte is not present in the subject string. This optimization cannot be used -for a subject string that might match only partially. -

-
RESTRICTED PATTERNS FOR PCRE_PARTIAL
-

-Because of the way certain internal optimizations are implemented in the -pcre_exec() function, the PCRE_PARTIAL option cannot be used with all -patterns. These restrictions do not apply when pcre_dfa_exec() is used. -For pcre_exec(), repeated single characters such as -

-  a{2,4}
-
-and repeated single metasequences such as -
-  \d+
-
-are not permitted if the maximum number of occurrences is greater than one. -Optional items such as \d? (where the maximum is one) are permitted. -Quantifiers with any values are permitted after parentheses, so the invalid -examples above can be coded thus: -
-  (a){2,4}
-  (\d)+
-
-These constructions run more slowly, but for the kinds of application that are -envisaged for this facility, this is not felt to be a major restriction. -

-

-If PCRE_PARTIAL is set for a pattern that does not conform to the restrictions, -pcre_exec() returns the error code PCRE_ERROR_BADPARTIAL (-13). -You can use the PCRE_INFO_OKPARTIAL call to pcre_fullinfo() to find out -if a compiled pattern can be used for partial matching. -

-
EXAMPLE OF PARTIAL MATCHING USING PCRETEST
-

-If the escape sequence \P is present in a pcretest data line, the -PCRE_PARTIAL flag is used for the match. Here is a run of pcretest that -uses the date example quoted above: -

-    re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/
-  data> 25jun04\P
-   0: 25jun04
-   1: jun
-  data> 25dec3\P
-  Partial match
-  data> 3ju\P
-  Partial match
-  data> 3juj\P
-  No match
-  data> j\P
-  No match
-
-The first data string is matched completely, so pcretest shows the -matched substrings. The remaining four strings do not match the complete -pattern, but the first two are partial matches. The same test, using -pcre_dfa_exec() matching (by means of the \D escape sequence), produces -the following output: -
-    re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/
-  data> 25jun04\P\D
-   0: 25jun04
-  data> 23dec3\P\D
-  Partial match: 23dec3
-  data> 3ju\P\D
-  Partial match: 3ju
-  data> 3juj\P\D
-  No match
-  data> j\P\D
-  No match
-
-Notice that in this case the portion of the string that was matched is made -available. -

-
MULTI-SEGMENT MATCHING WITH pcre_dfa_exec()
-

-When a partial match has been found using pcre_dfa_exec(), it is possible -to continue the match by providing additional subject data and calling -pcre_dfa_exec() again with the same compiled regular expression, this -time setting the PCRE_DFA_RESTART option. You must also pass the same working -space as before, because this is where details of the previous partial match -are stored. Here is an example using pcretest, using the \R escape -sequence to set the PCRE_DFA_RESTART option (\P and \D are as above): -

-    re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/
-  data> 23ja\P\D
-  Partial match: 23ja
-  data> n05\R\D
-   0: n05
-
-The first call has "23ja" as the subject, and requests partial matching; the -second call has "n05" as the subject for the continued (restarted) match. -Notice that when the match is complete, only the last part is shown; PCRE does -not retain the previously partially-matched string. It is up to the calling -program to do that if it needs to. -

-

-You can set PCRE_PARTIAL with PCRE_DFA_RESTART to continue partial matching -over multiple segments. This facility can be used to pass very long subject -strings to pcre_dfa_exec(). However, some care is needed for certain -types of pattern. -

-

-1. If the pattern contains tests for the beginning or end of a line, you need -to pass the PCRE_NOTBOL or PCRE_NOTEOL options, as appropriate, when the -subject string for any call does not contain the beginning or end of a line. -

-

-2. If the pattern contains backward assertions (including \b or \B), you need -to arrange for some overlap in the subject strings to allow for this. For -example, you could pass the subject in chunks that are 500 bytes long, but in -a buffer of 700 bytes, with the starting offset set to 200 and the previous 200 -bytes at the start of the buffer. -

-

-3. Matching a subject string that is split into multiple segments does not -always produce exactly the same result as matching over one single long string. -The difference arises when there are multiple matching possibilities, because a -partial match result is given only when there are no completed matches in a -call to pcre_dfa_exec(). This means that as soon as the shortest match has -been found, continuation to a new subject segment is no longer possible. -Consider this pcretest example: -

-    re> /dog(sbody)?/
-  data> do\P\D
-  Partial match: do
-  data> gsb\R\P\D
-   0: g
-  data> dogsbody\D
-   0: dogsbody
-   1: dog
-
-The pattern matches the words "dog" or "dogsbody". When the subject is -presented in several parts ("do" and "gsb" being the first two) the match stops -when "dog" has been found, and it is not possible to continue. On the other -hand, if "dogsbody" is presented as a single string, both matches are found. -

-

-Because of this phenomenon, it does not usually make sense to end a pattern -that is going to be matched in this way with a variable repeat. -

-

-4. Patterns that contain alternatives at the top level which do not all -start with the same pattern item may not work as expected. For example, -consider this pattern: -

-  1234|3789
-
-If the first part of the subject is "ABC123", a partial match of the first -alternative is found at offset 3. There is no partial match for the second -alternative, because such a match does not start at the same point in the -subject string. Attempting to continue with the string "789" does not yield a -match because only those alternatives that match at one point in the subject -are remembered. The problem arises because the start of the second alternative -matches within the first alternative. There is no problem with anchored -patterns or patterns such as: -
-  1234|ABCD
-
-where no string can be a partial match for both alternatives. -

-
AUTHOR
-

-Philip Hazel -
-University Computing Service -
-Cambridge CB2 3QH, England. -
-

-
REVISION
-

-Last updated: 04 June 2007 -
-Copyright © 1997-2007 University of Cambridge. -
-

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcrepattern.html b/libs/pcre/doc/html/pcrepattern.html deleted file mode 100644 index 5881bc3811..0000000000 --- a/libs/pcre/doc/html/pcrepattern.html +++ /dev/null @@ -1,2262 +0,0 @@ - - -pcrepattern specification - - -

pcrepattern man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-

-
PCRE REGULAR EXPRESSION DETAILS
-

-The syntax and semantics of the regular expressions that are supported by PCRE -are described in detail below. There is a quick-reference syntax summary in the -pcresyntax -page. PCRE tries to match Perl syntax and semantics as closely as it can. PCRE -also supports some alternative regular expression syntax (which does not -conflict with the Perl syntax) in order to provide some compatibility with -regular expressions in Python, .NET, and Oniguruma. -

-

-Perl's regular expressions are described in its own documentation, and -regular expressions in general are covered in a number of books, some of which -have copious examples. Jeffrey Friedl's "Mastering Regular Expressions", -published by O'Reilly, covers regular expressions in great detail. This -description of PCRE's regular expressions is intended as reference material. -

-

-The original operation of PCRE was on strings of one-byte characters. However, -there is now also support for UTF-8 character strings. To use this, you must -build PCRE to include UTF-8 support, and then call pcre_compile() with -the PCRE_UTF8 option. There is also a special sequence that can be given at the -start of a pattern: -

-  (*UTF8)
-
-Starting a pattern with this sequence is equivalent to setting the PCRE_UTF8 -option. This feature is not Perl-compatible. How setting UTF-8 mode affects -pattern matching is mentioned in several places below. There is also a summary -of UTF-8 features in the -section on UTF-8 support -in the main -pcre -page. -

-

-The remainder of this document discusses the patterns that are supported by -PCRE when its main matching function, pcre_exec(), is used. -From release 6.0, PCRE offers a second matching function, -pcre_dfa_exec(), which matches using a different algorithm that is not -Perl-compatible. Some of the features discussed below are not available when -pcre_dfa_exec() is used. The advantages and disadvantages of the -alternative function, and how it differs from the normal function, are -discussed in the -pcrematching -page. -

-
NEWLINE CONVENTIONS
-

-PCRE supports five different conventions for indicating line breaks in -strings: a single CR (carriage return) character, a single LF (linefeed) -character, the two-character sequence CRLF, any of the three preceding, or any -Unicode newline sequence. The -pcreapi -page has -further discussion -about newlines, and shows how to set the newline convention in the -options arguments for the compiling and matching functions. -

-

-It is also possible to specify a newline convention by starting a pattern -string with one of the following five sequences: -

-  (*CR)        carriage return
-  (*LF)        linefeed
-  (*CRLF)      carriage return, followed by linefeed
-  (*ANYCRLF)   any of the three above
-  (*ANY)       all Unicode newline sequences
-
-These override the default and the options given to pcre_compile(). For -example, on a Unix system where LF is the default newline sequence, the pattern -
-  (*CR)a.b
-
-changes the convention to CR. That pattern matches "a\nb" because LF is no -longer a newline. Note that these special settings, which are not -Perl-compatible, are recognized only at the very start of a pattern, and that -they must be in upper case. If more than one of them is present, the last one -is used. -

-

-The newline convention does not affect what the \R escape sequence matches. By -default, this is any Unicode newline sequence, for Perl compatibility. However, -this can be changed; see the description of \R in the section entitled -"Newline sequences" -below. A change of \R setting can be combined with a change of newline -convention. -

-
CHARACTERS AND METACHARACTERS
-

-A regular expression is a pattern that is matched against a subject string from -left to right. Most characters stand for themselves in a pattern, and match the -corresponding characters in the subject. As a trivial example, the pattern -

-  The quick brown fox
-
-matches a portion of a subject string that is identical to itself. When -caseless matching is specified (the PCRE_CASELESS option), letters are matched -independently of case. In UTF-8 mode, PCRE always understands the concept of -case for characters whose values are less than 128, so caseless matching is -always possible. For characters with higher values, the concept of case is -supported if PCRE is compiled with Unicode property support, but not otherwise. -If you want to use caseless matching for characters 128 and above, you must -ensure that PCRE is compiled with Unicode property support as well as with -UTF-8 support. -

-

-The power of regular expressions comes from the ability to include alternatives -and repetitions in the pattern. These are encoded in the pattern by the use of -metacharacters, which do not stand for themselves but instead are -interpreted in some special way. -

-

-There are two different sets of metacharacters: those that are recognized -anywhere in the pattern except within square brackets, and those that are -recognized within square brackets. Outside square brackets, the metacharacters -are as follows: -

-  \      general escape character with several uses
-  ^      assert start of string (or line, in multiline mode)
-  $      assert end of string (or line, in multiline mode)
-  .      match any character except newline (by default)
-  [      start character class definition
-  |      start of alternative branch
-  (      start subpattern
-  )      end subpattern
-  ?      extends the meaning of (
-         also 0 or 1 quantifier
-         also quantifier minimizer
-  *      0 or more quantifier
-  +      1 or more quantifier
-         also "possessive quantifier"
-  {      start min/max quantifier
-
-Part of a pattern that is in square brackets is called a "character class". In -a character class the only metacharacters are: -
-  \      general escape character
-  ^      negate the class, but only if the first character
-  -      indicates character range
-  [      POSIX character class (only if followed by POSIX syntax)
-  ]      terminates the character class
-
-The following sections describe the use of each of the metacharacters. -

-
BACKSLASH
-

-The backslash character has several uses. Firstly, if it is followed by a -non-alphanumeric character, it takes away any special meaning that character -may have. This use of backslash as an escape character applies both inside and -outside character classes. -

-

-For example, if you want to match a * character, you write \* in the pattern. -This escaping action applies whether or not the following character would -otherwise be interpreted as a metacharacter, so it is always safe to precede a -non-alphanumeric with backslash to specify that it stands for itself. In -particular, if you want to match a backslash, you write \\. -

-

-If a pattern is compiled with the PCRE_EXTENDED option, whitespace in the -pattern (other than in a character class) and characters between a # outside -a character class and the next newline are ignored. An escaping backslash can -be used to include a whitespace or # character as part of the pattern. -

-

-If you want to remove the special meaning from a sequence of characters, you -can do so by putting them between \Q and \E. This is different from Perl in -that $ and @ are handled as literals in \Q...\E sequences in PCRE, whereas in -Perl, $ and @ cause variable interpolation. Note the following examples: -

-  Pattern            PCRE matches   Perl matches
-
-  \Qabc$xyz\E        abc$xyz        abc followed by the contents of $xyz
-  \Qabc\$xyz\E       abc\$xyz       abc\$xyz
-  \Qabc\E\$\Qxyz\E   abc$xyz        abc$xyz
-
-The \Q...\E sequence is recognized both inside and outside character classes. -

-
-Non-printing characters -
-

-A second use of backslash provides a way of encoding non-printing characters -in patterns in a visible manner. There is no restriction on the appearance of -non-printing characters, apart from the binary zero that terminates a pattern, -but when a pattern is being prepared by text editing, it is usually easier to -use one of the following escape sequences than the binary character it -represents: -

-  \a        alarm, that is, the BEL character (hex 07)
-  \cx       "control-x", where x is any character
-  \e        escape (hex 1B)
-  \f        formfeed (hex 0C)
-  \n        linefeed (hex 0A)
-  \r        carriage return (hex 0D)
-  \t        tab (hex 09)
-  \ddd      character with octal code ddd, or backreference
-  \xhh      character with hex code hh
-  \x{hhh..} character with hex code hhh..
-
-The precise effect of \cx is as follows: if x is a lower case letter, it -is converted to upper case. Then bit 6 of the character (hex 40) is inverted. -Thus \cz becomes hex 1A, but \c{ becomes hex 3B, while \c; becomes hex -7B. -

-

-After \x, from zero to two hexadecimal digits are read (letters can be in -upper or lower case). Any number of hexadecimal digits may appear between \x{ -and }, but the value of the character code must be less than 256 in non-UTF-8 -mode, and less than 2**31 in UTF-8 mode. That is, the maximum value in -hexadecimal is 7FFFFFFF. Note that this is bigger than the largest Unicode code -point, which is 10FFFF. -

-

-If characters other than hexadecimal digits appear between \x{ and }, or if -there is no terminating }, this form of escape is not recognized. Instead, the -initial \x will be interpreted as a basic hexadecimal escape, with no -following digits, giving a character whose value is zero. -

-

-Characters whose value is less than 256 can be defined by either of the two -syntaxes for \x. There is no difference in the way they are handled. For -example, \xdc is exactly the same as \x{dc}. -

-

-After \0 up to two further octal digits are read. If there are fewer than two -digits, just those that are present are used. Thus the sequence \0\x\07 -specifies two binary zeros followed by a BEL character (code value 7). Make -sure you supply two digits after the initial zero if the pattern character that -follows is itself an octal digit. -

-

-The handling of a backslash followed by a digit other than 0 is complicated. -Outside a character class, PCRE reads it and any following digits as a decimal -number. If the number is less than 10, or if there have been at least that many -previous capturing left parentheses in the expression, the entire sequence is -taken as a back reference. A description of how this works is given -later, -following the discussion of -parenthesized subpatterns. -

-

-Inside a character class, or if the decimal number is greater than 9 and there -have not been that many capturing subpatterns, PCRE re-reads up to three octal -digits following the backslash, and uses them to generate a data character. Any -subsequent digits stand for themselves. In non-UTF-8 mode, the value of a -character specified in octal must be less than \400. In UTF-8 mode, values up -to \777 are permitted. For example: -

-  \040   is another way of writing a space
-  \40    is the same, provided there are fewer than 40 previous capturing subpatterns
-  \7     is always a back reference
-  \11    might be a back reference, or another way of writing a tab
-  \011   is always a tab
-  \0113  is a tab followed by the character "3"
-  \113   might be a back reference, otherwise the character with octal code 113
-  \377   might be a back reference, otherwise the byte consisting entirely of 1 bits
-  \81    is either a back reference, or a binary zero followed by the two characters "8" and "1"
-
-Note that octal values of 100 or greater must not be introduced by a leading -zero, because no more than three octal digits are ever read. -

-

-All the sequences that define a single character value can be used both inside -and outside character classes. In addition, inside a character class, the -sequence \b is interpreted as the backspace character (hex 08), and the -sequences \R and \X are interpreted as the characters "R" and "X", -respectively. Outside a character class, these sequences have different -meanings -(see below). -

-
-Absolute and relative back references -
-

-The sequence \g followed by an unsigned or a negative number, optionally -enclosed in braces, is an absolute or relative back reference. A named back -reference can be coded as \g{name}. Back references are discussed -later, -following the discussion of -parenthesized subpatterns. -

-
-Absolute and relative subroutine calls -
-

-For compatibility with Oniguruma, the non-Perl syntax \g followed by a name or -a number enclosed either in angle brackets or single quotes, is an alternative -syntax for referencing a subpattern as a "subroutine". Details are discussed -later. -Note that \g{...} (Perl syntax) and \g<...> (Oniguruma syntax) are not -synonymous. The former is a back reference; the latter is a subroutine call. -

-
-Generic character types -
-

-Another use of backslash is for specifying generic character types. The -following are always recognized: -

-  \d     any decimal digit
-  \D     any character that is not a decimal digit
-  \h     any horizontal whitespace character
-  \H     any character that is not a horizontal whitespace character
-  \s     any whitespace character
-  \S     any character that is not a whitespace character
-  \v     any vertical whitespace character
-  \V     any character that is not a vertical whitespace character
-  \w     any "word" character
-  \W     any "non-word" character
-
-Each pair of escape sequences partitions the complete set of characters into -two disjoint sets. Any given character matches one, and only one, of each pair. -

-

-These character type sequences can appear both inside and outside character -classes. They each match one character of the appropriate type. If the current -matching point is at the end of the subject string, all of them fail, since -there is no character to match. -

-

-For compatibility with Perl, \s does not match the VT character (code 11). -This makes it different from the the POSIX "space" class. The \s characters -are HT (9), LF (10), FF (12), CR (13), and space (32). If "use locale;" is -included in a Perl script, \s may match the VT character. In PCRE, it never -does. -

-

-In UTF-8 mode, characters with values greater than 128 never match \d, \s, or -\w, and always match \D, \S, and \W. This is true even when Unicode -character property support is available. These sequences retain their original -meanings from before UTF-8 support was available, mainly for efficiency -reasons. Note that this also affects \b, because it is defined in terms of \w -and \W. -

-

-The sequences \h, \H, \v, and \V are Perl 5.10 features. In contrast to the -other sequences, these do match certain high-valued codepoints in UTF-8 mode. -The horizontal space characters are: -

-  U+0009     Horizontal tab
-  U+0020     Space
-  U+00A0     Non-break space
-  U+1680     Ogham space mark
-  U+180E     Mongolian vowel separator
-  U+2000     En quad
-  U+2001     Em quad
-  U+2002     En space
-  U+2003     Em space
-  U+2004     Three-per-em space
-  U+2005     Four-per-em space
-  U+2006     Six-per-em space
-  U+2007     Figure space
-  U+2008     Punctuation space
-  U+2009     Thin space
-  U+200A     Hair space
-  U+202F     Narrow no-break space
-  U+205F     Medium mathematical space
-  U+3000     Ideographic space
-
-The vertical space characters are: -
-  U+000A     Linefeed
-  U+000B     Vertical tab
-  U+000C     Formfeed
-  U+000D     Carriage return
-  U+0085     Next line
-  U+2028     Line separator
-  U+2029     Paragraph separator
-
-

-

-A "word" character is an underscore or any character less than 256 that is a -letter or digit. The definition of letters and digits is controlled by PCRE's -low-valued character tables, and may vary if locale-specific matching is taking -place (see -"Locale support" -in the -pcreapi -page). For example, in a French locale such as "fr_FR" in Unix-like systems, -or "french" in Windows, some character codes greater than 128 are used for -accented letters, and these are matched by \w. The use of locales with Unicode -is discouraged. -

-
-Newline sequences -
-

-Outside a character class, by default, the escape sequence \R matches any -Unicode newline sequence. This is a Perl 5.10 feature. In non-UTF-8 mode \R is -equivalent to the following: -

-  (?>\r\n|\n|\x0b|\f|\r|\x85)
-
-This is an example of an "atomic group", details of which are given -below. -This particular group matches either the two-character sequence CR followed by -LF, or one of the single characters LF (linefeed, U+000A), VT (vertical tab, -U+000B), FF (formfeed, U+000C), CR (carriage return, U+000D), or NEL (next -line, U+0085). The two-character sequence is treated as a single unit that -cannot be split. -

-

-In UTF-8 mode, two additional characters whose codepoints are greater than 255 -are added: LS (line separator, U+2028) and PS (paragraph separator, U+2029). -Unicode character property support is not needed for these characters to be -recognized. -

-

-It is possible to restrict \R to match only CR, LF, or CRLF (instead of the -complete set of Unicode line endings) by setting the option PCRE_BSR_ANYCRLF -either at compile time or when the pattern is matched. (BSR is an abbrevation -for "backslash R".) This can be made the default when PCRE is built; if this is -the case, the other behaviour can be requested via the PCRE_BSR_UNICODE option. -It is also possible to specify these settings by starting a pattern string with -one of the following sequences: -

-  (*BSR_ANYCRLF)   CR, LF, or CRLF only
-  (*BSR_UNICODE)   any Unicode newline sequence
-
-These override the default and the options given to pcre_compile(), but -they can be overridden by options given to pcre_exec(). Note that these -special settings, which are not Perl-compatible, are recognized only at the -very start of a pattern, and that they must be in upper case. If more than one -of them is present, the last one is used. They can be combined with a change of -newline convention, for example, a pattern can start with: -
-  (*ANY)(*BSR_ANYCRLF)
-
-Inside a character class, \R matches the letter "R". -

-
-Unicode character properties -
-

-When PCRE is built with Unicode character property support, three additional -escape sequences that match characters with specific properties are available. -When not in UTF-8 mode, these sequences are of course limited to testing -characters whose codepoints are less than 256, but they do work in this mode. -The extra escape sequences are: -

-  \p{xx}   a character with the xx property
-  \P{xx}   a character without the xx property
-  \X       an extended Unicode sequence
-
-The property names represented by xx above are limited to the Unicode -script names, the general category properties, and "Any", which matches any -character (including newline). Other properties such as "InMusicalSymbols" are -not currently supported by PCRE. Note that \P{Any} does not match any -characters, so always causes a match failure. -

-

-Sets of Unicode characters are defined as belonging to certain scripts. A -character from one of these sets can be matched using a script name. For -example: -

-  \p{Greek}
-  \P{Han}
-
-Those that are not part of an identified script are lumped together as -"Common". The current list of scripts is: -

-

-Arabic, -Armenian, -Balinese, -Bengali, -Bopomofo, -Braille, -Buginese, -Buhid, -Canadian_Aboriginal, -Cherokee, -Common, -Coptic, -Cuneiform, -Cypriot, -Cyrillic, -Deseret, -Devanagari, -Ethiopic, -Georgian, -Glagolitic, -Gothic, -Greek, -Gujarati, -Gurmukhi, -Han, -Hangul, -Hanunoo, -Hebrew, -Hiragana, -Inherited, -Kannada, -Katakana, -Kharoshthi, -Khmer, -Lao, -Latin, -Limbu, -Linear_B, -Malayalam, -Mongolian, -Myanmar, -New_Tai_Lue, -Nko, -Ogham, -Old_Italic, -Old_Persian, -Oriya, -Osmanya, -Phags_Pa, -Phoenician, -Runic, -Shavian, -Sinhala, -Syloti_Nagri, -Syriac, -Tagalog, -Tagbanwa, -Tai_Le, -Tamil, -Telugu, -Thaana, -Thai, -Tibetan, -Tifinagh, -Ugaritic, -Yi. -

-

-Each character has exactly one general category property, specified by a -two-letter abbreviation. For compatibility with Perl, negation can be specified -by including a circumflex between the opening brace and the property name. For -example, \p{^Lu} is the same as \P{Lu}. -

-

-If only one letter is specified with \p or \P, it includes all the general -category properties that start with that letter. In this case, in the absence -of negation, the curly brackets in the escape sequence are optional; these two -examples have the same effect: -

-  \p{L}
-  \pL
-
-The following general category property codes are supported: -
-  C     Other
-  Cc    Control
-  Cf    Format
-  Cn    Unassigned
-  Co    Private use
-  Cs    Surrogate
-
-  L     Letter
-  Ll    Lower case letter
-  Lm    Modifier letter
-  Lo    Other letter
-  Lt    Title case letter
-  Lu    Upper case letter
-
-  M     Mark
-  Mc    Spacing mark
-  Me    Enclosing mark
-  Mn    Non-spacing mark
-
-  N     Number
-  Nd    Decimal number
-  Nl    Letter number
-  No    Other number
-
-  P     Punctuation
-  Pc    Connector punctuation
-  Pd    Dash punctuation
-  Pe    Close punctuation
-  Pf    Final punctuation
-  Pi    Initial punctuation
-  Po    Other punctuation
-  Ps    Open punctuation
-
-  S     Symbol
-  Sc    Currency symbol
-  Sk    Modifier symbol
-  Sm    Mathematical symbol
-  So    Other symbol
-
-  Z     Separator
-  Zl    Line separator
-  Zp    Paragraph separator
-  Zs    Space separator
-
-The special property L& is also supported: it matches a character that has -the Lu, Ll, or Lt property, in other words, a letter that is not classified as -a modifier or "other". -

-

-The Cs (Surrogate) property applies only to characters in the range U+D800 to -U+DFFF. Such characters are not valid in UTF-8 strings (see RFC 3629) and so -cannot be tested by PCRE, unless UTF-8 validity checking has been turned off -(see the discussion of PCRE_NO_UTF8_CHECK in the -pcreapi -page). -

-

-The long synonyms for these properties that Perl supports (such as \p{Letter}) -are not supported by PCRE, nor is it permitted to prefix any of these -properties with "Is". -

-

-No character that is in the Unicode table has the Cn (unassigned) property. -Instead, this property is assumed for any code point that is not in the -Unicode table. -

-

-Specifying caseless matching does not affect these escape sequences. For -example, \p{Lu} always matches only upper case letters. -

-

-The \X escape matches any number of Unicode characters that form an extended -Unicode sequence. \X is equivalent to -

-  (?>\PM\pM*)
-
-That is, it matches a character without the "mark" property, followed by zero -or more characters with the "mark" property, and treats the sequence as an -atomic group -(see below). -Characters with the "mark" property are typically accents that affect the -preceding character. None of them have codepoints less than 256, so in -non-UTF-8 mode \X matches any one character. -

-

-Matching characters by Unicode property is not fast, because PCRE has to search -a structure that contains data for over fifteen thousand characters. That is -why the traditional escape sequences such as \d and \w do not use Unicode -properties in PCRE. -

-
-Resetting the match start -
-

-The escape sequence \K, which is a Perl 5.10 feature, causes any previously -matched characters not to be included in the final matched sequence. For -example, the pattern: -

-  foo\Kbar
-
-matches "foobar", but reports that it has matched "bar". This feature is -similar to a lookbehind assertion -(described below). -However, in this case, the part of the subject before the real match does not -have to be of fixed length, as lookbehind assertions do. The use of \K does -not interfere with the setting of -captured substrings. -For example, when the pattern -
-  (foo)\Kbar
-
-matches "foobar", the first substring is still set to "foo". -

-
-Simple assertions -
-

-The final use of backslash is for certain simple assertions. An assertion -specifies a condition that has to be met at a particular point in a match, -without consuming any characters from the subject string. The use of -subpatterns for more complicated assertions is described -below. -The backslashed assertions are: -

-  \b     matches at a word boundary
-  \B     matches when not at a word boundary
-  \A     matches at the start of the subject
-  \Z     matches at the end of the subject
-          also matches before a newline at the end of the subject
-  \z     matches only at the end of the subject
-  \G     matches at the first matching position in the subject
-
-These assertions may not appear in character classes (but note that \b has a -different meaning, namely the backspace character, inside a character class). -

-

-A word boundary is a position in the subject string where the current character -and the previous character do not both match \w or \W (i.e. one matches -\w and the other matches \W), or the start or end of the string if the -first or last character matches \w, respectively. -

-

-The \A, \Z, and \z assertions differ from the traditional circumflex and -dollar (described in the next section) in that they only ever match at the very -start and end of the subject string, whatever options are set. Thus, they are -independent of multiline mode. These three assertions are not affected by the -PCRE_NOTBOL or PCRE_NOTEOL options, which affect only the behaviour of the -circumflex and dollar metacharacters. However, if the startoffset -argument of pcre_exec() is non-zero, indicating that matching is to start -at a point other than the beginning of the subject, \A can never match. The -difference between \Z and \z is that \Z matches before a newline at the end -of the string as well as at the very end, whereas \z matches only at the end. -

-

-The \G assertion is true only when the current matching position is at the -start point of the match, as specified by the startoffset argument of -pcre_exec(). It differs from \A when the value of startoffset is -non-zero. By calling pcre_exec() multiple times with appropriate -arguments, you can mimic Perl's /g option, and it is in this kind of -implementation where \G can be useful. -

-

-Note, however, that PCRE's interpretation of \G, as the start of the current -match, is subtly different from Perl's, which defines it as the end of the -previous match. In Perl, these can be different when the previously matched -string was empty. Because PCRE does just one match at a time, it cannot -reproduce this behaviour. -

-

-If all the alternatives of a pattern begin with \G, the expression is anchored -to the starting match position, and the "anchored" flag is set in the compiled -regular expression. -

-
CIRCUMFLEX AND DOLLAR
-

-Outside a character class, in the default matching mode, the circumflex -character is an assertion that is true only if the current matching point is -at the start of the subject string. If the startoffset argument of -pcre_exec() is non-zero, circumflex can never match if the PCRE_MULTILINE -option is unset. Inside a character class, circumflex has an entirely different -meaning -(see below). -

-

-Circumflex need not be the first character of the pattern if a number of -alternatives are involved, but it should be the first thing in each alternative -in which it appears if the pattern is ever to match that branch. If all -possible alternatives start with a circumflex, that is, if the pattern is -constrained to match only at the start of the subject, it is said to be an -"anchored" pattern. (There are also other constructs that can cause a pattern -to be anchored.) -

-

-A dollar character is an assertion that is true only if the current matching -point is at the end of the subject string, or immediately before a newline -at the end of the string (by default). Dollar need not be the last character of -the pattern if a number of alternatives are involved, but it should be the last -item in any branch in which it appears. Dollar has no special meaning in a -character class. -

-

-The meaning of dollar can be changed so that it matches only at the very end of -the string, by setting the PCRE_DOLLAR_ENDONLY option at compile time. This -does not affect the \Z assertion. -

-

-The meanings of the circumflex and dollar characters are changed if the -PCRE_MULTILINE option is set. When this is the case, a circumflex matches -immediately after internal newlines as well as at the start of the subject -string. It does not match after a newline that ends the string. A dollar -matches before any newlines in the string, as well as at the very end, when -PCRE_MULTILINE is set. When newline is specified as the two-character -sequence CRLF, isolated CR and LF characters do not indicate newlines. -

-

-For example, the pattern /^abc$/ matches the subject string "def\nabc" (where -\n represents a newline) in multiline mode, but not otherwise. Consequently, -patterns that are anchored in single line mode because all branches start with -^ are not anchored in multiline mode, and a match for circumflex is possible -when the startoffset argument of pcre_exec() is non-zero. The -PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is set. -

-

-Note that the sequences \A, \Z, and \z can be used to match the start and -end of the subject in both modes, and if all branches of a pattern start with -\A it is always anchored, whether or not PCRE_MULTILINE is set. -

-
FULL STOP (PERIOD, DOT)
-

-Outside a character class, a dot in the pattern matches any one character in -the subject string except (by default) a character that signifies the end of a -line. In UTF-8 mode, the matched character may be more than one byte long. -

-

-When a line ending is defined as a single character, dot never matches that -character; when the two-character sequence CRLF is used, dot does not match CR -if it is immediately followed by LF, but otherwise it matches all characters -(including isolated CRs and LFs). When any Unicode line endings are being -recognized, dot does not match CR or LF or any of the other line ending -characters. -

-

-The behaviour of dot with regard to newlines can be changed. If the PCRE_DOTALL -option is set, a dot matches any one character, without exception. If the -two-character sequence CRLF is present in the subject string, it takes two dots -to match it. -

-

-The handling of dot is entirely independent of the handling of circumflex and -dollar, the only relationship being that they both involve newlines. Dot has no -special meaning in a character class. -

-
MATCHING A SINGLE BYTE
-

-Outside a character class, the escape sequence \C matches any one byte, both -in and out of UTF-8 mode. Unlike a dot, it always matches any line-ending -characters. The feature is provided in Perl in order to match individual bytes -in UTF-8 mode. Because it breaks up UTF-8 characters into individual bytes, -what remains in the string may be a malformed UTF-8 string. For this reason, -the \C escape sequence is best avoided. -

-

-PCRE does not allow \C to appear in lookbehind assertions -(described below), -because in UTF-8 mode this would make it impossible to calculate the length of -the lookbehind. -

-
SQUARE BRACKETS AND CHARACTER CLASSES
-

-An opening square bracket introduces a character class, terminated by a closing -square bracket. A closing square bracket on its own is not special. If a -closing square bracket is required as a member of the class, it should be the -first data character in the class (after an initial circumflex, if present) or -escaped with a backslash. -

-

-A character class matches a single character in the subject. In UTF-8 mode, the -character may occupy more than one byte. A matched character must be in the set -of characters defined by the class, unless the first character in the class -definition is a circumflex, in which case the subject character must not be in -the set defined by the class. If a circumflex is actually required as a member -of the class, ensure it is not the first character, or escape it with a -backslash. -

-

-For example, the character class [aeiou] matches any lower case vowel, while -[^aeiou] matches any character that is not a lower case vowel. Note that a -circumflex is just a convenient notation for specifying the characters that -are in the class by enumerating those that are not. A class that starts with a -circumflex is not an assertion: it still consumes a character from the subject -string, and therefore it fails if the current pointer is at the end of the -string. -

-

-In UTF-8 mode, characters with values greater than 255 can be included in a -class as a literal string of bytes, or by using the \x{ escaping mechanism. -

-

-When caseless matching is set, any letters in a class represent both their -upper case and lower case versions, so for example, a caseless [aeiou] matches -"A" as well as "a", and a caseless [^aeiou] does not match "A", whereas a -caseful version would. In UTF-8 mode, PCRE always understands the concept of -case for characters whose values are less than 128, so caseless matching is -always possible. For characters with higher values, the concept of case is -supported if PCRE is compiled with Unicode property support, but not otherwise. -If you want to use caseless matching for characters 128 and above, you must -ensure that PCRE is compiled with Unicode property support as well as with -UTF-8 support. -

-

-Characters that might indicate line breaks are never treated in any special way -when matching character classes, whatever line-ending sequence is in use, and -whatever setting of the PCRE_DOTALL and PCRE_MULTILINE options is used. A class -such as [^a] always matches one of these characters. -

-

-The minus (hyphen) character can be used to specify a range of characters in a -character class. For example, [d-m] matches any letter between d and m, -inclusive. If a minus character is required in a class, it must be escaped with -a backslash or appear in a position where it cannot be interpreted as -indicating a range, typically as the first or last character in the class. -

-

-It is not possible to have the literal character "]" as the end character of a -range. A pattern such as [W-]46] is interpreted as a class of two characters -("W" and "-") followed by a literal string "46]", so it would match "W46]" or -"-46]". However, if the "]" is escaped with a backslash it is interpreted as -the end of range, so [W-\]46] is interpreted as a class containing a range -followed by two other characters. The octal or hexadecimal representation of -"]" can also be used to end a range. -

-

-Ranges operate in the collating sequence of character values. They can also be -used for characters specified numerically, for example [\000-\037]. In UTF-8 -mode, ranges can include characters whose values are greater than 255, for -example [\x{100}-\x{2ff}]. -

-

-If a range that includes letters is used when caseless matching is set, it -matches the letters in either case. For example, [W-c] is equivalent to -[][\\^_`wxyzabc], matched caselessly, and in non-UTF-8 mode, if character -tables for a French locale are in use, [\xc8-\xcb] matches accented E -characters in both cases. In UTF-8 mode, PCRE supports the concept of case for -characters with values greater than 128 only when it is compiled with Unicode -property support. -

-

-The character types \d, \D, \p, \P, \s, \S, \w, and \W may also appear -in a character class, and add the characters that they match to the class. For -example, [\dABCDEF] matches any hexadecimal digit. A circumflex can -conveniently be used with the upper case character types to specify a more -restricted set of characters than the matching lower case type. For example, -the class [^\W_] matches any letter or digit, but not underscore. -

-

-The only metacharacters that are recognized in character classes are backslash, -hyphen (only where it can be interpreted as specifying a range), circumflex -(only at the start), opening square bracket (only when it can be interpreted as -introducing a POSIX class name - see the next section), and the terminating -closing square bracket. However, escaping other non-alphanumeric characters -does no harm. -

-
POSIX CHARACTER CLASSES
-

-Perl supports the POSIX notation for character classes. This uses names -enclosed by [: and :] within the enclosing square brackets. PCRE also supports -this notation. For example, -

-  [01[:alpha:]%]
-
-matches "0", "1", any alphabetic character, or "%". The supported class names -are -
-  alnum    letters and digits
-  alpha    letters
-  ascii    character codes 0 - 127
-  blank    space or tab only
-  cntrl    control characters
-  digit    decimal digits (same as \d)
-  graph    printing characters, excluding space
-  lower    lower case letters
-  print    printing characters, including space
-  punct    printing characters, excluding letters and digits
-  space    white space (not quite the same as \s)
-  upper    upper case letters
-  word     "word" characters (same as \w)
-  xdigit   hexadecimal digits
-
-The "space" characters are HT (9), LF (10), VT (11), FF (12), CR (13), and -space (32). Notice that this list includes the VT character (code 11). This -makes "space" different to \s, which does not include VT (for Perl -compatibility). -

-

-The name "word" is a Perl extension, and "blank" is a GNU extension from Perl -5.8. Another Perl extension is negation, which is indicated by a ^ character -after the colon. For example, -

-  [12[:^digit:]]
-
-matches "1", "2", or any non-digit. PCRE (and Perl) also recognize the POSIX -syntax [.ch.] and [=ch=] where "ch" is a "collating element", but these are not -supported, and an error is given if they are encountered. -

-

-In UTF-8 mode, characters with values greater than 128 do not match any of -the POSIX character classes. -

-
VERTICAL BAR
-

-Vertical bar characters are used to separate alternative patterns. For example, -the pattern -

-  gilbert|sullivan
-
-matches either "gilbert" or "sullivan". Any number of alternatives may appear, -and an empty alternative is permitted (matching the empty string). The matching -process tries each alternative in turn, from left to right, and the first one -that succeeds is used. If the alternatives are within a subpattern -(defined below), -"succeeds" means matching the rest of the main pattern as well as the -alternative in the subpattern. -

-
INTERNAL OPTION SETTING
-

-The settings of the PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, and -PCRE_EXTENDED options (which are Perl-compatible) can be changed from within -the pattern by a sequence of Perl option letters enclosed between "(?" and ")". -The option letters are -

-  i  for PCRE_CASELESS
-  m  for PCRE_MULTILINE
-  s  for PCRE_DOTALL
-  x  for PCRE_EXTENDED
-
-For example, (?im) sets caseless, multiline matching. It is also possible to -unset these options by preceding the letter with a hyphen, and a combined -setting and unsetting such as (?im-sx), which sets PCRE_CASELESS and -PCRE_MULTILINE while unsetting PCRE_DOTALL and PCRE_EXTENDED, is also -permitted. If a letter appears both before and after the hyphen, the option is -unset. -

-

-The PCRE-specific options PCRE_DUPNAMES, PCRE_UNGREEDY, and PCRE_EXTRA can be -changed in the same way as the Perl-compatible options by using the characters -J, U and X respectively. -

-

-When one of these option changes occurs at top level (that is, not inside -subpattern parentheses), the change applies to the remainder of the pattern -that follows. If the change is placed right at the start of a pattern, PCRE -extracts it into the global options (and it will therefore show up in data -extracted by the pcre_fullinfo() function). -

-

-An option change within a subpattern (see below for a description of -subpatterns) affects only that part of the current pattern that follows it, so -

-  (a(?i)b)c
-
-matches abc and aBc and no other strings (assuming PCRE_CASELESS is not used). -By this means, options can be made to have different settings in different -parts of the pattern. Any changes made in one alternative do carry on -into subsequent branches within the same subpattern. For example, -
-  (a(?i)b|c)
-
-matches "ab", "aB", "c", and "C", even though when matching "C" the first -branch is abandoned before the option setting. This is because the effects of -option settings happen at compile time. There would be some very weird -behaviour otherwise. -

-

-Note: There are other PCRE-specific options that can be set by the -application when the compile or match functions are called. In some cases the -pattern can contain special leading sequences such as (*CRLF) to override what -the application has set or what has been defaulted. Details are given in the -section entitled -"Newline sequences" -above. There is also the (*UTF8) leading sequence that can be used to set UTF-8 -mode; this is equivalent to setting the PCRE_UTF8 option. -

-
SUBPATTERNS
-

-Subpatterns are delimited by parentheses (round brackets), which can be nested. -Turning part of a pattern into a subpattern does two things: -
-
-1. It localizes a set of alternatives. For example, the pattern -

-  cat(aract|erpillar|)
-
-matches one of the words "cat", "cataract", or "caterpillar". Without the -parentheses, it would match "cataract", "erpillar" or an empty string. -
-
-2. It sets up the subpattern as a capturing subpattern. This means that, when -the whole pattern matches, that portion of the subject string that matched the -subpattern is passed back to the caller via the ovector argument of -pcre_exec(). Opening parentheses are counted from left to right (starting -from 1) to obtain numbers for the capturing subpatterns. -

-

-For example, if the string "the red king" is matched against the pattern -

-  the ((red|white) (king|queen))
-
-the captured substrings are "red king", "red", and "king", and are numbered 1, -2, and 3, respectively. -

-

-The fact that plain parentheses fulfil two functions is not always helpful. -There are often times when a grouping subpattern is required without a -capturing requirement. If an opening parenthesis is followed by a question mark -and a colon, the subpattern does not do any capturing, and is not counted when -computing the number of any subsequent capturing subpatterns. For example, if -the string "the white queen" is matched against the pattern -

-  the ((?:red|white) (king|queen))
-
-the captured substrings are "white queen" and "queen", and are numbered 1 and -2. The maximum number of capturing subpatterns is 65535. -

-

-As a convenient shorthand, if any option settings are required at the start of -a non-capturing subpattern, the option letters may appear between the "?" and -the ":". Thus the two patterns -

-  (?i:saturday|sunday)
-  (?:(?i)saturday|sunday)
-
-match exactly the same set of strings. Because alternative branches are tried -from left to right, and options are not reset until the end of the subpattern -is reached, an option setting in one branch does affect subsequent branches, so -the above patterns match "SUNDAY" as well as "Saturday". -

-
DUPLICATE SUBPATTERN NUMBERS
-

-Perl 5.10 introduced a feature whereby each alternative in a subpattern uses -the same numbers for its capturing parentheses. Such a subpattern starts with -(?| and is itself a non-capturing subpattern. For example, consider this -pattern: -

-  (?|(Sat)ur|(Sun))day
-
-Because the two alternatives are inside a (?| group, both sets of capturing -parentheses are numbered one. Thus, when the pattern matches, you can look -at captured substring number one, whichever alternative matched. This construct -is useful when you want to capture part, but not all, of one of a number of -alternatives. Inside a (?| group, parentheses are numbered as usual, but the -number is reset at the start of each branch. The numbers of any capturing -buffers that follow the subpattern start after the highest number used in any -branch. The following example is taken from the Perl documentation. -The numbers underneath show in which buffer the captured content will be -stored. -
-  # before  ---------------branch-reset----------- after
-  / ( a )  (?| x ( y ) z | (p (q) r) | (t) u (v) ) ( z ) /x
-  # 1            2         2  3        2     3     4
-
-A backreference or a recursive call to a numbered subpattern always refers to -the first one in the pattern with the given number. -

-

-An alternative approach to using this "branch reset" feature is to use -duplicate named subpatterns, as described in the next section. -

-
NAMED SUBPATTERNS
-

-Identifying capturing parentheses by number is simple, but it can be very hard -to keep track of the numbers in complicated regular expressions. Furthermore, -if an expression is modified, the numbers may change. To help with this -difficulty, PCRE supports the naming of subpatterns. This feature was not -added to Perl until release 5.10. Python had the feature earlier, and PCRE -introduced it at release 4.0, using the Python syntax. PCRE now supports both -the Perl and the Python syntax. -

-

-In PCRE, a subpattern can be named in one of three ways: (?<name>...) or -(?'name'...) as in Perl, or (?P<name>...) as in Python. References to capturing -parentheses from other parts of the pattern, such as -backreferences, -recursion, -and -conditions, -can be made by name as well as by number. -

-

-Names consist of up to 32 alphanumeric characters and underscores. Named -capturing parentheses are still allocated numbers as well as names, exactly as -if the names were not present. The PCRE API provides function calls for -extracting the name-to-number translation table from a compiled pattern. There -is also a convenience function for extracting a captured substring by name. -

-

-By default, a name must be unique within a pattern, but it is possible to relax -this constraint by setting the PCRE_DUPNAMES option at compile time. This can -be useful for patterns where only one instance of the named parentheses can -match. Suppose you want to match the name of a weekday, either as a 3-letter -abbreviation or as the full name, and in both cases you want to extract the -abbreviation. This pattern (ignoring the line breaks) does the job: -

-  (?<DN>Mon|Fri|Sun)(?:day)?|
-  (?<DN>Tue)(?:sday)?|
-  (?<DN>Wed)(?:nesday)?|
-  (?<DN>Thu)(?:rsday)?|
-  (?<DN>Sat)(?:urday)?
-
-There are five capturing substrings, but only one is ever set after a match. -(An alternative way of solving this problem is to use a "branch reset" -subpattern, as described in the previous section.) -

-

-The convenience function for extracting the data by name returns the substring -for the first (and in this example, the only) subpattern of that name that -matched. This saves searching to find which numbered subpattern it was. If you -make a reference to a non-unique named subpattern from elsewhere in the -pattern, the one that corresponds to the lowest number is used. For further -details of the interfaces for handling named subpatterns, see the -pcreapi -documentation. -

-

-Warning: You cannot use different names to distinguish between two -subpatterns with the same number (see the previous section) because PCRE uses -only the numbers when matching. -

-
REPETITION
-

-Repetition is specified by quantifiers, which can follow any of the following -items: -

-  a literal data character
-  the dot metacharacter
-  the \C escape sequence
-  the \X escape sequence (in UTF-8 mode with Unicode properties)
-  the \R escape sequence
-  an escape such as \d that matches a single character
-  a character class
-  a back reference (see next section)
-  a parenthesized subpattern (unless it is an assertion)
-
-The general repetition quantifier specifies a minimum and maximum number of -permitted matches, by giving the two numbers in curly brackets (braces), -separated by a comma. The numbers must be less than 65536, and the first must -be less than or equal to the second. For example: -
-  z{2,4}
-
-matches "zz", "zzz", or "zzzz". A closing brace on its own is not a special -character. If the second number is omitted, but the comma is present, there is -no upper limit; if the second number and the comma are both omitted, the -quantifier specifies an exact number of required matches. Thus -
-  [aeiou]{3,}
-
-matches at least 3 successive vowels, but may match many more, while -
-  \d{8}
-
-matches exactly 8 digits. An opening curly bracket that appears in a position -where a quantifier is not allowed, or one that does not match the syntax of a -quantifier, is taken as a literal character. For example, {,6} is not a -quantifier, but a literal string of four characters. -

-

-In UTF-8 mode, quantifiers apply to UTF-8 characters rather than to individual -bytes. Thus, for example, \x{100}{2} matches two UTF-8 characters, each of -which is represented by a two-byte sequence. Similarly, when Unicode property -support is available, \X{3} matches three Unicode extended sequences, each of -which may be several bytes long (and they may be of different lengths). -

-

-The quantifier {0} is permitted, causing the expression to behave as if the -previous item and the quantifier were not present. This may be useful for -subpatterns that are referenced as -subroutines -from elsewhere in the pattern. Items other than subpatterns that have a {0} -quantifier are omitted from the compiled pattern. -

-

-For convenience, the three most common quantifiers have single-character -abbreviations: -

-  *    is equivalent to {0,}
-  +    is equivalent to {1,}
-  ?    is equivalent to {0,1}
-
-It is possible to construct infinite loops by following a subpattern that can -match no characters with a quantifier that has no upper limit, for example: -
-  (a?)*
-
-Earlier versions of Perl and PCRE used to give an error at compile time for -such patterns. However, because there are cases where this can be useful, such -patterns are now accepted, but if any repetition of the subpattern does in fact -match no characters, the loop is forcibly broken. -

-

-By default, the quantifiers are "greedy", that is, they match as much as -possible (up to the maximum number of permitted times), without causing the -rest of the pattern to fail. The classic example of where this gives problems -is in trying to match comments in C programs. These appear between /* and */ -and within the comment, individual * and / characters may appear. An attempt to -match C comments by applying the pattern -

-  /\*.*\*/
-
-to the string -
-  /* first comment */  not comment  /* second comment */
-
-fails, because it matches the entire string owing to the greediness of the .* -item. -

-

-However, if a quantifier is followed by a question mark, it ceases to be -greedy, and instead matches the minimum number of times possible, so the -pattern -

-  /\*.*?\*/
-
-does the right thing with the C comments. The meaning of the various -quantifiers is not otherwise changed, just the preferred number of matches. -Do not confuse this use of question mark with its use as a quantifier in its -own right. Because it has two uses, it can sometimes appear doubled, as in -
-  \d??\d
-
-which matches one digit by preference, but can match two if that is the only -way the rest of the pattern matches. -

-

-If the PCRE_UNGREEDY option is set (an option that is not available in Perl), -the quantifiers are not greedy by default, but individual ones can be made -greedy by following them with a question mark. In other words, it inverts the -default behaviour. -

-

-When a parenthesized subpattern is quantified with a minimum repeat count that -is greater than 1 or with a limited maximum, more memory is required for the -compiled pattern, in proportion to the size of the minimum or maximum. -

-

-If a pattern starts with .* or .{0,} and the PCRE_DOTALL option (equivalent -to Perl's /s) is set, thus allowing the dot to match newlines, the pattern is -implicitly anchored, because whatever follows will be tried against every -character position in the subject string, so there is no point in retrying the -overall match at any position after the first. PCRE normally treats such a -pattern as though it were preceded by \A. -

-

-In cases where it is known that the subject string contains no newlines, it is -worth setting PCRE_DOTALL in order to obtain this optimization, or -alternatively using ^ to indicate anchoring explicitly. -

-

-However, there is one situation where the optimization cannot be used. When .* -is inside capturing parentheses that are the subject of a backreference -elsewhere in the pattern, a match at the start may fail where a later one -succeeds. Consider, for example: -

-  (.*)abc\1
-
-If the subject is "xyz123abc123" the match point is the fourth character. For -this reason, such a pattern is not implicitly anchored. -

-

-When a capturing subpattern is repeated, the value captured is the substring -that matched the final iteration. For example, after -

-  (tweedle[dume]{3}\s*)+
-
-has matched "tweedledum tweedledee" the value of the captured substring is -"tweedledee". However, if there are nested capturing subpatterns, the -corresponding captured values may have been set in previous iterations. For -example, after -
-  /(a|(b))+/
-
-matches "aba" the value of the second captured substring is "b". -

-
ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS
-

-With both maximizing ("greedy") and minimizing ("ungreedy" or "lazy") -repetition, failure of what follows normally causes the repeated item to be -re-evaluated to see if a different number of repeats allows the rest of the -pattern to match. Sometimes it is useful to prevent this, either to change the -nature of the match, or to cause it fail earlier than it otherwise might, when -the author of the pattern knows there is no point in carrying on. -

-

-Consider, for example, the pattern \d+foo when applied to the subject line -

-  123456bar
-
-After matching all 6 digits and then failing to match "foo", the normal -action of the matcher is to try again with only 5 digits matching the \d+ -item, and then with 4, and so on, before ultimately failing. "Atomic grouping" -(a term taken from Jeffrey Friedl's book) provides the means for specifying -that once a subpattern has matched, it is not to be re-evaluated in this way. -

-

-If we use atomic grouping for the previous example, the matcher gives up -immediately on failing to match "foo" the first time. The notation is a kind of -special parenthesis, starting with (?> as in this example: -

-  (?>\d+)foo
-
-This kind of parenthesis "locks up" the part of the pattern it contains once -it has matched, and a failure further into the pattern is prevented from -backtracking into it. Backtracking past it to previous items, however, works as -normal. -

-

-An alternative description is that a subpattern of this type matches the string -of characters that an identical standalone pattern would match, if anchored at -the current point in the subject string. -

-

-Atomic grouping subpatterns are not capturing subpatterns. Simple cases such as -the above example can be thought of as a maximizing repeat that must swallow -everything it can. So, while both \d+ and \d+? are prepared to adjust the -number of digits they match in order to make the rest of the pattern match, -(?>\d+) can only match an entire sequence of digits. -

-

-Atomic groups in general can of course contain arbitrarily complicated -subpatterns, and can be nested. However, when the subpattern for an atomic -group is just a single repeated item, as in the example above, a simpler -notation, called a "possessive quantifier" can be used. This consists of an -additional + character following a quantifier. Using this notation, the -previous example can be rewritten as -

-  \d++foo
-
-Note that a possessive quantifier can be used with an entire group, for -example: -
-  (abc|xyz){2,3}+
-
-Possessive quantifiers are always greedy; the setting of the PCRE_UNGREEDY -option is ignored. They are a convenient notation for the simpler forms of -atomic group. However, there is no difference in the meaning of a possessive -quantifier and the equivalent atomic group, though there may be a performance -difference; possessive quantifiers should be slightly faster. -

-

-The possessive quantifier syntax is an extension to the Perl 5.8 syntax. -Jeffrey Friedl originated the idea (and the name) in the first edition of his -book. Mike McCloskey liked it, so implemented it when he built Sun's Java -package, and PCRE copied it from there. It ultimately found its way into Perl -at release 5.10. -

-

-PCRE has an optimization that automatically "possessifies" certain simple -pattern constructs. For example, the sequence A+B is treated as A++B because -there is no point in backtracking into a sequence of A's when B must follow. -

-

-When a pattern contains an unlimited repeat inside a subpattern that can itself -be repeated an unlimited number of times, the use of an atomic group is the -only way to avoid some failing matches taking a very long time indeed. The -pattern -

-  (\D+|<\d+>)*[!?]
-
-matches an unlimited number of substrings that either consist of non-digits, or -digits enclosed in <>, followed by either ! or ?. When it matches, it runs -quickly. However, if it is applied to -
-  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-
-it takes a long time before reporting failure. This is because the string can -be divided between the internal \D+ repeat and the external * repeat in a -large number of ways, and all have to be tried. (The example uses [!?] rather -than a single character at the end, because both PCRE and Perl have an -optimization that allows for fast failure when a single character is used. They -remember the last single character that is required for a match, and fail early -if it is not present in the string.) If the pattern is changed so that it uses -an atomic group, like this: -
-  ((?>\D+)|<\d+>)*[!?]
-
-sequences of non-digits cannot be broken, and failure happens quickly. -

-
BACK REFERENCES
-

-Outside a character class, a backslash followed by a digit greater than 0 (and -possibly further digits) is a back reference to a capturing subpattern earlier -(that is, to its left) in the pattern, provided there have been that many -previous capturing left parentheses. -

-

-However, if the decimal number following the backslash is less than 10, it is -always taken as a back reference, and causes an error only if there are not -that many capturing left parentheses in the entire pattern. In other words, the -parentheses that are referenced need not be to the left of the reference for -numbers less than 10. A "forward back reference" of this type can make sense -when a repetition is involved and the subpattern to the right has participated -in an earlier iteration. -

-

-It is not possible to have a numerical "forward back reference" to a subpattern -whose number is 10 or more using this syntax because a sequence such as \50 is -interpreted as a character defined in octal. See the subsection entitled -"Non-printing characters" -above -for further details of the handling of digits following a backslash. There is -no such problem when named parentheses are used. A back reference to any -subpattern is possible using named parentheses (see below). -

-

-Another way of avoiding the ambiguity inherent in the use of digits following a -backslash is to use the \g escape sequence, which is a feature introduced in -Perl 5.10. This escape must be followed by an unsigned number or a negative -number, optionally enclosed in braces. These examples are all identical: -

-  (ring), \1
-  (ring), \g1
-  (ring), \g{1}
-
-An unsigned number specifies an absolute reference without the ambiguity that -is present in the older syntax. It is also useful when literal digits follow -the reference. A negative number is a relative reference. Consider this -example: -
-  (abc(def)ghi)\g{-1}
-
-The sequence \g{-1} is a reference to the most recently started capturing -subpattern before \g, that is, is it equivalent to \2. Similarly, \g{-2} -would be equivalent to \1. The use of relative references can be helpful in -long patterns, and also in patterns that are created by joining together -fragments that contain references within themselves. -

-

-A back reference matches whatever actually matched the capturing subpattern in -the current subject string, rather than anything matching the subpattern -itself (see -"Subpatterns as subroutines" -below for a way of doing that). So the pattern -

-  (sens|respons)e and \1ibility
-
-matches "sense and sensibility" and "response and responsibility", but not -"sense and responsibility". If caseful matching is in force at the time of the -back reference, the case of letters is relevant. For example, -
-  ((?i)rah)\s+\1
-
-matches "rah rah" and "RAH RAH", but not "RAH rah", even though the original -capturing subpattern is matched caselessly. -

-

-There are several different ways of writing back references to named -subpatterns. The .NET syntax \k{name} and the Perl syntax \k<name> or -\k'name' are supported, as is the Python syntax (?P=name). Perl 5.10's unified -back reference syntax, in which \g can be used for both numeric and named -references, is also supported. We could rewrite the above example in any of -the following ways: -

-  (?<p1>(?i)rah)\s+\k<p1>
-  (?'p1'(?i)rah)\s+\k{p1}
-  (?P<p1>(?i)rah)\s+(?P=p1)
-  (?<p1>(?i)rah)\s+\g{p1}
-
-A subpattern that is referenced by name may appear in the pattern before or -after the reference. -

-

-There may be more than one back reference to the same subpattern. If a -subpattern has not actually been used in a particular match, any back -references to it always fail. For example, the pattern -

-  (a|(bc))\2
-
-always fails if it starts to match "a" rather than "bc". Because there may be -many capturing parentheses in a pattern, all digits following the backslash are -taken as part of a potential back reference number. If the pattern continues -with a digit character, some delimiter must be used to terminate the back -reference. If the PCRE_EXTENDED option is set, this can be whitespace. -Otherwise an empty comment (see -"Comments" -below) can be used. -

-

-A back reference that occurs inside the parentheses to which it refers fails -when the subpattern is first used, so, for example, (a\1) never matches. -However, such references can be useful inside repeated subpatterns. For -example, the pattern -

-  (a|b\1)+
-
-matches any number of "a"s and also "aba", "ababbaa" etc. At each iteration of -the subpattern, the back reference matches the character string corresponding -to the previous iteration. In order for this to work, the pattern must be such -that the first iteration does not need to match the back reference. This can be -done using alternation, as in the example above, or by a quantifier with a -minimum of zero. -

-
ASSERTIONS
-

-An assertion is a test on the characters following or preceding the current -matching point that does not actually consume any characters. The simple -assertions coded as \b, \B, \A, \G, \Z, \z, ^ and $ are described -above. -

-

-More complicated assertions are coded as subpatterns. There are two kinds: -those that look ahead of the current position in the subject string, and those -that look behind it. An assertion subpattern is matched in the normal way, -except that it does not cause the current matching position to be changed. -

-

-Assertion subpatterns are not capturing subpatterns, and may not be repeated, -because it makes no sense to assert the same thing several times. If any kind -of assertion contains capturing subpatterns within it, these are counted for -the purposes of numbering the capturing subpatterns in the whole pattern. -However, substring capturing is carried out only for positive assertions, -because it does not make sense for negative assertions. -

-
-Lookahead assertions -
-

-Lookahead assertions start with (?= for positive assertions and (?! for -negative assertions. For example, -

-  \w+(?=;)
-
-matches a word followed by a semicolon, but does not include the semicolon in -the match, and -
-  foo(?!bar)
-
-matches any occurrence of "foo" that is not followed by "bar". Note that the -apparently similar pattern -
-  (?!foo)bar
-
-does not find an occurrence of "bar" that is preceded by something other than -"foo"; it finds any occurrence of "bar" whatsoever, because the assertion -(?!foo) is always true when the next three characters are "bar". A -lookbehind assertion is needed to achieve the other effect. -

-

-If you want to force a matching failure at some point in a pattern, the most -convenient way to do it is with (?!) because an empty string always matches, so -an assertion that requires there not to be an empty string must always fail. -

-
-Lookbehind assertions -
-

-Lookbehind assertions start with (?<= for positive assertions and (?<! for -negative assertions. For example, -

-  (?<!foo)bar
-
-does find an occurrence of "bar" that is not preceded by "foo". The contents of -a lookbehind assertion are restricted such that all the strings it matches must -have a fixed length. However, if there are several top-level alternatives, they -do not all have to have the same fixed length. Thus -
-  (?<=bullock|donkey)
-
-is permitted, but -
-  (?<!dogs?|cats?)
-
-causes an error at compile time. Branches that match different length strings -are permitted only at the top level of a lookbehind assertion. This is an -extension compared with Perl (at least for 5.8), which requires all branches to -match the same length of string. An assertion such as -
-  (?<=ab(c|de))
-
-is not permitted, because its single top-level branch can match two different -lengths, but it is acceptable if rewritten to use two top-level branches: -
-  (?<=abc|abde)
-
-In some cases, the Perl 5.10 escape sequence \K -(see above) -can be used instead of a lookbehind assertion; this is not restricted to a -fixed-length. -

-

-The implementation of lookbehind assertions is, for each alternative, to -temporarily move the current position back by the fixed length and then try to -match. If there are insufficient characters before the current position, the -assertion fails. -

-

-PCRE does not allow the \C escape (which matches a single byte in UTF-8 mode) -to appear in lookbehind assertions, because it makes it impossible to calculate -the length of the lookbehind. The \X and \R escapes, which can match -different numbers of bytes, are also not permitted. -

-

-Possessive quantifiers can be used in conjunction with lookbehind assertions to -specify efficient matching at the end of the subject string. Consider a simple -pattern such as -

-  abcd$
-
-when applied to a long string that does not match. Because matching proceeds -from left to right, PCRE will look for each "a" in the subject and then see if -what follows matches the rest of the pattern. If the pattern is specified as -
-  ^.*abcd$
-
-the initial .* matches the entire string at first, but when this fails (because -there is no following "a"), it backtracks to match all but the last character, -then all but the last two characters, and so on. Once again the search for "a" -covers the entire string, from right to left, so we are no better off. However, -if the pattern is written as -
-  ^.*+(?<=abcd)
-
-there can be no backtracking for the .*+ item; it can match only the entire -string. The subsequent lookbehind assertion does a single test on the last four -characters. If it fails, the match fails immediately. For long strings, this -approach makes a significant difference to the processing time. -

-
-Using multiple assertions -
-

-Several assertions (of any sort) may occur in succession. For example, -

-  (?<=\d{3})(?<!999)foo
-
-matches "foo" preceded by three digits that are not "999". Notice that each of -the assertions is applied independently at the same point in the subject -string. First there is a check that the previous three characters are all -digits, and then there is a check that the same three characters are not "999". -This pattern does not match "foo" preceded by six characters, the first -of which are digits and the last three of which are not "999". For example, it -doesn't match "123abcfoo". A pattern to do that is -
-  (?<=\d{3}...)(?<!999)foo
-
-This time the first assertion looks at the preceding six characters, checking -that the first three are digits, and then the second assertion checks that the -preceding three characters are not "999". -

-

-Assertions can be nested in any combination. For example, -

-  (?<=(?<!foo)bar)baz
-
-matches an occurrence of "baz" that is preceded by "bar" which in turn is not -preceded by "foo", while -
-  (?<=\d{3}(?!999)...)foo
-
-is another pattern that matches "foo" preceded by three digits and any three -characters that are not "999". -

-
CONDITIONAL SUBPATTERNS
-

-It is possible to cause the matching process to obey a subpattern -conditionally or to choose between two alternative subpatterns, depending on -the result of an assertion, or whether a previous capturing subpattern matched -or not. The two possible forms of conditional subpattern are -

-  (?(condition)yes-pattern)
-  (?(condition)yes-pattern|no-pattern)
-
-If the condition is satisfied, the yes-pattern is used; otherwise the -no-pattern (if present) is used. If there are more than two alternatives in the -subpattern, a compile-time error occurs. -

-

-There are four kinds of condition: references to subpatterns, references to -recursion, a pseudo-condition called DEFINE, and assertions. -

-
-Checking for a used subpattern by number -
-

-If the text between the parentheses consists of a sequence of digits, the -condition is true if the capturing subpattern of that number has previously -matched. An alternative notation is to precede the digits with a plus or minus -sign. In this case, the subpattern number is relative rather than absolute. -The most recently opened parentheses can be referenced by (?(-1), the next most -recent by (?(-2), and so on. In looping constructs it can also make sense to -refer to subsequent groups with constructs such as (?(+2). -

-

-Consider the following pattern, which contains non-significant white space to -make it more readable (assume the PCRE_EXTENDED option) and to divide it into -three parts for ease of discussion: -

-  ( \( )?    [^()]+    (?(1) \) )
-
-The first part matches an optional opening parenthesis, and if that -character is present, sets it as the first captured substring. The second part -matches one or more characters that are not parentheses. The third part is a -conditional subpattern that tests whether the first set of parentheses matched -or not. If they did, that is, if subject started with an opening parenthesis, -the condition is true, and so the yes-pattern is executed and a closing -parenthesis is required. Otherwise, since no-pattern is not present, the -subpattern matches nothing. In other words, this pattern matches a sequence of -non-parentheses, optionally enclosed in parentheses. -

-

-If you were embedding this pattern in a larger one, you could use a relative -reference: -

-  ...other stuff... ( \( )?    [^()]+    (?(-1) \) ) ...
-
-This makes the fragment independent of the parentheses in the larger pattern. -

-
-Checking for a used subpattern by name -
-

-Perl uses the syntax (?(<name>)...) or (?('name')...) to test for a used -subpattern by name. For compatibility with earlier versions of PCRE, which had -this facility before Perl, the syntax (?(name)...) is also recognized. However, -there is a possible ambiguity with this syntax, because subpattern names may -consist entirely of digits. PCRE looks first for a named subpattern; if it -cannot find one and the name consists entirely of digits, PCRE looks for a -subpattern of that number, which must be greater than zero. Using subpattern -names that consist entirely of digits is not recommended. -

-

-Rewriting the above example to use a named subpattern gives this: -

-  (?<OPEN> \( )?    [^()]+    (?(<OPEN>) \) )
-
-
-

-
-Checking for pattern recursion -
-

-If the condition is the string (R), and there is no subpattern with the name R, -the condition is true if a recursive call to the whole pattern or any -subpattern has been made. If digits or a name preceded by ampersand follow the -letter R, for example: -

-  (?(R3)...) or (?(R&name)...)
-
-the condition is true if the most recent recursion is into the subpattern whose -number or name is given. This condition does not check the entire recursion -stack. -

-

-At "top level", all these recursion test conditions are false. Recursive -patterns are described below. -

-
-Defining subpatterns for use by reference only -
-

-If the condition is the string (DEFINE), and there is no subpattern with the -name DEFINE, the condition is always false. In this case, there may be only one -alternative in the subpattern. It is always skipped if control reaches this -point in the pattern; the idea of DEFINE is that it can be used to define -"subroutines" that can be referenced from elsewhere. (The use of "subroutines" -is described below.) For example, a pattern to match an IPv4 address could be -written like this (ignore whitespace and line breaks): -

-  (?(DEFINE) (?<byte> 2[0-4]\d | 25[0-5] | 1\d\d | [1-9]?\d) )
-  \b (?&byte) (\.(?&byte)){3} \b
-
-The first part of the pattern is a DEFINE group inside which a another group -named "byte" is defined. This matches an individual component of an IPv4 -address (a number less than 256). When matching takes place, this part of the -pattern is skipped because DEFINE acts like a false condition. -

-

-The rest of the pattern uses references to the named group to match the four -dot-separated components of an IPv4 address, insisting on a word boundary at -each end. -

-
-Assertion conditions -
-

-If the condition is not in any of the above formats, it must be an assertion. -This may be a positive or negative lookahead or lookbehind assertion. Consider -this pattern, again containing non-significant white space, and with the two -alternatives on the second line: -

-  (?(?=[^a-z]*[a-z])
-  \d{2}-[a-z]{3}-\d{2}  |  \d{2}-\d{2}-\d{2} )
-
-The condition is a positive lookahead assertion that matches an optional -sequence of non-letters followed by a letter. In other words, it tests for the -presence of at least one letter in the subject. If a letter is found, the -subject is matched against the first alternative; otherwise it is matched -against the second. This pattern matches strings in one of the two forms -dd-aaa-dd or dd-dd-dd, where aaa are letters and dd are digits. -

-
COMMENTS
-

-The sequence (?# marks the start of a comment that continues up to the next -closing parenthesis. Nested parentheses are not permitted. The characters -that make up a comment play no part in the pattern matching at all. -

-

-If the PCRE_EXTENDED option is set, an unescaped # character outside a -character class introduces a comment that continues to immediately after the -next newline in the pattern. -

-
RECURSIVE PATTERNS
-

-Consider the problem of matching a string in parentheses, allowing for -unlimited nested parentheses. Without the use of recursion, the best that can -be done is to use a pattern that matches up to some fixed depth of nesting. It -is not possible to handle an arbitrary nesting depth. -

-

-For some time, Perl has provided a facility that allows regular expressions to -recurse (amongst other things). It does this by interpolating Perl code in the -expression at run time, and the code can refer to the expression itself. A Perl -pattern using code interpolation to solve the parentheses problem can be -created like this: -

-  $re = qr{\( (?: (?>[^()]+) | (?p{$re}) )* \)}x;
-
-The (?p{...}) item interpolates Perl code at run time, and in this case refers -recursively to the pattern in which it appears. -

-

-Obviously, PCRE cannot support the interpolation of Perl code. Instead, it -supports special syntax for recursion of the entire pattern, and also for -individual subpattern recursion. After its introduction in PCRE and Python, -this kind of recursion was introduced into Perl at release 5.10. -

-

-A special item that consists of (? followed by a number greater than zero and a -closing parenthesis is a recursive call of the subpattern of the given number, -provided that it occurs inside that subpattern. (If not, it is a "subroutine" -call, which is described in the next section.) The special item (?R) or (?0) is -a recursive call of the entire regular expression. -

-

-In PCRE (like Python, but unlike Perl), a recursive subpattern call is always -treated as an atomic group. That is, once it has matched some of the subject -string, it is never re-entered, even if it contains untried alternatives and -there is a subsequent matching failure. -

-

-This PCRE pattern solves the nested parentheses problem (assume the -PCRE_EXTENDED option is set so that white space is ignored): -

-  \( ( (?>[^()]+) | (?R) )* \)
-
-First it matches an opening parenthesis. Then it matches any number of -substrings which can either be a sequence of non-parentheses, or a recursive -match of the pattern itself (that is, a correctly parenthesized substring). -Finally there is a closing parenthesis. -

-

-If this were part of a larger pattern, you would not want to recurse the entire -pattern, so instead you could use this: -

-  ( \( ( (?>[^()]+) | (?1) )* \) )
-
-We have put the pattern into parentheses, and caused the recursion to refer to -them instead of the whole pattern. -

-

-In a larger pattern, keeping track of parenthesis numbers can be tricky. This -is made easier by the use of relative references. (A Perl 5.10 feature.) -Instead of (?1) in the pattern above you can write (?-2) to refer to the second -most recently opened parentheses preceding the recursion. In other words, a -negative number counts capturing parentheses leftwards from the point at which -it is encountered. -

-

-It is also possible to refer to subsequently opened parentheses, by writing -references such as (?+2). However, these cannot be recursive because the -reference is not inside the parentheses that are referenced. They are always -"subroutine" calls, as described in the next section. -

-

-An alternative approach is to use named parentheses instead. The Perl syntax -for this is (?&name); PCRE's earlier syntax (?P>name) is also supported. We -could rewrite the above example as follows: -

-  (?<pn> \( ( (?>[^()]+) | (?&pn) )* \) )
-
-If there is more than one subpattern with the same name, the earliest one is -used. -

-

-This particular example pattern that we have been looking at contains nested -unlimited repeats, and so the use of atomic grouping for matching strings of -non-parentheses is important when applying the pattern to strings that do not -match. For example, when this pattern is applied to -

-  (aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa()
-
-it yields "no match" quickly. However, if atomic grouping is not used, -the match runs for a very long time indeed because there are so many different -ways the + and * repeats can carve up the subject, and all have to be tested -before failure can be reported. -

-

-At the end of a match, the values set for any capturing subpatterns are those -from the outermost level of the recursion at which the subpattern value is set. -If you want to obtain intermediate values, a callout function can be used (see -below and the -pcrecallout -documentation). If the pattern above is matched against -

-  (ab(cd)ef)
-
-the value for the capturing parentheses is "ef", which is the last value taken -on at the top level. If additional parentheses are added, giving -
-  \( ( ( (?>[^()]+) | (?R) )* ) \)
-     ^                        ^
-     ^                        ^
-
-the string they capture is "ab(cd)ef", the contents of the top level -parentheses. If there are more than 15 capturing parentheses in a pattern, PCRE -has to obtain extra memory to store data during a recursion, which it does by -using pcre_malloc, freeing it via pcre_free afterwards. If no -memory can be obtained, the match fails with the PCRE_ERROR_NOMEMORY error. -

-

-Do not confuse the (?R) item with the condition (R), which tests for recursion. -Consider this pattern, which matches text in angle brackets, allowing for -arbitrary nesting. Only digits are allowed in nested brackets (that is, when -recursing), whereas any characters are permitted at the outer level. -

-  < (?: (?(R) \d++  | [^<>]*+) | (?R)) * >
-
-In this pattern, (?(R) is the start of a conditional subpattern, with two -different alternatives for the recursive and non-recursive cases. The (?R) item -is the actual recursive call. -

-
SUBPATTERNS AS SUBROUTINES
-

-If the syntax for a recursive subpattern reference (either by number or by -name) is used outside the parentheses to which it refers, it operates like a -subroutine in a programming language. The "called" subpattern may be defined -before or after the reference. A numbered reference can be absolute or -relative, as in these examples: -

-  (...(absolute)...)...(?2)...
-  (...(relative)...)...(?-1)...
-  (...(?+1)...(relative)...
-
-An earlier example pointed out that the pattern -
-  (sens|respons)e and \1ibility
-
-matches "sense and sensibility" and "response and responsibility", but not -"sense and responsibility". If instead the pattern -
-  (sens|respons)e and (?1)ibility
-
-is used, it does match "sense and responsibility" as well as the other two -strings. Another example is given in the discussion of DEFINE above. -

-

-Like recursive subpatterns, a "subroutine" call is always treated as an atomic -group. That is, once it has matched some of the subject string, it is never -re-entered, even if it contains untried alternatives and there is a subsequent -matching failure. -

-

-When a subpattern is used as a subroutine, processing options such as -case-independence are fixed when the subpattern is defined. They cannot be -changed for different calls. For example, consider this pattern: -

-  (abc)(?i:(?-1))
-
-It matches "abcabc". It does not match "abcABC" because the change of -processing option does not affect the called subpattern. -

-
ONIGURUMA SUBROUTINE SYNTAX
-

-For compatibility with Oniguruma, the non-Perl syntax \g followed by a name or -a number enclosed either in angle brackets or single quotes, is an alternative -syntax for referencing a subpattern as a subroutine, possibly recursively. Here -are two of the examples used above, rewritten using this syntax: -

-  (?<pn> \( ( (?>[^()]+) | \g<pn> )* \) )
-  (sens|respons)e and \g'1'ibility
-
-PCRE supports an extension to Oniguruma: if a number is preceded by a -plus or a minus sign it is taken as a relative reference. For example: -
-  (abc)(?i:\g<-1>)
-
-Note that \g{...} (Perl syntax) and \g<...> (Oniguruma syntax) are not -synonymous. The former is a back reference; the latter is a subroutine call. -

-
CALLOUTS
-

-Perl has a feature whereby using the sequence (?{...}) causes arbitrary Perl -code to be obeyed in the middle of matching a regular expression. This makes it -possible, amongst other things, to extract different substrings that match the -same pair of parentheses when there is a repetition. -

-

-PCRE provides a similar feature, but of course it cannot obey arbitrary Perl -code. The feature is called "callout". The caller of PCRE provides an external -function by putting its entry point in the global variable pcre_callout. -By default, this variable contains NULL, which disables all calling out. -

-

-Within a regular expression, (?C) indicates the points at which the external -function is to be called. If you want to identify different callout points, you -can put a number less than 256 after the letter C. The default value is zero. -For example, this pattern has two callout points: -

-  (?C1)abc(?C2)def
-
-If the PCRE_AUTO_CALLOUT flag is passed to pcre_compile(), callouts are -automatically installed before each item in the pattern. They are all numbered -255. -

-

-During matching, when PCRE reaches a callout point (and pcre_callout is -set), the external function is called. It is provided with the number of the -callout, the position in the pattern, and, optionally, one item of data -originally supplied by the caller of pcre_exec(). The callout function -may cause matching to proceed, to backtrack, or to fail altogether. A complete -description of the interface to the callout function is given in the -pcrecallout -documentation. -

-
BACKTRACKING CONTROL
-

-Perl 5.10 introduced a number of "Special Backtracking Control Verbs", which -are described in the Perl documentation as "experimental and subject to change -or removal in a future version of Perl". It goes on to say: "Their usage in -production code should be noted to avoid problems during upgrades." The same -remarks apply to the PCRE features described in this section. -

-

-Since these verbs are specifically related to backtracking, most of them can be -used only when the pattern is to be matched using pcre_exec(), which uses -a backtracking algorithm. With the exception of (*FAIL), which behaves like a -failing negative assertion, they cause an error if encountered by -pcre_dfa_exec(). -

-

-The new verbs make use of what was previously invalid syntax: an opening -parenthesis followed by an asterisk. In Perl, they are generally of the form -(*VERB:ARG) but PCRE does not support the use of arguments, so its general -form is just (*VERB). Any number of these verbs may occur in a pattern. There -are two kinds: -

-
-Verbs that act immediately -
-

-The following verbs act as soon as they are encountered: -

-   (*ACCEPT)
-
-This verb causes the match to end successfully, skipping the remainder of the -pattern. When inside a recursion, only the innermost pattern is ended -immediately. PCRE differs from Perl in what happens if the (*ACCEPT) is inside -capturing parentheses. In Perl, the data so far is captured: in PCRE no data is -captured. For example: -
-  A(A|B(*ACCEPT)|C)D
-
-This matches "AB", "AAD", or "ACD", but when it matches "AB", no data is -captured. -
-  (*FAIL) or (*F)
-
-This verb causes the match to fail, forcing backtracking to occur. It is -equivalent to (?!) but easier to read. The Perl documentation notes that it is -probably useful only when combined with (?{}) or (??{}). Those are, of course, -Perl features that are not present in PCRE. The nearest equivalent is the -callout feature, as for example in this pattern: -
-  a+(?C)(*FAIL)
-
-A match with the string "aaaa" always fails, but the callout is taken before -each backtrack happens (in this example, 10 times). -

-
-Verbs that act after backtracking -
-

-The following verbs do nothing when they are encountered. Matching continues -with what follows, but if there is no subsequent match, a failure is forced. -The verbs differ in exactly what kind of failure occurs. -

-  (*COMMIT)
-
-This verb causes the whole match to fail outright if the rest of the pattern -does not match. Even if the pattern is unanchored, no further attempts to find -a match by advancing the start point take place. Once (*COMMIT) has been -passed, pcre_exec() is committed to finding a match at the current -starting point, or not at all. For example: -
-  a+(*COMMIT)b
-
-This matches "xxaab" but not "aacaab". It can be thought of as a kind of -dynamic anchor, or "I've started, so I must finish." -
-  (*PRUNE)
-
-This verb causes the match to fail at the current position if the rest of the -pattern does not match. If the pattern is unanchored, the normal "bumpalong" -advance to the next starting character then happens. Backtracking can occur as -usual to the left of (*PRUNE), or when matching to the right of (*PRUNE), but -if there is no match to the right, backtracking cannot cross (*PRUNE). -In simple cases, the use of (*PRUNE) is just an alternative to an atomic -group or possessive quantifier, but there are some uses of (*PRUNE) that cannot -be expressed in any other way. -
-  (*SKIP)
-
-This verb is like (*PRUNE), except that if the pattern is unanchored, the -"bumpalong" advance is not to the next character, but to the position in the -subject where (*SKIP) was encountered. (*SKIP) signifies that whatever text -was matched leading up to it cannot be part of a successful match. Consider: -
-  a+(*SKIP)b
-
-If the subject is "aaaac...", after the first match attempt fails (starting at -the first character in the string), the starting point skips on to start the -next attempt at "c". Note that a possessive quantifer does not have the same -effect in this example; although it would suppress backtracking during the -first match attempt, the second attempt would start at the second character -instead of skipping on to "c". -
-  (*THEN)
-
-This verb causes a skip to the next alternation if the rest of the pattern does -not match. That is, it cancels pending backtracking, but only within the -current alternation. Its name comes from the observation that it can be used -for a pattern-based if-then-else block: -
-  ( COND1 (*THEN) FOO | COND2 (*THEN) BAR | COND3 (*THEN) BAZ ) ...
-
-If the COND1 pattern matches, FOO is tried (and possibly further items after -the end of the group if FOO succeeds); on failure the matcher skips to the -second alternative and tries COND2, without backtracking into COND1. If (*THEN) -is used outside of any alternation, it acts exactly like (*PRUNE). -

-
SEE ALSO
-

-pcreapi(3), pcrecallout(3), pcrematching(3), pcre(3). -

-
AUTHOR
-

-Philip Hazel -
-University Computing Service -
-Cambridge CB2 3QH, England. -
-

-
REVISION
-

-Last updated: 11 April 2009 -
-Copyright © 1997-2009 University of Cambridge. -
-

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcreperform.html b/libs/pcre/doc/html/pcreperform.html deleted file mode 100644 index 41d893d706..0000000000 --- a/libs/pcre/doc/html/pcreperform.html +++ /dev/null @@ -1,173 +0,0 @@ - - -pcreperform specification - - -

pcreperform man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-
-PCRE PERFORMANCE -
-

-Two aspects of performance are discussed below: memory usage and processing -time. The way you express your pattern as a regular expression can affect both -of them. -

-
-MEMORY USAGE -
-

-Patterns are compiled by PCRE into a reasonably efficient byte code, so that -most simple patterns do not use much memory. However, there is one case where -memory usage can be unexpectedly large. When a parenthesized subpattern has a -quantifier with a minimum greater than 1 and/or a limited maximum, the whole -subpattern is repeated in the compiled code. For example, the pattern -

-  (abc|def){2,4}
-
-is compiled as if it were -
-  (abc|def)(abc|def)((abc|def)(abc|def)?)?
-
-(Technical aside: It is done this way so that backtrack points within each of -the repetitions can be independently maintained.) -

-

-For regular expressions whose quantifiers use only small numbers, this is not -usually a problem. However, if the numbers are large, and particularly if such -repetitions are nested, the memory usage can become an embarrassment. For -example, the very simple pattern -

-  ((ab){1,1000}c){1,3}
-
-uses 51K bytes when compiled. When PCRE is compiled with its default internal -pointer size of two bytes, the size limit on a compiled pattern is 64K, and -this is reached with the above pattern if the outer repetition is increased -from 3 to 4. PCRE can be compiled to use larger internal pointers and thus -handle larger compiled patterns, but it is better to try to rewrite your -pattern to use less memory if you can. -

-

-One way of reducing the memory usage for such patterns is to make use of PCRE's -"subroutine" -facility. Re-writing the above pattern as -

-  ((ab)(?2){0,999}c)(?1){0,2}
-
-reduces the memory requirements to 18K, and indeed it remains under 20K even -with the outer repetition increased to 100. However, this pattern is not -exactly equivalent, because the "subroutine" calls are treated as -atomic groups -into which there can be no backtracking if there is a subsequent matching -failure. Therefore, PCRE cannot do this kind of rewriting automatically. -Furthermore, there is a noticeable loss of speed when executing the modified -pattern. Nevertheless, if the atomic grouping is not a problem and the loss of -speed is acceptable, this kind of rewriting will allow you to process patterns -that PCRE cannot otherwise handle. -

-
-PROCESSING TIME -
-

-Certain items in regular expression patterns are processed more efficiently -than others. It is more efficient to use a character class like [aeiou] than a -set of single-character alternatives such as (a|e|i|o|u). In general, the -simplest construction that provides the required behaviour is usually the most -efficient. Jeffrey Friedl's book contains a lot of useful general discussion -about optimizing regular expressions for efficient performance. This document -contains a few observations about PCRE. -

-

-Using Unicode character properties (the \p, \P, and \X escapes) is slow, -because PCRE has to scan a structure that contains data for over fifteen -thousand characters whenever it needs a character's property. If you can find -an alternative pattern that does not use character properties, it will probably -be faster. -

-

-When a pattern begins with .* not in parentheses, or in parentheses that are -not the subject of a backreference, and the PCRE_DOTALL option is set, the -pattern is implicitly anchored by PCRE, since it can match only at the start of -a subject string. However, if PCRE_DOTALL is not set, PCRE cannot make this -optimization, because the . metacharacter does not then match a newline, and if -the subject string contains newlines, the pattern may match from the character -immediately following one of them instead of from the very start. For example, -the pattern -

-  .*second
-
-matches the subject "first\nand second" (where \n stands for a newline -character), with the match starting at the seventh character. In order to do -this, PCRE has to retry the match starting after every newline in the subject. -

-

-If you are using such a pattern with subject strings that do not contain -newlines, the best performance is obtained by setting PCRE_DOTALL, or starting -the pattern with ^.* or ^.*? to indicate explicit anchoring. That saves PCRE -from having to scan along the subject looking for a newline to restart at. -

-

-Beware of patterns that contain nested indefinite repeats. These can take a -long time to run when applied to a string that does not match. Consider the -pattern fragment -

-  ^(a+)*
-
-This can match "aaaa" in 16 different ways, and this number increases very -rapidly as the string gets longer. (The * repeat can match 0, 1, 2, 3, or 4 -times, and for each of those cases other than 0 or 4, the + repeats can match -different numbers of times.) When the remainder of the pattern is such that the -entire match is going to fail, PCRE has in principle to try every possible -variation, and this can take an extremely long time, even for relatively short -strings. -

-

-An optimization catches some of the more simple cases such as -

-  (a+)*b
-
-where a literal character follows. Before embarking on the standard matching -procedure, PCRE checks that there is a "b" later in the subject string, and if -there is not, it fails the match immediately. However, when there is no -following literal this optimization cannot be used. You can see the difference -by comparing the behaviour of -
-  (a+)*\d
-
-with the pattern above. The former gives a failure almost instantly when -applied to a whole line of "a" characters, whereas the latter takes an -appreciable time with strings longer than about 20 characters. -

-

-In many cases, the solution to this kind of performance issue is to use an -atomic group or a possessive quantifier. -

-
-AUTHOR -
-

-Philip Hazel -
-University Computing Service -
-Cambridge CB2 3QH, England. -
-

-
-REVISION -
-

-Last updated: 06 March 2007 -
-Copyright © 1997-2007 University of Cambridge. -
-

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcreposix.html b/libs/pcre/doc/html/pcreposix.html deleted file mode 100644 index 3a35664f7e..0000000000 --- a/libs/pcre/doc/html/pcreposix.html +++ /dev/null @@ -1,266 +0,0 @@ - - -pcreposix specification - - -

pcreposix man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-

-
SYNOPSIS OF POSIX API
-

-#include <pcreposix.h> -

-

-int regcomp(regex_t *preg, const char *pattern, -int cflags); -

-

-int regexec(regex_t *preg, const char *string, -size_t nmatch, regmatch_t pmatch[], int eflags); -

-

-size_t regerror(int errcode, const regex_t *preg, -char *errbuf, size_t errbuf_size); -

-

-void regfree(regex_t *preg); -

-
DESCRIPTION
-

-This set of functions provides a POSIX-style API to the PCRE regular expression -package. See the -pcreapi -documentation for a description of PCRE's native API, which contains much -additional functionality. -

-

-The functions described here are just wrapper functions that ultimately call -the PCRE native API. Their prototypes are defined in the pcreposix.h -header file, and on Unix systems the library itself is called -pcreposix.a, so can be accessed by adding -lpcreposix to the -command for linking an application that uses them. Because the POSIX functions -call the native ones, it is also necessary to add -lpcre. -

-

-I have implemented only those POSIX option bits that can be reasonably mapped -to PCRE native options. In addition, the option REG_EXTENDED is defined with -the value zero. This has no effect, but since programs that are written to the -POSIX interface often use it, this makes it easier to slot in PCRE as a -replacement library. Other POSIX options are not even defined. -

-

-When PCRE is called via these functions, it is only the API that is POSIX-like -in style. The syntax and semantics of the regular expressions themselves are -still those of Perl, subject to the setting of various PCRE options, as -described below. "POSIX-like in style" means that the API approximates to the -POSIX definition; it is not fully POSIX-compatible, and in multi-byte encoding -domains it is probably even less compatible. -

-

-The header for these functions is supplied as pcreposix.h to avoid any -potential clash with other POSIX libraries. It can, of course, be renamed or -aliased as regex.h, which is the "correct" name. It provides two -structure types, regex_t for compiled internal forms, and -regmatch_t for returning captured substrings. It also defines some -constants whose names start with "REG_"; these are used for setting options and -identifying error codes. -

-

-

-
COMPILING A PATTERN
-

-The function regcomp() is called to compile a pattern into an -internal form. The pattern is a C string terminated by a binary zero, and -is passed in the argument pattern. The preg argument is a pointer -to a regex_t structure that is used as a base for storing information -about the compiled regular expression. -

-

-The argument cflags is either zero, or contains one or more of the bits -defined by the following macros: -

-  REG_DOTALL
-
-The PCRE_DOTALL option is set when the regular expression is passed for -compilation to the native function. Note that REG_DOTALL is not part of the -POSIX standard. -
-  REG_ICASE
-
-The PCRE_CASELESS option is set when the regular expression is passed for -compilation to the native function. -
-  REG_NEWLINE
-
-The PCRE_MULTILINE option is set when the regular expression is passed for -compilation to the native function. Note that this does not mimic the -defined POSIX behaviour for REG_NEWLINE (see the following section). -
-  REG_NOSUB
-
-The PCRE_NO_AUTO_CAPTURE option is set when the regular expression is passed -for compilation to the native function. In addition, when a pattern that is -compiled with this flag is passed to regexec() for matching, the -nmatch and pmatch arguments are ignored, and no captured strings -are returned. -
-  REG_UTF8
-
-The PCRE_UTF8 option is set when the regular expression is passed for -compilation to the native function. This causes the pattern itself and all data -strings used for matching it to be treated as UTF-8 strings. Note that REG_UTF8 -is not part of the POSIX standard. -

-

-In the absence of these flags, no options are passed to the native function. -This means the the regex is compiled with PCRE default semantics. In -particular, the way it handles newline characters in the subject string is the -Perl way, not the POSIX way. Note that setting PCRE_MULTILINE has only -some of the effects specified for REG_NEWLINE. It does not affect the way -newlines are matched by . (they aren't) or by a negative class such as [^a] -(they are). -

-

-The yield of regcomp() is zero on success, and non-zero otherwise. The -preg structure is filled in on success, and one member of the structure -is public: re_nsub contains the number of capturing subpatterns in -the regular expression. Various error codes are defined in the header file. -

-
MATCHING NEWLINE CHARACTERS
-

-This area is not simple, because POSIX and Perl take different views of things. -It is not possible to get PCRE to obey POSIX semantics, but then PCRE was never -intended to be a POSIX engine. The following table lists the different -possibilities for matching newline characters in PCRE: -

-                          Default   Change with
-
-  . matches newline          no     PCRE_DOTALL
-  newline matches [^a]       yes    not changeable
-  $ matches \n at end        yes    PCRE_DOLLARENDONLY
-  $ matches \n in middle     no     PCRE_MULTILINE
-  ^ matches \n in middle     no     PCRE_MULTILINE
-
-This is the equivalent table for POSIX: -
-                          Default   Change with
-
-  . matches newline          yes    REG_NEWLINE
-  newline matches [^a]       yes    REG_NEWLINE
-  $ matches \n at end        no     REG_NEWLINE
-  $ matches \n in middle     no     REG_NEWLINE
-  ^ matches \n in middle     no     REG_NEWLINE
-
-PCRE's behaviour is the same as Perl's, except that there is no equivalent for -PCRE_DOLLAR_ENDONLY in Perl. In both PCRE and Perl, there is no way to stop -newline from matching [^a]. -

-

-The default POSIX newline handling can be obtained by setting PCRE_DOTALL and -PCRE_DOLLAR_ENDONLY, but there is no way to make PCRE behave exactly as for the -REG_NEWLINE action. -

-
MATCHING A PATTERN
-

-The function regexec() is called to match a compiled pattern preg -against a given string, which is by default terminated by a zero byte -(but see REG_STARTEND below), subject to the options in eflags. These can -be: -

-  REG_NOTBOL
-
-The PCRE_NOTBOL option is set when calling the underlying PCRE matching -function. -
-  REG_NOTEMPTY
-
-The PCRE_NOTEMPTY option is set when calling the underlying PCRE matching -function. Note that REG_NOTEMPTY is not part of the POSIX standard. However, -setting this option can give more POSIX-like behaviour in some situations. -
-  REG_NOTEOL
-
-The PCRE_NOTEOL option is set when calling the underlying PCRE matching -function. -
-  REG_STARTEND
-
-The string is considered to start at string + pmatch[0].rm_so and -to have a terminating NUL located at string + pmatch[0].rm_eo -(there need not actually be a NUL at that location), regardless of the value of -nmatch. This is a BSD extension, compatible with but not specified by -IEEE Standard 1003.2 (POSIX.2), and should be used with caution in software -intended to be portable to other systems. Note that a non-zero rm_so does -not imply REG_NOTBOL; REG_STARTEND affects only the location of the string, not -how it is matched. -

-

-If the pattern was compiled with the REG_NOSUB flag, no data about any matched -strings is returned. The nmatch and pmatch arguments of -regexec() are ignored. -

-

-Otherwise,the portion of the string that was matched, and also any captured -substrings, are returned via the pmatch argument, which points to an -array of nmatch structures of type regmatch_t, containing the -members rm_so and rm_eo. These contain the offset to the first -character of each substring and the offset to the first character after the end -of each substring, respectively. The 0th element of the vector relates to the -entire portion of string that was matched; subsequent elements relate to -the capturing subpatterns of the regular expression. Unused entries in the -array have both structure members set to -1. -

-

-A successful match yields a zero return; various error codes are defined in the -header file, of which REG_NOMATCH is the "expected" failure code. -

-
ERROR MESSAGES
-

-The regerror() function maps a non-zero errorcode from either -regcomp() or regexec() to a printable message. If preg is not -NULL, the error should have arisen from the use of that structure. A message -terminated by a binary zero is placed in errbuf. The length of the -message, including the zero, is limited to errbuf_size. The yield of the -function is the size of buffer needed to hold the whole message. -

-
MEMORY USAGE
-

-Compiling a regular expression causes memory to be allocated and associated -with the preg structure. The function regfree() frees all such -memory, after which preg may no longer be used as a compiled expression. -

-
AUTHOR
-

-Philip Hazel -
-University Computing Service -
-Cambridge CB2 3QH, England. -
-

-
REVISION
-

-Last updated: 11 March 2009 -
-Copyright © 1997-2009 University of Cambridge. -
-

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcreprecompile.html b/libs/pcre/doc/html/pcreprecompile.html deleted file mode 100644 index 83da22673d..0000000000 --- a/libs/pcre/doc/html/pcreprecompile.html +++ /dev/null @@ -1,148 +0,0 @@ - - -pcreprecompile specification - - -

pcreprecompile man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-

-
SAVING AND RE-USING PRECOMPILED PCRE PATTERNS
-

-If you are running an application that uses a large number of regular -expression patterns, it may be useful to store them in a precompiled form -instead of having to compile them every time the application is run. -If you are not using any private character tables (see the -pcre_maketables() -documentation), this is relatively straightforward. If you are using private -tables, it is a little bit more complicated. -

-

-If you save compiled patterns to a file, you can copy them to a different host -and run them there. This works even if the new host has the opposite endianness -to the one on which the patterns were compiled. There may be a small -performance penalty, but it should be insignificant. However, compiling regular -expressions with one version of PCRE for use with a different version is not -guaranteed to work and may cause crashes. -

-
SAVING A COMPILED PATTERN
-

-The value returned by pcre_compile() points to a single block of memory -that holds the compiled pattern and associated data. You can find the length of -this block in bytes by calling pcre_fullinfo() with an argument of -PCRE_INFO_SIZE. You can then save the data in any appropriate manner. Here is -sample code that compiles a pattern and writes it to a file. It assumes that -the variable fd refers to a file that is open for output: -

-  int erroroffset, rc, size;
-  char *error;
-  pcre *re;
-
-  re = pcre_compile("my pattern", 0, &error, &erroroffset, NULL);
-  if (re == NULL) { ... handle errors ... }
-  rc = pcre_fullinfo(re, NULL, PCRE_INFO_SIZE, &size);
-  if (rc < 0) { ... handle errors ... }
-  rc = fwrite(re, 1, size, fd);
-  if (rc != size) { ... handle errors ... }
-
-In this example, the bytes that comprise the compiled pattern are copied -exactly. Note that this is binary data that may contain any of the 256 possible -byte values. On systems that make a distinction between binary and non-binary -data, be sure that the file is opened for binary output. -

-

-If you want to write more than one pattern to a file, you will have to devise a -way of separating them. For binary data, preceding each pattern with its length -is probably the most straightforward approach. Another possibility is to write -out the data in hexadecimal instead of binary, one pattern to a line. -

-

-Saving compiled patterns in a file is only one possible way of storing them for -later use. They could equally well be saved in a database, or in the memory of -some daemon process that passes them via sockets to the processes that want -them. -

-

-If the pattern has been studied, it is also possible to save the study data in -a similar way to the compiled pattern itself. When studying generates -additional information, pcre_study() returns a pointer to a -pcre_extra data block. Its format is defined in the -section on matching a pattern -in the -pcreapi -documentation. The study_data field points to the binary study data, and -this is what you must save (not the pcre_extra block itself). The length -of the study data can be obtained by calling pcre_fullinfo() with an -argument of PCRE_INFO_STUDYSIZE. Remember to check that pcre_study() did -return a non-NULL value before trying to save the study data. -

-
RE-USING A PRECOMPILED PATTERN
-

-Re-using a precompiled pattern is straightforward. Having reloaded it into main -memory, you pass its pointer to pcre_exec() or pcre_dfa_exec() in -the usual way. This should work even on another host, and even if that host has -the opposite endianness to the one where the pattern was compiled. -

-

-However, if you passed a pointer to custom character tables when the pattern -was compiled (the tableptr argument of pcre_compile()), you must -now pass a similar pointer to pcre_exec() or pcre_dfa_exec(), -because the value saved with the compiled pattern will obviously be nonsense. A -field in a pcre_extra() block is used to pass this data, as described in -the -section on matching a pattern -in the -pcreapi -documentation. -

-

-If you did not provide custom character tables when the pattern was compiled, -the pointer in the compiled pattern is NULL, which causes pcre_exec() to -use PCRE's internal tables. Thus, you do not need to take any special action at -run time in this case. -

-

-If you saved study data with the compiled pattern, you need to create your own -pcre_extra data block and set the study_data field to point to the -reloaded study data. You must also set the PCRE_EXTRA_STUDY_DATA bit in the -flags field to indicate that study data is present. Then pass the -pcre_extra block to pcre_exec() or pcre_dfa_exec() in the -usual way. -

-
COMPATIBILITY WITH DIFFERENT PCRE RELEASES
-

-In general, it is safest to recompile all saved patterns when you update to a -new PCRE release, though not all updates actually require this. Recompiling is -definitely needed for release 7.2. -

-
AUTHOR
-

-Philip Hazel -
-University Computing Service -
-Cambridge CB2 3QH, England. -
-

-
REVISION
-

-Last updated: 13 June 2007 -
-Copyright © 1997-2007 University of Cambridge. -
-

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcresample.html b/libs/pcre/doc/html/pcresample.html deleted file mode 100644 index 6243be6a5a..0000000000 --- a/libs/pcre/doc/html/pcresample.html +++ /dev/null @@ -1,96 +0,0 @@ - - -pcresample specification - - -

pcresample man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-
-PCRE SAMPLE PROGRAM -
-

-A simple, complete demonstration program, to get you started with using PCRE, -is supplied in the file pcredemo.c in the PCRE distribution. -

-

-The program compiles the regular expression that is its first argument, and -matches it against the subject string in its second argument. No PCRE options -are set, and default character tables are used. If matching succeeds, the -program outputs the portion of the subject that matched, together with the -contents of any captured substrings. -

-

-If the -g option is given on the command line, the program then goes on to -check for further matches of the same regular expression in the same subject -string. The logic is a little bit tricky because of the possibility of matching -an empty string. Comments in the code explain what is going on. -

-

-If PCRE is installed in the standard include and library directories for your -system, you should be able to compile the demonstration program using this -command: -

-  gcc -o pcredemo pcredemo.c -lpcre
-
-If PCRE is installed elsewhere, you may need to add additional options to the -command line. For example, on a Unix-like system that has PCRE installed in -/usr/local, you can compile the demonstration program using a command -like this: -
-  gcc -o pcredemo -I/usr/local/include pcredemo.c -L/usr/local/lib -lpcre
-
-Once you have compiled the demonstration program, you can run simple tests like -this: -
-  ./pcredemo 'cat|dog' 'the cat sat on the mat'
-  ./pcredemo -g 'cat|dog' 'the dog sat on the cat'
-
-Note that there is a much more comprehensive test program, called -pcretest, -which supports many more facilities for testing regular expressions and the -PCRE library. The pcredemo program is provided as a simple coding -example. -

-

-On some operating systems (e.g. Solaris), when PCRE is not installed in the -standard library directory, you may get an error like this when you try to run -pcredemo: -

-  ld.so.1: a.out: fatal: libpcre.so.0: open failed: No such file or directory
-
-This is caused by the way shared library support works on those systems. You -need to add -
-  -R/usr/local/lib
-
-(for example) to the compile command to get round this problem. -

-
-AUTHOR -
-

-Philip Hazel -
-University Computing Service -
-Cambridge CB2 3QH, England. -
-

-
-REVISION -
-

-Last updated: 23 January 2008 -
-Copyright © 1997-2008 University of Cambridge. -
-

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcrestack.html b/libs/pcre/doc/html/pcrestack.html deleted file mode 100644 index 60488280e9..0000000000 --- a/libs/pcre/doc/html/pcrestack.html +++ /dev/null @@ -1,172 +0,0 @@ - - -pcrestack specification - - -

pcrestack man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-
-PCRE DISCUSSION OF STACK USAGE -
-

-When you call pcre_exec(), it makes use of an internal function called -match(). This calls itself recursively at branch points in the pattern, -in order to remember the state of the match so that it can back up and try a -different alternative if the first one fails. As matching proceeds deeper and -deeper into the tree of possibilities, the recursion depth increases. -

-

-Not all calls of match() increase the recursion depth; for an item such -as a* it may be called several times at the same level, after matching -different numbers of a's. Furthermore, in a number of cases where the result of -the recursive call would immediately be passed back as the result of the -current call (a "tail recursion"), the function is just restarted instead. -

-

-The pcre_dfa_exec() function operates in an entirely different way, and -hardly uses recursion at all. The limit on its complexity is the amount of -workspace it is given. The comments that follow do NOT apply to -pcre_dfa_exec(); they are relevant only for pcre_exec(). -

-

-You can set limits on the number of times that match() is called, both in -total and recursively. If the limit is exceeded, an error occurs. For details, -see the -section on extra data for pcre_exec() -in the -pcreapi -documentation. -

-

-Each time that match() is actually called recursively, it uses memory -from the process stack. For certain kinds of pattern and data, very large -amounts of stack may be needed, despite the recognition of "tail recursion". -You can often reduce the amount of recursion, and therefore the amount of stack -used, by modifying the pattern that is being matched. Consider, for example, -this pattern: -

-  ([^<]|<(?!inet))+
-
-It matches from wherever it starts until it encounters "<inet" or the end of -the data, and is the kind of pattern that might be used when processing an XML -file. Each iteration of the outer parentheses matches either one character that -is not "<" or a "<" that is not followed by "inet". However, each time a -parenthesis is processed, a recursion occurs, so this formulation uses a stack -frame for each matched character. For a long string, a lot of stack is -required. Consider now this rewritten pattern, which matches exactly the same -strings: -
-  ([^<]++|<(?!inet))+
-
-This uses very much less stack, because runs of characters that do not contain -"<" are "swallowed" in one item inside the parentheses. Recursion happens only -when a "<" character that is not followed by "inet" is encountered (and we -assume this is relatively rare). A possessive quantifier is used to stop any -backtracking into the runs of non-"<" characters, but that is not related to -stack usage. -

-

-This example shows that one way of avoiding stack problems when matching long -subject strings is to write repeated parenthesized subpatterns to match more -than one character whenever possible. -

-
-Compiling PCRE to use heap instead of stack -
-

-In environments where stack memory is constrained, you might want to compile -PCRE to use heap memory instead of stack for remembering back-up points. This -makes it run a lot more slowly, however. Details of how to do this are given in -the -pcrebuild -documentation. When built in this way, instead of using the stack, PCRE obtains -and frees memory by calling the functions that are pointed to by the -pcre_stack_malloc and pcre_stack_free variables. By default, these -point to malloc() and free(), but you can replace the pointers to -cause PCRE to use your own functions. Since the block sizes are always the -same, and are always freed in reverse order, it may be possible to implement -customized memory handlers that are more efficient than the standard functions. -

-
-Limiting PCRE's stack usage -
-

-PCRE has an internal counter that can be used to limit the depth of recursion, -and thus cause pcre_exec() to give an error code before it runs out of -stack. By default, the limit is very large, and unlikely ever to operate. It -can be changed when PCRE is built, and it can also be set when -pcre_exec() is called. For details of these interfaces, see the -pcrebuild -and -pcreapi -documentation. -

-

-As a very rough rule of thumb, you should reckon on about 500 bytes per -recursion. Thus, if you want to limit your stack usage to 8Mb, you -should set the limit at 16000 recursions. A 64Mb stack, on the other hand, can -support around 128000 recursions. The pcretest test program has a command -line option (-S) that can be used to increase the size of its stack. -

-
-Changing stack size in Unix-like systems -
-

-In Unix-like environments, there is not often a problem with the stack unless -very long strings are involved, though the default limit on stack size varies -from system to system. Values from 8Mb to 64Mb are common. You can find your -default limit by running the command: -

-  ulimit -s
-
-Unfortunately, the effect of running out of stack is often SIGSEGV, though -sometimes a more explicit error message is given. You can normally increase the -limit on stack size by code such as this: -
-  struct rlimit rlim;
-  getrlimit(RLIMIT_STACK, &rlim);
-  rlim.rlim_cur = 100*1024*1024;
-  setrlimit(RLIMIT_STACK, &rlim);
-
-This reads the current limits (soft and hard) using getrlimit(), then -attempts to increase the soft limit to 100Mb using setrlimit(). You must -do this before calling pcre_exec(). -

-
-Changing stack size in Mac OS X -
-

-Using setrlimit(), as described above, should also work on Mac OS X. It -is also possible to set a stack size when linking a program. There is a -discussion about stack sizes in Mac OS X at this web site: -http://developer.apple.com/qa/qa2005/qa1419.html. -

-
-AUTHOR -
-

-Philip Hazel -
-University Computing Service -
-Cambridge CB2 3QH, England. -
-

-
-REVISION -
-

-Last updated: 09 July 2008 -
-Copyright © 1997-2008 University of Cambridge. -
-

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcresyntax.html b/libs/pcre/doc/html/pcresyntax.html deleted file mode 100644 index 2a1a686284..0000000000 --- a/libs/pcre/doc/html/pcresyntax.html +++ /dev/null @@ -1,473 +0,0 @@ - - -pcresyntax specification - - -

pcresyntax man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-

-
PCRE REGULAR EXPRESSION SYNTAX SUMMARY
-

-The full syntax and semantics of the regular expressions that are supported by -PCRE are described in the -pcrepattern -documentation. This document contains just a quick-reference summary of the -syntax. -

-
QUOTING
-

-

-  \x         where x is non-alphanumeric is a literal x
-  \Q...\E    treat enclosed characters as literal
-
-

-
CHARACTERS
-

-

-  \a         alarm, that is, the BEL character (hex 07)
-  \cx        "control-x", where x is any character
-  \e         escape (hex 1B)
-  \f         formfeed (hex 0C)
-  \n         newline (hex 0A)
-  \r         carriage return (hex 0D)
-  \t         tab (hex 09)
-  \ddd       character with octal code ddd, or backreference
-  \xhh       character with hex code hh
-  \x{hhh..}  character with hex code hhh..
-
-

-
CHARACTER TYPES
-

-

-  .          any character except newline;
-               in dotall mode, any character whatsoever
-  \C         one byte, even in UTF-8 mode (best avoided)
-  \d         a decimal digit
-  \D         a character that is not a decimal digit
-  \h         a horizontal whitespace character
-  \H         a character that is not a horizontal whitespace character
-  \p{xx}     a character with the xx property
-  \P{xx}     a character without the xx property
-  \R         a newline sequence
-  \s         a whitespace character
-  \S         a character that is not a whitespace character
-  \v         a vertical whitespace character
-  \V         a character that is not a vertical whitespace character
-  \w         a "word" character
-  \W         a "non-word" character
-  \X         an extended Unicode sequence
-
-In PCRE, \d, \D, \s, \S, \w, and \W recognize only ASCII characters. -

-
GENERAL CATEGORY PROPERTY CODES FOR \p and \P
-

-

-  C          Other
-  Cc         Control
-  Cf         Format
-  Cn         Unassigned
-  Co         Private use
-  Cs         Surrogate
-
-  L          Letter
-  Ll         Lower case letter
-  Lm         Modifier letter
-  Lo         Other letter
-  Lt         Title case letter
-  Lu         Upper case letter
-  L&         Ll, Lu, or Lt
-
-  M          Mark
-  Mc         Spacing mark
-  Me         Enclosing mark
-  Mn         Non-spacing mark
-
-  N          Number
-  Nd         Decimal number
-  Nl         Letter number
-  No         Other number
-
-  P          Punctuation
-  Pc         Connector punctuation
-  Pd         Dash punctuation
-  Pe         Close punctuation
-  Pf         Final punctuation
-  Pi         Initial punctuation
-  Po         Other punctuation
-  Ps         Open punctuation
-
-  S          Symbol
-  Sc         Currency symbol
-  Sk         Modifier symbol
-  Sm         Mathematical symbol
-  So         Other symbol
-
-  Z          Separator
-  Zl         Line separator
-  Zp         Paragraph separator
-  Zs         Space separator
-
-

-
SCRIPT NAMES FOR \p AND \P
-

-Arabic, -Armenian, -Balinese, -Bengali, -Bopomofo, -Braille, -Buginese, -Buhid, -Canadian_Aboriginal, -Carian, -Cham, -Cherokee, -Common, -Coptic, -Cuneiform, -Cypriot, -Cyrillic, -Deseret, -Devanagari, -Ethiopic, -Georgian, -Glagolitic, -Gothic, -Greek, -Gujarati, -Gurmukhi, -Han, -Hangul, -Hanunoo, -Hebrew, -Hiragana, -Inherited, -Kannada, -Katakana, -Kayah_Li, -Kharoshthi, -Khmer, -Lao, -Latin, -Lepcha, -Limbu, -Linear_B, -Lycian, -Lydian, -Malayalam, -Mongolian, -Myanmar, -New_Tai_Lue, -Nko, -Ogham, -Old_Italic, -Old_Persian, -Ol_Chiki, -Oriya, -Osmanya, -Phags_Pa, -Phoenician, -Rejang, -Runic, -Saurashtra, -Shavian, -Sinhala, -Sudanese, -Syloti_Nagri, -Syriac, -Tagalog, -Tagbanwa, -Tai_Le, -Tamil, -Telugu, -Thaana, -Thai, -Tibetan, -Tifinagh, -Ugaritic, -Vai, -Yi. -

-
CHARACTER CLASSES
-

-

-  [...]       positive character class
-  [^...]      negative character class
-  [x-y]       range (can be used for hex characters)
-  [[:xxx:]]   positive POSIX named set
-  [[:^xxx:]]  negative POSIX named set
-
-  alnum       alphanumeric
-  alpha       alphabetic
-  ascii       0-127
-  blank       space or tab
-  cntrl       control character
-  digit       decimal digit
-  graph       printing, excluding space
-  lower       lower case letter
-  print       printing, including space
-  punct       printing, excluding alphanumeric
-  space       whitespace
-  upper       upper case letter
-  word        same as \w
-  xdigit      hexadecimal digit
-
-In PCRE, POSIX character set names recognize only ASCII characters. You can use -\Q...\E inside a character class. -

-
QUANTIFIERS
-

-

-  ?           0 or 1, greedy
-  ?+          0 or 1, possessive
-  ??          0 or 1, lazy
-  *           0 or more, greedy
-  *+          0 or more, possessive
-  *?          0 or more, lazy
-  +           1 or more, greedy
-  ++          1 or more, possessive
-  +?          1 or more, lazy
-  {n}         exactly n
-  {n,m}       at least n, no more than m, greedy
-  {n,m}+      at least n, no more than m, possessive
-  {n,m}?      at least n, no more than m, lazy
-  {n,}        n or more, greedy
-  {n,}+       n or more, possessive
-  {n,}?       n or more, lazy
-
-

-
ANCHORS AND SIMPLE ASSERTIONS
-

-

-  \b          word boundary (only ASCII letters recognized)
-  \B          not a word boundary
-  ^           start of subject
-               also after internal newline in multiline mode
-  \A          start of subject
-  $           end of subject
-               also before newline at end of subject
-               also before internal newline in multiline mode
-  \Z          end of subject
-               also before newline at end of subject
-  \z          end of subject
-  \G          first matching position in subject
-
-

-
MATCH POINT RESET
-

-

-  \K          reset start of match
-
-

-
ALTERNATION
-

-

-  expr|expr|expr...
-
-

-
CAPTURING
-

-

-  (...)           capturing group
-  (?<name>...)    named capturing group (Perl)
-  (?'name'...)    named capturing group (Perl)
-  (?P<name>...)   named capturing group (Python)
-  (?:...)         non-capturing group
-  (?|...)         non-capturing group; reset group numbers for
-                   capturing groups in each alternative
-
-

-
ATOMIC GROUPS
-

-

-  (?>...)         atomic, non-capturing group
-
-

-
COMMENT
-

-

-  (?#....)        comment (not nestable)
-
-

-
OPTION SETTING
-

-

-  (?i)            caseless
-  (?J)            allow duplicate names
-  (?m)            multiline
-  (?s)            single line (dotall)
-  (?U)            default ungreedy (lazy)
-  (?x)            extended (ignore white space)
-  (?-...)         unset option(s)
-
-The following is recognized only at the start of a pattern or after one of the -newline-setting options with similar syntax: -
-  (*UTF8)         set UTF-8 mode
-
-

-
LOOKAHEAD AND LOOKBEHIND ASSERTIONS
-

-

-  (?=...)         positive look ahead
-  (?!...)         negative look ahead
-  (?<=...)        positive look behind
-  (?<!...)        negative look behind
-
-Each top-level branch of a look behind must be of a fixed length. -

-
BACKREFERENCES
-

-

-  \n              reference by number (can be ambiguous)
-  \gn             reference by number
-  \g{n}           reference by number
-  \g{-n}          relative reference by number
-  \k<name>        reference by name (Perl)
-  \k'name'        reference by name (Perl)
-  \g{name}        reference by name (Perl)
-  \k{name}        reference by name (.NET)
-  (?P=name)       reference by name (Python)
-
-

-
SUBROUTINE REFERENCES (POSSIBLY RECURSIVE)
-

-

-  (?R)            recurse whole pattern
-  (?n)            call subpattern by absolute number
-  (?+n)           call subpattern by relative number
-  (?-n)           call subpattern by relative number
-  (?&name)        call subpattern by name (Perl)
-  (?P>name)       call subpattern by name (Python)
-  \g<name>        call subpattern by name (Oniguruma)
-  \g'name'        call subpattern by name (Oniguruma)
-  \g<n>           call subpattern by absolute number (Oniguruma)
-  \g'n'           call subpattern by absolute number (Oniguruma)
-  \g<+n>          call subpattern by relative number (PCRE extension)
-  \g'+n'          call subpattern by relative number (PCRE extension)
-  \g<-n>          call subpattern by relative number (PCRE extension)
-  \g'-n'          call subpattern by relative number (PCRE extension)
-
-

-
CONDITIONAL PATTERNS
-

-

-  (?(condition)yes-pattern)
-  (?(condition)yes-pattern|no-pattern)
-
-  (?(n)...        absolute reference condition
-  (?(+n)...       relative reference condition
-  (?(-n)...       relative reference condition
-  (?(<name>)...   named reference condition (Perl)
-  (?('name')...   named reference condition (Perl)
-  (?(name)...     named reference condition (PCRE)
-  (?(R)...        overall recursion condition
-  (?(Rn)...       specific group recursion condition
-  (?(R&name)...   specific recursion condition
-  (?(DEFINE)...   define subpattern for reference
-  (?(assert)...   assertion condition
-
-

-
BACKTRACKING CONTROL
-

-The following act immediately they are reached: -

-  (*ACCEPT)       force successful match
-  (*FAIL)         force backtrack; synonym (*F)
-
-The following act only when a subsequent match failure causes a backtrack to -reach them. They all force a match failure, but they differ in what happens -afterwards. Those that advance the start-of-match point do so only if the -pattern is not anchored. -
-  (*COMMIT)       overall failure, no advance of starting point
-  (*PRUNE)        advance to next starting character
-  (*SKIP)         advance start to current matching position
-  (*THEN)         local failure, backtrack to next alternation
-
-

-
NEWLINE CONVENTIONS
-

-These are recognized only at the very start of the pattern or after a -(*BSR_...) or (*UTF8) option. -

-  (*CR)           carriage return only
-  (*LF)           linefeed only
-  (*CRLF)         carriage return followed by linefeed
-  (*ANYCRLF)      all three of the above
-  (*ANY)          any Unicode newline sequence
-
-

-
WHAT \R MATCHES
-

-These are recognized only at the very start of the pattern or after a -(*...) option that sets the newline convention or UTF-8 mode. -

-  (*BSR_ANYCRLF)  CR, LF, or CRLF
-  (*BSR_UNICODE)  any Unicode newline sequence
-
-

-
CALLOUTS
-

-

-  (?C)      callout
-  (?Cn)     callout with data n
-
-

-
SEE ALSO
-

-pcrepattern(3), pcreapi(3), pcrecallout(3), -pcrematching(3), pcre(3). -

-
AUTHOR
-

-Philip Hazel -
-University Computing Service -
-Cambridge CB2 3QH, England. -
-

-
REVISION
-

-Last updated: 11 April 2009 -
-Copyright © 1997-2009 University of Cambridge. -
-

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/html/pcretest.html b/libs/pcre/doc/html/pcretest.html deleted file mode 100644 index 0358958b74..0000000000 --- a/libs/pcre/doc/html/pcretest.html +++ /dev/null @@ -1,712 +0,0 @@ - - -pcretest specification - - -

pcretest man page

-

-Return to the PCRE index page. -

-

-This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -
-

-
SYNOPSIS
-

-pcretest [options] [source] [destination] -
-
-pcretest was written as a test program for the PCRE regular expression -library itself, but it can also be used for experimenting with regular -expressions. This document describes the features of the test program; for -details of the regular expressions themselves, see the -pcrepattern -documentation. For details of the PCRE library function calls and their -options, see the -pcreapi -documentation. -

-
OPTIONS
-

--b -Behave as if each regex has the /B (show bytecode) modifier; the internal -form is output after compilation. -

-

--C -Output the version number of the PCRE library, and all available information -about the optional features that are included, and then exit. -

-

--d -Behave as if each regex has the /D (debug) modifier; the internal -form and information about the compiled pattern is output after compilation; --d is equivalent to -b -i. -

-

--dfa -Behave as if each data line contains the \D escape sequence; this causes the -alternative matching function, pcre_dfa_exec(), to be used instead of the -standard pcre_exec() function (more detail is given below). -

-

--help -Output a brief summary these options and then exit. -

-

--i -Behave as if each regex has the /I modifier; information about the -compiled pattern is given after compilation. -

-

--M -Behave as if each data line contains the \M escape sequence; this causes -PCRE to discover the minimum MATCH_LIMIT and MATCH_LIMIT_RECURSION settings by -calling pcre_exec() repeatedly with different limits. -

-

--m -Output the size of each compiled pattern after it has been compiled. This is -equivalent to adding /M to each regular expression. For compatibility -with earlier versions of pcretest, -s is a synonym for -m. -

-

--o osize -Set the number of elements in the output vector that is used when calling -pcre_exec() or pcre_dfa_exec() to be osize. The default value -is 45, which is enough for 14 capturing subexpressions for pcre_exec() or -22 different matches for pcre_dfa_exec(). The vector size can be -changed for individual matching calls by including \O in the data line (see -below). -

-

--p -Behave as if each regex has the /P modifier; the POSIX wrapper API is -used to call PCRE. None of the other options has any effect when -p is -set. -

-

--q -Do not output the version number of pcretest at the start of execution. -

-

--S size -On Unix-like systems, set the size of the runtime stack to size -megabytes. -

-

--t -Run each compile, study, and match many times with a timer, and output -resulting time per compile or match (in milliseconds). Do not set -m with --t, because you will then get the size output a zillion times, and the -timing will be distorted. You can control the number of iterations that are -used for timing by following -t with a number (as a separate item on the -command line). For example, "-t 1000" would iterate 1000 times. The default is -to iterate 500000 times. -

-

--tm -This is like -t except that it times only the matching phase, not the -compile or study phases. -

-
DESCRIPTION
-

-If pcretest is given two filename arguments, it reads from the first and -writes to the second. If it is given only one filename argument, it reads from -that file and writes to stdout. Otherwise, it reads from stdin and writes to -stdout, and prompts for each line of input, using "re>" to prompt for regular -expressions, and "data>" to prompt for data lines. -

-

-When pcretest is built, a configuration option can specify that it should -be linked with the libreadline library. When this is done, if the input -is from a terminal, it is read using the readline() function. This -provides line-editing and history facilities. The output from the -help -option states whether or not readline() will be used. -

-

-The program handles any number of sets of input on a single input file. Each -set starts with a regular expression, and continues with any number of data -lines to be matched against the pattern. -

-

-Each data line is matched separately and independently. If you want to do -multi-line matches, you have to use the \n escape sequence (or \r or \r\n, -etc., depending on the newline setting) in a single line of input to encode the -newline sequences. There is no limit on the length of data lines; the input -buffer is automatically extended if it is too small. -

-

-An empty line signals the end of the data lines, at which point a new regular -expression is read. The regular expressions are given enclosed in any -non-alphanumeric delimiters other than backslash, for example: -

-  /(a|bc)x+yz/
-
-White space before the initial delimiter is ignored. A regular expression may -be continued over several input lines, in which case the newline characters are -included within it. It is possible to include the delimiter within the pattern -by escaping it, for example -
-  /abc\/def/
-
-If you do so, the escape and the delimiter form part of the pattern, but since -delimiters are always non-alphanumeric, this does not affect its interpretation. -If the terminating delimiter is immediately followed by a backslash, for -example, -
-  /abc/\
-
-then a backslash is added to the end of the pattern. This is done to provide a -way of testing the error condition that arises if a pattern finishes with a -backslash, because -
-  /abc\/
-
-is interpreted as the first line of a pattern that starts with "abc/", causing -pcretest to read the next line as a continuation of the regular expression. -

-
PATTERN MODIFIERS
-

-A pattern may be followed by any number of modifiers, which are mostly single -characters. Following Perl usage, these are referred to below as, for example, -"the /i modifier", even though the delimiter of the pattern need not -always be a slash, and no slash is used when writing modifiers. Whitespace may -appear between the final pattern delimiter and the first modifier, and between -the modifiers themselves. -

-

-The /i, /m, /s, and /x modifiers set the PCRE_CASELESS, -PCRE_MULTILINE, PCRE_DOTALL, or PCRE_EXTENDED options, respectively, when -pcre_compile() is called. These four modifier letters have the same -effect as they do in Perl. For example: -

-  /caseless/i
-
-The following table shows additional modifiers for setting PCRE options that do -not correspond to anything in Perl: -
-  /A              PCRE_ANCHORED
-  /C              PCRE_AUTO_CALLOUT
-  /E              PCRE_DOLLAR_ENDONLY
-  /f              PCRE_FIRSTLINE
-  /J              PCRE_DUPNAMES
-  /N              PCRE_NO_AUTO_CAPTURE
-  /U              PCRE_UNGREEDY
-  /X              PCRE_EXTRA
-  /<JS>           PCRE_JAVASCRIPT_COMPAT
-  /<cr>           PCRE_NEWLINE_CR
-  /<lf>           PCRE_NEWLINE_LF
-  /<crlf>         PCRE_NEWLINE_CRLF
-  /<anycrlf>      PCRE_NEWLINE_ANYCRLF
-  /<any>          PCRE_NEWLINE_ANY
-  /<bsr_anycrlf>  PCRE_BSR_ANYCRLF
-  /<bsr_unicode>  PCRE_BSR_UNICODE
-
-Those specifying line ending sequences are literal strings as shown, but the -letters can be in either case. This example sets multiline matching with CRLF -as the line ending sequence: -
-  /^abc/m<crlf>
-
-Details of the meanings of these PCRE options are given in the -pcreapi -documentation. -

-
-Finding all matches in a string -
-

-Searching for all possible matches within each subject string can be requested -by the /g or /G modifier. After finding a match, PCRE is called -again to search the remainder of the subject string. The difference between -/g and /G is that the former uses the startoffset argument to -pcre_exec() to start searching at a new point within the entire string -(which is in effect what Perl does), whereas the latter passes over a shortened -substring. This makes a difference to the matching process if the pattern -begins with a lookbehind assertion (including \b or \B). -

-

-If any call to pcre_exec() in a /g or /G sequence matches an -empty string, the next call is done with the PCRE_NOTEMPTY and PCRE_ANCHORED -flags set in order to search for another, non-empty, match at the same point. -If this second match fails, the start offset is advanced by one, and the normal -match is retried. This imitates the way Perl handles such cases when using the -/g modifier or the split() function. -

-
-Other modifiers -
-

-There are yet more modifiers for controlling the way pcretest -operates. -

-

-The /+ modifier requests that as well as outputting the substring that -matched the entire pattern, pcretest should in addition output the remainder of -the subject string. This is useful for tests where the subject contains -multiple copies of the same substring. -

-

-The /B modifier is a debugging feature. It requests that pcretest -output a representation of the compiled byte code after compilation. Normally -this information contains length and offset values; however, if /Z is -also present, this data is replaced by spaces. This is a special feature for -use in the automatic test scripts; it ensures that the same output is generated -for different internal link sizes. -

-

-The /L modifier must be followed directly by the name of a locale, for -example, -

-  /pattern/Lfr_FR
-
-For this reason, it must be the last modifier. The given locale is set, -pcre_maketables() is called to build a set of character tables for the -locale, and this is then passed to pcre_compile() when compiling the -regular expression. Without an /L modifier, NULL is passed as the tables -pointer; that is, /L applies only to the expression on which it appears. -

-

-The /I modifier requests that pcretest output information about the -compiled pattern (whether it is anchored, has a fixed first character, and -so on). It does this by calling pcre_fullinfo() after compiling a -pattern. If the pattern is studied, the results of that are also output. -

-

-The /D modifier is a PCRE debugging feature, and is equivalent to -/BI, that is, both the /B and the /I modifiers. -

-

-The /F modifier causes pcretest to flip the byte order of the -fields in the compiled pattern that contain 2-byte and 4-byte numbers. This -facility is for testing the feature in PCRE that allows it to execute patterns -that were compiled on a host with a different endianness. This feature is not -available when the POSIX interface to PCRE is being used, that is, when the -/P pattern modifier is specified. See also the section about saving and -reloading compiled patterns below. -

-

-The /S modifier causes pcre_study() to be called after the -expression has been compiled, and the results used when the expression is -matched. -

-

-The /M modifier causes the size of memory block used to hold the compiled -pattern to be output. -

-

-The /P modifier causes pcretest to call PCRE via the POSIX wrapper -API rather than its native API. When this is done, all other modifiers except -/i, /m, and /+ are ignored. REG_ICASE is set if /i is -present, and REG_NEWLINE is set if /m is present. The wrapper functions -force PCRE_DOLLAR_ENDONLY always, and PCRE_DOTALL unless REG_NEWLINE is set. -

-

-The /8 modifier causes pcretest to call PCRE with the PCRE_UTF8 -option set. This turns on support for UTF-8 character handling in PCRE, -provided that it was compiled with this support enabled. This modifier also -causes any non-printing characters in output strings to be printed using the -\x{hh...} notation if they are valid UTF-8 sequences. -

-

-If the /? modifier is used with /8, it causes pcretest to -call pcre_compile() with the PCRE_NO_UTF8_CHECK option, to suppress the -checking of the string for UTF-8 validity. -

-
DATA LINES
-

-Before each data line is passed to pcre_exec(), leading and trailing -whitespace is removed, and it is then scanned for \ escapes. Some of these are -pretty esoteric features, intended for checking out some of the more -complicated features of PCRE. If you are just testing "ordinary" regular -expressions, you probably don't need any of these. The following escapes are -recognized: -

-  \a         alarm (BEL, \x07)
-  \b         backspace (\x08)
-  \e         escape (\x27)
-  \f         formfeed (\x0c)
-  \n         newline (\x0a)
-  \qdd       set the PCRE_MATCH_LIMIT limit to dd (any number of digits)
-  \r         carriage return (\x0d)
-  \t         tab (\x09)
-  \v         vertical tab (\x0b)
-  \nnn       octal character (up to 3 octal digits)
-  \xhh       hexadecimal character (up to 2 hex digits)
-  \x{hh...}  hexadecimal character, any number of digits in UTF-8 mode
-  \A         pass the PCRE_ANCHORED option to pcre_exec() or pcre_dfa_exec()
-  \B         pass the PCRE_NOTBOL option to pcre_exec() or pcre_dfa_exec()
-  \Cdd       call pcre_copy_substring() for substring dd after a successful match (number less than 32)
-  \Cname     call pcre_copy_named_substring() for substring "name" after a successful match (name termin-
-               ated by next non alphanumeric character)
-  \C+        show the current captured substrings at callout time
-  \C-        do not supply a callout function
-  \C!n       return 1 instead of 0 when callout number n is reached
-  \C!n!m     return 1 instead of 0 when callout number n is reached for the nth time
-  \C*n       pass the number n (may be negative) as callout data; this is used as the callout return value
-  \D         use the pcre_dfa_exec() match function
-  \F         only shortest match for pcre_dfa_exec()
-  \Gdd       call pcre_get_substring() for substring dd after a successful match (number less than 32)
-  \Gname     call pcre_get_named_substring() for substring "name" after a successful match (name termin-
-               ated by next non-alphanumeric character)
-  \L         call pcre_get_substringlist() after a successful match
-  \M         discover the minimum MATCH_LIMIT and MATCH_LIMIT_RECURSION settings
-  \N         pass the PCRE_NOTEMPTY option to pcre_exec() or pcre_dfa_exec()
-  \Odd       set the size of the output vector passed to pcre_exec() to dd (any number of digits)
-  \P         pass the PCRE_PARTIAL option to pcre_exec() or pcre_dfa_exec()
-  \Qdd       set the PCRE_MATCH_LIMIT_RECURSION limit to dd (any number of digits)
-  \R         pass the PCRE_DFA_RESTART option to pcre_dfa_exec()
-  \S         output details of memory get/free calls during matching
-  \Z         pass the PCRE_NOTEOL option to pcre_exec() or pcre_dfa_exec()
-  \?         pass the PCRE_NO_UTF8_CHECK option to pcre_exec() or pcre_dfa_exec()
-  \>dd       start the match at offset dd (any number of digits);
-               this sets the startoffset argument for pcre_exec() or pcre_dfa_exec()
-  \<cr>      pass the PCRE_NEWLINE_CR option to pcre_exec() or pcre_dfa_exec()
-  \<lf>      pass the PCRE_NEWLINE_LF option to pcre_exec() or pcre_dfa_exec()
-  \<crlf>    pass the PCRE_NEWLINE_CRLF option to pcre_exec() or pcre_dfa_exec()
-  \<anycrlf> pass the PCRE_NEWLINE_ANYCRLF option to pcre_exec() or pcre_dfa_exec()
-  \<any>     pass the PCRE_NEWLINE_ANY option to pcre_exec() or pcre_dfa_exec()
-
-The escapes that specify line ending sequences are literal strings, exactly as -shown. No more than one newline setting should be present in any data line. -

-

-A backslash followed by anything else just escapes the anything else. If -the very last character is a backslash, it is ignored. This gives a way of -passing an empty line as data, since a real empty line terminates the data -input. -

-

-If \M is present, pcretest calls pcre_exec() several times, with -different values in the match_limit and match_limit_recursion -fields of the pcre_extra data structure, until it finds the minimum -numbers for each parameter that allow pcre_exec() to complete. The -match_limit number is a measure of the amount of backtracking that takes -place, and checking it out can be instructive. For most simple matches, the -number is quite small, but for patterns with very large numbers of matching -possibilities, it can become large very quickly with increasing length of -subject string. The match_limit_recursion number is a measure of how much -stack (or, if PCRE is compiled with NO_RECURSE, how much heap) memory is needed -to complete the match attempt. -

-

-When \O is used, the value specified may be higher or lower than the size set -by the -O command line option (or defaulted to 45); \O applies only to -the call of pcre_exec() for the line in which it appears. -

-

-If the /P modifier was present on the pattern, causing the POSIX wrapper -API to be used, the only option-setting sequences that have any effect are \B -and \Z, causing REG_NOTBOL and REG_NOTEOL, respectively, to be passed to -regexec(). -

-

-The use of \x{hh...} to represent UTF-8 characters is not dependent on the use -of the /8 modifier on the pattern. It is recognized always. There may be -any number of hexadecimal digits inside the braces. The result is from one to -six bytes, encoded according to the original UTF-8 rules of RFC 2279. This -allows for values in the range 0 to 0x7FFFFFFF. Note that not all of those are -valid Unicode code points, or indeed valid UTF-8 characters according to the -later rules in RFC 3629. -

-
THE ALTERNATIVE MATCHING FUNCTION
-

-By default, pcretest uses the standard PCRE matching function, -pcre_exec() to match each data line. From release 6.0, PCRE supports an -alternative matching function, pcre_dfa_test(), which operates in a -different way, and has some restrictions. The differences between the two -functions are described in the -pcrematching -documentation. -

-

-If a data line contains the \D escape sequence, or if the command line -contains the -dfa option, the alternative matching function is called. -This function finds all possible matches at a given point. If, however, the \F -escape sequence is present in the data line, it stops after the first match is -found. This is always the shortest possible match. -

-
DEFAULT OUTPUT FROM PCRETEST
-

-This section describes the output when the normal matching function, -pcre_exec(), is being used. -

-

-When a match succeeds, pcretest outputs the list of captured substrings that -pcre_exec() returns, starting with number 0 for the string that matched -the whole pattern. Otherwise, it outputs "No match" or "Partial match" -when pcre_exec() returns PCRE_ERROR_NOMATCH or PCRE_ERROR_PARTIAL, -respectively, and otherwise the PCRE negative error number. Here is an example -of an interactive pcretest run. -

-  $ pcretest
-  PCRE version 7.0 30-Nov-2006
-
-    re> /^abc(\d+)/
-  data> abc123
-   0: abc123
-   1: 123
-  data> xyz
-  No match
-
-Note that unset capturing substrings that are not followed by one that is set -are not returned by pcre_exec(), and are not shown by pcretest. In -the following example, there are two capturing substrings, but when the first -data line is matched, the second, unset substring is not shown. An "internal" -unset substring is shown as "<unset>", as for the second data line. -
-    re> /(a)|(b)/
-  data> a
-   0: a
-   1: a
-  data> b
-   0: b
-   1: <unset>
-   2: b
-
-If the strings contain any non-printing characters, they are output as \0x -escapes, or as \x{...} escapes if the /8 modifier was present on the -pattern. See below for the definition of non-printing characters. If the -pattern has the /+ modifier, the output for substring 0 is followed by -the the rest of the subject string, identified by "0+" like this: -
-    re> /cat/+
-  data> cataract
-   0: cat
-   0+ aract
-
-If the pattern has the /g or /G modifier, the results of successive -matching attempts are output in sequence, like this: -
-    re> /\Bi(\w\w)/g
-  data> Mississippi
-   0: iss
-   1: ss
-   0: iss
-   1: ss
-   0: ipp
-   1: pp
-
-"No match" is output only if the first match attempt fails. -

-

-If any of the sequences \C, \G, or \L are present in a -data line that is successfully matched, the substrings extracted by the -convenience functions are output with C, G, or L after the string number -instead of a colon. This is in addition to the normal full list. The string -length (that is, the return from the extraction function) is given in -parentheses after each string for \C and \G. -

-

-Note that whereas patterns can be continued over several lines (a plain ">" -prompt is used for continuations), data lines may not. However newlines can be -included in data by means of the \n escape (or \r, \r\n, etc., depending on -the newline sequence setting). -

-
OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION
-

-When the alternative matching function, pcre_dfa_exec(), is used (by -means of the \D escape sequence or the -dfa command line option), the -output consists of a list of all the matches that start at the first point in -the subject where there is at least one match. For example: -

-    re> /(tang|tangerine|tan)/
-  data> yellow tangerine\D
-   0: tangerine
-   1: tang
-   2: tan
-
-(Using the normal matching function on this data finds only "tang".) The -longest matching string is always given first (and numbered zero). -

-

-If /g is present on the pattern, the search for further matches resumes -at the end of the longest match. For example: -

-    re> /(tang|tangerine|tan)/g
-  data> yellow tangerine and tangy sultana\D
-   0: tangerine
-   1: tang
-   2: tan
-   0: tang
-   1: tan
-   0: tan
-
-Since the matching function does not support substring capture, the escape -sequences that are concerned with captured substrings are not relevant. -

-
RESTARTING AFTER A PARTIAL MATCH
-

-When the alternative matching function has given the PCRE_ERROR_PARTIAL return, -indicating that the subject partially matched the pattern, you can restart the -match with additional subject data by means of the \R escape sequence. For -example: -

-    re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/
-  data> 23ja\P\D
-  Partial match: 23ja
-  data> n05\R\D
-   0: n05
-
-For further information about partial matching, see the -pcrepartial -documentation. -

-
CALLOUTS
-

-If the pattern contains any callout requests, pcretest's callout function -is called during matching. This works with both matching functions. By default, -the called function displays the callout number, the start and current -positions in the text at the callout time, and the next pattern item to be -tested. For example, the output -

-  --->pqrabcdef
-    0    ^  ^     \d
-
-indicates that callout number 0 occurred for a match attempt starting at the -fourth character of the subject string, when the pointer was at the seventh -character of the data, and when the next pattern item was \d. Just one -circumflex is output if the start and current positions are the same. -

-

-Callouts numbered 255 are assumed to be automatic callouts, inserted as a -result of the /C pattern modifier. In this case, instead of showing the -callout number, the offset in the pattern, preceded by a plus, is output. For -example: -

-    re> /\d?[A-E]\*/C
-  data> E*
-  --->E*
-   +0 ^      \d?
-   +3 ^      [A-E]
-   +8 ^^     \*
-  +10 ^ ^
-   0: E*
-
-The callout function in pcretest returns zero (carry on matching) by -default, but you can use a \C item in a data line (as described above) to -change this. -

-

-Inserting callouts can be helpful when using pcretest to check -complicated regular expressions. For further information about callouts, see -the -pcrecallout -documentation. -

-
NON-PRINTING CHARACTERS
-

-When pcretest is outputting text in the compiled version of a pattern, -bytes other than 32-126 are always treated as non-printing characters are are -therefore shown as hex escapes. -

-

-When pcretest is outputting text that is a matched part of a subject -string, it behaves in the same way, unless a different locale has been set for -the pattern (using the /L modifier). In this case, the isprint() -function to distinguish printing and non-printing characters. -

-
SAVING AND RELOADING COMPILED PATTERNS
-

-The facilities described in this section are not available when the POSIX -inteface to PCRE is being used, that is, when the /P pattern modifier is -specified. -

-

-When the POSIX interface is not in use, you can cause pcretest to write a -compiled pattern to a file, by following the modifiers with > and a file name. -For example: -

-  /pattern/im >/some/file
-
-See the -pcreprecompile -documentation for a discussion about saving and re-using compiled patterns. -

-

-The data that is written is binary. The first eight bytes are the length of the -compiled pattern data followed by the length of the optional study data, each -written as four bytes in big-endian order (most significant byte first). If -there is no study data (either the pattern was not studied, or studying did not -return any data), the second length is zero. The lengths are followed by an -exact copy of the compiled pattern. If there is additional study data, this -follows immediately after the compiled pattern. After writing the file, -pcretest expects to read a new pattern. -

-

-A saved pattern can be reloaded into pcretest by specifing < and a file -name instead of a pattern. The name of the file must not contain a < character, -as otherwise pcretest will interpret the line as a pattern delimited by < -characters. -For example: -

-   re> </some/file
-  Compiled regex loaded from /some/file
-  No study data
-
-When the pattern has been loaded, pcretest proceeds to read data lines in -the usual way. -

-

-You can copy a file written by pcretest to a different host and reload it -there, even if the new host has opposite endianness to the one on which the -pattern was compiled. For example, you can compile on an i86 machine and run on -a SPARC machine. -

-

-File names for saving and reloading can be absolute or relative, but note that -the shell facility of expanding a file name that starts with a tilde (~) is not -available. -

-

-The ability to save and reload files in pcretest is intended for testing -and experimentation. It is not intended for production use because only a -single pattern can be written to a file. Furthermore, there is no facility for -supplying custom character tables for use with a reloaded pattern. If the -original pattern was compiled with custom tables, an attempt to match a subject -string using a reloaded pattern is likely to cause pcretest to crash. -Finally, if you attempt to load a file that is not in the correct format, the -result is undefined. -

-
SEE ALSO
-

-pcre(3), pcreapi(3), pcrecallout(3), pcrematching(3), -pcrepartial(d), pcrepattern(3), pcreprecompile(3). -

-
AUTHOR
-

-Philip Hazel -
-University Computing Service -
-Cambridge CB2 3QH, England. -
-

-
REVISION
-

-Last updated: 10 March 2009 -
-Copyright © 1997-2009 University of Cambridge. -
-

-Return to the PCRE index page. -

diff --git a/libs/pcre/doc/index.html.src b/libs/pcre/doc/index.html.src deleted file mode 100644 index 888471ff75..0000000000 --- a/libs/pcre/doc/index.html.src +++ /dev/null @@ -1,140 +0,0 @@ - - - -PCRE specification - - -

Perl-compatible Regular Expressions (PCRE)

-

-The HTML documentation for PCRE comprises the following pages: -

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
pcre  Introductory page
pcre-config  Information about the installation configuration
pcreapi  PCRE's native API
pcrebuild  Options for building PCRE
pcrecallout  The callout facility
pcrecompat  Compability with Perl
pcrecpp  The C++ wrapper for the PCRE library
pcregrep  The pcregrep command
pcrematching  Discussion of the two matching algorithms
pcrepartial  Using PCRE for partial matching
pcrepattern  Specification of the regular expressions supported by PCRE
pcreperform  Some comments on performance
pcreposix  The POSIX API to the PCRE library
pcreprecompile  How to save and re-use compiled patterns
pcresample  Description of the sample program
pcrestack  Discussion of PCRE's stack usage
pcresyntax  Syntax quick-reference summary
pcretest  The pcretest command for testing PCRE
- -

-There are also individual pages that summarize the interface for each function -in the library: -

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
pcre_compile  Compile a regular expression
pcre_compile2  Compile a regular expression (alternate interface)
pcre_config  Show build-time configuration options
pcre_copy_named_substring  Extract named substring into given buffer
pcre_copy_substring  Extract numbered substring into given buffer
pcre_dfa_exec  Match a compiled pattern to a subject string - (DFA algorithm; not Perl compatible)
pcre_exec  Match a compiled pattern to a subject string - (Perl compatible)
pcre_free_substring  Free extracted substring
pcre_free_substring_list  Free list of extracted substrings
pcre_fullinfo  Extract information about a pattern
pcre_get_named_substring  Extract named substring into new memory
pcre_get_stringnumber  Convert captured string name to number
pcre_get_substring  Extract numbered substring into new memory
pcre_get_substring_list  Extract all substrings into new memory
pcre_info  Obsolete information extraction function
pcre_maketables  Build character tables in current locale
pcre_refcount  Maintain reference count in compiled pattern
pcre_study  Study a compiled pattern
pcre_version  Return PCRE version and release date
- - diff --git a/libs/pcre/doc/pcre-config.1 b/libs/pcre/doc/pcre-config.1 deleted file mode 100644 index afbd3a0182..0000000000 --- a/libs/pcre/doc/pcre-config.1 +++ /dev/null @@ -1,73 +0,0 @@ -.TH PCRE-CONFIG 1 -.SH NAME -pcre-config - program to return PCRE configuration -.SH SYNOPSIS -.rs -.sp -.B pcre-config [--prefix] [--exec-prefix] [--version] [--libs] -.ti +5n -.B [--libs-posix] [--cflags] [--cflags-posix] -. -. -.SH DESCRIPTION -.rs -.sp -\fBpcre-config\fP returns the configuration of the installed PCRE -libraries and the options required to compile a program to use them. -. -. -.SH OPTIONS -.rs -.TP 10 -\fB--prefix\fP -Writes the directory prefix used in the PCRE installation for architecture -independent files (\fI/usr\fP on many systems, \fI/usr/local\fP on some -systems) to the standard output. -.TP 10 -\fB--exec-prefix\fP -Writes the directory prefix used in the PCRE installation for architecture -dependent files (normally the same as \fB--prefix\fP) to the standard output. -.TP 10 -\fB--version\fP -Writes the version number of the installed PCRE libraries to the standard -output. -.TP 10 -\fB--libs\fP -Writes to the standard output the command line options required to link -with PCRE (\fB-lpcre\fP on many systems). -.TP 10 -\fB--libs-posix\fP -Writes to the standard output the command line options required to link with -the PCRE posix emulation library (\fB-lpcreposix\fP \fB-lpcre\fP on many -systems). -.TP 10 -\fB--cflags\fP -Writes to the standard output the command line options required to compile -files that use PCRE (this may include some \fB-I\fP options, but is blank on -many systems). -.TP 10 -\fB--cflags-posix\fP -Writes to the standard output the command line options required to compile -files that use the PCRE posix emulation library (this may include some \fB-I\fP -options, but is blank on many systems). -. -. -.SH "SEE ALSO" -.rs -.sp -\fBpcre(3)\fP -. -. -.SH AUTHOR -.rs -.sp -This manual page was originally written by Mark Baker for the Debian GNU/Linux -system. It has been slightly revised as a generic PCRE man page. -. -. -.SH REVISION -.rs -.sp -.nf -Last updated: 18 April 2007 -.fi diff --git a/libs/pcre/doc/pcre-config.txt b/libs/pcre/doc/pcre-config.txt deleted file mode 100644 index c979d455e8..0000000000 --- a/libs/pcre/doc/pcre-config.txt +++ /dev/null @@ -1,67 +0,0 @@ -PCRE-CONFIG(1) PCRE-CONFIG(1) - - - -NAME - pcre-config - program to return PCRE configuration - -SYNOPSIS - - pcre-config [--prefix] [--exec-prefix] [--version] [--libs] - [--libs-posix] [--cflags] [--cflags-posix] - - -DESCRIPTION - - pcre-config returns the configuration of the installed PCRE libraries - and the options required to compile a program to use them. - - -OPTIONS - - --prefix Writes the directory prefix used in the PCRE installation for - architecture independent files (/usr on many systems, - /usr/local on some systems) to the standard output. - - --exec-prefix - Writes the directory prefix used in the PCRE installation for - architecture dependent files (normally the same as --prefix) - to the standard output. - - --version Writes the version number of the installed PCRE libraries to - the standard output. - - --libs Writes to the standard output the command line options - required to link with PCRE (-lpcre on many systems). - - --libs-posix - Writes to the standard output the command line options - required to link with the PCRE posix emulation library - (-lpcreposix -lpcre on many systems). - - --cflags Writes to the standard output the command line options - required to compile files that use PCRE (this may include - some -I options, but is blank on many systems). - - --cflags-posix - Writes to the standard output the command line options - required to compile files that use the PCRE posix emulation - library (this may include some -I options, but is blank on - many systems). - - -SEE ALSO - - pcre(3) - - -AUTHOR - - This manual page was originally written by Mark Baker for the Debian - GNU/Linux system. It has been slightly revised as a generic PCRE man - page. - - -REVISION - - Last updated: 18 April 2007 diff --git a/libs/pcre/doc/pcre.3 b/libs/pcre/doc/pcre.3 deleted file mode 100644 index 6f174adf1e..0000000000 --- a/libs/pcre/doc/pcre.3 +++ /dev/null @@ -1,296 +0,0 @@ -.TH PCRE 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH INTRODUCTION -.rs -.sp -The PCRE library is a set of functions that implement regular expression -pattern matching using the same syntax and semantics as Perl, with just a few -differences. Certain features that appeared in Python and PCRE before they -appeared in Perl are also available using the Python syntax. There is also some -support for certain .NET and Oniguruma syntax items, and there is an option for -requesting some minor changes that give better JavaScript compatibility. -.P -The current implementation of PCRE (release 7.x) corresponds approximately with -Perl 5.10, including support for UTF-8 encoded strings and Unicode general -category properties. However, UTF-8 and Unicode support has to be explicitly -enabled; it is not the default. The Unicode tables correspond to Unicode -release 5.1. -.P -In addition to the Perl-compatible matching function, PCRE contains an -alternative matching function that matches the same compiled patterns in a -different way. In certain circumstances, the alternative function has some -advantages. For a discussion of the two matching algorithms, see the -.\" HREF -\fBpcrematching\fP -.\" -page. -.P -PCRE is written in C and released as a C library. A number of people have -written wrappers and interfaces of various kinds. In particular, Google Inc. -have provided a comprehensive C++ wrapper. This is now included as part of the -PCRE distribution. The -.\" HREF -\fBpcrecpp\fP -.\" -page has details of this interface. Other people's contributions can be found -in the \fIContrib\fR directory at the primary FTP site, which is: -.sp -.\" HTML -.\" -ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre -.P -Details of exactly which Perl regular expression features are and are not -supported by PCRE are given in separate documents. See the -.\" HREF -\fBpcrepattern\fR -.\" -and -.\" HREF -\fBpcrecompat\fR -.\" -pages. There is a syntax summary in the -.\" HREF -\fBpcresyntax\fR -.\" -page. -.P -Some features of PCRE can be included, excluded, or changed when the library is -built. The -.\" HREF -\fBpcre_config()\fR -.\" -function makes it possible for a client to discover which features are -available. The features themselves are described in the -.\" HREF -\fBpcrebuild\fP -.\" -page. Documentation about building PCRE for various operating systems can be -found in the \fBREADME\fP file in the source distribution. -.P -The library contains a number of undocumented internal functions and data -tables that are used by more than one of the exported external functions, but -which are not intended for use by external callers. Their names all begin with -"_pcre_", which hopefully will not provoke any name clashes. In some -environments, it is possible to control which external symbols are exported -when a shared library is built, and in these cases the undocumented symbols are -not exported. -. -. -.SH "USER DOCUMENTATION" -.rs -.sp -The user documentation for PCRE comprises a number of different sections. In -the "man" format, each of these is a separate "man page". In the HTML format, -each is a separate page, linked from the index page. In the plain text format, -all the sections are concatenated, for ease of searching. The sections are as -follows: -.sp - pcre this document - pcre-config show PCRE installation configuration information - pcreapi details of PCRE's native C API - pcrebuild options for building PCRE - pcrecallout details of the callout feature - pcrecompat discussion of Perl compatibility - pcrecpp details of the C++ wrapper - pcregrep description of the \fBpcregrep\fP command - pcrematching discussion of the two matching algorithms - pcrepartial details of the partial matching facility -.\" JOIN - pcrepattern syntax and semantics of supported - regular expressions - pcresyntax quick syntax reference - pcreperform discussion of performance issues - pcreposix the POSIX-compatible C API - pcreprecompile details of saving and re-using precompiled patterns - pcresample discussion of the sample program - pcrestack discussion of stack usage - pcretest description of the \fBpcretest\fP testing command -.sp -In addition, in the "man" and HTML formats, there is a short page for each -C library function, listing its arguments and results. -. -. -.SH LIMITATIONS -.rs -.sp -There are some size limitations in PCRE but it is hoped that they will never in -practice be relevant. -.P -The maximum length of a compiled pattern is 65539 (sic) bytes if PCRE is -compiled with the default internal linkage size of 2. If you want to process -regular expressions that are truly enormous, you can compile PCRE with an -internal linkage size of 3 or 4 (see the \fBREADME\fP file in the source -distribution and the -.\" HREF -\fBpcrebuild\fP -.\" -documentation for details). In these cases the limit is substantially larger. -However, the speed of execution is slower. -.P -All values in repeating quantifiers must be less than 65536. -.P -There is no limit to the number of parenthesized subpatterns, but there can be -no more than 65535 capturing subpatterns. -.P -The maximum length of name for a named subpattern is 32 characters, and the -maximum number of named subpatterns is 10000. -.P -The maximum length of a subject string is the largest positive number that an -integer variable can hold. However, when using the traditional matching -function, PCRE uses recursion to handle subpatterns and indefinite repetition. -This means that the available stack space may limit the size of a subject -string that can be processed by certain patterns. For a discussion of stack -issues, see the -.\" HREF -\fBpcrestack\fP -.\" -documentation. -. -.\" HTML -. -. -.SH "UTF-8 AND UNICODE PROPERTY SUPPORT" -.rs -.sp -From release 3.3, PCRE has had some support for character strings encoded in -the UTF-8 format. For release 4.0 this was greatly extended to cover most -common requirements, and in release 5.0 additional support for Unicode general -category properties was added. -.P -In order process UTF-8 strings, you must build PCRE to include UTF-8 support in -the code, and, in addition, you must call -.\" HREF -\fBpcre_compile()\fP -.\" -with the PCRE_UTF8 option flag, or the pattern must start with the sequence -(*UTF8). When either of these is the case, both the pattern and any subject -strings that are matched against it are treated as UTF-8 strings instead of -just strings of bytes. -.P -If you compile PCRE with UTF-8 support, but do not use it at run time, the -library will be a bit bigger, but the additional run time overhead is limited -to testing the PCRE_UTF8 flag occasionally, so should not be very big. -.P -If PCRE is built with Unicode character property support (which implies UTF-8 -support), the escape sequences \ep{..}, \eP{..}, and \eX are supported. -The available properties that can be tested are limited to the general -category properties such as Lu for an upper case letter or Nd for a decimal -number, the Unicode script names such as Arabic or Han, and the derived -properties Any and L&. A full list is given in the -.\" HREF -\fBpcrepattern\fP -.\" -documentation. Only the short names for properties are supported. For example, -\ep{L} matches a letter. Its Perl synonym, \ep{Letter}, is not supported. -Furthermore, in Perl, many properties may optionally be prefixed by "Is", for -compatibility with Perl 5.6. PCRE does not support this. -. -.\" HTML -. -.SS "Validity of UTF-8 strings" -.rs -.sp -When you set the PCRE_UTF8 flag, the strings passed as patterns and subjects -are (by default) checked for validity on entry to the relevant functions. From -release 7.3 of PCRE, the check is according the rules of RFC 3629, which are -themselves derived from the Unicode specification. Earlier releases of PCRE -followed the rules of RFC 2279, which allows the full range of 31-bit values (0 -to 0x7FFFFFFF). The current check allows only values in the range U+0 to -U+10FFFF, excluding U+D800 to U+DFFF. -.P -The excluded code points are the "Low Surrogate Area" of Unicode, of which the -Unicode Standard says this: "The Low Surrogate Area does not contain any -character assignments, consequently no character code charts or namelists are -provided for this area. Surrogates are reserved for use with UTF-16 and then -must be used in pairs." The code points that are encoded by UTF-16 pairs are -available as independent code points in the UTF-8 encoding. (In other words, -the whole surrogate thing is a fudge for UTF-16 which unfortunately messes up -UTF-8.) -.P -If an invalid UTF-8 string is passed to PCRE, an error return -(PCRE_ERROR_BADUTF8) is given. In some situations, you may already know that -your strings are valid, and therefore want to skip these checks in order to -improve performance. If you set the PCRE_NO_UTF8_CHECK flag at compile time or -at run time, PCRE assumes that the pattern or subject it is given -(respectively) contains only valid UTF-8 codes. In this case, it does not -diagnose an invalid UTF-8 string. -.P -If you pass an invalid UTF-8 string when PCRE_NO_UTF8_CHECK is set, what -happens depends on why the string is invalid. If the string conforms to the -"old" definition of UTF-8 (RFC 2279), it is processed as a string of characters -in the range 0 to 0x7FFFFFFF. In other words, apart from the initial validity -test, PCRE (when in UTF-8 mode) handles strings according to the more liberal -rules of RFC 2279. However, if the string does not even conform to RFC 2279, -the result is undefined. Your program may crash. -.P -If you want to process strings of values in the full range 0 to 0x7FFFFFFF, -encoded in a UTF-8-like manner as per the old RFC, you can set -PCRE_NO_UTF8_CHECK to bypass the more restrictive test. However, in this -situation, you will have to apply your own validity check. -. -.SS "General comments about UTF-8 mode" -.rs -.sp -1. An unbraced hexadecimal escape sequence (such as \exb3) matches a two-byte -UTF-8 character if the value is greater than 127. -.P -2. Octal numbers up to \e777 are recognized, and match two-byte UTF-8 -characters for values greater than \e177. -.P -3. Repeat quantifiers apply to complete UTF-8 characters, not to individual -bytes, for example: \ex{100}{3}. -.P -4. The dot metacharacter matches one UTF-8 character instead of a single byte. -.P -5. The escape sequence \eC can be used to match a single byte in UTF-8 mode, -but its use can lead to some strange effects. This facility is not available in -the alternative matching function, \fBpcre_dfa_exec()\fP. -.P -6. The character escapes \eb, \eB, \ed, \eD, \es, \eS, \ew, and \eW correctly -test characters of any code value, but the characters that PCRE recognizes as -digits, spaces, or word characters remain the same set as before, all with -values less than 256. This remains true even when PCRE includes Unicode -property support, because to do otherwise would slow down PCRE in many common -cases. If you really want to test for a wider sense of, say, "digit", you -must use Unicode property tests such as \ep{Nd}. Note that this also applies to -\eb, because it is defined in terms of \ew and \eW. -.P -7. Similarly, characters that match the POSIX named character classes are all -low-valued characters. -.P -8. However, the Perl 5.10 horizontal and vertical whitespace matching escapes -(\eh, \eH, \ev, and \eV) do match all the appropriate Unicode characters. -.P -9. Case-insensitive matching applies only to characters whose values are less -than 128, unless PCRE is built with Unicode property support. Even when Unicode -property support is available, PCRE still uses its own character tables when -checking the case of low-valued characters, so as not to degrade performance. -The Unicode property information is used only for characters with higher -values. Even when Unicode property support is available, PCRE supports -case-insensitive matching only when there is a one-to-one mapping between a -letter's cases. There are a small number of many-to-one mappings in Unicode; -these are not supported by PCRE. -. -. -.SH AUTHOR -.rs -.sp -.nf -Philip Hazel -University Computing Service -Cambridge CB2 3QH, England. -.fi -.P -Putting an actual email address here seems to have been a spam magnet, so I've -taken it away. If you want to email me, use my two initials, followed by the -two digits 10, at the domain cam.ac.uk. -. -. -.SH REVISION -.rs -.sp -.nf -Last updated: 11 April 2009 -Copyright (c) 1997-2009 University of Cambridge. -.fi diff --git a/libs/pcre/doc/pcre.txt b/libs/pcre/doc/pcre.txt deleted file mode 100644 index 9a2ce31598..0000000000 --- a/libs/pcre/doc/pcre.txt +++ /dev/null @@ -1,6680 +0,0 @@ ------------------------------------------------------------------------------ -This file contains a concatenation of the PCRE man pages, converted to plain -text format for ease of searching with a text editor, or for use on systems -that do not have a man page processor. The small individual files that give -synopses of each function in the library have not been included. There are -separate text files for the pcregrep and pcretest commands. ------------------------------------------------------------------------------ - - -PCRE(3) PCRE(3) - - -NAME - PCRE - Perl-compatible regular expressions - - -INTRODUCTION - - The PCRE library is a set of functions that implement regular expres- - sion pattern matching using the same syntax and semantics as Perl, with - just a few differences. Certain features that appeared in Python and - PCRE before they appeared in Perl are also available using the Python - syntax. There is also some support for certain .NET and Oniguruma syn- - tax items, and there is an option for requesting some minor changes - that give better JavaScript compatibility. - - The current implementation of PCRE (release 7.x) corresponds approxi- - mately with Perl 5.10, including support for UTF-8 encoded strings and - Unicode general category properties. However, UTF-8 and Unicode support - has to be explicitly enabled; it is not the default. The Unicode tables - correspond to Unicode release 5.1. - - In addition to the Perl-compatible matching function, PCRE contains an - alternative matching function that matches the same compiled patterns - in a different way. In certain circumstances, the alternative function - has some advantages. For a discussion of the two matching algorithms, - see the pcrematching page. - - PCRE is written in C and released as a C library. A number of people - have written wrappers and interfaces of various kinds. In particular, - Google Inc. have provided a comprehensive C++ wrapper. This is now - included as part of the PCRE distribution. The pcrecpp page has details - of this interface. Other people's contributions can be found in the - Contrib directory at the primary FTP site, which is: - - ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre - - Details of exactly which Perl regular expression features are and are - not supported by PCRE are given in separate documents. See the pcrepat- - tern and pcrecompat pages. There is a syntax summary in the pcresyntax - page. - - Some features of PCRE can be included, excluded, or changed when the - library is built. The pcre_config() function makes it possible for a - client to discover which features are available. The features them- - selves are described in the pcrebuild page. Documentation about build- - ing PCRE for various operating systems can be found in the README file - in the source distribution. - - The library contains a number of undocumented internal functions and - data tables that are used by more than one of the exported external - functions, but which are not intended for use by external callers. - Their names all begin with "_pcre_", which hopefully will not provoke - any name clashes. In some environments, it is possible to control which - external symbols are exported when a shared library is built, and in - these cases the undocumented symbols are not exported. - - -USER DOCUMENTATION - - The user documentation for PCRE comprises a number of different sec- - tions. In the "man" format, each of these is a separate "man page". In - the HTML format, each is a separate page, linked from the index page. - In the plain text format, all the sections are concatenated, for ease - of searching. The sections are as follows: - - pcre this document - pcre-config show PCRE installation configuration information - pcreapi details of PCRE's native C API - pcrebuild options for building PCRE - pcrecallout details of the callout feature - pcrecompat discussion of Perl compatibility - pcrecpp details of the C++ wrapper - pcregrep description of the pcregrep command - pcrematching discussion of the two matching algorithms - pcrepartial details of the partial matching facility - pcrepattern syntax and semantics of supported - regular expressions - pcresyntax quick syntax reference - pcreperform discussion of performance issues - pcreposix the POSIX-compatible C API - pcreprecompile details of saving and re-using precompiled patterns - pcresample discussion of the sample program - pcrestack discussion of stack usage - pcretest description of the pcretest testing command - - In addition, in the "man" and HTML formats, there is a short page for - each C library function, listing its arguments and results. - - -LIMITATIONS - - There are some size limitations in PCRE but it is hoped that they will - never in practice be relevant. - - The maximum length of a compiled pattern is 65539 (sic) bytes if PCRE - is compiled with the default internal linkage size of 2. If you want to - process regular expressions that are truly enormous, you can compile - PCRE with an internal linkage size of 3 or 4 (see the README file in - the source distribution and the pcrebuild documentation for details). - In these cases the limit is substantially larger. However, the speed - of execution is slower. - - All values in repeating quantifiers must be less than 65536. - - There is no limit to the number of parenthesized subpatterns, but there - can be no more than 65535 capturing subpatterns. - - The maximum length of name for a named subpattern is 32 characters, and - the maximum number of named subpatterns is 10000. - - The maximum length of a subject string is the largest positive number - that an integer variable can hold. However, when using the traditional - matching function, PCRE uses recursion to handle subpatterns and indef- - inite repetition. This means that the available stack space may limit - the size of a subject string that can be processed by certain patterns. - For a discussion of stack issues, see the pcrestack documentation. - - -UTF-8 AND UNICODE PROPERTY SUPPORT - - From release 3.3, PCRE has had some support for character strings - encoded in the UTF-8 format. For release 4.0 this was greatly extended - to cover most common requirements, and in release 5.0 additional sup- - port for Unicode general category properties was added. - - In order process UTF-8 strings, you must build PCRE to include UTF-8 - support in the code, and, in addition, you must call pcre_compile() - with the PCRE_UTF8 option flag, or the pattern must start with the - sequence (*UTF8). When either of these is the case, both the pattern - and any subject strings that are matched against it are treated as - UTF-8 strings instead of just strings of bytes. - - If you compile PCRE with UTF-8 support, but do not use it at run time, - the library will be a bit bigger, but the additional run time overhead - is limited to testing the PCRE_UTF8 flag occasionally, so should not be - very big. - - If PCRE is built with Unicode character property support (which implies - UTF-8 support), the escape sequences \p{..}, \P{..}, and \X are sup- - ported. The available properties that can be tested are limited to the - general category properties such as Lu for an upper case letter or Nd - for a decimal number, the Unicode script names such as Arabic or Han, - and the derived properties Any and L&. A full list is given in the - pcrepattern documentation. Only the short names for properties are sup- - ported. For example, \p{L} matches a letter. Its Perl synonym, \p{Let- - ter}, is not supported. Furthermore, in Perl, many properties may - optionally be prefixed by "Is", for compatibility with Perl 5.6. PCRE - does not support this. - - Validity of UTF-8 strings - - When you set the PCRE_UTF8 flag, the strings passed as patterns and - subjects are (by default) checked for validity on entry to the relevant - functions. From release 7.3 of PCRE, the check is according the rules - of RFC 3629, which are themselves derived from the Unicode specifica- - tion. Earlier releases of PCRE followed the rules of RFC 2279, which - allows the full range of 31-bit values (0 to 0x7FFFFFFF). The current - check allows only values in the range U+0 to U+10FFFF, excluding U+D800 - to U+DFFF. - - The excluded code points are the "Low Surrogate Area" of Unicode, of - which the Unicode Standard says this: "The Low Surrogate Area does not - contain any character assignments, consequently no character code - charts or namelists are provided for this area. Surrogates are reserved - for use with UTF-16 and then must be used in pairs." The code points - that are encoded by UTF-16 pairs are available as independent code - points in the UTF-8 encoding. (In other words, the whole surrogate - thing is a fudge for UTF-16 which unfortunately messes up UTF-8.) - - If an invalid UTF-8 string is passed to PCRE, an error return - (PCRE_ERROR_BADUTF8) is given. In some situations, you may already know - that your strings are valid, and therefore want to skip these checks in - order to improve performance. If you set the PCRE_NO_UTF8_CHECK flag at - compile time or at run time, PCRE assumes that the pattern or subject - it is given (respectively) contains only valid UTF-8 codes. In this - case, it does not diagnose an invalid UTF-8 string. - - If you pass an invalid UTF-8 string when PCRE_NO_UTF8_CHECK is set, - what happens depends on why the string is invalid. If the string con- - forms to the "old" definition of UTF-8 (RFC 2279), it is processed as a - string of characters in the range 0 to 0x7FFFFFFF. In other words, - apart from the initial validity test, PCRE (when in UTF-8 mode) handles - strings according to the more liberal rules of RFC 2279. However, if - the string does not even conform to RFC 2279, the result is undefined. - Your program may crash. - - If you want to process strings of values in the full range 0 to - 0x7FFFFFFF, encoded in a UTF-8-like manner as per the old RFC, you can - set PCRE_NO_UTF8_CHECK to bypass the more restrictive test. However, in - this situation, you will have to apply your own validity check. - - General comments about UTF-8 mode - - 1. An unbraced hexadecimal escape sequence (such as \xb3) matches a - two-byte UTF-8 character if the value is greater than 127. - - 2. Octal numbers up to \777 are recognized, and match two-byte UTF-8 - characters for values greater than \177. - - 3. Repeat quantifiers apply to complete UTF-8 characters, not to indi- - vidual bytes, for example: \x{100}{3}. - - 4. The dot metacharacter matches one UTF-8 character instead of a sin- - gle byte. - - 5. The escape sequence \C can be used to match a single byte in UTF-8 - mode, but its use can lead to some strange effects. This facility is - not available in the alternative matching function, pcre_dfa_exec(). - - 6. The character escapes \b, \B, \d, \D, \s, \S, \w, and \W correctly - test characters of any code value, but the characters that PCRE recog- - nizes as digits, spaces, or word characters remain the same set as - before, all with values less than 256. This remains true even when PCRE - includes Unicode property support, because to do otherwise would slow - down PCRE in many common cases. If you really want to test for a wider - sense of, say, "digit", you must use Unicode property tests such as - \p{Nd}. Note that this also applies to \b, because it is defined in - terms of \w and \W. - - 7. Similarly, characters that match the POSIX named character classes - are all low-valued characters. - - 8. However, the Perl 5.10 horizontal and vertical whitespace matching - escapes (\h, \H, \v, and \V) do match all the appropriate Unicode char- - acters. - - 9. Case-insensitive matching applies only to characters whose values - are less than 128, unless PCRE is built with Unicode property support. - Even when Unicode property support is available, PCRE still uses its - own character tables when checking the case of low-valued characters, - so as not to degrade performance. The Unicode property information is - used only for characters with higher values. Even when Unicode property - support is available, PCRE supports case-insensitive matching only when - there is a one-to-one mapping between a letter's cases. There are a - small number of many-to-one mappings in Unicode; these are not sup- - ported by PCRE. - - -AUTHOR - - Philip Hazel - University Computing Service - Cambridge CB2 3QH, England. - - Putting an actual email address here seems to have been a spam magnet, - so I've taken it away. If you want to email me, use my two initials, - followed by the two digits 10, at the domain cam.ac.uk. - - -REVISION - - Last updated: 11 April 2009 - Copyright (c) 1997-2009 University of Cambridge. ------------------------------------------------------------------------------- - - -PCREBUILD(3) PCREBUILD(3) - - -NAME - PCRE - Perl-compatible regular expressions - - -PCRE BUILD-TIME OPTIONS - - This document describes the optional features of PCRE that can be - selected when the library is compiled. It assumes use of the configure - script, where the optional features are selected or deselected by pro- - viding options to configure before running the make command. However, - the same options can be selected in both Unix-like and non-Unix-like - environments using the GUI facility of CMakeSetup if you are using - CMake instead of configure to build PCRE. - - The complete list of options for configure (which includes the standard - ones such as the selection of the installation directory) can be - obtained by running - - ./configure --help - - The following sections include descriptions of options whose names - begin with --enable or --disable. These settings specify changes to the - defaults for the configure command. Because of the way that configure - works, --enable and --disable always come in pairs, so the complemen- - tary option always exists as well, but as it specifies the default, it - is not described. - - -C++ SUPPORT - - By default, the configure script will search for a C++ compiler and C++ - header files. If it finds them, it automatically builds the C++ wrapper - library for PCRE. You can disable this by adding - - --disable-cpp - - to the configure command. - - -UTF-8 SUPPORT - - To build PCRE with support for UTF-8 Unicode character strings, add - - --enable-utf8 - - to the configure command. Of itself, this does not make PCRE treat - strings as UTF-8. As well as compiling PCRE with this option, you also - have have to set the PCRE_UTF8 option when you call the pcre_compile() - function. - - If you set --enable-utf8 when compiling in an EBCDIC environment, PCRE - expects its input to be either ASCII or UTF-8 (depending on the runtime - option). It is not possible to support both EBCDIC and UTF-8 codes in - the same version of the library. Consequently, --enable-utf8 and - --enable-ebcdic are mutually exclusive. - - -UNICODE CHARACTER PROPERTY SUPPORT - - UTF-8 support allows PCRE to process character values greater than 255 - in the strings that it handles. On its own, however, it does not pro- - vide any facilities for accessing the properties of such characters. If - you want to be able to use the pattern escapes \P, \p, and \X, which - refer to Unicode character properties, you must add - - --enable-unicode-properties - - to the configure command. This implies UTF-8 support, even if you have - not explicitly requested it. - - Including Unicode property support adds around 30K of tables to the - PCRE library. Only the general category properties such as Lu and Nd - are supported. Details are given in the pcrepattern documentation. - - -CODE VALUE OF NEWLINE - - By default, PCRE interprets the linefeed (LF) character as indicating - the end of a line. This is the normal newline character on Unix-like - systems. You can compile PCRE to use carriage return (CR) instead, by - adding - - --enable-newline-is-cr - - to the configure command. There is also a --enable-newline-is-lf - option, which explicitly specifies linefeed as the newline character. - - Alternatively, you can specify that line endings are to be indicated by - the two character sequence CRLF. If you want this, add - - --enable-newline-is-crlf - - to the configure command. There is a fourth option, specified by - - --enable-newline-is-anycrlf - - which causes PCRE to recognize any of the three sequences CR, LF, or - CRLF as indicating a line ending. Finally, a fifth option, specified by - - --enable-newline-is-any - - causes PCRE to recognize any Unicode newline sequence. - - Whatever line ending convention is selected when PCRE is built can be - overridden when the library functions are called. At build time it is - conventional to use the standard for your operating system. - - -WHAT \R MATCHES - - By default, the sequence \R in a pattern matches any Unicode newline - sequence, whatever has been selected as the line ending sequence. If - you specify - - --enable-bsr-anycrlf - - the default is changed so that \R matches only CR, LF, or CRLF. What- - ever is selected when PCRE is built can be overridden when the library - functions are called. - - -BUILDING SHARED AND STATIC LIBRARIES - - The PCRE building process uses libtool to build both shared and static - Unix libraries by default. You can suppress one of these by adding one - of - - --disable-shared - --disable-static - - to the configure command, as required. - - -POSIX MALLOC USAGE - - When PCRE is called through the POSIX interface (see the pcreposix doc- - umentation), additional working storage is required for holding the - pointers to capturing substrings, because PCRE requires three integers - per substring, whereas the POSIX interface provides only two. If the - number of expected substrings is small, the wrapper function uses space - on the stack, because this is faster than using malloc() for each call. - The default threshold above which the stack is no longer used is 10; it - can be changed by adding a setting such as - - --with-posix-malloc-threshold=20 - - to the configure command. - - -HANDLING VERY LARGE PATTERNS - - Within a compiled pattern, offset values are used to point from one - part to another (for example, from an opening parenthesis to an alter- - nation metacharacter). By default, two-byte values are used for these - offsets, leading to a maximum size for a compiled pattern of around - 64K. This is sufficient to handle all but the most gigantic patterns. - Nevertheless, some people do want to process enormous patterns, so it - is possible to compile PCRE to use three-byte or four-byte offsets by - adding a setting such as - - --with-link-size=3 - - to the configure command. The value given must be 2, 3, or 4. Using - longer offsets slows down the operation of PCRE because it has to load - additional bytes when handling them. - - -AVOIDING EXCESSIVE STACK USAGE - - When matching with the pcre_exec() function, PCRE implements backtrack- - ing by making recursive calls to an internal function called match(). - In environments where the size of the stack is limited, this can se- - verely limit PCRE's operation. (The Unix environment does not usually - suffer from this problem, but it may sometimes be necessary to increase - the maximum stack size. There is a discussion in the pcrestack docu- - mentation.) An alternative approach to recursion that uses memory from - the heap to remember data, instead of using recursive function calls, - has been implemented to work round the problem of limited stack size. - If you want to build a version of PCRE that works this way, add - - --disable-stack-for-recursion - - to the configure command. With this configuration, PCRE will use the - pcre_stack_malloc and pcre_stack_free variables to call memory manage- - ment functions. By default these point to malloc() and free(), but you - can replace the pointers so that your own functions are used. - - Separate functions are provided rather than using pcre_malloc and - pcre_free because the usage is very predictable: the block sizes - requested are always the same, and the blocks are always freed in - reverse order. A calling program might be able to implement optimized - functions that perform better than malloc() and free(). PCRE runs - noticeably more slowly when built in this way. This option affects only - the pcre_exec() function; it is not relevant for the the - pcre_dfa_exec() function. - - -LIMITING PCRE RESOURCE USAGE - - Internally, PCRE has a function called match(), which it calls repeat- - edly (sometimes recursively) when matching a pattern with the - pcre_exec() function. By controlling the maximum number of times this - function may be called during a single matching operation, a limit can - be placed on the resources used by a single call to pcre_exec(). The - limit can be changed at run time, as described in the pcreapi documen- - tation. The default is 10 million, but this can be changed by adding a - setting such as - - --with-match-limit=500000 - - to the configure command. This setting has no effect on the - pcre_dfa_exec() matching function. - - In some environments it is desirable to limit the depth of recursive - calls of match() more strictly than the total number of calls, in order - to restrict the maximum amount of stack (or heap, if --disable-stack- - for-recursion is specified) that is used. A second limit controls this; - it defaults to the value that is set for --with-match-limit, which - imposes no additional constraints. However, you can set a lower limit - by adding, for example, - - --with-match-limit-recursion=10000 - - to the configure command. This value can also be overridden at run - time. - - -CREATING CHARACTER TABLES AT BUILD TIME - - PCRE uses fixed tables for processing characters whose code values are - less than 256. By default, PCRE is built with a set of tables that are - distributed in the file pcre_chartables.c.dist. These tables are for - ASCII codes only. If you add - - --enable-rebuild-chartables - - to the configure command, the distributed tables are no longer used. - Instead, a program called dftables is compiled and run. This outputs - the source for new set of tables, created in the default locale of your - C runtime system. (This method of replacing the tables does not work if - you are cross compiling, because dftables is run on the local host. If - you need to create alternative tables when cross compiling, you will - have to do so "by hand".) - - -USING EBCDIC CODE - - PCRE assumes by default that it will run in an environment where the - character code is ASCII (or Unicode, which is a superset of ASCII). - This is the case for most computer operating systems. PCRE can, how- - ever, be compiled to run in an EBCDIC environment by adding - - --enable-ebcdic - - to the configure command. This setting implies --enable-rebuild-charta- - bles. You should only use it if you know that you are in an EBCDIC - environment (for example, an IBM mainframe operating system). The - --enable-ebcdic option is incompatible with --enable-utf8. - - -PCREGREP OPTIONS FOR COMPRESSED FILE SUPPORT - - By default, pcregrep reads all files as plain text. You can build it so - that it recognizes files whose names end in .gz or .bz2, and reads them - with libz or libbz2, respectively, by adding one or both of - - --enable-pcregrep-libz - --enable-pcregrep-libbz2 - - to the configure command. These options naturally require that the rel- - evant libraries are installed on your system. Configuration will fail - if they are not. - - -PCRETEST OPTION FOR LIBREADLINE SUPPORT - - If you add - - --enable-pcretest-libreadline - - to the configure command, pcretest is linked with the libreadline - library, and when its input is from a terminal, it reads it using the - readline() function. This provides line-editing and history facilities. - Note that libreadline is GPL-licenced, so if you distribute a binary of - pcretest linked in this way, there may be licensing issues. - - Setting this option causes the -lreadline option to be added to the - pcretest build. In many operating environments with a sytem-installed - libreadline this is sufficient. However, in some environments (e.g. if - an unmodified distribution version of readline is in use), some extra - configuration may be necessary. The INSTALL file for libreadline says - this: - - "Readline uses the termcap functions, but does not link with the - termcap or curses library itself, allowing applications which link - with readline the to choose an appropriate library." - - If your environment has not been set up so that an appropriate library - is automatically included, you may need to add something like - - LIBS="-ncurses" - - immediately before the configure command. - - -SEE ALSO - - pcreapi(3), pcre_config(3). - - -AUTHOR - - Philip Hazel - University Computing Service - Cambridge CB2 3QH, England. - - -REVISION - - Last updated: 17 March 2009 - Copyright (c) 1997-2009 University of Cambridge. ------------------------------------------------------------------------------- - - -PCREMATCHING(3) PCREMATCHING(3) - - -NAME - PCRE - Perl-compatible regular expressions - - -PCRE MATCHING ALGORITHMS - - This document describes the two different algorithms that are available - in PCRE for matching a compiled regular expression against a given sub- - ject string. The "standard" algorithm is the one provided by the - pcre_exec() function. This works in the same was as Perl's matching - function, and provides a Perl-compatible matching operation. - - An alternative algorithm is provided by the pcre_dfa_exec() function; - this operates in a different way, and is not Perl-compatible. It has - advantages and disadvantages compared with the standard algorithm, and - these are described below. - - When there is only one possible way in which a given subject string can - match a pattern, the two algorithms give the same answer. A difference - arises, however, when there are multiple possibilities. For example, if - the pattern - - ^<.*> - - is matched against the string - - - - there are three possible answers. The standard algorithm finds only one - of them, whereas the alternative algorithm finds all three. - - -REGULAR EXPRESSIONS AS TREES - - The set of strings that are matched by a regular expression can be rep- - resented as a tree structure. An unlimited repetition in the pattern - makes the tree of infinite size, but it is still a tree. Matching the - pattern to a given subject string (from a given starting point) can be - thought of as a search of the tree. There are two ways to search a - tree: depth-first and breadth-first, and these correspond to the two - matching algorithms provided by PCRE. - - -THE STANDARD MATCHING ALGORITHM - - In the terminology of Jeffrey Friedl's book "Mastering Regular Expres- - sions", the standard algorithm is an "NFA algorithm". It conducts a - depth-first search of the pattern tree. That is, it proceeds along a - single path through the tree, checking that the subject matches what is - required. When there is a mismatch, the algorithm tries any alterna- - tives at the current point, and if they all fail, it backs up to the - previous branch point in the tree, and tries the next alternative - branch at that level. This often involves backing up (moving to the - left) in the subject string as well. The order in which repetition - branches are tried is controlled by the greedy or ungreedy nature of - the quantifier. - - If a leaf node is reached, a matching string has been found, and at - that point the algorithm stops. Thus, if there is more than one possi- - ble match, this algorithm returns the first one that it finds. Whether - this is the shortest, the longest, or some intermediate length depends - on the way the greedy and ungreedy repetition quantifiers are specified - in the pattern. - - Because it ends up with a single path through the tree, it is rela- - tively straightforward for this algorithm to keep track of the sub- - strings that are matched by portions of the pattern in parentheses. - This provides support for capturing parentheses and back references. - - -THE ALTERNATIVE MATCHING ALGORITHM - - This algorithm conducts a breadth-first search of the tree. Starting - from the first matching point in the subject, it scans the subject - string from left to right, once, character by character, and as it does - this, it remembers all the paths through the tree that represent valid - matches. In Friedl's terminology, this is a kind of "DFA algorithm", - though it is not implemented as a traditional finite state machine (it - keeps multiple states active simultaneously). - - The scan continues until either the end of the subject is reached, or - there are no more unterminated paths. At this point, terminated paths - represent the different matching possibilities (if there are none, the - match has failed). Thus, if there is more than one possible match, - this algorithm finds all of them, and in particular, it finds the long- - est. In PCRE, there is an option to stop the algorithm after the first - match (which is necessarily the shortest) has been found. - - Note that all the matches that are found start at the same point in the - subject. If the pattern - - cat(er(pillar)?) - - is matched against the string "the caterpillar catchment", the result - will be the three strings "cat", "cater", and "caterpillar" that start - at the fourth character of the subject. The algorithm does not automat- - ically move on to find matches that start at later positions. - - There are a number of features of PCRE regular expressions that are not - supported by the alternative matching algorithm. They are as follows: - - 1. Because the algorithm finds all possible matches, the greedy or - ungreedy nature of repetition quantifiers is not relevant. Greedy and - ungreedy quantifiers are treated in exactly the same way. However, pos- - sessive quantifiers can make a difference when what follows could also - match what is quantified, for example in a pattern like this: - - ^a++\w! - - This pattern matches "aaab!" but not "aaa!", which would be matched by - a non-possessive quantifier. Similarly, if an atomic group is present, - it is matched as if it were a standalone pattern at the current point, - and the longest match is then "locked in" for the rest of the overall - pattern. - - 2. When dealing with multiple paths through the tree simultaneously, it - is not straightforward to keep track of captured substrings for the - different matching possibilities, and PCRE's implementation of this - algorithm does not attempt to do this. This means that no captured sub- - strings are available. - - 3. Because no substrings are captured, back references within the pat- - tern are not supported, and cause errors if encountered. - - 4. For the same reason, conditional expressions that use a backrefer- - ence as the condition or test for a specific group recursion are not - supported. - - 5. Because many paths through the tree may be active, the \K escape - sequence, which resets the start of the match when encountered (but may - be on some paths and not on others), is not supported. It causes an - error if encountered. - - 6. Callouts are supported, but the value of the capture_top field is - always 1, and the value of the capture_last field is always -1. - - 7. The \C escape sequence, which (in the standard algorithm) matches a - single byte, even in UTF-8 mode, is not supported because the alterna- - tive algorithm moves through the subject string one character at a - time, for all active paths through the tree. - - 8. Except for (*FAIL), the backtracking control verbs such as (*PRUNE) - are not supported. (*FAIL) is supported, and behaves like a failing - negative assertion. - - -ADVANTAGES OF THE ALTERNATIVE ALGORITHM - - Using the alternative matching algorithm provides the following advan- - tages: - - 1. All possible matches (at a single point in the subject) are automat- - ically found, and in particular, the longest match is found. To find - more than one match using the standard algorithm, you have to do kludgy - things with callouts. - - 2. There is much better support for partial matching. The restrictions - on the content of the pattern that apply when using the standard algo- - rithm for partial matching do not apply to the alternative algorithm. - For non-anchored patterns, the starting position of a partial match is - available. - - 3. Because the alternative algorithm scans the subject string just - once, and never needs to backtrack, it is possible to pass very long - subject strings to the matching function in several pieces, checking - for partial matching each time. - - -DISADVANTAGES OF THE ALTERNATIVE ALGORITHM - - The alternative algorithm suffers from a number of disadvantages: - - 1. It is substantially slower than the standard algorithm. This is - partly because it has to search for all possible matches, but is also - because it is less susceptible to optimization. - - 2. Capturing parentheses and back references are not supported. - - 3. Although atomic groups are supported, their use does not provide the - performance advantage that it does for the standard algorithm. - - -AUTHOR - - Philip Hazel - University Computing Service - Cambridge CB2 3QH, England. - - -REVISION - - Last updated: 19 April 2008 - Copyright (c) 1997-2008 University of Cambridge. ------------------------------------------------------------------------------- - - -PCREAPI(3) PCREAPI(3) - - -NAME - PCRE - Perl-compatible regular expressions - - -PCRE NATIVE API - - #include - - pcre *pcre_compile(const char *pattern, int options, - const char **errptr, int *erroffset, - const unsigned char *tableptr); - - pcre *pcre_compile2(const char *pattern, int options, - int *errorcodeptr, - const char **errptr, int *erroffset, - const unsigned char *tableptr); - - pcre_extra *pcre_study(const pcre *code, int options, - const char **errptr); - - int pcre_exec(const pcre *code, const pcre_extra *extra, - const char *subject, int length, int startoffset, - int options, int *ovector, int ovecsize); - - int pcre_dfa_exec(const pcre *code, const pcre_extra *extra, - const char *subject, int length, int startoffset, - int options, int *ovector, int ovecsize, - int *workspace, int wscount); - - int pcre_copy_named_substring(const pcre *code, - const char *subject, int *ovector, - int stringcount, const char *stringname, - char *buffer, int buffersize); - - int pcre_copy_substring(const char *subject, int *ovector, - int stringcount, int stringnumber, char *buffer, - int buffersize); - - int pcre_get_named_substring(const pcre *code, - const char *subject, int *ovector, - int stringcount, const char *stringname, - const char **stringptr); - - int pcre_get_stringnumber(const pcre *code, - const char *name); - - int pcre_get_stringtable_entries(const pcre *code, - const char *name, char **first, char **last); - - int pcre_get_substring(const char *subject, int *ovector, - int stringcount, int stringnumber, - const char **stringptr); - - int pcre_get_substring_list(const char *subject, - int *ovector, int stringcount, const char ***listptr); - - void pcre_free_substring(const char *stringptr); - - void pcre_free_substring_list(const char **stringptr); - - const unsigned char *pcre_maketables(void); - - int pcre_fullinfo(const pcre *code, const pcre_extra *extra, - int what, void *where); - - int pcre_info(const pcre *code, int *optptr, int *firstcharptr); - - int pcre_refcount(pcre *code, int adjust); - - int pcre_config(int what, void *where); - - char *pcre_version(void); - - void *(*pcre_malloc)(size_t); - - void (*pcre_free)(void *); - - void *(*pcre_stack_malloc)(size_t); - - void (*pcre_stack_free)(void *); - - int (*pcre_callout)(pcre_callout_block *); - - -PCRE API OVERVIEW - - PCRE has its own native API, which is described in this document. There - are also some wrapper functions that correspond to the POSIX regular - expression API. These are described in the pcreposix documentation. - Both of these APIs define a set of C function calls. A C++ wrapper is - distributed with PCRE. It is documented in the pcrecpp page. - - The native API C function prototypes are defined in the header file - pcre.h, and on Unix systems the library itself is called libpcre. It - can normally be accessed by adding -lpcre to the command for linking an - application that uses PCRE. The header file defines the macros - PCRE_MAJOR and PCRE_MINOR to contain the major and minor release num- - bers for the library. Applications can use these to include support - for different releases of PCRE. - - The functions pcre_compile(), pcre_compile2(), pcre_study(), and - pcre_exec() are used for compiling and matching regular expressions in - a Perl-compatible manner. A sample program that demonstrates the sim- - plest way of using them is provided in the file called pcredemo.c in - the source distribution. The pcresample documentation describes how to - compile and run it. - - A second matching function, pcre_dfa_exec(), which is not Perl-compati- - ble, is also provided. This uses a different algorithm for the match- - ing. The alternative algorithm finds all possible matches (at a given - point in the subject), and scans the subject just once. However, this - algorithm does not return captured substrings. A description of the two - matching algorithms and their advantages and disadvantages is given in - the pcrematching documentation. - - In addition to the main compiling and matching functions, there are - convenience functions for extracting captured substrings from a subject - string that is matched by pcre_exec(). They are: - - pcre_copy_substring() - pcre_copy_named_substring() - pcre_get_substring() - pcre_get_named_substring() - pcre_get_substring_list() - pcre_get_stringnumber() - pcre_get_stringtable_entries() - - pcre_free_substring() and pcre_free_substring_list() are also provided, - to free the memory used for extracted strings. - - The function pcre_maketables() is used to build a set of character - tables in the current locale for passing to pcre_compile(), - pcre_exec(), or pcre_dfa_exec(). This is an optional facility that is - provided for specialist use. Most commonly, no special tables are - passed, in which case internal tables that are generated when PCRE is - built are used. - - The function pcre_fullinfo() is used to find out information about a - compiled pattern; pcre_info() is an obsolete version that returns only - some of the available information, but is retained for backwards com- - patibility. The function pcre_version() returns a pointer to a string - containing the version of PCRE and its date of release. - - The function pcre_refcount() maintains a reference count in a data - block containing a compiled pattern. This is provided for the benefit - of object-oriented applications. - - The global variables pcre_malloc and pcre_free initially contain the - entry points of the standard malloc() and free() functions, respec- - tively. PCRE calls the memory management functions via these variables, - so a calling program can replace them if it wishes to intercept the - calls. This should be done before calling any PCRE functions. - - The global variables pcre_stack_malloc and pcre_stack_free are also - indirections to memory management functions. These special functions - are used only when PCRE is compiled to use the heap for remembering - data, instead of recursive function calls, when running the pcre_exec() - function. See the pcrebuild documentation for details of how to do - this. It is a non-standard way of building PCRE, for use in environ- - ments that have limited stacks. Because of the greater use of memory - management, it runs more slowly. Separate functions are provided so - that special-purpose external code can be used for this case. When - used, these functions are always called in a stack-like manner (last - obtained, first freed), and always for memory blocks of the same size. - There is a discussion about PCRE's stack usage in the pcrestack docu- - mentation. - - The global variable pcre_callout initially contains NULL. It can be set - by the caller to a "callout" function, which PCRE will then call at - specified points during a matching operation. Details are given in the - pcrecallout documentation. - - -NEWLINES - - PCRE supports five different conventions for indicating line breaks in - strings: a single CR (carriage return) character, a single LF (line- - feed) character, the two-character sequence CRLF, any of the three pre- - ceding, or any Unicode newline sequence. The Unicode newline sequences - are the three just mentioned, plus the single characters VT (vertical - tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line - separator, U+2028), and PS (paragraph separator, U+2029). - - Each of the first three conventions is used by at least one operating - system as its standard newline sequence. When PCRE is built, a default - can be specified. The default default is LF, which is the Unix stan- - dard. When PCRE is run, the default can be overridden, either when a - pattern is compiled, or when it is matched. - - At compile time, the newline convention can be specified by the options - argument of pcre_compile(), or it can be specified by special text at - the start of the pattern itself; this overrides any other settings. See - the pcrepattern page for details of the special character sequences. - - In the PCRE documentation the word "newline" is used to mean "the char- - acter or pair of characters that indicate a line break". The choice of - newline convention affects the handling of the dot, circumflex, and - dollar metacharacters, the handling of #-comments in /x mode, and, when - CRLF is a recognized line ending sequence, the match position advance- - ment for a non-anchored pattern. There is more detail about this in the - section on pcre_exec() options below. - - The choice of newline convention does not affect the interpretation of - the \n or \r escape sequences, nor does it affect what \R matches, - which is controlled in a similar way, but by separate options. - - -MULTITHREADING - - The PCRE functions can be used in multi-threading applications, with - the proviso that the memory management functions pointed to by - pcre_malloc, pcre_free, pcre_stack_malloc, and pcre_stack_free, and the - callout function pointed to by pcre_callout, are shared by all threads. - - The compiled form of a regular expression is not altered during match- - ing, so the same compiled pattern can safely be used by several threads - at once. - - -SAVING PRECOMPILED PATTERNS FOR LATER USE - - The compiled form of a regular expression can be saved and re-used at a - later time, possibly by a different program, and even on a host other - than the one on which it was compiled. Details are given in the - pcreprecompile documentation. However, compiling a regular expression - with one version of PCRE for use with a different version is not guar- - anteed to work and may cause crashes. - - -CHECKING BUILD-TIME OPTIONS - - int pcre_config(int what, void *where); - - The function pcre_config() makes it possible for a PCRE client to dis- - cover which optional features have been compiled into the PCRE library. - The pcrebuild documentation has more details about these optional fea- - tures. - - The first argument for pcre_config() is an integer, specifying which - information is required; the second argument is a pointer to a variable - into which the information is placed. The following information is - available: - - PCRE_CONFIG_UTF8 - - The output is an integer that is set to one if UTF-8 support is avail- - able; otherwise it is set to zero. - - PCRE_CONFIG_UNICODE_PROPERTIES - - The output is an integer that is set to one if support for Unicode - character properties is available; otherwise it is set to zero. - - PCRE_CONFIG_NEWLINE - - The output is an integer whose value specifies the default character - sequence that is recognized as meaning "newline". The four values that - are supported are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, - and -1 for ANY. Though they are derived from ASCII, the same values - are returned in EBCDIC environments. The default should normally corre- - spond to the standard sequence for your operating system. - - PCRE_CONFIG_BSR - - The output is an integer whose value indicates what character sequences - the \R escape sequence matches by default. A value of 0 means that \R - matches any Unicode line ending sequence; a value of 1 means that \R - matches only CR, LF, or CRLF. The default can be overridden when a pat- - tern is compiled or matched. - - PCRE_CONFIG_LINK_SIZE - - The output is an integer that contains the number of bytes used for - internal linkage in compiled regular expressions. The value is 2, 3, or - 4. Larger values allow larger regular expressions to be compiled, at - the expense of slower matching. The default value of 2 is sufficient - for all but the most massive patterns, since it allows the compiled - pattern to be up to 64K in size. - - PCRE_CONFIG_POSIX_MALLOC_THRESHOLD - - The output is an integer that contains the threshold above which the - POSIX interface uses malloc() for output vectors. Further details are - given in the pcreposix documentation. - - PCRE_CONFIG_MATCH_LIMIT - - The output is a long integer that gives the default limit for the num- - ber of internal matching function calls in a pcre_exec() execution. - Further details are given with pcre_exec() below. - - PCRE_CONFIG_MATCH_LIMIT_RECURSION - - The output is a long integer that gives the default limit for the depth - of recursion when calling the internal matching function in a - pcre_exec() execution. Further details are given with pcre_exec() - below. - - PCRE_CONFIG_STACKRECURSE - - The output is an integer that is set to one if internal recursion when - running pcre_exec() is implemented by recursive function calls that use - the stack to remember their state. This is the usual way that PCRE is - compiled. The output is zero if PCRE was compiled to use blocks of data - on the heap instead of recursive function calls. In this case, - pcre_stack_malloc and pcre_stack_free are called to manage memory - blocks on the heap, thus avoiding the use of the stack. - - -COMPILING A PATTERN - - pcre *pcre_compile(const char *pattern, int options, - const char **errptr, int *erroffset, - const unsigned char *tableptr); - - pcre *pcre_compile2(const char *pattern, int options, - int *errorcodeptr, - const char **errptr, int *erroffset, - const unsigned char *tableptr); - - Either of the functions pcre_compile() or pcre_compile2() can be called - to compile a pattern into an internal form. The only difference between - the two interfaces is that pcre_compile2() has an additional argument, - errorcodeptr, via which a numerical error code can be returned. - - The pattern is a C string terminated by a binary zero, and is passed in - the pattern argument. A pointer to a single block of memory that is - obtained via pcre_malloc is returned. This contains the compiled code - and related data. The pcre type is defined for the returned block; this - is a typedef for a structure whose contents are not externally defined. - It is up to the caller to free the memory (via pcre_free) when it is no - longer required. - - Although the compiled code of a PCRE regex is relocatable, that is, it - does not depend on memory location, the complete pcre data block is not - fully relocatable, because it may contain a copy of the tableptr argu- - ment, which is an address (see below). - - The options argument contains various bit settings that affect the com- - pilation. It should be zero if no options are required. The available - options are described below. Some of them (in particular, those that - are compatible with Perl, but also some others) can also be set and - unset from within the pattern (see the detailed description in the - pcrepattern documentation). For those options that can be different in - different parts of the pattern, the contents of the options argument - specifies their initial settings at the start of compilation and execu- - tion. The PCRE_ANCHORED and PCRE_NEWLINE_xxx options can be set at the - time of matching as well as at compile time. - - If errptr is NULL, pcre_compile() returns NULL immediately. Otherwise, - if compilation of a pattern fails, pcre_compile() returns NULL, and - sets the variable pointed to by errptr to point to a textual error mes- - sage. This is a static string that is part of the library. You must not - try to free it. The offset from the start of the pattern to the charac- - ter where the error was discovered is placed in the variable pointed to - by erroffset, which must not be NULL. If it is, an immediate error is - given. - - If pcre_compile2() is used instead of pcre_compile(), and the error- - codeptr argument is not NULL, a non-zero error code number is returned - via this argument in the event of an error. This is in addition to the - textual error message. Error codes and messages are listed below. - - If the final argument, tableptr, is NULL, PCRE uses a default set of - character tables that are built when PCRE is compiled, using the - default C locale. Otherwise, tableptr must be an address that is the - result of a call to pcre_maketables(). This value is stored with the - compiled pattern, and used again by pcre_exec(), unless another table - pointer is passed to it. For more discussion, see the section on locale - support below. - - This code fragment shows a typical straightforward call to pcre_com- - pile(): - - pcre *re; - const char *error; - int erroffset; - re = pcre_compile( - "^A.*Z", /* the pattern */ - 0, /* default options */ - &error, /* for error message */ - &erroffset, /* for error offset */ - NULL); /* use default character tables */ - - The following names for option bits are defined in the pcre.h header - file: - - PCRE_ANCHORED - - If this bit is set, the pattern is forced to be "anchored", that is, it - is constrained to match only at the first matching point in the string - that is being searched (the "subject string"). This effect can also be - achieved by appropriate constructs in the pattern itself, which is the - only way to do it in Perl. - - PCRE_AUTO_CALLOUT - - If this bit is set, pcre_compile() automatically inserts callout items, - all with number 255, before each pattern item. For discussion of the - callout facility, see the pcrecallout documentation. - - PCRE_BSR_ANYCRLF - PCRE_BSR_UNICODE - - These options (which are mutually exclusive) control what the \R escape - sequence matches. The choice is either to match only CR, LF, or CRLF, - or to match any Unicode newline sequence. The default is specified when - PCRE is built. It can be overridden from within the pattern, or by set- - ting an option when a compiled pattern is matched. - - PCRE_CASELESS - - If this bit is set, letters in the pattern match both upper and lower - case letters. It is equivalent to Perl's /i option, and it can be - changed within a pattern by a (?i) option setting. In UTF-8 mode, PCRE - always understands the concept of case for characters whose values are - less than 128, so caseless matching is always possible. For characters - with higher values, the concept of case is supported if PCRE is com- - piled with Unicode property support, but not otherwise. If you want to - use caseless matching for characters 128 and above, you must ensure - that PCRE is compiled with Unicode property support as well as with - UTF-8 support. - - PCRE_DOLLAR_ENDONLY - - If this bit is set, a dollar metacharacter in the pattern matches only - at the end of the subject string. Without this option, a dollar also - matches immediately before a newline at the end of the string (but not - before any other newlines). The PCRE_DOLLAR_ENDONLY option is ignored - if PCRE_MULTILINE is set. There is no equivalent to this option in - Perl, and no way to set it within a pattern. - - PCRE_DOTALL - - If this bit is set, a dot metacharater in the pattern matches all char- - acters, including those that indicate newline. Without it, a dot does - not match when the current position is at a newline. This option is - equivalent to Perl's /s option, and it can be changed within a pattern - by a (?s) option setting. A negative class such as [^a] always matches - newline characters, independent of the setting of this option. - - PCRE_DUPNAMES - - If this bit is set, names used to identify capturing subpatterns need - not be unique. This can be helpful for certain types of pattern when it - is known that only one instance of the named subpattern can ever be - matched. There are more details of named subpatterns below; see also - the pcrepattern documentation. - - PCRE_EXTENDED - - If this bit is set, whitespace data characters in the pattern are - totally ignored except when escaped or inside a character class. White- - space does not include the VT character (code 11). In addition, charac- - ters between an unescaped # outside a character class and the next new- - line, inclusive, are also ignored. This is equivalent to Perl's /x - option, and it can be changed within a pattern by a (?x) option set- - ting. - - This option makes it possible to include comments inside complicated - patterns. Note, however, that this applies only to data characters. - Whitespace characters may never appear within special character - sequences in a pattern, for example within the sequence (?( which - introduces a conditional subpattern. - - PCRE_EXTRA - - This option was invented in order to turn on additional functionality - of PCRE that is incompatible with Perl, but it is currently of very - little use. When set, any backslash in a pattern that is followed by a - letter that has no special meaning causes an error, thus reserving - these combinations for future expansion. By default, as in Perl, a - backslash followed by a letter with no special meaning is treated as a - literal. (Perl can, however, be persuaded to give a warning for this.) - There are at present no other features controlled by this option. It - can also be set by a (?X) option setting within a pattern. - - PCRE_FIRSTLINE - - If this option is set, an unanchored pattern is required to match - before or at the first newline in the subject string, though the - matched text may continue over the newline. - - PCRE_JAVASCRIPT_COMPAT - - If this option is set, PCRE's behaviour is changed in some ways so that - it is compatible with JavaScript rather than Perl. The changes are as - follows: - - (1) A lone closing square bracket in a pattern causes a compile-time - error, because this is illegal in JavaScript (by default it is treated - as a data character). Thus, the pattern AB]CD becomes illegal when this - option is set. - - (2) At run time, a back reference to an unset subpattern group matches - an empty string (by default this causes the current matching alterna- - tive to fail). A pattern such as (\1)(a) succeeds when this option is - set (assuming it can find an "a" in the subject), whereas it fails by - default, for Perl compatibility. - - PCRE_MULTILINE - - By default, PCRE treats the subject string as consisting of a single - line of characters (even if it actually contains newlines). The "start - of line" metacharacter (^) matches only at the start of the string, - while the "end of line" metacharacter ($) matches only at the end of - the string, or before a terminating newline (unless PCRE_DOLLAR_ENDONLY - is set). This is the same as Perl. - - When PCRE_MULTILINE it is set, the "start of line" and "end of line" - constructs match immediately following or immediately before internal - newlines in the subject string, respectively, as well as at the very - start and end. This is equivalent to Perl's /m option, and it can be - changed within a pattern by a (?m) option setting. If there are no new- - lines in a subject string, or no occurrences of ^ or $ in a pattern, - setting PCRE_MULTILINE has no effect. - - PCRE_NEWLINE_CR - PCRE_NEWLINE_LF - PCRE_NEWLINE_CRLF - PCRE_NEWLINE_ANYCRLF - PCRE_NEWLINE_ANY - - These options override the default newline definition that was chosen - when PCRE was built. Setting the first or the second specifies that a - newline is indicated by a single character (CR or LF, respectively). - Setting PCRE_NEWLINE_CRLF specifies that a newline is indicated by the - two-character CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies - that any of the three preceding sequences should be recognized. Setting - PCRE_NEWLINE_ANY specifies that any Unicode newline sequence should be - recognized. The Unicode newline sequences are the three just mentioned, - plus the single characters VT (vertical tab, U+000B), FF (formfeed, - U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS - (paragraph separator, U+2029). The last two are recognized only in - UTF-8 mode. - - The newline setting in the options word uses three bits that are - treated as a number, giving eight possibilities. Currently only six are - used (default plus the five values above). This means that if you set - more than one newline option, the combination may or may not be sensi- - ble. For example, PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to - PCRE_NEWLINE_CRLF, but other combinations may yield unused numbers and - cause an error. - - The only time that a line break is specially recognized when compiling - a pattern is if PCRE_EXTENDED is set, and an unescaped # outside a - character class is encountered. This indicates a comment that lasts - until after the next line break sequence. In other circumstances, line - break sequences are treated as literal data, except that in - PCRE_EXTENDED mode, both CR and LF are treated as whitespace characters - and are therefore ignored. - - The newline option that is set at compile time becomes the default that - is used for pcre_exec() and pcre_dfa_exec(), but it can be overridden. - - PCRE_NO_AUTO_CAPTURE - - If this option is set, it disables the use of numbered capturing paren- - theses in the pattern. Any opening parenthesis that is not followed by - ? behaves as if it were followed by ?: but named parentheses can still - be used for capturing (and they acquire numbers in the usual way). - There is no equivalent of this option in Perl. - - PCRE_UNGREEDY - - This option inverts the "greediness" of the quantifiers so that they - are not greedy by default, but become greedy if followed by "?". It is - not compatible with Perl. It can also be set by a (?U) option setting - within the pattern. - - PCRE_UTF8 - - This option causes PCRE to regard both the pattern and the subject as - strings of UTF-8 characters instead of single-byte character strings. - However, it is available only when PCRE is built to include UTF-8 sup- - port. If not, the use of this option provokes an error. Details of how - this option changes the behaviour of PCRE are given in the section on - UTF-8 support in the main pcre page. - - PCRE_NO_UTF8_CHECK - - When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is - automatically checked. There is a discussion about the validity of - UTF-8 strings in the main pcre page. If an invalid UTF-8 sequence of - bytes is found, pcre_compile() returns an error. If you already know - that your pattern is valid, and you want to skip this check for perfor- - mance reasons, you can set the PCRE_NO_UTF8_CHECK option. When it is - set, the effect of passing an invalid UTF-8 string as a pattern is - undefined. It may cause your program to crash. Note that this option - can also be passed to pcre_exec() and pcre_dfa_exec(), to suppress the - UTF-8 validity checking of subject strings. - - -COMPILATION ERROR CODES - - The following table lists the error codes than may be returned by - pcre_compile2(), along with the error messages that may be returned by - both compiling functions. As PCRE has developed, some error codes have - fallen out of use. To avoid confusion, they have not been re-used. - - 0 no error - 1 \ at end of pattern - 2 \c at end of pattern - 3 unrecognized character follows \ - 4 numbers out of order in {} quantifier - 5 number too big in {} quantifier - 6 missing terminating ] for character class - 7 invalid escape sequence in character class - 8 range out of order in character class - 9 nothing to repeat - 10 [this code is not in use] - 11 internal error: unexpected repeat - 12 unrecognized character after (? or (?- - 13 POSIX named classes are supported only within a class - 14 missing ) - 15 reference to non-existent subpattern - 16 erroffset passed as NULL - 17 unknown option bit(s) set - 18 missing ) after comment - 19 [this code is not in use] - 20 regular expression is too large - 21 failed to get memory - 22 unmatched parentheses - 23 internal error: code overflow - 24 unrecognized character after (?< - 25 lookbehind assertion is not fixed length - 26 malformed number or name after (?( - 27 conditional group contains more than two branches - 28 assertion expected after (?( - 29 (?R or (?[+-]digits must be followed by ) - 30 unknown POSIX class name - 31 POSIX collating elements are not supported - 32 this version of PCRE is not compiled with PCRE_UTF8 support - 33 [this code is not in use] - 34 character value in \x{...} sequence is too large - 35 invalid condition (?(0) - 36 \C not allowed in lookbehind assertion - 37 PCRE does not support \L, \l, \N, \U, or \u - 38 number after (?C is > 255 - 39 closing ) for (?C expected - 40 recursive call could loop indefinitely - 41 unrecognized character after (?P - 42 syntax error in subpattern name (missing terminator) - 43 two named subpatterns have the same name - 44 invalid UTF-8 string - 45 support for \P, \p, and \X has not been compiled - 46 malformed \P or \p sequence - 47 unknown property name after \P or \p - 48 subpattern name is too long (maximum 32 characters) - 49 too many named subpatterns (maximum 10000) - 50 [this code is not in use] - 51 octal value is greater than \377 (not in UTF-8 mode) - 52 internal error: overran compiling workspace - 53 internal error: previously-checked referenced subpattern not - found - 54 DEFINE group contains more than one branch - 55 repeating a DEFINE group is not allowed - 56 inconsistent NEWLINE options - 57 \g is not followed by a braced, angle-bracketed, or quoted - name/number or by a plain number - 58 a numbered reference must not be zero - 59 (*VERB) with an argument is not supported - 60 (*VERB) not recognized - 61 number is too big - 62 subpattern name expected - 63 digit expected after (?+ - 64 ] is an invalid data character in JavaScript compatibility mode - - The numbers 32 and 10000 in errors 48 and 49 are defaults; different - values may be used if the limits were changed when PCRE was built. - - -STUDYING A PATTERN - - pcre_extra *pcre_study(const pcre *code, int options - const char **errptr); - - If a compiled pattern is going to be used several times, it is worth - spending more time analyzing it in order to speed up the time taken for - matching. The function pcre_study() takes a pointer to a compiled pat- - tern as its first argument. If studying the pattern produces additional - information that will help speed up matching, pcre_study() returns a - pointer to a pcre_extra block, in which the study_data field points to - the results of the study. - - The returned value from pcre_study() can be passed directly to - pcre_exec(). However, a pcre_extra block also contains other fields - that can be set by the caller before the block is passed; these are - described below in the section on matching a pattern. - - If studying the pattern does not produce any additional information - pcre_study() returns NULL. In that circumstance, if the calling program - wants to pass any of the other fields to pcre_exec(), it must set up - its own pcre_extra block. - - The second argument of pcre_study() contains option bits. At present, - no options are defined, and this argument should always be zero. - - The third argument for pcre_study() is a pointer for an error message. - If studying succeeds (even if no data is returned), the variable it - points to is set to NULL. Otherwise it is set to point to a textual - error message. This is a static string that is part of the library. You - must not try to free it. You should test the error pointer for NULL - after calling pcre_study(), to be sure that it has run successfully. - - This is a typical call to pcre_study(): - - pcre_extra *pe; - pe = pcre_study( - re, /* result of pcre_compile() */ - 0, /* no options exist */ - &error); /* set to NULL or points to a message */ - - At present, studying a pattern is useful only for non-anchored patterns - that do not have a single fixed starting character. A bitmap of possi- - ble starting bytes is created. - - -LOCALE SUPPORT - - PCRE handles caseless matching, and determines whether characters are - letters, digits, or whatever, by reference to a set of tables, indexed - by character value. When running in UTF-8 mode, this applies only to - characters with codes less than 128. Higher-valued codes never match - escapes such as \w or \d, but can be tested with \p if PCRE is built - with Unicode character property support. The use of locales with Uni- - code is discouraged. If you are handling characters with codes greater - than 128, you should either use UTF-8 and Unicode, or use locales, but - not try to mix the two. - - PCRE contains an internal set of tables that are used when the final - argument of pcre_compile() is NULL. These are sufficient for many - applications. Normally, the internal tables recognize only ASCII char- - acters. However, when PCRE is built, it is possible to cause the inter- - nal tables to be rebuilt in the default "C" locale of the local system, - which may cause them to be different. - - The internal tables can always be overridden by tables supplied by the - application that calls PCRE. These may be created in a different locale - from the default. As more and more applications change to using Uni- - code, the need for this locale support is expected to die away. - - External tables are built by calling the pcre_maketables() function, - which has no arguments, in the relevant locale. The result can then be - passed to pcre_compile() or pcre_exec() as often as necessary. For - example, to build and use tables that are appropriate for the French - locale (where accented characters with values greater than 128 are - treated as letters), the following code could be used: - - setlocale(LC_CTYPE, "fr_FR"); - tables = pcre_maketables(); - re = pcre_compile(..., tables); - - The locale name "fr_FR" is used on Linux and other Unix-like systems; - if you are using Windows, the name for the French locale is "french". - - When pcre_maketables() runs, the tables are built in memory that is - obtained via pcre_malloc. It is the caller's responsibility to ensure - that the memory containing the tables remains available for as long as - it is needed. - - The pointer that is passed to pcre_compile() is saved with the compiled - pattern, and the same tables are used via this pointer by pcre_study() - and normally also by pcre_exec(). Thus, by default, for any single pat- - tern, compilation, studying and matching all happen in the same locale, - but different patterns can be compiled in different locales. - - It is possible to pass a table pointer or NULL (indicating the use of - the internal tables) to pcre_exec(). Although not intended for this - purpose, this facility could be used to match a pattern in a different - locale from the one in which it was compiled. Passing table pointers at - run time is discussed below in the section on matching a pattern. - - -INFORMATION ABOUT A PATTERN - - int pcre_fullinfo(const pcre *code, const pcre_extra *extra, - int what, void *where); - - The pcre_fullinfo() function returns information about a compiled pat- - tern. It replaces the obsolete pcre_info() function, which is neverthe- - less retained for backwards compability (and is documented below). - - The first argument for pcre_fullinfo() is a pointer to the compiled - pattern. The second argument is the result of pcre_study(), or NULL if - the pattern was not studied. The third argument specifies which piece - of information is required, and the fourth argument is a pointer to a - variable to receive the data. The yield of the function is zero for - success, or one of the following negative numbers: - - PCRE_ERROR_NULL the argument code was NULL - the argument where was NULL - PCRE_ERROR_BADMAGIC the "magic number" was not found - PCRE_ERROR_BADOPTION the value of what was invalid - - The "magic number" is placed at the start of each compiled pattern as - an simple check against passing an arbitrary memory pointer. Here is a - typical call of pcre_fullinfo(), to obtain the length of the compiled - pattern: - - int rc; - size_t length; - rc = pcre_fullinfo( - re, /* result of pcre_compile() */ - pe, /* result of pcre_study(), or NULL */ - PCRE_INFO_SIZE, /* what is required */ - &length); /* where to put the data */ - - The possible values for the third argument are defined in pcre.h, and - are as follows: - - PCRE_INFO_BACKREFMAX - - Return the number of the highest back reference in the pattern. The - fourth argument should point to an int variable. Zero is returned if - there are no back references. - - PCRE_INFO_CAPTURECOUNT - - Return the number of capturing subpatterns in the pattern. The fourth - argument should point to an int variable. - - PCRE_INFO_DEFAULT_TABLES - - Return a pointer to the internal default character tables within PCRE. - The fourth argument should point to an unsigned char * variable. This - information call is provided for internal use by the pcre_study() func- - tion. External callers can cause PCRE to use its internal tables by - passing a NULL table pointer. - - PCRE_INFO_FIRSTBYTE - - Return information about the first byte of any matched string, for a - non-anchored pattern. The fourth argument should point to an int vari- - able. (This option used to be called PCRE_INFO_FIRSTCHAR; the old name - is still recognized for backwards compatibility.) - - If there is a fixed first byte, for example, from a pattern such as - (cat|cow|coyote), its value is returned. Otherwise, if either - - (a) the pattern was compiled with the PCRE_MULTILINE option, and every - branch starts with "^", or - - (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not - set (if it were set, the pattern would be anchored), - - -1 is returned, indicating that the pattern matches only at the start - of a subject string or after any newline within the string. Otherwise - -2 is returned. For anchored patterns, -2 is returned. - - PCRE_INFO_FIRSTTABLE - - If the pattern was studied, and this resulted in the construction of a - 256-bit table indicating a fixed set of bytes for the first byte in any - matching string, a pointer to the table is returned. Otherwise NULL is - returned. The fourth argument should point to an unsigned char * vari- - able. - - PCRE_INFO_HASCRORLF - - Return 1 if the pattern contains any explicit matches for CR or LF - characters, otherwise 0. The fourth argument should point to an int - variable. An explicit match is either a literal CR or LF character, or - \r or \n. - - PCRE_INFO_JCHANGED - - Return 1 if the (?J) or (?-J) option setting is used in the pattern, - otherwise 0. The fourth argument should point to an int variable. (?J) - and (?-J) set and unset the local PCRE_DUPNAMES option, respectively. - - PCRE_INFO_LASTLITERAL - - Return the value of the rightmost literal byte that must exist in any - matched string, other than at its start, if such a byte has been - recorded. The fourth argument should point to an int variable. If there - is no such byte, -1 is returned. For anchored patterns, a last literal - byte is recorded only if it follows something of variable length. For - example, for the pattern /^a\d+z\d+/ the returned value is "z", but for - /^a\dz\d/ the returned value is -1. - - PCRE_INFO_NAMECOUNT - PCRE_INFO_NAMEENTRYSIZE - PCRE_INFO_NAMETABLE - - PCRE supports the use of named as well as numbered capturing parenthe- - ses. The names are just an additional way of identifying the parenthe- - ses, which still acquire numbers. Several convenience functions such as - pcre_get_named_substring() are provided for extracting captured sub- - strings by name. It is also possible to extract the data directly, by - first converting the name to a number in order to access the correct - pointers in the output vector (described with pcre_exec() below). To do - the conversion, you need to use the name-to-number map, which is - described by these three values. - - The map consists of a number of fixed-size entries. PCRE_INFO_NAMECOUNT - gives the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size - of each entry; both of these return an int value. The entry size - depends on the length of the longest name. PCRE_INFO_NAMETABLE returns - a pointer to the first entry of the table (a pointer to char). The - first two bytes of each entry are the number of the capturing parenthe- - sis, most significant byte first. The rest of the entry is the corre- - sponding name, zero terminated. The names are in alphabetical order. - When PCRE_DUPNAMES is set, duplicate names are in order of their paren- - theses numbers. For example, consider the following pattern (assume - PCRE_EXTENDED is set, so white space - including newlines - is - ignored): - - (? (?(\d\d)?\d\d) - - (?\d\d) - (?\d\d) ) - - There are four named subpatterns, so the table has four entries, and - each entry in the table is eight bytes long. The table is as follows, - with non-printing bytes shows in hexadecimal, and undefined bytes shown - as ??: - - 00 01 d a t e 00 ?? - 00 05 d a y 00 ?? ?? - 00 04 m o n t h 00 - 00 02 y e a r 00 ?? - - When writing code to extract data from named subpatterns using the - name-to-number map, remember that the length of the entries is likely - to be different for each compiled pattern. - - PCRE_INFO_OKPARTIAL - - Return 1 if the pattern can be used for partial matching, otherwise 0. - The fourth argument should point to an int variable. The pcrepartial - documentation lists the restrictions that apply to patterns when par- - tial matching is used. - - PCRE_INFO_OPTIONS - - Return a copy of the options with which the pattern was compiled. The - fourth argument should point to an unsigned long int variable. These - option bits are those specified in the call to pcre_compile(), modified - by any top-level option settings at the start of the pattern itself. In - other words, they are the options that will be in force when matching - starts. For example, if the pattern /(?im)abc(?-i)d/ is compiled with - the PCRE_EXTENDED option, the result is PCRE_CASELESS, PCRE_MULTILINE, - and PCRE_EXTENDED. - - A pattern is automatically anchored by PCRE if all of its top-level - alternatives begin with one of the following: - - ^ unless PCRE_MULTILINE is set - \A always - \G always - .* if PCRE_DOTALL is set and there are no back - references to the subpattern in which .* appears - - For such patterns, the PCRE_ANCHORED bit is set in the options returned - by pcre_fullinfo(). - - PCRE_INFO_SIZE - - Return the size of the compiled pattern, that is, the value that was - passed as the argument to pcre_malloc() when PCRE was getting memory in - which to place the compiled data. The fourth argument should point to a - size_t variable. - - PCRE_INFO_STUDYSIZE - - Return the size of the data block pointed to by the study_data field in - a pcre_extra block. That is, it is the value that was passed to - pcre_malloc() when PCRE was getting memory into which to place the data - created by pcre_study(). The fourth argument should point to a size_t - variable. - - -OBSOLETE INFO FUNCTION - - int pcre_info(const pcre *code, int *optptr, int *firstcharptr); - - The pcre_info() function is now obsolete because its interface is too - restrictive to return all the available data about a compiled pattern. - New programs should use pcre_fullinfo() instead. The yield of - pcre_info() is the number of capturing subpatterns, or one of the fol- - lowing negative numbers: - - PCRE_ERROR_NULL the argument code was NULL - PCRE_ERROR_BADMAGIC the "magic number" was not found - - If the optptr argument is not NULL, a copy of the options with which - the pattern was compiled is placed in the integer it points to (see - PCRE_INFO_OPTIONS above). - - If the pattern is not anchored and the firstcharptr argument is not - NULL, it is used to pass back information about the first character of - any matched string (see PCRE_INFO_FIRSTBYTE above). - - -REFERENCE COUNTS - - int pcre_refcount(pcre *code, int adjust); - - The pcre_refcount() function is used to maintain a reference count in - the data block that contains a compiled pattern. It is provided for the - benefit of applications that operate in an object-oriented manner, - where different parts of the application may be using the same compiled - pattern, but you want to free the block when they are all done. - - When a pattern is compiled, the reference count field is initialized to - zero. It is changed only by calling this function, whose action is to - add the adjust value (which may be positive or negative) to it. The - yield of the function is the new value. However, the value of the count - is constrained to lie between 0 and 65535, inclusive. If the new value - is outside these limits, it is forced to the appropriate limit value. - - Except when it is zero, the reference count is not correctly preserved - if a pattern is compiled on one host and then transferred to a host - whose byte-order is different. (This seems a highly unlikely scenario.) - - -MATCHING A PATTERN: THE TRADITIONAL FUNCTION - - int pcre_exec(const pcre *code, const pcre_extra *extra, - const char *subject, int length, int startoffset, - int options, int *ovector, int ovecsize); - - The function pcre_exec() is called to match a subject string against a - compiled pattern, which is passed in the code argument. If the pattern - has been studied, the result of the study should be passed in the extra - argument. This function is the main matching facility of the library, - and it operates in a Perl-like manner. For specialist use there is also - an alternative matching function, which is described below in the sec- - tion about the pcre_dfa_exec() function. - - In most applications, the pattern will have been compiled (and option- - ally studied) in the same process that calls pcre_exec(). However, it - is possible to save compiled patterns and study data, and then use them - later in different processes, possibly even on different hosts. For a - discussion about this, see the pcreprecompile documentation. - - Here is an example of a simple call to pcre_exec(): - - int rc; - int ovector[30]; - rc = pcre_exec( - re, /* result of pcre_compile() */ - NULL, /* we didn't study the pattern */ - "some string", /* the subject string */ - 11, /* the length of the subject string */ - 0, /* start at offset 0 in the subject */ - 0, /* default options */ - ovector, /* vector of integers for substring information */ - 30); /* number of elements (NOT size in bytes) */ - - Extra data for pcre_exec() - - If the extra argument is not NULL, it must point to a pcre_extra data - block. The pcre_study() function returns such a block (when it doesn't - return NULL), but you can also create one for yourself, and pass addi- - tional information in it. The pcre_extra block contains the following - fields (not necessarily in this order): - - unsigned long int flags; - void *study_data; - unsigned long int match_limit; - unsigned long int match_limit_recursion; - void *callout_data; - const unsigned char *tables; - - The flags field is a bitmap that specifies which of the other fields - are set. The flag bits are: - - PCRE_EXTRA_STUDY_DATA - PCRE_EXTRA_MATCH_LIMIT - PCRE_EXTRA_MATCH_LIMIT_RECURSION - PCRE_EXTRA_CALLOUT_DATA - PCRE_EXTRA_TABLES - - Other flag bits should be set to zero. The study_data field is set in - the pcre_extra block that is returned by pcre_study(), together with - the appropriate flag bit. You should not set this yourself, but you may - add to the block by setting the other fields and their corresponding - flag bits. - - The match_limit field provides a means of preventing PCRE from using up - a vast amount of resources when running patterns that are not going to - match, but which have a very large number of possibilities in their - search trees. The classic example is the use of nested unlimited - repeats. - - Internally, PCRE uses a function called match() which it calls repeat- - edly (sometimes recursively). The limit set by match_limit is imposed - on the number of times this function is called during a match, which - has the effect of limiting the amount of backtracking that can take - place. For patterns that are not anchored, the count restarts from zero - for each position in the subject string. - - The default value for the limit can be set when PCRE is built; the - default default is 10 million, which handles all but the most extreme - cases. You can override the default by suppling pcre_exec() with a - pcre_extra block in which match_limit is set, and - PCRE_EXTRA_MATCH_LIMIT is set in the flags field. If the limit is - exceeded, pcre_exec() returns PCRE_ERROR_MATCHLIMIT. - - The match_limit_recursion field is similar to match_limit, but instead - of limiting the total number of times that match() is called, it limits - the depth of recursion. The recursion depth is a smaller number than - the total number of calls, because not all calls to match() are recur- - sive. This limit is of use only if it is set smaller than match_limit. - - Limiting the recursion depth limits the amount of stack that can be - used, or, when PCRE has been compiled to use memory on the heap instead - of the stack, the amount of heap memory that can be used. - - The default value for match_limit_recursion can be set when PCRE is - built; the default default is the same value as the default for - match_limit. You can override the default by suppling pcre_exec() with - a pcre_extra block in which match_limit_recursion is set, and - PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the flags field. If the - limit is exceeded, pcre_exec() returns PCRE_ERROR_RECURSIONLIMIT. - - The pcre_callout field is used in conjunction with the "callout" fea- - ture, which is described in the pcrecallout documentation. - - The tables field is used to pass a character tables pointer to - pcre_exec(); this overrides the value that is stored with the compiled - pattern. A non-NULL value is stored with the compiled pattern only if - custom tables were supplied to pcre_compile() via its tableptr argu- - ment. If NULL is passed to pcre_exec() using this mechanism, it forces - PCRE's internal tables to be used. This facility is helpful when re- - using patterns that have been saved after compiling with an external - set of tables, because the external tables might be at a different - address when pcre_exec() is called. See the pcreprecompile documenta- - tion for a discussion of saving compiled patterns for later use. - - Option bits for pcre_exec() - - The unused bits of the options argument for pcre_exec() must be zero. - The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_xxx, - PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_START_OPTIMIZE, - PCRE_NO_UTF8_CHECK and PCRE_PARTIAL. - - PCRE_ANCHORED - - The PCRE_ANCHORED option limits pcre_exec() to matching at the first - matching position. If a pattern was compiled with PCRE_ANCHORED, or - turned out to be anchored by virtue of its contents, it cannot be made - unachored at matching time. - - PCRE_BSR_ANYCRLF - PCRE_BSR_UNICODE - - These options (which are mutually exclusive) control what the \R escape - sequence matches. The choice is either to match only CR, LF, or CRLF, - or to match any Unicode newline sequence. These options override the - choice that was made or defaulted when the pattern was compiled. - - PCRE_NEWLINE_CR - PCRE_NEWLINE_LF - PCRE_NEWLINE_CRLF - PCRE_NEWLINE_ANYCRLF - PCRE_NEWLINE_ANY - - These options override the newline definition that was chosen or - defaulted when the pattern was compiled. For details, see the descrip- - tion of pcre_compile() above. During matching, the newline choice - affects the behaviour of the dot, circumflex, and dollar metacharac- - ters. It may also alter the way the match position is advanced after a - match failure for an unanchored pattern. - - When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is - set, and a match attempt for an unanchored pattern fails when the cur- - rent position is at a CRLF sequence, and the pattern contains no - explicit matches for CR or LF characters, the match position is - advanced by two characters instead of one, in other words, to after the - CRLF. - - The above rule is a compromise that makes the most common cases work as - expected. For example, if the pattern is .+A (and the PCRE_DOTALL - option is not set), it does not match the string "\r\nA" because, after - failing at the start, it skips both the CR and the LF before retrying. - However, the pattern [\r\n]A does match that string, because it con- - tains an explicit CR or LF reference, and so advances only by one char- - acter after the first failure. - - An explicit match for CR of LF is either a literal appearance of one of - those characters, or one of the \r or \n escape sequences. Implicit - matches such as [^X] do not count, nor does \s (which includes CR and - LF in the characters that it matches). - - Notwithstanding the above, anomalous effects may still occur when CRLF - is a valid newline sequence and explicit \r or \n escapes appear in the - pattern. - - PCRE_NOTBOL - - This option specifies that first character of the subject string is not - the beginning of a line, so the circumflex metacharacter should not - match before it. Setting this without PCRE_MULTILINE (at compile time) - causes circumflex never to match. This option affects only the behav- - iour of the circumflex metacharacter. It does not affect \A. - - PCRE_NOTEOL - - This option specifies that the end of the subject string is not the end - of a line, so the dollar metacharacter should not match it nor (except - in multiline mode) a newline immediately before it. Setting this with- - out PCRE_MULTILINE (at compile time) causes dollar never to match. This - option affects only the behaviour of the dollar metacharacter. It does - not affect \Z or \z. - - PCRE_NOTEMPTY - - An empty string is not considered to be a valid match if this option is - set. If there are alternatives in the pattern, they are tried. If all - the alternatives match the empty string, the entire match fails. For - example, if the pattern - - a?b? - - is applied to a string not beginning with "a" or "b", it matches the - empty string at the start of the subject. With PCRE_NOTEMPTY set, this - match is not valid, so PCRE searches further into the string for occur- - rences of "a" or "b". - - Perl has no direct equivalent of PCRE_NOTEMPTY, but it does make a spe- - cial case of a pattern match of the empty string within its split() - function, and when using the /g modifier. It is possible to emulate - Perl's behaviour after matching a null string by first trying the match - again at the same offset with PCRE_NOTEMPTY and PCRE_ANCHORED, and then - if that fails by advancing the starting offset (see below) and trying - an ordinary match again. There is some code that demonstrates how to do - this in the pcredemo.c sample program. - - PCRE_NO_START_OPTIMIZE - - There are a number of optimizations that pcre_exec() uses at the start - of a match, in order to speed up the process. For example, if it is - known that a match must start with a specific character, it searches - the subject for that character, and fails immediately if it cannot find - it, without actually running the main matching function. When callouts - are in use, these optimizations can cause them to be skipped. This - option disables the "start-up" optimizations, causing performance to - suffer, but ensuring that the callouts do occur. - - PCRE_NO_UTF8_CHECK - - When PCRE_UTF8 is set at compile time, the validity of the subject as a - UTF-8 string is automatically checked when pcre_exec() is subsequently - called. The value of startoffset is also checked to ensure that it - points to the start of a UTF-8 character. There is a discussion about - the validity of UTF-8 strings in the section on UTF-8 support in the - main pcre page. If an invalid UTF-8 sequence of bytes is found, - pcre_exec() returns the error PCRE_ERROR_BADUTF8. If startoffset con- - tains an invalid value, PCRE_ERROR_BADUTF8_OFFSET is returned. - - If you already know that your subject is valid, and you want to skip - these checks for performance reasons, you can set the - PCRE_NO_UTF8_CHECK option when calling pcre_exec(). You might want to - do this for the second and subsequent calls to pcre_exec() if you are - making repeated calls to find all the matches in a single subject - string. However, you should be sure that the value of startoffset - points to the start of a UTF-8 character. When PCRE_NO_UTF8_CHECK is - set, the effect of passing an invalid UTF-8 string as a subject, or a - value of startoffset that does not point to the start of a UTF-8 char- - acter, is undefined. Your program may crash. - - PCRE_PARTIAL - - This option turns on the partial matching feature. If the subject - string fails to match the pattern, but at some point during the match- - ing process the end of the subject was reached (that is, the subject - partially matches the pattern and the failure to match occurred only - because there were not enough subject characters), pcre_exec() returns - PCRE_ERROR_PARTIAL instead of PCRE_ERROR_NOMATCH. When PCRE_PARTIAL is - used, there are restrictions on what may appear in the pattern. These - are discussed in the pcrepartial documentation. - - The string to be matched by pcre_exec() - - The subject string is passed to pcre_exec() as a pointer in subject, a - length (in bytes) in length, and a starting byte offset in startoffset. - In UTF-8 mode, the byte offset must point to the start of a UTF-8 char- - acter. Unlike the pattern string, the subject may contain binary zero - bytes. When the starting offset is zero, the search for a match starts - at the beginning of the subject, and this is by far the most common - case. - - A non-zero starting offset is useful when searching for another match - in the same subject by calling pcre_exec() again after a previous suc- - cess. Setting startoffset differs from just passing over a shortened - string and setting PCRE_NOTBOL in the case of a pattern that begins - with any kind of lookbehind. For example, consider the pattern - - \Biss\B - - which finds occurrences of "iss" in the middle of words. (\B matches - only if the current position in the subject is not a word boundary.) - When applied to the string "Mississipi" the first call to pcre_exec() - finds the first occurrence. If pcre_exec() is called again with just - the remainder of the subject, namely "issipi", it does not match, - because \B is always false at the start of the subject, which is deemed - to be a word boundary. However, if pcre_exec() is passed the entire - string again, but with startoffset set to 4, it finds the second occur- - rence of "iss" because it is able to look behind the starting point to - discover that it is preceded by a letter. - - If a non-zero starting offset is passed when the pattern is anchored, - one attempt to match at the given offset is made. This can only succeed - if the pattern does not require the match to be at the start of the - subject. - - How pcre_exec() returns captured substrings - - In general, a pattern matches a certain portion of the subject, and in - addition, further substrings from the subject may be picked out by - parts of the pattern. Following the usage in Jeffrey Friedl's book, - this is called "capturing" in what follows, and the phrase "capturing - subpattern" is used for a fragment of a pattern that picks out a sub- - string. PCRE supports several other kinds of parenthesized subpattern - that do not cause substrings to be captured. - - Captured substrings are returned to the caller via a vector of integers - whose address is passed in ovector. The number of elements in the vec- - tor is passed in ovecsize, which must be a non-negative number. Note: - this argument is NOT the size of ovector in bytes. - - The first two-thirds of the vector is used to pass back captured sub- - strings, each substring using a pair of integers. The remaining third - of the vector is used as workspace by pcre_exec() while matching cap- - turing subpatterns, and is not available for passing back information. - The number passed in ovecsize should always be a multiple of three. If - it is not, it is rounded down. - - When a match is successful, information about captured substrings is - returned in pairs of integers, starting at the beginning of ovector, - and continuing up to two-thirds of its length at the most. The first - element of each pair is set to the byte offset of the first character - in a substring, and the second is set to the byte offset of the first - character after the end of a substring. Note: these values are always - byte offsets, even in UTF-8 mode. They are not character counts. - - The first pair of integers, ovector[0] and ovector[1], identify the - portion of the subject string matched by the entire pattern. The next - pair is used for the first capturing subpattern, and so on. The value - returned by pcre_exec() is one more than the highest numbered pair that - has been set. For example, if two substrings have been captured, the - returned value is 3. If there are no capturing subpatterns, the return - value from a successful match is 1, indicating that just the first pair - of offsets has been set. - - If a capturing subpattern is matched repeatedly, it is the last portion - of the string that it matched that is returned. - - If the vector is too small to hold all the captured substring offsets, - it is used as far as possible (up to two-thirds of its length), and the - function returns a value of zero. If the substring offsets are not of - interest, pcre_exec() may be called with ovector passed as NULL and - ovecsize as zero. However, if the pattern contains back references and - the ovector is not big enough to remember the related substrings, PCRE - has to get additional memory for use during matching. Thus it is usu- - ally advisable to supply an ovector. - - The pcre_info() function can be used to find out how many capturing - subpatterns there are in a compiled pattern. The smallest size for - ovector that will allow for n captured substrings, in addition to the - offsets of the substring matched by the whole pattern, is (n+1)*3. - - It is possible for capturing subpattern number n+1 to match some part - of the subject when subpattern n has not been used at all. For example, - if the string "abc" is matched against the pattern (a|(z))(bc) the - return from the function is 4, and subpatterns 1 and 3 are matched, but - 2 is not. When this happens, both values in the offset pairs corre- - sponding to unused subpatterns are set to -1. - - Offset values that correspond to unused subpatterns at the end of the - expression are also set to -1. For example, if the string "abc" is - matched against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not - matched. The return from the function is 2, because the highest used - capturing subpattern number is 1. However, you can refer to the offsets - for the second and third capturing subpatterns if you wish (assuming - the vector is large enough, of course). - - Some convenience functions are provided for extracting the captured - substrings as separate strings. These are described below. - - Error return values from pcre_exec() - - If pcre_exec() fails, it returns a negative number. The following are - defined in the header file: - - PCRE_ERROR_NOMATCH (-1) - - The subject string did not match the pattern. - - PCRE_ERROR_NULL (-2) - - Either code or subject was passed as NULL, or ovector was NULL and - ovecsize was not zero. - - PCRE_ERROR_BADOPTION (-3) - - An unrecognized bit was set in the options argument. - - PCRE_ERROR_BADMAGIC (-4) - - PCRE stores a 4-byte "magic number" at the start of the compiled code, - to catch the case when it is passed a junk pointer and to detect when a - pattern that was compiled in an environment of one endianness is run in - an environment with the other endianness. This is the error that PCRE - gives when the magic number is not present. - - PCRE_ERROR_UNKNOWN_OPCODE (-5) - - While running the pattern match, an unknown item was encountered in the - compiled pattern. This error could be caused by a bug in PCRE or by - overwriting of the compiled pattern. - - PCRE_ERROR_NOMEMORY (-6) - - If a pattern contains back references, but the ovector that is passed - to pcre_exec() is not big enough to remember the referenced substrings, - PCRE gets a block of memory at the start of matching to use for this - purpose. If the call via pcre_malloc() fails, this error is given. The - memory is automatically freed at the end of matching. - - PCRE_ERROR_NOSUBSTRING (-7) - - This error is used by the pcre_copy_substring(), pcre_get_substring(), - and pcre_get_substring_list() functions (see below). It is never - returned by pcre_exec(). - - PCRE_ERROR_MATCHLIMIT (-8) - - The backtracking limit, as specified by the match_limit field in a - pcre_extra structure (or defaulted) was reached. See the description - above. - - PCRE_ERROR_CALLOUT (-9) - - This error is never generated by pcre_exec() itself. It is provided for - use by callout functions that want to yield a distinctive error code. - See the pcrecallout documentation for details. - - PCRE_ERROR_BADUTF8 (-10) - - A string that contains an invalid UTF-8 byte sequence was passed as a - subject. - - PCRE_ERROR_BADUTF8_OFFSET (-11) - - The UTF-8 byte sequence that was passed as a subject was valid, but the - value of startoffset did not point to the beginning of a UTF-8 charac- - ter. - - PCRE_ERROR_PARTIAL (-12) - - The subject string did not match, but it did match partially. See the - pcrepartial documentation for details of partial matching. - - PCRE_ERROR_BADPARTIAL (-13) - - The PCRE_PARTIAL option was used with a compiled pattern containing - items that are not supported for partial matching. See the pcrepartial - documentation for details of partial matching. - - PCRE_ERROR_INTERNAL (-14) - - An unexpected internal error has occurred. This error could be caused - by a bug in PCRE or by overwriting of the compiled pattern. - - PCRE_ERROR_BADCOUNT (-15) - - This error is given if the value of the ovecsize argument is negative. - - PCRE_ERROR_RECURSIONLIMIT (-21) - - The internal recursion limit, as specified by the match_limit_recursion - field in a pcre_extra structure (or defaulted) was reached. See the - description above. - - PCRE_ERROR_BADNEWLINE (-23) - - An invalid combination of PCRE_NEWLINE_xxx options was given. - - Error numbers -16 to -20 and -22 are not used by pcre_exec(). - - -EXTRACTING CAPTURED SUBSTRINGS BY NUMBER - - int pcre_copy_substring(const char *subject, int *ovector, - int stringcount, int stringnumber, char *buffer, - int buffersize); - - int pcre_get_substring(const char *subject, int *ovector, - int stringcount, int stringnumber, - const char **stringptr); - - int pcre_get_substring_list(const char *subject, - int *ovector, int stringcount, const char ***listptr); - - Captured substrings can be accessed directly by using the offsets - returned by pcre_exec() in ovector. For convenience, the functions - pcre_copy_substring(), pcre_get_substring(), and pcre_get_sub- - string_list() are provided for extracting captured substrings as new, - separate, zero-terminated strings. These functions identify substrings - by number. The next section describes functions for extracting named - substrings. - - A substring that contains a binary zero is correctly extracted and has - a further zero added on the end, but the result is not, of course, a C - string. However, you can process such a string by referring to the - length that is returned by pcre_copy_substring() and pcre_get_sub- - string(). Unfortunately, the interface to pcre_get_substring_list() is - not adequate for handling strings containing binary zeros, because the - end of the final string is not independently indicated. - - The first three arguments are the same for all three of these func- - tions: subject is the subject string that has just been successfully - matched, ovector is a pointer to the vector of integer offsets that was - passed to pcre_exec(), and stringcount is the number of substrings that - were captured by the match, including the substring that matched the - entire regular expression. This is the value returned by pcre_exec() if - it is greater than zero. If pcre_exec() returned zero, indicating that - it ran out of space in ovector, the value passed as stringcount should - be the number of elements in the vector divided by three. - - The functions pcre_copy_substring() and pcre_get_substring() extract a - single substring, whose number is given as stringnumber. A value of - zero extracts the substring that matched the entire pattern, whereas - higher values extract the captured substrings. For pcre_copy_sub- - string(), the string is placed in buffer, whose length is given by - buffersize, while for pcre_get_substring() a new block of memory is - obtained via pcre_malloc, and its address is returned via stringptr. - The yield of the function is the length of the string, not including - the terminating zero, or one of these error codes: - - PCRE_ERROR_NOMEMORY (-6) - - The buffer was too small for pcre_copy_substring(), or the attempt to - get memory failed for pcre_get_substring(). - - PCRE_ERROR_NOSUBSTRING (-7) - - There is no substring whose number is stringnumber. - - The pcre_get_substring_list() function extracts all available sub- - strings and builds a list of pointers to them. All this is done in a - single block of memory that is obtained via pcre_malloc. The address of - the memory block is returned via listptr, which is also the start of - the list of string pointers. The end of the list is marked by a NULL - pointer. The yield of the function is zero if all went well, or the - error code - - PCRE_ERROR_NOMEMORY (-6) - - if the attempt to get the memory block failed. - - When any of these functions encounter a substring that is unset, which - can happen when capturing subpattern number n+1 matches some part of - the subject, but subpattern n has not been used at all, they return an - empty string. This can be distinguished from a genuine zero-length sub- - string by inspecting the appropriate offset in ovector, which is nega- - tive for unset substrings. - - The two convenience functions pcre_free_substring() and pcre_free_sub- - string_list() can be used to free the memory returned by a previous - call of pcre_get_substring() or pcre_get_substring_list(), respec- - tively. They do nothing more than call the function pointed to by - pcre_free, which of course could be called directly from a C program. - However, PCRE is used in some situations where it is linked via a spe- - cial interface to another programming language that cannot use - pcre_free directly; it is for these cases that the functions are pro- - vided. - - -EXTRACTING CAPTURED SUBSTRINGS BY NAME - - int pcre_get_stringnumber(const pcre *code, - const char *name); - - int pcre_copy_named_substring(const pcre *code, - const char *subject, int *ovector, - int stringcount, const char *stringname, - char *buffer, int buffersize); - - int pcre_get_named_substring(const pcre *code, - const char *subject, int *ovector, - int stringcount, const char *stringname, - const char **stringptr); - - To extract a substring by name, you first have to find associated num- - ber. For example, for this pattern - - (a+)b(?\d+)... - - the number of the subpattern called "xxx" is 2. If the name is known to - be unique (PCRE_DUPNAMES was not set), you can find the number from the - name by calling pcre_get_stringnumber(). The first argument is the com- - piled pattern, and the second is the name. The yield of the function is - the subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no - subpattern of that name. - - Given the number, you can extract the substring directly, or use one of - the functions described in the previous section. For convenience, there - are also two functions that do the whole job. - - Most of the arguments of pcre_copy_named_substring() and - pcre_get_named_substring() are the same as those for the similarly - named functions that extract by number. As these are described in the - previous section, they are not re-described here. There are just two - differences: - - First, instead of a substring number, a substring name is given. Sec- - ond, there is an extra argument, given at the start, which is a pointer - to the compiled pattern. This is needed in order to gain access to the - name-to-number translation table. - - These functions call pcre_get_stringnumber(), and if it succeeds, they - then call pcre_copy_substring() or pcre_get_substring(), as appropri- - ate. NOTE: If PCRE_DUPNAMES is set and there are duplicate names, the - behaviour may not be what you want (see the next section). - - Warning: If the pattern uses the "(?|" feature to set up multiple sub- - patterns with the same number, you cannot use names to distinguish - them, because names are not included in the compiled code. The matching - process uses only numbers. - - -DUPLICATE SUBPATTERN NAMES - - int pcre_get_stringtable_entries(const pcre *code, - const char *name, char **first, char **last); - - When a pattern is compiled with the PCRE_DUPNAMES option, names for - subpatterns are not required to be unique. Normally, patterns with - duplicate names are such that in any one match, only one of the named - subpatterns participates. An example is shown in the pcrepattern docu- - mentation. - - When duplicates are present, pcre_copy_named_substring() and - pcre_get_named_substring() return the first substring corresponding to - the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING - (-7) is returned; no data is returned. The pcre_get_stringnumber() - function returns one of the numbers that are associated with the name, - but it is not defined which it is. - - If you want to get full details of all captured substrings for a given - name, you must use the pcre_get_stringtable_entries() function. The - first argument is the compiled pattern, and the second is the name. The - third and fourth are pointers to variables which are updated by the - function. After it has run, they point to the first and last entries in - the name-to-number table for the given name. The function itself - returns the length of each entry, or PCRE_ERROR_NOSUBSTRING (-7) if - there are none. The format of the table is described above in the sec- - tion entitled Information about a pattern. Given all the relevant - entries for the name, you can extract each of their numbers, and hence - the captured data, if any. - - -FINDING ALL POSSIBLE MATCHES - - The traditional matching function uses a similar algorithm to Perl, - which stops when it finds the first match, starting at a given point in - the subject. If you want to find all possible matches, or the longest - possible match, consider using the alternative matching function (see - below) instead. If you cannot use the alternative function, but still - need to find all possible matches, you can kludge it up by making use - of the callout facility, which is described in the pcrecallout documen- - tation. - - What you have to do is to insert a callout right at the end of the pat- - tern. When your callout function is called, extract and save the cur- - rent matched substring. Then return 1, which forces pcre_exec() to - backtrack and try other alternatives. Ultimately, when it runs out of - matches, pcre_exec() will yield PCRE_ERROR_NOMATCH. - - -MATCHING A PATTERN: THE ALTERNATIVE FUNCTION - - int pcre_dfa_exec(const pcre *code, const pcre_extra *extra, - const char *subject, int length, int startoffset, - int options, int *ovector, int ovecsize, - int *workspace, int wscount); - - The function pcre_dfa_exec() is called to match a subject string - against a compiled pattern, using a matching algorithm that scans the - subject string just once, and does not backtrack. This has different - characteristics to the normal algorithm, and is not compatible with - Perl. Some of the features of PCRE patterns are not supported. Never- - theless, there are times when this kind of matching can be useful. For - a discussion of the two matching algorithms, see the pcrematching docu- - mentation. - - The arguments for the pcre_dfa_exec() function are the same as for - pcre_exec(), plus two extras. The ovector argument is used in a differ- - ent way, and this is described below. The other common arguments are - used in the same way as for pcre_exec(), so their description is not - repeated here. - - The two additional arguments provide workspace for the function. The - workspace vector should contain at least 20 elements. It is used for - keeping track of multiple paths through the pattern tree. More - workspace will be needed for patterns and subjects where there are a - lot of potential matches. - - Here is an example of a simple call to pcre_dfa_exec(): - - int rc; - int ovector[10]; - int wspace[20]; - rc = pcre_dfa_exec( - re, /* result of pcre_compile() */ - NULL, /* we didn't study the pattern */ - "some string", /* the subject string */ - 11, /* the length of the subject string */ - 0, /* start at offset 0 in the subject */ - 0, /* default options */ - ovector, /* vector of integers for substring information */ - 10, /* number of elements (NOT size in bytes) */ - wspace, /* working space vector */ - 20); /* number of elements (NOT size in bytes) */ - - Option bits for pcre_dfa_exec() - - The unused bits of the options argument for pcre_dfa_exec() must be - zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEW- - LINE_xxx, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, - PCRE_PARTIAL, PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last - three of these are the same as for pcre_exec(), so their description is - not repeated here. - - PCRE_PARTIAL - - This has the same general effect as it does for pcre_exec(), but the - details are slightly different. When PCRE_PARTIAL is set for - pcre_dfa_exec(), the return code PCRE_ERROR_NOMATCH is converted into - PCRE_ERROR_PARTIAL if the end of the subject is reached, there have - been no complete matches, but there is still at least one matching pos- - sibility. The portion of the string that provided the partial match is - set as the first matching string. - - PCRE_DFA_SHORTEST - - Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to - stop as soon as it has found one match. Because of the way the alterna- - tive algorithm works, this is necessarily the shortest possible match - at the first possible matching point in the subject string. - - PCRE_DFA_RESTART - - When pcre_dfa_exec() is called with the PCRE_PARTIAL option, and - returns a partial match, it is possible to call it again, with addi- - tional subject characters, and have it continue with the same match. - The PCRE_DFA_RESTART option requests this action; when it is set, the - workspace and wscount options must reference the same vector as before - because data about the match so far is left in them after a partial - match. There is more discussion of this facility in the pcrepartial - documentation. - - Successful returns from pcre_dfa_exec() - - When pcre_dfa_exec() succeeds, it may have matched more than one sub- - string in the subject. Note, however, that all the matches from one run - of the function start at the same point in the subject. The shorter - matches are all initial substrings of the longer matches. For example, - if the pattern - - <.*> - - is matched against the string - - This is no more - - the three matched strings are - - - - - - On success, the yield of the function is a number greater than zero, - which is the number of matched substrings. The substrings themselves - are returned in ovector. Each string uses two elements; the first is - the offset to the start, and the second is the offset to the end. In - fact, all the strings have the same start offset. (Space could have - been saved by giving this only once, but it was decided to retain some - compatibility with the way pcre_exec() returns data, even though the - meaning of the strings is different.) - - The strings are returned in reverse order of length; that is, the long- - est matching string is given first. If there were too many matches to - fit into ovector, the yield of the function is zero, and the vector is - filled with the longest matches. - - Error returns from pcre_dfa_exec() - - The pcre_dfa_exec() function returns a negative number when it fails. - Many of the errors are the same as for pcre_exec(), and these are - described above. There are in addition the following errors that are - specific to pcre_dfa_exec(): - - PCRE_ERROR_DFA_UITEM (-16) - - This return is given if pcre_dfa_exec() encounters an item in the pat- - tern that it does not support, for instance, the use of \C or a back - reference. - - PCRE_ERROR_DFA_UCOND (-17) - - This return is given if pcre_dfa_exec() encounters a condition item - that uses a back reference for the condition, or a test for recursion - in a specific group. These are not supported. - - PCRE_ERROR_DFA_UMLIMIT (-18) - - This return is given if pcre_dfa_exec() is called with an extra block - that contains a setting of the match_limit field. This is not supported - (it is meaningless). - - PCRE_ERROR_DFA_WSSIZE (-19) - - This return is given if pcre_dfa_exec() runs out of space in the - workspace vector. - - PCRE_ERROR_DFA_RECURSE (-20) - - When a recursive subpattern is processed, the matching function calls - itself recursively, using private vectors for ovector and workspace. - This error is given if the output vector is not large enough. This - should be extremely rare, as a vector of size 1000 is used. - - -SEE ALSO - - pcrebuild(3), pcrecallout(3), pcrecpp(3)(3), pcrematching(3), pcrepar- - tial(3), pcreposix(3), pcreprecompile(3), pcresample(3), pcrestack(3). - - -AUTHOR - - Philip Hazel - University Computing Service - Cambridge CB2 3QH, England. - - -REVISION - - Last updated: 11 April 2009 - Copyright (c) 1997-2009 University of Cambridge. ------------------------------------------------------------------------------- - - -PCRECALLOUT(3) PCRECALLOUT(3) - - -NAME - PCRE - Perl-compatible regular expressions - - -PCRE CALLOUTS - - int (*pcre_callout)(pcre_callout_block *); - - PCRE provides a feature called "callout", which is a means of temporar- - ily passing control to the caller of PCRE in the middle of pattern - matching. The caller of PCRE provides an external function by putting - its entry point in the global variable pcre_callout. By default, this - variable contains NULL, which disables all calling out. - - Within a regular expression, (?C) indicates the points at which the - external function is to be called. Different callout points can be - identified by putting a number less than 256 after the letter C. The - default value is zero. For example, this pattern has two callout - points: - - (?C1)abc(?C2)def - - If the PCRE_AUTO_CALLOUT option bit is set when pcre_compile() is - called, PCRE automatically inserts callouts, all with number 255, - before each item in the pattern. For example, if PCRE_AUTO_CALLOUT is - used with the pattern - - A(\d{2}|--) - - it is processed as if it were - - (?C255)A(?C255)((?C255)\d{2}(?C255)|(?C255)-(?C255)-(?C255))(?C255) - - Notice that there is a callout before and after each parenthesis and - alternation bar. Automatic callouts can be used for tracking the - progress of pattern matching. The pcretest command has an option that - sets automatic callouts; when it is used, the output indicates how the - pattern is matched. This is useful information when you are trying to - optimize the performance of a particular pattern. - - -MISSING CALLOUTS - - You should be aware that, because of optimizations in the way PCRE - matches patterns by default, callouts sometimes do not happen. For - example, if the pattern is - - ab(?C4)cd - - PCRE knows that any matching string must contain the letter "d". If the - subject string is "abyz", the lack of "d" means that matching doesn't - ever start, and the callout is never reached. However, with "abyd", - though the result is still no match, the callout is obeyed. - - You can disable these optimizations by passing the PCRE_NO_START_OPTI- - MIZE option to pcre_exec() or pcre_dfa_exec(). This slows down the - matching process, but does ensure that callouts such as the example - above are obeyed. - - -THE CALLOUT INTERFACE - - During matching, when PCRE reaches a callout point, the external func- - tion defined by pcre_callout is called (if it is set). This applies to - both the pcre_exec() and the pcre_dfa_exec() matching functions. The - only argument to the callout function is a pointer to a pcre_callout - block. This structure contains the following fields: - - int version; - int callout_number; - int *offset_vector; - const char *subject; - int subject_length; - int start_match; - int current_position; - int capture_top; - int capture_last; - void *callout_data; - int pattern_position; - int next_item_length; - - The version field is an integer containing the version number of the - block format. The initial version was 0; the current version is 1. The - version number will change again in future if additional fields are - added, but the intention is never to remove any of the existing fields. - - The callout_number field contains the number of the callout, as com- - piled into the pattern (that is, the number after ?C for manual call- - outs, and 255 for automatically generated callouts). - - The offset_vector field is a pointer to the vector of offsets that was - passed by the caller to pcre_exec() or pcre_dfa_exec(). When - pcre_exec() is used, the contents can be inspected in order to extract - substrings that have been matched so far, in the same way as for - extracting substrings after a match has completed. For pcre_dfa_exec() - this field is not useful. - - The subject and subject_length fields contain copies of the values that - were passed to pcre_exec(). - - The start_match field normally contains the offset within the subject - at which the current match attempt started. However, if the escape - sequence \K has been encountered, this value is changed to reflect the - modified starting point. If the pattern is not anchored, the callout - function may be called several times from the same point in the pattern - for different starting points in the subject. - - The current_position field contains the offset within the subject of - the current match pointer. - - When the pcre_exec() function is used, the capture_top field contains - one more than the number of the highest numbered captured substring so - far. If no substrings have been captured, the value of capture_top is - one. This is always the case when pcre_dfa_exec() is used, because it - does not support captured substrings. - - The capture_last field contains the number of the most recently cap- - tured substring. If no substrings have been captured, its value is -1. - This is always the case when pcre_dfa_exec() is used. - - The callout_data field contains a value that is passed to pcre_exec() - or pcre_dfa_exec() specifically so that it can be passed back in call- - outs. It is passed in the pcre_callout field of the pcre_extra data - structure. If no such data was passed, the value of callout_data in a - pcre_callout block is NULL. There is a description of the pcre_extra - structure in the pcreapi documentation. - - The pattern_position field is present from version 1 of the pcre_call- - out structure. It contains the offset to the next item to be matched in - the pattern string. - - The next_item_length field is present from version 1 of the pcre_call- - out structure. It contains the length of the next item to be matched in - the pattern string. When the callout immediately precedes an alterna- - tion bar, a closing parenthesis, or the end of the pattern, the length - is zero. When the callout precedes an opening parenthesis, the length - is that of the entire subpattern. - - The pattern_position and next_item_length fields are intended to help - in distinguishing between different automatic callouts, which all have - the same callout number. However, they are set for all callouts. - - -RETURN VALUES - - The external callout function returns an integer to PCRE. If the value - is zero, matching proceeds as normal. If the value is greater than - zero, matching fails at the current point, but the testing of other - matching possibilities goes ahead, just as if a lookahead assertion had - failed. If the value is less than zero, the match is abandoned, and - pcre_exec() (or pcre_dfa_exec()) returns the negative value. - - Negative values should normally be chosen from the set of - PCRE_ERROR_xxx values. In particular, PCRE_ERROR_NOMATCH forces a stan- - dard "no match" failure. The error number PCRE_ERROR_CALLOUT is - reserved for use by callout functions; it will never be used by PCRE - itself. - - -AUTHOR - - Philip Hazel - University Computing Service - Cambridge CB2 3QH, England. - - -REVISION - - Last updated: 15 March 2009 - Copyright (c) 1997-2009 University of Cambridge. ------------------------------------------------------------------------------- - - -PCRECOMPAT(3) PCRECOMPAT(3) - - -NAME - PCRE - Perl-compatible regular expressions - - -DIFFERENCES BETWEEN PCRE AND PERL - - This document describes the differences in the ways that PCRE and Perl - handle regular expressions. The differences described here are mainly - with respect to Perl 5.8, though PCRE versions 7.0 and later contain - some features that are expected to be in the forthcoming Perl 5.10. - - 1. PCRE has only a subset of Perl's UTF-8 and Unicode support. Details - of what it does have are given in the section on UTF-8 support in the - main pcre page. - - 2. PCRE does not allow repeat quantifiers on lookahead assertions. Perl - permits them, but they do not mean what you might think. For example, - (?!a){3} does not assert that the next three characters are not "a". It - just asserts that the next character is not "a" three times. - - 3. Capturing subpatterns that occur inside negative lookahead asser- - tions are counted, but their entries in the offsets vector are never - set. Perl sets its numerical variables from any such patterns that are - matched before the assertion fails to match something (thereby succeed- - ing), but only if the negative lookahead assertion contains just one - branch. - - 4. Though binary zero characters are supported in the subject string, - they are not allowed in a pattern string because it is passed as a nor- - mal C string, terminated by zero. The escape sequence \0 can be used in - the pattern to represent a binary zero. - - 5. The following Perl escape sequences are not supported: \l, \u, \L, - \U, and \N. In fact these are implemented by Perl's general string-han- - dling and are not part of its pattern matching engine. If any of these - are encountered by PCRE, an error is generated. - - 6. The Perl escape sequences \p, \P, and \X are supported only if PCRE - is built with Unicode character property support. The properties that - can be tested with \p and \P are limited to the general category prop- - erties such as Lu and Nd, script names such as Greek or Han, and the - derived properties Any and L&. - - 7. PCRE does support the \Q...\E escape for quoting substrings. Charac- - ters in between are treated as literals. This is slightly different - from Perl in that $ and @ are also handled as literals inside the - quotes. In Perl, they cause variable interpolation (but of course PCRE - does not have variables). Note the following examples: - - Pattern PCRE matches Perl matches - - \Qabc$xyz\E abc$xyz abc followed by the - contents of $xyz - \Qabc\$xyz\E abc\$xyz abc\$xyz - \Qabc\E\$\Qxyz\E abc$xyz abc$xyz - - The \Q...\E sequence is recognized both inside and outside character - classes. - - 8. Fairly obviously, PCRE does not support the (?{code}) and (??{code}) - constructions. However, there is support for recursive patterns. This - is not available in Perl 5.8, but will be in Perl 5.10. Also, the PCRE - "callout" feature allows an external function to be called during pat- - tern matching. See the pcrecallout documentation for details. - - 9. Subpatterns that are called recursively or as "subroutines" are - always treated as atomic groups in PCRE. This is like Python, but - unlike Perl. - - 10. There are some differences that are concerned with the settings of - captured strings when part of a pattern is repeated. For example, - matching "aba" against the pattern /^(a(b)?)+$/ in Perl leaves $2 - unset, but in PCRE it is set to "b". - - 11. PCRE does support Perl 5.10's backtracking verbs (*ACCEPT), - (*FAIL), (*F), (*COMMIT), (*PRUNE), (*SKIP), and (*THEN), but only in - the forms without an argument. PCRE does not support (*MARK). If - (*ACCEPT) is within capturing parentheses, PCRE does not set that cap- - ture group; this is different to Perl. - - 12. PCRE provides some extensions to the Perl regular expression facil- - ities. Perl 5.10 will include new features that are not in earlier - versions, some of which (such as named parentheses) have been in PCRE - for some time. This list is with respect to Perl 5.10: - - (a) Although lookbehind assertions must match fixed length strings, - each alternative branch of a lookbehind assertion can match a different - length of string. Perl requires them all to have the same length. - - (b) If PCRE_DOLLAR_ENDONLY is set and PCRE_MULTILINE is not set, the $ - meta-character matches only at the very end of the string. - - (c) If PCRE_EXTRA is set, a backslash followed by a letter with no spe- - cial meaning is faulted. Otherwise, like Perl, the backslash is quietly - ignored. (Perl can be made to issue a warning.) - - (d) If PCRE_UNGREEDY is set, the greediness of the repetition quanti- - fiers is inverted, that is, by default they are not greedy, but if fol- - lowed by a question mark they are. - - (e) PCRE_ANCHORED can be used at matching time to force a pattern to be - tried only at the first matching position in the subject string. - - (f) The PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, and PCRE_NO_AUTO_CAP- - TURE options for pcre_exec() have no Perl equivalents. - - (g) The \R escape sequence can be restricted to match only CR, LF, or - CRLF by the PCRE_BSR_ANYCRLF option. - - (h) The callout facility is PCRE-specific. - - (i) The partial matching facility is PCRE-specific. - - (j) Patterns compiled by PCRE can be saved and re-used at a later time, - even on different hosts that have the other endianness. - - (k) The alternative matching function (pcre_dfa_exec()) matches in a - different way and is not Perl-compatible. - - (l) PCRE recognizes some special sequences such as (*CR) at the start - of a pattern that set overall options that cannot be changed within the - pattern. - - -AUTHOR - - Philip Hazel - University Computing Service - Cambridge CB2 3QH, England. - - -REVISION - - Last updated: 11 September 2007 - Copyright (c) 1997-2007 University of Cambridge. ------------------------------------------------------------------------------- - - -PCREPATTERN(3) PCREPATTERN(3) - - -NAME - PCRE - Perl-compatible regular expressions - - -PCRE REGULAR EXPRESSION DETAILS - - The syntax and semantics of the regular expressions that are supported - by PCRE are described in detail below. There is a quick-reference syn- - tax summary in the pcresyntax page. PCRE tries to match Perl syntax and - semantics as closely as it can. PCRE also supports some alternative - regular expression syntax (which does not conflict with the Perl syn- - tax) in order to provide some compatibility with regular expressions in - Python, .NET, and Oniguruma. - - Perl's regular expressions are described in its own documentation, and - regular expressions in general are covered in a number of books, some - of which have copious examples. Jeffrey Friedl's "Mastering Regular - Expressions", published by O'Reilly, covers regular expressions in - great detail. This description of PCRE's regular expressions is - intended as reference material. - - The original operation of PCRE was on strings of one-byte characters. - However, there is now also support for UTF-8 character strings. To use - this, you must build PCRE to include UTF-8 support, and then call - pcre_compile() with the PCRE_UTF8 option. There is also a special - sequence that can be given at the start of a pattern: - - (*UTF8) - - Starting a pattern with this sequence is equivalent to setting the - PCRE_UTF8 option. This feature is not Perl-compatible. How setting - UTF-8 mode affects pattern matching is mentioned in several places - below. There is also a summary of UTF-8 features in the section on - UTF-8 support in the main pcre page. - - The remainder of this document discusses the patterns that are sup- - ported by PCRE when its main matching function, pcre_exec(), is used. - From release 6.0, PCRE offers a second matching function, - pcre_dfa_exec(), which matches using a different algorithm that is not - Perl-compatible. Some of the features discussed below are not available - when pcre_dfa_exec() is used. The advantages and disadvantages of the - alternative function, and how it differs from the normal function, are - discussed in the pcrematching page. - - -NEWLINE CONVENTIONS - - PCRE supports five different conventions for indicating line breaks in - strings: a single CR (carriage return) character, a single LF (line- - feed) character, the two-character sequence CRLF, any of the three pre- - ceding, or any Unicode newline sequence. The pcreapi page has further - discussion about newlines, and shows how to set the newline convention - in the options arguments for the compiling and matching functions. - - It is also possible to specify a newline convention by starting a pat- - tern string with one of the following five sequences: - - (*CR) carriage return - (*LF) linefeed - (*CRLF) carriage return, followed by linefeed - (*ANYCRLF) any of the three above - (*ANY) all Unicode newline sequences - - These override the default and the options given to pcre_compile(). For - example, on a Unix system where LF is the default newline sequence, the - pattern - - (*CR)a.b - - changes the convention to CR. That pattern matches "a\nb" because LF is - no longer a newline. Note that these special settings, which are not - Perl-compatible, are recognized only at the very start of a pattern, - and that they must be in upper case. If more than one of them is - present, the last one is used. - - The newline convention does not affect what the \R escape sequence - matches. By default, this is any Unicode newline sequence, for Perl - compatibility. However, this can be changed; see the description of \R - in the section entitled "Newline sequences" below. A change of \R set- - ting can be combined with a change of newline convention. - - -CHARACTERS AND METACHARACTERS - - A regular expression is a pattern that is matched against a subject - string from left to right. Most characters stand for themselves in a - pattern, and match the corresponding characters in the subject. As a - trivial example, the pattern - - The quick brown fox - - matches a portion of a subject string that is identical to itself. When - caseless matching is specified (the PCRE_CASELESS option), letters are - matched independently of case. In UTF-8 mode, PCRE always understands - the concept of case for characters whose values are less than 128, so - caseless matching is always possible. For characters with higher val- - ues, the concept of case is supported if PCRE is compiled with Unicode - property support, but not otherwise. If you want to use caseless - matching for characters 128 and above, you must ensure that PCRE is - compiled with Unicode property support as well as with UTF-8 support. - - The power of regular expressions comes from the ability to include - alternatives and repetitions in the pattern. These are encoded in the - pattern by the use of metacharacters, which do not stand for themselves - but instead are interpreted in some special way. - - There are two different sets of metacharacters: those that are recog- - nized anywhere in the pattern except within square brackets, and those - that are recognized within square brackets. Outside square brackets, - the metacharacters are as follows: - - \ general escape character with several uses - ^ assert start of string (or line, in multiline mode) - $ assert end of string (or line, in multiline mode) - . match any character except newline (by default) - [ start character class definition - | start of alternative branch - ( start subpattern - ) end subpattern - ? extends the meaning of ( - also 0 or 1 quantifier - also quantifier minimizer - * 0 or more quantifier - + 1 or more quantifier - also "possessive quantifier" - { start min/max quantifier - - Part of a pattern that is in square brackets is called a "character - class". In a character class the only metacharacters are: - - \ general escape character - ^ negate the class, but only if the first character - - indicates character range - [ POSIX character class (only if followed by POSIX - syntax) - ] terminates the character class - - The following sections describe the use of each of the metacharacters. - - -BACKSLASH - - The backslash character has several uses. Firstly, if it is followed by - a non-alphanumeric character, it takes away any special meaning that - character may have. This use of backslash as an escape character - applies both inside and outside character classes. - - For example, if you want to match a * character, you write \* in the - pattern. This escaping action applies whether or not the following - character would otherwise be interpreted as a metacharacter, so it is - always safe to precede a non-alphanumeric with backslash to specify - that it stands for itself. In particular, if you want to match a back- - slash, you write \\. - - If a pattern is compiled with the PCRE_EXTENDED option, whitespace in - the pattern (other than in a character class) and characters between a - # outside a character class and the next newline are ignored. An escap- - ing backslash can be used to include a whitespace or # character as - part of the pattern. - - If you want to remove the special meaning from a sequence of charac- - ters, you can do so by putting them between \Q and \E. This is differ- - ent from Perl in that $ and @ are handled as literals in \Q...\E - sequences in PCRE, whereas in Perl, $ and @ cause variable interpola- - tion. Note the following examples: - - Pattern PCRE matches Perl matches - - \Qabc$xyz\E abc$xyz abc followed by the - contents of $xyz - \Qabc\$xyz\E abc\$xyz abc\$xyz - \Qabc\E\$\Qxyz\E abc$xyz abc$xyz - - The \Q...\E sequence is recognized both inside and outside character - classes. - - Non-printing characters - - A second use of backslash provides a way of encoding non-printing char- - acters in patterns in a visible manner. There is no restriction on the - appearance of non-printing characters, apart from the binary zero that - terminates a pattern, but when a pattern is being prepared by text - editing, it is usually easier to use one of the following escape - sequences than the binary character it represents: - - \a alarm, that is, the BEL character (hex 07) - \cx "control-x", where x is any character - \e escape (hex 1B) - \f formfeed (hex 0C) - \n linefeed (hex 0A) - \r carriage return (hex 0D) - \t tab (hex 09) - \ddd character with octal code ddd, or backreference - \xhh character with hex code hh - \x{hhh..} character with hex code hhh.. - - The precise effect of \cx is as follows: if x is a lower case letter, - it is converted to upper case. Then bit 6 of the character (hex 40) is - inverted. Thus \cz becomes hex 1A, but \c{ becomes hex 3B, while \c; - becomes hex 7B. - - After \x, from zero to two hexadecimal digits are read (letters can be - in upper or lower case). Any number of hexadecimal digits may appear - between \x{ and }, but the value of the character code must be less - than 256 in non-UTF-8 mode, and less than 2**31 in UTF-8 mode. That is, - the maximum value in hexadecimal is 7FFFFFFF. Note that this is bigger - than the largest Unicode code point, which is 10FFFF. - - If characters other than hexadecimal digits appear between \x{ and }, - or if there is no terminating }, this form of escape is not recognized. - Instead, the initial \x will be interpreted as a basic hexadecimal - escape, with no following digits, giving a character whose value is - zero. - - Characters whose value is less than 256 can be defined by either of the - two syntaxes for \x. There is no difference in the way they are han- - dled. For example, \xdc is exactly the same as \x{dc}. - - After \0 up to two further octal digits are read. If there are fewer - than two digits, just those that are present are used. Thus the - sequence \0\x\07 specifies two binary zeros followed by a BEL character - (code value 7). Make sure you supply two digits after the initial zero - if the pattern character that follows is itself an octal digit. - - The handling of a backslash followed by a digit other than 0 is compli- - cated. Outside a character class, PCRE reads it and any following dig- - its as a decimal number. If the number is less than 10, or if there - have been at least that many previous capturing left parentheses in the - expression, the entire sequence is taken as a back reference. A - description of how this works is given later, following the discussion - of parenthesized subpatterns. - - Inside a character class, or if the decimal number is greater than 9 - and there have not been that many capturing subpatterns, PCRE re-reads - up to three octal digits following the backslash, and uses them to gen- - erate a data character. Any subsequent digits stand for themselves. In - non-UTF-8 mode, the value of a character specified in octal must be - less than \400. In UTF-8 mode, values up to \777 are permitted. For - example: - - \040 is another way of writing a space - \40 is the same, provided there are fewer than 40 - previous capturing subpatterns - \7 is always a back reference - \11 might be a back reference, or another way of - writing a tab - \011 is always a tab - \0113 is a tab followed by the character "3" - \113 might be a back reference, otherwise the - character with octal code 113 - \377 might be a back reference, otherwise - the byte consisting entirely of 1 bits - \81 is either a back reference, or a binary zero - followed by the two characters "8" and "1" - - Note that octal values of 100 or greater must not be introduced by a - leading zero, because no more than three octal digits are ever read. - - All the sequences that define a single character value can be used both - inside and outside character classes. In addition, inside a character - class, the sequence \b is interpreted as the backspace character (hex - 08), and the sequences \R and \X are interpreted as the characters "R" - and "X", respectively. Outside a character class, these sequences have - different meanings (see below). - - Absolute and relative back references - - The sequence \g followed by an unsigned or a negative number, option- - ally enclosed in braces, is an absolute or relative back reference. A - named back reference can be coded as \g{name}. Back references are dis- - cussed later, following the discussion of parenthesized subpatterns. - - Absolute and relative subroutine calls - - For compatibility with Oniguruma, the non-Perl syntax \g followed by a - name or a number enclosed either in angle brackets or single quotes, is - an alternative syntax for referencing a subpattern as a "subroutine". - Details are discussed later. Note that \g{...} (Perl syntax) and - \g<...> (Oniguruma syntax) are not synonymous. The former is a back - reference; the latter is a subroutine call. - - Generic character types - - Another use of backslash is for specifying generic character types. The - following are always recognized: - - \d any decimal digit - \D any character that is not a decimal digit - \h any horizontal whitespace character - \H any character that is not a horizontal whitespace character - \s any whitespace character - \S any character that is not a whitespace character - \v any vertical whitespace character - \V any character that is not a vertical whitespace character - \w any "word" character - \W any "non-word" character - - Each pair of escape sequences partitions the complete set of characters - into two disjoint sets. Any given character matches one, and only one, - of each pair. - - These character type sequences can appear both inside and outside char- - acter classes. They each match one character of the appropriate type. - If the current matching point is at the end of the subject string, all - of them fail, since there is no character to match. - - For compatibility with Perl, \s does not match the VT character (code - 11). This makes it different from the the POSIX "space" class. The \s - characters are HT (9), LF (10), FF (12), CR (13), and space (32). If - "use locale;" is included in a Perl script, \s may match the VT charac- - ter. In PCRE, it never does. - - In UTF-8 mode, characters with values greater than 128 never match \d, - \s, or \w, and always match \D, \S, and \W. This is true even when Uni- - code character property support is available. These sequences retain - their original meanings from before UTF-8 support was available, mainly - for efficiency reasons. Note that this also affects \b, because it is - defined in terms of \w and \W. - - The sequences \h, \H, \v, and \V are Perl 5.10 features. In contrast to - the other sequences, these do match certain high-valued codepoints in - UTF-8 mode. The horizontal space characters are: - - U+0009 Horizontal tab - U+0020 Space - U+00A0 Non-break space - U+1680 Ogham space mark - U+180E Mongolian vowel separator - U+2000 En quad - U+2001 Em quad - U+2002 En space - U+2003 Em space - U+2004 Three-per-em space - U+2005 Four-per-em space - U+2006 Six-per-em space - U+2007 Figure space - U+2008 Punctuation space - U+2009 Thin space - U+200A Hair space - U+202F Narrow no-break space - U+205F Medium mathematical space - U+3000 Ideographic space - - The vertical space characters are: - - U+000A Linefeed - U+000B Vertical tab - U+000C Formfeed - U+000D Carriage return - U+0085 Next line - U+2028 Line separator - U+2029 Paragraph separator - - A "word" character is an underscore or any character less than 256 that - is a letter or digit. The definition of letters and digits is con- - trolled by PCRE's low-valued character tables, and may vary if locale- - specific matching is taking place (see "Locale support" in the pcreapi - page). For example, in a French locale such as "fr_FR" in Unix-like - systems, or "french" in Windows, some character codes greater than 128 - are used for accented letters, and these are matched by \w. The use of - locales with Unicode is discouraged. - - Newline sequences - - Outside a character class, by default, the escape sequence \R matches - any Unicode newline sequence. This is a Perl 5.10 feature. In non-UTF-8 - mode \R is equivalent to the following: - - (?>\r\n|\n|\x0b|\f|\r|\x85) - - This is an example of an "atomic group", details of which are given - below. This particular group matches either the two-character sequence - CR followed by LF, or one of the single characters LF (linefeed, - U+000A), VT (vertical tab, U+000B), FF (formfeed, U+000C), CR (carriage - return, U+000D), or NEL (next line, U+0085). The two-character sequence - is treated as a single unit that cannot be split. - - In UTF-8 mode, two additional characters whose codepoints are greater - than 255 are added: LS (line separator, U+2028) and PS (paragraph sepa- - rator, U+2029). Unicode character property support is not needed for - these characters to be recognized. - - It is possible to restrict \R to match only CR, LF, or CRLF (instead of - the complete set of Unicode line endings) by setting the option - PCRE_BSR_ANYCRLF either at compile time or when the pattern is matched. - (BSR is an abbrevation for "backslash R".) This can be made the default - when PCRE is built; if this is the case, the other behaviour can be - requested via the PCRE_BSR_UNICODE option. It is also possible to - specify these settings by starting a pattern string with one of the - following sequences: - - (*BSR_ANYCRLF) CR, LF, or CRLF only - (*BSR_UNICODE) any Unicode newline sequence - - These override the default and the options given to pcre_compile(), but - they can be overridden by options given to pcre_exec(). Note that these - special settings, which are not Perl-compatible, are recognized only at - the very start of a pattern, and that they must be in upper case. If - more than one of them is present, the last one is used. They can be - combined with a change of newline convention, for example, a pattern - can start with: - - (*ANY)(*BSR_ANYCRLF) - - Inside a character class, \R matches the letter "R". - - Unicode character properties - - When PCRE is built with Unicode character property support, three addi- - tional escape sequences that match characters with specific properties - are available. When not in UTF-8 mode, these sequences are of course - limited to testing characters whose codepoints are less than 256, but - they do work in this mode. The extra escape sequences are: - - \p{xx} a character with the xx property - \P{xx} a character without the xx property - \X an extended Unicode sequence - - The property names represented by xx above are limited to the Unicode - script names, the general category properties, and "Any", which matches - any character (including newline). Other properties such as "InMusical- - Symbols" are not currently supported by PCRE. Note that \P{Any} does - not match any characters, so always causes a match failure. - - Sets of Unicode characters are defined as belonging to certain scripts. - A character from one of these sets can be matched using a script name. - For example: - - \p{Greek} - \P{Han} - - Those that are not part of an identified script are lumped together as - "Common". The current list of scripts is: - - Arabic, Armenian, Balinese, Bengali, Bopomofo, Braille, Buginese, - Buhid, Canadian_Aboriginal, Cherokee, Common, Coptic, Cuneiform, - Cypriot, Cyrillic, Deseret, Devanagari, Ethiopic, Georgian, Glagolitic, - Gothic, Greek, Gujarati, Gurmukhi, Han, Hangul, Hanunoo, Hebrew, Hira- - gana, Inherited, Kannada, Katakana, Kharoshthi, Khmer, Lao, Latin, - Limbu, Linear_B, Malayalam, Mongolian, Myanmar, New_Tai_Lue, Nko, - Ogham, Old_Italic, Old_Persian, Oriya, Osmanya, Phags_Pa, Phoenician, - Runic, Shavian, Sinhala, Syloti_Nagri, Syriac, Tagalog, Tagbanwa, - Tai_Le, Tamil, Telugu, Thaana, Thai, Tibetan, Tifinagh, Ugaritic, Yi. - - Each character has exactly one general category property, specified by - a two-letter abbreviation. For compatibility with Perl, negation can be - specified by including a circumflex between the opening brace and the - property name. For example, \p{^Lu} is the same as \P{Lu}. - - If only one letter is specified with \p or \P, it includes all the gen- - eral category properties that start with that letter. In this case, in - the absence of negation, the curly brackets in the escape sequence are - optional; these two examples have the same effect: - - \p{L} - \pL - - The following general category property codes are supported: - - C Other - Cc Control - Cf Format - Cn Unassigned - Co Private use - Cs Surrogate - - L Letter - Ll Lower case letter - Lm Modifier letter - Lo Other letter - Lt Title case letter - Lu Upper case letter - - M Mark - Mc Spacing mark - Me Enclosing mark - Mn Non-spacing mark - - N Number - Nd Decimal number - Nl Letter number - No Other number - - P Punctuation - Pc Connector punctuation - Pd Dash punctuation - Pe Close punctuation - Pf Final punctuation - Pi Initial punctuation - Po Other punctuation - Ps Open punctuation - - S Symbol - Sc Currency symbol - Sk Modifier symbol - Sm Mathematical symbol - So Other symbol - - Z Separator - Zl Line separator - Zp Paragraph separator - Zs Space separator - - The special property L& is also supported: it matches a character that - has the Lu, Ll, or Lt property, in other words, a letter that is not - classified as a modifier or "other". - - The Cs (Surrogate) property applies only to characters in the range - U+D800 to U+DFFF. Such characters are not valid in UTF-8 strings (see - RFC 3629) and so cannot be tested by PCRE, unless UTF-8 validity check- - ing has been turned off (see the discussion of PCRE_NO_UTF8_CHECK in - the pcreapi page). - - The long synonyms for these properties that Perl supports (such as - \p{Letter}) are not supported by PCRE, nor is it permitted to prefix - any of these properties with "Is". - - No character that is in the Unicode table has the Cn (unassigned) prop- - erty. Instead, this property is assumed for any code point that is not - in the Unicode table. - - Specifying caseless matching does not affect these escape sequences. - For example, \p{Lu} always matches only upper case letters. - - The \X escape matches any number of Unicode characters that form an - extended Unicode sequence. \X is equivalent to - - (?>\PM\pM*) - - That is, it matches a character without the "mark" property, followed - by zero or more characters with the "mark" property, and treats the - sequence as an atomic group (see below). Characters with the "mark" - property are typically accents that affect the preceding character. - None of them have codepoints less than 256, so in non-UTF-8 mode \X - matches any one character. - - Matching characters by Unicode property is not fast, because PCRE has - to search a structure that contains data for over fifteen thousand - characters. That is why the traditional escape sequences such as \d and - \w do not use Unicode properties in PCRE. - - Resetting the match start - - The escape sequence \K, which is a Perl 5.10 feature, causes any previ- - ously matched characters not to be included in the final matched - sequence. For example, the pattern: - - foo\Kbar - - matches "foobar", but reports that it has matched "bar". This feature - is similar to a lookbehind assertion (described below). However, in - this case, the part of the subject before the real match does not have - to be of fixed length, as lookbehind assertions do. The use of \K does - not interfere with the setting of captured substrings. For example, - when the pattern - - (foo)\Kbar - - matches "foobar", the first substring is still set to "foo". - - Simple assertions - - The final use of backslash is for certain simple assertions. An asser- - tion specifies a condition that has to be met at a particular point in - a match, without consuming any characters from the subject string. The - use of subpatterns for more complicated assertions is described below. - The backslashed assertions are: - - \b matches at a word boundary - \B matches when not at a word boundary - \A matches at the start of the subject - \Z matches at the end of the subject - also matches before a newline at the end of the subject - \z matches only at the end of the subject - \G matches at the first matching position in the subject - - These assertions may not appear in character classes (but note that \b - has a different meaning, namely the backspace character, inside a char- - acter class). - - A word boundary is a position in the subject string where the current - character and the previous character do not both match \w or \W (i.e. - one matches \w and the other matches \W), or the start or end of the - string if the first or last character matches \w, respectively. - - The \A, \Z, and \z assertions differ from the traditional circumflex - and dollar (described in the next section) in that they only ever match - at the very start and end of the subject string, whatever options are - set. Thus, they are independent of multiline mode. These three asser- - tions are not affected by the PCRE_NOTBOL or PCRE_NOTEOL options, which - affect only the behaviour of the circumflex and dollar metacharacters. - However, if the startoffset argument of pcre_exec() is non-zero, indi- - cating that matching is to start at a point other than the beginning of - the subject, \A can never match. The difference between \Z and \z is - that \Z matches before a newline at the end of the string as well as at - the very end, whereas \z matches only at the end. - - The \G assertion is true only when the current matching position is at - the start point of the match, as specified by the startoffset argument - of pcre_exec(). It differs from \A when the value of startoffset is - non-zero. By calling pcre_exec() multiple times with appropriate argu- - ments, you can mimic Perl's /g option, and it is in this kind of imple- - mentation where \G can be useful. - - Note, however, that PCRE's interpretation of \G, as the start of the - current match, is subtly different from Perl's, which defines it as the - end of the previous match. In Perl, these can be different when the - previously matched string was empty. Because PCRE does just one match - at a time, it cannot reproduce this behaviour. - - If all the alternatives of a pattern begin with \G, the expression is - anchored to the starting match position, and the "anchored" flag is set - in the compiled regular expression. - - -CIRCUMFLEX AND DOLLAR - - Outside a character class, in the default matching mode, the circumflex - character is an assertion that is true only if the current matching - point is at the start of the subject string. If the startoffset argu- - ment of pcre_exec() is non-zero, circumflex can never match if the - PCRE_MULTILINE option is unset. Inside a character class, circumflex - has an entirely different meaning (see below). - - Circumflex need not be the first character of the pattern if a number - of alternatives are involved, but it should be the first thing in each - alternative in which it appears if the pattern is ever to match that - branch. If all possible alternatives start with a circumflex, that is, - if the pattern is constrained to match only at the start of the sub- - ject, it is said to be an "anchored" pattern. (There are also other - constructs that can cause a pattern to be anchored.) - - A dollar character is an assertion that is true only if the current - matching point is at the end of the subject string, or immediately - before a newline at the end of the string (by default). Dollar need not - be the last character of the pattern if a number of alternatives are - involved, but it should be the last item in any branch in which it - appears. Dollar has no special meaning in a character class. - - The meaning of dollar can be changed so that it matches only at the - very end of the string, by setting the PCRE_DOLLAR_ENDONLY option at - compile time. This does not affect the \Z assertion. - - The meanings of the circumflex and dollar characters are changed if the - PCRE_MULTILINE option is set. When this is the case, a circumflex - matches immediately after internal newlines as well as at the start of - the subject string. It does not match after a newline that ends the - string. A dollar matches before any newlines in the string, as well as - at the very end, when PCRE_MULTILINE is set. When newline is specified - as the two-character sequence CRLF, isolated CR and LF characters do - not indicate newlines. - - For example, the pattern /^abc$/ matches the subject string "def\nabc" - (where \n represents a newline) in multiline mode, but not otherwise. - Consequently, patterns that are anchored in single line mode because - all branches start with ^ are not anchored in multiline mode, and a - match for circumflex is possible when the startoffset argument of - pcre_exec() is non-zero. The PCRE_DOLLAR_ENDONLY option is ignored if - PCRE_MULTILINE is set. - - Note that the sequences \A, \Z, and \z can be used to match the start - and end of the subject in both modes, and if all branches of a pattern - start with \A it is always anchored, whether or not PCRE_MULTILINE is - set. - - -FULL STOP (PERIOD, DOT) - - Outside a character class, a dot in the pattern matches any one charac- - ter in the subject string except (by default) a character that signi- - fies the end of a line. In UTF-8 mode, the matched character may be - more than one byte long. - - When a line ending is defined as a single character, dot never matches - that character; when the two-character sequence CRLF is used, dot does - not match CR if it is immediately followed by LF, but otherwise it - matches all characters (including isolated CRs and LFs). When any Uni- - code line endings are being recognized, dot does not match CR or LF or - any of the other line ending characters. - - The behaviour of dot with regard to newlines can be changed. If the - PCRE_DOTALL option is set, a dot matches any one character, without - exception. If the two-character sequence CRLF is present in the subject - string, it takes two dots to match it. - - The handling of dot is entirely independent of the handling of circum- - flex and dollar, the only relationship being that they both involve - newlines. Dot has no special meaning in a character class. - - -MATCHING A SINGLE BYTE - - Outside a character class, the escape sequence \C matches any one byte, - both in and out of UTF-8 mode. Unlike a dot, it always matches any - line-ending characters. The feature is provided in Perl in order to - match individual bytes in UTF-8 mode. Because it breaks up UTF-8 char- - acters into individual bytes, what remains in the string may be a mal- - formed UTF-8 string. For this reason, the \C escape sequence is best - avoided. - - PCRE does not allow \C to appear in lookbehind assertions (described - below), because in UTF-8 mode this would make it impossible to calcu- - late the length of the lookbehind. - - -SQUARE BRACKETS AND CHARACTER CLASSES - - An opening square bracket introduces a character class, terminated by a - closing square bracket. A closing square bracket on its own is not spe- - cial. If a closing square bracket is required as a member of the class, - it should be the first data character in the class (after an initial - circumflex, if present) or escaped with a backslash. - - A character class matches a single character in the subject. In UTF-8 - mode, the character may occupy more than one byte. A matched character - must be in the set of characters defined by the class, unless the first - character in the class definition is a circumflex, in which case the - subject character must not be in the set defined by the class. If a - circumflex is actually required as a member of the class, ensure it is - not the first character, or escape it with a backslash. - - For example, the character class [aeiou] matches any lower case vowel, - while [^aeiou] matches any character that is not a lower case vowel. - Note that a circumflex is just a convenient notation for specifying the - characters that are in the class by enumerating those that are not. A - class that starts with a circumflex is not an assertion: it still con- - sumes a character from the subject string, and therefore it fails if - the current pointer is at the end of the string. - - In UTF-8 mode, characters with values greater than 255 can be included - in a class as a literal string of bytes, or by using the \x{ escaping - mechanism. - - When caseless matching is set, any letters in a class represent both - their upper case and lower case versions, so for example, a caseless - [aeiou] matches "A" as well as "a", and a caseless [^aeiou] does not - match "A", whereas a caseful version would. In UTF-8 mode, PCRE always - understands the concept of case for characters whose values are less - than 128, so caseless matching is always possible. For characters with - higher values, the concept of case is supported if PCRE is compiled - with Unicode property support, but not otherwise. If you want to use - caseless matching for characters 128 and above, you must ensure that - PCRE is compiled with Unicode property support as well as with UTF-8 - support. - - Characters that might indicate line breaks are never treated in any - special way when matching character classes, whatever line-ending - sequence is in use, and whatever setting of the PCRE_DOTALL and - PCRE_MULTILINE options is used. A class such as [^a] always matches one - of these characters. - - The minus (hyphen) character can be used to specify a range of charac- - ters in a character class. For example, [d-m] matches any letter - between d and m, inclusive. If a minus character is required in a - class, it must be escaped with a backslash or appear in a position - where it cannot be interpreted as indicating a range, typically as the - first or last character in the class. - - It is not possible to have the literal character "]" as the end charac- - ter of a range. A pattern such as [W-]46] is interpreted as a class of - two characters ("W" and "-") followed by a literal string "46]", so it - would match "W46]" or "-46]". However, if the "]" is escaped with a - backslash it is interpreted as the end of range, so [W-\]46] is inter- - preted as a class containing a range followed by two other characters. - The octal or hexadecimal representation of "]" can also be used to end - a range. - - Ranges operate in the collating sequence of character values. They can - also be used for characters specified numerically, for example - [\000-\037]. In UTF-8 mode, ranges can include characters whose values - are greater than 255, for example [\x{100}-\x{2ff}]. - - If a range that includes letters is used when caseless matching is set, - it matches the letters in either case. For example, [W-c] is equivalent - to [][\\^_`wxyzabc], matched caselessly, and in non-UTF-8 mode, if - character tables for a French locale are in use, [\xc8-\xcb] matches - accented E characters in both cases. In UTF-8 mode, PCRE supports the - concept of case for characters with values greater than 128 only when - it is compiled with Unicode property support. - - The character types \d, \D, \p, \P, \s, \S, \w, and \W may also appear - in a character class, and add the characters that they match to the - class. For example, [\dABCDEF] matches any hexadecimal digit. A circum- - flex can conveniently be used with the upper case character types to - specify a more restricted set of characters than the matching lower - case type. For example, the class [^\W_] matches any letter or digit, - but not underscore. - - The only metacharacters that are recognized in character classes are - backslash, hyphen (only where it can be interpreted as specifying a - range), circumflex (only at the start), opening square bracket (only - when it can be interpreted as introducing a POSIX class name - see the - next section), and the terminating closing square bracket. However, - escaping other non-alphanumeric characters does no harm. - - -POSIX CHARACTER CLASSES - - Perl supports the POSIX notation for character classes. This uses names - enclosed by [: and :] within the enclosing square brackets. PCRE also - supports this notation. For example, - - [01[:alpha:]%] - - matches "0", "1", any alphabetic character, or "%". The supported class - names are - - alnum letters and digits - alpha letters - ascii character codes 0 - 127 - blank space or tab only - cntrl control characters - digit decimal digits (same as \d) - graph printing characters, excluding space - lower lower case letters - print printing characters, including space - punct printing characters, excluding letters and digits - space white space (not quite the same as \s) - upper upper case letters - word "word" characters (same as \w) - xdigit hexadecimal digits - - The "space" characters are HT (9), LF (10), VT (11), FF (12), CR (13), - and space (32). Notice that this list includes the VT character (code - 11). This makes "space" different to \s, which does not include VT (for - Perl compatibility). - - The name "word" is a Perl extension, and "blank" is a GNU extension - from Perl 5.8. Another Perl extension is negation, which is indicated - by a ^ character after the colon. For example, - - [12[:^digit:]] - - matches "1", "2", or any non-digit. PCRE (and Perl) also recognize the - POSIX syntax [.ch.] and [=ch=] where "ch" is a "collating element", but - these are not supported, and an error is given if they are encountered. - - In UTF-8 mode, characters with values greater than 128 do not match any - of the POSIX character classes. - - -VERTICAL BAR - - Vertical bar characters are used to separate alternative patterns. For - example, the pattern - - gilbert|sullivan - - matches either "gilbert" or "sullivan". Any number of alternatives may - appear, and an empty alternative is permitted (matching the empty - string). The matching process tries each alternative in turn, from left - to right, and the first one that succeeds is used. If the alternatives - are within a subpattern (defined below), "succeeds" means matching the - rest of the main pattern as well as the alternative in the subpattern. - - -INTERNAL OPTION SETTING - - The settings of the PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, and - PCRE_EXTENDED options (which are Perl-compatible) can be changed from - within the pattern by a sequence of Perl option letters enclosed - between "(?" and ")". The option letters are - - i for PCRE_CASELESS - m for PCRE_MULTILINE - s for PCRE_DOTALL - x for PCRE_EXTENDED - - For example, (?im) sets caseless, multiline matching. It is also possi- - ble to unset these options by preceding the letter with a hyphen, and a - combined setting and unsetting such as (?im-sx), which sets PCRE_CASE- - LESS and PCRE_MULTILINE while unsetting PCRE_DOTALL and PCRE_EXTENDED, - is also permitted. If a letter appears both before and after the - hyphen, the option is unset. - - The PCRE-specific options PCRE_DUPNAMES, PCRE_UNGREEDY, and PCRE_EXTRA - can be changed in the same way as the Perl-compatible options by using - the characters J, U and X respectively. - - When one of these option changes occurs at top level (that is, not - inside subpattern parentheses), the change applies to the remainder of - the pattern that follows. If the change is placed right at the start of - a pattern, PCRE extracts it into the global options (and it will there- - fore show up in data extracted by the pcre_fullinfo() function). - - An option change within a subpattern (see below for a description of - subpatterns) affects only that part of the current pattern that follows - it, so - - (a(?i)b)c - - matches abc and aBc and no other strings (assuming PCRE_CASELESS is not - used). By this means, options can be made to have different settings - in different parts of the pattern. Any changes made in one alternative - do carry on into subsequent branches within the same subpattern. For - example, - - (a(?i)b|c) - - matches "ab", "aB", "c", and "C", even though when matching "C" the - first branch is abandoned before the option setting. This is because - the effects of option settings happen at compile time. There would be - some very weird behaviour otherwise. - - Note: There are other PCRE-specific options that can be set by the - application when the compile or match functions are called. In some - cases the pattern can contain special leading sequences such as (*CRLF) - to override what the application has set or what has been defaulted. - Details are given in the section entitled "Newline sequences" above. - There is also the (*UTF8) leading sequence that can be used to set - UTF-8 mode; this is equivalent to setting the PCRE_UTF8 option. - - -SUBPATTERNS - - Subpatterns are delimited by parentheses (round brackets), which can be - nested. Turning part of a pattern into a subpattern does two things: - - 1. It localizes a set of alternatives. For example, the pattern - - cat(aract|erpillar|) - - matches one of the words "cat", "cataract", or "caterpillar". Without - the parentheses, it would match "cataract", "erpillar" or an empty - string. - - 2. It sets up the subpattern as a capturing subpattern. This means - that, when the whole pattern matches, that portion of the subject - string that matched the subpattern is passed back to the caller via the - ovector argument of pcre_exec(). Opening parentheses are counted from - left to right (starting from 1) to obtain numbers for the capturing - subpatterns. - - For example, if the string "the red king" is matched against the pat- - tern - - the ((red|white) (king|queen)) - - the captured substrings are "red king", "red", and "king", and are num- - bered 1, 2, and 3, respectively. - - The fact that plain parentheses fulfil two functions is not always - helpful. There are often times when a grouping subpattern is required - without a capturing requirement. If an opening parenthesis is followed - by a question mark and a colon, the subpattern does not do any captur- - ing, and is not counted when computing the number of any subsequent - capturing subpatterns. For example, if the string "the white queen" is - matched against the pattern - - the ((?:red|white) (king|queen)) - - the captured substrings are "white queen" and "queen", and are numbered - 1 and 2. The maximum number of capturing subpatterns is 65535. - - As a convenient shorthand, if any option settings are required at the - start of a non-capturing subpattern, the option letters may appear - between the "?" and the ":". Thus the two patterns - - (?i:saturday|sunday) - (?:(?i)saturday|sunday) - - match exactly the same set of strings. Because alternative branches are - tried from left to right, and options are not reset until the end of - the subpattern is reached, an option setting in one branch does affect - subsequent branches, so the above patterns match "SUNDAY" as well as - "Saturday". - - -DUPLICATE SUBPATTERN NUMBERS - - Perl 5.10 introduced a feature whereby each alternative in a subpattern - uses the same numbers for its capturing parentheses. Such a subpattern - starts with (?| and is itself a non-capturing subpattern. For example, - consider this pattern: - - (?|(Sat)ur|(Sun))day - - Because the two alternatives are inside a (?| group, both sets of cap- - turing parentheses are numbered one. Thus, when the pattern matches, - you can look at captured substring number one, whichever alternative - matched. This construct is useful when you want to capture part, but - not all, of one of a number of alternatives. Inside a (?| group, paren- - theses are numbered as usual, but the number is reset at the start of - each branch. The numbers of any capturing buffers that follow the sub- - pattern start after the highest number used in any branch. The follow- - ing example is taken from the Perl documentation. The numbers under- - neath show in which buffer the captured content will be stored. - - # before ---------------branch-reset----------- after - / ( a ) (?| x ( y ) z | (p (q) r) | (t) u (v) ) ( z ) /x - # 1 2 2 3 2 3 4 - - A backreference or a recursive call to a numbered subpattern always - refers to the first one in the pattern with the given number. - - An alternative approach to using this "branch reset" feature is to use - duplicate named subpatterns, as described in the next section. - - -NAMED SUBPATTERNS - - Identifying capturing parentheses by number is simple, but it can be - very hard to keep track of the numbers in complicated regular expres- - sions. Furthermore, if an expression is modified, the numbers may - change. To help with this difficulty, PCRE supports the naming of sub- - patterns. This feature was not added to Perl until release 5.10. Python - had the feature earlier, and PCRE introduced it at release 4.0, using - the Python syntax. PCRE now supports both the Perl and the Python syn- - tax. - - In PCRE, a subpattern can be named in one of three ways: (?...) - or (?'name'...) as in Perl, or (?P...) as in Python. References - to capturing parentheses from other parts of the pattern, such as back- - references, recursion, and conditions, can be made by name as well as - by number. - - Names consist of up to 32 alphanumeric characters and underscores. - Named capturing parentheses are still allocated numbers as well as - names, exactly as if the names were not present. The PCRE API provides - function calls for extracting the name-to-number translation table from - a compiled pattern. There is also a convenience function for extracting - a captured substring by name. - - By default, a name must be unique within a pattern, but it is possible - to relax this constraint by setting the PCRE_DUPNAMES option at compile - time. This can be useful for patterns where only one instance of the - named parentheses can match. Suppose you want to match the name of a - weekday, either as a 3-letter abbreviation or as the full name, and in - both cases you want to extract the abbreviation. This pattern (ignoring - the line breaks) does the job: - - (?Mon|Fri|Sun)(?:day)?| - (?Tue)(?:sday)?| - (?Wed)(?:nesday)?| - (?Thu)(?:rsday)?| - (?Sat)(?:urday)? - - There are five capturing substrings, but only one is ever set after a - match. (An alternative way of solving this problem is to use a "branch - reset" subpattern, as described in the previous section.) - - The convenience function for extracting the data by name returns the - substring for the first (and in this example, the only) subpattern of - that name that matched. This saves searching to find which numbered - subpattern it was. If you make a reference to a non-unique named sub- - pattern from elsewhere in the pattern, the one that corresponds to the - lowest number is used. For further details of the interfaces for han- - dling named subpatterns, see the pcreapi documentation. - - Warning: You cannot use different names to distinguish between two sub- - patterns with the same number (see the previous section) because PCRE - uses only the numbers when matching. - - -REPETITION - - Repetition is specified by quantifiers, which can follow any of the - following items: - - a literal data character - the dot metacharacter - the \C escape sequence - the \X escape sequence (in UTF-8 mode with Unicode properties) - the \R escape sequence - an escape such as \d that matches a single character - a character class - a back reference (see next section) - a parenthesized subpattern (unless it is an assertion) - - The general repetition quantifier specifies a minimum and maximum num- - ber of permitted matches, by giving the two numbers in curly brackets - (braces), separated by a comma. The numbers must be less than 65536, - and the first must be less than or equal to the second. For example: - - z{2,4} - - matches "zz", "zzz", or "zzzz". A closing brace on its own is not a - special character. If the second number is omitted, but the comma is - present, there is no upper limit; if the second number and the comma - are both omitted, the quantifier specifies an exact number of required - matches. Thus - - [aeiou]{3,} - - matches at least 3 successive vowels, but may match many more, while - - \d{8} - - matches exactly 8 digits. An opening curly bracket that appears in a - position where a quantifier is not allowed, or one that does not match - the syntax of a quantifier, is taken as a literal character. For exam- - ple, {,6} is not a quantifier, but a literal string of four characters. - - In UTF-8 mode, quantifiers apply to UTF-8 characters rather than to - individual bytes. Thus, for example, \x{100}{2} matches two UTF-8 char- - acters, each of which is represented by a two-byte sequence. Similarly, - when Unicode property support is available, \X{3} matches three Unicode - extended sequences, each of which may be several bytes long (and they - may be of different lengths). - - The quantifier {0} is permitted, causing the expression to behave as if - the previous item and the quantifier were not present. This may be use- - ful for subpatterns that are referenced as subroutines from elsewhere - in the pattern. Items other than subpatterns that have a {0} quantifier - are omitted from the compiled pattern. - - For convenience, the three most common quantifiers have single-charac- - ter abbreviations: - - * is equivalent to {0,} - + is equivalent to {1,} - ? is equivalent to {0,1} - - It is possible to construct infinite loops by following a subpattern - that can match no characters with a quantifier that has no upper limit, - for example: - - (a?)* - - Earlier versions of Perl and PCRE used to give an error at compile time - for such patterns. However, because there are cases where this can be - useful, such patterns are now accepted, but if any repetition of the - subpattern does in fact match no characters, the loop is forcibly bro- - ken. - - By default, the quantifiers are "greedy", that is, they match as much - as possible (up to the maximum number of permitted times), without - causing the rest of the pattern to fail. The classic example of where - this gives problems is in trying to match comments in C programs. These - appear between /* and */ and within the comment, individual * and / - characters may appear. An attempt to match C comments by applying the - pattern - - /\*.*\*/ - - to the string - - /* first comment */ not comment /* second comment */ - - fails, because it matches the entire string owing to the greediness of - the .* item. - - However, if a quantifier is followed by a question mark, it ceases to - be greedy, and instead matches the minimum number of times possible, so - the pattern - - /\*.*?\*/ - - does the right thing with the C comments. The meaning of the various - quantifiers is not otherwise changed, just the preferred number of - matches. Do not confuse this use of question mark with its use as a - quantifier in its own right. Because it has two uses, it can sometimes - appear doubled, as in - - \d??\d - - which matches one digit by preference, but can match two if that is the - only way the rest of the pattern matches. - - If the PCRE_UNGREEDY option is set (an option that is not available in - Perl), the quantifiers are not greedy by default, but individual ones - can be made greedy by following them with a question mark. In other - words, it inverts the default behaviour. - - When a parenthesized subpattern is quantified with a minimum repeat - count that is greater than 1 or with a limited maximum, more memory is - required for the compiled pattern, in proportion to the size of the - minimum or maximum. - - If a pattern starts with .* or .{0,} and the PCRE_DOTALL option (equiv- - alent to Perl's /s) is set, thus allowing the dot to match newlines, - the pattern is implicitly anchored, because whatever follows will be - tried against every character position in the subject string, so there - is no point in retrying the overall match at any position after the - first. PCRE normally treats such a pattern as though it were preceded - by \A. - - In cases where it is known that the subject string contains no new- - lines, it is worth setting PCRE_DOTALL in order to obtain this opti- - mization, or alternatively using ^ to indicate anchoring explicitly. - - However, there is one situation where the optimization cannot be used. - When .* is inside capturing parentheses that are the subject of a - backreference elsewhere in the pattern, a match at the start may fail - where a later one succeeds. Consider, for example: - - (.*)abc\1 - - If the subject is "xyz123abc123" the match point is the fourth charac- - ter. For this reason, such a pattern is not implicitly anchored. - - When a capturing subpattern is repeated, the value captured is the sub- - string that matched the final iteration. For example, after - - (tweedle[dume]{3}\s*)+ - - has matched "tweedledum tweedledee" the value of the captured substring - is "tweedledee". However, if there are nested capturing subpatterns, - the corresponding captured values may have been set in previous itera- - tions. For example, after - - /(a|(b))+/ - - matches "aba" the value of the second captured substring is "b". - - -ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS - - With both maximizing ("greedy") and minimizing ("ungreedy" or "lazy") - repetition, failure of what follows normally causes the repeated item - to be re-evaluated to see if a different number of repeats allows the - rest of the pattern to match. Sometimes it is useful to prevent this, - either to change the nature of the match, or to cause it fail earlier - than it otherwise might, when the author of the pattern knows there is - no point in carrying on. - - Consider, for example, the pattern \d+foo when applied to the subject - line - - 123456bar - - After matching all 6 digits and then failing to match "foo", the normal - action of the matcher is to try again with only 5 digits matching the - \d+ item, and then with 4, and so on, before ultimately failing. - "Atomic grouping" (a term taken from Jeffrey Friedl's book) provides - the means for specifying that once a subpattern has matched, it is not - to be re-evaluated in this way. - - If we use atomic grouping for the previous example, the matcher gives - up immediately on failing to match "foo" the first time. The notation - is a kind of special parenthesis, starting with (?> as in this example: - - (?>\d+)foo - - This kind of parenthesis "locks up" the part of the pattern it con- - tains once it has matched, and a failure further into the pattern is - prevented from backtracking into it. Backtracking past it to previous - items, however, works as normal. - - An alternative description is that a subpattern of this type matches - the string of characters that an identical standalone pattern would - match, if anchored at the current point in the subject string. - - Atomic grouping subpatterns are not capturing subpatterns. Simple cases - such as the above example can be thought of as a maximizing repeat that - must swallow everything it can. So, while both \d+ and \d+? are pre- - pared to adjust the number of digits they match in order to make the - rest of the pattern match, (?>\d+) can only match an entire sequence of - digits. - - Atomic groups in general can of course contain arbitrarily complicated - subpatterns, and can be nested. However, when the subpattern for an - atomic group is just a single repeated item, as in the example above, a - simpler notation, called a "possessive quantifier" can be used. This - consists of an additional + character following a quantifier. Using - this notation, the previous example can be rewritten as - - \d++foo - - Note that a possessive quantifier can be used with an entire group, for - example: - - (abc|xyz){2,3}+ - - Possessive quantifiers are always greedy; the setting of the - PCRE_UNGREEDY option is ignored. They are a convenient notation for the - simpler forms of atomic group. However, there is no difference in the - meaning of a possessive quantifier and the equivalent atomic group, - though there may be a performance difference; possessive quantifiers - should be slightly faster. - - The possessive quantifier syntax is an extension to the Perl 5.8 syn- - tax. Jeffrey Friedl originated the idea (and the name) in the first - edition of his book. Mike McCloskey liked it, so implemented it when he - built Sun's Java package, and PCRE copied it from there. It ultimately - found its way into Perl at release 5.10. - - PCRE has an optimization that automatically "possessifies" certain sim- - ple pattern constructs. For example, the sequence A+B is treated as - A++B because there is no point in backtracking into a sequence of A's - when B must follow. - - When a pattern contains an unlimited repeat inside a subpattern that - can itself be repeated an unlimited number of times, the use of an - atomic group is the only way to avoid some failing matches taking a - very long time indeed. The pattern - - (\D+|<\d+>)*[!?] - - matches an unlimited number of substrings that either consist of non- - digits, or digits enclosed in <>, followed by either ! or ?. When it - matches, it runs quickly. However, if it is applied to - - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - - it takes a long time before reporting failure. This is because the - string can be divided between the internal \D+ repeat and the external - * repeat in a large number of ways, and all have to be tried. (The - example uses [!?] rather than a single character at the end, because - both PCRE and Perl have an optimization that allows for fast failure - when a single character is used. They remember the last single charac- - ter that is required for a match, and fail early if it is not present - in the string.) If the pattern is changed so that it uses an atomic - group, like this: - - ((?>\D+)|<\d+>)*[!?] - - sequences of non-digits cannot be broken, and failure happens quickly. - - -BACK REFERENCES - - Outside a character class, a backslash followed by a digit greater than - 0 (and possibly further digits) is a back reference to a capturing sub- - pattern earlier (that is, to its left) in the pattern, provided there - have been that many previous capturing left parentheses. - - However, if the decimal number following the backslash is less than 10, - it is always taken as a back reference, and causes an error only if - there are not that many capturing left parentheses in the entire pat- - tern. In other words, the parentheses that are referenced need not be - to the left of the reference for numbers less than 10. A "forward back - reference" of this type can make sense when a repetition is involved - and the subpattern to the right has participated in an earlier itera- - tion. - - It is not possible to have a numerical "forward back reference" to a - subpattern whose number is 10 or more using this syntax because a - sequence such as \50 is interpreted as a character defined in octal. - See the subsection entitled "Non-printing characters" above for further - details of the handling of digits following a backslash. There is no - such problem when named parentheses are used. A back reference to any - subpattern is possible using named parentheses (see below). - - Another way of avoiding the ambiguity inherent in the use of digits - following a backslash is to use the \g escape sequence, which is a fea- - ture introduced in Perl 5.10. This escape must be followed by an - unsigned number or a negative number, optionally enclosed in braces. - These examples are all identical: - - (ring), \1 - (ring), \g1 - (ring), \g{1} - - An unsigned number specifies an absolute reference without the ambigu- - ity that is present in the older syntax. It is also useful when literal - digits follow the reference. A negative number is a relative reference. - Consider this example: - - (abc(def)ghi)\g{-1} - - The sequence \g{-1} is a reference to the most recently started captur- - ing subpattern before \g, that is, is it equivalent to \2. Similarly, - \g{-2} would be equivalent to \1. The use of relative references can be - helpful in long patterns, and also in patterns that are created by - joining together fragments that contain references within themselves. - - A back reference matches whatever actually matched the capturing sub- - pattern in the current subject string, rather than anything matching - the subpattern itself (see "Subpatterns as subroutines" below for a way - of doing that). So the pattern - - (sens|respons)e and \1ibility - - matches "sense and sensibility" and "response and responsibility", but - not "sense and responsibility". If caseful matching is in force at the - time of the back reference, the case of letters is relevant. For exam- - ple, - - ((?i)rah)\s+\1 - - matches "rah rah" and "RAH RAH", but not "RAH rah", even though the - original capturing subpattern is matched caselessly. - - There are several different ways of writing back references to named - subpatterns. The .NET syntax \k{name} and the Perl syntax \k or - \k'name' are supported, as is the Python syntax (?P=name). Perl 5.10's - unified back reference syntax, in which \g can be used for both numeric - and named references, is also supported. We could rewrite the above - example in any of the following ways: - - (?(?i)rah)\s+\k - (?'p1'(?i)rah)\s+\k{p1} - (?P(?i)rah)\s+(?P=p1) - (?(?i)rah)\s+\g{p1} - - A subpattern that is referenced by name may appear in the pattern - before or after the reference. - - There may be more than one back reference to the same subpattern. If a - subpattern has not actually been used in a particular match, any back - references to it always fail. For example, the pattern - - (a|(bc))\2 - - always fails if it starts to match "a" rather than "bc". Because there - may be many capturing parentheses in a pattern, all digits following - the backslash are taken as part of a potential back reference number. - If the pattern continues with a digit character, some delimiter must be - used to terminate the back reference. If the PCRE_EXTENDED option is - set, this can be whitespace. Otherwise an empty comment (see "Com- - ments" below) can be used. - - A back reference that occurs inside the parentheses to which it refers - fails when the subpattern is first used, so, for example, (a\1) never - matches. However, such references can be useful inside repeated sub- - patterns. For example, the pattern - - (a|b\1)+ - - matches any number of "a"s and also "aba", "ababbaa" etc. At each iter- - ation of the subpattern, the back reference matches the character - string corresponding to the previous iteration. In order for this to - work, the pattern must be such that the first iteration does not need - to match the back reference. This can be done using alternation, as in - the example above, or by a quantifier with a minimum of zero. - - -ASSERTIONS - - An assertion is a test on the characters following or preceding the - current matching point that does not actually consume any characters. - The simple assertions coded as \b, \B, \A, \G, \Z, \z, ^ and $ are - described above. - - More complicated assertions are coded as subpatterns. There are two - kinds: those that look ahead of the current position in the subject - string, and those that look behind it. An assertion subpattern is - matched in the normal way, except that it does not cause the current - matching position to be changed. - - Assertion subpatterns are not capturing subpatterns, and may not be - repeated, because it makes no sense to assert the same thing several - times. If any kind of assertion contains capturing subpatterns within - it, these are counted for the purposes of numbering the capturing sub- - patterns in the whole pattern. However, substring capturing is carried - out only for positive assertions, because it does not make sense for - negative assertions. - - Lookahead assertions - - Lookahead assertions start with (?= for positive assertions and (?! for - negative assertions. For example, - - \w+(?=;) - - matches a word followed by a semicolon, but does not include the semi- - colon in the match, and - - foo(?!bar) - - matches any occurrence of "foo" that is not followed by "bar". Note - that the apparently similar pattern - - (?!foo)bar - - does not find an occurrence of "bar" that is preceded by something - other than "foo"; it finds any occurrence of "bar" whatsoever, because - the assertion (?!foo) is always true when the next three characters are - "bar". A lookbehind assertion is needed to achieve the other effect. - - If you want to force a matching failure at some point in a pattern, the - most convenient way to do it is with (?!) because an empty string - always matches, so an assertion that requires there not to be an empty - string must always fail. - - Lookbehind assertions - - Lookbehind assertions start with (?<= for positive assertions and (?)...) or (?('name')...) to test for a - used subpattern by name. For compatibility with earlier versions of - PCRE, which had this facility before Perl, the syntax (?(name)...) is - also recognized. However, there is a possible ambiguity with this syn- - tax, because subpattern names may consist entirely of digits. PCRE - looks first for a named subpattern; if it cannot find one and the name - consists entirely of digits, PCRE looks for a subpattern of that num- - ber, which must be greater than zero. Using subpattern names that con- - sist entirely of digits is not recommended. - - Rewriting the above example to use a named subpattern gives this: - - (? \( )? [^()]+ (?() \) ) - - - Checking for pattern recursion - - If the condition is the string (R), and there is no subpattern with the - name R, the condition is true if a recursive call to the whole pattern - or any subpattern has been made. If digits or a name preceded by amper- - sand follow the letter R, for example: - - (?(R3)...) or (?(R&name)...) - - the condition is true if the most recent recursion is into the subpat- - tern whose number or name is given. This condition does not check the - entire recursion stack. - - At "top level", all these recursion test conditions are false. Recur- - sive patterns are described below. - - Defining subpatterns for use by reference only - - If the condition is the string (DEFINE), and there is no subpattern - with the name DEFINE, the condition is always false. In this case, - there may be only one alternative in the subpattern. It is always - skipped if control reaches this point in the pattern; the idea of - DEFINE is that it can be used to define "subroutines" that can be ref- - erenced from elsewhere. (The use of "subroutines" is described below.) - For example, a pattern to match an IPv4 address could be written like - this (ignore whitespace and line breaks): - - (?(DEFINE) (? 2[0-4]\d | 25[0-5] | 1\d\d | [1-9]?\d) ) - \b (?&byte) (\.(?&byte)){3} \b - - The first part of the pattern is a DEFINE group inside which a another - group named "byte" is defined. This matches an individual component of - an IPv4 address (a number less than 256). When matching takes place, - this part of the pattern is skipped because DEFINE acts like a false - condition. - - The rest of the pattern uses references to the named group to match the - four dot-separated components of an IPv4 address, insisting on a word - boundary at each end. - - Assertion conditions - - If the condition is not in any of the above formats, it must be an - assertion. This may be a positive or negative lookahead or lookbehind - assertion. Consider this pattern, again containing non-significant - white space, and with the two alternatives on the second line: - - (?(?=[^a-z]*[a-z]) - \d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} ) - - The condition is a positive lookahead assertion that matches an - optional sequence of non-letters followed by a letter. In other words, - it tests for the presence of at least one letter in the subject. If a - letter is found, the subject is matched against the first alternative; - otherwise it is matched against the second. This pattern matches - strings in one of the two forms dd-aaa-dd or dd-dd-dd, where aaa are - letters and dd are digits. - - -COMMENTS - - The sequence (?# marks the start of a comment that continues up to the - next closing parenthesis. Nested parentheses are not permitted. The - characters that make up a comment play no part in the pattern matching - at all. - - If the PCRE_EXTENDED option is set, an unescaped # character outside a - character class introduces a comment that continues to immediately - after the next newline in the pattern. - - -RECURSIVE PATTERNS - - Consider the problem of matching a string in parentheses, allowing for - unlimited nested parentheses. Without the use of recursion, the best - that can be done is to use a pattern that matches up to some fixed - depth of nesting. It is not possible to handle an arbitrary nesting - depth. - - For some time, Perl has provided a facility that allows regular expres- - sions to recurse (amongst other things). It does this by interpolating - Perl code in the expression at run time, and the code can refer to the - expression itself. A Perl pattern using code interpolation to solve the - parentheses problem can be created like this: - - $re = qr{\( (?: (?>[^()]+) | (?p{$re}) )* \)}x; - - The (?p{...}) item interpolates Perl code at run time, and in this case - refers recursively to the pattern in which it appears. - - Obviously, PCRE cannot support the interpolation of Perl code. Instead, - it supports special syntax for recursion of the entire pattern, and - also for individual subpattern recursion. After its introduction in - PCRE and Python, this kind of recursion was introduced into Perl at - release 5.10. - - A special item that consists of (? followed by a number greater than - zero and a closing parenthesis is a recursive call of the subpattern of - the given number, provided that it occurs inside that subpattern. (If - not, it is a "subroutine" call, which is described in the next sec- - tion.) The special item (?R) or (?0) is a recursive call of the entire - regular expression. - - In PCRE (like Python, but unlike Perl), a recursive subpattern call is - always treated as an atomic group. That is, once it has matched some of - the subject string, it is never re-entered, even if it contains untried - alternatives and there is a subsequent matching failure. - - This PCRE pattern solves the nested parentheses problem (assume the - PCRE_EXTENDED option is set so that white space is ignored): - - \( ( (?>[^()]+) | (?R) )* \) - - First it matches an opening parenthesis. Then it matches any number of - substrings which can either be a sequence of non-parentheses, or a - recursive match of the pattern itself (that is, a correctly parenthe- - sized substring). Finally there is a closing parenthesis. - - If this were part of a larger pattern, you would not want to recurse - the entire pattern, so instead you could use this: - - ( \( ( (?>[^()]+) | (?1) )* \) ) - - We have put the pattern into parentheses, and caused the recursion to - refer to them instead of the whole pattern. - - In a larger pattern, keeping track of parenthesis numbers can be - tricky. This is made easier by the use of relative references. (A Perl - 5.10 feature.) Instead of (?1) in the pattern above you can write - (?-2) to refer to the second most recently opened parentheses preceding - the recursion. In other words, a negative number counts capturing - parentheses leftwards from the point at which it is encountered. - - It is also possible to refer to subsequently opened parentheses, by - writing references such as (?+2). However, these cannot be recursive - because the reference is not inside the parentheses that are refer- - enced. They are always "subroutine" calls, as described in the next - section. - - An alternative approach is to use named parentheses instead. The Perl - syntax for this is (?&name); PCRE's earlier syntax (?P>name) is also - supported. We could rewrite the above example as follows: - - (? \( ( (?>[^()]+) | (?&pn) )* \) ) - - If there is more than one subpattern with the same name, the earliest - one is used. - - This particular example pattern that we have been looking at contains - nested unlimited repeats, and so the use of atomic grouping for match- - ing strings of non-parentheses is important when applying the pattern - to strings that do not match. For example, when this pattern is applied - to - - (aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa() - - it yields "no match" quickly. However, if atomic grouping is not used, - the match runs for a very long time indeed because there are so many - different ways the + and * repeats can carve up the subject, and all - have to be tested before failure can be reported. - - At the end of a match, the values set for any capturing subpatterns are - those from the outermost level of the recursion at which the subpattern - value is set. If you want to obtain intermediate values, a callout - function can be used (see below and the pcrecallout documentation). If - the pattern above is matched against - - (ab(cd)ef) - - the value for the capturing parentheses is "ef", which is the last - value taken on at the top level. If additional parentheses are added, - giving - - \( ( ( (?>[^()]+) | (?R) )* ) \) - ^ ^ - ^ ^ - - the string they capture is "ab(cd)ef", the contents of the top level - parentheses. If there are more than 15 capturing parentheses in a pat- - tern, PCRE has to obtain extra memory to store data during a recursion, - which it does by using pcre_malloc, freeing it via pcre_free after- - wards. If no memory can be obtained, the match fails with the - PCRE_ERROR_NOMEMORY error. - - Do not confuse the (?R) item with the condition (R), which tests for - recursion. Consider this pattern, which matches text in angle brack- - ets, allowing for arbitrary nesting. Only digits are allowed in nested - brackets (that is, when recursing), whereas any characters are permit- - ted at the outer level. - - < (?: (?(R) \d++ | [^<>]*+) | (?R)) * > - - In this pattern, (?(R) is the start of a conditional subpattern, with - two different alternatives for the recursive and non-recursive cases. - The (?R) item is the actual recursive call. - - -SUBPATTERNS AS SUBROUTINES - - If the syntax for a recursive subpattern reference (either by number or - by name) is used outside the parentheses to which it refers, it oper- - ates like a subroutine in a programming language. The "called" subpat- - tern may be defined before or after the reference. A numbered reference - can be absolute or relative, as in these examples: - - (...(absolute)...)...(?2)... - (...(relative)...)...(?-1)... - (...(?+1)...(relative)... - - An earlier example pointed out that the pattern - - (sens|respons)e and \1ibility - - matches "sense and sensibility" and "response and responsibility", but - not "sense and responsibility". If instead the pattern - - (sens|respons)e and (?1)ibility - - is used, it does match "sense and responsibility" as well as the other - two strings. Another example is given in the discussion of DEFINE - above. - - Like recursive subpatterns, a "subroutine" call is always treated as an - atomic group. That is, once it has matched some of the subject string, - it is never re-entered, even if it contains untried alternatives and - there is a subsequent matching failure. - - When a subpattern is used as a subroutine, processing options such as - case-independence are fixed when the subpattern is defined. They cannot - be changed for different calls. For example, consider this pattern: - - (abc)(?i:(?-1)) - - It matches "abcabc". It does not match "abcABC" because the change of - processing option does not affect the called subpattern. - - -ONIGURUMA SUBROUTINE SYNTAX - - For compatibility with Oniguruma, the non-Perl syntax \g followed by a - name or a number enclosed either in angle brackets or single quotes, is - an alternative syntax for referencing a subpattern as a subroutine, - possibly recursively. Here are two of the examples used above, rewrit- - ten using this syntax: - - (? \( ( (?>[^()]+) | \g )* \) ) - (sens|respons)e and \g'1'ibility - - PCRE supports an extension to Oniguruma: if a number is preceded by a - plus or a minus sign it is taken as a relative reference. For example: - - (abc)(?i:\g<-1>) - - Note that \g{...} (Perl syntax) and \g<...> (Oniguruma syntax) are not - synonymous. The former is a back reference; the latter is a subroutine - call. - - -CALLOUTS - - Perl has a feature whereby using the sequence (?{...}) causes arbitrary - Perl code to be obeyed in the middle of matching a regular expression. - This makes it possible, amongst other things, to extract different sub- - strings that match the same pair of parentheses when there is a repeti- - tion. - - PCRE provides a similar feature, but of course it cannot obey arbitrary - Perl code. The feature is called "callout". The caller of PCRE provides - an external function by putting its entry point in the global variable - pcre_callout. By default, this variable contains NULL, which disables - all calling out. - - Within a regular expression, (?C) indicates the points at which the - external function is to be called. If you want to identify different - callout points, you can put a number less than 256 after the letter C. - The default value is zero. For example, this pattern has two callout - points: - - (?C1)abc(?C2)def - - If the PCRE_AUTO_CALLOUT flag is passed to pcre_compile(), callouts are - automatically installed before each item in the pattern. They are all - numbered 255. - - During matching, when PCRE reaches a callout point (and pcre_callout is - set), the external function is called. It is provided with the number - of the callout, the position in the pattern, and, optionally, one item - of data originally supplied by the caller of pcre_exec(). The callout - function may cause matching to proceed, to backtrack, or to fail alto- - gether. A complete description of the interface to the callout function - is given in the pcrecallout documentation. - - -BACKTRACKING CONTROL - - Perl 5.10 introduced a number of "Special Backtracking Control Verbs", - which are described in the Perl documentation as "experimental and sub- - ject to change or removal in a future version of Perl". It goes on to - say: "Their usage in production code should be noted to avoid problems - during upgrades." The same remarks apply to the PCRE features described - in this section. - - Since these verbs are specifically related to backtracking, most of - them can be used only when the pattern is to be matched using - pcre_exec(), which uses a backtracking algorithm. With the exception of - (*FAIL), which behaves like a failing negative assertion, they cause an - error if encountered by pcre_dfa_exec(). - - The new verbs make use of what was previously invalid syntax: an open- - ing parenthesis followed by an asterisk. In Perl, they are generally of - the form (*VERB:ARG) but PCRE does not support the use of arguments, so - its general form is just (*VERB). Any number of these verbs may occur - in a pattern. There are two kinds: - - Verbs that act immediately - - The following verbs act as soon as they are encountered: - - (*ACCEPT) - - This verb causes the match to end successfully, skipping the remainder - of the pattern. When inside a recursion, only the innermost pattern is - ended immediately. PCRE differs from Perl in what happens if the - (*ACCEPT) is inside capturing parentheses. In Perl, the data so far is - captured: in PCRE no data is captured. For example: - - A(A|B(*ACCEPT)|C)D - - This matches "AB", "AAD", or "ACD", but when it matches "AB", no data - is captured. - - (*FAIL) or (*F) - - This verb causes the match to fail, forcing backtracking to occur. It - is equivalent to (?!) but easier to read. The Perl documentation notes - that it is probably useful only when combined with (?{}) or (??{}). - Those are, of course, Perl features that are not present in PCRE. The - nearest equivalent is the callout feature, as for example in this pat- - tern: - - a+(?C)(*FAIL) - - A match with the string "aaaa" always fails, but the callout is taken - before each backtrack happens (in this example, 10 times). - - Verbs that act after backtracking - - The following verbs do nothing when they are encountered. Matching con- - tinues with what follows, but if there is no subsequent match, a fail- - ure is forced. The verbs differ in exactly what kind of failure - occurs. - - (*COMMIT) - - This verb causes the whole match to fail outright if the rest of the - pattern does not match. Even if the pattern is unanchored, no further - attempts to find a match by advancing the start point take place. Once - (*COMMIT) has been passed, pcre_exec() is committed to finding a match - at the current starting point, or not at all. For example: - - a+(*COMMIT)b - - This matches "xxaab" but not "aacaab". It can be thought of as a kind - of dynamic anchor, or "I've started, so I must finish." - - (*PRUNE) - - This verb causes the match to fail at the current position if the rest - of the pattern does not match. If the pattern is unanchored, the normal - "bumpalong" advance to the next starting character then happens. Back- - tracking can occur as usual to the left of (*PRUNE), or when matching - to the right of (*PRUNE), but if there is no match to the right, back- - tracking cannot cross (*PRUNE). In simple cases, the use of (*PRUNE) - is just an alternative to an atomic group or possessive quantifier, but - there are some uses of (*PRUNE) that cannot be expressed in any other - way. - - (*SKIP) - - This verb is like (*PRUNE), except that if the pattern is unanchored, - the "bumpalong" advance is not to the next character, but to the posi- - tion in the subject where (*SKIP) was encountered. (*SKIP) signifies - that whatever text was matched leading up to it cannot be part of a - successful match. Consider: - - a+(*SKIP)b - - If the subject is "aaaac...", after the first match attempt fails - (starting at the first character in the string), the starting point - skips on to start the next attempt at "c". Note that a possessive quan- - tifer does not have the same effect in this example; although it would - suppress backtracking during the first match attempt, the second - attempt would start at the second character instead of skipping on to - "c". - - (*THEN) - - This verb causes a skip to the next alternation if the rest of the pat- - tern does not match. That is, it cancels pending backtracking, but only - within the current alternation. Its name comes from the observation - that it can be used for a pattern-based if-then-else block: - - ( COND1 (*THEN) FOO | COND2 (*THEN) BAR | COND3 (*THEN) BAZ ) ... - - If the COND1 pattern matches, FOO is tried (and possibly further items - after the end of the group if FOO succeeds); on failure the matcher - skips to the second alternative and tries COND2, without backtracking - into COND1. If (*THEN) is used outside of any alternation, it acts - exactly like (*PRUNE). - - -SEE ALSO - - pcreapi(3), pcrecallout(3), pcrematching(3), pcre(3). - - -AUTHOR - - Philip Hazel - University Computing Service - Cambridge CB2 3QH, England. - - -REVISION - - Last updated: 11 April 2009 - Copyright (c) 1997-2009 University of Cambridge. ------------------------------------------------------------------------------- - - -PCRESYNTAX(3) PCRESYNTAX(3) - - -NAME - PCRE - Perl-compatible regular expressions - - -PCRE REGULAR EXPRESSION SYNTAX SUMMARY - - The full syntax and semantics of the regular expressions that are sup- - ported by PCRE are described in the pcrepattern documentation. This - document contains just a quick-reference summary of the syntax. - - -QUOTING - - \x where x is non-alphanumeric is a literal x - \Q...\E treat enclosed characters as literal - - -CHARACTERS - - \a alarm, that is, the BEL character (hex 07) - \cx "control-x", where x is any character - \e escape (hex 1B) - \f formfeed (hex 0C) - \n newline (hex 0A) - \r carriage return (hex 0D) - \t tab (hex 09) - \ddd character with octal code ddd, or backreference - \xhh character with hex code hh - \x{hhh..} character with hex code hhh.. - - -CHARACTER TYPES - - . any character except newline; - in dotall mode, any character whatsoever - \C one byte, even in UTF-8 mode (best avoided) - \d a decimal digit - \D a character that is not a decimal digit - \h a horizontal whitespace character - \H a character that is not a horizontal whitespace character - \p{xx} a character with the xx property - \P{xx} a character without the xx property - \R a newline sequence - \s a whitespace character - \S a character that is not a whitespace character - \v a vertical whitespace character - \V a character that is not a vertical whitespace character - \w a "word" character - \W a "non-word" character - \X an extended Unicode sequence - - In PCRE, \d, \D, \s, \S, \w, and \W recognize only ASCII characters. - - -GENERAL CATEGORY PROPERTY CODES FOR \p and \P - - C Other - Cc Control - Cf Format - Cn Unassigned - Co Private use - Cs Surrogate - - L Letter - Ll Lower case letter - Lm Modifier letter - Lo Other letter - Lt Title case letter - Lu Upper case letter - L& Ll, Lu, or Lt - - M Mark - Mc Spacing mark - Me Enclosing mark - Mn Non-spacing mark - - N Number - Nd Decimal number - Nl Letter number - No Other number - - P Punctuation - Pc Connector punctuation - Pd Dash punctuation - Pe Close punctuation - Pf Final punctuation - Pi Initial punctuation - Po Other punctuation - Ps Open punctuation - - S Symbol - Sc Currency symbol - Sk Modifier symbol - Sm Mathematical symbol - So Other symbol - - Z Separator - Zl Line separator - Zp Paragraph separator - Zs Space separator - - -SCRIPT NAMES FOR \p AND \P - - Arabic, Armenian, Balinese, Bengali, Bopomofo, Braille, Buginese, - Buhid, Canadian_Aboriginal, Carian, Cham, Cherokee, Common, Coptic, Cu- - neiform, Cypriot, Cyrillic, Deseret, Devanagari, Ethiopic, Georgian, - Glagolitic, Gothic, Greek, Gujarati, Gurmukhi, Han, Hangul, Hanunoo, - Hebrew, Hiragana, Inherited, Kannada, Katakana, Kayah_Li, Kharoshthi, - Khmer, Lao, Latin, Lepcha, Limbu, Linear_B, Lycian, Lydian, Malayalam, - Mongolian, Myanmar, New_Tai_Lue, Nko, Ogham, Old_Italic, Old_Persian, - Ol_Chiki, Oriya, Osmanya, Phags_Pa, Phoenician, Rejang, Runic, Saurash- - tra, Shavian, Sinhala, Sudanese, Syloti_Nagri, Syriac, Tagalog, Tag- - banwa, Tai_Le, Tamil, Telugu, Thaana, Thai, Tibetan, Tifinagh, - Ugaritic, Vai, Yi. - - -CHARACTER CLASSES - - [...] positive character class - [^...] negative character class - [x-y] range (can be used for hex characters) - [[:xxx:]] positive POSIX named set - [[:^xxx:]] negative POSIX named set - - alnum alphanumeric - alpha alphabetic - ascii 0-127 - blank space or tab - cntrl control character - digit decimal digit - graph printing, excluding space - lower lower case letter - print printing, including space - punct printing, excluding alphanumeric - space whitespace - upper upper case letter - word same as \w - xdigit hexadecimal digit - - In PCRE, POSIX character set names recognize only ASCII characters. You - can use \Q...\E inside a character class. - - -QUANTIFIERS - - ? 0 or 1, greedy - ?+ 0 or 1, possessive - ?? 0 or 1, lazy - * 0 or more, greedy - *+ 0 or more, possessive - *? 0 or more, lazy - + 1 or more, greedy - ++ 1 or more, possessive - +? 1 or more, lazy - {n} exactly n - {n,m} at least n, no more than m, greedy - {n,m}+ at least n, no more than m, possessive - {n,m}? at least n, no more than m, lazy - {n,} n or more, greedy - {n,}+ n or more, possessive - {n,}? n or more, lazy - - -ANCHORS AND SIMPLE ASSERTIONS - - \b word boundary (only ASCII letters recognized) - \B not a word boundary - ^ start of subject - also after internal newline in multiline mode - \A start of subject - $ end of subject - also before newline at end of subject - also before internal newline in multiline mode - \Z end of subject - also before newline at end of subject - \z end of subject - \G first matching position in subject - - -MATCH POINT RESET - - \K reset start of match - - -ALTERNATION - - expr|expr|expr... - - -CAPTURING - - (...) capturing group - (?...) named capturing group (Perl) - (?'name'...) named capturing group (Perl) - (?P...) named capturing group (Python) - (?:...) non-capturing group - (?|...) non-capturing group; reset group numbers for - capturing groups in each alternative - - -ATOMIC GROUPS - - (?>...) atomic, non-capturing group - - -COMMENT - - (?#....) comment (not nestable) - - -OPTION SETTING - - (?i) caseless - (?J) allow duplicate names - (?m) multiline - (?s) single line (dotall) - (?U) default ungreedy (lazy) - (?x) extended (ignore white space) - (?-...) unset option(s) - - The following is recognized only at the start of a pattern or after one - of the newline-setting options with similar syntax: - - (*UTF8) set UTF-8 mode - - -LOOKAHEAD AND LOOKBEHIND ASSERTIONS - - (?=...) positive look ahead - (?!...) negative look ahead - (?<=...) positive look behind - (? reference by name (Perl) - \k'name' reference by name (Perl) - \g{name} reference by name (Perl) - \k{name} reference by name (.NET) - (?P=name) reference by name (Python) - - -SUBROUTINE REFERENCES (POSSIBLY RECURSIVE) - - (?R) recurse whole pattern - (?n) call subpattern by absolute number - (?+n) call subpattern by relative number - (?-n) call subpattern by relative number - (?&name) call subpattern by name (Perl) - (?P>name) call subpattern by name (Python) - \g call subpattern by name (Oniguruma) - \g'name' call subpattern by name (Oniguruma) - \g call subpattern by absolute number (Oniguruma) - \g'n' call subpattern by absolute number (Oniguruma) - \g<+n> call subpattern by relative number (PCRE extension) - \g'+n' call subpattern by relative number (PCRE extension) - \g<-n> call subpattern by relative number (PCRE extension) - \g'-n' call subpattern by relative number (PCRE extension) - - -CONDITIONAL PATTERNS - - (?(condition)yes-pattern) - (?(condition)yes-pattern|no-pattern) - - (?(n)... absolute reference condition - (?(+n)... relative reference condition - (?(-n)... relative reference condition - (?()... named reference condition (Perl) - (?('name')... named reference condition (Perl) - (?(name)... named reference condition (PCRE) - (?(R)... overall recursion condition - (?(Rn)... specific group recursion condition - (?(R&name)... specific recursion condition - (?(DEFINE)... define subpattern for reference - (?(assert)... assertion condition - - -BACKTRACKING CONTROL - - The following act immediately they are reached: - - (*ACCEPT) force successful match - (*FAIL) force backtrack; synonym (*F) - - The following act only when a subsequent match failure causes a back- - track to reach them. They all force a match failure, but they differ in - what happens afterwards. Those that advance the start-of-match point do - so only if the pattern is not anchored. - - (*COMMIT) overall failure, no advance of starting point - (*PRUNE) advance to next starting character - (*SKIP) advance start to current matching position - (*THEN) local failure, backtrack to next alternation - - -NEWLINE CONVENTIONS - - These are recognized only at the very start of the pattern or after a - (*BSR_...) or (*UTF8) option. - - (*CR) carriage return only - (*LF) linefeed only - (*CRLF) carriage return followed by linefeed - (*ANYCRLF) all three of the above - (*ANY) any Unicode newline sequence - - -WHAT \R MATCHES - - These are recognized only at the very start of the pattern or after a - (*...) option that sets the newline convention or UTF-8 mode. - - (*BSR_ANYCRLF) CR, LF, or CRLF - (*BSR_UNICODE) any Unicode newline sequence - - -CALLOUTS - - (?C) callout - (?Cn) callout with data n - - -SEE ALSO - - pcrepattern(3), pcreapi(3), pcrecallout(3), pcrematching(3), pcre(3). - - -AUTHOR - - Philip Hazel - University Computing Service - Cambridge CB2 3QH, England. - - -REVISION - - Last updated: 11 April 2009 - Copyright (c) 1997-2009 University of Cambridge. ------------------------------------------------------------------------------- - - -PCREPARTIAL(3) PCREPARTIAL(3) - - -NAME - PCRE - Perl-compatible regular expressions - - -PARTIAL MATCHING IN PCRE - - In normal use of PCRE, if the subject string that is passed to - pcre_exec() or pcre_dfa_exec() matches as far as it goes, but is too - short to match the entire pattern, PCRE_ERROR_NOMATCH is returned. - There are circumstances where it might be helpful to distinguish this - case from other cases in which there is no match. - - Consider, for example, an application where a human is required to type - in data for a field with specific formatting requirements. An example - might be a date in the form ddmmmyy, defined by this pattern: - - ^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$ - - If the application sees the user's keystrokes one by one, and can check - that what has been typed so far is potentially valid, it is able to - raise an error as soon as a mistake is made, possibly beeping and not - reflecting the character that has been typed. This immediate feedback - is likely to be a better user interface than a check that is delayed - until the entire string has been entered. - - PCRE supports the concept of partial matching by means of the PCRE_PAR- - TIAL option, which can be set when calling pcre_exec() or - pcre_dfa_exec(). When this flag is set for pcre_exec(), the return code - PCRE_ERROR_NOMATCH is converted into PCRE_ERROR_PARTIAL if at any time - during the matching process the last part of the subject string matched - part of the pattern. Unfortunately, for non-anchored matching, it is - not possible to obtain the position of the start of the partial match. - No captured data is set when PCRE_ERROR_PARTIAL is returned. - - When PCRE_PARTIAL is set for pcre_dfa_exec(), the return code - PCRE_ERROR_NOMATCH is converted into PCRE_ERROR_PARTIAL if the end of - the subject is reached, there have been no complete matches, but there - is still at least one matching possibility. The portion of the string - that provided the partial match is set as the first matching string. - - Using PCRE_PARTIAL disables one of PCRE's optimizations. PCRE remembers - the last literal byte in a pattern, and abandons matching immediately - if such a byte is not present in the subject string. This optimization - cannot be used for a subject string that might match only partially. - - -RESTRICTED PATTERNS FOR PCRE_PARTIAL - - Because of the way certain internal optimizations are implemented in - the pcre_exec() function, the PCRE_PARTIAL option cannot be used with - all patterns. These restrictions do not apply when pcre_dfa_exec() is - used. For pcre_exec(), repeated single characters such as - - a{2,4} - - and repeated single metasequences such as - - \d+ - - are not permitted if the maximum number of occurrences is greater than - one. Optional items such as \d? (where the maximum is one) are permit- - ted. Quantifiers with any values are permitted after parentheses, so - the invalid examples above can be coded thus: - - (a){2,4} - (\d)+ - - These constructions run more slowly, but for the kinds of application - that are envisaged for this facility, this is not felt to be a major - restriction. - - If PCRE_PARTIAL is set for a pattern that does not conform to the - restrictions, pcre_exec() returns the error code PCRE_ERROR_BADPARTIAL - (-13). You can use the PCRE_INFO_OKPARTIAL call to pcre_fullinfo() to - find out if a compiled pattern can be used for partial matching. - - -EXAMPLE OF PARTIAL MATCHING USING PCRETEST - - If the escape sequence \P is present in a pcretest data line, the - PCRE_PARTIAL flag is used for the match. Here is a run of pcretest that - uses the date example quoted above: - - re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/ - data> 25jun04\P - 0: 25jun04 - 1: jun - data> 25dec3\P - Partial match - data> 3ju\P - Partial match - data> 3juj\P - No match - data> j\P - No match - - The first data string is matched completely, so pcretest shows the - matched substrings. The remaining four strings do not match the com- - plete pattern, but the first two are partial matches. The same test, - using pcre_dfa_exec() matching (by means of the \D escape sequence), - produces the following output: - - re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/ - data> 25jun04\P\D - 0: 25jun04 - data> 23dec3\P\D - Partial match: 23dec3 - data> 3ju\P\D - Partial match: 3ju - data> 3juj\P\D - No match - data> j\P\D - No match - - Notice that in this case the portion of the string that was matched is - made available. - - -MULTI-SEGMENT MATCHING WITH pcre_dfa_exec() - - When a partial match has been found using pcre_dfa_exec(), it is possi- - ble to continue the match by providing additional subject data and - calling pcre_dfa_exec() again with the same compiled regular expres- - sion, this time setting the PCRE_DFA_RESTART option. You must also pass - the same working space as before, because this is where details of the - previous partial match are stored. Here is an example using pcretest, - using the \R escape sequence to set the PCRE_DFA_RESTART option (\P and - \D are as above): - - re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/ - data> 23ja\P\D - Partial match: 23ja - data> n05\R\D - 0: n05 - - The first call has "23ja" as the subject, and requests partial match- - ing; the second call has "n05" as the subject for the continued - (restarted) match. Notice that when the match is complete, only the - last part is shown; PCRE does not retain the previously partially- - matched string. It is up to the calling program to do that if it needs - to. - - You can set PCRE_PARTIAL with PCRE_DFA_RESTART to continue partial - matching over multiple segments. This facility can be used to pass very - long subject strings to pcre_dfa_exec(). However, some care is needed - for certain types of pattern. - - 1. If the pattern contains tests for the beginning or end of a line, - you need to pass the PCRE_NOTBOL or PCRE_NOTEOL options, as appropri- - ate, when the subject string for any call does not contain the begin- - ning or end of a line. - - 2. If the pattern contains backward assertions (including \b or \B), - you need to arrange for some overlap in the subject strings to allow - for this. For example, you could pass the subject in chunks that are - 500 bytes long, but in a buffer of 700 bytes, with the starting offset - set to 200 and the previous 200 bytes at the start of the buffer. - - 3. Matching a subject string that is split into multiple segments does - not always produce exactly the same result as matching over one single - long string. The difference arises when there are multiple matching - possibilities, because a partial match result is given only when there - are no completed matches in a call to pcre_dfa_exec(). This means that - as soon as the shortest match has been found, continuation to a new - subject segment is no longer possible. Consider this pcretest example: - - re> /dog(sbody)?/ - data> do\P\D - Partial match: do - data> gsb\R\P\D - 0: g - data> dogsbody\D - 0: dogsbody - 1: dog - - The pattern matches the words "dog" or "dogsbody". When the subject is - presented in several parts ("do" and "gsb" being the first two) the - match stops when "dog" has been found, and it is not possible to con- - tinue. On the other hand, if "dogsbody" is presented as a single - string, both matches are found. - - Because of this phenomenon, it does not usually make sense to end a - pattern that is going to be matched in this way with a variable repeat. - - 4. Patterns that contain alternatives at the top level which do not all - start with the same pattern item may not work as expected. For example, - consider this pattern: - - 1234|3789 - - If the first part of the subject is "ABC123", a partial match of the - first alternative is found at offset 3. There is no partial match for - the second alternative, because such a match does not start at the same - point in the subject string. Attempting to continue with the string - "789" does not yield a match because only those alternatives that match - at one point in the subject are remembered. The problem arises because - the start of the second alternative matches within the first alterna- - tive. There is no problem with anchored patterns or patterns such as: - - 1234|ABCD - - where no string can be a partial match for both alternatives. - - -AUTHOR - - Philip Hazel - University Computing Service - Cambridge CB2 3QH, England. - - -REVISION - - Last updated: 04 June 2007 - Copyright (c) 1997-2007 University of Cambridge. ------------------------------------------------------------------------------- - - -PCREPRECOMPILE(3) PCREPRECOMPILE(3) - - -NAME - PCRE - Perl-compatible regular expressions - - -SAVING AND RE-USING PRECOMPILED PCRE PATTERNS - - If you are running an application that uses a large number of regular - expression patterns, it may be useful to store them in a precompiled - form instead of having to compile them every time the application is - run. If you are not using any private character tables (see the - pcre_maketables() documentation), this is relatively straightforward. - If you are using private tables, it is a little bit more complicated. - - If you save compiled patterns to a file, you can copy them to a differ- - ent host and run them there. This works even if the new host has the - opposite endianness to the one on which the patterns were compiled. - There may be a small performance penalty, but it should be insignifi- - cant. However, compiling regular expressions with one version of PCRE - for use with a different version is not guaranteed to work and may - cause crashes. - - -SAVING A COMPILED PATTERN - The value returned by pcre_compile() points to a single block of memory - that holds the compiled pattern and associated data. You can find the - length of this block in bytes by calling pcre_fullinfo() with an argu- - ment of PCRE_INFO_SIZE. You can then save the data in any appropriate - manner. Here is sample code that compiles a pattern and writes it to a - file. It assumes that the variable fd refers to a file that is open for - output: - - int erroroffset, rc, size; - char *error; - pcre *re; - - re = pcre_compile("my pattern", 0, &error, &erroroffset, NULL); - if (re == NULL) { ... handle errors ... } - rc = pcre_fullinfo(re, NULL, PCRE_INFO_SIZE, &size); - if (rc < 0) { ... handle errors ... } - rc = fwrite(re, 1, size, fd); - if (rc != size) { ... handle errors ... } - - In this example, the bytes that comprise the compiled pattern are - copied exactly. Note that this is binary data that may contain any of - the 256 possible byte values. On systems that make a distinction - between binary and non-binary data, be sure that the file is opened for - binary output. - - If you want to write more than one pattern to a file, you will have to - devise a way of separating them. For binary data, preceding each pat- - tern with its length is probably the most straightforward approach. - Another possibility is to write out the data in hexadecimal instead of - binary, one pattern to a line. - - Saving compiled patterns in a file is only one possible way of storing - them for later use. They could equally well be saved in a database, or - in the memory of some daemon process that passes them via sockets to - the processes that want them. - - If the pattern has been studied, it is also possible to save the study - data in a similar way to the compiled pattern itself. When studying - generates additional information, pcre_study() returns a pointer to a - pcre_extra data block. Its format is defined in the section on matching - a pattern in the pcreapi documentation. The study_data field points to - the binary study data, and this is what you must save (not the - pcre_extra block itself). The length of the study data can be obtained - by calling pcre_fullinfo() with an argument of PCRE_INFO_STUDYSIZE. - Remember to check that pcre_study() did return a non-NULL value before - trying to save the study data. - - -RE-USING A PRECOMPILED PATTERN - - Re-using a precompiled pattern is straightforward. Having reloaded it - into main memory, you pass its pointer to pcre_exec() or - pcre_dfa_exec() in the usual way. This should work even on another - host, and even if that host has the opposite endianness to the one - where the pattern was compiled. - - However, if you passed a pointer to custom character tables when the - pattern was compiled (the tableptr argument of pcre_compile()), you - must now pass a similar pointer to pcre_exec() or pcre_dfa_exec(), - because the value saved with the compiled pattern will obviously be - nonsense. A field in a pcre_extra() block is used to pass this data, as - described in the section on matching a pattern in the pcreapi documen- - tation. - - If you did not provide custom character tables when the pattern was - compiled, the pointer in the compiled pattern is NULL, which causes - pcre_exec() to use PCRE's internal tables. Thus, you do not need to - take any special action at run time in this case. - - If you saved study data with the compiled pattern, you need to create - your own pcre_extra data block and set the study_data field to point to - the reloaded study data. You must also set the PCRE_EXTRA_STUDY_DATA - bit in the flags field to indicate that study data is present. Then - pass the pcre_extra block to pcre_exec() or pcre_dfa_exec() in the - usual way. - - -COMPATIBILITY WITH DIFFERENT PCRE RELEASES - - In general, it is safest to recompile all saved patterns when you - update to a new PCRE release, though not all updates actually require - this. Recompiling is definitely needed for release 7.2. - - -AUTHOR - - Philip Hazel - University Computing Service - Cambridge CB2 3QH, England. - - -REVISION - - Last updated: 13 June 2007 - Copyright (c) 1997-2007 University of Cambridge. ------------------------------------------------------------------------------- - - -PCREPERFORM(3) PCREPERFORM(3) - - -NAME - PCRE - Perl-compatible regular expressions - - -PCRE PERFORMANCE - - Two aspects of performance are discussed below: memory usage and pro- - cessing time. The way you express your pattern as a regular expression - can affect both of them. - - -MEMORY USAGE - - Patterns are compiled by PCRE into a reasonably efficient byte code, so - that most simple patterns do not use much memory. However, there is one - case where memory usage can be unexpectedly large. When a parenthesized - subpattern has a quantifier with a minimum greater than 1 and/or a lim- - ited maximum, the whole subpattern is repeated in the compiled code. - For example, the pattern - - (abc|def){2,4} - - is compiled as if it were - - (abc|def)(abc|def)((abc|def)(abc|def)?)? - - (Technical aside: It is done this way so that backtrack points within - each of the repetitions can be independently maintained.) - - For regular expressions whose quantifiers use only small numbers, this - is not usually a problem. However, if the numbers are large, and par- - ticularly if such repetitions are nested, the memory usage can become - an embarrassment. For example, the very simple pattern - - ((ab){1,1000}c){1,3} - - uses 51K bytes when compiled. When PCRE is compiled with its default - internal pointer size of two bytes, the size limit on a compiled pat- - tern is 64K, and this is reached with the above pattern if the outer - repetition is increased from 3 to 4. PCRE can be compiled to use larger - internal pointers and thus handle larger compiled patterns, but it is - better to try to rewrite your pattern to use less memory if you can. - - One way of reducing the memory usage for such patterns is to make use - of PCRE's "subroutine" facility. Re-writing the above pattern as - - ((ab)(?2){0,999}c)(?1){0,2} - - reduces the memory requirements to 18K, and indeed it remains under 20K - even with the outer repetition increased to 100. However, this pattern - is not exactly equivalent, because the "subroutine" calls are treated - as atomic groups into which there can be no backtracking if there is a - subsequent matching failure. Therefore, PCRE cannot do this kind of - rewriting automatically. Furthermore, there is a noticeable loss of - speed when executing the modified pattern. Nevertheless, if the atomic - grouping is not a problem and the loss of speed is acceptable, this - kind of rewriting will allow you to process patterns that PCRE cannot - otherwise handle. - - -PROCESSING TIME - - Certain items in regular expression patterns are processed more effi- - ciently than others. It is more efficient to use a character class like - [aeiou] than a set of single-character alternatives such as - (a|e|i|o|u). In general, the simplest construction that provides the - required behaviour is usually the most efficient. Jeffrey Friedl's book - contains a lot of useful general discussion about optimizing regular - expressions for efficient performance. This document contains a few - observations about PCRE. - - Using Unicode character properties (the \p, \P, and \X escapes) is - slow, because PCRE has to scan a structure that contains data for over - fifteen thousand characters whenever it needs a character's property. - If you can find an alternative pattern that does not use character - properties, it will probably be faster. - - When a pattern begins with .* not in parentheses, or in parentheses - that are not the subject of a backreference, and the PCRE_DOTALL option - is set, the pattern is implicitly anchored by PCRE, since it can match - only at the start of a subject string. However, if PCRE_DOTALL is not - set, PCRE cannot make this optimization, because the . metacharacter - does not then match a newline, and if the subject string contains new- - lines, the pattern may match from the character immediately following - one of them instead of from the very start. For example, the pattern - - .*second - - matches the subject "first\nand second" (where \n stands for a newline - character), with the match starting at the seventh character. In order - to do this, PCRE has to retry the match starting after every newline in - the subject. - - If you are using such a pattern with subject strings that do not con- - tain newlines, the best performance is obtained by setting PCRE_DOTALL, - or starting the pattern with ^.* or ^.*? to indicate explicit anchor- - ing. That saves PCRE from having to scan along the subject looking for - a newline to restart at. - - Beware of patterns that contain nested indefinite repeats. These can - take a long time to run when applied to a string that does not match. - Consider the pattern fragment - - ^(a+)* - - This can match "aaaa" in 16 different ways, and this number increases - very rapidly as the string gets longer. (The * repeat can match 0, 1, - 2, 3, or 4 times, and for each of those cases other than 0 or 4, the + - repeats can match different numbers of times.) When the remainder of - the pattern is such that the entire match is going to fail, PCRE has in - principle to try every possible variation, and this can take an - extremely long time, even for relatively short strings. - - An optimization catches some of the more simple cases such as - - (a+)*b - - where a literal character follows. Before embarking on the standard - matching procedure, PCRE checks that there is a "b" later in the sub- - ject string, and if there is not, it fails the match immediately. How- - ever, when there is no following literal this optimization cannot be - used. You can see the difference by comparing the behaviour of - - (a+)*\d - - with the pattern above. The former gives a failure almost instantly - when applied to a whole line of "a" characters, whereas the latter - takes an appreciable time with strings longer than about 20 characters. - - In many cases, the solution to this kind of performance issue is to use - an atomic group or a possessive quantifier. - - -AUTHOR - - Philip Hazel - University Computing Service - Cambridge CB2 3QH, England. - - -REVISION - - Last updated: 06 March 2007 - Copyright (c) 1997-2007 University of Cambridge. ------------------------------------------------------------------------------- - - -PCREPOSIX(3) PCREPOSIX(3) - - -NAME - PCRE - Perl-compatible regular expressions. - - -SYNOPSIS OF POSIX API - - #include - - int regcomp(regex_t *preg, const char *pattern, - int cflags); - - int regexec(regex_t *preg, const char *string, - size_t nmatch, regmatch_t pmatch[], int eflags); - - size_t regerror(int errcode, const regex_t *preg, - char *errbuf, size_t errbuf_size); - - void regfree(regex_t *preg); - - -DESCRIPTION - - This set of functions provides a POSIX-style API to the PCRE regular - expression package. See the pcreapi documentation for a description of - PCRE's native API, which contains much additional functionality. - - The functions described here are just wrapper functions that ultimately - call the PCRE native API. Their prototypes are defined in the - pcreposix.h header file, and on Unix systems the library itself is - called pcreposix.a, so can be accessed by adding -lpcreposix to the - command for linking an application that uses them. Because the POSIX - functions call the native ones, it is also necessary to add -lpcre. - - I have implemented only those POSIX option bits that can be reasonably - mapped to PCRE native options. In addition, the option REG_EXTENDED is - defined with the value zero. This has no effect, but since programs - that are written to the POSIX interface often use it, this makes it - easier to slot in PCRE as a replacement library. Other POSIX options - are not even defined. - - When PCRE is called via these functions, it is only the API that is - POSIX-like in style. The syntax and semantics of the regular expres- - sions themselves are still those of Perl, subject to the setting of - various PCRE options, as described below. "POSIX-like in style" means - that the API approximates to the POSIX definition; it is not fully - POSIX-compatible, and in multi-byte encoding domains it is probably - even less compatible. - - The header for these functions is supplied as pcreposix.h to avoid any - potential clash with other POSIX libraries. It can, of course, be - renamed or aliased as regex.h, which is the "correct" name. It provides - two structure types, regex_t for compiled internal forms, and reg- - match_t for returning captured substrings. It also defines some con- - stants whose names start with "REG_"; these are used for setting - options and identifying error codes. - - -COMPILING A PATTERN - - The function regcomp() is called to compile a pattern into an internal - form. The pattern is a C string terminated by a binary zero, and is - passed in the argument pattern. The preg argument is a pointer to a - regex_t structure that is used as a base for storing information about - the compiled regular expression. - - The argument cflags is either zero, or contains one or more of the bits - defined by the following macros: - - REG_DOTALL - - The PCRE_DOTALL option is set when the regular expression is passed for - compilation to the native function. Note that REG_DOTALL is not part of - the POSIX standard. - - REG_ICASE - - The PCRE_CASELESS option is set when the regular expression is passed - for compilation to the native function. - - REG_NEWLINE - - The PCRE_MULTILINE option is set when the regular expression is passed - for compilation to the native function. Note that this does not mimic - the defined POSIX behaviour for REG_NEWLINE (see the following sec- - tion). - - REG_NOSUB - - The PCRE_NO_AUTO_CAPTURE option is set when the regular expression is - passed for compilation to the native function. In addition, when a pat- - tern that is compiled with this flag is passed to regexec() for match- - ing, the nmatch and pmatch arguments are ignored, and no captured - strings are returned. - - REG_UTF8 - - The PCRE_UTF8 option is set when the regular expression is passed for - compilation to the native function. This causes the pattern itself and - all data strings used for matching it to be treated as UTF-8 strings. - Note that REG_UTF8 is not part of the POSIX standard. - - In the absence of these flags, no options are passed to the native - function. This means the the regex is compiled with PCRE default - semantics. In particular, the way it handles newline characters in the - subject string is the Perl way, not the POSIX way. Note that setting - PCRE_MULTILINE has only some of the effects specified for REG_NEWLINE. - It does not affect the way newlines are matched by . (they aren't) or - by a negative class such as [^a] (they are). - - The yield of regcomp() is zero on success, and non-zero otherwise. The - preg structure is filled in on success, and one member of the structure - is public: re_nsub contains the number of capturing subpatterns in the - regular expression. Various error codes are defined in the header file. - - -MATCHING NEWLINE CHARACTERS - - This area is not simple, because POSIX and Perl take different views of - things. It is not possible to get PCRE to obey POSIX semantics, but - then PCRE was never intended to be a POSIX engine. The following table - lists the different possibilities for matching newline characters in - PCRE: - - Default Change with - - . matches newline no PCRE_DOTALL - newline matches [^a] yes not changeable - $ matches \n at end yes PCRE_DOLLARENDONLY - $ matches \n in middle no PCRE_MULTILINE - ^ matches \n in middle no PCRE_MULTILINE - - This is the equivalent table for POSIX: - - Default Change with - - . matches newline yes REG_NEWLINE - newline matches [^a] yes REG_NEWLINE - $ matches \n at end no REG_NEWLINE - $ matches \n in middle no REG_NEWLINE - ^ matches \n in middle no REG_NEWLINE - - PCRE's behaviour is the same as Perl's, except that there is no equiva- - lent for PCRE_DOLLAR_ENDONLY in Perl. In both PCRE and Perl, there is - no way to stop newline from matching [^a]. - - The default POSIX newline handling can be obtained by setting - PCRE_DOTALL and PCRE_DOLLAR_ENDONLY, but there is no way to make PCRE - behave exactly as for the REG_NEWLINE action. - - -MATCHING A PATTERN - - The function regexec() is called to match a compiled pattern preg - against a given string, which is by default terminated by a zero byte - (but see REG_STARTEND below), subject to the options in eflags. These - can be: - - REG_NOTBOL - - The PCRE_NOTBOL option is set when calling the underlying PCRE matching - function. - - REG_NOTEMPTY - - The PCRE_NOTEMPTY option is set when calling the underlying PCRE match- - ing function. Note that REG_NOTEMPTY is not part of the POSIX standard. - However, setting this option can give more POSIX-like behaviour in some - situations. - - REG_NOTEOL - - The PCRE_NOTEOL option is set when calling the underlying PCRE matching - function. - - REG_STARTEND - - The string is considered to start at string + pmatch[0].rm_so and to - have a terminating NUL located at string + pmatch[0].rm_eo (there need - not actually be a NUL at that location), regardless of the value of - nmatch. This is a BSD extension, compatible with but not specified by - IEEE Standard 1003.2 (POSIX.2), and should be used with caution in - software intended to be portable to other systems. Note that a non-zero - rm_so does not imply REG_NOTBOL; REG_STARTEND affects only the location - of the string, not how it is matched. - - If the pattern was compiled with the REG_NOSUB flag, no data about any - matched strings is returned. The nmatch and pmatch arguments of - regexec() are ignored. - - Otherwise,the portion of the string that was matched, and also any cap- - tured substrings, are returned via the pmatch argument, which points to - an array of nmatch structures of type regmatch_t, containing the mem- - bers rm_so and rm_eo. These contain the offset to the first character - of each substring and the offset to the first character after the end - of each substring, respectively. The 0th element of the vector relates - to the entire portion of string that was matched; subsequent elements - relate to the capturing subpatterns of the regular expression. Unused - entries in the array have both structure members set to -1. - - A successful match yields a zero return; various error codes are - defined in the header file, of which REG_NOMATCH is the "expected" - failure code. - - -ERROR MESSAGES - - The regerror() function maps a non-zero errorcode from either regcomp() - or regexec() to a printable message. If preg is not NULL, the error - should have arisen from the use of that structure. A message terminated - by a binary zero is placed in errbuf. The length of the message, - including the zero, is limited to errbuf_size. The yield of the func- - tion is the size of buffer needed to hold the whole message. - - -MEMORY USAGE - - Compiling a regular expression causes memory to be allocated and asso- - ciated with the preg structure. The function regfree() frees all such - memory, after which preg may no longer be used as a compiled expres- - sion. - - -AUTHOR - - Philip Hazel - University Computing Service - Cambridge CB2 3QH, England. - - -REVISION - - Last updated: 11 March 2009 - Copyright (c) 1997-2009 University of Cambridge. ------------------------------------------------------------------------------- - - -PCRECPP(3) PCRECPP(3) - - -NAME - PCRE - Perl-compatible regular expressions. - - -SYNOPSIS OF C++ WRAPPER - - #include - - -DESCRIPTION - - The C++ wrapper for PCRE was provided by Google Inc. Some additional - functionality was added by Giuseppe Maxia. This brief man page was con- - structed from the notes in the pcrecpp.h file, which should be con- - sulted for further details. - - -MATCHING INTERFACE - - The "FullMatch" operation checks that supplied text matches a supplied - pattern exactly. If pointer arguments are supplied, it copies matched - sub-strings that match sub-patterns into them. - - Example: successful match - pcrecpp::RE re("h.*o"); - re.FullMatch("hello"); - - Example: unsuccessful match (requires full match): - pcrecpp::RE re("e"); - !re.FullMatch("hello"); - - Example: creating a temporary RE object: - pcrecpp::RE("h.*o").FullMatch("hello"); - - You can pass in a "const char*" or a "string" for "text". The examples - below tend to use a const char*. You can, as in the different examples - above, store the RE object explicitly in a variable or use a temporary - RE object. The examples below use one mode or the other arbitrarily. - Either could correctly be used for any of these examples. - - You must supply extra pointer arguments to extract matched subpieces. - - Example: extracts "ruby" into "s" and 1234 into "i" - int i; - string s; - pcrecpp::RE re("(\\w+):(\\d+)"); - re.FullMatch("ruby:1234", &s, &i); - - Example: does not try to extract any extra sub-patterns - re.FullMatch("ruby:1234", &s); - - Example: does not try to extract into NULL - re.FullMatch("ruby:1234", NULL, &i); - - Example: integer overflow causes failure - !re.FullMatch("ruby:1234567891234", NULL, &i); - - Example: fails because there aren't enough sub-patterns: - !pcrecpp::RE("\\w+:\\d+").FullMatch("ruby:1234", &s); - - Example: fails because string cannot be stored in integer - !pcrecpp::RE("(.*)").FullMatch("ruby", &i); - - The provided pointer arguments can be pointers to any scalar numeric - type, or one of: - - string (matched piece is copied to string) - StringPiece (StringPiece is mutated to point to matched piece) - T (where "bool T::ParseFrom(const char*, int)" exists) - NULL (the corresponding matched sub-pattern is not copied) - - The function returns true iff all of the following conditions are sat- - isfied: - - a. "text" matches "pattern" exactly; - - b. The number of matched sub-patterns is >= number of supplied - pointers; - - c. The "i"th argument has a suitable type for holding the - string captured as the "i"th sub-pattern. If you pass in - void * NULL for the "i"th argument, or a non-void * NULL - of the correct type, or pass fewer arguments than the - number of sub-patterns, "i"th captured sub-pattern is - ignored. - - CAVEAT: An optional sub-pattern that does not exist in the matched - string is assigned the empty string. Therefore, the following will - return false (because the empty string is not a valid number): - - int number; - pcrecpp::RE::FullMatch("abc", "[a-z]+(\\d+)?", &number); - - The matching interface supports at most 16 arguments per call. If you - need more, consider using the more general interface - pcrecpp::RE::DoMatch. See pcrecpp.h for the signature for DoMatch. - - NOTE: Do not use no_arg, which is used internally to mark the end of a - list of optional arguments, as a placeholder for missing arguments, as - this can lead to segfaults. - - -QUOTING METACHARACTERS - - You can use the "QuoteMeta" operation to insert backslashes before all - potentially meaningful characters in a string. The returned string, - used as a regular expression, will exactly match the original string. - - Example: - string quoted = RE::QuoteMeta(unquoted); - - Note that it's legal to escape a character even if it has no special - meaning in a regular expression -- so this function does that. (This - also makes it identical to the perl function of the same name; see - "perldoc -f quotemeta".) For example, "1.5-2.0?" becomes - "1\.5\-2\.0\?". - - -PARTIAL MATCHES - - You can use the "PartialMatch" operation when you want the pattern to - match any substring of the text. - - Example: simple search for a string: - pcrecpp::RE("ell").PartialMatch("hello"); - - Example: find first number in a string: - int number; - pcrecpp::RE re("(\\d+)"); - re.PartialMatch("x*100 + 20", &number); - assert(number == 100); - - -UTF-8 AND THE MATCHING INTERFACE - - By default, pattern and text are plain text, one byte per character. - The UTF8 flag, passed to the constructor, causes both pattern and - string to be treated as UTF-8 text, still a byte stream but potentially - multiple bytes per character. In practice, the text is likelier to be - UTF-8 than the pattern, but the match returned may depend on the UTF8 - flag, so always use it when matching UTF8 text. For example, "." will - match one byte normally but with UTF8 set may match up to three bytes - of a multi-byte character. - - Example: - pcrecpp::RE_Options options; - options.set_utf8(); - pcrecpp::RE re(utf8_pattern, options); - re.FullMatch(utf8_string); - - Example: using the convenience function UTF8(): - pcrecpp::RE re(utf8_pattern, pcrecpp::UTF8()); - re.FullMatch(utf8_string); - - NOTE: The UTF8 flag is ignored if pcre was not configured with the - --enable-utf8 flag. - - -PASSING MODIFIERS TO THE REGULAR EXPRESSION ENGINE - - PCRE defines some modifiers to change the behavior of the regular - expression engine. The C++ wrapper defines an auxiliary class, - RE_Options, as a vehicle to pass such modifiers to a RE class. Cur- - rently, the following modifiers are supported: - - modifier description Perl corresponding - - PCRE_CASELESS case insensitive match /i - PCRE_MULTILINE multiple lines match /m - PCRE_DOTALL dot matches newlines /s - PCRE_DOLLAR_ENDONLY $ matches only at end N/A - PCRE_EXTRA strict escape parsing N/A - PCRE_EXTENDED ignore whitespaces /x - PCRE_UTF8 handles UTF8 chars built-in - PCRE_UNGREEDY reverses * and *? N/A - PCRE_NO_AUTO_CAPTURE disables capturing parens N/A (*) - - (*) Both Perl and PCRE allow non capturing parentheses by means of the - "?:" modifier within the pattern itself. e.g. (?:ab|cd) does not cap- - ture, while (ab|cd) does. - - For a full account on how each modifier works, please check the PCRE - API reference page. - - For each modifier, there are two member functions whose name is made - out of the modifier in lowercase, without the "PCRE_" prefix. For - instance, PCRE_CASELESS is handled by - - bool caseless() - - which returns true if the modifier is set, and - - RE_Options & set_caseless(bool) - - which sets or unsets the modifier. Moreover, PCRE_EXTRA_MATCH_LIMIT can - be accessed through the set_match_limit() and match_limit() member - functions. Setting match_limit to a non-zero value will limit the exe- - cution of pcre to keep it from doing bad things like blowing the stack - or taking an eternity to return a result. A value of 5000 is good - enough to stop stack blowup in a 2MB thread stack. Setting match_limit - to zero disables match limiting. Alternatively, you can call - match_limit_recursion() which uses PCRE_EXTRA_MATCH_LIMIT_RECURSION to - limit how much PCRE recurses. match_limit() limits the number of - matches PCRE does; match_limit_recursion() limits the depth of internal - recursion, and therefore the amount of stack that is used. - - Normally, to pass one or more modifiers to a RE class, you declare a - RE_Options object, set the appropriate options, and pass this object to - a RE constructor. Example: - - RE_options opt; - opt.set_caseless(true); - if (RE("HELLO", opt).PartialMatch("hello world")) ... - - RE_options has two constructors. The default constructor takes no argu- - ments and creates a set of flags that are off by default. The optional - parameter option_flags is to facilitate transfer of legacy code from C - programs. This lets you do - - RE(pattern, - RE_Options(PCRE_CASELESS|PCRE_MULTILINE)).PartialMatch(str); - - However, new code is better off doing - - RE(pattern, - RE_Options().set_caseless(true).set_multiline(true)) - .PartialMatch(str); - - If you are going to pass one of the most used modifiers, there are some - convenience functions that return a RE_Options class with the appropri- - ate modifier already set: CASELESS(), UTF8(), MULTILINE(), DOTALL(), - and EXTENDED(). - - If you need to set several options at once, and you don't want to go - through the pains of declaring a RE_Options object and setting several - options, there is a parallel method that give you such ability on the - fly. You can concatenate several set_xxxxx() member functions, since - each of them returns a reference to its class object. For example, to - pass PCRE_CASELESS, PCRE_EXTENDED, and PCRE_MULTILINE to a RE with one - statement, you may write: - - RE(" ^ xyz \\s+ .* blah$", - RE_Options() - .set_caseless(true) - .set_extended(true) - .set_multiline(true)).PartialMatch(sometext); - - -SCANNING TEXT INCREMENTALLY - - The "Consume" operation may be useful if you want to repeatedly match - regular expressions at the front of a string and skip over them as they - match. This requires use of the "StringPiece" type, which represents a - sub-range of a real string. Like RE, StringPiece is defined in the - pcrecpp namespace. - - Example: read lines of the form "var = value" from a string. - string contents = ...; // Fill string somehow - pcrecpp::StringPiece input(contents); // Wrap in a StringPiece - - string var; - int value; - pcrecpp::RE re("(\\w+) = (\\d+)\n"); - while (re.Consume(&input, &var, &value)) { - ...; - } - - Each successful call to "Consume" will set "var/value", and also - advance "input" so it points past the matched text. - - The "FindAndConsume" operation is similar to "Consume" but does not - anchor your match at the beginning of the string. For example, you - could extract all words from a string by repeatedly calling - - pcrecpp::RE("(\\w+)").FindAndConsume(&input, &word) - - -PARSING HEX/OCTAL/C-RADIX NUMBERS - - By default, if you pass a pointer to a numeric value, the corresponding - text is interpreted as a base-10 number. You can instead wrap the - pointer with a call to one of the operators Hex(), Octal(), or CRadix() - to interpret the text in another base. The CRadix operator interprets - C-style "0" (base-8) and "0x" (base-16) prefixes, but defaults to - base-10. - - Example: - int a, b, c, d; - pcrecpp::RE re("(.*) (.*) (.*) (.*)"); - re.FullMatch("100 40 0100 0x40", - pcrecpp::Octal(&a), pcrecpp::Hex(&b), - pcrecpp::CRadix(&c), pcrecpp::CRadix(&d)); - - will leave 64 in a, b, c, and d. - - -REPLACING PARTS OF STRINGS - - You can replace the first match of "pattern" in "str" with "rewrite". - Within "rewrite", backslash-escaped digits (\1 to \9) can be used to - insert text matching corresponding parenthesized group from the pat- - tern. \0 in "rewrite" refers to the entire matching text. For example: - - string s = "yabba dabba doo"; - pcrecpp::RE("b+").Replace("d", &s); - - will leave "s" containing "yada dabba doo". The result is true if the - pattern matches and a replacement occurs, false otherwise. - - GlobalReplace is like Replace except that it replaces all occurrences - of the pattern in the string with the rewrite. Replacements are not - subject to re-matching. For example: - - string s = "yabba dabba doo"; - pcrecpp::RE("b+").GlobalReplace("d", &s); - - will leave "s" containing "yada dada doo". It returns the number of - replacements made. - - Extract is like Replace, except that if the pattern matches, "rewrite" - is copied into "out" (an additional argument) with substitutions. The - non-matching portions of "text" are ignored. Returns true iff a match - occurred and the extraction happened successfully; if no match occurs, - the string is left unaffected. - - -AUTHOR - - The C++ wrapper was contributed by Google Inc. - Copyright (c) 2007 Google Inc. - - -REVISION - - Last updated: 17 March 2009 ------------------------------------------------------------------------------- - - -PCRESAMPLE(3) PCRESAMPLE(3) - - -NAME - PCRE - Perl-compatible regular expressions - - -PCRE SAMPLE PROGRAM - - A simple, complete demonstration program, to get you started with using - PCRE, is supplied in the file pcredemo.c in the PCRE distribution. - - The program compiles the regular expression that is its first argument, - and matches it against the subject string in its second argument. No - PCRE options are set, and default character tables are used. If match- - ing succeeds, the program outputs the portion of the subject that - matched, together with the contents of any captured substrings. - - If the -g option is given on the command line, the program then goes on - to check for further matches of the same regular expression in the same - subject string. The logic is a little bit tricky because of the possi- - bility of matching an empty string. Comments in the code explain what - is going on. - - If PCRE is installed in the standard include and library directories - for your system, you should be able to compile the demonstration pro- - gram using this command: - - gcc -o pcredemo pcredemo.c -lpcre - - If PCRE is installed elsewhere, you may need to add additional options - to the command line. For example, on a Unix-like system that has PCRE - installed in /usr/local, you can compile the demonstration program - using a command like this: - - gcc -o pcredemo -I/usr/local/include pcredemo.c \ - -L/usr/local/lib -lpcre - - Once you have compiled the demonstration program, you can run simple - tests like this: - - ./pcredemo 'cat|dog' 'the cat sat on the mat' - ./pcredemo -g 'cat|dog' 'the dog sat on the cat' - - Note that there is a much more comprehensive test program, called - pcretest, which supports many more facilities for testing regular - expressions and the PCRE library. The pcredemo program is provided as a - simple coding example. - - On some operating systems (e.g. Solaris), when PCRE is not installed in - the standard library directory, you may get an error like this when you - try to run pcredemo: - - ld.so.1: a.out: fatal: libpcre.so.0: open failed: No such file or - directory - - This is caused by the way shared library support works on those sys- - tems. You need to add - - -R/usr/local/lib - - (for example) to the compile command to get round this problem. - - -AUTHOR - - Philip Hazel - University Computing Service - Cambridge CB2 3QH, England. - - -REVISION - - Last updated: 23 January 2008 - Copyright (c) 1997-2008 University of Cambridge. ------------------------------------------------------------------------------- -PCRESTACK(3) PCRESTACK(3) - - -NAME - PCRE - Perl-compatible regular expressions - - -PCRE DISCUSSION OF STACK USAGE - - When you call pcre_exec(), it makes use of an internal function called - match(). This calls itself recursively at branch points in the pattern, - in order to remember the state of the match so that it can back up and - try a different alternative if the first one fails. As matching pro- - ceeds deeper and deeper into the tree of possibilities, the recursion - depth increases. - - Not all calls of match() increase the recursion depth; for an item such - as a* it may be called several times at the same level, after matching - different numbers of a's. Furthermore, in a number of cases where the - result of the recursive call would immediately be passed back as the - result of the current call (a "tail recursion"), the function is just - restarted instead. - - The pcre_dfa_exec() function operates in an entirely different way, and - hardly uses recursion at all. The limit on its complexity is the amount - of workspace it is given. The comments that follow do NOT apply to - pcre_dfa_exec(); they are relevant only for pcre_exec(). - - You can set limits on the number of times that match() is called, both - in total and recursively. If the limit is exceeded, an error occurs. - For details, see the section on extra data for pcre_exec() in the - pcreapi documentation. - - Each time that match() is actually called recursively, it uses memory - from the process stack. For certain kinds of pattern and data, very - large amounts of stack may be needed, despite the recognition of "tail - recursion". You can often reduce the amount of recursion, and there- - fore the amount of stack used, by modifying the pattern that is being - matched. Consider, for example, this pattern: - - ([^<]|<(?!inet))+ - - It matches from wherever it starts until it encounters " -.PP -.SM -.B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP, -.ti +5n -.B const char **\fIerrptr\fP, int *\fIerroffset\fP, -.ti +5n -.B const unsigned char *\fItableptr\fP); -. -.SH DESCRIPTION -.rs -.sp -This function compiles a regular expression into an internal form. It is the -same as \fBpcre_compile2()\fP, except for the absence of the \fIerrorcodeptr\fP -argument. Its arguments are: -.sp - \fIpattern\fR A zero-terminated string containing the - regular expression to be compiled - \fIoptions\fR Zero or more option bits - \fIerrptr\fR Where to put an error message - \fIerroffset\fR Offset in pattern where error was found - \fItableptr\fR Pointer to character tables, or NULL to - use the built-in default -.sp -The option bits are: -.sp - PCRE_ANCHORED Force pattern anchoring - PCRE_AUTO_CALLOUT Compile automatic callouts - PCRE_BSR_ANYCRLF \eR matches only CR, LF, or CRLF - PCRE_BSR_UNICODE \eR matches all Unicode line endings - PCRE_CASELESS Do caseless matching - PCRE_DOLLAR_ENDONLY $ not to match newline at end - PCRE_DOTALL . matches anything including NL - PCRE_DUPNAMES Allow duplicate names for subpatterns - PCRE_EXTENDED Ignore whitespace and # comments - PCRE_EXTRA PCRE extra features - (not much use currently) - PCRE_FIRSTLINE Force matching to be before newline - PCRE_JAVASCRIPT_COMPAT JavaScript compatibility - PCRE_MULTILINE ^ and $ match newlines within data - PCRE_NEWLINE_ANY Recognize any Unicode newline sequence - PCRE_NEWLINE_ANYCRLF Recognize CR, LF, and CRLF as newline - sequences - PCRE_NEWLINE_CR Set CR as the newline sequence - PCRE_NEWLINE_CRLF Set CRLF as the newline sequence - PCRE_NEWLINE_LF Set LF as the newline sequence - PCRE_NO_AUTO_CAPTURE Disable numbered capturing paren- - theses (named ones available) - PCRE_UNGREEDY Invert greediness of quantifiers - PCRE_UTF8 Run in UTF-8 mode - PCRE_NO_UTF8_CHECK Do not check the pattern for UTF-8 - validity (only relevant if - PCRE_UTF8 is set) -.sp -PCRE must be built with UTF-8 support in order to use PCRE_UTF8 and -PCRE_NO_UTF8_CHECK. -.P -The yield of the function is a pointer to a private data structure that -contains the compiled pattern, or NULL if an error was detected. Note that -compiling regular expressions with one version of PCRE for use with a different -version is not guaranteed to work and may cause crashes. -.P -There is a complete description of the PCRE native API in the -.\" HREF -\fBpcreapi\fR -.\" -page and a description of the POSIX API in the -.\" HREF -\fBpcreposix\fR -.\" -page. diff --git a/libs/pcre/doc/pcre_compile2.3 b/libs/pcre/doc/pcre_compile2.3 deleted file mode 100644 index 1e71aff60e..0000000000 --- a/libs/pcre/doc/pcre_compile2.3 +++ /dev/null @@ -1,77 +0,0 @@ -.TH PCRE_COMPILE2 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include -.PP -.SM -.B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP, -.ti +5n -.B int *\fIerrorcodeptr\fP, -.ti +5n -.B const char **\fIerrptr\fP, int *\fIerroffset\fP, -.ti +5n -.B const unsigned char *\fItableptr\fP); -. -.SH DESCRIPTION -.rs -.sp -This function compiles a regular expression into an internal form. It is the -same as \fBpcre_compile()\fP, except for the addition of the \fIerrorcodeptr\fP -argument. The arguments are: - -.sp - \fIpattern\fR A zero-terminated string containing the - regular expression to be compiled - \fIoptions\fR Zero or more option bits - \fIerrorcodeptr\fP Where to put an error code - \fIerrptr\fR Where to put an error message - \fIerroffset\fR Offset in pattern where error was found - \fItableptr\fR Pointer to character tables, or NULL to - use the built-in default -.sp -The option bits are: -.sp - PCRE_ANCHORED Force pattern anchoring - PCRE_AUTO_CALLOUT Compile automatic callouts - PCRE_CASELESS Do caseless matching - PCRE_DOLLAR_ENDONLY $ not to match newline at end - PCRE_DOTALL . matches anything including NL - PCRE_DUPNAMES Allow duplicate names for subpatterns - PCRE_EXTENDED Ignore whitespace and # comments - PCRE_EXTRA PCRE extra features - (not much use currently) - PCRE_FIRSTLINE Force matching to be before newline - PCRE_MULTILINE ^ and $ match newlines within data - PCRE_NEWLINE_ANY Recognize any Unicode newline sequence - PCRE_NEWLINE_ANYCRLF Recognize CR, LF, and CRLF as newline sequences - PCRE_NEWLINE_CR Set CR as the newline sequence - PCRE_NEWLINE_CRLF Set CRLF as the newline sequence - PCRE_NEWLINE_LF Set LF as the newline sequence - PCRE_NO_AUTO_CAPTURE Disable numbered capturing paren- - theses (named ones available) - PCRE_UNGREEDY Invert greediness of quantifiers - PCRE_UTF8 Run in UTF-8 mode - PCRE_NO_UTF8_CHECK Do not check the pattern for UTF-8 - validity (only relevant if - PCRE_UTF8 is set) -.sp -PCRE must be built with UTF-8 support in order to use PCRE_UTF8 and -PCRE_NO_UTF8_CHECK. -.P -The yield of the function is a pointer to a private data structure that -contains the compiled pattern, or NULL if an error was detected. Note that -compiling regular expressions with one version of PCRE for use with a different -version is not guaranteed to work and may cause crashes. -.P -There is a complete description of the PCRE native API in the -.\" HREF -\fBpcreapi\fR -.\" -page and a description of the POSIX API in the -.\" HREF -\fBpcreposix\fR -.\" -page. diff --git a/libs/pcre/doc/pcre_config.3 b/libs/pcre/doc/pcre_config.3 deleted file mode 100644 index b111a70cad..0000000000 --- a/libs/pcre/doc/pcre_config.3 +++ /dev/null @@ -1,57 +0,0 @@ -.TH PCRE_CONFIG 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include -.PP -.SM -.B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP); -. -.SH DESCRIPTION -.rs -.sp -This function makes it possible for a client program to find out which optional -features are available in the version of the PCRE library it is using. Its -arguments are as follows: -.sp - \fIwhat\fR A code specifying what information is required - \fIwhere\fR Points to where to put the data -.sp -The available codes are: -.sp - PCRE_CONFIG_LINK_SIZE Internal link size: 2, 3, or 4 - PCRE_CONFIG_MATCH_LIMIT Internal resource limit - PCRE_CONFIG_MATCH_LIMIT_RECURSION - Internal recursion depth limit - PCRE_CONFIG_NEWLINE Value of the default newline sequence: - 13 (0x000d) for CR - 10 (0x000a) for LF - 3338 (0x0d0a) for CRLF - -2 for ANYCRLF - -1 for ANY - PCRE_CONFIG_BSR Indicates what \eR matches by default: - 0 all Unicode line endings - 1 CR, LF, or CRLF only - PCRE_CONFIG_POSIX_MALLOC_THRESHOLD - Threshold of return slots, above - which \fBmalloc()\fR is used by - the POSIX API - PCRE_CONFIG_STACKRECURSE Recursion implementation (1=stack 0=heap) - PCRE_CONFIG_UTF8 Availability of UTF-8 support (1=yes 0=no) - PCRE_CONFIG_UNICODE_PROPERTIES - Availability of Unicode property support - (1=yes 0=no) -.sp -The function yields 0 on success or PCRE_ERROR_BADOPTION otherwise. -.P -There is a complete description of the PCRE native API in the -.\" HREF -\fBpcreapi\fR -.\" -page and a description of the POSIX API in the -.\" HREF -\fBpcreposix\fR -.\" -page. diff --git a/libs/pcre/doc/pcre_copy_named_substring.3 b/libs/pcre/doc/pcre_copy_named_substring.3 deleted file mode 100644 index 9ad682655b..0000000000 --- a/libs/pcre/doc/pcre_copy_named_substring.3 +++ /dev/null @@ -1,43 +0,0 @@ -.TH PCRE_COPY_NAMED_SUBSTRING 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include -.PP -.SM -.B int pcre_copy_named_substring(const pcre *\fIcode\fP, -.ti +5n -.B const char *\fIsubject\fP, int *\fIovector\fP, -.ti +5n -.B int \fIstringcount\fP, const char *\fIstringname\fP, -.ti +5n -.B char *\fIbuffer\fP, int \fIbuffersize\fP); -. -.SH DESCRIPTION -.rs -.sp -This is a convenience function for extracting a captured substring, identified -by name, into a given buffer. The arguments are: -.sp - \fIcode\fP Pattern that was successfully matched - \fIsubject\fP Subject that has been successfully matched - \fIovector\fP Offset vector that \fBpcre_exec()\fP used - \fIstringcount\fP Value returned by \fBpcre_exec()\fP - \fIstringname\fP Name of the required substring - \fIbuffer\fP Buffer to receive the string - \fIbuffersize\fP Size of buffer -.sp -The yield is the length of the substring, PCRE_ERROR_NOMEMORY if the buffer was -too small, or PCRE_ERROR_NOSUBSTRING if the string name is invalid. -.P -There is a complete description of the PCRE native API in the -.\" HREF -\fBpcreapi\fP -.\" -page and a description of the POSIX API in the -.\" HREF -\fBpcreposix\fP -.\" -page. diff --git a/libs/pcre/doc/pcre_copy_substring.3 b/libs/pcre/doc/pcre_copy_substring.3 deleted file mode 100644 index 1910d185e7..0000000000 --- a/libs/pcre/doc/pcre_copy_substring.3 +++ /dev/null @@ -1,40 +0,0 @@ -.TH PCRE_COPY_SUBSTRING 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include -.PP -.SM -.B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP, -.ti +5n -.B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP, -.ti +5n -.B int \fIbuffersize\fP); -. -.SH DESCRIPTION -.rs -.sp -This is a convenience function for extracting a captured substring into a given -buffer. The arguments are: -.sp - \fIsubject\fP Subject that has been successfully matched - \fIovector\fP Offset vector that \fBpcre_exec()\fP used - \fIstringcount\fP Value returned by \fBpcre_exec()\fP - \fIstringnumber\fP Number of the required substring - \fIbuffer\fP Buffer to receive the string - \fIbuffersize\fP Size of buffer -.sp -The yield is the length of the string, PCRE_ERROR_NOMEMORY if the buffer was -too small, or PCRE_ERROR_NOSUBSTRING if the string number is invalid. -.P -There is a complete description of the PCRE native API in the -.\" HREF -\fBpcreapi\fP -.\" -page and a description of the POSIX API in the -.\" HREF -\fBpcreposix\fP -.\" -page. diff --git a/libs/pcre/doc/pcre_dfa_exec.3 b/libs/pcre/doc/pcre_dfa_exec.3 deleted file mode 100644 index a046276d63..0000000000 --- a/libs/pcre/doc/pcre_dfa_exec.3 +++ /dev/null @@ -1,89 +0,0 @@ -.TH PCRE_DFA_EXEC 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include -.PP -.SM -.B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," -.ti +5n -.B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP, -.ti +5n -.B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP, -.ti +5n -.B int *\fIworkspace\fP, int \fIwscount\fP); -. -.SH DESCRIPTION -.rs -.sp -This function matches a compiled regular expression against a given subject -string, using an alternative matching algorithm that scans the subject string -just once (\fInot\fP Perl-compatible). Note that the main, Perl-compatible, -matching function is \fBpcre_exec()\fP. The arguments for this function are: -.sp - \fIcode\fP Points to the compiled pattern - \fIextra\fP Points to an associated \fBpcre_extra\fP structure, - or is NULL - \fIsubject\fP Points to the subject string - \fIlength\fP Length of the subject string, in bytes - \fIstartoffset\fP Offset in bytes in the subject at which to - start matching - \fIoptions\fP Option bits - \fIovector\fP Points to a vector of ints for result offsets - \fIovecsize\fP Number of elements in the vector - \fIworkspace\fP Points to a vector of ints used as working space - \fIwscount\fP Number of elements in the vector -.sp -The options are: -.sp - PCRE_ANCHORED Match only at the first position - PCRE_BSR_ANYCRLF \eR matches only CR, LF, or CRLF - PCRE_BSR_UNICODE \eR matches all Unicode line endings - PCRE_NEWLINE_ANY Recognize any Unicode newline sequence - PCRE_NEWLINE_ANYCRLF Recognize CR, LF, and CRLF as newline sequences - PCRE_NEWLINE_CR Set CR as the newline sequence - PCRE_NEWLINE_CRLF Set CRLF as the newline sequence - PCRE_NEWLINE_LF Set LF as the newline sequence - PCRE_NOTBOL Subject is not the beginning of a line - PCRE_NOTEOL Subject is not the end of a line - PCRE_NOTEMPTY An empty string is not a valid match - PCRE_NO_START_OPTIMIZE Do not do "start-match" optimizations - PCRE_NO_UTF8_CHECK Do not check the subject for UTF-8 - validity (only relevant if PCRE_UTF8 - was set at compile time) - PCRE_PARTIAL Return PCRE_ERROR_PARTIAL for a partial match - PCRE_DFA_SHORTEST Return only the shortest match - PCRE_DFA_RESTART This is a restart after a partial match -.sp -There are restrictions on what may appear in a pattern when using this matching -function. Details are given in the -.\" HREF -\fBpcrematching\fP -.\" -documentation. -.P -A \fBpcre_extra\fP structure contains the following fields: -.sp - \fIflags\fP Bits indicating which fields are set - \fIstudy_data\fP Opaque data from \fBpcre_study()\fP - \fImatch_limit\fP Limit on internal resource use - \fImatch_limit_recursion\fP Limit on internal recursion depth - \fIcallout_data\fP Opaque data passed back to callouts - \fItables\fP Points to character tables or is NULL -.sp -The flag bits are PCRE_EXTRA_STUDY_DATA, PCRE_EXTRA_MATCH_LIMIT, -PCRE_EXTRA_MATCH_LIMIT_RECURSION, PCRE_EXTRA_CALLOUT_DATA, and -PCRE_EXTRA_TABLES. For this matching function, the \fImatch_limit\fP and -\fImatch_limit_recursion\fP fields are not used, and must not be set. -.P -There is a complete description of the PCRE native API in the -.\" HREF -\fBpcreapi\fP -.\" -page and a description of the POSIX API in the -.\" HREF -\fBpcreposix\fP -.\" -page. diff --git a/libs/pcre/doc/pcre_exec.3 b/libs/pcre/doc/pcre_exec.3 deleted file mode 100644 index 21bf6da5e0..0000000000 --- a/libs/pcre/doc/pcre_exec.3 +++ /dev/null @@ -1,81 +0,0 @@ -.TH PCRE_EXEC 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include -.PP -.SM -.B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," -.ti +5n -.B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP, -.ti +5n -.B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP); -. -.SH DESCRIPTION -.rs -.sp -This function matches a compiled regular expression against a given subject -string, using a matching algorithm that is similar to Perl's. It returns -offsets to captured substrings. Its arguments are: -.sp - \fIcode\fP Points to the compiled pattern - \fIextra\fP Points to an associated \fBpcre_extra\fP structure, - or is NULL - \fIsubject\fP Points to the subject string - \fIlength\fP Length of the subject string, in bytes - \fIstartoffset\fP Offset in bytes in the subject at which to - start matching - \fIoptions\fP Option bits - \fIovector\fP Points to a vector of ints for result offsets - \fIovecsize\fP Number of elements in the vector (a multiple of 3) -.sp -The options are: -.sp - PCRE_ANCHORED Match only at the first position - PCRE_BSR_ANYCRLF \eR matches only CR, LF, or CRLF - PCRE_BSR_UNICODE \eR matches all Unicode line endings - PCRE_NEWLINE_ANY Recognize any Unicode newline sequence - PCRE_NEWLINE_ANYCRLF Recognize CR, LF, and CRLF as newline sequences - PCRE_NEWLINE_CR Set CR as the newline sequence - PCRE_NEWLINE_CRLF Set CRLF as the newline sequence - PCRE_NEWLINE_LF Set LF as the newline sequence - PCRE_NOTBOL Subject is not the beginning of a line - PCRE_NOTEOL Subject is not the end of a line - PCRE_NOTEMPTY An empty string is not a valid match - PCRE_NO_START_OPTIMIZE Do not do "start-match" optimizations - PCRE_NO_UTF8_CHECK Do not check the subject for UTF-8 - validity (only relevant if PCRE_UTF8 - was set at compile time) - PCRE_PARTIAL Return PCRE_ERROR_PARTIAL for a partial match -.sp -There are restrictions on what may appear in a pattern when partial matching is -requested. For details, see the -.\" HREF -\fBpcrepartial\fP -.\" -page. -.P -A \fBpcre_extra\fP structure contains the following fields: -.sp - \fIflags\fP Bits indicating which fields are set - \fIstudy_data\fP Opaque data from \fBpcre_study()\fP - \fImatch_limit\fP Limit on internal resource use - \fImatch_limit_recursion\fP Limit on internal recursion depth - \fIcallout_data\fP Opaque data passed back to callouts - \fItables\fP Points to character tables or is NULL -.sp -The flag bits are PCRE_EXTRA_STUDY_DATA, PCRE_EXTRA_MATCH_LIMIT, -PCRE_EXTRA_MATCH_LIMIT_RECURSION, PCRE_EXTRA_CALLOUT_DATA, and -PCRE_EXTRA_TABLES. -.P -There is a complete description of the PCRE native API in the -.\" HREF -\fBpcreapi\fP -.\" -page and a description of the POSIX API in the -.\" HREF -\fBpcreposix\fP -.\" -page. diff --git a/libs/pcre/doc/pcre_free_substring.3 b/libs/pcre/doc/pcre_free_substring.3 deleted file mode 100644 index ed3999a746..0000000000 --- a/libs/pcre/doc/pcre_free_substring.3 +++ /dev/null @@ -1,27 +0,0 @@ -.TH PCRE_FREE_SUBSTRING 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include -.PP -.SM -.B void pcre_free_substring(const char *\fIstringptr\fP); -. -.SH DESCRIPTION -.rs -.sp -This is a convenience function for freeing the store obtained by a previous -call to \fBpcre_get_substring()\fP or \fBpcre_get_named_substring()\fP. Its -only argument is a pointer to the string. -.P -There is a complete description of the PCRE native API in the -.\" HREF -\fBpcreapi\fP -.\" -page and a description of the POSIX API in the -.\" HREF -\fBpcreposix\fP -.\" -page. diff --git a/libs/pcre/doc/pcre_free_substring_list.3 b/libs/pcre/doc/pcre_free_substring_list.3 deleted file mode 100644 index 89b7078524..0000000000 --- a/libs/pcre/doc/pcre_free_substring_list.3 +++ /dev/null @@ -1,27 +0,0 @@ -.TH PCRE_FREE_SUBSTRING_LIST 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include -.PP -.SM -.B void pcre_free_substring_list(const char **\fIstringptr\fP); -. -.SH DESCRIPTION -.rs -.sp -This is a convenience function for freeing the store obtained by a previous -call to \fBpcre_get_substring_list()\fP. Its only argument is a pointer to the -list of string pointers. -.P -There is a complete description of the PCRE native API in the -.\" HREF -\fBpcreapi\fP -.\" -page and a description of the POSIX API in the -.\" HREF -\fBpcreposix\fP -.\" -page. diff --git a/libs/pcre/doc/pcre_fullinfo.3 b/libs/pcre/doc/pcre_fullinfo.3 deleted file mode 100644 index 3cf8cbddef..0000000000 --- a/libs/pcre/doc/pcre_fullinfo.3 +++ /dev/null @@ -1,59 +0,0 @@ -.TH PCRE_FULLINFO 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include -.PP -.SM -.B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," -.ti +5n -.B int \fIwhat\fP, void *\fIwhere\fP); -. -.SH DESCRIPTION -.rs -.sp -This function returns information about a compiled pattern. Its arguments are: -.sp - \fIcode\fP Compiled regular expression - \fIextra\fP Result of \fBpcre_study()\fP or NULL - \fIwhat\fP What information is required - \fIwhere\fP Where to put the information -.sp -The following information is available: -.sp - PCRE_INFO_BACKREFMAX Number of highest back reference - PCRE_INFO_CAPTURECOUNT Number of capturing subpatterns - PCRE_INFO_DEFAULT_TABLES Pointer to default tables - PCRE_INFO_FIRSTBYTE Fixed first byte for a match, or - -1 for start of string - or after newline, or - -2 otherwise - PCRE_INFO_FIRSTTABLE Table of first bytes (after studying) - PCRE_INFO_JCHANGED Return 1 if (?J) or (?-J) was used - PCRE_INFO_LASTLITERAL Literal last byte required - PCRE_INFO_NAMECOUNT Number of named subpatterns - PCRE_INFO_NAMEENTRYSIZE Size of name table entry - PCRE_INFO_NAMETABLE Pointer to name table - PCRE_INFO_OKPARTIAL Return 1 if partial matching can be tried - PCRE_INFO_OPTIONS Option bits used for compilation - PCRE_INFO_SIZE Size of compiled pattern - PCRE_INFO_STUDYSIZE Size of study data -.sp -The yield of the function is zero on success or: -.sp - PCRE_ERROR_NULL the argument \fIcode\fP was NULL - the argument \fIwhere\fP was NULL - PCRE_ERROR_BADMAGIC the "magic number" was not found - PCRE_ERROR_BADOPTION the value of \fIwhat\fP was invalid -.P -There is a complete description of the PCRE native API in the -.\" HREF -\fBpcreapi\fP -.\" -page and a description of the POSIX API in the -.\" HREF -\fBpcreposix\fP -.\" -page. diff --git a/libs/pcre/doc/pcre_get_named_substring.3 b/libs/pcre/doc/pcre_get_named_substring.3 deleted file mode 100644 index 22d0c1be32..0000000000 --- a/libs/pcre/doc/pcre_get_named_substring.3 +++ /dev/null @@ -1,45 +0,0 @@ -.TH PCRE_GET_NAMED_SUBSTRING 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include -.PP -.SM -.B int pcre_get_named_substring(const pcre *\fIcode\fP, -.ti +5n -.B const char *\fIsubject\fP, int *\fIovector\fP, -.ti +5n -.B int \fIstringcount\fP, const char *\fIstringname\fP, -.ti +5n -.B const char **\fIstringptr\fP); -. -.SH DESCRIPTION -.rs -.sp -This is a convenience function for extracting a captured substring by name. The -arguments are: -.sp - \fIcode\fP Compiled pattern - \fIsubject\fP Subject that has been successfully matched - \fIovector\fP Offset vector that \fBpcre_exec()\fP used - \fIstringcount\fP Value returned by \fBpcre_exec()\fP - \fIstringname\fP Name of the required substring - \fIstringptr\fP Where to put the string pointer -.sp -The memory in which the substring is placed is obtained by calling -\fBpcre_malloc()\fP. The convenience function \fBpcre_free_substring()\fP can -be used to free it when it is no longer needed. The yield of the function is -the length of the extracted substring, PCRE_ERROR_NOMEMORY if sufficient memory -could not be obtained, or PCRE_ERROR_NOSUBSTRING if the string name is invalid. -.P -There is a complete description of the PCRE native API in the -.\" HREF -\fBpcreapi\fP -.\" -page and a description of the POSIX API in the -.\" HREF -\fBpcreposix\fP -.\" -page. diff --git a/libs/pcre/doc/pcre_get_stringnumber.3 b/libs/pcre/doc/pcre_get_stringnumber.3 deleted file mode 100644 index f6017ffba4..0000000000 --- a/libs/pcre/doc/pcre_get_stringnumber.3 +++ /dev/null @@ -1,37 +0,0 @@ -.TH PCRE_GET_STRINGNUMBER 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include -.PP -.SM -.B int pcre_get_stringnumber(const pcre *\fIcode\fP, -.ti +5n -.B const char *\fIname\fP); -. -.SH DESCRIPTION -.rs -.sp -This convenience function finds the number of a named substring capturing -parenthesis in a compiled pattern. Its arguments are: -.sp - \fIcode\fP Compiled regular expression - \fIname\fP Name whose number is required -.sp -The yield of the function is the number of the parenthesis if the name is -found, or PCRE_ERROR_NOSUBSTRING otherwise. When duplicate names are allowed -(PCRE_DUPNAMES is set), it is not defined which of the numbers is returned by -\fBpcre_get_stringnumber()\fP. You can obtain the complete list by calling -\fBpcre_get_stringtable_entries()\fP. -.P -There is a complete description of the PCRE native API in the -.\" HREF -\fBpcreapi\fP -.\" -page and a description of the POSIX API in the -.\" HREF -\fBpcreposix\fP -.\" -page. diff --git a/libs/pcre/doc/pcre_get_stringtable_entries.3 b/libs/pcre/doc/pcre_get_stringtable_entries.3 deleted file mode 100644 index 979c4be5b9..0000000000 --- a/libs/pcre/doc/pcre_get_stringtable_entries.3 +++ /dev/null @@ -1,40 +0,0 @@ -.TH PCRE_GET_STRINGTABLE_ENTRIES 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include -.PP -.SM -.B int pcre_get_stringtable_entries(const pcre *\fIcode\fP, -.ti +5n -.B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP); -. -.SH DESCRIPTION -.rs -.sp -This convenience function finds, for a compiled pattern, the first and last -entries for a given name in the table that translates capturing parenthesis -names into numbers. When names are required to be unique (PCRE_DUPNAMES is -\fInot\fP set), it is usually easier to use \fBpcre_get_stringnumber()\fP -instead. -.sp - \fIcode\fP Compiled regular expression - \fIname\fP Name whose entries required - \fIfirst\fP Where to return a pointer to the first entry - \fIlast\fP Where to return a pointer to the last entry -.sp -The yield of the function is the length of each entry, or -PCRE_ERROR_NOSUBSTRING if none are found. -.P -There is a complete description of the PCRE native API, including the format of -the table entries, in the -.\" HREF -\fBpcreapi\fP -.\" -page, and a description of the POSIX API in the -.\" HREF -\fBpcreposix\fP -.\" -page. diff --git a/libs/pcre/doc/pcre_get_substring.3 b/libs/pcre/doc/pcre_get_substring.3 deleted file mode 100644 index 8fb11ec6d1..0000000000 --- a/libs/pcre/doc/pcre_get_substring.3 +++ /dev/null @@ -1,42 +0,0 @@ -.TH PCRE_GET_SUBSTRING 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include -.PP -.SM -.B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP, -.ti +5n -.B int \fIstringcount\fP, int \fIstringnumber\fP, -.ti +5n -.B const char **\fIstringptr\fP); -. -.SH DESCRIPTION -.rs -.sp -This is a convenience function for extracting a captured substring. The -arguments are: -.sp - \fIsubject\fP Subject that has been successfully matched - \fIovector\fP Offset vector that \fBpcre_exec()\fP used - \fIstringcount\fP Value returned by \fBpcre_exec()\fP - \fIstringnumber\fP Number of the required substring - \fIstringptr\fP Where to put the string pointer -.sp -The memory in which the substring is placed is obtained by calling -\fBpcre_malloc()\fP. The convenience function \fBpcre_free_substring()\fP can -be used to free it when it is no longer needed. The yield of the function is -the length of the substring, PCRE_ERROR_NOMEMORY if sufficient memory could not -be obtained, or PCRE_ERROR_NOSUBSTRING if the string number is invalid. -.P -There is a complete description of the PCRE native API in the -.\" HREF -\fBpcreapi\fP -.\" -page and a description of the POSIX API in the -.\" HREF -\fBpcreposix\fP -.\" -page. diff --git a/libs/pcre/doc/pcre_get_substring_list.3 b/libs/pcre/doc/pcre_get_substring_list.3 deleted file mode 100644 index 647ae39191..0000000000 --- a/libs/pcre/doc/pcre_get_substring_list.3 +++ /dev/null @@ -1,41 +0,0 @@ -.TH PCRE_GET_SUBSTRING_LIST 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include -.PP -.SM -.B int pcre_get_substring_list(const char *\fIsubject\fP, -.ti +5n -.B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);" -. -.SH DESCRIPTION -.rs -.sp -This is a convenience function for extracting a list of all the captured -substrings. The arguments are: -.sp - \fIsubject\fP Subject that has been successfully matched - \fIovector\fP Offset vector that \fBpcre_exec\fP used - \fIstringcount\fP Value returned by \fBpcre_exec\fP - \fIlistptr\fP Where to put a pointer to the list -.sp -The memory in which the substrings and the list are placed is obtained by -calling \fBpcre_malloc()\fP. The convenience function -\fBpcre_free_substring_list()\fP can be used to free it when it is no longer -needed. A pointer to a list of pointers is put in the variable whose address is -in \fIlistptr\fP. The list is terminated by a NULL pointer. The yield of the -function is zero on success or PCRE_ERROR_NOMEMORY if sufficient memory could -not be obtained. -.P -There is a complete description of the PCRE native API in the -.\" HREF -\fBpcreapi\fP -.\" -page and a description of the POSIX API in the -.\" HREF -\fBpcreposix\fP -.\" -page. diff --git a/libs/pcre/doc/pcre_info.3 b/libs/pcre/doc/pcre_info.3 deleted file mode 100644 index 8c78121de1..0000000000 --- a/libs/pcre/doc/pcre_info.3 +++ /dev/null @@ -1,26 +0,0 @@ -.TH PCRE_INFO 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include -.PP -.SM -.B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int -.B *\fIfirstcharptr\fP); -. -.SH DESCRIPTION -.rs -.sp -This function is obsolete. You should be using \fBpcre_fullinfo()\fP instead. -.P -There is a complete description of the PCRE native API in the -.\" HREF -\fBpcreapi\fP -.\" -page and a description of the POSIX API in the -.\" HREF -\fBpcreposix\fP -.\" -page. diff --git a/libs/pcre/doc/pcre_maketables.3 b/libs/pcre/doc/pcre_maketables.3 deleted file mode 100644 index 8d3978c251..0000000000 --- a/libs/pcre/doc/pcre_maketables.3 +++ /dev/null @@ -1,29 +0,0 @@ -.TH PCRE_MAKETABLES 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include -.PP -.SM -.B const unsigned char *pcre_maketables(void); -. -.SH DESCRIPTION -.rs -.sp -This function builds a set of character tables for character values less than -256. These can be passed to \fBpcre_compile()\fP to override PCRE's internal, -built-in tables (which were made by \fBpcre_maketables()\fP when PCRE was -compiled). You might want to do this if you are using a non-standard locale. -The function yields a pointer to the tables. -.P -There is a complete description of the PCRE native API in the -.\" HREF -\fBpcreapi\fP -.\" -page and a description of the POSIX API in the -.\" HREF -\fBpcreposix\fP -.\" -page. diff --git a/libs/pcre/doc/pcre_refcount.3 b/libs/pcre/doc/pcre_refcount.3 deleted file mode 100644 index 6ab9f4fee7..0000000000 --- a/libs/pcre/doc/pcre_refcount.3 +++ /dev/null @@ -1,32 +0,0 @@ -.TH PCRE_REFCOUNT 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include -.PP -.SM -.B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP); -. -.SH DESCRIPTION -.rs -.sp -This function is used to maintain a reference count inside a data block that -contains a compiled pattern. Its arguments are: -.sp - \fIcode\fP Compiled regular expression - \fIadjust\fP Adjustment to reference value -.sp -The yield of the function is the adjusted reference value, which is constrained -to lie between 0 and 65535. -.P -There is a complete description of the PCRE native API in the -.\" HREF -\fBpcreapi\fP -.\" -page and a description of the POSIX API in the -.\" HREF -\fBpcreposix\fP -.\" -page. diff --git a/libs/pcre/doc/pcre_study.3 b/libs/pcre/doc/pcre_study.3 deleted file mode 100644 index 53f5bc1b48..0000000000 --- a/libs/pcre/doc/pcre_study.3 +++ /dev/null @@ -1,42 +0,0 @@ -.TH PCRE_STUDY 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include -.PP -.SM -.B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP, -.ti +5n -.B const char **\fIerrptr\fP); -. -.SH DESCRIPTION -.rs -.sp -This function studies a compiled pattern, to see if additional information can -be extracted that might speed up matching. Its arguments are: -.sp - \fIcode\fP A compiled regular expression - \fIoptions\fP Options for \fBpcre_study()\fP - \fIerrptr\fP Where to put an error message -.sp -If the function succeeds, it returns a value that can be passed to -\fBpcre_exec()\fP via its \fIextra\fP argument. -.P -If the function returns NULL, either it could not find any additional -information, or there was an error. You can tell the difference by looking at -the error value. It is NULL in first case. -.P -There are currently no options defined; the value of the second argument should -always be zero. -.P -There is a complete description of the PCRE native API in the -.\" HREF -\fBpcreapi\fP -.\" -page and a description of the POSIX API in the -.\" HREF -\fBpcreposix\fP -.\" -page. diff --git a/libs/pcre/doc/pcre_version.3 b/libs/pcre/doc/pcre_version.3 deleted file mode 100644 index f1563fac6a..0000000000 --- a/libs/pcre/doc/pcre_version.3 +++ /dev/null @@ -1,26 +0,0 @@ -.TH PCRE_VERSION 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include -.PP -.SM -.B char *pcre_version(void); -. -.SH DESCRIPTION -.rs -.sp -This function returns a character string that gives the version number of the -PCRE library and the date of its release. -.P -There is a complete description of the PCRE native API in the -.\" HREF -\fBpcreapi\fP -.\" -page and a description of the POSIX API in the -.\" HREF -\fBpcreposix\fP -.\" -page. diff --git a/libs/pcre/doc/pcreapi.3 b/libs/pcre/doc/pcreapi.3 deleted file mode 100644 index 7c830ff454..0000000000 --- a/libs/pcre/doc/pcreapi.3 +++ /dev/null @@ -1,2001 +0,0 @@ -.TH PCREAPI 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH "PCRE NATIVE API" -.rs -.sp -.B #include -.PP -.SM -.B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP, -.ti +5n -.B const char **\fIerrptr\fP, int *\fIerroffset\fP, -.ti +5n -.B const unsigned char *\fItableptr\fP); -.PP -.B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP, -.ti +5n -.B int *\fIerrorcodeptr\fP, -.ti +5n -.B const char **\fIerrptr\fP, int *\fIerroffset\fP, -.ti +5n -.B const unsigned char *\fItableptr\fP); -.PP -.B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP, -.ti +5n -.B const char **\fIerrptr\fP); -.PP -.B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," -.ti +5n -.B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP, -.ti +5n -.B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP); -.PP -.B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," -.ti +5n -.B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP, -.ti +5n -.B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP, -.ti +5n -.B int *\fIworkspace\fP, int \fIwscount\fP); -.PP -.B int pcre_copy_named_substring(const pcre *\fIcode\fP, -.ti +5n -.B const char *\fIsubject\fP, int *\fIovector\fP, -.ti +5n -.B int \fIstringcount\fP, const char *\fIstringname\fP, -.ti +5n -.B char *\fIbuffer\fP, int \fIbuffersize\fP); -.PP -.B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP, -.ti +5n -.B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP, -.ti +5n -.B int \fIbuffersize\fP); -.PP -.B int pcre_get_named_substring(const pcre *\fIcode\fP, -.ti +5n -.B const char *\fIsubject\fP, int *\fIovector\fP, -.ti +5n -.B int \fIstringcount\fP, const char *\fIstringname\fP, -.ti +5n -.B const char **\fIstringptr\fP); -.PP -.B int pcre_get_stringnumber(const pcre *\fIcode\fP, -.ti +5n -.B const char *\fIname\fP); -.PP -.B int pcre_get_stringtable_entries(const pcre *\fIcode\fP, -.ti +5n -.B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP); -.PP -.B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP, -.ti +5n -.B int \fIstringcount\fP, int \fIstringnumber\fP, -.ti +5n -.B const char **\fIstringptr\fP); -.PP -.B int pcre_get_substring_list(const char *\fIsubject\fP, -.ti +5n -.B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);" -.PP -.B void pcre_free_substring(const char *\fIstringptr\fP); -.PP -.B void pcre_free_substring_list(const char **\fIstringptr\fP); -.PP -.B const unsigned char *pcre_maketables(void); -.PP -.B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," -.ti +5n -.B int \fIwhat\fP, void *\fIwhere\fP); -.PP -.B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int -.B *\fIfirstcharptr\fP); -.PP -.B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP); -.PP -.B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP); -.PP -.B char *pcre_version(void); -.PP -.B void *(*pcre_malloc)(size_t); -.PP -.B void (*pcre_free)(void *); -.PP -.B void *(*pcre_stack_malloc)(size_t); -.PP -.B void (*pcre_stack_free)(void *); -.PP -.B int (*pcre_callout)(pcre_callout_block *); -. -. -.SH "PCRE API OVERVIEW" -.rs -.sp -PCRE has its own native API, which is described in this document. There are -also some wrapper functions that correspond to the POSIX regular expression -API. These are described in the -.\" HREF -\fBpcreposix\fP -.\" -documentation. Both of these APIs define a set of C function calls. A C++ -wrapper is distributed with PCRE. It is documented in the -.\" HREF -\fBpcrecpp\fP -.\" -page. -.P -The native API C function prototypes are defined in the header file -\fBpcre.h\fP, and on Unix systems the library itself is called \fBlibpcre\fP. -It can normally be accessed by adding \fB-lpcre\fP to the command for linking -an application that uses PCRE. The header file defines the macros PCRE_MAJOR -and PCRE_MINOR to contain the major and minor release numbers for the library. -Applications can use these to include support for different releases of PCRE. -.P -The functions \fBpcre_compile()\fP, \fBpcre_compile2()\fP, \fBpcre_study()\fP, -and \fBpcre_exec()\fP are used for compiling and matching regular expressions -in a Perl-compatible manner. A sample program that demonstrates the simplest -way of using them is provided in the file called \fIpcredemo.c\fP in the source -distribution. The -.\" HREF -\fBpcresample\fP -.\" -documentation describes how to compile and run it. -.P -A second matching function, \fBpcre_dfa_exec()\fP, which is not -Perl-compatible, is also provided. This uses a different algorithm for the -matching. The alternative algorithm finds all possible matches (at a given -point in the subject), and scans the subject just once. However, this algorithm -does not return captured substrings. A description of the two matching -algorithms and their advantages and disadvantages is given in the -.\" HREF -\fBpcrematching\fP -.\" -documentation. -.P -In addition to the main compiling and matching functions, there are convenience -functions for extracting captured substrings from a subject string that is -matched by \fBpcre_exec()\fP. They are: -.sp - \fBpcre_copy_substring()\fP - \fBpcre_copy_named_substring()\fP - \fBpcre_get_substring()\fP - \fBpcre_get_named_substring()\fP - \fBpcre_get_substring_list()\fP - \fBpcre_get_stringnumber()\fP - \fBpcre_get_stringtable_entries()\fP -.sp -\fBpcre_free_substring()\fP and \fBpcre_free_substring_list()\fP are also -provided, to free the memory used for extracted strings. -.P -The function \fBpcre_maketables()\fP is used to build a set of character tables -in the current locale for passing to \fBpcre_compile()\fP, \fBpcre_exec()\fP, -or \fBpcre_dfa_exec()\fP. This is an optional facility that is provided for -specialist use. Most commonly, no special tables are passed, in which case -internal tables that are generated when PCRE is built are used. -.P -The function \fBpcre_fullinfo()\fP is used to find out information about a -compiled pattern; \fBpcre_info()\fP is an obsolete version that returns only -some of the available information, but is retained for backwards compatibility. -The function \fBpcre_version()\fP returns a pointer to a string containing the -version of PCRE and its date of release. -.P -The function \fBpcre_refcount()\fP maintains a reference count in a data block -containing a compiled pattern. This is provided for the benefit of -object-oriented applications. -.P -The global variables \fBpcre_malloc\fP and \fBpcre_free\fP initially contain -the entry points of the standard \fBmalloc()\fP and \fBfree()\fP functions, -respectively. PCRE calls the memory management functions via these variables, -so a calling program can replace them if it wishes to intercept the calls. This -should be done before calling any PCRE functions. -.P -The global variables \fBpcre_stack_malloc\fP and \fBpcre_stack_free\fP are also -indirections to memory management functions. These special functions are used -only when PCRE is compiled to use the heap for remembering data, instead of -recursive function calls, when running the \fBpcre_exec()\fP function. See the -.\" HREF -\fBpcrebuild\fP -.\" -documentation for details of how to do this. It is a non-standard way of -building PCRE, for use in environments that have limited stacks. Because of the -greater use of memory management, it runs more slowly. Separate functions are -provided so that special-purpose external code can be used for this case. When -used, these functions are always called in a stack-like manner (last obtained, -first freed), and always for memory blocks of the same size. There is a -discussion about PCRE's stack usage in the -.\" HREF -\fBpcrestack\fP -.\" -documentation. -.P -The global variable \fBpcre_callout\fP initially contains NULL. It can be set -by the caller to a "callout" function, which PCRE will then call at specified -points during a matching operation. Details are given in the -.\" HREF -\fBpcrecallout\fP -.\" -documentation. -. -. -.\" HTML -.SH NEWLINES -.rs -.sp -PCRE supports five different conventions for indicating line breaks in -strings: a single CR (carriage return) character, a single LF (linefeed) -character, the two-character sequence CRLF, any of the three preceding, or any -Unicode newline sequence. The Unicode newline sequences are the three just -mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed, -U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS -(paragraph separator, U+2029). -.P -Each of the first three conventions is used by at least one operating system as -its standard newline sequence. When PCRE is built, a default can be specified. -The default default is LF, which is the Unix standard. When PCRE is run, the -default can be overridden, either when a pattern is compiled, or when it is -matched. -.P -At compile time, the newline convention can be specified by the \fIoptions\fP -argument of \fBpcre_compile()\fP, or it can be specified by special text at the -start of the pattern itself; this overrides any other settings. See the -.\" HREF -\fBpcrepattern\fP -.\" -page for details of the special character sequences. -.P -In the PCRE documentation the word "newline" is used to mean "the character or -pair of characters that indicate a line break". The choice of newline -convention affects the handling of the dot, circumflex, and dollar -metacharacters, the handling of #-comments in /x mode, and, when CRLF is a -recognized line ending sequence, the match position advancement for a -non-anchored pattern. There is more detail about this in the -.\" HTML -.\" -section on \fBpcre_exec()\fP options -.\" -below. -.P -The choice of newline convention does not affect the interpretation of -the \en or \er escape sequences, nor does it affect what \eR matches, which is -controlled in a similar way, but by separate options. -. -. -.SH MULTITHREADING -.rs -.sp -The PCRE functions can be used in multi-threading applications, with the -proviso that the memory management functions pointed to by \fBpcre_malloc\fP, -\fBpcre_free\fP, \fBpcre_stack_malloc\fP, and \fBpcre_stack_free\fP, and the -callout function pointed to by \fBpcre_callout\fP, are shared by all threads. -.P -The compiled form of a regular expression is not altered during matching, so -the same compiled pattern can safely be used by several threads at once. -. -. -.SH "SAVING PRECOMPILED PATTERNS FOR LATER USE" -.rs -.sp -The compiled form of a regular expression can be saved and re-used at a later -time, possibly by a different program, and even on a host other than the one on -which it was compiled. Details are given in the -.\" HREF -\fBpcreprecompile\fP -.\" -documentation. However, compiling a regular expression with one version of PCRE -for use with a different version is not guaranteed to work and may cause -crashes. -. -. -.SH "CHECKING BUILD-TIME OPTIONS" -.rs -.sp -.B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP); -.PP -The function \fBpcre_config()\fP makes it possible for a PCRE client to -discover which optional features have been compiled into the PCRE library. The -.\" HREF -\fBpcrebuild\fP -.\" -documentation has more details about these optional features. -.P -The first argument for \fBpcre_config()\fP is an integer, specifying which -information is required; the second argument is a pointer to a variable into -which the information is placed. The following information is available: -.sp - PCRE_CONFIG_UTF8 -.sp -The output is an integer that is set to one if UTF-8 support is available; -otherwise it is set to zero. -.sp - PCRE_CONFIG_UNICODE_PROPERTIES -.sp -The output is an integer that is set to one if support for Unicode character -properties is available; otherwise it is set to zero. -.sp - PCRE_CONFIG_NEWLINE -.sp -The output is an integer whose value specifies the default character sequence -that is recognized as meaning "newline". The four values that are supported -are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, and -1 for ANY. -Though they are derived from ASCII, the same values are returned in EBCDIC -environments. The default should normally correspond to the standard sequence -for your operating system. -.sp - PCRE_CONFIG_BSR -.sp -The output is an integer whose value indicates what character sequences the \eR -escape sequence matches by default. A value of 0 means that \eR matches any -Unicode line ending sequence; a value of 1 means that \eR matches only CR, LF, -or CRLF. The default can be overridden when a pattern is compiled or matched. -.sp - PCRE_CONFIG_LINK_SIZE -.sp -The output is an integer that contains the number of bytes used for internal -linkage in compiled regular expressions. The value is 2, 3, or 4. Larger values -allow larger regular expressions to be compiled, at the expense of slower -matching. The default value of 2 is sufficient for all but the most massive -patterns, since it allows the compiled pattern to be up to 64K in size. -.sp - PCRE_CONFIG_POSIX_MALLOC_THRESHOLD -.sp -The output is an integer that contains the threshold above which the POSIX -interface uses \fBmalloc()\fP for output vectors. Further details are given in -the -.\" HREF -\fBpcreposix\fP -.\" -documentation. -.sp - PCRE_CONFIG_MATCH_LIMIT -.sp -The output is a long integer that gives the default limit for the number of -internal matching function calls in a \fBpcre_exec()\fP execution. Further -details are given with \fBpcre_exec()\fP below. -.sp - PCRE_CONFIG_MATCH_LIMIT_RECURSION -.sp -The output is a long integer that gives the default limit for the depth of -recursion when calling the internal matching function in a \fBpcre_exec()\fP -execution. Further details are given with \fBpcre_exec()\fP below. -.sp - PCRE_CONFIG_STACKRECURSE -.sp -The output is an integer that is set to one if internal recursion when running -\fBpcre_exec()\fP is implemented by recursive function calls that use the stack -to remember their state. This is the usual way that PCRE is compiled. The -output is zero if PCRE was compiled to use blocks of data on the heap instead -of recursive function calls. In this case, \fBpcre_stack_malloc\fP and -\fBpcre_stack_free\fP are called to manage memory blocks on the heap, thus -avoiding the use of the stack. -. -. -.SH "COMPILING A PATTERN" -.rs -.sp -.B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP, -.ti +5n -.B const char **\fIerrptr\fP, int *\fIerroffset\fP, -.ti +5n -.B const unsigned char *\fItableptr\fP); -.sp -.B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP, -.ti +5n -.B int *\fIerrorcodeptr\fP, -.ti +5n -.B const char **\fIerrptr\fP, int *\fIerroffset\fP, -.ti +5n -.B const unsigned char *\fItableptr\fP); -.P -Either of the functions \fBpcre_compile()\fP or \fBpcre_compile2()\fP can be -called to compile a pattern into an internal form. The only difference between -the two interfaces is that \fBpcre_compile2()\fP has an additional argument, -\fIerrorcodeptr\fP, via which a numerical error code can be returned. -.P -The pattern is a C string terminated by a binary zero, and is passed in the -\fIpattern\fP argument. A pointer to a single block of memory that is obtained -via \fBpcre_malloc\fP is returned. This contains the compiled code and related -data. The \fBpcre\fP type is defined for the returned block; this is a typedef -for a structure whose contents are not externally defined. It is up to the -caller to free the memory (via \fBpcre_free\fP) when it is no longer required. -.P -Although the compiled code of a PCRE regex is relocatable, that is, it does not -depend on memory location, the complete \fBpcre\fP data block is not -fully relocatable, because it may contain a copy of the \fItableptr\fP -argument, which is an address (see below). -.P -The \fIoptions\fP argument contains various bit settings that affect the -compilation. It should be zero if no options are required. The available -options are described below. Some of them (in particular, those that are -compatible with Perl, but also some others) can also be set and unset from -within the pattern (see the detailed description in the -.\" HREF -\fBpcrepattern\fP -.\" -documentation). For those options that can be different in different parts of -the pattern, the contents of the \fIoptions\fP argument specifies their initial -settings at the start of compilation and execution. The PCRE_ANCHORED and -PCRE_NEWLINE_\fIxxx\fP options can be set at the time of matching as well as at -compile time. -.P -If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately. -Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns -NULL, and sets the variable pointed to by \fIerrptr\fP to point to a textual -error message. This is a static string that is part of the library. You must -not try to free it. The offset from the start of the pattern to the character -where the error was discovered is placed in the variable pointed to by -\fIerroffset\fP, which must not be NULL. If it is, an immediate error is given. -.P -If \fBpcre_compile2()\fP is used instead of \fBpcre_compile()\fP, and the -\fIerrorcodeptr\fP argument is not NULL, a non-zero error code number is -returned via this argument in the event of an error. This is in addition to the -textual error message. Error codes and messages are listed below. -.P -If the final argument, \fItableptr\fP, is NULL, PCRE uses a default set of -character tables that are built when PCRE is compiled, using the default C -locale. Otherwise, \fItableptr\fP must be an address that is the result of a -call to \fBpcre_maketables()\fP. This value is stored with the compiled -pattern, and used again by \fBpcre_exec()\fP, unless another table pointer is -passed to it. For more discussion, see the section on locale support below. -.P -This code fragment shows a typical straightforward call to \fBpcre_compile()\fP: -.sp - pcre *re; - const char *error; - int erroffset; - re = pcre_compile( - "^A.*Z", /* the pattern */ - 0, /* default options */ - &error, /* for error message */ - &erroffset, /* for error offset */ - NULL); /* use default character tables */ -.sp -The following names for option bits are defined in the \fBpcre.h\fP header -file: -.sp - PCRE_ANCHORED -.sp -If this bit is set, the pattern is forced to be "anchored", that is, it is -constrained to match only at the first matching point in the string that is -being searched (the "subject string"). This effect can also be achieved by -appropriate constructs in the pattern itself, which is the only way to do it in -Perl. -.sp - PCRE_AUTO_CALLOUT -.sp -If this bit is set, \fBpcre_compile()\fP automatically inserts callout items, -all with number 255, before each pattern item. For discussion of the callout -facility, see the -.\" HREF -\fBpcrecallout\fP -.\" -documentation. -.sp - PCRE_BSR_ANYCRLF - PCRE_BSR_UNICODE -.sp -These options (which are mutually exclusive) control what the \eR escape -sequence matches. The choice is either to match only CR, LF, or CRLF, or to -match any Unicode newline sequence. The default is specified when PCRE is -built. It can be overridden from within the pattern, or by setting an option -when a compiled pattern is matched. -.sp - PCRE_CASELESS -.sp -If this bit is set, letters in the pattern match both upper and lower case -letters. It is equivalent to Perl's /i option, and it can be changed within a -pattern by a (?i) option setting. In UTF-8 mode, PCRE always understands the -concept of case for characters whose values are less than 128, so caseless -matching is always possible. For characters with higher values, the concept of -case is supported if PCRE is compiled with Unicode property support, but not -otherwise. If you want to use caseless matching for characters 128 and above, -you must ensure that PCRE is compiled with Unicode property support as well as -with UTF-8 support. -.sp - PCRE_DOLLAR_ENDONLY -.sp -If this bit is set, a dollar metacharacter in the pattern matches only at the -end of the subject string. Without this option, a dollar also matches -immediately before a newline at the end of the string (but not before any other -newlines). The PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is set. -There is no equivalent to this option in Perl, and no way to set it within a -pattern. -.sp - PCRE_DOTALL -.sp -If this bit is set, a dot metacharater in the pattern matches all characters, -including those that indicate newline. Without it, a dot does not match when -the current position is at a newline. This option is equivalent to Perl's /s -option, and it can be changed within a pattern by a (?s) option setting. A -negative class such as [^a] always matches newline characters, independent of -the setting of this option. -.sp - PCRE_DUPNAMES -.sp -If this bit is set, names used to identify capturing subpatterns need not be -unique. This can be helpful for certain types of pattern when it is known that -only one instance of the named subpattern can ever be matched. There are more -details of named subpatterns below; see also the -.\" HREF -\fBpcrepattern\fP -.\" -documentation. -.sp - PCRE_EXTENDED -.sp -If this bit is set, whitespace data characters in the pattern are totally -ignored except when escaped or inside a character class. Whitespace does not -include the VT character (code 11). In addition, characters between an -unescaped # outside a character class and the next newline, inclusive, are also -ignored. This is equivalent to Perl's /x option, and it can be changed within a -pattern by a (?x) option setting. -.P -This option makes it possible to include comments inside complicated patterns. -Note, however, that this applies only to data characters. Whitespace characters -may never appear within special character sequences in a pattern, for example -within the sequence (?( which introduces a conditional subpattern. -.sp - PCRE_EXTRA -.sp -This option was invented in order to turn on additional functionality of PCRE -that is incompatible with Perl, but it is currently of very little use. When -set, any backslash in a pattern that is followed by a letter that has no -special meaning causes an error, thus reserving these combinations for future -expansion. By default, as in Perl, a backslash followed by a letter with no -special meaning is treated as a literal. (Perl can, however, be persuaded to -give a warning for this.) There are at present no other features controlled by -this option. It can also be set by a (?X) option setting within a pattern. -.sp - PCRE_FIRSTLINE -.sp -If this option is set, an unanchored pattern is required to match before or at -the first newline in the subject string, though the matched text may continue -over the newline. -.sp - PCRE_JAVASCRIPT_COMPAT -.sp -If this option is set, PCRE's behaviour is changed in some ways so that it is -compatible with JavaScript rather than Perl. The changes are as follows: -.P -(1) A lone closing square bracket in a pattern causes a compile-time error, -because this is illegal in JavaScript (by default it is treated as a data -character). Thus, the pattern AB]CD becomes illegal when this option is set. -.P -(2) At run time, a back reference to an unset subpattern group matches an empty -string (by default this causes the current matching alternative to fail). A -pattern such as (\e1)(a) succeeds when this option is set (assuming it can find -an "a" in the subject), whereas it fails by default, for Perl compatibility. -.sp - PCRE_MULTILINE -.sp -By default, PCRE treats the subject string as consisting of a single line of -characters (even if it actually contains newlines). The "start of line" -metacharacter (^) matches only at the start of the string, while the "end of -line" metacharacter ($) matches only at the end of the string, or before a -terminating newline (unless PCRE_DOLLAR_ENDONLY is set). This is the same as -Perl. -.P -When PCRE_MULTILINE it is set, the "start of line" and "end of line" constructs -match immediately following or immediately before internal newlines in the -subject string, respectively, as well as at the very start and end. This is -equivalent to Perl's /m option, and it can be changed within a pattern by a -(?m) option setting. If there are no newlines in a subject string, or no -occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect. -.sp - PCRE_NEWLINE_CR - PCRE_NEWLINE_LF - PCRE_NEWLINE_CRLF - PCRE_NEWLINE_ANYCRLF - PCRE_NEWLINE_ANY -.sp -These options override the default newline definition that was chosen when PCRE -was built. Setting the first or the second specifies that a newline is -indicated by a single character (CR or LF, respectively). Setting -PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character -CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three -preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies -that any Unicode newline sequence should be recognized. The Unicode newline -sequences are the three just mentioned, plus the single characters VT (vertical -tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line -separator, U+2028), and PS (paragraph separator, U+2029). The last two are -recognized only in UTF-8 mode. -.P -The newline setting in the options word uses three bits that are treated -as a number, giving eight possibilities. Currently only six are used (default -plus the five values above). This means that if you set more than one newline -option, the combination may or may not be sensible. For example, -PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but -other combinations may yield unused numbers and cause an error. -.P -The only time that a line break is specially recognized when compiling a -pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character -class is encountered. This indicates a comment that lasts until after the next -line break sequence. In other circumstances, line break sequences are treated -as literal data, except that in PCRE_EXTENDED mode, both CR and LF are treated -as whitespace characters and are therefore ignored. -.P -The newline option that is set at compile time becomes the default that is used -for \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, but it can be overridden. -.sp - PCRE_NO_AUTO_CAPTURE -.sp -If this option is set, it disables the use of numbered capturing parentheses in -the pattern. Any opening parenthesis that is not followed by ? behaves as if it -were followed by ?: but named parentheses can still be used for capturing (and -they acquire numbers in the usual way). There is no equivalent of this option -in Perl. -.sp - PCRE_UNGREEDY -.sp -This option inverts the "greediness" of the quantifiers so that they are not -greedy by default, but become greedy if followed by "?". It is not compatible -with Perl. It can also be set by a (?U) option setting within the pattern. -.sp - PCRE_UTF8 -.sp -This option causes PCRE to regard both the pattern and the subject as strings -of UTF-8 characters instead of single-byte character strings. However, it is -available only when PCRE is built to include UTF-8 support. If not, the use -of this option provokes an error. Details of how this option changes the -behaviour of PCRE are given in the -.\" HTML -.\" -section on UTF-8 support -.\" -in the main -.\" HREF -\fBpcre\fP -.\" -page. -.sp - PCRE_NO_UTF8_CHECK -.sp -When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is -automatically checked. There is a discussion about the -.\" HTML -.\" -validity of UTF-8 strings -.\" -in the main -.\" HREF -\fBpcre\fP -.\" -page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_compile()\fP -returns an error. If you already know that your pattern is valid, and you want -to skip this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK -option. When it is set, the effect of passing an invalid UTF-8 string as a -pattern is undefined. It may cause your program to crash. Note that this option -can also be passed to \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, to suppress -the UTF-8 validity checking of subject strings. -. -. -.SH "COMPILATION ERROR CODES" -.rs -.sp -The following table lists the error codes than may be returned by -\fBpcre_compile2()\fP, along with the error messages that may be returned by -both compiling functions. As PCRE has developed, some error codes have fallen -out of use. To avoid confusion, they have not been re-used. -.sp - 0 no error - 1 \e at end of pattern - 2 \ec at end of pattern - 3 unrecognized character follows \e - 4 numbers out of order in {} quantifier - 5 number too big in {} quantifier - 6 missing terminating ] for character class - 7 invalid escape sequence in character class - 8 range out of order in character class - 9 nothing to repeat - 10 [this code is not in use] - 11 internal error: unexpected repeat - 12 unrecognized character after (? or (?- - 13 POSIX named classes are supported only within a class - 14 missing ) - 15 reference to non-existent subpattern - 16 erroffset passed as NULL - 17 unknown option bit(s) set - 18 missing ) after comment - 19 [this code is not in use] - 20 regular expression is too large - 21 failed to get memory - 22 unmatched parentheses - 23 internal error: code overflow - 24 unrecognized character after (?< - 25 lookbehind assertion is not fixed length - 26 malformed number or name after (?( - 27 conditional group contains more than two branches - 28 assertion expected after (?( - 29 (?R or (?[+-]digits must be followed by ) - 30 unknown POSIX class name - 31 POSIX collating elements are not supported - 32 this version of PCRE is not compiled with PCRE_UTF8 support - 33 [this code is not in use] - 34 character value in \ex{...} sequence is too large - 35 invalid condition (?(0) - 36 \eC not allowed in lookbehind assertion - 37 PCRE does not support \eL, \el, \eN, \eU, or \eu - 38 number after (?C is > 255 - 39 closing ) for (?C expected - 40 recursive call could loop indefinitely - 41 unrecognized character after (?P - 42 syntax error in subpattern name (missing terminator) - 43 two named subpatterns have the same name - 44 invalid UTF-8 string - 45 support for \eP, \ep, and \eX has not been compiled - 46 malformed \eP or \ep sequence - 47 unknown property name after \eP or \ep - 48 subpattern name is too long (maximum 32 characters) - 49 too many named subpatterns (maximum 10000) - 50 [this code is not in use] - 51 octal value is greater than \e377 (not in UTF-8 mode) - 52 internal error: overran compiling workspace - 53 internal error: previously-checked referenced subpattern not found - 54 DEFINE group contains more than one branch - 55 repeating a DEFINE group is not allowed - 56 inconsistent NEWLINE options - 57 \eg is not followed by a braced, angle-bracketed, or quoted - name/number or by a plain number - 58 a numbered reference must not be zero - 59 (*VERB) with an argument is not supported - 60 (*VERB) not recognized - 61 number is too big - 62 subpattern name expected - 63 digit expected after (?+ - 64 ] is an invalid data character in JavaScript compatibility mode -.sp -The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may -be used if the limits were changed when PCRE was built. -. -. -.SH "STUDYING A PATTERN" -.rs -.sp -.B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP -.ti +5n -.B const char **\fIerrptr\fP); -.PP -If a compiled pattern is going to be used several times, it is worth spending -more time analyzing it in order to speed up the time taken for matching. The -function \fBpcre_study()\fP takes a pointer to a compiled pattern as its first -argument. If studying the pattern produces additional information that will -help speed up matching, \fBpcre_study()\fP returns a pointer to a -\fBpcre_extra\fP block, in which the \fIstudy_data\fP field points to the -results of the study. -.P -The returned value from \fBpcre_study()\fP can be passed directly to -\fBpcre_exec()\fP. However, a \fBpcre_extra\fP block also contains other -fields that can be set by the caller before the block is passed; these are -described -.\" HTML -.\" -below -.\" -in the section on matching a pattern. -.P -If studying the pattern does not produce any additional information -\fBpcre_study()\fP returns NULL. In that circumstance, if the calling program -wants to pass any of the other fields to \fBpcre_exec()\fP, it must set up its -own \fBpcre_extra\fP block. -.P -The second argument of \fBpcre_study()\fP contains option bits. At present, no -options are defined, and this argument should always be zero. -.P -The third argument for \fBpcre_study()\fP is a pointer for an error message. If -studying succeeds (even if no data is returned), the variable it points to is -set to NULL. Otherwise it is set to point to a textual error message. This is a -static string that is part of the library. You must not try to free it. You -should test the error pointer for NULL after calling \fBpcre_study()\fP, to be -sure that it has run successfully. -.P -This is a typical call to \fBpcre_study\fP(): -.sp - pcre_extra *pe; - pe = pcre_study( - re, /* result of pcre_compile() */ - 0, /* no options exist */ - &error); /* set to NULL or points to a message */ -.sp -At present, studying a pattern is useful only for non-anchored patterns that do -not have a single fixed starting character. A bitmap of possible starting -bytes is created. -. -. -.\" HTML -.SH "LOCALE SUPPORT" -.rs -.sp -PCRE handles caseless matching, and determines whether characters are letters, -digits, or whatever, by reference to a set of tables, indexed by character -value. When running in UTF-8 mode, this applies only to characters with codes -less than 128. Higher-valued codes never match escapes such as \ew or \ed, but -can be tested with \ep if PCRE is built with Unicode character property -support. The use of locales with Unicode is discouraged. If you are handling -characters with codes greater than 128, you should either use UTF-8 and -Unicode, or use locales, but not try to mix the two. -.P -PCRE contains an internal set of tables that are used when the final argument -of \fBpcre_compile()\fP is NULL. These are sufficient for many applications. -Normally, the internal tables recognize only ASCII characters. However, when -PCRE is built, it is possible to cause the internal tables to be rebuilt in the -default "C" locale of the local system, which may cause them to be different. -.P -The internal tables can always be overridden by tables supplied by the -application that calls PCRE. These may be created in a different locale from -the default. As more and more applications change to using Unicode, the need -for this locale support is expected to die away. -.P -External tables are built by calling the \fBpcre_maketables()\fP function, -which has no arguments, in the relevant locale. The result can then be passed -to \fBpcre_compile()\fP or \fBpcre_exec()\fP as often as necessary. For -example, to build and use tables that are appropriate for the French locale -(where accented characters with values greater than 128 are treated as letters), -the following code could be used: -.sp - setlocale(LC_CTYPE, "fr_FR"); - tables = pcre_maketables(); - re = pcre_compile(..., tables); -.sp -The locale name "fr_FR" is used on Linux and other Unix-like systems; if you -are using Windows, the name for the French locale is "french". -.P -When \fBpcre_maketables()\fP runs, the tables are built in memory that is -obtained via \fBpcre_malloc\fP. It is the caller's responsibility to ensure -that the memory containing the tables remains available for as long as it is -needed. -.P -The pointer that is passed to \fBpcre_compile()\fP is saved with the compiled -pattern, and the same tables are used via this pointer by \fBpcre_study()\fP -and normally also by \fBpcre_exec()\fP. Thus, by default, for any single -pattern, compilation, studying and matching all happen in the same locale, but -different patterns can be compiled in different locales. -.P -It is possible to pass a table pointer or NULL (indicating the use of the -internal tables) to \fBpcre_exec()\fP. Although not intended for this purpose, -this facility could be used to match a pattern in a different locale from the -one in which it was compiled. Passing table pointers at run time is discussed -below in the section on matching a pattern. -. -. -.SH "INFORMATION ABOUT A PATTERN" -.rs -.sp -.B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," -.ti +5n -.B int \fIwhat\fP, void *\fIwhere\fP); -.PP -The \fBpcre_fullinfo()\fP function returns information about a compiled -pattern. It replaces the obsolete \fBpcre_info()\fP function, which is -nevertheless retained for backwards compability (and is documented below). -.P -The first argument for \fBpcre_fullinfo()\fP is a pointer to the compiled -pattern. The second argument is the result of \fBpcre_study()\fP, or NULL if -the pattern was not studied. The third argument specifies which piece of -information is required, and the fourth argument is a pointer to a variable -to receive the data. The yield of the function is zero for success, or one of -the following negative numbers: -.sp - PCRE_ERROR_NULL the argument \fIcode\fP was NULL - the argument \fIwhere\fP was NULL - PCRE_ERROR_BADMAGIC the "magic number" was not found - PCRE_ERROR_BADOPTION the value of \fIwhat\fP was invalid -.sp -The "magic number" is placed at the start of each compiled pattern as an simple -check against passing an arbitrary memory pointer. Here is a typical call of -\fBpcre_fullinfo()\fP, to obtain the length of the compiled pattern: -.sp - int rc; - size_t length; - rc = pcre_fullinfo( - re, /* result of pcre_compile() */ - pe, /* result of pcre_study(), or NULL */ - PCRE_INFO_SIZE, /* what is required */ - &length); /* where to put the data */ -.sp -The possible values for the third argument are defined in \fBpcre.h\fP, and are -as follows: -.sp - PCRE_INFO_BACKREFMAX -.sp -Return the number of the highest back reference in the pattern. The fourth -argument should point to an \fBint\fP variable. Zero is returned if there are -no back references. -.sp - PCRE_INFO_CAPTURECOUNT -.sp -Return the number of capturing subpatterns in the pattern. The fourth argument -should point to an \fBint\fP variable. -.sp - PCRE_INFO_DEFAULT_TABLES -.sp -Return a pointer to the internal default character tables within PCRE. The -fourth argument should point to an \fBunsigned char *\fP variable. This -information call is provided for internal use by the \fBpcre_study()\fP -function. External callers can cause PCRE to use its internal tables by passing -a NULL table pointer. -.sp - PCRE_INFO_FIRSTBYTE -.sp -Return information about the first byte of any matched string, for a -non-anchored pattern. The fourth argument should point to an \fBint\fP -variable. (This option used to be called PCRE_INFO_FIRSTCHAR; the old name is -still recognized for backwards compatibility.) -.P -If there is a fixed first byte, for example, from a pattern such as -(cat|cow|coyote), its value is returned. Otherwise, if either -.sp -(a) the pattern was compiled with the PCRE_MULTILINE option, and every branch -starts with "^", or -.sp -(b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set -(if it were set, the pattern would be anchored), -.sp --1 is returned, indicating that the pattern matches only at the start of a -subject string or after any newline within the string. Otherwise -2 is -returned. For anchored patterns, -2 is returned. -.sp - PCRE_INFO_FIRSTTABLE -.sp -If the pattern was studied, and this resulted in the construction of a 256-bit -table indicating a fixed set of bytes for the first byte in any matching -string, a pointer to the table is returned. Otherwise NULL is returned. The -fourth argument should point to an \fBunsigned char *\fP variable. -.sp - PCRE_INFO_HASCRORLF -.sp -Return 1 if the pattern contains any explicit matches for CR or LF characters, -otherwise 0. The fourth argument should point to an \fBint\fP variable. An -explicit match is either a literal CR or LF character, or \er or \en. -.sp - PCRE_INFO_JCHANGED -.sp -Return 1 if the (?J) or (?-J) option setting is used in the pattern, otherwise -0. The fourth argument should point to an \fBint\fP variable. (?J) and -(?-J) set and unset the local PCRE_DUPNAMES option, respectively. -.sp - PCRE_INFO_LASTLITERAL -.sp -Return the value of the rightmost literal byte that must exist in any matched -string, other than at its start, if such a byte has been recorded. The fourth -argument should point to an \fBint\fP variable. If there is no such byte, -1 is -returned. For anchored patterns, a last literal byte is recorded only if it -follows something of variable length. For example, for the pattern -/^a\ed+z\ed+/ the returned value is "z", but for /^a\edz\ed/ the returned value -is -1. -.sp - PCRE_INFO_NAMECOUNT - PCRE_INFO_NAMEENTRYSIZE - PCRE_INFO_NAMETABLE -.sp -PCRE supports the use of named as well as numbered capturing parentheses. The -names are just an additional way of identifying the parentheses, which still -acquire numbers. Several convenience functions such as -\fBpcre_get_named_substring()\fP are provided for extracting captured -substrings by name. It is also possible to extract the data directly, by first -converting the name to a number in order to access the correct pointers in the -output vector (described with \fBpcre_exec()\fP below). To do the conversion, -you need to use the name-to-number map, which is described by these three -values. -.P -The map consists of a number of fixed-size entries. PCRE_INFO_NAMECOUNT gives -the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size of each -entry; both of these return an \fBint\fP value. The entry size depends on the -length of the longest name. PCRE_INFO_NAMETABLE returns a pointer to the first -entry of the table (a pointer to \fBchar\fP). The first two bytes of each entry -are the number of the capturing parenthesis, most significant byte first. The -rest of the entry is the corresponding name, zero terminated. The names are in -alphabetical order. When PCRE_DUPNAMES is set, duplicate names are in order of -their parentheses numbers. For example, consider the following pattern (assume -PCRE_EXTENDED is set, so white space - including newlines - is ignored): -.sp -.\" JOIN - (? (?(\ed\ed)?\ed\ed) - - (?\ed\ed) - (?\ed\ed) ) -.sp -There are four named subpatterns, so the table has four entries, and each entry -in the table is eight bytes long. The table is as follows, with non-printing -bytes shows in hexadecimal, and undefined bytes shown as ??: -.sp - 00 01 d a t e 00 ?? - 00 05 d a y 00 ?? ?? - 00 04 m o n t h 00 - 00 02 y e a r 00 ?? -.sp -When writing code to extract data from named subpatterns using the -name-to-number map, remember that the length of the entries is likely to be -different for each compiled pattern. -.sp - PCRE_INFO_OKPARTIAL -.sp -Return 1 if the pattern can be used for partial matching, otherwise 0. The -fourth argument should point to an \fBint\fP variable. The -.\" HREF -\fBpcrepartial\fP -.\" -documentation lists the restrictions that apply to patterns when partial -matching is used. -.sp - PCRE_INFO_OPTIONS -.sp -Return a copy of the options with which the pattern was compiled. The fourth -argument should point to an \fBunsigned long int\fP variable. These option bits -are those specified in the call to \fBpcre_compile()\fP, modified by any -top-level option settings at the start of the pattern itself. In other words, -they are the options that will be in force when matching starts. For example, -if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the -result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED. -.P -A pattern is automatically anchored by PCRE if all of its top-level -alternatives begin with one of the following: -.sp - ^ unless PCRE_MULTILINE is set - \eA always - \eG always -.\" JOIN - .* if PCRE_DOTALL is set and there are no back - references to the subpattern in which .* appears -.sp -For such patterns, the PCRE_ANCHORED bit is set in the options returned by -\fBpcre_fullinfo()\fP. -.sp - PCRE_INFO_SIZE -.sp -Return the size of the compiled pattern, that is, the value that was passed as -the argument to \fBpcre_malloc()\fP when PCRE was getting memory in which to -place the compiled data. The fourth argument should point to a \fBsize_t\fP -variable. -.sp - PCRE_INFO_STUDYSIZE -.sp -Return the size of the data block pointed to by the \fIstudy_data\fP field in -a \fBpcre_extra\fP block. That is, it is the value that was passed to -\fBpcre_malloc()\fP when PCRE was getting memory into which to place the data -created by \fBpcre_study()\fP. The fourth argument should point to a -\fBsize_t\fP variable. -. -. -.SH "OBSOLETE INFO FUNCTION" -.rs -.sp -.B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int -.B *\fIfirstcharptr\fP); -.PP -The \fBpcre_info()\fP function is now obsolete because its interface is too -restrictive to return all the available data about a compiled pattern. New -programs should use \fBpcre_fullinfo()\fP instead. The yield of -\fBpcre_info()\fP is the number of capturing subpatterns, or one of the -following negative numbers: -.sp - PCRE_ERROR_NULL the argument \fIcode\fP was NULL - PCRE_ERROR_BADMAGIC the "magic number" was not found -.sp -If the \fIoptptr\fP argument is not NULL, a copy of the options with which the -pattern was compiled is placed in the integer it points to (see -PCRE_INFO_OPTIONS above). -.P -If the pattern is not anchored and the \fIfirstcharptr\fP argument is not NULL, -it is used to pass back information about the first character of any matched -string (see PCRE_INFO_FIRSTBYTE above). -. -. -.SH "REFERENCE COUNTS" -.rs -.sp -.B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP); -.PP -The \fBpcre_refcount()\fP function is used to maintain a reference count in the -data block that contains a compiled pattern. It is provided for the benefit of -applications that operate in an object-oriented manner, where different parts -of the application may be using the same compiled pattern, but you want to free -the block when they are all done. -.P -When a pattern is compiled, the reference count field is initialized to zero. -It is changed only by calling this function, whose action is to add the -\fIadjust\fP value (which may be positive or negative) to it. The yield of the -function is the new value. However, the value of the count is constrained to -lie between 0 and 65535, inclusive. If the new value is outside these limits, -it is forced to the appropriate limit value. -.P -Except when it is zero, the reference count is not correctly preserved if a -pattern is compiled on one host and then transferred to a host whose byte-order -is different. (This seems a highly unlikely scenario.) -. -. -.SH "MATCHING A PATTERN: THE TRADITIONAL FUNCTION" -.rs -.sp -.B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," -.ti +5n -.B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP, -.ti +5n -.B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP); -.P -The function \fBpcre_exec()\fP is called to match a subject string against a -compiled pattern, which is passed in the \fIcode\fP argument. If the -pattern has been studied, the result of the study should be passed in the -\fIextra\fP argument. This function is the main matching facility of the -library, and it operates in a Perl-like manner. For specialist use there is -also an alternative matching function, which is described -.\" HTML -.\" -below -.\" -in the section about the \fBpcre_dfa_exec()\fP function. -.P -In most applications, the pattern will have been compiled (and optionally -studied) in the same process that calls \fBpcre_exec()\fP. However, it is -possible to save compiled patterns and study data, and then use them later -in different processes, possibly even on different hosts. For a discussion -about this, see the -.\" HREF -\fBpcreprecompile\fP -.\" -documentation. -.P -Here is an example of a simple call to \fBpcre_exec()\fP: -.sp - int rc; - int ovector[30]; - rc = pcre_exec( - re, /* result of pcre_compile() */ - NULL, /* we didn't study the pattern */ - "some string", /* the subject string */ - 11, /* the length of the subject string */ - 0, /* start at offset 0 in the subject */ - 0, /* default options */ - ovector, /* vector of integers for substring information */ - 30); /* number of elements (NOT size in bytes) */ -. -.\" HTML -.SS "Extra data for \fBpcre_exec()\fR" -.rs -.sp -If the \fIextra\fP argument is not NULL, it must point to a \fBpcre_extra\fP -data block. The \fBpcre_study()\fP function returns such a block (when it -doesn't return NULL), but you can also create one for yourself, and pass -additional information in it. The \fBpcre_extra\fP block contains the following -fields (not necessarily in this order): -.sp - unsigned long int \fIflags\fP; - void *\fIstudy_data\fP; - unsigned long int \fImatch_limit\fP; - unsigned long int \fImatch_limit_recursion\fP; - void *\fIcallout_data\fP; - const unsigned char *\fItables\fP; -.sp -The \fIflags\fP field is a bitmap that specifies which of the other fields -are set. The flag bits are: -.sp - PCRE_EXTRA_STUDY_DATA - PCRE_EXTRA_MATCH_LIMIT - PCRE_EXTRA_MATCH_LIMIT_RECURSION - PCRE_EXTRA_CALLOUT_DATA - PCRE_EXTRA_TABLES -.sp -Other flag bits should be set to zero. The \fIstudy_data\fP field is set in the -\fBpcre_extra\fP block that is returned by \fBpcre_study()\fP, together with -the appropriate flag bit. You should not set this yourself, but you may add to -the block by setting the other fields and their corresponding flag bits. -.P -The \fImatch_limit\fP field provides a means of preventing PCRE from using up a -vast amount of resources when running patterns that are not going to match, -but which have a very large number of possibilities in their search trees. The -classic example is the use of nested unlimited repeats. -.P -Internally, PCRE uses a function called \fBmatch()\fP which it calls repeatedly -(sometimes recursively). The limit set by \fImatch_limit\fP is imposed on the -number of times this function is called during a match, which has the effect of -limiting the amount of backtracking that can take place. For patterns that are -not anchored, the count restarts from zero for each position in the subject -string. -.P -The default value for the limit can be set when PCRE is built; the default -default is 10 million, which handles all but the most extreme cases. You can -override the default by suppling \fBpcre_exec()\fP with a \fBpcre_extra\fP -block in which \fImatch_limit\fP is set, and PCRE_EXTRA_MATCH_LIMIT is set in -the \fIflags\fP field. If the limit is exceeded, \fBpcre_exec()\fP returns -PCRE_ERROR_MATCHLIMIT. -.P -The \fImatch_limit_recursion\fP field is similar to \fImatch_limit\fP, but -instead of limiting the total number of times that \fBmatch()\fP is called, it -limits the depth of recursion. The recursion depth is a smaller number than the -total number of calls, because not all calls to \fBmatch()\fP are recursive. -This limit is of use only if it is set smaller than \fImatch_limit\fP. -.P -Limiting the recursion depth limits the amount of stack that can be used, or, -when PCRE has been compiled to use memory on the heap instead of the stack, the -amount of heap memory that can be used. -.P -The default value for \fImatch_limit_recursion\fP can be set when PCRE is -built; the default default is the same value as the default for -\fImatch_limit\fP. You can override the default by suppling \fBpcre_exec()\fP -with a \fBpcre_extra\fP block in which \fImatch_limit_recursion\fP is set, and -PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the \fIflags\fP field. If the limit -is exceeded, \fBpcre_exec()\fP returns PCRE_ERROR_RECURSIONLIMIT. -.P -The \fIpcre_callout\fP field is used in conjunction with the "callout" feature, -which is described in the -.\" HREF -\fBpcrecallout\fP -.\" -documentation. -.P -The \fItables\fP field is used to pass a character tables pointer to -\fBpcre_exec()\fP; this overrides the value that is stored with the compiled -pattern. A non-NULL value is stored with the compiled pattern only if custom -tables were supplied to \fBpcre_compile()\fP via its \fItableptr\fP argument. -If NULL is passed to \fBpcre_exec()\fP using this mechanism, it forces PCRE's -internal tables to be used. This facility is helpful when re-using patterns -that have been saved after compiling with an external set of tables, because -the external tables might be at a different address when \fBpcre_exec()\fP is -called. See the -.\" HREF -\fBpcreprecompile\fP -.\" -documentation for a discussion of saving compiled patterns for later use. -. -.\" HTML -.SS "Option bits for \fBpcre_exec()\fP" -.rs -.sp -The unused bits of the \fIoptions\fP argument for \fBpcre_exec()\fP must be -zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP, -PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_START_OPTIMIZE, -PCRE_NO_UTF8_CHECK and PCRE_PARTIAL. -.sp - PCRE_ANCHORED -.sp -The PCRE_ANCHORED option limits \fBpcre_exec()\fP to matching at the first -matching position. If a pattern was compiled with PCRE_ANCHORED, or turned out -to be anchored by virtue of its contents, it cannot be made unachored at -matching time. -.sp - PCRE_BSR_ANYCRLF - PCRE_BSR_UNICODE -.sp -These options (which are mutually exclusive) control what the \eR escape -sequence matches. The choice is either to match only CR, LF, or CRLF, or to -match any Unicode newline sequence. These options override the choice that was -made or defaulted when the pattern was compiled. -.sp - PCRE_NEWLINE_CR - PCRE_NEWLINE_LF - PCRE_NEWLINE_CRLF - PCRE_NEWLINE_ANYCRLF - PCRE_NEWLINE_ANY -.sp -These options override the newline definition that was chosen or defaulted when -the pattern was compiled. For details, see the description of -\fBpcre_compile()\fP above. During matching, the newline choice affects the -behaviour of the dot, circumflex, and dollar metacharacters. It may also alter -the way the match position is advanced after a match failure for an unanchored -pattern. -.P -When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is set, and a -match attempt for an unanchored pattern fails when the current position is at a -CRLF sequence, and the pattern contains no explicit matches for CR or LF -characters, the match position is advanced by two characters instead of one, in -other words, to after the CRLF. -.P -The above rule is a compromise that makes the most common cases work as -expected. For example, if the pattern is .+A (and the PCRE_DOTALL option is not -set), it does not match the string "\er\enA" because, after failing at the -start, it skips both the CR and the LF before retrying. However, the pattern -[\er\en]A does match that string, because it contains an explicit CR or LF -reference, and so advances only by one character after the first failure. -.P -An explicit match for CR of LF is either a literal appearance of one of those -characters, or one of the \er or \en escape sequences. Implicit matches such as -[^X] do not count, nor does \es (which includes CR and LF in the characters -that it matches). -.P -Notwithstanding the above, anomalous effects may still occur when CRLF is a -valid newline sequence and explicit \er or \en escapes appear in the pattern. -.sp - PCRE_NOTBOL -.sp -This option specifies that first character of the subject string is not the -beginning of a line, so the circumflex metacharacter should not match before -it. Setting this without PCRE_MULTILINE (at compile time) causes circumflex -never to match. This option affects only the behaviour of the circumflex -metacharacter. It does not affect \eA. -.sp - PCRE_NOTEOL -.sp -This option specifies that the end of the subject string is not the end of a -line, so the dollar metacharacter should not match it nor (except in multiline -mode) a newline immediately before it. Setting this without PCRE_MULTILINE (at -compile time) causes dollar never to match. This option affects only the -behaviour of the dollar metacharacter. It does not affect \eZ or \ez. -.sp - PCRE_NOTEMPTY -.sp -An empty string is not considered to be a valid match if this option is set. If -there are alternatives in the pattern, they are tried. If all the alternatives -match the empty string, the entire match fails. For example, if the pattern -.sp - a?b? -.sp -is applied to a string not beginning with "a" or "b", it matches the empty -string at the start of the subject. With PCRE_NOTEMPTY set, this match is not -valid, so PCRE searches further into the string for occurrences of "a" or "b". -.P -Perl has no direct equivalent of PCRE_NOTEMPTY, but it does make a special case -of a pattern match of the empty string within its \fBsplit()\fP function, and -when using the /g modifier. It is possible to emulate Perl's behaviour after -matching a null string by first trying the match again at the same offset with -PCRE_NOTEMPTY and PCRE_ANCHORED, and then if that fails by advancing the -starting offset (see below) and trying an ordinary match again. There is some -code that demonstrates how to do this in the \fIpcredemo.c\fP sample program. -.sp - PCRE_NO_START_OPTIMIZE -.sp -There are a number of optimizations that \fBpcre_exec()\fP uses at the start of -a match, in order to speed up the process. For example, if it is known that a -match must start with a specific character, it searches the subject for that -character, and fails immediately if it cannot find it, without actually running -the main matching function. When callouts are in use, these optimizations can -cause them to be skipped. This option disables the "start-up" optimizations, -causing performance to suffer, but ensuring that the callouts do occur. -.sp - PCRE_NO_UTF8_CHECK -.sp -When PCRE_UTF8 is set at compile time, the validity of the subject as a UTF-8 -string is automatically checked when \fBpcre_exec()\fP is subsequently called. -The value of \fIstartoffset\fP is also checked to ensure that it points to the -start of a UTF-8 character. There is a discussion about the validity of UTF-8 -strings in the -.\" HTML -.\" -section on UTF-8 support -.\" -in the main -.\" HREF -\fBpcre\fP -.\" -page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_exec()\fP returns -the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP contains an invalid value, -PCRE_ERROR_BADUTF8_OFFSET is returned. -.P -If you already know that your subject is valid, and you want to skip these -checks for performance reasons, you can set the PCRE_NO_UTF8_CHECK option when -calling \fBpcre_exec()\fP. You might want to do this for the second and -subsequent calls to \fBpcre_exec()\fP if you are making repeated calls to find -all the matches in a single subject string. However, you should be sure that -the value of \fIstartoffset\fP points to the start of a UTF-8 character. When -PCRE_NO_UTF8_CHECK is set, the effect of passing an invalid UTF-8 string as a -subject, or a value of \fIstartoffset\fP that does not point to the start of a -UTF-8 character, is undefined. Your program may crash. -.sp - PCRE_PARTIAL -.sp -This option turns on the partial matching feature. If the subject string fails -to match the pattern, but at some point during the matching process the end of -the subject was reached (that is, the subject partially matches the pattern and -the failure to match occurred only because there were not enough subject -characters), \fBpcre_exec()\fP returns PCRE_ERROR_PARTIAL instead of -PCRE_ERROR_NOMATCH. When PCRE_PARTIAL is used, there are restrictions on what -may appear in the pattern. These are discussed in the -.\" HREF -\fBpcrepartial\fP -.\" -documentation. -. -.SS "The string to be matched by \fBpcre_exec()\fP" -.rs -.sp -The subject string is passed to \fBpcre_exec()\fP as a pointer in -\fIsubject\fP, a length (in bytes) in \fIlength\fP, and a starting byte offset -in \fIstartoffset\fP. In UTF-8 mode, the byte offset must point to the start of -a UTF-8 character. Unlike the pattern string, the subject may contain binary -zero bytes. When the starting offset is zero, the search for a match starts at -the beginning of the subject, and this is by far the most common case. -.P -A non-zero starting offset is useful when searching for another match in the -same subject by calling \fBpcre_exec()\fP again after a previous success. -Setting \fIstartoffset\fP differs from just passing over a shortened string and -setting PCRE_NOTBOL in the case of a pattern that begins with any kind of -lookbehind. For example, consider the pattern -.sp - \eBiss\eB -.sp -which finds occurrences of "iss" in the middle of words. (\eB matches only if -the current position in the subject is not a word boundary.) When applied to -the string "Mississipi" the first call to \fBpcre_exec()\fP finds the first -occurrence. If \fBpcre_exec()\fP is called again with just the remainder of the -subject, namely "issipi", it does not match, because \eB is always false at the -start of the subject, which is deemed to be a word boundary. However, if -\fBpcre_exec()\fP is passed the entire string again, but with \fIstartoffset\fP -set to 4, it finds the second occurrence of "iss" because it is able to look -behind the starting point to discover that it is preceded by a letter. -.P -If a non-zero starting offset is passed when the pattern is anchored, one -attempt to match at the given offset is made. This can only succeed if the -pattern does not require the match to be at the start of the subject. -. -.SS "How \fBpcre_exec()\fP returns captured substrings" -.rs -.sp -In general, a pattern matches a certain portion of the subject, and in -addition, further substrings from the subject may be picked out by parts of the -pattern. Following the usage in Jeffrey Friedl's book, this is called -"capturing" in what follows, and the phrase "capturing subpattern" is used for -a fragment of a pattern that picks out a substring. PCRE supports several other -kinds of parenthesized subpattern that do not cause substrings to be captured. -.P -Captured substrings are returned to the caller via a vector of integers whose -address is passed in \fIovector\fP. The number of elements in the vector is -passed in \fIovecsize\fP, which must be a non-negative number. \fBNote\fP: this -argument is NOT the size of \fIovector\fP in bytes. -.P -The first two-thirds of the vector is used to pass back captured substrings, -each substring using a pair of integers. The remaining third of the vector is -used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns, -and is not available for passing back information. The number passed in -\fIovecsize\fP should always be a multiple of three. If it is not, it is -rounded down. -.P -When a match is successful, information about captured substrings is returned -in pairs of integers, starting at the beginning of \fIovector\fP, and -continuing up to two-thirds of its length at the most. The first element of -each pair is set to the byte offset of the first character in a substring, and -the second is set to the byte offset of the first character after the end of a -substring. \fBNote\fP: these values are always byte offsets, even in UTF-8 -mode. They are not character counts. -.P -The first pair of integers, \fIovector[0]\fP and \fIovector[1]\fP, identify the -portion of the subject string matched by the entire pattern. The next pair is -used for the first capturing subpattern, and so on. The value returned by -\fBpcre_exec()\fP is one more than the highest numbered pair that has been set. -For example, if two substrings have been captured, the returned value is 3. If -there are no capturing subpatterns, the return value from a successful match is -1, indicating that just the first pair of offsets has been set. -.P -If a capturing subpattern is matched repeatedly, it is the last portion of the -string that it matched that is returned. -.P -If the vector is too small to hold all the captured substring offsets, it is -used as far as possible (up to two-thirds of its length), and the function -returns a value of zero. If the substring offsets are not of interest, -\fBpcre_exec()\fP may be called with \fIovector\fP passed as NULL and -\fIovecsize\fP as zero. However, if the pattern contains back references and -the \fIovector\fP is not big enough to remember the related substrings, PCRE -has to get additional memory for use during matching. Thus it is usually -advisable to supply an \fIovector\fP. -.P -The \fBpcre_info()\fP function can be used to find out how many capturing -subpatterns there are in a compiled pattern. The smallest size for -\fIovector\fP that will allow for \fIn\fP captured substrings, in addition to -the offsets of the substring matched by the whole pattern, is (\fIn\fP+1)*3. -.P -It is possible for capturing subpattern number \fIn+1\fP to match some part of -the subject when subpattern \fIn\fP has not been used at all. For example, if -the string "abc" is matched against the pattern (a|(z))(bc) the return from the -function is 4, and subpatterns 1 and 3 are matched, but 2 is not. When this -happens, both values in the offset pairs corresponding to unused subpatterns -are set to -1. -.P -Offset values that correspond to unused subpatterns at the end of the -expression are also set to -1. For example, if the string "abc" is matched -against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The -return from the function is 2, because the highest used capturing subpattern -number is 1. However, you can refer to the offsets for the second and third -capturing subpatterns if you wish (assuming the vector is large enough, of -course). -.P -Some convenience functions are provided for extracting the captured substrings -as separate strings. These are described below. -. -.\" HTML -.SS "Error return values from \fBpcre_exec()\fP" -.rs -.sp -If \fBpcre_exec()\fP fails, it returns a negative number. The following are -defined in the header file: -.sp - PCRE_ERROR_NOMATCH (-1) -.sp -The subject string did not match the pattern. -.sp - PCRE_ERROR_NULL (-2) -.sp -Either \fIcode\fP or \fIsubject\fP was passed as NULL, or \fIovector\fP was -NULL and \fIovecsize\fP was not zero. -.sp - PCRE_ERROR_BADOPTION (-3) -.sp -An unrecognized bit was set in the \fIoptions\fP argument. -.sp - PCRE_ERROR_BADMAGIC (-4) -.sp -PCRE stores a 4-byte "magic number" at the start of the compiled code, to catch -the case when it is passed a junk pointer and to detect when a pattern that was -compiled in an environment of one endianness is run in an environment with the -other endianness. This is the error that PCRE gives when the magic number is -not present. -.sp - PCRE_ERROR_UNKNOWN_OPCODE (-5) -.sp -While running the pattern match, an unknown item was encountered in the -compiled pattern. This error could be caused by a bug in PCRE or by overwriting -of the compiled pattern. -.sp - PCRE_ERROR_NOMEMORY (-6) -.sp -If a pattern contains back references, but the \fIovector\fP that is passed to -\fBpcre_exec()\fP is not big enough to remember the referenced substrings, PCRE -gets a block of memory at the start of matching to use for this purpose. If the -call via \fBpcre_malloc()\fP fails, this error is given. The memory is -automatically freed at the end of matching. -.sp - PCRE_ERROR_NOSUBSTRING (-7) -.sp -This error is used by the \fBpcre_copy_substring()\fP, -\fBpcre_get_substring()\fP, and \fBpcre_get_substring_list()\fP functions (see -below). It is never returned by \fBpcre_exec()\fP. -.sp - PCRE_ERROR_MATCHLIMIT (-8) -.sp -The backtracking limit, as specified by the \fImatch_limit\fP field in a -\fBpcre_extra\fP structure (or defaulted) was reached. See the description -above. -.sp - PCRE_ERROR_CALLOUT (-9) -.sp -This error is never generated by \fBpcre_exec()\fP itself. It is provided for -use by callout functions that want to yield a distinctive error code. See the -.\" HREF -\fBpcrecallout\fP -.\" -documentation for details. -.sp - PCRE_ERROR_BADUTF8 (-10) -.sp -A string that contains an invalid UTF-8 byte sequence was passed as a subject. -.sp - PCRE_ERROR_BADUTF8_OFFSET (-11) -.sp -The UTF-8 byte sequence that was passed as a subject was valid, but the value -of \fIstartoffset\fP did not point to the beginning of a UTF-8 character. -.sp - PCRE_ERROR_PARTIAL (-12) -.sp -The subject string did not match, but it did match partially. See the -.\" HREF -\fBpcrepartial\fP -.\" -documentation for details of partial matching. -.sp - PCRE_ERROR_BADPARTIAL (-13) -.sp -The PCRE_PARTIAL option was used with a compiled pattern containing items that -are not supported for partial matching. See the -.\" HREF -\fBpcrepartial\fP -.\" -documentation for details of partial matching. -.sp - PCRE_ERROR_INTERNAL (-14) -.sp -An unexpected internal error has occurred. This error could be caused by a bug -in PCRE or by overwriting of the compiled pattern. -.sp - PCRE_ERROR_BADCOUNT (-15) -.sp -This error is given if the value of the \fIovecsize\fP argument is negative. -.sp - PCRE_ERROR_RECURSIONLIMIT (-21) -.sp -The internal recursion limit, as specified by the \fImatch_limit_recursion\fP -field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the -description above. -.sp - PCRE_ERROR_BADNEWLINE (-23) -.sp -An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given. -.P -Error numbers -16 to -20 and -22 are not used by \fBpcre_exec()\fP. -. -. -.SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER" -.rs -.sp -.B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP, -.ti +5n -.B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP, -.ti +5n -.B int \fIbuffersize\fP); -.PP -.B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP, -.ti +5n -.B int \fIstringcount\fP, int \fIstringnumber\fP, -.ti +5n -.B const char **\fIstringptr\fP); -.PP -.B int pcre_get_substring_list(const char *\fIsubject\fP, -.ti +5n -.B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);" -.PP -Captured substrings can be accessed directly by using the offsets returned by -\fBpcre_exec()\fP in \fIovector\fP. For convenience, the functions -\fBpcre_copy_substring()\fP, \fBpcre_get_substring()\fP, and -\fBpcre_get_substring_list()\fP are provided for extracting captured substrings -as new, separate, zero-terminated strings. These functions identify substrings -by number. The next section describes functions for extracting named -substrings. -.P -A substring that contains a binary zero is correctly extracted and has a -further zero added on the end, but the result is not, of course, a C string. -However, you can process such a string by referring to the length that is -returned by \fBpcre_copy_substring()\fP and \fBpcre_get_substring()\fP. -Unfortunately, the interface to \fBpcre_get_substring_list()\fP is not adequate -for handling strings containing binary zeros, because the end of the final -string is not independently indicated. -.P -The first three arguments are the same for all three of these functions: -\fIsubject\fP is the subject string that has just been successfully matched, -\fIovector\fP is a pointer to the vector of integer offsets that was passed to -\fBpcre_exec()\fP, and \fIstringcount\fP is the number of substrings that were -captured by the match, including the substring that matched the entire regular -expression. This is the value returned by \fBpcre_exec()\fP if it is greater -than zero. If \fBpcre_exec()\fP returned zero, indicating that it ran out of -space in \fIovector\fP, the value passed as \fIstringcount\fP should be the -number of elements in the vector divided by three. -.P -The functions \fBpcre_copy_substring()\fP and \fBpcre_get_substring()\fP -extract a single substring, whose number is given as \fIstringnumber\fP. A -value of zero extracts the substring that matched the entire pattern, whereas -higher values extract the captured substrings. For \fBpcre_copy_substring()\fP, -the string is placed in \fIbuffer\fP, whose length is given by -\fIbuffersize\fP, while for \fBpcre_get_substring()\fP a new block of memory is -obtained via \fBpcre_malloc\fP, and its address is returned via -\fIstringptr\fP. The yield of the function is the length of the string, not -including the terminating zero, or one of these error codes: -.sp - PCRE_ERROR_NOMEMORY (-6) -.sp -The buffer was too small for \fBpcre_copy_substring()\fP, or the attempt to get -memory failed for \fBpcre_get_substring()\fP. -.sp - PCRE_ERROR_NOSUBSTRING (-7) -.sp -There is no substring whose number is \fIstringnumber\fP. -.P -The \fBpcre_get_substring_list()\fP function extracts all available substrings -and builds a list of pointers to them. All this is done in a single block of -memory that is obtained via \fBpcre_malloc\fP. The address of the memory block -is returned via \fIlistptr\fP, which is also the start of the list of string -pointers. The end of the list is marked by a NULL pointer. The yield of the -function is zero if all went well, or the error code -.sp - PCRE_ERROR_NOMEMORY (-6) -.sp -if the attempt to get the memory block failed. -.P -When any of these functions encounter a substring that is unset, which can -happen when capturing subpattern number \fIn+1\fP matches some part of the -subject, but subpattern \fIn\fP has not been used at all, they return an empty -string. This can be distinguished from a genuine zero-length substring by -inspecting the appropriate offset in \fIovector\fP, which is negative for unset -substrings. -.P -The two convenience functions \fBpcre_free_substring()\fP and -\fBpcre_free_substring_list()\fP can be used to free the memory returned by -a previous call of \fBpcre_get_substring()\fP or -\fBpcre_get_substring_list()\fP, respectively. They do nothing more than call -the function pointed to by \fBpcre_free\fP, which of course could be called -directly from a C program. However, PCRE is used in some situations where it is -linked via a special interface to another programming language that cannot use -\fBpcre_free\fP directly; it is for these cases that the functions are -provided. -. -. -.SH "EXTRACTING CAPTURED SUBSTRINGS BY NAME" -.rs -.sp -.B int pcre_get_stringnumber(const pcre *\fIcode\fP, -.ti +5n -.B const char *\fIname\fP); -.PP -.B int pcre_copy_named_substring(const pcre *\fIcode\fP, -.ti +5n -.B const char *\fIsubject\fP, int *\fIovector\fP, -.ti +5n -.B int \fIstringcount\fP, const char *\fIstringname\fP, -.ti +5n -.B char *\fIbuffer\fP, int \fIbuffersize\fP); -.PP -.B int pcre_get_named_substring(const pcre *\fIcode\fP, -.ti +5n -.B const char *\fIsubject\fP, int *\fIovector\fP, -.ti +5n -.B int \fIstringcount\fP, const char *\fIstringname\fP, -.ti +5n -.B const char **\fIstringptr\fP); -.PP -To extract a substring by name, you first have to find associated number. -For example, for this pattern -.sp - (a+)b(?\ed+)... -.sp -the number of the subpattern called "xxx" is 2. If the name is known to be -unique (PCRE_DUPNAMES was not set), you can find the number from the name by -calling \fBpcre_get_stringnumber()\fP. The first argument is the compiled -pattern, and the second is the name. The yield of the function is the -subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no subpattern of -that name. -.P -Given the number, you can extract the substring directly, or use one of the -functions described in the previous section. For convenience, there are also -two functions that do the whole job. -.P -Most of the arguments of \fBpcre_copy_named_substring()\fP and -\fBpcre_get_named_substring()\fP are the same as those for the similarly named -functions that extract by number. As these are described in the previous -section, they are not re-described here. There are just two differences: -.P -First, instead of a substring number, a substring name is given. Second, there -is an extra argument, given at the start, which is a pointer to the compiled -pattern. This is needed in order to gain access to the name-to-number -translation table. -.P -These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they -then call \fBpcre_copy_substring()\fP or \fBpcre_get_substring()\fP, as -appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names, -the behaviour may not be what you want (see the next section). -.P -\fBWarning:\fP If the pattern uses the "(?|" feature to set up multiple -subpatterns with the same number, you cannot use names to distinguish them, -because names are not included in the compiled code. The matching process uses -only numbers. -. -.SH "DUPLICATE SUBPATTERN NAMES" -.rs -.sp -.B int pcre_get_stringtable_entries(const pcre *\fIcode\fP, -.ti +5n -.B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP); -.PP -When a pattern is compiled with the PCRE_DUPNAMES option, names for subpatterns -are not required to be unique. Normally, patterns with duplicate names are such -that in any one match, only one of the named subpatterns participates. An -example is shown in the -.\" HREF -\fBpcrepattern\fP -.\" -documentation. -.P -When duplicates are present, \fBpcre_copy_named_substring()\fP and -\fBpcre_get_named_substring()\fP return the first substring corresponding to -the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING (-7) is -returned; no data is returned. The \fBpcre_get_stringnumber()\fP function -returns one of the numbers that are associated with the name, but it is not -defined which it is. -.P -If you want to get full details of all captured substrings for a given name, -you must use the \fBpcre_get_stringtable_entries()\fP function. The first -argument is the compiled pattern, and the second is the name. The third and -fourth are pointers to variables which are updated by the function. After it -has run, they point to the first and last entries in the name-to-number table -for the given name. The function itself returns the length of each entry, or -PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is -described above in the section entitled \fIInformation about a pattern\fP. -Given all the relevant entries for the name, you can extract each of their -numbers, and hence the captured data, if any. -. -. -.SH "FINDING ALL POSSIBLE MATCHES" -.rs -.sp -The traditional matching function uses a similar algorithm to Perl, which stops -when it finds the first match, starting at a given point in the subject. If you -want to find all possible matches, or the longest possible match, consider -using the alternative matching function (see below) instead. If you cannot use -the alternative function, but still need to find all possible matches, you -can kludge it up by making use of the callout facility, which is described in -the -.\" HREF -\fBpcrecallout\fP -.\" -documentation. -.P -What you have to do is to insert a callout right at the end of the pattern. -When your callout function is called, extract and save the current matched -substring. Then return 1, which forces \fBpcre_exec()\fP to backtrack and try -other alternatives. Ultimately, when it runs out of matches, \fBpcre_exec()\fP -will yield PCRE_ERROR_NOMATCH. -. -. -.\" HTML -.SH "MATCHING A PATTERN: THE ALTERNATIVE FUNCTION" -.rs -.sp -.B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," -.ti +5n -.B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP, -.ti +5n -.B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP, -.ti +5n -.B int *\fIworkspace\fP, int \fIwscount\fP); -.P -The function \fBpcre_dfa_exec()\fP is called to match a subject string against -a compiled pattern, using a matching algorithm that scans the subject string -just once, and does not backtrack. This has different characteristics to the -normal algorithm, and is not compatible with Perl. Some of the features of PCRE -patterns are not supported. Nevertheless, there are times when this kind of -matching can be useful. For a discussion of the two matching algorithms, see -the -.\" HREF -\fBpcrematching\fP -.\" -documentation. -.P -The arguments for the \fBpcre_dfa_exec()\fP function are the same as for -\fBpcre_exec()\fP, plus two extras. The \fIovector\fP argument is used in a -different way, and this is described below. The other common arguments are used -in the same way as for \fBpcre_exec()\fP, so their description is not repeated -here. -.P -The two additional arguments provide workspace for the function. The workspace -vector should contain at least 20 elements. It is used for keeping track of -multiple paths through the pattern tree. More workspace will be needed for -patterns and subjects where there are a lot of potential matches. -.P -Here is an example of a simple call to \fBpcre_dfa_exec()\fP: -.sp - int rc; - int ovector[10]; - int wspace[20]; - rc = pcre_dfa_exec( - re, /* result of pcre_compile() */ - NULL, /* we didn't study the pattern */ - "some string", /* the subject string */ - 11, /* the length of the subject string */ - 0, /* start at offset 0 in the subject */ - 0, /* default options */ - ovector, /* vector of integers for substring information */ - 10, /* number of elements (NOT size in bytes) */ - wspace, /* working space vector */ - 20); /* number of elements (NOT size in bytes) */ -. -.SS "Option bits for \fBpcre_dfa_exec()\fP" -.rs -.sp -The unused bits of the \fIoptions\fP argument for \fBpcre_dfa_exec()\fP must be -zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP, -PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL, -PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last three of these are -the same as for \fBpcre_exec()\fP, so their description is not repeated here. -.sp - PCRE_PARTIAL -.sp -This has the same general effect as it does for \fBpcre_exec()\fP, but the -details are slightly different. When PCRE_PARTIAL is set for -\fBpcre_dfa_exec()\fP, the return code PCRE_ERROR_NOMATCH is converted into -PCRE_ERROR_PARTIAL if the end of the subject is reached, there have been no -complete matches, but there is still at least one matching possibility. The -portion of the string that provided the partial match is set as the first -matching string. -.sp - PCRE_DFA_SHORTEST -.sp -Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to stop as -soon as it has found one match. Because of the way the alternative algorithm -works, this is necessarily the shortest possible match at the first possible -matching point in the subject string. -.sp - PCRE_DFA_RESTART -.sp -When \fBpcre_dfa_exec()\fP is called with the PCRE_PARTIAL option, and returns -a partial match, it is possible to call it again, with additional subject -characters, and have it continue with the same match. The PCRE_DFA_RESTART -option requests this action; when it is set, the \fIworkspace\fP and -\fIwscount\fP options must reference the same vector as before because data -about the match so far is left in them after a partial match. There is more -discussion of this facility in the -.\" HREF -\fBpcrepartial\fP -.\" -documentation. -. -.SS "Successful returns from \fBpcre_dfa_exec()\fP" -.rs -.sp -When \fBpcre_dfa_exec()\fP succeeds, it may have matched more than one -substring in the subject. Note, however, that all the matches from one run of -the function start at the same point in the subject. The shorter matches are -all initial substrings of the longer matches. For example, if the pattern -.sp - <.*> -.sp -is matched against the string -.sp - This is no more -.sp -the three matched strings are -.sp - - - -.sp -On success, the yield of the function is a number greater than zero, which is -the number of matched substrings. The substrings themselves are returned in -\fIovector\fP. Each string uses two elements; the first is the offset to the -start, and the second is the offset to the end. In fact, all the strings have -the same start offset. (Space could have been saved by giving this only once, -but it was decided to retain some compatibility with the way \fBpcre_exec()\fP -returns data, even though the meaning of the strings is different.) -.P -The strings are returned in reverse order of length; that is, the longest -matching string is given first. If there were too many matches to fit into -\fIovector\fP, the yield of the function is zero, and the vector is filled with -the longest matches. -. -.SS "Error returns from \fBpcre_dfa_exec()\fP" -.rs -.sp -The \fBpcre_dfa_exec()\fP function returns a negative number when it fails. -Many of the errors are the same as for \fBpcre_exec()\fP, and these are -described -.\" HTML -.\" -above. -.\" -There are in addition the following errors that are specific to -\fBpcre_dfa_exec()\fP: -.sp - PCRE_ERROR_DFA_UITEM (-16) -.sp -This return is given if \fBpcre_dfa_exec()\fP encounters an item in the pattern -that it does not support, for instance, the use of \eC or a back reference. -.sp - PCRE_ERROR_DFA_UCOND (-17) -.sp -This return is given if \fBpcre_dfa_exec()\fP encounters a condition item that -uses a back reference for the condition, or a test for recursion in a specific -group. These are not supported. -.sp - PCRE_ERROR_DFA_UMLIMIT (-18) -.sp -This return is given if \fBpcre_dfa_exec()\fP is called with an \fIextra\fP -block that contains a setting of the \fImatch_limit\fP field. This is not -supported (it is meaningless). -.sp - PCRE_ERROR_DFA_WSSIZE (-19) -.sp -This return is given if \fBpcre_dfa_exec()\fP runs out of space in the -\fIworkspace\fP vector. -.sp - PCRE_ERROR_DFA_RECURSE (-20) -.sp -When a recursive subpattern is processed, the matching function calls itself -recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This -error is given if the output vector is not large enough. This should be -extremely rare, as a vector of size 1000 is used. -. -. -.SH "SEE ALSO" -.rs -.sp -\fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3), -\fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3), -\fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3). -. -. -.SH AUTHOR -.rs -.sp -.nf -Philip Hazel -University Computing Service -Cambridge CB2 3QH, England. -.fi -. -. -.SH REVISION -.rs -.sp -.nf -Last updated: 11 April 2009 -Copyright (c) 1997-2009 University of Cambridge. -.fi diff --git a/libs/pcre/doc/pcrebuild.3 b/libs/pcre/doc/pcrebuild.3 deleted file mode 100644 index 926a4af10c..0000000000 --- a/libs/pcre/doc/pcrebuild.3 +++ /dev/null @@ -1,334 +0,0 @@ -.TH PCREBUILD 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH "PCRE BUILD-TIME OPTIONS" -.rs -.sp -This document describes the optional features of PCRE that can be selected when -the library is compiled. It assumes use of the \fBconfigure\fP script, where -the optional features are selected or deselected by providing options to -\fBconfigure\fP before running the \fBmake\fP command. However, the same -options can be selected in both Unix-like and non-Unix-like environments using -the GUI facility of \fBCMakeSetup\fP if you are using \fBCMake\fP instead of -\fBconfigure\fP to build PCRE. -.P -The complete list of options for \fBconfigure\fP (which includes the standard -ones such as the selection of the installation directory) can be obtained by -running -.sp - ./configure --help -.sp -The following sections include descriptions of options whose names begin with ---enable or --disable. These settings specify changes to the defaults for the -\fBconfigure\fP command. Because of the way that \fBconfigure\fP works, ---enable and --disable always come in pairs, so the complementary option always -exists as well, but as it specifies the default, it is not described. -. -.SH "C++ SUPPORT" -.rs -.sp -By default, the \fBconfigure\fP script will search for a C++ compiler and C++ -header files. If it finds them, it automatically builds the C++ wrapper library -for PCRE. You can disable this by adding -.sp - --disable-cpp -.sp -to the \fBconfigure\fP command. -. -.SH "UTF-8 SUPPORT" -.rs -.sp -To build PCRE with support for UTF-8 Unicode character strings, add -.sp - --enable-utf8 -.sp -to the \fBconfigure\fP command. Of itself, this does not make PCRE treat -strings as UTF-8. As well as compiling PCRE with this option, you also have -have to set the PCRE_UTF8 option when you call the \fBpcre_compile()\fP -function. -.P -If you set --enable-utf8 when compiling in an EBCDIC environment, PCRE expects -its input to be either ASCII or UTF-8 (depending on the runtime option). It is -not possible to support both EBCDIC and UTF-8 codes in the same version of the -library. Consequently, --enable-utf8 and --enable-ebcdic are mutually -exclusive. -. -.SH "UNICODE CHARACTER PROPERTY SUPPORT" -.rs -.sp -UTF-8 support allows PCRE to process character values greater than 255 in the -strings that it handles. On its own, however, it does not provide any -facilities for accessing the properties of such characters. If you want to be -able to use the pattern escapes \eP, \ep, and \eX, which refer to Unicode -character properties, you must add -.sp - --enable-unicode-properties -.sp -to the \fBconfigure\fP command. This implies UTF-8 support, even if you have -not explicitly requested it. -.P -Including Unicode property support adds around 30K of tables to the PCRE -library. Only the general category properties such as \fILu\fP and \fINd\fP are -supported. Details are given in the -.\" HREF -\fBpcrepattern\fP -.\" -documentation. -. -.SH "CODE VALUE OF NEWLINE" -.rs -.sp -By default, PCRE interprets the linefeed (LF) character as indicating the end -of a line. This is the normal newline character on Unix-like systems. You can -compile PCRE to use carriage return (CR) instead, by adding -.sp - --enable-newline-is-cr -.sp -to the \fBconfigure\fP command. There is also a --enable-newline-is-lf option, -which explicitly specifies linefeed as the newline character. -.sp -Alternatively, you can specify that line endings are to be indicated by the two -character sequence CRLF. If you want this, add -.sp - --enable-newline-is-crlf -.sp -to the \fBconfigure\fP command. There is a fourth option, specified by -.sp - --enable-newline-is-anycrlf -.sp -which causes PCRE to recognize any of the three sequences CR, LF, or CRLF as -indicating a line ending. Finally, a fifth option, specified by -.sp - --enable-newline-is-any -.sp -causes PCRE to recognize any Unicode newline sequence. -.P -Whatever line ending convention is selected when PCRE is built can be -overridden when the library functions are called. At build time it is -conventional to use the standard for your operating system. -. -.SH "WHAT \eR MATCHES" -.rs -.sp -By default, the sequence \eR in a pattern matches any Unicode newline sequence, -whatever has been selected as the line ending sequence. If you specify -.sp - --enable-bsr-anycrlf -.sp -the default is changed so that \eR matches only CR, LF, or CRLF. Whatever is -selected when PCRE is built can be overridden when the library functions are -called. -. -.SH "BUILDING SHARED AND STATIC LIBRARIES" -.rs -.sp -The PCRE building process uses \fBlibtool\fP to build both shared and static -Unix libraries by default. You can suppress one of these by adding one of -.sp - --disable-shared - --disable-static -.sp -to the \fBconfigure\fP command, as required. -. -.SH "POSIX MALLOC USAGE" -.rs -.sp -When PCRE is called through the POSIX interface (see the -.\" HREF -\fBpcreposix\fP -.\" -documentation), additional working storage is required for holding the pointers -to capturing substrings, because PCRE requires three integers per substring, -whereas the POSIX interface provides only two. If the number of expected -substrings is small, the wrapper function uses space on the stack, because this -is faster than using \fBmalloc()\fP for each call. The default threshold above -which the stack is no longer used is 10; it can be changed by adding a setting -such as -.sp - --with-posix-malloc-threshold=20 -.sp -to the \fBconfigure\fP command. -. -.SH "HANDLING VERY LARGE PATTERNS" -.rs -.sp -Within a compiled pattern, offset values are used to point from one part to -another (for example, from an opening parenthesis to an alternation -metacharacter). By default, two-byte values are used for these offsets, leading -to a maximum size for a compiled pattern of around 64K. This is sufficient to -handle all but the most gigantic patterns. Nevertheless, some people do want to -process enormous patterns, so it is possible to compile PCRE to use three-byte -or four-byte offsets by adding a setting such as -.sp - --with-link-size=3 -.sp -to the \fBconfigure\fP command. The value given must be 2, 3, or 4. Using -longer offsets slows down the operation of PCRE because it has to load -additional bytes when handling them. -. -.SH "AVOIDING EXCESSIVE STACK USAGE" -.rs -.sp -When matching with the \fBpcre_exec()\fP function, PCRE implements backtracking -by making recursive calls to an internal function called \fBmatch()\fP. In -environments where the size of the stack is limited, this can severely limit -PCRE's operation. (The Unix environment does not usually suffer from this -problem, but it may sometimes be necessary to increase the maximum stack size. -There is a discussion in the -.\" HREF -\fBpcrestack\fP -.\" -documentation.) An alternative approach to recursion that uses memory from the -heap to remember data, instead of using recursive function calls, has been -implemented to work round the problem of limited stack size. If you want to -build a version of PCRE that works this way, add -.sp - --disable-stack-for-recursion -.sp -to the \fBconfigure\fP command. With this configuration, PCRE will use the -\fBpcre_stack_malloc\fP and \fBpcre_stack_free\fP variables to call memory -management functions. By default these point to \fBmalloc()\fP and -\fBfree()\fP, but you can replace the pointers so that your own functions are -used. -.P -Separate functions are provided rather than using \fBpcre_malloc\fP and -\fBpcre_free\fP because the usage is very predictable: the block sizes -requested are always the same, and the blocks are always freed in reverse -order. A calling program might be able to implement optimized functions that -perform better than \fBmalloc()\fP and \fBfree()\fP. PCRE runs noticeably more -slowly when built in this way. This option affects only the \fBpcre_exec()\fP -function; it is not relevant for the the \fBpcre_dfa_exec()\fP function. -. -.SH "LIMITING PCRE RESOURCE USAGE" -.rs -.sp -Internally, PCRE has a function called \fBmatch()\fP, which it calls repeatedly -(sometimes recursively) when matching a pattern with the \fBpcre_exec()\fP -function. By controlling the maximum number of times this function may be -called during a single matching operation, a limit can be placed on the -resources used by a single call to \fBpcre_exec()\fP. The limit can be changed -at run time, as described in the -.\" HREF -\fBpcreapi\fP -.\" -documentation. The default is 10 million, but this can be changed by adding a -setting such as -.sp - --with-match-limit=500000 -.sp -to the \fBconfigure\fP command. This setting has no effect on the -\fBpcre_dfa_exec()\fP matching function. -.P -In some environments it is desirable to limit the depth of recursive calls of -\fBmatch()\fP more strictly than the total number of calls, in order to -restrict the maximum amount of stack (or heap, if --disable-stack-for-recursion -is specified) that is used. A second limit controls this; it defaults to the -value that is set for --with-match-limit, which imposes no additional -constraints. However, you can set a lower limit by adding, for example, -.sp - --with-match-limit-recursion=10000 -.sp -to the \fBconfigure\fP command. This value can also be overridden at run time. -. -.SH "CREATING CHARACTER TABLES AT BUILD TIME" -.rs -.sp -PCRE uses fixed tables for processing characters whose code values are less -than 256. By default, PCRE is built with a set of tables that are distributed -in the file \fIpcre_chartables.c.dist\fP. These tables are for ASCII codes -only. If you add -.sp - --enable-rebuild-chartables -.sp -to the \fBconfigure\fP command, the distributed tables are no longer used. -Instead, a program called \fBdftables\fP is compiled and run. This outputs the -source for new set of tables, created in the default locale of your C runtime -system. (This method of replacing the tables does not work if you are cross -compiling, because \fBdftables\fP is run on the local host. If you need to -create alternative tables when cross compiling, you will have to do so "by -hand".) -. -.SH "USING EBCDIC CODE" -.rs -.sp -PCRE assumes by default that it will run in an environment where the character -code is ASCII (or Unicode, which is a superset of ASCII). This is the case for -most computer operating systems. PCRE can, however, be compiled to run in an -EBCDIC environment by adding -.sp - --enable-ebcdic -.sp -to the \fBconfigure\fP command. This setting implies ---enable-rebuild-chartables. You should only use it if you know that you are in -an EBCDIC environment (for example, an IBM mainframe operating system). The ---enable-ebcdic option is incompatible with --enable-utf8. -. -.SH "PCREGREP OPTIONS FOR COMPRESSED FILE SUPPORT" -.rs -.sp -By default, \fBpcregrep\fP reads all files as plain text. You can build it so -that it recognizes files whose names end in \fB.gz\fP or \fB.bz2\fP, and reads -them with \fBlibz\fP or \fBlibbz2\fP, respectively, by adding one or both of -.sp - --enable-pcregrep-libz - --enable-pcregrep-libbz2 -.sp -to the \fBconfigure\fP command. These options naturally require that the -relevant libraries are installed on your system. Configuration will fail if -they are not. -. -.SH "PCRETEST OPTION FOR LIBREADLINE SUPPORT" -.rs -.sp -If you add -.sp - --enable-pcretest-libreadline -.sp -to the \fBconfigure\fP command, \fBpcretest\fP is linked with the -\fBlibreadline\fP library, and when its input is from a terminal, it reads it -using the \fBreadline()\fP function. This provides line-editing and history -facilities. Note that \fBlibreadline\fP is GPL-licenced, so if you distribute a -binary of \fBpcretest\fP linked in this way, there may be licensing issues. -.P -Setting this option causes the \fB-lreadline\fP option to be added to the -\fBpcretest\fP build. In many operating environments with a sytem-installed -\fBlibreadline\fP this is sufficient. However, in some environments (e.g. -if an unmodified distribution version of readline is in use), some extra -configuration may be necessary. The INSTALL file for \fBlibreadline\fP says -this: -.sp - "Readline uses the termcap functions, but does not link with the - termcap or curses library itself, allowing applications which link - with readline the to choose an appropriate library." -.sp -If your environment has not been set up so that an appropriate library is -automatically included, you may need to add something like -.sp - LIBS="-ncurses" -.sp -immediately before the \fBconfigure\fP command. -. -. -.SH "SEE ALSO" -.rs -.sp -\fBpcreapi\fP(3), \fBpcre_config\fP(3). -. -. -.SH AUTHOR -.rs -.sp -.nf -Philip Hazel -University Computing Service -Cambridge CB2 3QH, England. -.fi -. -. -.SH REVISION -.rs -.sp -.nf -Last updated: 17 March 2009 -Copyright (c) 1997-2009 University of Cambridge. -.fi diff --git a/libs/pcre/doc/pcrecallout.3 b/libs/pcre/doc/pcrecallout.3 deleted file mode 100644 index abdbaed054..0000000000 --- a/libs/pcre/doc/pcrecallout.3 +++ /dev/null @@ -1,183 +0,0 @@ -.TH PCRECALLOUT 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH "PCRE CALLOUTS" -.rs -.sp -.B int (*pcre_callout)(pcre_callout_block *); -.PP -PCRE provides a feature called "callout", which is a means of temporarily -passing control to the caller of PCRE in the middle of pattern matching. The -caller of PCRE provides an external function by putting its entry point in the -global variable \fIpcre_callout\fP. By default, this variable contains NULL, -which disables all calling out. -.P -Within a regular expression, (?C) indicates the points at which the external -function is to be called. Different callout points can be identified by putting -a number less than 256 after the letter C. The default value is zero. -For example, this pattern has two callout points: -.sp - (?C1)abc(?C2)def -.sp -If the PCRE_AUTO_CALLOUT option bit is set when \fBpcre_compile()\fP is called, -PCRE automatically inserts callouts, all with number 255, before each item in -the pattern. For example, if PCRE_AUTO_CALLOUT is used with the pattern -.sp - A(\ed{2}|--) -.sp -it is processed as if it were -.sp -(?C255)A(?C255)((?C255)\ed{2}(?C255)|(?C255)-(?C255)-(?C255))(?C255) -.sp -Notice that there is a callout before and after each parenthesis and -alternation bar. Automatic callouts can be used for tracking the progress of -pattern matching. The -.\" HREF -\fBpcretest\fP -.\" -command has an option that sets automatic callouts; when it is used, the output -indicates how the pattern is matched. This is useful information when you are -trying to optimize the performance of a particular pattern. -. -. -.SH "MISSING CALLOUTS" -.rs -.sp -You should be aware that, because of optimizations in the way PCRE matches -patterns by default, callouts sometimes do not happen. For example, if the -pattern is -.sp - ab(?C4)cd -.sp -PCRE knows that any matching string must contain the letter "d". If the subject -string is "abyz", the lack of "d" means that matching doesn't ever start, and -the callout is never reached. However, with "abyd", though the result is still -no match, the callout is obeyed. -.P -You can disable these optimizations by passing the PCRE_NO_START_OPTIMIZE -option to \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP. This slows down the -matching process, but does ensure that callouts such as the example above are -obeyed. -. -. -.SH "THE CALLOUT INTERFACE" -.rs -.sp -During matching, when PCRE reaches a callout point, the external function -defined by \fIpcre_callout\fP is called (if it is set). This applies to both -the \fBpcre_exec()\fP and the \fBpcre_dfa_exec()\fP matching functions. The -only argument to the callout function is a pointer to a \fBpcre_callout\fP -block. This structure contains the following fields: -.sp - int \fIversion\fP; - int \fIcallout_number\fP; - int *\fIoffset_vector\fP; - const char *\fIsubject\fP; - int \fIsubject_length\fP; - int \fIstart_match\fP; - int \fIcurrent_position\fP; - int \fIcapture_top\fP; - int \fIcapture_last\fP; - void *\fIcallout_data\fP; - int \fIpattern_position\fP; - int \fInext_item_length\fP; -.sp -The \fIversion\fP field is an integer containing the version number of the -block format. The initial version was 0; the current version is 1. The version -number will change again in future if additional fields are added, but the -intention is never to remove any of the existing fields. -.P -The \fIcallout_number\fP field contains the number of the callout, as compiled -into the pattern (that is, the number after ?C for manual callouts, and 255 for -automatically generated callouts). -.P -The \fIoffset_vector\fP field is a pointer to the vector of offsets that was -passed by the caller to \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP. When -\fBpcre_exec()\fP is used, the contents can be inspected in order to extract -substrings that have been matched so far, in the same way as for extracting -substrings after a match has completed. For \fBpcre_dfa_exec()\fP this field is -not useful. -.P -The \fIsubject\fP and \fIsubject_length\fP fields contain copies of the values -that were passed to \fBpcre_exec()\fP. -.P -The \fIstart_match\fP field normally contains the offset within the subject at -which the current match attempt started. However, if the escape sequence \eK -has been encountered, this value is changed to reflect the modified starting -point. If the pattern is not anchored, the callout function may be called -several times from the same point in the pattern for different starting points -in the subject. -.P -The \fIcurrent_position\fP field contains the offset within the subject of the -current match pointer. -.P -When the \fBpcre_exec()\fP function is used, the \fIcapture_top\fP field -contains one more than the number of the highest numbered captured substring so -far. If no substrings have been captured, the value of \fIcapture_top\fP is -one. This is always the case when \fBpcre_dfa_exec()\fP is used, because it -does not support captured substrings. -.P -The \fIcapture_last\fP field contains the number of the most recently captured -substring. If no substrings have been captured, its value is -1. This is always -the case when \fBpcre_dfa_exec()\fP is used. -.P -The \fIcallout_data\fP field contains a value that is passed to -\fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP specifically so that it can be -passed back in callouts. It is passed in the \fIpcre_callout\fP field of the -\fBpcre_extra\fP data structure. If no such data was passed, the value of -\fIcallout_data\fP in a \fBpcre_callout\fP block is NULL. There is a -description of the \fBpcre_extra\fP structure in the -.\" HREF -\fBpcreapi\fP -.\" -documentation. -.P -The \fIpattern_position\fP field is present from version 1 of the -\fIpcre_callout\fP structure. It contains the offset to the next item to be -matched in the pattern string. -.P -The \fInext_item_length\fP field is present from version 1 of the -\fIpcre_callout\fP structure. It contains the length of the next item to be -matched in the pattern string. When the callout immediately precedes an -alternation bar, a closing parenthesis, or the end of the pattern, the length -is zero. When the callout precedes an opening parenthesis, the length is that -of the entire subpattern. -.P -The \fIpattern_position\fP and \fInext_item_length\fP fields are intended to -help in distinguishing between different automatic callouts, which all have the -same callout number. However, they are set for all callouts. -. -. -.SH "RETURN VALUES" -.rs -.sp -The external callout function returns an integer to PCRE. If the value is zero, -matching proceeds as normal. If the value is greater than zero, matching fails -at the current point, but the testing of other matching possibilities goes -ahead, just as if a lookahead assertion had failed. If the value is less than -zero, the match is abandoned, and \fBpcre_exec()\fP (or \fBpcre_dfa_exec()\fP) -returns the negative value. -.P -Negative values should normally be chosen from the set of PCRE_ERROR_xxx -values. In particular, PCRE_ERROR_NOMATCH forces a standard "no match" failure. -The error number PCRE_ERROR_CALLOUT is reserved for use by callout functions; -it will never be used by PCRE itself. -. -. -.SH AUTHOR -.rs -.sp -.nf -Philip Hazel -University Computing Service -Cambridge CB2 3QH, England. -.fi -. -. -.SH REVISION -.rs -.sp -.nf -Last updated: 15 March 2009 -Copyright (c) 1997-2009 University of Cambridge. -.fi diff --git a/libs/pcre/doc/pcrecompat.3 b/libs/pcre/doc/pcrecompat.3 deleted file mode 100644 index 3be6a6a38d..0000000000 --- a/libs/pcre/doc/pcrecompat.3 +++ /dev/null @@ -1,148 +0,0 @@ -.TH PCRECOMPAT 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH "DIFFERENCES BETWEEN PCRE AND PERL" -.rs -.sp -This document describes the differences in the ways that PCRE and Perl handle -regular expressions. The differences described here are mainly with respect to -Perl 5.8, though PCRE versions 7.0 and later contain some features that are -expected to be in the forthcoming Perl 5.10. -.P -1. PCRE has only a subset of Perl's UTF-8 and Unicode support. Details of what -it does have are given in the -.\" HTML -.\" -section on UTF-8 support -.\" -in the main -.\" HREF -\fBpcre\fP -.\" -page. -.P -2. PCRE does not allow repeat quantifiers on lookahead assertions. Perl permits -them, but they do not mean what you might think. For example, (?!a){3} does -not assert that the next three characters are not "a". It just asserts that the -next character is not "a" three times. -.P -3. Capturing subpatterns that occur inside negative lookahead assertions are -counted, but their entries in the offsets vector are never set. Perl sets its -numerical variables from any such patterns that are matched before the -assertion fails to match something (thereby succeeding), but only if the -negative lookahead assertion contains just one branch. -.P -4. Though binary zero characters are supported in the subject string, they are -not allowed in a pattern string because it is passed as a normal C string, -terminated by zero. The escape sequence \e0 can be used in the pattern to -represent a binary zero. -.P -5. The following Perl escape sequences are not supported: \el, \eu, \eL, -\eU, and \eN. In fact these are implemented by Perl's general string-handling -and are not part of its pattern matching engine. If any of these are -encountered by PCRE, an error is generated. -.P -6. The Perl escape sequences \ep, \eP, and \eX are supported only if PCRE is -built with Unicode character property support. The properties that can be -tested with \ep and \eP are limited to the general category properties such as -Lu and Nd, script names such as Greek or Han, and the derived properties Any -and L&. -.P -7. PCRE does support the \eQ...\eE escape for quoting substrings. Characters in -between are treated as literals. This is slightly different from Perl in that $ -and @ are also handled as literals inside the quotes. In Perl, they cause -variable interpolation (but of course PCRE does not have variables). Note the -following examples: -.sp - Pattern PCRE matches Perl matches -.sp -.\" JOIN - \eQabc$xyz\eE abc$xyz abc followed by the - contents of $xyz - \eQabc\e$xyz\eE abc\e$xyz abc\e$xyz - \eQabc\eE\e$\eQxyz\eE abc$xyz abc$xyz -.sp -The \eQ...\eE sequence is recognized both inside and outside character classes. -.P -8. Fairly obviously, PCRE does not support the (?{code}) and (??{code}) -constructions. However, there is support for recursive patterns. This is not -available in Perl 5.8, but will be in Perl 5.10. Also, the PCRE "callout" -feature allows an external function to be called during pattern matching. See -the -.\" HREF -\fBpcrecallout\fP -.\" -documentation for details. -.P -9. Subpatterns that are called recursively or as "subroutines" are always -treated as atomic groups in PCRE. This is like Python, but unlike Perl. -.P -10. There are some differences that are concerned with the settings of captured -strings when part of a pattern is repeated. For example, matching "aba" against -the pattern /^(a(b)?)+$/ in Perl leaves $2 unset, but in PCRE it is set to "b". -.P -11. PCRE does support Perl 5.10's backtracking verbs (*ACCEPT), (*FAIL), (*F), -(*COMMIT), (*PRUNE), (*SKIP), and (*THEN), but only in the forms without an -argument. PCRE does not support (*MARK). If (*ACCEPT) is within capturing -parentheses, PCRE does not set that capture group; this is different to Perl. -.P -12. PCRE provides some extensions to the Perl regular expression facilities. -Perl 5.10 will include new features that are not in earlier versions, some of -which (such as named parentheses) have been in PCRE for some time. This list is -with respect to Perl 5.10: -.sp -(a) Although lookbehind assertions must match fixed length strings, each -alternative branch of a lookbehind assertion can match a different length of -string. Perl requires them all to have the same length. -.sp -(b) If PCRE_DOLLAR_ENDONLY is set and PCRE_MULTILINE is not set, the $ -meta-character matches only at the very end of the string. -.sp -(c) If PCRE_EXTRA is set, a backslash followed by a letter with no special -meaning is faulted. Otherwise, like Perl, the backslash is quietly ignored. -(Perl can be made to issue a warning.) -.sp -(d) If PCRE_UNGREEDY is set, the greediness of the repetition quantifiers is -inverted, that is, by default they are not greedy, but if followed by a -question mark they are. -.sp -(e) PCRE_ANCHORED can be used at matching time to force a pattern to be tried -only at the first matching position in the subject string. -.sp -(f) The PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, and PCRE_NO_AUTO_CAPTURE -options for \fBpcre_exec()\fP have no Perl equivalents. -.sp -(g) The \eR escape sequence can be restricted to match only CR, LF, or CRLF -by the PCRE_BSR_ANYCRLF option. -.sp -(h) The callout facility is PCRE-specific. -.sp -(i) The partial matching facility is PCRE-specific. -.sp -(j) Patterns compiled by PCRE can be saved and re-used at a later time, even on -different hosts that have the other endianness. -.sp -(k) The alternative matching function (\fBpcre_dfa_exec()\fP) matches in a -different way and is not Perl-compatible. -.sp -(l) PCRE recognizes some special sequences such as (*CR) at the start of -a pattern that set overall options that cannot be changed within the pattern. -. -. -.SH AUTHOR -.rs -.sp -.nf -Philip Hazel -University Computing Service -Cambridge CB2 3QH, England. -.fi -. -. -.SH REVISION -.rs -.sp -.nf -Last updated: 11 September 2007 -Copyright (c) 1997-2007 University of Cambridge. -.fi diff --git a/libs/pcre/doc/pcrecpp.3 b/libs/pcre/doc/pcrecpp.3 deleted file mode 100644 index fa8c5581be..0000000000 --- a/libs/pcre/doc/pcrecpp.3 +++ /dev/null @@ -1,347 +0,0 @@ -.TH PCRECPP 3 -.SH NAME -PCRE - Perl-compatible regular expressions. -.SH "SYNOPSIS OF C++ WRAPPER" -.rs -.sp -.B #include -. -.SH DESCRIPTION -.rs -.sp -The C++ wrapper for PCRE was provided by Google Inc. Some additional -functionality was added by Giuseppe Maxia. This brief man page was constructed -from the notes in the \fIpcrecpp.h\fP file, which should be consulted for -further details. -. -. -.SH "MATCHING INTERFACE" -.rs -.sp -The "FullMatch" operation checks that supplied text matches a supplied pattern -exactly. If pointer arguments are supplied, it copies matched sub-strings that -match sub-patterns into them. -.sp - Example: successful match - pcrecpp::RE re("h.*o"); - re.FullMatch("hello"); -.sp - Example: unsuccessful match (requires full match): - pcrecpp::RE re("e"); - !re.FullMatch("hello"); -.sp - Example: creating a temporary RE object: - pcrecpp::RE("h.*o").FullMatch("hello"); -.sp -You can pass in a "const char*" or a "string" for "text". The examples below -tend to use a const char*. You can, as in the different examples above, store -the RE object explicitly in a variable or use a temporary RE object. The -examples below use one mode or the other arbitrarily. Either could correctly be -used for any of these examples. -.P -You must supply extra pointer arguments to extract matched subpieces. -.sp - Example: extracts "ruby" into "s" and 1234 into "i" - int i; - string s; - pcrecpp::RE re("(\e\ew+):(\e\ed+)"); - re.FullMatch("ruby:1234", &s, &i); -.sp - Example: does not try to extract any extra sub-patterns - re.FullMatch("ruby:1234", &s); -.sp - Example: does not try to extract into NULL - re.FullMatch("ruby:1234", NULL, &i); -.sp - Example: integer overflow causes failure - !re.FullMatch("ruby:1234567891234", NULL, &i); -.sp - Example: fails because there aren't enough sub-patterns: - !pcrecpp::RE("\e\ew+:\e\ed+").FullMatch("ruby:1234", &s); -.sp - Example: fails because string cannot be stored in integer - !pcrecpp::RE("(.*)").FullMatch("ruby", &i); -.sp -The provided pointer arguments can be pointers to any scalar numeric -type, or one of: -.sp - string (matched piece is copied to string) - StringPiece (StringPiece is mutated to point to matched piece) - T (where "bool T::ParseFrom(const char*, int)" exists) - NULL (the corresponding matched sub-pattern is not copied) -.sp -The function returns true iff all of the following conditions are satisfied: -.sp - a. "text" matches "pattern" exactly; -.sp - b. The number of matched sub-patterns is >= number of supplied - pointers; -.sp - c. The "i"th argument has a suitable type for holding the - string captured as the "i"th sub-pattern. If you pass in - void * NULL for the "i"th argument, or a non-void * NULL - of the correct type, or pass fewer arguments than the - number of sub-patterns, "i"th captured sub-pattern is - ignored. -.sp -CAVEAT: An optional sub-pattern that does not exist in the matched -string is assigned the empty string. Therefore, the following will -return false (because the empty string is not a valid number): -.sp - int number; - pcrecpp::RE::FullMatch("abc", "[a-z]+(\e\ed+)?", &number); -.sp -The matching interface supports at most 16 arguments per call. -If you need more, consider using the more general interface -\fBpcrecpp::RE::DoMatch\fP. See \fBpcrecpp.h\fP for the signature for -\fBDoMatch\fP. -.P -NOTE: Do not use \fBno_arg\fP, which is used internally to mark the end of a -list of optional arguments, as a placeholder for missing arguments, as this can -lead to segfaults. -. -. -.SH "QUOTING METACHARACTERS" -.rs -.sp -You can use the "QuoteMeta" operation to insert backslashes before all -potentially meaningful characters in a string. The returned string, used as a -regular expression, will exactly match the original string. -.sp - Example: - string quoted = RE::QuoteMeta(unquoted); -.sp -Note that it's legal to escape a character even if it has no special meaning in -a regular expression -- so this function does that. (This also makes it -identical to the perl function of the same name; see "perldoc -f quotemeta".) -For example, "1.5-2.0?" becomes "1\e.5\e-2\e.0\e?". -. -.SH "PARTIAL MATCHES" -.rs -.sp -You can use the "PartialMatch" operation when you want the pattern -to match any substring of the text. -.sp - Example: simple search for a string: - pcrecpp::RE("ell").PartialMatch("hello"); -.sp - Example: find first number in a string: - int number; - pcrecpp::RE re("(\e\ed+)"); - re.PartialMatch("x*100 + 20", &number); - assert(number == 100); -. -. -.SH "UTF-8 AND THE MATCHING INTERFACE" -.rs -.sp -By default, pattern and text are plain text, one byte per character. The UTF8 -flag, passed to the constructor, causes both pattern and string to be treated -as UTF-8 text, still a byte stream but potentially multiple bytes per -character. In practice, the text is likelier to be UTF-8 than the pattern, but -the match returned may depend on the UTF8 flag, so always use it when matching -UTF8 text. For example, "." will match one byte normally but with UTF8 set may -match up to three bytes of a multi-byte character. -.sp - Example: - pcrecpp::RE_Options options; - options.set_utf8(); - pcrecpp::RE re(utf8_pattern, options); - re.FullMatch(utf8_string); -.sp - Example: using the convenience function UTF8(): - pcrecpp::RE re(utf8_pattern, pcrecpp::UTF8()); - re.FullMatch(utf8_string); -.sp -NOTE: The UTF8 flag is ignored if pcre was not configured with the - --enable-utf8 flag. -. -. -.SH "PASSING MODIFIERS TO THE REGULAR EXPRESSION ENGINE" -.rs -.sp -PCRE defines some modifiers to change the behavior of the regular expression -engine. The C++ wrapper defines an auxiliary class, RE_Options, as a vehicle to -pass such modifiers to a RE class. Currently, the following modifiers are -supported: -.sp - modifier description Perl corresponding -.sp - PCRE_CASELESS case insensitive match /i - PCRE_MULTILINE multiple lines match /m - PCRE_DOTALL dot matches newlines /s - PCRE_DOLLAR_ENDONLY $ matches only at end N/A - PCRE_EXTRA strict escape parsing N/A - PCRE_EXTENDED ignore whitespaces /x - PCRE_UTF8 handles UTF8 chars built-in - PCRE_UNGREEDY reverses * and *? N/A - PCRE_NO_AUTO_CAPTURE disables capturing parens N/A (*) -.sp -(*) Both Perl and PCRE allow non capturing parentheses by means of the -"?:" modifier within the pattern itself. e.g. (?:ab|cd) does not -capture, while (ab|cd) does. -.P -For a full account on how each modifier works, please check the -PCRE API reference page. -.P -For each modifier, there are two member functions whose name is made -out of the modifier in lowercase, without the "PCRE_" prefix. For -instance, PCRE_CASELESS is handled by -.sp - bool caseless() -.sp -which returns true if the modifier is set, and -.sp - RE_Options & set_caseless(bool) -.sp -which sets or unsets the modifier. Moreover, PCRE_EXTRA_MATCH_LIMIT can be -accessed through the \fBset_match_limit()\fR and \fBmatch_limit()\fR member -functions. Setting \fImatch_limit\fR to a non-zero value will limit the -execution of pcre to keep it from doing bad things like blowing the stack or -taking an eternity to return a result. A value of 5000 is good enough to stop -stack blowup in a 2MB thread stack. Setting \fImatch_limit\fR to zero disables -match limiting. Alternatively, you can call \fBmatch_limit_recursion()\fP -which uses PCRE_EXTRA_MATCH_LIMIT_RECURSION to limit how much PCRE -recurses. \fBmatch_limit()\fP limits the number of matches PCRE does; -\fBmatch_limit_recursion()\fP limits the depth of internal recursion, and -therefore the amount of stack that is used. -.P -Normally, to pass one or more modifiers to a RE class, you declare -a \fIRE_Options\fR object, set the appropriate options, and pass this -object to a RE constructor. Example: -.sp - RE_options opt; - opt.set_caseless(true); - if (RE("HELLO", opt).PartialMatch("hello world")) ... -.sp -RE_options has two constructors. The default constructor takes no arguments and -creates a set of flags that are off by default. The optional parameter -\fIoption_flags\fR is to facilitate transfer of legacy code from C programs. -This lets you do -.sp - RE(pattern, - RE_Options(PCRE_CASELESS|PCRE_MULTILINE)).PartialMatch(str); -.sp -However, new code is better off doing -.sp - RE(pattern, - RE_Options().set_caseless(true).set_multiline(true)) - .PartialMatch(str); -.sp -If you are going to pass one of the most used modifiers, there are some -convenience functions that return a RE_Options class with the -appropriate modifier already set: \fBCASELESS()\fR, \fBUTF8()\fR, -\fBMULTILINE()\fR, \fBDOTALL\fR(), and \fBEXTENDED()\fR. -.P -If you need to set several options at once, and you don't want to go through -the pains of declaring a RE_Options object and setting several options, there -is a parallel method that give you such ability on the fly. You can concatenate -several \fBset_xxxxx()\fR member functions, since each of them returns a -reference to its class object. For example, to pass PCRE_CASELESS, -PCRE_EXTENDED, and PCRE_MULTILINE to a RE with one statement, you may write: -.sp - RE(" ^ xyz \e\es+ .* blah$", - RE_Options() - .set_caseless(true) - .set_extended(true) - .set_multiline(true)).PartialMatch(sometext); -.sp -. -. -.SH "SCANNING TEXT INCREMENTALLY" -.rs -.sp -The "Consume" operation may be useful if you want to repeatedly -match regular expressions at the front of a string and skip over -them as they match. This requires use of the "StringPiece" type, -which represents a sub-range of a real string. Like RE, StringPiece -is defined in the pcrecpp namespace. -.sp - Example: read lines of the form "var = value" from a string. - string contents = ...; // Fill string somehow - pcrecpp::StringPiece input(contents); // Wrap in a StringPiece - - string var; - int value; - pcrecpp::RE re("(\e\ew+) = (\e\ed+)\en"); - while (re.Consume(&input, &var, &value)) { - ...; - } -.sp -Each successful call to "Consume" will set "var/value", and also -advance "input" so it points past the matched text. -.P -The "FindAndConsume" operation is similar to "Consume" but does not -anchor your match at the beginning of the string. For example, you -could extract all words from a string by repeatedly calling -.sp - pcrecpp::RE("(\e\ew+)").FindAndConsume(&input, &word) -. -. -.SH "PARSING HEX/OCTAL/C-RADIX NUMBERS" -.rs -.sp -By default, if you pass a pointer to a numeric value, the -corresponding text is interpreted as a base-10 number. You can -instead wrap the pointer with a call to one of the operators Hex(), -Octal(), or CRadix() to interpret the text in another base. The -CRadix operator interprets C-style "0" (base-8) and "0x" (base-16) -prefixes, but defaults to base-10. -.sp - Example: - int a, b, c, d; - pcrecpp::RE re("(.*) (.*) (.*) (.*)"); - re.FullMatch("100 40 0100 0x40", - pcrecpp::Octal(&a), pcrecpp::Hex(&b), - pcrecpp::CRadix(&c), pcrecpp::CRadix(&d)); -.sp -will leave 64 in a, b, c, and d. -. -. -.SH "REPLACING PARTS OF STRINGS" -.rs -.sp -You can replace the first match of "pattern" in "str" with "rewrite". -Within "rewrite", backslash-escaped digits (\e1 to \e9) can be -used to insert text matching corresponding parenthesized group -from the pattern. \e0 in "rewrite" refers to the entire matching -text. For example: -.sp - string s = "yabba dabba doo"; - pcrecpp::RE("b+").Replace("d", &s); -.sp -will leave "s" containing "yada dabba doo". The result is true if the pattern -matches and a replacement occurs, false otherwise. -.P -\fBGlobalReplace\fP is like \fBReplace\fP except that it replaces all -occurrences of the pattern in the string with the rewrite. Replacements are -not subject to re-matching. For example: -.sp - string s = "yabba dabba doo"; - pcrecpp::RE("b+").GlobalReplace("d", &s); -.sp -will leave "s" containing "yada dada doo". It returns the number of -replacements made. -.P -\fBExtract\fP is like \fBReplace\fP, except that if the pattern matches, -"rewrite" is copied into "out" (an additional argument) with substitutions. -The non-matching portions of "text" are ignored. Returns true iff a match -occurred and the extraction happened successfully; if no match occurs, the -string is left unaffected. -. -. -.SH AUTHOR -.rs -.sp -.nf -The C++ wrapper was contributed by Google Inc. -Copyright (c) 2007 Google Inc. -.fi -. -. -.SH REVISION -.rs -.sp -.nf -Last updated: 17 March 2009 -.fi diff --git a/libs/pcre/doc/pcregrep.1 b/libs/pcre/doc/pcregrep.1 deleted file mode 100644 index e0d05197d1..0000000000 --- a/libs/pcre/doc/pcregrep.1 +++ /dev/null @@ -1,477 +0,0 @@ -.TH PCREGREP 1 -.SH NAME -pcregrep - a grep with Perl-compatible regular expressions. -.SH SYNOPSIS -.B pcregrep [options] [long options] [pattern] [path1 path2 ...] -. -.SH DESCRIPTION -.rs -.sp -\fBpcregrep\fP searches files for character patterns, in the same way as other -grep commands do, but it uses the PCRE regular expression library to support -patterns that are compatible with the regular expressions of Perl 5. See -.\" HREF -\fBpcrepattern\fP(3) -.\" -for a full description of syntax and semantics of the regular expressions -that PCRE supports. -.P -Patterns, whether supplied on the command line or in a separate file, are given -without delimiters. For example: -.sp - pcregrep Thursday /etc/motd -.sp -If you attempt to use delimiters (for example, by surrounding a pattern with -slashes, as is common in Perl scripts), they are interpreted as part of the -pattern. Quotes can of course be used to delimit patterns on the command line -because they are interpreted by the shell, and indeed they are required if a -pattern contains white space or shell metacharacters. -.P -The first argument that follows any option settings is treated as the single -pattern to be matched when neither \fB-e\fP nor \fB-f\fP is present. -Conversely, when one or both of these options are used to specify patterns, all -arguments are treated as path names. At least one of \fB-e\fP, \fB-f\fP, or an -argument pattern must be provided. -.P -If no files are specified, \fBpcregrep\fP reads the standard input. The -standard input can also be referenced by a name consisting of a single hyphen. -For example: -.sp - pcregrep some-pattern /file1 - /file3 -.sp -By default, each line that matches a pattern is copied to the standard -output, and if there is more than one file, the file name is output at the -start of each line, followed by a colon. However, there are options that can -change how \fBpcregrep\fP behaves. In particular, the \fB-M\fP option makes it -possible to search for patterns that span line boundaries. What defines a line -boundary is controlled by the \fB-N\fP (\fB--newline\fP) option. -.P -Patterns are limited to 8K or BUFSIZ characters, whichever is the greater. -BUFSIZ is defined in \fB\fP. When there is more than one pattern -(specified by the use of \fB-e\fP and/or \fB-f\fP), each pattern is applied to -each line in the order in which they are defined, except that all the \fB-e\fP -patterns are tried before the \fB-f\fP patterns. -.P -By default, as soon as one pattern matches (or fails to match when \fB-v\fP is -used), no further patterns are considered. However, if \fB--colour\fP (or -\fB--color\fP) is used to colour the matching substrings, or if -\fB--only-matching\fP, \fB--file-offsets\fP, or \fB--line-offsets\fP is used to -output only the part of the line that matched (either shown literally, or as an -offset), scanning resumes immediately following the match, so that further -matches on the same line can be found. If there are multiple patterns, they are -all tried on the remainder of the line, but patterns that follow the one that -matched are not tried on the earlier part of the line. -.P -This is the same behaviour as GNU grep, but it does mean that the order in -which multiple patterns are specified can affect the output when one of the -above options is used. -.P -Patterns that can match an empty string are accepted, but empty string -matches are not recognized. An example is the pattern "(super)?(man)?", in -which all components are optional. This pattern finds all occurrences of both -"super" and "man"; the output differs from matching with "super|man" when only -the matching substrings are being shown. -.P -If the \fBLC_ALL\fP or \fBLC_CTYPE\fP environment variable is set, -\fBpcregrep\fP uses the value to set a locale when calling the PCRE library. -The \fB--locale\fP option can be used to override this. -. -.SH "SUPPORT FOR COMPRESSED FILES" -.rs -.sp -It is possible to compile \fBpcregrep\fP so that it uses \fBlibz\fP or -\fBlibbz2\fP to read files whose names end in \fB.gz\fP or \fB.bz2\fP, -respectively. You can find out whether your binary has support for one or both -of these file types by running it with the \fB--help\fP option. If the -appropriate support is not present, files are treated as plain text. The -standard input is always so treated. -. -.SH OPTIONS -.rs -.TP 10 -\fB--\fP -This terminate the list of options. It is useful if the next item on the -command line starts with a hyphen but is not an option. This allows for the -processing of patterns and filenames that start with hyphens. -.TP -\fB-A\fP \fInumber\fP, \fB--after-context=\fP\fInumber\fP -Output \fInumber\fP lines of context after each matching line. If filenames -and/or line numbers are being output, a hyphen separator is used instead of a -colon for the context lines. A line containing "--" is output between each -group of lines, unless they are in fact contiguous in the input file. The value -of \fInumber\fP is expected to be relatively small. However, \fBpcregrep\fP -guarantees to have up to 8K of following text available for context output. -.TP -\fB-B\fP \fInumber\fP, \fB--before-context=\fP\fInumber\fP -Output \fInumber\fP lines of context before each matching line. If filenames -and/or line numbers are being output, a hyphen separator is used instead of a -colon for the context lines. A line containing "--" is output between each -group of lines, unless they are in fact contiguous in the input file. The value -of \fInumber\fP is expected to be relatively small. However, \fBpcregrep\fP -guarantees to have up to 8K of preceding text available for context output. -.TP -\fB-C\fP \fInumber\fP, \fB--context=\fP\fInumber\fP -Output \fInumber\fP lines of context both before and after each matching line. -This is equivalent to setting both \fB-A\fP and \fB-B\fP to the same value. -.TP -\fB-c\fP, \fB--count\fP -Do not output individual lines; instead just output a count of the number of -lines that would otherwise have been output. If several files are given, a -count is output for each of them. In this mode, the \fB-A\fP, \fB-B\fP, and -\fB-C\fP options are ignored. -.TP -\fB--colour\fP, \fB--color\fP -If this option is given without any data, it is equivalent to "--colour=auto". -If data is required, it must be given in the same shell item, separated by an -equals sign. -.TP -\fB--colour=\fP\fIvalue\fP, \fB--color=\fP\fIvalue\fP -This option specifies under what circumstances the parts of a line that matched -a pattern should be coloured in the output. By default, the output is not -coloured. The value (which is optional, see above) may be "never", "always", or -"auto". In the latter case, colouring happens only if the standard output is -connected to a terminal. More resources are used when colouring is enabled, -because \fBpcregrep\fP has to search for all possible matches in a line, not -just one, in order to colour them all. - -The colour that is used can be specified by setting the environment variable -PCREGREP_COLOUR or PCREGREP_COLOR. The value of this variable should be a -string of two numbers, separated by a semicolon. They are copied directly into -the control string for setting colour on a terminal, so it is your -responsibility to ensure that they make sense. If neither of the environment -variables is set, the default is "1;31", which gives red. -.TP -\fB-D\fP \fIaction\fP, \fB--devices=\fP\fIaction\fP -If an input path is not a regular file or a directory, "action" specifies how -it is to be processed. Valid values are "read" (the default) or "skip" -(silently skip the path). -.TP -\fB-d\fP \fIaction\fP, \fB--directories=\fP\fIaction\fP -If an input path is a directory, "action" specifies how it is to be processed. -Valid values are "read" (the default), "recurse" (equivalent to the \fB-r\fP -option), or "skip" (silently skip the path). In the default case, directories -are read as if they were ordinary files. In some operating systems the effect -of reading a directory like this is an immediate end-of-file. -.TP -\fB-e\fP \fIpattern\fP, \fB--regex=\fP\fIpattern\fP, \fB--regexp=\fP\fIpattern\fP -Specify a pattern to be matched. This option can be used multiple times in -order to specify several patterns. It can also be used as a way of specifying a -single pattern that starts with a hyphen. When \fB-e\fP is used, no argument -pattern is taken from the command line; all arguments are treated as file -names. There is an overall maximum of 100 patterns. They are applied to each -line in the order in which they are defined until one matches (or fails to -match if \fB-v\fP is used). If \fB-f\fP is used with \fB-e\fP, the command line -patterns are matched first, followed by the patterns from the file, independent -of the order in which these options are specified. Note that multiple use of -\fB-e\fP is not the same as a single pattern with alternatives. For example, -X|Y finds the first character in a line that is X or Y, whereas if the two -patterns are given separately, \fBpcregrep\fP finds X if it is present, even if -it follows Y in the line. It finds Y only if there is no X in the line. This -really matters only if you are using \fB-o\fP to show the part(s) of the line -that matched. -.TP -\fB--exclude\fP=\fIpattern\fP -When \fBpcregrep\fP is searching the files in a directory as a consequence of -the \fB-r\fP (recursive search) option, any regular files whose names match the -pattern are excluded. Subdirectories are not excluded by this option; they are -searched recursively, subject to the \fB--exclude_dir\fP and -\fB--include_dir\fP options. The pattern is a PCRE regular expression, and is -matched against the final component of the file name (not the entire path). If -a file name matches both \fB--include\fP and \fB--exclude\fP, it is excluded. -There is no short form for this option. -.TP -\fB--exclude_dir\fP=\fIpattern\fP -When \fBpcregrep\fP is searching the contents of a directory as a consequence -of the \fB-r\fP (recursive search) option, any subdirectories whose names match -the pattern are excluded. (Note that the \fP--exclude\fP option does not affect -subdirectories.) The pattern is a PCRE regular expression, and is matched -against the final component of the name (not the entire path). If a -subdirectory name matches both \fB--include_dir\fP and \fB--exclude_dir\fP, it -is excluded. There is no short form for this option. -.TP -\fB-F\fP, \fB--fixed-strings\fP -Interpret each pattern as a list of fixed strings, separated by newlines, -instead of as a regular expression. The \fB-w\fP (match as a word) and \fB-x\fP -(match whole line) options can be used with \fB-F\fP. They apply to each of the -fixed strings. A line is selected if any of the fixed strings are found in it -(subject to \fB-w\fP or \fB-x\fP, if present). -.TP -\fB-f\fP \fIfilename\fP, \fB--file=\fP\fIfilename\fP -Read a number of patterns from the file, one per line, and match them against -each line of input. A data line is output if any of the patterns match it. The -filename can be given as "-" to refer to the standard input. When \fB-f\fP is -used, patterns specified on the command line using \fB-e\fP may also be -present; they are tested before the file's patterns. However, no other pattern -is taken from the command line; all arguments are treated as file names. There -is an overall maximum of 100 patterns. Trailing white space is removed from -each line, and blank lines are ignored. An empty file contains no patterns and -therefore matches nothing. See also the comments about multiple patterns versus -a single pattern with alternatives in the description of \fB-e\fP above. -.TP -\fB--file-offsets\fP -Instead of showing lines or parts of lines that match, show each match as an -offset from the start of the file and a length, separated by a comma. In this -mode, no context is shown. That is, the \fB-A\fP, \fB-B\fP, and \fB-C\fP -options are ignored. If there is more than one match in a line, each of them is -shown separately. This option is mutually exclusive with \fB--line-offsets\fP -and \fB--only-matching\fP. -.TP -\fB-H\fP, \fB--with-filename\fP -Force the inclusion of the filename at the start of output lines when searching -a single file. By default, the filename is not shown in this case. For matching -lines, the filename is followed by a colon; for context lines, a hyphen -separator is used. If a line number is also being output, it follows the file -name. -.TP -\fB-h\fP, \fB--no-filename\fP -Suppress the output filenames when searching multiple files. By default, -filenames are shown when multiple files are searched. For matching lines, the -filename is followed by a colon; for context lines, a hyphen separator is used. -If a line number is also being output, it follows the file name. -.TP -\fB--help\fP -Output a help message, giving brief details of the command options and file -type support, and then exit. -.TP -\fB-i\fP, \fB--ignore-case\fP -Ignore upper/lower case distinctions during comparisons. -.TP -\fB--include\fP=\fIpattern\fP -When \fBpcregrep\fP is searching the files in a directory as a consequence of -the \fB-r\fP (recursive search) option, only those regular files whose names -match the pattern are included. Subdirectories are always included and searched -recursively, subject to the \fP--include_dir\fP and \fB--exclude_dir\fP -options. The pattern is a PCRE regular expression, and is matched against the -final component of the file name (not the entire path). If a file name matches -both \fB--include\fP and \fB--exclude\fP, it is excluded. There is no short -form for this option. -.TP -\fB--include_dir\fP=\fIpattern\fP -When \fBpcregrep\fP is searching the contents of a directory as a consequence -of the \fB-r\fP (recursive search) option, only those subdirectories whose -names match the pattern are included. (Note that the \fB--include\fP option -does not affect subdirectories.) The pattern is a PCRE regular expression, and -is matched against the final component of the name (not the entire path). If a -subdirectory name matches both \fB--include_dir\fP and \fB--exclude_dir\fP, it -is excluded. There is no short form for this option. -.TP -\fB-L\fP, \fB--files-without-match\fP -Instead of outputting lines from the files, just output the names of the files -that do not contain any lines that would have been output. Each file name is -output once, on a separate line. -.TP -\fB-l\fP, \fB--files-with-matches\fP -Instead of outputting lines from the files, just output the names of the files -containing lines that would have been output. Each file name is output -once, on a separate line. Searching stops as soon as a matching line is found -in a file. -.TP -\fB--label\fP=\fIname\fP -This option supplies a name to be used for the standard input when file names -are being output. If not supplied, "(standard input)" is used. There is no -short form for this option. -.TP -\fB--line-offsets\fP -Instead of showing lines or parts of lines that match, show each match as a -line number, the offset from the start of the line, and a length. The line -number is terminated by a colon (as usual; see the \fB-n\fP option), and the -offset and length are separated by a comma. In this mode, no context is shown. -That is, the \fB-A\fP, \fB-B\fP, and \fB-C\fP options are ignored. If there is -more than one match in a line, each of them is shown separately. This option is -mutually exclusive with \fB--file-offsets\fP and \fB--only-matching\fP. -.TP -\fB--locale\fP=\fIlocale-name\fP -This option specifies a locale to be used for pattern matching. It overrides -the value in the \fBLC_ALL\fP or \fBLC_CTYPE\fP environment variables. If no -locale is specified, the PCRE library's default (usually the "C" locale) is -used. There is no short form for this option. -.TP -\fB-M\fP, \fB--multiline\fP -Allow patterns to match more than one line. When this option is given, patterns -may usefully contain literal newline characters and internal occurrences of ^ -and $ characters. The output for any one match may consist of more than one -line. When this option is set, the PCRE library is called in "multiline" mode. -There is a limit to the number of lines that can be matched, imposed by the way -that \fBpcregrep\fP buffers the input file as it scans it. However, -\fBpcregrep\fP ensures that at least 8K characters or the rest of the document -(whichever is the shorter) are available for forward matching, and similarly -the previous 8K characters (or all the previous characters, if fewer than 8K) -are guaranteed to be available for lookbehind assertions. -.TP -\fB-N\fP \fInewline-type\fP, \fB--newline=\fP\fInewline-type\fP -The PCRE library supports five different conventions for indicating -the ends of lines. They are the single-character sequences CR (carriage return) -and LF (linefeed), the two-character sequence CRLF, an "anycrlf" convention, -which recognizes any of the preceding three types, and an "any" convention, in -which any Unicode line ending sequence is assumed to end a line. The Unicode -sequences are the three just mentioned, plus VT (vertical tab, U+000B), FF -(formfeed, U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and -PS (paragraph separator, U+2029). -.sp -When the PCRE library is built, a default line-ending sequence is specified. -This is normally the standard sequence for the operating system. Unless -otherwise specified by this option, \fBpcregrep\fP uses the library's default. -The possible values for this option are CR, LF, CRLF, ANYCRLF, or ANY. This -makes it possible to use \fBpcregrep\fP on files that have come from other -environments without having to modify their line endings. If the data that is -being scanned does not agree with the convention set by this option, -\fBpcregrep\fP may behave in strange ways. -.TP -\fB-n\fP, \fB--line-number\fP -Precede each output line by its line number in the file, followed by a colon -for matching lines or a hyphen for context lines. If the filename is also being -output, it precedes the line number. This option is forced if -\fB--line-offsets\fP is used. -.TP -\fB-o\fP, \fB--only-matching\fP -Show only the part of the line that matched a pattern. In this mode, no -context is shown. That is, the \fB-A\fP, \fB-B\fP, and \fB-C\fP options are -ignored. If there is more than one match in a line, each of them is shown -separately. If \fB-o\fP is combined with \fB-v\fP (invert the sense of the -match to find non-matching lines), no output is generated, but the return code -is set appropriately. This option is mutually exclusive with -\fB--file-offsets\fP and \fB--line-offsets\fP. -.TP -\fB-q\fP, \fB--quiet\fP -Work quietly, that is, display nothing except error messages. The exit -status indicates whether or not any matches were found. -.TP -\fB-r\fP, \fB--recursive\fP -If any given path is a directory, recursively scan the files it contains, -taking note of any \fB--include\fP and \fB--exclude\fP settings. By default, a -directory is read as a normal file; in some operating systems this gives an -immediate end-of-file. This option is a shorthand for setting the \fB-d\fP -option to "recurse". -.TP -\fB-s\fP, \fB--no-messages\fP -Suppress error messages about non-existent or unreadable files. Such files are -quietly skipped. However, the return code is still 2, even if matches were -found in other files. -.TP -\fB-u\fP, \fB--utf-8\fP -Operate in UTF-8 mode. This option is available only if PCRE has been compiled -with UTF-8 support. Both patterns and subject lines must be valid strings of -UTF-8 characters. -.TP -\fB-V\fP, \fB--version\fP -Write the version numbers of \fBpcregrep\fP and the PCRE library that is being -used to the standard error stream. -.TP -\fB-v\fP, \fB--invert-match\fP -Invert the sense of the match, so that lines which do \fInot\fP match any of -the patterns are the ones that are found. -.TP -\fB-w\fP, \fB--word-regex\fP, \fB--word-regexp\fP -Force the patterns to match only whole words. This is equivalent to having \eb -at the start and end of the pattern. -.TP -\fB-x\fP, \fB--line-regex\fP, \fB--line-regexp\fP -Force the patterns to be anchored (each must start matching at the beginning of -a line) and in addition, require them to match entire lines. This is -equivalent to having ^ and $ characters at the start and end of each -alternative branch in every pattern. -. -. -.SH "ENVIRONMENT VARIABLES" -.rs -.sp -The environment variables \fBLC_ALL\fP and \fBLC_CTYPE\fP are examined, in that -order, for a locale. The first one that is set is used. This can be overridden -by the \fB--locale\fP option. If no locale is set, the PCRE library's default -(usually the "C" locale) is used. -. -. -.SH "NEWLINES" -.rs -.sp -The \fB-N\fP (\fB--newline\fP) option allows \fBpcregrep\fP to scan files with -different newline conventions from the default. However, the setting of this -option does not affect the way in which \fBpcregrep\fP writes information to -the standard error and output streams. It uses the string "\en" in C -\fBprintf()\fP calls to indicate newlines, relying on the C I/O library to -convert this to an appropriate sequence if the output is sent to a file. -. -. -.SH "OPTIONS COMPATIBILITY" -.rs -.sp -The majority of short and long forms of \fBpcregrep\fP's options are the same -as in the GNU \fBgrep\fP program. Any long option of the form -\fB--xxx-regexp\fP (GNU terminology) is also available as \fB--xxx-regex\fP -(PCRE terminology). However, the \fB--locale\fP, \fB-M\fP, \fB--multiline\fP, -\fB-u\fP, and \fB--utf-8\fP options are specific to \fBpcregrep\fP. -. -. -.SH "OPTIONS WITH DATA" -.rs -.sp -There are four different ways in which an option with data can be specified. -If a short form option is used, the data may follow immediately, or in the next -command line item. For example: -.sp - -f/some/file - -f /some/file -.sp -If a long form option is used, the data may appear in the same command line -item, separated by an equals character, or (with one exception) it may appear -in the next command line item. For example: -.sp - --file=/some/file - --file /some/file -.sp -Note, however, that if you want to supply a file name beginning with ~ as data -in a shell command, and have the shell expand ~ to a home directory, you must -separate the file name from the option, because the shell does not treat ~ -specially unless it is at the start of an item. -.P -The exception to the above is the \fB--colour\fP (or \fB--color\fP) option, -for which the data is optional. If this option does have data, it must be given -in the first form, using an equals character. Otherwise it will be assumed that -it has no data. -. -. -.SH "MATCHING ERRORS" -.rs -.sp -It is possible to supply a regular expression that takes a very long time to -fail to match certain lines. Such patterns normally involve nested indefinite -repeats, for example: (a+)*\ed when matched against a line of a's with no final -digit. The PCRE matching function has a resource limit that causes it to abort -in these circumstances. If this happens, \fBpcregrep\fP outputs an error -message and the line that caused the problem to the standard error stream. If -there are more than 20 such errors, \fBpcregrep\fP gives up. -. -. -.SH DIAGNOSTICS -.rs -.sp -Exit status is 0 if any matches were found, 1 if no matches were found, and 2 -for syntax errors and non-existent or inacessible files (even if matches were -found in other files) or too many matching errors. Using the \fB-s\fP option to -suppress error messages about inaccessble files does not affect the return -code. -. -. -.SH "SEE ALSO" -.rs -.sp -\fBpcrepattern\fP(3), \fBpcretest\fP(1). -. -. -.SH AUTHOR -.rs -.sp -.nf -Philip Hazel -University Computing Service -Cambridge CB2 3QH, England. -.fi -. -. -.SH REVISION -.rs -.sp -.nf -Last updated: 01 March 2009 -Copyright (c) 1997-2009 University of Cambridge. -.fi diff --git a/libs/pcre/doc/pcregrep.txt b/libs/pcre/doc/pcregrep.txt deleted file mode 100644 index 0163d58060..0000000000 --- a/libs/pcre/doc/pcregrep.txt +++ /dev/null @@ -1,512 +0,0 @@ -PCREGREP(1) PCREGREP(1) - - -NAME - pcregrep - a grep with Perl-compatible regular expressions. - - -SYNOPSIS - pcregrep [options] [long options] [pattern] [path1 path2 ...] - - -DESCRIPTION - - pcregrep searches files for character patterns, in the same way as - other grep commands do, but it uses the PCRE regular expression library - to support patterns that are compatible with the regular expressions of - Perl 5. See pcrepattern(3) for a full description of syntax and seman- - tics of the regular expressions that PCRE supports. - - Patterns, whether supplied on the command line or in a separate file, - are given without delimiters. For example: - - pcregrep Thursday /etc/motd - - If you attempt to use delimiters (for example, by surrounding a pattern - with slashes, as is common in Perl scripts), they are interpreted as - part of the pattern. Quotes can of course be used to delimit patterns - on the command line because they are interpreted by the shell, and - indeed they are required if a pattern contains white space or shell - metacharacters. - - The first argument that follows any option settings is treated as the - single pattern to be matched when neither -e nor -f is present. Con- - versely, when one or both of these options are used to specify pat- - terns, all arguments are treated as path names. At least one of -e, -f, - or an argument pattern must be provided. - - If no files are specified, pcregrep reads the standard input. The stan- - dard input can also be referenced by a name consisting of a single - hyphen. For example: - - pcregrep some-pattern /file1 - /file3 - - By default, each line that matches a pattern is copied to the standard - output, and if there is more than one file, the file name is output at - the start of each line, followed by a colon. However, there are options - that can change how pcregrep behaves. In particular, the -M option - makes it possible to search for patterns that span line boundaries. - What defines a line boundary is controlled by the -N (--newline) - option. - - Patterns are limited to 8K or BUFSIZ characters, whichever is the - greater. BUFSIZ is defined in . When there is more than one - pattern (specified by the use of -e and/or -f), each pattern is applied - to each line in the order in which they are defined, except that all - the -e patterns are tried before the -f patterns. - - By default, as soon as one pattern matches (or fails to match when -v - is used), no further patterns are considered. However, if --colour (or - --color) is used to colour the matching substrings, or if --only-match- - ing, --file-offsets, or --line-offsets is used to output only the part - of the line that matched (either shown literally, or as an offset), - scanning resumes immediately following the match, so that further - matches on the same line can be found. If there are multiple patterns, - they are all tried on the remainder of the line, but patterns that fol- - low the one that matched are not tried on the earlier part of the line. - - This is the same behaviour as GNU grep, but it does mean that the order - in which multiple patterns are specified can affect the output when one - of the above options is used. - - Patterns that can match an empty string are accepted, but empty string - matches are not recognized. An example is the pattern "(super)?(man)?", - in which all components are optional. This pattern finds all occur- - rences of both "super" and "man"; the output differs from matching with - "super|man" when only the matching substrings are being shown. - - If the LC_ALL or LC_CTYPE environment variable is set, pcregrep uses - the value to set a locale when calling the PCRE library. The --locale - option can be used to override this. - - -SUPPORT FOR COMPRESSED FILES - - It is possible to compile pcregrep so that it uses libz or libbz2 to - read files whose names end in .gz or .bz2, respectively. You can find - out whether your binary has support for one or both of these file types - by running it with the --help option. If the appropriate support is not - present, files are treated as plain text. The standard input is always - so treated. - - -OPTIONS - - -- This terminate the list of options. It is useful if the next - item on the command line starts with a hyphen but is not an - option. This allows for the processing of patterns and file- - names that start with hyphens. - - -A number, --after-context=number - Output number lines of context after each matching line. If - filenames and/or line numbers are being output, a hyphen sep- - arator is used instead of a colon for the context lines. A - line containing "--" is output between each group of lines, - unless they are in fact contiguous in the input file. The - value of number is expected to be relatively small. However, - pcregrep guarantees to have up to 8K of following text avail- - able for context output. - - -B number, --before-context=number - Output number lines of context before each matching line. If - filenames and/or line numbers are being output, a hyphen sep- - arator is used instead of a colon for the context lines. A - line containing "--" is output between each group of lines, - unless they are in fact contiguous in the input file. The - value of number is expected to be relatively small. However, - pcregrep guarantees to have up to 8K of preceding text avail- - able for context output. - - -C number, --context=number - Output number lines of context both before and after each - matching line. This is equivalent to setting both -A and -B - to the same value. - - -c, --count - Do not output individual lines; instead just output a count - of the number of lines that would otherwise have been output. - If several files are given, a count is output for each of - them. In this mode, the -A, -B, and -C options are ignored. - - --colour, --color - If this option is given without any data, it is equivalent to - "--colour=auto". If data is required, it must be given in - the same shell item, separated by an equals sign. - - --colour=value, --color=value - This option specifies under what circumstances the parts of a - line that matched a pattern should be coloured in the output. - By default, the output is not coloured. The value (which is - optional, see above) may be "never", "always", or "auto". In - the latter case, colouring happens only if the standard out- - put is connected to a terminal. More resources are used when - colouring is enabled, because pcregrep has to search for all - possible matches in a line, not just one, in order to colour - them all. - - The colour that is used can be specified by setting the envi- - ronment variable PCREGREP_COLOUR or PCREGREP_COLOR. The value - of this variable should be a string of two numbers, separated - by a semicolon. They are copied directly into the control - string for setting colour on a terminal, so it is your - responsibility to ensure that they make sense. If neither of - the environment variables is set, the default is "1;31", - which gives red. - - -D action, --devices=action - If an input path is not a regular file or a directory, - "action" specifies how it is to be processed. Valid values - are "read" (the default) or "skip" (silently skip the path). - - -d action, --directories=action - If an input path is a directory, "action" specifies how it is - to be processed. Valid values are "read" (the default), - "recurse" (equivalent to the -r option), or "skip" (silently - skip the path). In the default case, directories are read as - if they were ordinary files. In some operating systems the - effect of reading a directory like this is an immediate end- - of-file. - - -e pattern, --regex=pattern, --regexp=pattern - Specify a pattern to be matched. This option can be used mul- - tiple times in order to specify several patterns. It can also - be used as a way of specifying a single pattern that starts - with a hyphen. When -e is used, no argument pattern is taken - from the command line; all arguments are treated as file - names. There is an overall maximum of 100 patterns. They are - applied to each line in the order in which they are defined - until one matches (or fails to match if -v is used). If -f is - used with -e, the command line patterns are matched first, - followed by the patterns from the file, independent of the - order in which these options are specified. Note that multi- - ple use of -e is not the same as a single pattern with alter- - natives. For example, X|Y finds the first character in a line - that is X or Y, whereas if the two patterns are given sepa- - rately, pcregrep finds X if it is present, even if it follows - Y in the line. It finds Y only if there is no X in the line. - This really matters only if you are using -o to show the - part(s) of the line that matched. - - --exclude=pattern - When pcregrep is searching the files in a directory as a con- - sequence of the -r (recursive search) option, any regular - files whose names match the pattern are excluded. Subdirecto- - ries are not excluded by this option; they are searched - recursively, subject to the --exclude_dir and --include_dir - options. The pattern is a PCRE regular expression, and is - matched against the final component of the file name (not the - entire path). If a file name matches both --include and - --exclude, it is excluded. There is no short form for this - option. - - --exclude_dir=pattern - When pcregrep is searching the contents of a directory as a - consequence of the -r (recursive search) option, any subdi- - rectories whose names match the pattern are excluded. (Note - that the --exclude option does not affect subdirectories.) - The pattern is a PCRE regular expression, and is matched - against the final component of the name (not the entire - path). If a subdirectory name matches both --include_dir and - --exclude_dir, it is excluded. There is no short form for - this option. - - -F, --fixed-strings - Interpret each pattern as a list of fixed strings, separated - by newlines, instead of as a regular expression. The -w - (match as a word) and -x (match whole line) options can be - used with -F. They apply to each of the fixed strings. A line - is selected if any of the fixed strings are found in it (sub- - ject to -w or -x, if present). - - -f filename, --file=filename - Read a number of patterns from the file, one per line, and - match them against each line of input. A data line is output - if any of the patterns match it. The filename can be given as - "-" to refer to the standard input. When -f is used, patterns - specified on the command line using -e may also be present; - they are tested before the file's patterns. However, no other - pattern is taken from the command line; all arguments are - treated as file names. There is an overall maximum of 100 - patterns. Trailing white space is removed from each line, and - blank lines are ignored. An empty file contains no patterns - and therefore matches nothing. See also the comments about - multiple patterns versus a single pattern with alternatives - in the description of -e above. - - --file-offsets - Instead of showing lines or parts of lines that match, show - each match as an offset from the start of the file and a - length, separated by a comma. In this mode, no context is - shown. That is, the -A, -B, and -C options are ignored. If - there is more than one match in a line, each of them is shown - separately. This option is mutually exclusive with --line- - offsets and --only-matching. - - -H, --with-filename - Force the inclusion of the filename at the start of output - lines when searching a single file. By default, the filename - is not shown in this case. For matching lines, the filename - is followed by a colon; for context lines, a hyphen separator - is used. If a line number is also being output, it follows - the file name. - - -h, --no-filename - Suppress the output filenames when searching multiple files. - By default, filenames are shown when multiple files are - searched. For matching lines, the filename is followed by a - colon; for context lines, a hyphen separator is used. If a - line number is also being output, it follows the file name. - - --help Output a help message, giving brief details of the command - options and file type support, and then exit. - - -i, --ignore-case - Ignore upper/lower case distinctions during comparisons. - - --include=pattern - When pcregrep is searching the files in a directory as a con- - sequence of the -r (recursive search) option, only those reg- - ular files whose names match the pattern are included. Subdi- - rectories are always included and searched recursively, sub- - ject to the --include_dir and --exclude_dir options. The pat- - tern is a PCRE regular expression, and is matched against the - final component of the file name (not the entire path). If a - file name matches both --include and --exclude, it is - excluded. There is no short form for this option. - - --include_dir=pattern - When pcregrep is searching the contents of a directory as a - consequence of the -r (recursive search) option, only those - subdirectories whose names match the pattern are included. - (Note that the --include option does not affect subdirecto- - ries.) The pattern is a PCRE regular expression, and is - matched against the final component of the name (not the - entire path). If a subdirectory name matches both - --include_dir and --exclude_dir, it is excluded. There is no - short form for this option. - - -L, --files-without-match - Instead of outputting lines from the files, just output the - names of the files that do not contain any lines that would - have been output. Each file name is output once, on a sepa- - rate line. - - -l, --files-with-matches - Instead of outputting lines from the files, just output the - names of the files containing lines that would have been out- - put. Each file name is output once, on a separate line. - Searching stops as soon as a matching line is found in a - file. - - --label=name - This option supplies a name to be used for the standard input - when file names are being output. If not supplied, "(standard - input)" is used. There is no short form for this option. - - --line-offsets - Instead of showing lines or parts of lines that match, show - each match as a line number, the offset from the start of the - line, and a length. The line number is terminated by a colon - (as usual; see the -n option), and the offset and length are - separated by a comma. In this mode, no context is shown. - That is, the -A, -B, and -C options are ignored. If there is - more than one match in a line, each of them is shown sepa- - rately. This option is mutually exclusive with --file-offsets - and --only-matching. - - --locale=locale-name - This option specifies a locale to be used for pattern match- - ing. It overrides the value in the LC_ALL or LC_CTYPE envi- - ronment variables. If no locale is specified, the PCRE - library's default (usually the "C" locale) is used. There is - no short form for this option. - - -M, --multiline - Allow patterns to match more than one line. When this option - is given, patterns may usefully contain literal newline char- - acters and internal occurrences of ^ and $ characters. The - output for any one match may consist of more than one line. - When this option is set, the PCRE library is called in "mul- - tiline" mode. There is a limit to the number of lines that - can be matched, imposed by the way that pcregrep buffers the - input file as it scans it. However, pcregrep ensures that at - least 8K characters or the rest of the document (whichever is - the shorter) are available for forward matching, and simi- - larly the previous 8K characters (or all the previous charac- - ters, if fewer than 8K) are guaranteed to be available for - lookbehind assertions. - - -N newline-type, --newline=newline-type - The PCRE library supports five different conventions for - indicating the ends of lines. They are the single-character - sequences CR (carriage return) and LF (linefeed), the two- - character sequence CRLF, an "anycrlf" convention, which rec- - ognizes any of the preceding three types, and an "any" con- - vention, in which any Unicode line ending sequence is assumed - to end a line. The Unicode sequences are the three just men- - tioned, plus VT (vertical tab, U+000B), FF (formfeed, - U+000C), NEL (next line, U+0085), LS (line separator, - U+2028), and PS (paragraph separator, U+2029). - - When the PCRE library is built, a default line-ending - sequence is specified. This is normally the standard - sequence for the operating system. Unless otherwise specified - by this option, pcregrep uses the library's default. The - possible values for this option are CR, LF, CRLF, ANYCRLF, or - ANY. This makes it possible to use pcregrep on files that - have come from other environments without having to modify - their line endings. If the data that is being scanned does - not agree with the convention set by this option, pcregrep - may behave in strange ways. - - -n, --line-number - Precede each output line by its line number in the file, fol- - lowed by a colon for matching lines or a hyphen for context - lines. If the filename is also being output, it precedes the - line number. This option is forced if --line-offsets is used. - - -o, --only-matching - Show only the part of the line that matched a pattern. In - this mode, no context is shown. That is, the -A, -B, and -C - options are ignored. If there is more than one match in a - line, each of them is shown separately. If -o is combined - with -v (invert the sense of the match to find non-matching - lines), no output is generated, but the return code is set - appropriately. This option is mutually exclusive with --file- - offsets and --line-offsets. - - -q, --quiet - Work quietly, that is, display nothing except error messages. - The exit status indicates whether or not any matches were - found. - - -r, --recursive - If any given path is a directory, recursively scan the files - it contains, taking note of any --include and --exclude set- - tings. By default, a directory is read as a normal file; in - some operating systems this gives an immediate end-of-file. - This option is a shorthand for setting the -d option to - "recurse". - - -s, --no-messages - Suppress error messages about non-existent or unreadable - files. Such files are quietly skipped. However, the return - code is still 2, even if matches were found in other files. - - -u, --utf-8 - Operate in UTF-8 mode. This option is available only if PCRE - has been compiled with UTF-8 support. Both patterns and sub- - ject lines must be valid strings of UTF-8 characters. - - -V, --version - Write the version numbers of pcregrep and the PCRE library - that is being used to the standard error stream. - - -v, --invert-match - Invert the sense of the match, so that lines which do not - match any of the patterns are the ones that are found. - - -w, --word-regex, --word-regexp - Force the patterns to match only whole words. This is equiva- - lent to having \b at the start and end of the pattern. - - -x, --line-regex, --line-regexp - Force the patterns to be anchored (each must start matching - at the beginning of a line) and in addition, require them to - match entire lines. This is equivalent to having ^ and $ - characters at the start and end of each alternative branch in - every pattern. - - -ENVIRONMENT VARIABLES - - The environment variables LC_ALL and LC_CTYPE are examined, in that - order, for a locale. The first one that is set is used. This can be - overridden by the --locale option. If no locale is set, the PCRE - library's default (usually the "C" locale) is used. - - -NEWLINES - - The -N (--newline) option allows pcregrep to scan files with different - newline conventions from the default. However, the setting of this - option does not affect the way in which pcregrep writes information to - the standard error and output streams. It uses the string "\n" in C - printf() calls to indicate newlines, relying on the C I/O library to - convert this to an appropriate sequence if the output is sent to a - file. - - -OPTIONS COMPATIBILITY - - The majority of short and long forms of pcregrep's options are the same - as in the GNU grep program. Any long option of the form --xxx-regexp - (GNU terminology) is also available as --xxx-regex (PCRE terminology). - However, the --locale, -M, --multiline, -u, and --utf-8 options are - specific to pcregrep. - - -OPTIONS WITH DATA - - There are four different ways in which an option with data can be spec- - ified. If a short form option is used, the data may follow immedi- - ately, or in the next command line item. For example: - - -f/some/file - -f /some/file - - If a long form option is used, the data may appear in the same command - line item, separated by an equals character, or (with one exception) it - may appear in the next command line item. For example: - - --file=/some/file - --file /some/file - - Note, however, that if you want to supply a file name beginning with ~ - as data in a shell command, and have the shell expand ~ to a home - directory, you must separate the file name from the option, because the - shell does not treat ~ specially unless it is at the start of an item. - - The exception to the above is the --colour (or --color) option, for - which the data is optional. If this option does have data, it must be - given in the first form, using an equals character. Otherwise it will - be assumed that it has no data. - - -MATCHING ERRORS - - It is possible to supply a regular expression that takes a very long - time to fail to match certain lines. Such patterns normally involve - nested indefinite repeats, for example: (a+)*\d when matched against a - line of a's with no final digit. The PCRE matching function has a - resource limit that causes it to abort in these circumstances. If this - happens, pcregrep outputs an error message and the line that caused the - problem to the standard error stream. If there are more than 20 such - errors, pcregrep gives up. - - -DIAGNOSTICS - - Exit status is 0 if any matches were found, 1 if no matches were found, - and 2 for syntax errors and non-existent or inacessible files (even if - matches were found in other files) or too many matching errors. Using - the -s option to suppress error messages about inaccessble files does - not affect the return code. - - -SEE ALSO - - pcrepattern(3), pcretest(1). - - -AUTHOR - - Philip Hazel - University Computing Service - Cambridge CB2 3QH, England. - - -REVISION - - Last updated: 01 March 2009 - Copyright (c) 1997-2009 University of Cambridge. diff --git a/libs/pcre/doc/pcrematching.3 b/libs/pcre/doc/pcrematching.3 deleted file mode 100644 index 560a48c022..0000000000 --- a/libs/pcre/doc/pcrematching.3 +++ /dev/null @@ -1,188 +0,0 @@ -.TH PCREMATCHING 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH "PCRE MATCHING ALGORITHMS" -.rs -.sp -This document describes the two different algorithms that are available in PCRE -for matching a compiled regular expression against a given subject string. The -"standard" algorithm is the one provided by the \fBpcre_exec()\fP function. -This works in the same was as Perl's matching function, and provides a -Perl-compatible matching operation. -.P -An alternative algorithm is provided by the \fBpcre_dfa_exec()\fP function; -this operates in a different way, and is not Perl-compatible. It has advantages -and disadvantages compared with the standard algorithm, and these are described -below. -.P -When there is only one possible way in which a given subject string can match a -pattern, the two algorithms give the same answer. A difference arises, however, -when there are multiple possibilities. For example, if the pattern -.sp - ^<.*> -.sp -is matched against the string -.sp - -.sp -there are three possible answers. The standard algorithm finds only one of -them, whereas the alternative algorithm finds all three. -. -.SH "REGULAR EXPRESSIONS AS TREES" -.rs -.sp -The set of strings that are matched by a regular expression can be represented -as a tree structure. An unlimited repetition in the pattern makes the tree of -infinite size, but it is still a tree. Matching the pattern to a given subject -string (from a given starting point) can be thought of as a search of the tree. -There are two ways to search a tree: depth-first and breadth-first, and these -correspond to the two matching algorithms provided by PCRE. -. -.SH "THE STANDARD MATCHING ALGORITHM" -.rs -.sp -In the terminology of Jeffrey Friedl's book "Mastering Regular -Expressions", the standard algorithm is an "NFA algorithm". It conducts a -depth-first search of the pattern tree. That is, it proceeds along a single -path through the tree, checking that the subject matches what is required. When -there is a mismatch, the algorithm tries any alternatives at the current point, -and if they all fail, it backs up to the previous branch point in the tree, and -tries the next alternative branch at that level. This often involves backing up -(moving to the left) in the subject string as well. The order in which -repetition branches are tried is controlled by the greedy or ungreedy nature of -the quantifier. -.P -If a leaf node is reached, a matching string has been found, and at that point -the algorithm stops. Thus, if there is more than one possible match, this -algorithm returns the first one that it finds. Whether this is the shortest, -the longest, or some intermediate length depends on the way the greedy and -ungreedy repetition quantifiers are specified in the pattern. -.P -Because it ends up with a single path through the tree, it is relatively -straightforward for this algorithm to keep track of the substrings that are -matched by portions of the pattern in parentheses. This provides support for -capturing parentheses and back references. -. -.SH "THE ALTERNATIVE MATCHING ALGORITHM" -.rs -.sp -This algorithm conducts a breadth-first search of the tree. Starting from the -first matching point in the subject, it scans the subject string from left to -right, once, character by character, and as it does this, it remembers all the -paths through the tree that represent valid matches. In Friedl's terminology, -this is a kind of "DFA algorithm", though it is not implemented as a -traditional finite state machine (it keeps multiple states active -simultaneously). -.P -The scan continues until either the end of the subject is reached, or there are -no more unterminated paths. At this point, terminated paths represent the -different matching possibilities (if there are none, the match has failed). -Thus, if there is more than one possible match, this algorithm finds all of -them, and in particular, it finds the longest. In PCRE, there is an option to -stop the algorithm after the first match (which is necessarily the shortest) -has been found. -.P -Note that all the matches that are found start at the same point in the -subject. If the pattern -.sp - cat(er(pillar)?) -.sp -is matched against the string "the caterpillar catchment", the result will be -the three strings "cat", "cater", and "caterpillar" that start at the fourth -character of the subject. The algorithm does not automatically move on to find -matches that start at later positions. -.P -There are a number of features of PCRE regular expressions that are not -supported by the alternative matching algorithm. They are as follows: -.P -1. Because the algorithm finds all possible matches, the greedy or ungreedy -nature of repetition quantifiers is not relevant. Greedy and ungreedy -quantifiers are treated in exactly the same way. However, possessive -quantifiers can make a difference when what follows could also match what is -quantified, for example in a pattern like this: -.sp - ^a++\ew! -.sp -This pattern matches "aaab!" but not "aaa!", which would be matched by a -non-possessive quantifier. Similarly, if an atomic group is present, it is -matched as if it were a standalone pattern at the current point, and the -longest match is then "locked in" for the rest of the overall pattern. -.P -2. When dealing with multiple paths through the tree simultaneously, it is not -straightforward to keep track of captured substrings for the different matching -possibilities, and PCRE's implementation of this algorithm does not attempt to -do this. This means that no captured substrings are available. -.P -3. Because no substrings are captured, back references within the pattern are -not supported, and cause errors if encountered. -.P -4. For the same reason, conditional expressions that use a backreference as the -condition or test for a specific group recursion are not supported. -.P -5. Because many paths through the tree may be active, the \eK escape sequence, -which resets the start of the match when encountered (but may be on some paths -and not on others), is not supported. It causes an error if encountered. -.P -6. Callouts are supported, but the value of the \fIcapture_top\fP field is -always 1, and the value of the \fIcapture_last\fP field is always -1. -.P -7. The \eC escape sequence, which (in the standard algorithm) matches a single -byte, even in UTF-8 mode, is not supported because the alternative algorithm -moves through the subject string one character at a time, for all active paths -through the tree. -.P -8. Except for (*FAIL), the backtracking control verbs such as (*PRUNE) are not -supported. (*FAIL) is supported, and behaves like a failing negative assertion. -. -.SH "ADVANTAGES OF THE ALTERNATIVE ALGORITHM" -.rs -.sp -Using the alternative matching algorithm provides the following advantages: -.P -1. All possible matches (at a single point in the subject) are automatically -found, and in particular, the longest match is found. To find more than one -match using the standard algorithm, you have to do kludgy things with -callouts. -.P -2. There is much better support for partial matching. The restrictions on the -content of the pattern that apply when using the standard algorithm for partial -matching do not apply to the alternative algorithm. For non-anchored patterns, -the starting position of a partial match is available. -.P -3. Because the alternative algorithm scans the subject string just once, and -never needs to backtrack, it is possible to pass very long subject strings to -the matching function in several pieces, checking for partial matching each -time. -. -.SH "DISADVANTAGES OF THE ALTERNATIVE ALGORITHM" -.rs -.sp -The alternative algorithm suffers from a number of disadvantages: -.P -1. It is substantially slower than the standard algorithm. This is partly -because it has to search for all possible matches, but is also because it is -less susceptible to optimization. -.P -2. Capturing parentheses and back references are not supported. -.P -3. Although atomic groups are supported, their use does not provide the -performance advantage that it does for the standard algorithm. -. -. -.SH AUTHOR -.rs -.sp -.nf -Philip Hazel -University Computing Service -Cambridge CB2 3QH, England. -.fi -. -. -.SH REVISION -.rs -.sp -.nf -Last updated: 19 April 2008 -Copyright (c) 1997-2008 University of Cambridge. -.fi diff --git a/libs/pcre/doc/pcrepartial.3 b/libs/pcre/doc/pcrepartial.3 deleted file mode 100644 index e418734073..0000000000 --- a/libs/pcre/doc/pcrepartial.3 +++ /dev/null @@ -1,219 +0,0 @@ -.TH PCREPARTIAL 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH "PARTIAL MATCHING IN PCRE" -.rs -.sp -In normal use of PCRE, if the subject string that is passed to -\fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP matches as far as it goes, but is -too short to match the entire pattern, PCRE_ERROR_NOMATCH is returned. There -are circumstances where it might be helpful to distinguish this case from other -cases in which there is no match. -.P -Consider, for example, an application where a human is required to type in data -for a field with specific formatting requirements. An example might be a date -in the form \fIddmmmyy\fP, defined by this pattern: -.sp - ^\ed?\ed(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\ed\ed$ -.sp -If the application sees the user's keystrokes one by one, and can check that -what has been typed so far is potentially valid, it is able to raise an error -as soon as a mistake is made, possibly beeping and not reflecting the -character that has been typed. This immediate feedback is likely to be a better -user interface than a check that is delayed until the entire string has been -entered. -.P -PCRE supports the concept of partial matching by means of the PCRE_PARTIAL -option, which can be set when calling \fBpcre_exec()\fP or -\fBpcre_dfa_exec()\fP. When this flag is set for \fBpcre_exec()\fP, the return -code PCRE_ERROR_NOMATCH is converted into PCRE_ERROR_PARTIAL if at any time -during the matching process the last part of the subject string matched part of -the pattern. Unfortunately, for non-anchored matching, it is not possible to -obtain the position of the start of the partial match. No captured data is set -when PCRE_ERROR_PARTIAL is returned. -.P -When PCRE_PARTIAL is set for \fBpcre_dfa_exec()\fP, the return code -PCRE_ERROR_NOMATCH is converted into PCRE_ERROR_PARTIAL if the end of the -subject is reached, there have been no complete matches, but there is still at -least one matching possibility. The portion of the string that provided the -partial match is set as the first matching string. -.P -Using PCRE_PARTIAL disables one of PCRE's optimizations. PCRE remembers the -last literal byte in a pattern, and abandons matching immediately if such a -byte is not present in the subject string. This optimization cannot be used -for a subject string that might match only partially. -. -. -.SH "RESTRICTED PATTERNS FOR PCRE_PARTIAL" -.rs -.sp -Because of the way certain internal optimizations are implemented in the -\fBpcre_exec()\fP function, the PCRE_PARTIAL option cannot be used with all -patterns. These restrictions do not apply when \fBpcre_dfa_exec()\fP is used. -For \fBpcre_exec()\fP, repeated single characters such as -.sp - a{2,4} -.sp -and repeated single metasequences such as -.sp - \ed+ -.sp -are not permitted if the maximum number of occurrences is greater than one. -Optional items such as \ed? (where the maximum is one) are permitted. -Quantifiers with any values are permitted after parentheses, so the invalid -examples above can be coded thus: -.sp - (a){2,4} - (\ed)+ -.sp -These constructions run more slowly, but for the kinds of application that are -envisaged for this facility, this is not felt to be a major restriction. -.P -If PCRE_PARTIAL is set for a pattern that does not conform to the restrictions, -\fBpcre_exec()\fP returns the error code PCRE_ERROR_BADPARTIAL (-13). -You can use the PCRE_INFO_OKPARTIAL call to \fBpcre_fullinfo()\fP to find out -if a compiled pattern can be used for partial matching. -. -. -.SH "EXAMPLE OF PARTIAL MATCHING USING PCRETEST" -.rs -.sp -If the escape sequence \eP is present in a \fBpcretest\fP data line, the -PCRE_PARTIAL flag is used for the match. Here is a run of \fBpcretest\fP that -uses the date example quoted above: -.sp - re> /^\ed?\ed(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\ed\ed$/ - data> 25jun04\eP - 0: 25jun04 - 1: jun - data> 25dec3\eP - Partial match - data> 3ju\eP - Partial match - data> 3juj\eP - No match - data> j\eP - No match -.sp -The first data string is matched completely, so \fBpcretest\fP shows the -matched substrings. The remaining four strings do not match the complete -pattern, but the first two are partial matches. The same test, using -\fBpcre_dfa_exec()\fP matching (by means of the \eD escape sequence), produces -the following output: -.sp - re> /^\ed?\ed(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\ed\ed$/ - data> 25jun04\eP\eD - 0: 25jun04 - data> 23dec3\eP\eD - Partial match: 23dec3 - data> 3ju\eP\eD - Partial match: 3ju - data> 3juj\eP\eD - No match - data> j\eP\eD - No match -.sp -Notice that in this case the portion of the string that was matched is made -available. -. -. -.SH "MULTI-SEGMENT MATCHING WITH pcre_dfa_exec()" -.rs -.sp -When a partial match has been found using \fBpcre_dfa_exec()\fP, it is possible -to continue the match by providing additional subject data and calling -\fBpcre_dfa_exec()\fP again with the same compiled regular expression, this -time setting the PCRE_DFA_RESTART option. You must also pass the same working -space as before, because this is where details of the previous partial match -are stored. Here is an example using \fBpcretest\fP, using the \eR escape -sequence to set the PCRE_DFA_RESTART option (\eP and \eD are as above): -.sp - re> /^\ed?\ed(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\ed\ed$/ - data> 23ja\eP\eD - Partial match: 23ja - data> n05\eR\eD - 0: n05 -.sp -The first call has "23ja" as the subject, and requests partial matching; the -second call has "n05" as the subject for the continued (restarted) match. -Notice that when the match is complete, only the last part is shown; PCRE does -not retain the previously partially-matched string. It is up to the calling -program to do that if it needs to. -.P -You can set PCRE_PARTIAL with PCRE_DFA_RESTART to continue partial matching -over multiple segments. This facility can be used to pass very long subject -strings to \fBpcre_dfa_exec()\fP. However, some care is needed for certain -types of pattern. -.P -1. If the pattern contains tests for the beginning or end of a line, you need -to pass the PCRE_NOTBOL or PCRE_NOTEOL options, as appropriate, when the -subject string for any call does not contain the beginning or end of a line. -.P -2. If the pattern contains backward assertions (including \eb or \eB), you need -to arrange for some overlap in the subject strings to allow for this. For -example, you could pass the subject in chunks that are 500 bytes long, but in -a buffer of 700 bytes, with the starting offset set to 200 and the previous 200 -bytes at the start of the buffer. -.P -3. Matching a subject string that is split into multiple segments does not -always produce exactly the same result as matching over one single long string. -The difference arises when there are multiple matching possibilities, because a -partial match result is given only when there are no completed matches in a -call to \fBpcre_dfa_exec()\fP. This means that as soon as the shortest match has -been found, continuation to a new subject segment is no longer possible. -Consider this \fBpcretest\fP example: -.sp - re> /dog(sbody)?/ - data> do\eP\eD - Partial match: do - data> gsb\eR\eP\eD - 0: g - data> dogsbody\eD - 0: dogsbody - 1: dog -.sp -The pattern matches the words "dog" or "dogsbody". When the subject is -presented in several parts ("do" and "gsb" being the first two) the match stops -when "dog" has been found, and it is not possible to continue. On the other -hand, if "dogsbody" is presented as a single string, both matches are found. -.P -Because of this phenomenon, it does not usually make sense to end a pattern -that is going to be matched in this way with a variable repeat. -.P -4. Patterns that contain alternatives at the top level which do not all -start with the same pattern item may not work as expected. For example, -consider this pattern: -.sp - 1234|3789 -.sp -If the first part of the subject is "ABC123", a partial match of the first -alternative is found at offset 3. There is no partial match for the second -alternative, because such a match does not start at the same point in the -subject string. Attempting to continue with the string "789" does not yield a -match because only those alternatives that match at one point in the subject -are remembered. The problem arises because the start of the second alternative -matches within the first alternative. There is no problem with anchored -patterns or patterns such as: -.sp - 1234|ABCD -.sp -where no string can be a partial match for both alternatives. -. -. -.SH AUTHOR -.rs -.sp -.nf -Philip Hazel -University Computing Service -Cambridge CB2 3QH, England. -.fi -. -. -.SH REVISION -.rs -.sp -.nf -Last updated: 04 June 2007 -Copyright (c) 1997-2007 University of Cambridge. -.fi diff --git a/libs/pcre/doc/pcrepattern.3 b/libs/pcre/doc/pcrepattern.3 deleted file mode 100644 index c6ea30a94a..0000000000 --- a/libs/pcre/doc/pcrepattern.3 +++ /dev/null @@ -1,2259 +0,0 @@ -.TH PCREPATTERN 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH "PCRE REGULAR EXPRESSION DETAILS" -.rs -.sp -The syntax and semantics of the regular expressions that are supported by PCRE -are described in detail below. There is a quick-reference syntax summary in the -.\" HREF -\fBpcresyntax\fP -.\" -page. PCRE tries to match Perl syntax and semantics as closely as it can. PCRE -also supports some alternative regular expression syntax (which does not -conflict with the Perl syntax) in order to provide some compatibility with -regular expressions in Python, .NET, and Oniguruma. -.P -Perl's regular expressions are described in its own documentation, and -regular expressions in general are covered in a number of books, some of which -have copious examples. Jeffrey Friedl's "Mastering Regular Expressions", -published by O'Reilly, covers regular expressions in great detail. This -description of PCRE's regular expressions is intended as reference material. -.P -The original operation of PCRE was on strings of one-byte characters. However, -there is now also support for UTF-8 character strings. To use this, you must -build PCRE to include UTF-8 support, and then call \fBpcre_compile()\fP with -the PCRE_UTF8 option. There is also a special sequence that can be given at the -start of a pattern: -.sp - (*UTF8) -.sp -Starting a pattern with this sequence is equivalent to setting the PCRE_UTF8 -option. This feature is not Perl-compatible. How setting UTF-8 mode affects -pattern matching is mentioned in several places below. There is also a summary -of UTF-8 features in the -.\" HTML -.\" -section on UTF-8 support -.\" -in the main -.\" HREF -\fBpcre\fP -.\" -page. -.P -The remainder of this document discusses the patterns that are supported by -PCRE when its main matching function, \fBpcre_exec()\fP, is used. -From release 6.0, PCRE offers a second matching function, -\fBpcre_dfa_exec()\fP, which matches using a different algorithm that is not -Perl-compatible. Some of the features discussed below are not available when -\fBpcre_dfa_exec()\fP is used. The advantages and disadvantages of the -alternative function, and how it differs from the normal function, are -discussed in the -.\" HREF -\fBpcrematching\fP -.\" -page. -. -. -.SH "NEWLINE CONVENTIONS" -.rs -.sp -PCRE supports five different conventions for indicating line breaks in -strings: a single CR (carriage return) character, a single LF (linefeed) -character, the two-character sequence CRLF, any of the three preceding, or any -Unicode newline sequence. The -.\" HREF -\fBpcreapi\fP -.\" -page has -.\" HTML -.\" -further discussion -.\" -about newlines, and shows how to set the newline convention in the -\fIoptions\fP arguments for the compiling and matching functions. -.P -It is also possible to specify a newline convention by starting a pattern -string with one of the following five sequences: -.sp - (*CR) carriage return - (*LF) linefeed - (*CRLF) carriage return, followed by linefeed - (*ANYCRLF) any of the three above - (*ANY) all Unicode newline sequences -.sp -These override the default and the options given to \fBpcre_compile()\fP. For -example, on a Unix system where LF is the default newline sequence, the pattern -.sp - (*CR)a.b -.sp -changes the convention to CR. That pattern matches "a\enb" because LF is no -longer a newline. Note that these special settings, which are not -Perl-compatible, are recognized only at the very start of a pattern, and that -they must be in upper case. If more than one of them is present, the last one -is used. -.P -The newline convention does not affect what the \eR escape sequence matches. By -default, this is any Unicode newline sequence, for Perl compatibility. However, -this can be changed; see the description of \eR in the section entitled -.\" HTML -.\" -"Newline sequences" -.\" -below. A change of \eR setting can be combined with a change of newline -convention. -. -. -.SH "CHARACTERS AND METACHARACTERS" -.rs -.sp -A regular expression is a pattern that is matched against a subject string from -left to right. Most characters stand for themselves in a pattern, and match the -corresponding characters in the subject. As a trivial example, the pattern -.sp - The quick brown fox -.sp -matches a portion of a subject string that is identical to itself. When -caseless matching is specified (the PCRE_CASELESS option), letters are matched -independently of case. In UTF-8 mode, PCRE always understands the concept of -case for characters whose values are less than 128, so caseless matching is -always possible. For characters with higher values, the concept of case is -supported if PCRE is compiled with Unicode property support, but not otherwise. -If you want to use caseless matching for characters 128 and above, you must -ensure that PCRE is compiled with Unicode property support as well as with -UTF-8 support. -.P -The power of regular expressions comes from the ability to include alternatives -and repetitions in the pattern. These are encoded in the pattern by the use of -\fImetacharacters\fP, which do not stand for themselves but instead are -interpreted in some special way. -.P -There are two different sets of metacharacters: those that are recognized -anywhere in the pattern except within square brackets, and those that are -recognized within square brackets. Outside square brackets, the metacharacters -are as follows: -.sp - \e general escape character with several uses - ^ assert start of string (or line, in multiline mode) - $ assert end of string (or line, in multiline mode) - . match any character except newline (by default) - [ start character class definition - | start of alternative branch - ( start subpattern - ) end subpattern - ? extends the meaning of ( - also 0 or 1 quantifier - also quantifier minimizer - * 0 or more quantifier - + 1 or more quantifier - also "possessive quantifier" - { start min/max quantifier -.sp -Part of a pattern that is in square brackets is called a "character class". In -a character class the only metacharacters are: -.sp - \e general escape character - ^ negate the class, but only if the first character - - indicates character range -.\" JOIN - [ POSIX character class (only if followed by POSIX - syntax) - ] terminates the character class -.sp -The following sections describe the use of each of the metacharacters. -. -. -.SH BACKSLASH -.rs -.sp -The backslash character has several uses. Firstly, if it is followed by a -non-alphanumeric character, it takes away any special meaning that character -may have. This use of backslash as an escape character applies both inside and -outside character classes. -.P -For example, if you want to match a * character, you write \e* in the pattern. -This escaping action applies whether or not the following character would -otherwise be interpreted as a metacharacter, so it is always safe to precede a -non-alphanumeric with backslash to specify that it stands for itself. In -particular, if you want to match a backslash, you write \e\e. -.P -If a pattern is compiled with the PCRE_EXTENDED option, whitespace in the -pattern (other than in a character class) and characters between a # outside -a character class and the next newline are ignored. An escaping backslash can -be used to include a whitespace or # character as part of the pattern. -.P -If you want to remove the special meaning from a sequence of characters, you -can do so by putting them between \eQ and \eE. This is different from Perl in -that $ and @ are handled as literals in \eQ...\eE sequences in PCRE, whereas in -Perl, $ and @ cause variable interpolation. Note the following examples: -.sp - Pattern PCRE matches Perl matches -.sp -.\" JOIN - \eQabc$xyz\eE abc$xyz abc followed by the - contents of $xyz - \eQabc\e$xyz\eE abc\e$xyz abc\e$xyz - \eQabc\eE\e$\eQxyz\eE abc$xyz abc$xyz -.sp -The \eQ...\eE sequence is recognized both inside and outside character classes. -. -. -.\" HTML -.SS "Non-printing characters" -.rs -.sp -A second use of backslash provides a way of encoding non-printing characters -in patterns in a visible manner. There is no restriction on the appearance of -non-printing characters, apart from the binary zero that terminates a pattern, -but when a pattern is being prepared by text editing, it is usually easier to -use one of the following escape sequences than the binary character it -represents: -.sp - \ea alarm, that is, the BEL character (hex 07) - \ecx "control-x", where x is any character - \ee escape (hex 1B) - \ef formfeed (hex 0C) - \en linefeed (hex 0A) - \er carriage return (hex 0D) - \et tab (hex 09) - \eddd character with octal code ddd, or backreference - \exhh character with hex code hh - \ex{hhh..} character with hex code hhh.. -.sp -The precise effect of \ecx is as follows: if x is a lower case letter, it -is converted to upper case. Then bit 6 of the character (hex 40) is inverted. -Thus \ecz becomes hex 1A, but \ec{ becomes hex 3B, while \ec; becomes hex -7B. -.P -After \ex, from zero to two hexadecimal digits are read (letters can be in -upper or lower case). Any number of hexadecimal digits may appear between \ex{ -and }, but the value of the character code must be less than 256 in non-UTF-8 -mode, and less than 2**31 in UTF-8 mode. That is, the maximum value in -hexadecimal is 7FFFFFFF. Note that this is bigger than the largest Unicode code -point, which is 10FFFF. -.P -If characters other than hexadecimal digits appear between \ex{ and }, or if -there is no terminating }, this form of escape is not recognized. Instead, the -initial \ex will be interpreted as a basic hexadecimal escape, with no -following digits, giving a character whose value is zero. -.P -Characters whose value is less than 256 can be defined by either of the two -syntaxes for \ex. There is no difference in the way they are handled. For -example, \exdc is exactly the same as \ex{dc}. -.P -After \e0 up to two further octal digits are read. If there are fewer than two -digits, just those that are present are used. Thus the sequence \e0\ex\e07 -specifies two binary zeros followed by a BEL character (code value 7). Make -sure you supply two digits after the initial zero if the pattern character that -follows is itself an octal digit. -.P -The handling of a backslash followed by a digit other than 0 is complicated. -Outside a character class, PCRE reads it and any following digits as a decimal -number. If the number is less than 10, or if there have been at least that many -previous capturing left parentheses in the expression, the entire sequence is -taken as a \fIback reference\fP. A description of how this works is given -.\" HTML -.\" -later, -.\" -following the discussion of -.\" HTML -.\" -parenthesized subpatterns. -.\" -.P -Inside a character class, or if the decimal number is greater than 9 and there -have not been that many capturing subpatterns, PCRE re-reads up to three octal -digits following the backslash, and uses them to generate a data character. Any -subsequent digits stand for themselves. In non-UTF-8 mode, the value of a -character specified in octal must be less than \e400. In UTF-8 mode, values up -to \e777 are permitted. For example: -.sp - \e040 is another way of writing a space -.\" JOIN - \e40 is the same, provided there are fewer than 40 - previous capturing subpatterns - \e7 is always a back reference -.\" JOIN - \e11 might be a back reference, or another way of - writing a tab - \e011 is always a tab - \e0113 is a tab followed by the character "3" -.\" JOIN - \e113 might be a back reference, otherwise the - character with octal code 113 -.\" JOIN - \e377 might be a back reference, otherwise - the byte consisting entirely of 1 bits -.\" JOIN - \e81 is either a back reference, or a binary zero - followed by the two characters "8" and "1" -.sp -Note that octal values of 100 or greater must not be introduced by a leading -zero, because no more than three octal digits are ever read. -.P -All the sequences that define a single character value can be used both inside -and outside character classes. In addition, inside a character class, the -sequence \eb is interpreted as the backspace character (hex 08), and the -sequences \eR and \eX are interpreted as the characters "R" and "X", -respectively. Outside a character class, these sequences have different -meanings -.\" HTML -.\" -(see below). -.\" -. -. -.SS "Absolute and relative back references" -.rs -.sp -The sequence \eg followed by an unsigned or a negative number, optionally -enclosed in braces, is an absolute or relative back reference. A named back -reference can be coded as \eg{name}. Back references are discussed -.\" HTML -.\" -later, -.\" -following the discussion of -.\" HTML -.\" -parenthesized subpatterns. -.\" -. -. -.SS "Absolute and relative subroutine calls" -.rs -.sp -For compatibility with Oniguruma, the non-Perl syntax \eg followed by a name or -a number enclosed either in angle brackets or single quotes, is an alternative -syntax for referencing a subpattern as a "subroutine". Details are discussed -.\" HTML -.\" -later. -.\" -Note that \eg{...} (Perl syntax) and \eg<...> (Oniguruma syntax) are \fInot\fP -synonymous. The former is a back reference; the latter is a subroutine call. -. -. -.SS "Generic character types" -.rs -.sp -Another use of backslash is for specifying generic character types. The -following are always recognized: -.sp - \ed any decimal digit - \eD any character that is not a decimal digit - \eh any horizontal whitespace character - \eH any character that is not a horizontal whitespace character - \es any whitespace character - \eS any character that is not a whitespace character - \ev any vertical whitespace character - \eV any character that is not a vertical whitespace character - \ew any "word" character - \eW any "non-word" character -.sp -Each pair of escape sequences partitions the complete set of characters into -two disjoint sets. Any given character matches one, and only one, of each pair. -.P -These character type sequences can appear both inside and outside character -classes. They each match one character of the appropriate type. If the current -matching point is at the end of the subject string, all of them fail, since -there is no character to match. -.P -For compatibility with Perl, \es does not match the VT character (code 11). -This makes it different from the the POSIX "space" class. The \es characters -are HT (9), LF (10), FF (12), CR (13), and space (32). If "use locale;" is -included in a Perl script, \es may match the VT character. In PCRE, it never -does. -.P -In UTF-8 mode, characters with values greater than 128 never match \ed, \es, or -\ew, and always match \eD, \eS, and \eW. This is true even when Unicode -character property support is available. These sequences retain their original -meanings from before UTF-8 support was available, mainly for efficiency -reasons. Note that this also affects \eb, because it is defined in terms of \ew -and \eW. -.P -The sequences \eh, \eH, \ev, and \eV are Perl 5.10 features. In contrast to the -other sequences, these do match certain high-valued codepoints in UTF-8 mode. -The horizontal space characters are: -.sp - U+0009 Horizontal tab - U+0020 Space - U+00A0 Non-break space - U+1680 Ogham space mark - U+180E Mongolian vowel separator - U+2000 En quad - U+2001 Em quad - U+2002 En space - U+2003 Em space - U+2004 Three-per-em space - U+2005 Four-per-em space - U+2006 Six-per-em space - U+2007 Figure space - U+2008 Punctuation space - U+2009 Thin space - U+200A Hair space - U+202F Narrow no-break space - U+205F Medium mathematical space - U+3000 Ideographic space -.sp -The vertical space characters are: -.sp - U+000A Linefeed - U+000B Vertical tab - U+000C Formfeed - U+000D Carriage return - U+0085 Next line - U+2028 Line separator - U+2029 Paragraph separator -.P -A "word" character is an underscore or any character less than 256 that is a -letter or digit. The definition of letters and digits is controlled by PCRE's -low-valued character tables, and may vary if locale-specific matching is taking -place (see -.\" HTML -.\" -"Locale support" -.\" -in the -.\" HREF -\fBpcreapi\fP -.\" -page). For example, in a French locale such as "fr_FR" in Unix-like systems, -or "french" in Windows, some character codes greater than 128 are used for -accented letters, and these are matched by \ew. The use of locales with Unicode -is discouraged. -. -. -.\" HTML -.SS "Newline sequences" -.rs -.sp -Outside a character class, by default, the escape sequence \eR matches any -Unicode newline sequence. This is a Perl 5.10 feature. In non-UTF-8 mode \eR is -equivalent to the following: -.sp - (?>\er\en|\en|\ex0b|\ef|\er|\ex85) -.sp -This is an example of an "atomic group", details of which are given -.\" HTML -.\" -below. -.\" -This particular group matches either the two-character sequence CR followed by -LF, or one of the single characters LF (linefeed, U+000A), VT (vertical tab, -U+000B), FF (formfeed, U+000C), CR (carriage return, U+000D), or NEL (next -line, U+0085). The two-character sequence is treated as a single unit that -cannot be split. -.P -In UTF-8 mode, two additional characters whose codepoints are greater than 255 -are added: LS (line separator, U+2028) and PS (paragraph separator, U+2029). -Unicode character property support is not needed for these characters to be -recognized. -.P -It is possible to restrict \eR to match only CR, LF, or CRLF (instead of the -complete set of Unicode line endings) by setting the option PCRE_BSR_ANYCRLF -either at compile time or when the pattern is matched. (BSR is an abbrevation -for "backslash R".) This can be made the default when PCRE is built; if this is -the case, the other behaviour can be requested via the PCRE_BSR_UNICODE option. -It is also possible to specify these settings by starting a pattern string with -one of the following sequences: -.sp - (*BSR_ANYCRLF) CR, LF, or CRLF only - (*BSR_UNICODE) any Unicode newline sequence -.sp -These override the default and the options given to \fBpcre_compile()\fP, but -they can be overridden by options given to \fBpcre_exec()\fP. Note that these -special settings, which are not Perl-compatible, are recognized only at the -very start of a pattern, and that they must be in upper case. If more than one -of them is present, the last one is used. They can be combined with a change of -newline convention, for example, a pattern can start with: -.sp - (*ANY)(*BSR_ANYCRLF) -.sp -Inside a character class, \eR matches the letter "R". -. -. -.\" HTML -.SS Unicode character properties -.rs -.sp -When PCRE is built with Unicode character property support, three additional -escape sequences that match characters with specific properties are available. -When not in UTF-8 mode, these sequences are of course limited to testing -characters whose codepoints are less than 256, but they do work in this mode. -The extra escape sequences are: -.sp - \ep{\fIxx\fP} a character with the \fIxx\fP property - \eP{\fIxx\fP} a character without the \fIxx\fP property - \eX an extended Unicode sequence -.sp -The property names represented by \fIxx\fP above are limited to the Unicode -script names, the general category properties, and "Any", which matches any -character (including newline). Other properties such as "InMusicalSymbols" are -not currently supported by PCRE. Note that \eP{Any} does not match any -characters, so always causes a match failure. -.P -Sets of Unicode characters are defined as belonging to certain scripts. A -character from one of these sets can be matched using a script name. For -example: -.sp - \ep{Greek} - \eP{Han} -.sp -Those that are not part of an identified script are lumped together as -"Common". The current list of scripts is: -.P -Arabic, -Armenian, -Balinese, -Bengali, -Bopomofo, -Braille, -Buginese, -Buhid, -Canadian_Aboriginal, -Cherokee, -Common, -Coptic, -Cuneiform, -Cypriot, -Cyrillic, -Deseret, -Devanagari, -Ethiopic, -Georgian, -Glagolitic, -Gothic, -Greek, -Gujarati, -Gurmukhi, -Han, -Hangul, -Hanunoo, -Hebrew, -Hiragana, -Inherited, -Kannada, -Katakana, -Kharoshthi, -Khmer, -Lao, -Latin, -Limbu, -Linear_B, -Malayalam, -Mongolian, -Myanmar, -New_Tai_Lue, -Nko, -Ogham, -Old_Italic, -Old_Persian, -Oriya, -Osmanya, -Phags_Pa, -Phoenician, -Runic, -Shavian, -Sinhala, -Syloti_Nagri, -Syriac, -Tagalog, -Tagbanwa, -Tai_Le, -Tamil, -Telugu, -Thaana, -Thai, -Tibetan, -Tifinagh, -Ugaritic, -Yi. -.P -Each character has exactly one general category property, specified by a -two-letter abbreviation. For compatibility with Perl, negation can be specified -by including a circumflex between the opening brace and the property name. For -example, \ep{^Lu} is the same as \eP{Lu}. -.P -If only one letter is specified with \ep or \eP, it includes all the general -category properties that start with that letter. In this case, in the absence -of negation, the curly brackets in the escape sequence are optional; these two -examples have the same effect: -.sp - \ep{L} - \epL -.sp -The following general category property codes are supported: -.sp - C Other - Cc Control - Cf Format - Cn Unassigned - Co Private use - Cs Surrogate -.sp - L Letter - Ll Lower case letter - Lm Modifier letter - Lo Other letter - Lt Title case letter - Lu Upper case letter -.sp - M Mark - Mc Spacing mark - Me Enclosing mark - Mn Non-spacing mark -.sp - N Number - Nd Decimal number - Nl Letter number - No Other number -.sp - P Punctuation - Pc Connector punctuation - Pd Dash punctuation - Pe Close punctuation - Pf Final punctuation - Pi Initial punctuation - Po Other punctuation - Ps Open punctuation -.sp - S Symbol - Sc Currency symbol - Sk Modifier symbol - Sm Mathematical symbol - So Other symbol -.sp - Z Separator - Zl Line separator - Zp Paragraph separator - Zs Space separator -.sp -The special property L& is also supported: it matches a character that has -the Lu, Ll, or Lt property, in other words, a letter that is not classified as -a modifier or "other". -.P -The Cs (Surrogate) property applies only to characters in the range U+D800 to -U+DFFF. Such characters are not valid in UTF-8 strings (see RFC 3629) and so -cannot be tested by PCRE, unless UTF-8 validity checking has been turned off -(see the discussion of PCRE_NO_UTF8_CHECK in the -.\" HREF -\fBpcreapi\fP -.\" -page). -.P -The long synonyms for these properties that Perl supports (such as \ep{Letter}) -are not supported by PCRE, nor is it permitted to prefix any of these -properties with "Is". -.P -No character that is in the Unicode table has the Cn (unassigned) property. -Instead, this property is assumed for any code point that is not in the -Unicode table. -.P -Specifying caseless matching does not affect these escape sequences. For -example, \ep{Lu} always matches only upper case letters. -.P -The \eX escape matches any number of Unicode characters that form an extended -Unicode sequence. \eX is equivalent to -.sp - (?>\ePM\epM*) -.sp -That is, it matches a character without the "mark" property, followed by zero -or more characters with the "mark" property, and treats the sequence as an -atomic group -.\" HTML -.\" -(see below). -.\" -Characters with the "mark" property are typically accents that affect the -preceding character. None of them have codepoints less than 256, so in -non-UTF-8 mode \eX matches any one character. -.P -Matching characters by Unicode property is not fast, because PCRE has to search -a structure that contains data for over fifteen thousand characters. That is -why the traditional escape sequences such as \ed and \ew do not use Unicode -properties in PCRE. -. -. -.\" HTML -.SS "Resetting the match start" -.rs -.sp -The escape sequence \eK, which is a Perl 5.10 feature, causes any previously -matched characters not to be included in the final matched sequence. For -example, the pattern: -.sp - foo\eKbar -.sp -matches "foobar", but reports that it has matched "bar". This feature is -similar to a lookbehind assertion -.\" HTML -.\" -(described below). -.\" -However, in this case, the part of the subject before the real match does not -have to be of fixed length, as lookbehind assertions do. The use of \eK does -not interfere with the setting of -.\" HTML -.\" -captured substrings. -.\" -For example, when the pattern -.sp - (foo)\eKbar -.sp -matches "foobar", the first substring is still set to "foo". -. -. -.\" HTML -.SS "Simple assertions" -.rs -.sp -The final use of backslash is for certain simple assertions. An assertion -specifies a condition that has to be met at a particular point in a match, -without consuming any characters from the subject string. The use of -subpatterns for more complicated assertions is described -.\" HTML -.\" -below. -.\" -The backslashed assertions are: -.sp - \eb matches at a word boundary - \eB matches when not at a word boundary - \eA matches at the start of the subject - \eZ matches at the end of the subject - also matches before a newline at the end of the subject - \ez matches only at the end of the subject - \eG matches at the first matching position in the subject -.sp -These assertions may not appear in character classes (but note that \eb has a -different meaning, namely the backspace character, inside a character class). -.P -A word boundary is a position in the subject string where the current character -and the previous character do not both match \ew or \eW (i.e. one matches -\ew and the other matches \eW), or the start or end of the string if the -first or last character matches \ew, respectively. -.P -The \eA, \eZ, and \ez assertions differ from the traditional circumflex and -dollar (described in the next section) in that they only ever match at the very -start and end of the subject string, whatever options are set. Thus, they are -independent of multiline mode. These three assertions are not affected by the -PCRE_NOTBOL or PCRE_NOTEOL options, which affect only the behaviour of the -circumflex and dollar metacharacters. However, if the \fIstartoffset\fP -argument of \fBpcre_exec()\fP is non-zero, indicating that matching is to start -at a point other than the beginning of the subject, \eA can never match. The -difference between \eZ and \ez is that \eZ matches before a newline at the end -of the string as well as at the very end, whereas \ez matches only at the end. -.P -The \eG assertion is true only when the current matching position is at the -start point of the match, as specified by the \fIstartoffset\fP argument of -\fBpcre_exec()\fP. It differs from \eA when the value of \fIstartoffset\fP is -non-zero. By calling \fBpcre_exec()\fP multiple times with appropriate -arguments, you can mimic Perl's /g option, and it is in this kind of -implementation where \eG can be useful. -.P -Note, however, that PCRE's interpretation of \eG, as the start of the current -match, is subtly different from Perl's, which defines it as the end of the -previous match. In Perl, these can be different when the previously matched -string was empty. Because PCRE does just one match at a time, it cannot -reproduce this behaviour. -.P -If all the alternatives of a pattern begin with \eG, the expression is anchored -to the starting match position, and the "anchored" flag is set in the compiled -regular expression. -. -. -.SH "CIRCUMFLEX AND DOLLAR" -.rs -.sp -Outside a character class, in the default matching mode, the circumflex -character is an assertion that is true only if the current matching point is -at the start of the subject string. If the \fIstartoffset\fP argument of -\fBpcre_exec()\fP is non-zero, circumflex can never match if the PCRE_MULTILINE -option is unset. Inside a character class, circumflex has an entirely different -meaning -.\" HTML -.\" -(see below). -.\" -.P -Circumflex need not be the first character of the pattern if a number of -alternatives are involved, but it should be the first thing in each alternative -in which it appears if the pattern is ever to match that branch. If all -possible alternatives start with a circumflex, that is, if the pattern is -constrained to match only at the start of the subject, it is said to be an -"anchored" pattern. (There are also other constructs that can cause a pattern -to be anchored.) -.P -A dollar character is an assertion that is true only if the current matching -point is at the end of the subject string, or immediately before a newline -at the end of the string (by default). Dollar need not be the last character of -the pattern if a number of alternatives are involved, but it should be the last -item in any branch in which it appears. Dollar has no special meaning in a -character class. -.P -The meaning of dollar can be changed so that it matches only at the very end of -the string, by setting the PCRE_DOLLAR_ENDONLY option at compile time. This -does not affect the \eZ assertion. -.P -The meanings of the circumflex and dollar characters are changed if the -PCRE_MULTILINE option is set. When this is the case, a circumflex matches -immediately after internal newlines as well as at the start of the subject -string. It does not match after a newline that ends the string. A dollar -matches before any newlines in the string, as well as at the very end, when -PCRE_MULTILINE is set. When newline is specified as the two-character -sequence CRLF, isolated CR and LF characters do not indicate newlines. -.P -For example, the pattern /^abc$/ matches the subject string "def\enabc" (where -\en represents a newline) in multiline mode, but not otherwise. Consequently, -patterns that are anchored in single line mode because all branches start with -^ are not anchored in multiline mode, and a match for circumflex is possible -when the \fIstartoffset\fP argument of \fBpcre_exec()\fP is non-zero. The -PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is set. -.P -Note that the sequences \eA, \eZ, and \ez can be used to match the start and -end of the subject in both modes, and if all branches of a pattern start with -\eA it is always anchored, whether or not PCRE_MULTILINE is set. -. -. -.SH "FULL STOP (PERIOD, DOT)" -.rs -.sp -Outside a character class, a dot in the pattern matches any one character in -the subject string except (by default) a character that signifies the end of a -line. In UTF-8 mode, the matched character may be more than one byte long. -.P -When a line ending is defined as a single character, dot never matches that -character; when the two-character sequence CRLF is used, dot does not match CR -if it is immediately followed by LF, but otherwise it matches all characters -(including isolated CRs and LFs). When any Unicode line endings are being -recognized, dot does not match CR or LF or any of the other line ending -characters. -.P -The behaviour of dot with regard to newlines can be changed. If the PCRE_DOTALL -option is set, a dot matches any one character, without exception. If the -two-character sequence CRLF is present in the subject string, it takes two dots -to match it. -.P -The handling of dot is entirely independent of the handling of circumflex and -dollar, the only relationship being that they both involve newlines. Dot has no -special meaning in a character class. -. -. -.SH "MATCHING A SINGLE BYTE" -.rs -.sp -Outside a character class, the escape sequence \eC matches any one byte, both -in and out of UTF-8 mode. Unlike a dot, it always matches any line-ending -characters. The feature is provided in Perl in order to match individual bytes -in UTF-8 mode. Because it breaks up UTF-8 characters into individual bytes, -what remains in the string may be a malformed UTF-8 string. For this reason, -the \eC escape sequence is best avoided. -.P -PCRE does not allow \eC to appear in lookbehind assertions -.\" HTML -.\" -(described below), -.\" -because in UTF-8 mode this would make it impossible to calculate the length of -the lookbehind. -. -. -.\" HTML -.SH "SQUARE BRACKETS AND CHARACTER CLASSES" -.rs -.sp -An opening square bracket introduces a character class, terminated by a closing -square bracket. A closing square bracket on its own is not special. If a -closing square bracket is required as a member of the class, it should be the -first data character in the class (after an initial circumflex, if present) or -escaped with a backslash. -.P -A character class matches a single character in the subject. In UTF-8 mode, the -character may occupy more than one byte. A matched character must be in the set -of characters defined by the class, unless the first character in the class -definition is a circumflex, in which case the subject character must not be in -the set defined by the class. If a circumflex is actually required as a member -of the class, ensure it is not the first character, or escape it with a -backslash. -.P -For example, the character class [aeiou] matches any lower case vowel, while -[^aeiou] matches any character that is not a lower case vowel. Note that a -circumflex is just a convenient notation for specifying the characters that -are in the class by enumerating those that are not. A class that starts with a -circumflex is not an assertion: it still consumes a character from the subject -string, and therefore it fails if the current pointer is at the end of the -string. -.P -In UTF-8 mode, characters with values greater than 255 can be included in a -class as a literal string of bytes, or by using the \ex{ escaping mechanism. -.P -When caseless matching is set, any letters in a class represent both their -upper case and lower case versions, so for example, a caseless [aeiou] matches -"A" as well as "a", and a caseless [^aeiou] does not match "A", whereas a -caseful version would. In UTF-8 mode, PCRE always understands the concept of -case for characters whose values are less than 128, so caseless matching is -always possible. For characters with higher values, the concept of case is -supported if PCRE is compiled with Unicode property support, but not otherwise. -If you want to use caseless matching for characters 128 and above, you must -ensure that PCRE is compiled with Unicode property support as well as with -UTF-8 support. -.P -Characters that might indicate line breaks are never treated in any special way -when matching character classes, whatever line-ending sequence is in use, and -whatever setting of the PCRE_DOTALL and PCRE_MULTILINE options is used. A class -such as [^a] always matches one of these characters. -.P -The minus (hyphen) character can be used to specify a range of characters in a -character class. For example, [d-m] matches any letter between d and m, -inclusive. If a minus character is required in a class, it must be escaped with -a backslash or appear in a position where it cannot be interpreted as -indicating a range, typically as the first or last character in the class. -.P -It is not possible to have the literal character "]" as the end character of a -range. A pattern such as [W-]46] is interpreted as a class of two characters -("W" and "-") followed by a literal string "46]", so it would match "W46]" or -"-46]". However, if the "]" is escaped with a backslash it is interpreted as -the end of range, so [W-\e]46] is interpreted as a class containing a range -followed by two other characters. The octal or hexadecimal representation of -"]" can also be used to end a range. -.P -Ranges operate in the collating sequence of character values. They can also be -used for characters specified numerically, for example [\e000-\e037]. In UTF-8 -mode, ranges can include characters whose values are greater than 255, for -example [\ex{100}-\ex{2ff}]. -.P -If a range that includes letters is used when caseless matching is set, it -matches the letters in either case. For example, [W-c] is equivalent to -[][\e\e^_`wxyzabc], matched caselessly, and in non-UTF-8 mode, if character -tables for a French locale are in use, [\exc8-\excb] matches accented E -characters in both cases. In UTF-8 mode, PCRE supports the concept of case for -characters with values greater than 128 only when it is compiled with Unicode -property support. -.P -The character types \ed, \eD, \ep, \eP, \es, \eS, \ew, and \eW may also appear -in a character class, and add the characters that they match to the class. For -example, [\edABCDEF] matches any hexadecimal digit. A circumflex can -conveniently be used with the upper case character types to specify a more -restricted set of characters than the matching lower case type. For example, -the class [^\eW_] matches any letter or digit, but not underscore. -.P -The only metacharacters that are recognized in character classes are backslash, -hyphen (only where it can be interpreted as specifying a range), circumflex -(only at the start), opening square bracket (only when it can be interpreted as -introducing a POSIX class name - see the next section), and the terminating -closing square bracket. However, escaping other non-alphanumeric characters -does no harm. -. -. -.SH "POSIX CHARACTER CLASSES" -.rs -.sp -Perl supports the POSIX notation for character classes. This uses names -enclosed by [: and :] within the enclosing square brackets. PCRE also supports -this notation. For example, -.sp - [01[:alpha:]%] -.sp -matches "0", "1", any alphabetic character, or "%". The supported class names -are -.sp - alnum letters and digits - alpha letters - ascii character codes 0 - 127 - blank space or tab only - cntrl control characters - digit decimal digits (same as \ed) - graph printing characters, excluding space - lower lower case letters - print printing characters, including space - punct printing characters, excluding letters and digits - space white space (not quite the same as \es) - upper upper case letters - word "word" characters (same as \ew) - xdigit hexadecimal digits -.sp -The "space" characters are HT (9), LF (10), VT (11), FF (12), CR (13), and -space (32). Notice that this list includes the VT character (code 11). This -makes "space" different to \es, which does not include VT (for Perl -compatibility). -.P -The name "word" is a Perl extension, and "blank" is a GNU extension from Perl -5.8. Another Perl extension is negation, which is indicated by a ^ character -after the colon. For example, -.sp - [12[:^digit:]] -.sp -matches "1", "2", or any non-digit. PCRE (and Perl) also recognize the POSIX -syntax [.ch.] and [=ch=] where "ch" is a "collating element", but these are not -supported, and an error is given if they are encountered. -.P -In UTF-8 mode, characters with values greater than 128 do not match any of -the POSIX character classes. -. -. -.SH "VERTICAL BAR" -.rs -.sp -Vertical bar characters are used to separate alternative patterns. For example, -the pattern -.sp - gilbert|sullivan -.sp -matches either "gilbert" or "sullivan". Any number of alternatives may appear, -and an empty alternative is permitted (matching the empty string). The matching -process tries each alternative in turn, from left to right, and the first one -that succeeds is used. If the alternatives are within a subpattern -.\" HTML -.\" -(defined below), -.\" -"succeeds" means matching the rest of the main pattern as well as the -alternative in the subpattern. -. -. -.SH "INTERNAL OPTION SETTING" -.rs -.sp -The settings of the PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, and -PCRE_EXTENDED options (which are Perl-compatible) can be changed from within -the pattern by a sequence of Perl option letters enclosed between "(?" and ")". -The option letters are -.sp - i for PCRE_CASELESS - m for PCRE_MULTILINE - s for PCRE_DOTALL - x for PCRE_EXTENDED -.sp -For example, (?im) sets caseless, multiline matching. It is also possible to -unset these options by preceding the letter with a hyphen, and a combined -setting and unsetting such as (?im-sx), which sets PCRE_CASELESS and -PCRE_MULTILINE while unsetting PCRE_DOTALL and PCRE_EXTENDED, is also -permitted. If a letter appears both before and after the hyphen, the option is -unset. -.P -The PCRE-specific options PCRE_DUPNAMES, PCRE_UNGREEDY, and PCRE_EXTRA can be -changed in the same way as the Perl-compatible options by using the characters -J, U and X respectively. -.P -When one of these option changes occurs at top level (that is, not inside -subpattern parentheses), the change applies to the remainder of the pattern -that follows. If the change is placed right at the start of a pattern, PCRE -extracts it into the global options (and it will therefore show up in data -extracted by the \fBpcre_fullinfo()\fP function). -.P -An option change within a subpattern (see below for a description of -subpatterns) affects only that part of the current pattern that follows it, so -.sp - (a(?i)b)c -.sp -matches abc and aBc and no other strings (assuming PCRE_CASELESS is not used). -By this means, options can be made to have different settings in different -parts of the pattern. Any changes made in one alternative do carry on -into subsequent branches within the same subpattern. For example, -.sp - (a(?i)b|c) -.sp -matches "ab", "aB", "c", and "C", even though when matching "C" the first -branch is abandoned before the option setting. This is because the effects of -option settings happen at compile time. There would be some very weird -behaviour otherwise. -.P -\fBNote:\fP There are other PCRE-specific options that can be set by the -application when the compile or match functions are called. In some cases the -pattern can contain special leading sequences such as (*CRLF) to override what -the application has set or what has been defaulted. Details are given in the -section entitled -.\" HTML -.\" -"Newline sequences" -.\" -above. There is also the (*UTF8) leading sequence that can be used to set UTF-8 -mode; this is equivalent to setting the PCRE_UTF8 option. -. -. -.\" HTML -.SH SUBPATTERNS -.rs -.sp -Subpatterns are delimited by parentheses (round brackets), which can be nested. -Turning part of a pattern into a subpattern does two things: -.sp -1. It localizes a set of alternatives. For example, the pattern -.sp - cat(aract|erpillar|) -.sp -matches one of the words "cat", "cataract", or "caterpillar". Without the -parentheses, it would match "cataract", "erpillar" or an empty string. -.sp -2. It sets up the subpattern as a capturing subpattern. This means that, when -the whole pattern matches, that portion of the subject string that matched the -subpattern is passed back to the caller via the \fIovector\fP argument of -\fBpcre_exec()\fP. Opening parentheses are counted from left to right (starting -from 1) to obtain numbers for the capturing subpatterns. -.P -For example, if the string "the red king" is matched against the pattern -.sp - the ((red|white) (king|queen)) -.sp -the captured substrings are "red king", "red", and "king", and are numbered 1, -2, and 3, respectively. -.P -The fact that plain parentheses fulfil two functions is not always helpful. -There are often times when a grouping subpattern is required without a -capturing requirement. If an opening parenthesis is followed by a question mark -and a colon, the subpattern does not do any capturing, and is not counted when -computing the number of any subsequent capturing subpatterns. For example, if -the string "the white queen" is matched against the pattern -.sp - the ((?:red|white) (king|queen)) -.sp -the captured substrings are "white queen" and "queen", and are numbered 1 and -2. The maximum number of capturing subpatterns is 65535. -.P -As a convenient shorthand, if any option settings are required at the start of -a non-capturing subpattern, the option letters may appear between the "?" and -the ":". Thus the two patterns -.sp - (?i:saturday|sunday) - (?:(?i)saturday|sunday) -.sp -match exactly the same set of strings. Because alternative branches are tried -from left to right, and options are not reset until the end of the subpattern -is reached, an option setting in one branch does affect subsequent branches, so -the above patterns match "SUNDAY" as well as "Saturday". -. -. -.SH "DUPLICATE SUBPATTERN NUMBERS" -.rs -.sp -Perl 5.10 introduced a feature whereby each alternative in a subpattern uses -the same numbers for its capturing parentheses. Such a subpattern starts with -(?| and is itself a non-capturing subpattern. For example, consider this -pattern: -.sp - (?|(Sat)ur|(Sun))day -.sp -Because the two alternatives are inside a (?| group, both sets of capturing -parentheses are numbered one. Thus, when the pattern matches, you can look -at captured substring number one, whichever alternative matched. This construct -is useful when you want to capture part, but not all, of one of a number of -alternatives. Inside a (?| group, parentheses are numbered as usual, but the -number is reset at the start of each branch. The numbers of any capturing -buffers that follow the subpattern start after the highest number used in any -branch. The following example is taken from the Perl documentation. -The numbers underneath show in which buffer the captured content will be -stored. -.sp - # before ---------------branch-reset----------- after - / ( a ) (?| x ( y ) z | (p (q) r) | (t) u (v) ) ( z ) /x - # 1 2 2 3 2 3 4 -.sp -A backreference or a recursive call to a numbered subpattern always refers to -the first one in the pattern with the given number. -.P -An alternative approach to using this "branch reset" feature is to use -duplicate named subpatterns, as described in the next section. -. -. -.SH "NAMED SUBPATTERNS" -.rs -.sp -Identifying capturing parentheses by number is simple, but it can be very hard -to keep track of the numbers in complicated regular expressions. Furthermore, -if an expression is modified, the numbers may change. To help with this -difficulty, PCRE supports the naming of subpatterns. This feature was not -added to Perl until release 5.10. Python had the feature earlier, and PCRE -introduced it at release 4.0, using the Python syntax. PCRE now supports both -the Perl and the Python syntax. -.P -In PCRE, a subpattern can be named in one of three ways: (?...) or -(?'name'...) as in Perl, or (?P...) as in Python. References to capturing -parentheses from other parts of the pattern, such as -.\" HTML -.\" -backreferences, -.\" -.\" HTML -.\" -recursion, -.\" -and -.\" HTML -.\" -conditions, -.\" -can be made by name as well as by number. -.P -Names consist of up to 32 alphanumeric characters and underscores. Named -capturing parentheses are still allocated numbers as well as names, exactly as -if the names were not present. The PCRE API provides function calls for -extracting the name-to-number translation table from a compiled pattern. There -is also a convenience function for extracting a captured substring by name. -.P -By default, a name must be unique within a pattern, but it is possible to relax -this constraint by setting the PCRE_DUPNAMES option at compile time. This can -be useful for patterns where only one instance of the named parentheses can -match. Suppose you want to match the name of a weekday, either as a 3-letter -abbreviation or as the full name, and in both cases you want to extract the -abbreviation. This pattern (ignoring the line breaks) does the job: -.sp - (?Mon|Fri|Sun)(?:day)?| - (?Tue)(?:sday)?| - (?Wed)(?:nesday)?| - (?Thu)(?:rsday)?| - (?Sat)(?:urday)? -.sp -There are five capturing substrings, but only one is ever set after a match. -(An alternative way of solving this problem is to use a "branch reset" -subpattern, as described in the previous section.) -.P -The convenience function for extracting the data by name returns the substring -for the first (and in this example, the only) subpattern of that name that -matched. This saves searching to find which numbered subpattern it was. If you -make a reference to a non-unique named subpattern from elsewhere in the -pattern, the one that corresponds to the lowest number is used. For further -details of the interfaces for handling named subpatterns, see the -.\" HREF -\fBpcreapi\fP -.\" -documentation. -.P -\fBWarning:\fP You cannot use different names to distinguish between two -subpatterns with the same number (see the previous section) because PCRE uses -only the numbers when matching. -. -. -.SH REPETITION -.rs -.sp -Repetition is specified by quantifiers, which can follow any of the following -items: -.sp - a literal data character - the dot metacharacter - the \eC escape sequence - the \eX escape sequence (in UTF-8 mode with Unicode properties) - the \eR escape sequence - an escape such as \ed that matches a single character - a character class - a back reference (see next section) - a parenthesized subpattern (unless it is an assertion) -.sp -The general repetition quantifier specifies a minimum and maximum number of -permitted matches, by giving the two numbers in curly brackets (braces), -separated by a comma. The numbers must be less than 65536, and the first must -be less than or equal to the second. For example: -.sp - z{2,4} -.sp -matches "zz", "zzz", or "zzzz". A closing brace on its own is not a special -character. If the second number is omitted, but the comma is present, there is -no upper limit; if the second number and the comma are both omitted, the -quantifier specifies an exact number of required matches. Thus -.sp - [aeiou]{3,} -.sp -matches at least 3 successive vowels, but may match many more, while -.sp - \ed{8} -.sp -matches exactly 8 digits. An opening curly bracket that appears in a position -where a quantifier is not allowed, or one that does not match the syntax of a -quantifier, is taken as a literal character. For example, {,6} is not a -quantifier, but a literal string of four characters. -.P -In UTF-8 mode, quantifiers apply to UTF-8 characters rather than to individual -bytes. Thus, for example, \ex{100}{2} matches two UTF-8 characters, each of -which is represented by a two-byte sequence. Similarly, when Unicode property -support is available, \eX{3} matches three Unicode extended sequences, each of -which may be several bytes long (and they may be of different lengths). -.P -The quantifier {0} is permitted, causing the expression to behave as if the -previous item and the quantifier were not present. This may be useful for -subpatterns that are referenced as -.\" HTML -.\" -subroutines -.\" -from elsewhere in the pattern. Items other than subpatterns that have a {0} -quantifier are omitted from the compiled pattern. -.P -For convenience, the three most common quantifiers have single-character -abbreviations: -.sp - * is equivalent to {0,} - + is equivalent to {1,} - ? is equivalent to {0,1} -.sp -It is possible to construct infinite loops by following a subpattern that can -match no characters with a quantifier that has no upper limit, for example: -.sp - (a?)* -.sp -Earlier versions of Perl and PCRE used to give an error at compile time for -such patterns. However, because there are cases where this can be useful, such -patterns are now accepted, but if any repetition of the subpattern does in fact -match no characters, the loop is forcibly broken. -.P -By default, the quantifiers are "greedy", that is, they match as much as -possible (up to the maximum number of permitted times), without causing the -rest of the pattern to fail. The classic example of where this gives problems -is in trying to match comments in C programs. These appear between /* and */ -and within the comment, individual * and / characters may appear. An attempt to -match C comments by applying the pattern -.sp - /\e*.*\e*/ -.sp -to the string -.sp - /* first comment */ not comment /* second comment */ -.sp -fails, because it matches the entire string owing to the greediness of the .* -item. -.P -However, if a quantifier is followed by a question mark, it ceases to be -greedy, and instead matches the minimum number of times possible, so the -pattern -.sp - /\e*.*?\e*/ -.sp -does the right thing with the C comments. The meaning of the various -quantifiers is not otherwise changed, just the preferred number of matches. -Do not confuse this use of question mark with its use as a quantifier in its -own right. Because it has two uses, it can sometimes appear doubled, as in -.sp - \ed??\ed -.sp -which matches one digit by preference, but can match two if that is the only -way the rest of the pattern matches. -.P -If the PCRE_UNGREEDY option is set (an option that is not available in Perl), -the quantifiers are not greedy by default, but individual ones can be made -greedy by following them with a question mark. In other words, it inverts the -default behaviour. -.P -When a parenthesized subpattern is quantified with a minimum repeat count that -is greater than 1 or with a limited maximum, more memory is required for the -compiled pattern, in proportion to the size of the minimum or maximum. -.P -If a pattern starts with .* or .{0,} and the PCRE_DOTALL option (equivalent -to Perl's /s) is set, thus allowing the dot to match newlines, the pattern is -implicitly anchored, because whatever follows will be tried against every -character position in the subject string, so there is no point in retrying the -overall match at any position after the first. PCRE normally treats such a -pattern as though it were preceded by \eA. -.P -In cases where it is known that the subject string contains no newlines, it is -worth setting PCRE_DOTALL in order to obtain this optimization, or -alternatively using ^ to indicate anchoring explicitly. -.P -However, there is one situation where the optimization cannot be used. When .* -is inside capturing parentheses that are the subject of a backreference -elsewhere in the pattern, a match at the start may fail where a later one -succeeds. Consider, for example: -.sp - (.*)abc\e1 -.sp -If the subject is "xyz123abc123" the match point is the fourth character. For -this reason, such a pattern is not implicitly anchored. -.P -When a capturing subpattern is repeated, the value captured is the substring -that matched the final iteration. For example, after -.sp - (tweedle[dume]{3}\es*)+ -.sp -has matched "tweedledum tweedledee" the value of the captured substring is -"tweedledee". However, if there are nested capturing subpatterns, the -corresponding captured values may have been set in previous iterations. For -example, after -.sp - /(a|(b))+/ -.sp -matches "aba" the value of the second captured substring is "b". -. -. -.\" HTML -.SH "ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS" -.rs -.sp -With both maximizing ("greedy") and minimizing ("ungreedy" or "lazy") -repetition, failure of what follows normally causes the repeated item to be -re-evaluated to see if a different number of repeats allows the rest of the -pattern to match. Sometimes it is useful to prevent this, either to change the -nature of the match, or to cause it fail earlier than it otherwise might, when -the author of the pattern knows there is no point in carrying on. -.P -Consider, for example, the pattern \ed+foo when applied to the subject line -.sp - 123456bar -.sp -After matching all 6 digits and then failing to match "foo", the normal -action of the matcher is to try again with only 5 digits matching the \ed+ -item, and then with 4, and so on, before ultimately failing. "Atomic grouping" -(a term taken from Jeffrey Friedl's book) provides the means for specifying -that once a subpattern has matched, it is not to be re-evaluated in this way. -.P -If we use atomic grouping for the previous example, the matcher gives up -immediately on failing to match "foo" the first time. The notation is a kind of -special parenthesis, starting with (?> as in this example: -.sp - (?>\ed+)foo -.sp -This kind of parenthesis "locks up" the part of the pattern it contains once -it has matched, and a failure further into the pattern is prevented from -backtracking into it. Backtracking past it to previous items, however, works as -normal. -.P -An alternative description is that a subpattern of this type matches the string -of characters that an identical standalone pattern would match, if anchored at -the current point in the subject string. -.P -Atomic grouping subpatterns are not capturing subpatterns. Simple cases such as -the above example can be thought of as a maximizing repeat that must swallow -everything it can. So, while both \ed+ and \ed+? are prepared to adjust the -number of digits they match in order to make the rest of the pattern match, -(?>\ed+) can only match an entire sequence of digits. -.P -Atomic groups in general can of course contain arbitrarily complicated -subpatterns, and can be nested. However, when the subpattern for an atomic -group is just a single repeated item, as in the example above, a simpler -notation, called a "possessive quantifier" can be used. This consists of an -additional + character following a quantifier. Using this notation, the -previous example can be rewritten as -.sp - \ed++foo -.sp -Note that a possessive quantifier can be used with an entire group, for -example: -.sp - (abc|xyz){2,3}+ -.sp -Possessive quantifiers are always greedy; the setting of the PCRE_UNGREEDY -option is ignored. They are a convenient notation for the simpler forms of -atomic group. However, there is no difference in the meaning of a possessive -quantifier and the equivalent atomic group, though there may be a performance -difference; possessive quantifiers should be slightly faster. -.P -The possessive quantifier syntax is an extension to the Perl 5.8 syntax. -Jeffrey Friedl originated the idea (and the name) in the first edition of his -book. Mike McCloskey liked it, so implemented it when he built Sun's Java -package, and PCRE copied it from there. It ultimately found its way into Perl -at release 5.10. -.P -PCRE has an optimization that automatically "possessifies" certain simple -pattern constructs. For example, the sequence A+B is treated as A++B because -there is no point in backtracking into a sequence of A's when B must follow. -.P -When a pattern contains an unlimited repeat inside a subpattern that can itself -be repeated an unlimited number of times, the use of an atomic group is the -only way to avoid some failing matches taking a very long time indeed. The -pattern -.sp - (\eD+|<\ed+>)*[!?] -.sp -matches an unlimited number of substrings that either consist of non-digits, or -digits enclosed in <>, followed by either ! or ?. When it matches, it runs -quickly. However, if it is applied to -.sp - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -.sp -it takes a long time before reporting failure. This is because the string can -be divided between the internal \eD+ repeat and the external * repeat in a -large number of ways, and all have to be tried. (The example uses [!?] rather -than a single character at the end, because both PCRE and Perl have an -optimization that allows for fast failure when a single character is used. They -remember the last single character that is required for a match, and fail early -if it is not present in the string.) If the pattern is changed so that it uses -an atomic group, like this: -.sp - ((?>\eD+)|<\ed+>)*[!?] -.sp -sequences of non-digits cannot be broken, and failure happens quickly. -. -. -.\" HTML -.SH "BACK REFERENCES" -.rs -.sp -Outside a character class, a backslash followed by a digit greater than 0 (and -possibly further digits) is a back reference to a capturing subpattern earlier -(that is, to its left) in the pattern, provided there have been that many -previous capturing left parentheses. -.P -However, if the decimal number following the backslash is less than 10, it is -always taken as a back reference, and causes an error only if there are not -that many capturing left parentheses in the entire pattern. In other words, the -parentheses that are referenced need not be to the left of the reference for -numbers less than 10. A "forward back reference" of this type can make sense -when a repetition is involved and the subpattern to the right has participated -in an earlier iteration. -.P -It is not possible to have a numerical "forward back reference" to a subpattern -whose number is 10 or more using this syntax because a sequence such as \e50 is -interpreted as a character defined in octal. See the subsection entitled -"Non-printing characters" -.\" HTML -.\" -above -.\" -for further details of the handling of digits following a backslash. There is -no such problem when named parentheses are used. A back reference to any -subpattern is possible using named parentheses (see below). -.P -Another way of avoiding the ambiguity inherent in the use of digits following a -backslash is to use the \eg escape sequence, which is a feature introduced in -Perl 5.10. This escape must be followed by an unsigned number or a negative -number, optionally enclosed in braces. These examples are all identical: -.sp - (ring), \e1 - (ring), \eg1 - (ring), \eg{1} -.sp -An unsigned number specifies an absolute reference without the ambiguity that -is present in the older syntax. It is also useful when literal digits follow -the reference. A negative number is a relative reference. Consider this -example: -.sp - (abc(def)ghi)\eg{-1} -.sp -The sequence \eg{-1} is a reference to the most recently started capturing -subpattern before \eg, that is, is it equivalent to \e2. Similarly, \eg{-2} -would be equivalent to \e1. The use of relative references can be helpful in -long patterns, and also in patterns that are created by joining together -fragments that contain references within themselves. -.P -A back reference matches whatever actually matched the capturing subpattern in -the current subject string, rather than anything matching the subpattern -itself (see -.\" HTML -.\" -"Subpatterns as subroutines" -.\" -below for a way of doing that). So the pattern -.sp - (sens|respons)e and \e1ibility -.sp -matches "sense and sensibility" and "response and responsibility", but not -"sense and responsibility". If caseful matching is in force at the time of the -back reference, the case of letters is relevant. For example, -.sp - ((?i)rah)\es+\e1 -.sp -matches "rah rah" and "RAH RAH", but not "RAH rah", even though the original -capturing subpattern is matched caselessly. -.P -There are several different ways of writing back references to named -subpatterns. The .NET syntax \ek{name} and the Perl syntax \ek or -\ek'name' are supported, as is the Python syntax (?P=name). Perl 5.10's unified -back reference syntax, in which \eg can be used for both numeric and named -references, is also supported. We could rewrite the above example in any of -the following ways: -.sp - (?(?i)rah)\es+\ek - (?'p1'(?i)rah)\es+\ek{p1} - (?P(?i)rah)\es+(?P=p1) - (?(?i)rah)\es+\eg{p1} -.sp -A subpattern that is referenced by name may appear in the pattern before or -after the reference. -.P -There may be more than one back reference to the same subpattern. If a -subpattern has not actually been used in a particular match, any back -references to it always fail. For example, the pattern -.sp - (a|(bc))\e2 -.sp -always fails if it starts to match "a" rather than "bc". Because there may be -many capturing parentheses in a pattern, all digits following the backslash are -taken as part of a potential back reference number. If the pattern continues -with a digit character, some delimiter must be used to terminate the back -reference. If the PCRE_EXTENDED option is set, this can be whitespace. -Otherwise an empty comment (see -.\" HTML -.\" -"Comments" -.\" -below) can be used. -.P -A back reference that occurs inside the parentheses to which it refers fails -when the subpattern is first used, so, for example, (a\e1) never matches. -However, such references can be useful inside repeated subpatterns. For -example, the pattern -.sp - (a|b\e1)+ -.sp -matches any number of "a"s and also "aba", "ababbaa" etc. At each iteration of -the subpattern, the back reference matches the character string corresponding -to the previous iteration. In order for this to work, the pattern must be such -that the first iteration does not need to match the back reference. This can be -done using alternation, as in the example above, or by a quantifier with a -minimum of zero. -. -. -.\" HTML -.SH ASSERTIONS -.rs -.sp -An assertion is a test on the characters following or preceding the current -matching point that does not actually consume any characters. The simple -assertions coded as \eb, \eB, \eA, \eG, \eZ, \ez, ^ and $ are described -.\" HTML -.\" -above. -.\" -.P -More complicated assertions are coded as subpatterns. There are two kinds: -those that look ahead of the current position in the subject string, and those -that look behind it. An assertion subpattern is matched in the normal way, -except that it does not cause the current matching position to be changed. -.P -Assertion subpatterns are not capturing subpatterns, and may not be repeated, -because it makes no sense to assert the same thing several times. If any kind -of assertion contains capturing subpatterns within it, these are counted for -the purposes of numbering the capturing subpatterns in the whole pattern. -However, substring capturing is carried out only for positive assertions, -because it does not make sense for negative assertions. -. -. -.SS "Lookahead assertions" -.rs -.sp -Lookahead assertions start with (?= for positive assertions and (?! for -negative assertions. For example, -.sp - \ew+(?=;) -.sp -matches a word followed by a semicolon, but does not include the semicolon in -the match, and -.sp - foo(?!bar) -.sp -matches any occurrence of "foo" that is not followed by "bar". Note that the -apparently similar pattern -.sp - (?!foo)bar -.sp -does not find an occurrence of "bar" that is preceded by something other than -"foo"; it finds any occurrence of "bar" whatsoever, because the assertion -(?!foo) is always true when the next three characters are "bar". A -lookbehind assertion is needed to achieve the other effect. -.P -If you want to force a matching failure at some point in a pattern, the most -convenient way to do it is with (?!) because an empty string always matches, so -an assertion that requires there not to be an empty string must always fail. -. -. -.\" HTML -.SS "Lookbehind assertions" -.rs -.sp -Lookbehind assertions start with (?<= for positive assertions and (? -.\" -(see above) -.\" -can be used instead of a lookbehind assertion; this is not restricted to a -fixed-length. -.P -The implementation of lookbehind assertions is, for each alternative, to -temporarily move the current position back by the fixed length and then try to -match. If there are insufficient characters before the current position, the -assertion fails. -.P -PCRE does not allow the \eC escape (which matches a single byte in UTF-8 mode) -to appear in lookbehind assertions, because it makes it impossible to calculate -the length of the lookbehind. The \eX and \eR escapes, which can match -different numbers of bytes, are also not permitted. -.P -Possessive quantifiers can be used in conjunction with lookbehind assertions to -specify efficient matching at the end of the subject string. Consider a simple -pattern such as -.sp - abcd$ -.sp -when applied to a long string that does not match. Because matching proceeds -from left to right, PCRE will look for each "a" in the subject and then see if -what follows matches the rest of the pattern. If the pattern is specified as -.sp - ^.*abcd$ -.sp -the initial .* matches the entire string at first, but when this fails (because -there is no following "a"), it backtracks to match all but the last character, -then all but the last two characters, and so on. Once again the search for "a" -covers the entire string, from right to left, so we are no better off. However, -if the pattern is written as -.sp - ^.*+(?<=abcd) -.sp -there can be no backtracking for the .*+ item; it can match only the entire -string. The subsequent lookbehind assertion does a single test on the last four -characters. If it fails, the match fails immediately. For long strings, this -approach makes a significant difference to the processing time. -. -. -.SS "Using multiple assertions" -.rs -.sp -Several assertions (of any sort) may occur in succession. For example, -.sp - (?<=\ed{3})(? -.SH "CONDITIONAL SUBPATTERNS" -.rs -.sp -It is possible to cause the matching process to obey a subpattern -conditionally or to choose between two alternative subpatterns, depending on -the result of an assertion, or whether a previous capturing subpattern matched -or not. The two possible forms of conditional subpattern are -.sp - (?(condition)yes-pattern) - (?(condition)yes-pattern|no-pattern) -.sp -If the condition is satisfied, the yes-pattern is used; otherwise the -no-pattern (if present) is used. If there are more than two alternatives in the -subpattern, a compile-time error occurs. -.P -There are four kinds of condition: references to subpatterns, references to -recursion, a pseudo-condition called DEFINE, and assertions. -. -.SS "Checking for a used subpattern by number" -.rs -.sp -If the text between the parentheses consists of a sequence of digits, the -condition is true if the capturing subpattern of that number has previously -matched. An alternative notation is to precede the digits with a plus or minus -sign. In this case, the subpattern number is relative rather than absolute. -The most recently opened parentheses can be referenced by (?(-1), the next most -recent by (?(-2), and so on. In looping constructs it can also make sense to -refer to subsequent groups with constructs such as (?(+2). -.P -Consider the following pattern, which contains non-significant white space to -make it more readable (assume the PCRE_EXTENDED option) and to divide it into -three parts for ease of discussion: -.sp - ( \e( )? [^()]+ (?(1) \e) ) -.sp -The first part matches an optional opening parenthesis, and if that -character is present, sets it as the first captured substring. The second part -matches one or more characters that are not parentheses. The third part is a -conditional subpattern that tests whether the first set of parentheses matched -or not. If they did, that is, if subject started with an opening parenthesis, -the condition is true, and so the yes-pattern is executed and a closing -parenthesis is required. Otherwise, since no-pattern is not present, the -subpattern matches nothing. In other words, this pattern matches a sequence of -non-parentheses, optionally enclosed in parentheses. -.P -If you were embedding this pattern in a larger one, you could use a relative -reference: -.sp - ...other stuff... ( \e( )? [^()]+ (?(-1) \e) ) ... -.sp -This makes the fragment independent of the parentheses in the larger pattern. -. -.SS "Checking for a used subpattern by name" -.rs -.sp -Perl uses the syntax (?()...) or (?('name')...) to test for a used -subpattern by name. For compatibility with earlier versions of PCRE, which had -this facility before Perl, the syntax (?(name)...) is also recognized. However, -there is a possible ambiguity with this syntax, because subpattern names may -consist entirely of digits. PCRE looks first for a named subpattern; if it -cannot find one and the name consists entirely of digits, PCRE looks for a -subpattern of that number, which must be greater than zero. Using subpattern -names that consist entirely of digits is not recommended. -.P -Rewriting the above example to use a named subpattern gives this: -.sp - (? \e( )? [^()]+ (?() \e) ) -.sp -. -.SS "Checking for pattern recursion" -.rs -.sp -If the condition is the string (R), and there is no subpattern with the name R, -the condition is true if a recursive call to the whole pattern or any -subpattern has been made. If digits or a name preceded by ampersand follow the -letter R, for example: -.sp - (?(R3)...) or (?(R&name)...) -.sp -the condition is true if the most recent recursion is into the subpattern whose -number or name is given. This condition does not check the entire recursion -stack. -.P -At "top level", all these recursion test conditions are false. Recursive -patterns are described below. -. -.SS "Defining subpatterns for use by reference only" -.rs -.sp -If the condition is the string (DEFINE), and there is no subpattern with the -name DEFINE, the condition is always false. In this case, there may be only one -alternative in the subpattern. It is always skipped if control reaches this -point in the pattern; the idea of DEFINE is that it can be used to define -"subroutines" that can be referenced from elsewhere. (The use of "subroutines" -is described below.) For example, a pattern to match an IPv4 address could be -written like this (ignore whitespace and line breaks): -.sp - (?(DEFINE) (? 2[0-4]\ed | 25[0-5] | 1\ed\ed | [1-9]?\ed) ) - \eb (?&byte) (\e.(?&byte)){3} \eb -.sp -The first part of the pattern is a DEFINE group inside which a another group -named "byte" is defined. This matches an individual component of an IPv4 -address (a number less than 256). When matching takes place, this part of the -pattern is skipped because DEFINE acts like a false condition. -.P -The rest of the pattern uses references to the named group to match the four -dot-separated components of an IPv4 address, insisting on a word boundary at -each end. -. -.SS "Assertion conditions" -.rs -.sp -If the condition is not in any of the above formats, it must be an assertion. -This may be a positive or negative lookahead or lookbehind assertion. Consider -this pattern, again containing non-significant white space, and with the two -alternatives on the second line: -.sp - (?(?=[^a-z]*[a-z]) - \ed{2}-[a-z]{3}-\ed{2} | \ed{2}-\ed{2}-\ed{2} ) -.sp -The condition is a positive lookahead assertion that matches an optional -sequence of non-letters followed by a letter. In other words, it tests for the -presence of at least one letter in the subject. If a letter is found, the -subject is matched against the first alternative; otherwise it is matched -against the second. This pattern matches strings in one of the two forms -dd-aaa-dd or dd-dd-dd, where aaa are letters and dd are digits. -. -. -.\" HTML -.SH COMMENTS -.rs -.sp -The sequence (?# marks the start of a comment that continues up to the next -closing parenthesis. Nested parentheses are not permitted. The characters -that make up a comment play no part in the pattern matching at all. -.P -If the PCRE_EXTENDED option is set, an unescaped # character outside a -character class introduces a comment that continues to immediately after the -next newline in the pattern. -. -. -.\" HTML -.SH "RECURSIVE PATTERNS" -.rs -.sp -Consider the problem of matching a string in parentheses, allowing for -unlimited nested parentheses. Without the use of recursion, the best that can -be done is to use a pattern that matches up to some fixed depth of nesting. It -is not possible to handle an arbitrary nesting depth. -.P -For some time, Perl has provided a facility that allows regular expressions to -recurse (amongst other things). It does this by interpolating Perl code in the -expression at run time, and the code can refer to the expression itself. A Perl -pattern using code interpolation to solve the parentheses problem can be -created like this: -.sp - $re = qr{\e( (?: (?>[^()]+) | (?p{$re}) )* \e)}x; -.sp -The (?p{...}) item interpolates Perl code at run time, and in this case refers -recursively to the pattern in which it appears. -.P -Obviously, PCRE cannot support the interpolation of Perl code. Instead, it -supports special syntax for recursion of the entire pattern, and also for -individual subpattern recursion. After its introduction in PCRE and Python, -this kind of recursion was introduced into Perl at release 5.10. -.P -A special item that consists of (? followed by a number greater than zero and a -closing parenthesis is a recursive call of the subpattern of the given number, -provided that it occurs inside that subpattern. (If not, it is a "subroutine" -call, which is described in the next section.) The special item (?R) or (?0) is -a recursive call of the entire regular expression. -.P -In PCRE (like Python, but unlike Perl), a recursive subpattern call is always -treated as an atomic group. That is, once it has matched some of the subject -string, it is never re-entered, even if it contains untried alternatives and -there is a subsequent matching failure. -.P -This PCRE pattern solves the nested parentheses problem (assume the -PCRE_EXTENDED option is set so that white space is ignored): -.sp - \e( ( (?>[^()]+) | (?R) )* \e) -.sp -First it matches an opening parenthesis. Then it matches any number of -substrings which can either be a sequence of non-parentheses, or a recursive -match of the pattern itself (that is, a correctly parenthesized substring). -Finally there is a closing parenthesis. -.P -If this were part of a larger pattern, you would not want to recurse the entire -pattern, so instead you could use this: -.sp - ( \e( ( (?>[^()]+) | (?1) )* \e) ) -.sp -We have put the pattern into parentheses, and caused the recursion to refer to -them instead of the whole pattern. -.P -In a larger pattern, keeping track of parenthesis numbers can be tricky. This -is made easier by the use of relative references. (A Perl 5.10 feature.) -Instead of (?1) in the pattern above you can write (?-2) to refer to the second -most recently opened parentheses preceding the recursion. In other words, a -negative number counts capturing parentheses leftwards from the point at which -it is encountered. -.P -It is also possible to refer to subsequently opened parentheses, by writing -references such as (?+2). However, these cannot be recursive because the -reference is not inside the parentheses that are referenced. They are always -"subroutine" calls, as described in the next section. -.P -An alternative approach is to use named parentheses instead. The Perl syntax -for this is (?&name); PCRE's earlier syntax (?P>name) is also supported. We -could rewrite the above example as follows: -.sp - (? \e( ( (?>[^()]+) | (?&pn) )* \e) ) -.sp -If there is more than one subpattern with the same name, the earliest one is -used. -.P -This particular example pattern that we have been looking at contains nested -unlimited repeats, and so the use of atomic grouping for matching strings of -non-parentheses is important when applying the pattern to strings that do not -match. For example, when this pattern is applied to -.sp - (aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa() -.sp -it yields "no match" quickly. However, if atomic grouping is not used, -the match runs for a very long time indeed because there are so many different -ways the + and * repeats can carve up the subject, and all have to be tested -before failure can be reported. -.P -At the end of a match, the values set for any capturing subpatterns are those -from the outermost level of the recursion at which the subpattern value is set. -If you want to obtain intermediate values, a callout function can be used (see -below and the -.\" HREF -\fBpcrecallout\fP -.\" -documentation). If the pattern above is matched against -.sp - (ab(cd)ef) -.sp -the value for the capturing parentheses is "ef", which is the last value taken -on at the top level. If additional parentheses are added, giving -.sp - \e( ( ( (?>[^()]+) | (?R) )* ) \e) - ^ ^ - ^ ^ -.sp -the string they capture is "ab(cd)ef", the contents of the top level -parentheses. If there are more than 15 capturing parentheses in a pattern, PCRE -has to obtain extra memory to store data during a recursion, which it does by -using \fBpcre_malloc\fP, freeing it via \fBpcre_free\fP afterwards. If no -memory can be obtained, the match fails with the PCRE_ERROR_NOMEMORY error. -.P -Do not confuse the (?R) item with the condition (R), which tests for recursion. -Consider this pattern, which matches text in angle brackets, allowing for -arbitrary nesting. Only digits are allowed in nested brackets (that is, when -recursing), whereas any characters are permitted at the outer level. -.sp - < (?: (?(R) \ed++ | [^<>]*+) | (?R)) * > -.sp -In this pattern, (?(R) is the start of a conditional subpattern, with two -different alternatives for the recursive and non-recursive cases. The (?R) item -is the actual recursive call. -. -. -.\" HTML -.SH "SUBPATTERNS AS SUBROUTINES" -.rs -.sp -If the syntax for a recursive subpattern reference (either by number or by -name) is used outside the parentheses to which it refers, it operates like a -subroutine in a programming language. The "called" subpattern may be defined -before or after the reference. A numbered reference can be absolute or -relative, as in these examples: -.sp - (...(absolute)...)...(?2)... - (...(relative)...)...(?-1)... - (...(?+1)...(relative)... -.sp -An earlier example pointed out that the pattern -.sp - (sens|respons)e and \e1ibility -.sp -matches "sense and sensibility" and "response and responsibility", but not -"sense and responsibility". If instead the pattern -.sp - (sens|respons)e and (?1)ibility -.sp -is used, it does match "sense and responsibility" as well as the other two -strings. Another example is given in the discussion of DEFINE above. -.P -Like recursive subpatterns, a "subroutine" call is always treated as an atomic -group. That is, once it has matched some of the subject string, it is never -re-entered, even if it contains untried alternatives and there is a subsequent -matching failure. -.P -When a subpattern is used as a subroutine, processing options such as -case-independence are fixed when the subpattern is defined. They cannot be -changed for different calls. For example, consider this pattern: -.sp - (abc)(?i:(?-1)) -.sp -It matches "abcabc". It does not match "abcABC" because the change of -processing option does not affect the called subpattern. -. -. -.\" HTML -.SH "ONIGURUMA SUBROUTINE SYNTAX" -.rs -.sp -For compatibility with Oniguruma, the non-Perl syntax \eg followed by a name or -a number enclosed either in angle brackets or single quotes, is an alternative -syntax for referencing a subpattern as a subroutine, possibly recursively. Here -are two of the examples used above, rewritten using this syntax: -.sp - (? \e( ( (?>[^()]+) | \eg )* \e) ) - (sens|respons)e and \eg'1'ibility -.sp -PCRE supports an extension to Oniguruma: if a number is preceded by a -plus or a minus sign it is taken as a relative reference. For example: -.sp - (abc)(?i:\eg<-1>) -.sp -Note that \eg{...} (Perl syntax) and \eg<...> (Oniguruma syntax) are \fInot\fP -synonymous. The former is a back reference; the latter is a subroutine call. -. -. -.SH CALLOUTS -.rs -.sp -Perl has a feature whereby using the sequence (?{...}) causes arbitrary Perl -code to be obeyed in the middle of matching a regular expression. This makes it -possible, amongst other things, to extract different substrings that match the -same pair of parentheses when there is a repetition. -.P -PCRE provides a similar feature, but of course it cannot obey arbitrary Perl -code. The feature is called "callout". The caller of PCRE provides an external -function by putting its entry point in the global variable \fIpcre_callout\fP. -By default, this variable contains NULL, which disables all calling out. -.P -Within a regular expression, (?C) indicates the points at which the external -function is to be called. If you want to identify different callout points, you -can put a number less than 256 after the letter C. The default value is zero. -For example, this pattern has two callout points: -.sp - (?C1)abc(?C2)def -.sp -If the PCRE_AUTO_CALLOUT flag is passed to \fBpcre_compile()\fP, callouts are -automatically installed before each item in the pattern. They are all numbered -255. -.P -During matching, when PCRE reaches a callout point (and \fIpcre_callout\fP is -set), the external function is called. It is provided with the number of the -callout, the position in the pattern, and, optionally, one item of data -originally supplied by the caller of \fBpcre_exec()\fP. The callout function -may cause matching to proceed, to backtrack, or to fail altogether. A complete -description of the interface to the callout function is given in the -.\" HREF -\fBpcrecallout\fP -.\" -documentation. -. -. -.SH "BACKTRACKING CONTROL" -.rs -.sp -Perl 5.10 introduced a number of "Special Backtracking Control Verbs", which -are described in the Perl documentation as "experimental and subject to change -or removal in a future version of Perl". It goes on to say: "Their usage in -production code should be noted to avoid problems during upgrades." The same -remarks apply to the PCRE features described in this section. -.P -Since these verbs are specifically related to backtracking, most of them can be -used only when the pattern is to be matched using \fBpcre_exec()\fP, which uses -a backtracking algorithm. With the exception of (*FAIL), which behaves like a -failing negative assertion, they cause an error if encountered by -\fBpcre_dfa_exec()\fP. -.P -The new verbs make use of what was previously invalid syntax: an opening -parenthesis followed by an asterisk. In Perl, they are generally of the form -(*VERB:ARG) but PCRE does not support the use of arguments, so its general -form is just (*VERB). Any number of these verbs may occur in a pattern. There -are two kinds: -. -.SS "Verbs that act immediately" -.rs -.sp -The following verbs act as soon as they are encountered: -.sp - (*ACCEPT) -.sp -This verb causes the match to end successfully, skipping the remainder of the -pattern. When inside a recursion, only the innermost pattern is ended -immediately. PCRE differs from Perl in what happens if the (*ACCEPT) is inside -capturing parentheses. In Perl, the data so far is captured: in PCRE no data is -captured. For example: -.sp - A(A|B(*ACCEPT)|C)D -.sp -This matches "AB", "AAD", or "ACD", but when it matches "AB", no data is -captured. -.sp - (*FAIL) or (*F) -.sp -This verb causes the match to fail, forcing backtracking to occur. It is -equivalent to (?!) but easier to read. The Perl documentation notes that it is -probably useful only when combined with (?{}) or (??{}). Those are, of course, -Perl features that are not present in PCRE. The nearest equivalent is the -callout feature, as for example in this pattern: -.sp - a+(?C)(*FAIL) -.sp -A match with the string "aaaa" always fails, but the callout is taken before -each backtrack happens (in this example, 10 times). -. -.SS "Verbs that act after backtracking" -.rs -.sp -The following verbs do nothing when they are encountered. Matching continues -with what follows, but if there is no subsequent match, a failure is forced. -The verbs differ in exactly what kind of failure occurs. -.sp - (*COMMIT) -.sp -This verb causes the whole match to fail outright if the rest of the pattern -does not match. Even if the pattern is unanchored, no further attempts to find -a match by advancing the start point take place. Once (*COMMIT) has been -passed, \fBpcre_exec()\fP is committed to finding a match at the current -starting point, or not at all. For example: -.sp - a+(*COMMIT)b -.sp -This matches "xxaab" but not "aacaab". It can be thought of as a kind of -dynamic anchor, or "I've started, so I must finish." -.sp - (*PRUNE) -.sp -This verb causes the match to fail at the current position if the rest of the -pattern does not match. If the pattern is unanchored, the normal "bumpalong" -advance to the next starting character then happens. Backtracking can occur as -usual to the left of (*PRUNE), or when matching to the right of (*PRUNE), but -if there is no match to the right, backtracking cannot cross (*PRUNE). -In simple cases, the use of (*PRUNE) is just an alternative to an atomic -group or possessive quantifier, but there are some uses of (*PRUNE) that cannot -be expressed in any other way. -.sp - (*SKIP) -.sp -This verb is like (*PRUNE), except that if the pattern is unanchored, the -"bumpalong" advance is not to the next character, but to the position in the -subject where (*SKIP) was encountered. (*SKIP) signifies that whatever text -was matched leading up to it cannot be part of a successful match. Consider: -.sp - a+(*SKIP)b -.sp -If the subject is "aaaac...", after the first match attempt fails (starting at -the first character in the string), the starting point skips on to start the -next attempt at "c". Note that a possessive quantifer does not have the same -effect in this example; although it would suppress backtracking during the -first match attempt, the second attempt would start at the second character -instead of skipping on to "c". -.sp - (*THEN) -.sp -This verb causes a skip to the next alternation if the rest of the pattern does -not match. That is, it cancels pending backtracking, but only within the -current alternation. Its name comes from the observation that it can be used -for a pattern-based if-then-else block: -.sp - ( COND1 (*THEN) FOO | COND2 (*THEN) BAR | COND3 (*THEN) BAZ ) ... -.sp -If the COND1 pattern matches, FOO is tried (and possibly further items after -the end of the group if FOO succeeds); on failure the matcher skips to the -second alternative and tries COND2, without backtracking into COND1. If (*THEN) -is used outside of any alternation, it acts exactly like (*PRUNE). -. -. -.SH "SEE ALSO" -.rs -.sp -\fBpcreapi\fP(3), \fBpcrecallout\fP(3), \fBpcrematching\fP(3), \fBpcre\fP(3). -. -. -.SH AUTHOR -.rs -.sp -.nf -Philip Hazel -University Computing Service -Cambridge CB2 3QH, England. -.fi -. -. -.SH REVISION -.rs -.sp -.nf -Last updated: 11 April 2009 -Copyright (c) 1997-2009 University of Cambridge. -.fi diff --git a/libs/pcre/doc/pcreperform.3 b/libs/pcre/doc/pcreperform.3 deleted file mode 100644 index 915f7b7854..0000000000 --- a/libs/pcre/doc/pcreperform.3 +++ /dev/null @@ -1,153 +0,0 @@ -.TH PCREPERFORM 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH "PCRE PERFORMANCE" -.rs -.sp -Two aspects of performance are discussed below: memory usage and processing -time. The way you express your pattern as a regular expression can affect both -of them. -. -.SH "MEMORY USAGE" -.rs -.sp -Patterns are compiled by PCRE into a reasonably efficient byte code, so that -most simple patterns do not use much memory. However, there is one case where -memory usage can be unexpectedly large. When a parenthesized subpattern has a -quantifier with a minimum greater than 1 and/or a limited maximum, the whole -subpattern is repeated in the compiled code. For example, the pattern -.sp - (abc|def){2,4} -.sp -is compiled as if it were -.sp - (abc|def)(abc|def)((abc|def)(abc|def)?)? -.sp -(Technical aside: It is done this way so that backtrack points within each of -the repetitions can be independently maintained.) -.P -For regular expressions whose quantifiers use only small numbers, this is not -usually a problem. However, if the numbers are large, and particularly if such -repetitions are nested, the memory usage can become an embarrassment. For -example, the very simple pattern -.sp - ((ab){1,1000}c){1,3} -.sp -uses 51K bytes when compiled. When PCRE is compiled with its default internal -pointer size of two bytes, the size limit on a compiled pattern is 64K, and -this is reached with the above pattern if the outer repetition is increased -from 3 to 4. PCRE can be compiled to use larger internal pointers and thus -handle larger compiled patterns, but it is better to try to rewrite your -pattern to use less memory if you can. -.P -One way of reducing the memory usage for such patterns is to make use of PCRE's -.\" HTML -.\" -"subroutine" -.\" -facility. Re-writing the above pattern as -.sp - ((ab)(?2){0,999}c)(?1){0,2} -.sp -reduces the memory requirements to 18K, and indeed it remains under 20K even -with the outer repetition increased to 100. However, this pattern is not -exactly equivalent, because the "subroutine" calls are treated as -.\" HTML -.\" -atomic groups -.\" -into which there can be no backtracking if there is a subsequent matching -failure. Therefore, PCRE cannot do this kind of rewriting automatically. -Furthermore, there is a noticeable loss of speed when executing the modified -pattern. Nevertheless, if the atomic grouping is not a problem and the loss of -speed is acceptable, this kind of rewriting will allow you to process patterns -that PCRE cannot otherwise handle. -. -.SH "PROCESSING TIME" -.rs -.sp -Certain items in regular expression patterns are processed more efficiently -than others. It is more efficient to use a character class like [aeiou] than a -set of single-character alternatives such as (a|e|i|o|u). In general, the -simplest construction that provides the required behaviour is usually the most -efficient. Jeffrey Friedl's book contains a lot of useful general discussion -about optimizing regular expressions for efficient performance. This document -contains a few observations about PCRE. -.P -Using Unicode character properties (the \ep, \eP, and \eX escapes) is slow, -because PCRE has to scan a structure that contains data for over fifteen -thousand characters whenever it needs a character's property. If you can find -an alternative pattern that does not use character properties, it will probably -be faster. -.P -When a pattern begins with .* not in parentheses, or in parentheses that are -not the subject of a backreference, and the PCRE_DOTALL option is set, the -pattern is implicitly anchored by PCRE, since it can match only at the start of -a subject string. However, if PCRE_DOTALL is not set, PCRE cannot make this -optimization, because the . metacharacter does not then match a newline, and if -the subject string contains newlines, the pattern may match from the character -immediately following one of them instead of from the very start. For example, -the pattern -.sp - .*second -.sp -matches the subject "first\enand second" (where \en stands for a newline -character), with the match starting at the seventh character. In order to do -this, PCRE has to retry the match starting after every newline in the subject. -.P -If you are using such a pattern with subject strings that do not contain -newlines, the best performance is obtained by setting PCRE_DOTALL, or starting -the pattern with ^.* or ^.*? to indicate explicit anchoring. That saves PCRE -from having to scan along the subject looking for a newline to restart at. -.P -Beware of patterns that contain nested indefinite repeats. These can take a -long time to run when applied to a string that does not match. Consider the -pattern fragment -.sp - ^(a+)* -.sp -This can match "aaaa" in 16 different ways, and this number increases very -rapidly as the string gets longer. (The * repeat can match 0, 1, 2, 3, or 4 -times, and for each of those cases other than 0 or 4, the + repeats can match -different numbers of times.) When the remainder of the pattern is such that the -entire match is going to fail, PCRE has in principle to try every possible -variation, and this can take an extremely long time, even for relatively short -strings. -.P -An optimization catches some of the more simple cases such as -.sp - (a+)*b -.sp -where a literal character follows. Before embarking on the standard matching -procedure, PCRE checks that there is a "b" later in the subject string, and if -there is not, it fails the match immediately. However, when there is no -following literal this optimization cannot be used. You can see the difference -by comparing the behaviour of -.sp - (a+)*\ed -.sp -with the pattern above. The former gives a failure almost instantly when -applied to a whole line of "a" characters, whereas the latter takes an -appreciable time with strings longer than about 20 characters. -.P -In many cases, the solution to this kind of performance issue is to use an -atomic group or a possessive quantifier. -. -. -.SH AUTHOR -.rs -.sp -.nf -Philip Hazel -University Computing Service -Cambridge CB2 3QH, England. -.fi -. -. -.SH REVISION -.rs -.sp -.nf -Last updated: 06 March 2007 -Copyright (c) 1997-2007 University of Cambridge. -.fi diff --git a/libs/pcre/doc/pcreposix.3 b/libs/pcre/doc/pcreposix.3 deleted file mode 100644 index d63ac035a7..0000000000 --- a/libs/pcre/doc/pcreposix.3 +++ /dev/null @@ -1,244 +0,0 @@ -.TH PCREPOSIX 3 -.SH NAME -PCRE - Perl-compatible regular expressions. -.SH "SYNOPSIS OF POSIX API" -.rs -.sp -.B #include -.PP -.SM -.B int regcomp(regex_t *\fIpreg\fP, const char *\fIpattern\fP, -.ti +5n -.B int \fIcflags\fP); -.PP -.B int regexec(regex_t *\fIpreg\fP, const char *\fIstring\fP, -.ti +5n -.B size_t \fInmatch\fP, regmatch_t \fIpmatch\fP[], int \fIeflags\fP); -.PP -.B size_t regerror(int \fIerrcode\fP, const regex_t *\fIpreg\fP, -.ti +5n -.B char *\fIerrbuf\fP, size_t \fIerrbuf_size\fP); -.PP -.B void regfree(regex_t *\fIpreg\fP); -. -.SH DESCRIPTION -.rs -.sp -This set of functions provides a POSIX-style API to the PCRE regular expression -package. See the -.\" HREF -\fBpcreapi\fP -.\" -documentation for a description of PCRE's native API, which contains much -additional functionality. -.P -The functions described here are just wrapper functions that ultimately call -the PCRE native API. Their prototypes are defined in the \fBpcreposix.h\fP -header file, and on Unix systems the library itself is called -\fBpcreposix.a\fP, so can be accessed by adding \fB-lpcreposix\fP to the -command for linking an application that uses them. Because the POSIX functions -call the native ones, it is also necessary to add \fB-lpcre\fP. -.P -I have implemented only those POSIX option bits that can be reasonably mapped -to PCRE native options. In addition, the option REG_EXTENDED is defined with -the value zero. This has no effect, but since programs that are written to the -POSIX interface often use it, this makes it easier to slot in PCRE as a -replacement library. Other POSIX options are not even defined. -.P -When PCRE is called via these functions, it is only the API that is POSIX-like -in style. The syntax and semantics of the regular expressions themselves are -still those of Perl, subject to the setting of various PCRE options, as -described below. "POSIX-like in style" means that the API approximates to the -POSIX definition; it is not fully POSIX-compatible, and in multi-byte encoding -domains it is probably even less compatible. -.P -The header for these functions is supplied as \fBpcreposix.h\fP to avoid any -potential clash with other POSIX libraries. It can, of course, be renamed or -aliased as \fBregex.h\fP, which is the "correct" name. It provides two -structure types, \fIregex_t\fP for compiled internal forms, and -\fIregmatch_t\fP for returning captured substrings. It also defines some -constants whose names start with "REG_"; these are used for setting options and -identifying error codes. -.P -.SH "COMPILING A PATTERN" -.rs -.sp -The function \fBregcomp()\fP is called to compile a pattern into an -internal form. The pattern is a C string terminated by a binary zero, and -is passed in the argument \fIpattern\fP. The \fIpreg\fP argument is a pointer -to a \fBregex_t\fP structure that is used as a base for storing information -about the compiled regular expression. -.P -The argument \fIcflags\fP is either zero, or contains one or more of the bits -defined by the following macros: -.sp - REG_DOTALL -.sp -The PCRE_DOTALL option is set when the regular expression is passed for -compilation to the native function. Note that REG_DOTALL is not part of the -POSIX standard. -.sp - REG_ICASE -.sp -The PCRE_CASELESS option is set when the regular expression is passed for -compilation to the native function. -.sp - REG_NEWLINE -.sp -The PCRE_MULTILINE option is set when the regular expression is passed for -compilation to the native function. Note that this does \fInot\fP mimic the -defined POSIX behaviour for REG_NEWLINE (see the following section). -.sp - REG_NOSUB -.sp -The PCRE_NO_AUTO_CAPTURE option is set when the regular expression is passed -for compilation to the native function. In addition, when a pattern that is -compiled with this flag is passed to \fBregexec()\fP for matching, the -\fInmatch\fP and \fIpmatch\fP arguments are ignored, and no captured strings -are returned. -.sp - REG_UTF8 -.sp -The PCRE_UTF8 option is set when the regular expression is passed for -compilation to the native function. This causes the pattern itself and all data -strings used for matching it to be treated as UTF-8 strings. Note that REG_UTF8 -is not part of the POSIX standard. -.P -In the absence of these flags, no options are passed to the native function. -This means the the regex is compiled with PCRE default semantics. In -particular, the way it handles newline characters in the subject string is the -Perl way, not the POSIX way. Note that setting PCRE_MULTILINE has only -\fIsome\fP of the effects specified for REG_NEWLINE. It does not affect the way -newlines are matched by . (they aren't) or by a negative class such as [^a] -(they are). -.P -The yield of \fBregcomp()\fP is zero on success, and non-zero otherwise. The -\fIpreg\fP structure is filled in on success, and one member of the structure -is public: \fIre_nsub\fP contains the number of capturing subpatterns in -the regular expression. Various error codes are defined in the header file. -. -. -.SH "MATCHING NEWLINE CHARACTERS" -.rs -.sp -This area is not simple, because POSIX and Perl take different views of things. -It is not possible to get PCRE to obey POSIX semantics, but then PCRE was never -intended to be a POSIX engine. The following table lists the different -possibilities for matching newline characters in PCRE: -.sp - Default Change with -.sp - . matches newline no PCRE_DOTALL - newline matches [^a] yes not changeable - $ matches \en at end yes PCRE_DOLLARENDONLY - $ matches \en in middle no PCRE_MULTILINE - ^ matches \en in middle no PCRE_MULTILINE -.sp -This is the equivalent table for POSIX: -.sp - Default Change with -.sp - . matches newline yes REG_NEWLINE - newline matches [^a] yes REG_NEWLINE - $ matches \en at end no REG_NEWLINE - $ matches \en in middle no REG_NEWLINE - ^ matches \en in middle no REG_NEWLINE -.sp -PCRE's behaviour is the same as Perl's, except that there is no equivalent for -PCRE_DOLLAR_ENDONLY in Perl. In both PCRE and Perl, there is no way to stop -newline from matching [^a]. -.P -The default POSIX newline handling can be obtained by setting PCRE_DOTALL and -PCRE_DOLLAR_ENDONLY, but there is no way to make PCRE behave exactly as for the -REG_NEWLINE action. -. -. -.SH "MATCHING A PATTERN" -.rs -.sp -The function \fBregexec()\fP is called to match a compiled pattern \fIpreg\fP -against a given \fIstring\fP, which is by default terminated by a zero byte -(but see REG_STARTEND below), subject to the options in \fIeflags\fP. These can -be: -.sp - REG_NOTBOL -.sp -The PCRE_NOTBOL option is set when calling the underlying PCRE matching -function. -.sp - REG_NOTEMPTY -.sp -The PCRE_NOTEMPTY option is set when calling the underlying PCRE matching -function. Note that REG_NOTEMPTY is not part of the POSIX standard. However, -setting this option can give more POSIX-like behaviour in some situations. -.sp - REG_NOTEOL -.sp -The PCRE_NOTEOL option is set when calling the underlying PCRE matching -function. -.sp - REG_STARTEND -.sp -The string is considered to start at \fIstring\fP + \fIpmatch[0].rm_so\fP and -to have a terminating NUL located at \fIstring\fP + \fIpmatch[0].rm_eo\fP -(there need not actually be a NUL at that location), regardless of the value of -\fInmatch\fP. This is a BSD extension, compatible with but not specified by -IEEE Standard 1003.2 (POSIX.2), and should be used with caution in software -intended to be portable to other systems. Note that a non-zero \fIrm_so\fP does -not imply REG_NOTBOL; REG_STARTEND affects only the location of the string, not -how it is matched. -.P -If the pattern was compiled with the REG_NOSUB flag, no data about any matched -strings is returned. The \fInmatch\fP and \fIpmatch\fP arguments of -\fBregexec()\fP are ignored. -.P -Otherwise,the portion of the string that was matched, and also any captured -substrings, are returned via the \fIpmatch\fP argument, which points to an -array of \fInmatch\fP structures of type \fIregmatch_t\fP, containing the -members \fIrm_so\fP and \fIrm_eo\fP. These contain the offset to the first -character of each substring and the offset to the first character after the end -of each substring, respectively. The 0th element of the vector relates to the -entire portion of \fIstring\fP that was matched; subsequent elements relate to -the capturing subpatterns of the regular expression. Unused entries in the -array have both structure members set to -1. -.P -A successful match yields a zero return; various error codes are defined in the -header file, of which REG_NOMATCH is the "expected" failure code. -. -. -.SH "ERROR MESSAGES" -.rs -.sp -The \fBregerror()\fP function maps a non-zero errorcode from either -\fBregcomp()\fP or \fBregexec()\fP to a printable message. If \fIpreg\fP is not -NULL, the error should have arisen from the use of that structure. A message -terminated by a binary zero is placed in \fIerrbuf\fP. The length of the -message, including the zero, is limited to \fIerrbuf_size\fP. The yield of the -function is the size of buffer needed to hold the whole message. -. -. -.SH MEMORY USAGE -.rs -.sp -Compiling a regular expression causes memory to be allocated and associated -with the \fIpreg\fP structure. The function \fBregfree()\fP frees all such -memory, after which \fIpreg\fP may no longer be used as a compiled expression. -. -. -.SH AUTHOR -.rs -.sp -.nf -Philip Hazel -University Computing Service -Cambridge CB2 3QH, England. -.fi -. -. -.SH REVISION -.rs -.sp -.nf -Last updated: 11 March 2009 -Copyright (c) 1997-2009 University of Cambridge. -.fi diff --git a/libs/pcre/doc/pcreprecompile.3 b/libs/pcre/doc/pcreprecompile.3 deleted file mode 100644 index aa525426bd..0000000000 --- a/libs/pcre/doc/pcreprecompile.3 +++ /dev/null @@ -1,142 +0,0 @@ -.TH PCREPRECOMPILE 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH "SAVING AND RE-USING PRECOMPILED PCRE PATTERNS" -.rs -.sp -If you are running an application that uses a large number of regular -expression patterns, it may be useful to store them in a precompiled form -instead of having to compile them every time the application is run. -If you are not using any private character tables (see the -.\" HREF -\fBpcre_maketables()\fP -.\" -documentation), this is relatively straightforward. If you are using private -tables, it is a little bit more complicated. -.P -If you save compiled patterns to a file, you can copy them to a different host -and run them there. This works even if the new host has the opposite endianness -to the one on which the patterns were compiled. There may be a small -performance penalty, but it should be insignificant. However, compiling regular -expressions with one version of PCRE for use with a different version is not -guaranteed to work and may cause crashes. -. -. -.SH "SAVING A COMPILED PATTERN" -.rs -.sh -The value returned by \fBpcre_compile()\fP points to a single block of memory -that holds the compiled pattern and associated data. You can find the length of -this block in bytes by calling \fBpcre_fullinfo()\fP with an argument of -PCRE_INFO_SIZE. You can then save the data in any appropriate manner. Here is -sample code that compiles a pattern and writes it to a file. It assumes that -the variable \fIfd\fP refers to a file that is open for output: -.sp - int erroroffset, rc, size; - char *error; - pcre *re; -.sp - re = pcre_compile("my pattern", 0, &error, &erroroffset, NULL); - if (re == NULL) { ... handle errors ... } - rc = pcre_fullinfo(re, NULL, PCRE_INFO_SIZE, &size); - if (rc < 0) { ... handle errors ... } - rc = fwrite(re, 1, size, fd); - if (rc != size) { ... handle errors ... } -.sp -In this example, the bytes that comprise the compiled pattern are copied -exactly. Note that this is binary data that may contain any of the 256 possible -byte values. On systems that make a distinction between binary and non-binary -data, be sure that the file is opened for binary output. -.P -If you want to write more than one pattern to a file, you will have to devise a -way of separating them. For binary data, preceding each pattern with its length -is probably the most straightforward approach. Another possibility is to write -out the data in hexadecimal instead of binary, one pattern to a line. -.P -Saving compiled patterns in a file is only one possible way of storing them for -later use. They could equally well be saved in a database, or in the memory of -some daemon process that passes them via sockets to the processes that want -them. -.P -If the pattern has been studied, it is also possible to save the study data in -a similar way to the compiled pattern itself. When studying generates -additional information, \fBpcre_study()\fP returns a pointer to a -\fBpcre_extra\fP data block. Its format is defined in the -.\" HTML -.\" -section on matching a pattern -.\" -in the -.\" HREF -\fBpcreapi\fP -.\" -documentation. The \fIstudy_data\fP field points to the binary study data, and -this is what you must save (not the \fBpcre_extra\fP block itself). The length -of the study data can be obtained by calling \fBpcre_fullinfo()\fP with an -argument of PCRE_INFO_STUDYSIZE. Remember to check that \fBpcre_study()\fP did -return a non-NULL value before trying to save the study data. -. -. -.SH "RE-USING A PRECOMPILED PATTERN" -.rs -.sp -Re-using a precompiled pattern is straightforward. Having reloaded it into main -memory, you pass its pointer to \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP in -the usual way. This should work even on another host, and even if that host has -the opposite endianness to the one where the pattern was compiled. -.P -However, if you passed a pointer to custom character tables when the pattern -was compiled (the \fItableptr\fP argument of \fBpcre_compile()\fP), you must -now pass a similar pointer to \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP, -because the value saved with the compiled pattern will obviously be nonsense. A -field in a \fBpcre_extra()\fP block is used to pass this data, as described in -the -.\" HTML -.\" -section on matching a pattern -.\" -in the -.\" HREF -\fBpcreapi\fP -.\" -documentation. -.P -If you did not provide custom character tables when the pattern was compiled, -the pointer in the compiled pattern is NULL, which causes \fBpcre_exec()\fP to -use PCRE's internal tables. Thus, you do not need to take any special action at -run time in this case. -.P -If you saved study data with the compiled pattern, you need to create your own -\fBpcre_extra\fP data block and set the \fIstudy_data\fP field to point to the -reloaded study data. You must also set the PCRE_EXTRA_STUDY_DATA bit in the -\fIflags\fP field to indicate that study data is present. Then pass the -\fBpcre_extra\fP block to \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP in the -usual way. -. -. -.SH "COMPATIBILITY WITH DIFFERENT PCRE RELEASES" -.rs -.sp -In general, it is safest to recompile all saved patterns when you update to a -new PCRE release, though not all updates actually require this. Recompiling is -definitely needed for release 7.2. -. -. -. -.SH AUTHOR -.rs -.sp -.nf -Philip Hazel -University Computing Service -Cambridge CB2 3QH, England. -.fi -. -. -.SH REVISION -.rs -.sp -.nf -Last updated: 13 June 2007 -Copyright (c) 1997-2007 University of Cambridge. -.fi diff --git a/libs/pcre/doc/pcresample.3 b/libs/pcre/doc/pcresample.3 deleted file mode 100644 index d27690a78c..0000000000 --- a/libs/pcre/doc/pcresample.3 +++ /dev/null @@ -1,80 +0,0 @@ -.TH PCRESAMPLE 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH "PCRE SAMPLE PROGRAM" -.rs -.sp -A simple, complete demonstration program, to get you started with using PCRE, -is supplied in the file \fIpcredemo.c\fP in the PCRE distribution. -.P -The program compiles the regular expression that is its first argument, and -matches it against the subject string in its second argument. No PCRE options -are set, and default character tables are used. If matching succeeds, the -program outputs the portion of the subject that matched, together with the -contents of any captured substrings. -.P -If the -g option is given on the command line, the program then goes on to -check for further matches of the same regular expression in the same subject -string. The logic is a little bit tricky because of the possibility of matching -an empty string. Comments in the code explain what is going on. -.P -If PCRE is installed in the standard include and library directories for your -system, you should be able to compile the demonstration program using this -command: -.sp - gcc -o pcredemo pcredemo.c -lpcre -.sp -If PCRE is installed elsewhere, you may need to add additional options to the -command line. For example, on a Unix-like system that has PCRE installed in -\fI/usr/local\fP, you can compile the demonstration program using a command -like this: -.sp -.\" JOINSH - gcc -o pcredemo -I/usr/local/include pcredemo.c \e - -L/usr/local/lib -lpcre -.sp -Once you have compiled the demonstration program, you can run simple tests like -this: -.sp - ./pcredemo 'cat|dog' 'the cat sat on the mat' - ./pcredemo -g 'cat|dog' 'the dog sat on the cat' -.sp -Note that there is a much more comprehensive test program, called -.\" HREF -\fBpcretest\fP, -.\" -which supports many more facilities for testing regular expressions and the -PCRE library. The \fBpcredemo\fP program is provided as a simple coding -example. -.P -On some operating systems (e.g. Solaris), when PCRE is not installed in the -standard library directory, you may get an error like this when you try to run -\fBpcredemo\fP: -.sp - ld.so.1: a.out: fatal: libpcre.so.0: open failed: No such file or directory -.sp -This is caused by the way shared library support works on those systems. You -need to add -.sp - -R/usr/local/lib -.sp -(for example) to the compile command to get round this problem. -. -. -.SH AUTHOR -.rs -.sp -.nf -Philip Hazel -University Computing Service -Cambridge CB2 3QH, England. -.fi -. -. -.SH REVISION -.rs -.sp -.nf -Last updated: 23 January 2008 -Copyright (c) 1997-2008 University of Cambridge. -.fi diff --git a/libs/pcre/doc/pcrestack.3 b/libs/pcre/doc/pcrestack.3 deleted file mode 100644 index 845425d97d..0000000000 --- a/libs/pcre/doc/pcrestack.3 +++ /dev/null @@ -1,160 +0,0 @@ -.TH PCRESTACK 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH "PCRE DISCUSSION OF STACK USAGE" -.rs -.sp -When you call \fBpcre_exec()\fP, it makes use of an internal function called -\fBmatch()\fP. This calls itself recursively at branch points in the pattern, -in order to remember the state of the match so that it can back up and try a -different alternative if the first one fails. As matching proceeds deeper and -deeper into the tree of possibilities, the recursion depth increases. -.P -Not all calls of \fBmatch()\fP increase the recursion depth; for an item such -as a* it may be called several times at the same level, after matching -different numbers of a's. Furthermore, in a number of cases where the result of -the recursive call would immediately be passed back as the result of the -current call (a "tail recursion"), the function is just restarted instead. -.P -The \fBpcre_dfa_exec()\fP function operates in an entirely different way, and -hardly uses recursion at all. The limit on its complexity is the amount of -workspace it is given. The comments that follow do NOT apply to -\fBpcre_dfa_exec()\fP; they are relevant only for \fBpcre_exec()\fP. -.P -You can set limits on the number of times that \fBmatch()\fP is called, both in -total and recursively. If the limit is exceeded, an error occurs. For details, -see the -.\" HTML -.\" -section on extra data for \fBpcre_exec()\fP -.\" -in the -.\" HREF -\fBpcreapi\fP -.\" -documentation. -.P -Each time that \fBmatch()\fP is actually called recursively, it uses memory -from the process stack. For certain kinds of pattern and data, very large -amounts of stack may be needed, despite the recognition of "tail recursion". -You can often reduce the amount of recursion, and therefore the amount of stack -used, by modifying the pattern that is being matched. Consider, for example, -this pattern: -.sp - ([^<]|<(?!inet))+ -.sp -It matches from wherever it starts until it encounters " -.\" -http://developer.apple.com/qa/qa2005/qa1419.html. -.\" -. -. -.SH AUTHOR -.rs -.sp -.nf -Philip Hazel -University Computing Service -Cambridge CB2 3QH, England. -.fi -. -. -.SH REVISION -.rs -.sp -.nf -Last updated: 09 July 2008 -Copyright (c) 1997-2008 University of Cambridge. -.fi diff --git a/libs/pcre/doc/pcresyntax.3 b/libs/pcre/doc/pcresyntax.3 deleted file mode 100644 index 13c1e0f3a0..0000000000 --- a/libs/pcre/doc/pcresyntax.3 +++ /dev/null @@ -1,449 +0,0 @@ -.TH PCRESYNTAX 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH "PCRE REGULAR EXPRESSION SYNTAX SUMMARY" -.rs -.sp -The full syntax and semantics of the regular expressions that are supported by -PCRE are described in the -.\" HREF -\fBpcrepattern\fP -.\" -documentation. This document contains just a quick-reference summary of the -syntax. -. -. -.SH "QUOTING" -.rs -.sp - \ex where x is non-alphanumeric is a literal x - \eQ...\eE treat enclosed characters as literal -. -. -.SH "CHARACTERS" -.rs -.sp - \ea alarm, that is, the BEL character (hex 07) - \ecx "control-x", where x is any character - \ee escape (hex 1B) - \ef formfeed (hex 0C) - \en newline (hex 0A) - \er carriage return (hex 0D) - \et tab (hex 09) - \eddd character with octal code ddd, or backreference - \exhh character with hex code hh - \ex{hhh..} character with hex code hhh.. -. -. -.SH "CHARACTER TYPES" -.rs -.sp - . any character except newline; - in dotall mode, any character whatsoever - \eC one byte, even in UTF-8 mode (best avoided) - \ed a decimal digit - \eD a character that is not a decimal digit - \eh a horizontal whitespace character - \eH a character that is not a horizontal whitespace character - \ep{\fIxx\fP} a character with the \fIxx\fP property - \eP{\fIxx\fP} a character without the \fIxx\fP property - \eR a newline sequence - \es a whitespace character - \eS a character that is not a whitespace character - \ev a vertical whitespace character - \eV a character that is not a vertical whitespace character - \ew a "word" character - \eW a "non-word" character - \eX an extended Unicode sequence -.sp -In PCRE, \ed, \eD, \es, \eS, \ew, and \eW recognize only ASCII characters. -. -. -.SH "GENERAL CATEGORY PROPERTY CODES FOR \ep and \eP" -.rs -.sp - C Other - Cc Control - Cf Format - Cn Unassigned - Co Private use - Cs Surrogate -.sp - L Letter - Ll Lower case letter - Lm Modifier letter - Lo Other letter - Lt Title case letter - Lu Upper case letter - L& Ll, Lu, or Lt -.sp - M Mark - Mc Spacing mark - Me Enclosing mark - Mn Non-spacing mark -.sp - N Number - Nd Decimal number - Nl Letter number - No Other number -.sp - P Punctuation - Pc Connector punctuation - Pd Dash punctuation - Pe Close punctuation - Pf Final punctuation - Pi Initial punctuation - Po Other punctuation - Ps Open punctuation -.sp - S Symbol - Sc Currency symbol - Sk Modifier symbol - Sm Mathematical symbol - So Other symbol -.sp - Z Separator - Zl Line separator - Zp Paragraph separator - Zs Space separator -. -. -.SH "SCRIPT NAMES FOR \ep AND \eP" -.rs -.sp -Arabic, -Armenian, -Balinese, -Bengali, -Bopomofo, -Braille, -Buginese, -Buhid, -Canadian_Aboriginal, -Carian, -Cham, -Cherokee, -Common, -Coptic, -Cuneiform, -Cypriot, -Cyrillic, -Deseret, -Devanagari, -Ethiopic, -Georgian, -Glagolitic, -Gothic, -Greek, -Gujarati, -Gurmukhi, -Han, -Hangul, -Hanunoo, -Hebrew, -Hiragana, -Inherited, -Kannada, -Katakana, -Kayah_Li, -Kharoshthi, -Khmer, -Lao, -Latin, -Lepcha, -Limbu, -Linear_B, -Lycian, -Lydian, -Malayalam, -Mongolian, -Myanmar, -New_Tai_Lue, -Nko, -Ogham, -Old_Italic, -Old_Persian, -Ol_Chiki, -Oriya, -Osmanya, -Phags_Pa, -Phoenician, -Rejang, -Runic, -Saurashtra, -Shavian, -Sinhala, -Sudanese, -Syloti_Nagri, -Syriac, -Tagalog, -Tagbanwa, -Tai_Le, -Tamil, -Telugu, -Thaana, -Thai, -Tibetan, -Tifinagh, -Ugaritic, -Vai, -Yi. -. -. -.SH "CHARACTER CLASSES" -.rs -.sp - [...] positive character class - [^...] negative character class - [x-y] range (can be used for hex characters) - [[:xxx:]] positive POSIX named set - [[:^xxx:]] negative POSIX named set -.sp - alnum alphanumeric - alpha alphabetic - ascii 0-127 - blank space or tab - cntrl control character - digit decimal digit - graph printing, excluding space - lower lower case letter - print printing, including space - punct printing, excluding alphanumeric - space whitespace - upper upper case letter - word same as \ew - xdigit hexadecimal digit -.sp -In PCRE, POSIX character set names recognize only ASCII characters. You can use -\eQ...\eE inside a character class. -. -. -.SH "QUANTIFIERS" -.rs -.sp - ? 0 or 1, greedy - ?+ 0 or 1, possessive - ?? 0 or 1, lazy - * 0 or more, greedy - *+ 0 or more, possessive - *? 0 or more, lazy - + 1 or more, greedy - ++ 1 or more, possessive - +? 1 or more, lazy - {n} exactly n - {n,m} at least n, no more than m, greedy - {n,m}+ at least n, no more than m, possessive - {n,m}? at least n, no more than m, lazy - {n,} n or more, greedy - {n,}+ n or more, possessive - {n,}? n or more, lazy -. -. -.SH "ANCHORS AND SIMPLE ASSERTIONS" -.rs -.sp - \eb word boundary (only ASCII letters recognized) - \eB not a word boundary - ^ start of subject - also after internal newline in multiline mode - \eA start of subject - $ end of subject - also before newline at end of subject - also before internal newline in multiline mode - \eZ end of subject - also before newline at end of subject - \ez end of subject - \eG first matching position in subject -. -. -.SH "MATCH POINT RESET" -.rs -.sp - \eK reset start of match -. -. -.SH "ALTERNATION" -.rs -.sp - expr|expr|expr... -. -. -.SH "CAPTURING" -.rs -.sp - (...) capturing group - (?...) named capturing group (Perl) - (?'name'...) named capturing group (Perl) - (?P...) named capturing group (Python) - (?:...) non-capturing group - (?|...) non-capturing group; reset group numbers for - capturing groups in each alternative -. -. -.SH "ATOMIC GROUPS" -.rs -.sp - (?>...) atomic, non-capturing group -. -. -. -. -.SH "COMMENT" -.rs -.sp - (?#....) comment (not nestable) -. -. -.SH "OPTION SETTING" -.rs -.sp - (?i) caseless - (?J) allow duplicate names - (?m) multiline - (?s) single line (dotall) - (?U) default ungreedy (lazy) - (?x) extended (ignore white space) - (?-...) unset option(s) -.sp -The following is recognized only at the start of a pattern or after one of the -newline-setting options with similar syntax: -.sp - (*UTF8) set UTF-8 mode -. -. -.SH "LOOKAHEAD AND LOOKBEHIND ASSERTIONS" -.rs -.sp - (?=...) positive look ahead - (?!...) negative look ahead - (?<=...) positive look behind - (? reference by name (Perl) - \ek'name' reference by name (Perl) - \eg{name} reference by name (Perl) - \ek{name} reference by name (.NET) - (?P=name) reference by name (Python) -. -. -.SH "SUBROUTINE REFERENCES (POSSIBLY RECURSIVE)" -.rs -.sp - (?R) recurse whole pattern - (?n) call subpattern by absolute number - (?+n) call subpattern by relative number - (?-n) call subpattern by relative number - (?&name) call subpattern by name (Perl) - (?P>name) call subpattern by name (Python) - \eg call subpattern by name (Oniguruma) - \eg'name' call subpattern by name (Oniguruma) - \eg call subpattern by absolute number (Oniguruma) - \eg'n' call subpattern by absolute number (Oniguruma) - \eg<+n> call subpattern by relative number (PCRE extension) - \eg'+n' call subpattern by relative number (PCRE extension) - \eg<-n> call subpattern by relative number (PCRE extension) - \eg'-n' call subpattern by relative number (PCRE extension) -. -. -.SH "CONDITIONAL PATTERNS" -.rs -.sp - (?(condition)yes-pattern) - (?(condition)yes-pattern|no-pattern) -.sp - (?(n)... absolute reference condition - (?(+n)... relative reference condition - (?(-n)... relative reference condition - (?()... named reference condition (Perl) - (?('name')... named reference condition (Perl) - (?(name)... named reference condition (PCRE) - (?(R)... overall recursion condition - (?(Rn)... specific group recursion condition - (?(R&name)... specific recursion condition - (?(DEFINE)... define subpattern for reference - (?(assert)... assertion condition -. -. -.SH "BACKTRACKING CONTROL" -.rs -.sp -The following act immediately they are reached: -.sp - (*ACCEPT) force successful match - (*FAIL) force backtrack; synonym (*F) -.sp -The following act only when a subsequent match failure causes a backtrack to -reach them. They all force a match failure, but they differ in what happens -afterwards. Those that advance the start-of-match point do so only if the -pattern is not anchored. -.sp - (*COMMIT) overall failure, no advance of starting point - (*PRUNE) advance to next starting character - (*SKIP) advance start to current matching position - (*THEN) local failure, backtrack to next alternation -. -. -.SH "NEWLINE CONVENTIONS" -.rs -.sp -These are recognized only at the very start of the pattern or after a -(*BSR_...) or (*UTF8) option. -.sp - (*CR) carriage return only - (*LF) linefeed only - (*CRLF) carriage return followed by linefeed - (*ANYCRLF) all three of the above - (*ANY) any Unicode newline sequence -. -. -.SH "WHAT \eR MATCHES" -.rs -.sp -These are recognized only at the very start of the pattern or after a -(*...) option that sets the newline convention or UTF-8 mode. -.sp - (*BSR_ANYCRLF) CR, LF, or CRLF - (*BSR_UNICODE) any Unicode newline sequence -. -. -.SH "CALLOUTS" -.rs -.sp - (?C) callout - (?Cn) callout with data n -. -. -.SH "SEE ALSO" -.rs -.sp -\fBpcrepattern\fP(3), \fBpcreapi\fP(3), \fBpcrecallout\fP(3), -\fBpcrematching\fP(3), \fBpcre\fP(3). -. -. -.SH AUTHOR -.rs -.sp -.nf -Philip Hazel -University Computing Service -Cambridge CB2 3QH, England. -.fi -. -. -.SH REVISION -.rs -.sp -.nf -Last updated: 11 April 2009 -Copyright (c) 1997-2009 University of Cambridge. -.fi diff --git a/libs/pcre/doc/pcretest.1 b/libs/pcre/doc/pcretest.1 deleted file mode 100644 index dc2f4a8c13..0000000000 --- a/libs/pcre/doc/pcretest.1 +++ /dev/null @@ -1,728 +0,0 @@ -.TH PCRETEST 1 -.SH NAME -pcretest - a program for testing Perl-compatible regular expressions. -.SH SYNOPSIS -.rs -.sp -.B pcretest "[options] [source] [destination]" -.sp -\fBpcretest\fP was written as a test program for the PCRE regular expression -library itself, but it can also be used for experimenting with regular -expressions. This document describes the features of the test program; for -details of the regular expressions themselves, see the -.\" HREF -\fBpcrepattern\fP -.\" -documentation. For details of the PCRE library function calls and their -options, see the -.\" HREF -\fBpcreapi\fP -.\" -documentation. -. -. -.SH OPTIONS -.rs -.TP 10 -\fB-b\fP -Behave as if each regex has the \fB/B\fP (show bytecode) modifier; the internal -form is output after compilation. -.TP 10 -\fB-C\fP -Output the version number of the PCRE library, and all available information -about the optional features that are included, and then exit. -.TP 10 -\fB-d\fP -Behave as if each regex has the \fB/D\fP (debug) modifier; the internal -form and information about the compiled pattern is output after compilation; -\fB-d\fP is equivalent to \fB-b -i\fP. -.TP 10 -\fB-dfa\fP -Behave as if each data line contains the \eD escape sequence; this causes the -alternative matching function, \fBpcre_dfa_exec()\fP, to be used instead of the -standard \fBpcre_exec()\fP function (more detail is given below). -.TP 10 -\fB-help\fP -Output a brief summary these options and then exit. -.TP 10 -\fB-i\fP -Behave as if each regex has the \fB/I\fP modifier; information about the -compiled pattern is given after compilation. -.TP 10 -\fB-M\fP -Behave as if each data line contains the \eM escape sequence; this causes -PCRE to discover the minimum MATCH_LIMIT and MATCH_LIMIT_RECURSION settings by -calling \fBpcre_exec()\fP repeatedly with different limits. -.TP 10 -\fB-m\fP -Output the size of each compiled pattern after it has been compiled. This is -equivalent to adding \fB/M\fP to each regular expression. For compatibility -with earlier versions of pcretest, \fB-s\fP is a synonym for \fB-m\fP. -.TP 10 -\fB-o\fP \fIosize\fP -Set the number of elements in the output vector that is used when calling -\fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP to be \fIosize\fP. The default value -is 45, which is enough for 14 capturing subexpressions for \fBpcre_exec()\fP or -22 different matches for \fBpcre_dfa_exec()\fP. The vector size can be -changed for individual matching calls by including \eO in the data line (see -below). -.TP 10 -\fB-p\fP -Behave as if each regex has the \fB/P\fP modifier; the POSIX wrapper API is -used to call PCRE. None of the other options has any effect when \fB-p\fP is -set. -.TP 10 -\fB-q\fP -Do not output the version number of \fBpcretest\fP at the start of execution. -.TP 10 -\fB-S\fP \fIsize\fP -On Unix-like systems, set the size of the runtime stack to \fIsize\fP -megabytes. -.TP 10 -\fB-t\fP -Run each compile, study, and match many times with a timer, and output -resulting time per compile or match (in milliseconds). Do not set \fB-m\fP with -\fB-t\fP, because you will then get the size output a zillion times, and the -timing will be distorted. You can control the number of iterations that are -used for timing by following \fB-t\fP with a number (as a separate item on the -command line). For example, "-t 1000" would iterate 1000 times. The default is -to iterate 500000 times. -.TP 10 -\fB-tm\fP -This is like \fB-t\fP except that it times only the matching phase, not the -compile or study phases. -. -. -.SH DESCRIPTION -.rs -.sp -If \fBpcretest\fP is given two filename arguments, it reads from the first and -writes to the second. If it is given only one filename argument, it reads from -that file and writes to stdout. Otherwise, it reads from stdin and writes to -stdout, and prompts for each line of input, using "re>" to prompt for regular -expressions, and "data>" to prompt for data lines. -.P -When \fBpcretest\fP is built, a configuration option can specify that it should -be linked with the \fBlibreadline\fP library. When this is done, if the input -is from a terminal, it is read using the \fBreadline()\fP function. This -provides line-editing and history facilities. The output from the \fB-help\fP -option states whether or not \fBreadline()\fP will be used. -.P -The program handles any number of sets of input on a single input file. Each -set starts with a regular expression, and continues with any number of data -lines to be matched against the pattern. -.P -Each data line is matched separately and independently. If you want to do -multi-line matches, you have to use the \en escape sequence (or \er or \er\en, -etc., depending on the newline setting) in a single line of input to encode the -newline sequences. There is no limit on the length of data lines; the input -buffer is automatically extended if it is too small. -.P -An empty line signals the end of the data lines, at which point a new regular -expression is read. The regular expressions are given enclosed in any -non-alphanumeric delimiters other than backslash, for example: -.sp - /(a|bc)x+yz/ -.sp -White space before the initial delimiter is ignored. A regular expression may -be continued over several input lines, in which case the newline characters are -included within it. It is possible to include the delimiter within the pattern -by escaping it, for example -.sp - /abc\e/def/ -.sp -If you do so, the escape and the delimiter form part of the pattern, but since -delimiters are always non-alphanumeric, this does not affect its interpretation. -If the terminating delimiter is immediately followed by a backslash, for -example, -.sp - /abc/\e -.sp -then a backslash is added to the end of the pattern. This is done to provide a -way of testing the error condition that arises if a pattern finishes with a -backslash, because -.sp - /abc\e/ -.sp -is interpreted as the first line of a pattern that starts with "abc/", causing -pcretest to read the next line as a continuation of the regular expression. -. -. -.SH "PATTERN MODIFIERS" -.rs -.sp -A pattern may be followed by any number of modifiers, which are mostly single -characters. Following Perl usage, these are referred to below as, for example, -"the \fB/i\fP modifier", even though the delimiter of the pattern need not -always be a slash, and no slash is used when writing modifiers. Whitespace may -appear between the final pattern delimiter and the first modifier, and between -the modifiers themselves. -.P -The \fB/i\fP, \fB/m\fP, \fB/s\fP, and \fB/x\fP modifiers set the PCRE_CASELESS, -PCRE_MULTILINE, PCRE_DOTALL, or PCRE_EXTENDED options, respectively, when -\fBpcre_compile()\fP is called. These four modifier letters have the same -effect as they do in Perl. For example: -.sp - /caseless/i -.sp -The following table shows additional modifiers for setting PCRE options that do -not correspond to anything in Perl: -.sp - \fB/A\fP PCRE_ANCHORED - \fB/C\fP PCRE_AUTO_CALLOUT - \fB/E\fP PCRE_DOLLAR_ENDONLY - \fB/f\fP PCRE_FIRSTLINE - \fB/J\fP PCRE_DUPNAMES - \fB/N\fP PCRE_NO_AUTO_CAPTURE - \fB/U\fP PCRE_UNGREEDY - \fB/X\fP PCRE_EXTRA - \fB/\fP PCRE_JAVASCRIPT_COMPAT - \fB/\fP PCRE_NEWLINE_CR - \fB/\fP PCRE_NEWLINE_LF - \fB/\fP PCRE_NEWLINE_CRLF - \fB/\fP PCRE_NEWLINE_ANYCRLF - \fB/\fP PCRE_NEWLINE_ANY - \fB/\fP PCRE_BSR_ANYCRLF - \fB/\fP PCRE_BSR_UNICODE -.sp -Those specifying line ending sequences are literal strings as shown, but the -letters can be in either case. This example sets multiline matching with CRLF -as the line ending sequence: -.sp - /^abc/m -.sp -Details of the meanings of these PCRE options are given in the -.\" HREF -\fBpcreapi\fP -.\" -documentation. -. -. -.SS "Finding all matches in a string" -.rs -.sp -Searching for all possible matches within each subject string can be requested -by the \fB/g\fP or \fB/G\fP modifier. After finding a match, PCRE is called -again to search the remainder of the subject string. The difference between -\fB/g\fP and \fB/G\fP is that the former uses the \fIstartoffset\fP argument to -\fBpcre_exec()\fP to start searching at a new point within the entire string -(which is in effect what Perl does), whereas the latter passes over a shortened -substring. This makes a difference to the matching process if the pattern -begins with a lookbehind assertion (including \eb or \eB). -.P -If any call to \fBpcre_exec()\fP in a \fB/g\fP or \fB/G\fP sequence matches an -empty string, the next call is done with the PCRE_NOTEMPTY and PCRE_ANCHORED -flags set in order to search for another, non-empty, match at the same point. -If this second match fails, the start offset is advanced by one, and the normal -match is retried. This imitates the way Perl handles such cases when using the -\fB/g\fP modifier or the \fBsplit()\fP function. -. -. -.SS "Other modifiers" -.rs -.sp -There are yet more modifiers for controlling the way \fBpcretest\fP -operates. -.P -The \fB/+\fP modifier requests that as well as outputting the substring that -matched the entire pattern, pcretest should in addition output the remainder of -the subject string. This is useful for tests where the subject contains -multiple copies of the same substring. -.P -The \fB/B\fP modifier is a debugging feature. It requests that \fBpcretest\fP -output a representation of the compiled byte code after compilation. Normally -this information contains length and offset values; however, if \fB/Z\fP is -also present, this data is replaced by spaces. This is a special feature for -use in the automatic test scripts; it ensures that the same output is generated -for different internal link sizes. -.P -The \fB/L\fP modifier must be followed directly by the name of a locale, for -example, -.sp - /pattern/Lfr_FR -.sp -For this reason, it must be the last modifier. The given locale is set, -\fBpcre_maketables()\fP is called to build a set of character tables for the -locale, and this is then passed to \fBpcre_compile()\fP when compiling the -regular expression. Without an \fB/L\fP modifier, NULL is passed as the tables -pointer; that is, \fB/L\fP applies only to the expression on which it appears. -.P -The \fB/I\fP modifier requests that \fBpcretest\fP output information about the -compiled pattern (whether it is anchored, has a fixed first character, and -so on). It does this by calling \fBpcre_fullinfo()\fP after compiling a -pattern. If the pattern is studied, the results of that are also output. -.P -The \fB/D\fP modifier is a PCRE debugging feature, and is equivalent to -\fB/BI\fP, that is, both the \fB/B\fP and the \fB/I\fP modifiers. -.P -The \fB/F\fP modifier causes \fBpcretest\fP to flip the byte order of the -fields in the compiled pattern that contain 2-byte and 4-byte numbers. This -facility is for testing the feature in PCRE that allows it to execute patterns -that were compiled on a host with a different endianness. This feature is not -available when the POSIX interface to PCRE is being used, that is, when the -\fB/P\fP pattern modifier is specified. See also the section about saving and -reloading compiled patterns below. -.P -The \fB/S\fP modifier causes \fBpcre_study()\fP to be called after the -expression has been compiled, and the results used when the expression is -matched. -.P -The \fB/M\fP modifier causes the size of memory block used to hold the compiled -pattern to be output. -.P -The \fB/P\fP modifier causes \fBpcretest\fP to call PCRE via the POSIX wrapper -API rather than its native API. When this is done, all other modifiers except -\fB/i\fP, \fB/m\fP, and \fB/+\fP are ignored. REG_ICASE is set if \fB/i\fP is -present, and REG_NEWLINE is set if \fB/m\fP is present. The wrapper functions -force PCRE_DOLLAR_ENDONLY always, and PCRE_DOTALL unless REG_NEWLINE is set. -.P -The \fB/8\fP modifier causes \fBpcretest\fP to call PCRE with the PCRE_UTF8 -option set. This turns on support for UTF-8 character handling in PCRE, -provided that it was compiled with this support enabled. This modifier also -causes any non-printing characters in output strings to be printed using the -\ex{hh...} notation if they are valid UTF-8 sequences. -.P -If the \fB/?\fP modifier is used with \fB/8\fP, it causes \fBpcretest\fP to -call \fBpcre_compile()\fP with the PCRE_NO_UTF8_CHECK option, to suppress the -checking of the string for UTF-8 validity. -. -. -.SH "DATA LINES" -.rs -.sp -Before each data line is passed to \fBpcre_exec()\fP, leading and trailing -whitespace is removed, and it is then scanned for \e escapes. Some of these are -pretty esoteric features, intended for checking out some of the more -complicated features of PCRE. If you are just testing "ordinary" regular -expressions, you probably don't need any of these. The following escapes are -recognized: -.sp - \ea alarm (BEL, \ex07) - \eb backspace (\ex08) - \ee escape (\ex27) - \ef formfeed (\ex0c) - \en newline (\ex0a) -.\" JOIN - \eqdd set the PCRE_MATCH_LIMIT limit to dd - (any number of digits) - \er carriage return (\ex0d) - \et tab (\ex09) - \ev vertical tab (\ex0b) - \ennn octal character (up to 3 octal digits) - \exhh hexadecimal character (up to 2 hex digits) -.\" JOIN - \ex{hh...} hexadecimal character, any number of digits - in UTF-8 mode -.\" JOIN - \eA pass the PCRE_ANCHORED option to \fBpcre_exec()\fP - or \fBpcre_dfa_exec()\fP -.\" JOIN - \eB pass the PCRE_NOTBOL option to \fBpcre_exec()\fP - or \fBpcre_dfa_exec()\fP -.\" JOIN - \eCdd call pcre_copy_substring() for substring dd - after a successful match (number less than 32) -.\" JOIN - \eCname call pcre_copy_named_substring() for substring - "name" after a successful match (name termin- - ated by next non alphanumeric character) -.\" JOIN - \eC+ show the current captured substrings at callout - time - \eC- do not supply a callout function -.\" JOIN - \eC!n return 1 instead of 0 when callout number n is - reached -.\" JOIN - \eC!n!m return 1 instead of 0 when callout number n is - reached for the nth time -.\" JOIN - \eC*n pass the number n (may be negative) as callout - data; this is used as the callout return value - \eD use the \fBpcre_dfa_exec()\fP match function - \eF only shortest match for \fBpcre_dfa_exec()\fP -.\" JOIN - \eGdd call pcre_get_substring() for substring dd - after a successful match (number less than 32) -.\" JOIN - \eGname call pcre_get_named_substring() for substring - "name" after a successful match (name termin- - ated by next non-alphanumeric character) -.\" JOIN - \eL call pcre_get_substringlist() after a - successful match -.\" JOIN - \eM discover the minimum MATCH_LIMIT and - MATCH_LIMIT_RECURSION settings -.\" JOIN - \eN pass the PCRE_NOTEMPTY option to \fBpcre_exec()\fP - or \fBpcre_dfa_exec()\fP -.\" JOIN - \eOdd set the size of the output vector passed to - \fBpcre_exec()\fP to dd (any number of digits) -.\" JOIN - \eP pass the PCRE_PARTIAL option to \fBpcre_exec()\fP - or \fBpcre_dfa_exec()\fP -.\" JOIN - \eQdd set the PCRE_MATCH_LIMIT_RECURSION limit to dd - (any number of digits) - \eR pass the PCRE_DFA_RESTART option to \fBpcre_dfa_exec()\fP - \eS output details of memory get/free calls during matching -.\" JOIN - \eZ pass the PCRE_NOTEOL option to \fBpcre_exec()\fP - or \fBpcre_dfa_exec()\fP -.\" JOIN - \e? pass the PCRE_NO_UTF8_CHECK option to - \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP - \e>dd start the match at offset dd (any number of digits); -.\" JOIN - this sets the \fIstartoffset\fP argument for \fBpcre_exec()\fP - or \fBpcre_dfa_exec()\fP -.\" JOIN - \e pass the PCRE_NEWLINE_CR option to \fBpcre_exec()\fP - or \fBpcre_dfa_exec()\fP -.\" JOIN - \e pass the PCRE_NEWLINE_LF option to \fBpcre_exec()\fP - or \fBpcre_dfa_exec()\fP -.\" JOIN - \e pass the PCRE_NEWLINE_CRLF option to \fBpcre_exec()\fP - or \fBpcre_dfa_exec()\fP -.\" JOIN - \e pass the PCRE_NEWLINE_ANYCRLF option to \fBpcre_exec()\fP - or \fBpcre_dfa_exec()\fP -.\" JOIN - \e pass the PCRE_NEWLINE_ANY option to \fBpcre_exec()\fP - or \fBpcre_dfa_exec()\fP -.sp -The escapes that specify line ending sequences are literal strings, exactly as -shown. No more than one newline setting should be present in any data line. -.P -A backslash followed by anything else just escapes the anything else. If -the very last character is a backslash, it is ignored. This gives a way of -passing an empty line as data, since a real empty line terminates the data -input. -.P -If \eM is present, \fBpcretest\fP calls \fBpcre_exec()\fP several times, with -different values in the \fImatch_limit\fP and \fImatch_limit_recursion\fP -fields of the \fBpcre_extra\fP data structure, until it finds the minimum -numbers for each parameter that allow \fBpcre_exec()\fP to complete. The -\fImatch_limit\fP number is a measure of the amount of backtracking that takes -place, and checking it out can be instructive. For most simple matches, the -number is quite small, but for patterns with very large numbers of matching -possibilities, it can become large very quickly with increasing length of -subject string. The \fImatch_limit_recursion\fP number is a measure of how much -stack (or, if PCRE is compiled with NO_RECURSE, how much heap) memory is needed -to complete the match attempt. -.P -When \eO is used, the value specified may be higher or lower than the size set -by the \fB-O\fP command line option (or defaulted to 45); \eO applies only to -the call of \fBpcre_exec()\fP for the line in which it appears. -.P -If the \fB/P\fP modifier was present on the pattern, causing the POSIX wrapper -API to be used, the only option-setting sequences that have any effect are \eB -and \eZ, causing REG_NOTBOL and REG_NOTEOL, respectively, to be passed to -\fBregexec()\fP. -.P -The use of \ex{hh...} to represent UTF-8 characters is not dependent on the use -of the \fB/8\fP modifier on the pattern. It is recognized always. There may be -any number of hexadecimal digits inside the braces. The result is from one to -six bytes, encoded according to the original UTF-8 rules of RFC 2279. This -allows for values in the range 0 to 0x7FFFFFFF. Note that not all of those are -valid Unicode code points, or indeed valid UTF-8 characters according to the -later rules in RFC 3629. -. -. -.SH "THE ALTERNATIVE MATCHING FUNCTION" -.rs -.sp -By default, \fBpcretest\fP uses the standard PCRE matching function, -\fBpcre_exec()\fP to match each data line. From release 6.0, PCRE supports an -alternative matching function, \fBpcre_dfa_test()\fP, which operates in a -different way, and has some restrictions. The differences between the two -functions are described in the -.\" HREF -\fBpcrematching\fP -.\" -documentation. -.P -If a data line contains the \eD escape sequence, or if the command line -contains the \fB-dfa\fP option, the alternative matching function is called. -This function finds all possible matches at a given point. If, however, the \eF -escape sequence is present in the data line, it stops after the first match is -found. This is always the shortest possible match. -. -. -.SH "DEFAULT OUTPUT FROM PCRETEST" -.rs -.sp -This section describes the output when the normal matching function, -\fBpcre_exec()\fP, is being used. -.P -When a match succeeds, pcretest outputs the list of captured substrings that -\fBpcre_exec()\fP returns, starting with number 0 for the string that matched -the whole pattern. Otherwise, it outputs "No match" or "Partial match" -when \fBpcre_exec()\fP returns PCRE_ERROR_NOMATCH or PCRE_ERROR_PARTIAL, -respectively, and otherwise the PCRE negative error number. Here is an example -of an interactive \fBpcretest\fP run. -.sp - $ pcretest - PCRE version 7.0 30-Nov-2006 -.sp - re> /^abc(\ed+)/ - data> abc123 - 0: abc123 - 1: 123 - data> xyz - No match -.sp -Note that unset capturing substrings that are not followed by one that is set -are not returned by \fBpcre_exec()\fP, and are not shown by \fBpcretest\fP. In -the following example, there are two capturing substrings, but when the first -data line is matched, the second, unset substring is not shown. An "internal" -unset substring is shown as "", as for the second data line. -.sp - re> /(a)|(b)/ - data> a - 0: a - 1: a - data> b - 0: b - 1: - 2: b -.sp -If the strings contain any non-printing characters, they are output as \e0x -escapes, or as \ex{...} escapes if the \fB/8\fP modifier was present on the -pattern. See below for the definition of non-printing characters. If the -pattern has the \fB/+\fP modifier, the output for substring 0 is followed by -the the rest of the subject string, identified by "0+" like this: -.sp - re> /cat/+ - data> cataract - 0: cat - 0+ aract -.sp -If the pattern has the \fB/g\fP or \fB/G\fP modifier, the results of successive -matching attempts are output in sequence, like this: -.sp - re> /\eBi(\ew\ew)/g - data> Mississippi - 0: iss - 1: ss - 0: iss - 1: ss - 0: ipp - 1: pp -.sp -"No match" is output only if the first match attempt fails. -.P -If any of the sequences \fB\eC\fP, \fB\eG\fP, or \fB\eL\fP are present in a -data line that is successfully matched, the substrings extracted by the -convenience functions are output with C, G, or L after the string number -instead of a colon. This is in addition to the normal full list. The string -length (that is, the return from the extraction function) is given in -parentheses after each string for \fB\eC\fP and \fB\eG\fP. -.P -Note that whereas patterns can be continued over several lines (a plain ">" -prompt is used for continuations), data lines may not. However newlines can be -included in data by means of the \en escape (or \er, \er\en, etc., depending on -the newline sequence setting). -. -. -. -.SH "OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION" -.rs -.sp -When the alternative matching function, \fBpcre_dfa_exec()\fP, is used (by -means of the \eD escape sequence or the \fB-dfa\fP command line option), the -output consists of a list of all the matches that start at the first point in -the subject where there is at least one match. For example: -.sp - re> /(tang|tangerine|tan)/ - data> yellow tangerine\eD - 0: tangerine - 1: tang - 2: tan -.sp -(Using the normal matching function on this data finds only "tang".) The -longest matching string is always given first (and numbered zero). -.P -If \fB/g\fP is present on the pattern, the search for further matches resumes -at the end of the longest match. For example: -.sp - re> /(tang|tangerine|tan)/g - data> yellow tangerine and tangy sultana\eD - 0: tangerine - 1: tang - 2: tan - 0: tang - 1: tan - 0: tan -.sp -Since the matching function does not support substring capture, the escape -sequences that are concerned with captured substrings are not relevant. -. -. -.SH "RESTARTING AFTER A PARTIAL MATCH" -.rs -.sp -When the alternative matching function has given the PCRE_ERROR_PARTIAL return, -indicating that the subject partially matched the pattern, you can restart the -match with additional subject data by means of the \eR escape sequence. For -example: -.sp - re> /^\ed?\ed(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\ed\ed$/ - data> 23ja\eP\eD - Partial match: 23ja - data> n05\eR\eD - 0: n05 -.sp -For further information about partial matching, see the -.\" HREF -\fBpcrepartial\fP -.\" -documentation. -. -. -.SH CALLOUTS -.rs -.sp -If the pattern contains any callout requests, \fBpcretest\fP's callout function -is called during matching. This works with both matching functions. By default, -the called function displays the callout number, the start and current -positions in the text at the callout time, and the next pattern item to be -tested. For example, the output -.sp - --->pqrabcdef - 0 ^ ^ \ed -.sp -indicates that callout number 0 occurred for a match attempt starting at the -fourth character of the subject string, when the pointer was at the seventh -character of the data, and when the next pattern item was \ed. Just one -circumflex is output if the start and current positions are the same. -.P -Callouts numbered 255 are assumed to be automatic callouts, inserted as a -result of the \fB/C\fP pattern modifier. In this case, instead of showing the -callout number, the offset in the pattern, preceded by a plus, is output. For -example: -.sp - re> /\ed?[A-E]\e*/C - data> E* - --->E* - +0 ^ \ed? - +3 ^ [A-E] - +8 ^^ \e* - +10 ^ ^ - 0: E* -.sp -The callout function in \fBpcretest\fP returns zero (carry on matching) by -default, but you can use a \eC item in a data line (as described above) to -change this. -.P -Inserting callouts can be helpful when using \fBpcretest\fP to check -complicated regular expressions. For further information about callouts, see -the -.\" HREF -\fBpcrecallout\fP -.\" -documentation. -. -. -. -.SH "NON-PRINTING CHARACTERS" -.rs -.sp -When \fBpcretest\fP is outputting text in the compiled version of a pattern, -bytes other than 32-126 are always treated as non-printing characters are are -therefore shown as hex escapes. -.P -When \fBpcretest\fP is outputting text that is a matched part of a subject -string, it behaves in the same way, unless a different locale has been set for -the pattern (using the \fB/L\fP modifier). In this case, the \fBisprint()\fP -function to distinguish printing and non-printing characters. -. -. -. -.SH "SAVING AND RELOADING COMPILED PATTERNS" -.rs -.sp -The facilities described in this section are not available when the POSIX -inteface to PCRE is being used, that is, when the \fB/P\fP pattern modifier is -specified. -.P -When the POSIX interface is not in use, you can cause \fBpcretest\fP to write a -compiled pattern to a file, by following the modifiers with > and a file name. -For example: -.sp - /pattern/im >/some/file -.sp -See the -.\" HREF -\fBpcreprecompile\fP -.\" -documentation for a discussion about saving and re-using compiled patterns. -.P -The data that is written is binary. The first eight bytes are the length of the -compiled pattern data followed by the length of the optional study data, each -written as four bytes in big-endian order (most significant byte first). If -there is no study data (either the pattern was not studied, or studying did not -return any data), the second length is zero. The lengths are followed by an -exact copy of the compiled pattern. If there is additional study data, this -follows immediately after the compiled pattern. After writing the file, -\fBpcretest\fP expects to read a new pattern. -.P -A saved pattern can be reloaded into \fBpcretest\fP by specifing < and a file -name instead of a pattern. The name of the file must not contain a < character, -as otherwise \fBpcretest\fP will interpret the line as a pattern delimited by < -characters. -For example: -.sp - re> " to prompt for regular expressions, and "data>" to prompt for data - lines. - - When pcretest is built, a configuration option can specify that it - should be linked with the libreadline library. When this is done, if - the input is from a terminal, it is read using the readline() function. - This provides line-editing and history facilities. The output from the - -help option states whether or not readline() will be used. - - The program handles any number of sets of input on a single input file. - Each set starts with a regular expression, and continues with any num- - ber of data lines to be matched against the pattern. - - Each data line is matched separately and independently. If you want to - do multi-line matches, you have to use the \n escape sequence (or \r or - \r\n, etc., depending on the newline setting) in a single line of input - to encode the newline sequences. There is no limit on the length of - data lines; the input buffer is automatically extended if it is too - small. - - An empty line signals the end of the data lines, at which point a new - regular expression is read. The regular expressions are given enclosed - in any non-alphanumeric delimiters other than backslash, for example: - - /(a|bc)x+yz/ - - White space before the initial delimiter is ignored. A regular expres- - sion may be continued over several input lines, in which case the new- - line characters are included within it. It is possible to include the - delimiter within the pattern by escaping it, for example - - /abc\/def/ - - If you do so, the escape and the delimiter form part of the pattern, - but since delimiters are always non-alphanumeric, this does not affect - its interpretation. If the terminating delimiter is immediately fol- - lowed by a backslash, for example, - - /abc/\ - - then a backslash is added to the end of the pattern. This is done to - provide a way of testing the error condition that arises if a pattern - finishes with a backslash, because - - /abc\/ - - is interpreted as the first line of a pattern that starts with "abc/", - causing pcretest to read the next line as a continuation of the regular - expression. - - -PATTERN MODIFIERS - - A pattern may be followed by any number of modifiers, which are mostly - single characters. Following Perl usage, these are referred to below - as, for example, "the /i modifier", even though the delimiter of the - pattern need not always be a slash, and no slash is used when writing - modifiers. Whitespace may appear between the final pattern delimiter - and the first modifier, and between the modifiers themselves. - - The /i, /m, /s, and /x modifiers set the PCRE_CASELESS, PCRE_MULTILINE, - PCRE_DOTALL, or PCRE_EXTENDED options, respectively, when pcre_com- - pile() is called. These four modifier letters have the same effect as - they do in Perl. For example: - - /caseless/i - - The following table shows additional modifiers for setting PCRE options - that do not correspond to anything in Perl: - - /A PCRE_ANCHORED - /C PCRE_AUTO_CALLOUT - /E PCRE_DOLLAR_ENDONLY - /f PCRE_FIRSTLINE - /J PCRE_DUPNAMES - /N PCRE_NO_AUTO_CAPTURE - /U PCRE_UNGREEDY - /X PCRE_EXTRA - / PCRE_JAVASCRIPT_COMPAT - / PCRE_NEWLINE_CR - / PCRE_NEWLINE_LF - / PCRE_NEWLINE_CRLF - / PCRE_NEWLINE_ANYCRLF - / PCRE_NEWLINE_ANY - / PCRE_BSR_ANYCRLF - / PCRE_BSR_UNICODE - - Those specifying line ending sequences are literal strings as shown, - but the letters can be in either case. This example sets multiline - matching with CRLF as the line ending sequence: - - /^abc/m - - Details of the meanings of these PCRE options are given in the pcreapi - documentation. - - Finding all matches in a string - - Searching for all possible matches within each subject string can be - requested by the /g or /G modifier. After finding a match, PCRE is - called again to search the remainder of the subject string. The differ- - ence between /g and /G is that the former uses the startoffset argument - to pcre_exec() to start searching at a new point within the entire - string (which is in effect what Perl does), whereas the latter passes - over a shortened substring. This makes a difference to the matching - process if the pattern begins with a lookbehind assertion (including \b - or \B). - - If any call to pcre_exec() in a /g or /G sequence matches an empty - string, the next call is done with the PCRE_NOTEMPTY and PCRE_ANCHORED - flags set in order to search for another, non-empty, match at the same - point. If this second match fails, the start offset is advanced by - one, and the normal match is retried. This imitates the way Perl han- - dles such cases when using the /g modifier or the split() function. - - Other modifiers - - There are yet more modifiers for controlling the way pcretest operates. - - The /+ modifier requests that as well as outputting the substring that - matched the entire pattern, pcretest should in addition output the - remainder of the subject string. This is useful for tests where the - subject contains multiple copies of the same substring. - - The /B modifier is a debugging feature. It requests that pcretest out- - put a representation of the compiled byte code after compilation. Nor- - mally this information contains length and offset values; however, if - /Z is also present, this data is replaced by spaces. This is a special - feature for use in the automatic test scripts; it ensures that the same - output is generated for different internal link sizes. - - The /L modifier must be followed directly by the name of a locale, for - example, - - /pattern/Lfr_FR - - For this reason, it must be the last modifier. The given locale is set, - pcre_maketables() is called to build a set of character tables for the - locale, and this is then passed to pcre_compile() when compiling the - regular expression. Without an /L modifier, NULL is passed as the - tables pointer; that is, /L applies only to the expression on which it - appears. - - The /I modifier requests that pcretest output information about the - compiled pattern (whether it is anchored, has a fixed first character, - and so on). It does this by calling pcre_fullinfo() after compiling a - pattern. If the pattern is studied, the results of that are also out- - put. - - The /D modifier is a PCRE debugging feature, and is equivalent to /BI, - that is, both the /B and the /I modifiers. - - The /F modifier causes pcretest to flip the byte order of the fields in - the compiled pattern that contain 2-byte and 4-byte numbers. This - facility is for testing the feature in PCRE that allows it to execute - patterns that were compiled on a host with a different endianness. This - feature is not available when the POSIX interface to PCRE is being - used, that is, when the /P pattern modifier is specified. See also the - section about saving and reloading compiled patterns below. - - The /S modifier causes pcre_study() to be called after the expression - has been compiled, and the results used when the expression is matched. - - The /M modifier causes the size of memory block used to hold the com- - piled pattern to be output. - - The /P modifier causes pcretest to call PCRE via the POSIX wrapper API - rather than its native API. When this is done, all other modifiers - except /i, /m, and /+ are ignored. REG_ICASE is set if /i is present, - and REG_NEWLINE is set if /m is present. The wrapper functions force - PCRE_DOLLAR_ENDONLY always, and PCRE_DOTALL unless REG_NEWLINE is set. - - The /8 modifier causes pcretest to call PCRE with the PCRE_UTF8 option - set. This turns on support for UTF-8 character handling in PCRE, pro- - vided that it was compiled with this support enabled. This modifier - also causes any non-printing characters in output strings to be printed - using the \x{hh...} notation if they are valid UTF-8 sequences. - - If the /? modifier is used with /8, it causes pcretest to call - pcre_compile() with the PCRE_NO_UTF8_CHECK option, to suppress the - checking of the string for UTF-8 validity. - - -DATA LINES - - Before each data line is passed to pcre_exec(), leading and trailing - whitespace is removed, and it is then scanned for \ escapes. Some of - these are pretty esoteric features, intended for checking out some of - the more complicated features of PCRE. If you are just testing "ordi- - nary" regular expressions, you probably don't need any of these. The - following escapes are recognized: - - \a alarm (BEL, \x07) - \b backspace (\x08) - \e escape (\x27) - \f formfeed (\x0c) - \n newline (\x0a) - \qdd set the PCRE_MATCH_LIMIT limit to dd - (any number of digits) - \r carriage return (\x0d) - \t tab (\x09) - \v vertical tab (\x0b) - \nnn octal character (up to 3 octal digits) - \xhh hexadecimal character (up to 2 hex digits) - \x{hh...} hexadecimal character, any number of digits - in UTF-8 mode - \A pass the PCRE_ANCHORED option to pcre_exec() - or pcre_dfa_exec() - \B pass the PCRE_NOTBOL option to pcre_exec() - or pcre_dfa_exec() - \Cdd call pcre_copy_substring() for substring dd - after a successful match (number less than 32) - \Cname call pcre_copy_named_substring() for substring - "name" after a successful match (name termin- - ated by next non alphanumeric character) - \C+ show the current captured substrings at callout - time - \C- do not supply a callout function - \C!n return 1 instead of 0 when callout number n is - reached - \C!n!m return 1 instead of 0 when callout number n is - reached for the nth time - \C*n pass the number n (may be negative) as callout - data; this is used as the callout return value - \D use the pcre_dfa_exec() match function - \F only shortest match for pcre_dfa_exec() - \Gdd call pcre_get_substring() for substring dd - after a successful match (number less than 32) - \Gname call pcre_get_named_substring() for substring - "name" after a successful match (name termin- - ated by next non-alphanumeric character) - \L call pcre_get_substringlist() after a - successful match - \M discover the minimum MATCH_LIMIT and - MATCH_LIMIT_RECURSION settings - \N pass the PCRE_NOTEMPTY option to pcre_exec() - or pcre_dfa_exec() - \Odd set the size of the output vector passed to - pcre_exec() to dd (any number of digits) - \P pass the PCRE_PARTIAL option to pcre_exec() - or pcre_dfa_exec() - \Qdd set the PCRE_MATCH_LIMIT_RECURSION limit to dd - (any number of digits) - \R pass the PCRE_DFA_RESTART option to pcre_dfa_exec() - \S output details of memory get/free calls during matching - \Z pass the PCRE_NOTEOL option to pcre_exec() - or pcre_dfa_exec() - \? pass the PCRE_NO_UTF8_CHECK option to - pcre_exec() or pcre_dfa_exec() - \>dd start the match at offset dd (any number of digits); - this sets the startoffset argument for pcre_exec() - or pcre_dfa_exec() - \ pass the PCRE_NEWLINE_CR option to pcre_exec() - or pcre_dfa_exec() - \ pass the PCRE_NEWLINE_LF option to pcre_exec() - or pcre_dfa_exec() - \ pass the PCRE_NEWLINE_CRLF option to pcre_exec() - or pcre_dfa_exec() - \ pass the PCRE_NEWLINE_ANYCRLF option to pcre_exec() - or pcre_dfa_exec() - \ pass the PCRE_NEWLINE_ANY option to pcre_exec() - or pcre_dfa_exec() - - The escapes that specify line ending sequences are literal strings, - exactly as shown. No more than one newline setting should be present in - any data line. - - A backslash followed by anything else just escapes the anything else. - If the very last character is a backslash, it is ignored. This gives a - way of passing an empty line as data, since a real empty line termi- - nates the data input. - - If \M is present, pcretest calls pcre_exec() several times, with dif- - ferent values in the match_limit and match_limit_recursion fields of - the pcre_extra data structure, until it finds the minimum numbers for - each parameter that allow pcre_exec() to complete. The match_limit num- - ber is a measure of the amount of backtracking that takes place, and - checking it out can be instructive. For most simple matches, the number - is quite small, but for patterns with very large numbers of matching - possibilities, it can become large very quickly with increasing length - of subject string. The match_limit_recursion number is a measure of how - much stack (or, if PCRE is compiled with NO_RECURSE, how much heap) - memory is needed to complete the match attempt. - - When \O is used, the value specified may be higher or lower than the - size set by the -O command line option (or defaulted to 45); \O applies - only to the call of pcre_exec() for the line in which it appears. - - If the /P modifier was present on the pattern, causing the POSIX wrap- - per API to be used, the only option-setting sequences that have any - effect are \B and \Z, causing REG_NOTBOL and REG_NOTEOL, respectively, - to be passed to regexec(). - - The use of \x{hh...} to represent UTF-8 characters is not dependent on - the use of the /8 modifier on the pattern. It is recognized always. - There may be any number of hexadecimal digits inside the braces. The - result is from one to six bytes, encoded according to the original - UTF-8 rules of RFC 2279. This allows for values in the range 0 to - 0x7FFFFFFF. Note that not all of those are valid Unicode code points, - or indeed valid UTF-8 characters according to the later rules in RFC - 3629. - - -THE ALTERNATIVE MATCHING FUNCTION - - By default, pcretest uses the standard PCRE matching function, - pcre_exec() to match each data line. From release 6.0, PCRE supports an - alternative matching function, pcre_dfa_test(), which operates in a - different way, and has some restrictions. The differences between the - two functions are described in the pcrematching documentation. - - If a data line contains the \D escape sequence, or if the command line - contains the -dfa option, the alternative matching function is called. - This function finds all possible matches at a given point. If, however, - the \F escape sequence is present in the data line, it stops after the - first match is found. This is always the shortest possible match. - - -DEFAULT OUTPUT FROM PCRETEST - - This section describes the output when the normal matching function, - pcre_exec(), is being used. - - When a match succeeds, pcretest outputs the list of captured substrings - that pcre_exec() returns, starting with number 0 for the string that - matched the whole pattern. Otherwise, it outputs "No match" or "Partial - match" when pcre_exec() returns PCRE_ERROR_NOMATCH or PCRE_ERROR_PAR- - TIAL, respectively, and otherwise the PCRE negative error number. Here - is an example of an interactive pcretest run. - - $ pcretest - PCRE version 7.0 30-Nov-2006 - - re> /^abc(\d+)/ - data> abc123 - 0: abc123 - 1: 123 - data> xyz - No match - - Note that unset capturing substrings that are not followed by one that - is set are not returned by pcre_exec(), and are not shown by pcretest. - In the following example, there are two capturing substrings, but when - the first data line is matched, the second, unset substring is not - shown. An "internal" unset substring is shown as "", as for the - second data line. - - re> /(a)|(b)/ - data> a - 0: a - 1: a - data> b - 0: b - 1: - 2: b - - If the strings contain any non-printing characters, they are output as - \0x escapes, or as \x{...} escapes if the /8 modifier was present on - the pattern. See below for the definition of non-printing characters. - If the pattern has the /+ modifier, the output for substring 0 is fol- - lowed by the the rest of the subject string, identified by "0+" like - this: - - re> /cat/+ - data> cataract - 0: cat - 0+ aract - - If the pattern has the /g or /G modifier, the results of successive - matching attempts are output in sequence, like this: - - re> /\Bi(\w\w)/g - data> Mississippi - 0: iss - 1: ss - 0: iss - 1: ss - 0: ipp - 1: pp - - "No match" is output only if the first match attempt fails. - - If any of the sequences \C, \G, or \L are present in a data line that - is successfully matched, the substrings extracted by the convenience - functions are output with C, G, or L after the string number instead of - a colon. This is in addition to the normal full list. The string length - (that is, the return from the extraction function) is given in paren- - theses after each string for \C and \G. - - Note that whereas patterns can be continued over several lines (a plain - ">" prompt is used for continuations), data lines may not. However new- - lines can be included in data by means of the \n escape (or \r, \r\n, - etc., depending on the newline sequence setting). - - -OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION - - When the alternative matching function, pcre_dfa_exec(), is used (by - means of the \D escape sequence or the -dfa command line option), the - output consists of a list of all the matches that start at the first - point in the subject where there is at least one match. For example: - - re> /(tang|tangerine|tan)/ - data> yellow tangerine\D - 0: tangerine - 1: tang - 2: tan - - (Using the normal matching function on this data finds only "tang".) - The longest matching string is always given first (and numbered zero). - - If /g is present on the pattern, the search for further matches resumes - at the end of the longest match. For example: - - re> /(tang|tangerine|tan)/g - data> yellow tangerine and tangy sultana\D - 0: tangerine - 1: tang - 2: tan - 0: tang - 1: tan - 0: tan - - Since the matching function does not support substring capture, the - escape sequences that are concerned with captured substrings are not - relevant. - - -RESTARTING AFTER A PARTIAL MATCH - - When the alternative matching function has given the PCRE_ERROR_PARTIAL - return, indicating that the subject partially matched the pattern, you - can restart the match with additional subject data by means of the \R - escape sequence. For example: - - re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/ - data> 23ja\P\D - Partial match: 23ja - data> n05\R\D - 0: n05 - - For further information about partial matching, see the pcrepartial - documentation. - - -CALLOUTS - - If the pattern contains any callout requests, pcretest's callout func- - tion is called during matching. This works with both matching func- - tions. By default, the called function displays the callout number, the - start and current positions in the text at the callout time, and the - next pattern item to be tested. For example, the output - - --->pqrabcdef - 0 ^ ^ \d - - indicates that callout number 0 occurred for a match attempt starting - at the fourth character of the subject string, when the pointer was at - the seventh character of the data, and when the next pattern item was - \d. Just one circumflex is output if the start and current positions - are the same. - - Callouts numbered 255 are assumed to be automatic callouts, inserted as - a result of the /C pattern modifier. In this case, instead of showing - the callout number, the offset in the pattern, preceded by a plus, is - output. For example: - - re> /\d?[A-E]\*/C - data> E* - --->E* - +0 ^ \d? - +3 ^ [A-E] - +8 ^^ \* - +10 ^ ^ - 0: E* - - The callout function in pcretest returns zero (carry on matching) by - default, but you can use a \C item in a data line (as described above) - to change this. - - Inserting callouts can be helpful when using pcretest to check compli- - cated regular expressions. For further information about callouts, see - the pcrecallout documentation. - - -NON-PRINTING CHARACTERS - - When pcretest is outputting text in the compiled version of a pattern, - bytes other than 32-126 are always treated as non-printing characters - are are therefore shown as hex escapes. - - When pcretest is outputting text that is a matched part of a subject - string, it behaves in the same way, unless a different locale has been - set for the pattern (using the /L modifier). In this case, the - isprint() function to distinguish printing and non-printing characters. - - -SAVING AND RELOADING COMPILED PATTERNS - - The facilities described in this section are not available when the - POSIX inteface to PCRE is being used, that is, when the /P pattern mod- - ifier is specified. - - When the POSIX interface is not in use, you can cause pcretest to write - a compiled pattern to a file, by following the modifiers with > and a - file name. For example: - - /pattern/im >/some/file - - See the pcreprecompile documentation for a discussion about saving and - re-using compiled patterns. - - The data that is written is binary. The first eight bytes are the - length of the compiled pattern data followed by the length of the - optional study data, each written as four bytes in big-endian order - (most significant byte first). If there is no study data (either the - pattern was not studied, or studying did not return any data), the sec- - ond length is zero. The lengths are followed by an exact copy of the - compiled pattern. If there is additional study data, this follows imme- - diately after the compiled pattern. After writing the file, pcretest - expects to read a new pattern. - - A saved pattern can be reloaded into pcretest by specifing < and a file - name instead of a pattern. The name of the file must not contain a < - character, as otherwise pcretest will interpret the line as a pattern - delimited by < characters. For example: - - re> nul 2>nul - -:: sh configure - -:: check for needed header files -if not exist pcre.h copy pcre.h.generic pcre.h -if not exist config.h copy config.h.generic config.h - -bcc32 -DDFTABLES %COMPILE_DEFAULTS% -L%BORLAND%\lib dftables.c -IF ERRORLEVEL 1 GOTO ERROR - -:: dftables > chartables.c -dftables pcre_chartables.c - -REM compile and link the PCRE library into lib: option -B for ASM compile works too -bcc32 -a4 -c -RT- -y- -v- -u- -R- -Q- -X -d -fp -ff -P- -O2 -Oc -Ov -3 -w-8004 -w-8064 -w-8065 -w-8012 -UDFTABLES -DVPCOMPAT %COMPILE_DEFAULTS% @makevp_c.txt -IF ERRORLEVEL 1 GOTO ERROR - -tlib %BORLAND%\lib\cw32.lib *calloc *del *strncmp *memcpy *memmove *memset *memcmp *strlen -IF ERRORLEVEL 1 GOTO ERROR -tlib pcre%PCRE_VER%.lib @makevp_l.txt +calloc.obj +del.obj +strncmp.obj +memcpy.obj +memmove.obj +memset.obj +memcmp.obj +strlen.obj -IF ERRORLEVEL 1 GOTO ERROR - -del *.obj *.tds *.bak >nul 2>nul - -echo --- -echo Now the library should be complete. Please check all messages above. -echo Don't care for warnings, it's OK. -goto END - -:ERROR -echo --- -echo Error while compiling PCRE. Aborting... -pause -goto END - -:END diff --git a/libs/pcre/makevp_c.txt b/libs/pcre/makevp_c.txt deleted file mode 100644 index 931b8ab88d..0000000000 --- a/libs/pcre/makevp_c.txt +++ /dev/null @@ -1,20 +0,0 @@ -pcre_chartables.c -pcre_compile.c -pcre_config.c -pcre_dfa_exec.c -pcre_exec.c -pcre_fullinfo.c -pcre_get.c -pcre_globals.c -pcre_info.c -pcre_maketables.c -pcre_newline.c -pcre_ord2utf8.c -pcre_refcount.c -pcre_study.c -pcre_tables.c -pcre_try_flipped.c -pcre_ucd.c -pcre_valid_utf8.c -pcre_version.c -pcre_xclass.c diff --git a/libs/pcre/makevp_l.txt b/libs/pcre/makevp_l.txt deleted file mode 100644 index 6de1cb438e..0000000000 --- a/libs/pcre/makevp_l.txt +++ /dev/null @@ -1,20 +0,0 @@ -+pcre_chartables.obj & -+pcre_compile.obj & -+pcre_config.obj & -+pcre_dfa_exec.obj & -+pcre_exec.obj & -+pcre_fullinfo.obj & -+pcre_get.obj & -+pcre_globals.obj & -+pcre_info.obj & -+pcre_maketables.obj & -+pcre_newline.obj & -+pcre_ord2utf8.obj & -+pcre_refcount.obj & -+pcre_study.obj & -+pcre_tables.obj & -+pcre_try_flipped.obj & -+pcre_ucd.obj & -+pcre_valid_utf8.obj & -+pcre_version.obj & -+pcre_xclass.obj diff --git a/libs/pcre/pcre-config.in b/libs/pcre/pcre-config.in deleted file mode 100644 index 3b52101b9b..0000000000 --- a/libs/pcre/pcre-config.in +++ /dev/null @@ -1,69 +0,0 @@ -#!/bin/sh - -prefix=@prefix@ -exec_prefix=@exec_prefix@ -exec_prefix_set=no - -usage="\ -Usage: pcre-config [--prefix] [--exec-prefix] [--version] [--libs] [--libs-posix] [--cflags] [--cflags-posix]" - -if test $# -eq 0; then - echo "${usage}" 1>&2 - exit 1 -fi - -libR= -case `uname -s` in - *SunOS*) - libR=" -R@libdir@" - ;; - *BSD*) - libR=" -Wl,-R@libdir@" - ;; -esac - -while test $# -gt 0; do - case "$1" in - -*=*) optarg=`echo "$1" | sed 's/[-_a-zA-Z0-9]*=//'` ;; - *) optarg= ;; - esac - - case $1 in - --prefix=*) - prefix=$optarg - if test $exec_prefix_set = no ; then - exec_prefix=$optarg - fi - ;; - --prefix) - echo $prefix - ;; - --exec-prefix=*) - exec_prefix=$optarg - exec_prefix_set=yes - ;; - --exec-prefix) - echo $exec_prefix - ;; - --version) - echo @PACKAGE_VERSION@ - ;; - --cflags | --cflags-posix) - if test @includedir@ != /usr/include ; then - includes=-I@includedir@ - fi - echo $includes - ;; - --libs-posix) - echo -L@libdir@$libR -lpcreposix -lpcre - ;; - --libs) - echo -L@libdir@$libR -lpcre - ;; - *) - echo "${usage}" 1>&2 - exit 1 - ;; - esac - shift -done diff --git a/libs/pcre/pcre.def b/libs/pcre/pcre.def deleted file mode 100644 index ec2c7b395b..0000000000 --- a/libs/pcre/pcre.def +++ /dev/null @@ -1,29 +0,0 @@ -EXPORTS - -pcre_malloc DATA -pcre_free DATA - -pcre_compile -pcre_compile2 -pcre_config -pcre_copy_named_substring -pcre_copy_substring -pcre_dfa_exec -pcre_exec -pcre_free_substring -pcre_free_substring_list -pcre_fullinfo -pcre_get_named_substring -pcre_get_stringnumber -pcre_get_substring -pcre_get_substring_list -pcre_info -pcre_maketables -pcre_refcount -pcre_study -pcre_version - -regcomp -regexec -regerror -regfree diff --git a/libs/pcre/pcre.h b/libs/pcre/pcre.h deleted file mode 100644 index c5fc4c13e4..0000000000 --- a/libs/pcre/pcre.h +++ /dev/null @@ -1,307 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* This is the public header file for the PCRE library, to be #included by -applications that call the PCRE functions. - - Copyright (c) 1997-2009 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -#ifndef _PCRE_H -#define _PCRE_H - -/* The current PCRE version information. */ - -#define PCRE_MAJOR 7 -#define PCRE_MINOR 9 -#define PCRE_PRERELEASE -#define PCRE_DATE 2009-04-11 - -/* When an application links to a PCRE DLL in Windows, the symbols that are -imported have to be identified as such. When building PCRE, the appropriate -export setting is defined in pcre_internal.h, which includes this file. So we -don't change existing definitions of PCRE_EXP_DECL and PCRECPP_EXP_DECL. */ - -#if defined(_WIN32) && !defined(PCRE_STATIC) -# ifndef PCRE_EXP_DECL -# define PCRE_EXP_DECL extern __declspec(dllimport) -# endif -# ifdef __cplusplus -# ifndef PCRECPP_EXP_DECL -# define PCRECPP_EXP_DECL extern __declspec(dllimport) -# endif -# ifndef PCRECPP_EXP_DEFN -# define PCRECPP_EXP_DEFN __declspec(dllimport) -# endif -# endif -#endif - -/* By default, we use the standard "extern" declarations. */ - -#ifndef PCRE_EXP_DECL -# ifdef __cplusplus -# define PCRE_EXP_DECL extern "C" -# else -# define PCRE_EXP_DECL extern -# endif -#endif - -#ifdef __cplusplus -# ifndef PCRECPP_EXP_DECL -# define PCRECPP_EXP_DECL extern -# endif -# ifndef PCRECPP_EXP_DEFN -# define PCRECPP_EXP_DEFN -# endif -#endif - -/* Have to include stdlib.h in order to ensure that size_t is defined; -it is needed here for malloc. */ - -#include - -/* Allow for C++ users */ - -#ifdef __cplusplus -extern "C" { -#endif - -/* Options. Some are compile-time only, some are run-time only, and some are -both, so we keep them all distinct. */ - -#define PCRE_CASELESS 0x00000001 -#define PCRE_MULTILINE 0x00000002 -#define PCRE_DOTALL 0x00000004 -#define PCRE_EXTENDED 0x00000008 -#define PCRE_ANCHORED 0x00000010 -#define PCRE_DOLLAR_ENDONLY 0x00000020 -#define PCRE_EXTRA 0x00000040 -#define PCRE_NOTBOL 0x00000080 -#define PCRE_NOTEOL 0x00000100 -#define PCRE_UNGREEDY 0x00000200 -#define PCRE_NOTEMPTY 0x00000400 -#define PCRE_UTF8 0x00000800 -#define PCRE_NO_AUTO_CAPTURE 0x00001000 -#define PCRE_NO_UTF8_CHECK 0x00002000 -#define PCRE_AUTO_CALLOUT 0x00004000 -#define PCRE_PARTIAL 0x00008000 -#define PCRE_DFA_SHORTEST 0x00010000 -#define PCRE_DFA_RESTART 0x00020000 -#define PCRE_FIRSTLINE 0x00040000 -#define PCRE_DUPNAMES 0x00080000 -#define PCRE_NEWLINE_CR 0x00100000 -#define PCRE_NEWLINE_LF 0x00200000 -#define PCRE_NEWLINE_CRLF 0x00300000 -#define PCRE_NEWLINE_ANY 0x00400000 -#define PCRE_NEWLINE_ANYCRLF 0x00500000 -#define PCRE_BSR_ANYCRLF 0x00800000 -#define PCRE_BSR_UNICODE 0x01000000 -#define PCRE_JAVASCRIPT_COMPAT 0x02000000 -#define PCRE_NO_START_OPTIMIZE 0x04000000 -#define PCRE_NO_START_OPTIMISE 0x04000000 - -/* Exec-time and get/set-time error codes */ - -#define PCRE_ERROR_NOMATCH (-1) -#define PCRE_ERROR_NULL (-2) -#define PCRE_ERROR_BADOPTION (-3) -#define PCRE_ERROR_BADMAGIC (-4) -#define PCRE_ERROR_UNKNOWN_OPCODE (-5) -#define PCRE_ERROR_UNKNOWN_NODE (-5) /* For backward compatibility */ -#define PCRE_ERROR_NOMEMORY (-6) -#define PCRE_ERROR_NOSUBSTRING (-7) -#define PCRE_ERROR_MATCHLIMIT (-8) -#define PCRE_ERROR_CALLOUT (-9) /* Never used by PCRE itself */ -#define PCRE_ERROR_BADUTF8 (-10) -#define PCRE_ERROR_BADUTF8_OFFSET (-11) -#define PCRE_ERROR_PARTIAL (-12) -#define PCRE_ERROR_BADPARTIAL (-13) -#define PCRE_ERROR_INTERNAL (-14) -#define PCRE_ERROR_BADCOUNT (-15) -#define PCRE_ERROR_DFA_UITEM (-16) -#define PCRE_ERROR_DFA_UCOND (-17) -#define PCRE_ERROR_DFA_UMLIMIT (-18) -#define PCRE_ERROR_DFA_WSSIZE (-19) -#define PCRE_ERROR_DFA_RECURSE (-20) -#define PCRE_ERROR_RECURSIONLIMIT (-21) -#define PCRE_ERROR_NULLWSLIMIT (-22) /* No longer actually used */ -#define PCRE_ERROR_BADNEWLINE (-23) - -/* Request types for pcre_fullinfo() */ - -#define PCRE_INFO_OPTIONS 0 -#define PCRE_INFO_SIZE 1 -#define PCRE_INFO_CAPTURECOUNT 2 -#define PCRE_INFO_BACKREFMAX 3 -#define PCRE_INFO_FIRSTBYTE 4 -#define PCRE_INFO_FIRSTCHAR 4 /* For backwards compatibility */ -#define PCRE_INFO_FIRSTTABLE 5 -#define PCRE_INFO_LASTLITERAL 6 -#define PCRE_INFO_NAMEENTRYSIZE 7 -#define PCRE_INFO_NAMECOUNT 8 -#define PCRE_INFO_NAMETABLE 9 -#define PCRE_INFO_STUDYSIZE 10 -#define PCRE_INFO_DEFAULT_TABLES 11 -#define PCRE_INFO_OKPARTIAL 12 -#define PCRE_INFO_JCHANGED 13 -#define PCRE_INFO_HASCRORLF 14 - -/* Request types for pcre_config(). Do not re-arrange, in order to remain -compatible. */ - -#define PCRE_CONFIG_UTF8 0 -#define PCRE_CONFIG_NEWLINE 1 -#define PCRE_CONFIG_LINK_SIZE 2 -#define PCRE_CONFIG_POSIX_MALLOC_THRESHOLD 3 -#define PCRE_CONFIG_MATCH_LIMIT 4 -#define PCRE_CONFIG_STACKRECURSE 5 -#define PCRE_CONFIG_UNICODE_PROPERTIES 6 -#define PCRE_CONFIG_MATCH_LIMIT_RECURSION 7 -#define PCRE_CONFIG_BSR 8 - -/* Bit flags for the pcre_extra structure. Do not re-arrange or redefine -these bits, just add new ones on the end, in order to remain compatible. */ - -#define PCRE_EXTRA_STUDY_DATA 0x0001 -#define PCRE_EXTRA_MATCH_LIMIT 0x0002 -#define PCRE_EXTRA_CALLOUT_DATA 0x0004 -#define PCRE_EXTRA_TABLES 0x0008 -#define PCRE_EXTRA_MATCH_LIMIT_RECURSION 0x0010 - -/* Types */ - -struct real_pcre; /* declaration; the definition is private */ -typedef struct real_pcre pcre; - -/* When PCRE is compiled as a C++ library, the subject pointer type can be -replaced with a custom type. For conventional use, the public interface is a -const char *. */ - -#ifndef PCRE_SPTR -#define PCRE_SPTR const char * -#endif - -/* The structure for passing additional data to pcre_exec(). This is defined in -such as way as to be extensible. Always add new fields at the end, in order to -remain compatible. */ - -typedef struct pcre_extra { - unsigned long int flags; /* Bits for which fields are set */ - void *study_data; /* Opaque data from pcre_study() */ - unsigned long int match_limit; /* Maximum number of calls to match() */ - void *callout_data; /* Data passed back in callouts */ - const unsigned char *tables; /* Pointer to character tables */ - unsigned long int match_limit_recursion; /* Max recursive calls to match() */ -} pcre_extra; - -/* The structure for passing out data via the pcre_callout_function. We use a -structure so that new fields can be added on the end in future versions, -without changing the API of the function, thereby allowing old clients to work -without modification. */ - -typedef struct pcre_callout_block { - int version; /* Identifies version of block */ - /* ------------------------ Version 0 ------------------------------- */ - int callout_number; /* Number compiled into pattern */ - int *offset_vector; /* The offset vector */ - PCRE_SPTR subject; /* The subject being matched */ - int subject_length; /* The length of the subject */ - int start_match; /* Offset to start of this match attempt */ - int current_position; /* Where we currently are in the subject */ - int capture_top; /* Max current capture */ - int capture_last; /* Most recently closed capture */ - void *callout_data; /* Data passed in with the call */ - /* ------------------- Added for Version 1 -------------------------- */ - int pattern_position; /* Offset to next item in the pattern */ - int next_item_length; /* Length of next item in the pattern */ - /* ------------------------------------------------------------------ */ -} pcre_callout_block; - -/* Indirection for store get and free functions. These can be set to -alternative malloc/free functions if required. Special ones are used in the -non-recursive case for "frames". There is also an optional callout function -that is triggered by the (?) regex item. For Virtual Pascal, these definitions -have to take another form. */ - -#ifndef VPCOMPAT -PCRE_EXP_DECL void *(*pcre_malloc)(size_t); -PCRE_EXP_DECL void (*pcre_free)(void *); -PCRE_EXP_DECL void *(*pcre_stack_malloc)(size_t); -PCRE_EXP_DECL void (*pcre_stack_free)(void *); -PCRE_EXP_DECL int (*pcre_callout)(pcre_callout_block *); -#else /* VPCOMPAT */ -PCRE_EXP_DECL void *pcre_malloc(size_t); -PCRE_EXP_DECL void pcre_free(void *); -PCRE_EXP_DECL void *pcre_stack_malloc(size_t); -PCRE_EXP_DECL void pcre_stack_free(void *); -PCRE_EXP_DECL int pcre_callout(pcre_callout_block *); -#endif /* VPCOMPAT */ - -/* Exported PCRE functions */ - -PCRE_EXP_DECL pcre *pcre_compile(const char *, int, const char **, int *, - const unsigned char *); -PCRE_EXP_DECL pcre *pcre_compile2(const char *, int, int *, const char **, - int *, const unsigned char *); -PCRE_EXP_DECL int pcre_config(int, void *); -PCRE_EXP_DECL int pcre_copy_named_substring(const pcre *, const char *, - int *, int, const char *, char *, int); -PCRE_EXP_DECL int pcre_copy_substring(const char *, int *, int, int, char *, - int); -PCRE_EXP_DECL int pcre_dfa_exec(const pcre *, const pcre_extra *, - const char *, int, int, int, int *, int , int *, int); -PCRE_EXP_DECL int pcre_exec(const pcre *, const pcre_extra *, PCRE_SPTR, - int, int, int, int *, int); -PCRE_EXP_DECL void pcre_free_substring(const char *); -PCRE_EXP_DECL void pcre_free_substring_list(const char **); -PCRE_EXP_DECL int pcre_fullinfo(const pcre *, const pcre_extra *, int, - void *); -PCRE_EXP_DECL int pcre_get_named_substring(const pcre *, const char *, - int *, int, const char *, const char **); -PCRE_EXP_DECL int pcre_get_stringnumber(const pcre *, const char *); -PCRE_EXP_DECL int pcre_get_stringtable_entries(const pcre *, const char *, - char **, char **); -PCRE_EXP_DECL int pcre_get_substring(const char *, int *, int, int, - const char **); -PCRE_EXP_DECL int pcre_get_substring_list(const char *, int *, int, - const char ***); -PCRE_EXP_DECL int pcre_info(const pcre *, int *, int *); -PCRE_EXP_DECL const unsigned char *pcre_maketables(void); -PCRE_EXP_DECL int pcre_refcount(pcre *, int); -PCRE_EXP_DECL pcre_extra *pcre_study(const pcre *, int, const char **); -PCRE_EXP_DECL const char *pcre_version(void); - -#ifdef __cplusplus -} /* extern "C" */ -#endif - -#endif /* End of pcre.h */ diff --git a/libs/pcre/pcre.h.generic b/libs/pcre/pcre.h.generic deleted file mode 100644 index c5fc4c13e4..0000000000 --- a/libs/pcre/pcre.h.generic +++ /dev/null @@ -1,307 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* This is the public header file for the PCRE library, to be #included by -applications that call the PCRE functions. - - Copyright (c) 1997-2009 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -#ifndef _PCRE_H -#define _PCRE_H - -/* The current PCRE version information. */ - -#define PCRE_MAJOR 7 -#define PCRE_MINOR 9 -#define PCRE_PRERELEASE -#define PCRE_DATE 2009-04-11 - -/* When an application links to a PCRE DLL in Windows, the symbols that are -imported have to be identified as such. When building PCRE, the appropriate -export setting is defined in pcre_internal.h, which includes this file. So we -don't change existing definitions of PCRE_EXP_DECL and PCRECPP_EXP_DECL. */ - -#if defined(_WIN32) && !defined(PCRE_STATIC) -# ifndef PCRE_EXP_DECL -# define PCRE_EXP_DECL extern __declspec(dllimport) -# endif -# ifdef __cplusplus -# ifndef PCRECPP_EXP_DECL -# define PCRECPP_EXP_DECL extern __declspec(dllimport) -# endif -# ifndef PCRECPP_EXP_DEFN -# define PCRECPP_EXP_DEFN __declspec(dllimport) -# endif -# endif -#endif - -/* By default, we use the standard "extern" declarations. */ - -#ifndef PCRE_EXP_DECL -# ifdef __cplusplus -# define PCRE_EXP_DECL extern "C" -# else -# define PCRE_EXP_DECL extern -# endif -#endif - -#ifdef __cplusplus -# ifndef PCRECPP_EXP_DECL -# define PCRECPP_EXP_DECL extern -# endif -# ifndef PCRECPP_EXP_DEFN -# define PCRECPP_EXP_DEFN -# endif -#endif - -/* Have to include stdlib.h in order to ensure that size_t is defined; -it is needed here for malloc. */ - -#include - -/* Allow for C++ users */ - -#ifdef __cplusplus -extern "C" { -#endif - -/* Options. Some are compile-time only, some are run-time only, and some are -both, so we keep them all distinct. */ - -#define PCRE_CASELESS 0x00000001 -#define PCRE_MULTILINE 0x00000002 -#define PCRE_DOTALL 0x00000004 -#define PCRE_EXTENDED 0x00000008 -#define PCRE_ANCHORED 0x00000010 -#define PCRE_DOLLAR_ENDONLY 0x00000020 -#define PCRE_EXTRA 0x00000040 -#define PCRE_NOTBOL 0x00000080 -#define PCRE_NOTEOL 0x00000100 -#define PCRE_UNGREEDY 0x00000200 -#define PCRE_NOTEMPTY 0x00000400 -#define PCRE_UTF8 0x00000800 -#define PCRE_NO_AUTO_CAPTURE 0x00001000 -#define PCRE_NO_UTF8_CHECK 0x00002000 -#define PCRE_AUTO_CALLOUT 0x00004000 -#define PCRE_PARTIAL 0x00008000 -#define PCRE_DFA_SHORTEST 0x00010000 -#define PCRE_DFA_RESTART 0x00020000 -#define PCRE_FIRSTLINE 0x00040000 -#define PCRE_DUPNAMES 0x00080000 -#define PCRE_NEWLINE_CR 0x00100000 -#define PCRE_NEWLINE_LF 0x00200000 -#define PCRE_NEWLINE_CRLF 0x00300000 -#define PCRE_NEWLINE_ANY 0x00400000 -#define PCRE_NEWLINE_ANYCRLF 0x00500000 -#define PCRE_BSR_ANYCRLF 0x00800000 -#define PCRE_BSR_UNICODE 0x01000000 -#define PCRE_JAVASCRIPT_COMPAT 0x02000000 -#define PCRE_NO_START_OPTIMIZE 0x04000000 -#define PCRE_NO_START_OPTIMISE 0x04000000 - -/* Exec-time and get/set-time error codes */ - -#define PCRE_ERROR_NOMATCH (-1) -#define PCRE_ERROR_NULL (-2) -#define PCRE_ERROR_BADOPTION (-3) -#define PCRE_ERROR_BADMAGIC (-4) -#define PCRE_ERROR_UNKNOWN_OPCODE (-5) -#define PCRE_ERROR_UNKNOWN_NODE (-5) /* For backward compatibility */ -#define PCRE_ERROR_NOMEMORY (-6) -#define PCRE_ERROR_NOSUBSTRING (-7) -#define PCRE_ERROR_MATCHLIMIT (-8) -#define PCRE_ERROR_CALLOUT (-9) /* Never used by PCRE itself */ -#define PCRE_ERROR_BADUTF8 (-10) -#define PCRE_ERROR_BADUTF8_OFFSET (-11) -#define PCRE_ERROR_PARTIAL (-12) -#define PCRE_ERROR_BADPARTIAL (-13) -#define PCRE_ERROR_INTERNAL (-14) -#define PCRE_ERROR_BADCOUNT (-15) -#define PCRE_ERROR_DFA_UITEM (-16) -#define PCRE_ERROR_DFA_UCOND (-17) -#define PCRE_ERROR_DFA_UMLIMIT (-18) -#define PCRE_ERROR_DFA_WSSIZE (-19) -#define PCRE_ERROR_DFA_RECURSE (-20) -#define PCRE_ERROR_RECURSIONLIMIT (-21) -#define PCRE_ERROR_NULLWSLIMIT (-22) /* No longer actually used */ -#define PCRE_ERROR_BADNEWLINE (-23) - -/* Request types for pcre_fullinfo() */ - -#define PCRE_INFO_OPTIONS 0 -#define PCRE_INFO_SIZE 1 -#define PCRE_INFO_CAPTURECOUNT 2 -#define PCRE_INFO_BACKREFMAX 3 -#define PCRE_INFO_FIRSTBYTE 4 -#define PCRE_INFO_FIRSTCHAR 4 /* For backwards compatibility */ -#define PCRE_INFO_FIRSTTABLE 5 -#define PCRE_INFO_LASTLITERAL 6 -#define PCRE_INFO_NAMEENTRYSIZE 7 -#define PCRE_INFO_NAMECOUNT 8 -#define PCRE_INFO_NAMETABLE 9 -#define PCRE_INFO_STUDYSIZE 10 -#define PCRE_INFO_DEFAULT_TABLES 11 -#define PCRE_INFO_OKPARTIAL 12 -#define PCRE_INFO_JCHANGED 13 -#define PCRE_INFO_HASCRORLF 14 - -/* Request types for pcre_config(). Do not re-arrange, in order to remain -compatible. */ - -#define PCRE_CONFIG_UTF8 0 -#define PCRE_CONFIG_NEWLINE 1 -#define PCRE_CONFIG_LINK_SIZE 2 -#define PCRE_CONFIG_POSIX_MALLOC_THRESHOLD 3 -#define PCRE_CONFIG_MATCH_LIMIT 4 -#define PCRE_CONFIG_STACKRECURSE 5 -#define PCRE_CONFIG_UNICODE_PROPERTIES 6 -#define PCRE_CONFIG_MATCH_LIMIT_RECURSION 7 -#define PCRE_CONFIG_BSR 8 - -/* Bit flags for the pcre_extra structure. Do not re-arrange or redefine -these bits, just add new ones on the end, in order to remain compatible. */ - -#define PCRE_EXTRA_STUDY_DATA 0x0001 -#define PCRE_EXTRA_MATCH_LIMIT 0x0002 -#define PCRE_EXTRA_CALLOUT_DATA 0x0004 -#define PCRE_EXTRA_TABLES 0x0008 -#define PCRE_EXTRA_MATCH_LIMIT_RECURSION 0x0010 - -/* Types */ - -struct real_pcre; /* declaration; the definition is private */ -typedef struct real_pcre pcre; - -/* When PCRE is compiled as a C++ library, the subject pointer type can be -replaced with a custom type. For conventional use, the public interface is a -const char *. */ - -#ifndef PCRE_SPTR -#define PCRE_SPTR const char * -#endif - -/* The structure for passing additional data to pcre_exec(). This is defined in -such as way as to be extensible. Always add new fields at the end, in order to -remain compatible. */ - -typedef struct pcre_extra { - unsigned long int flags; /* Bits for which fields are set */ - void *study_data; /* Opaque data from pcre_study() */ - unsigned long int match_limit; /* Maximum number of calls to match() */ - void *callout_data; /* Data passed back in callouts */ - const unsigned char *tables; /* Pointer to character tables */ - unsigned long int match_limit_recursion; /* Max recursive calls to match() */ -} pcre_extra; - -/* The structure for passing out data via the pcre_callout_function. We use a -structure so that new fields can be added on the end in future versions, -without changing the API of the function, thereby allowing old clients to work -without modification. */ - -typedef struct pcre_callout_block { - int version; /* Identifies version of block */ - /* ------------------------ Version 0 ------------------------------- */ - int callout_number; /* Number compiled into pattern */ - int *offset_vector; /* The offset vector */ - PCRE_SPTR subject; /* The subject being matched */ - int subject_length; /* The length of the subject */ - int start_match; /* Offset to start of this match attempt */ - int current_position; /* Where we currently are in the subject */ - int capture_top; /* Max current capture */ - int capture_last; /* Most recently closed capture */ - void *callout_data; /* Data passed in with the call */ - /* ------------------- Added for Version 1 -------------------------- */ - int pattern_position; /* Offset to next item in the pattern */ - int next_item_length; /* Length of next item in the pattern */ - /* ------------------------------------------------------------------ */ -} pcre_callout_block; - -/* Indirection for store get and free functions. These can be set to -alternative malloc/free functions if required. Special ones are used in the -non-recursive case for "frames". There is also an optional callout function -that is triggered by the (?) regex item. For Virtual Pascal, these definitions -have to take another form. */ - -#ifndef VPCOMPAT -PCRE_EXP_DECL void *(*pcre_malloc)(size_t); -PCRE_EXP_DECL void (*pcre_free)(void *); -PCRE_EXP_DECL void *(*pcre_stack_malloc)(size_t); -PCRE_EXP_DECL void (*pcre_stack_free)(void *); -PCRE_EXP_DECL int (*pcre_callout)(pcre_callout_block *); -#else /* VPCOMPAT */ -PCRE_EXP_DECL void *pcre_malloc(size_t); -PCRE_EXP_DECL void pcre_free(void *); -PCRE_EXP_DECL void *pcre_stack_malloc(size_t); -PCRE_EXP_DECL void pcre_stack_free(void *); -PCRE_EXP_DECL int pcre_callout(pcre_callout_block *); -#endif /* VPCOMPAT */ - -/* Exported PCRE functions */ - -PCRE_EXP_DECL pcre *pcre_compile(const char *, int, const char **, int *, - const unsigned char *); -PCRE_EXP_DECL pcre *pcre_compile2(const char *, int, int *, const char **, - int *, const unsigned char *); -PCRE_EXP_DECL int pcre_config(int, void *); -PCRE_EXP_DECL int pcre_copy_named_substring(const pcre *, const char *, - int *, int, const char *, char *, int); -PCRE_EXP_DECL int pcre_copy_substring(const char *, int *, int, int, char *, - int); -PCRE_EXP_DECL int pcre_dfa_exec(const pcre *, const pcre_extra *, - const char *, int, int, int, int *, int , int *, int); -PCRE_EXP_DECL int pcre_exec(const pcre *, const pcre_extra *, PCRE_SPTR, - int, int, int, int *, int); -PCRE_EXP_DECL void pcre_free_substring(const char *); -PCRE_EXP_DECL void pcre_free_substring_list(const char **); -PCRE_EXP_DECL int pcre_fullinfo(const pcre *, const pcre_extra *, int, - void *); -PCRE_EXP_DECL int pcre_get_named_substring(const pcre *, const char *, - int *, int, const char *, const char **); -PCRE_EXP_DECL int pcre_get_stringnumber(const pcre *, const char *); -PCRE_EXP_DECL int pcre_get_stringtable_entries(const pcre *, const char *, - char **, char **); -PCRE_EXP_DECL int pcre_get_substring(const char *, int *, int, int, - const char **); -PCRE_EXP_DECL int pcre_get_substring_list(const char *, int *, int, - const char ***); -PCRE_EXP_DECL int pcre_info(const pcre *, int *, int *); -PCRE_EXP_DECL const unsigned char *pcre_maketables(void); -PCRE_EXP_DECL int pcre_refcount(pcre *, int); -PCRE_EXP_DECL pcre_extra *pcre_study(const pcre *, int, const char **); -PCRE_EXP_DECL const char *pcre_version(void); - -#ifdef __cplusplus -} /* extern "C" */ -#endif - -#endif /* End of pcre.h */ diff --git a/libs/pcre/pcre.h.in b/libs/pcre/pcre.h.in deleted file mode 100644 index 484ddfd3d5..0000000000 --- a/libs/pcre/pcre.h.in +++ /dev/null @@ -1,307 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* This is the public header file for the PCRE library, to be #included by -applications that call the PCRE functions. - - Copyright (c) 1997-2009 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -#ifndef _PCRE_H -#define _PCRE_H - -/* The current PCRE version information. */ - -#define PCRE_MAJOR @PCRE_MAJOR@ -#define PCRE_MINOR @PCRE_MINOR@ -#define PCRE_PRERELEASE @PCRE_PRERELEASE@ -#define PCRE_DATE @PCRE_DATE@ - -/* When an application links to a PCRE DLL in Windows, the symbols that are -imported have to be identified as such. When building PCRE, the appropriate -export setting is defined in pcre_internal.h, which includes this file. So we -don't change existing definitions of PCRE_EXP_DECL and PCRECPP_EXP_DECL. */ - -#if defined(_WIN32) && !defined(PCRE_STATIC) -# ifndef PCRE_EXP_DECL -# define PCRE_EXP_DECL extern __declspec(dllimport) -# endif -# ifdef __cplusplus -# ifndef PCRECPP_EXP_DECL -# define PCRECPP_EXP_DECL extern __declspec(dllimport) -# endif -# ifndef PCRECPP_EXP_DEFN -# define PCRECPP_EXP_DEFN __declspec(dllimport) -# endif -# endif -#endif - -/* By default, we use the standard "extern" declarations. */ - -#ifndef PCRE_EXP_DECL -# ifdef __cplusplus -# define PCRE_EXP_DECL extern "C" -# else -# define PCRE_EXP_DECL extern -# endif -#endif - -#ifdef __cplusplus -# ifndef PCRECPP_EXP_DECL -# define PCRECPP_EXP_DECL extern -# endif -# ifndef PCRECPP_EXP_DEFN -# define PCRECPP_EXP_DEFN -# endif -#endif - -/* Have to include stdlib.h in order to ensure that size_t is defined; -it is needed here for malloc. */ - -#include - -/* Allow for C++ users */ - -#ifdef __cplusplus -extern "C" { -#endif - -/* Options. Some are compile-time only, some are run-time only, and some are -both, so we keep them all distinct. */ - -#define PCRE_CASELESS 0x00000001 -#define PCRE_MULTILINE 0x00000002 -#define PCRE_DOTALL 0x00000004 -#define PCRE_EXTENDED 0x00000008 -#define PCRE_ANCHORED 0x00000010 -#define PCRE_DOLLAR_ENDONLY 0x00000020 -#define PCRE_EXTRA 0x00000040 -#define PCRE_NOTBOL 0x00000080 -#define PCRE_NOTEOL 0x00000100 -#define PCRE_UNGREEDY 0x00000200 -#define PCRE_NOTEMPTY 0x00000400 -#define PCRE_UTF8 0x00000800 -#define PCRE_NO_AUTO_CAPTURE 0x00001000 -#define PCRE_NO_UTF8_CHECK 0x00002000 -#define PCRE_AUTO_CALLOUT 0x00004000 -#define PCRE_PARTIAL 0x00008000 -#define PCRE_DFA_SHORTEST 0x00010000 -#define PCRE_DFA_RESTART 0x00020000 -#define PCRE_FIRSTLINE 0x00040000 -#define PCRE_DUPNAMES 0x00080000 -#define PCRE_NEWLINE_CR 0x00100000 -#define PCRE_NEWLINE_LF 0x00200000 -#define PCRE_NEWLINE_CRLF 0x00300000 -#define PCRE_NEWLINE_ANY 0x00400000 -#define PCRE_NEWLINE_ANYCRLF 0x00500000 -#define PCRE_BSR_ANYCRLF 0x00800000 -#define PCRE_BSR_UNICODE 0x01000000 -#define PCRE_JAVASCRIPT_COMPAT 0x02000000 -#define PCRE_NO_START_OPTIMIZE 0x04000000 -#define PCRE_NO_START_OPTIMISE 0x04000000 - -/* Exec-time and get/set-time error codes */ - -#define PCRE_ERROR_NOMATCH (-1) -#define PCRE_ERROR_NULL (-2) -#define PCRE_ERROR_BADOPTION (-3) -#define PCRE_ERROR_BADMAGIC (-4) -#define PCRE_ERROR_UNKNOWN_OPCODE (-5) -#define PCRE_ERROR_UNKNOWN_NODE (-5) /* For backward compatibility */ -#define PCRE_ERROR_NOMEMORY (-6) -#define PCRE_ERROR_NOSUBSTRING (-7) -#define PCRE_ERROR_MATCHLIMIT (-8) -#define PCRE_ERROR_CALLOUT (-9) /* Never used by PCRE itself */ -#define PCRE_ERROR_BADUTF8 (-10) -#define PCRE_ERROR_BADUTF8_OFFSET (-11) -#define PCRE_ERROR_PARTIAL (-12) -#define PCRE_ERROR_BADPARTIAL (-13) -#define PCRE_ERROR_INTERNAL (-14) -#define PCRE_ERROR_BADCOUNT (-15) -#define PCRE_ERROR_DFA_UITEM (-16) -#define PCRE_ERROR_DFA_UCOND (-17) -#define PCRE_ERROR_DFA_UMLIMIT (-18) -#define PCRE_ERROR_DFA_WSSIZE (-19) -#define PCRE_ERROR_DFA_RECURSE (-20) -#define PCRE_ERROR_RECURSIONLIMIT (-21) -#define PCRE_ERROR_NULLWSLIMIT (-22) /* No longer actually used */ -#define PCRE_ERROR_BADNEWLINE (-23) - -/* Request types for pcre_fullinfo() */ - -#define PCRE_INFO_OPTIONS 0 -#define PCRE_INFO_SIZE 1 -#define PCRE_INFO_CAPTURECOUNT 2 -#define PCRE_INFO_BACKREFMAX 3 -#define PCRE_INFO_FIRSTBYTE 4 -#define PCRE_INFO_FIRSTCHAR 4 /* For backwards compatibility */ -#define PCRE_INFO_FIRSTTABLE 5 -#define PCRE_INFO_LASTLITERAL 6 -#define PCRE_INFO_NAMEENTRYSIZE 7 -#define PCRE_INFO_NAMECOUNT 8 -#define PCRE_INFO_NAMETABLE 9 -#define PCRE_INFO_STUDYSIZE 10 -#define PCRE_INFO_DEFAULT_TABLES 11 -#define PCRE_INFO_OKPARTIAL 12 -#define PCRE_INFO_JCHANGED 13 -#define PCRE_INFO_HASCRORLF 14 - -/* Request types for pcre_config(). Do not re-arrange, in order to remain -compatible. */ - -#define PCRE_CONFIG_UTF8 0 -#define PCRE_CONFIG_NEWLINE 1 -#define PCRE_CONFIG_LINK_SIZE 2 -#define PCRE_CONFIG_POSIX_MALLOC_THRESHOLD 3 -#define PCRE_CONFIG_MATCH_LIMIT 4 -#define PCRE_CONFIG_STACKRECURSE 5 -#define PCRE_CONFIG_UNICODE_PROPERTIES 6 -#define PCRE_CONFIG_MATCH_LIMIT_RECURSION 7 -#define PCRE_CONFIG_BSR 8 - -/* Bit flags for the pcre_extra structure. Do not re-arrange or redefine -these bits, just add new ones on the end, in order to remain compatible. */ - -#define PCRE_EXTRA_STUDY_DATA 0x0001 -#define PCRE_EXTRA_MATCH_LIMIT 0x0002 -#define PCRE_EXTRA_CALLOUT_DATA 0x0004 -#define PCRE_EXTRA_TABLES 0x0008 -#define PCRE_EXTRA_MATCH_LIMIT_RECURSION 0x0010 - -/* Types */ - -struct real_pcre; /* declaration; the definition is private */ -typedef struct real_pcre pcre; - -/* When PCRE is compiled as a C++ library, the subject pointer type can be -replaced with a custom type. For conventional use, the public interface is a -const char *. */ - -#ifndef PCRE_SPTR -#define PCRE_SPTR const char * -#endif - -/* The structure for passing additional data to pcre_exec(). This is defined in -such as way as to be extensible. Always add new fields at the end, in order to -remain compatible. */ - -typedef struct pcre_extra { - unsigned long int flags; /* Bits for which fields are set */ - void *study_data; /* Opaque data from pcre_study() */ - unsigned long int match_limit; /* Maximum number of calls to match() */ - void *callout_data; /* Data passed back in callouts */ - const unsigned char *tables; /* Pointer to character tables */ - unsigned long int match_limit_recursion; /* Max recursive calls to match() */ -} pcre_extra; - -/* The structure for passing out data via the pcre_callout_function. We use a -structure so that new fields can be added on the end in future versions, -without changing the API of the function, thereby allowing old clients to work -without modification. */ - -typedef struct pcre_callout_block { - int version; /* Identifies version of block */ - /* ------------------------ Version 0 ------------------------------- */ - int callout_number; /* Number compiled into pattern */ - int *offset_vector; /* The offset vector */ - PCRE_SPTR subject; /* The subject being matched */ - int subject_length; /* The length of the subject */ - int start_match; /* Offset to start of this match attempt */ - int current_position; /* Where we currently are in the subject */ - int capture_top; /* Max current capture */ - int capture_last; /* Most recently closed capture */ - void *callout_data; /* Data passed in with the call */ - /* ------------------- Added for Version 1 -------------------------- */ - int pattern_position; /* Offset to next item in the pattern */ - int next_item_length; /* Length of next item in the pattern */ - /* ------------------------------------------------------------------ */ -} pcre_callout_block; - -/* Indirection for store get and free functions. These can be set to -alternative malloc/free functions if required. Special ones are used in the -non-recursive case for "frames". There is also an optional callout function -that is triggered by the (?) regex item. For Virtual Pascal, these definitions -have to take another form. */ - -#ifndef VPCOMPAT -PCRE_EXP_DECL void *(*pcre_malloc)(size_t); -PCRE_EXP_DECL void (*pcre_free)(void *); -PCRE_EXP_DECL void *(*pcre_stack_malloc)(size_t); -PCRE_EXP_DECL void (*pcre_stack_free)(void *); -PCRE_EXP_DECL int (*pcre_callout)(pcre_callout_block *); -#else /* VPCOMPAT */ -PCRE_EXP_DECL void *pcre_malloc(size_t); -PCRE_EXP_DECL void pcre_free(void *); -PCRE_EXP_DECL void *pcre_stack_malloc(size_t); -PCRE_EXP_DECL void pcre_stack_free(void *); -PCRE_EXP_DECL int pcre_callout(pcre_callout_block *); -#endif /* VPCOMPAT */ - -/* Exported PCRE functions */ - -PCRE_EXP_DECL pcre *pcre_compile(const char *, int, const char **, int *, - const unsigned char *); -PCRE_EXP_DECL pcre *pcre_compile2(const char *, int, int *, const char **, - int *, const unsigned char *); -PCRE_EXP_DECL int pcre_config(int, void *); -PCRE_EXP_DECL int pcre_copy_named_substring(const pcre *, const char *, - int *, int, const char *, char *, int); -PCRE_EXP_DECL int pcre_copy_substring(const char *, int *, int, int, char *, - int); -PCRE_EXP_DECL int pcre_dfa_exec(const pcre *, const pcre_extra *, - const char *, int, int, int, int *, int , int *, int); -PCRE_EXP_DECL int pcre_exec(const pcre *, const pcre_extra *, PCRE_SPTR, - int, int, int, int *, int); -PCRE_EXP_DECL void pcre_free_substring(const char *); -PCRE_EXP_DECL void pcre_free_substring_list(const char **); -PCRE_EXP_DECL int pcre_fullinfo(const pcre *, const pcre_extra *, int, - void *); -PCRE_EXP_DECL int pcre_get_named_substring(const pcre *, const char *, - int *, int, const char *, const char **); -PCRE_EXP_DECL int pcre_get_stringnumber(const pcre *, const char *); -PCRE_EXP_DECL int pcre_get_stringtable_entries(const pcre *, const char *, - char **, char **); -PCRE_EXP_DECL int pcre_get_substring(const char *, int *, int, int, - const char **); -PCRE_EXP_DECL int pcre_get_substring_list(const char *, int *, int, - const char ***); -PCRE_EXP_DECL int pcre_info(const pcre *, int *, int *); -PCRE_EXP_DECL const unsigned char *pcre_maketables(void); -PCRE_EXP_DECL int pcre_refcount(pcre *, int); -PCRE_EXP_DECL pcre_extra *pcre_study(const pcre *, int, const char **); -PCRE_EXP_DECL const char *pcre_version(void); - -#ifdef __cplusplus -} /* extern "C" */ -#endif - -#endif /* End of pcre.h */ diff --git a/libs/pcre/pcre_chartables.c.dist b/libs/pcre/pcre_chartables.c.dist deleted file mode 100644 index ae45db0ca3..0000000000 --- a/libs/pcre/pcre_chartables.c.dist +++ /dev/null @@ -1,198 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* This file contains character tables that are used when no external tables -are passed to PCRE by the application that calls it. The tables are used only -for characters whose code values are less than 256. - -This is a default version of the tables that assumes ASCII encoding. A program -called dftables (which is distributed with PCRE) can be used to build -alternative versions of this file. This is necessary if you are running in an -EBCDIC environment, or if you want to default to a different encoding, for -example ISO-8859-1. When dftables is run, it creates these tables in the -current locale. If PCRE is configured with --enable-rebuild-chartables, this -happens automatically. - -The following #includes are present because without the gcc 4.x may remove the -array definition from the final binary if PCRE is built into a static library -and dead code stripping is activated. This leads to link errors. Pulling in the -header ensures that the array gets flagged as "someone outside this compilation -unit might reference this" and so it will always be supplied to the linker. */ - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - -const unsigned char _pcre_default_tables[] = { - -/* This table is a lower casing table. */ - - 0, 1, 2, 3, 4, 5, 6, 7, - 8, 9, 10, 11, 12, 13, 14, 15, - 16, 17, 18, 19, 20, 21, 22, 23, - 24, 25, 26, 27, 28, 29, 30, 31, - 32, 33, 34, 35, 36, 37, 38, 39, - 40, 41, 42, 43, 44, 45, 46, 47, - 48, 49, 50, 51, 52, 53, 54, 55, - 56, 57, 58, 59, 60, 61, 62, 63, - 64, 97, 98, 99,100,101,102,103, - 104,105,106,107,108,109,110,111, - 112,113,114,115,116,117,118,119, - 120,121,122, 91, 92, 93, 94, 95, - 96, 97, 98, 99,100,101,102,103, - 104,105,106,107,108,109,110,111, - 112,113,114,115,116,117,118,119, - 120,121,122,123,124,125,126,127, - 128,129,130,131,132,133,134,135, - 136,137,138,139,140,141,142,143, - 144,145,146,147,148,149,150,151, - 152,153,154,155,156,157,158,159, - 160,161,162,163,164,165,166,167, - 168,169,170,171,172,173,174,175, - 176,177,178,179,180,181,182,183, - 184,185,186,187,188,189,190,191, - 192,193,194,195,196,197,198,199, - 200,201,202,203,204,205,206,207, - 208,209,210,211,212,213,214,215, - 216,217,218,219,220,221,222,223, - 224,225,226,227,228,229,230,231, - 232,233,234,235,236,237,238,239, - 240,241,242,243,244,245,246,247, - 248,249,250,251,252,253,254,255, - -/* This table is a case flipping table. */ - - 0, 1, 2, 3, 4, 5, 6, 7, - 8, 9, 10, 11, 12, 13, 14, 15, - 16, 17, 18, 19, 20, 21, 22, 23, - 24, 25, 26, 27, 28, 29, 30, 31, - 32, 33, 34, 35, 36, 37, 38, 39, - 40, 41, 42, 43, 44, 45, 46, 47, - 48, 49, 50, 51, 52, 53, 54, 55, - 56, 57, 58, 59, 60, 61, 62, 63, - 64, 97, 98, 99,100,101,102,103, - 104,105,106,107,108,109,110,111, - 112,113,114,115,116,117,118,119, - 120,121,122, 91, 92, 93, 94, 95, - 96, 65, 66, 67, 68, 69, 70, 71, - 72, 73, 74, 75, 76, 77, 78, 79, - 80, 81, 82, 83, 84, 85, 86, 87, - 88, 89, 90,123,124,125,126,127, - 128,129,130,131,132,133,134,135, - 136,137,138,139,140,141,142,143, - 144,145,146,147,148,149,150,151, - 152,153,154,155,156,157,158,159, - 160,161,162,163,164,165,166,167, - 168,169,170,171,172,173,174,175, - 176,177,178,179,180,181,182,183, - 184,185,186,187,188,189,190,191, - 192,193,194,195,196,197,198,199, - 200,201,202,203,204,205,206,207, - 208,209,210,211,212,213,214,215, - 216,217,218,219,220,221,222,223, - 224,225,226,227,228,229,230,231, - 232,233,234,235,236,237,238,239, - 240,241,242,243,244,245,246,247, - 248,249,250,251,252,253,254,255, - -/* This table contains bit maps for various character classes. Each map is 32 -bytes long and the bits run from the least significant end of each byte. The -classes that have their own maps are: space, xdigit, digit, upper, lower, word, -graph, print, punct, and cntrl. Other classes are built from combinations. */ - - 0x00,0x3e,0x00,0x00,0x01,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, - 0x7e,0x00,0x00,0x00,0x7e,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0xfe,0xff,0xff,0x07,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0x07, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, - 0xfe,0xff,0xff,0x87,0xfe,0xff,0xff,0x07, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0xff, - 0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0xff,0xff,0xff,0xff, - 0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0xfe,0xff,0x00,0xfc, - 0x01,0x00,0x00,0xf8,0x01,0x00,0x00,0x78, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0xff,0xff,0xff,0xff,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x80, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - -/* This table identifies various classes of character by individual bits: - 0x01 white space character - 0x02 letter - 0x04 decimal digit - 0x08 hexadecimal digit - 0x10 alphanumeric or '_' - 0x80 regular expression metacharacter or binary zero -*/ - - 0x80,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 */ - 0x00,0x01,0x01,0x00,0x01,0x01,0x00,0x00, /* 8- 15 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 16- 23 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */ - 0x01,0x00,0x00,0x00,0x80,0x00,0x00,0x00, /* - ' */ - 0x80,0x80,0x80,0x80,0x00,0x00,0x80,0x00, /* ( - / */ - 0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c, /* 0 - 7 */ - 0x1c,0x1c,0x00,0x00,0x00,0x00,0x00,0x80, /* 8 - ? */ - 0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* @ - G */ - 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* H - O */ - 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* P - W */ - 0x12,0x12,0x12,0x80,0x80,0x00,0x80,0x10, /* X - _ */ - 0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* ` - g */ - 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* h - o */ - 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* p - w */ - 0x12,0x12,0x12,0x80,0x80,0x00,0x00,0x00, /* x -127 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 128-135 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 136-143 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144-151 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 152-159 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160-167 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 168-175 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 176-183 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 192-199 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 200-207 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 208-215 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 216-223 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 224-231 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 232-239 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 240-247 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */ - -/* End of pcre_chartables.c */ diff --git a/libs/pcre/pcre_compile.c b/libs/pcre/pcre_compile.c deleted file mode 100644 index a90f105b06..0000000000 --- a/libs/pcre/pcre_compile.c +++ /dev/null @@ -1,6605 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2009 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains the external function pcre_compile(), along with -supporting internal functions that are not used by other modules. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#define NLBLOCK cd /* Block containing newline information */ -#define PSSTART start_pattern /* Field containing processed string start */ -#define PSEND end_pattern /* Field containing processed string end */ - -#include "pcre_internal.h" - - -/* When PCRE_DEBUG is defined, we need the pcre_printint() function, which is also -used by pcretest. PCRE_DEBUG is not defined when building a production library. */ - -#ifdef PCRE_DEBUG -#include "pcre_printint.src" -#endif - - -/* Macro for setting individual bits in class bitmaps. */ - -#define SETBIT(a,b) a[b/8] |= (1 << (b%8)) - -/* Maximum length value to check against when making sure that the integer that -holds the compiled pattern length does not overflow. We make it a bit less than -INT_MAX to allow for adding in group terminating bytes, so that we don't have -to check them every time. */ - -#define OFLOW_MAX (INT_MAX - 20) - - -/************************************************* -* Code parameters and static tables * -*************************************************/ - -/* This value specifies the size of stack workspace that is used during the -first pre-compile phase that determines how much memory is required. The regex -is partly compiled into this space, but the compiled parts are discarded as -soon as they can be, so that hopefully there will never be an overrun. The code -does, however, check for an overrun. The largest amount I've seen used is 218, -so this number is very generous. - -The same workspace is used during the second, actual compile phase for -remembering forward references to groups so that they can be filled in at the -end. Each entry in this list occupies LINK_SIZE bytes, so even when LINK_SIZE -is 4 there is plenty of room. */ - -#define COMPILE_WORK_SIZE (4096) - - -/* Table for handling escaped characters in the range '0'-'z'. Positive returns -are simple data values; negative values are for special things like \d and so -on. Zero means further processing is needed (for things like \x), or the escape -is invalid. */ - -#ifndef EBCDIC - -/* This is the "normal" table for ASCII systems or for EBCDIC systems running -in UTF-8 mode. */ - -static const short int escapes[] = { - 0, 0, - 0, 0, - 0, 0, - 0, 0, - 0, 0, - CHAR_COLON, CHAR_SEMICOLON, - CHAR_LESS_THAN_SIGN, CHAR_EQUALS_SIGN, - CHAR_GREATER_THAN_SIGN, CHAR_QUESTION_MARK, - CHAR_COMMERCIAL_AT, -ESC_A, - -ESC_B, -ESC_C, - -ESC_D, -ESC_E, - 0, -ESC_G, - -ESC_H, 0, - 0, -ESC_K, - 0, 0, - 0, 0, - -ESC_P, -ESC_Q, - -ESC_R, -ESC_S, - 0, 0, - -ESC_V, -ESC_W, - -ESC_X, 0, - -ESC_Z, CHAR_LEFT_SQUARE_BRACKET, - CHAR_BACKSLASH, CHAR_RIGHT_SQUARE_BRACKET, - CHAR_CIRCUMFLEX_ACCENT, CHAR_UNDERSCORE, - CHAR_GRAVE_ACCENT, 7, - -ESC_b, 0, - -ESC_d, ESC_e, - ESC_f, 0, - -ESC_h, 0, - 0, -ESC_k, - 0, 0, - ESC_n, 0, - -ESC_p, 0, - ESC_r, -ESC_s, - ESC_tee, 0, - -ESC_v, -ESC_w, - 0, 0, - -ESC_z -}; - -#else - -/* This is the "abnormal" table for EBCDIC systems without UTF-8 support. */ - -static const short int escapes[] = { -/* 48 */ 0, 0, 0, '.', '<', '(', '+', '|', -/* 50 */ '&', 0, 0, 0, 0, 0, 0, 0, -/* 58 */ 0, 0, '!', '$', '*', ')', ';', '~', -/* 60 */ '-', '/', 0, 0, 0, 0, 0, 0, -/* 68 */ 0, 0, '|', ',', '%', '_', '>', '?', -/* 70 */ 0, 0, 0, 0, 0, 0, 0, 0, -/* 78 */ 0, '`', ':', '#', '@', '\'', '=', '"', -/* 80 */ 0, 7, -ESC_b, 0, -ESC_d, ESC_e, ESC_f, 0, -/* 88 */-ESC_h, 0, 0, '{', 0, 0, 0, 0, -/* 90 */ 0, 0, -ESC_k, 'l', 0, ESC_n, 0, -ESC_p, -/* 98 */ 0, ESC_r, 0, '}', 0, 0, 0, 0, -/* A0 */ 0, '~', -ESC_s, ESC_tee, 0,-ESC_v, -ESC_w, 0, -/* A8 */ 0,-ESC_z, 0, 0, 0, '[', 0, 0, -/* B0 */ 0, 0, 0, 0, 0, 0, 0, 0, -/* B8 */ 0, 0, 0, 0, 0, ']', '=', '-', -/* C0 */ '{',-ESC_A, -ESC_B, -ESC_C, -ESC_D,-ESC_E, 0, -ESC_G, -/* C8 */-ESC_H, 0, 0, 0, 0, 0, 0, 0, -/* D0 */ '}', 0, -ESC_K, 0, 0, 0, 0, -ESC_P, -/* D8 */-ESC_Q,-ESC_R, 0, 0, 0, 0, 0, 0, -/* E0 */ '\\', 0, -ESC_S, 0, 0,-ESC_V, -ESC_W, -ESC_X, -/* E8 */ 0,-ESC_Z, 0, 0, 0, 0, 0, 0, -/* F0 */ 0, 0, 0, 0, 0, 0, 0, 0, -/* F8 */ 0, 0, 0, 0, 0, 0, 0, 0 -}; -#endif - - -/* Table of special "verbs" like (*PRUNE). This is a short table, so it is -searched linearly. Put all the names into a single string, in order to reduce -the number of relocations when a shared library is dynamically linked. The -string is built from string macros so that it works in UTF-8 mode on EBCDIC -platforms. */ - -typedef struct verbitem { - int len; - int op; -} verbitem; - -static const char verbnames[] = - STRING_ACCEPT0 - STRING_COMMIT0 - STRING_F0 - STRING_FAIL0 - STRING_PRUNE0 - STRING_SKIP0 - STRING_THEN; - -static const verbitem verbs[] = { - { 6, OP_ACCEPT }, - { 6, OP_COMMIT }, - { 1, OP_FAIL }, - { 4, OP_FAIL }, - { 5, OP_PRUNE }, - { 4, OP_SKIP }, - { 4, OP_THEN } -}; - -static const int verbcount = sizeof(verbs)/sizeof(verbitem); - - -/* Tables of names of POSIX character classes and their lengths. The names are -now all in a single string, to reduce the number of relocations when a shared -library is dynamically loaded. The list of lengths is terminated by a zero -length entry. The first three must be alpha, lower, upper, as this is assumed -for handling case independence. */ - -static const char posix_names[] = - STRING_alpha0 STRING_lower0 STRING_upper0 STRING_alnum0 - STRING_ascii0 STRING_blank0 STRING_cntrl0 STRING_digit0 - STRING_graph0 STRING_print0 STRING_punct0 STRING_space0 - STRING_word0 STRING_xdigit; - -static const uschar posix_name_lengths[] = { - 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 4, 6, 0 }; - -/* Table of class bit maps for each POSIX class. Each class is formed from a -base map, with an optional addition or removal of another map. Then, for some -classes, there is some additional tweaking: for [:blank:] the vertical space -characters are removed, and for [:alpha:] and [:alnum:] the underscore -character is removed. The triples in the table consist of the base map offset, -second map offset or -1 if no second map, and a non-negative value for map -addition or a negative value for map subtraction (if there are two maps). The -absolute value of the third field has these meanings: 0 => no tweaking, 1 => -remove vertical space characters, 2 => remove underscore. */ - -static const int posix_class_maps[] = { - cbit_word, cbit_digit, -2, /* alpha */ - cbit_lower, -1, 0, /* lower */ - cbit_upper, -1, 0, /* upper */ - cbit_word, -1, 2, /* alnum - word without underscore */ - cbit_print, cbit_cntrl, 0, /* ascii */ - cbit_space, -1, 1, /* blank - a GNU extension */ - cbit_cntrl, -1, 0, /* cntrl */ - cbit_digit, -1, 0, /* digit */ - cbit_graph, -1, 0, /* graph */ - cbit_print, -1, 0, /* print */ - cbit_punct, -1, 0, /* punct */ - cbit_space, -1, 0, /* space */ - cbit_word, -1, 0, /* word - a Perl extension */ - cbit_xdigit,-1, 0 /* xdigit */ -}; - - -#define STRING(a) # a -#define XSTRING(s) STRING(s) - -/* The texts of compile-time error messages. These are "char *" because they -are passed to the outside world. Do not ever re-use any error number, because -they are documented. Always add a new error instead. Messages marked DEAD below -are no longer used. This used to be a table of strings, but in order to reduce -the number of relocations needed when a shared library is loaded dynamically, -it is now one long string. We cannot use a table of offsets, because the -lengths of inserts such as XSTRING(MAX_NAME_SIZE) are not known. Instead, we -simply count through to the one we want - this isn't a performance issue -because these strings are used only when there is a compilation error. */ - -static const char error_texts[] = - "no error\0" - "\\ at end of pattern\0" - "\\c at end of pattern\0" - "unrecognized character follows \\\0" - "numbers out of order in {} quantifier\0" - /* 5 */ - "number too big in {} quantifier\0" - "missing terminating ] for character class\0" - "invalid escape sequence in character class\0" - "range out of order in character class\0" - "nothing to repeat\0" - /* 10 */ - "operand of unlimited repeat could match the empty string\0" /** DEAD **/ - "internal error: unexpected repeat\0" - "unrecognized character after (? or (?-\0" - "POSIX named classes are supported only within a class\0" - "missing )\0" - /* 15 */ - "reference to non-existent subpattern\0" - "erroffset passed as NULL\0" - "unknown option bit(s) set\0" - "missing ) after comment\0" - "parentheses nested too deeply\0" /** DEAD **/ - /* 20 */ - "regular expression is too large\0" - "failed to get memory\0" - "unmatched parentheses\0" - "internal error: code overflow\0" - "unrecognized character after (?<\0" - /* 25 */ - "lookbehind assertion is not fixed length\0" - "malformed number or name after (?(\0" - "conditional group contains more than two branches\0" - "assertion expected after (?(\0" - "(?R or (?[+-]digits must be followed by )\0" - /* 30 */ - "unknown POSIX class name\0" - "POSIX collating elements are not supported\0" - "this version of PCRE is not compiled with PCRE_UTF8 support\0" - "spare error\0" /** DEAD **/ - "character value in \\x{...} sequence is too large\0" - /* 35 */ - "invalid condition (?(0)\0" - "\\C not allowed in lookbehind assertion\0" - "PCRE does not support \\L, \\l, \\N, \\U, or \\u\0" - "number after (?C is > 255\0" - "closing ) for (?C expected\0" - /* 40 */ - "recursive call could loop indefinitely\0" - "unrecognized character after (?P\0" - "syntax error in subpattern name (missing terminator)\0" - "two named subpatterns have the same name\0" - "invalid UTF-8 string\0" - /* 45 */ - "support for \\P, \\p, and \\X has not been compiled\0" - "malformed \\P or \\p sequence\0" - "unknown property name after \\P or \\p\0" - "subpattern name is too long (maximum " XSTRING(MAX_NAME_SIZE) " characters)\0" - "too many named subpatterns (maximum " XSTRING(MAX_NAME_COUNT) ")\0" - /* 50 */ - "repeated subpattern is too long\0" /** DEAD **/ - "octal value is greater than \\377 (not in UTF-8 mode)\0" - "internal error: overran compiling workspace\0" - "internal error: previously-checked referenced subpattern not found\0" - "DEFINE group contains more than one branch\0" - /* 55 */ - "repeating a DEFINE group is not allowed\0" - "inconsistent NEWLINE options\0" - "\\g is not followed by a braced, angle-bracketed, or quoted name/number or by a plain number\0" - "a numbered reference must not be zero\0" - "(*VERB) with an argument is not supported\0" - /* 60 */ - "(*VERB) not recognized\0" - "number is too big\0" - "subpattern name expected\0" - "digit expected after (?+\0" - "] is an invalid data character in JavaScript compatibility mode"; - - -/* Table to identify digits and hex digits. This is used when compiling -patterns. Note that the tables in chartables are dependent on the locale, and -may mark arbitrary characters as digits - but the PCRE compiling code expects -to handle only 0-9, a-z, and A-Z as digits when compiling. That is why we have -a private table here. It costs 256 bytes, but it is a lot faster than doing -character value tests (at least in some simple cases I timed), and in some -applications one wants PCRE to compile efficiently as well as match -efficiently. - -For convenience, we use the same bit definitions as in chartables: - - 0x04 decimal digit - 0x08 hexadecimal digit - -Then we can use ctype_digit and ctype_xdigit in the code. */ - -#ifndef EBCDIC - -/* This is the "normal" case, for ASCII systems, and EBCDIC systems running in -UTF-8 mode. */ - -static const unsigned char digitab[] = - { - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 8- 15 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 16- 23 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - ' */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* ( - / */ - 0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c, /* 0 - 7 */ - 0x0c,0x0c,0x00,0x00,0x00,0x00,0x00,0x00, /* 8 - ? */ - 0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* @ - G */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* H - O */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* P - W */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* X - _ */ - 0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* ` - g */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* h - o */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* p - w */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* x -127 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 128-135 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 136-143 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144-151 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 152-159 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160-167 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 168-175 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 176-183 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 192-199 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 200-207 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 208-215 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 216-223 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 224-231 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 232-239 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 240-247 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */ - -#else - -/* This is the "abnormal" case, for EBCDIC systems not running in UTF-8 mode. */ - -static const unsigned char digitab[] = - { - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 0 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 8- 15 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 16- 23 10 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 32- 39 20 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 40- 47 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 48- 55 30 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 56- 63 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - 71 40 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 72- | */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* & - 87 50 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 88- 95 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - -103 60 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 104- ? */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 112-119 70 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 120- " */ - 0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* 128- g 80 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* h -143 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144- p 90 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* q -159 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160- x A0 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* y -175 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* ^ -183 B0 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */ - 0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* { - G C0 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* H -207 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* } - P D0 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* Q -223 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* \ - X E0 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* Y -239 */ - 0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c, /* 0 - 7 F0 */ - 0x0c,0x0c,0x00,0x00,0x00,0x00,0x00,0x00};/* 8 -255 */ - -static const unsigned char ebcdic_chartab[] = { /* chartable partial dup */ - 0x80,0x00,0x00,0x00,0x00,0x01,0x00,0x00, /* 0- 7 */ - 0x00,0x00,0x00,0x00,0x01,0x01,0x00,0x00, /* 8- 15 */ - 0x00,0x00,0x00,0x00,0x00,0x01,0x00,0x00, /* 16- 23 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */ - 0x00,0x00,0x00,0x00,0x00,0x01,0x00,0x00, /* 32- 39 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 40- 47 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 48- 55 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 56- 63 */ - 0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - 71 */ - 0x00,0x00,0x00,0x80,0x00,0x80,0x80,0x80, /* 72- | */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* & - 87 */ - 0x00,0x00,0x00,0x80,0x80,0x80,0x00,0x00, /* 88- 95 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - -103 */ - 0x00,0x00,0x00,0x00,0x00,0x10,0x00,0x80, /* 104- ? */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 112-119 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 120- " */ - 0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* 128- g */ - 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* h -143 */ - 0x00,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* 144- p */ - 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* q -159 */ - 0x00,0x00,0x12,0x12,0x12,0x12,0x12,0x12, /* 160- x */ - 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* y -175 */ - 0x80,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* ^ -183 */ - 0x00,0x00,0x80,0x00,0x00,0x00,0x00,0x00, /* 184-191 */ - 0x80,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* { - G */ - 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* H -207 */ - 0x00,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* } - P */ - 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* Q -223 */ - 0x00,0x00,0x12,0x12,0x12,0x12,0x12,0x12, /* \ - X */ - 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* Y -239 */ - 0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c, /* 0 - 7 */ - 0x1c,0x1c,0x00,0x00,0x00,0x00,0x00,0x00};/* 8 -255 */ -#endif - - -/* Definition to allow mutual recursion */ - -static BOOL - compile_regex(int, int, uschar **, const uschar **, int *, BOOL, BOOL, int, - int *, int *, branch_chain *, compile_data *, int *); - - - -/************************************************* -* Find an error text * -*************************************************/ - -/* The error texts are now all in one long string, to save on relocations. As -some of the text is of unknown length, we can't use a table of offsets. -Instead, just count through the strings. This is not a performance issue -because it happens only when there has been a compilation error. - -Argument: the error number -Returns: pointer to the error string -*/ - -static const char * -find_error_text(int n) -{ -const char *s = error_texts; -for (; n > 0; n--) while (*s++ != 0) {}; -return s; -} - - -/************************************************* -* Handle escapes * -*************************************************/ - -/* This function is called when a \ has been encountered. It either returns a -positive value for a simple escape such as \n, or a negative value which -encodes one of the more complicated things such as \d. A backreference to group -n is returned as -(ESC_REF + n); ESC_REF is the highest ESC_xxx macro. When -UTF-8 is enabled, a positive value greater than 255 may be returned. On entry, -ptr is pointing at the \. On exit, it is on the final character of the escape -sequence. - -Arguments: - ptrptr points to the pattern position pointer - errorcodeptr points to the errorcode variable - bracount number of previous extracting brackets - options the options bits - isclass TRUE if inside a character class - -Returns: zero or positive => a data character - negative => a special escape sequence - on error, errorcodeptr is set -*/ - -static int -check_escape(const uschar **ptrptr, int *errorcodeptr, int bracount, - int options, BOOL isclass) -{ -BOOL utf8 = (options & PCRE_UTF8) != 0; -const uschar *ptr = *ptrptr + 1; -int c, i; - -GETCHARINCTEST(c, ptr); /* Get character value, increment pointer */ -ptr--; /* Set pointer back to the last byte */ - -/* If backslash is at the end of the pattern, it's an error. */ - -if (c == 0) *errorcodeptr = ERR1; - -/* Non-alphanumerics are literals. For digits or letters, do an initial lookup -in a table. A non-zero result is something that can be returned immediately. -Otherwise further processing may be required. */ - -#ifndef EBCDIC /* ASCII/UTF-8 coding */ -else if (c < CHAR_0 || c > CHAR_z) {} /* Not alphanumeric */ -else if ((i = escapes[c - CHAR_0]) != 0) c = i; - -#else /* EBCDIC coding */ -else if (c < 'a' || (ebcdic_chartab[c] & 0x0E) == 0) {} /* Not alphanumeric */ -else if ((i = escapes[c - 0x48]) != 0) c = i; -#endif - -/* Escapes that need further processing, or are illegal. */ - -else - { - const uschar *oldptr; - BOOL braced, negated; - - switch (c) - { - /* A number of Perl escapes are not handled by PCRE. We give an explicit - error. */ - - case CHAR_l: - case CHAR_L: - case CHAR_N: - case CHAR_u: - case CHAR_U: - *errorcodeptr = ERR37; - break; - - /* \g must be followed by one of a number of specific things: - - (1) A number, either plain or braced. If positive, it is an absolute - backreference. If negative, it is a relative backreference. This is a Perl - 5.10 feature. - - (2) Perl 5.10 also supports \g{name} as a reference to a named group. This - is part of Perl's movement towards a unified syntax for back references. As - this is synonymous with \k{name}, we fudge it up by pretending it really - was \k. - - (3) For Oniguruma compatibility we also support \g followed by a name or a - number either in angle brackets or in single quotes. However, these are - (possibly recursive) subroutine calls, _not_ backreferences. Just return - the -ESC_g code (cf \k). */ - - case CHAR_g: - if (ptr[1] == CHAR_LESS_THAN_SIGN || ptr[1] == CHAR_APOSTROPHE) - { - c = -ESC_g; - break; - } - - /* Handle the Perl-compatible cases */ - - if (ptr[1] == CHAR_LEFT_CURLY_BRACKET) - { - const uschar *p; - for (p = ptr+2; *p != 0 && *p != CHAR_RIGHT_CURLY_BRACKET; p++) - if (*p != CHAR_MINUS && (digitab[*p] & ctype_digit) == 0) break; - if (*p != 0 && *p != CHAR_RIGHT_CURLY_BRACKET) - { - c = -ESC_k; - break; - } - braced = TRUE; - ptr++; - } - else braced = FALSE; - - if (ptr[1] == CHAR_MINUS) - { - negated = TRUE; - ptr++; - } - else negated = FALSE; - - c = 0; - while ((digitab[ptr[1]] & ctype_digit) != 0) - c = c * 10 + *(++ptr) - CHAR_0; - - if (c < 0) /* Integer overflow */ - { - *errorcodeptr = ERR61; - break; - } - - if (braced && *(++ptr) != CHAR_RIGHT_CURLY_BRACKET) - { - *errorcodeptr = ERR57; - break; - } - - if (c == 0) - { - *errorcodeptr = ERR58; - break; - } - - if (negated) - { - if (c > bracount) - { - *errorcodeptr = ERR15; - break; - } - c = bracount - (c - 1); - } - - c = -(ESC_REF + c); - break; - - /* The handling of escape sequences consisting of a string of digits - starting with one that is not zero is not straightforward. By experiment, - the way Perl works seems to be as follows: - - Outside a character class, the digits are read as a decimal number. If the - number is less than 10, or if there are that many previous extracting - left brackets, then it is a back reference. Otherwise, up to three octal - digits are read to form an escaped byte. Thus \123 is likely to be octal - 123 (cf \0123, which is octal 012 followed by the literal 3). If the octal - value is greater than 377, the least significant 8 bits are taken. Inside a - character class, \ followed by a digit is always an octal number. */ - - case CHAR_1: case CHAR_2: case CHAR_3: case CHAR_4: case CHAR_5: - case CHAR_6: case CHAR_7: case CHAR_8: case CHAR_9: - - if (!isclass) - { - oldptr = ptr; - c -= CHAR_0; - while ((digitab[ptr[1]] & ctype_digit) != 0) - c = c * 10 + *(++ptr) - CHAR_0; - if (c < 0) /* Integer overflow */ - { - *errorcodeptr = ERR61; - break; - } - if (c < 10 || c <= bracount) - { - c = -(ESC_REF + c); - break; - } - ptr = oldptr; /* Put the pointer back and fall through */ - } - - /* Handle an octal number following \. If the first digit is 8 or 9, Perl - generates a binary zero byte and treats the digit as a following literal. - Thus we have to pull back the pointer by one. */ - - if ((c = *ptr) >= CHAR_8) - { - ptr--; - c = 0; - break; - } - - /* \0 always starts an octal number, but we may drop through to here with a - larger first octal digit. The original code used just to take the least - significant 8 bits of octal numbers (I think this is what early Perls used - to do). Nowadays we allow for larger numbers in UTF-8 mode, but no more - than 3 octal digits. */ - - case CHAR_0: - c -= CHAR_0; - while(i++ < 2 && ptr[1] >= CHAR_0 && ptr[1] <= CHAR_7) - c = c * 8 + *(++ptr) - CHAR_0; - if (!utf8 && c > 255) *errorcodeptr = ERR51; - break; - - /* \x is complicated. \x{ddd} is a character number which can be greater - than 0xff in utf8 mode, but only if the ddd are hex digits. If not, { is - treated as a data character. */ - - case CHAR_x: - if (ptr[1] == CHAR_LEFT_CURLY_BRACKET) - { - const uschar *pt = ptr + 2; - int count = 0; - - c = 0; - while ((digitab[*pt] & ctype_xdigit) != 0) - { - register int cc = *pt++; - if (c == 0 && cc == CHAR_0) continue; /* Leading zeroes */ - count++; - -#ifndef EBCDIC /* ASCII/UTF-8 coding */ - if (cc >= CHAR_a) cc -= 32; /* Convert to upper case */ - c = (c << 4) + cc - ((cc < CHAR_A)? CHAR_0 : (CHAR_A - 10)); -#else /* EBCDIC coding */ - if (cc >= CHAR_a && cc <= CHAR_z) cc += 64; /* Convert to upper case */ - c = (c << 4) + cc - ((cc >= CHAR_0)? CHAR_0 : (CHAR_A - 10)); -#endif - } - - if (*pt == CHAR_RIGHT_CURLY_BRACKET) - { - if (c < 0 || count > (utf8? 8 : 2)) *errorcodeptr = ERR34; - ptr = pt; - break; - } - - /* If the sequence of hex digits does not end with '}', then we don't - recognize this construct; fall through to the normal \x handling. */ - } - - /* Read just a single-byte hex-defined char */ - - c = 0; - while (i++ < 2 && (digitab[ptr[1]] & ctype_xdigit) != 0) - { - int cc; /* Some compilers don't like */ - cc = *(++ptr); /* ++ in initializers */ -#ifndef EBCDIC /* ASCII/UTF-8 coding */ - if (cc >= CHAR_a) cc -= 32; /* Convert to upper case */ - c = c * 16 + cc - ((cc < CHAR_A)? CHAR_0 : (CHAR_A - 10)); -#else /* EBCDIC coding */ - if (cc <= CHAR_z) cc += 64; /* Convert to upper case */ - c = c * 16 + cc - ((cc >= CHAR_0)? CHAR_0 : (CHAR_A - 10)); -#endif - } - break; - - /* For \c, a following letter is upper-cased; then the 0x40 bit is flipped. - This coding is ASCII-specific, but then the whole concept of \cx is - ASCII-specific. (However, an EBCDIC equivalent has now been added.) */ - - case CHAR_c: - c = *(++ptr); - if (c == 0) - { - *errorcodeptr = ERR2; - break; - } - -#ifndef EBCDIC /* ASCII/UTF-8 coding */ - if (c >= CHAR_a && c <= CHAR_z) c -= 32; - c ^= 0x40; -#else /* EBCDIC coding */ - if (c >= CHAR_a && c <= CHAR_z) c += 64; - c ^= 0xC0; -#endif - break; - - /* PCRE_EXTRA enables extensions to Perl in the matter of escapes. Any - other alphanumeric following \ is an error if PCRE_EXTRA was set; - otherwise, for Perl compatibility, it is a literal. This code looks a bit - odd, but there used to be some cases other than the default, and there may - be again in future, so I haven't "optimized" it. */ - - default: - if ((options & PCRE_EXTRA) != 0) switch(c) - { - default: - *errorcodeptr = ERR3; - break; - } - break; - } - } - -*ptrptr = ptr; -return c; -} - - - -#ifdef SUPPORT_UCP -/************************************************* -* Handle \P and \p * -*************************************************/ - -/* This function is called after \P or \p has been encountered, provided that -PCRE is compiled with support for Unicode properties. On entry, ptrptr is -pointing at the P or p. On exit, it is pointing at the final character of the -escape sequence. - -Argument: - ptrptr points to the pattern position pointer - negptr points to a boolean that is set TRUE for negation else FALSE - dptr points to an int that is set to the detailed property value - errorcodeptr points to the error code variable - -Returns: type value from ucp_type_table, or -1 for an invalid type -*/ - -static int -get_ucp(const uschar **ptrptr, BOOL *negptr, int *dptr, int *errorcodeptr) -{ -int c, i, bot, top; -const uschar *ptr = *ptrptr; -char name[32]; - -c = *(++ptr); -if (c == 0) goto ERROR_RETURN; - -*negptr = FALSE; - -/* \P or \p can be followed by a name in {}, optionally preceded by ^ for -negation. */ - -if (c == CHAR_LEFT_CURLY_BRACKET) - { - if (ptr[1] == CHAR_CIRCUMFLEX_ACCENT) - { - *negptr = TRUE; - ptr++; - } - for (i = 0; i < (int)sizeof(name) - 1; i++) - { - c = *(++ptr); - if (c == 0) goto ERROR_RETURN; - if (c == CHAR_RIGHT_CURLY_BRACKET) break; - name[i] = c; - } - if (c != CHAR_RIGHT_CURLY_BRACKET) goto ERROR_RETURN; - name[i] = 0; - } - -/* Otherwise there is just one following character */ - -else - { - name[0] = c; - name[1] = 0; - } - -*ptrptr = ptr; - -/* Search for a recognized property name using binary chop */ - -bot = 0; -top = _pcre_utt_size; - -while (bot < top) - { - i = (bot + top) >> 1; - c = strcmp(name, _pcre_utt_names + _pcre_utt[i].name_offset); - if (c == 0) - { - *dptr = _pcre_utt[i].value; - return _pcre_utt[i].type; - } - if (c > 0) bot = i + 1; else top = i; - } - -*errorcodeptr = ERR47; -*ptrptr = ptr; -return -1; - -ERROR_RETURN: -*errorcodeptr = ERR46; -*ptrptr = ptr; -return -1; -} -#endif - - - - -/************************************************* -* Check for counted repeat * -*************************************************/ - -/* This function is called when a '{' is encountered in a place where it might -start a quantifier. It looks ahead to see if it really is a quantifier or not. -It is only a quantifier if it is one of the forms {ddd} {ddd,} or {ddd,ddd} -where the ddds are digits. - -Arguments: - p pointer to the first char after '{' - -Returns: TRUE or FALSE -*/ - -static BOOL -is_counted_repeat(const uschar *p) -{ -if ((digitab[*p++] & ctype_digit) == 0) return FALSE; -while ((digitab[*p] & ctype_digit) != 0) p++; -if (*p == CHAR_RIGHT_CURLY_BRACKET) return TRUE; - -if (*p++ != CHAR_COMMA) return FALSE; -if (*p == CHAR_RIGHT_CURLY_BRACKET) return TRUE; - -if ((digitab[*p++] & ctype_digit) == 0) return FALSE; -while ((digitab[*p] & ctype_digit) != 0) p++; - -return (*p == CHAR_RIGHT_CURLY_BRACKET); -} - - - -/************************************************* -* Read repeat counts * -*************************************************/ - -/* Read an item of the form {n,m} and return the values. This is called only -after is_counted_repeat() has confirmed that a repeat-count quantifier exists, -so the syntax is guaranteed to be correct, but we need to check the values. - -Arguments: - p pointer to first char after '{' - minp pointer to int for min - maxp pointer to int for max - returned as -1 if no max - errorcodeptr points to error code variable - -Returns: pointer to '}' on success; - current ptr on error, with errorcodeptr set non-zero -*/ - -static const uschar * -read_repeat_counts(const uschar *p, int *minp, int *maxp, int *errorcodeptr) -{ -int min = 0; -int max = -1; - -/* Read the minimum value and do a paranoid check: a negative value indicates -an integer overflow. */ - -while ((digitab[*p] & ctype_digit) != 0) min = min * 10 + *p++ - CHAR_0; -if (min < 0 || min > 65535) - { - *errorcodeptr = ERR5; - return p; - } - -/* Read the maximum value if there is one, and again do a paranoid on its size. -Also, max must not be less than min. */ - -if (*p == CHAR_RIGHT_CURLY_BRACKET) max = min; else - { - if (*(++p) != CHAR_RIGHT_CURLY_BRACKET) - { - max = 0; - while((digitab[*p] & ctype_digit) != 0) max = max * 10 + *p++ - CHAR_0; - if (max < 0 || max > 65535) - { - *errorcodeptr = ERR5; - return p; - } - if (max < min) - { - *errorcodeptr = ERR4; - return p; - } - } - } - -/* Fill in the required variables, and pass back the pointer to the terminating -'}'. */ - -*minp = min; -*maxp = max; -return p; -} - - - -/************************************************* -* Subroutine for finding forward reference * -*************************************************/ - -/* This recursive function is called only from find_parens() below. The -top-level call starts at the beginning of the pattern. All other calls must -start at a parenthesis. It scans along a pattern's text looking for capturing -subpatterns, and counting them. If it finds a named pattern that matches the -name it is given, it returns its number. Alternatively, if the name is NULL, it -returns when it reaches a given numbered subpattern. We know that if (?P< is -encountered, the name will be terminated by '>' because that is checked in the -first pass. Recursion is used to keep track of subpatterns that reset the -capturing group numbers - the (?| feature. - -Arguments: - ptrptr address of the current character pointer (updated) - cd compile background data - name name to seek, or NULL if seeking a numbered subpattern - lorn name length, or subpattern number if name is NULL - xmode TRUE if we are in /x mode - count pointer to the current capturing subpattern number (updated) - -Returns: the number of the named subpattern, or -1 if not found -*/ - -static int -find_parens_sub(uschar **ptrptr, compile_data *cd, const uschar *name, int lorn, - BOOL xmode, int *count) -{ -uschar *ptr = *ptrptr; -int start_count = *count; -int hwm_count = start_count; -BOOL dup_parens = FALSE; - -/* If the first character is a parenthesis, check on the type of group we are -dealing with. The very first call may not start with a parenthesis. */ - -if (ptr[0] == CHAR_LEFT_PARENTHESIS) - { - if (ptr[1] == CHAR_QUESTION_MARK && - ptr[2] == CHAR_VERTICAL_LINE) - { - ptr += 3; - dup_parens = TRUE; - } - - /* Handle a normal, unnamed capturing parenthesis */ - - else if (ptr[1] != CHAR_QUESTION_MARK && ptr[1] != CHAR_ASTERISK) - { - *count += 1; - if (name == NULL && *count == lorn) return *count; - ptr++; - } - - /* Handle a condition. If it is an assertion, just carry on so that it - is processed as normal. If not, skip to the closing parenthesis of the - condition (there can't be any nested parens. */ - - else if (ptr[2] == CHAR_LEFT_PARENTHESIS) - { - ptr += 2; - if (ptr[1] != CHAR_QUESTION_MARK) - { - while (*ptr != 0 && *ptr != CHAR_RIGHT_PARENTHESIS) ptr++; - if (*ptr != 0) ptr++; - } - } - - /* We have either (? or (* and not a condition */ - - else - { - ptr += 2; - if (*ptr == CHAR_P) ptr++; /* Allow optional P */ - - /* We have to disambiguate (? for named groups */ - - if ((*ptr == CHAR_LESS_THAN_SIGN && ptr[1] != CHAR_EXCLAMATION_MARK && - ptr[1] != CHAR_EQUALS_SIGN) || *ptr == CHAR_APOSTROPHE) - { - int term; - const uschar *thisname; - *count += 1; - if (name == NULL && *count == lorn) return *count; - term = *ptr++; - if (term == CHAR_LESS_THAN_SIGN) term = CHAR_GREATER_THAN_SIGN; - thisname = ptr; - while (*ptr != term) ptr++; - if (name != NULL && lorn == ptr - thisname && - strncmp((const char *)name, (const char *)thisname, lorn) == 0) - return *count; - } - } - } - -/* Past any initial parenthesis handling, scan for parentheses or vertical -bars. */ - -for (; *ptr != 0; ptr++) - { - /* Skip over backslashed characters and also entire \Q...\E */ - - if (*ptr == CHAR_BACKSLASH) - { - if (*(++ptr) == 0) goto FAIL_EXIT; - if (*ptr == CHAR_Q) for (;;) - { - while (*(++ptr) != 0 && *ptr != CHAR_BACKSLASH) {}; - if (*ptr == 0) goto FAIL_EXIT; - if (*(++ptr) == CHAR_E) break; - } - continue; - } - - /* Skip over character classes; this logic must be similar to the way they - are handled for real. If the first character is '^', skip it. Also, if the - first few characters (either before or after ^) are \Q\E or \E we skip them - too. This makes for compatibility with Perl. Note the use of STR macros to - encode "Q\\E" so that it works in UTF-8 on EBCDIC platforms. */ - - if (*ptr == CHAR_LEFT_SQUARE_BRACKET) - { - BOOL negate_class = FALSE; - for (;;) - { - int c = *(++ptr); - if (c == CHAR_BACKSLASH) - { - if (ptr[1] == CHAR_E) - ptr++; - else if (strncmp((const char *)ptr+1, - STR_Q STR_BACKSLASH STR_E, 3) == 0) - ptr += 3; - else - break; - } - else if (!negate_class && c == CHAR_CIRCUMFLEX_ACCENT) - negate_class = TRUE; - else break; - } - - /* If the next character is ']', it is a data character that must be - skipped, except in JavaScript compatibility mode. */ - - if (ptr[1] == CHAR_RIGHT_SQUARE_BRACKET && - (cd->external_options & PCRE_JAVASCRIPT_COMPAT) == 0) - ptr++; - - while (*(++ptr) != CHAR_RIGHT_SQUARE_BRACKET) - { - if (*ptr == 0) return -1; - if (*ptr == CHAR_BACKSLASH) - { - if (*(++ptr) == 0) goto FAIL_EXIT; - if (*ptr == CHAR_Q) for (;;) - { - while (*(++ptr) != 0 && *ptr != CHAR_BACKSLASH) {}; - if (*ptr == 0) goto FAIL_EXIT; - if (*(++ptr) == CHAR_E) break; - } - continue; - } - } - continue; - } - - /* Skip comments in /x mode */ - - if (xmode && *ptr == CHAR_NUMBER_SIGN) - { - while (*(++ptr) != 0 && *ptr != CHAR_NL) {}; - if (*ptr == 0) goto FAIL_EXIT; - continue; - } - - /* Check for the special metacharacters */ - - if (*ptr == CHAR_LEFT_PARENTHESIS) - { - int rc = find_parens_sub(&ptr, cd, name, lorn, xmode, count); - if (rc > 0) return rc; - if (*ptr == 0) goto FAIL_EXIT; - } - - else if (*ptr == CHAR_RIGHT_PARENTHESIS) - { - if (dup_parens && *count < hwm_count) *count = hwm_count; - *ptrptr = ptr; - return -1; - } - - else if (*ptr == CHAR_VERTICAL_LINE && dup_parens) - { - if (*count > hwm_count) hwm_count = *count; - *count = start_count; - } - } - -FAIL_EXIT: -*ptrptr = ptr; -return -1; -} - - - - -/************************************************* -* Find forward referenced subpattern * -*************************************************/ - -/* This function scans along a pattern's text looking for capturing -subpatterns, and counting them. If it finds a named pattern that matches the -name it is given, it returns its number. Alternatively, if the name is NULL, it -returns when it reaches a given numbered subpattern. This is used for forward -references to subpatterns. We used to be able to start this scan from the -current compiling point, using the current count value from cd->bracount, and -do it all in a single loop, but the addition of the possibility of duplicate -subpattern numbers means that we have to scan from the very start, in order to -take account of such duplicates, and to use a recursive function to keep track -of the different types of group. - -Arguments: - cd compile background data - name name to seek, or NULL if seeking a numbered subpattern - lorn name length, or subpattern number if name is NULL - xmode TRUE if we are in /x mode - -Returns: the number of the found subpattern, or -1 if not found -*/ - -static int -find_parens(compile_data *cd, const uschar *name, int lorn, BOOL xmode) -{ -uschar *ptr = (uschar *)cd->start_pattern; -int count = 0; -int rc; - -/* If the pattern does not start with an opening parenthesis, the first call -to find_parens_sub() will scan right to the end (if necessary). However, if it -does start with a parenthesis, find_parens_sub() will return when it hits the -matching closing parens. That is why we have to have a loop. */ - -for (;;) - { - rc = find_parens_sub(&ptr, cd, name, lorn, xmode, &count); - if (rc > 0 || *ptr++ == 0) break; - } - -return rc; -} - - - - -/************************************************* -* Find first significant op code * -*************************************************/ - -/* This is called by several functions that scan a compiled expression looking -for a fixed first character, or an anchoring op code etc. It skips over things -that do not influence this. For some calls, a change of option is important. -For some calls, it makes sense to skip negative forward and all backward -assertions, and also the \b assertion; for others it does not. - -Arguments: - code pointer to the start of the group - options pointer to external options - optbit the option bit whose changing is significant, or - zero if none are - skipassert TRUE if certain assertions are to be skipped - -Returns: pointer to the first significant opcode -*/ - -static const uschar* -first_significant_code(const uschar *code, int *options, int optbit, - BOOL skipassert) -{ -for (;;) - { - switch ((int)*code) - { - case OP_OPT: - if (optbit > 0 && ((int)code[1] & optbit) != (*options & optbit)) - *options = (int)code[1]; - code += 2; - break; - - case OP_ASSERT_NOT: - case OP_ASSERTBACK: - case OP_ASSERTBACK_NOT: - if (!skipassert) return code; - do code += GET(code, 1); while (*code == OP_ALT); - code += _pcre_OP_lengths[*code]; - break; - - case OP_WORD_BOUNDARY: - case OP_NOT_WORD_BOUNDARY: - if (!skipassert) return code; - /* Fall through */ - - case OP_CALLOUT: - case OP_CREF: - case OP_RREF: - case OP_DEF: - code += _pcre_OP_lengths[*code]; - break; - - default: - return code; - } - } -/* Control never reaches here */ -} - - - - -/************************************************* -* Find the fixed length of a pattern * -*************************************************/ - -/* Scan a pattern and compute the fixed length of subject that will match it, -if the length is fixed. This is needed for dealing with backward assertions. -In UTF8 mode, the result is in characters rather than bytes. - -Arguments: - code points to the start of the pattern (the bracket) - options the compiling options - -Returns: the fixed length, or -1 if there is no fixed length, - or -2 if \C was encountered -*/ - -static int -find_fixedlength(uschar *code, int options) -{ -int length = -1; - -register int branchlength = 0; -register uschar *cc = code + 1 + LINK_SIZE; - -/* Scan along the opcodes for this branch. If we get to the end of the -branch, check the length against that of the other branches. */ - -for (;;) - { - int d; - register int op = *cc; - switch (op) - { - case OP_CBRA: - case OP_BRA: - case OP_ONCE: - case OP_COND: - d = find_fixedlength(cc + ((op == OP_CBRA)? 2:0), options); - if (d < 0) return d; - branchlength += d; - do cc += GET(cc, 1); while (*cc == OP_ALT); - cc += 1 + LINK_SIZE; - break; - - /* Reached end of a branch; if it's a ket it is the end of a nested - call. If it's ALT it is an alternation in a nested call. If it is - END it's the end of the outer call. All can be handled by the same code. */ - - case OP_ALT: - case OP_KET: - case OP_KETRMAX: - case OP_KETRMIN: - case OP_END: - if (length < 0) length = branchlength; - else if (length != branchlength) return -1; - if (*cc != OP_ALT) return length; - cc += 1 + LINK_SIZE; - branchlength = 0; - break; - - /* Skip over assertive subpatterns */ - - case OP_ASSERT: - case OP_ASSERT_NOT: - case OP_ASSERTBACK: - case OP_ASSERTBACK_NOT: - do cc += GET(cc, 1); while (*cc == OP_ALT); - /* Fall through */ - - /* Skip over things that don't match chars */ - - case OP_REVERSE: - case OP_CREF: - case OP_RREF: - case OP_DEF: - case OP_OPT: - case OP_CALLOUT: - case OP_SOD: - case OP_SOM: - case OP_EOD: - case OP_EODN: - case OP_CIRC: - case OP_DOLL: - case OP_NOT_WORD_BOUNDARY: - case OP_WORD_BOUNDARY: - cc += _pcre_OP_lengths[*cc]; - break; - - /* Handle literal characters */ - - case OP_CHAR: - case OP_CHARNC: - case OP_NOT: - branchlength++; - cc += 2; -#ifdef SUPPORT_UTF8 - if ((options & PCRE_UTF8) != 0) - { - while ((*cc & 0xc0) == 0x80) cc++; - } -#endif - break; - - /* Handle exact repetitions. The count is already in characters, but we - need to skip over a multibyte character in UTF8 mode. */ - - case OP_EXACT: - branchlength += GET2(cc,1); - cc += 4; -#ifdef SUPPORT_UTF8 - if ((options & PCRE_UTF8) != 0) - { - while((*cc & 0x80) == 0x80) cc++; - } -#endif - break; - - case OP_TYPEEXACT: - branchlength += GET2(cc,1); - if (cc[3] == OP_PROP || cc[3] == OP_NOTPROP) cc += 2; - cc += 4; - break; - - /* Handle single-char matchers */ - - case OP_PROP: - case OP_NOTPROP: - cc += 2; - /* Fall through */ - - case OP_NOT_DIGIT: - case OP_DIGIT: - case OP_NOT_WHITESPACE: - case OP_WHITESPACE: - case OP_NOT_WORDCHAR: - case OP_WORDCHAR: - case OP_ANY: - case OP_ALLANY: - branchlength++; - cc++; - break; - - /* The single-byte matcher isn't allowed */ - - case OP_ANYBYTE: - return -2; - - /* Check a class for variable quantification */ - -#ifdef SUPPORT_UTF8 - case OP_XCLASS: - cc += GET(cc, 1) - 33; - /* Fall through */ -#endif - - case OP_CLASS: - case OP_NCLASS: - cc += 33; - - switch (*cc) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRQUERY: - case OP_CRMINQUERY: - return -1; - - case OP_CRRANGE: - case OP_CRMINRANGE: - if (GET2(cc,1) != GET2(cc,3)) return -1; - branchlength += GET2(cc,1); - cc += 5; - break; - - default: - branchlength++; - } - break; - - /* Anything else is variable length */ - - default: - return -1; - } - } -/* Control never gets here */ -} - - - - -/************************************************* -* Scan compiled regex for numbered bracket * -*************************************************/ - -/* This little function scans through a compiled pattern until it finds a -capturing bracket with the given number. - -Arguments: - code points to start of expression - utf8 TRUE in UTF-8 mode - number the required bracket number - -Returns: pointer to the opcode for the bracket, or NULL if not found -*/ - -static const uschar * -find_bracket(const uschar *code, BOOL utf8, int number) -{ -for (;;) - { - register int c = *code; - if (c == OP_END) return NULL; - - /* XCLASS is used for classes that cannot be represented just by a bit - map. This includes negated single high-valued characters. The length in - the table is zero; the actual length is stored in the compiled code. */ - - if (c == OP_XCLASS) code += GET(code, 1); - - /* Handle capturing bracket */ - - else if (c == OP_CBRA) - { - int n = GET2(code, 1+LINK_SIZE); - if (n == number) return (uschar *)code; - code += _pcre_OP_lengths[c]; - } - - /* Otherwise, we can get the item's length from the table, except that for - repeated character types, we have to test for \p and \P, which have an extra - two bytes of parameters. */ - - else - { - switch(c) - { - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - case OP_TYPEPOSSTAR: - case OP_TYPEPOSPLUS: - case OP_TYPEPOSQUERY: - if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2; - break; - - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - case OP_TYPEEXACT: - case OP_TYPEPOSUPTO: - if (code[3] == OP_PROP || code[3] == OP_NOTPROP) code += 2; - break; - } - - /* Add in the fixed length from the table */ - - code += _pcre_OP_lengths[c]; - - /* In UTF-8 mode, opcodes that are followed by a character may be followed by - a multi-byte character. The length in the table is a minimum, so we have to - arrange to skip the extra bytes. */ - -#ifdef SUPPORT_UTF8 - if (utf8) switch(c) - { - case OP_CHAR: - case OP_CHARNC: - case OP_EXACT: - case OP_UPTO: - case OP_MINUPTO: - case OP_POSUPTO: - case OP_STAR: - case OP_MINSTAR: - case OP_POSSTAR: - case OP_PLUS: - case OP_MINPLUS: - case OP_POSPLUS: - case OP_QUERY: - case OP_MINQUERY: - case OP_POSQUERY: - if (code[-1] >= 0xc0) code += _pcre_utf8_table4[code[-1] & 0x3f]; - break; - } -#else - (void)(utf8); /* Keep compiler happy by referencing function argument */ -#endif - } - } -} - - - -/************************************************* -* Scan compiled regex for recursion reference * -*************************************************/ - -/* This little function scans through a compiled pattern until it finds an -instance of OP_RECURSE. - -Arguments: - code points to start of expression - utf8 TRUE in UTF-8 mode - -Returns: pointer to the opcode for OP_RECURSE, or NULL if not found -*/ - -static const uschar * -find_recurse(const uschar *code, BOOL utf8) -{ -for (;;) - { - register int c = *code; - if (c == OP_END) return NULL; - if (c == OP_RECURSE) return code; - - /* XCLASS is used for classes that cannot be represented just by a bit - map. This includes negated single high-valued characters. The length in - the table is zero; the actual length is stored in the compiled code. */ - - if (c == OP_XCLASS) code += GET(code, 1); - - /* Otherwise, we can get the item's length from the table, except that for - repeated character types, we have to test for \p and \P, which have an extra - two bytes of parameters. */ - - else - { - switch(c) - { - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - case OP_TYPEPOSSTAR: - case OP_TYPEPOSPLUS: - case OP_TYPEPOSQUERY: - if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2; - break; - - case OP_TYPEPOSUPTO: - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - case OP_TYPEEXACT: - if (code[3] == OP_PROP || code[3] == OP_NOTPROP) code += 2; - break; - } - - /* Add in the fixed length from the table */ - - code += _pcre_OP_lengths[c]; - - /* In UTF-8 mode, opcodes that are followed by a character may be followed - by a multi-byte character. The length in the table is a minimum, so we have - to arrange to skip the extra bytes. */ - -#ifdef SUPPORT_UTF8 - if (utf8) switch(c) - { - case OP_CHAR: - case OP_CHARNC: - case OP_EXACT: - case OP_UPTO: - case OP_MINUPTO: - case OP_POSUPTO: - case OP_STAR: - case OP_MINSTAR: - case OP_POSSTAR: - case OP_PLUS: - case OP_MINPLUS: - case OP_POSPLUS: - case OP_QUERY: - case OP_MINQUERY: - case OP_POSQUERY: - if (code[-1] >= 0xc0) code += _pcre_utf8_table4[code[-1] & 0x3f]; - break; - } -#else - (void)(utf8); /* Keep compiler happy by referencing function argument */ -#endif - } - } -} - - - -/************************************************* -* Scan compiled branch for non-emptiness * -*************************************************/ - -/* This function scans through a branch of a compiled pattern to see whether it -can match the empty string or not. It is called from could_be_empty() -below and from compile_branch() when checking for an unlimited repeat of a -group that can match nothing. Note that first_significant_code() skips over -backward and negative forward assertions when its final argument is TRUE. If we -hit an unclosed bracket, we return "empty" - this means we've struck an inner -bracket whose current branch will already have been scanned. - -Arguments: - code points to start of search - endcode points to where to stop - utf8 TRUE if in UTF8 mode - -Returns: TRUE if what is matched could be empty -*/ - -static BOOL -could_be_empty_branch(const uschar *code, const uschar *endcode, BOOL utf8) -{ -register int c; -for (code = first_significant_code(code + _pcre_OP_lengths[*code], NULL, 0, TRUE); - code < endcode; - code = first_significant_code(code + _pcre_OP_lengths[c], NULL, 0, TRUE)) - { - const uschar *ccode; - - c = *code; - - /* Skip over forward assertions; the other assertions are skipped by - first_significant_code() with a TRUE final argument. */ - - if (c == OP_ASSERT) - { - do code += GET(code, 1); while (*code == OP_ALT); - c = *code; - continue; - } - - /* Groups with zero repeats can of course be empty; skip them. */ - - if (c == OP_BRAZERO || c == OP_BRAMINZERO || c == OP_SKIPZERO) - { - code += _pcre_OP_lengths[c]; - do code += GET(code, 1); while (*code == OP_ALT); - c = *code; - continue; - } - - /* For other groups, scan the branches. */ - - if (c == OP_BRA || c == OP_CBRA || c == OP_ONCE || c == OP_COND) - { - BOOL empty_branch; - if (GET(code, 1) == 0) return TRUE; /* Hit unclosed bracket */ - - /* If a conditional group has only one branch, there is a second, implied, - empty branch, so just skip over the conditional, because it could be empty. - Otherwise, scan the individual branches of the group. */ - - if (c == OP_COND && code[GET(code, 1)] != OP_ALT) - code += GET(code, 1); - else - { - empty_branch = FALSE; - do - { - if (!empty_branch && could_be_empty_branch(code, endcode, utf8)) - empty_branch = TRUE; - code += GET(code, 1); - } - while (*code == OP_ALT); - if (!empty_branch) return FALSE; /* All branches are non-empty */ - } - - c = *code; - continue; - } - - /* Handle the other opcodes */ - - switch (c) - { - /* Check for quantifiers after a class. XCLASS is used for classes that - cannot be represented just by a bit map. This includes negated single - high-valued characters. The length in _pcre_OP_lengths[] is zero; the - actual length is stored in the compiled code, so we must update "code" - here. */ - -#ifdef SUPPORT_UTF8 - case OP_XCLASS: - ccode = code += GET(code, 1); - goto CHECK_CLASS_REPEAT; -#endif - - case OP_CLASS: - case OP_NCLASS: - ccode = code + 33; - -#ifdef SUPPORT_UTF8 - CHECK_CLASS_REPEAT: -#endif - - switch (*ccode) - { - case OP_CRSTAR: /* These could be empty; continue */ - case OP_CRMINSTAR: - case OP_CRQUERY: - case OP_CRMINQUERY: - break; - - default: /* Non-repeat => class must match */ - case OP_CRPLUS: /* These repeats aren't empty */ - case OP_CRMINPLUS: - return FALSE; - - case OP_CRRANGE: - case OP_CRMINRANGE: - if (GET2(ccode, 1) > 0) return FALSE; /* Minimum > 0 */ - break; - } - break; - - /* Opcodes that must match a character */ - - case OP_PROP: - case OP_NOTPROP: - case OP_EXTUNI: - case OP_NOT_DIGIT: - case OP_DIGIT: - case OP_NOT_WHITESPACE: - case OP_WHITESPACE: - case OP_NOT_WORDCHAR: - case OP_WORDCHAR: - case OP_ANY: - case OP_ALLANY: - case OP_ANYBYTE: - case OP_CHAR: - case OP_CHARNC: - case OP_NOT: - case OP_PLUS: - case OP_MINPLUS: - case OP_POSPLUS: - case OP_EXACT: - case OP_NOTPLUS: - case OP_NOTMINPLUS: - case OP_NOTPOSPLUS: - case OP_NOTEXACT: - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEPOSPLUS: - case OP_TYPEEXACT: - return FALSE; - - /* These are going to continue, as they may be empty, but we have to - fudge the length for the \p and \P cases. */ - - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPOSSTAR: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - case OP_TYPEPOSQUERY: - if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2; - break; - - /* Same for these */ - - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - case OP_TYPEPOSUPTO: - if (code[3] == OP_PROP || code[3] == OP_NOTPROP) code += 2; - break; - - /* End of branch */ - - case OP_KET: - case OP_KETRMAX: - case OP_KETRMIN: - case OP_ALT: - return TRUE; - - /* In UTF-8 mode, STAR, MINSTAR, POSSTAR, QUERY, MINQUERY, POSQUERY, UPTO, - MINUPTO, and POSUPTO may be followed by a multibyte character */ - -#ifdef SUPPORT_UTF8 - case OP_STAR: - case OP_MINSTAR: - case OP_POSSTAR: - case OP_QUERY: - case OP_MINQUERY: - case OP_POSQUERY: - case OP_UPTO: - case OP_MINUPTO: - case OP_POSUPTO: - if (utf8) while ((code[2] & 0xc0) == 0x80) code++; - break; -#endif - } - } - -return TRUE; -} - - - -/************************************************* -* Scan compiled regex for non-emptiness * -*************************************************/ - -/* This function is called to check for left recursive calls. We want to check -the current branch of the current pattern to see if it could match the empty -string. If it could, we must look outwards for branches at other levels, -stopping when we pass beyond the bracket which is the subject of the recursion. - -Arguments: - code points to start of the recursion - endcode points to where to stop (current RECURSE item) - bcptr points to the chain of current (unclosed) branch starts - utf8 TRUE if in UTF-8 mode - -Returns: TRUE if what is matched could be empty -*/ - -static BOOL -could_be_empty(const uschar *code, const uschar *endcode, branch_chain *bcptr, - BOOL utf8) -{ -while (bcptr != NULL && bcptr->current >= code) - { - if (!could_be_empty_branch(bcptr->current, endcode, utf8)) return FALSE; - bcptr = bcptr->outer; - } -return TRUE; -} - - - -/************************************************* -* Check for POSIX class syntax * -*************************************************/ - -/* This function is called when the sequence "[:" or "[." or "[=" is -encountered in a character class. It checks whether this is followed by a -sequence of characters terminated by a matching ":]" or ".]" or "=]". If we -reach an unescaped ']' without the special preceding character, return FALSE. - -Originally, this function only recognized a sequence of letters between the -terminators, but it seems that Perl recognizes any sequence of characters, -though of course unknown POSIX names are subsequently rejected. Perl gives an -"Unknown POSIX class" error for [:f\oo:] for example, where previously PCRE -didn't consider this to be a POSIX class. Likewise for [:1234:]. - -The problem in trying to be exactly like Perl is in the handling of escapes. We -have to be sure that [abc[:x\]pqr] is *not* treated as containing a POSIX -class, but [abc[:x\]pqr:]] is (so that an error can be generated). The code -below handles the special case of \], but does not try to do any other escape -processing. This makes it different from Perl for cases such as [:l\ower:] -where Perl recognizes it as the POSIX class "lower" but PCRE does not recognize -"l\ower". This is a lesser evil that not diagnosing bad classes when Perl does, -I think. - -Arguments: - ptr pointer to the initial [ - endptr where to return the end pointer - -Returns: TRUE or FALSE -*/ - -static BOOL -check_posix_syntax(const uschar *ptr, const uschar **endptr) -{ -int terminator; /* Don't combine these lines; the Solaris cc */ -terminator = *(++ptr); /* compiler warns about "non-constant" initializer. */ -for (++ptr; *ptr != 0; ptr++) - { - if (*ptr == CHAR_BACKSLASH && ptr[1] == CHAR_RIGHT_SQUARE_BRACKET) ptr++; else - { - if (*ptr == CHAR_RIGHT_SQUARE_BRACKET) return FALSE; - if (*ptr == terminator && ptr[1] == CHAR_RIGHT_SQUARE_BRACKET) - { - *endptr = ptr; - return TRUE; - } - } - } -return FALSE; -} - - - - -/************************************************* -* Check POSIX class name * -*************************************************/ - -/* This function is called to check the name given in a POSIX-style class entry -such as [:alnum:]. - -Arguments: - ptr points to the first letter - len the length of the name - -Returns: a value representing the name, or -1 if unknown -*/ - -static int -check_posix_name(const uschar *ptr, int len) -{ -const char *pn = posix_names; -register int yield = 0; -while (posix_name_lengths[yield] != 0) - { - if (len == posix_name_lengths[yield] && - strncmp((const char *)ptr, pn, len) == 0) return yield; - pn += posix_name_lengths[yield] + 1; - yield++; - } -return -1; -} - - -/************************************************* -* Adjust OP_RECURSE items in repeated group * -*************************************************/ - -/* OP_RECURSE items contain an offset from the start of the regex to the group -that is referenced. This means that groups can be replicated for fixed -repetition simply by copying (because the recursion is allowed to refer to -earlier groups that are outside the current group). However, when a group is -optional (i.e. the minimum quantifier is zero), OP_BRAZERO or OP_SKIPZERO is -inserted before it, after it has been compiled. This means that any OP_RECURSE -items within it that refer to the group itself or any contained groups have to -have their offsets adjusted. That one of the jobs of this function. Before it -is called, the partially compiled regex must be temporarily terminated with -OP_END. - -This function has been extended with the possibility of forward references for -recursions and subroutine calls. It must also check the list of such references -for the group we are dealing with. If it finds that one of the recursions in -the current group is on this list, it adjusts the offset in the list, not the -value in the reference (which is a group number). - -Arguments: - group points to the start of the group - adjust the amount by which the group is to be moved - utf8 TRUE in UTF-8 mode - cd contains pointers to tables etc. - save_hwm the hwm forward reference pointer at the start of the group - -Returns: nothing -*/ - -static void -adjust_recurse(uschar *group, int adjust, BOOL utf8, compile_data *cd, - uschar *save_hwm) -{ -uschar *ptr = group; - -while ((ptr = (uschar *)find_recurse(ptr, utf8)) != NULL) - { - int offset; - uschar *hc; - - /* See if this recursion is on the forward reference list. If so, adjust the - reference. */ - - for (hc = save_hwm; hc < cd->hwm; hc += LINK_SIZE) - { - offset = GET(hc, 0); - if (cd->start_code + offset == ptr + 1) - { - PUT(hc, 0, offset + adjust); - break; - } - } - - /* Otherwise, adjust the recursion offset if it's after the start of this - group. */ - - if (hc >= cd->hwm) - { - offset = GET(ptr, 1); - if (cd->start_code + offset >= group) PUT(ptr, 1, offset + adjust); - } - - ptr += 1 + LINK_SIZE; - } -} - - - -/************************************************* -* Insert an automatic callout point * -*************************************************/ - -/* This function is called when the PCRE_AUTO_CALLOUT option is set, to insert -callout points before each pattern item. - -Arguments: - code current code pointer - ptr current pattern pointer - cd pointers to tables etc - -Returns: new code pointer -*/ - -static uschar * -auto_callout(uschar *code, const uschar *ptr, compile_data *cd) -{ -*code++ = OP_CALLOUT; -*code++ = 255; -PUT(code, 0, ptr - cd->start_pattern); /* Pattern offset */ -PUT(code, LINK_SIZE, 0); /* Default length */ -return code + 2*LINK_SIZE; -} - - - -/************************************************* -* Complete a callout item * -*************************************************/ - -/* A callout item contains the length of the next item in the pattern, which -we can't fill in till after we have reached the relevant point. This is used -for both automatic and manual callouts. - -Arguments: - previous_callout points to previous callout item - ptr current pattern pointer - cd pointers to tables etc - -Returns: nothing -*/ - -static void -complete_callout(uschar *previous_callout, const uschar *ptr, compile_data *cd) -{ -int length = ptr - cd->start_pattern - GET(previous_callout, 2); -PUT(previous_callout, 2 + LINK_SIZE, length); -} - - - -#ifdef SUPPORT_UCP -/************************************************* -* Get othercase range * -*************************************************/ - -/* This function is passed the start and end of a class range, in UTF-8 mode -with UCP support. It searches up the characters, looking for internal ranges of -characters in the "other" case. Each call returns the next one, updating the -start address. - -Arguments: - cptr points to starting character value; updated - d end value - ocptr where to put start of othercase range - odptr where to put end of othercase range - -Yield: TRUE when range returned; FALSE when no more -*/ - -static BOOL -get_othercase_range(unsigned int *cptr, unsigned int d, unsigned int *ocptr, - unsigned int *odptr) -{ -unsigned int c, othercase, next; - -for (c = *cptr; c <= d; c++) - { if ((othercase = UCD_OTHERCASE(c)) != c) break; } - -if (c > d) return FALSE; - -*ocptr = othercase; -next = othercase + 1; - -for (++c; c <= d; c++) - { - if (UCD_OTHERCASE(c) != next) break; - next++; - } - -*odptr = next - 1; -*cptr = c; - -return TRUE; -} -#endif /* SUPPORT_UCP */ - - - -/************************************************* -* Check if auto-possessifying is possible * -*************************************************/ - -/* This function is called for unlimited repeats of certain items, to see -whether the next thing could possibly match the repeated item. If not, it makes -sense to automatically possessify the repeated item. - -Arguments: - op_code the repeated op code - this data for this item, depends on the opcode - utf8 TRUE in UTF-8 mode - utf8_char used for utf8 character bytes, NULL if not relevant - ptr next character in pattern - options options bits - cd contains pointers to tables etc. - -Returns: TRUE if possessifying is wanted -*/ - -static BOOL -check_auto_possessive(int op_code, int item, BOOL utf8, uschar *utf8_char, - const uschar *ptr, int options, compile_data *cd) -{ -int next; - -/* Skip whitespace and comments in extended mode */ - -if ((options & PCRE_EXTENDED) != 0) - { - for (;;) - { - while ((cd->ctypes[*ptr] & ctype_space) != 0) ptr++; - if (*ptr == CHAR_NUMBER_SIGN) - { - while (*(++ptr) != 0) - if (IS_NEWLINE(ptr)) { ptr += cd->nllen; break; } - } - else break; - } - } - -/* If the next item is one that we can handle, get its value. A non-negative -value is a character, a negative value is an escape value. */ - -if (*ptr == CHAR_BACKSLASH) - { - int temperrorcode = 0; - next = check_escape(&ptr, &temperrorcode, cd->bracount, options, FALSE); - if (temperrorcode != 0) return FALSE; - ptr++; /* Point after the escape sequence */ - } - -else if ((cd->ctypes[*ptr] & ctype_meta) == 0) - { -#ifdef SUPPORT_UTF8 - if (utf8) { GETCHARINC(next, ptr); } else -#endif - next = *ptr++; - } - -else return FALSE; - -/* Skip whitespace and comments in extended mode */ - -if ((options & PCRE_EXTENDED) != 0) - { - for (;;) - { - while ((cd->ctypes[*ptr] & ctype_space) != 0) ptr++; - if (*ptr == CHAR_NUMBER_SIGN) - { - while (*(++ptr) != 0) - if (IS_NEWLINE(ptr)) { ptr += cd->nllen; break; } - } - else break; - } - } - -/* If the next thing is itself optional, we have to give up. */ - -if (*ptr == CHAR_ASTERISK || *ptr == CHAR_QUESTION_MARK || - strncmp((char *)ptr, STR_LEFT_CURLY_BRACKET STR_0 STR_COMMA, 3) == 0) - return FALSE; - -/* Now compare the next item with the previous opcode. If the previous is a -positive single character match, "item" either contains the character or, if -"item" is greater than 127 in utf8 mode, the character's bytes are in -utf8_char. */ - - -/* Handle cases when the next item is a character. */ - -if (next >= 0) switch(op_code) - { - case OP_CHAR: -#ifdef SUPPORT_UTF8 - if (utf8 && item > 127) { GETCHAR(item, utf8_char); } -#else - (void)(utf8_char); /* Keep compiler happy by referencing function argument */ -#endif - return item != next; - - /* For CHARNC (caseless character) we must check the other case. If we have - Unicode property support, we can use it to test the other case of - high-valued characters. */ - - case OP_CHARNC: -#ifdef SUPPORT_UTF8 - if (utf8 && item > 127) { GETCHAR(item, utf8_char); } -#endif - if (item == next) return FALSE; -#ifdef SUPPORT_UTF8 - if (utf8) - { - unsigned int othercase; - if (next < 128) othercase = cd->fcc[next]; else -#ifdef SUPPORT_UCP - othercase = UCD_OTHERCASE((unsigned int)next); -#else - othercase = NOTACHAR; -#endif - return (unsigned int)item != othercase; - } - else -#endif /* SUPPORT_UTF8 */ - return (item != cd->fcc[next]); /* Non-UTF-8 mode */ - - /* For OP_NOT, "item" must be a single-byte character. */ - - case OP_NOT: - if (item == next) return TRUE; - if ((options & PCRE_CASELESS) == 0) return FALSE; -#ifdef SUPPORT_UTF8 - if (utf8) - { - unsigned int othercase; - if (next < 128) othercase = cd->fcc[next]; else -#ifdef SUPPORT_UCP - othercase = UCD_OTHERCASE(next); -#else - othercase = NOTACHAR; -#endif - return (unsigned int)item == othercase; - } - else -#endif /* SUPPORT_UTF8 */ - return (item == cd->fcc[next]); /* Non-UTF-8 mode */ - - case OP_DIGIT: - return next > 127 || (cd->ctypes[next] & ctype_digit) == 0; - - case OP_NOT_DIGIT: - return next <= 127 && (cd->ctypes[next] & ctype_digit) != 0; - - case OP_WHITESPACE: - return next > 127 || (cd->ctypes[next] & ctype_space) == 0; - - case OP_NOT_WHITESPACE: - return next <= 127 && (cd->ctypes[next] & ctype_space) != 0; - - case OP_WORDCHAR: - return next > 127 || (cd->ctypes[next] & ctype_word) == 0; - - case OP_NOT_WORDCHAR: - return next <= 127 && (cd->ctypes[next] & ctype_word) != 0; - - case OP_HSPACE: - case OP_NOT_HSPACE: - switch(next) - { - case 0x09: - case 0x20: - case 0xa0: - case 0x1680: - case 0x180e: - case 0x2000: - case 0x2001: - case 0x2002: - case 0x2003: - case 0x2004: - case 0x2005: - case 0x2006: - case 0x2007: - case 0x2008: - case 0x2009: - case 0x200A: - case 0x202f: - case 0x205f: - case 0x3000: - return op_code != OP_HSPACE; - default: - return op_code == OP_HSPACE; - } - - case OP_VSPACE: - case OP_NOT_VSPACE: - switch(next) - { - case 0x0a: - case 0x0b: - case 0x0c: - case 0x0d: - case 0x85: - case 0x2028: - case 0x2029: - return op_code != OP_VSPACE; - default: - return op_code == OP_VSPACE; - } - - default: - return FALSE; - } - - -/* Handle the case when the next item is \d, \s, etc. */ - -switch(op_code) - { - case OP_CHAR: - case OP_CHARNC: -#ifdef SUPPORT_UTF8 - if (utf8 && item > 127) { GETCHAR(item, utf8_char); } -#endif - switch(-next) - { - case ESC_d: - return item > 127 || (cd->ctypes[item] & ctype_digit) == 0; - - case ESC_D: - return item <= 127 && (cd->ctypes[item] & ctype_digit) != 0; - - case ESC_s: - return item > 127 || (cd->ctypes[item] & ctype_space) == 0; - - case ESC_S: - return item <= 127 && (cd->ctypes[item] & ctype_space) != 0; - - case ESC_w: - return item > 127 || (cd->ctypes[item] & ctype_word) == 0; - - case ESC_W: - return item <= 127 && (cd->ctypes[item] & ctype_word) != 0; - - case ESC_h: - case ESC_H: - switch(item) - { - case 0x09: - case 0x20: - case 0xa0: - case 0x1680: - case 0x180e: - case 0x2000: - case 0x2001: - case 0x2002: - case 0x2003: - case 0x2004: - case 0x2005: - case 0x2006: - case 0x2007: - case 0x2008: - case 0x2009: - case 0x200A: - case 0x202f: - case 0x205f: - case 0x3000: - return -next != ESC_h; - default: - return -next == ESC_h; - } - - case ESC_v: - case ESC_V: - switch(item) - { - case 0x0a: - case 0x0b: - case 0x0c: - case 0x0d: - case 0x85: - case 0x2028: - case 0x2029: - return -next != ESC_v; - default: - return -next == ESC_v; - } - - default: - return FALSE; - } - - case OP_DIGIT: - return next == -ESC_D || next == -ESC_s || next == -ESC_W || - next == -ESC_h || next == -ESC_v; - - case OP_NOT_DIGIT: - return next == -ESC_d; - - case OP_WHITESPACE: - return next == -ESC_S || next == -ESC_d || next == -ESC_w; - - case OP_NOT_WHITESPACE: - return next == -ESC_s || next == -ESC_h || next == -ESC_v; - - case OP_HSPACE: - return next == -ESC_S || next == -ESC_H || next == -ESC_d || next == -ESC_w; - - case OP_NOT_HSPACE: - return next == -ESC_h; - - /* Can't have \S in here because VT matches \S (Perl anomaly) */ - case OP_VSPACE: - return next == -ESC_V || next == -ESC_d || next == -ESC_w; - - case OP_NOT_VSPACE: - return next == -ESC_v; - - case OP_WORDCHAR: - return next == -ESC_W || next == -ESC_s || next == -ESC_h || next == -ESC_v; - - case OP_NOT_WORDCHAR: - return next == -ESC_w || next == -ESC_d; - - default: - return FALSE; - } - -/* Control does not reach here */ -} - - - -/************************************************* -* Compile one branch * -*************************************************/ - -/* Scan the pattern, compiling it into the a vector. If the options are -changed during the branch, the pointer is used to change the external options -bits. This function is used during the pre-compile phase when we are trying -to find out the amount of memory needed, as well as during the real compile -phase. The value of lengthptr distinguishes the two phases. - -Arguments: - optionsptr pointer to the option bits - codeptr points to the pointer to the current code point - ptrptr points to the current pattern pointer - errorcodeptr points to error code variable - firstbyteptr set to initial literal character, or < 0 (REQ_UNSET, REQ_NONE) - reqbyteptr set to the last literal character required, else < 0 - bcptr points to current branch chain - cd contains pointers to tables etc. - lengthptr NULL during the real compile phase - points to length accumulator during pre-compile phase - -Returns: TRUE on success - FALSE, with *errorcodeptr set non-zero on error -*/ - -static BOOL -compile_branch(int *optionsptr, uschar **codeptr, const uschar **ptrptr, - int *errorcodeptr, int *firstbyteptr, int *reqbyteptr, branch_chain *bcptr, - compile_data *cd, int *lengthptr) -{ -int repeat_type, op_type; -int repeat_min = 0, repeat_max = 0; /* To please picky compilers */ -int bravalue = 0; -int greedy_default, greedy_non_default; -int firstbyte, reqbyte; -int zeroreqbyte, zerofirstbyte; -int req_caseopt, reqvary, tempreqvary; -int options = *optionsptr; -int after_manual_callout = 0; -int length_prevgroup = 0; -register int c; -register uschar *code = *codeptr; -uschar *last_code = code; -uschar *orig_code = code; -uschar *tempcode; -BOOL inescq = FALSE; -BOOL groupsetfirstbyte = FALSE; -const uschar *ptr = *ptrptr; -const uschar *tempptr; -uschar *previous = NULL; -uschar *previous_callout = NULL; -uschar *save_hwm = NULL; -uschar classbits[32]; - -#ifdef SUPPORT_UTF8 -BOOL class_utf8; -BOOL utf8 = (options & PCRE_UTF8) != 0; -uschar *class_utf8data; -uschar *class_utf8data_base; -uschar utf8_char[6]; -#else -BOOL utf8 = FALSE; -uschar *utf8_char = NULL; -#endif - -#ifdef PCRE_DEBUG -if (lengthptr != NULL) DPRINTF((">> start branch\n")); -#endif - -/* Set up the default and non-default settings for greediness */ - -greedy_default = ((options & PCRE_UNGREEDY) != 0); -greedy_non_default = greedy_default ^ 1; - -/* Initialize no first byte, no required byte. REQ_UNSET means "no char -matching encountered yet". It gets changed to REQ_NONE if we hit something that -matches a non-fixed char first char; reqbyte just remains unset if we never -find one. - -When we hit a repeat whose minimum is zero, we may have to adjust these values -to take the zero repeat into account. This is implemented by setting them to -zerofirstbyte and zeroreqbyte when such a repeat is encountered. The individual -item types that can be repeated set these backoff variables appropriately. */ - -firstbyte = reqbyte = zerofirstbyte = zeroreqbyte = REQ_UNSET; - -/* The variable req_caseopt contains either the REQ_CASELESS value or zero, -according to the current setting of the caseless flag. REQ_CASELESS is a bit -value > 255. It is added into the firstbyte or reqbyte variables to record the -case status of the value. This is used only for ASCII characters. */ - -req_caseopt = ((options & PCRE_CASELESS) != 0)? REQ_CASELESS : 0; - -/* Switch on next character until the end of the branch */ - -for (;; ptr++) - { - BOOL negate_class; - BOOL should_flip_negation; - BOOL possessive_quantifier; - BOOL is_quantifier; - BOOL is_recurse; - BOOL reset_bracount; - int class_charcount; - int class_lastchar; - int newoptions; - int recno; - int refsign; - int skipbytes; - int subreqbyte; - int subfirstbyte; - int terminator; - int mclength; - uschar mcbuffer[8]; - - /* Get next byte in the pattern */ - - c = *ptr; - - /* If we are in the pre-compile phase, accumulate the length used for the - previous cycle of this loop. */ - - if (lengthptr != NULL) - { -#ifdef PCRE_DEBUG - if (code > cd->hwm) cd->hwm = code; /* High water info */ -#endif - if (code > cd->start_workspace + COMPILE_WORK_SIZE) /* Check for overrun */ - { - *errorcodeptr = ERR52; - goto FAILED; - } - - /* There is at least one situation where code goes backwards: this is the - case of a zero quantifier after a class (e.g. [ab]{0}). At compile time, - the class is simply eliminated. However, it is created first, so we have to - allow memory for it. Therefore, don't ever reduce the length at this point. - */ - - if (code < last_code) code = last_code; - - /* Paranoid check for integer overflow */ - - if (OFLOW_MAX - *lengthptr < code - last_code) - { - *errorcodeptr = ERR20; - goto FAILED; - } - - *lengthptr += code - last_code; - DPRINTF(("length=%d added %d c=%c\n", *lengthptr, code - last_code, c)); - - /* If "previous" is set and it is not at the start of the work space, move - it back to there, in order to avoid filling up the work space. Otherwise, - if "previous" is NULL, reset the current code pointer to the start. */ - - if (previous != NULL) - { - if (previous > orig_code) - { - memmove(orig_code, previous, code - previous); - code -= previous - orig_code; - previous = orig_code; - } - } - else code = orig_code; - - /* Remember where this code item starts so we can pick up the length - next time round. */ - - last_code = code; - } - - /* In the real compile phase, just check the workspace used by the forward - reference list. */ - - else if (cd->hwm > cd->start_workspace + COMPILE_WORK_SIZE) - { - *errorcodeptr = ERR52; - goto FAILED; - } - - /* If in \Q...\E, check for the end; if not, we have a literal */ - - if (inescq && c != 0) - { - if (c == CHAR_BACKSLASH && ptr[1] == CHAR_E) - { - inescq = FALSE; - ptr++; - continue; - } - else - { - if (previous_callout != NULL) - { - if (lengthptr == NULL) /* Don't attempt in pre-compile phase */ - complete_callout(previous_callout, ptr, cd); - previous_callout = NULL; - } - if ((options & PCRE_AUTO_CALLOUT) != 0) - { - previous_callout = code; - code = auto_callout(code, ptr, cd); - } - goto NORMAL_CHAR; - } - } - - /* Fill in length of a previous callout, except when the next thing is - a quantifier. */ - - is_quantifier = - c == CHAR_ASTERISK || c == CHAR_PLUS || c == CHAR_QUESTION_MARK || - (c == CHAR_LEFT_CURLY_BRACKET && is_counted_repeat(ptr+1)); - - if (!is_quantifier && previous_callout != NULL && - after_manual_callout-- <= 0) - { - if (lengthptr == NULL) /* Don't attempt in pre-compile phase */ - complete_callout(previous_callout, ptr, cd); - previous_callout = NULL; - } - - /* In extended mode, skip white space and comments */ - - if ((options & PCRE_EXTENDED) != 0) - { - if ((cd->ctypes[c] & ctype_space) != 0) continue; - if (c == CHAR_NUMBER_SIGN) - { - while (*(++ptr) != 0) - { - if (IS_NEWLINE(ptr)) { ptr += cd->nllen - 1; break; } - } - if (*ptr != 0) continue; - - /* Else fall through to handle end of string */ - c = 0; - } - } - - /* No auto callout for quantifiers. */ - - if ((options & PCRE_AUTO_CALLOUT) != 0 && !is_quantifier) - { - previous_callout = code; - code = auto_callout(code, ptr, cd); - } - - switch(c) - { - /* ===================================================================*/ - case 0: /* The branch terminates at string end */ - case CHAR_VERTICAL_LINE: /* or | or ) */ - case CHAR_RIGHT_PARENTHESIS: - *firstbyteptr = firstbyte; - *reqbyteptr = reqbyte; - *codeptr = code; - *ptrptr = ptr; - if (lengthptr != NULL) - { - if (OFLOW_MAX - *lengthptr < code - last_code) - { - *errorcodeptr = ERR20; - goto FAILED; - } - *lengthptr += code - last_code; /* To include callout length */ - DPRINTF((">> end branch\n")); - } - return TRUE; - - - /* ===================================================================*/ - /* Handle single-character metacharacters. In multiline mode, ^ disables - the setting of any following char as a first character. */ - - case CHAR_CIRCUMFLEX_ACCENT: - if ((options & PCRE_MULTILINE) != 0) - { - if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE; - } - previous = NULL; - *code++ = OP_CIRC; - break; - - case CHAR_DOLLAR_SIGN: - previous = NULL; - *code++ = OP_DOLL; - break; - - /* There can never be a first char if '.' is first, whatever happens about - repeats. The value of reqbyte doesn't change either. */ - - case CHAR_DOT: - if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE; - zerofirstbyte = firstbyte; - zeroreqbyte = reqbyte; - previous = code; - *code++ = ((options & PCRE_DOTALL) != 0)? OP_ALLANY: OP_ANY; - break; - - - /* ===================================================================*/ - /* Character classes. If the included characters are all < 256, we build a - 32-byte bitmap of the permitted characters, except in the special case - where there is only one such character. For negated classes, we build the - map as usual, then invert it at the end. However, we use a different opcode - so that data characters > 255 can be handled correctly. - - If the class contains characters outside the 0-255 range, a different - opcode is compiled. It may optionally have a bit map for characters < 256, - but those above are are explicitly listed afterwards. A flag byte tells - whether the bitmap is present, and whether this is a negated class or not. - - In JavaScript compatibility mode, an isolated ']' causes an error. In - default (Perl) mode, it is treated as a data character. */ - - case CHAR_RIGHT_SQUARE_BRACKET: - if ((cd->external_options & PCRE_JAVASCRIPT_COMPAT) != 0) - { - *errorcodeptr = ERR64; - goto FAILED; - } - goto NORMAL_CHAR; - - case CHAR_LEFT_SQUARE_BRACKET: - previous = code; - - /* PCRE supports POSIX class stuff inside a class. Perl gives an error if - they are encountered at the top level, so we'll do that too. */ - - if ((ptr[1] == CHAR_COLON || ptr[1] == CHAR_DOT || - ptr[1] == CHAR_EQUALS_SIGN) && - check_posix_syntax(ptr, &tempptr)) - { - *errorcodeptr = (ptr[1] == CHAR_COLON)? ERR13 : ERR31; - goto FAILED; - } - - /* If the first character is '^', set the negation flag and skip it. Also, - if the first few characters (either before or after ^) are \Q\E or \E we - skip them too. This makes for compatibility with Perl. */ - - negate_class = FALSE; - for (;;) - { - c = *(++ptr); - if (c == CHAR_BACKSLASH) - { - if (ptr[1] == CHAR_E) - ptr++; - else if (strncmp((const char *)ptr+1, - STR_Q STR_BACKSLASH STR_E, 3) == 0) - ptr += 3; - else - break; - } - else if (!negate_class && c == CHAR_CIRCUMFLEX_ACCENT) - negate_class = TRUE; - else break; - } - - /* Empty classes are allowed in JavaScript compatibility mode. Otherwise, - an initial ']' is taken as a data character -- the code below handles - that. In JS mode, [] must always fail, so generate OP_FAIL, whereas - [^] must match any character, so generate OP_ALLANY. */ - - if (c == CHAR_RIGHT_SQUARE_BRACKET && - (cd->external_options & PCRE_JAVASCRIPT_COMPAT) != 0) - { - *code++ = negate_class? OP_ALLANY : OP_FAIL; - if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE; - zerofirstbyte = firstbyte; - break; - } - - /* If a class contains a negative special such as \S, we need to flip the - negation flag at the end, so that support for characters > 255 works - correctly (they are all included in the class). */ - - should_flip_negation = FALSE; - - /* Keep a count of chars with values < 256 so that we can optimize the case - of just a single character (as long as it's < 256). However, For higher - valued UTF-8 characters, we don't yet do any optimization. */ - - class_charcount = 0; - class_lastchar = -1; - - /* Initialize the 32-char bit map to all zeros. We build the map in a - temporary bit of memory, in case the class contains only 1 character (less - than 256), because in that case the compiled code doesn't use the bit map. - */ - - memset(classbits, 0, 32 * sizeof(uschar)); - -#ifdef SUPPORT_UTF8 - class_utf8 = FALSE; /* No chars >= 256 */ - class_utf8data = code + LINK_SIZE + 2; /* For UTF-8 items */ - class_utf8data_base = class_utf8data; /* For resetting in pass 1 */ -#endif - - /* Process characters until ] is reached. By writing this as a "do" it - means that an initial ] is taken as a data character. At the start of the - loop, c contains the first byte of the character. */ - - if (c != 0) do - { - const uschar *oldptr; - -#ifdef SUPPORT_UTF8 - if (utf8 && c > 127) - { /* Braces are required because the */ - GETCHARLEN(c, ptr, ptr); /* macro generates multiple statements */ - } - - /* In the pre-compile phase, accumulate the length of any UTF-8 extra - data and reset the pointer. This is so that very large classes that - contain a zillion UTF-8 characters no longer overwrite the work space - (which is on the stack). */ - - if (lengthptr != NULL) - { - *lengthptr += class_utf8data - class_utf8data_base; - class_utf8data = class_utf8data_base; - } - -#endif - - /* Inside \Q...\E everything is literal except \E */ - - if (inescq) - { - if (c == CHAR_BACKSLASH && ptr[1] == CHAR_E) /* If we are at \E */ - { - inescq = FALSE; /* Reset literal state */ - ptr++; /* Skip the 'E' */ - continue; /* Carry on with next */ - } - goto CHECK_RANGE; /* Could be range if \E follows */ - } - - /* Handle POSIX class names. Perl allows a negation extension of the - form [:^name:]. A square bracket that doesn't match the syntax is - treated as a literal. We also recognize the POSIX constructions - [.ch.] and [=ch=] ("collating elements") and fault them, as Perl - 5.6 and 5.8 do. */ - - if (c == CHAR_LEFT_SQUARE_BRACKET && - (ptr[1] == CHAR_COLON || ptr[1] == CHAR_DOT || - ptr[1] == CHAR_EQUALS_SIGN) && check_posix_syntax(ptr, &tempptr)) - { - BOOL local_negate = FALSE; - int posix_class, taboffset, tabopt; - register const uschar *cbits = cd->cbits; - uschar pbits[32]; - - if (ptr[1] != CHAR_COLON) - { - *errorcodeptr = ERR31; - goto FAILED; - } - - ptr += 2; - if (*ptr == CHAR_CIRCUMFLEX_ACCENT) - { - local_negate = TRUE; - should_flip_negation = TRUE; /* Note negative special */ - ptr++; - } - - posix_class = check_posix_name(ptr, tempptr - ptr); - if (posix_class < 0) - { - *errorcodeptr = ERR30; - goto FAILED; - } - - /* If matching is caseless, upper and lower are converted to - alpha. This relies on the fact that the class table starts with - alpha, lower, upper as the first 3 entries. */ - - if ((options & PCRE_CASELESS) != 0 && posix_class <= 2) - posix_class = 0; - - /* We build the bit map for the POSIX class in a chunk of local store - because we may be adding and subtracting from it, and we don't want to - subtract bits that may be in the main map already. At the end we or the - result into the bit map that is being built. */ - - posix_class *= 3; - - /* Copy in the first table (always present) */ - - memcpy(pbits, cbits + posix_class_maps[posix_class], - 32 * sizeof(uschar)); - - /* If there is a second table, add or remove it as required. */ - - taboffset = posix_class_maps[posix_class + 1]; - tabopt = posix_class_maps[posix_class + 2]; - - if (taboffset >= 0) - { - if (tabopt >= 0) - for (c = 0; c < 32; c++) pbits[c] |= cbits[c + taboffset]; - else - for (c = 0; c < 32; c++) pbits[c] &= ~cbits[c + taboffset]; - } - - /* Not see if we need to remove any special characters. An option - value of 1 removes vertical space and 2 removes underscore. */ - - if (tabopt < 0) tabopt = -tabopt; - if (tabopt == 1) pbits[1] &= ~0x3c; - else if (tabopt == 2) pbits[11] &= 0x7f; - - /* Add the POSIX table or its complement into the main table that is - being built and we are done. */ - - if (local_negate) - for (c = 0; c < 32; c++) classbits[c] |= ~pbits[c]; - else - for (c = 0; c < 32; c++) classbits[c] |= pbits[c]; - - ptr = tempptr + 1; - class_charcount = 10; /* Set > 1; assumes more than 1 per class */ - continue; /* End of POSIX syntax handling */ - } - - /* Backslash may introduce a single character, or it may introduce one - of the specials, which just set a flag. The sequence \b is a special - case. Inside a class (and only there) it is treated as backspace. - Elsewhere it marks a word boundary. Other escapes have preset maps ready - to 'or' into the one we are building. We assume they have more than one - character in them, so set class_charcount bigger than one. */ - - if (c == CHAR_BACKSLASH) - { - c = check_escape(&ptr, errorcodeptr, cd->bracount, options, TRUE); - if (*errorcodeptr != 0) goto FAILED; - - if (-c == ESC_b) c = CHAR_BS; /* \b is backspace in a class */ - else if (-c == ESC_X) c = CHAR_X; /* \X is literal X in a class */ - else if (-c == ESC_R) c = CHAR_R; /* \R is literal R in a class */ - else if (-c == ESC_Q) /* Handle start of quoted string */ - { - if (ptr[1] == CHAR_BACKSLASH && ptr[2] == CHAR_E) - { - ptr += 2; /* avoid empty string */ - } - else inescq = TRUE; - continue; - } - else if (-c == ESC_E) continue; /* Ignore orphan \E */ - - if (c < 0) - { - register const uschar *cbits = cd->cbits; - class_charcount += 2; /* Greater than 1 is what matters */ - - /* Save time by not doing this in the pre-compile phase. */ - - if (lengthptr == NULL) switch (-c) - { - case ESC_d: - for (c = 0; c < 32; c++) classbits[c] |= cbits[c+cbit_digit]; - continue; - - case ESC_D: - should_flip_negation = TRUE; - for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_digit]; - continue; - - case ESC_w: - for (c = 0; c < 32; c++) classbits[c] |= cbits[c+cbit_word]; - continue; - - case ESC_W: - should_flip_negation = TRUE; - for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_word]; - continue; - - case ESC_s: - for (c = 0; c < 32; c++) classbits[c] |= cbits[c+cbit_space]; - classbits[1] &= ~0x08; /* Perl 5.004 onwards omits VT from \s */ - continue; - - case ESC_S: - should_flip_negation = TRUE; - for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_space]; - classbits[1] |= 0x08; /* Perl 5.004 onwards omits VT from \s */ - continue; - - default: /* Not recognized; fall through */ - break; /* Need "default" setting to stop compiler warning. */ - } - - /* In the pre-compile phase, just do the recognition. */ - - else if (c == -ESC_d || c == -ESC_D || c == -ESC_w || - c == -ESC_W || c == -ESC_s || c == -ESC_S) continue; - - /* We need to deal with \H, \h, \V, and \v in both phases because - they use extra memory. */ - - if (-c == ESC_h) - { - SETBIT(classbits, 0x09); /* VT */ - SETBIT(classbits, 0x20); /* SPACE */ - SETBIT(classbits, 0xa0); /* NSBP */ -#ifdef SUPPORT_UTF8 - if (utf8) - { - class_utf8 = TRUE; - *class_utf8data++ = XCL_SINGLE; - class_utf8data += _pcre_ord2utf8(0x1680, class_utf8data); - *class_utf8data++ = XCL_SINGLE; - class_utf8data += _pcre_ord2utf8(0x180e, class_utf8data); - *class_utf8data++ = XCL_RANGE; - class_utf8data += _pcre_ord2utf8(0x2000, class_utf8data); - class_utf8data += _pcre_ord2utf8(0x200A, class_utf8data); - *class_utf8data++ = XCL_SINGLE; - class_utf8data += _pcre_ord2utf8(0x202f, class_utf8data); - *class_utf8data++ = XCL_SINGLE; - class_utf8data += _pcre_ord2utf8(0x205f, class_utf8data); - *class_utf8data++ = XCL_SINGLE; - class_utf8data += _pcre_ord2utf8(0x3000, class_utf8data); - } -#endif - continue; - } - - if (-c == ESC_H) - { - for (c = 0; c < 32; c++) - { - int x = 0xff; - switch (c) - { - case 0x09/8: x ^= 1 << (0x09%8); break; - case 0x20/8: x ^= 1 << (0x20%8); break; - case 0xa0/8: x ^= 1 << (0xa0%8); break; - default: break; - } - classbits[c] |= x; - } - -#ifdef SUPPORT_UTF8 - if (utf8) - { - class_utf8 = TRUE; - *class_utf8data++ = XCL_RANGE; - class_utf8data += _pcre_ord2utf8(0x0100, class_utf8data); - class_utf8data += _pcre_ord2utf8(0x167f, class_utf8data); - *class_utf8data++ = XCL_RANGE; - class_utf8data += _pcre_ord2utf8(0x1681, class_utf8data); - class_utf8data += _pcre_ord2utf8(0x180d, class_utf8data); - *class_utf8data++ = XCL_RANGE; - class_utf8data += _pcre_ord2utf8(0x180f, class_utf8data); - class_utf8data += _pcre_ord2utf8(0x1fff, class_utf8data); - *class_utf8data++ = XCL_RANGE; - class_utf8data += _pcre_ord2utf8(0x200B, class_utf8data); - class_utf8data += _pcre_ord2utf8(0x202e, class_utf8data); - *class_utf8data++ = XCL_RANGE; - class_utf8data += _pcre_ord2utf8(0x2030, class_utf8data); - class_utf8data += _pcre_ord2utf8(0x205e, class_utf8data); - *class_utf8data++ = XCL_RANGE; - class_utf8data += _pcre_ord2utf8(0x2060, class_utf8data); - class_utf8data += _pcre_ord2utf8(0x2fff, class_utf8data); - *class_utf8data++ = XCL_RANGE; - class_utf8data += _pcre_ord2utf8(0x3001, class_utf8data); - class_utf8data += _pcre_ord2utf8(0x7fffffff, class_utf8data); - } -#endif - continue; - } - - if (-c == ESC_v) - { - SETBIT(classbits, 0x0a); /* LF */ - SETBIT(classbits, 0x0b); /* VT */ - SETBIT(classbits, 0x0c); /* FF */ - SETBIT(classbits, 0x0d); /* CR */ - SETBIT(classbits, 0x85); /* NEL */ -#ifdef SUPPORT_UTF8 - if (utf8) - { - class_utf8 = TRUE; - *class_utf8data++ = XCL_RANGE; - class_utf8data += _pcre_ord2utf8(0x2028, class_utf8data); - class_utf8data += _pcre_ord2utf8(0x2029, class_utf8data); - } -#endif - continue; - } - - if (-c == ESC_V) - { - for (c = 0; c < 32; c++) - { - int x = 0xff; - switch (c) - { - case 0x0a/8: x ^= 1 << (0x0a%8); - x ^= 1 << (0x0b%8); - x ^= 1 << (0x0c%8); - x ^= 1 << (0x0d%8); - break; - case 0x85/8: x ^= 1 << (0x85%8); break; - default: break; - } - classbits[c] |= x; - } - -#ifdef SUPPORT_UTF8 - if (utf8) - { - class_utf8 = TRUE; - *class_utf8data++ = XCL_RANGE; - class_utf8data += _pcre_ord2utf8(0x0100, class_utf8data); - class_utf8data += _pcre_ord2utf8(0x2027, class_utf8data); - *class_utf8data++ = XCL_RANGE; - class_utf8data += _pcre_ord2utf8(0x2029, class_utf8data); - class_utf8data += _pcre_ord2utf8(0x7fffffff, class_utf8data); - } -#endif - continue; - } - - /* We need to deal with \P and \p in both phases. */ - -#ifdef SUPPORT_UCP - if (-c == ESC_p || -c == ESC_P) - { - BOOL negated; - int pdata; - int ptype = get_ucp(&ptr, &negated, &pdata, errorcodeptr); - if (ptype < 0) goto FAILED; - class_utf8 = TRUE; - *class_utf8data++ = ((-c == ESC_p) != negated)? - XCL_PROP : XCL_NOTPROP; - *class_utf8data++ = ptype; - *class_utf8data++ = pdata; - class_charcount -= 2; /* Not a < 256 character */ - continue; - } -#endif - /* Unrecognized escapes are faulted if PCRE is running in its - strict mode. By default, for compatibility with Perl, they are - treated as literals. */ - - if ((options & PCRE_EXTRA) != 0) - { - *errorcodeptr = ERR7; - goto FAILED; - } - - class_charcount -= 2; /* Undo the default count from above */ - c = *ptr; /* Get the final character and fall through */ - } - - /* Fall through if we have a single character (c >= 0). This may be - greater than 256 in UTF-8 mode. */ - - } /* End of backslash handling */ - - /* A single character may be followed by '-' to form a range. However, - Perl does not permit ']' to be the end of the range. A '-' character - at the end is treated as a literal. Perl ignores orphaned \E sequences - entirely. The code for handling \Q and \E is messy. */ - - CHECK_RANGE: - while (ptr[1] == CHAR_BACKSLASH && ptr[2] == CHAR_E) - { - inescq = FALSE; - ptr += 2; - } - - oldptr = ptr; - - /* Remember \r or \n */ - - if (c == CHAR_CR || c == CHAR_NL) cd->external_flags |= PCRE_HASCRORLF; - - /* Check for range */ - - if (!inescq && ptr[1] == CHAR_MINUS) - { - int d; - ptr += 2; - while (*ptr == CHAR_BACKSLASH && ptr[1] == CHAR_E) ptr += 2; - - /* If we hit \Q (not followed by \E) at this point, go into escaped - mode. */ - - while (*ptr == CHAR_BACKSLASH && ptr[1] == CHAR_Q) - { - ptr += 2; - if (*ptr == CHAR_BACKSLASH && ptr[1] == CHAR_E) - { ptr += 2; continue; } - inescq = TRUE; - break; - } - - if (*ptr == 0 || (!inescq && *ptr == CHAR_RIGHT_SQUARE_BRACKET)) - { - ptr = oldptr; - goto LONE_SINGLE_CHARACTER; - } - -#ifdef SUPPORT_UTF8 - if (utf8) - { /* Braces are required because the */ - GETCHARLEN(d, ptr, ptr); /* macro generates multiple statements */ - } - else -#endif - d = *ptr; /* Not UTF-8 mode */ - - /* The second part of a range can be a single-character escape, but - not any of the other escapes. Perl 5.6 treats a hyphen as a literal - in such circumstances. */ - - if (!inescq && d == CHAR_BACKSLASH) - { - d = check_escape(&ptr, errorcodeptr, cd->bracount, options, TRUE); - if (*errorcodeptr != 0) goto FAILED; - - /* \b is backspace; \X is literal X; \R is literal R; any other - special means the '-' was literal */ - - if (d < 0) - { - if (d == -ESC_b) d = CHAR_BS; - else if (d == -ESC_X) d = CHAR_X; - else if (d == -ESC_R) d = CHAR_R; else - { - ptr = oldptr; - goto LONE_SINGLE_CHARACTER; /* A few lines below */ - } - } - } - - /* Check that the two values are in the correct order. Optimize - one-character ranges */ - - if (d < c) - { - *errorcodeptr = ERR8; - goto FAILED; - } - - if (d == c) goto LONE_SINGLE_CHARACTER; /* A few lines below */ - - /* Remember \r or \n */ - - if (d == CHAR_CR || d == CHAR_NL) cd->external_flags |= PCRE_HASCRORLF; - - /* In UTF-8 mode, if the upper limit is > 255, or > 127 for caseless - matching, we have to use an XCLASS with extra data items. Caseless - matching for characters > 127 is available only if UCP support is - available. */ - -#ifdef SUPPORT_UTF8 - if (utf8 && (d > 255 || ((options & PCRE_CASELESS) != 0 && d > 127))) - { - class_utf8 = TRUE; - - /* With UCP support, we can find the other case equivalents of - the relevant characters. There may be several ranges. Optimize how - they fit with the basic range. */ - -#ifdef SUPPORT_UCP - if ((options & PCRE_CASELESS) != 0) - { - unsigned int occ, ocd; - unsigned int cc = c; - unsigned int origd = d; - while (get_othercase_range(&cc, origd, &occ, &ocd)) - { - if (occ >= (unsigned int)c && - ocd <= (unsigned int)d) - continue; /* Skip embedded ranges */ - - if (occ < (unsigned int)c && - ocd >= (unsigned int)c - 1) /* Extend the basic range */ - { /* if there is overlap, */ - c = occ; /* noting that if occ < c */ - continue; /* we can't have ocd > d */ - } /* because a subrange is */ - if (ocd > (unsigned int)d && - occ <= (unsigned int)d + 1) /* always shorter than */ - { /* the basic range. */ - d = ocd; - continue; - } - - if (occ == ocd) - { - *class_utf8data++ = XCL_SINGLE; - } - else - { - *class_utf8data++ = XCL_RANGE; - class_utf8data += _pcre_ord2utf8(occ, class_utf8data); - } - class_utf8data += _pcre_ord2utf8(ocd, class_utf8data); - } - } -#endif /* SUPPORT_UCP */ - - /* Now record the original range, possibly modified for UCP caseless - overlapping ranges. */ - - *class_utf8data++ = XCL_RANGE; - class_utf8data += _pcre_ord2utf8(c, class_utf8data); - class_utf8data += _pcre_ord2utf8(d, class_utf8data); - - /* With UCP support, we are done. Without UCP support, there is no - caseless matching for UTF-8 characters > 127; we can use the bit map - for the smaller ones. */ - -#ifdef SUPPORT_UCP - continue; /* With next character in the class */ -#else - if ((options & PCRE_CASELESS) == 0 || c > 127) continue; - - /* Adjust upper limit and fall through to set up the map */ - - d = 127; - -#endif /* SUPPORT_UCP */ - } -#endif /* SUPPORT_UTF8 */ - - /* We use the bit map for all cases when not in UTF-8 mode; else - ranges that lie entirely within 0-127 when there is UCP support; else - for partial ranges without UCP support. */ - - class_charcount += d - c + 1; - class_lastchar = d; - - /* We can save a bit of time by skipping this in the pre-compile. */ - - if (lengthptr == NULL) for (; c <= d; c++) - { - classbits[c/8] |= (1 << (c&7)); - if ((options & PCRE_CASELESS) != 0) - { - int uc = cd->fcc[c]; /* flip case */ - classbits[uc/8] |= (1 << (uc&7)); - } - } - - continue; /* Go get the next char in the class */ - } - - /* Handle a lone single character - we can get here for a normal - non-escape char, or after \ that introduces a single character or for an - apparent range that isn't. */ - - LONE_SINGLE_CHARACTER: - - /* Handle a character that cannot go in the bit map */ - -#ifdef SUPPORT_UTF8 - if (utf8 && (c > 255 || ((options & PCRE_CASELESS) != 0 && c > 127))) - { - class_utf8 = TRUE; - *class_utf8data++ = XCL_SINGLE; - class_utf8data += _pcre_ord2utf8(c, class_utf8data); - -#ifdef SUPPORT_UCP - if ((options & PCRE_CASELESS) != 0) - { - unsigned int othercase; - if ((othercase = UCD_OTHERCASE(c)) != c) - { - *class_utf8data++ = XCL_SINGLE; - class_utf8data += _pcre_ord2utf8(othercase, class_utf8data); - } - } -#endif /* SUPPORT_UCP */ - - } - else -#endif /* SUPPORT_UTF8 */ - - /* Handle a single-byte character */ - { - classbits[c/8] |= (1 << (c&7)); - if ((options & PCRE_CASELESS) != 0) - { - c = cd->fcc[c]; /* flip case */ - classbits[c/8] |= (1 << (c&7)); - } - class_charcount++; - class_lastchar = c; - } - } - - /* Loop until ']' reached. This "while" is the end of the "do" above. */ - - while ((c = *(++ptr)) != 0 && (c != CHAR_RIGHT_SQUARE_BRACKET || inescq)); - - if (c == 0) /* Missing terminating ']' */ - { - *errorcodeptr = ERR6; - goto FAILED; - } - - -/* This code has been disabled because it would mean that \s counts as -an explicit \r or \n reference, and that's not really what is wanted. Now -we set the flag only if there is a literal "\r" or "\n" in the class. */ - -#if 0 - /* Remember whether \r or \n are in this class */ - - if (negate_class) - { - if ((classbits[1] & 0x24) != 0x24) cd->external_flags |= PCRE_HASCRORLF; - } - else - { - if ((classbits[1] & 0x24) != 0) cd->external_flags |= PCRE_HASCRORLF; - } -#endif - - - /* If class_charcount is 1, we saw precisely one character whose value is - less than 256. As long as there were no characters >= 128 and there was no - use of \p or \P, in other words, no use of any XCLASS features, we can - optimize. - - In UTF-8 mode, we can optimize the negative case only if there were no - characters >= 128 because OP_NOT and the related opcodes like OP_NOTSTAR - operate on single-bytes only. This is an historical hangover. Maybe one day - we can tidy these opcodes to handle multi-byte characters. - - The optimization throws away the bit map. We turn the item into a - 1-character OP_CHAR[NC] if it's positive, or OP_NOT if it's negative. Note - that OP_NOT does not support multibyte characters. In the positive case, it - can cause firstbyte to be set. Otherwise, there can be no first char if - this item is first, whatever repeat count may follow. In the case of - reqbyte, save the previous value for reinstating. */ - -#ifdef SUPPORT_UTF8 - if (class_charcount == 1 && !class_utf8 && - (!utf8 || !negate_class || class_lastchar < 128)) -#else - if (class_charcount == 1) -#endif - { - zeroreqbyte = reqbyte; - - /* The OP_NOT opcode works on one-byte characters only. */ - - if (negate_class) - { - if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE; - zerofirstbyte = firstbyte; - *code++ = OP_NOT; - *code++ = class_lastchar; - break; - } - - /* For a single, positive character, get the value into mcbuffer, and - then we can handle this with the normal one-character code. */ - -#ifdef SUPPORT_UTF8 - if (utf8 && class_lastchar > 127) - mclength = _pcre_ord2utf8(class_lastchar, mcbuffer); - else -#endif - { - mcbuffer[0] = class_lastchar; - mclength = 1; - } - goto ONE_CHAR; - } /* End of 1-char optimization */ - - /* The general case - not the one-char optimization. If this is the first - thing in the branch, there can be no first char setting, whatever the - repeat count. Any reqbyte setting must remain unchanged after any kind of - repeat. */ - - if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE; - zerofirstbyte = firstbyte; - zeroreqbyte = reqbyte; - - /* If there are characters with values > 255, we have to compile an - extended class, with its own opcode, unless there was a negated special - such as \S in the class, because in that case all characters > 255 are in - the class, so any that were explicitly given as well can be ignored. If - (when there are explicit characters > 255 that must be listed) there are no - characters < 256, we can omit the bitmap in the actual compiled code. */ - -#ifdef SUPPORT_UTF8 - if (class_utf8 && !should_flip_negation) - { - *class_utf8data++ = XCL_END; /* Marks the end of extra data */ - *code++ = OP_XCLASS; - code += LINK_SIZE; - *code = negate_class? XCL_NOT : 0; - - /* If the map is required, move up the extra data to make room for it; - otherwise just move the code pointer to the end of the extra data. */ - - if (class_charcount > 0) - { - *code++ |= XCL_MAP; - memmove(code + 32, code, class_utf8data - code); - memcpy(code, classbits, 32); - code = class_utf8data + 32; - } - else code = class_utf8data; - - /* Now fill in the complete length of the item */ - - PUT(previous, 1, code - previous); - break; /* End of class handling */ - } -#endif - - /* If there are no characters > 255, set the opcode to OP_CLASS or - OP_NCLASS, depending on whether the whole class was negated and whether - there were negative specials such as \S in the class. Then copy the 32-byte - map into the code vector, negating it if necessary. */ - - *code++ = (negate_class == should_flip_negation) ? OP_CLASS : OP_NCLASS; - if (negate_class) - { - if (lengthptr == NULL) /* Save time in the pre-compile phase */ - for (c = 0; c < 32; c++) code[c] = ~classbits[c]; - } - else - { - memcpy(code, classbits, 32); - } - code += 32; - break; - - - /* ===================================================================*/ - /* Various kinds of repeat; '{' is not necessarily a quantifier, but this - has been tested above. */ - - case CHAR_LEFT_CURLY_BRACKET: - if (!is_quantifier) goto NORMAL_CHAR; - ptr = read_repeat_counts(ptr+1, &repeat_min, &repeat_max, errorcodeptr); - if (*errorcodeptr != 0) goto FAILED; - goto REPEAT; - - case CHAR_ASTERISK: - repeat_min = 0; - repeat_max = -1; - goto REPEAT; - - case CHAR_PLUS: - repeat_min = 1; - repeat_max = -1; - goto REPEAT; - - case CHAR_QUESTION_MARK: - repeat_min = 0; - repeat_max = 1; - - REPEAT: - if (previous == NULL) - { - *errorcodeptr = ERR9; - goto FAILED; - } - - if (repeat_min == 0) - { - firstbyte = zerofirstbyte; /* Adjust for zero repeat */ - reqbyte = zeroreqbyte; /* Ditto */ - } - - /* Remember whether this is a variable length repeat */ - - reqvary = (repeat_min == repeat_max)? 0 : REQ_VARY; - - op_type = 0; /* Default single-char op codes */ - possessive_quantifier = FALSE; /* Default not possessive quantifier */ - - /* Save start of previous item, in case we have to move it up to make space - for an inserted OP_ONCE for the additional '+' extension. */ - - tempcode = previous; - - /* If the next character is '+', we have a possessive quantifier. This - implies greediness, whatever the setting of the PCRE_UNGREEDY option. - If the next character is '?' this is a minimizing repeat, by default, - but if PCRE_UNGREEDY is set, it works the other way round. We change the - repeat type to the non-default. */ - - if (ptr[1] == CHAR_PLUS) - { - repeat_type = 0; /* Force greedy */ - possessive_quantifier = TRUE; - ptr++; - } - else if (ptr[1] == CHAR_QUESTION_MARK) - { - repeat_type = greedy_non_default; - ptr++; - } - else repeat_type = greedy_default; - - /* If previous was a character match, abolish the item and generate a - repeat item instead. If a char item has a minumum of more than one, ensure - that it is set in reqbyte - it might not be if a sequence such as x{3} is - the first thing in a branch because the x will have gone into firstbyte - instead. */ - - if (*previous == OP_CHAR || *previous == OP_CHARNC) - { - /* Deal with UTF-8 characters that take up more than one byte. It's - easier to write this out separately than try to macrify it. Use c to - hold the length of the character in bytes, plus 0x80 to flag that it's a - length rather than a small character. */ - -#ifdef SUPPORT_UTF8 - if (utf8 && (code[-1] & 0x80) != 0) - { - uschar *lastchar = code - 1; - while((*lastchar & 0xc0) == 0x80) lastchar--; - c = code - lastchar; /* Length of UTF-8 character */ - memcpy(utf8_char, lastchar, c); /* Save the char */ - c |= 0x80; /* Flag c as a length */ - } - else -#endif - - /* Handle the case of a single byte - either with no UTF8 support, or - with UTF-8 disabled, or for a UTF-8 character < 128. */ - - { - c = code[-1]; - if (repeat_min > 1) reqbyte = c | req_caseopt | cd->req_varyopt; - } - - /* If the repetition is unlimited, it pays to see if the next thing on - the line is something that cannot possibly match this character. If so, - automatically possessifying this item gains some performance in the case - where the match fails. */ - - if (!possessive_quantifier && - repeat_max < 0 && - check_auto_possessive(*previous, c, utf8, utf8_char, ptr + 1, - options, cd)) - { - repeat_type = 0; /* Force greedy */ - possessive_quantifier = TRUE; - } - - goto OUTPUT_SINGLE_REPEAT; /* Code shared with single character types */ - } - - /* If previous was a single negated character ([^a] or similar), we use - one of the special opcodes, replacing it. The code is shared with single- - character repeats by setting opt_type to add a suitable offset into - repeat_type. We can also test for auto-possessification. OP_NOT is - currently used only for single-byte chars. */ - - else if (*previous == OP_NOT) - { - op_type = OP_NOTSTAR - OP_STAR; /* Use "not" opcodes */ - c = previous[1]; - if (!possessive_quantifier && - repeat_max < 0 && - check_auto_possessive(OP_NOT, c, utf8, NULL, ptr + 1, options, cd)) - { - repeat_type = 0; /* Force greedy */ - possessive_quantifier = TRUE; - } - goto OUTPUT_SINGLE_REPEAT; - } - - /* If previous was a character type match (\d or similar), abolish it and - create a suitable repeat item. The code is shared with single-character - repeats by setting op_type to add a suitable offset into repeat_type. Note - the the Unicode property types will be present only when SUPPORT_UCP is - defined, but we don't wrap the little bits of code here because it just - makes it horribly messy. */ - - else if (*previous < OP_EODN) - { - uschar *oldcode; - int prop_type, prop_value; - op_type = OP_TYPESTAR - OP_STAR; /* Use type opcodes */ - c = *previous; - - if (!possessive_quantifier && - repeat_max < 0 && - check_auto_possessive(c, 0, utf8, NULL, ptr + 1, options, cd)) - { - repeat_type = 0; /* Force greedy */ - possessive_quantifier = TRUE; - } - - OUTPUT_SINGLE_REPEAT: - if (*previous == OP_PROP || *previous == OP_NOTPROP) - { - prop_type = previous[1]; - prop_value = previous[2]; - } - else prop_type = prop_value = -1; - - oldcode = code; - code = previous; /* Usually overwrite previous item */ - - /* If the maximum is zero then the minimum must also be zero; Perl allows - this case, so we do too - by simply omitting the item altogether. */ - - if (repeat_max == 0) goto END_REPEAT; - - /* All real repeats make it impossible to handle partial matching (maybe - one day we will be able to remove this restriction). */ - - if (repeat_max != 1) cd->external_flags |= PCRE_NOPARTIAL; - - /* Combine the op_type with the repeat_type */ - - repeat_type += op_type; - - /* A minimum of zero is handled either as the special case * or ?, or as - an UPTO, with the maximum given. */ - - if (repeat_min == 0) - { - if (repeat_max == -1) *code++ = OP_STAR + repeat_type; - else if (repeat_max == 1) *code++ = OP_QUERY + repeat_type; - else - { - *code++ = OP_UPTO + repeat_type; - PUT2INC(code, 0, repeat_max); - } - } - - /* A repeat minimum of 1 is optimized into some special cases. If the - maximum is unlimited, we use OP_PLUS. Otherwise, the original item is - left in place and, if the maximum is greater than 1, we use OP_UPTO with - one less than the maximum. */ - - else if (repeat_min == 1) - { - if (repeat_max == -1) - *code++ = OP_PLUS + repeat_type; - else - { - code = oldcode; /* leave previous item in place */ - if (repeat_max == 1) goto END_REPEAT; - *code++ = OP_UPTO + repeat_type; - PUT2INC(code, 0, repeat_max - 1); - } - } - - /* The case {n,n} is just an EXACT, while the general case {n,m} is - handled as an EXACT followed by an UPTO. */ - - else - { - *code++ = OP_EXACT + op_type; /* NB EXACT doesn't have repeat_type */ - PUT2INC(code, 0, repeat_min); - - /* If the maximum is unlimited, insert an OP_STAR. Before doing so, - we have to insert the character for the previous code. For a repeated - Unicode property match, there are two extra bytes that define the - required property. In UTF-8 mode, long characters have their length in - c, with the 0x80 bit as a flag. */ - - if (repeat_max < 0) - { -#ifdef SUPPORT_UTF8 - if (utf8 && c >= 128) - { - memcpy(code, utf8_char, c & 7); - code += c & 7; - } - else -#endif - { - *code++ = c; - if (prop_type >= 0) - { - *code++ = prop_type; - *code++ = prop_value; - } - } - *code++ = OP_STAR + repeat_type; - } - - /* Else insert an UPTO if the max is greater than the min, again - preceded by the character, for the previously inserted code. If the - UPTO is just for 1 instance, we can use QUERY instead. */ - - else if (repeat_max != repeat_min) - { -#ifdef SUPPORT_UTF8 - if (utf8 && c >= 128) - { - memcpy(code, utf8_char, c & 7); - code += c & 7; - } - else -#endif - *code++ = c; - if (prop_type >= 0) - { - *code++ = prop_type; - *code++ = prop_value; - } - repeat_max -= repeat_min; - - if (repeat_max == 1) - { - *code++ = OP_QUERY + repeat_type; - } - else - { - *code++ = OP_UPTO + repeat_type; - PUT2INC(code, 0, repeat_max); - } - } - } - - /* The character or character type itself comes last in all cases. */ - -#ifdef SUPPORT_UTF8 - if (utf8 && c >= 128) - { - memcpy(code, utf8_char, c & 7); - code += c & 7; - } - else -#endif - *code++ = c; - - /* For a repeated Unicode property match, there are two extra bytes that - define the required property. */ - -#ifdef SUPPORT_UCP - if (prop_type >= 0) - { - *code++ = prop_type; - *code++ = prop_value; - } -#endif - } - - /* If previous was a character class or a back reference, we put the repeat - stuff after it, but just skip the item if the repeat was {0,0}. */ - - else if (*previous == OP_CLASS || - *previous == OP_NCLASS || -#ifdef SUPPORT_UTF8 - *previous == OP_XCLASS || -#endif - *previous == OP_REF) - { - if (repeat_max == 0) - { - code = previous; - goto END_REPEAT; - } - - /* All real repeats make it impossible to handle partial matching (maybe - one day we will be able to remove this restriction). */ - - if (repeat_max != 1) cd->external_flags |= PCRE_NOPARTIAL; - - if (repeat_min == 0 && repeat_max == -1) - *code++ = OP_CRSTAR + repeat_type; - else if (repeat_min == 1 && repeat_max == -1) - *code++ = OP_CRPLUS + repeat_type; - else if (repeat_min == 0 && repeat_max == 1) - *code++ = OP_CRQUERY + repeat_type; - else - { - *code++ = OP_CRRANGE + repeat_type; - PUT2INC(code, 0, repeat_min); - if (repeat_max == -1) repeat_max = 0; /* 2-byte encoding for max */ - PUT2INC(code, 0, repeat_max); - } - } - - /* If previous was a bracket group, we may have to replicate it in certain - cases. */ - - else if (*previous == OP_BRA || *previous == OP_CBRA || - *previous == OP_ONCE || *previous == OP_COND) - { - register int i; - int ketoffset = 0; - int len = code - previous; - uschar *bralink = NULL; - - /* Repeating a DEFINE group is pointless */ - - if (*previous == OP_COND && previous[LINK_SIZE+1] == OP_DEF) - { - *errorcodeptr = ERR55; - goto FAILED; - } - - /* If the maximum repeat count is unlimited, find the end of the bracket - by scanning through from the start, and compute the offset back to it - from the current code pointer. There may be an OP_OPT setting following - the final KET, so we can't find the end just by going back from the code - pointer. */ - - if (repeat_max == -1) - { - register uschar *ket = previous; - do ket += GET(ket, 1); while (*ket != OP_KET); - ketoffset = code - ket; - } - - /* The case of a zero minimum is special because of the need to stick - OP_BRAZERO in front of it, and because the group appears once in the - data, whereas in other cases it appears the minimum number of times. For - this reason, it is simplest to treat this case separately, as otherwise - the code gets far too messy. There are several special subcases when the - minimum is zero. */ - - if (repeat_min == 0) - { - /* If the maximum is also zero, we used to just omit the group from the - output altogether, like this: - - ** if (repeat_max == 0) - ** { - ** code = previous; - ** goto END_REPEAT; - ** } - - However, that fails when a group is referenced as a subroutine from - elsewhere in the pattern, so now we stick in OP_SKIPZERO in front of it - so that it is skipped on execution. As we don't have a list of which - groups are referenced, we cannot do this selectively. - - If the maximum is 1 or unlimited, we just have to stick in the BRAZERO - and do no more at this point. However, we do need to adjust any - OP_RECURSE calls inside the group that refer to the group itself or any - internal or forward referenced group, because the offset is from the - start of the whole regex. Temporarily terminate the pattern while doing - this. */ - - if (repeat_max <= 1) /* Covers 0, 1, and unlimited */ - { - *code = OP_END; - adjust_recurse(previous, 1, utf8, cd, save_hwm); - memmove(previous+1, previous, len); - code++; - if (repeat_max == 0) - { - *previous++ = OP_SKIPZERO; - goto END_REPEAT; - } - *previous++ = OP_BRAZERO + repeat_type; - } - - /* If the maximum is greater than 1 and limited, we have to replicate - in a nested fashion, sticking OP_BRAZERO before each set of brackets. - The first one has to be handled carefully because it's the original - copy, which has to be moved up. The remainder can be handled by code - that is common with the non-zero minimum case below. We have to - adjust the value or repeat_max, since one less copy is required. Once - again, we may have to adjust any OP_RECURSE calls inside the group. */ - - else - { - int offset; - *code = OP_END; - adjust_recurse(previous, 2 + LINK_SIZE, utf8, cd, save_hwm); - memmove(previous + 2 + LINK_SIZE, previous, len); - code += 2 + LINK_SIZE; - *previous++ = OP_BRAZERO + repeat_type; - *previous++ = OP_BRA; - - /* We chain together the bracket offset fields that have to be - filled in later when the ends of the brackets are reached. */ - - offset = (bralink == NULL)? 0 : previous - bralink; - bralink = previous; - PUTINC(previous, 0, offset); - } - - repeat_max--; - } - - /* If the minimum is greater than zero, replicate the group as many - times as necessary, and adjust the maximum to the number of subsequent - copies that we need. If we set a first char from the group, and didn't - set a required char, copy the latter from the former. If there are any - forward reference subroutine calls in the group, there will be entries on - the workspace list; replicate these with an appropriate increment. */ - - else - { - if (repeat_min > 1) - { - /* In the pre-compile phase, we don't actually do the replication. We - just adjust the length as if we had. Do some paranoid checks for - potential integer overflow. */ - - if (lengthptr != NULL) - { - int delta = (repeat_min - 1)*length_prevgroup; - if ((double)(repeat_min - 1)*(double)length_prevgroup > - (double)INT_MAX || - OFLOW_MAX - *lengthptr < delta) - { - *errorcodeptr = ERR20; - goto FAILED; - } - *lengthptr += delta; - } - - /* This is compiling for real */ - - else - { - if (groupsetfirstbyte && reqbyte < 0) reqbyte = firstbyte; - for (i = 1; i < repeat_min; i++) - { - uschar *hc; - uschar *this_hwm = cd->hwm; - memcpy(code, previous, len); - for (hc = save_hwm; hc < this_hwm; hc += LINK_SIZE) - { - PUT(cd->hwm, 0, GET(hc, 0) + len); - cd->hwm += LINK_SIZE; - } - save_hwm = this_hwm; - code += len; - } - } - } - - if (repeat_max > 0) repeat_max -= repeat_min; - } - - /* This code is common to both the zero and non-zero minimum cases. If - the maximum is limited, it replicates the group in a nested fashion, - remembering the bracket starts on a stack. In the case of a zero minimum, - the first one was set up above. In all cases the repeat_max now specifies - the number of additional copies needed. Again, we must remember to - replicate entries on the forward reference list. */ - - if (repeat_max >= 0) - { - /* In the pre-compile phase, we don't actually do the replication. We - just adjust the length as if we had. For each repetition we must add 1 - to the length for BRAZERO and for all but the last repetition we must - add 2 + 2*LINKSIZE to allow for the nesting that occurs. Do some - paranoid checks to avoid integer overflow. */ - - if (lengthptr != NULL && repeat_max > 0) - { - int delta = repeat_max * (length_prevgroup + 1 + 2 + 2*LINK_SIZE) - - 2 - 2*LINK_SIZE; /* Last one doesn't nest */ - if ((double)repeat_max * - (double)(length_prevgroup + 1 + 2 + 2*LINK_SIZE) - > (double)INT_MAX || - OFLOW_MAX - *lengthptr < delta) - { - *errorcodeptr = ERR20; - goto FAILED; - } - *lengthptr += delta; - } - - /* This is compiling for real */ - - else for (i = repeat_max - 1; i >= 0; i--) - { - uschar *hc; - uschar *this_hwm = cd->hwm; - - *code++ = OP_BRAZERO + repeat_type; - - /* All but the final copy start a new nesting, maintaining the - chain of brackets outstanding. */ - - if (i != 0) - { - int offset; - *code++ = OP_BRA; - offset = (bralink == NULL)? 0 : code - bralink; - bralink = code; - PUTINC(code, 0, offset); - } - - memcpy(code, previous, len); - for (hc = save_hwm; hc < this_hwm; hc += LINK_SIZE) - { - PUT(cd->hwm, 0, GET(hc, 0) + len + ((i != 0)? 2+LINK_SIZE : 1)); - cd->hwm += LINK_SIZE; - } - save_hwm = this_hwm; - code += len; - } - - /* Now chain through the pending brackets, and fill in their length - fields (which are holding the chain links pro tem). */ - - while (bralink != NULL) - { - int oldlinkoffset; - int offset = code - bralink + 1; - uschar *bra = code - offset; - oldlinkoffset = GET(bra, 1); - bralink = (oldlinkoffset == 0)? NULL : bralink - oldlinkoffset; - *code++ = OP_KET; - PUTINC(code, 0, offset); - PUT(bra, 1, offset); - } - } - - /* If the maximum is unlimited, set a repeater in the final copy. We - can't just offset backwards from the current code point, because we - don't know if there's been an options resetting after the ket. The - correct offset was computed above. - - Then, when we are doing the actual compile phase, check to see whether - this group is a non-atomic one that could match an empty string. If so, - convert the initial operator to the S form (e.g. OP_BRA -> OP_SBRA) so - that runtime checking can be done. [This check is also applied to - atomic groups at runtime, but in a different way.] */ - - else - { - uschar *ketcode = code - ketoffset; - uschar *bracode = ketcode - GET(ketcode, 1); - *ketcode = OP_KETRMAX + repeat_type; - if (lengthptr == NULL && *bracode != OP_ONCE) - { - uschar *scode = bracode; - do - { - if (could_be_empty_branch(scode, ketcode, utf8)) - { - *bracode += OP_SBRA - OP_BRA; - break; - } - scode += GET(scode, 1); - } - while (*scode == OP_ALT); - } - } - } - - /* If previous is OP_FAIL, it was generated by an empty class [] in - JavaScript mode. The other ways in which OP_FAIL can be generated, that is - by (*FAIL) or (?!) set previous to NULL, which gives a "nothing to repeat" - error above. We can just ignore the repeat in JS case. */ - - else if (*previous == OP_FAIL) goto END_REPEAT; - - /* Else there's some kind of shambles */ - - else - { - *errorcodeptr = ERR11; - goto FAILED; - } - - /* If the character following a repeat is '+', or if certain optimization - tests above succeeded, possessive_quantifier is TRUE. For some of the - simpler opcodes, there is an special alternative opcode for this. For - anything else, we wrap the entire repeated item inside OP_ONCE brackets. - The '+' notation is just syntactic sugar, taken from Sun's Java package, - but the special opcodes can optimize it a bit. The repeated item starts at - tempcode, not at previous, which might be the first part of a string whose - (former) last char we repeated. - - Possessifying an 'exact' quantifier has no effect, so we can ignore it. But - an 'upto' may follow. We skip over an 'exact' item, and then test the - length of what remains before proceeding. */ - - if (possessive_quantifier) - { - int len; - if (*tempcode == OP_EXACT || *tempcode == OP_TYPEEXACT || - *tempcode == OP_NOTEXACT) - tempcode += _pcre_OP_lengths[*tempcode] + - ((*tempcode == OP_TYPEEXACT && - (tempcode[3] == OP_PROP || tempcode[3] == OP_NOTPROP))? 2:0); - len = code - tempcode; - if (len > 0) switch (*tempcode) - { - case OP_STAR: *tempcode = OP_POSSTAR; break; - case OP_PLUS: *tempcode = OP_POSPLUS; break; - case OP_QUERY: *tempcode = OP_POSQUERY; break; - case OP_UPTO: *tempcode = OP_POSUPTO; break; - - case OP_TYPESTAR: *tempcode = OP_TYPEPOSSTAR; break; - case OP_TYPEPLUS: *tempcode = OP_TYPEPOSPLUS; break; - case OP_TYPEQUERY: *tempcode = OP_TYPEPOSQUERY; break; - case OP_TYPEUPTO: *tempcode = OP_TYPEPOSUPTO; break; - - case OP_NOTSTAR: *tempcode = OP_NOTPOSSTAR; break; - case OP_NOTPLUS: *tempcode = OP_NOTPOSPLUS; break; - case OP_NOTQUERY: *tempcode = OP_NOTPOSQUERY; break; - case OP_NOTUPTO: *tempcode = OP_NOTPOSUPTO; break; - - default: - memmove(tempcode + 1+LINK_SIZE, tempcode, len); - code += 1 + LINK_SIZE; - len += 1 + LINK_SIZE; - tempcode[0] = OP_ONCE; - *code++ = OP_KET; - PUTINC(code, 0, len); - PUT(tempcode, 1, len); - break; - } - } - - /* In all case we no longer have a previous item. We also set the - "follows varying string" flag for subsequently encountered reqbytes if - it isn't already set and we have just passed a varying length item. */ - - END_REPEAT: - previous = NULL; - cd->req_varyopt |= reqvary; - break; - - - /* ===================================================================*/ - /* Start of nested parenthesized sub-expression, or comment or lookahead or - lookbehind or option setting or condition or all the other extended - parenthesis forms. */ - - case CHAR_LEFT_PARENTHESIS: - newoptions = options; - skipbytes = 0; - bravalue = OP_CBRA; - save_hwm = cd->hwm; - reset_bracount = FALSE; - - /* First deal with various "verbs" that can be introduced by '*'. */ - - if (*(++ptr) == CHAR_ASTERISK && (cd->ctypes[ptr[1]] & ctype_letter) != 0) - { - int i, namelen; - const char *vn = verbnames; - const uschar *name = ++ptr; - previous = NULL; - while ((cd->ctypes[*++ptr] & ctype_letter) != 0) {}; - if (*ptr == CHAR_COLON) - { - *errorcodeptr = ERR59; /* Not supported */ - goto FAILED; - } - if (*ptr != CHAR_RIGHT_PARENTHESIS) - { - *errorcodeptr = ERR60; - goto FAILED; - } - namelen = ptr - name; - for (i = 0; i < verbcount; i++) - { - if (namelen == verbs[i].len && - strncmp((char *)name, vn, namelen) == 0) - { - *code = verbs[i].op; - if (*code++ == OP_ACCEPT) cd->had_accept = TRUE; - break; - } - vn += verbs[i].len + 1; - } - if (i < verbcount) continue; - *errorcodeptr = ERR60; - goto FAILED; - } - - /* Deal with the extended parentheses; all are introduced by '?', and the - appearance of any of them means that this is not a capturing group. */ - - else if (*ptr == CHAR_QUESTION_MARK) - { - int i, set, unset, namelen; - int *optset; - const uschar *name; - uschar *slot; - - switch (*(++ptr)) - { - case CHAR_NUMBER_SIGN: /* Comment; skip to ket */ - ptr++; - while (*ptr != 0 && *ptr != CHAR_RIGHT_PARENTHESIS) ptr++; - if (*ptr == 0) - { - *errorcodeptr = ERR18; - goto FAILED; - } - continue; - - - /* ------------------------------------------------------------ */ - case CHAR_VERTICAL_LINE: /* Reset capture count for each branch */ - reset_bracount = TRUE; - /* Fall through */ - - /* ------------------------------------------------------------ */ - case CHAR_COLON: /* Non-capturing bracket */ - bravalue = OP_BRA; - ptr++; - break; - - - /* ------------------------------------------------------------ */ - case CHAR_LEFT_PARENTHESIS: - bravalue = OP_COND; /* Conditional group */ - - /* A condition can be an assertion, a number (referring to a numbered - group), a name (referring to a named group), or 'R', referring to - recursion. R and R&name are also permitted for recursion tests. - - There are several syntaxes for testing a named group: (?(name)) is used - by Python; Perl 5.10 onwards uses (?() or (?('name')). - - There are two unfortunate ambiguities, caused by history. (a) 'R' can - be the recursive thing or the name 'R' (and similarly for 'R' followed - by digits), and (b) a number could be a name that consists of digits. - In both cases, we look for a name first; if not found, we try the other - cases. */ - - /* For conditions that are assertions, check the syntax, and then exit - the switch. This will take control down to where bracketed groups, - including assertions, are processed. */ - - if (ptr[1] == CHAR_QUESTION_MARK && (ptr[2] == CHAR_EQUALS_SIGN || - ptr[2] == CHAR_EXCLAMATION_MARK || ptr[2] == CHAR_LESS_THAN_SIGN)) - break; - - /* Most other conditions use OP_CREF (a couple change to OP_RREF - below), and all need to skip 3 bytes at the start of the group. */ - - code[1+LINK_SIZE] = OP_CREF; - skipbytes = 3; - refsign = -1; - - /* Check for a test for recursion in a named group. */ - - if (ptr[1] == CHAR_R && ptr[2] == CHAR_AMPERSAND) - { - terminator = -1; - ptr += 2; - code[1+LINK_SIZE] = OP_RREF; /* Change the type of test */ - } - - /* Check for a test for a named group's having been set, using the Perl - syntax (?() or (?('name') */ - - else if (ptr[1] == CHAR_LESS_THAN_SIGN) - { - terminator = CHAR_GREATER_THAN_SIGN; - ptr++; - } - else if (ptr[1] == CHAR_APOSTROPHE) - { - terminator = CHAR_APOSTROPHE; - ptr++; - } - else - { - terminator = 0; - if (ptr[1] == CHAR_MINUS || ptr[1] == CHAR_PLUS) refsign = *(++ptr); - } - - /* We now expect to read a name; any thing else is an error */ - - if ((cd->ctypes[ptr[1]] & ctype_word) == 0) - { - ptr += 1; /* To get the right offset */ - *errorcodeptr = ERR28; - goto FAILED; - } - - /* Read the name, but also get it as a number if it's all digits */ - - recno = 0; - name = ++ptr; - while ((cd->ctypes[*ptr] & ctype_word) != 0) - { - if (recno >= 0) - recno = ((digitab[*ptr] & ctype_digit) != 0)? - recno * 10 + *ptr - CHAR_0 : -1; - ptr++; - } - namelen = ptr - name; - - if ((terminator > 0 && *ptr++ != terminator) || - *ptr++ != CHAR_RIGHT_PARENTHESIS) - { - ptr--; /* Error offset */ - *errorcodeptr = ERR26; - goto FAILED; - } - - /* Do no further checking in the pre-compile phase. */ - - if (lengthptr != NULL) break; - - /* In the real compile we do the work of looking for the actual - reference. If the string started with "+" or "-" we require the rest to - be digits, in which case recno will be set. */ - - if (refsign > 0) - { - if (recno <= 0) - { - *errorcodeptr = ERR58; - goto FAILED; - } - recno = (refsign == CHAR_MINUS)? - cd->bracount - recno + 1 : recno +cd->bracount; - if (recno <= 0 || recno > cd->final_bracount) - { - *errorcodeptr = ERR15; - goto FAILED; - } - PUT2(code, 2+LINK_SIZE, recno); - break; - } - - /* Otherwise (did not start with "+" or "-"), start by looking for the - name. */ - - slot = cd->name_table; - for (i = 0; i < cd->names_found; i++) - { - if (strncmp((char *)name, (char *)slot+2, namelen) == 0) break; - slot += cd->name_entry_size; - } - - /* Found a previous named subpattern */ - - if (i < cd->names_found) - { - recno = GET2(slot, 0); - PUT2(code, 2+LINK_SIZE, recno); - } - - /* Search the pattern for a forward reference */ - - else if ((i = find_parens(cd, name, namelen, - (options & PCRE_EXTENDED) != 0)) > 0) - { - PUT2(code, 2+LINK_SIZE, i); - } - - /* If terminator == 0 it means that the name followed directly after - the opening parenthesis [e.g. (?(abc)...] and in this case there are - some further alternatives to try. For the cases where terminator != 0 - [things like (?(... or (?('name')... or (?(R&name)... ] we have - now checked all the possibilities, so give an error. */ - - else if (terminator != 0) - { - *errorcodeptr = ERR15; - goto FAILED; - } - - /* Check for (?(R) for recursion. Allow digits after R to specify a - specific group number. */ - - else if (*name == CHAR_R) - { - recno = 0; - for (i = 1; i < namelen; i++) - { - if ((digitab[name[i]] & ctype_digit) == 0) - { - *errorcodeptr = ERR15; - goto FAILED; - } - recno = recno * 10 + name[i] - CHAR_0; - } - if (recno == 0) recno = RREF_ANY; - code[1+LINK_SIZE] = OP_RREF; /* Change test type */ - PUT2(code, 2+LINK_SIZE, recno); - } - - /* Similarly, check for the (?(DEFINE) "condition", which is always - false. */ - - else if (namelen == 6 && strncmp((char *)name, STRING_DEFINE, 6) == 0) - { - code[1+LINK_SIZE] = OP_DEF; - skipbytes = 1; - } - - /* Check for the "name" actually being a subpattern number. We are - in the second pass here, so final_bracount is set. */ - - else if (recno > 0 && recno <= cd->final_bracount) - { - PUT2(code, 2+LINK_SIZE, recno); - } - - /* Either an unidentified subpattern, or a reference to (?(0) */ - - else - { - *errorcodeptr = (recno == 0)? ERR35: ERR15; - goto FAILED; - } - break; - - - /* ------------------------------------------------------------ */ - case CHAR_EQUALS_SIGN: /* Positive lookahead */ - bravalue = OP_ASSERT; - ptr++; - break; - - - /* ------------------------------------------------------------ */ - case CHAR_EXCLAMATION_MARK: /* Negative lookahead */ - ptr++; - if (*ptr == CHAR_RIGHT_PARENTHESIS) /* Optimize (?!) */ - { - *code++ = OP_FAIL; - previous = NULL; - continue; - } - bravalue = OP_ASSERT_NOT; - break; - - - /* ------------------------------------------------------------ */ - case CHAR_LESS_THAN_SIGN: /* Lookbehind or named define */ - switch (ptr[1]) - { - case CHAR_EQUALS_SIGN: /* Positive lookbehind */ - bravalue = OP_ASSERTBACK; - ptr += 2; - break; - - case CHAR_EXCLAMATION_MARK: /* Negative lookbehind */ - bravalue = OP_ASSERTBACK_NOT; - ptr += 2; - break; - - default: /* Could be name define, else bad */ - if ((cd->ctypes[ptr[1]] & ctype_word) != 0) goto DEFINE_NAME; - ptr++; /* Correct offset for error */ - *errorcodeptr = ERR24; - goto FAILED; - } - break; - - - /* ------------------------------------------------------------ */ - case CHAR_GREATER_THAN_SIGN: /* One-time brackets */ - bravalue = OP_ONCE; - ptr++; - break; - - - /* ------------------------------------------------------------ */ - case CHAR_C: /* Callout - may be followed by digits; */ - previous_callout = code; /* Save for later completion */ - after_manual_callout = 1; /* Skip one item before completing */ - *code++ = OP_CALLOUT; - { - int n = 0; - while ((digitab[*(++ptr)] & ctype_digit) != 0) - n = n * 10 + *ptr - CHAR_0; - if (*ptr != CHAR_RIGHT_PARENTHESIS) - { - *errorcodeptr = ERR39; - goto FAILED; - } - if (n > 255) - { - *errorcodeptr = ERR38; - goto FAILED; - } - *code++ = n; - PUT(code, 0, ptr - cd->start_pattern + 1); /* Pattern offset */ - PUT(code, LINK_SIZE, 0); /* Default length */ - code += 2 * LINK_SIZE; - } - previous = NULL; - continue; - - - /* ------------------------------------------------------------ */ - case CHAR_P: /* Python-style named subpattern handling */ - if (*(++ptr) == CHAR_EQUALS_SIGN || - *ptr == CHAR_GREATER_THAN_SIGN) /* Reference or recursion */ - { - is_recurse = *ptr == CHAR_GREATER_THAN_SIGN; - terminator = CHAR_RIGHT_PARENTHESIS; - goto NAMED_REF_OR_RECURSE; - } - else if (*ptr != CHAR_LESS_THAN_SIGN) /* Test for Python-style defn */ - { - *errorcodeptr = ERR41; - goto FAILED; - } - /* Fall through to handle (?P< as (?< is handled */ - - - /* ------------------------------------------------------------ */ - DEFINE_NAME: /* Come here from (?< handling */ - case CHAR_APOSTROPHE: - { - terminator = (*ptr == CHAR_LESS_THAN_SIGN)? - CHAR_GREATER_THAN_SIGN : CHAR_APOSTROPHE; - name = ++ptr; - - while ((cd->ctypes[*ptr] & ctype_word) != 0) ptr++; - namelen = ptr - name; - - /* In the pre-compile phase, just do a syntax check. */ - - if (lengthptr != NULL) - { - if (*ptr != terminator) - { - *errorcodeptr = ERR42; - goto FAILED; - } - if (cd->names_found >= MAX_NAME_COUNT) - { - *errorcodeptr = ERR49; - goto FAILED; - } - if (namelen + 3 > cd->name_entry_size) - { - cd->name_entry_size = namelen + 3; - if (namelen > MAX_NAME_SIZE) - { - *errorcodeptr = ERR48; - goto FAILED; - } - } - } - - /* In the real compile, create the entry in the table */ - - else - { - slot = cd->name_table; - for (i = 0; i < cd->names_found; i++) - { - int crc = memcmp(name, slot+2, namelen); - if (crc == 0) - { - if (slot[2+namelen] == 0) - { - if ((options & PCRE_DUPNAMES) == 0) - { - *errorcodeptr = ERR43; - goto FAILED; - } - } - else crc = -1; /* Current name is substring */ - } - if (crc < 0) - { - memmove(slot + cd->name_entry_size, slot, - (cd->names_found - i) * cd->name_entry_size); - break; - } - slot += cd->name_entry_size; - } - - PUT2(slot, 0, cd->bracount + 1); - memcpy(slot + 2, name, namelen); - slot[2+namelen] = 0; - } - } - - /* In both cases, count the number of names we've encountered. */ - - ptr++; /* Move past > or ' */ - cd->names_found++; - goto NUMBERED_GROUP; - - - /* ------------------------------------------------------------ */ - case CHAR_AMPERSAND: /* Perl recursion/subroutine syntax */ - terminator = CHAR_RIGHT_PARENTHESIS; - is_recurse = TRUE; - /* Fall through */ - - /* We come here from the Python syntax above that handles both - references (?P=name) and recursion (?P>name), as well as falling - through from the Perl recursion syntax (?&name). We also come here from - the Perl \k or \k'name' back reference syntax and the \k{name} - .NET syntax, and the Oniguruma \g<...> and \g'...' subroutine syntax. */ - - NAMED_REF_OR_RECURSE: - name = ++ptr; - while ((cd->ctypes[*ptr] & ctype_word) != 0) ptr++; - namelen = ptr - name; - - /* In the pre-compile phase, do a syntax check and set a dummy - reference number. */ - - if (lengthptr != NULL) - { - if (namelen == 0) - { - *errorcodeptr = ERR62; - goto FAILED; - } - if (*ptr != terminator) - { - *errorcodeptr = ERR42; - goto FAILED; - } - if (namelen > MAX_NAME_SIZE) - { - *errorcodeptr = ERR48; - goto FAILED; - } - recno = 0; - } - - /* In the real compile, seek the name in the table. We check the name - first, and then check that we have reached the end of the name in the - table. That way, if the name that is longer than any in the table, - the comparison will fail without reading beyond the table entry. */ - - else - { - slot = cd->name_table; - for (i = 0; i < cd->names_found; i++) - { - if (strncmp((char *)name, (char *)slot+2, namelen) == 0 && - slot[2+namelen] == 0) - break; - slot += cd->name_entry_size; - } - - if (i < cd->names_found) /* Back reference */ - { - recno = GET2(slot, 0); - } - else if ((recno = /* Forward back reference */ - find_parens(cd, name, namelen, - (options & PCRE_EXTENDED) != 0)) <= 0) - { - *errorcodeptr = ERR15; - goto FAILED; - } - } - - /* In both phases, we can now go to the code than handles numerical - recursion or backreferences. */ - - if (is_recurse) goto HANDLE_RECURSION; - else goto HANDLE_REFERENCE; - - - /* ------------------------------------------------------------ */ - case CHAR_R: /* Recursion */ - ptr++; /* Same as (?0) */ - /* Fall through */ - - - /* ------------------------------------------------------------ */ - case CHAR_MINUS: case CHAR_PLUS: /* Recursion or subroutine */ - case CHAR_0: case CHAR_1: case CHAR_2: case CHAR_3: case CHAR_4: - case CHAR_5: case CHAR_6: case CHAR_7: case CHAR_8: case CHAR_9: - { - const uschar *called; - terminator = CHAR_RIGHT_PARENTHESIS; - - /* Come here from the \g<...> and \g'...' code (Oniguruma - compatibility). However, the syntax has been checked to ensure that - the ... are a (signed) number, so that neither ERR63 nor ERR29 will - be called on this path, nor with the jump to OTHER_CHAR_AFTER_QUERY - ever be taken. */ - - HANDLE_NUMERICAL_RECURSION: - - if ((refsign = *ptr) == CHAR_PLUS) - { - ptr++; - if ((digitab[*ptr] & ctype_digit) == 0) - { - *errorcodeptr = ERR63; - goto FAILED; - } - } - else if (refsign == CHAR_MINUS) - { - if ((digitab[ptr[1]] & ctype_digit) == 0) - goto OTHER_CHAR_AFTER_QUERY; - ptr++; - } - - recno = 0; - while((digitab[*ptr] & ctype_digit) != 0) - recno = recno * 10 + *ptr++ - CHAR_0; - - if (*ptr != terminator) - { - *errorcodeptr = ERR29; - goto FAILED; - } - - if (refsign == CHAR_MINUS) - { - if (recno == 0) - { - *errorcodeptr = ERR58; - goto FAILED; - } - recno = cd->bracount - recno + 1; - if (recno <= 0) - { - *errorcodeptr = ERR15; - goto FAILED; - } - } - else if (refsign == CHAR_PLUS) - { - if (recno == 0) - { - *errorcodeptr = ERR58; - goto FAILED; - } - recno += cd->bracount; - } - - /* Come here from code above that handles a named recursion */ - - HANDLE_RECURSION: - - previous = code; - called = cd->start_code; - - /* When we are actually compiling, find the bracket that is being - referenced. Temporarily end the regex in case it doesn't exist before - this point. If we end up with a forward reference, first check that - the bracket does occur later so we can give the error (and position) - now. Then remember this forward reference in the workspace so it can - be filled in at the end. */ - - if (lengthptr == NULL) - { - *code = OP_END; - if (recno != 0) called = find_bracket(cd->start_code, utf8, recno); - - /* Forward reference */ - - if (called == NULL) - { - if (find_parens(cd, NULL, recno, - (options & PCRE_EXTENDED) != 0) < 0) - { - *errorcodeptr = ERR15; - goto FAILED; - } - called = cd->start_code + recno; - PUTINC(cd->hwm, 0, code + 2 + LINK_SIZE - cd->start_code); - } - - /* If not a forward reference, and the subpattern is still open, - this is a recursive call. We check to see if this is a left - recursion that could loop for ever, and diagnose that case. */ - - else if (GET(called, 1) == 0 && - could_be_empty(called, code, bcptr, utf8)) - { - *errorcodeptr = ERR40; - goto FAILED; - } - } - - /* Insert the recursion/subroutine item, automatically wrapped inside - "once" brackets. Set up a "previous group" length so that a - subsequent quantifier will work. */ - - *code = OP_ONCE; - PUT(code, 1, 2 + 2*LINK_SIZE); - code += 1 + LINK_SIZE; - - *code = OP_RECURSE; - PUT(code, 1, called - cd->start_code); - code += 1 + LINK_SIZE; - - *code = OP_KET; - PUT(code, 1, 2 + 2*LINK_SIZE); - code += 1 + LINK_SIZE; - - length_prevgroup = 3 + 3*LINK_SIZE; - } - - /* Can't determine a first byte now */ - - if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE; - continue; - - - /* ------------------------------------------------------------ */ - default: /* Other characters: check option setting */ - OTHER_CHAR_AFTER_QUERY: - set = unset = 0; - optset = &set; - - while (*ptr != CHAR_RIGHT_PARENTHESIS && *ptr != CHAR_COLON) - { - switch (*ptr++) - { - case CHAR_MINUS: optset = &unset; break; - - case CHAR_J: /* Record that it changed in the external options */ - *optset |= PCRE_DUPNAMES; - cd->external_flags |= PCRE_JCHANGED; - break; - - case CHAR_i: *optset |= PCRE_CASELESS; break; - case CHAR_m: *optset |= PCRE_MULTILINE; break; - case CHAR_s: *optset |= PCRE_DOTALL; break; - case CHAR_x: *optset |= PCRE_EXTENDED; break; - case CHAR_U: *optset |= PCRE_UNGREEDY; break; - case CHAR_X: *optset |= PCRE_EXTRA; break; - - default: *errorcodeptr = ERR12; - ptr--; /* Correct the offset */ - goto FAILED; - } - } - - /* Set up the changed option bits, but don't change anything yet. */ - - newoptions = (options | set) & (~unset); - - /* If the options ended with ')' this is not the start of a nested - group with option changes, so the options change at this level. If this - item is right at the start of the pattern, the options can be - abstracted and made external in the pre-compile phase, and ignored in - the compile phase. This can be helpful when matching -- for instance in - caseless checking of required bytes. - - If the code pointer is not (cd->start_code + 1 + LINK_SIZE), we are - definitely *not* at the start of the pattern because something has been - compiled. In the pre-compile phase, however, the code pointer can have - that value after the start, because it gets reset as code is discarded - during the pre-compile. However, this can happen only at top level - if - we are within parentheses, the starting BRA will still be present. At - any parenthesis level, the length value can be used to test if anything - has been compiled at that level. Thus, a test for both these conditions - is necessary to ensure we correctly detect the start of the pattern in - both phases. - - If we are not at the pattern start, compile code to change the ims - options if this setting actually changes any of them, and reset the - greedy defaults and the case value for firstbyte and reqbyte. */ - - if (*ptr == CHAR_RIGHT_PARENTHESIS) - { - if (code == cd->start_code + 1 + LINK_SIZE && - (lengthptr == NULL || *lengthptr == 2 + 2*LINK_SIZE)) - { - cd->external_options = newoptions; - } - else - { - if ((options & PCRE_IMS) != (newoptions & PCRE_IMS)) - { - *code++ = OP_OPT; - *code++ = newoptions & PCRE_IMS; - } - greedy_default = ((newoptions & PCRE_UNGREEDY) != 0); - greedy_non_default = greedy_default ^ 1; - req_caseopt = ((newoptions & PCRE_CASELESS) != 0)? REQ_CASELESS : 0; - } - - /* Change options at this level, and pass them back for use - in subsequent branches. When not at the start of the pattern, this - information is also necessary so that a resetting item can be - compiled at the end of a group (if we are in a group). */ - - *optionsptr = options = newoptions; - previous = NULL; /* This item can't be repeated */ - continue; /* It is complete */ - } - - /* If the options ended with ':' we are heading into a nested group - with possible change of options. Such groups are non-capturing and are - not assertions of any kind. All we need to do is skip over the ':'; - the newoptions value is handled below. */ - - bravalue = OP_BRA; - ptr++; - } /* End of switch for character following (? */ - } /* End of (? handling */ - - /* Opening parenthesis not followed by '?'. If PCRE_NO_AUTO_CAPTURE is set, - all unadorned brackets become non-capturing and behave like (?:...) - brackets. */ - - else if ((options & PCRE_NO_AUTO_CAPTURE) != 0) - { - bravalue = OP_BRA; - } - - /* Else we have a capturing group. */ - - else - { - NUMBERED_GROUP: - cd->bracount += 1; - PUT2(code, 1+LINK_SIZE, cd->bracount); - skipbytes = 2; - } - - /* Process nested bracketed regex. Assertions may not be repeated, but - other kinds can be. All their opcodes are >= OP_ONCE. We copy code into a - non-register variable in order to be able to pass its address because some - compilers complain otherwise. Pass in a new setting for the ims options if - they have changed. */ - - previous = (bravalue >= OP_ONCE)? code : NULL; - *code = bravalue; - tempcode = code; - tempreqvary = cd->req_varyopt; /* Save value before bracket */ - length_prevgroup = 0; /* Initialize for pre-compile phase */ - - if (!compile_regex( - newoptions, /* The complete new option state */ - options & PCRE_IMS, /* The previous ims option state */ - &tempcode, /* Where to put code (updated) */ - &ptr, /* Input pointer (updated) */ - errorcodeptr, /* Where to put an error message */ - (bravalue == OP_ASSERTBACK || - bravalue == OP_ASSERTBACK_NOT), /* TRUE if back assert */ - reset_bracount, /* True if (?| group */ - skipbytes, /* Skip over bracket number */ - &subfirstbyte, /* For possible first char */ - &subreqbyte, /* For possible last char */ - bcptr, /* Current branch chain */ - cd, /* Tables block */ - (lengthptr == NULL)? NULL : /* Actual compile phase */ - &length_prevgroup /* Pre-compile phase */ - )) - goto FAILED; - - /* At the end of compiling, code is still pointing to the start of the - group, while tempcode has been updated to point past the end of the group - and any option resetting that may follow it. The pattern pointer (ptr) - is on the bracket. */ - - /* If this is a conditional bracket, check that there are no more than - two branches in the group, or just one if it's a DEFINE group. We do this - in the real compile phase, not in the pre-pass, where the whole group may - not be available. */ - - if (bravalue == OP_COND && lengthptr == NULL) - { - uschar *tc = code; - int condcount = 0; - - do { - condcount++; - tc += GET(tc,1); - } - while (*tc != OP_KET); - - /* A DEFINE group is never obeyed inline (the "condition" is always - false). It must have only one branch. */ - - if (code[LINK_SIZE+1] == OP_DEF) - { - if (condcount > 1) - { - *errorcodeptr = ERR54; - goto FAILED; - } - bravalue = OP_DEF; /* Just a flag to suppress char handling below */ - } - - /* A "normal" conditional group. If there is just one branch, we must not - make use of its firstbyte or reqbyte, because this is equivalent to an - empty second branch. */ - - else - { - if (condcount > 2) - { - *errorcodeptr = ERR27; - goto FAILED; - } - if (condcount == 1) subfirstbyte = subreqbyte = REQ_NONE; - } - } - - /* Error if hit end of pattern */ - - if (*ptr != CHAR_RIGHT_PARENTHESIS) - { - *errorcodeptr = ERR14; - goto FAILED; - } - - /* In the pre-compile phase, update the length by the length of the group, - less the brackets at either end. Then reduce the compiled code to just a - set of non-capturing brackets so that it doesn't use much memory if it is - duplicated by a quantifier.*/ - - if (lengthptr != NULL) - { - if (OFLOW_MAX - *lengthptr < length_prevgroup - 2 - 2*LINK_SIZE) - { - *errorcodeptr = ERR20; - goto FAILED; - } - *lengthptr += length_prevgroup - 2 - 2*LINK_SIZE; - *code++ = OP_BRA; - PUTINC(code, 0, 1 + LINK_SIZE); - *code++ = OP_KET; - PUTINC(code, 0, 1 + LINK_SIZE); - break; /* No need to waste time with special character handling */ - } - - /* Otherwise update the main code pointer to the end of the group. */ - - code = tempcode; - - /* For a DEFINE group, required and first character settings are not - relevant. */ - - if (bravalue == OP_DEF) break; - - /* Handle updating of the required and first characters for other types of - group. Update for normal brackets of all kinds, and conditions with two - branches (see code above). If the bracket is followed by a quantifier with - zero repeat, we have to back off. Hence the definition of zeroreqbyte and - zerofirstbyte outside the main loop so that they can be accessed for the - back off. */ - - zeroreqbyte = reqbyte; - zerofirstbyte = firstbyte; - groupsetfirstbyte = FALSE; - - if (bravalue >= OP_ONCE) - { - /* If we have not yet set a firstbyte in this branch, take it from the - subpattern, remembering that it was set here so that a repeat of more - than one can replicate it as reqbyte if necessary. If the subpattern has - no firstbyte, set "none" for the whole branch. In both cases, a zero - repeat forces firstbyte to "none". */ - - if (firstbyte == REQ_UNSET) - { - if (subfirstbyte >= 0) - { - firstbyte = subfirstbyte; - groupsetfirstbyte = TRUE; - } - else firstbyte = REQ_NONE; - zerofirstbyte = REQ_NONE; - } - - /* If firstbyte was previously set, convert the subpattern's firstbyte - into reqbyte if there wasn't one, using the vary flag that was in - existence beforehand. */ - - else if (subfirstbyte >= 0 && subreqbyte < 0) - subreqbyte = subfirstbyte | tempreqvary; - - /* If the subpattern set a required byte (or set a first byte that isn't - really the first byte - see above), set it. */ - - if (subreqbyte >= 0) reqbyte = subreqbyte; - } - - /* For a forward assertion, we take the reqbyte, if set. This can be - helpful if the pattern that follows the assertion doesn't set a different - char. For example, it's useful for /(?=abcde).+/. We can't set firstbyte - for an assertion, however because it leads to incorrect effect for patterns - such as /(?=a)a.+/ when the "real" "a" would then become a reqbyte instead - of a firstbyte. This is overcome by a scan at the end if there's no - firstbyte, looking for an asserted first char. */ - - else if (bravalue == OP_ASSERT && subreqbyte >= 0) reqbyte = subreqbyte; - break; /* End of processing '(' */ - - - /* ===================================================================*/ - /* Handle metasequences introduced by \. For ones like \d, the ESC_ values - are arranged to be the negation of the corresponding OP_values. For the - back references, the values are ESC_REF plus the reference number. Only - back references and those types that consume a character may be repeated. - We can test for values between ESC_b and ESC_Z for the latter; this may - have to change if any new ones are ever created. */ - - case CHAR_BACKSLASH: - tempptr = ptr; - c = check_escape(&ptr, errorcodeptr, cd->bracount, options, FALSE); - if (*errorcodeptr != 0) goto FAILED; - - if (c < 0) - { - if (-c == ESC_Q) /* Handle start of quoted string */ - { - if (ptr[1] == CHAR_BACKSLASH && ptr[2] == CHAR_E) - ptr += 2; /* avoid empty string */ - else inescq = TRUE; - continue; - } - - if (-c == ESC_E) continue; /* Perl ignores an orphan \E */ - - /* For metasequences that actually match a character, we disable the - setting of a first character if it hasn't already been set. */ - - if (firstbyte == REQ_UNSET && -c > ESC_b && -c < ESC_Z) - firstbyte = REQ_NONE; - - /* Set values to reset to if this is followed by a zero repeat. */ - - zerofirstbyte = firstbyte; - zeroreqbyte = reqbyte; - - /* \g or \g'name' is a subroutine call by name and \g or \g'n' - is a subroutine call by number (Oniguruma syntax). In fact, the value - -ESC_g is returned only for these cases. So we don't need to check for < - or ' if the value is -ESC_g. For the Perl syntax \g{n} the value is - -ESC_REF+n, and for the Perl syntax \g{name} the result is -ESC_k (as - that is a synonym for a named back reference). */ - - if (-c == ESC_g) - { - const uschar *p; - save_hwm = cd->hwm; /* Normally this is set when '(' is read */ - terminator = (*(++ptr) == CHAR_LESS_THAN_SIGN)? - CHAR_GREATER_THAN_SIGN : CHAR_APOSTROPHE; - - /* These two statements stop the compiler for warning about possibly - unset variables caused by the jump to HANDLE_NUMERICAL_RECURSION. In - fact, because we actually check for a number below, the paths that - would actually be in error are never taken. */ - - skipbytes = 0; - reset_bracount = FALSE; - - /* Test for a name */ - - if (ptr[1] != CHAR_PLUS && ptr[1] != CHAR_MINUS) - { - BOOL isnumber = TRUE; - for (p = ptr + 1; *p != 0 && *p != terminator; p++) - { - if ((cd->ctypes[*p] & ctype_digit) == 0) isnumber = FALSE; - if ((cd->ctypes[*p] & ctype_word) == 0) break; - } - if (*p != terminator) - { - *errorcodeptr = ERR57; - break; - } - if (isnumber) - { - ptr++; - goto HANDLE_NUMERICAL_RECURSION; - } - is_recurse = TRUE; - goto NAMED_REF_OR_RECURSE; - } - - /* Test a signed number in angle brackets or quotes. */ - - p = ptr + 2; - while ((digitab[*p] & ctype_digit) != 0) p++; - if (*p != terminator) - { - *errorcodeptr = ERR57; - break; - } - ptr++; - goto HANDLE_NUMERICAL_RECURSION; - } - - /* \k or \k'name' is a back reference by name (Perl syntax). - We also support \k{name} (.NET syntax) */ - - if (-c == ESC_k && (ptr[1] == CHAR_LESS_THAN_SIGN || - ptr[1] == CHAR_APOSTROPHE || ptr[1] == CHAR_LEFT_CURLY_BRACKET)) - { - is_recurse = FALSE; - terminator = (*(++ptr) == CHAR_LESS_THAN_SIGN)? - CHAR_GREATER_THAN_SIGN : (*ptr == CHAR_APOSTROPHE)? - CHAR_APOSTROPHE : CHAR_RIGHT_CURLY_BRACKET; - goto NAMED_REF_OR_RECURSE; - } - - /* Back references are handled specially; must disable firstbyte if - not set to cope with cases like (?=(\w+))\1: which would otherwise set - ':' later. */ - - if (-c >= ESC_REF) - { - recno = -c - ESC_REF; - - HANDLE_REFERENCE: /* Come here from named backref handling */ - if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE; - previous = code; - *code++ = OP_REF; - PUT2INC(code, 0, recno); - cd->backref_map |= (recno < 32)? (1 << recno) : 1; - if (recno > cd->top_backref) cd->top_backref = recno; - } - - /* So are Unicode property matches, if supported. */ - -#ifdef SUPPORT_UCP - else if (-c == ESC_P || -c == ESC_p) - { - BOOL negated; - int pdata; - int ptype = get_ucp(&ptr, &negated, &pdata, errorcodeptr); - if (ptype < 0) goto FAILED; - previous = code; - *code++ = ((-c == ESC_p) != negated)? OP_PROP : OP_NOTPROP; - *code++ = ptype; - *code++ = pdata; - } -#else - - /* If Unicode properties are not supported, \X, \P, and \p are not - allowed. */ - - else if (-c == ESC_X || -c == ESC_P || -c == ESC_p) - { - *errorcodeptr = ERR45; - goto FAILED; - } -#endif - - /* For the rest (including \X when Unicode properties are supported), we - can obtain the OP value by negating the escape value. */ - - else - { - previous = (-c > ESC_b && -c < ESC_Z)? code : NULL; - *code++ = -c; - } - continue; - } - - /* We have a data character whose value is in c. In UTF-8 mode it may have - a value > 127. We set its representation in the length/buffer, and then - handle it as a data character. */ - -#ifdef SUPPORT_UTF8 - if (utf8 && c > 127) - mclength = _pcre_ord2utf8(c, mcbuffer); - else -#endif - - { - mcbuffer[0] = c; - mclength = 1; - } - goto ONE_CHAR; - - - /* ===================================================================*/ - /* Handle a literal character. It is guaranteed not to be whitespace or # - when the extended flag is set. If we are in UTF-8 mode, it may be a - multi-byte literal character. */ - - default: - NORMAL_CHAR: - mclength = 1; - mcbuffer[0] = c; - -#ifdef SUPPORT_UTF8 - if (utf8 && c >= 0xc0) - { - while ((ptr[1] & 0xc0) == 0x80) - mcbuffer[mclength++] = *(++ptr); - } -#endif - - /* At this point we have the character's bytes in mcbuffer, and the length - in mclength. When not in UTF-8 mode, the length is always 1. */ - - ONE_CHAR: - previous = code; - *code++ = ((options & PCRE_CASELESS) != 0)? OP_CHARNC : OP_CHAR; - for (c = 0; c < mclength; c++) *code++ = mcbuffer[c]; - - /* Remember if \r or \n were seen */ - - if (mcbuffer[0] == CHAR_CR || mcbuffer[0] == CHAR_NL) - cd->external_flags |= PCRE_HASCRORLF; - - /* Set the first and required bytes appropriately. If no previous first - byte, set it from this character, but revert to none on a zero repeat. - Otherwise, leave the firstbyte value alone, and don't change it on a zero - repeat. */ - - if (firstbyte == REQ_UNSET) - { - zerofirstbyte = REQ_NONE; - zeroreqbyte = reqbyte; - - /* If the character is more than one byte long, we can set firstbyte - only if it is not to be matched caselessly. */ - - if (mclength == 1 || req_caseopt == 0) - { - firstbyte = mcbuffer[0] | req_caseopt; - if (mclength != 1) reqbyte = code[-1] | cd->req_varyopt; - } - else firstbyte = reqbyte = REQ_NONE; - } - - /* firstbyte was previously set; we can set reqbyte only the length is - 1 or the matching is caseful. */ - - else - { - zerofirstbyte = firstbyte; - zeroreqbyte = reqbyte; - if (mclength == 1 || req_caseopt == 0) - reqbyte = code[-1] | req_caseopt | cd->req_varyopt; - } - - break; /* End of literal character handling */ - } - } /* end of big loop */ - - -/* Control never reaches here by falling through, only by a goto for all the -error states. Pass back the position in the pattern so that it can be displayed -to the user for diagnosing the error. */ - -FAILED: -*ptrptr = ptr; -return FALSE; -} - - - - -/************************************************* -* Compile sequence of alternatives * -*************************************************/ - -/* On entry, ptr is pointing past the bracket character, but on return it -points to the closing bracket, or vertical bar, or end of string. The code -variable is pointing at the byte into which the BRA operator has been stored. -If the ims options are changed at the start (for a (?ims: group) or during any -branch, we need to insert an OP_OPT item at the start of every following branch -to ensure they get set correctly at run time, and also pass the new options -into every subsequent branch compile. - -This function is used during the pre-compile phase when we are trying to find -out the amount of memory needed, as well as during the real compile phase. The -value of lengthptr distinguishes the two phases. - -Arguments: - options option bits, including any changes for this subpattern - oldims previous settings of ims option bits - codeptr -> the address of the current code pointer - ptrptr -> the address of the current pattern pointer - errorcodeptr -> pointer to error code variable - lookbehind TRUE if this is a lookbehind assertion - reset_bracount TRUE to reset the count for each branch - skipbytes skip this many bytes at start (for brackets and OP_COND) - firstbyteptr place to put the first required character, or a negative number - reqbyteptr place to put the last required character, or a negative number - bcptr pointer to the chain of currently open branches - cd points to the data block with tables pointers etc. - lengthptr NULL during the real compile phase - points to length accumulator during pre-compile phase - -Returns: TRUE on success -*/ - -static BOOL -compile_regex(int options, int oldims, uschar **codeptr, const uschar **ptrptr, - int *errorcodeptr, BOOL lookbehind, BOOL reset_bracount, int skipbytes, - int *firstbyteptr, int *reqbyteptr, branch_chain *bcptr, compile_data *cd, - int *lengthptr) -{ -const uschar *ptr = *ptrptr; -uschar *code = *codeptr; -uschar *last_branch = code; -uschar *start_bracket = code; -uschar *reverse_count = NULL; -int firstbyte, reqbyte; -int branchfirstbyte, branchreqbyte; -int length; -int orig_bracount; -int max_bracount; -branch_chain bc; - -bc.outer = bcptr; -bc.current = code; - -firstbyte = reqbyte = REQ_UNSET; - -/* Accumulate the length for use in the pre-compile phase. Start with the -length of the BRA and KET and any extra bytes that are required at the -beginning. We accumulate in a local variable to save frequent testing of -lenthptr for NULL. We cannot do this by looking at the value of code at the -start and end of each alternative, because compiled items are discarded during -the pre-compile phase so that the work space is not exceeded. */ - -length = 2 + 2*LINK_SIZE + skipbytes; - -/* WARNING: If the above line is changed for any reason, you must also change -the code that abstracts option settings at the start of the pattern and makes -them global. It tests the value of length for (2 + 2*LINK_SIZE) in the -pre-compile phase to find out whether anything has yet been compiled or not. */ - -/* Offset is set zero to mark that this bracket is still open */ - -PUT(code, 1, 0); -code += 1 + LINK_SIZE + skipbytes; - -/* Loop for each alternative branch */ - -orig_bracount = max_bracount = cd->bracount; -for (;;) - { - /* For a (?| group, reset the capturing bracket count so that each branch - uses the same numbers. */ - - if (reset_bracount) cd->bracount = orig_bracount; - - /* Handle a change of ims options at the start of the branch */ - - if ((options & PCRE_IMS) != oldims) - { - *code++ = OP_OPT; - *code++ = options & PCRE_IMS; - length += 2; - } - - /* Set up dummy OP_REVERSE if lookbehind assertion */ - - if (lookbehind) - { - *code++ = OP_REVERSE; - reverse_count = code; - PUTINC(code, 0, 0); - length += 1 + LINK_SIZE; - } - - /* Now compile the branch; in the pre-compile phase its length gets added - into the length. */ - - if (!compile_branch(&options, &code, &ptr, errorcodeptr, &branchfirstbyte, - &branchreqbyte, &bc, cd, (lengthptr == NULL)? NULL : &length)) - { - *ptrptr = ptr; - return FALSE; - } - - /* Keep the highest bracket count in case (?| was used and some branch - has fewer than the rest. */ - - if (cd->bracount > max_bracount) max_bracount = cd->bracount; - - /* In the real compile phase, there is some post-processing to be done. */ - - if (lengthptr == NULL) - { - /* If this is the first branch, the firstbyte and reqbyte values for the - branch become the values for the regex. */ - - if (*last_branch != OP_ALT) - { - firstbyte = branchfirstbyte; - reqbyte = branchreqbyte; - } - - /* If this is not the first branch, the first char and reqbyte have to - match the values from all the previous branches, except that if the - previous value for reqbyte didn't have REQ_VARY set, it can still match, - and we set REQ_VARY for the regex. */ - - else - { - /* If we previously had a firstbyte, but it doesn't match the new branch, - we have to abandon the firstbyte for the regex, but if there was - previously no reqbyte, it takes on the value of the old firstbyte. */ - - if (firstbyte >= 0 && firstbyte != branchfirstbyte) - { - if (reqbyte < 0) reqbyte = firstbyte; - firstbyte = REQ_NONE; - } - - /* If we (now or from before) have no firstbyte, a firstbyte from the - branch becomes a reqbyte if there isn't a branch reqbyte. */ - - if (firstbyte < 0 && branchfirstbyte >= 0 && branchreqbyte < 0) - branchreqbyte = branchfirstbyte; - - /* Now ensure that the reqbytes match */ - - if ((reqbyte & ~REQ_VARY) != (branchreqbyte & ~REQ_VARY)) - reqbyte = REQ_NONE; - else reqbyte |= branchreqbyte; /* To "or" REQ_VARY */ - } - - /* If lookbehind, check that this branch matches a fixed-length string, and - put the length into the OP_REVERSE item. Temporarily mark the end of the - branch with OP_END. */ - - if (lookbehind) - { - int fixed_length; - *code = OP_END; - fixed_length = find_fixedlength(last_branch, options); - DPRINTF(("fixed length = %d\n", fixed_length)); - if (fixed_length < 0) - { - *errorcodeptr = (fixed_length == -2)? ERR36 : ERR25; - *ptrptr = ptr; - return FALSE; - } - PUT(reverse_count, 0, fixed_length); - } - } - - /* Reached end of expression, either ')' or end of pattern. In the real - compile phase, go back through the alternative branches and reverse the chain - of offsets, with the field in the BRA item now becoming an offset to the - first alternative. If there are no alternatives, it points to the end of the - group. The length in the terminating ket is always the length of the whole - bracketed item. If any of the ims options were changed inside the group, - compile a resetting op-code following, except at the very end of the pattern. - Return leaving the pointer at the terminating char. */ - - if (*ptr != CHAR_VERTICAL_LINE) - { - if (lengthptr == NULL) - { - int branch_length = code - last_branch; - do - { - int prev_length = GET(last_branch, 1); - PUT(last_branch, 1, branch_length); - branch_length = prev_length; - last_branch -= branch_length; - } - while (branch_length > 0); - } - - /* Fill in the ket */ - - *code = OP_KET; - PUT(code, 1, code - start_bracket); - code += 1 + LINK_SIZE; - - /* Resetting option if needed */ - - if ((options & PCRE_IMS) != oldims && *ptr == CHAR_RIGHT_PARENTHESIS) - { - *code++ = OP_OPT; - *code++ = oldims; - length += 2; - } - - /* Retain the highest bracket number, in case resetting was used. */ - - cd->bracount = max_bracount; - - /* Set values to pass back */ - - *codeptr = code; - *ptrptr = ptr; - *firstbyteptr = firstbyte; - *reqbyteptr = reqbyte; - if (lengthptr != NULL) - { - if (OFLOW_MAX - *lengthptr < length) - { - *errorcodeptr = ERR20; - return FALSE; - } - *lengthptr += length; - } - return TRUE; - } - - /* Another branch follows. In the pre-compile phase, we can move the code - pointer back to where it was for the start of the first branch. (That is, - pretend that each branch is the only one.) - - In the real compile phase, insert an ALT node. Its length field points back - to the previous branch while the bracket remains open. At the end the chain - is reversed. It's done like this so that the start of the bracket has a - zero offset until it is closed, making it possible to detect recursion. */ - - if (lengthptr != NULL) - { - code = *codeptr + 1 + LINK_SIZE + skipbytes; - length += 1 + LINK_SIZE; - } - else - { - *code = OP_ALT; - PUT(code, 1, code - last_branch); - bc.current = last_branch = code; - code += 1 + LINK_SIZE; - } - - ptr++; - } -/* Control never reaches here */ -} - - - - -/************************************************* -* Check for anchored expression * -*************************************************/ - -/* Try to find out if this is an anchored regular expression. Consider each -alternative branch. If they all start with OP_SOD or OP_CIRC, or with a bracket -all of whose alternatives start with OP_SOD or OP_CIRC (recurse ad lib), then -it's anchored. However, if this is a multiline pattern, then only OP_SOD -counts, since OP_CIRC can match in the middle. - -We can also consider a regex to be anchored if OP_SOM starts all its branches. -This is the code for \G, which means "match at start of match position, taking -into account the match offset". - -A branch is also implicitly anchored if it starts with .* and DOTALL is set, -because that will try the rest of the pattern at all possible matching points, -so there is no point trying again.... er .... - -.... except when the .* appears inside capturing parentheses, and there is a -subsequent back reference to those parentheses. We haven't enough information -to catch that case precisely. - -At first, the best we could do was to detect when .* was in capturing brackets -and the highest back reference was greater than or equal to that level. -However, by keeping a bitmap of the first 31 back references, we can catch some -of the more common cases more precisely. - -Arguments: - code points to start of expression (the bracket) - options points to the options setting - bracket_map a bitmap of which brackets we are inside while testing; this - handles up to substring 31; after that we just have to take - the less precise approach - backref_map the back reference bitmap - -Returns: TRUE or FALSE -*/ - -static BOOL -is_anchored(register const uschar *code, int *options, unsigned int bracket_map, - unsigned int backref_map) -{ -do { - const uschar *scode = first_significant_code(code + _pcre_OP_lengths[*code], - options, PCRE_MULTILINE, FALSE); - register int op = *scode; - - /* Non-capturing brackets */ - - if (op == OP_BRA) - { - if (!is_anchored(scode, options, bracket_map, backref_map)) return FALSE; - } - - /* Capturing brackets */ - - else if (op == OP_CBRA) - { - int n = GET2(scode, 1+LINK_SIZE); - int new_map = bracket_map | ((n < 32)? (1 << n) : 1); - if (!is_anchored(scode, options, new_map, backref_map)) return FALSE; - } - - /* Other brackets */ - - else if (op == OP_ASSERT || op == OP_ONCE || op == OP_COND) - { - if (!is_anchored(scode, options, bracket_map, backref_map)) return FALSE; - } - - /* .* is not anchored unless DOTALL is set (which generates OP_ALLANY) and - it isn't in brackets that are or may be referenced. */ - - else if ((op == OP_TYPESTAR || op == OP_TYPEMINSTAR || - op == OP_TYPEPOSSTAR)) - { - if (scode[1] != OP_ALLANY || (bracket_map & backref_map) != 0) - return FALSE; - } - - /* Check for explicit anchoring */ - - else if (op != OP_SOD && op != OP_SOM && - ((*options & PCRE_MULTILINE) != 0 || op != OP_CIRC)) - return FALSE; - code += GET(code, 1); - } -while (*code == OP_ALT); /* Loop for each alternative */ -return TRUE; -} - - - -/************************************************* -* Check for starting with ^ or .* * -*************************************************/ - -/* This is called to find out if every branch starts with ^ or .* so that -"first char" processing can be done to speed things up in multiline -matching and for non-DOTALL patterns that start with .* (which must start at -the beginning or after \n). As in the case of is_anchored() (see above), we -have to take account of back references to capturing brackets that contain .* -because in that case we can't make the assumption. - -Arguments: - code points to start of expression (the bracket) - bracket_map a bitmap of which brackets we are inside while testing; this - handles up to substring 31; after that we just have to take - the less precise approach - backref_map the back reference bitmap - -Returns: TRUE or FALSE -*/ - -static BOOL -is_startline(const uschar *code, unsigned int bracket_map, - unsigned int backref_map) -{ -do { - const uschar *scode = first_significant_code(code + _pcre_OP_lengths[*code], - NULL, 0, FALSE); - register int op = *scode; - - /* If we are at the start of a conditional assertion group, *both* the - conditional assertion *and* what follows the condition must satisfy the test - for start of line. Other kinds of condition fail. Note that there may be an - auto-callout at the start of a condition. */ - - if (op == OP_COND) - { - scode += 1 + LINK_SIZE; - if (*scode == OP_CALLOUT) scode += _pcre_OP_lengths[OP_CALLOUT]; - switch (*scode) - { - case OP_CREF: - case OP_RREF: - case OP_DEF: - return FALSE; - - default: /* Assertion */ - if (!is_startline(scode, bracket_map, backref_map)) return FALSE; - do scode += GET(scode, 1); while (*scode == OP_ALT); - scode += 1 + LINK_SIZE; - break; - } - scode = first_significant_code(scode, NULL, 0, FALSE); - op = *scode; - } - - /* Non-capturing brackets */ - - if (op == OP_BRA) - { - if (!is_startline(scode, bracket_map, backref_map)) return FALSE; - } - - /* Capturing brackets */ - - else if (op == OP_CBRA) - { - int n = GET2(scode, 1+LINK_SIZE); - int new_map = bracket_map | ((n < 32)? (1 << n) : 1); - if (!is_startline(scode, new_map, backref_map)) return FALSE; - } - - /* Other brackets */ - - else if (op == OP_ASSERT || op == OP_ONCE) - { - if (!is_startline(scode, bracket_map, backref_map)) return FALSE; - } - - /* .* means "start at start or after \n" if it isn't in brackets that - may be referenced. */ - - else if (op == OP_TYPESTAR || op == OP_TYPEMINSTAR || op == OP_TYPEPOSSTAR) - { - if (scode[1] != OP_ANY || (bracket_map & backref_map) != 0) return FALSE; - } - - /* Check for explicit circumflex */ - - else if (op != OP_CIRC) return FALSE; - - /* Move on to the next alternative */ - - code += GET(code, 1); - } -while (*code == OP_ALT); /* Loop for each alternative */ -return TRUE; -} - - - -/************************************************* -* Check for asserted fixed first char * -*************************************************/ - -/* During compilation, the "first char" settings from forward assertions are -discarded, because they can cause conflicts with actual literals that follow. -However, if we end up without a first char setting for an unanchored pattern, -it is worth scanning the regex to see if there is an initial asserted first -char. If all branches start with the same asserted char, or with a bracket all -of whose alternatives start with the same asserted char (recurse ad lib), then -we return that char, otherwise -1. - -Arguments: - code points to start of expression (the bracket) - options pointer to the options (used to check casing changes) - inassert TRUE if in an assertion - -Returns: -1 or the fixed first char -*/ - -static int -find_firstassertedchar(const uschar *code, int *options, BOOL inassert) -{ -register int c = -1; -do { - int d; - const uschar *scode = - first_significant_code(code + 1+LINK_SIZE, options, PCRE_CASELESS, TRUE); - register int op = *scode; - - switch(op) - { - default: - return -1; - - case OP_BRA: - case OP_CBRA: - case OP_ASSERT: - case OP_ONCE: - case OP_COND: - if ((d = find_firstassertedchar(scode, options, op == OP_ASSERT)) < 0) - return -1; - if (c < 0) c = d; else if (c != d) return -1; - break; - - case OP_EXACT: /* Fall through */ - scode += 2; - - case OP_CHAR: - case OP_CHARNC: - case OP_PLUS: - case OP_MINPLUS: - case OP_POSPLUS: - if (!inassert) return -1; - if (c < 0) - { - c = scode[1]; - if ((*options & PCRE_CASELESS) != 0) c |= REQ_CASELESS; - } - else if (c != scode[1]) return -1; - break; - } - - code += GET(code, 1); - } -while (*code == OP_ALT); -return c; -} - - - -/************************************************* -* Compile a Regular Expression * -*************************************************/ - -/* This function takes a string and returns a pointer to a block of store -holding a compiled version of the expression. The original API for this -function had no error code return variable; it is retained for backwards -compatibility. The new function is given a new name. - -Arguments: - pattern the regular expression - options various option bits - errorcodeptr pointer to error code variable (pcre_compile2() only) - can be NULL if you don't want a code value - errorptr pointer to pointer to error text - erroroffset ptr offset in pattern where error was detected - tables pointer to character tables or NULL - -Returns: pointer to compiled data block, or NULL on error, - with errorptr and erroroffset set -*/ - -PCRE_EXP_DEFN pcre * PCRE_CALL_CONVENTION -pcre_compile(const char *pattern, int options, const char **errorptr, - int *erroroffset, const unsigned char *tables) -{ -return pcre_compile2(pattern, options, NULL, errorptr, erroroffset, tables); -} - - -PCRE_EXP_DEFN pcre * PCRE_CALL_CONVENTION -pcre_compile2(const char *pattern, int options, int *errorcodeptr, - const char **errorptr, int *erroroffset, const unsigned char *tables) -{ -real_pcre *re; -int length = 1; /* For final END opcode */ -int firstbyte, reqbyte, newline; -int errorcode = 0; -int skipatstart = 0; -#ifdef SUPPORT_UTF8 -BOOL utf8; -#endif -size_t size; -uschar *code; -const uschar *codestart; -const uschar *ptr; -compile_data compile_block; -compile_data *cd = &compile_block; - -/* This space is used for "compiling" into during the first phase, when we are -computing the amount of memory that is needed. Compiled items are thrown away -as soon as possible, so that a fairly large buffer should be sufficient for -this purpose. The same space is used in the second phase for remembering where -to fill in forward references to subpatterns. */ - -uschar cworkspace[COMPILE_WORK_SIZE]; - -/* Set this early so that early errors get offset 0. */ - -ptr = (const uschar *)pattern; - -/* We can't pass back an error message if errorptr is NULL; I guess the best we -can do is just return NULL, but we can set a code value if there is a code -pointer. */ - -if (errorptr == NULL) - { - if (errorcodeptr != NULL) *errorcodeptr = 99; - return NULL; - } - -*errorptr = NULL; -if (errorcodeptr != NULL) *errorcodeptr = ERR0; - -/* However, we can give a message for this error */ - -if (erroroffset == NULL) - { - errorcode = ERR16; - goto PCRE_EARLY_ERROR_RETURN2; - } - -*erroroffset = 0; - -/* Set up pointers to the individual character tables */ - -if (tables == NULL) tables = _pcre_default_tables; -cd->lcc = tables + lcc_offset; -cd->fcc = tables + fcc_offset; -cd->cbits = tables + cbits_offset; -cd->ctypes = tables + ctypes_offset; - -/* Check that all undefined public option bits are zero */ - -if ((options & ~PUBLIC_COMPILE_OPTIONS) != 0) - { - errorcode = ERR17; - goto PCRE_EARLY_ERROR_RETURN; - } - -/* Check for global one-time settings at the start of the pattern, and remember -the offset for later. */ - -while (ptr[skipatstart] == CHAR_LEFT_PARENTHESIS && - ptr[skipatstart+1] == CHAR_ASTERISK) - { - int newnl = 0; - int newbsr = 0; - - if (strncmp((char *)(ptr+skipatstart+2), STRING_UTF8_RIGHTPAR, 5) == 0) - { skipatstart += 7; options |= PCRE_UTF8; continue; } - - if (strncmp((char *)(ptr+skipatstart+2), STRING_CR_RIGHTPAR, 3) == 0) - { skipatstart += 5; newnl = PCRE_NEWLINE_CR; } - else if (strncmp((char *)(ptr+skipatstart+2), STRING_LF_RIGHTPAR, 3) == 0) - { skipatstart += 5; newnl = PCRE_NEWLINE_LF; } - else if (strncmp((char *)(ptr+skipatstart+2), STRING_CRLF_RIGHTPAR, 5) == 0) - { skipatstart += 7; newnl = PCRE_NEWLINE_CR + PCRE_NEWLINE_LF; } - else if (strncmp((char *)(ptr+skipatstart+2), STRING_ANY_RIGHTPAR, 4) == 0) - { skipatstart += 6; newnl = PCRE_NEWLINE_ANY; } - else if (strncmp((char *)(ptr+skipatstart+2), STRING_ANYCRLF_RIGHTPAR, 8) == 0) - { skipatstart += 10; newnl = PCRE_NEWLINE_ANYCRLF; } - - else if (strncmp((char *)(ptr+skipatstart+2), STRING_BSR_ANYCRLF_RIGHTPAR, 12) == 0) - { skipatstart += 14; newbsr = PCRE_BSR_ANYCRLF; } - else if (strncmp((char *)(ptr+skipatstart+2), STRING_BSR_UNICODE_RIGHTPAR, 12) == 0) - { skipatstart += 14; newbsr = PCRE_BSR_UNICODE; } - - if (newnl != 0) - options = (options & ~PCRE_NEWLINE_BITS) | newnl; - else if (newbsr != 0) - options = (options & ~(PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) | newbsr; - else break; - } - -/* Can't support UTF8 unless PCRE has been compiled to include the code. */ - -#ifdef SUPPORT_UTF8 -utf8 = (options & PCRE_UTF8) != 0; -if (utf8 && (options & PCRE_NO_UTF8_CHECK) == 0 && - (*erroroffset = _pcre_valid_utf8((uschar *)pattern, -1)) >= 0) - { - errorcode = ERR44; - goto PCRE_EARLY_ERROR_RETURN2; - } -#else -if ((options & PCRE_UTF8) != 0) - { - errorcode = ERR32; - goto PCRE_EARLY_ERROR_RETURN; - } -#endif - -/* Check validity of \R options. */ - -switch (options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) - { - case 0: - case PCRE_BSR_ANYCRLF: - case PCRE_BSR_UNICODE: - break; - default: errorcode = ERR56; goto PCRE_EARLY_ERROR_RETURN; - } - -/* Handle different types of newline. The three bits give seven cases. The -current code allows for fixed one- or two-byte sequences, plus "any" and -"anycrlf". */ - -switch (options & PCRE_NEWLINE_BITS) - { - case 0: newline = NEWLINE; break; /* Build-time default */ - case PCRE_NEWLINE_CR: newline = CHAR_CR; break; - case PCRE_NEWLINE_LF: newline = CHAR_NL; break; - case PCRE_NEWLINE_CR+ - PCRE_NEWLINE_LF: newline = (CHAR_CR << 8) | CHAR_NL; break; - case PCRE_NEWLINE_ANY: newline = -1; break; - case PCRE_NEWLINE_ANYCRLF: newline = -2; break; - default: errorcode = ERR56; goto PCRE_EARLY_ERROR_RETURN; - } - -if (newline == -2) - { - cd->nltype = NLTYPE_ANYCRLF; - } -else if (newline < 0) - { - cd->nltype = NLTYPE_ANY; - } -else - { - cd->nltype = NLTYPE_FIXED; - if (newline > 255) - { - cd->nllen = 2; - cd->nl[0] = (newline >> 8) & 255; - cd->nl[1] = newline & 255; - } - else - { - cd->nllen = 1; - cd->nl[0] = newline; - } - } - -/* Maximum back reference and backref bitmap. The bitmap records up to 31 back -references to help in deciding whether (.*) can be treated as anchored or not. -*/ - -cd->top_backref = 0; -cd->backref_map = 0; - -/* Reflect pattern for debugging output */ - -DPRINTF(("------------------------------------------------------------------\n")); -DPRINTF(("%s\n", pattern)); - -/* Pretend to compile the pattern while actually just accumulating the length -of memory required. This behaviour is triggered by passing a non-NULL final -argument to compile_regex(). We pass a block of workspace (cworkspace) for it -to compile parts of the pattern into; the compiled code is discarded when it is -no longer needed, so hopefully this workspace will never overflow, though there -is a test for its doing so. */ - -cd->bracount = cd->final_bracount = 0; -cd->names_found = 0; -cd->name_entry_size = 0; -cd->name_table = NULL; -cd->start_workspace = cworkspace; -cd->start_code = cworkspace; -cd->hwm = cworkspace; -cd->start_pattern = (const uschar *)pattern; -cd->end_pattern = (const uschar *)(pattern + strlen(pattern)); -cd->req_varyopt = 0; -cd->external_options = options; -cd->external_flags = 0; - -/* Now do the pre-compile. On error, errorcode will be set non-zero, so we -don't need to look at the result of the function here. The initial options have -been put into the cd block so that they can be changed if an option setting is -found within the regex right at the beginning. Bringing initial option settings -outside can help speed up starting point checks. */ - -ptr += skipatstart; -code = cworkspace; -*code = OP_BRA; -(void)compile_regex(cd->external_options, cd->external_options & PCRE_IMS, - &code, &ptr, &errorcode, FALSE, FALSE, 0, &firstbyte, &reqbyte, NULL, cd, - &length); -if (errorcode != 0) goto PCRE_EARLY_ERROR_RETURN; - -DPRINTF(("end pre-compile: length=%d workspace=%d\n", length, - cd->hwm - cworkspace)); - -if (length > MAX_PATTERN_SIZE) - { - errorcode = ERR20; - goto PCRE_EARLY_ERROR_RETURN; - } - -/* Compute the size of data block needed and get it, either from malloc or -externally provided function. Integer overflow should no longer be possible -because nowadays we limit the maximum value of cd->names_found and -cd->name_entry_size. */ - -size = length + sizeof(real_pcre) + cd->names_found * (cd->name_entry_size + 3); -re = (real_pcre *)(pcre_malloc)(size); - -if (re == NULL) - { - errorcode = ERR21; - goto PCRE_EARLY_ERROR_RETURN; - } - -/* Put in the magic number, and save the sizes, initial options, internal -flags, and character table pointer. NULL is used for the default character -tables. The nullpad field is at the end; it's there to help in the case when a -regex compiled on a system with 4-byte pointers is run on another with 8-byte -pointers. */ - -re->magic_number = MAGIC_NUMBER; -re->size = size; -re->options = cd->external_options; -re->flags = cd->external_flags; -re->dummy1 = 0; -re->first_byte = 0; -re->req_byte = 0; -re->name_table_offset = sizeof(real_pcre); -re->name_entry_size = cd->name_entry_size; -re->name_count = cd->names_found; -re->ref_count = 0; -re->tables = (tables == _pcre_default_tables)? NULL : tables; -re->nullpad = NULL; - -/* The starting points of the name/number translation table and of the code are -passed around in the compile data block. The start/end pattern and initial -options are already set from the pre-compile phase, as is the name_entry_size -field. Reset the bracket count and the names_found field. Also reset the hwm -field; this time it's used for remembering forward references to subpatterns. -*/ - -cd->final_bracount = cd->bracount; /* Save for checking forward references */ -cd->bracount = 0; -cd->names_found = 0; -cd->name_table = (uschar *)re + re->name_table_offset; -codestart = cd->name_table + re->name_entry_size * re->name_count; -cd->start_code = codestart; -cd->hwm = cworkspace; -cd->req_varyopt = 0; -cd->had_accept = FALSE; - -/* Set up a starting, non-extracting bracket, then compile the expression. On -error, errorcode will be set non-zero, so we don't need to look at the result -of the function here. */ - -ptr = (const uschar *)pattern + skipatstart; -code = (uschar *)codestart; -*code = OP_BRA; -(void)compile_regex(re->options, re->options & PCRE_IMS, &code, &ptr, - &errorcode, FALSE, FALSE, 0, &firstbyte, &reqbyte, NULL, cd, NULL); -re->top_bracket = cd->bracount; -re->top_backref = cd->top_backref; -re->flags = cd->external_flags; - -if (cd->had_accept) reqbyte = -1; /* Must disable after (*ACCEPT) */ - -/* If not reached end of pattern on success, there's an excess bracket. */ - -if (errorcode == 0 && *ptr != 0) errorcode = ERR22; - -/* Fill in the terminating state and check for disastrous overflow, but -if debugging, leave the test till after things are printed out. */ - -*code++ = OP_END; - -#ifndef PCRE_DEBUG -if (code - codestart > length) errorcode = ERR23; -#endif - -/* Fill in any forward references that are required. */ - -while (errorcode == 0 && cd->hwm > cworkspace) - { - int offset, recno; - const uschar *groupptr; - cd->hwm -= LINK_SIZE; - offset = GET(cd->hwm, 0); - recno = GET(codestart, offset); - groupptr = find_bracket(codestart, (re->options & PCRE_UTF8) != 0, recno); - if (groupptr == NULL) errorcode = ERR53; - else PUT(((uschar *)codestart), offset, groupptr - codestart); - } - -/* Give an error if there's back reference to a non-existent capturing -subpattern. */ - -if (errorcode == 0 && re->top_backref > re->top_bracket) errorcode = ERR15; - -/* Failed to compile, or error while post-processing */ - -if (errorcode != 0) - { - (pcre_free)(re); - PCRE_EARLY_ERROR_RETURN: - *erroroffset = ptr - (const uschar *)pattern; - PCRE_EARLY_ERROR_RETURN2: - *errorptr = find_error_text(errorcode); - if (errorcodeptr != NULL) *errorcodeptr = errorcode; - return NULL; - } - -/* If the anchored option was not passed, set the flag if we can determine that -the pattern is anchored by virtue of ^ characters or \A or anything else (such -as starting with .* when DOTALL is set). - -Otherwise, if we know what the first byte has to be, save it, because that -speeds up unanchored matches no end. If not, see if we can set the -PCRE_STARTLINE flag. This is helpful for multiline matches when all branches -start with ^. and also when all branches start with .* for non-DOTALL matches. -*/ - -if ((re->options & PCRE_ANCHORED) == 0) - { - int temp_options = re->options; /* May get changed during these scans */ - if (is_anchored(codestart, &temp_options, 0, cd->backref_map)) - re->options |= PCRE_ANCHORED; - else - { - if (firstbyte < 0) - firstbyte = find_firstassertedchar(codestart, &temp_options, FALSE); - if (firstbyte >= 0) /* Remove caseless flag for non-caseable chars */ - { - int ch = firstbyte & 255; - re->first_byte = ((firstbyte & REQ_CASELESS) != 0 && - cd->fcc[ch] == ch)? ch : firstbyte; - re->flags |= PCRE_FIRSTSET; - } - else if (is_startline(codestart, 0, cd->backref_map)) - re->flags |= PCRE_STARTLINE; - } - } - -/* For an anchored pattern, we use the "required byte" only if it follows a -variable length item in the regex. Remove the caseless flag for non-caseable -bytes. */ - -if (reqbyte >= 0 && - ((re->options & PCRE_ANCHORED) == 0 || (reqbyte & REQ_VARY) != 0)) - { - int ch = reqbyte & 255; - re->req_byte = ((reqbyte & REQ_CASELESS) != 0 && - cd->fcc[ch] == ch)? (reqbyte & ~REQ_CASELESS) : reqbyte; - re->flags |= PCRE_REQCHSET; - } - -/* Print out the compiled data if debugging is enabled. This is never the -case when building a production library. */ - -#ifdef PCRE_DEBUG - -printf("Length = %d top_bracket = %d top_backref = %d\n", - length, re->top_bracket, re->top_backref); - -printf("Options=%08x\n", re->options); - -if ((re->flags & PCRE_FIRSTSET) != 0) - { - int ch = re->first_byte & 255; - const char *caseless = ((re->first_byte & REQ_CASELESS) == 0)? - "" : " (caseless)"; - if (isprint(ch)) printf("First char = %c%s\n", ch, caseless); - else printf("First char = \\x%02x%s\n", ch, caseless); - } - -if ((re->flags & PCRE_REQCHSET) != 0) - { - int ch = re->req_byte & 255; - const char *caseless = ((re->req_byte & REQ_CASELESS) == 0)? - "" : " (caseless)"; - if (isprint(ch)) printf("Req char = %c%s\n", ch, caseless); - else printf("Req char = \\x%02x%s\n", ch, caseless); - } - -pcre_printint(re, stdout, TRUE); - -/* This check is done here in the debugging case so that the code that -was compiled can be seen. */ - -if (code - codestart > length) - { - (pcre_free)(re); - *errorptr = find_error_text(ERR23); - *erroroffset = ptr - (uschar *)pattern; - if (errorcodeptr != NULL) *errorcodeptr = ERR23; - return NULL; - } -#endif /* PCRE_DEBUG */ - -return (pcre *)re; -} - -/* End of pcre_compile.c */ diff --git a/libs/pcre/pcre_config.c b/libs/pcre/pcre_config.c deleted file mode 100644 index 78e8560ba6..0000000000 --- a/libs/pcre/pcre_config.c +++ /dev/null @@ -1,128 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2009 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains the external function pcre_config(). */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - - -/************************************************* -* Return info about what features are configured * -*************************************************/ - -/* This function has an extensible interface so that additional items can be -added compatibly. - -Arguments: - what what information is required - where where to put the information - -Returns: 0 if data returned, negative on error -*/ - -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre_config(int what, void *where) -{ -switch (what) - { - case PCRE_CONFIG_UTF8: -#ifdef SUPPORT_UTF8 - *((int *)where) = 1; -#else - *((int *)where) = 0; -#endif - break; - - case PCRE_CONFIG_UNICODE_PROPERTIES: -#ifdef SUPPORT_UCP - *((int *)where) = 1; -#else - *((int *)where) = 0; -#endif - break; - - case PCRE_CONFIG_NEWLINE: - *((int *)where) = NEWLINE; - break; - - case PCRE_CONFIG_BSR: -#ifdef BSR_ANYCRLF - *((int *)where) = 1; -#else - *((int *)where) = 0; -#endif - break; - - case PCRE_CONFIG_LINK_SIZE: - *((int *)where) = LINK_SIZE; - break; - - case PCRE_CONFIG_POSIX_MALLOC_THRESHOLD: - *((int *)where) = POSIX_MALLOC_THRESHOLD; - break; - - case PCRE_CONFIG_MATCH_LIMIT: - *((unsigned long int *)where) = MATCH_LIMIT; - break; - - case PCRE_CONFIG_MATCH_LIMIT_RECURSION: - *((unsigned long int *)where) = MATCH_LIMIT_RECURSION; - break; - - case PCRE_CONFIG_STACKRECURSE: -#ifdef NO_RECURSE - *((int *)where) = 0; -#else - *((int *)where) = 1; -#endif - break; - - default: return PCRE_ERROR_BADOPTION; - } - -return 0; -} - -/* End of pcre_config.c */ diff --git a/libs/pcre/pcre_dfa_exec.c b/libs/pcre/pcre_dfa_exec.c deleted file mode 100644 index d0d0ee5174..0000000000 --- a/libs/pcre/pcre_dfa_exec.c +++ /dev/null @@ -1,2963 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language (but see -below for why this module is different). - - Written by Philip Hazel - Copyright (c) 1997-2009 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains the external function pcre_dfa_exec(), which is an -alternative matching function that uses a sort of DFA algorithm (not a true -FSM). This is NOT Perl- compatible, but it has advantages in certain -applications. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#define NLBLOCK md /* Block containing newline information */ -#define PSSTART start_subject /* Field containing processed string start */ -#define PSEND end_subject /* Field containing processed string end */ - -#include "pcre_internal.h" - - -/* For use to indent debugging output */ - -#define SP " " - - -/************************************************* -* Code parameters and static tables * -*************************************************/ - -/* These are offsets that are used to turn the OP_TYPESTAR and friends opcodes -into others, under special conditions. A gap of 20 between the blocks should be -enough. The resulting opcodes don't have to be less than 256 because they are -never stored, so we push them well clear of the normal opcodes. */ - -#define OP_PROP_EXTRA 300 -#define OP_EXTUNI_EXTRA 320 -#define OP_ANYNL_EXTRA 340 -#define OP_HSPACE_EXTRA 360 -#define OP_VSPACE_EXTRA 380 - - -/* This table identifies those opcodes that are followed immediately by a -character that is to be tested in some way. This makes is possible to -centralize the loading of these characters. In the case of Type * etc, the -"character" is the opcode for \D, \d, \S, \s, \W, or \w, which will always be a -small value. ***NOTE*** If the start of this table is modified, the two tables -that follow must also be modified. */ - -static const uschar coptable[] = { - 0, /* End */ - 0, 0, 0, 0, 0, /* \A, \G, \K, \B, \b */ - 0, 0, 0, 0, 0, 0, /* \D, \d, \S, \s, \W, \w */ - 0, 0, 0, /* Any, AllAny, Anybyte */ - 0, 0, 0, /* NOTPROP, PROP, EXTUNI */ - 0, 0, 0, 0, 0, /* \R, \H, \h, \V, \v */ - 0, 0, 0, 0, 0, /* \Z, \z, Opt, ^, $ */ - 1, /* Char */ - 1, /* Charnc */ - 1, /* not */ - /* Positive single-char repeats */ - 1, 1, 1, 1, 1, 1, /* *, *?, +, +?, ?, ?? */ - 3, 3, 3, /* upto, minupto, exact */ - 1, 1, 1, 3, /* *+, ++, ?+, upto+ */ - /* Negative single-char repeats - only for chars < 256 */ - 1, 1, 1, 1, 1, 1, /* NOT *, *?, +, +?, ?, ?? */ - 3, 3, 3, /* NOT upto, minupto, exact */ - 1, 1, 1, 3, /* NOT *+, ++, ?+, updo+ */ - /* Positive type repeats */ - 1, 1, 1, 1, 1, 1, /* Type *, *?, +, +?, ?, ?? */ - 3, 3, 3, /* Type upto, minupto, exact */ - 1, 1, 1, 3, /* Type *+, ++, ?+, upto+ */ - /* Character class & ref repeats */ - 0, 0, 0, 0, 0, 0, /* *, *?, +, +?, ?, ?? */ - 0, 0, /* CRRANGE, CRMINRANGE */ - 0, /* CLASS */ - 0, /* NCLASS */ - 0, /* XCLASS - variable length */ - 0, /* REF */ - 0, /* RECURSE */ - 0, /* CALLOUT */ - 0, /* Alt */ - 0, /* Ket */ - 0, /* KetRmax */ - 0, /* KetRmin */ - 0, /* Assert */ - 0, /* Assert not */ - 0, /* Assert behind */ - 0, /* Assert behind not */ - 0, /* Reverse */ - 0, 0, 0, 0, /* ONCE, BRA, CBRA, COND */ - 0, 0, 0, /* SBRA, SCBRA, SCOND */ - 0, /* CREF */ - 0, /* RREF */ - 0, /* DEF */ - 0, 0, /* BRAZERO, BRAMINZERO */ - 0, 0, 0, 0, /* PRUNE, SKIP, THEN, COMMIT */ - 0, 0, 0 /* FAIL, ACCEPT, SKIPZERO */ -}; - -/* These 2 tables allow for compact code for testing for \D, \d, \S, \s, \W, -and \w */ - -static const uschar toptable1[] = { - 0, 0, 0, 0, 0, 0, - ctype_digit, ctype_digit, - ctype_space, ctype_space, - ctype_word, ctype_word, - 0, 0 /* OP_ANY, OP_ALLANY */ -}; - -static const uschar toptable2[] = { - 0, 0, 0, 0, 0, 0, - ctype_digit, 0, - ctype_space, 0, - ctype_word, 0, - 1, 1 /* OP_ANY, OP_ALLANY */ -}; - - -/* Structure for holding data about a particular state, which is in effect the -current data for an active path through the match tree. It must consist -entirely of ints because the working vector we are passed, and which we put -these structures in, is a vector of ints. */ - -typedef struct stateblock { - int offset; /* Offset to opcode */ - int count; /* Count for repeats */ - int ims; /* ims flag bits */ - int data; /* Some use extra data */ -} stateblock; - -#define INTS_PER_STATEBLOCK (sizeof(stateblock)/sizeof(int)) - - -#ifdef PCRE_DEBUG -/************************************************* -* Print character string * -*************************************************/ - -/* Character string printing function for debugging. - -Arguments: - p points to string - length number of bytes - f where to print - -Returns: nothing -*/ - -static void -pchars(unsigned char *p, int length, FILE *f) -{ -int c; -while (length-- > 0) - { - if (isprint(c = *(p++))) - fprintf(f, "%c", c); - else - fprintf(f, "\\x%02x", c); - } -} -#endif - - - -/************************************************* -* Execute a Regular Expression - DFA engine * -*************************************************/ - -/* This internal function applies a compiled pattern to a subject string, -starting at a given point, using a DFA engine. This function is called from the -external one, possibly multiple times if the pattern is not anchored. The -function calls itself recursively for some kinds of subpattern. - -Arguments: - md the match_data block with fixed information - this_start_code the opening bracket of this subexpression's code - current_subject where we currently are in the subject string - start_offset start offset in the subject string - offsets vector to contain the matching string offsets - offsetcount size of same - workspace vector of workspace - wscount size of same - ims the current ims flags - rlevel function call recursion level - recursing regex recursive call level - -Returns: > 0 => number of match offset pairs placed in offsets - = 0 => offsets overflowed; longest matches are present - -1 => failed to match - < -1 => some kind of unexpected problem - -The following macros are used for adding states to the two state vectors (one -for the current character, one for the following character). */ - -#define ADD_ACTIVE(x,y) \ - if (active_count++ < wscount) \ - { \ - next_active_state->offset = (x); \ - next_active_state->count = (y); \ - next_active_state->ims = ims; \ - next_active_state++; \ - DPRINTF(("%.*sADD_ACTIVE(%d,%d)\n", rlevel*2-2, SP, (x), (y))); \ - } \ - else return PCRE_ERROR_DFA_WSSIZE - -#define ADD_ACTIVE_DATA(x,y,z) \ - if (active_count++ < wscount) \ - { \ - next_active_state->offset = (x); \ - next_active_state->count = (y); \ - next_active_state->ims = ims; \ - next_active_state->data = (z); \ - next_active_state++; \ - DPRINTF(("%.*sADD_ACTIVE_DATA(%d,%d,%d)\n", rlevel*2-2, SP, (x), (y), (z))); \ - } \ - else return PCRE_ERROR_DFA_WSSIZE - -#define ADD_NEW(x,y) \ - if (new_count++ < wscount) \ - { \ - next_new_state->offset = (x); \ - next_new_state->count = (y); \ - next_new_state->ims = ims; \ - next_new_state++; \ - DPRINTF(("%.*sADD_NEW(%d,%d)\n", rlevel*2-2, SP, (x), (y))); \ - } \ - else return PCRE_ERROR_DFA_WSSIZE - -#define ADD_NEW_DATA(x,y,z) \ - if (new_count++ < wscount) \ - { \ - next_new_state->offset = (x); \ - next_new_state->count = (y); \ - next_new_state->ims = ims; \ - next_new_state->data = (z); \ - next_new_state++; \ - DPRINTF(("%.*sADD_NEW_DATA(%d,%d,%d)\n", rlevel*2-2, SP, (x), (y), (z))); \ - } \ - else return PCRE_ERROR_DFA_WSSIZE - -/* And now, here is the code */ - -static int -internal_dfa_exec( - dfa_match_data *md, - const uschar *this_start_code, - const uschar *current_subject, - int start_offset, - int *offsets, - int offsetcount, - int *workspace, - int wscount, - int ims, - int rlevel, - int recursing) -{ -stateblock *active_states, *new_states, *temp_states; -stateblock *next_active_state, *next_new_state; - -const uschar *ctypes, *lcc, *fcc; -const uschar *ptr; -const uschar *end_code, *first_op; - -int active_count, new_count, match_count; - -/* Some fields in the md block are frequently referenced, so we load them into -independent variables in the hope that this will perform better. */ - -const uschar *start_subject = md->start_subject; -const uschar *end_subject = md->end_subject; -const uschar *start_code = md->start_code; - -#ifdef SUPPORT_UTF8 -BOOL utf8 = (md->poptions & PCRE_UTF8) != 0; -#else -BOOL utf8 = FALSE; -#endif - -rlevel++; -offsetcount &= (-2); - -wscount -= 2; -wscount = (wscount - (wscount % (INTS_PER_STATEBLOCK * 2))) / - (2 * INTS_PER_STATEBLOCK); - -DPRINTF(("\n%.*s---------------------\n" - "%.*sCall to internal_dfa_exec f=%d r=%d\n", - rlevel*2-2, SP, rlevel*2-2, SP, rlevel, recursing)); - -ctypes = md->tables + ctypes_offset; -lcc = md->tables + lcc_offset; -fcc = md->tables + fcc_offset; - -match_count = PCRE_ERROR_NOMATCH; /* A negative number */ - -active_states = (stateblock *)(workspace + 2); -next_new_state = new_states = active_states + wscount; -new_count = 0; - -first_op = this_start_code + 1 + LINK_SIZE + - ((*this_start_code == OP_CBRA || *this_start_code == OP_SCBRA)? 2:0); - -/* The first thing in any (sub) pattern is a bracket of some sort. Push all -the alternative states onto the list, and find out where the end is. This -makes is possible to use this function recursively, when we want to stop at a -matching internal ket rather than at the end. - -If the first opcode in the first alternative is OP_REVERSE, we are dealing with -a backward assertion. In that case, we have to find out the maximum amount to -move back, and set up each alternative appropriately. */ - -if (*first_op == OP_REVERSE) - { - int max_back = 0; - int gone_back; - - end_code = this_start_code; - do - { - int back = GET(end_code, 2+LINK_SIZE); - if (back > max_back) max_back = back; - end_code += GET(end_code, 1); - } - while (*end_code == OP_ALT); - - /* If we can't go back the amount required for the longest lookbehind - pattern, go back as far as we can; some alternatives may still be viable. */ - -#ifdef SUPPORT_UTF8 - /* In character mode we have to step back character by character */ - - if (utf8) - { - for (gone_back = 0; gone_back < max_back; gone_back++) - { - if (current_subject <= start_subject) break; - current_subject--; - while (current_subject > start_subject && - (*current_subject & 0xc0) == 0x80) - current_subject--; - } - } - else -#endif - - /* In byte-mode we can do this quickly. */ - - { - gone_back = (current_subject - max_back < start_subject)? - current_subject - start_subject : max_back; - current_subject -= gone_back; - } - - /* Now we can process the individual branches. */ - - end_code = this_start_code; - do - { - int back = GET(end_code, 2+LINK_SIZE); - if (back <= gone_back) - { - int bstate = end_code - start_code + 2 + 2*LINK_SIZE; - ADD_NEW_DATA(-bstate, 0, gone_back - back); - } - end_code += GET(end_code, 1); - } - while (*end_code == OP_ALT); - } - -/* This is the code for a "normal" subpattern (not a backward assertion). The -start of a whole pattern is always one of these. If we are at the top level, -we may be asked to restart matching from the same point that we reached for a -previous partial match. We still have to scan through the top-level branches to -find the end state. */ - -else - { - end_code = this_start_code; - - /* Restarting */ - - if (rlevel == 1 && (md->moptions & PCRE_DFA_RESTART) != 0) - { - do { end_code += GET(end_code, 1); } while (*end_code == OP_ALT); - new_count = workspace[1]; - if (!workspace[0]) - memcpy(new_states, active_states, new_count * sizeof(stateblock)); - } - - /* Not restarting */ - - else - { - int length = 1 + LINK_SIZE + - ((*this_start_code == OP_CBRA || *this_start_code == OP_SCBRA)? 2:0); - do - { - ADD_NEW(end_code - start_code + length, 0); - end_code += GET(end_code, 1); - length = 1 + LINK_SIZE; - } - while (*end_code == OP_ALT); - } - } - -workspace[0] = 0; /* Bit indicating which vector is current */ - -DPRINTF(("%.*sEnd state = %d\n", rlevel*2-2, SP, end_code - start_code)); - -/* Loop for scanning the subject */ - -ptr = current_subject; -for (;;) - { - int i, j; - int clen, dlen; - unsigned int c, d; - - /* Make the new state list into the active state list and empty the - new state list. */ - - temp_states = active_states; - active_states = new_states; - new_states = temp_states; - active_count = new_count; - new_count = 0; - - workspace[0] ^= 1; /* Remember for the restarting feature */ - workspace[1] = active_count; - -#ifdef PCRE_DEBUG - printf("%.*sNext character: rest of subject = \"", rlevel*2-2, SP); - pchars((uschar *)ptr, strlen((char *)ptr), stdout); - printf("\"\n"); - - printf("%.*sActive states: ", rlevel*2-2, SP); - for (i = 0; i < active_count; i++) - printf("%d/%d ", active_states[i].offset, active_states[i].count); - printf("\n"); -#endif - - /* Set the pointers for adding new states */ - - next_active_state = active_states + active_count; - next_new_state = new_states; - - /* Load the current character from the subject outside the loop, as many - different states may want to look at it, and we assume that at least one - will. */ - - if (ptr < end_subject) - { - clen = 1; /* Number of bytes in the character */ -#ifdef SUPPORT_UTF8 - if (utf8) { GETCHARLEN(c, ptr, clen); } else -#endif /* SUPPORT_UTF8 */ - c = *ptr; - } - else - { - clen = 0; /* This indicates the end of the subject */ - c = NOTACHAR; /* This value should never actually be used */ - } - - /* Scan up the active states and act on each one. The result of an action - may be to add more states to the currently active list (e.g. on hitting a - parenthesis) or it may be to put states on the new list, for considering - when we move the character pointer on. */ - - for (i = 0; i < active_count; i++) - { - stateblock *current_state = active_states + i; - const uschar *code; - int state_offset = current_state->offset; - int count, codevalue, rrc; - -#ifdef PCRE_DEBUG - printf ("%.*sProcessing state %d c=", rlevel*2-2, SP, state_offset); - if (clen == 0) printf("EOL\n"); - else if (c > 32 && c < 127) printf("'%c'\n", c); - else printf("0x%02x\n", c); -#endif - - /* This variable is referred to implicity in the ADD_xxx macros. */ - - ims = current_state->ims; - - /* A negative offset is a special case meaning "hold off going to this - (negated) state until the number of characters in the data field have - been skipped". */ - - if (state_offset < 0) - { - if (current_state->data > 0) - { - DPRINTF(("%.*sSkipping this character\n", rlevel*2-2, SP)); - ADD_NEW_DATA(state_offset, current_state->count, - current_state->data - 1); - continue; - } - else - { - current_state->offset = state_offset = -state_offset; - } - } - - /* Check for a duplicate state with the same count, and skip if found. */ - - for (j = 0; j < i; j++) - { - if (active_states[j].offset == state_offset && - active_states[j].count == current_state->count) - { - DPRINTF(("%.*sDuplicate state: skipped\n", rlevel*2-2, SP)); - goto NEXT_ACTIVE_STATE; - } - } - - /* The state offset is the offset to the opcode */ - - code = start_code + state_offset; - codevalue = *code; - - /* If this opcode is followed by an inline character, load it. It is - tempting to test for the presence of a subject character here, but that - is wrong, because sometimes zero repetitions of the subject are - permitted. - - We also use this mechanism for opcodes such as OP_TYPEPLUS that take an - argument that is not a data character - but is always one byte long. We - have to take special action to deal with \P, \p, \H, \h, \V, \v and \X in - this case. To keep the other cases fast, convert these ones to new opcodes. - */ - - if (coptable[codevalue] > 0) - { - dlen = 1; -#ifdef SUPPORT_UTF8 - if (utf8) { GETCHARLEN(d, (code + coptable[codevalue]), dlen); } else -#endif /* SUPPORT_UTF8 */ - d = code[coptable[codevalue]]; - if (codevalue >= OP_TYPESTAR) - { - switch(d) - { - case OP_ANYBYTE: return PCRE_ERROR_DFA_UITEM; - case OP_NOTPROP: - case OP_PROP: codevalue += OP_PROP_EXTRA; break; - case OP_ANYNL: codevalue += OP_ANYNL_EXTRA; break; - case OP_EXTUNI: codevalue += OP_EXTUNI_EXTRA; break; - case OP_NOT_HSPACE: - case OP_HSPACE: codevalue += OP_HSPACE_EXTRA; break; - case OP_NOT_VSPACE: - case OP_VSPACE: codevalue += OP_VSPACE_EXTRA; break; - default: break; - } - } - } - else - { - dlen = 0; /* Not strictly necessary, but compilers moan */ - d = NOTACHAR; /* if these variables are not set. */ - } - - - /* Now process the individual opcodes */ - - switch (codevalue) - { - -/* ========================================================================== */ - /* Reached a closing bracket. If not at the end of the pattern, carry - on with the next opcode. Otherwise, unless we have an empty string and - PCRE_NOTEMPTY is set, save the match data, shifting up all previous - matches so we always have the longest first. */ - - case OP_KET: - case OP_KETRMIN: - case OP_KETRMAX: - if (code != end_code) - { - ADD_ACTIVE(state_offset + 1 + LINK_SIZE, 0); - if (codevalue != OP_KET) - { - ADD_ACTIVE(state_offset - GET(code, 1), 0); - } - } - else if (ptr > current_subject || (md->moptions & PCRE_NOTEMPTY) == 0) - { - if (match_count < 0) match_count = (offsetcount >= 2)? 1 : 0; - else if (match_count > 0 && ++match_count * 2 >= offsetcount) - match_count = 0; - count = ((match_count == 0)? offsetcount : match_count * 2) - 2; - if (count > 0) memmove(offsets + 2, offsets, count * sizeof(int)); - if (offsetcount >= 2) - { - offsets[0] = current_subject - start_subject; - offsets[1] = ptr - start_subject; - DPRINTF(("%.*sSet matched string = \"%.*s\"\n", rlevel*2-2, SP, - offsets[1] - offsets[0], current_subject)); - } - if ((md->moptions & PCRE_DFA_SHORTEST) != 0) - { - DPRINTF(("%.*sEnd of internal_dfa_exec %d: returning %d\n" - "%.*s---------------------\n\n", rlevel*2-2, SP, rlevel, - match_count, rlevel*2-2, SP)); - return match_count; - } - } - break; - -/* ========================================================================== */ - /* These opcodes add to the current list of states without looking - at the current character. */ - - /*-----------------------------------------------------------------*/ - case OP_ALT: - do { code += GET(code, 1); } while (*code == OP_ALT); - ADD_ACTIVE(code - start_code, 0); - break; - - /*-----------------------------------------------------------------*/ - case OP_BRA: - case OP_SBRA: - do - { - ADD_ACTIVE(code - start_code + 1 + LINK_SIZE, 0); - code += GET(code, 1); - } - while (*code == OP_ALT); - break; - - /*-----------------------------------------------------------------*/ - case OP_CBRA: - case OP_SCBRA: - ADD_ACTIVE(code - start_code + 3 + LINK_SIZE, 0); - code += GET(code, 1); - while (*code == OP_ALT) - { - ADD_ACTIVE(code - start_code + 1 + LINK_SIZE, 0); - code += GET(code, 1); - } - break; - - /*-----------------------------------------------------------------*/ - case OP_BRAZERO: - case OP_BRAMINZERO: - ADD_ACTIVE(state_offset + 1, 0); - code += 1 + GET(code, 2); - while (*code == OP_ALT) code += GET(code, 1); - ADD_ACTIVE(code - start_code + 1 + LINK_SIZE, 0); - break; - - /*-----------------------------------------------------------------*/ - case OP_SKIPZERO: - code += 1 + GET(code, 2); - while (*code == OP_ALT) code += GET(code, 1); - ADD_ACTIVE(code - start_code + 1 + LINK_SIZE, 0); - break; - - /*-----------------------------------------------------------------*/ - case OP_CIRC: - if ((ptr == start_subject && (md->moptions & PCRE_NOTBOL) == 0) || - ((ims & PCRE_MULTILINE) != 0 && - ptr != end_subject && - WAS_NEWLINE(ptr))) - { ADD_ACTIVE(state_offset + 1, 0); } - break; - - /*-----------------------------------------------------------------*/ - case OP_EOD: - if (ptr >= end_subject) { ADD_ACTIVE(state_offset + 1, 0); } - break; - - /*-----------------------------------------------------------------*/ - case OP_OPT: - ims = code[1]; - ADD_ACTIVE(state_offset + 2, 0); - break; - - /*-----------------------------------------------------------------*/ - case OP_SOD: - if (ptr == start_subject) { ADD_ACTIVE(state_offset + 1, 0); } - break; - - /*-----------------------------------------------------------------*/ - case OP_SOM: - if (ptr == start_subject + start_offset) { ADD_ACTIVE(state_offset + 1, 0); } - break; - - -/* ========================================================================== */ - /* These opcodes inspect the next subject character, and sometimes - the previous one as well, but do not have an argument. The variable - clen contains the length of the current character and is zero if we are - at the end of the subject. */ - - /*-----------------------------------------------------------------*/ - case OP_ANY: - if (clen > 0 && !IS_NEWLINE(ptr)) - { ADD_NEW(state_offset + 1, 0); } - break; - - /*-----------------------------------------------------------------*/ - case OP_ALLANY: - if (clen > 0) - { ADD_NEW(state_offset + 1, 0); } - break; - - /*-----------------------------------------------------------------*/ - case OP_EODN: - if (clen == 0 || (IS_NEWLINE(ptr) && ptr == end_subject - md->nllen)) - { ADD_ACTIVE(state_offset + 1, 0); } - break; - - /*-----------------------------------------------------------------*/ - case OP_DOLL: - if ((md->moptions & PCRE_NOTEOL) == 0) - { - if (clen == 0 || - ((md->poptions & PCRE_DOLLAR_ENDONLY) == 0 && IS_NEWLINE(ptr) && - ((ims & PCRE_MULTILINE) != 0 || ptr == end_subject - md->nllen) - )) - { ADD_ACTIVE(state_offset + 1, 0); } - } - else if ((ims & PCRE_MULTILINE) != 0 && IS_NEWLINE(ptr)) - { ADD_ACTIVE(state_offset + 1, 0); } - break; - - /*-----------------------------------------------------------------*/ - - case OP_DIGIT: - case OP_WHITESPACE: - case OP_WORDCHAR: - if (clen > 0 && c < 256 && - ((ctypes[c] & toptable1[codevalue]) ^ toptable2[codevalue]) != 0) - { ADD_NEW(state_offset + 1, 0); } - break; - - /*-----------------------------------------------------------------*/ - case OP_NOT_DIGIT: - case OP_NOT_WHITESPACE: - case OP_NOT_WORDCHAR: - if (clen > 0 && (c >= 256 || - ((ctypes[c] & toptable1[codevalue]) ^ toptable2[codevalue]) != 0)) - { ADD_NEW(state_offset + 1, 0); } - break; - - /*-----------------------------------------------------------------*/ - case OP_WORD_BOUNDARY: - case OP_NOT_WORD_BOUNDARY: - { - int left_word, right_word; - - if (ptr > start_subject) - { - const uschar *temp = ptr - 1; -#ifdef SUPPORT_UTF8 - if (utf8) BACKCHAR(temp); -#endif - GETCHARTEST(d, temp); - left_word = d < 256 && (ctypes[d] & ctype_word) != 0; - } - else left_word = 0; - - if (clen > 0) right_word = c < 256 && (ctypes[c] & ctype_word) != 0; - else right_word = 0; - - if ((left_word == right_word) == (codevalue == OP_NOT_WORD_BOUNDARY)) - { ADD_ACTIVE(state_offset + 1, 0); } - } - break; - - - /*-----------------------------------------------------------------*/ - /* Check the next character by Unicode property. We will get here only - if the support is in the binary; otherwise a compile-time error occurs. - */ - -#ifdef SUPPORT_UCP - case OP_PROP: - case OP_NOTPROP: - if (clen > 0) - { - BOOL OK; - const ucd_record * prop = GET_UCD(c); - switch(code[1]) - { - case PT_ANY: - OK = TRUE; - break; - - case PT_LAMP: - OK = prop->chartype == ucp_Lu || prop->chartype == ucp_Ll || prop->chartype == ucp_Lt; - break; - - case PT_GC: - OK = _pcre_ucp_gentype[prop->chartype] == code[2]; - break; - - case PT_PC: - OK = prop->chartype == code[2]; - break; - - case PT_SC: - OK = prop->script == code[2]; - break; - - /* Should never occur, but keep compilers from grumbling. */ - - default: - OK = codevalue != OP_PROP; - break; - } - - if (OK == (codevalue == OP_PROP)) { ADD_NEW(state_offset + 3, 0); } - } - break; -#endif - - - -/* ========================================================================== */ - /* These opcodes likewise inspect the subject character, but have an - argument that is not a data character. It is one of these opcodes: - OP_ANY, OP_ALLANY, OP_DIGIT, OP_NOT_DIGIT, OP_WHITESPACE, OP_NOT_SPACE, - OP_WORDCHAR, OP_NOT_WORDCHAR. The value is loaded into d. */ - - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEPOSPLUS: - count = current_state->count; /* Already matched */ - if (count > 0) { ADD_ACTIVE(state_offset + 2, 0); } - if (clen > 0) - { - if ((c >= 256 && d != OP_DIGIT && d != OP_WHITESPACE && d != OP_WORDCHAR) || - (c < 256 && - (d != OP_ANY || !IS_NEWLINE(ptr)) && - ((ctypes[c] & toptable1[d]) ^ toptable2[d]) != 0)) - { - if (count > 0 && codevalue == OP_TYPEPOSPLUS) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - count++; - ADD_NEW(state_offset, count); - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - case OP_TYPEPOSQUERY: - ADD_ACTIVE(state_offset + 2, 0); - if (clen > 0) - { - if ((c >= 256 && d != OP_DIGIT && d != OP_WHITESPACE && d != OP_WORDCHAR) || - (c < 256 && - (d != OP_ANY || !IS_NEWLINE(ptr)) && - ((ctypes[c] & toptable1[d]) ^ toptable2[d]) != 0)) - { - if (codevalue == OP_TYPEPOSQUERY) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - ADD_NEW(state_offset + 2, 0); - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPOSSTAR: - ADD_ACTIVE(state_offset + 2, 0); - if (clen > 0) - { - if ((c >= 256 && d != OP_DIGIT && d != OP_WHITESPACE && d != OP_WORDCHAR) || - (c < 256 && - (d != OP_ANY || !IS_NEWLINE(ptr)) && - ((ctypes[c] & toptable1[d]) ^ toptable2[d]) != 0)) - { - if (codevalue == OP_TYPEPOSSTAR) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - ADD_NEW(state_offset, 0); - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_TYPEEXACT: - count = current_state->count; /* Number already matched */ - if (clen > 0) - { - if ((c >= 256 && d != OP_DIGIT && d != OP_WHITESPACE && d != OP_WORDCHAR) || - (c < 256 && - (d != OP_ANY || !IS_NEWLINE(ptr)) && - ((ctypes[c] & toptable1[d]) ^ toptable2[d]) != 0)) - { - if (++count >= GET2(code, 1)) - { ADD_NEW(state_offset + 4, 0); } - else - { ADD_NEW(state_offset, count); } - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - case OP_TYPEPOSUPTO: - ADD_ACTIVE(state_offset + 4, 0); - count = current_state->count; /* Number already matched */ - if (clen > 0) - { - if ((c >= 256 && d != OP_DIGIT && d != OP_WHITESPACE && d != OP_WORDCHAR) || - (c < 256 && - (d != OP_ANY || !IS_NEWLINE(ptr)) && - ((ctypes[c] & toptable1[d]) ^ toptable2[d]) != 0)) - { - if (codevalue == OP_TYPEPOSUPTO) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - if (++count >= GET2(code, 1)) - { ADD_NEW(state_offset + 4, 0); } - else - { ADD_NEW(state_offset, count); } - } - } - break; - -/* ========================================================================== */ - /* These are virtual opcodes that are used when something like - OP_TYPEPLUS has OP_PROP, OP_NOTPROP, OP_ANYNL, or OP_EXTUNI as its - argument. It keeps the code above fast for the other cases. The argument - is in the d variable. */ - -#ifdef SUPPORT_UCP - case OP_PROP_EXTRA + OP_TYPEPLUS: - case OP_PROP_EXTRA + OP_TYPEMINPLUS: - case OP_PROP_EXTRA + OP_TYPEPOSPLUS: - count = current_state->count; /* Already matched */ - if (count > 0) { ADD_ACTIVE(state_offset + 4, 0); } - if (clen > 0) - { - BOOL OK; - const ucd_record * prop = GET_UCD(c); - switch(code[2]) - { - case PT_ANY: - OK = TRUE; - break; - - case PT_LAMP: - OK = prop->chartype == ucp_Lu || prop->chartype == ucp_Ll || prop->chartype == ucp_Lt; - break; - - case PT_GC: - OK = _pcre_ucp_gentype[prop->chartype] == code[3]; - break; - - case PT_PC: - OK = prop->chartype == code[3]; - break; - - case PT_SC: - OK = prop->script == code[3]; - break; - - /* Should never occur, but keep compilers from grumbling. */ - - default: - OK = codevalue != OP_PROP; - break; - } - - if (OK == (d == OP_PROP)) - { - if (count > 0 && codevalue == OP_PROP_EXTRA + OP_TYPEPOSPLUS) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - count++; - ADD_NEW(state_offset, count); - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_EXTUNI_EXTRA + OP_TYPEPLUS: - case OP_EXTUNI_EXTRA + OP_TYPEMINPLUS: - case OP_EXTUNI_EXTRA + OP_TYPEPOSPLUS: - count = current_state->count; /* Already matched */ - if (count > 0) { ADD_ACTIVE(state_offset + 2, 0); } - if (clen > 0 && UCD_CATEGORY(c) != ucp_M) - { - const uschar *nptr = ptr + clen; - int ncount = 0; - if (count > 0 && codevalue == OP_EXTUNI_EXTRA + OP_TYPEPOSPLUS) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - while (nptr < end_subject) - { - int nd; - int ndlen = 1; - GETCHARLEN(nd, nptr, ndlen); - if (UCD_CATEGORY(nd) != ucp_M) break; - ncount++; - nptr += ndlen; - } - count++; - ADD_NEW_DATA(-state_offset, count, ncount); - } - break; -#endif - - /*-----------------------------------------------------------------*/ - case OP_ANYNL_EXTRA + OP_TYPEPLUS: - case OP_ANYNL_EXTRA + OP_TYPEMINPLUS: - case OP_ANYNL_EXTRA + OP_TYPEPOSPLUS: - count = current_state->count; /* Already matched */ - if (count > 0) { ADD_ACTIVE(state_offset + 2, 0); } - if (clen > 0) - { - int ncount = 0; - switch (c) - { - case 0x000b: - case 0x000c: - case 0x0085: - case 0x2028: - case 0x2029: - if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break; - goto ANYNL01; - - case 0x000d: - if (ptr + 1 < end_subject && ptr[1] == 0x0a) ncount = 1; - /* Fall through */ - - ANYNL01: - case 0x000a: - if (count > 0 && codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSPLUS) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - count++; - ADD_NEW_DATA(-state_offset, count, ncount); - break; - - default: - break; - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_VSPACE_EXTRA + OP_TYPEPLUS: - case OP_VSPACE_EXTRA + OP_TYPEMINPLUS: - case OP_VSPACE_EXTRA + OP_TYPEPOSPLUS: - count = current_state->count; /* Already matched */ - if (count > 0) { ADD_ACTIVE(state_offset + 2, 0); } - if (clen > 0) - { - BOOL OK; - switch (c) - { - case 0x000a: - case 0x000b: - case 0x000c: - case 0x000d: - case 0x0085: - case 0x2028: - case 0x2029: - OK = TRUE; - break; - - default: - OK = FALSE; - break; - } - - if (OK == (d == OP_VSPACE)) - { - if (count > 0 && codevalue == OP_VSPACE_EXTRA + OP_TYPEPOSPLUS) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - count++; - ADD_NEW_DATA(-state_offset, count, 0); - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_HSPACE_EXTRA + OP_TYPEPLUS: - case OP_HSPACE_EXTRA + OP_TYPEMINPLUS: - case OP_HSPACE_EXTRA + OP_TYPEPOSPLUS: - count = current_state->count; /* Already matched */ - if (count > 0) { ADD_ACTIVE(state_offset + 2, 0); } - if (clen > 0) - { - BOOL OK; - switch (c) - { - case 0x09: /* HT */ - case 0x20: /* SPACE */ - case 0xa0: /* NBSP */ - case 0x1680: /* OGHAM SPACE MARK */ - case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ - case 0x2000: /* EN QUAD */ - case 0x2001: /* EM QUAD */ - case 0x2002: /* EN SPACE */ - case 0x2003: /* EM SPACE */ - case 0x2004: /* THREE-PER-EM SPACE */ - case 0x2005: /* FOUR-PER-EM SPACE */ - case 0x2006: /* SIX-PER-EM SPACE */ - case 0x2007: /* FIGURE SPACE */ - case 0x2008: /* PUNCTUATION SPACE */ - case 0x2009: /* THIN SPACE */ - case 0x200A: /* HAIR SPACE */ - case 0x202f: /* NARROW NO-BREAK SPACE */ - case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ - case 0x3000: /* IDEOGRAPHIC SPACE */ - OK = TRUE; - break; - - default: - OK = FALSE; - break; - } - - if (OK == (d == OP_HSPACE)) - { - if (count > 0 && codevalue == OP_HSPACE_EXTRA + OP_TYPEPOSPLUS) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - count++; - ADD_NEW_DATA(-state_offset, count, 0); - } - } - break; - - /*-----------------------------------------------------------------*/ -#ifdef SUPPORT_UCP - case OP_PROP_EXTRA + OP_TYPEQUERY: - case OP_PROP_EXTRA + OP_TYPEMINQUERY: - case OP_PROP_EXTRA + OP_TYPEPOSQUERY: - count = 4; - goto QS1; - - case OP_PROP_EXTRA + OP_TYPESTAR: - case OP_PROP_EXTRA + OP_TYPEMINSTAR: - case OP_PROP_EXTRA + OP_TYPEPOSSTAR: - count = 0; - - QS1: - - ADD_ACTIVE(state_offset + 4, 0); - if (clen > 0) - { - BOOL OK; - const ucd_record * prop = GET_UCD(c); - switch(code[2]) - { - case PT_ANY: - OK = TRUE; - break; - - case PT_LAMP: - OK = prop->chartype == ucp_Lu || prop->chartype == ucp_Ll || prop->chartype == ucp_Lt; - break; - - case PT_GC: - OK = _pcre_ucp_gentype[prop->chartype] == code[3]; - break; - - case PT_PC: - OK = prop->chartype == code[3]; - break; - - case PT_SC: - OK = prop->script == code[3]; - break; - - /* Should never occur, but keep compilers from grumbling. */ - - default: - OK = codevalue != OP_PROP; - break; - } - - if (OK == (d == OP_PROP)) - { - if (codevalue == OP_PROP_EXTRA + OP_TYPEPOSSTAR || - codevalue == OP_PROP_EXTRA + OP_TYPEPOSQUERY) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - ADD_NEW(state_offset + count, 0); - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_EXTUNI_EXTRA + OP_TYPEQUERY: - case OP_EXTUNI_EXTRA + OP_TYPEMINQUERY: - case OP_EXTUNI_EXTRA + OP_TYPEPOSQUERY: - count = 2; - goto QS2; - - case OP_EXTUNI_EXTRA + OP_TYPESTAR: - case OP_EXTUNI_EXTRA + OP_TYPEMINSTAR: - case OP_EXTUNI_EXTRA + OP_TYPEPOSSTAR: - count = 0; - - QS2: - - ADD_ACTIVE(state_offset + 2, 0); - if (clen > 0 && UCD_CATEGORY(c) != ucp_M) - { - const uschar *nptr = ptr + clen; - int ncount = 0; - if (codevalue == OP_EXTUNI_EXTRA + OP_TYPEPOSSTAR || - codevalue == OP_EXTUNI_EXTRA + OP_TYPEPOSQUERY) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - while (nptr < end_subject) - { - int nd; - int ndlen = 1; - GETCHARLEN(nd, nptr, ndlen); - if (UCD_CATEGORY(nd) != ucp_M) break; - ncount++; - nptr += ndlen; - } - ADD_NEW_DATA(-(state_offset + count), 0, ncount); - } - break; -#endif - - /*-----------------------------------------------------------------*/ - case OP_ANYNL_EXTRA + OP_TYPEQUERY: - case OP_ANYNL_EXTRA + OP_TYPEMINQUERY: - case OP_ANYNL_EXTRA + OP_TYPEPOSQUERY: - count = 2; - goto QS3; - - case OP_ANYNL_EXTRA + OP_TYPESTAR: - case OP_ANYNL_EXTRA + OP_TYPEMINSTAR: - case OP_ANYNL_EXTRA + OP_TYPEPOSSTAR: - count = 0; - - QS3: - ADD_ACTIVE(state_offset + 2, 0); - if (clen > 0) - { - int ncount = 0; - switch (c) - { - case 0x000b: - case 0x000c: - case 0x0085: - case 0x2028: - case 0x2029: - if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break; - goto ANYNL02; - - case 0x000d: - if (ptr + 1 < end_subject && ptr[1] == 0x0a) ncount = 1; - /* Fall through */ - - ANYNL02: - case 0x000a: - if (codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSSTAR || - codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSQUERY) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - ADD_NEW_DATA(-(state_offset + count), 0, ncount); - break; - - default: - break; - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_VSPACE_EXTRA + OP_TYPEQUERY: - case OP_VSPACE_EXTRA + OP_TYPEMINQUERY: - case OP_VSPACE_EXTRA + OP_TYPEPOSQUERY: - count = 2; - goto QS4; - - case OP_VSPACE_EXTRA + OP_TYPESTAR: - case OP_VSPACE_EXTRA + OP_TYPEMINSTAR: - case OP_VSPACE_EXTRA + OP_TYPEPOSSTAR: - count = 0; - - QS4: - ADD_ACTIVE(state_offset + 2, 0); - if (clen > 0) - { - BOOL OK; - switch (c) - { - case 0x000a: - case 0x000b: - case 0x000c: - case 0x000d: - case 0x0085: - case 0x2028: - case 0x2029: - OK = TRUE; - break; - - default: - OK = FALSE; - break; - } - if (OK == (d == OP_VSPACE)) - { - if (codevalue == OP_VSPACE_EXTRA + OP_TYPEPOSSTAR || - codevalue == OP_VSPACE_EXTRA + OP_TYPEPOSQUERY) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - ADD_NEW_DATA(-(state_offset + count), 0, 0); - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_HSPACE_EXTRA + OP_TYPEQUERY: - case OP_HSPACE_EXTRA + OP_TYPEMINQUERY: - case OP_HSPACE_EXTRA + OP_TYPEPOSQUERY: - count = 2; - goto QS5; - - case OP_HSPACE_EXTRA + OP_TYPESTAR: - case OP_HSPACE_EXTRA + OP_TYPEMINSTAR: - case OP_HSPACE_EXTRA + OP_TYPEPOSSTAR: - count = 0; - - QS5: - ADD_ACTIVE(state_offset + 2, 0); - if (clen > 0) - { - BOOL OK; - switch (c) - { - case 0x09: /* HT */ - case 0x20: /* SPACE */ - case 0xa0: /* NBSP */ - case 0x1680: /* OGHAM SPACE MARK */ - case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ - case 0x2000: /* EN QUAD */ - case 0x2001: /* EM QUAD */ - case 0x2002: /* EN SPACE */ - case 0x2003: /* EM SPACE */ - case 0x2004: /* THREE-PER-EM SPACE */ - case 0x2005: /* FOUR-PER-EM SPACE */ - case 0x2006: /* SIX-PER-EM SPACE */ - case 0x2007: /* FIGURE SPACE */ - case 0x2008: /* PUNCTUATION SPACE */ - case 0x2009: /* THIN SPACE */ - case 0x200A: /* HAIR SPACE */ - case 0x202f: /* NARROW NO-BREAK SPACE */ - case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ - case 0x3000: /* IDEOGRAPHIC SPACE */ - OK = TRUE; - break; - - default: - OK = FALSE; - break; - } - - if (OK == (d == OP_HSPACE)) - { - if (codevalue == OP_HSPACE_EXTRA + OP_TYPEPOSSTAR || - codevalue == OP_HSPACE_EXTRA + OP_TYPEPOSQUERY) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - ADD_NEW_DATA(-(state_offset + count), 0, 0); - } - } - break; - - /*-----------------------------------------------------------------*/ -#ifdef SUPPORT_UCP - case OP_PROP_EXTRA + OP_TYPEEXACT: - case OP_PROP_EXTRA + OP_TYPEUPTO: - case OP_PROP_EXTRA + OP_TYPEMINUPTO: - case OP_PROP_EXTRA + OP_TYPEPOSUPTO: - if (codevalue != OP_PROP_EXTRA + OP_TYPEEXACT) - { ADD_ACTIVE(state_offset + 6, 0); } - count = current_state->count; /* Number already matched */ - if (clen > 0) - { - BOOL OK; - const ucd_record * prop = GET_UCD(c); - switch(code[4]) - { - case PT_ANY: - OK = TRUE; - break; - - case PT_LAMP: - OK = prop->chartype == ucp_Lu || prop->chartype == ucp_Ll || prop->chartype == ucp_Lt; - break; - - case PT_GC: - OK = _pcre_ucp_gentype[prop->chartype] == code[5]; - break; - - case PT_PC: - OK = prop->chartype == code[5]; - break; - - case PT_SC: - OK = prop->script == code[5]; - break; - - /* Should never occur, but keep compilers from grumbling. */ - - default: - OK = codevalue != OP_PROP; - break; - } - - if (OK == (d == OP_PROP)) - { - if (codevalue == OP_PROP_EXTRA + OP_TYPEPOSUPTO) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - if (++count >= GET2(code, 1)) - { ADD_NEW(state_offset + 6, 0); } - else - { ADD_NEW(state_offset, count); } - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_EXTUNI_EXTRA + OP_TYPEEXACT: - case OP_EXTUNI_EXTRA + OP_TYPEUPTO: - case OP_EXTUNI_EXTRA + OP_TYPEMINUPTO: - case OP_EXTUNI_EXTRA + OP_TYPEPOSUPTO: - if (codevalue != OP_EXTUNI_EXTRA + OP_TYPEEXACT) - { ADD_ACTIVE(state_offset + 4, 0); } - count = current_state->count; /* Number already matched */ - if (clen > 0 && UCD_CATEGORY(c) != ucp_M) - { - const uschar *nptr = ptr + clen; - int ncount = 0; - if (codevalue == OP_EXTUNI_EXTRA + OP_TYPEPOSUPTO) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - while (nptr < end_subject) - { - int nd; - int ndlen = 1; - GETCHARLEN(nd, nptr, ndlen); - if (UCD_CATEGORY(nd) != ucp_M) break; - ncount++; - nptr += ndlen; - } - if (++count >= GET2(code, 1)) - { ADD_NEW_DATA(-(state_offset + 4), 0, ncount); } - else - { ADD_NEW_DATA(-state_offset, count, ncount); } - } - break; -#endif - - /*-----------------------------------------------------------------*/ - case OP_ANYNL_EXTRA + OP_TYPEEXACT: - case OP_ANYNL_EXTRA + OP_TYPEUPTO: - case OP_ANYNL_EXTRA + OP_TYPEMINUPTO: - case OP_ANYNL_EXTRA + OP_TYPEPOSUPTO: - if (codevalue != OP_ANYNL_EXTRA + OP_TYPEEXACT) - { ADD_ACTIVE(state_offset + 4, 0); } - count = current_state->count; /* Number already matched */ - if (clen > 0) - { - int ncount = 0; - switch (c) - { - case 0x000b: - case 0x000c: - case 0x0085: - case 0x2028: - case 0x2029: - if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break; - goto ANYNL03; - - case 0x000d: - if (ptr + 1 < end_subject && ptr[1] == 0x0a) ncount = 1; - /* Fall through */ - - ANYNL03: - case 0x000a: - if (codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSUPTO) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - if (++count >= GET2(code, 1)) - { ADD_NEW_DATA(-(state_offset + 4), 0, ncount); } - else - { ADD_NEW_DATA(-state_offset, count, ncount); } - break; - - default: - break; - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_VSPACE_EXTRA + OP_TYPEEXACT: - case OP_VSPACE_EXTRA + OP_TYPEUPTO: - case OP_VSPACE_EXTRA + OP_TYPEMINUPTO: - case OP_VSPACE_EXTRA + OP_TYPEPOSUPTO: - if (codevalue != OP_VSPACE_EXTRA + OP_TYPEEXACT) - { ADD_ACTIVE(state_offset + 4, 0); } - count = current_state->count; /* Number already matched */ - if (clen > 0) - { - BOOL OK; - switch (c) - { - case 0x000a: - case 0x000b: - case 0x000c: - case 0x000d: - case 0x0085: - case 0x2028: - case 0x2029: - OK = TRUE; - break; - - default: - OK = FALSE; - } - - if (OK == (d == OP_VSPACE)) - { - if (codevalue == OP_VSPACE_EXTRA + OP_TYPEPOSUPTO) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - if (++count >= GET2(code, 1)) - { ADD_NEW_DATA(-(state_offset + 4), 0, 0); } - else - { ADD_NEW_DATA(-state_offset, count, 0); } - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_HSPACE_EXTRA + OP_TYPEEXACT: - case OP_HSPACE_EXTRA + OP_TYPEUPTO: - case OP_HSPACE_EXTRA + OP_TYPEMINUPTO: - case OP_HSPACE_EXTRA + OP_TYPEPOSUPTO: - if (codevalue != OP_HSPACE_EXTRA + OP_TYPEEXACT) - { ADD_ACTIVE(state_offset + 4, 0); } - count = current_state->count; /* Number already matched */ - if (clen > 0) - { - BOOL OK; - switch (c) - { - case 0x09: /* HT */ - case 0x20: /* SPACE */ - case 0xa0: /* NBSP */ - case 0x1680: /* OGHAM SPACE MARK */ - case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ - case 0x2000: /* EN QUAD */ - case 0x2001: /* EM QUAD */ - case 0x2002: /* EN SPACE */ - case 0x2003: /* EM SPACE */ - case 0x2004: /* THREE-PER-EM SPACE */ - case 0x2005: /* FOUR-PER-EM SPACE */ - case 0x2006: /* SIX-PER-EM SPACE */ - case 0x2007: /* FIGURE SPACE */ - case 0x2008: /* PUNCTUATION SPACE */ - case 0x2009: /* THIN SPACE */ - case 0x200A: /* HAIR SPACE */ - case 0x202f: /* NARROW NO-BREAK SPACE */ - case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ - case 0x3000: /* IDEOGRAPHIC SPACE */ - OK = TRUE; - break; - - default: - OK = FALSE; - break; - } - - if (OK == (d == OP_HSPACE)) - { - if (codevalue == OP_HSPACE_EXTRA + OP_TYPEPOSUPTO) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - if (++count >= GET2(code, 1)) - { ADD_NEW_DATA(-(state_offset + 4), 0, 0); } - else - { ADD_NEW_DATA(-state_offset, count, 0); } - } - } - break; - -/* ========================================================================== */ - /* These opcodes are followed by a character that is usually compared - to the current subject character; it is loaded into d. We still get - here even if there is no subject character, because in some cases zero - repetitions are permitted. */ - - /*-----------------------------------------------------------------*/ - case OP_CHAR: - if (clen > 0 && c == d) { ADD_NEW(state_offset + dlen + 1, 0); } - break; - - /*-----------------------------------------------------------------*/ - case OP_CHARNC: - if (clen == 0) break; - -#ifdef SUPPORT_UTF8 - if (utf8) - { - if (c == d) { ADD_NEW(state_offset + dlen + 1, 0); } else - { - unsigned int othercase; - if (c < 128) othercase = fcc[c]; else - - /* If we have Unicode property support, we can use it to test the - other case of the character. */ - -#ifdef SUPPORT_UCP - othercase = UCD_OTHERCASE(c); -#else - othercase = NOTACHAR; -#endif - - if (d == othercase) { ADD_NEW(state_offset + dlen + 1, 0); } - } - } - else -#endif /* SUPPORT_UTF8 */ - - /* Non-UTF-8 mode */ - { - if (lcc[c] == lcc[d]) { ADD_NEW(state_offset + 2, 0); } - } - break; - - -#ifdef SUPPORT_UCP - /*-----------------------------------------------------------------*/ - /* This is a tricky one because it can match more than one character. - Find out how many characters to skip, and then set up a negative state - to wait for them to pass before continuing. */ - - case OP_EXTUNI: - if (clen > 0 && UCD_CATEGORY(c) != ucp_M) - { - const uschar *nptr = ptr + clen; - int ncount = 0; - while (nptr < end_subject) - { - int nclen = 1; - GETCHARLEN(c, nptr, nclen); - if (UCD_CATEGORY(c) != ucp_M) break; - ncount++; - nptr += nclen; - } - ADD_NEW_DATA(-(state_offset + 1), 0, ncount); - } - break; -#endif - - /*-----------------------------------------------------------------*/ - /* This is a tricky like EXTUNI because it too can match more than one - character (when CR is followed by LF). In this case, set up a negative - state to wait for one character to pass before continuing. */ - - case OP_ANYNL: - if (clen > 0) switch(c) - { - case 0x000b: - case 0x000c: - case 0x0085: - case 0x2028: - case 0x2029: - if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break; - - case 0x000a: - ADD_NEW(state_offset + 1, 0); - break; - - case 0x000d: - if (ptr + 1 < end_subject && ptr[1] == 0x0a) - { - ADD_NEW_DATA(-(state_offset + 1), 0, 1); - } - else - { - ADD_NEW(state_offset + 1, 0); - } - break; - } - break; - - /*-----------------------------------------------------------------*/ - case OP_NOT_VSPACE: - if (clen > 0) switch(c) - { - case 0x000a: - case 0x000b: - case 0x000c: - case 0x000d: - case 0x0085: - case 0x2028: - case 0x2029: - break; - - default: - ADD_NEW(state_offset + 1, 0); - break; - } - break; - - /*-----------------------------------------------------------------*/ - case OP_VSPACE: - if (clen > 0) switch(c) - { - case 0x000a: - case 0x000b: - case 0x000c: - case 0x000d: - case 0x0085: - case 0x2028: - case 0x2029: - ADD_NEW(state_offset + 1, 0); - break; - - default: break; - } - break; - - /*-----------------------------------------------------------------*/ - case OP_NOT_HSPACE: - if (clen > 0) switch(c) - { - case 0x09: /* HT */ - case 0x20: /* SPACE */ - case 0xa0: /* NBSP */ - case 0x1680: /* OGHAM SPACE MARK */ - case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ - case 0x2000: /* EN QUAD */ - case 0x2001: /* EM QUAD */ - case 0x2002: /* EN SPACE */ - case 0x2003: /* EM SPACE */ - case 0x2004: /* THREE-PER-EM SPACE */ - case 0x2005: /* FOUR-PER-EM SPACE */ - case 0x2006: /* SIX-PER-EM SPACE */ - case 0x2007: /* FIGURE SPACE */ - case 0x2008: /* PUNCTUATION SPACE */ - case 0x2009: /* THIN SPACE */ - case 0x200A: /* HAIR SPACE */ - case 0x202f: /* NARROW NO-BREAK SPACE */ - case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ - case 0x3000: /* IDEOGRAPHIC SPACE */ - break; - - default: - ADD_NEW(state_offset + 1, 0); - break; - } - break; - - /*-----------------------------------------------------------------*/ - case OP_HSPACE: - if (clen > 0) switch(c) - { - case 0x09: /* HT */ - case 0x20: /* SPACE */ - case 0xa0: /* NBSP */ - case 0x1680: /* OGHAM SPACE MARK */ - case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ - case 0x2000: /* EN QUAD */ - case 0x2001: /* EM QUAD */ - case 0x2002: /* EN SPACE */ - case 0x2003: /* EM SPACE */ - case 0x2004: /* THREE-PER-EM SPACE */ - case 0x2005: /* FOUR-PER-EM SPACE */ - case 0x2006: /* SIX-PER-EM SPACE */ - case 0x2007: /* FIGURE SPACE */ - case 0x2008: /* PUNCTUATION SPACE */ - case 0x2009: /* THIN SPACE */ - case 0x200A: /* HAIR SPACE */ - case 0x202f: /* NARROW NO-BREAK SPACE */ - case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ - case 0x3000: /* IDEOGRAPHIC SPACE */ - ADD_NEW(state_offset + 1, 0); - break; - } - break; - - /*-----------------------------------------------------------------*/ - /* Match a negated single character. This is only used for one-byte - characters, that is, we know that d < 256. The character we are - checking (c) can be multibyte. */ - - case OP_NOT: - if (clen > 0) - { - unsigned int otherd = ((ims & PCRE_CASELESS) != 0)? fcc[d] : d; - if (c != d && c != otherd) { ADD_NEW(state_offset + dlen + 1, 0); } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_PLUS: - case OP_MINPLUS: - case OP_POSPLUS: - case OP_NOTPLUS: - case OP_NOTMINPLUS: - case OP_NOTPOSPLUS: - count = current_state->count; /* Already matched */ - if (count > 0) { ADD_ACTIVE(state_offset + dlen + 1, 0); } - if (clen > 0) - { - unsigned int otherd = NOTACHAR; - if ((ims & PCRE_CASELESS) != 0) - { -#ifdef SUPPORT_UTF8 - if (utf8 && d >= 128) - { -#ifdef SUPPORT_UCP - otherd = UCD_OTHERCASE(d); -#endif /* SUPPORT_UCP */ - } - else -#endif /* SUPPORT_UTF8 */ - otherd = fcc[d]; - } - if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR)) - { - if (count > 0 && - (codevalue == OP_POSPLUS || codevalue == OP_NOTPOSPLUS)) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - count++; - ADD_NEW(state_offset, count); - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_QUERY: - case OP_MINQUERY: - case OP_POSQUERY: - case OP_NOTQUERY: - case OP_NOTMINQUERY: - case OP_NOTPOSQUERY: - ADD_ACTIVE(state_offset + dlen + 1, 0); - if (clen > 0) - { - unsigned int otherd = NOTACHAR; - if ((ims & PCRE_CASELESS) != 0) - { -#ifdef SUPPORT_UTF8 - if (utf8 && d >= 128) - { -#ifdef SUPPORT_UCP - otherd = UCD_OTHERCASE(d); -#endif /* SUPPORT_UCP */ - } - else -#endif /* SUPPORT_UTF8 */ - otherd = fcc[d]; - } - if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR)) - { - if (codevalue == OP_POSQUERY || codevalue == OP_NOTPOSQUERY) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - ADD_NEW(state_offset + dlen + 1, 0); - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_STAR: - case OP_MINSTAR: - case OP_POSSTAR: - case OP_NOTSTAR: - case OP_NOTMINSTAR: - case OP_NOTPOSSTAR: - ADD_ACTIVE(state_offset + dlen + 1, 0); - if (clen > 0) - { - unsigned int otherd = NOTACHAR; - if ((ims & PCRE_CASELESS) != 0) - { -#ifdef SUPPORT_UTF8 - if (utf8 && d >= 128) - { -#ifdef SUPPORT_UCP - otherd = UCD_OTHERCASE(d); -#endif /* SUPPORT_UCP */ - } - else -#endif /* SUPPORT_UTF8 */ - otherd = fcc[d]; - } - if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR)) - { - if (codevalue == OP_POSSTAR || codevalue == OP_NOTPOSSTAR) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - ADD_NEW(state_offset, 0); - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_EXACT: - case OP_NOTEXACT: - count = current_state->count; /* Number already matched */ - if (clen > 0) - { - unsigned int otherd = NOTACHAR; - if ((ims & PCRE_CASELESS) != 0) - { -#ifdef SUPPORT_UTF8 - if (utf8 && d >= 128) - { -#ifdef SUPPORT_UCP - otherd = UCD_OTHERCASE(d); -#endif /* SUPPORT_UCP */ - } - else -#endif /* SUPPORT_UTF8 */ - otherd = fcc[d]; - } - if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR)) - { - if (++count >= GET2(code, 1)) - { ADD_NEW(state_offset + dlen + 3, 0); } - else - { ADD_NEW(state_offset, count); } - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_UPTO: - case OP_MINUPTO: - case OP_POSUPTO: - case OP_NOTUPTO: - case OP_NOTMINUPTO: - case OP_NOTPOSUPTO: - ADD_ACTIVE(state_offset + dlen + 3, 0); - count = current_state->count; /* Number already matched */ - if (clen > 0) - { - unsigned int otherd = NOTACHAR; - if ((ims & PCRE_CASELESS) != 0) - { -#ifdef SUPPORT_UTF8 - if (utf8 && d >= 128) - { -#ifdef SUPPORT_UCP - otherd = UCD_OTHERCASE(d); -#endif /* SUPPORT_UCP */ - } - else -#endif /* SUPPORT_UTF8 */ - otherd = fcc[d]; - } - if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR)) - { - if (codevalue == OP_POSUPTO || codevalue == OP_NOTPOSUPTO) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - if (++count >= GET2(code, 1)) - { ADD_NEW(state_offset + dlen + 3, 0); } - else - { ADD_NEW(state_offset, count); } - } - } - break; - - -/* ========================================================================== */ - /* These are the class-handling opcodes */ - - case OP_CLASS: - case OP_NCLASS: - case OP_XCLASS: - { - BOOL isinclass = FALSE; - int next_state_offset; - const uschar *ecode; - - /* For a simple class, there is always just a 32-byte table, and we - can set isinclass from it. */ - - if (codevalue != OP_XCLASS) - { - ecode = code + 33; - if (clen > 0) - { - isinclass = (c > 255)? (codevalue == OP_NCLASS) : - ((code[1 + c/8] & (1 << (c&7))) != 0); - } - } - - /* An extended class may have a table or a list of single characters, - ranges, or both, and it may be positive or negative. There's a - function that sorts all this out. */ - - else - { - ecode = code + GET(code, 1); - if (clen > 0) isinclass = _pcre_xclass(c, code + 1 + LINK_SIZE); - } - - /* At this point, isinclass is set for all kinds of class, and ecode - points to the byte after the end of the class. If there is a - quantifier, this is where it will be. */ - - next_state_offset = ecode - start_code; - - switch (*ecode) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - ADD_ACTIVE(next_state_offset + 1, 0); - if (isinclass) { ADD_NEW(state_offset, 0); } - break; - - case OP_CRPLUS: - case OP_CRMINPLUS: - count = current_state->count; /* Already matched */ - if (count > 0) { ADD_ACTIVE(next_state_offset + 1, 0); } - if (isinclass) { count++; ADD_NEW(state_offset, count); } - break; - - case OP_CRQUERY: - case OP_CRMINQUERY: - ADD_ACTIVE(next_state_offset + 1, 0); - if (isinclass) { ADD_NEW(next_state_offset + 1, 0); } - break; - - case OP_CRRANGE: - case OP_CRMINRANGE: - count = current_state->count; /* Already matched */ - if (count >= GET2(ecode, 1)) - { ADD_ACTIVE(next_state_offset + 5, 0); } - if (isinclass) - { - int max = GET2(ecode, 3); - if (++count >= max && max != 0) /* Max 0 => no limit */ - { ADD_NEW(next_state_offset + 5, 0); } - else - { ADD_NEW(state_offset, count); } - } - break; - - default: - if (isinclass) { ADD_NEW(next_state_offset, 0); } - break; - } - } - break; - -/* ========================================================================== */ - /* These are the opcodes for fancy brackets of various kinds. We have - to use recursion in order to handle them. The "always failing" assersion - (?!) is optimised when compiling to OP_FAIL, so we have to support that, - though the other "backtracking verbs" are not supported. */ - - case OP_FAIL: - break; - - case OP_ASSERT: - case OP_ASSERT_NOT: - case OP_ASSERTBACK: - case OP_ASSERTBACK_NOT: - { - int rc; - int local_offsets[2]; - int local_workspace[1000]; - const uschar *endasscode = code + GET(code, 1); - - while (*endasscode == OP_ALT) endasscode += GET(endasscode, 1); - - rc = internal_dfa_exec( - md, /* static match data */ - code, /* this subexpression's code */ - ptr, /* where we currently are */ - ptr - start_subject, /* start offset */ - local_offsets, /* offset vector */ - sizeof(local_offsets)/sizeof(int), /* size of same */ - local_workspace, /* workspace vector */ - sizeof(local_workspace)/sizeof(int), /* size of same */ - ims, /* the current ims flags */ - rlevel, /* function recursion level */ - recursing); /* pass on regex recursion */ - - if ((rc >= 0) == (codevalue == OP_ASSERT || codevalue == OP_ASSERTBACK)) - { ADD_ACTIVE(endasscode + LINK_SIZE + 1 - start_code, 0); } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_COND: - case OP_SCOND: - { - int local_offsets[1000]; - int local_workspace[1000]; - int codelink = GET(code, 1); - int condcode; - - /* Because of the way auto-callout works during compile, a callout item - is inserted between OP_COND and an assertion condition. This does not - happen for the other conditions. */ - - if (code[LINK_SIZE+1] == OP_CALLOUT) - { - rrc = 0; - if (pcre_callout != NULL) - { - pcre_callout_block cb; - cb.version = 1; /* Version 1 of the callout block */ - cb.callout_number = code[LINK_SIZE+2]; - cb.offset_vector = offsets; - cb.subject = (PCRE_SPTR)start_subject; - cb.subject_length = end_subject - start_subject; - cb.start_match = current_subject - start_subject; - cb.current_position = ptr - start_subject; - cb.pattern_position = GET(code, LINK_SIZE + 3); - cb.next_item_length = GET(code, 3 + 2*LINK_SIZE); - cb.capture_top = 1; - cb.capture_last = -1; - cb.callout_data = md->callout_data; - if ((rrc = (*pcre_callout)(&cb)) < 0) return rrc; /* Abandon */ - } - if (rrc > 0) break; /* Fail this thread */ - code += _pcre_OP_lengths[OP_CALLOUT]; /* Skip callout data */ - } - - condcode = code[LINK_SIZE+1]; - - /* Back reference conditions are not supported */ - - if (condcode == OP_CREF) return PCRE_ERROR_DFA_UCOND; - - /* The DEFINE condition is always false */ - - if (condcode == OP_DEF) - { ADD_ACTIVE(state_offset + codelink + LINK_SIZE + 1, 0); } - - /* The only supported version of OP_RREF is for the value RREF_ANY, - which means "test if in any recursion". We can't test for specifically - recursed groups. */ - - else if (condcode == OP_RREF) - { - int value = GET2(code, LINK_SIZE+2); - if (value != RREF_ANY) return PCRE_ERROR_DFA_UCOND; - if (recursing > 0) - { ADD_ACTIVE(state_offset + LINK_SIZE + 4, 0); } - else { ADD_ACTIVE(state_offset + codelink + LINK_SIZE + 1, 0); } - } - - /* Otherwise, the condition is an assertion */ - - else - { - int rc; - const uschar *asscode = code + LINK_SIZE + 1; - const uschar *endasscode = asscode + GET(asscode, 1); - - while (*endasscode == OP_ALT) endasscode += GET(endasscode, 1); - - rc = internal_dfa_exec( - md, /* fixed match data */ - asscode, /* this subexpression's code */ - ptr, /* where we currently are */ - ptr - start_subject, /* start offset */ - local_offsets, /* offset vector */ - sizeof(local_offsets)/sizeof(int), /* size of same */ - local_workspace, /* workspace vector */ - sizeof(local_workspace)/sizeof(int), /* size of same */ - ims, /* the current ims flags */ - rlevel, /* function recursion level */ - recursing); /* pass on regex recursion */ - - if ((rc >= 0) == - (condcode == OP_ASSERT || condcode == OP_ASSERTBACK)) - { ADD_ACTIVE(endasscode + LINK_SIZE + 1 - start_code, 0); } - else - { ADD_ACTIVE(state_offset + codelink + LINK_SIZE + 1, 0); } - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_RECURSE: - { - int local_offsets[1000]; - int local_workspace[1000]; - int rc; - - DPRINTF(("%.*sStarting regex recursion %d\n", rlevel*2-2, SP, - recursing + 1)); - - rc = internal_dfa_exec( - md, /* fixed match data */ - start_code + GET(code, 1), /* this subexpression's code */ - ptr, /* where we currently are */ - ptr - start_subject, /* start offset */ - local_offsets, /* offset vector */ - sizeof(local_offsets)/sizeof(int), /* size of same */ - local_workspace, /* workspace vector */ - sizeof(local_workspace)/sizeof(int), /* size of same */ - ims, /* the current ims flags */ - rlevel, /* function recursion level */ - recursing + 1); /* regex recurse level */ - - DPRINTF(("%.*sReturn from regex recursion %d: rc=%d\n", rlevel*2-2, SP, - recursing + 1, rc)); - - /* Ran out of internal offsets */ - - if (rc == 0) return PCRE_ERROR_DFA_RECURSE; - - /* For each successful matched substring, set up the next state with a - count of characters to skip before trying it. Note that the count is in - characters, not bytes. */ - - if (rc > 0) - { - for (rc = rc*2 - 2; rc >= 0; rc -= 2) - { - const uschar *p = start_subject + local_offsets[rc]; - const uschar *pp = start_subject + local_offsets[rc+1]; - int charcount = local_offsets[rc+1] - local_offsets[rc]; - while (p < pp) if ((*p++ & 0xc0) == 0x80) charcount--; - if (charcount > 0) - { - ADD_NEW_DATA(-(state_offset + LINK_SIZE + 1), 0, (charcount - 1)); - } - else - { - ADD_ACTIVE(state_offset + LINK_SIZE + 1, 0); - } - } - } - else if (rc != PCRE_ERROR_NOMATCH) return rc; - } - break; - - /*-----------------------------------------------------------------*/ - case OP_ONCE: - { - int local_offsets[2]; - int local_workspace[1000]; - - int rc = internal_dfa_exec( - md, /* fixed match data */ - code, /* this subexpression's code */ - ptr, /* where we currently are */ - ptr - start_subject, /* start offset */ - local_offsets, /* offset vector */ - sizeof(local_offsets)/sizeof(int), /* size of same */ - local_workspace, /* workspace vector */ - sizeof(local_workspace)/sizeof(int), /* size of same */ - ims, /* the current ims flags */ - rlevel, /* function recursion level */ - recursing); /* pass on regex recursion */ - - if (rc >= 0) - { - const uschar *end_subpattern = code; - int charcount = local_offsets[1] - local_offsets[0]; - int next_state_offset, repeat_state_offset; - - do { end_subpattern += GET(end_subpattern, 1); } - while (*end_subpattern == OP_ALT); - next_state_offset = end_subpattern - start_code + LINK_SIZE + 1; - - /* If the end of this subpattern is KETRMAX or KETRMIN, we must - arrange for the repeat state also to be added to the relevant list. - Calculate the offset, or set -1 for no repeat. */ - - repeat_state_offset = (*end_subpattern == OP_KETRMAX || - *end_subpattern == OP_KETRMIN)? - end_subpattern - start_code - GET(end_subpattern, 1) : -1; - - /* If we have matched an empty string, add the next state at the - current character pointer. This is important so that the duplicate - checking kicks in, which is what breaks infinite loops that match an - empty string. */ - - if (charcount == 0) - { - ADD_ACTIVE(next_state_offset, 0); - } - - /* Optimization: if there are no more active states, and there - are no new states yet set up, then skip over the subject string - right here, to save looping. Otherwise, set up the new state to swing - into action when the end of the substring is reached. */ - - else if (i + 1 >= active_count && new_count == 0) - { - ptr += charcount; - clen = 0; - ADD_NEW(next_state_offset, 0); - - /* If we are adding a repeat state at the new character position, - we must fudge things so that it is the only current state. - Otherwise, it might be a duplicate of one we processed before, and - that would cause it to be skipped. */ - - if (repeat_state_offset >= 0) - { - next_active_state = active_states; - active_count = 0; - i = -1; - ADD_ACTIVE(repeat_state_offset, 0); - } - } - else - { - const uschar *p = start_subject + local_offsets[0]; - const uschar *pp = start_subject + local_offsets[1]; - while (p < pp) if ((*p++ & 0xc0) == 0x80) charcount--; - ADD_NEW_DATA(-next_state_offset, 0, (charcount - 1)); - if (repeat_state_offset >= 0) - { ADD_NEW_DATA(-repeat_state_offset, 0, (charcount - 1)); } - } - - } - else if (rc != PCRE_ERROR_NOMATCH) return rc; - } - break; - - -/* ========================================================================== */ - /* Handle callouts */ - - case OP_CALLOUT: - rrc = 0; - if (pcre_callout != NULL) - { - pcre_callout_block cb; - cb.version = 1; /* Version 1 of the callout block */ - cb.callout_number = code[1]; - cb.offset_vector = offsets; - cb.subject = (PCRE_SPTR)start_subject; - cb.subject_length = end_subject - start_subject; - cb.start_match = current_subject - start_subject; - cb.current_position = ptr - start_subject; - cb.pattern_position = GET(code, 2); - cb.next_item_length = GET(code, 2 + LINK_SIZE); - cb.capture_top = 1; - cb.capture_last = -1; - cb.callout_data = md->callout_data; - if ((rrc = (*pcre_callout)(&cb)) < 0) return rrc; /* Abandon */ - } - if (rrc == 0) - { ADD_ACTIVE(state_offset + _pcre_OP_lengths[OP_CALLOUT], 0); } - break; - - -/* ========================================================================== */ - default: /* Unsupported opcode */ - return PCRE_ERROR_DFA_UITEM; - } - - NEXT_ACTIVE_STATE: continue; - - } /* End of loop scanning active states */ - - /* We have finished the processing at the current subject character. If no - new states have been set for the next character, we have found all the - matches that we are going to find. If we are at the top level and partial - matching has been requested, check for appropriate conditions. */ - - if (new_count <= 0) - { - if (match_count < 0 && /* No matches found */ - rlevel == 1 && /* Top level match function */ - (md->moptions & PCRE_PARTIAL) != 0 && /* Want partial matching */ - ptr >= end_subject && /* Reached end of subject */ - ptr > current_subject) /* Matched non-empty string */ - { - if (offsetcount >= 2) - { - offsets[0] = current_subject - start_subject; - offsets[1] = end_subject - start_subject; - } - match_count = PCRE_ERROR_PARTIAL; - } - - DPRINTF(("%.*sEnd of internal_dfa_exec %d: returning %d\n" - "%.*s---------------------\n\n", rlevel*2-2, SP, rlevel, match_count, - rlevel*2-2, SP)); - break; /* In effect, "return", but see the comment below */ - } - - /* One or more states are active for the next character. */ - - ptr += clen; /* Advance to next subject character */ - } /* Loop to move along the subject string */ - -/* Control gets here from "break" a few lines above. We do it this way because -if we use "return" above, we have compiler trouble. Some compilers warn if -there's nothing here because they think the function doesn't return a value. On -the other hand, if we put a dummy statement here, some more clever compilers -complain that it can't be reached. Sigh. */ - -return match_count; -} - - - - -/************************************************* -* Execute a Regular Expression - DFA engine * -*************************************************/ - -/* This external function applies a compiled re to a subject string using a DFA -engine. This function calls the internal function multiple times if the pattern -is not anchored. - -Arguments: - argument_re points to the compiled expression - extra_data points to extra data or is NULL - subject points to the subject string - length length of subject string (may contain binary zeros) - start_offset where to start in the subject string - options option bits - offsets vector of match offsets - offsetcount size of same - workspace workspace vector - wscount size of same - -Returns: > 0 => number of match offset pairs placed in offsets - = 0 => offsets overflowed; longest matches are present - -1 => failed to match - < -1 => some kind of unexpected problem -*/ - -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre_dfa_exec(const pcre *argument_re, const pcre_extra *extra_data, - const char *subject, int length, int start_offset, int options, int *offsets, - int offsetcount, int *workspace, int wscount) -{ -real_pcre *re = (real_pcre *)argument_re; -dfa_match_data match_block; -dfa_match_data *md = &match_block; -BOOL utf8, anchored, startline, firstline; -const uschar *current_subject, *end_subject, *lcc; - -pcre_study_data internal_study; -const pcre_study_data *study = NULL; -real_pcre internal_re; - -const uschar *req_byte_ptr; -const uschar *start_bits = NULL; -BOOL first_byte_caseless = FALSE; -BOOL req_byte_caseless = FALSE; -int first_byte = -1; -int req_byte = -1; -int req_byte2 = -1; -int newline; - -/* Plausibility checks */ - -if ((options & ~PUBLIC_DFA_EXEC_OPTIONS) != 0) return PCRE_ERROR_BADOPTION; -if (re == NULL || subject == NULL || workspace == NULL || - (offsets == NULL && offsetcount > 0)) return PCRE_ERROR_NULL; -if (offsetcount < 0) return PCRE_ERROR_BADCOUNT; -if (wscount < 20) return PCRE_ERROR_DFA_WSSIZE; - -/* We need to find the pointer to any study data before we test for byte -flipping, so we scan the extra_data block first. This may set two fields in the -match block, so we must initialize them beforehand. However, the other fields -in the match block must not be set until after the byte flipping. */ - -md->tables = re->tables; -md->callout_data = NULL; - -if (extra_data != NULL) - { - unsigned int flags = extra_data->flags; - if ((flags & PCRE_EXTRA_STUDY_DATA) != 0) - study = (const pcre_study_data *)extra_data->study_data; - if ((flags & PCRE_EXTRA_MATCH_LIMIT) != 0) return PCRE_ERROR_DFA_UMLIMIT; - if ((flags & PCRE_EXTRA_MATCH_LIMIT_RECURSION) != 0) - return PCRE_ERROR_DFA_UMLIMIT; - if ((flags & PCRE_EXTRA_CALLOUT_DATA) != 0) - md->callout_data = extra_data->callout_data; - if ((flags & PCRE_EXTRA_TABLES) != 0) - md->tables = extra_data->tables; - } - -/* Check that the first field in the block is the magic number. If it is not, -test for a regex that was compiled on a host of opposite endianness. If this is -the case, flipped values are put in internal_re and internal_study if there was -study data too. */ - -if (re->magic_number != MAGIC_NUMBER) - { - re = _pcre_try_flipped(re, &internal_re, study, &internal_study); - if (re == NULL) return PCRE_ERROR_BADMAGIC; - if (study != NULL) study = &internal_study; - } - -/* Set some local values */ - -current_subject = (const unsigned char *)subject + start_offset; -end_subject = (const unsigned char *)subject + length; -req_byte_ptr = current_subject - 1; - -#ifdef SUPPORT_UTF8 -utf8 = (re->options & PCRE_UTF8) != 0; -#else -utf8 = FALSE; -#endif - -anchored = (options & (PCRE_ANCHORED|PCRE_DFA_RESTART)) != 0 || - (re->options & PCRE_ANCHORED) != 0; - -/* The remaining fixed data for passing around. */ - -md->start_code = (const uschar *)argument_re + - re->name_table_offset + re->name_count * re->name_entry_size; -md->start_subject = (const unsigned char *)subject; -md->end_subject = end_subject; -md->moptions = options; -md->poptions = re->options; - -/* If the BSR option is not set at match time, copy what was set -at compile time. */ - -if ((md->moptions & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) == 0) - { - if ((re->options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) != 0) - md->moptions |= re->options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE); -#ifdef BSR_ANYCRLF - else md->moptions |= PCRE_BSR_ANYCRLF; -#endif - } - -/* Handle different types of newline. The three bits give eight cases. If -nothing is set at run time, whatever was used at compile time applies. */ - -switch ((((options & PCRE_NEWLINE_BITS) == 0)? re->options : (pcre_uint32)options) & - PCRE_NEWLINE_BITS) - { - case 0: newline = NEWLINE; break; /* Compile-time default */ - case PCRE_NEWLINE_CR: newline = CHAR_CR; break; - case PCRE_NEWLINE_LF: newline = CHAR_NL; break; - case PCRE_NEWLINE_CR+ - PCRE_NEWLINE_LF: newline = (CHAR_CR << 8) | CHAR_NL; break; - case PCRE_NEWLINE_ANY: newline = -1; break; - case PCRE_NEWLINE_ANYCRLF: newline = -2; break; - default: return PCRE_ERROR_BADNEWLINE; - } - -if (newline == -2) - { - md->nltype = NLTYPE_ANYCRLF; - } -else if (newline < 0) - { - md->nltype = NLTYPE_ANY; - } -else - { - md->nltype = NLTYPE_FIXED; - if (newline > 255) - { - md->nllen = 2; - md->nl[0] = (newline >> 8) & 255; - md->nl[1] = newline & 255; - } - else - { - md->nllen = 1; - md->nl[0] = newline; - } - } - -/* Check a UTF-8 string if required. Unfortunately there's no way of passing -back the character offset. */ - -#ifdef SUPPORT_UTF8 -if (utf8 && (options & PCRE_NO_UTF8_CHECK) == 0) - { - if (_pcre_valid_utf8((uschar *)subject, length) >= 0) - return PCRE_ERROR_BADUTF8; - if (start_offset > 0 && start_offset < length) - { - int tb = ((uschar *)subject)[start_offset]; - if (tb > 127) - { - tb &= 0xc0; - if (tb != 0 && tb != 0xc0) return PCRE_ERROR_BADUTF8_OFFSET; - } - } - } -#endif - -/* If the exec call supplied NULL for tables, use the inbuilt ones. This -is a feature that makes it possible to save compiled regex and re-use them -in other programs later. */ - -if (md->tables == NULL) md->tables = _pcre_default_tables; - -/* The lower casing table and the "must be at the start of a line" flag are -used in a loop when finding where to start. */ - -lcc = md->tables + lcc_offset; -startline = (re->flags & PCRE_STARTLINE) != 0; -firstline = (re->options & PCRE_FIRSTLINE) != 0; - -/* Set up the first character to match, if available. The first_byte value is -never set for an anchored regular expression, but the anchoring may be forced -at run time, so we have to test for anchoring. The first char may be unset for -an unanchored pattern, of course. If there's no first char and the pattern was -studied, there may be a bitmap of possible first characters. */ - -if (!anchored) - { - if ((re->flags & PCRE_FIRSTSET) != 0) - { - first_byte = re->first_byte & 255; - if ((first_byte_caseless = ((re->first_byte & REQ_CASELESS) != 0)) == TRUE) - first_byte = lcc[first_byte]; - } - else - { - if (startline && study != NULL && - (study->options & PCRE_STUDY_MAPPED) != 0) - start_bits = study->start_bits; - } - } - -/* For anchored or unanchored matches, there may be a "last known required -character" set. */ - -if ((re->flags & PCRE_REQCHSET) != 0) - { - req_byte = re->req_byte & 255; - req_byte_caseless = (re->req_byte & REQ_CASELESS) != 0; - req_byte2 = (md->tables + fcc_offset)[req_byte]; /* case flipped */ - } - -/* Call the main matching function, looping for a non-anchored regex after a -failed match. If not restarting, perform certain optimizations at the start of -a match. */ - -for (;;) - { - int rc; - - if ((options & PCRE_DFA_RESTART) == 0) - { - const uschar *save_end_subject = end_subject; - - /* If firstline is TRUE, the start of the match is constrained to the first - line of a multiline string. Implement this by temporarily adjusting - end_subject so that we stop scanning at a newline. If the match fails at - the newline, later code breaks this loop. */ - - if (firstline) - { - USPTR t = current_subject; -#ifdef SUPPORT_UTF8 - if (utf8) - { - while (t < md->end_subject && !IS_NEWLINE(t)) - { - t++; - while (t < end_subject && (*t & 0xc0) == 0x80) t++; - } - } - else -#endif - while (t < md->end_subject && !IS_NEWLINE(t)) t++; - end_subject = t; - } - - /* There are some optimizations that avoid running the match if a known - starting point is not found, or if a known later character is not present. - However, there is an option that disables these, for testing and for - ensuring that all callouts do actually occur. */ - - if ((options & PCRE_NO_START_OPTIMIZE) == 0) - { - - /* Advance to a known first byte. */ - - if (first_byte >= 0) - { - if (first_byte_caseless) - while (current_subject < end_subject && - lcc[*current_subject] != first_byte) - current_subject++; - else - while (current_subject < end_subject && - *current_subject != first_byte) - current_subject++; - } - - /* Or to just after a linebreak for a multiline match if possible */ - - else if (startline) - { - if (current_subject > md->start_subject + start_offset) - { -#ifdef SUPPORT_UTF8 - if (utf8) - { - while (current_subject < end_subject && - !WAS_NEWLINE(current_subject)) - { - current_subject++; - while(current_subject < end_subject && - (*current_subject & 0xc0) == 0x80) - current_subject++; - } - } - else -#endif - while (current_subject < end_subject && !WAS_NEWLINE(current_subject)) - current_subject++; - - /* If we have just passed a CR and the newline option is ANY or - ANYCRLF, and we are now at a LF, advance the match position by one - more character. */ - - if (current_subject[-1] == CHAR_CR && - (md->nltype == NLTYPE_ANY || md->nltype == NLTYPE_ANYCRLF) && - current_subject < end_subject && - *current_subject == CHAR_NL) - current_subject++; - } - } - - /* Or to a non-unique first char after study */ - - else if (start_bits != NULL) - { - while (current_subject < end_subject) - { - register unsigned int c = *current_subject; - if ((start_bits[c/8] & (1 << (c&7))) == 0) current_subject++; - else break; - } - } - } - - /* Restore fudged end_subject */ - - end_subject = save_end_subject; - } - - /* If req_byte is set, we know that that character must appear in the subject - for the match to succeed. If the first character is set, req_byte must be - later in the subject; otherwise the test starts at the match point. This - optimization can save a huge amount of work in patterns with nested unlimited - repeats that aren't going to match. Writing separate code for cased/caseless - versions makes it go faster, as does using an autoincrement and backing off - on a match. - - HOWEVER: when the subject string is very, very long, searching to its end can - take a long time, and give bad performance on quite ordinary patterns. This - showed up when somebody was matching /^C/ on a 32-megabyte string... so we - don't do this when the string is sufficiently long. - - ALSO: this processing is disabled when partial matching is requested, and can - also be explicitly deactivated. */ - - if ((options & PCRE_NO_START_OPTIMIZE) == 0 && - req_byte >= 0 && - end_subject - current_subject < REQ_BYTE_MAX && - (options & PCRE_PARTIAL) == 0) - { - register const uschar *p = current_subject + ((first_byte >= 0)? 1 : 0); - - /* We don't need to repeat the search if we haven't yet reached the - place we found it at last time. */ - - if (p > req_byte_ptr) - { - if (req_byte_caseless) - { - while (p < end_subject) - { - register int pp = *p++; - if (pp == req_byte || pp == req_byte2) { p--; break; } - } - } - else - { - while (p < end_subject) - { - if (*p++ == req_byte) { p--; break; } - } - } - - /* If we can't find the required character, break the matching loop, - which will cause a return or PCRE_ERROR_NOMATCH. */ - - if (p >= end_subject) break; - - /* If we have found the required character, save the point where we - found it, so that we don't search again next time round the loop if - the start hasn't passed this character yet. */ - - req_byte_ptr = p; - } - } - - /* OK, now we can do the business */ - - rc = internal_dfa_exec( - md, /* fixed match data */ - md->start_code, /* this subexpression's code */ - current_subject, /* where we currently are */ - start_offset, /* start offset in subject */ - offsets, /* offset vector */ - offsetcount, /* size of same */ - workspace, /* workspace vector */ - wscount, /* size of same */ - re->options & (PCRE_CASELESS|PCRE_MULTILINE|PCRE_DOTALL), /* ims flags */ - 0, /* function recurse level */ - 0); /* regex recurse level */ - - /* Anything other than "no match" means we are done, always; otherwise, carry - on only if not anchored. */ - - if (rc != PCRE_ERROR_NOMATCH || anchored) return rc; - - /* Advance to the next subject character unless we are at the end of a line - and firstline is set. */ - - if (firstline && IS_NEWLINE(current_subject)) break; - current_subject++; - if (utf8) - { - while (current_subject < end_subject && (*current_subject & 0xc0) == 0x80) - current_subject++; - } - if (current_subject > end_subject) break; - - /* If we have just passed a CR and we are now at a LF, and the pattern does - not contain any explicit matches for \r or \n, and the newline option is CRLF - or ANY or ANYCRLF, advance the match position by one more character. */ - - if (current_subject[-1] == CHAR_CR && - current_subject < end_subject && - *current_subject == CHAR_NL && - (re->flags & PCRE_HASCRORLF) == 0 && - (md->nltype == NLTYPE_ANY || - md->nltype == NLTYPE_ANYCRLF || - md->nllen == 2)) - current_subject++; - - } /* "Bumpalong" loop */ - -return PCRE_ERROR_NOMATCH; -} - -/* End of pcre_dfa_exec.c */ diff --git a/libs/pcre/pcre_exec.c b/libs/pcre/pcre_exec.c deleted file mode 100644 index 9756362445..0000000000 --- a/libs/pcre/pcre_exec.c +++ /dev/null @@ -1,5050 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2009 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains pcre_exec(), the externally visible function that does -pattern matching using an NFA algorithm, trying to mimic Perl as closely as -possible. There are also some static supporting functions. */ - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#define NLBLOCK md /* Block containing newline information */ -#define PSSTART start_subject /* Field containing processed string start */ -#define PSEND end_subject /* Field containing processed string end */ - -#include "pcre_internal.h" - -/* Undefine some potentially clashing cpp symbols */ - -#undef min -#undef max - -/* Flag bits for the match() function */ - -#define match_condassert 0x01 /* Called to check a condition assertion */ -#define match_cbegroup 0x02 /* Could-be-empty unlimited repeat group */ - -/* Non-error returns from the match() function. Error returns are externally -defined PCRE_ERROR_xxx codes, which are all negative. */ - -#define MATCH_MATCH 1 -#define MATCH_NOMATCH 0 - -/* Special internal returns from the match() function. Make them sufficiently -negative to avoid the external error codes. */ - -#define MATCH_COMMIT (-999) -#define MATCH_PRUNE (-998) -#define MATCH_SKIP (-997) -#define MATCH_THEN (-996) - -/* Maximum number of ints of offset to save on the stack for recursive calls. -If the offset vector is bigger, malloc is used. This should be a multiple of 3, -because the offset vector is always a multiple of 3 long. */ - -#define REC_STACK_SAVE_MAX 30 - -/* Min and max values for the common repeats; for the maxima, 0 => infinity */ - -static const char rep_min[] = { 0, 0, 1, 1, 0, 0 }; -static const char rep_max[] = { 0, 0, 0, 0, 1, 1 }; - - - -#ifdef PCRE_DEBUG -/************************************************* -* Debugging function to print chars * -*************************************************/ - -/* Print a sequence of chars in printable format, stopping at the end of the -subject if the requested. - -Arguments: - p points to characters - length number to print - is_subject TRUE if printing from within md->start_subject - md pointer to matching data block, if is_subject is TRUE - -Returns: nothing -*/ - -static void -pchars(const uschar *p, int length, BOOL is_subject, match_data *md) -{ -unsigned int c; -if (is_subject && length > md->end_subject - p) length = md->end_subject - p; -while (length-- > 0) - if (isprint(c = *(p++))) printf("%c", c); else printf("\\x%02x", c); -} -#endif - - - -/************************************************* -* Match a back-reference * -*************************************************/ - -/* If a back reference hasn't been set, the length that is passed is greater -than the number of characters left in the string, so the match fails. - -Arguments: - offset index into the offset vector - eptr points into the subject - length length to be matched - md points to match data block - ims the ims flags - -Returns: TRUE if matched -*/ - -static BOOL -match_ref(int offset, register USPTR eptr, int length, match_data *md, - unsigned long int ims) -{ -USPTR p = md->start_subject + md->offset_vector[offset]; - -#ifdef PCRE_DEBUG -if (eptr >= md->end_subject) - printf("matching subject "); -else - { - printf("matching subject "); - pchars(eptr, length, TRUE, md); - } -printf(" against backref "); -pchars(p, length, FALSE, md); -printf("\n"); -#endif - -/* Always fail if not enough characters left */ - -if (length > md->end_subject - eptr) return FALSE; - -/* Separate the caseless case for speed. In UTF-8 mode we can only do this -properly if Unicode properties are supported. Otherwise, we can check only -ASCII characters. */ - -if ((ims & PCRE_CASELESS) != 0) - { -#ifdef SUPPORT_UTF8 -#ifdef SUPPORT_UCP - if (md->utf8) - { - USPTR endptr = eptr + length; - while (eptr < endptr) - { - int c, d; - GETCHARINC(c, eptr); - GETCHARINC(d, p); - if (c != d && c != UCD_OTHERCASE(d)) return FALSE; - } - } - else -#endif -#endif - - /* The same code works when not in UTF-8 mode and in UTF-8 mode when there - is no UCP support. */ - - while (length-- > 0) - { if (md->lcc[*p++] != md->lcc[*eptr++]) return FALSE; } - } - -/* In the caseful case, we can just compare the bytes, whether or not we -are in UTF-8 mode. */ - -else - { while (length-- > 0) if (*p++ != *eptr++) return FALSE; } - -return TRUE; -} - - - -/*************************************************************************** -**************************************************************************** - RECURSION IN THE match() FUNCTION - -The match() function is highly recursive, though not every recursive call -increases the recursive depth. Nevertheless, some regular expressions can cause -it to recurse to a great depth. I was writing for Unix, so I just let it call -itself recursively. This uses the stack for saving everything that has to be -saved for a recursive call. On Unix, the stack can be large, and this works -fine. - -It turns out that on some non-Unix-like systems there are problems with -programs that use a lot of stack. (This despite the fact that every last chip -has oodles of memory these days, and techniques for extending the stack have -been known for decades.) So.... - -There is a fudge, triggered by defining NO_RECURSE, which avoids recursive -calls by keeping local variables that need to be preserved in blocks of memory -obtained from malloc() instead instead of on the stack. Macros are used to -achieve this so that the actual code doesn't look very different to what it -always used to. - -The original heap-recursive code used longjmp(). However, it seems that this -can be very slow on some operating systems. Following a suggestion from Stan -Switzer, the use of longjmp() has been abolished, at the cost of having to -provide a unique number for each call to RMATCH. There is no way of generating -a sequence of numbers at compile time in C. I have given them names, to make -them stand out more clearly. - -Crude tests on x86 Linux show a small speedup of around 5-8%. However, on -FreeBSD, avoiding longjmp() more than halves the time taken to run the standard -tests. Furthermore, not using longjmp() means that local dynamic variables -don't have indeterminate values; this has meant that the frame size can be -reduced because the result can be "passed back" by straight setting of the -variable instead of being passed in the frame. -**************************************************************************** -***************************************************************************/ - -/* Numbers for RMATCH calls. When this list is changed, the code at HEAP_RETURN -below must be updated in sync. */ - -enum { RM1=1, RM2, RM3, RM4, RM5, RM6, RM7, RM8, RM9, RM10, - RM11, RM12, RM13, RM14, RM15, RM16, RM17, RM18, RM19, RM20, - RM21, RM22, RM23, RM24, RM25, RM26, RM27, RM28, RM29, RM30, - RM31, RM32, RM33, RM34, RM35, RM36, RM37, RM38, RM39, RM40, - RM41, RM42, RM43, RM44, RM45, RM46, RM47, RM48, RM49, RM50, - RM51, RM52, RM53, RM54 }; - -/* These versions of the macros use the stack, as normal. There are debugging -versions and production versions. Note that the "rw" argument of RMATCH isn't -actuall used in this definition. */ - -#ifndef NO_RECURSE -#define REGISTER register - -#ifdef PCRE_DEBUG -#define RMATCH(ra,rb,rc,rd,re,rf,rg,rw) \ - { \ - printf("match() called in line %d\n", __LINE__); \ - rrc = match(ra,rb,mstart,rc,rd,re,rf,rg,rdepth+1); \ - printf("to line %d\n", __LINE__); \ - } -#define RRETURN(ra) \ - { \ - printf("match() returned %d from line %d ", ra, __LINE__); \ - return ra; \ - } -#else -#define RMATCH(ra,rb,rc,rd,re,rf,rg,rw) \ - rrc = match(ra,rb,mstart,rc,rd,re,rf,rg,rdepth+1) -#define RRETURN(ra) return ra -#endif - -#else - - -/* These versions of the macros manage a private stack on the heap. Note that -the "rd" argument of RMATCH isn't actually used in this definition. It's the md -argument of match(), which never changes. */ - -#define REGISTER - -#define RMATCH(ra,rb,rc,rd,re,rf,rg,rw)\ - {\ - heapframe *newframe = (pcre_stack_malloc)(sizeof(heapframe));\ - frame->Xwhere = rw; \ - newframe->Xeptr = ra;\ - newframe->Xecode = rb;\ - newframe->Xmstart = mstart;\ - newframe->Xoffset_top = rc;\ - newframe->Xims = re;\ - newframe->Xeptrb = rf;\ - newframe->Xflags = rg;\ - newframe->Xrdepth = frame->Xrdepth + 1;\ - newframe->Xprevframe = frame;\ - frame = newframe;\ - DPRINTF(("restarting from line %d\n", __LINE__));\ - goto HEAP_RECURSE;\ - L_##rw:\ - DPRINTF(("jumped back to line %d\n", __LINE__));\ - } - -#define RRETURN(ra)\ - {\ - heapframe *newframe = frame;\ - frame = newframe->Xprevframe;\ - (pcre_stack_free)(newframe);\ - if (frame != NULL)\ - {\ - rrc = ra;\ - goto HEAP_RETURN;\ - }\ - return ra;\ - } - - -/* Structure for remembering the local variables in a private frame */ - -typedef struct heapframe { - struct heapframe *Xprevframe; - - /* Function arguments that may change */ - - USPTR Xeptr; - const uschar *Xecode; - USPTR Xmstart; - int Xoffset_top; - long int Xims; - eptrblock *Xeptrb; - int Xflags; - unsigned int Xrdepth; - - /* Function local variables */ - - USPTR Xcallpat; -#ifdef SUPPORT_UTF8 - USPTR Xcharptr; -#endif - USPTR Xdata; - USPTR Xnext; - USPTR Xpp; - USPTR Xprev; - USPTR Xsaved_eptr; - - recursion_info Xnew_recursive; - - BOOL Xcur_is_word; - BOOL Xcondition; - BOOL Xprev_is_word; - - unsigned long int Xoriginal_ims; - -#ifdef SUPPORT_UCP - int Xprop_type; - int Xprop_value; - int Xprop_fail_result; - int Xprop_category; - int Xprop_chartype; - int Xprop_script; - int Xoclength; - uschar Xocchars[8]; -#endif - - int Xcodelink; - int Xctype; - unsigned int Xfc; - int Xfi; - int Xlength; - int Xmax; - int Xmin; - int Xnumber; - int Xoffset; - int Xop; - int Xsave_capture_last; - int Xsave_offset1, Xsave_offset2, Xsave_offset3; - int Xstacksave[REC_STACK_SAVE_MAX]; - - eptrblock Xnewptrb; - - /* Where to jump back to */ - - int Xwhere; - -} heapframe; - -#endif - - -/*************************************************************************** -***************************************************************************/ - - - -/************************************************* -* Match from current position * -*************************************************/ - -/* This function is called recursively in many circumstances. Whenever it -returns a negative (error) response, the outer incarnation must also return the -same response. - -Performance note: It might be tempting to extract commonly used fields from the -md structure (e.g. utf8, end_subject) into individual variables to improve -performance. Tests using gcc on a SPARC disproved this; in the first case, it -made performance worse. - -Arguments: - eptr pointer to current character in subject - ecode pointer to current position in compiled code - mstart pointer to the current match start position (can be modified - by encountering \K) - offset_top current top pointer - md pointer to "static" info for the match - ims current /i, /m, and /s options - eptrb pointer to chain of blocks containing eptr at start of - brackets - for testing for empty matches - flags can contain - match_condassert - this is an assertion condition - match_cbegroup - this is the start of an unlimited repeat - group that can match an empty string - rdepth the recursion depth - -Returns: MATCH_MATCH if matched ) these values are >= 0 - MATCH_NOMATCH if failed to match ) - a negative PCRE_ERROR_xxx value if aborted by an error condition - (e.g. stopped by repeated call or recursion limit) -*/ - -static int -match(REGISTER USPTR eptr, REGISTER const uschar *ecode, USPTR mstart, - int offset_top, match_data *md, unsigned long int ims, eptrblock *eptrb, - int flags, unsigned int rdepth) -{ -/* These variables do not need to be preserved over recursion in this function, -so they can be ordinary variables in all cases. Mark some of them with -"register" because they are used a lot in loops. */ - -register int rrc; /* Returns from recursive calls */ -register int i; /* Used for loops not involving calls to RMATCH() */ -register unsigned int c; /* Character values not kept over RMATCH() calls */ -register BOOL utf8; /* Local copy of UTF-8 flag for speed */ - -BOOL minimize, possessive; /* Quantifier options */ -int condcode; - -/* When recursion is not being used, all "local" variables that have to be -preserved over calls to RMATCH() are part of a "frame" which is obtained from -heap storage. Set up the top-level frame here; others are obtained from the -heap whenever RMATCH() does a "recursion". See the macro definitions above. */ - -#ifdef NO_RECURSE -heapframe *frame = (pcre_stack_malloc)(sizeof(heapframe)); -frame->Xprevframe = NULL; /* Marks the top level */ - -/* Copy in the original argument variables */ - -frame->Xeptr = eptr; -frame->Xecode = ecode; -frame->Xmstart = mstart; -frame->Xoffset_top = offset_top; -frame->Xims = ims; -frame->Xeptrb = eptrb; -frame->Xflags = flags; -frame->Xrdepth = rdepth; - -/* This is where control jumps back to to effect "recursion" */ - -HEAP_RECURSE: - -/* Macros make the argument variables come from the current frame */ - -#define eptr frame->Xeptr -#define ecode frame->Xecode -#define mstart frame->Xmstart -#define offset_top frame->Xoffset_top -#define ims frame->Xims -#define eptrb frame->Xeptrb -#define flags frame->Xflags -#define rdepth frame->Xrdepth - -/* Ditto for the local variables */ - -#ifdef SUPPORT_UTF8 -#define charptr frame->Xcharptr -#endif -#define callpat frame->Xcallpat -#define codelink frame->Xcodelink -#define data frame->Xdata -#define next frame->Xnext -#define pp frame->Xpp -#define prev frame->Xprev -#define saved_eptr frame->Xsaved_eptr - -#define new_recursive frame->Xnew_recursive - -#define cur_is_word frame->Xcur_is_word -#define condition frame->Xcondition -#define prev_is_word frame->Xprev_is_word - -#define original_ims frame->Xoriginal_ims - -#ifdef SUPPORT_UCP -#define prop_type frame->Xprop_type -#define prop_value frame->Xprop_value -#define prop_fail_result frame->Xprop_fail_result -#define prop_category frame->Xprop_category -#define prop_chartype frame->Xprop_chartype -#define prop_script frame->Xprop_script -#define oclength frame->Xoclength -#define occhars frame->Xocchars -#endif - -#define ctype frame->Xctype -#define fc frame->Xfc -#define fi frame->Xfi -#define length frame->Xlength -#define max frame->Xmax -#define min frame->Xmin -#define number frame->Xnumber -#define offset frame->Xoffset -#define op frame->Xop -#define save_capture_last frame->Xsave_capture_last -#define save_offset1 frame->Xsave_offset1 -#define save_offset2 frame->Xsave_offset2 -#define save_offset3 frame->Xsave_offset3 -#define stacksave frame->Xstacksave - -#define newptrb frame->Xnewptrb - -/* When recursion is being used, local variables are allocated on the stack and -get preserved during recursion in the normal way. In this environment, fi and -i, and fc and c, can be the same variables. */ - -#else /* NO_RECURSE not defined */ -#define fi i -#define fc c - - -#ifdef SUPPORT_UTF8 /* Many of these variables are used only */ -const uschar *charptr; /* in small blocks of the code. My normal */ -#endif /* style of coding would have declared */ -const uschar *callpat; /* them within each of those blocks. */ -const uschar *data; /* However, in order to accommodate the */ -const uschar *next; /* version of this code that uses an */ -USPTR pp; /* external "stack" implemented on the */ -const uschar *prev; /* heap, it is easier to declare them all */ -USPTR saved_eptr; /* here, so the declarations can be cut */ - /* out in a block. The only declarations */ -recursion_info new_recursive; /* within blocks below are for variables */ - /* that do not have to be preserved over */ -BOOL cur_is_word; /* a recursive call to RMATCH(). */ -BOOL condition; -BOOL prev_is_word; - -unsigned long int original_ims; - -#ifdef SUPPORT_UCP -int prop_type; -int prop_value; -int prop_fail_result; -int prop_category; -int prop_chartype; -int prop_script; -int oclength; -uschar occhars[8]; -#endif - -int codelink; -int ctype; -int length; -int max; -int min; -int number; -int offset; -int op; -int save_capture_last; -int save_offset1, save_offset2, save_offset3; -int stacksave[REC_STACK_SAVE_MAX]; - -eptrblock newptrb; -#endif /* NO_RECURSE */ - -/* These statements are here to stop the compiler complaining about unitialized -variables. */ - -#ifdef SUPPORT_UCP -prop_value = 0; -prop_fail_result = 0; -#endif - - -/* This label is used for tail recursion, which is used in a few cases even -when NO_RECURSE is not defined, in order to reduce the amount of stack that is -used. Thanks to Ian Taylor for noticing this possibility and sending the -original patch. */ - -TAIL_RECURSE: - -/* OK, now we can get on with the real code of the function. Recursive calls -are specified by the macro RMATCH and RRETURN is used to return. When -NO_RECURSE is *not* defined, these just turn into a recursive call to match() -and a "return", respectively (possibly with some debugging if PCRE_DEBUG is -defined). However, RMATCH isn't like a function call because it's quite a -complicated macro. It has to be used in one particular way. This shouldn't, -however, impact performance when true recursion is being used. */ - -#ifdef SUPPORT_UTF8 -utf8 = md->utf8; /* Local copy of the flag */ -#else -utf8 = FALSE; -#endif - -/* First check that we haven't called match() too many times, or that we -haven't exceeded the recursive call limit. */ - -if (md->match_call_count++ >= md->match_limit) RRETURN(PCRE_ERROR_MATCHLIMIT); -if (rdepth >= md->match_limit_recursion) RRETURN(PCRE_ERROR_RECURSIONLIMIT); - -original_ims = ims; /* Save for resetting on ')' */ - -/* At the start of a group with an unlimited repeat that may match an empty -string, the match_cbegroup flag is set. When this is the case, add the current -subject pointer to the chain of such remembered pointers, to be checked when we -hit the closing ket, in order to break infinite loops that match no characters. -When match() is called in other circumstances, don't add to the chain. The -match_cbegroup flag must NOT be used with tail recursion, because the memory -block that is used is on the stack, so a new one may be required for each -match(). */ - -if ((flags & match_cbegroup) != 0) - { - newptrb.epb_saved_eptr = eptr; - newptrb.epb_prev = eptrb; - eptrb = &newptrb; - } - -/* Now start processing the opcodes. */ - -for (;;) - { - minimize = possessive = FALSE; - op = *ecode; - - /* For partial matching, remember if we ever hit the end of the subject after - matching at least one subject character. */ - - if (md->partial && - eptr >= md->end_subject && - eptr > mstart) - md->hitend = TRUE; - - switch(op) - { - case OP_FAIL: - RRETURN(MATCH_NOMATCH); - - case OP_PRUNE: - RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, - ims, eptrb, flags, RM51); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - RRETURN(MATCH_PRUNE); - - case OP_COMMIT: - RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, - ims, eptrb, flags, RM52); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - RRETURN(MATCH_COMMIT); - - case OP_SKIP: - RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, - ims, eptrb, flags, RM53); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - md->start_match_ptr = eptr; /* Pass back current position */ - RRETURN(MATCH_SKIP); - - case OP_THEN: - RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, - ims, eptrb, flags, RM54); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - RRETURN(MATCH_THEN); - - /* Handle a capturing bracket. If there is space in the offset vector, save - the current subject position in the working slot at the top of the vector. - We mustn't change the current values of the data slot, because they may be - set from a previous iteration of this group, and be referred to by a - reference inside the group. - - If the bracket fails to match, we need to restore this value and also the - values of the final offsets, in case they were set by a previous iteration - of the same bracket. - - If there isn't enough space in the offset vector, treat this as if it were - a non-capturing bracket. Don't worry about setting the flag for the error - case here; that is handled in the code for KET. */ - - case OP_CBRA: - case OP_SCBRA: - number = GET2(ecode, 1+LINK_SIZE); - offset = number << 1; - -#ifdef PCRE_DEBUG - printf("start bracket %d\n", number); - printf("subject="); - pchars(eptr, 16, TRUE, md); - printf("\n"); -#endif - - if (offset < md->offset_max) - { - save_offset1 = md->offset_vector[offset]; - save_offset2 = md->offset_vector[offset+1]; - save_offset3 = md->offset_vector[md->offset_end - number]; - save_capture_last = md->capture_last; - - DPRINTF(("saving %d %d %d\n", save_offset1, save_offset2, save_offset3)); - md->offset_vector[md->offset_end - number] = eptr - md->start_subject; - - flags = (op == OP_SCBRA)? match_cbegroup : 0; - do - { - RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, - ims, eptrb, flags, RM1); - if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc); - md->capture_last = save_capture_last; - ecode += GET(ecode, 1); - } - while (*ecode == OP_ALT); - - DPRINTF(("bracket %d failed\n", number)); - - md->offset_vector[offset] = save_offset1; - md->offset_vector[offset+1] = save_offset2; - md->offset_vector[md->offset_end - number] = save_offset3; - - RRETURN(MATCH_NOMATCH); - } - - /* FALL THROUGH ... Insufficient room for saving captured contents. Treat - as a non-capturing bracket. */ - - /* VVVVVVVVVVVVVVVVVVVVVVVVV */ - /* VVVVVVVVVVVVVVVVVVVVVVVVV */ - - DPRINTF(("insufficient capture room: treat as non-capturing\n")); - - /* VVVVVVVVVVVVVVVVVVVVVVVVV */ - /* VVVVVVVVVVVVVVVVVVVVVVVVV */ - - /* Non-capturing bracket. Loop for all the alternatives. When we get to the - final alternative within the brackets, we would return the result of a - recursive call to match() whatever happened. We can reduce stack usage by - turning this into a tail recursion, except in the case when match_cbegroup - is set.*/ - - case OP_BRA: - case OP_SBRA: - DPRINTF(("start non-capturing bracket\n")); - flags = (op >= OP_SBRA)? match_cbegroup : 0; - for (;;) - { - if (ecode[GET(ecode, 1)] != OP_ALT) /* Final alternative */ - { - if (flags == 0) /* Not a possibly empty group */ - { - ecode += _pcre_OP_lengths[*ecode]; - DPRINTF(("bracket 0 tail recursion\n")); - goto TAIL_RECURSE; - } - - /* Possibly empty group; can't use tail recursion. */ - - RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, ims, - eptrb, flags, RM48); - RRETURN(rrc); - } - - /* For non-final alternatives, continue the loop for a NOMATCH result; - otherwise return. */ - - RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, ims, - eptrb, flags, RM2); - if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc); - ecode += GET(ecode, 1); - } - /* Control never reaches here. */ - - /* Conditional group: compilation checked that there are no more than - two branches. If the condition is false, skipping the first branch takes us - past the end if there is only one branch, but that's OK because that is - exactly what going to the ket would do. As there is only one branch to be - obeyed, we can use tail recursion to avoid using another stack frame. */ - - case OP_COND: - case OP_SCOND: - codelink= GET(ecode, 1); - - /* Because of the way auto-callout works during compile, a callout item is - inserted between OP_COND and an assertion condition. */ - - if (ecode[LINK_SIZE+1] == OP_CALLOUT) - { - if (pcre_callout != NULL) - { - pcre_callout_block cb; - cb.version = 1; /* Version 1 of the callout block */ - cb.callout_number = ecode[LINK_SIZE+2]; - cb.offset_vector = md->offset_vector; - cb.subject = (PCRE_SPTR)md->start_subject; - cb.subject_length = md->end_subject - md->start_subject; - cb.start_match = mstart - md->start_subject; - cb.current_position = eptr - md->start_subject; - cb.pattern_position = GET(ecode, LINK_SIZE + 3); - cb.next_item_length = GET(ecode, 3 + 2*LINK_SIZE); - cb.capture_top = offset_top/2; - cb.capture_last = md->capture_last; - cb.callout_data = md->callout_data; - if ((rrc = (*pcre_callout)(&cb)) > 0) RRETURN(MATCH_NOMATCH); - if (rrc < 0) RRETURN(rrc); - } - ecode += _pcre_OP_lengths[OP_CALLOUT]; - } - - condcode = ecode[LINK_SIZE+1]; - - /* Now see what the actual condition is */ - - if (condcode == OP_RREF) /* Recursion test */ - { - offset = GET2(ecode, LINK_SIZE + 2); /* Recursion group number*/ - condition = md->recursive != NULL && - (offset == RREF_ANY || offset == md->recursive->group_num); - ecode += condition? 3 : GET(ecode, 1); - } - - else if (condcode == OP_CREF) /* Group used test */ - { - offset = GET2(ecode, LINK_SIZE+2) << 1; /* Doubled ref number */ - condition = offset < offset_top && md->offset_vector[offset] >= 0; - ecode += condition? 3 : GET(ecode, 1); - } - - else if (condcode == OP_DEF) /* DEFINE - always false */ - { - condition = FALSE; - ecode += GET(ecode, 1); - } - - /* The condition is an assertion. Call match() to evaluate it - setting - the final argument match_condassert causes it to stop at the end of an - assertion. */ - - else - { - RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, - match_condassert, RM3); - if (rrc == MATCH_MATCH) - { - condition = TRUE; - ecode += 1 + LINK_SIZE + GET(ecode, LINK_SIZE + 2); - while (*ecode == OP_ALT) ecode += GET(ecode, 1); - } - else if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) - { - RRETURN(rrc); /* Need braces because of following else */ - } - else - { - condition = FALSE; - ecode += codelink; - } - } - - /* We are now at the branch that is to be obeyed. As there is only one, - we can use tail recursion to avoid using another stack frame, except when - match_cbegroup is required for an unlimited repeat of a possibly empty - group. If the second alternative doesn't exist, we can just plough on. */ - - if (condition || *ecode == OP_ALT) - { - ecode += 1 + LINK_SIZE; - if (op == OP_SCOND) /* Possibly empty group */ - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, match_cbegroup, RM49); - RRETURN(rrc); - } - else /* Group must match something */ - { - flags = 0; - goto TAIL_RECURSE; - } - } - else /* Condition false & no alternative */ - { - ecode += 1 + LINK_SIZE; - } - break; - - - /* End of the pattern, either real or forced. If we are in a top-level - recursion, we should restore the offsets appropriately and continue from - after the call. */ - - case OP_ACCEPT: - case OP_END: - if (md->recursive != NULL && md->recursive->group_num == 0) - { - recursion_info *rec = md->recursive; - DPRINTF(("End of pattern in a (?0) recursion\n")); - md->recursive = rec->prevrec; - memmove(md->offset_vector, rec->offset_save, - rec->saved_max * sizeof(int)); - mstart = rec->save_start; - ims = original_ims; - ecode = rec->after_call; - break; - } - - /* Otherwise, if PCRE_NOTEMPTY is set, fail if we have matched an empty - string - backtracking will then try other alternatives, if any. */ - - if (md->notempty && eptr == mstart) RRETURN(MATCH_NOMATCH); - md->end_match_ptr = eptr; /* Record where we ended */ - md->end_offset_top = offset_top; /* and how many extracts were taken */ - md->start_match_ptr = mstart; /* and the start (\K can modify) */ - RRETURN(MATCH_MATCH); - - /* Change option settings */ - - case OP_OPT: - ims = ecode[1]; - ecode += 2; - DPRINTF(("ims set to %02lx\n", ims)); - break; - - /* Assertion brackets. Check the alternative branches in turn - the - matching won't pass the KET for an assertion. If any one branch matches, - the assertion is true. Lookbehind assertions have an OP_REVERSE item at the - start of each branch to move the current point backwards, so the code at - this level is identical to the lookahead case. */ - - case OP_ASSERT: - case OP_ASSERTBACK: - do - { - RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, 0, - RM4); - if (rrc == MATCH_MATCH) break; - if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc); - ecode += GET(ecode, 1); - } - while (*ecode == OP_ALT); - if (*ecode == OP_KET) RRETURN(MATCH_NOMATCH); - - /* If checking an assertion for a condition, return MATCH_MATCH. */ - - if ((flags & match_condassert) != 0) RRETURN(MATCH_MATCH); - - /* Continue from after the assertion, updating the offsets high water - mark, since extracts may have been taken during the assertion. */ - - do ecode += GET(ecode,1); while (*ecode == OP_ALT); - ecode += 1 + LINK_SIZE; - offset_top = md->end_offset_top; - continue; - - /* Negative assertion: all branches must fail to match */ - - case OP_ASSERT_NOT: - case OP_ASSERTBACK_NOT: - do - { - RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, 0, - RM5); - if (rrc == MATCH_MATCH) RRETURN(MATCH_NOMATCH); - if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc); - ecode += GET(ecode,1); - } - while (*ecode == OP_ALT); - - if ((flags & match_condassert) != 0) RRETURN(MATCH_MATCH); - - ecode += 1 + LINK_SIZE; - continue; - - /* Move the subject pointer back. This occurs only at the start of - each branch of a lookbehind assertion. If we are too close to the start to - move back, this match function fails. When working with UTF-8 we move - back a number of characters, not bytes. */ - - case OP_REVERSE: -#ifdef SUPPORT_UTF8 - if (utf8) - { - i = GET(ecode, 1); - while (i-- > 0) - { - eptr--; - if (eptr < md->start_subject) RRETURN(MATCH_NOMATCH); - BACKCHAR(eptr); - } - } - else -#endif - - /* No UTF-8 support, or not in UTF-8 mode: count is byte count */ - - { - eptr -= GET(ecode, 1); - if (eptr < md->start_subject) RRETURN(MATCH_NOMATCH); - } - - /* Skip to next op code */ - - ecode += 1 + LINK_SIZE; - break; - - /* The callout item calls an external function, if one is provided, passing - details of the match so far. This is mainly for debugging, though the - function is able to force a failure. */ - - case OP_CALLOUT: - if (pcre_callout != NULL) - { - pcre_callout_block cb; - cb.version = 1; /* Version 1 of the callout block */ - cb.callout_number = ecode[1]; - cb.offset_vector = md->offset_vector; - cb.subject = (PCRE_SPTR)md->start_subject; - cb.subject_length = md->end_subject - md->start_subject; - cb.start_match = mstart - md->start_subject; - cb.current_position = eptr - md->start_subject; - cb.pattern_position = GET(ecode, 2); - cb.next_item_length = GET(ecode, 2 + LINK_SIZE); - cb.capture_top = offset_top/2; - cb.capture_last = md->capture_last; - cb.callout_data = md->callout_data; - if ((rrc = (*pcre_callout)(&cb)) > 0) RRETURN(MATCH_NOMATCH); - if (rrc < 0) RRETURN(rrc); - } - ecode += 2 + 2*LINK_SIZE; - break; - - /* Recursion either matches the current regex, or some subexpression. The - offset data is the offset to the starting bracket from the start of the - whole pattern. (This is so that it works from duplicated subpatterns.) - - If there are any capturing brackets started but not finished, we have to - save their starting points and reinstate them after the recursion. However, - we don't know how many such there are (offset_top records the completed - total) so we just have to save all the potential data. There may be up to - 65535 such values, which is too large to put on the stack, but using malloc - for small numbers seems expensive. As a compromise, the stack is used when - there are no more than REC_STACK_SAVE_MAX values to store; otherwise malloc - is used. A problem is what to do if the malloc fails ... there is no way of - returning to the top level with an error. Save the top REC_STACK_SAVE_MAX - values on the stack, and accept that the rest may be wrong. - - There are also other values that have to be saved. We use a chained - sequence of blocks that actually live on the stack. Thanks to Robin Houston - for the original version of this logic. */ - - case OP_RECURSE: - { - callpat = md->start_code + GET(ecode, 1); - new_recursive.group_num = (callpat == md->start_code)? 0 : - GET2(callpat, 1 + LINK_SIZE); - - /* Add to "recursing stack" */ - - new_recursive.prevrec = md->recursive; - md->recursive = &new_recursive; - - /* Find where to continue from afterwards */ - - ecode += 1 + LINK_SIZE; - new_recursive.after_call = ecode; - - /* Now save the offset data. */ - - new_recursive.saved_max = md->offset_end; - if (new_recursive.saved_max <= REC_STACK_SAVE_MAX) - new_recursive.offset_save = stacksave; - else - { - new_recursive.offset_save = - (int *)(pcre_malloc)(new_recursive.saved_max * sizeof(int)); - if (new_recursive.offset_save == NULL) RRETURN(PCRE_ERROR_NOMEMORY); - } - - memcpy(new_recursive.offset_save, md->offset_vector, - new_recursive.saved_max * sizeof(int)); - new_recursive.save_start = mstart; - mstart = eptr; - - /* OK, now we can do the recursion. For each top-level alternative we - restore the offset and recursion data. */ - - DPRINTF(("Recursing into group %d\n", new_recursive.group_num)); - flags = (*callpat >= OP_SBRA)? match_cbegroup : 0; - do - { - RMATCH(eptr, callpat + _pcre_OP_lengths[*callpat], offset_top, - md, ims, eptrb, flags, RM6); - if (rrc == MATCH_MATCH) - { - DPRINTF(("Recursion matched\n")); - md->recursive = new_recursive.prevrec; - if (new_recursive.offset_save != stacksave) - (pcre_free)(new_recursive.offset_save); - RRETURN(MATCH_MATCH); - } - else if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) - { - DPRINTF(("Recursion gave error %d\n", rrc)); - if (new_recursive.offset_save != stacksave) - (pcre_free)(new_recursive.offset_save); - RRETURN(rrc); - } - - md->recursive = &new_recursive; - memcpy(md->offset_vector, new_recursive.offset_save, - new_recursive.saved_max * sizeof(int)); - callpat += GET(callpat, 1); - } - while (*callpat == OP_ALT); - - DPRINTF(("Recursion didn't match\n")); - md->recursive = new_recursive.prevrec; - if (new_recursive.offset_save != stacksave) - (pcre_free)(new_recursive.offset_save); - RRETURN(MATCH_NOMATCH); - } - /* Control never reaches here */ - - /* "Once" brackets are like assertion brackets except that after a match, - the point in the subject string is not moved back. Thus there can never be - a move back into the brackets. Friedl calls these "atomic" subpatterns. - Check the alternative branches in turn - the matching won't pass the KET - for this kind of subpattern. If any one branch matches, we carry on as at - the end of a normal bracket, leaving the subject pointer. */ - - case OP_ONCE: - prev = ecode; - saved_eptr = eptr; - - do - { - RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, 0, RM7); - if (rrc == MATCH_MATCH) break; - if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc); - ecode += GET(ecode,1); - } - while (*ecode == OP_ALT); - - /* If hit the end of the group (which could be repeated), fail */ - - if (*ecode != OP_ONCE && *ecode != OP_ALT) RRETURN(MATCH_NOMATCH); - - /* Continue as from after the assertion, updating the offsets high water - mark, since extracts may have been taken. */ - - do ecode += GET(ecode, 1); while (*ecode == OP_ALT); - - offset_top = md->end_offset_top; - eptr = md->end_match_ptr; - - /* For a non-repeating ket, just continue at this level. This also - happens for a repeating ket if no characters were matched in the group. - This is the forcible breaking of infinite loops as implemented in Perl - 5.005. If there is an options reset, it will get obeyed in the normal - course of events. */ - - if (*ecode == OP_KET || eptr == saved_eptr) - { - ecode += 1+LINK_SIZE; - break; - } - - /* The repeating kets try the rest of the pattern or restart from the - preceding bracket, in the appropriate order. The second "call" of match() - uses tail recursion, to avoid using another stack frame. We need to reset - any options that changed within the bracket before re-running it, so - check the next opcode. */ - - if (ecode[1+LINK_SIZE] == OP_OPT) - { - ims = (ims & ~PCRE_IMS) | ecode[4]; - DPRINTF(("ims set to %02lx at group repeat\n", ims)); - } - - if (*ecode == OP_KETRMIN) - { - RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, 0, RM8); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - ecode = prev; - flags = 0; - goto TAIL_RECURSE; - } - else /* OP_KETRMAX */ - { - RMATCH(eptr, prev, offset_top, md, ims, eptrb, match_cbegroup, RM9); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - ecode += 1 + LINK_SIZE; - flags = 0; - goto TAIL_RECURSE; - } - /* Control never gets here */ - - /* An alternation is the end of a branch; scan along to find the end of the - bracketed group and go to there. */ - - case OP_ALT: - do ecode += GET(ecode,1); while (*ecode == OP_ALT); - break; - - /* BRAZERO, BRAMINZERO and SKIPZERO occur just before a bracket group, - indicating that it may occur zero times. It may repeat infinitely, or not - at all - i.e. it could be ()* or ()? or even (){0} in the pattern. Brackets - with fixed upper repeat limits are compiled as a number of copies, with the - optional ones preceded by BRAZERO or BRAMINZERO. */ - - case OP_BRAZERO: - { - next = ecode+1; - RMATCH(eptr, next, offset_top, md, ims, eptrb, 0, RM10); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - do next += GET(next,1); while (*next == OP_ALT); - ecode = next + 1 + LINK_SIZE; - } - break; - - case OP_BRAMINZERO: - { - next = ecode+1; - do next += GET(next, 1); while (*next == OP_ALT); - RMATCH(eptr, next + 1+LINK_SIZE, offset_top, md, ims, eptrb, 0, RM11); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - ecode++; - } - break; - - case OP_SKIPZERO: - { - next = ecode+1; - do next += GET(next,1); while (*next == OP_ALT); - ecode = next + 1 + LINK_SIZE; - } - break; - - /* End of a group, repeated or non-repeating. */ - - case OP_KET: - case OP_KETRMIN: - case OP_KETRMAX: - prev = ecode - GET(ecode, 1); - - /* If this was a group that remembered the subject start, in order to break - infinite repeats of empty string matches, retrieve the subject start from - the chain. Otherwise, set it NULL. */ - - if (*prev >= OP_SBRA) - { - saved_eptr = eptrb->epb_saved_eptr; /* Value at start of group */ - eptrb = eptrb->epb_prev; /* Backup to previous group */ - } - else saved_eptr = NULL; - - /* If we are at the end of an assertion group, stop matching and return - MATCH_MATCH, but record the current high water mark for use by positive - assertions. Do this also for the "once" (atomic) groups. */ - - if (*prev == OP_ASSERT || *prev == OP_ASSERT_NOT || - *prev == OP_ASSERTBACK || *prev == OP_ASSERTBACK_NOT || - *prev == OP_ONCE) - { - md->end_match_ptr = eptr; /* For ONCE */ - md->end_offset_top = offset_top; - RRETURN(MATCH_MATCH); - } - - /* For capturing groups we have to check the group number back at the start - and if necessary complete handling an extraction by setting the offsets and - bumping the high water mark. Note that whole-pattern recursion is coded as - a recurse into group 0, so it won't be picked up here. Instead, we catch it - when the OP_END is reached. Other recursion is handled here. */ - - if (*prev == OP_CBRA || *prev == OP_SCBRA) - { - number = GET2(prev, 1+LINK_SIZE); - offset = number << 1; - -#ifdef PCRE_DEBUG - printf("end bracket %d", number); - printf("\n"); -#endif - - md->capture_last = number; - if (offset >= md->offset_max) md->offset_overflow = TRUE; else - { - md->offset_vector[offset] = - md->offset_vector[md->offset_end - number]; - md->offset_vector[offset+1] = eptr - md->start_subject; - if (offset_top <= offset) offset_top = offset + 2; - } - - /* Handle a recursively called group. Restore the offsets - appropriately and continue from after the call. */ - - if (md->recursive != NULL && md->recursive->group_num == number) - { - recursion_info *rec = md->recursive; - DPRINTF(("Recursion (%d) succeeded - continuing\n", number)); - md->recursive = rec->prevrec; - mstart = rec->save_start; - memcpy(md->offset_vector, rec->offset_save, - rec->saved_max * sizeof(int)); - ecode = rec->after_call; - ims = original_ims; - break; - } - } - - /* For both capturing and non-capturing groups, reset the value of the ims - flags, in case they got changed during the group. */ - - ims = original_ims; - DPRINTF(("ims reset to %02lx\n", ims)); - - /* For a non-repeating ket, just continue at this level. This also - happens for a repeating ket if no characters were matched in the group. - This is the forcible breaking of infinite loops as implemented in Perl - 5.005. If there is an options reset, it will get obeyed in the normal - course of events. */ - - if (*ecode == OP_KET || eptr == saved_eptr) - { - ecode += 1 + LINK_SIZE; - break; - } - - /* The repeating kets try the rest of the pattern or restart from the - preceding bracket, in the appropriate order. In the second case, we can use - tail recursion to avoid using another stack frame, unless we have an - unlimited repeat of a group that can match an empty string. */ - - flags = (*prev >= OP_SBRA)? match_cbegroup : 0; - - if (*ecode == OP_KETRMIN) - { - RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, 0, RM12); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (flags != 0) /* Could match an empty string */ - { - RMATCH(eptr, prev, offset_top, md, ims, eptrb, flags, RM50); - RRETURN(rrc); - } - ecode = prev; - goto TAIL_RECURSE; - } - else /* OP_KETRMAX */ - { - RMATCH(eptr, prev, offset_top, md, ims, eptrb, flags, RM13); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - ecode += 1 + LINK_SIZE; - flags = 0; - goto TAIL_RECURSE; - } - /* Control never gets here */ - - /* Start of subject unless notbol, or after internal newline if multiline */ - - case OP_CIRC: - if (md->notbol && eptr == md->start_subject) RRETURN(MATCH_NOMATCH); - if ((ims & PCRE_MULTILINE) != 0) - { - if (eptr != md->start_subject && - (eptr == md->end_subject || !WAS_NEWLINE(eptr))) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - } - /* ... else fall through */ - - /* Start of subject assertion */ - - case OP_SOD: - if (eptr != md->start_subject) RRETURN(MATCH_NOMATCH); - ecode++; - break; - - /* Start of match assertion */ - - case OP_SOM: - if (eptr != md->start_subject + md->start_offset) RRETURN(MATCH_NOMATCH); - ecode++; - break; - - /* Reset the start of match point */ - - case OP_SET_SOM: - mstart = eptr; - ecode++; - break; - - /* Assert before internal newline if multiline, or before a terminating - newline unless endonly is set, else end of subject unless noteol is set. */ - - case OP_DOLL: - if ((ims & PCRE_MULTILINE) != 0) - { - if (eptr < md->end_subject) - { if (!IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH); } - else - { if (md->noteol) RRETURN(MATCH_NOMATCH); } - ecode++; - break; - } - else - { - if (md->noteol) RRETURN(MATCH_NOMATCH); - if (!md->endonly) - { - if (eptr != md->end_subject && - (!IS_NEWLINE(eptr) || eptr != md->end_subject - md->nllen)) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - } - } - /* ... else fall through for endonly */ - - /* End of subject assertion (\z) */ - - case OP_EOD: - if (eptr < md->end_subject) RRETURN(MATCH_NOMATCH); - ecode++; - break; - - /* End of subject or ending \n assertion (\Z) */ - - case OP_EODN: - if (eptr != md->end_subject && - (!IS_NEWLINE(eptr) || eptr != md->end_subject - md->nllen)) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - - /* Word boundary assertions */ - - case OP_NOT_WORD_BOUNDARY: - case OP_WORD_BOUNDARY: - { - - /* Find out if the previous and current characters are "word" characters. - It takes a bit more work in UTF-8 mode. Characters > 255 are assumed to - be "non-word" characters. */ - -#ifdef SUPPORT_UTF8 - if (utf8) - { - if (eptr == md->start_subject) prev_is_word = FALSE; else - { - USPTR lastptr = eptr - 1; - while((*lastptr & 0xc0) == 0x80) lastptr--; - GETCHAR(c, lastptr); - prev_is_word = c < 256 && (md->ctypes[c] & ctype_word) != 0; - } - if (eptr >= md->end_subject) cur_is_word = FALSE; else - { - GETCHAR(c, eptr); - cur_is_word = c < 256 && (md->ctypes[c] & ctype_word) != 0; - } - } - else -#endif - - /* More streamlined when not in UTF-8 mode */ - - { - prev_is_word = (eptr != md->start_subject) && - ((md->ctypes[eptr[-1]] & ctype_word) != 0); - cur_is_word = (eptr < md->end_subject) && - ((md->ctypes[*eptr] & ctype_word) != 0); - } - - /* Now see if the situation is what we want */ - - if ((*ecode++ == OP_WORD_BOUNDARY)? - cur_is_word == prev_is_word : cur_is_word != prev_is_word) - RRETURN(MATCH_NOMATCH); - } - break; - - /* Match a single character type; inline for speed */ - - case OP_ANY: - if (IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH); - /* Fall through */ - - case OP_ALLANY: - if (eptr++ >= md->end_subject) RRETURN(MATCH_NOMATCH); - if (utf8) while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; - ecode++; - break; - - /* Match a single byte, even in UTF-8 mode. This opcode really does match - any byte, even newline, independent of the setting of PCRE_DOTALL. */ - - case OP_ANYBYTE: - if (eptr++ >= md->end_subject) RRETURN(MATCH_NOMATCH); - ecode++; - break; - - case OP_NOT_DIGIT: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - if ( -#ifdef SUPPORT_UTF8 - c < 256 && -#endif - (md->ctypes[c] & ctype_digit) != 0 - ) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - - case OP_DIGIT: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - if ( -#ifdef SUPPORT_UTF8 - c >= 256 || -#endif - (md->ctypes[c] & ctype_digit) == 0 - ) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - - case OP_NOT_WHITESPACE: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - if ( -#ifdef SUPPORT_UTF8 - c < 256 && -#endif - (md->ctypes[c] & ctype_space) != 0 - ) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - - case OP_WHITESPACE: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - if ( -#ifdef SUPPORT_UTF8 - c >= 256 || -#endif - (md->ctypes[c] & ctype_space) == 0 - ) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - - case OP_NOT_WORDCHAR: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - if ( -#ifdef SUPPORT_UTF8 - c < 256 && -#endif - (md->ctypes[c] & ctype_word) != 0 - ) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - - case OP_WORDCHAR: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - if ( -#ifdef SUPPORT_UTF8 - c >= 256 || -#endif - (md->ctypes[c] & ctype_word) == 0 - ) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - - case OP_ANYNL: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - switch(c) - { - default: RRETURN(MATCH_NOMATCH); - case 0x000d: - if (eptr < md->end_subject && *eptr == 0x0a) eptr++; - break; - - case 0x000a: - break; - - case 0x000b: - case 0x000c: - case 0x0085: - case 0x2028: - case 0x2029: - if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); - break; - } - ecode++; - break; - - case OP_NOT_HSPACE: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - switch(c) - { - default: break; - case 0x09: /* HT */ - case 0x20: /* SPACE */ - case 0xa0: /* NBSP */ - case 0x1680: /* OGHAM SPACE MARK */ - case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ - case 0x2000: /* EN QUAD */ - case 0x2001: /* EM QUAD */ - case 0x2002: /* EN SPACE */ - case 0x2003: /* EM SPACE */ - case 0x2004: /* THREE-PER-EM SPACE */ - case 0x2005: /* FOUR-PER-EM SPACE */ - case 0x2006: /* SIX-PER-EM SPACE */ - case 0x2007: /* FIGURE SPACE */ - case 0x2008: /* PUNCTUATION SPACE */ - case 0x2009: /* THIN SPACE */ - case 0x200A: /* HAIR SPACE */ - case 0x202f: /* NARROW NO-BREAK SPACE */ - case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ - case 0x3000: /* IDEOGRAPHIC SPACE */ - RRETURN(MATCH_NOMATCH); - } - ecode++; - break; - - case OP_HSPACE: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - switch(c) - { - default: RRETURN(MATCH_NOMATCH); - case 0x09: /* HT */ - case 0x20: /* SPACE */ - case 0xa0: /* NBSP */ - case 0x1680: /* OGHAM SPACE MARK */ - case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ - case 0x2000: /* EN QUAD */ - case 0x2001: /* EM QUAD */ - case 0x2002: /* EN SPACE */ - case 0x2003: /* EM SPACE */ - case 0x2004: /* THREE-PER-EM SPACE */ - case 0x2005: /* FOUR-PER-EM SPACE */ - case 0x2006: /* SIX-PER-EM SPACE */ - case 0x2007: /* FIGURE SPACE */ - case 0x2008: /* PUNCTUATION SPACE */ - case 0x2009: /* THIN SPACE */ - case 0x200A: /* HAIR SPACE */ - case 0x202f: /* NARROW NO-BREAK SPACE */ - case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ - case 0x3000: /* IDEOGRAPHIC SPACE */ - break; - } - ecode++; - break; - - case OP_NOT_VSPACE: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - switch(c) - { - default: break; - case 0x0a: /* LF */ - case 0x0b: /* VT */ - case 0x0c: /* FF */ - case 0x0d: /* CR */ - case 0x85: /* NEL */ - case 0x2028: /* LINE SEPARATOR */ - case 0x2029: /* PARAGRAPH SEPARATOR */ - RRETURN(MATCH_NOMATCH); - } - ecode++; - break; - - case OP_VSPACE: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - switch(c) - { - default: RRETURN(MATCH_NOMATCH); - case 0x0a: /* LF */ - case 0x0b: /* VT */ - case 0x0c: /* FF */ - case 0x0d: /* CR */ - case 0x85: /* NEL */ - case 0x2028: /* LINE SEPARATOR */ - case 0x2029: /* PARAGRAPH SEPARATOR */ - break; - } - ecode++; - break; - -#ifdef SUPPORT_UCP - /* Check the next character by Unicode property. We will get here only - if the support is in the binary; otherwise a compile-time error occurs. */ - - case OP_PROP: - case OP_NOTPROP: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - { - const ucd_record *prop = GET_UCD(c); - - switch(ecode[1]) - { - case PT_ANY: - if (op == OP_NOTPROP) RRETURN(MATCH_NOMATCH); - break; - - case PT_LAMP: - if ((prop->chartype == ucp_Lu || - prop->chartype == ucp_Ll || - prop->chartype == ucp_Lt) == (op == OP_NOTPROP)) - RRETURN(MATCH_NOMATCH); - break; - - case PT_GC: - if ((ecode[2] != _pcre_ucp_gentype[prop->chartype]) == (op == OP_PROP)) - RRETURN(MATCH_NOMATCH); - break; - - case PT_PC: - if ((ecode[2] != prop->chartype) == (op == OP_PROP)) - RRETURN(MATCH_NOMATCH); - break; - - case PT_SC: - if ((ecode[2] != prop->script) == (op == OP_PROP)) - RRETURN(MATCH_NOMATCH); - break; - - default: - RRETURN(PCRE_ERROR_INTERNAL); - } - - ecode += 3; - } - break; - - /* Match an extended Unicode sequence. We will get here only if the support - is in the binary; otherwise a compile-time error occurs. */ - - case OP_EXTUNI: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - { - int category = UCD_CATEGORY(c); - if (category == ucp_M) RRETURN(MATCH_NOMATCH); - while (eptr < md->end_subject) - { - int len = 1; - if (!utf8) c = *eptr; else - { - GETCHARLEN(c, eptr, len); - } - category = UCD_CATEGORY(c); - if (category != ucp_M) break; - eptr += len; - } - } - ecode++; - break; -#endif - - - /* Match a back reference, possibly repeatedly. Look past the end of the - item to see if there is repeat information following. The code is similar - to that for character classes, but repeated for efficiency. Then obey - similar code to character type repeats - written out again for speed. - However, if the referenced string is the empty string, always treat - it as matched, any number of times (otherwise there could be infinite - loops). */ - - case OP_REF: - { - offset = GET2(ecode, 1) << 1; /* Doubled ref number */ - ecode += 3; - - /* If the reference is unset, there are two possibilities: - - (a) In the default, Perl-compatible state, set the length to be longer - than the amount of subject left; this ensures that every attempt at a - match fails. We can't just fail here, because of the possibility of - quantifiers with zero minima. - - (b) If the JavaScript compatibility flag is set, set the length to zero - so that the back reference matches an empty string. - - Otherwise, set the length to the length of what was matched by the - referenced subpattern. */ - - if (offset >= offset_top || md->offset_vector[offset] < 0) - length = (md->jscript_compat)? 0 : md->end_subject - eptr + 1; - else - length = md->offset_vector[offset+1] - md->offset_vector[offset]; - - /* Set up for repetition, or handle the non-repeated case */ - - switch (*ecode) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRPLUS: - case OP_CRMINPLUS: - case OP_CRQUERY: - case OP_CRMINQUERY: - c = *ecode++ - OP_CRSTAR; - minimize = (c & 1) != 0; - min = rep_min[c]; /* Pick up values from tables; */ - max = rep_max[c]; /* zero for max => infinity */ - if (max == 0) max = INT_MAX; - break; - - case OP_CRRANGE: - case OP_CRMINRANGE: - minimize = (*ecode == OP_CRMINRANGE); - min = GET2(ecode, 1); - max = GET2(ecode, 3); - if (max == 0) max = INT_MAX; - ecode += 5; - break; - - default: /* No repeat follows */ - if (!match_ref(offset, eptr, length, md, ims)) RRETURN(MATCH_NOMATCH); - eptr += length; - continue; /* With the main loop */ - } - - /* If the length of the reference is zero, just continue with the - main loop. */ - - if (length == 0) continue; - - /* First, ensure the minimum number of matches are present. We get back - the length of the reference string explicitly rather than passing the - address of eptr, so that eptr can be a register variable. */ - - for (i = 1; i <= min; i++) - { - if (!match_ref(offset, eptr, length, md, ims)) RRETURN(MATCH_NOMATCH); - eptr += length; - } - - /* If min = max, continue at the same level without recursion. - They are not both allowed to be zero. */ - - if (min == max) continue; - - /* If minimizing, keep trying and advancing the pointer */ - - if (minimize) - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM14); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || !match_ref(offset, eptr, length, md, ims)) - RRETURN(MATCH_NOMATCH); - eptr += length; - } - /* Control never gets here */ - } - - /* If maximizing, find the longest string and work backwards */ - - else - { - pp = eptr; - for (i = min; i < max; i++) - { - if (!match_ref(offset, eptr, length, md, ims)) break; - eptr += length; - } - while (eptr >= pp) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM15); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - eptr -= length; - } - RRETURN(MATCH_NOMATCH); - } - } - /* Control never gets here */ - - - - /* Match a bit-mapped character class, possibly repeatedly. This op code is - used when all the characters in the class have values in the range 0-255, - and either the matching is caseful, or the characters are in the range - 0-127 when UTF-8 processing is enabled. The only difference between - OP_CLASS and OP_NCLASS occurs when a data character outside the range is - encountered. - - First, look past the end of the item to see if there is repeat information - following. Then obey similar code to character type repeats - written out - again for speed. */ - - case OP_NCLASS: - case OP_CLASS: - { - data = ecode + 1; /* Save for matching */ - ecode += 33; /* Advance past the item */ - - switch (*ecode) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRPLUS: - case OP_CRMINPLUS: - case OP_CRQUERY: - case OP_CRMINQUERY: - c = *ecode++ - OP_CRSTAR; - minimize = (c & 1) != 0; - min = rep_min[c]; /* Pick up values from tables; */ - max = rep_max[c]; /* zero for max => infinity */ - if (max == 0) max = INT_MAX; - break; - - case OP_CRRANGE: - case OP_CRMINRANGE: - minimize = (*ecode == OP_CRMINRANGE); - min = GET2(ecode, 1); - max = GET2(ecode, 3); - if (max == 0) max = INT_MAX; - ecode += 5; - break; - - default: /* No repeat follows */ - min = max = 1; - break; - } - - /* First, ensure the minimum number of matches are present. */ - -#ifdef SUPPORT_UTF8 - /* UTF-8 mode */ - if (utf8) - { - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - if (c > 255) - { - if (op == OP_CLASS) RRETURN(MATCH_NOMATCH); - } - else - { - if ((data[c/8] & (1 << (c&7))) == 0) RRETURN(MATCH_NOMATCH); - } - } - } - else -#endif - /* Not UTF-8 mode */ - { - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - c = *eptr++; - if ((data[c/8] & (1 << (c&7))) == 0) RRETURN(MATCH_NOMATCH); - } - } - - /* If max == min we can continue with the main loop without the - need to recurse. */ - - if (min == max) continue; - - /* If minimizing, keep testing the rest of the expression and advancing - the pointer while it matches the class. */ - - if (minimize) - { -#ifdef SUPPORT_UTF8 - /* UTF-8 mode */ - if (utf8) - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM16); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - if (c > 255) - { - if (op == OP_CLASS) RRETURN(MATCH_NOMATCH); - } - else - { - if ((data[c/8] & (1 << (c&7))) == 0) RRETURN(MATCH_NOMATCH); - } - } - } - else -#endif - /* Not UTF-8 mode */ - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM17); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - c = *eptr++; - if ((data[c/8] & (1 << (c&7))) == 0) RRETURN(MATCH_NOMATCH); - } - } - /* Control never gets here */ - } - - /* If maximizing, find the longest possible run, then work backwards. */ - - else - { - pp = eptr; - -#ifdef SUPPORT_UTF8 - /* UTF-8 mode */ - if (utf8) - { - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - if (c > 255) - { - if (op == OP_CLASS) break; - } - else - { - if ((data[c/8] & (1 << (c&7))) == 0) break; - } - eptr += len; - } - for (;;) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM18); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (eptr-- == pp) break; /* Stop if tried at original pos */ - BACKCHAR(eptr); - } - } - else -#endif - /* Not UTF-8 mode */ - { - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) break; - c = *eptr; - if ((data[c/8] & (1 << (c&7))) == 0) break; - eptr++; - } - while (eptr >= pp) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM19); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - eptr--; - } - } - - RRETURN(MATCH_NOMATCH); - } - } - /* Control never gets here */ - - - /* Match an extended character class. This opcode is encountered only - when UTF-8 mode mode is supported. Nevertheless, we may not be in UTF-8 - mode, because Unicode properties are supported in non-UTF-8 mode. */ - -#ifdef SUPPORT_UTF8 - case OP_XCLASS: - { - data = ecode + 1 + LINK_SIZE; /* Save for matching */ - ecode += GET(ecode, 1); /* Advance past the item */ - - switch (*ecode) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRPLUS: - case OP_CRMINPLUS: - case OP_CRQUERY: - case OP_CRMINQUERY: - c = *ecode++ - OP_CRSTAR; - minimize = (c & 1) != 0; - min = rep_min[c]; /* Pick up values from tables; */ - max = rep_max[c]; /* zero for max => infinity */ - if (max == 0) max = INT_MAX; - break; - - case OP_CRRANGE: - case OP_CRMINRANGE: - minimize = (*ecode == OP_CRMINRANGE); - min = GET2(ecode, 1); - max = GET2(ecode, 3); - if (max == 0) max = INT_MAX; - ecode += 5; - break; - - default: /* No repeat follows */ - min = max = 1; - break; - } - - /* First, ensure the minimum number of matches are present. */ - - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - if (!_pcre_xclass(c, data)) RRETURN(MATCH_NOMATCH); - } - - /* If max == min we can continue with the main loop without the - need to recurse. */ - - if (min == max) continue; - - /* If minimizing, keep testing the rest of the expression and advancing - the pointer while it matches the class. */ - - if (minimize) - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM20); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - if (!_pcre_xclass(c, data)) RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - } - - /* If maximizing, find the longest possible run, then work backwards. */ - - else - { - pp = eptr; - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLENTEST(c, eptr, len); - if (!_pcre_xclass(c, data)) break; - eptr += len; - } - for(;;) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM21); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (eptr-- == pp) break; /* Stop if tried at original pos */ - if (utf8) BACKCHAR(eptr); - } - RRETURN(MATCH_NOMATCH); - } - - /* Control never gets here */ - } -#endif /* End of XCLASS */ - - /* Match a single character, casefully */ - - case OP_CHAR: -#ifdef SUPPORT_UTF8 - if (utf8) - { - length = 1; - ecode++; - GETCHARLEN(fc, ecode, length); - if (length > md->end_subject - eptr) RRETURN(MATCH_NOMATCH); - while (length-- > 0) if (*ecode++ != *eptr++) RRETURN(MATCH_NOMATCH); - } - else -#endif - - /* Non-UTF-8 mode */ - { - if (md->end_subject - eptr < 1) RRETURN(MATCH_NOMATCH); - if (ecode[1] != *eptr++) RRETURN(MATCH_NOMATCH); - ecode += 2; - } - break; - - /* Match a single character, caselessly */ - - case OP_CHARNC: -#ifdef SUPPORT_UTF8 - if (utf8) - { - length = 1; - ecode++; - GETCHARLEN(fc, ecode, length); - - if (length > md->end_subject - eptr) RRETURN(MATCH_NOMATCH); - - /* If the pattern character's value is < 128, we have only one byte, and - can use the fast lookup table. */ - - if (fc < 128) - { - if (md->lcc[*ecode++] != md->lcc[*eptr++]) RRETURN(MATCH_NOMATCH); - } - - /* Otherwise we must pick up the subject character */ - - else - { - unsigned int dc; - GETCHARINC(dc, eptr); - ecode += length; - - /* If we have Unicode property support, we can use it to test the other - case of the character, if there is one. */ - - if (fc != dc) - { -#ifdef SUPPORT_UCP - if (dc != UCD_OTHERCASE(fc)) -#endif - RRETURN(MATCH_NOMATCH); - } - } - } - else -#endif /* SUPPORT_UTF8 */ - - /* Non-UTF-8 mode */ - { - if (md->end_subject - eptr < 1) RRETURN(MATCH_NOMATCH); - if (md->lcc[ecode[1]] != md->lcc[*eptr++]) RRETURN(MATCH_NOMATCH); - ecode += 2; - } - break; - - /* Match a single character repeatedly. */ - - case OP_EXACT: - min = max = GET2(ecode, 1); - ecode += 3; - goto REPEATCHAR; - - case OP_POSUPTO: - possessive = TRUE; - /* Fall through */ - - case OP_UPTO: - case OP_MINUPTO: - min = 0; - max = GET2(ecode, 1); - minimize = *ecode == OP_MINUPTO; - ecode += 3; - goto REPEATCHAR; - - case OP_POSSTAR: - possessive = TRUE; - min = 0; - max = INT_MAX; - ecode++; - goto REPEATCHAR; - - case OP_POSPLUS: - possessive = TRUE; - min = 1; - max = INT_MAX; - ecode++; - goto REPEATCHAR; - - case OP_POSQUERY: - possessive = TRUE; - min = 0; - max = 1; - ecode++; - goto REPEATCHAR; - - case OP_STAR: - case OP_MINSTAR: - case OP_PLUS: - case OP_MINPLUS: - case OP_QUERY: - case OP_MINQUERY: - c = *ecode++ - OP_STAR; - minimize = (c & 1) != 0; - min = rep_min[c]; /* Pick up values from tables; */ - max = rep_max[c]; /* zero for max => infinity */ - if (max == 0) max = INT_MAX; - - /* Common code for all repeated single-character matches. We can give - up quickly if there are fewer than the minimum number of characters left in - the subject. */ - - REPEATCHAR: -#ifdef SUPPORT_UTF8 - if (utf8) - { - length = 1; - charptr = ecode; - GETCHARLEN(fc, ecode, length); - if (min * length > md->end_subject - eptr) RRETURN(MATCH_NOMATCH); - ecode += length; - - /* Handle multibyte character matching specially here. There is - support for caseless matching if UCP support is present. */ - - if (length > 1) - { -#ifdef SUPPORT_UCP - unsigned int othercase; - if ((ims & PCRE_CASELESS) != 0 && - (othercase = UCD_OTHERCASE(fc)) != fc) - oclength = _pcre_ord2utf8(othercase, occhars); - else oclength = 0; -#endif /* SUPPORT_UCP */ - - for (i = 1; i <= min; i++) - { - if (memcmp(eptr, charptr, length) == 0) eptr += length; -#ifdef SUPPORT_UCP - /* Need braces because of following else */ - else if (oclength == 0) { RRETURN(MATCH_NOMATCH); } - else - { - if (memcmp(eptr, occhars, oclength) != 0) RRETURN(MATCH_NOMATCH); - eptr += oclength; - } -#else /* without SUPPORT_UCP */ - else { RRETURN(MATCH_NOMATCH); } -#endif /* SUPPORT_UCP */ - } - - if (min == max) continue; - - if (minimize) - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM22); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - if (memcmp(eptr, charptr, length) == 0) eptr += length; -#ifdef SUPPORT_UCP - /* Need braces because of following else */ - else if (oclength == 0) { RRETURN(MATCH_NOMATCH); } - else - { - if (memcmp(eptr, occhars, oclength) != 0) RRETURN(MATCH_NOMATCH); - eptr += oclength; - } -#else /* without SUPPORT_UCP */ - else { RRETURN (MATCH_NOMATCH); } -#endif /* SUPPORT_UCP */ - } - /* Control never gets here */ - } - - else /* Maximize */ - { - pp = eptr; - for (i = min; i < max; i++) - { - if (eptr > md->end_subject - length) break; - if (memcmp(eptr, charptr, length) == 0) eptr += length; -#ifdef SUPPORT_UCP - else if (oclength == 0) break; - else - { - if (memcmp(eptr, occhars, oclength) != 0) break; - eptr += oclength; - } -#else /* without SUPPORT_UCP */ - else break; -#endif /* SUPPORT_UCP */ - } - - if (possessive) continue; - for(;;) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM23); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (eptr == pp) RRETURN(MATCH_NOMATCH); -#ifdef SUPPORT_UCP - eptr--; - BACKCHAR(eptr); -#else /* without SUPPORT_UCP */ - eptr -= length; -#endif /* SUPPORT_UCP */ - } - } - /* Control never gets here */ - } - - /* If the length of a UTF-8 character is 1, we fall through here, and - obey the code as for non-UTF-8 characters below, though in this case the - value of fc will always be < 128. */ - } - else -#endif /* SUPPORT_UTF8 */ - - /* When not in UTF-8 mode, load a single-byte character. */ - { - if (min > md->end_subject - eptr) RRETURN(MATCH_NOMATCH); - fc = *ecode++; - } - - /* The value of fc at this point is always less than 256, though we may or - may not be in UTF-8 mode. The code is duplicated for the caseless and - caseful cases, for speed, since matching characters is likely to be quite - common. First, ensure the minimum number of matches are present. If min = - max, continue at the same level without recursing. Otherwise, if - minimizing, keep trying the rest of the expression and advancing one - matching character if failing, up to the maximum. Alternatively, if - maximizing, find the maximum number of characters and work backwards. */ - - DPRINTF(("matching %c{%d,%d} against subject %.*s\n", fc, min, max, - max, eptr)); - - if ((ims & PCRE_CASELESS) != 0) - { - fc = md->lcc[fc]; - for (i = 1; i <= min; i++) - if (fc != md->lcc[*eptr++]) RRETURN(MATCH_NOMATCH); - if (min == max) continue; - if (minimize) - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM24); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject || - fc != md->lcc[*eptr++]) - RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - } - else /* Maximize */ - { - pp = eptr; - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || fc != md->lcc[*eptr]) break; - eptr++; - } - if (possessive) continue; - while (eptr >= pp) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM25); - eptr--; - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - } - RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - } - - /* Caseful comparisons (includes all multi-byte characters) */ - - else - { - for (i = 1; i <= min; i++) if (fc != *eptr++) RRETURN(MATCH_NOMATCH); - if (min == max) continue; - if (minimize) - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM26); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject || fc != *eptr++) - RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - } - else /* Maximize */ - { - pp = eptr; - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || fc != *eptr) break; - eptr++; - } - if (possessive) continue; - while (eptr >= pp) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM27); - eptr--; - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - } - RRETURN(MATCH_NOMATCH); - } - } - /* Control never gets here */ - - /* Match a negated single one-byte character. The character we are - checking can be multibyte. */ - - case OP_NOT: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - ecode++; - GETCHARINCTEST(c, eptr); - if ((ims & PCRE_CASELESS) != 0) - { -#ifdef SUPPORT_UTF8 - if (c < 256) -#endif - c = md->lcc[c]; - if (md->lcc[*ecode++] == c) RRETURN(MATCH_NOMATCH); - } - else - { - if (*ecode++ == c) RRETURN(MATCH_NOMATCH); - } - break; - - /* Match a negated single one-byte character repeatedly. This is almost a - repeat of the code for a repeated single character, but I haven't found a - nice way of commoning these up that doesn't require a test of the - positive/negative option for each character match. Maybe that wouldn't add - very much to the time taken, but character matching *is* what this is all - about... */ - - case OP_NOTEXACT: - min = max = GET2(ecode, 1); - ecode += 3; - goto REPEATNOTCHAR; - - case OP_NOTUPTO: - case OP_NOTMINUPTO: - min = 0; - max = GET2(ecode, 1); - minimize = *ecode == OP_NOTMINUPTO; - ecode += 3; - goto REPEATNOTCHAR; - - case OP_NOTPOSSTAR: - possessive = TRUE; - min = 0; - max = INT_MAX; - ecode++; - goto REPEATNOTCHAR; - - case OP_NOTPOSPLUS: - possessive = TRUE; - min = 1; - max = INT_MAX; - ecode++; - goto REPEATNOTCHAR; - - case OP_NOTPOSQUERY: - possessive = TRUE; - min = 0; - max = 1; - ecode++; - goto REPEATNOTCHAR; - - case OP_NOTPOSUPTO: - possessive = TRUE; - min = 0; - max = GET2(ecode, 1); - ecode += 3; - goto REPEATNOTCHAR; - - case OP_NOTSTAR: - case OP_NOTMINSTAR: - case OP_NOTPLUS: - case OP_NOTMINPLUS: - case OP_NOTQUERY: - case OP_NOTMINQUERY: - c = *ecode++ - OP_NOTSTAR; - minimize = (c & 1) != 0; - min = rep_min[c]; /* Pick up values from tables; */ - max = rep_max[c]; /* zero for max => infinity */ - if (max == 0) max = INT_MAX; - - /* Common code for all repeated single-byte matches. We can give up quickly - if there are fewer than the minimum number of bytes left in the - subject. */ - - REPEATNOTCHAR: - if (min > md->end_subject - eptr) RRETURN(MATCH_NOMATCH); - fc = *ecode++; - - /* The code is duplicated for the caseless and caseful cases, for speed, - since matching characters is likely to be quite common. First, ensure the - minimum number of matches are present. If min = max, continue at the same - level without recursing. Otherwise, if minimizing, keep trying the rest of - the expression and advancing one matching character if failing, up to the - maximum. Alternatively, if maximizing, find the maximum number of - characters and work backwards. */ - - DPRINTF(("negative matching %c{%d,%d} against subject %.*s\n", fc, min, max, - max, eptr)); - - if ((ims & PCRE_CASELESS) != 0) - { - fc = md->lcc[fc]; - -#ifdef SUPPORT_UTF8 - /* UTF-8 mode */ - if (utf8) - { - register unsigned int d; - for (i = 1; i <= min; i++) - { - GETCHARINC(d, eptr); - if (d < 256) d = md->lcc[d]; - if (fc == d) RRETURN(MATCH_NOMATCH); - } - } - else -#endif - - /* Not UTF-8 mode */ - { - for (i = 1; i <= min; i++) - if (fc == md->lcc[*eptr++]) RRETURN(MATCH_NOMATCH); - } - - if (min == max) continue; - - if (minimize) - { -#ifdef SUPPORT_UTF8 - /* UTF-8 mode */ - if (utf8) - { - register unsigned int d; - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM28); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(d, eptr); - if (d < 256) d = md->lcc[d]; - if (fc == d) RRETURN(MATCH_NOMATCH); - - } - } - else -#endif - /* Not UTF-8 mode */ - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM29); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject || fc == md->lcc[*eptr++]) - RRETURN(MATCH_NOMATCH); - } - } - /* Control never gets here */ - } - - /* Maximize case */ - - else - { - pp = eptr; - -#ifdef SUPPORT_UTF8 - /* UTF-8 mode */ - if (utf8) - { - register unsigned int d; - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(d, eptr, len); - if (d < 256) d = md->lcc[d]; - if (fc == d) break; - eptr += len; - } - if (possessive) continue; - for(;;) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM30); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (eptr-- == pp) break; /* Stop if tried at original pos */ - BACKCHAR(eptr); - } - } - else -#endif - /* Not UTF-8 mode */ - { - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || fc == md->lcc[*eptr]) break; - eptr++; - } - if (possessive) continue; - while (eptr >= pp) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM31); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - eptr--; - } - } - - RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - } - - /* Caseful comparisons */ - - else - { -#ifdef SUPPORT_UTF8 - /* UTF-8 mode */ - if (utf8) - { - register unsigned int d; - for (i = 1; i <= min; i++) - { - GETCHARINC(d, eptr); - if (fc == d) RRETURN(MATCH_NOMATCH); - } - } - else -#endif - /* Not UTF-8 mode */ - { - for (i = 1; i <= min; i++) - if (fc == *eptr++) RRETURN(MATCH_NOMATCH); - } - - if (min == max) continue; - - if (minimize) - { -#ifdef SUPPORT_UTF8 - /* UTF-8 mode */ - if (utf8) - { - register unsigned int d; - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM32); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(d, eptr); - if (fc == d) RRETURN(MATCH_NOMATCH); - } - } - else -#endif - /* Not UTF-8 mode */ - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM33); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject || fc == *eptr++) - RRETURN(MATCH_NOMATCH); - } - } - /* Control never gets here */ - } - - /* Maximize case */ - - else - { - pp = eptr; - -#ifdef SUPPORT_UTF8 - /* UTF-8 mode */ - if (utf8) - { - register unsigned int d; - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(d, eptr, len); - if (fc == d) break; - eptr += len; - } - if (possessive) continue; - for(;;) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM34); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (eptr-- == pp) break; /* Stop if tried at original pos */ - BACKCHAR(eptr); - } - } - else -#endif - /* Not UTF-8 mode */ - { - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || fc == *eptr) break; - eptr++; - } - if (possessive) continue; - while (eptr >= pp) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM35); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - eptr--; - } - } - - RRETURN(MATCH_NOMATCH); - } - } - /* Control never gets here */ - - /* Match a single character type repeatedly; several different opcodes - share code. This is very similar to the code for single characters, but we - repeat it in the interests of efficiency. */ - - case OP_TYPEEXACT: - min = max = GET2(ecode, 1); - minimize = TRUE; - ecode += 3; - goto REPEATTYPE; - - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - min = 0; - max = GET2(ecode, 1); - minimize = *ecode == OP_TYPEMINUPTO; - ecode += 3; - goto REPEATTYPE; - - case OP_TYPEPOSSTAR: - possessive = TRUE; - min = 0; - max = INT_MAX; - ecode++; - goto REPEATTYPE; - - case OP_TYPEPOSPLUS: - possessive = TRUE; - min = 1; - max = INT_MAX; - ecode++; - goto REPEATTYPE; - - case OP_TYPEPOSQUERY: - possessive = TRUE; - min = 0; - max = 1; - ecode++; - goto REPEATTYPE; - - case OP_TYPEPOSUPTO: - possessive = TRUE; - min = 0; - max = GET2(ecode, 1); - ecode += 3; - goto REPEATTYPE; - - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - c = *ecode++ - OP_TYPESTAR; - minimize = (c & 1) != 0; - min = rep_min[c]; /* Pick up values from tables; */ - max = rep_max[c]; /* zero for max => infinity */ - if (max == 0) max = INT_MAX; - - /* Common code for all repeated single character type matches. Note that - in UTF-8 mode, '.' matches a character of any length, but for the other - character types, the valid characters are all one-byte long. */ - - REPEATTYPE: - ctype = *ecode++; /* Code for the character type */ - -#ifdef SUPPORT_UCP - if (ctype == OP_PROP || ctype == OP_NOTPROP) - { - prop_fail_result = ctype == OP_NOTPROP; - prop_type = *ecode++; - prop_value = *ecode++; - } - else prop_type = -1; -#endif - - /* First, ensure the minimum number of matches are present. Use inline - code for maximizing the speed, and do the type test once at the start - (i.e. keep it out of the loop). Also we can test that there are at least - the minimum number of bytes before we start. This isn't as effective in - UTF-8 mode, but it does no harm. Separate the UTF-8 code completely as that - is tidier. Also separate the UCP code, which can be the same for both UTF-8 - and single-bytes. */ - - if (min > md->end_subject - eptr) RRETURN(MATCH_NOMATCH); - if (min > 0) - { -#ifdef SUPPORT_UCP - if (prop_type >= 0) - { - switch(prop_type) - { - case PT_ANY: - if (prop_fail_result) RRETURN(MATCH_NOMATCH); - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - } - break; - - case PT_LAMP: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - prop_chartype = UCD_CHARTYPE(c); - if ((prop_chartype == ucp_Lu || - prop_chartype == ucp_Ll || - prop_chartype == ucp_Lt) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - break; - - case PT_GC: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - prop_category = UCD_CATEGORY(c); - if ((prop_category == prop_value) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - break; - - case PT_PC: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - prop_chartype = UCD_CHARTYPE(c); - if ((prop_chartype == prop_value) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - break; - - case PT_SC: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - prop_script = UCD_SCRIPT(c); - if ((prop_script == prop_value) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - break; - - default: - RRETURN(PCRE_ERROR_INTERNAL); - } - } - - /* Match extended Unicode sequences. We will get here only if the - support is in the binary; otherwise a compile-time error occurs. */ - - else if (ctype == OP_EXTUNI) - { - for (i = 1; i <= min; i++) - { - GETCHARINCTEST(c, eptr); - prop_category = UCD_CATEGORY(c); - if (prop_category == ucp_M) RRETURN(MATCH_NOMATCH); - while (eptr < md->end_subject) - { - int len = 1; - if (!utf8) c = *eptr; else - { - GETCHARLEN(c, eptr, len); - } - prop_category = UCD_CATEGORY(c); - if (prop_category != ucp_M) break; - eptr += len; - } - } - } - - else -#endif /* SUPPORT_UCP */ - -/* Handle all other cases when the coding is UTF-8 */ - -#ifdef SUPPORT_UTF8 - if (utf8) switch(ctype) - { - case OP_ANY: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject || IS_NEWLINE(eptr)) - RRETURN(MATCH_NOMATCH); - eptr++; - while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; - } - break; - - case OP_ALLANY: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - eptr++; - while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; - } - break; - - case OP_ANYBYTE: - eptr += min; - break; - - case OP_ANYNL: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - switch(c) - { - default: RRETURN(MATCH_NOMATCH); - case 0x000d: - if (eptr < md->end_subject && *eptr == 0x0a) eptr++; - break; - - case 0x000a: - break; - - case 0x000b: - case 0x000c: - case 0x0085: - case 0x2028: - case 0x2029: - if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); - break; - } - } - break; - - case OP_NOT_HSPACE: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - switch(c) - { - default: break; - case 0x09: /* HT */ - case 0x20: /* SPACE */ - case 0xa0: /* NBSP */ - case 0x1680: /* OGHAM SPACE MARK */ - case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ - case 0x2000: /* EN QUAD */ - case 0x2001: /* EM QUAD */ - case 0x2002: /* EN SPACE */ - case 0x2003: /* EM SPACE */ - case 0x2004: /* THREE-PER-EM SPACE */ - case 0x2005: /* FOUR-PER-EM SPACE */ - case 0x2006: /* SIX-PER-EM SPACE */ - case 0x2007: /* FIGURE SPACE */ - case 0x2008: /* PUNCTUATION SPACE */ - case 0x2009: /* THIN SPACE */ - case 0x200A: /* HAIR SPACE */ - case 0x202f: /* NARROW NO-BREAK SPACE */ - case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ - case 0x3000: /* IDEOGRAPHIC SPACE */ - RRETURN(MATCH_NOMATCH); - } - } - break; - - case OP_HSPACE: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - switch(c) - { - default: RRETURN(MATCH_NOMATCH); - case 0x09: /* HT */ - case 0x20: /* SPACE */ - case 0xa0: /* NBSP */ - case 0x1680: /* OGHAM SPACE MARK */ - case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ - case 0x2000: /* EN QUAD */ - case 0x2001: /* EM QUAD */ - case 0x2002: /* EN SPACE */ - case 0x2003: /* EM SPACE */ - case 0x2004: /* THREE-PER-EM SPACE */ - case 0x2005: /* FOUR-PER-EM SPACE */ - case 0x2006: /* SIX-PER-EM SPACE */ - case 0x2007: /* FIGURE SPACE */ - case 0x2008: /* PUNCTUATION SPACE */ - case 0x2009: /* THIN SPACE */ - case 0x200A: /* HAIR SPACE */ - case 0x202f: /* NARROW NO-BREAK SPACE */ - case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ - case 0x3000: /* IDEOGRAPHIC SPACE */ - break; - } - } - break; - - case OP_NOT_VSPACE: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - switch(c) - { - default: break; - case 0x0a: /* LF */ - case 0x0b: /* VT */ - case 0x0c: /* FF */ - case 0x0d: /* CR */ - case 0x85: /* NEL */ - case 0x2028: /* LINE SEPARATOR */ - case 0x2029: /* PARAGRAPH SEPARATOR */ - RRETURN(MATCH_NOMATCH); - } - } - break; - - case OP_VSPACE: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - switch(c) - { - default: RRETURN(MATCH_NOMATCH); - case 0x0a: /* LF */ - case 0x0b: /* VT */ - case 0x0c: /* FF */ - case 0x0d: /* CR */ - case 0x85: /* NEL */ - case 0x2028: /* LINE SEPARATOR */ - case 0x2029: /* PARAGRAPH SEPARATOR */ - break; - } - } - break; - - case OP_NOT_DIGIT: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - if (c < 128 && (md->ctypes[c] & ctype_digit) != 0) - RRETURN(MATCH_NOMATCH); - } - break; - - case OP_DIGIT: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject || - *eptr >= 128 || (md->ctypes[*eptr++] & ctype_digit) == 0) - RRETURN(MATCH_NOMATCH); - /* No need to skip more bytes - we know it's a 1-byte character */ - } - break; - - case OP_NOT_WHITESPACE: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject || - (*eptr < 128 && (md->ctypes[*eptr] & ctype_space) != 0)) - RRETURN(MATCH_NOMATCH); - while (++eptr < md->end_subject && (*eptr & 0xc0) == 0x80); - } - break; - - case OP_WHITESPACE: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject || - *eptr >= 128 || (md->ctypes[*eptr++] & ctype_space) == 0) - RRETURN(MATCH_NOMATCH); - /* No need to skip more bytes - we know it's a 1-byte character */ - } - break; - - case OP_NOT_WORDCHAR: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject || - (*eptr < 128 && (md->ctypes[*eptr] & ctype_word) != 0)) - RRETURN(MATCH_NOMATCH); - while (++eptr < md->end_subject && (*eptr & 0xc0) == 0x80); - } - break; - - case OP_WORDCHAR: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject || - *eptr >= 128 || (md->ctypes[*eptr++] & ctype_word) == 0) - RRETURN(MATCH_NOMATCH); - /* No need to skip more bytes - we know it's a 1-byte character */ - } - break; - - default: - RRETURN(PCRE_ERROR_INTERNAL); - } /* End switch(ctype) */ - - else -#endif /* SUPPORT_UTF8 */ - - /* Code for the non-UTF-8 case for minimum matching of operators other - than OP_PROP and OP_NOTPROP. We can assume that there are the minimum - number of bytes present, as this was tested above. */ - - switch(ctype) - { - case OP_ANY: - for (i = 1; i <= min; i++) - { - if (IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH); - eptr++; - } - break; - - case OP_ALLANY: - eptr += min; - break; - - case OP_ANYBYTE: - eptr += min; - break; - - /* Because of the CRLF case, we can't assume the minimum number of - bytes are present in this case. */ - - case OP_ANYNL: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - switch(*eptr++) - { - default: RRETURN(MATCH_NOMATCH); - case 0x000d: - if (eptr < md->end_subject && *eptr == 0x0a) eptr++; - break; - case 0x000a: - break; - - case 0x000b: - case 0x000c: - case 0x0085: - if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); - break; - } - } - break; - - case OP_NOT_HSPACE: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - switch(*eptr++) - { - default: break; - case 0x09: /* HT */ - case 0x20: /* SPACE */ - case 0xa0: /* NBSP */ - RRETURN(MATCH_NOMATCH); - } - } - break; - - case OP_HSPACE: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - switch(*eptr++) - { - default: RRETURN(MATCH_NOMATCH); - case 0x09: /* HT */ - case 0x20: /* SPACE */ - case 0xa0: /* NBSP */ - break; - } - } - break; - - case OP_NOT_VSPACE: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - switch(*eptr++) - { - default: break; - case 0x0a: /* LF */ - case 0x0b: /* VT */ - case 0x0c: /* FF */ - case 0x0d: /* CR */ - case 0x85: /* NEL */ - RRETURN(MATCH_NOMATCH); - } - } - break; - - case OP_VSPACE: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - switch(*eptr++) - { - default: RRETURN(MATCH_NOMATCH); - case 0x0a: /* LF */ - case 0x0b: /* VT */ - case 0x0c: /* FF */ - case 0x0d: /* CR */ - case 0x85: /* NEL */ - break; - } - } - break; - - case OP_NOT_DIGIT: - for (i = 1; i <= min; i++) - if ((md->ctypes[*eptr++] & ctype_digit) != 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_DIGIT: - for (i = 1; i <= min; i++) - if ((md->ctypes[*eptr++] & ctype_digit) == 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_NOT_WHITESPACE: - for (i = 1; i <= min; i++) - if ((md->ctypes[*eptr++] & ctype_space) != 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_WHITESPACE: - for (i = 1; i <= min; i++) - if ((md->ctypes[*eptr++] & ctype_space) == 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_NOT_WORDCHAR: - for (i = 1; i <= min; i++) - if ((md->ctypes[*eptr++] & ctype_word) != 0) - RRETURN(MATCH_NOMATCH); - break; - - case OP_WORDCHAR: - for (i = 1; i <= min; i++) - if ((md->ctypes[*eptr++] & ctype_word) == 0) - RRETURN(MATCH_NOMATCH); - break; - - default: - RRETURN(PCRE_ERROR_INTERNAL); - } - } - - /* If min = max, continue at the same level without recursing */ - - if (min == max) continue; - - /* If minimizing, we have to test the rest of the pattern before each - subsequent match. Again, separate the UTF-8 case for speed, and also - separate the UCP cases. */ - - if (minimize) - { -#ifdef SUPPORT_UCP - if (prop_type >= 0) - { - switch(prop_type) - { - case PT_ANY: - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM36); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - if (prop_fail_result) RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - - case PT_LAMP: - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM37); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - prop_chartype = UCD_CHARTYPE(c); - if ((prop_chartype == ucp_Lu || - prop_chartype == ucp_Ll || - prop_chartype == ucp_Lt) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - - case PT_GC: - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM38); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - prop_category = UCD_CATEGORY(c); - if ((prop_category == prop_value) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - - case PT_PC: - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM39); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - prop_chartype = UCD_CHARTYPE(c); - if ((prop_chartype == prop_value) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - - case PT_SC: - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM40); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - prop_script = UCD_SCRIPT(c); - if ((prop_script == prop_value) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - - default: - RRETURN(PCRE_ERROR_INTERNAL); - } - } - - /* Match extended Unicode sequences. We will get here only if the - support is in the binary; otherwise a compile-time error occurs. */ - - else if (ctype == OP_EXTUNI) - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM41); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - prop_category = UCD_CATEGORY(c); - if (prop_category == ucp_M) RRETURN(MATCH_NOMATCH); - while (eptr < md->end_subject) - { - int len = 1; - if (!utf8) c = *eptr; else - { - GETCHARLEN(c, eptr, len); - } - prop_category = UCD_CATEGORY(c); - if (prop_category != ucp_M) break; - eptr += len; - } - } - } - - else -#endif /* SUPPORT_UCP */ - -#ifdef SUPPORT_UTF8 - /* UTF-8 mode */ - if (utf8) - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM42); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject || - (ctype == OP_ANY && IS_NEWLINE(eptr))) - RRETURN(MATCH_NOMATCH); - - GETCHARINC(c, eptr); - switch(ctype) - { - case OP_ANY: /* This is the non-NL case */ - case OP_ALLANY: - case OP_ANYBYTE: - break; - - case OP_ANYNL: - switch(c) - { - default: RRETURN(MATCH_NOMATCH); - case 0x000d: - if (eptr < md->end_subject && *eptr == 0x0a) eptr++; - break; - case 0x000a: - break; - - case 0x000b: - case 0x000c: - case 0x0085: - case 0x2028: - case 0x2029: - if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); - break; - } - break; - - case OP_NOT_HSPACE: - switch(c) - { - default: break; - case 0x09: /* HT */ - case 0x20: /* SPACE */ - case 0xa0: /* NBSP */ - case 0x1680: /* OGHAM SPACE MARK */ - case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ - case 0x2000: /* EN QUAD */ - case 0x2001: /* EM QUAD */ - case 0x2002: /* EN SPACE */ - case 0x2003: /* EM SPACE */ - case 0x2004: /* THREE-PER-EM SPACE */ - case 0x2005: /* FOUR-PER-EM SPACE */ - case 0x2006: /* SIX-PER-EM SPACE */ - case 0x2007: /* FIGURE SPACE */ - case 0x2008: /* PUNCTUATION SPACE */ - case 0x2009: /* THIN SPACE */ - case 0x200A: /* HAIR SPACE */ - case 0x202f: /* NARROW NO-BREAK SPACE */ - case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ - case 0x3000: /* IDEOGRAPHIC SPACE */ - RRETURN(MATCH_NOMATCH); - } - break; - - case OP_HSPACE: - switch(c) - { - default: RRETURN(MATCH_NOMATCH); - case 0x09: /* HT */ - case 0x20: /* SPACE */ - case 0xa0: /* NBSP */ - case 0x1680: /* OGHAM SPACE MARK */ - case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ - case 0x2000: /* EN QUAD */ - case 0x2001: /* EM QUAD */ - case 0x2002: /* EN SPACE */ - case 0x2003: /* EM SPACE */ - case 0x2004: /* THREE-PER-EM SPACE */ - case 0x2005: /* FOUR-PER-EM SPACE */ - case 0x2006: /* SIX-PER-EM SPACE */ - case 0x2007: /* FIGURE SPACE */ - case 0x2008: /* PUNCTUATION SPACE */ - case 0x2009: /* THIN SPACE */ - case 0x200A: /* HAIR SPACE */ - case 0x202f: /* NARROW NO-BREAK SPACE */ - case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ - case 0x3000: /* IDEOGRAPHIC SPACE */ - break; - } - break; - - case OP_NOT_VSPACE: - switch(c) - { - default: break; - case 0x0a: /* LF */ - case 0x0b: /* VT */ - case 0x0c: /* FF */ - case 0x0d: /* CR */ - case 0x85: /* NEL */ - case 0x2028: /* LINE SEPARATOR */ - case 0x2029: /* PARAGRAPH SEPARATOR */ - RRETURN(MATCH_NOMATCH); - } - break; - - case OP_VSPACE: - switch(c) - { - default: RRETURN(MATCH_NOMATCH); - case 0x0a: /* LF */ - case 0x0b: /* VT */ - case 0x0c: /* FF */ - case 0x0d: /* CR */ - case 0x85: /* NEL */ - case 0x2028: /* LINE SEPARATOR */ - case 0x2029: /* PARAGRAPH SEPARATOR */ - break; - } - break; - - case OP_NOT_DIGIT: - if (c < 256 && (md->ctypes[c] & ctype_digit) != 0) - RRETURN(MATCH_NOMATCH); - break; - - case OP_DIGIT: - if (c >= 256 || (md->ctypes[c] & ctype_digit) == 0) - RRETURN(MATCH_NOMATCH); - break; - - case OP_NOT_WHITESPACE: - if (c < 256 && (md->ctypes[c] & ctype_space) != 0) - RRETURN(MATCH_NOMATCH); - break; - - case OP_WHITESPACE: - if (c >= 256 || (md->ctypes[c] & ctype_space) == 0) - RRETURN(MATCH_NOMATCH); - break; - - case OP_NOT_WORDCHAR: - if (c < 256 && (md->ctypes[c] & ctype_word) != 0) - RRETURN(MATCH_NOMATCH); - break; - - case OP_WORDCHAR: - if (c >= 256 || (md->ctypes[c] & ctype_word) == 0) - RRETURN(MATCH_NOMATCH); - break; - - default: - RRETURN(PCRE_ERROR_INTERNAL); - } - } - } - else -#endif - /* Not UTF-8 mode */ - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM43); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject || - (ctype == OP_ANY && IS_NEWLINE(eptr))) - RRETURN(MATCH_NOMATCH); - - c = *eptr++; - switch(ctype) - { - case OP_ANY: /* This is the non-NL case */ - case OP_ALLANY: - case OP_ANYBYTE: - break; - - case OP_ANYNL: - switch(c) - { - default: RRETURN(MATCH_NOMATCH); - case 0x000d: - if (eptr < md->end_subject && *eptr == 0x0a) eptr++; - break; - - case 0x000a: - break; - - case 0x000b: - case 0x000c: - case 0x0085: - if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); - break; - } - break; - - case OP_NOT_HSPACE: - switch(c) - { - default: break; - case 0x09: /* HT */ - case 0x20: /* SPACE */ - case 0xa0: /* NBSP */ - RRETURN(MATCH_NOMATCH); - } - break; - - case OP_HSPACE: - switch(c) - { - default: RRETURN(MATCH_NOMATCH); - case 0x09: /* HT */ - case 0x20: /* SPACE */ - case 0xa0: /* NBSP */ - break; - } - break; - - case OP_NOT_VSPACE: - switch(c) - { - default: break; - case 0x0a: /* LF */ - case 0x0b: /* VT */ - case 0x0c: /* FF */ - case 0x0d: /* CR */ - case 0x85: /* NEL */ - RRETURN(MATCH_NOMATCH); - } - break; - - case OP_VSPACE: - switch(c) - { - default: RRETURN(MATCH_NOMATCH); - case 0x0a: /* LF */ - case 0x0b: /* VT */ - case 0x0c: /* FF */ - case 0x0d: /* CR */ - case 0x85: /* NEL */ - break; - } - break; - - case OP_NOT_DIGIT: - if ((md->ctypes[c] & ctype_digit) != 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_DIGIT: - if ((md->ctypes[c] & ctype_digit) == 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_NOT_WHITESPACE: - if ((md->ctypes[c] & ctype_space) != 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_WHITESPACE: - if ((md->ctypes[c] & ctype_space) == 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_NOT_WORDCHAR: - if ((md->ctypes[c] & ctype_word) != 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_WORDCHAR: - if ((md->ctypes[c] & ctype_word) == 0) RRETURN(MATCH_NOMATCH); - break; - - default: - RRETURN(PCRE_ERROR_INTERNAL); - } - } - } - /* Control never gets here */ - } - - /* If maximizing, it is worth using inline code for speed, doing the type - test once at the start (i.e. keep it out of the loop). Again, keep the - UTF-8 and UCP stuff separate. */ - - else - { - pp = eptr; /* Remember where we started */ - -#ifdef SUPPORT_UCP - if (prop_type >= 0) - { - switch(prop_type) - { - case PT_ANY: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - if (prop_fail_result) break; - eptr+= len; - } - break; - - case PT_LAMP: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - prop_chartype = UCD_CHARTYPE(c); - if ((prop_chartype == ucp_Lu || - prop_chartype == ucp_Ll || - prop_chartype == ucp_Lt) == prop_fail_result) - break; - eptr+= len; - } - break; - - case PT_GC: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - prop_category = UCD_CATEGORY(c); - if ((prop_category == prop_value) == prop_fail_result) - break; - eptr+= len; - } - break; - - case PT_PC: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - prop_chartype = UCD_CHARTYPE(c); - if ((prop_chartype == prop_value) == prop_fail_result) - break; - eptr+= len; - } - break; - - case PT_SC: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - prop_script = UCD_SCRIPT(c); - if ((prop_script == prop_value) == prop_fail_result) - break; - eptr+= len; - } - break; - } - - /* eptr is now past the end of the maximum run */ - - if (possessive) continue; - for(;;) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM44); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (eptr-- == pp) break; /* Stop if tried at original pos */ - if (utf8) BACKCHAR(eptr); - } - } - - /* Match extended Unicode sequences. We will get here only if the - support is in the binary; otherwise a compile-time error occurs. */ - - else if (ctype == OP_EXTUNI) - { - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) break; - GETCHARINCTEST(c, eptr); - prop_category = UCD_CATEGORY(c); - if (prop_category == ucp_M) break; - while (eptr < md->end_subject) - { - int len = 1; - if (!utf8) c = *eptr; else - { - GETCHARLEN(c, eptr, len); - } - prop_category = UCD_CATEGORY(c); - if (prop_category != ucp_M) break; - eptr += len; - } - } - - /* eptr is now past the end of the maximum run */ - - if (possessive) continue; - for(;;) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM45); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (eptr-- == pp) break; /* Stop if tried at original pos */ - for (;;) /* Move back over one extended */ - { - int len = 1; - if (!utf8) c = *eptr; else - { - BACKCHAR(eptr); - GETCHARLEN(c, eptr, len); - } - prop_category = UCD_CATEGORY(c); - if (prop_category != ucp_M) break; - eptr--; - } - } - } - - else -#endif /* SUPPORT_UCP */ - -#ifdef SUPPORT_UTF8 - /* UTF-8 mode */ - - if (utf8) - { - switch(ctype) - { - case OP_ANY: - if (max < INT_MAX) - { - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || IS_NEWLINE(eptr)) break; - eptr++; - while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; - } - } - - /* Handle unlimited UTF-8 repeat */ - - else - { - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || IS_NEWLINE(eptr)) break; - eptr++; - while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; - } - } - break; - - case OP_ALLANY: - if (max < INT_MAX) - { - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) break; - eptr++; - while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; - } - } - else eptr = md->end_subject; /* Unlimited UTF-8 repeat */ - break; - - /* The byte case is the same as non-UTF8 */ - - case OP_ANYBYTE: - c = max - min; - if (c > (unsigned int)(md->end_subject - eptr)) - c = md->end_subject - eptr; - eptr += c; - break; - - case OP_ANYNL: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - if (c == 0x000d) - { - if (++eptr >= md->end_subject) break; - if (*eptr == 0x000a) eptr++; - } - else - { - if (c != 0x000a && - (md->bsr_anycrlf || - (c != 0x000b && c != 0x000c && - c != 0x0085 && c != 0x2028 && c != 0x2029))) - break; - eptr += len; - } - } - break; - - case OP_NOT_HSPACE: - case OP_HSPACE: - for (i = min; i < max; i++) - { - BOOL gotspace; - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - switch(c) - { - default: gotspace = FALSE; break; - case 0x09: /* HT */ - case 0x20: /* SPACE */ - case 0xa0: /* NBSP */ - case 0x1680: /* OGHAM SPACE MARK */ - case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ - case 0x2000: /* EN QUAD */ - case 0x2001: /* EM QUAD */ - case 0x2002: /* EN SPACE */ - case 0x2003: /* EM SPACE */ - case 0x2004: /* THREE-PER-EM SPACE */ - case 0x2005: /* FOUR-PER-EM SPACE */ - case 0x2006: /* SIX-PER-EM SPACE */ - case 0x2007: /* FIGURE SPACE */ - case 0x2008: /* PUNCTUATION SPACE */ - case 0x2009: /* THIN SPACE */ - case 0x200A: /* HAIR SPACE */ - case 0x202f: /* NARROW NO-BREAK SPACE */ - case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ - case 0x3000: /* IDEOGRAPHIC SPACE */ - gotspace = TRUE; - break; - } - if (gotspace == (ctype == OP_NOT_HSPACE)) break; - eptr += len; - } - break; - - case OP_NOT_VSPACE: - case OP_VSPACE: - for (i = min; i < max; i++) - { - BOOL gotspace; - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - switch(c) - { - default: gotspace = FALSE; break; - case 0x0a: /* LF */ - case 0x0b: /* VT */ - case 0x0c: /* FF */ - case 0x0d: /* CR */ - case 0x85: /* NEL */ - case 0x2028: /* LINE SEPARATOR */ - case 0x2029: /* PARAGRAPH SEPARATOR */ - gotspace = TRUE; - break; - } - if (gotspace == (ctype == OP_NOT_VSPACE)) break; - eptr += len; - } - break; - - case OP_NOT_DIGIT: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - if (c < 256 && (md->ctypes[c] & ctype_digit) != 0) break; - eptr+= len; - } - break; - - case OP_DIGIT: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - if (c >= 256 ||(md->ctypes[c] & ctype_digit) == 0) break; - eptr+= len; - } - break; - - case OP_NOT_WHITESPACE: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - if (c < 256 && (md->ctypes[c] & ctype_space) != 0) break; - eptr+= len; - } - break; - - case OP_WHITESPACE: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - if (c >= 256 ||(md->ctypes[c] & ctype_space) == 0) break; - eptr+= len; - } - break; - - case OP_NOT_WORDCHAR: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - if (c < 256 && (md->ctypes[c] & ctype_word) != 0) break; - eptr+= len; - } - break; - - case OP_WORDCHAR: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - if (c >= 256 || (md->ctypes[c] & ctype_word) == 0) break; - eptr+= len; - } - break; - - default: - RRETURN(PCRE_ERROR_INTERNAL); - } - - /* eptr is now past the end of the maximum run */ - - if (possessive) continue; - for(;;) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM46); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (eptr-- == pp) break; /* Stop if tried at original pos */ - BACKCHAR(eptr); - } - } - else -#endif /* SUPPORT_UTF8 */ - - /* Not UTF-8 mode */ - { - switch(ctype) - { - case OP_ANY: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || IS_NEWLINE(eptr)) break; - eptr++; - } - break; - - case OP_ALLANY: - case OP_ANYBYTE: - c = max - min; - if (c > (unsigned int)(md->end_subject - eptr)) - c = md->end_subject - eptr; - eptr += c; - break; - - case OP_ANYNL: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) break; - c = *eptr; - if (c == 0x000d) - { - if (++eptr >= md->end_subject) break; - if (*eptr == 0x000a) eptr++; - } - else - { - if (c != 0x000a && - (md->bsr_anycrlf || - (c != 0x000b && c != 0x000c && c != 0x0085))) - break; - eptr++; - } - } - break; - - case OP_NOT_HSPACE: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) break; - c = *eptr; - if (c == 0x09 || c == 0x20 || c == 0xa0) break; - eptr++; - } - break; - - case OP_HSPACE: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) break; - c = *eptr; - if (c != 0x09 && c != 0x20 && c != 0xa0) break; - eptr++; - } - break; - - case OP_NOT_VSPACE: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) break; - c = *eptr; - if (c == 0x0a || c == 0x0b || c == 0x0c || c == 0x0d || c == 0x85) - break; - eptr++; - } - break; - - case OP_VSPACE: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) break; - c = *eptr; - if (c != 0x0a && c != 0x0b && c != 0x0c && c != 0x0d && c != 0x85) - break; - eptr++; - } - break; - - case OP_NOT_DIGIT: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || (md->ctypes[*eptr] & ctype_digit) != 0) - break; - eptr++; - } - break; - - case OP_DIGIT: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || (md->ctypes[*eptr] & ctype_digit) == 0) - break; - eptr++; - } - break; - - case OP_NOT_WHITESPACE: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || (md->ctypes[*eptr] & ctype_space) != 0) - break; - eptr++; - } - break; - - case OP_WHITESPACE: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || (md->ctypes[*eptr] & ctype_space) == 0) - break; - eptr++; - } - break; - - case OP_NOT_WORDCHAR: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || (md->ctypes[*eptr] & ctype_word) != 0) - break; - eptr++; - } - break; - - case OP_WORDCHAR: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || (md->ctypes[*eptr] & ctype_word) == 0) - break; - eptr++; - } - break; - - default: - RRETURN(PCRE_ERROR_INTERNAL); - } - - /* eptr is now past the end of the maximum run */ - - if (possessive) continue; - while (eptr >= pp) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM47); - eptr--; - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - } - } - - /* Get here if we can't make it match with any permitted repetitions */ - - RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - - /* There's been some horrible disaster. Arrival here can only mean there is - something seriously wrong in the code above or the OP_xxx definitions. */ - - default: - DPRINTF(("Unknown opcode %d\n", *ecode)); - RRETURN(PCRE_ERROR_UNKNOWN_OPCODE); - } - - /* Do not stick any code in here without much thought; it is assumed - that "continue" in the code above comes out to here to repeat the main - loop. */ - - } /* End of main loop */ -/* Control never reaches here */ - - -/* When compiling to use the heap rather than the stack for recursive calls to -match(), the RRETURN() macro jumps here. The number that is saved in -frame->Xwhere indicates which label we actually want to return to. */ - -#ifdef NO_RECURSE -#define LBL(val) case val: goto L_RM##val; -HEAP_RETURN: -switch (frame->Xwhere) - { - LBL( 1) LBL( 2) LBL( 3) LBL( 4) LBL( 5) LBL( 6) LBL( 7) LBL( 8) - LBL( 9) LBL(10) LBL(11) LBL(12) LBL(13) LBL(14) LBL(15) LBL(17) - LBL(19) LBL(24) LBL(25) LBL(26) LBL(27) LBL(29) LBL(31) LBL(33) - LBL(35) LBL(43) LBL(47) LBL(48) LBL(49) LBL(50) LBL(51) LBL(52) - LBL(53) LBL(54) -#ifdef SUPPORT_UTF8 - LBL(16) LBL(18) LBL(20) LBL(21) LBL(22) LBL(23) LBL(28) LBL(30) - LBL(32) LBL(34) LBL(42) LBL(46) -#ifdef SUPPORT_UCP - LBL(36) LBL(37) LBL(38) LBL(39) LBL(40) LBL(41) LBL(44) LBL(45) -#endif /* SUPPORT_UCP */ -#endif /* SUPPORT_UTF8 */ - default: - DPRINTF(("jump error in pcre match: label %d non-existent\n", frame->Xwhere)); - return PCRE_ERROR_INTERNAL; - } -#undef LBL -#endif /* NO_RECURSE */ -} - - -/*************************************************************************** -**************************************************************************** - RECURSION IN THE match() FUNCTION - -Undefine all the macros that were defined above to handle this. */ - -#ifdef NO_RECURSE -#undef eptr -#undef ecode -#undef mstart -#undef offset_top -#undef ims -#undef eptrb -#undef flags - -#undef callpat -#undef charptr -#undef data -#undef next -#undef pp -#undef prev -#undef saved_eptr - -#undef new_recursive - -#undef cur_is_word -#undef condition -#undef prev_is_word - -#undef original_ims - -#undef ctype -#undef length -#undef max -#undef min -#undef number -#undef offset -#undef op -#undef save_capture_last -#undef save_offset1 -#undef save_offset2 -#undef save_offset3 -#undef stacksave - -#undef newptrb - -#endif - -/* These two are defined as macros in both cases */ - -#undef fc -#undef fi - -/*************************************************************************** -***************************************************************************/ - - - -/************************************************* -* Execute a Regular Expression * -*************************************************/ - -/* This function applies a compiled re to a subject string and picks out -portions of the string if it matches. Two elements in the vector are set for -each substring: the offsets to the start and end of the substring. - -Arguments: - argument_re points to the compiled expression - extra_data points to extra data or is NULL - subject points to the subject string - length length of subject string (may contain binary zeros) - start_offset where to start in the subject string - options option bits - offsets points to a vector of ints to be filled in with offsets - offsetcount the number of elements in the vector - -Returns: > 0 => success; value is the number of elements filled in - = 0 => success, but offsets is not big enough - -1 => failed to match - < -1 => some kind of unexpected problem -*/ - -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre_exec(const pcre *argument_re, const pcre_extra *extra_data, - PCRE_SPTR subject, int length, int start_offset, int options, int *offsets, - int offsetcount) -{ -int rc, resetcount, ocount; -int first_byte = -1; -int req_byte = -1; -int req_byte2 = -1; -int newline; -unsigned long int ims; -BOOL using_temporary_offsets = FALSE; -BOOL anchored; -BOOL startline; -BOOL firstline; -BOOL first_byte_caseless = FALSE; -BOOL req_byte_caseless = FALSE; -BOOL utf8; -match_data match_block; -match_data *md = &match_block; -const uschar *tables; -const uschar *start_bits = NULL; -USPTR start_match = (USPTR)subject + start_offset; -USPTR end_subject; -USPTR req_byte_ptr = start_match - 1; - -pcre_study_data internal_study; -const pcre_study_data *study; - -real_pcre internal_re; -const real_pcre *external_re = (const real_pcre *)argument_re; -const real_pcre *re = external_re; - -/* Plausibility checks */ - -if ((options & ~PUBLIC_EXEC_OPTIONS) != 0) return PCRE_ERROR_BADOPTION; -if (re == NULL || subject == NULL || - (offsets == NULL && offsetcount > 0)) return PCRE_ERROR_NULL; -if (offsetcount < 0) return PCRE_ERROR_BADCOUNT; - -/* Fish out the optional data from the extra_data structure, first setting -the default values. */ - -study = NULL; -md->match_limit = MATCH_LIMIT; -md->match_limit_recursion = MATCH_LIMIT_RECURSION; -md->callout_data = NULL; - -/* The table pointer is always in native byte order. */ - -tables = external_re->tables; - -if (extra_data != NULL) - { - register unsigned int flags = extra_data->flags; - if ((flags & PCRE_EXTRA_STUDY_DATA) != 0) - study = (const pcre_study_data *)extra_data->study_data; - if ((flags & PCRE_EXTRA_MATCH_LIMIT) != 0) - md->match_limit = extra_data->match_limit; - if ((flags & PCRE_EXTRA_MATCH_LIMIT_RECURSION) != 0) - md->match_limit_recursion = extra_data->match_limit_recursion; - if ((flags & PCRE_EXTRA_CALLOUT_DATA) != 0) - md->callout_data = extra_data->callout_data; - if ((flags & PCRE_EXTRA_TABLES) != 0) tables = extra_data->tables; - } - -/* If the exec call supplied NULL for tables, use the inbuilt ones. This -is a feature that makes it possible to save compiled regex and re-use them -in other programs later. */ - -if (tables == NULL) tables = _pcre_default_tables; - -/* Check that the first field in the block is the magic number. If it is not, -test for a regex that was compiled on a host of opposite endianness. If this is -the case, flipped values are put in internal_re and internal_study if there was -study data too. */ - -if (re->magic_number != MAGIC_NUMBER) - { - re = _pcre_try_flipped(re, &internal_re, study, &internal_study); - if (re == NULL) return PCRE_ERROR_BADMAGIC; - if (study != NULL) study = &internal_study; - } - -/* Set up other data */ - -anchored = ((re->options | options) & PCRE_ANCHORED) != 0; -startline = (re->flags & PCRE_STARTLINE) != 0; -firstline = (re->options & PCRE_FIRSTLINE) != 0; - -/* The code starts after the real_pcre block and the capture name table. */ - -md->start_code = (const uschar *)external_re + re->name_table_offset + - re->name_count * re->name_entry_size; - -md->start_subject = (USPTR)subject; -md->start_offset = start_offset; -md->end_subject = md->start_subject + length; -end_subject = md->end_subject; - -md->endonly = (re->options & PCRE_DOLLAR_ENDONLY) != 0; -utf8 = md->utf8 = (re->options & PCRE_UTF8) != 0; -md->jscript_compat = (re->options & PCRE_JAVASCRIPT_COMPAT) != 0; - -md->notbol = (options & PCRE_NOTBOL) != 0; -md->noteol = (options & PCRE_NOTEOL) != 0; -md->notempty = (options & PCRE_NOTEMPTY) != 0; -md->partial = (options & PCRE_PARTIAL) != 0; -md->hitend = FALSE; - -md->recursive = NULL; /* No recursion at top level */ - -md->lcc = tables + lcc_offset; -md->ctypes = tables + ctypes_offset; - -/* Handle different \R options. */ - -switch (options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) - { - case 0: - if ((re->options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) != 0) - md->bsr_anycrlf = (re->options & PCRE_BSR_ANYCRLF) != 0; - else -#ifdef BSR_ANYCRLF - md->bsr_anycrlf = TRUE; -#else - md->bsr_anycrlf = FALSE; -#endif - break; - - case PCRE_BSR_ANYCRLF: - md->bsr_anycrlf = TRUE; - break; - - case PCRE_BSR_UNICODE: - md->bsr_anycrlf = FALSE; - break; - - default: return PCRE_ERROR_BADNEWLINE; - } - -/* Handle different types of newline. The three bits give eight cases. If -nothing is set at run time, whatever was used at compile time applies. */ - -switch ((((options & PCRE_NEWLINE_BITS) == 0)? re->options : - (pcre_uint32)options) & PCRE_NEWLINE_BITS) - { - case 0: newline = NEWLINE; break; /* Compile-time default */ - case PCRE_NEWLINE_CR: newline = CHAR_CR; break; - case PCRE_NEWLINE_LF: newline = CHAR_NL; break; - case PCRE_NEWLINE_CR+ - PCRE_NEWLINE_LF: newline = (CHAR_CR << 8) | CHAR_NL; break; - case PCRE_NEWLINE_ANY: newline = -1; break; - case PCRE_NEWLINE_ANYCRLF: newline = -2; break; - default: return PCRE_ERROR_BADNEWLINE; - } - -if (newline == -2) - { - md->nltype = NLTYPE_ANYCRLF; - } -else if (newline < 0) - { - md->nltype = NLTYPE_ANY; - } -else - { - md->nltype = NLTYPE_FIXED; - if (newline > 255) - { - md->nllen = 2; - md->nl[0] = (newline >> 8) & 255; - md->nl[1] = newline & 255; - } - else - { - md->nllen = 1; - md->nl[0] = newline; - } - } - -/* Partial matching is supported only for a restricted set of regexes at the -moment. */ - -if (md->partial && (re->flags & PCRE_NOPARTIAL) != 0) - return PCRE_ERROR_BADPARTIAL; - -/* Check a UTF-8 string if required. Unfortunately there's no way of passing -back the character offset. */ - -#ifdef SUPPORT_UTF8 -if (utf8 && (options & PCRE_NO_UTF8_CHECK) == 0) - { - if (_pcre_valid_utf8((USPTR)subject, length) >= 0) - return PCRE_ERROR_BADUTF8; - if (start_offset > 0 && start_offset < length) - { - int tb = ((USPTR)subject)[start_offset]; - if (tb > 127) - { - tb &= 0xc0; - if (tb != 0 && tb != 0xc0) return PCRE_ERROR_BADUTF8_OFFSET; - } - } - } -#endif - -/* The ims options can vary during the matching as a result of the presence -of (?ims) items in the pattern. They are kept in a local variable so that -restoring at the exit of a group is easy. */ - -ims = re->options & (PCRE_CASELESS|PCRE_MULTILINE|PCRE_DOTALL); - -/* If the expression has got more back references than the offsets supplied can -hold, we get a temporary chunk of working store to use during the matching. -Otherwise, we can use the vector supplied, rounding down its size to a multiple -of 3. */ - -ocount = offsetcount - (offsetcount % 3); - -if (re->top_backref > 0 && re->top_backref >= ocount/3) - { - ocount = re->top_backref * 3 + 3; - md->offset_vector = (int *)(pcre_malloc)(ocount * sizeof(int)); - if (md->offset_vector == NULL) return PCRE_ERROR_NOMEMORY; - using_temporary_offsets = TRUE; - DPRINTF(("Got memory to hold back references\n")); - } -else md->offset_vector = offsets; - -md->offset_end = ocount; -md->offset_max = (2*ocount)/3; -md->offset_overflow = FALSE; -md->capture_last = -1; - -/* Compute the minimum number of offsets that we need to reset each time. Doing -this makes a huge difference to execution time when there aren't many brackets -in the pattern. */ - -resetcount = 2 + re->top_bracket * 2; -if (resetcount > offsetcount) resetcount = ocount; - -/* Reset the working variable associated with each extraction. These should -never be used unless previously set, but they get saved and restored, and so we -initialize them to avoid reading uninitialized locations. */ - -if (md->offset_vector != NULL) - { - register int *iptr = md->offset_vector + ocount; - register int *iend = iptr - resetcount/2 + 1; - while (--iptr >= iend) *iptr = -1; - } - -/* Set up the first character to match, if available. The first_byte value is -never set for an anchored regular expression, but the anchoring may be forced -at run time, so we have to test for anchoring. The first char may be unset for -an unanchored pattern, of course. If there's no first char and the pattern was -studied, there may be a bitmap of possible first characters. */ - -if (!anchored) - { - if ((re->flags & PCRE_FIRSTSET) != 0) - { - first_byte = re->first_byte & 255; - if ((first_byte_caseless = ((re->first_byte & REQ_CASELESS) != 0)) == TRUE) - first_byte = md->lcc[first_byte]; - } - else - if (!startline && study != NULL && - (study->options & PCRE_STUDY_MAPPED) != 0) - start_bits = study->start_bits; - } - -/* For anchored or unanchored matches, there may be a "last known required -character" set. */ - -if ((re->flags & PCRE_REQCHSET) != 0) - { - req_byte = re->req_byte & 255; - req_byte_caseless = (re->req_byte & REQ_CASELESS) != 0; - req_byte2 = (tables + fcc_offset)[req_byte]; /* case flipped */ - } - - -/* ==========================================================================*/ - -/* Loop for handling unanchored repeated matching attempts; for anchored regexs -the loop runs just once. */ - -for(;;) - { - USPTR save_end_subject = end_subject; - USPTR new_start_match; - - /* Reset the maximum number of extractions we might see. */ - - if (md->offset_vector != NULL) - { - register int *iptr = md->offset_vector; - register int *iend = iptr + resetcount; - while (iptr < iend) *iptr++ = -1; - } - - /* If firstline is TRUE, the start of the match is constrained to the first - line of a multiline string. That is, the match must be before or at the first - newline. Implement this by temporarily adjusting end_subject so that we stop - scanning at a newline. If the match fails at the newline, later code breaks - this loop. */ - - if (firstline) - { - USPTR t = start_match; -#ifdef SUPPORT_UTF8 - if (utf8) - { - while (t < md->end_subject && !IS_NEWLINE(t)) - { - t++; - while (t < end_subject && (*t & 0xc0) == 0x80) t++; - } - } - else -#endif - while (t < md->end_subject && !IS_NEWLINE(t)) t++; - end_subject = t; - } - - /* There are some optimizations that avoid running the match if a known - starting point is not found, or if a known later character is not present. - However, there is an option that disables these, for testing and for ensuring - that all callouts do actually occur. */ - - if ((options & PCRE_NO_START_OPTIMIZE) == 0) - { - /* Advance to a unique first byte if there is one. */ - - if (first_byte >= 0) - { - if (first_byte_caseless) - while (start_match < end_subject && md->lcc[*start_match] != first_byte) - start_match++; - else - while (start_match < end_subject && *start_match != first_byte) - start_match++; - } - - /* Or to just after a linebreak for a multiline match */ - - else if (startline) - { - if (start_match > md->start_subject + start_offset) - { -#ifdef SUPPORT_UTF8 - if (utf8) - { - while (start_match < end_subject && !WAS_NEWLINE(start_match)) - { - start_match++; - while(start_match < end_subject && (*start_match & 0xc0) == 0x80) - start_match++; - } - } - else -#endif - while (start_match < end_subject && !WAS_NEWLINE(start_match)) - start_match++; - - /* If we have just passed a CR and the newline option is ANY or ANYCRLF, - and we are now at a LF, advance the match position by one more character. - */ - - if (start_match[-1] == CHAR_CR && - (md->nltype == NLTYPE_ANY || md->nltype == NLTYPE_ANYCRLF) && - start_match < end_subject && - *start_match == CHAR_NL) - start_match++; - } - } - - /* Or to a non-unique first byte after study */ - - else if (start_bits != NULL) - { - while (start_match < end_subject) - { - register unsigned int c = *start_match; - if ((start_bits[c/8] & (1 << (c&7))) == 0) start_match++; - else break; - } - } - } /* Starting optimizations */ - - /* Restore fudged end_subject */ - - end_subject = save_end_subject; - -#ifdef PCRE_DEBUG /* Sigh. Some compilers never learn. */ - printf(">>>> Match against: "); - pchars(start_match, end_subject - start_match, TRUE, md); - printf("\n"); -#endif - - /* If req_byte is set, we know that that character must appear in the - subject for the match to succeed. If the first character is set, req_byte - must be later in the subject; otherwise the test starts at the match point. - This optimization can save a huge amount of backtracking in patterns with - nested unlimited repeats that aren't going to match. Writing separate code - for cased/caseless versions makes it go faster, as does using an - autoincrement and backing off on a match. - - HOWEVER: when the subject string is very, very long, searching to its end - can take a long time, and give bad performance on quite ordinary patterns. - This showed up when somebody was matching something like /^\d+C/ on a - 32-megabyte string... so we don't do this when the string is sufficiently - long. - - ALSO: this processing is disabled when partial matching is requested, or if - disabling is explicitly requested. */ - - if ((options & PCRE_NO_START_OPTIMIZE) == 0 && - req_byte >= 0 && - end_subject - start_match < REQ_BYTE_MAX && - !md->partial) - { - register USPTR p = start_match + ((first_byte >= 0)? 1 : 0); - - /* We don't need to repeat the search if we haven't yet reached the - place we found it at last time. */ - - if (p > req_byte_ptr) - { - if (req_byte_caseless) - { - while (p < end_subject) - { - register int pp = *p++; - if (pp == req_byte || pp == req_byte2) { p--; break; } - } - } - else - { - while (p < end_subject) - { - if (*p++ == req_byte) { p--; break; } - } - } - - /* If we can't find the required character, break the matching loop, - forcing a match failure. */ - - if (p >= end_subject) - { - rc = MATCH_NOMATCH; - break; - } - - /* If we have found the required character, save the point where we - found it, so that we don't search again next time round the loop if - the start hasn't passed this character yet. */ - - req_byte_ptr = p; - } - } - - /* OK, we can now run the match. */ - - md->start_match_ptr = start_match; - md->match_call_count = 0; - rc = match(start_match, md->start_code, start_match, 2, md, ims, NULL, 0, 0); - - switch(rc) - { - /* NOMATCH and PRUNE advance by one character. THEN at this level acts - exactly like PRUNE. */ - - case MATCH_NOMATCH: - case MATCH_PRUNE: - case MATCH_THEN: - new_start_match = start_match + 1; -#ifdef SUPPORT_UTF8 - if (utf8) - while(new_start_match < end_subject && (*new_start_match & 0xc0) == 0x80) - new_start_match++; -#endif - break; - - /* SKIP passes back the next starting point explicitly. */ - - case MATCH_SKIP: - new_start_match = md->start_match_ptr; - break; - - /* COMMIT disables the bumpalong, but otherwise behaves as NOMATCH. */ - - case MATCH_COMMIT: - rc = MATCH_NOMATCH; - goto ENDLOOP; - - /* Any other return is some kind of error. */ - - default: - goto ENDLOOP; - } - - /* Control reaches here for the various types of "no match at this point" - result. Reset the code to MATCH_NOMATCH for subsequent checking. */ - - rc = MATCH_NOMATCH; - - /* If PCRE_FIRSTLINE is set, the match must happen before or at the first - newline in the subject (though it may continue over the newline). Therefore, - if we have just failed to match, starting at a newline, do not continue. */ - - if (firstline && IS_NEWLINE(start_match)) break; - - /* Advance to new matching position */ - - start_match = new_start_match; - - /* Break the loop if the pattern is anchored or if we have passed the end of - the subject. */ - - if (anchored || start_match > end_subject) break; - - /* If we have just passed a CR and we are now at a LF, and the pattern does - not contain any explicit matches for \r or \n, and the newline option is CRLF - or ANY or ANYCRLF, advance the match position by one more character. */ - - if (start_match[-1] == CHAR_CR && - start_match < end_subject && - *start_match == CHAR_NL && - (re->flags & PCRE_HASCRORLF) == 0 && - (md->nltype == NLTYPE_ANY || - md->nltype == NLTYPE_ANYCRLF || - md->nllen == 2)) - start_match++; - - } /* End of for(;;) "bumpalong" loop */ - -/* ==========================================================================*/ - -/* We reach here when rc is not MATCH_NOMATCH, or if one of the stopping -conditions is true: - -(1) The pattern is anchored or the match was failed by (*COMMIT); - -(2) We are past the end of the subject; - -(3) PCRE_FIRSTLINE is set and we have failed to match at a newline, because - this option requests that a match occur at or before the first newline in - the subject. - -When we have a match and the offset vector is big enough to deal with any -backreferences, captured substring offsets will already be set up. In the case -where we had to get some local store to hold offsets for backreference -processing, copy those that we can. In this case there need not be overflow if -certain parts of the pattern were not used, even though there are more -capturing parentheses than vector slots. */ - -ENDLOOP: - -if (rc == MATCH_MATCH) - { - if (using_temporary_offsets) - { - if (offsetcount >= 4) - { - memcpy(offsets + 2, md->offset_vector + 2, - (offsetcount - 2) * sizeof(int)); - DPRINTF(("Copied offsets from temporary memory\n")); - } - if (md->end_offset_top > offsetcount) md->offset_overflow = TRUE; - DPRINTF(("Freeing temporary memory\n")); - (pcre_free)(md->offset_vector); - } - - /* Set the return code to the number of captured strings, or 0 if there are - too many to fit into the vector. */ - - rc = md->offset_overflow? 0 : md->end_offset_top/2; - - /* If there is space, set up the whole thing as substring 0. The value of - md->start_match_ptr might be modified if \K was encountered on the success - matching path. */ - - if (offsetcount < 2) rc = 0; else - { - offsets[0] = md->start_match_ptr - md->start_subject; - offsets[1] = md->end_match_ptr - md->start_subject; - } - - DPRINTF((">>>> returning %d\n", rc)); - return rc; - } - -/* Control gets here if there has been an error, or if the overall match -attempt has failed at all permitted starting positions. */ - -if (using_temporary_offsets) - { - DPRINTF(("Freeing temporary memory\n")); - (pcre_free)(md->offset_vector); - } - -if (rc != MATCH_NOMATCH) - { - DPRINTF((">>>> error: returning %d\n", rc)); - return rc; - } -else if (md->partial && md->hitend) - { - DPRINTF((">>>> returning PCRE_ERROR_PARTIAL\n")); - return PCRE_ERROR_PARTIAL; - } -else - { - DPRINTF((">>>> returning PCRE_ERROR_NOMATCH\n")); - return PCRE_ERROR_NOMATCH; - } -} - -/* End of pcre_exec.c */ diff --git a/libs/pcre/pcre_fullinfo.c b/libs/pcre/pcre_fullinfo.c deleted file mode 100644 index 3a343bd4a1..0000000000 --- a/libs/pcre/pcre_fullinfo.c +++ /dev/null @@ -1,165 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2009 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains the external function pcre_fullinfo(), which returns -information about a compiled pattern. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - - -/************************************************* -* Return info about compiled pattern * -*************************************************/ - -/* This is a newer "info" function which has an extensible interface so -that additional items can be added compatibly. - -Arguments: - argument_re points to compiled code - extra_data points extra data, or NULL - what what information is required - where where to put the information - -Returns: 0 if data returned, negative on error -*/ - -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre_fullinfo(const pcre *argument_re, const pcre_extra *extra_data, int what, - void *where) -{ -real_pcre internal_re; -pcre_study_data internal_study; -const real_pcre *re = (const real_pcre *)argument_re; -const pcre_study_data *study = NULL; - -if (re == NULL || where == NULL) return PCRE_ERROR_NULL; - -if (extra_data != NULL && (extra_data->flags & PCRE_EXTRA_STUDY_DATA) != 0) - study = (const pcre_study_data *)extra_data->study_data; - -if (re->magic_number != MAGIC_NUMBER) - { - re = _pcre_try_flipped(re, &internal_re, study, &internal_study); - if (re == NULL) return PCRE_ERROR_BADMAGIC; - if (study != NULL) study = &internal_study; - } - -switch (what) - { - case PCRE_INFO_OPTIONS: - *((unsigned long int *)where) = re->options & PUBLIC_COMPILE_OPTIONS; - break; - - case PCRE_INFO_SIZE: - *((size_t *)where) = re->size; - break; - - case PCRE_INFO_STUDYSIZE: - *((size_t *)where) = (study == NULL)? 0 : study->size; - break; - - case PCRE_INFO_CAPTURECOUNT: - *((int *)where) = re->top_bracket; - break; - - case PCRE_INFO_BACKREFMAX: - *((int *)where) = re->top_backref; - break; - - case PCRE_INFO_FIRSTBYTE: - *((int *)where) = - ((re->flags & PCRE_FIRSTSET) != 0)? re->first_byte : - ((re->flags & PCRE_STARTLINE) != 0)? -1 : -2; - break; - - /* Make sure we pass back the pointer to the bit vector in the external - block, not the internal copy (with flipped integer fields). */ - - case PCRE_INFO_FIRSTTABLE: - *((const uschar **)where) = - (study != NULL && (study->options & PCRE_STUDY_MAPPED) != 0)? - ((const pcre_study_data *)extra_data->study_data)->start_bits : NULL; - break; - - case PCRE_INFO_LASTLITERAL: - *((int *)where) = - ((re->flags & PCRE_REQCHSET) != 0)? re->req_byte : -1; - break; - - case PCRE_INFO_NAMEENTRYSIZE: - *((int *)where) = re->name_entry_size; - break; - - case PCRE_INFO_NAMECOUNT: - *((int *)where) = re->name_count; - break; - - case PCRE_INFO_NAMETABLE: - *((const uschar **)where) = (const uschar *)re + re->name_table_offset; - break; - - case PCRE_INFO_DEFAULT_TABLES: - *((const uschar **)where) = (const uschar *)(_pcre_default_tables); - break; - - case PCRE_INFO_OKPARTIAL: - *((int *)where) = (re->flags & PCRE_NOPARTIAL) == 0; - break; - - case PCRE_INFO_JCHANGED: - *((int *)where) = (re->flags & PCRE_JCHANGED) != 0; - break; - - case PCRE_INFO_HASCRORLF: - *((int *)where) = (re->flags & PCRE_HASCRORLF) != 0; - break; - - default: return PCRE_ERROR_BADOPTION; - } - -return 0; -} - -/* End of pcre_fullinfo.c */ diff --git a/libs/pcre/pcre_get.c b/libs/pcre/pcre_get.c deleted file mode 100644 index 6117786409..0000000000 --- a/libs/pcre/pcre_get.c +++ /dev/null @@ -1,465 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2008 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains some convenience functions for extracting substrings -from the subject string after a regex match has succeeded. The original idea -for these functions came from Scott Wimer. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - - -/************************************************* -* Find number for named string * -*************************************************/ - -/* This function is used by the get_first_set() function below, as well -as being generally available. It assumes that names are unique. - -Arguments: - code the compiled regex - stringname the name whose number is required - -Returns: the number of the named parentheses, or a negative number - (PCRE_ERROR_NOSUBSTRING) if not found -*/ - -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre_get_stringnumber(const pcre *code, const char *stringname) -{ -int rc; -int entrysize; -int top, bot; -uschar *nametable; - -if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMECOUNT, &top)) != 0) - return rc; -if (top <= 0) return PCRE_ERROR_NOSUBSTRING; - -if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMEENTRYSIZE, &entrysize)) != 0) - return rc; -if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMETABLE, &nametable)) != 0) - return rc; - -bot = 0; -while (top > bot) - { - int mid = (top + bot) / 2; - uschar *entry = nametable + entrysize*mid; - int c = strcmp(stringname, (char *)(entry + 2)); - if (c == 0) return (entry[0] << 8) + entry[1]; - if (c > 0) bot = mid + 1; else top = mid; - } - -return PCRE_ERROR_NOSUBSTRING; -} - - - -/************************************************* -* Find (multiple) entries for named string * -*************************************************/ - -/* This is used by the get_first_set() function below, as well as being -generally available. It is used when duplicated names are permitted. - -Arguments: - code the compiled regex - stringname the name whose entries required - firstptr where to put the pointer to the first entry - lastptr where to put the pointer to the last entry - -Returns: the length of each entry, or a negative number - (PCRE_ERROR_NOSUBSTRING) if not found -*/ - -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre_get_stringtable_entries(const pcre *code, const char *stringname, - char **firstptr, char **lastptr) -{ -int rc; -int entrysize; -int top, bot; -uschar *nametable, *lastentry; - -if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMECOUNT, &top)) != 0) - return rc; -if (top <= 0) return PCRE_ERROR_NOSUBSTRING; - -if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMEENTRYSIZE, &entrysize)) != 0) - return rc; -if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMETABLE, &nametable)) != 0) - return rc; - -lastentry = nametable + entrysize * (top - 1); -bot = 0; -while (top > bot) - { - int mid = (top + bot) / 2; - uschar *entry = nametable + entrysize*mid; - int c = strcmp(stringname, (char *)(entry + 2)); - if (c == 0) - { - uschar *first = entry; - uschar *last = entry; - while (first > nametable) - { - if (strcmp(stringname, (char *)(first - entrysize + 2)) != 0) break; - first -= entrysize; - } - while (last < lastentry) - { - if (strcmp(stringname, (char *)(last + entrysize + 2)) != 0) break; - last += entrysize; - } - *firstptr = (char *)first; - *lastptr = (char *)last; - return entrysize; - } - if (c > 0) bot = mid + 1; else top = mid; - } - -return PCRE_ERROR_NOSUBSTRING; -} - - - -/************************************************* -* Find first set of multiple named strings * -*************************************************/ - -/* This function allows for duplicate names in the table of named substrings. -It returns the number of the first one that was set in a pattern match. - -Arguments: - code the compiled regex - stringname the name of the capturing substring - ovector the vector of matched substrings - -Returns: the number of the first that is set, - or the number of the last one if none are set, - or a negative number on error -*/ - -static int -get_first_set(const pcre *code, const char *stringname, int *ovector) -{ -const real_pcre *re = (const real_pcre *)code; -int entrysize; -char *first, *last; -uschar *entry; -if ((re->options & PCRE_DUPNAMES) == 0 && (re->flags & PCRE_JCHANGED) == 0) - return pcre_get_stringnumber(code, stringname); -entrysize = pcre_get_stringtable_entries(code, stringname, &first, &last); -if (entrysize <= 0) return entrysize; -for (entry = (uschar *)first; entry <= (uschar *)last; entry += entrysize) - { - int n = (entry[0] << 8) + entry[1]; - if (ovector[n*2] >= 0) return n; - } -return (first[0] << 8) + first[1]; -} - - - - -/************************************************* -* Copy captured string to given buffer * -*************************************************/ - -/* This function copies a single captured substring into a given buffer. -Note that we use memcpy() rather than strncpy() in case there are binary zeros -in the string. - -Arguments: - subject the subject string that was matched - ovector pointer to the offsets table - stringcount the number of substrings that were captured - (i.e. the yield of the pcre_exec call, unless - that was zero, in which case it should be 1/3 - of the offset table size) - stringnumber the number of the required substring - buffer where to put the substring - size the size of the buffer - -Returns: if successful: - the length of the copied string, not including the zero - that is put on the end; can be zero - if not successful: - PCRE_ERROR_NOMEMORY (-6) buffer too small - PCRE_ERROR_NOSUBSTRING (-7) no such captured substring -*/ - -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre_copy_substring(const char *subject, int *ovector, int stringcount, - int stringnumber, char *buffer, int size) -{ -int yield; -if (stringnumber < 0 || stringnumber >= stringcount) - return PCRE_ERROR_NOSUBSTRING; -stringnumber *= 2; -yield = ovector[stringnumber+1] - ovector[stringnumber]; -if (size < yield + 1) return PCRE_ERROR_NOMEMORY; -memcpy(buffer, subject + ovector[stringnumber], yield); -buffer[yield] = 0; -return yield; -} - - - -/************************************************* -* Copy named captured string to given buffer * -*************************************************/ - -/* This function copies a single captured substring into a given buffer, -identifying it by name. If the regex permits duplicate names, the first -substring that is set is chosen. - -Arguments: - code the compiled regex - subject the subject string that was matched - ovector pointer to the offsets table - stringcount the number of substrings that were captured - (i.e. the yield of the pcre_exec call, unless - that was zero, in which case it should be 1/3 - of the offset table size) - stringname the name of the required substring - buffer where to put the substring - size the size of the buffer - -Returns: if successful: - the length of the copied string, not including the zero - that is put on the end; can be zero - if not successful: - PCRE_ERROR_NOMEMORY (-6) buffer too small - PCRE_ERROR_NOSUBSTRING (-7) no such captured substring -*/ - -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre_copy_named_substring(const pcre *code, const char *subject, int *ovector, - int stringcount, const char *stringname, char *buffer, int size) -{ -int n = get_first_set(code, stringname, ovector); -if (n <= 0) return n; -return pcre_copy_substring(subject, ovector, stringcount, n, buffer, size); -} - - - -/************************************************* -* Copy all captured strings to new store * -*************************************************/ - -/* This function gets one chunk of store and builds a list of pointers and all -of the captured substrings in it. A NULL pointer is put on the end of the list. - -Arguments: - subject the subject string that was matched - ovector pointer to the offsets table - stringcount the number of substrings that were captured - (i.e. the yield of the pcre_exec call, unless - that was zero, in which case it should be 1/3 - of the offset table size) - listptr set to point to the list of pointers - -Returns: if successful: 0 - if not successful: - PCRE_ERROR_NOMEMORY (-6) failed to get store -*/ - -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre_get_substring_list(const char *subject, int *ovector, int stringcount, - const char ***listptr) -{ -int i; -int size = sizeof(char *); -int double_count = stringcount * 2; -char **stringlist; -char *p; - -for (i = 0; i < double_count; i += 2) - size += sizeof(char *) + ovector[i+1] - ovector[i] + 1; - -stringlist = (char **)(pcre_malloc)(size); -if (stringlist == NULL) return PCRE_ERROR_NOMEMORY; - -*listptr = (const char **)stringlist; -p = (char *)(stringlist + stringcount + 1); - -for (i = 0; i < double_count; i += 2) - { - int len = ovector[i+1] - ovector[i]; - memcpy(p, subject + ovector[i], len); - *stringlist++ = p; - p += len; - *p++ = 0; - } - -*stringlist = NULL; -return 0; -} - - - -/************************************************* -* Free store obtained by get_substring_list * -*************************************************/ - -/* This function exists for the benefit of people calling PCRE from non-C -programs that can call its functions, but not free() or (pcre_free)() directly. - -Argument: the result of a previous pcre_get_substring_list() -Returns: nothing -*/ - -PCRE_EXP_DEFN void PCRE_CALL_CONVENTION -pcre_free_substring_list(const char **pointer) -{ -(pcre_free)((void *)pointer); -} - - - -/************************************************* -* Copy captured string to new store * -*************************************************/ - -/* This function copies a single captured substring into a piece of new -store - -Arguments: - subject the subject string that was matched - ovector pointer to the offsets table - stringcount the number of substrings that were captured - (i.e. the yield of the pcre_exec call, unless - that was zero, in which case it should be 1/3 - of the offset table size) - stringnumber the number of the required substring - stringptr where to put a pointer to the substring - -Returns: if successful: - the length of the string, not including the zero that - is put on the end; can be zero - if not successful: - PCRE_ERROR_NOMEMORY (-6) failed to get store - PCRE_ERROR_NOSUBSTRING (-7) substring not present -*/ - -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre_get_substring(const char *subject, int *ovector, int stringcount, - int stringnumber, const char **stringptr) -{ -int yield; -char *substring; -if (stringnumber < 0 || stringnumber >= stringcount) - return PCRE_ERROR_NOSUBSTRING; -stringnumber *= 2; -yield = ovector[stringnumber+1] - ovector[stringnumber]; -substring = (char *)(pcre_malloc)(yield + 1); -if (substring == NULL) return PCRE_ERROR_NOMEMORY; -memcpy(substring, subject + ovector[stringnumber], yield); -substring[yield] = 0; -*stringptr = substring; -return yield; -} - - - -/************************************************* -* Copy named captured string to new store * -*************************************************/ - -/* This function copies a single captured substring, identified by name, into -new store. If the regex permits duplicate names, the first substring that is -set is chosen. - -Arguments: - code the compiled regex - subject the subject string that was matched - ovector pointer to the offsets table - stringcount the number of substrings that were captured - (i.e. the yield of the pcre_exec call, unless - that was zero, in which case it should be 1/3 - of the offset table size) - stringname the name of the required substring - stringptr where to put the pointer - -Returns: if successful: - the length of the copied string, not including the zero - that is put on the end; can be zero - if not successful: - PCRE_ERROR_NOMEMORY (-6) couldn't get memory - PCRE_ERROR_NOSUBSTRING (-7) no such captured substring -*/ - -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre_get_named_substring(const pcre *code, const char *subject, int *ovector, - int stringcount, const char *stringname, const char **stringptr) -{ -int n = get_first_set(code, stringname, ovector); -if (n <= 0) return n; -return pcre_get_substring(subject, ovector, stringcount, n, stringptr); -} - - - - -/************************************************* -* Free store obtained by get_substring * -*************************************************/ - -/* This function exists for the benefit of people calling PCRE from non-C -programs that can call its functions, but not free() or (pcre_free)() directly. - -Argument: the result of a previous pcre_get_substring() -Returns: nothing -*/ - -PCRE_EXP_DEFN void PCRE_CALL_CONVENTION -pcre_free_substring(const char *pointer) -{ -(pcre_free)((void *)pointer); -} - -/* End of pcre_get.c */ diff --git a/libs/pcre/pcre_globals.c b/libs/pcre/pcre_globals.c deleted file mode 100644 index 24ed03d396..0000000000 --- a/libs/pcre/pcre_globals.c +++ /dev/null @@ -1,63 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2008 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains global variables that are exported by the PCRE library. -PCRE is thread-clean and doesn't use any global variables in the normal sense. -However, it calls memory allocation and freeing functions via the four -indirections below, and it can optionally do callouts, using the fifth -indirection. These values can be changed by the caller, but are shared between -all threads. However, when compiling for Virtual Pascal, things are done -differently, and global variables are not used (see pcre.in). */ - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - -#ifndef VPCOMPAT -PCRE_EXP_DATA_DEFN void *(*pcre_malloc)(size_t) = malloc; -PCRE_EXP_DATA_DEFN void (*pcre_free)(void *) = free; -PCRE_EXP_DATA_DEFN void *(*pcre_stack_malloc)(size_t) = malloc; -PCRE_EXP_DATA_DEFN void (*pcre_stack_free)(void *) = free; -PCRE_EXP_DATA_DEFN int (*pcre_callout)(pcre_callout_block *) = NULL; -#endif - -/* End of pcre_globals.c */ diff --git a/libs/pcre/pcre_info.c b/libs/pcre/pcre_info.c deleted file mode 100644 index f35f398db5..0000000000 --- a/libs/pcre/pcre_info.c +++ /dev/null @@ -1,93 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2009 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains the external function pcre_info(), which gives some -information about a compiled pattern. However, use of this function is now -deprecated, as it has been superseded by pcre_fullinfo(). */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - - -/************************************************* -* (Obsolete) Return info about compiled pattern * -*************************************************/ - -/* This is the original "info" function. It picks potentially useful data out -of the private structure, but its interface was too rigid. It remains for -backwards compatibility. The public options are passed back in an int - though -the re->options field has been expanded to a long int, all the public options -at the low end of it, and so even on 16-bit systems this will still be OK. -Therefore, I haven't changed the API for pcre_info(). - -Arguments: - argument_re points to compiled code - optptr where to pass back the options - first_byte where to pass back the first character, - or -1 if multiline and all branches start ^, - or -2 otherwise - -Returns: number of capturing subpatterns - or negative values on error -*/ - -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre_info(const pcre *argument_re, int *optptr, int *first_byte) -{ -real_pcre internal_re; -const real_pcre *re = (const real_pcre *)argument_re; -if (re == NULL) return PCRE_ERROR_NULL; -if (re->magic_number != MAGIC_NUMBER) - { - re = _pcre_try_flipped(re, &internal_re, NULL, NULL); - if (re == NULL) return PCRE_ERROR_BADMAGIC; - } -if (optptr != NULL) *optptr = (int)(re->options & PUBLIC_COMPILE_OPTIONS); -if (first_byte != NULL) - *first_byte = ((re->flags & PCRE_FIRSTSET) != 0)? re->first_byte : - ((re->flags & PCRE_STARTLINE) != 0)? -1 : -2; -return re->top_bracket; -} - -/* End of pcre_info.c */ diff --git a/libs/pcre/pcre_internal.h b/libs/pcre/pcre_internal.h deleted file mode 100644 index 850b3b2a60..0000000000 --- a/libs/pcre/pcre_internal.h +++ /dev/null @@ -1,1744 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2009 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* This header contains definitions that are shared between the different -modules, but which are not relevant to the exported API. This includes some -functions whose names all begin with "_pcre_". */ - -#ifndef PCRE_INTERNAL_H -#define PCRE_INTERNAL_H - -/* Define PCRE_DEBUG to get debugging output on stdout. */ - -#if 0 -#define PCRE_DEBUG -#endif - -/* We do not support both EBCDIC and UTF-8 at the same time. The "configure" -script prevents both being selected, but not everybody uses "configure". */ - -#if defined EBCDIC && defined SUPPORT_UTF8 -#error The use of both EBCDIC and SUPPORT_UTF8 is not supported. -#endif - -/* If SUPPORT_UCP is defined, SUPPORT_UTF8 must also be defined. The -"configure" script ensures this, but not everybody uses "configure". */ - -#if defined SUPPORT_UCP && !defined SUPPORT_UTF8 -#define SUPPORT_UTF8 1 -#endif - -/* Use a macro for debugging printing, 'cause that eliminates the use of #ifdef -inline, and there are *still* stupid compilers about that don't like indented -pre-processor statements, or at least there were when I first wrote this. After -all, it had only been about 10 years then... - -It turns out that the Mac Debugging.h header also defines the macro DPRINTF, so -be absolutely sure we get our version. */ - -#undef DPRINTF -#ifdef PCRE_DEBUG -#define DPRINTF(p) printf p -#else -#define DPRINTF(p) /* Nothing */ -#endif - - -/* Standard C headers plus the external interface definition. The only time -setjmp and stdarg are used is when NO_RECURSE is set. */ - -#include -#include -#include -#include -#include -#include -#include -#include - -/* When compiling a DLL for Windows, the exported symbols have to be declared -using some MS magic. I found some useful information on this web page: -http://msdn2.microsoft.com/en-us/library/y4h7bcy6(VS.80).aspx. According to the -information there, using __declspec(dllexport) without "extern" we have a -definition; with "extern" we have a declaration. The settings here override the -setting in pcre.h (which is included below); it defines only PCRE_EXP_DECL, -which is all that is needed for applications (they just import the symbols). We -use: - - PCRE_EXP_DECL for declarations - PCRE_EXP_DEFN for definitions of exported functions - PCRE_EXP_DATA_DEFN for definitions of exported variables - -The reason for the two DEFN macros is that in non-Windows environments, one -does not want to have "extern" before variable definitions because it leads to -compiler warnings. So we distinguish between functions and variables. In -Windows, the two should always be the same. - -The reason for wrapping this in #ifndef PCRE_EXP_DECL is so that pcretest, -which is an application, but needs to import this file in order to "peek" at -internals, can #include pcre.h first to get an application's-eye view. - -In principle, people compiling for non-Windows, non-Unix-like (i.e. uncommon, -special-purpose environments) might want to stick other stuff in front of -exported symbols. That's why, in the non-Windows case, we set PCRE_EXP_DEFN and -PCRE_EXP_DATA_DEFN only if they are not already set. */ - -#ifndef PCRE_EXP_DECL -# ifdef _WIN32 -# ifndef PCRE_STATIC -# define PCRE_EXP_DECL extern __declspec(dllexport) -# define PCRE_EXP_DEFN __declspec(dllexport) -# define PCRE_EXP_DATA_DEFN __declspec(dllexport) -# else -# define PCRE_EXP_DECL extern -# define PCRE_EXP_DEFN -# define PCRE_EXP_DATA_DEFN -# endif -# else -# ifdef __cplusplus -# define PCRE_EXP_DECL extern "C" -# else -# define PCRE_EXP_DECL extern -# endif -# ifndef PCRE_EXP_DEFN -# define PCRE_EXP_DEFN PCRE_EXP_DECL -# endif -# ifndef PCRE_EXP_DATA_DEFN -# define PCRE_EXP_DATA_DEFN -# endif -# endif -#endif - -/* When compiling with the MSVC compiler, it is sometimes necessary to include -a "calling convention" before exported function names. (This is secondhand -information; I know nothing about MSVC myself). For example, something like - - void __cdecl function(....) - -might be needed. In order so make this easy, all the exported functions have -PCRE_CALL_CONVENTION just before their names. It is rarely needed; if not -set, we ensure here that it has no effect. */ - -#ifndef PCRE_CALL_CONVENTION -#define PCRE_CALL_CONVENTION -#endif - -/* We need to have types that specify unsigned 16-bit and 32-bit integers. We -cannot determine these outside the compilation (e.g. by running a program as -part of "configure") because PCRE is often cross-compiled for use on other -systems. Instead we make use of the maximum sizes that are available at -preprocessor time in standard C environments. */ - -#if USHRT_MAX == 65535 - typedef unsigned short pcre_uint16; - typedef short pcre_int16; -#elif UINT_MAX == 65535 - typedef unsigned int pcre_uint16; - typedef int pcre_int16; -#else - #error Cannot determine a type for 16-bit unsigned integers -#endif - -#if UINT_MAX == 4294967295 - typedef unsigned int pcre_uint32; - typedef int pcre_int32; -#elif ULONG_MAX == 4294967295 - typedef unsigned long int pcre_uint32; - typedef long int pcre_int32; -#else - #error Cannot determine a type for 32-bit unsigned integers -#endif - -/* All character handling must be done as unsigned characters. Otherwise there -are problems with top-bit-set characters and functions such as isspace(). -However, we leave the interface to the outside world as char *, because that -should make things easier for callers. We define a short type for unsigned char -to save lots of typing. I tried "uchar", but it causes problems on Digital -Unix, where it is defined in sys/types, so use "uschar" instead. */ - -typedef unsigned char uschar; - -/* This is an unsigned int value that no character can ever have. UTF-8 -characters only go up to 0x7fffffff (though Unicode doesn't go beyond -0x0010ffff). */ - -#define NOTACHAR 0xffffffff - -/* PCRE is able to support several different kinds of newline (CR, LF, CRLF, -"any" and "anycrlf" at present). The following macros are used to package up -testing for newlines. NLBLOCK, PSSTART, and PSEND are defined in the various -modules to indicate in which datablock the parameters exist, and what the -start/end of string field names are. */ - -#define NLTYPE_FIXED 0 /* Newline is a fixed length string */ -#define NLTYPE_ANY 1 /* Newline is any Unicode line ending */ -#define NLTYPE_ANYCRLF 2 /* Newline is CR, LF, or CRLF */ - -/* This macro checks for a newline at the given position */ - -#define IS_NEWLINE(p) \ - ((NLBLOCK->nltype != NLTYPE_FIXED)? \ - ((p) < NLBLOCK->PSEND && \ - _pcre_is_newline((p), NLBLOCK->nltype, NLBLOCK->PSEND, &(NLBLOCK->nllen),\ - utf8)) \ - : \ - ((p) <= NLBLOCK->PSEND - NLBLOCK->nllen && \ - (p)[0] == NLBLOCK->nl[0] && \ - (NLBLOCK->nllen == 1 || (p)[1] == NLBLOCK->nl[1]) \ - ) \ - ) - -/* This macro checks for a newline immediately preceding the given position */ - -#define WAS_NEWLINE(p) \ - ((NLBLOCK->nltype != NLTYPE_FIXED)? \ - ((p) > NLBLOCK->PSSTART && \ - _pcre_was_newline((p), NLBLOCK->nltype, NLBLOCK->PSSTART, \ - &(NLBLOCK->nllen), utf8)) \ - : \ - ((p) >= NLBLOCK->PSSTART + NLBLOCK->nllen && \ - (p)[-NLBLOCK->nllen] == NLBLOCK->nl[0] && \ - (NLBLOCK->nllen == 1 || (p)[-NLBLOCK->nllen+1] == NLBLOCK->nl[1]) \ - ) \ - ) - -/* When PCRE is compiled as a C++ library, the subject pointer can be replaced -with a custom type. This makes it possible, for example, to allow pcre_exec() -to process subject strings that are discontinuous by using a smart pointer -class. It must always be possible to inspect all of the subject string in -pcre_exec() because of the way it backtracks. Two macros are required in the -normal case, for sign-unspecified and unsigned char pointers. The former is -used for the external interface and appears in pcre.h, which is why its name -must begin with PCRE_. */ - -#ifdef CUSTOM_SUBJECT_PTR -#define PCRE_SPTR CUSTOM_SUBJECT_PTR -#define USPTR CUSTOM_SUBJECT_PTR -#else -#define PCRE_SPTR const char * -#define USPTR const unsigned char * -#endif - - - -/* Include the public PCRE header and the definitions of UCP character property -values. */ - -#include "pcre.h" -#include "ucp.h" - -/* When compiling for use with the Virtual Pascal compiler, these functions -need to have their names changed. PCRE must be compiled with the -DVPCOMPAT -option on the command line. */ - -#ifdef VPCOMPAT -#define strlen(s) _strlen(s) -#define strncmp(s1,s2,m) _strncmp(s1,s2,m) -#define memcmp(s,c,n) _memcmp(s,c,n) -#define memcpy(d,s,n) _memcpy(d,s,n) -#define memmove(d,s,n) _memmove(d,s,n) -#define memset(s,c,n) _memset(s,c,n) -#else /* VPCOMPAT */ - -/* To cope with SunOS4 and other systems that lack memmove() but have bcopy(), -define a macro for memmove() if HAVE_MEMMOVE is false, provided that HAVE_BCOPY -is set. Otherwise, include an emulating function for those systems that have -neither (there some non-Unix environments where this is the case). */ - -#ifndef HAVE_MEMMOVE -#undef memmove /* some systems may have a macro */ -#ifdef HAVE_BCOPY -#define memmove(a, b, c) bcopy(b, a, c) -#else /* HAVE_BCOPY */ -static void * -pcre_memmove(void *d, const void *s, size_t n) -{ -size_t i; -unsigned char *dest = (unsigned char *)d; -const unsigned char *src = (const unsigned char *)s; -if (dest > src) - { - dest += n; - src += n; - for (i = 0; i < n; ++i) *(--dest) = *(--src); - return (void *)dest; - } -else - { - for (i = 0; i < n; ++i) *dest++ = *src++; - return (void *)(dest - n); - } -} -#define memmove(a, b, c) pcre_memmove(a, b, c) -#endif /* not HAVE_BCOPY */ -#endif /* not HAVE_MEMMOVE */ -#endif /* not VPCOMPAT */ - - -/* PCRE keeps offsets in its compiled code as 2-byte quantities (always stored -in big-endian order) by default. These are used, for example, to link from the -start of a subpattern to its alternatives and its end. The use of 2 bytes per -offset limits the size of the compiled regex to around 64K, which is big enough -for almost everybody. However, I received a request for an even bigger limit. -For this reason, and also to make the code easier to maintain, the storing and -loading of offsets from the byte string is now handled by the macros that are -defined here. - -The macros are controlled by the value of LINK_SIZE. This defaults to 2 in -the config.h file, but can be overridden by using -D on the command line. This -is automated on Unix systems via the "configure" command. */ - -#if LINK_SIZE == 2 - -#define PUT(a,n,d) \ - (a[n] = (d) >> 8), \ - (a[(n)+1] = (d) & 255) - -#define GET(a,n) \ - (((a)[n] << 8) | (a)[(n)+1]) - -#define MAX_PATTERN_SIZE (1 << 16) - - -#elif LINK_SIZE == 3 - -#define PUT(a,n,d) \ - (a[n] = (d) >> 16), \ - (a[(n)+1] = (d) >> 8), \ - (a[(n)+2] = (d) & 255) - -#define GET(a,n) \ - (((a)[n] << 16) | ((a)[(n)+1] << 8) | (a)[(n)+2]) - -#define MAX_PATTERN_SIZE (1 << 24) - - -#elif LINK_SIZE == 4 - -#define PUT(a,n,d) \ - (a[n] = (d) >> 24), \ - (a[(n)+1] = (d) >> 16), \ - (a[(n)+2] = (d) >> 8), \ - (a[(n)+3] = (d) & 255) - -#define GET(a,n) \ - (((a)[n] << 24) | ((a)[(n)+1] << 16) | ((a)[(n)+2] << 8) | (a)[(n)+3]) - -#define MAX_PATTERN_SIZE (1 << 30) /* Keep it positive */ - - -#else -#error LINK_SIZE must be either 2, 3, or 4 -#endif - - -/* Convenience macro defined in terms of the others */ - -#define PUTINC(a,n,d) PUT(a,n,d), a += LINK_SIZE - - -/* PCRE uses some other 2-byte quantities that do not change when the size of -offsets changes. There are used for repeat counts and for other things such as -capturing parenthesis numbers in back references. */ - -#define PUT2(a,n,d) \ - a[n] = (d) >> 8; \ - a[(n)+1] = (d) & 255 - -#define GET2(a,n) \ - (((a)[n] << 8) | (a)[(n)+1]) - -#define PUT2INC(a,n,d) PUT2(a,n,d), a += 2 - - -/* When UTF-8 encoding is being used, a character is no longer just a single -byte. The macros for character handling generate simple sequences when used in -byte-mode, and more complicated ones for UTF-8 characters. BACKCHAR should -never be called in byte mode. To make sure it can never even appear when UTF-8 -support is omitted, we don't even define it. */ - -#ifndef SUPPORT_UTF8 -#define GETCHAR(c, eptr) c = *eptr; -#define GETCHARTEST(c, eptr) c = *eptr; -#define GETCHARINC(c, eptr) c = *eptr++; -#define GETCHARINCTEST(c, eptr) c = *eptr++; -#define GETCHARLEN(c, eptr, len) c = *eptr; -/* #define BACKCHAR(eptr) */ - -#else /* SUPPORT_UTF8 */ - -/* Get the next UTF-8 character, not advancing the pointer. This is called when -we know we are in UTF-8 mode. */ - -#define GETCHAR(c, eptr) \ - c = *eptr; \ - if (c >= 0xc0) \ - { \ - int gcii; \ - int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ - int gcss = 6*gcaa; \ - c = (c & _pcre_utf8_table3[gcaa]) << gcss; \ - for (gcii = 1; gcii <= gcaa; gcii++) \ - { \ - gcss -= 6; \ - c |= (eptr[gcii] & 0x3f) << gcss; \ - } \ - } - -/* Get the next UTF-8 character, testing for UTF-8 mode, and not advancing the -pointer. */ - -#define GETCHARTEST(c, eptr) \ - c = *eptr; \ - if (utf8 && c >= 0xc0) \ - { \ - int gcii; \ - int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ - int gcss = 6*gcaa; \ - c = (c & _pcre_utf8_table3[gcaa]) << gcss; \ - for (gcii = 1; gcii <= gcaa; gcii++) \ - { \ - gcss -= 6; \ - c |= (eptr[gcii] & 0x3f) << gcss; \ - } \ - } - -/* Get the next UTF-8 character, advancing the pointer. This is called when we -know we are in UTF-8 mode. */ - -#define GETCHARINC(c, eptr) \ - c = *eptr++; \ - if (c >= 0xc0) \ - { \ - int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ - int gcss = 6*gcaa; \ - c = (c & _pcre_utf8_table3[gcaa]) << gcss; \ - while (gcaa-- > 0) \ - { \ - gcss -= 6; \ - c |= (*eptr++ & 0x3f) << gcss; \ - } \ - } - -/* Get the next character, testing for UTF-8 mode, and advancing the pointer */ - -#define GETCHARINCTEST(c, eptr) \ - c = *eptr++; \ - if (utf8 && c >= 0xc0) \ - { \ - int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ - int gcss = 6*gcaa; \ - c = (c & _pcre_utf8_table3[gcaa]) << gcss; \ - while (gcaa-- > 0) \ - { \ - gcss -= 6; \ - c |= (*eptr++ & 0x3f) << gcss; \ - } \ - } - -/* Get the next UTF-8 character, not advancing the pointer, incrementing length -if there are extra bytes. This is called when we know we are in UTF-8 mode. */ - -#define GETCHARLEN(c, eptr, len) \ - c = *eptr; \ - if (c >= 0xc0) \ - { \ - int gcii; \ - int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ - int gcss = 6*gcaa; \ - c = (c & _pcre_utf8_table3[gcaa]) << gcss; \ - for (gcii = 1; gcii <= gcaa; gcii++) \ - { \ - gcss -= 6; \ - c |= (eptr[gcii] & 0x3f) << gcss; \ - } \ - len += gcaa; \ - } - -/* Get the next UTF-8 character, testing for UTF-8 mode, not advancing the -pointer, incrementing length if there are extra bytes. This is called when we -know we are in UTF-8 mode. */ - -#define GETCHARLENTEST(c, eptr, len) \ - c = *eptr; \ - if (utf8 && c >= 0xc0) \ - { \ - int gcii; \ - int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ - int gcss = 6*gcaa; \ - c = (c & _pcre_utf8_table3[gcaa]) << gcss; \ - for (gcii = 1; gcii <= gcaa; gcii++) \ - { \ - gcss -= 6; \ - c |= (eptr[gcii] & 0x3f) << gcss; \ - } \ - len += gcaa; \ - } - -/* If the pointer is not at the start of a character, move it back until -it is. This is called only in UTF-8 mode - we don't put a test within the macro -because almost all calls are already within a block of UTF-8 only code. */ - -#define BACKCHAR(eptr) while((*eptr & 0xc0) == 0x80) eptr-- - -#endif - - -/* In case there is no definition of offsetof() provided - though any proper -Standard C system should have one. */ - -#ifndef offsetof -#define offsetof(p_type,field) ((size_t)&(((p_type *)0)->field)) -#endif - - -/* These are the public options that can change during matching. */ - -#define PCRE_IMS (PCRE_CASELESS|PCRE_MULTILINE|PCRE_DOTALL) - -/* Private flags containing information about the compiled regex. They used to -live at the top end of the options word, but that got almost full, so now they -are in a 16-bit flags word. */ - -#define PCRE_NOPARTIAL 0x0001 /* can't use partial with this regex */ -#define PCRE_FIRSTSET 0x0002 /* first_byte is set */ -#define PCRE_REQCHSET 0x0004 /* req_byte is set */ -#define PCRE_STARTLINE 0x0008 /* start after \n for multiline */ -#define PCRE_JCHANGED 0x0010 /* j option used in regex */ -#define PCRE_HASCRORLF 0x0020 /* explicit \r or \n in pattern */ - -/* Options for the "extra" block produced by pcre_study(). */ - -#define PCRE_STUDY_MAPPED 0x01 /* a map of starting chars exists */ - -/* Masks for identifying the public options that are permitted at compile -time, run time, or study time, respectively. */ - -#define PCRE_NEWLINE_BITS (PCRE_NEWLINE_CR|PCRE_NEWLINE_LF|PCRE_NEWLINE_ANY| \ - PCRE_NEWLINE_ANYCRLF) - -#define PUBLIC_COMPILE_OPTIONS \ - (PCRE_CASELESS|PCRE_EXTENDED|PCRE_ANCHORED|PCRE_MULTILINE| \ - PCRE_DOTALL|PCRE_DOLLAR_ENDONLY|PCRE_EXTRA|PCRE_UNGREEDY|PCRE_UTF8| \ - PCRE_NO_AUTO_CAPTURE|PCRE_NO_UTF8_CHECK|PCRE_AUTO_CALLOUT|PCRE_FIRSTLINE| \ - PCRE_DUPNAMES|PCRE_NEWLINE_BITS|PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE| \ - PCRE_JAVASCRIPT_COMPAT) - -#define PUBLIC_EXEC_OPTIONS \ - (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK| \ - PCRE_PARTIAL|PCRE_NEWLINE_BITS|PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE| \ - PCRE_NO_START_OPTIMIZE) - -#define PUBLIC_DFA_EXEC_OPTIONS \ - (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK| \ - PCRE_PARTIAL|PCRE_DFA_SHORTEST|PCRE_DFA_RESTART|PCRE_NEWLINE_BITS| \ - PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE|PCRE_NO_START_OPTIMIZE) - -#define PUBLIC_STUDY_OPTIONS 0 /* None defined */ - -/* Magic number to provide a small check against being handed junk. Also used -to detect whether a pattern was compiled on a host of different endianness. */ - -#define MAGIC_NUMBER 0x50435245UL /* 'PCRE' */ - -/* Negative values for the firstchar and reqchar variables */ - -#define REQ_UNSET (-2) -#define REQ_NONE (-1) - -/* The maximum remaining length of subject we are prepared to search for a -req_byte match. */ - -#define REQ_BYTE_MAX 1000 - -/* Flags added to firstbyte or reqbyte; a "non-literal" item is either a -variable-length repeat, or a anything other than literal characters. */ - -#define REQ_CASELESS 0x0100 /* indicates caselessness */ -#define REQ_VARY 0x0200 /* reqbyte followed non-literal item */ - -/* Miscellaneous definitions. The #ifndef is to pacify compiler warnings in -environments where these macros are defined elsewhere. Unfortunately, there -is no way to do the same for the typedef. */ - -typedef int BOOL; - -#ifndef FALSE -#define FALSE 0 -#define TRUE 1 -#endif - -/* If PCRE is to support UTF-8 on EBCDIC platforms, we cannot use normal -character constants like '*' because the compiler would emit their EBCDIC code, -which is different from their ASCII/UTF-8 code. Instead we define macros for -the characters so that they always use the ASCII/UTF-8 code when UTF-8 support -is enabled. When UTF-8 support is not enabled, the definitions use character -literals. Both character and string versions of each character are needed, and -there are some longer strings as well. - -This means that, on EBCDIC platforms, the PCRE library can handle either -EBCDIC, or UTF-8, but not both. To support both in the same compiled library -would need different lookups depending on whether PCRE_UTF8 was set or not. -This would make it impossible to use characters in switch/case statements, -which would reduce performance. For a theoretical use (which nobody has asked -for) in a minority area (EBCDIC platforms), this is not sensible. Any -application that did need both could compile two versions of the library, using -macros to give the functions distinct names. */ - -#ifndef SUPPORT_UTF8 - -/* UTF-8 support is not enabled; use the platform-dependent character literals -so that PCRE works on both ASCII and EBCDIC platforms, in non-UTF-mode only. */ - -#define CHAR_HT '\t' -#define CHAR_VT '\v' -#define CHAR_FF '\f' -#define CHAR_CR '\r' -#define CHAR_NL '\n' -#define CHAR_BS '\b' -#define CHAR_BEL '\a' -#ifdef EBCDIC -#define CHAR_ESC '\047' -#define CHAR_DEL '\007' -#else -#define CHAR_ESC '\033' -#define CHAR_DEL '\177' -#endif - -#define CHAR_SPACE ' ' -#define CHAR_EXCLAMATION_MARK '!' -#define CHAR_QUOTATION_MARK '"' -#define CHAR_NUMBER_SIGN '#' -#define CHAR_DOLLAR_SIGN '$' -#define CHAR_PERCENT_SIGN '%' -#define CHAR_AMPERSAND '&' -#define CHAR_APOSTROPHE '\'' -#define CHAR_LEFT_PARENTHESIS '(' -#define CHAR_RIGHT_PARENTHESIS ')' -#define CHAR_ASTERISK '*' -#define CHAR_PLUS '+' -#define CHAR_COMMA ',' -#define CHAR_MINUS '-' -#define CHAR_DOT '.' -#define CHAR_SLASH '/' -#define CHAR_0 '0' -#define CHAR_1 '1' -#define CHAR_2 '2' -#define CHAR_3 '3' -#define CHAR_4 '4' -#define CHAR_5 '5' -#define CHAR_6 '6' -#define CHAR_7 '7' -#define CHAR_8 '8' -#define CHAR_9 '9' -#define CHAR_COLON ':' -#define CHAR_SEMICOLON ';' -#define CHAR_LESS_THAN_SIGN '<' -#define CHAR_EQUALS_SIGN '=' -#define CHAR_GREATER_THAN_SIGN '>' -#define CHAR_QUESTION_MARK '?' -#define CHAR_COMMERCIAL_AT '@' -#define CHAR_A 'A' -#define CHAR_B 'B' -#define CHAR_C 'C' -#define CHAR_D 'D' -#define CHAR_E 'E' -#define CHAR_F 'F' -#define CHAR_G 'G' -#define CHAR_H 'H' -#define CHAR_I 'I' -#define CHAR_J 'J' -#define CHAR_K 'K' -#define CHAR_L 'L' -#define CHAR_M 'M' -#define CHAR_N 'N' -#define CHAR_O 'O' -#define CHAR_P 'P' -#define CHAR_Q 'Q' -#define CHAR_R 'R' -#define CHAR_S 'S' -#define CHAR_T 'T' -#define CHAR_U 'U' -#define CHAR_V 'V' -#define CHAR_W 'W' -#define CHAR_X 'X' -#define CHAR_Y 'Y' -#define CHAR_Z 'Z' -#define CHAR_LEFT_SQUARE_BRACKET '[' -#define CHAR_BACKSLASH '\\' -#define CHAR_RIGHT_SQUARE_BRACKET ']' -#define CHAR_CIRCUMFLEX_ACCENT '^' -#define CHAR_UNDERSCORE '_' -#define CHAR_GRAVE_ACCENT '`' -#define CHAR_a 'a' -#define CHAR_b 'b' -#define CHAR_c 'c' -#define CHAR_d 'd' -#define CHAR_e 'e' -#define CHAR_f 'f' -#define CHAR_g 'g' -#define CHAR_h 'h' -#define CHAR_i 'i' -#define CHAR_j 'j' -#define CHAR_k 'k' -#define CHAR_l 'l' -#define CHAR_m 'm' -#define CHAR_n 'n' -#define CHAR_o 'o' -#define CHAR_p 'p' -#define CHAR_q 'q' -#define CHAR_r 'r' -#define CHAR_s 's' -#define CHAR_t 't' -#define CHAR_u 'u' -#define CHAR_v 'v' -#define CHAR_w 'w' -#define CHAR_x 'x' -#define CHAR_y 'y' -#define CHAR_z 'z' -#define CHAR_LEFT_CURLY_BRACKET '{' -#define CHAR_VERTICAL_LINE '|' -#define CHAR_RIGHT_CURLY_BRACKET '}' -#define CHAR_TILDE '~' - -#define STR_HT "\t" -#define STR_VT "\v" -#define STR_FF "\f" -#define STR_CR "\r" -#define STR_NL "\n" -#define STR_BS "\b" -#define STR_BEL "\a" -#ifdef EBCDIC -#define STR_ESC "\047" -#define STR_DEL "\007" -#else -#define STR_ESC "\033" -#define STR_DEL "\177" -#endif - -#define STR_SPACE " " -#define STR_EXCLAMATION_MARK "!" -#define STR_QUOTATION_MARK "\"" -#define STR_NUMBER_SIGN "#" -#define STR_DOLLAR_SIGN "$" -#define STR_PERCENT_SIGN "%" -#define STR_AMPERSAND "&" -#define STR_APOSTROPHE "'" -#define STR_LEFT_PARENTHESIS "(" -#define STR_RIGHT_PARENTHESIS ")" -#define STR_ASTERISK "*" -#define STR_PLUS "+" -#define STR_COMMA "," -#define STR_MINUS "-" -#define STR_DOT "." -#define STR_SLASH "/" -#define STR_0 "0" -#define STR_1 "1" -#define STR_2 "2" -#define STR_3 "3" -#define STR_4 "4" -#define STR_5 "5" -#define STR_6 "6" -#define STR_7 "7" -#define STR_8 "8" -#define STR_9 "9" -#define STR_COLON ":" -#define STR_SEMICOLON ";" -#define STR_LESS_THAN_SIGN "<" -#define STR_EQUALS_SIGN "=" -#define STR_GREATER_THAN_SIGN ">" -#define STR_QUESTION_MARK "?" -#define STR_COMMERCIAL_AT "@" -#define STR_A "A" -#define STR_B "B" -#define STR_C "C" -#define STR_D "D" -#define STR_E "E" -#define STR_F "F" -#define STR_G "G" -#define STR_H "H" -#define STR_I "I" -#define STR_J "J" -#define STR_K "K" -#define STR_L "L" -#define STR_M "M" -#define STR_N "N" -#define STR_O "O" -#define STR_P "P" -#define STR_Q "Q" -#define STR_R "R" -#define STR_S "S" -#define STR_T "T" -#define STR_U "U" -#define STR_V "V" -#define STR_W "W" -#define STR_X "X" -#define STR_Y "Y" -#define STR_Z "Z" -#define STR_LEFT_SQUARE_BRACKET "[" -#define STR_BACKSLASH "\\" -#define STR_RIGHT_SQUARE_BRACKET "]" -#define STR_CIRCUMFLEX_ACCENT "^" -#define STR_UNDERSCORE "_" -#define STR_GRAVE_ACCENT "`" -#define STR_a "a" -#define STR_b "b" -#define STR_c "c" -#define STR_d "d" -#define STR_e "e" -#define STR_f "f" -#define STR_g "g" -#define STR_h "h" -#define STR_i "i" -#define STR_j "j" -#define STR_k "k" -#define STR_l "l" -#define STR_m "m" -#define STR_n "n" -#define STR_o "o" -#define STR_p "p" -#define STR_q "q" -#define STR_r "r" -#define STR_s "s" -#define STR_t "t" -#define STR_u "u" -#define STR_v "v" -#define STR_w "w" -#define STR_x "x" -#define STR_y "y" -#define STR_z "z" -#define STR_LEFT_CURLY_BRACKET "{" -#define STR_VERTICAL_LINE "|" -#define STR_RIGHT_CURLY_BRACKET "}" -#define STR_TILDE "~" - -#define STRING_ACCEPT0 "ACCEPT\0" -#define STRING_COMMIT0 "COMMIT\0" -#define STRING_F0 "F\0" -#define STRING_FAIL0 "FAIL\0" -#define STRING_PRUNE0 "PRUNE\0" -#define STRING_SKIP0 "SKIP\0" -#define STRING_THEN "THEN" - -#define STRING_alpha0 "alpha\0" -#define STRING_lower0 "lower\0" -#define STRING_upper0 "upper\0" -#define STRING_alnum0 "alnum\0" -#define STRING_ascii0 "ascii\0" -#define STRING_blank0 "blank\0" -#define STRING_cntrl0 "cntrl\0" -#define STRING_digit0 "digit\0" -#define STRING_graph0 "graph\0" -#define STRING_print0 "print\0" -#define STRING_punct0 "punct\0" -#define STRING_space0 "space\0" -#define STRING_word0 "word\0" -#define STRING_xdigit "xdigit" - -#define STRING_DEFINE "DEFINE" - -#define STRING_CR_RIGHTPAR "CR)" -#define STRING_LF_RIGHTPAR "LF)" -#define STRING_CRLF_RIGHTPAR "CRLF)" -#define STRING_ANY_RIGHTPAR "ANY)" -#define STRING_ANYCRLF_RIGHTPAR "ANYCRLF)" -#define STRING_BSR_ANYCRLF_RIGHTPAR "BSR_ANYCRLF)" -#define STRING_BSR_UNICODE_RIGHTPAR "BSR_UNICODE)" -#define STRING_UTF8_RIGHTPAR "UTF8)" - -#else /* SUPPORT_UTF8 */ - -/* UTF-8 support is enabled; always use UTF-8 (=ASCII) character codes. This -works in both modes non-EBCDIC platforms, and on EBCDIC platforms in UTF-8 mode -only. */ - -#define CHAR_HT '\011' -#define CHAR_VT '\013' -#define CHAR_FF '\014' -#define CHAR_CR '\015' -#define CHAR_NL '\012' -#define CHAR_BS '\010' -#define CHAR_BEL '\007' -#define CHAR_ESC '\033' -#define CHAR_DEL '\177' - -#define CHAR_SPACE '\040' -#define CHAR_EXCLAMATION_MARK '\041' -#define CHAR_QUOTATION_MARK '\042' -#define CHAR_NUMBER_SIGN '\043' -#define CHAR_DOLLAR_SIGN '\044' -#define CHAR_PERCENT_SIGN '\045' -#define CHAR_AMPERSAND '\046' -#define CHAR_APOSTROPHE '\047' -#define CHAR_LEFT_PARENTHESIS '\050' -#define CHAR_RIGHT_PARENTHESIS '\051' -#define CHAR_ASTERISK '\052' -#define CHAR_PLUS '\053' -#define CHAR_COMMA '\054' -#define CHAR_MINUS '\055' -#define CHAR_DOT '\056' -#define CHAR_SLASH '\057' -#define CHAR_0 '\060' -#define CHAR_1 '\061' -#define CHAR_2 '\062' -#define CHAR_3 '\063' -#define CHAR_4 '\064' -#define CHAR_5 '\065' -#define CHAR_6 '\066' -#define CHAR_7 '\067' -#define CHAR_8 '\070' -#define CHAR_9 '\071' -#define CHAR_COLON '\072' -#define CHAR_SEMICOLON '\073' -#define CHAR_LESS_THAN_SIGN '\074' -#define CHAR_EQUALS_SIGN '\075' -#define CHAR_GREATER_THAN_SIGN '\076' -#define CHAR_QUESTION_MARK '\077' -#define CHAR_COMMERCIAL_AT '\100' -#define CHAR_A '\101' -#define CHAR_B '\102' -#define CHAR_C '\103' -#define CHAR_D '\104' -#define CHAR_E '\105' -#define CHAR_F '\106' -#define CHAR_G '\107' -#define CHAR_H '\110' -#define CHAR_I '\111' -#define CHAR_J '\112' -#define CHAR_K '\113' -#define CHAR_L '\114' -#define CHAR_M '\115' -#define CHAR_N '\116' -#define CHAR_O '\117' -#define CHAR_P '\120' -#define CHAR_Q '\121' -#define CHAR_R '\122' -#define CHAR_S '\123' -#define CHAR_T '\124' -#define CHAR_U '\125' -#define CHAR_V '\126' -#define CHAR_W '\127' -#define CHAR_X '\130' -#define CHAR_Y '\131' -#define CHAR_Z '\132' -#define CHAR_LEFT_SQUARE_BRACKET '\133' -#define CHAR_BACKSLASH '\134' -#define CHAR_RIGHT_SQUARE_BRACKET '\135' -#define CHAR_CIRCUMFLEX_ACCENT '\136' -#define CHAR_UNDERSCORE '\137' -#define CHAR_GRAVE_ACCENT '\140' -#define CHAR_a '\141' -#define CHAR_b '\142' -#define CHAR_c '\143' -#define CHAR_d '\144' -#define CHAR_e '\145' -#define CHAR_f '\146' -#define CHAR_g '\147' -#define CHAR_h '\150' -#define CHAR_i '\151' -#define CHAR_j '\152' -#define CHAR_k '\153' -#define CHAR_l '\154' -#define CHAR_m '\155' -#define CHAR_n '\156' -#define CHAR_o '\157' -#define CHAR_p '\160' -#define CHAR_q '\161' -#define CHAR_r '\162' -#define CHAR_s '\163' -#define CHAR_t '\164' -#define CHAR_u '\165' -#define CHAR_v '\166' -#define CHAR_w '\167' -#define CHAR_x '\170' -#define CHAR_y '\171' -#define CHAR_z '\172' -#define CHAR_LEFT_CURLY_BRACKET '\173' -#define CHAR_VERTICAL_LINE '\174' -#define CHAR_RIGHT_CURLY_BRACKET '\175' -#define CHAR_TILDE '\176' - -#define STR_HT "\011" -#define STR_VT "\013" -#define STR_FF "\014" -#define STR_CR "\015" -#define STR_NL "\012" -#define STR_BS "\010" -#define STR_BEL "\007" -#define STR_ESC "\033" -#define STR_DEL "\177" - -#define STR_SPACE "\040" -#define STR_EXCLAMATION_MARK "\041" -#define STR_QUOTATION_MARK "\042" -#define STR_NUMBER_SIGN "\043" -#define STR_DOLLAR_SIGN "\044" -#define STR_PERCENT_SIGN "\045" -#define STR_AMPERSAND "\046" -#define STR_APOSTROPHE "\047" -#define STR_LEFT_PARENTHESIS "\050" -#define STR_RIGHT_PARENTHESIS "\051" -#define STR_ASTERISK "\052" -#define STR_PLUS "\053" -#define STR_COMMA "\054" -#define STR_MINUS "\055" -#define STR_DOT "\056" -#define STR_SLASH "\057" -#define STR_0 "\060" -#define STR_1 "\061" -#define STR_2 "\062" -#define STR_3 "\063" -#define STR_4 "\064" -#define STR_5 "\065" -#define STR_6 "\066" -#define STR_7 "\067" -#define STR_8 "\070" -#define STR_9 "\071" -#define STR_COLON "\072" -#define STR_SEMICOLON "\073" -#define STR_LESS_THAN_SIGN "\074" -#define STR_EQUALS_SIGN "\075" -#define STR_GREATER_THAN_SIGN "\076" -#define STR_QUESTION_MARK "\077" -#define STR_COMMERCIAL_AT "\100" -#define STR_A "\101" -#define STR_B "\102" -#define STR_C "\103" -#define STR_D "\104" -#define STR_E "\105" -#define STR_F "\106" -#define STR_G "\107" -#define STR_H "\110" -#define STR_I "\111" -#define STR_J "\112" -#define STR_K "\113" -#define STR_L "\114" -#define STR_M "\115" -#define STR_N "\116" -#define STR_O "\117" -#define STR_P "\120" -#define STR_Q "\121" -#define STR_R "\122" -#define STR_S "\123" -#define STR_T "\124" -#define STR_U "\125" -#define STR_V "\126" -#define STR_W "\127" -#define STR_X "\130" -#define STR_Y "\131" -#define STR_Z "\132" -#define STR_LEFT_SQUARE_BRACKET "\133" -#define STR_BACKSLASH "\134" -#define STR_RIGHT_SQUARE_BRACKET "\135" -#define STR_CIRCUMFLEX_ACCENT "\136" -#define STR_UNDERSCORE "\137" -#define STR_GRAVE_ACCENT "\140" -#define STR_a "\141" -#define STR_b "\142" -#define STR_c "\143" -#define STR_d "\144" -#define STR_e "\145" -#define STR_f "\146" -#define STR_g "\147" -#define STR_h "\150" -#define STR_i "\151" -#define STR_j "\152" -#define STR_k "\153" -#define STR_l "\154" -#define STR_m "\155" -#define STR_n "\156" -#define STR_o "\157" -#define STR_p "\160" -#define STR_q "\161" -#define STR_r "\162" -#define STR_s "\163" -#define STR_t "\164" -#define STR_u "\165" -#define STR_v "\166" -#define STR_w "\167" -#define STR_x "\170" -#define STR_y "\171" -#define STR_z "\172" -#define STR_LEFT_CURLY_BRACKET "\173" -#define STR_VERTICAL_LINE "\174" -#define STR_RIGHT_CURLY_BRACKET "\175" -#define STR_TILDE "\176" - -#define STRING_ACCEPT0 STR_A STR_C STR_C STR_E STR_P STR_T "\0" -#define STRING_COMMIT0 STR_C STR_O STR_M STR_M STR_I STR_T "\0" -#define STRING_F0 STR_F "\0" -#define STRING_FAIL0 STR_F STR_A STR_I STR_L "\0" -#define STRING_PRUNE0 STR_P STR_R STR_U STR_N STR_E "\0" -#define STRING_SKIP0 STR_S STR_K STR_I STR_P "\0" -#define STRING_THEN STR_T STR_H STR_E STR_N - -#define STRING_alpha0 STR_a STR_l STR_p STR_h STR_a "\0" -#define STRING_lower0 STR_l STR_o STR_w STR_e STR_r "\0" -#define STRING_upper0 STR_u STR_p STR_p STR_e STR_r "\0" -#define STRING_alnum0 STR_a STR_l STR_n STR_u STR_m "\0" -#define STRING_ascii0 STR_a STR_s STR_c STR_i STR_i "\0" -#define STRING_blank0 STR_b STR_l STR_a STR_n STR_k "\0" -#define STRING_cntrl0 STR_c STR_n STR_t STR_r STR_l "\0" -#define STRING_digit0 STR_d STR_i STR_g STR_i STR_t "\0" -#define STRING_graph0 STR_g STR_r STR_a STR_p STR_h "\0" -#define STRING_print0 STR_p STR_r STR_i STR_n STR_t "\0" -#define STRING_punct0 STR_p STR_u STR_n STR_c STR_t "\0" -#define STRING_space0 STR_s STR_p STR_a STR_c STR_e "\0" -#define STRING_word0 STR_w STR_o STR_r STR_d "\0" -#define STRING_xdigit STR_x STR_d STR_i STR_g STR_i STR_t - -#define STRING_DEFINE STR_D STR_E STR_F STR_I STR_N STR_E - -#define STRING_CR_RIGHTPAR STR_C STR_R STR_RIGHT_PARENTHESIS -#define STRING_LF_RIGHTPAR STR_L STR_F STR_RIGHT_PARENTHESIS -#define STRING_CRLF_RIGHTPAR STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS -#define STRING_ANY_RIGHTPAR STR_A STR_N STR_Y STR_RIGHT_PARENTHESIS -#define STRING_ANYCRLF_RIGHTPAR STR_A STR_N STR_Y STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS -#define STRING_BSR_ANYCRLF_RIGHTPAR STR_B STR_S STR_R STR_UNDERSCORE STR_A STR_N STR_Y STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS -#define STRING_BSR_UNICODE_RIGHTPAR STR_B STR_S STR_R STR_UNDERSCORE STR_U STR_N STR_I STR_C STR_O STR_D STR_E STR_RIGHT_PARENTHESIS -#define STRING_UTF8_RIGHTPAR STR_U STR_T STR_F STR_8 STR_RIGHT_PARENTHESIS - -#endif /* SUPPORT_UTF8 */ - -/* Escape items that are just an encoding of a particular data value. */ - -#ifndef ESC_e -#define ESC_e CHAR_ESC -#endif - -#ifndef ESC_f -#define ESC_f CHAR_FF -#endif - -#ifndef ESC_n -#define ESC_n CHAR_NL -#endif - -#ifndef ESC_r -#define ESC_r CHAR_CR -#endif - -/* We can't officially use ESC_t because it is a POSIX reserved identifier -(presumably because of all the others like size_t). */ - -#ifndef ESC_tee -#define ESC_tee CHAR_HT -#endif - -/* Codes for different types of Unicode property */ - -#define PT_ANY 0 /* Any property - matches all chars */ -#define PT_LAMP 1 /* L& - the union of Lu, Ll, Lt */ -#define PT_GC 2 /* General characteristic (e.g. L) */ -#define PT_PC 3 /* Particular characteristic (e.g. Lu) */ -#define PT_SC 4 /* Script (e.g. Han) */ - -/* Flag bits and data types for the extended class (OP_XCLASS) for classes that -contain UTF-8 characters with values greater than 255. */ - -#define XCL_NOT 0x01 /* Flag: this is a negative class */ -#define XCL_MAP 0x02 /* Flag: a 32-byte map is present */ - -#define XCL_END 0 /* Marks end of individual items */ -#define XCL_SINGLE 1 /* Single item (one multibyte char) follows */ -#define XCL_RANGE 2 /* A range (two multibyte chars) follows */ -#define XCL_PROP 3 /* Unicode property (2-byte property code follows) */ -#define XCL_NOTPROP 4 /* Unicode inverted property (ditto) */ - -/* These are escaped items that aren't just an encoding of a particular data -value such as \n. They must have non-zero values, as check_escape() returns -their negation. Also, they must appear in the same order as in the opcode -definitions below, up to ESC_z. There's a dummy for OP_ANY because it -corresponds to "." rather than an escape sequence, and another for OP_ALLANY -(which is used for [^] in JavaScript compatibility mode). - -The final escape must be ESC_REF as subsequent values are used for -backreferences (\1, \2, \3, etc). There are two tests in the code for an escape -greater than ESC_b and less than ESC_Z to detect the types that may be -repeated. These are the types that consume characters. If any new escapes are -put in between that don't consume a character, that code will have to change. -*/ - -enum { ESC_A = 1, ESC_G, ESC_K, ESC_B, ESC_b, ESC_D, ESC_d, ESC_S, ESC_s, - ESC_W, ESC_w, ESC_dum1, ESC_dum2, ESC_C, ESC_P, ESC_p, ESC_R, ESC_H, - ESC_h, ESC_V, ESC_v, ESC_X, ESC_Z, ESC_z, ESC_E, ESC_Q, ESC_g, ESC_k, - ESC_REF }; - - -/* Opcode table: Starting from 1 (i.e. after OP_END), the values up to -OP_EOD must correspond in order to the list of escapes immediately above. - -*** NOTE NOTE NOTE *** Whenever this list is updated, the two macro definitions -that follow must also be updated to match. There is also a table called -"coptable" in pcre_dfa_exec.c that must be updated. */ - -enum { - OP_END, /* 0 End of pattern */ - - /* Values corresponding to backslashed metacharacters */ - - OP_SOD, /* 1 Start of data: \A */ - OP_SOM, /* 2 Start of match (subject + offset): \G */ - OP_SET_SOM, /* 3 Set start of match (\K) */ - OP_NOT_WORD_BOUNDARY, /* 4 \B */ - OP_WORD_BOUNDARY, /* 5 \b */ - OP_NOT_DIGIT, /* 6 \D */ - OP_DIGIT, /* 7 \d */ - OP_NOT_WHITESPACE, /* 8 \S */ - OP_WHITESPACE, /* 9 \s */ - OP_NOT_WORDCHAR, /* 10 \W */ - OP_WORDCHAR, /* 11 \w */ - OP_ANY, /* 12 Match any character (subject to DOTALL) */ - OP_ALLANY, /* 13 Match any character (not subject to DOTALL) */ - OP_ANYBYTE, /* 14 Match any byte (\C); different to OP_ANY for UTF-8 */ - OP_NOTPROP, /* 15 \P (not Unicode property) */ - OP_PROP, /* 16 \p (Unicode property) */ - OP_ANYNL, /* 17 \R (any newline sequence) */ - OP_NOT_HSPACE, /* 18 \H (not horizontal whitespace) */ - OP_HSPACE, /* 19 \h (horizontal whitespace) */ - OP_NOT_VSPACE, /* 20 \V (not vertical whitespace) */ - OP_VSPACE, /* 21 \v (vertical whitespace) */ - OP_EXTUNI, /* 22 \X (extended Unicode sequence */ - OP_EODN, /* 23 End of data or \n at end of data: \Z. */ - OP_EOD, /* 24 End of data: \z */ - - OP_OPT, /* 25 Set runtime options */ - OP_CIRC, /* 26 Start of line - varies with multiline switch */ - OP_DOLL, /* 27 End of line - varies with multiline switch */ - OP_CHAR, /* 28 Match one character, casefully */ - OP_CHARNC, /* 29 Match one character, caselessly */ - OP_NOT, /* 30 Match one character, not the following one */ - - OP_STAR, /* 31 The maximizing and minimizing versions of */ - OP_MINSTAR, /* 32 these six opcodes must come in pairs, with */ - OP_PLUS, /* 33 the minimizing one second. */ - OP_MINPLUS, /* 34 This first set applies to single characters.*/ - OP_QUERY, /* 35 */ - OP_MINQUERY, /* 36 */ - - OP_UPTO, /* 37 From 0 to n matches */ - OP_MINUPTO, /* 38 */ - OP_EXACT, /* 39 Exactly n matches */ - - OP_POSSTAR, /* 40 Possessified star */ - OP_POSPLUS, /* 41 Possessified plus */ - OP_POSQUERY, /* 42 Posesssified query */ - OP_POSUPTO, /* 43 Possessified upto */ - - OP_NOTSTAR, /* 44 The maximizing and minimizing versions of */ - OP_NOTMINSTAR, /* 45 these six opcodes must come in pairs, with */ - OP_NOTPLUS, /* 46 the minimizing one second. They must be in */ - OP_NOTMINPLUS, /* 47 exactly the same order as those above. */ - OP_NOTQUERY, /* 48 This set applies to "not" single characters. */ - OP_NOTMINQUERY, /* 49 */ - - OP_NOTUPTO, /* 50 From 0 to n matches */ - OP_NOTMINUPTO, /* 51 */ - OP_NOTEXACT, /* 52 Exactly n matches */ - - OP_NOTPOSSTAR, /* 53 Possessified versions */ - OP_NOTPOSPLUS, /* 54 */ - OP_NOTPOSQUERY, /* 55 */ - OP_NOTPOSUPTO, /* 56 */ - - OP_TYPESTAR, /* 57 The maximizing and minimizing versions of */ - OP_TYPEMINSTAR, /* 58 these six opcodes must come in pairs, with */ - OP_TYPEPLUS, /* 59 the minimizing one second. These codes must */ - OP_TYPEMINPLUS, /* 60 be in exactly the same order as those above. */ - OP_TYPEQUERY, /* 61 This set applies to character types such as \d */ - OP_TYPEMINQUERY, /* 62 */ - - OP_TYPEUPTO, /* 63 From 0 to n matches */ - OP_TYPEMINUPTO, /* 64 */ - OP_TYPEEXACT, /* 65 Exactly n matches */ - - OP_TYPEPOSSTAR, /* 66 Possessified versions */ - OP_TYPEPOSPLUS, /* 67 */ - OP_TYPEPOSQUERY, /* 68 */ - OP_TYPEPOSUPTO, /* 69 */ - - OP_CRSTAR, /* 70 The maximizing and minimizing versions of */ - OP_CRMINSTAR, /* 71 all these opcodes must come in pairs, with */ - OP_CRPLUS, /* 72 the minimizing one second. These codes must */ - OP_CRMINPLUS, /* 73 be in exactly the same order as those above. */ - OP_CRQUERY, /* 74 These are for character classes and back refs */ - OP_CRMINQUERY, /* 75 */ - OP_CRRANGE, /* 76 These are different to the three sets above. */ - OP_CRMINRANGE, /* 77 */ - - OP_CLASS, /* 78 Match a character class, chars < 256 only */ - OP_NCLASS, /* 79 Same, but the bitmap was created from a negative - class - the difference is relevant only when a UTF-8 - character > 255 is encountered. */ - - OP_XCLASS, /* 80 Extended class for handling UTF-8 chars within the - class. This does both positive and negative. */ - - OP_REF, /* 81 Match a back reference */ - OP_RECURSE, /* 82 Match a numbered subpattern (possibly recursive) */ - OP_CALLOUT, /* 83 Call out to external function if provided */ - - OP_ALT, /* 84 Start of alternation */ - OP_KET, /* 85 End of group that doesn't have an unbounded repeat */ - OP_KETRMAX, /* 86 These two must remain together and in this */ - OP_KETRMIN, /* 87 order. They are for groups the repeat for ever. */ - - /* The assertions must come before BRA, CBRA, ONCE, and COND.*/ - - OP_ASSERT, /* 88 Positive lookahead */ - OP_ASSERT_NOT, /* 89 Negative lookahead */ - OP_ASSERTBACK, /* 90 Positive lookbehind */ - OP_ASSERTBACK_NOT, /* 91 Negative lookbehind */ - OP_REVERSE, /* 92 Move pointer back - used in lookbehind assertions */ - - /* ONCE, BRA, CBRA, and COND must come after the assertions, with ONCE first, - as there's a test for >= ONCE for a subpattern that isn't an assertion. */ - - OP_ONCE, /* 93 Atomic group */ - OP_BRA, /* 94 Start of non-capturing bracket */ - OP_CBRA, /* 95 Start of capturing bracket */ - OP_COND, /* 96 Conditional group */ - - /* These three must follow the previous three, in the same order. There's a - check for >= SBRA to distinguish the two sets. */ - - OP_SBRA, /* 97 Start of non-capturing bracket, check empty */ - OP_SCBRA, /* 98 Start of capturing bracket, check empty */ - OP_SCOND, /* 99 Conditional group, check empty */ - - OP_CREF, /* 100 Used to hold a capture number as condition */ - OP_RREF, /* 101 Used to hold a recursion number as condition */ - OP_DEF, /* 102 The DEFINE condition */ - - OP_BRAZERO, /* 103 These two must remain together and in this */ - OP_BRAMINZERO, /* 104 order. */ - - /* These are backtracking control verbs */ - - OP_PRUNE, /* 105 */ - OP_SKIP, /* 106 */ - OP_THEN, /* 107 */ - OP_COMMIT, /* 108 */ - - /* These are forced failure and success verbs */ - - OP_FAIL, /* 109 */ - OP_ACCEPT, /* 110 */ - - /* This is used to skip a subpattern with a {0} quantifier */ - - OP_SKIPZERO /* 111 */ -}; - - -/* This macro defines textual names for all the opcodes. These are used only -for debugging. The macro is referenced only in pcre_printint.c. */ - -#define OP_NAME_LIST \ - "End", "\\A", "\\G", "\\K", "\\B", "\\b", "\\D", "\\d", \ - "\\S", "\\s", "\\W", "\\w", "Any", "AllAny", "Anybyte", \ - "notprop", "prop", "\\R", "\\H", "\\h", "\\V", "\\v", \ - "extuni", "\\Z", "\\z", \ - "Opt", "^", "$", "char", "charnc", "not", \ - "*", "*?", "+", "+?", "?", "??", "{", "{", "{", \ - "*+","++", "?+", "{", \ - "*", "*?", "+", "+?", "?", "??", "{", "{", "{", \ - "*+","++", "?+", "{", \ - "*", "*?", "+", "+?", "?", "??", "{", "{", "{", \ - "*+","++", "?+", "{", \ - "*", "*?", "+", "+?", "?", "??", "{", "{", \ - "class", "nclass", "xclass", "Ref", "Recurse", "Callout", \ - "Alt", "Ket", "KetRmax", "KetRmin", "Assert", "Assert not", \ - "AssertB", "AssertB not", "Reverse", \ - "Once", "Bra", "CBra", "Cond", "SBra", "SCBra", "SCond", \ - "Cond ref", "Cond rec", "Cond def", "Brazero", "Braminzero", \ - "*PRUNE", "*SKIP", "*THEN", "*COMMIT", "*FAIL", "*ACCEPT", \ - "Skip zero" - - -/* This macro defines the length of fixed length operations in the compiled -regex. The lengths are used when searching for specific things, and also in the -debugging printing of a compiled regex. We use a macro so that it can be -defined close to the definitions of the opcodes themselves. - -As things have been extended, some of these are no longer fixed lenths, but are -minima instead. For example, the length of a single-character repeat may vary -in UTF-8 mode. The code that uses this table must know about such things. */ - -#define OP_LENGTHS \ - 1, /* End */ \ - 1, 1, 1, 1, 1, /* \A, \G, \K, \B, \b */ \ - 1, 1, 1, 1, 1, 1, /* \D, \d, \S, \s, \W, \w */ \ - 1, 1, 1, /* Any, AllAny, Anybyte */ \ - 3, 3, 1, /* NOTPROP, PROP, EXTUNI */ \ - 1, 1, 1, 1, 1, /* \R, \H, \h, \V, \v */ \ - 1, 1, 2, 1, 1, /* \Z, \z, Opt, ^, $ */ \ - 2, /* Char - the minimum length */ \ - 2, /* Charnc - the minimum length */ \ - 2, /* not */ \ - /* Positive single-char repeats ** These are */ \ - 2, 2, 2, 2, 2, 2, /* *, *?, +, +?, ?, ?? ** minima in */ \ - 4, 4, 4, /* upto, minupto, exact ** UTF-8 mode */ \ - 2, 2, 2, 4, /* *+, ++, ?+, upto+ */ \ - /* Negative single-char repeats - only for chars < 256 */ \ - 2, 2, 2, 2, 2, 2, /* NOT *, *?, +, +?, ?, ?? */ \ - 4, 4, 4, /* NOT upto, minupto, exact */ \ - 2, 2, 2, 4, /* Possessive *, +, ?, upto */ \ - /* Positive type repeats */ \ - 2, 2, 2, 2, 2, 2, /* Type *, *?, +, +?, ?, ?? */ \ - 4, 4, 4, /* Type upto, minupto, exact */ \ - 2, 2, 2, 4, /* Possessive *+, ++, ?+, upto+ */ \ - /* Character class & ref repeats */ \ - 1, 1, 1, 1, 1, 1, /* *, *?, +, +?, ?, ?? */ \ - 5, 5, /* CRRANGE, CRMINRANGE */ \ - 33, /* CLASS */ \ - 33, /* NCLASS */ \ - 0, /* XCLASS - variable length */ \ - 3, /* REF */ \ - 1+LINK_SIZE, /* RECURSE */ \ - 2+2*LINK_SIZE, /* CALLOUT */ \ - 1+LINK_SIZE, /* Alt */ \ - 1+LINK_SIZE, /* Ket */ \ - 1+LINK_SIZE, /* KetRmax */ \ - 1+LINK_SIZE, /* KetRmin */ \ - 1+LINK_SIZE, /* Assert */ \ - 1+LINK_SIZE, /* Assert not */ \ - 1+LINK_SIZE, /* Assert behind */ \ - 1+LINK_SIZE, /* Assert behind not */ \ - 1+LINK_SIZE, /* Reverse */ \ - 1+LINK_SIZE, /* ONCE */ \ - 1+LINK_SIZE, /* BRA */ \ - 3+LINK_SIZE, /* CBRA */ \ - 1+LINK_SIZE, /* COND */ \ - 1+LINK_SIZE, /* SBRA */ \ - 3+LINK_SIZE, /* SCBRA */ \ - 1+LINK_SIZE, /* SCOND */ \ - 3, /* CREF */ \ - 3, /* RREF */ \ - 1, /* DEF */ \ - 1, 1, /* BRAZERO, BRAMINZERO */ \ - 1, 1, 1, 1, /* PRUNE, SKIP, THEN, COMMIT, */ \ - 1, 1, 1 /* FAIL, ACCEPT, SKIPZERO */ - - -/* A magic value for OP_RREF to indicate the "any recursion" condition. */ - -#define RREF_ANY 0xffff - -/* Error code numbers. They are given names so that they can more easily be -tracked. */ - -enum { ERR0, ERR1, ERR2, ERR3, ERR4, ERR5, ERR6, ERR7, ERR8, ERR9, - ERR10, ERR11, ERR12, ERR13, ERR14, ERR15, ERR16, ERR17, ERR18, ERR19, - ERR20, ERR21, ERR22, ERR23, ERR24, ERR25, ERR26, ERR27, ERR28, ERR29, - ERR30, ERR31, ERR32, ERR33, ERR34, ERR35, ERR36, ERR37, ERR38, ERR39, - ERR40, ERR41, ERR42, ERR43, ERR44, ERR45, ERR46, ERR47, ERR48, ERR49, - ERR50, ERR51, ERR52, ERR53, ERR54, ERR55, ERR56, ERR57, ERR58, ERR59, - ERR60, ERR61, ERR62, ERR63, ERR64 }; - -/* The real format of the start of the pcre block; the index of names and the -code vector run on as long as necessary after the end. We store an explicit -offset to the name table so that if a regex is compiled on one host, saved, and -then run on another where the size of pointers is different, all might still -be well. For the case of compiled-on-4 and run-on-8, we include an extra -pointer that is always NULL. For future-proofing, a few dummy fields were -originally included - even though you can never get this planning right - but -there is only one left now. - -NOTE NOTE NOTE: -Because people can now save and re-use compiled patterns, any additions to this -structure should be made at the end, and something earlier (e.g. a new -flag in the options or one of the dummy fields) should indicate that the new -fields are present. Currently PCRE always sets the dummy fields to zero. -NOTE NOTE NOTE: -*/ - -typedef struct real_pcre { - pcre_uint32 magic_number; - pcre_uint32 size; /* Total that was malloced */ - pcre_uint32 options; /* Public options */ - pcre_uint16 flags; /* Private flags */ - pcre_uint16 dummy1; /* For future use */ - pcre_uint16 top_bracket; - pcre_uint16 top_backref; - pcre_uint16 first_byte; - pcre_uint16 req_byte; - pcre_uint16 name_table_offset; /* Offset to name table that follows */ - pcre_uint16 name_entry_size; /* Size of any name items */ - pcre_uint16 name_count; /* Number of name items */ - pcre_uint16 ref_count; /* Reference count */ - - const unsigned char *tables; /* Pointer to tables or NULL for std */ - const unsigned char *nullpad; /* NULL padding */ -} real_pcre; - -/* The format of the block used to store data from pcre_study(). The same -remark (see NOTE above) about extending this structure applies. */ - -typedef struct pcre_study_data { - pcre_uint32 size; /* Total that was malloced */ - pcre_uint32 options; - uschar start_bits[32]; -} pcre_study_data; - -/* Structure for passing "static" information around between the functions -doing the compiling, so that they are thread-safe. */ - -typedef struct compile_data { - const uschar *lcc; /* Points to lower casing table */ - const uschar *fcc; /* Points to case-flipping table */ - const uschar *cbits; /* Points to character type table */ - const uschar *ctypes; /* Points to table of type maps */ - const uschar *start_workspace;/* The start of working space */ - const uschar *start_code; /* The start of the compiled code */ - const uschar *start_pattern; /* The start of the pattern */ - const uschar *end_pattern; /* The end of the pattern */ - uschar *hwm; /* High watermark of workspace */ - uschar *name_table; /* The name/number table */ - int names_found; /* Number of entries so far */ - int name_entry_size; /* Size of each entry */ - int bracount; /* Count of capturing parens as we compile */ - int final_bracount; /* Saved value after first pass */ - int top_backref; /* Maximum back reference */ - unsigned int backref_map; /* Bitmap of low back refs */ - int external_options; /* External (initial) options */ - int external_flags; /* External flag bits to be set */ - int req_varyopt; /* "After variable item" flag for reqbyte */ - BOOL had_accept; /* (*ACCEPT) encountered */ - int nltype; /* Newline type */ - int nllen; /* Newline string length */ - uschar nl[4]; /* Newline string when fixed length */ -} compile_data; - -/* Structure for maintaining a chain of pointers to the currently incomplete -branches, for testing for left recursion. */ - -typedef struct branch_chain { - struct branch_chain *outer; - uschar *current; -} branch_chain; - -/* Structure for items in a linked list that represents an explicit recursive -call within the pattern. */ - -typedef struct recursion_info { - struct recursion_info *prevrec; /* Previous recursion record (or NULL) */ - int group_num; /* Number of group that was called */ - const uschar *after_call; /* "Return value": points after the call in the expr */ - USPTR save_start; /* Old value of mstart */ - int *offset_save; /* Pointer to start of saved offsets */ - int saved_max; /* Number of saved offsets */ -} recursion_info; - -/* Structure for building a chain of data for holding the values of the subject -pointer at the start of each subpattern, so as to detect when an empty string -has been matched by a subpattern - to break infinite loops. */ - -typedef struct eptrblock { - struct eptrblock *epb_prev; - USPTR epb_saved_eptr; -} eptrblock; - - -/* Structure for passing "static" information around between the functions -doing traditional NFA matching, so that they are thread-safe. */ - -typedef struct match_data { - unsigned long int match_call_count; /* As it says */ - unsigned long int match_limit; /* As it says */ - unsigned long int match_limit_recursion; /* As it says */ - int *offset_vector; /* Offset vector */ - int offset_end; /* One past the end */ - int offset_max; /* The maximum usable for return data */ - int nltype; /* Newline type */ - int nllen; /* Newline string length */ - uschar nl[4]; /* Newline string when fixed */ - const uschar *lcc; /* Points to lower casing table */ - const uschar *ctypes; /* Points to table of type maps */ - BOOL offset_overflow; /* Set if too many extractions */ - BOOL notbol; /* NOTBOL flag */ - BOOL noteol; /* NOTEOL flag */ - BOOL utf8; /* UTF8 flag */ - BOOL jscript_compat; /* JAVASCRIPT_COMPAT flag */ - BOOL endonly; /* Dollar not before final \n */ - BOOL notempty; /* Empty string match not wanted */ - BOOL partial; /* PARTIAL flag */ - BOOL hitend; /* Hit the end of the subject at some point */ - BOOL bsr_anycrlf; /* \R is just any CRLF, not full Unicode */ - const uschar *start_code; /* For use when recursing */ - USPTR start_subject; /* Start of the subject string */ - USPTR end_subject; /* End of the subject string */ - USPTR start_match_ptr; /* Start of matched string */ - USPTR end_match_ptr; /* Subject position at end match */ - int end_offset_top; /* Highwater mark at end of match */ - int capture_last; /* Most recent capture number */ - int start_offset; /* The start offset value */ - eptrblock *eptrchain; /* Chain of eptrblocks for tail recursions */ - int eptrn; /* Next free eptrblock */ - recursion_info *recursive; /* Linked list of recursion data */ - void *callout_data; /* To pass back to callouts */ -} match_data; - -/* A similar structure is used for the same purpose by the DFA matching -functions. */ - -typedef struct dfa_match_data { - const uschar *start_code; /* Start of the compiled pattern */ - const uschar *start_subject; /* Start of the subject string */ - const uschar *end_subject; /* End of subject string */ - const uschar *tables; /* Character tables */ - int moptions; /* Match options */ - int poptions; /* Pattern options */ - int nltype; /* Newline type */ - int nllen; /* Newline string length */ - uschar nl[4]; /* Newline string when fixed */ - void *callout_data; /* To pass back to callouts */ -} dfa_match_data; - -/* Bit definitions for entries in the pcre_ctypes table. */ - -#define ctype_space 0x01 -#define ctype_letter 0x02 -#define ctype_digit 0x04 -#define ctype_xdigit 0x08 -#define ctype_word 0x10 /* alphanumeric or '_' */ -#define ctype_meta 0x80 /* regexp meta char or zero (end pattern) */ - -/* Offsets for the bitmap tables in pcre_cbits. Each table contains a set -of bits for a class map. Some classes are built by combining these tables. */ - -#define cbit_space 0 /* [:space:] or \s */ -#define cbit_xdigit 32 /* [:xdigit:] */ -#define cbit_digit 64 /* [:digit:] or \d */ -#define cbit_upper 96 /* [:upper:] */ -#define cbit_lower 128 /* [:lower:] */ -#define cbit_word 160 /* [:word:] or \w */ -#define cbit_graph 192 /* [:graph:] */ -#define cbit_print 224 /* [:print:] */ -#define cbit_punct 256 /* [:punct:] */ -#define cbit_cntrl 288 /* [:cntrl:] */ -#define cbit_length 320 /* Length of the cbits table */ - -/* Offsets of the various tables from the base tables pointer, and -total length. */ - -#define lcc_offset 0 -#define fcc_offset 256 -#define cbits_offset 512 -#define ctypes_offset (cbits_offset + cbit_length) -#define tables_length (ctypes_offset + 256) - -/* Layout of the UCP type table that translates property names into types and -codes. Each entry used to point directly to a name, but to reduce the number of -relocations in shared libraries, it now has an offset into a single string -instead. */ - -typedef struct { - pcre_uint16 name_offset; - pcre_uint16 type; - pcre_uint16 value; -} ucp_type_table; - - -/* Internal shared data tables. These are tables that are used by more than one -of the exported public functions. They have to be "external" in the C sense, -but are not part of the PCRE public API. The data for these tables is in the -pcre_tables.c module. */ - -extern const int _pcre_utf8_table1[]; -extern const int _pcre_utf8_table2[]; -extern const int _pcre_utf8_table3[]; -extern const uschar _pcre_utf8_table4[]; - -extern const int _pcre_utf8_table1_size; - -extern const char _pcre_utt_names[]; -extern const ucp_type_table _pcre_utt[]; -extern const int _pcre_utt_size; - -extern const uschar _pcre_default_tables[]; - -extern const uschar _pcre_OP_lengths[]; - - -/* Internal shared functions. These are functions that are used by more than -one of the exported public functions. They have to be "external" in the C -sense, but are not part of the PCRE public API. */ - -extern BOOL _pcre_is_newline(const uschar *, int, const uschar *, - int *, BOOL); -extern int _pcre_ord2utf8(int, uschar *); -extern real_pcre *_pcre_try_flipped(const real_pcre *, real_pcre *, - const pcre_study_data *, pcre_study_data *); -extern int _pcre_valid_utf8(const uschar *, int); -extern BOOL _pcre_was_newline(const uschar *, int, const uschar *, - int *, BOOL); -extern BOOL _pcre_xclass(int, const uschar *); - - -/* Unicode character database (UCD) */ - -typedef struct { - uschar script; - uschar chartype; - pcre_int32 other_case; -} ucd_record; - -extern const ucd_record _pcre_ucd_records[]; -extern const uschar _pcre_ucd_stage1[]; -extern const pcre_uint16 _pcre_ucd_stage2[]; -extern const int _pcre_ucp_gentype[]; - - -/* UCD access macros */ - -#define UCD_BLOCK_SIZE 128 -#define GET_UCD(ch) (_pcre_ucd_records + \ - _pcre_ucd_stage2[_pcre_ucd_stage1[(ch) / UCD_BLOCK_SIZE] * \ - UCD_BLOCK_SIZE + ch % UCD_BLOCK_SIZE]) - -#define UCD_CHARTYPE(ch) GET_UCD(ch)->chartype -#define UCD_SCRIPT(ch) GET_UCD(ch)->script -#define UCD_CATEGORY(ch) _pcre_ucp_gentype[UCD_CHARTYPE(ch)] -#define UCD_OTHERCASE(ch) (ch + GET_UCD(ch)->other_case) - -#endif - -/* End of pcre_internal.h */ diff --git a/libs/pcre/pcre_maketables.c b/libs/pcre/pcre_maketables.c deleted file mode 100644 index 219973e378..0000000000 --- a/libs/pcre/pcre_maketables.c +++ /dev/null @@ -1,143 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2008 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains the external function pcre_maketables(), which builds -character tables for PCRE in the current locale. The file is compiled on its -own as part of the PCRE library. However, it is also included in the -compilation of dftables.c, in which case the macro DFTABLES is defined. */ - - -#ifndef DFTABLES -# ifdef HAVE_CONFIG_H -# include "config.h" -# endif -# include "pcre_internal.h" -#endif - - -/************************************************* -* Create PCRE character tables * -*************************************************/ - -/* This function builds a set of character tables for use by PCRE and returns -a pointer to them. They are build using the ctype functions, and consequently -their contents will depend upon the current locale setting. When compiled as -part of the library, the store is obtained via pcre_malloc(), but when compiled -inside dftables, use malloc(). - -Arguments: none -Returns: pointer to the contiguous block of data -*/ - -const unsigned char * -pcre_maketables(void) -{ -unsigned char *yield, *p; -int i; - -#ifndef DFTABLES -yield = (unsigned char*)(pcre_malloc)(tables_length); -#else -yield = (unsigned char*)malloc(tables_length); -#endif - -if (yield == NULL) return NULL; -p = yield; - -/* First comes the lower casing table */ - -for (i = 0; i < 256; i++) *p++ = tolower(i); - -/* Next the case-flipping table */ - -for (i = 0; i < 256; i++) *p++ = islower(i)? toupper(i) : tolower(i); - -/* Then the character class tables. Don't try to be clever and save effort on -exclusive ones - in some locales things may be different. Note that the table -for "space" includes everything "isspace" gives, including VT in the default -locale. This makes it work for the POSIX class [:space:]. Note also that it is -possible for a character to be alnum or alpha without being lower or upper, -such as "male and female ordinals" (\xAA and \xBA) in the fr_FR locale (at -least under Debian Linux's locales as of 12/2005). So we must test for alnum -specially. */ - -memset(p, 0, cbit_length); -for (i = 0; i < 256; i++) - { - if (isdigit(i)) p[cbit_digit + i/8] |= 1 << (i&7); - if (isupper(i)) p[cbit_upper + i/8] |= 1 << (i&7); - if (islower(i)) p[cbit_lower + i/8] |= 1 << (i&7); - if (isalnum(i)) p[cbit_word + i/8] |= 1 << (i&7); - if (i == '_') p[cbit_word + i/8] |= 1 << (i&7); - if (isspace(i)) p[cbit_space + i/8] |= 1 << (i&7); - if (isxdigit(i))p[cbit_xdigit + i/8] |= 1 << (i&7); - if (isgraph(i)) p[cbit_graph + i/8] |= 1 << (i&7); - if (isprint(i)) p[cbit_print + i/8] |= 1 << (i&7); - if (ispunct(i)) p[cbit_punct + i/8] |= 1 << (i&7); - if (iscntrl(i)) p[cbit_cntrl + i/8] |= 1 << (i&7); - } -p += cbit_length; - -/* Finally, the character type table. In this, we exclude VT from the white -space chars, because Perl doesn't recognize it as such for \s and for comments -within regexes. */ - -for (i = 0; i < 256; i++) - { - int x = 0; - if (i != 0x0b && isspace(i)) x += ctype_space; - if (isalpha(i)) x += ctype_letter; - if (isdigit(i)) x += ctype_digit; - if (isxdigit(i)) x += ctype_xdigit; - if (isalnum(i) || i == '_') x += ctype_word; - - /* Note: strchr includes the terminating zero in the characters it considers. - In this instance, that is ok because we want binary zero to be flagged as a - meta-character, which in this sense is any character that terminates a run - of data characters. */ - - if (strchr("\\*+?{^.$|()[", i) != 0) x += ctype_meta; - *p++ = x; - } - -return yield; -} - -/* End of pcre_maketables.c */ diff --git a/libs/pcre/pcre_newline.c b/libs/pcre/pcre_newline.c deleted file mode 100644 index 38cf7f72f8..0000000000 --- a/libs/pcre/pcre_newline.c +++ /dev/null @@ -1,162 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2009 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains internal functions for testing newlines when more than -one kind of newline is to be recognized. When a newline is found, its length is -returned. In principle, we could implement several newline "types", each -referring to a different set of newline characters. At present, PCRE supports -only NLTYPE_FIXED, which gets handled without these functions, NLTYPE_ANYCRLF, -and NLTYPE_ANY. The full list of Unicode newline characters is taken from -http://unicode.org/unicode/reports/tr18/. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - - - -/************************************************* -* Check for newline at given position * -*************************************************/ - -/* It is guaranteed that the initial value of ptr is less than the end of the -string that is being processed. - -Arguments: - ptr pointer to possible newline - type the newline type - endptr pointer to the end of the string - lenptr where to return the length - utf8 TRUE if in utf8 mode - -Returns: TRUE or FALSE -*/ - -BOOL -_pcre_is_newline(USPTR ptr, int type, USPTR endptr, int *lenptr, BOOL utf8) -{ -int c; -if (utf8) { GETCHAR(c, ptr); } else c = *ptr; - -if (type == NLTYPE_ANYCRLF) switch(c) - { - case 0x000a: *lenptr = 1; return TRUE; /* LF */ - case 0x000d: *lenptr = (ptr < endptr - 1 && ptr[1] == 0x0a)? 2 : 1; - return TRUE; /* CR */ - default: return FALSE; - } - -/* NLTYPE_ANY */ - -else switch(c) - { - case 0x000a: /* LF */ - case 0x000b: /* VT */ - case 0x000c: *lenptr = 1; return TRUE; /* FF */ - case 0x000d: *lenptr = (ptr < endptr - 1 && ptr[1] == 0x0a)? 2 : 1; - return TRUE; /* CR */ - case 0x0085: *lenptr = utf8? 2 : 1; return TRUE; /* NEL */ - case 0x2028: /* LS */ - case 0x2029: *lenptr = 3; return TRUE; /* PS */ - default: return FALSE; - } -} - - - -/************************************************* -* Check for newline at previous position * -*************************************************/ - -/* It is guaranteed that the initial value of ptr is greater than the start of -the string that is being processed. - -Arguments: - ptr pointer to possible newline - type the newline type - startptr pointer to the start of the string - lenptr where to return the length - utf8 TRUE if in utf8 mode - -Returns: TRUE or FALSE -*/ - -BOOL -_pcre_was_newline(USPTR ptr, int type, USPTR startptr, int *lenptr, BOOL utf8) -{ -int c; -ptr--; -#ifdef SUPPORT_UTF8 -if (utf8) - { - BACKCHAR(ptr); - GETCHAR(c, ptr); - } -else c = *ptr; -#else /* no UTF-8 support */ -c = *ptr; -#endif /* SUPPORT_UTF8 */ - -if (type == NLTYPE_ANYCRLF) switch(c) - { - case 0x000a: *lenptr = (ptr > startptr && ptr[-1] == 0x0d)? 2 : 1; - return TRUE; /* LF */ - case 0x000d: *lenptr = 1; return TRUE; /* CR */ - default: return FALSE; - } - -else switch(c) - { - case 0x000a: *lenptr = (ptr > startptr && ptr[-1] == 0x0d)? 2 : 1; - return TRUE; /* LF */ - case 0x000b: /* VT */ - case 0x000c: /* FF */ - case 0x000d: *lenptr = 1; return TRUE; /* CR */ - case 0x0085: *lenptr = utf8? 2 : 1; return TRUE; /* NEL */ - case 0x2028: /* LS */ - case 0x2029: *lenptr = 3; return TRUE; /* PS */ - default: return FALSE; - } -} - -/* End of pcre_newline.c */ diff --git a/libs/pcre/pcre_ord2utf8.c b/libs/pcre/pcre_ord2utf8.c deleted file mode 100644 index 6f4eb9ebe9..0000000000 --- a/libs/pcre/pcre_ord2utf8.c +++ /dev/null @@ -1,87 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2008 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This file contains a private PCRE function that converts an ordinal -character value into a UTF8 string. */ - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - - -/************************************************* -* Convert character value to UTF-8 * -*************************************************/ - -/* This function takes an integer value in the range 0 - 0x7fffffff -and encodes it as a UTF-8 character in 0 to 6 bytes. - -Arguments: - cvalue the character value - buffer pointer to buffer for result - at least 6 bytes long - -Returns: number of characters placed in the buffer -*/ - -int -_pcre_ord2utf8(int cvalue, uschar *buffer) -{ -#ifdef SUPPORT_UTF8 -register int i, j; -for (i = 0; i < _pcre_utf8_table1_size; i++) - if (cvalue <= _pcre_utf8_table1[i]) break; -buffer += i; -for (j = i; j > 0; j--) - { - *buffer-- = 0x80 | (cvalue & 0x3f); - cvalue >>= 6; - } -*buffer = _pcre_utf8_table2[i] | cvalue; -return i + 1; -#else -(void)(cvalue); /* Keep compiler happy; this function won't ever be */ -(void)(buffer); /* called when SUPPORT_UTF8 is not defined. */ -return 0; -#endif -} - -/* End of pcre_ord2utf8.c */ diff --git a/libs/pcre/pcre_printint.src b/libs/pcre/pcre_printint.src deleted file mode 100644 index 5f45fc1985..0000000000 --- a/libs/pcre/pcre_printint.src +++ /dev/null @@ -1,516 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2009 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains a PCRE private debugging function for printing out the -internal form of a compiled regular expression, along with some supporting -local functions. This source file is used in two places: - -(1) It is #included by pcre_compile.c when it is compiled in debugging mode -(DEBUG defined in pcre_internal.h). It is not included in production compiles. - -(2) It is always #included by pcretest.c, which can be asked to print out a -compiled regex for debugging purposes. */ - - -/* Macro that decides whether a character should be output as a literal or in -hexadecimal. We don't use isprint() because that can vary from system to system -(even without the use of locales) and we want the output always to be the same, -for testing purposes. This macro is used in pcretest as well as in this file. */ - -#ifdef EBCDIC -#define PRINTABLE(c) ((c) >= 64 && (c) < 255) -#else -#define PRINTABLE(c) ((c) >= 32 && (c) < 127) -#endif - -/* The table of operator names. */ - -static const char *OP_names[] = { OP_NAME_LIST }; - - - -/************************************************* -* Print single- or multi-byte character * -*************************************************/ - -static int -print_char(FILE *f, uschar *ptr, BOOL utf8) -{ -int c = *ptr; - -#ifndef SUPPORT_UTF8 -utf8 = utf8; /* Avoid compiler warning */ -if (PRINTABLE(c)) fprintf(f, "%c", c); else fprintf(f, "\\x%02x", c); -return 0; - -#else -if (!utf8 || (c & 0xc0) != 0xc0) - { - if (PRINTABLE(c)) fprintf(f, "%c", c); else fprintf(f, "\\x%02x", c); - return 0; - } -else - { - int i; - int a = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ - int s = 6*a; - c = (c & _pcre_utf8_table3[a]) << s; - for (i = 1; i <= a; i++) - { - /* This is a check for malformed UTF-8; it should only occur if the sanity - check has been turned off. Rather than swallow random bytes, just stop if - we hit a bad one. Print it with \X instead of \x as an indication. */ - - if ((ptr[i] & 0xc0) != 0x80) - { - fprintf(f, "\\X{%x}", c); - return i - 1; - } - - /* The byte is OK */ - - s -= 6; - c |= (ptr[i] & 0x3f) << s; - } - if (c < 128) fprintf(f, "\\x%02x", c); else fprintf(f, "\\x{%x}", c); - return a; - } -#endif -} - - - -/************************************************* -* Find Unicode property name * -*************************************************/ - -static const char * -get_ucpname(int ptype, int pvalue) -{ -#ifdef SUPPORT_UCP -int i; -for (i = _pcre_utt_size - 1; i >= 0; i--) - { - if (ptype == _pcre_utt[i].type && pvalue == _pcre_utt[i].value) break; - } -return (i >= 0)? _pcre_utt_names + _pcre_utt[i].name_offset : "??"; -#else -/* It gets harder and harder to shut off unwanted compiler warnings. */ -ptype = ptype * pvalue; -return (ptype == pvalue)? "??" : "??"; -#endif -} - - - -/************************************************* -* Print compiled regex * -*************************************************/ - -/* Make this function work for a regex with integers either byte order. -However, we assume that what we are passed is a compiled regex. The -print_lengths flag controls whether offsets and lengths of items are printed. -They can be turned off from pcretest so that automatic tests on bytecode can be -written that do not depend on the value of LINK_SIZE. */ - -static void -pcre_printint(pcre *external_re, FILE *f, BOOL print_lengths) -{ -real_pcre *re = (real_pcre *)external_re; -uschar *codestart, *code; -BOOL utf8; - -unsigned int options = re->options; -int offset = re->name_table_offset; -int count = re->name_count; -int size = re->name_entry_size; - -if (re->magic_number != MAGIC_NUMBER) - { - offset = ((offset << 8) & 0xff00) | ((offset >> 8) & 0xff); - count = ((count << 8) & 0xff00) | ((count >> 8) & 0xff); - size = ((size << 8) & 0xff00) | ((size >> 8) & 0xff); - options = ((options << 24) & 0xff000000) | - ((options << 8) & 0x00ff0000) | - ((options >> 8) & 0x0000ff00) | - ((options >> 24) & 0x000000ff); - } - -code = codestart = (uschar *)re + offset + count * size; -utf8 = (options & PCRE_UTF8) != 0; - -for(;;) - { - uschar *ccode; - int c; - int extra = 0; - - if (print_lengths) - fprintf(f, "%3d ", (int)(code - codestart)); - else - fprintf(f, " "); - - switch(*code) - { - case OP_END: - fprintf(f, " %s\n", OP_names[*code]); - fprintf(f, "------------------------------------------------------------------\n"); - return; - - case OP_OPT: - fprintf(f, " %.2x %s", code[1], OP_names[*code]); - break; - - case OP_CHAR: - fprintf(f, " "); - do - { - code++; - code += 1 + print_char(f, code, utf8); - } - while (*code == OP_CHAR); - fprintf(f, "\n"); - continue; - - case OP_CHARNC: - fprintf(f, " NC "); - do - { - code++; - code += 1 + print_char(f, code, utf8); - } - while (*code == OP_CHARNC); - fprintf(f, "\n"); - continue; - - case OP_CBRA: - case OP_SCBRA: - if (print_lengths) fprintf(f, "%3d ", GET(code, 1)); - else fprintf(f, " "); - fprintf(f, "%s %d", OP_names[*code], GET2(code, 1+LINK_SIZE)); - break; - - case OP_BRA: - case OP_SBRA: - case OP_KETRMAX: - case OP_KETRMIN: - case OP_ALT: - case OP_KET: - case OP_ASSERT: - case OP_ASSERT_NOT: - case OP_ASSERTBACK: - case OP_ASSERTBACK_NOT: - case OP_ONCE: - case OP_COND: - case OP_SCOND: - case OP_REVERSE: - if (print_lengths) fprintf(f, "%3d ", GET(code, 1)); - else fprintf(f, " "); - fprintf(f, "%s", OP_names[*code]); - break; - - case OP_CREF: - fprintf(f, "%3d %s", GET2(code,1), OP_names[*code]); - break; - - case OP_RREF: - c = GET2(code, 1); - if (c == RREF_ANY) - fprintf(f, " Cond recurse any"); - else - fprintf(f, " Cond recurse %d", c); - break; - - case OP_DEF: - fprintf(f, " Cond def"); - break; - - case OP_STAR: - case OP_MINSTAR: - case OP_POSSTAR: - case OP_PLUS: - case OP_MINPLUS: - case OP_POSPLUS: - case OP_QUERY: - case OP_MINQUERY: - case OP_POSQUERY: - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPOSSTAR: - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEPOSPLUS: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - case OP_TYPEPOSQUERY: - fprintf(f, " "); - if (*code >= OP_TYPESTAR) - { - fprintf(f, "%s", OP_names[code[1]]); - if (code[1] == OP_PROP || code[1] == OP_NOTPROP) - { - fprintf(f, " %s ", get_ucpname(code[2], code[3])); - extra = 2; - } - } - else extra = print_char(f, code+1, utf8); - fprintf(f, "%s", OP_names[*code]); - break; - - case OP_EXACT: - case OP_UPTO: - case OP_MINUPTO: - case OP_POSUPTO: - fprintf(f, " "); - extra = print_char(f, code+3, utf8); - fprintf(f, "{"); - if (*code != OP_EXACT) fprintf(f, "0,"); - fprintf(f, "%d}", GET2(code,1)); - if (*code == OP_MINUPTO) fprintf(f, "?"); - else if (*code == OP_POSUPTO) fprintf(f, "+"); - break; - - case OP_TYPEEXACT: - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - case OP_TYPEPOSUPTO: - fprintf(f, " %s", OP_names[code[3]]); - if (code[3] == OP_PROP || code[3] == OP_NOTPROP) - { - fprintf(f, " %s ", get_ucpname(code[4], code[5])); - extra = 2; - } - fprintf(f, "{"); - if (*code != OP_TYPEEXACT) fprintf(f, "0,"); - fprintf(f, "%d}", GET2(code,1)); - if (*code == OP_TYPEMINUPTO) fprintf(f, "?"); - else if (*code == OP_TYPEPOSUPTO) fprintf(f, "+"); - break; - - case OP_NOT: - c = code[1]; - if (PRINTABLE(c)) fprintf(f, " [^%c]", c); - else fprintf(f, " [^\\x%02x]", c); - break; - - case OP_NOTSTAR: - case OP_NOTMINSTAR: - case OP_NOTPOSSTAR: - case OP_NOTPLUS: - case OP_NOTMINPLUS: - case OP_NOTPOSPLUS: - case OP_NOTQUERY: - case OP_NOTMINQUERY: - case OP_NOTPOSQUERY: - c = code[1]; - if (PRINTABLE(c)) fprintf(f, " [^%c]", c); - else fprintf(f, " [^\\x%02x]", c); - fprintf(f, "%s", OP_names[*code]); - break; - - case OP_NOTEXACT: - case OP_NOTUPTO: - case OP_NOTMINUPTO: - case OP_NOTPOSUPTO: - c = code[3]; - if (PRINTABLE(c)) fprintf(f, " [^%c]{", c); - else fprintf(f, " [^\\x%02x]{", c); - if (*code != OP_NOTEXACT) fprintf(f, "0,"); - fprintf(f, "%d}", GET2(code,1)); - if (*code == OP_NOTMINUPTO) fprintf(f, "?"); - else if (*code == OP_NOTPOSUPTO) fprintf(f, "+"); - break; - - case OP_RECURSE: - if (print_lengths) fprintf(f, "%3d ", GET(code, 1)); - else fprintf(f, " "); - fprintf(f, "%s", OP_names[*code]); - break; - - case OP_REF: - fprintf(f, " \\%d", GET2(code,1)); - ccode = code + _pcre_OP_lengths[*code]; - goto CLASS_REF_REPEAT; - - case OP_CALLOUT: - fprintf(f, " %s %d %d %d", OP_names[*code], code[1], GET(code,2), - GET(code, 2 + LINK_SIZE)); - break; - - case OP_PROP: - case OP_NOTPROP: - fprintf(f, " %s %s", OP_names[*code], get_ucpname(code[1], code[2])); - break; - - /* OP_XCLASS can only occur in UTF-8 mode. However, there's no harm in - having this code always here, and it makes it less messy without all those - #ifdefs. */ - - case OP_CLASS: - case OP_NCLASS: - case OP_XCLASS: - { - int i, min, max; - BOOL printmap; - - fprintf(f, " ["); - - if (*code == OP_XCLASS) - { - extra = GET(code, 1); - ccode = code + LINK_SIZE + 1; - printmap = (*ccode & XCL_MAP) != 0; - if ((*ccode++ & XCL_NOT) != 0) fprintf(f, "^"); - } - else - { - printmap = TRUE; - ccode = code + 1; - } - - /* Print a bit map */ - - if (printmap) - { - for (i = 0; i < 256; i++) - { - if ((ccode[i/8] & (1 << (i&7))) != 0) - { - int j; - for (j = i+1; j < 256; j++) - if ((ccode[j/8] & (1 << (j&7))) == 0) break; - if (i == '-' || i == ']') fprintf(f, "\\"); - if (PRINTABLE(i)) fprintf(f, "%c", i); - else fprintf(f, "\\x%02x", i); - if (--j > i) - { - if (j != i + 1) fprintf(f, "-"); - if (j == '-' || j == ']') fprintf(f, "\\"); - if (PRINTABLE(j)) fprintf(f, "%c", j); - else fprintf(f, "\\x%02x", j); - } - i = j; - } - } - ccode += 32; - } - - /* For an XCLASS there is always some additional data */ - - if (*code == OP_XCLASS) - { - int ch; - while ((ch = *ccode++) != XCL_END) - { - if (ch == XCL_PROP) - { - int ptype = *ccode++; - int pvalue = *ccode++; - fprintf(f, "\\p{%s}", get_ucpname(ptype, pvalue)); - } - else if (ch == XCL_NOTPROP) - { - int ptype = *ccode++; - int pvalue = *ccode++; - fprintf(f, "\\P{%s}", get_ucpname(ptype, pvalue)); - } - else - { - ccode += 1 + print_char(f, ccode, TRUE); - if (ch == XCL_RANGE) - { - fprintf(f, "-"); - ccode += 1 + print_char(f, ccode, TRUE); - } - } - } - } - - /* Indicate a non-UTF8 class which was created by negation */ - - fprintf(f, "]%s", (*code == OP_NCLASS)? " (neg)" : ""); - - /* Handle repeats after a class or a back reference */ - - CLASS_REF_REPEAT: - switch(*ccode) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRPLUS: - case OP_CRMINPLUS: - case OP_CRQUERY: - case OP_CRMINQUERY: - fprintf(f, "%s", OP_names[*ccode]); - extra += _pcre_OP_lengths[*ccode]; - break; - - case OP_CRRANGE: - case OP_CRMINRANGE: - min = GET2(ccode,1); - max = GET2(ccode,3); - if (max == 0) fprintf(f, "{%d,}", min); - else fprintf(f, "{%d,%d}", min, max); - if (*ccode == OP_CRMINRANGE) fprintf(f, "?"); - extra += _pcre_OP_lengths[*ccode]; - break; - - /* Do nothing if it's not a repeat; this code stops picky compilers - warning about the lack of a default code path. */ - - default: - break; - } - } - break; - - /* Anything else is just an item with no data*/ - - default: - fprintf(f, " %s", OP_names[*code]); - break; - } - - code += _pcre_OP_lengths[*code] + extra; - fprintf(f, "\n"); - } -} - -/* End of pcre_printint.src */ diff --git a/libs/pcre/pcre_refcount.c b/libs/pcre/pcre_refcount.c deleted file mode 100644 index 92e4b8505c..0000000000 --- a/libs/pcre/pcre_refcount.c +++ /dev/null @@ -1,82 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2008 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains the external function pcre_refcount(), which is an -auxiliary function that can be used to maintain a reference count in a compiled -pattern data block. This might be helpful in applications where the block is -shared by different users. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - - -/************************************************* -* Maintain reference count * -*************************************************/ - -/* The reference count is a 16-bit field, initialized to zero. It is not -possible to transfer a non-zero count from one host to a different host that -has a different byte order - though I can't see why anyone in their right mind -would ever want to do that! - -Arguments: - argument_re points to compiled code - adjust value to add to the count - -Returns: the (possibly updated) count value (a non-negative number), or - a negative error number -*/ - -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre_refcount(pcre *argument_re, int adjust) -{ -real_pcre *re = (real_pcre *)argument_re; -if (re == NULL) return PCRE_ERROR_NULL; -re->ref_count = (-adjust > re->ref_count)? 0 : - (adjust + re->ref_count > 65535)? 65535 : - re->ref_count + adjust; -return re->ref_count; -} - -/* End of pcre_refcount.c */ diff --git a/libs/pcre/pcre_scanner.cc b/libs/pcre/pcre_scanner.cc deleted file mode 100644 index a817a684e2..0000000000 --- a/libs/pcre/pcre_scanner.cc +++ /dev/null @@ -1,199 +0,0 @@ -// Copyright (c) 2005, Google Inc. -// All rights reserved. -// -// Redistribution and use in source and binary forms, with or without -// modification, are permitted provided that the following conditions are -// met: -// -// * Redistributions of source code must retain the above copyright -// notice, this list of conditions and the following disclaimer. -// * Redistributions in binary form must reproduce the above -// copyright notice, this list of conditions and the following disclaimer -// in the documentation and/or other materials provided with the -// distribution. -// * Neither the name of Google Inc. nor the names of its -// contributors may be used to endorse or promote products derived from -// this software without specific prior written permission. -// -// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS -// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT -// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR -// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT -// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, -// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT -// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, -// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY -// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT -// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE -// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. -// -// Author: Sanjay Ghemawat - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include -#include - -#include "pcrecpp_internal.h" -#include "pcre_scanner.h" - -using std::vector; - -namespace pcrecpp { - -Scanner::Scanner() - : data_(), - input_(data_), - skip_(NULL), - should_skip_(false), - skip_repeat_(false), - save_comments_(false), - comments_(NULL), - comments_offset_(0) { -} - -Scanner::Scanner(const string& in) - : data_(in), - input_(data_), - skip_(NULL), - should_skip_(false), - skip_repeat_(false), - save_comments_(false), - comments_(NULL), - comments_offset_(0) { -} - -Scanner::~Scanner() { - delete skip_; - delete comments_; -} - -void Scanner::SetSkipExpression(const char* re) { - delete skip_; - if (re != NULL) { - skip_ = new RE(re); - should_skip_ = true; - skip_repeat_ = true; - ConsumeSkip(); - } else { - skip_ = NULL; - should_skip_ = false; - skip_repeat_ = false; - } -} - -void Scanner::Skip(const char* re) { - delete skip_; - if (re != NULL) { - skip_ = new RE(re); - should_skip_ = true; - skip_repeat_ = false; - ConsumeSkip(); - } else { - skip_ = NULL; - should_skip_ = false; - skip_repeat_ = false; - } -} - -void Scanner::DisableSkip() { - assert(skip_ != NULL); - should_skip_ = false; -} - -void Scanner::EnableSkip() { - assert(skip_ != NULL); - should_skip_ = true; - ConsumeSkip(); -} - -int Scanner::LineNumber() const { - // TODO: Make it more efficient by keeping track of the last point - // where we computed line numbers and counting newlines since then. - // We could use std:count, but not all systems have it. :-( - int count = 1; - for (const char* p = data_.data(); p < input_.data(); ++p) - if (*p == '\n') - ++count; - return count; -} - -int Scanner::Offset() const { - return input_.data() - data_.c_str(); -} - -bool Scanner::LookingAt(const RE& re) const { - int consumed; - return re.DoMatch(input_, RE::ANCHOR_START, &consumed, 0, 0); -} - - -bool Scanner::Consume(const RE& re, - const Arg& arg0, - const Arg& arg1, - const Arg& arg2) { - const bool result = re.Consume(&input_, arg0, arg1, arg2); - if (result && should_skip_) ConsumeSkip(); - return result; -} - -// helper function to consume *skip_ and honour save_comments_ -void Scanner::ConsumeSkip() { - const char* start_data = input_.data(); - while (skip_->Consume(&input_)) { - if (!skip_repeat_) { - // Only one skip allowed. - break; - } - } - if (save_comments_) { - if (comments_ == NULL) { - comments_ = new vector; - } - // already pointing one past end, so no need to +1 - int length = input_.data() - start_data; - if (length > 0) { - comments_->push_back(StringPiece(start_data, length)); - } - } -} - - -void Scanner::GetComments(int start, int end, vector *ranges) { - // short circuit out if we've not yet initialized comments_ - // (e.g., when save_comments is false) - if (!comments_) { - return; - } - // TODO: if we guarantee that comments_ will contain StringPieces - // that are ordered by their start, then we can do a binary search - // for the first StringPiece at or past start and then scan for the - // ones contained in the range, quit early (use equal_range or - // lower_bound) - for (vector::const_iterator it = comments_->begin(); - it != comments_->end(); ++it) { - if ((it->data() >= data_.c_str() + start && - it->data() + it->size() <= data_.c_str() + end)) { - ranges->push_back(*it); - } - } -} - - -void Scanner::GetNextComments(vector *ranges) { - // short circuit out if we've not yet initialized comments_ - // (e.g., when save_comments is false) - if (!comments_) { - return; - } - for (vector::const_iterator it = - comments_->begin() + comments_offset_; - it != comments_->end(); ++it) { - ranges->push_back(*it); - ++comments_offset_; - } -} - -} // namespace pcrecpp diff --git a/libs/pcre/pcre_scanner.h b/libs/pcre/pcre_scanner.h deleted file mode 100644 index 5617e4515c..0000000000 --- a/libs/pcre/pcre_scanner.h +++ /dev/null @@ -1,172 +0,0 @@ -// Copyright (c) 2005, Google Inc. -// All rights reserved. -// -// Redistribution and use in source and binary forms, with or without -// modification, are permitted provided that the following conditions are -// met: -// -// * Redistributions of source code must retain the above copyright -// notice, this list of conditions and the following disclaimer. -// * Redistributions in binary form must reproduce the above -// copyright notice, this list of conditions and the following disclaimer -// in the documentation and/or other materials provided with the -// distribution. -// * Neither the name of Google Inc. nor the names of its -// contributors may be used to endorse or promote products derived from -// this software without specific prior written permission. -// -// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS -// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT -// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR -// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT -// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, -// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT -// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, -// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY -// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT -// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE -// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. -// -// Author: Sanjay Ghemawat -// -// Regular-expression based scanner for parsing an input stream. -// -// Example 1: parse a sequence of "var = number" entries from input: -// -// Scanner scanner(input); -// string var; -// int number; -// scanner.SetSkipExpression("\\s+"); // Skip any white space we encounter -// while (scanner.Consume("(\\w+) = (\\d+)", &var, &number)) { -// ...; -// } - -#ifndef _PCRE_SCANNER_H -#define _PCRE_SCANNER_H - -#include -#include -#include - -#include -#include - -namespace pcrecpp { - -class PCRECPP_EXP_DEFN Scanner { - public: - Scanner(); - explicit Scanner(const std::string& input); - ~Scanner(); - - // Return current line number. The returned line-number is - // one-based. I.e. it returns 1 + the number of consumed newlines. - // - // Note: this method may be slow. It may take time proportional to - // the size of the input. - int LineNumber() const; - - // Return the byte-offset that the scanner is looking in the - // input data; - int Offset() const; - - // Return true iff the start of the remaining input matches "re" - bool LookingAt(const RE& re) const; - - // Return true iff all of the following are true - // a. the start of the remaining input matches "re", - // b. if any arguments are supplied, matched sub-patterns can be - // parsed and stored into the arguments. - // If it returns true, it skips over the matched input and any - // following input that matches the "skip" regular expression. - bool Consume(const RE& re, - const Arg& arg0 = RE::no_arg, - const Arg& arg1 = RE::no_arg, - const Arg& arg2 = RE::no_arg - // TODO: Allow more arguments? - ); - - // Set the "skip" regular expression. If after consuming some data, - // a prefix of the input matches this RE, it is automatically - // skipped. For example, a programming language scanner would use - // a skip RE that matches white space and comments. - // - // scanner.SetSkipExpression("\\s+|//.*|/[*](.|\n)*?[*]/"); - // - // Skipping repeats as long as it succeeds. We used to let people do - // this by writing "(...)*" in the regular expression, but that added - // up to lots of recursive calls within the pcre library, so now we - // control repetition explicitly via the function call API. - // - // You can pass NULL for "re" if you do not want any data to be skipped. - void Skip(const char* re); // DEPRECATED; does *not* repeat - void SetSkipExpression(const char* re); - - // Temporarily pause "skip"ing. This - // Skip("Foo"); code ; DisableSkip(); code; EnableSkip() - // is similar to - // Skip("Foo"); code ; Skip(NULL); code ; Skip("Foo"); - // but avoids creating/deleting new RE objects. - void DisableSkip(); - - // Reenable previously paused skipping. Any prefix of the input - // that matches the skip pattern is immediately dropped. - void EnableSkip(); - - /***** Special wrappers around SetSkip() for some common idioms *****/ - - // Arranges to skip whitespace, C comments, C++ comments. - // The overall RE is a disjunction of the following REs: - // \\s whitespace - // //.*\n C++ comment - // /[*](.|\n)*?[*]/ C comment (x*? means minimal repetitions of x) - // We get repetition via the semantics of SetSkipExpression, not by using * - void SkipCXXComments() { - SetSkipExpression("\\s|//.*\n|/[*](?:\n|.)*?[*]/"); - } - - void set_save_comments(bool comments) { - save_comments_ = comments; - } - - bool save_comments() { - return save_comments_; - } - - // Append to vector ranges the comments found in the - // byte range [start,end] (inclusive) of the input data. - // Only comments that were extracted entirely within that - // range are returned: no range splitting of atomically-extracted - // comments is performed. - void GetComments(int start, int end, std::vector *ranges); - - // Append to vector ranges the comments added - // since the last time this was called. This - // functionality is provided for efficiency when - // interleaving scanning with parsing. - void GetNextComments(std::vector *ranges); - - private: - std::string data_; // All the input data - StringPiece input_; // Unprocessed input - RE* skip_; // If non-NULL, RE for skipping input - bool should_skip_; // If true, use skip_ - bool skip_repeat_; // If true, repeat skip_ as long as it works - bool save_comments_; // If true, aggregate the skip expression - - // the skipped comments - // TODO: later consider requiring that the StringPieces be added - // in order by their start position - std::vector *comments_; - - // the offset into comments_ that has been returned by GetNextComments - int comments_offset_; - - // helper function to consume *skip_ and honour - // save_comments_ - void ConsumeSkip(); -}; - -} // namespace pcrecpp - -#endif /* _PCRE_SCANNER_H */ diff --git a/libs/pcre/pcre_scanner_unittest.cc b/libs/pcre/pcre_scanner_unittest.cc deleted file mode 100644 index 284c8ea99e..0000000000 --- a/libs/pcre/pcre_scanner_unittest.cc +++ /dev/null @@ -1,158 +0,0 @@ -// Copyright (c) 2005, Google Inc. -// All rights reserved. -// -// Redistribution and use in source and binary forms, with or without -// modification, are permitted provided that the following conditions are -// met: -// -// * Redistributions of source code must retain the above copyright -// notice, this list of conditions and the following disclaimer. -// * Redistributions in binary form must reproduce the above -// copyright notice, this list of conditions and the following disclaimer -// in the documentation and/or other materials provided with the -// distribution. -// * Neither the name of Google Inc. nor the names of its -// contributors may be used to endorse or promote products derived from -// this software without specific prior written permission. -// -// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS -// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT -// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR -// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT -// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, -// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT -// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, -// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY -// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT -// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE -// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. -// -// Author: Greg J. Badros -// -// Unittest for scanner, especially GetNextComments and GetComments() -// functionality. - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include -#include -#include - -#include "pcrecpp.h" -#include "pcre_stringpiece.h" -#include "pcre_scanner.h" - -#define FLAGS_unittest_stack_size 49152 - -// Dies with a fatal error if the two values are not equal. -#define CHECK_EQ(a, b) do { \ - if ( (a) != (b) ) { \ - fprintf(stderr, "%s:%d: Check failed because %s != %s\n", \ - __FILE__, __LINE__, #a, #b); \ - exit(1); \ - } \ -} while (0) - -using std::vector; -using pcrecpp::StringPiece; -using pcrecpp::Scanner; - -static void TestScanner() { - const char input[] = "\n" - "alpha = 1; // this sets alpha\n" - "bravo = 2; // bravo is set here\n" - "gamma = 33; /* and here is gamma */\n"; - - const char *re = "(\\w+) = (\\d+);"; - - Scanner s(input); - string var; - int number; - s.SkipCXXComments(); - s.set_save_comments(true); - vector comments; - - s.Consume(re, &var, &number); - CHECK_EQ(var, "alpha"); - CHECK_EQ(number, 1); - CHECK_EQ(s.LineNumber(), 3); - s.GetNextComments(&comments); - CHECK_EQ(comments.size(), 1); - CHECK_EQ(comments[0].as_string(), " // this sets alpha\n"); - comments.resize(0); - - s.Consume(re, &var, &number); - CHECK_EQ(var, "bravo"); - CHECK_EQ(number, 2); - s.GetNextComments(&comments); - CHECK_EQ(comments.size(), 1); - CHECK_EQ(comments[0].as_string(), " // bravo is set here\n"); - comments.resize(0); - - s.Consume(re, &var, &number); - CHECK_EQ(var, "gamma"); - CHECK_EQ(number, 33); - s.GetNextComments(&comments); - CHECK_EQ(comments.size(), 1); - CHECK_EQ(comments[0].as_string(), " /* and here is gamma */\n"); - comments.resize(0); - - s.GetComments(0, sizeof(input), &comments); - CHECK_EQ(comments.size(), 3); - CHECK_EQ(comments[0].as_string(), " // this sets alpha\n"); - CHECK_EQ(comments[1].as_string(), " // bravo is set here\n"); - CHECK_EQ(comments[2].as_string(), " /* and here is gamma */\n"); - comments.resize(0); - - s.GetComments(0, strchr(input, '/') - input, &comments); - CHECK_EQ(comments.size(), 0); - comments.resize(0); - - s.GetComments(strchr(input, '/') - input - 1, sizeof(input), - &comments); - CHECK_EQ(comments.size(), 3); - CHECK_EQ(comments[0].as_string(), " // this sets alpha\n"); - CHECK_EQ(comments[1].as_string(), " // bravo is set here\n"); - CHECK_EQ(comments[2].as_string(), " /* and here is gamma */\n"); - comments.resize(0); - - s.GetComments(strchr(input, '/') - input - 1, - strchr(input + 1, '\n') - input + 1, &comments); - CHECK_EQ(comments.size(), 1); - CHECK_EQ(comments[0].as_string(), " // this sets alpha\n"); - comments.resize(0); -} - -static void TestBigComment() { - string input; - for (int i = 0; i < 1024; ++i) { - char buf[1024]; // definitely big enough - sprintf(buf, " # Comment %d\n", i); - input += buf; - } - input += "name = value;\n"; - - Scanner s(input.c_str()); - s.SetSkipExpression("\\s+|#.*\n"); - - string name; - string value; - s.Consume("(\\w+) = (\\w+);", &name, &value); - CHECK_EQ(name, "name"); - CHECK_EQ(value, "value"); -} - -// TODO: also test scanner and big-comment in a thread with a -// small stack size - -int main(int argc, char** argv) { - TestScanner(); - TestBigComment(); - - // Done - printf("OK\n"); - - return 0; -} diff --git a/libs/pcre/pcre_stringpiece.cc b/libs/pcre/pcre_stringpiece.cc deleted file mode 100644 index 67c0f1fc0e..0000000000 --- a/libs/pcre/pcre_stringpiece.cc +++ /dev/null @@ -1,43 +0,0 @@ -// Copyright (c) 2005, Google Inc. -// All rights reserved. -// -// Redistribution and use in source and binary forms, with or without -// modification, are permitted provided that the following conditions are -// met: -// -// * Redistributions of source code must retain the above copyright -// notice, this list of conditions and the following disclaimer. -// * Redistributions in binary form must reproduce the above -// copyright notice, this list of conditions and the following disclaimer -// in the documentation and/or other materials provided with the -// distribution. -// * Neither the name of Google Inc. nor the names of its -// contributors may be used to endorse or promote products derived from -// this software without specific prior written permission. -// -// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS -// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT -// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR -// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT -// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, -// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT -// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, -// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY -// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT -// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE -// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. -// -// Author: wilsonh@google.com (Wilson Hsieh) -// - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include -#include "pcrecpp_internal.h" -#include "pcre_stringpiece.h" - -std::ostream& operator<<(std::ostream& o, const pcrecpp::StringPiece& piece) { - return (o << piece.as_string()); -} diff --git a/libs/pcre/pcre_stringpiece.h.in b/libs/pcre/pcre_stringpiece.h.in deleted file mode 100644 index b017661eb4..0000000000 --- a/libs/pcre/pcre_stringpiece.h.in +++ /dev/null @@ -1,177 +0,0 @@ -// Copyright (c) 2005, Google Inc. -// All rights reserved. -// -// Redistribution and use in source and binary forms, with or without -// modification, are permitted provided that the following conditions are -// met: -// -// * Redistributions of source code must retain the above copyright -// notice, this list of conditions and the following disclaimer. -// * Redistributions in binary form must reproduce the above -// copyright notice, this list of conditions and the following disclaimer -// in the documentation and/or other materials provided with the -// distribution. -// * Neither the name of Google Inc. nor the names of its -// contributors may be used to endorse or promote products derived from -// this software without specific prior written permission. -// -// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS -// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT -// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR -// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT -// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, -// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT -// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, -// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY -// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT -// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE -// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. -// -// Author: Sanjay Ghemawat -// -// A string like object that points into another piece of memory. -// Useful for providing an interface that allows clients to easily -// pass in either a "const char*" or a "string". -// -// Arghh! I wish C++ literals were automatically of type "string". - -#ifndef _PCRE_STRINGPIECE_H -#define _PCRE_STRINGPIECE_H - -#include -#include -#include // for ostream forward-declaration - -#if @pcre_have_type_traits@ -#define HAVE_TYPE_TRAITS -#include -#elif @pcre_have_bits_type_traits@ -#define HAVE_TYPE_TRAITS -#include -#endif - -#include - -using std::string; - -namespace pcrecpp { - -class PCRECPP_EXP_DEFN StringPiece { - private: - const char* ptr_; - int length_; - - public: - // We provide non-explicit singleton constructors so users can pass - // in a "const char*" or a "string" wherever a "StringPiece" is - // expected. - StringPiece() - : ptr_(NULL), length_(0) { } - StringPiece(const char* str) - : ptr_(str), length_(static_cast(strlen(ptr_))) { } - StringPiece(const unsigned char* str) - : ptr_(reinterpret_cast(str)), - length_(static_cast(strlen(ptr_))) { } - StringPiece(const string& str) - : ptr_(str.data()), length_(static_cast(str.size())) { } - StringPiece(const char* offset, int len) - : ptr_(offset), length_(len) { } - - // data() may return a pointer to a buffer with embedded NULs, and the - // returned buffer may or may not be null terminated. Therefore it is - // typically a mistake to pass data() to a routine that expects a NUL - // terminated string. Use "as_string().c_str()" if you really need to do - // this. Or better yet, change your routine so it does not rely on NUL - // termination. - const char* data() const { return ptr_; } - int size() const { return length_; } - bool empty() const { return length_ == 0; } - - void clear() { ptr_ = NULL; length_ = 0; } - void set(const char* buffer, int len) { ptr_ = buffer; length_ = len; } - void set(const char* str) { - ptr_ = str; - length_ = static_cast(strlen(str)); - } - void set(const void* buffer, int len) { - ptr_ = reinterpret_cast(buffer); - length_ = len; - } - - char operator[](int i) const { return ptr_[i]; } - - void remove_prefix(int n) { - ptr_ += n; - length_ -= n; - } - - void remove_suffix(int n) { - length_ -= n; - } - - bool operator==(const StringPiece& x) const { - return ((length_ == x.length_) && - (memcmp(ptr_, x.ptr_, length_) == 0)); - } - bool operator!=(const StringPiece& x) const { - return !(*this == x); - } - -#define STRINGPIECE_BINARY_PREDICATE(cmp,auxcmp) \ - bool operator cmp (const StringPiece& x) const { \ - int r = memcmp(ptr_, x.ptr_, length_ < x.length_ ? length_ : x.length_); \ - return ((r auxcmp 0) || ((r == 0) && (length_ cmp x.length_))); \ - } - STRINGPIECE_BINARY_PREDICATE(<, <); - STRINGPIECE_BINARY_PREDICATE(<=, <); - STRINGPIECE_BINARY_PREDICATE(>=, >); - STRINGPIECE_BINARY_PREDICATE(>, >); -#undef STRINGPIECE_BINARY_PREDICATE - - int compare(const StringPiece& x) const { - int r = memcmp(ptr_, x.ptr_, length_ < x.length_ ? length_ : x.length_); - if (r == 0) { - if (length_ < x.length_) r = -1; - else if (length_ > x.length_) r = +1; - } - return r; - } - - string as_string() const { - return string(data(), size()); - } - - void CopyToString(string* target) const { - target->assign(ptr_, length_); - } - - // Does "this" start with "x" - bool starts_with(const StringPiece& x) const { - return ((length_ >= x.length_) && (memcmp(ptr_, x.ptr_, x.length_) == 0)); - } -}; - -} // namespace pcrecpp - -// ------------------------------------------------------------------ -// Functions used to create STL containers that use StringPiece -// Remember that a StringPiece's lifetime had better be less than -// that of the underlying string or char*. If it is not, then you -// cannot safely store a StringPiece into an STL container -// ------------------------------------------------------------------ - -#ifdef HAVE_TYPE_TRAITS -// This makes vector really fast for some STL implementations -template<> struct __type_traits { - typedef __true_type has_trivial_default_constructor; - typedef __true_type has_trivial_copy_constructor; - typedef __true_type has_trivial_assignment_operator; - typedef __true_type has_trivial_destructor; - typedef __true_type is_POD_type; -}; -#endif - -// allow StringPiece to be logged -std::ostream& operator<<(std::ostream& o, const pcrecpp::StringPiece& piece); - -#endif /* _PCRE_STRINGPIECE_H */ diff --git a/libs/pcre/pcre_stringpiece_unittest.cc b/libs/pcre/pcre_stringpiece_unittest.cc deleted file mode 100644 index 1e821ab6e4..0000000000 --- a/libs/pcre/pcre_stringpiece_unittest.cc +++ /dev/null @@ -1,151 +0,0 @@ -// Copyright 2003 and onwards Google Inc. -// Author: Sanjay Ghemawat - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include -#include -#include // for make_pair - -#include "pcrecpp.h" -#include "pcre_stringpiece.h" - -// CHECK dies with a fatal error if condition is not true. It is *not* -// controlled by NDEBUG, so the check will be executed regardless of -// compilation mode. Therefore, it is safe to do things like: -// CHECK(fp->Write(x) == 4) -#define CHECK(condition) do { \ - if (!(condition)) { \ - fprintf(stderr, "%s:%d: Check failed: %s\n", \ - __FILE__, __LINE__, #condition); \ - exit(1); \ - } \ -} while (0) - -using std::map; -using std::make_pair; -using pcrecpp::StringPiece; - -static void CheckSTLComparator() { - string s1("foo"); - string s2("bar"); - string s3("baz"); - - StringPiece p1(s1); - StringPiece p2(s2); - StringPiece p3(s3); - - typedef map TestMap; - TestMap map; - - map.insert(make_pair(p1, 0)); - map.insert(make_pair(p2, 1)); - map.insert(make_pair(p3, 2)); - CHECK(map.size() == 3); - - TestMap::const_iterator iter = map.begin(); - CHECK(iter->second == 1); - ++iter; - CHECK(iter->second == 2); - ++iter; - CHECK(iter->second == 0); - ++iter; - CHECK(iter == map.end()); - - TestMap::iterator new_iter = map.find("zot"); - CHECK(new_iter == map.end()); - - new_iter = map.find("bar"); - CHECK(new_iter != map.end()); - - map.erase(new_iter); - CHECK(map.size() == 2); - - iter = map.begin(); - CHECK(iter->second == 2); - ++iter; - CHECK(iter->second == 0); - ++iter; - CHECK(iter == map.end()); -} - -static void CheckComparisonOperators() { -#define CMP_Y(op, x, y) \ - CHECK( (StringPiece((x)) op StringPiece((y)))); \ - CHECK( (StringPiece((x)).compare(StringPiece((y))) op 0)) - -#define CMP_N(op, x, y) \ - CHECK(!(StringPiece((x)) op StringPiece((y)))); \ - CHECK(!(StringPiece((x)).compare(StringPiece((y))) op 0)) - - CMP_Y(==, "", ""); - CMP_Y(==, "a", "a"); - CMP_Y(==, "aa", "aa"); - CMP_N(==, "a", ""); - CMP_N(==, "", "a"); - CMP_N(==, "a", "b"); - CMP_N(==, "a", "aa"); - CMP_N(==, "aa", "a"); - - CMP_N(!=, "", ""); - CMP_N(!=, "a", "a"); - CMP_N(!=, "aa", "aa"); - CMP_Y(!=, "a", ""); - CMP_Y(!=, "", "a"); - CMP_Y(!=, "a", "b"); - CMP_Y(!=, "a", "aa"); - CMP_Y(!=, "aa", "a"); - - CMP_Y(<, "a", "b"); - CMP_Y(<, "a", "aa"); - CMP_Y(<, "aa", "b"); - CMP_Y(<, "aa", "bb"); - CMP_N(<, "a", "a"); - CMP_N(<, "b", "a"); - CMP_N(<, "aa", "a"); - CMP_N(<, "b", "aa"); - CMP_N(<, "bb", "aa"); - - CMP_Y(<=, "a", "a"); - CMP_Y(<=, "a", "b"); - CMP_Y(<=, "a", "aa"); - CMP_Y(<=, "aa", "b"); - CMP_Y(<=, "aa", "bb"); - CMP_N(<=, "b", "a"); - CMP_N(<=, "aa", "a"); - CMP_N(<=, "b", "aa"); - CMP_N(<=, "bb", "aa"); - - CMP_N(>=, "a", "b"); - CMP_N(>=, "a", "aa"); - CMP_N(>=, "aa", "b"); - CMP_N(>=, "aa", "bb"); - CMP_Y(>=, "a", "a"); - CMP_Y(>=, "b", "a"); - CMP_Y(>=, "aa", "a"); - CMP_Y(>=, "b", "aa"); - CMP_Y(>=, "bb", "aa"); - - CMP_N(>, "a", "a"); - CMP_N(>, "a", "b"); - CMP_N(>, "a", "aa"); - CMP_N(>, "aa", "b"); - CMP_N(>, "aa", "bb"); - CMP_Y(>, "b", "a"); - CMP_Y(>, "aa", "a"); - CMP_Y(>, "b", "aa"); - CMP_Y(>, "bb", "aa"); - -#undef CMP_Y -#undef CMP_N -} - -int main(int argc, char** argv) { - CheckComparisonOperators(); - CheckSTLComparator(); - - printf("OK\n"); - return 0; -} diff --git a/libs/pcre/pcre_study.c b/libs/pcre/pcre_study.c deleted file mode 100644 index 778851d24c..0000000000 --- a/libs/pcre/pcre_study.c +++ /dev/null @@ -1,588 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2008 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains the external function pcre_study(), along with local -supporting functions. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - - -/* Returns from set_start_bits() */ - -enum { SSB_FAIL, SSB_DONE, SSB_CONTINUE }; - - -/************************************************* -* Set a bit and maybe its alternate case * -*************************************************/ - -/* Given a character, set its bit in the table, and also the bit for the other -version of a letter if we are caseless. - -Arguments: - start_bits points to the bit map - c is the character - caseless the caseless flag - cd the block with char table pointers - -Returns: nothing -*/ - -static void -set_bit(uschar *start_bits, unsigned int c, BOOL caseless, compile_data *cd) -{ -start_bits[c/8] |= (1 << (c&7)); -if (caseless && (cd->ctypes[c] & ctype_letter) != 0) - start_bits[cd->fcc[c]/8] |= (1 << (cd->fcc[c]&7)); -} - - - -/************************************************* -* Create bitmap of starting bytes * -*************************************************/ - -/* This function scans a compiled unanchored expression recursively and -attempts to build a bitmap of the set of possible starting bytes. As time goes -by, we may be able to get more clever at doing this. The SSB_CONTINUE return is -useful for parenthesized groups in patterns such as (a*)b where the group -provides some optional starting bytes but scanning must continue at the outer -level to find at least one mandatory byte. At the outermost level, this -function fails unless the result is SSB_DONE. - -Arguments: - code points to an expression - start_bits points to a 32-byte table, initialized to 0 - caseless the current state of the caseless flag - utf8 TRUE if in UTF-8 mode - cd the block with char table pointers - -Returns: SSB_FAIL => Failed to find any starting bytes - SSB_DONE => Found mandatory starting bytes - SSB_CONTINUE => Found optional starting bytes -*/ - -static int -set_start_bits(const uschar *code, uschar *start_bits, BOOL caseless, - BOOL utf8, compile_data *cd) -{ -register int c; -int yield = SSB_DONE; - -#if 0 -/* ========================================================================= */ -/* The following comment and code was inserted in January 1999. In May 2006, -when it was observed to cause compiler warnings about unused values, I took it -out again. If anybody is still using OS/2, they will have to put it back -manually. */ - -/* This next statement and the later reference to dummy are here in order to -trick the optimizer of the IBM C compiler for OS/2 into generating correct -code. Apparently IBM isn't going to fix the problem, and we would rather not -disable optimization (in this module it actually makes a big difference, and -the pcre module can use all the optimization it can get). */ - -volatile int dummy; -/* ========================================================================= */ -#endif - -do - { - const uschar *tcode = code + (((int)*code == OP_CBRA)? 3:1) + LINK_SIZE; - BOOL try_next = TRUE; - - while (try_next) /* Loop for items in this branch */ - { - int rc; - switch(*tcode) - { - /* Fail if we reach something we don't understand */ - - default: - return SSB_FAIL; - - /* If we hit a bracket or a positive lookahead assertion, recurse to set - bits from within the subpattern. If it can't find anything, we have to - give up. If it finds some mandatory character(s), we are done for this - branch. Otherwise, carry on scanning after the subpattern. */ - - case OP_BRA: - case OP_SBRA: - case OP_CBRA: - case OP_SCBRA: - case OP_ONCE: - case OP_ASSERT: - rc = set_start_bits(tcode, start_bits, caseless, utf8, cd); - if (rc == SSB_FAIL) return SSB_FAIL; - if (rc == SSB_DONE) try_next = FALSE; else - { - do tcode += GET(tcode, 1); while (*tcode == OP_ALT); - tcode += 1 + LINK_SIZE; - } - break; - - /* If we hit ALT or KET, it means we haven't found anything mandatory in - this branch, though we might have found something optional. For ALT, we - continue with the next alternative, but we have to arrange that the final - result from subpattern is SSB_CONTINUE rather than SSB_DONE. For KET, - return SSB_CONTINUE: if this is the top level, that indicates failure, - but after a nested subpattern, it causes scanning to continue. */ - - case OP_ALT: - yield = SSB_CONTINUE; - try_next = FALSE; - break; - - case OP_KET: - case OP_KETRMAX: - case OP_KETRMIN: - return SSB_CONTINUE; - - /* Skip over callout */ - - case OP_CALLOUT: - tcode += 2 + 2*LINK_SIZE; - break; - - /* Skip over lookbehind and negative lookahead assertions */ - - case OP_ASSERT_NOT: - case OP_ASSERTBACK: - case OP_ASSERTBACK_NOT: - do tcode += GET(tcode, 1); while (*tcode == OP_ALT); - tcode += 1 + LINK_SIZE; - break; - - /* Skip over an option setting, changing the caseless flag */ - - case OP_OPT: - caseless = (tcode[1] & PCRE_CASELESS) != 0; - tcode += 2; - break; - - /* BRAZERO does the bracket, but carries on. */ - - case OP_BRAZERO: - case OP_BRAMINZERO: - if (set_start_bits(++tcode, start_bits, caseless, utf8, cd) == SSB_FAIL) - return SSB_FAIL; -/* ========================================================================= - See the comment at the head of this function concerning the next line, - which was an old fudge for the benefit of OS/2. - dummy = 1; - ========================================================================= */ - do tcode += GET(tcode,1); while (*tcode == OP_ALT); - tcode += 1 + LINK_SIZE; - break; - - /* SKIPZERO skips the bracket. */ - - case OP_SKIPZERO: - tcode++; - do tcode += GET(tcode,1); while (*tcode == OP_ALT); - tcode += 1 + LINK_SIZE; - break; - - /* Single-char * or ? sets the bit and tries the next item */ - - case OP_STAR: - case OP_MINSTAR: - case OP_POSSTAR: - case OP_QUERY: - case OP_MINQUERY: - case OP_POSQUERY: - set_bit(start_bits, tcode[1], caseless, cd); - tcode += 2; -#ifdef SUPPORT_UTF8 - if (utf8 && tcode[-1] >= 0xc0) - tcode += _pcre_utf8_table4[tcode[-1] & 0x3f]; -#endif - break; - - /* Single-char upto sets the bit and tries the next */ - - case OP_UPTO: - case OP_MINUPTO: - case OP_POSUPTO: - set_bit(start_bits, tcode[3], caseless, cd); - tcode += 4; -#ifdef SUPPORT_UTF8 - if (utf8 && tcode[-1] >= 0xc0) - tcode += _pcre_utf8_table4[tcode[-1] & 0x3f]; -#endif - break; - - /* At least one single char sets the bit and stops */ - - case OP_EXACT: /* Fall through */ - tcode += 2; - - case OP_CHAR: - case OP_CHARNC: - case OP_PLUS: - case OP_MINPLUS: - case OP_POSPLUS: - set_bit(start_bits, tcode[1], caseless, cd); - try_next = FALSE; - break; - - /* Single character type sets the bits and stops */ - - case OP_NOT_DIGIT: - for (c = 0; c < 32; c++) - start_bits[c] |= ~cd->cbits[c+cbit_digit]; - try_next = FALSE; - break; - - case OP_DIGIT: - for (c = 0; c < 32; c++) - start_bits[c] |= cd->cbits[c+cbit_digit]; - try_next = FALSE; - break; - - /* The cbit_space table has vertical tab as whitespace; we have to - discard it. */ - - case OP_NOT_WHITESPACE: - for (c = 0; c < 32; c++) - { - int d = cd->cbits[c+cbit_space]; - if (c == 1) d &= ~0x08; - start_bits[c] |= ~d; - } - try_next = FALSE; - break; - - /* The cbit_space table has vertical tab as whitespace; we have to - discard it. */ - - case OP_WHITESPACE: - for (c = 0; c < 32; c++) - { - int d = cd->cbits[c+cbit_space]; - if (c == 1) d &= ~0x08; - start_bits[c] |= d; - } - try_next = FALSE; - break; - - case OP_NOT_WORDCHAR: - for (c = 0; c < 32; c++) - start_bits[c] |= ~cd->cbits[c+cbit_word]; - try_next = FALSE; - break; - - case OP_WORDCHAR: - for (c = 0; c < 32; c++) - start_bits[c] |= cd->cbits[c+cbit_word]; - try_next = FALSE; - break; - - /* One or more character type fudges the pointer and restarts, knowing - it will hit a single character type and stop there. */ - - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - tcode++; - break; - - case OP_TYPEEXACT: - tcode += 3; - break; - - /* Zero or more repeats of character types set the bits and then - try again. */ - - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - case OP_TYPEPOSUPTO: - tcode += 2; /* Fall through */ - - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPOSSTAR: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - case OP_TYPEPOSQUERY: - switch(tcode[1]) - { - case OP_ANY: - case OP_ALLANY: - return SSB_FAIL; - - case OP_NOT_DIGIT: - for (c = 0; c < 32; c++) - start_bits[c] |= ~cd->cbits[c+cbit_digit]; - break; - - case OP_DIGIT: - for (c = 0; c < 32; c++) - start_bits[c] |= cd->cbits[c+cbit_digit]; - break; - - /* The cbit_space table has vertical tab as whitespace; we have to - discard it. */ - - case OP_NOT_WHITESPACE: - for (c = 0; c < 32; c++) - { - int d = cd->cbits[c+cbit_space]; - if (c == 1) d &= ~0x08; - start_bits[c] |= ~d; - } - break; - - /* The cbit_space table has vertical tab as whitespace; we have to - discard it. */ - - case OP_WHITESPACE: - for (c = 0; c < 32; c++) - { - int d = cd->cbits[c+cbit_space]; - if (c == 1) d &= ~0x08; - start_bits[c] |= d; - } - break; - - case OP_NOT_WORDCHAR: - for (c = 0; c < 32; c++) - start_bits[c] |= ~cd->cbits[c+cbit_word]; - break; - - case OP_WORDCHAR: - for (c = 0; c < 32; c++) - start_bits[c] |= cd->cbits[c+cbit_word]; - break; - } - - tcode += 2; - break; - - /* Character class where all the information is in a bit map: set the - bits and either carry on or not, according to the repeat count. If it was - a negative class, and we are operating with UTF-8 characters, any byte - with a value >= 0xc4 is a potentially valid starter because it starts a - character with a value > 255. */ - - case OP_NCLASS: -#ifdef SUPPORT_UTF8 - if (utf8) - { - start_bits[24] |= 0xf0; /* Bits for 0xc4 - 0xc8 */ - memset(start_bits+25, 0xff, 7); /* Bits for 0xc9 - 0xff */ - } -#endif - /* Fall through */ - - case OP_CLASS: - { - tcode++; - - /* In UTF-8 mode, the bits in a bit map correspond to character - values, not to byte values. However, the bit map we are constructing is - for byte values. So we have to do a conversion for characters whose - value is > 127. In fact, there are only two possible starting bytes for - characters in the range 128 - 255. */ - -#ifdef SUPPORT_UTF8 - if (utf8) - { - for (c = 0; c < 16; c++) start_bits[c] |= tcode[c]; - for (c = 128; c < 256; c++) - { - if ((tcode[c/8] && (1 << (c&7))) != 0) - { - int d = (c >> 6) | 0xc0; /* Set bit for this starter */ - start_bits[d/8] |= (1 << (d&7)); /* and then skip on to the */ - c = (c & 0xc0) + 0x40 - 1; /* next relevant character. */ - } - } - } - - /* In non-UTF-8 mode, the two bit maps are completely compatible. */ - - else -#endif - { - for (c = 0; c < 32; c++) start_bits[c] |= tcode[c]; - } - - /* Advance past the bit map, and act on what follows */ - - tcode += 32; - switch (*tcode) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRQUERY: - case OP_CRMINQUERY: - tcode++; - break; - - case OP_CRRANGE: - case OP_CRMINRANGE: - if (((tcode[1] << 8) + tcode[2]) == 0) tcode += 5; - else try_next = FALSE; - break; - - default: - try_next = FALSE; - break; - } - } - break; /* End of bitmap class handling */ - - } /* End of switch */ - } /* End of try_next loop */ - - code += GET(code, 1); /* Advance to next branch */ - } -while (*code == OP_ALT); -return yield; -} - - - -/************************************************* -* Study a compiled expression * -*************************************************/ - -/* This function is handed a compiled expression that it must study to produce -information that will speed up the matching. It returns a pcre_extra block -which then gets handed back to pcre_exec(). - -Arguments: - re points to the compiled expression - options contains option bits - errorptr points to where to place error messages; - set NULL unless error - -Returns: pointer to a pcre_extra block, with study_data filled in and the - appropriate flag set; - NULL on error or if no optimization possible -*/ - -PCRE_EXP_DEFN pcre_extra * PCRE_CALL_CONVENTION -pcre_study(const pcre *external_re, int options, const char **errorptr) -{ -uschar start_bits[32]; -pcre_extra *extra; -pcre_study_data *study; -const uschar *tables; -uschar *code; -compile_data compile_block; -const real_pcre *re = (const real_pcre *)external_re; - -*errorptr = NULL; - -if (re == NULL || re->magic_number != MAGIC_NUMBER) - { - *errorptr = "argument is not a compiled regular expression"; - return NULL; - } - -if ((options & ~PUBLIC_STUDY_OPTIONS) != 0) - { - *errorptr = "unknown or incorrect option bit(s) set"; - return NULL; - } - -code = (uschar *)re + re->name_table_offset + - (re->name_count * re->name_entry_size); - -/* For an anchored pattern, or an unanchored pattern that has a first char, or -a multiline pattern that matches only at "line starts", no further processing -at present. */ - -if ((re->options & PCRE_ANCHORED) != 0 || - (re->flags & (PCRE_FIRSTSET|PCRE_STARTLINE)) != 0) - return NULL; - -/* Set the character tables in the block that is passed around */ - -tables = re->tables; -if (tables == NULL) - (void)pcre_fullinfo(external_re, NULL, PCRE_INFO_DEFAULT_TABLES, - (void *)(&tables)); - -compile_block.lcc = tables + lcc_offset; -compile_block.fcc = tables + fcc_offset; -compile_block.cbits = tables + cbits_offset; -compile_block.ctypes = tables + ctypes_offset; - -/* See if we can find a fixed set of initial characters for the pattern. */ - -memset(start_bits, 0, 32 * sizeof(uschar)); -if (set_start_bits(code, start_bits, (re->options & PCRE_CASELESS) != 0, - (re->options & PCRE_UTF8) != 0, &compile_block) != SSB_DONE) return NULL; - -/* Get a pcre_extra block and a pcre_study_data block. The study data is put in -the latter, which is pointed to by the former, which may also get additional -data set later by the calling program. At the moment, the size of -pcre_study_data is fixed. We nevertheless save it in a field for returning via -the pcre_fullinfo() function so that if it becomes variable in the future, we -don't have to change that code. */ - -extra = (pcre_extra *)(pcre_malloc) - (sizeof(pcre_extra) + sizeof(pcre_study_data)); - -if (extra == NULL) - { - *errorptr = "failed to get memory"; - return NULL; - } - -study = (pcre_study_data *)((char *)extra + sizeof(pcre_extra)); -extra->flags = PCRE_EXTRA_STUDY_DATA; -extra->study_data = study; - -study->size = sizeof(pcre_study_data); -study->options = PCRE_STUDY_MAPPED; -memcpy(study->start_bits, start_bits, sizeof(start_bits)); - -return extra; -} - -/* End of pcre_study.c */ diff --git a/libs/pcre/pcre_tables.c b/libs/pcre/pcre_tables.c deleted file mode 100644 index 633313497b..0000000000 --- a/libs/pcre/pcre_tables.c +++ /dev/null @@ -1,478 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2009 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains some fixed tables that are used by more than one of the -PCRE code modules. The tables are also #included by the pcretest program, which -uses macros to change their names from _pcre_xxx to xxxx, thereby avoiding name -clashes with the library. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - - -/* Table of sizes for the fixed-length opcodes. It's defined in a macro so that -the definition is next to the definition of the opcodes in pcre_internal.h. */ - -const uschar _pcre_OP_lengths[] = { OP_LENGTHS }; - - - -/************************************************* -* Tables for UTF-8 support * -*************************************************/ - -/* These are the breakpoints for different numbers of bytes in a UTF-8 -character. */ - -#ifdef SUPPORT_UTF8 - -const int _pcre_utf8_table1[] = - { 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff}; - -const int _pcre_utf8_table1_size = sizeof(_pcre_utf8_table1)/sizeof(int); - -/* These are the indicator bits and the mask for the data bits to set in the -first byte of a character, indexed by the number of additional bytes. */ - -const int _pcre_utf8_table2[] = { 0, 0xc0, 0xe0, 0xf0, 0xf8, 0xfc}; -const int _pcre_utf8_table3[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01}; - -/* Table of the number of extra bytes, indexed by the first byte masked with -0x3f. The highest number for a valid UTF-8 first byte is in fact 0x3d. */ - -const uschar _pcre_utf8_table4[] = { - 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, - 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, - 2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, - 3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 }; - -/* Table to translate from particular type value to the general value. */ - -const int _pcre_ucp_gentype[] = { - ucp_C, ucp_C, ucp_C, ucp_C, ucp_C, /* Cc, Cf, Cn, Co, Cs */ - ucp_L, ucp_L, ucp_L, ucp_L, ucp_L, /* Ll, Lu, Lm, Lo, Lt */ - ucp_M, ucp_M, ucp_M, /* Mc, Me, Mn */ - ucp_N, ucp_N, ucp_N, /* Nd, Nl, No */ - ucp_P, ucp_P, ucp_P, ucp_P, ucp_P, /* Pc, Pd, Pe, Pf, Pi */ - ucp_P, ucp_P, /* Ps, Po */ - ucp_S, ucp_S, ucp_S, ucp_S, /* Sc, Sk, Sm, So */ - ucp_Z, ucp_Z, ucp_Z /* Zl, Zp, Zs */ -}; - -/* The pcre_utt[] table below translates Unicode property names into type and -code values. It is searched by binary chop, so must be in collating sequence of -name. Originally, the table contained pointers to the name strings in the first -field of each entry. However, that leads to a large number of relocations when -a shared library is dynamically loaded. A significant reduction is made by -putting all the names into a single, large string and then using offsets in the -table itself. Maintenance is more error-prone, but frequent changes to this -data are unlikely. - -July 2008: There is now a script called maint/GenerateUtt.py that can be used -to generate this data instead of maintaining it entirely by hand. - -The script was updated in March 2009 to generate a new EBCDIC-compliant -version. Like all other character and string literals that are compared against -the regular expression pattern, we must use STR_ macros instead of literal -strings to make sure that UTF-8 support works on EBCDIC platforms. */ - -#define STRING_Any0 STR_A STR_n STR_y "\0" -#define STRING_Arabic0 STR_A STR_r STR_a STR_b STR_i STR_c "\0" -#define STRING_Armenian0 STR_A STR_r STR_m STR_e STR_n STR_i STR_a STR_n "\0" -#define STRING_Balinese0 STR_B STR_a STR_l STR_i STR_n STR_e STR_s STR_e "\0" -#define STRING_Bengali0 STR_B STR_e STR_n STR_g STR_a STR_l STR_i "\0" -#define STRING_Bopomofo0 STR_B STR_o STR_p STR_o STR_m STR_o STR_f STR_o "\0" -#define STRING_Braille0 STR_B STR_r STR_a STR_i STR_l STR_l STR_e "\0" -#define STRING_Buginese0 STR_B STR_u STR_g STR_i STR_n STR_e STR_s STR_e "\0" -#define STRING_Buhid0 STR_B STR_u STR_h STR_i STR_d "\0" -#define STRING_C0 STR_C "\0" -#define STRING_Canadian_Aboriginal0 STR_C STR_a STR_n STR_a STR_d STR_i STR_a STR_n STR_UNDERSCORE STR_A STR_b STR_o STR_r STR_i STR_g STR_i STR_n STR_a STR_l "\0" -#define STRING_Carian0 STR_C STR_a STR_r STR_i STR_a STR_n "\0" -#define STRING_Cc0 STR_C STR_c "\0" -#define STRING_Cf0 STR_C STR_f "\0" -#define STRING_Cham0 STR_C STR_h STR_a STR_m "\0" -#define STRING_Cherokee0 STR_C STR_h STR_e STR_r STR_o STR_k STR_e STR_e "\0" -#define STRING_Cn0 STR_C STR_n "\0" -#define STRING_Co0 STR_C STR_o "\0" -#define STRING_Common0 STR_C STR_o STR_m STR_m STR_o STR_n "\0" -#define STRING_Coptic0 STR_C STR_o STR_p STR_t STR_i STR_c "\0" -#define STRING_Cs0 STR_C STR_s "\0" -#define STRING_Cuneiform0 STR_C STR_u STR_n STR_e STR_i STR_f STR_o STR_r STR_m "\0" -#define STRING_Cypriot0 STR_C STR_y STR_p STR_r STR_i STR_o STR_t "\0" -#define STRING_Cyrillic0 STR_C STR_y STR_r STR_i STR_l STR_l STR_i STR_c "\0" -#define STRING_Deseret0 STR_D STR_e STR_s STR_e STR_r STR_e STR_t "\0" -#define STRING_Devanagari0 STR_D STR_e STR_v STR_a STR_n STR_a STR_g STR_a STR_r STR_i "\0" -#define STRING_Ethiopic0 STR_E STR_t STR_h STR_i STR_o STR_p STR_i STR_c "\0" -#define STRING_Georgian0 STR_G STR_e STR_o STR_r STR_g STR_i STR_a STR_n "\0" -#define STRING_Glagolitic0 STR_G STR_l STR_a STR_g STR_o STR_l STR_i STR_t STR_i STR_c "\0" -#define STRING_Gothic0 STR_G STR_o STR_t STR_h STR_i STR_c "\0" -#define STRING_Greek0 STR_G STR_r STR_e STR_e STR_k "\0" -#define STRING_Gujarati0 STR_G STR_u STR_j STR_a STR_r STR_a STR_t STR_i "\0" -#define STRING_Gurmukhi0 STR_G STR_u STR_r STR_m STR_u STR_k STR_h STR_i "\0" -#define STRING_Han0 STR_H STR_a STR_n "\0" -#define STRING_Hangul0 STR_H STR_a STR_n STR_g STR_u STR_l "\0" -#define STRING_Hanunoo0 STR_H STR_a STR_n STR_u STR_n STR_o STR_o "\0" -#define STRING_Hebrew0 STR_H STR_e STR_b STR_r STR_e STR_w "\0" -#define STRING_Hiragana0 STR_H STR_i STR_r STR_a STR_g STR_a STR_n STR_a "\0" -#define STRING_Inherited0 STR_I STR_n STR_h STR_e STR_r STR_i STR_t STR_e STR_d "\0" -#define STRING_Kannada0 STR_K STR_a STR_n STR_n STR_a STR_d STR_a "\0" -#define STRING_Katakana0 STR_K STR_a STR_t STR_a STR_k STR_a STR_n STR_a "\0" -#define STRING_Kayah_Li0 STR_K STR_a STR_y STR_a STR_h STR_UNDERSCORE STR_L STR_i "\0" -#define STRING_Kharoshthi0 STR_K STR_h STR_a STR_r STR_o STR_s STR_h STR_t STR_h STR_i "\0" -#define STRING_Khmer0 STR_K STR_h STR_m STR_e STR_r "\0" -#define STRING_L0 STR_L "\0" -#define STRING_L_AMPERSAND0 STR_L STR_AMPERSAND "\0" -#define STRING_Lao0 STR_L STR_a STR_o "\0" -#define STRING_Latin0 STR_L STR_a STR_t STR_i STR_n "\0" -#define STRING_Lepcha0 STR_L STR_e STR_p STR_c STR_h STR_a "\0" -#define STRING_Limbu0 STR_L STR_i STR_m STR_b STR_u "\0" -#define STRING_Linear_B0 STR_L STR_i STR_n STR_e STR_a STR_r STR_UNDERSCORE STR_B "\0" -#define STRING_Ll0 STR_L STR_l "\0" -#define STRING_Lm0 STR_L STR_m "\0" -#define STRING_Lo0 STR_L STR_o "\0" -#define STRING_Lt0 STR_L STR_t "\0" -#define STRING_Lu0 STR_L STR_u "\0" -#define STRING_Lycian0 STR_L STR_y STR_c STR_i STR_a STR_n "\0" -#define STRING_Lydian0 STR_L STR_y STR_d STR_i STR_a STR_n "\0" -#define STRING_M0 STR_M "\0" -#define STRING_Malayalam0 STR_M STR_a STR_l STR_a STR_y STR_a STR_l STR_a STR_m "\0" -#define STRING_Mc0 STR_M STR_c "\0" -#define STRING_Me0 STR_M STR_e "\0" -#define STRING_Mn0 STR_M STR_n "\0" -#define STRING_Mongolian0 STR_M STR_o STR_n STR_g STR_o STR_l STR_i STR_a STR_n "\0" -#define STRING_Myanmar0 STR_M STR_y STR_a STR_n STR_m STR_a STR_r "\0" -#define STRING_N0 STR_N "\0" -#define STRING_Nd0 STR_N STR_d "\0" -#define STRING_New_Tai_Lue0 STR_N STR_e STR_w STR_UNDERSCORE STR_T STR_a STR_i STR_UNDERSCORE STR_L STR_u STR_e "\0" -#define STRING_Nko0 STR_N STR_k STR_o "\0" -#define STRING_Nl0 STR_N STR_l "\0" -#define STRING_No0 STR_N STR_o "\0" -#define STRING_Ogham0 STR_O STR_g STR_h STR_a STR_m "\0" -#define STRING_Ol_Chiki0 STR_O STR_l STR_UNDERSCORE STR_C STR_h STR_i STR_k STR_i "\0" -#define STRING_Old_Italic0 STR_O STR_l STR_d STR_UNDERSCORE STR_I STR_t STR_a STR_l STR_i STR_c "\0" -#define STRING_Old_Persian0 STR_O STR_l STR_d STR_UNDERSCORE STR_P STR_e STR_r STR_s STR_i STR_a STR_n "\0" -#define STRING_Oriya0 STR_O STR_r STR_i STR_y STR_a "\0" -#define STRING_Osmanya0 STR_O STR_s STR_m STR_a STR_n STR_y STR_a "\0" -#define STRING_P0 STR_P "\0" -#define STRING_Pc0 STR_P STR_c "\0" -#define STRING_Pd0 STR_P STR_d "\0" -#define STRING_Pe0 STR_P STR_e "\0" -#define STRING_Pf0 STR_P STR_f "\0" -#define STRING_Phags_Pa0 STR_P STR_h STR_a STR_g STR_s STR_UNDERSCORE STR_P STR_a "\0" -#define STRING_Phoenician0 STR_P STR_h STR_o STR_e STR_n STR_i STR_c STR_i STR_a STR_n "\0" -#define STRING_Pi0 STR_P STR_i "\0" -#define STRING_Po0 STR_P STR_o "\0" -#define STRING_Ps0 STR_P STR_s "\0" -#define STRING_Rejang0 STR_R STR_e STR_j STR_a STR_n STR_g "\0" -#define STRING_Runic0 STR_R STR_u STR_n STR_i STR_c "\0" -#define STRING_S0 STR_S "\0" -#define STRING_Saurashtra0 STR_S STR_a STR_u STR_r STR_a STR_s STR_h STR_t STR_r STR_a "\0" -#define STRING_Sc0 STR_S STR_c "\0" -#define STRING_Shavian0 STR_S STR_h STR_a STR_v STR_i STR_a STR_n "\0" -#define STRING_Sinhala0 STR_S STR_i STR_n STR_h STR_a STR_l STR_a "\0" -#define STRING_Sk0 STR_S STR_k "\0" -#define STRING_Sm0 STR_S STR_m "\0" -#define STRING_So0 STR_S STR_o "\0" -#define STRING_Sundanese0 STR_S STR_u STR_n STR_d STR_a STR_n STR_e STR_s STR_e "\0" -#define STRING_Syloti_Nagri0 STR_S STR_y STR_l STR_o STR_t STR_i STR_UNDERSCORE STR_N STR_a STR_g STR_r STR_i "\0" -#define STRING_Syriac0 STR_S STR_y STR_r STR_i STR_a STR_c "\0" -#define STRING_Tagalog0 STR_T STR_a STR_g STR_a STR_l STR_o STR_g "\0" -#define STRING_Tagbanwa0 STR_T STR_a STR_g STR_b STR_a STR_n STR_w STR_a "\0" -#define STRING_Tai_Le0 STR_T STR_a STR_i STR_UNDERSCORE STR_L STR_e "\0" -#define STRING_Tamil0 STR_T STR_a STR_m STR_i STR_l "\0" -#define STRING_Telugu0 STR_T STR_e STR_l STR_u STR_g STR_u "\0" -#define STRING_Thaana0 STR_T STR_h STR_a STR_a STR_n STR_a "\0" -#define STRING_Thai0 STR_T STR_h STR_a STR_i "\0" -#define STRING_Tibetan0 STR_T STR_i STR_b STR_e STR_t STR_a STR_n "\0" -#define STRING_Tifinagh0 STR_T STR_i STR_f STR_i STR_n STR_a STR_g STR_h "\0" -#define STRING_Ugaritic0 STR_U STR_g STR_a STR_r STR_i STR_t STR_i STR_c "\0" -#define STRING_Vai0 STR_V STR_a STR_i "\0" -#define STRING_Yi0 STR_Y STR_i "\0" -#define STRING_Z0 STR_Z "\0" -#define STRING_Zl0 STR_Z STR_l "\0" -#define STRING_Zp0 STR_Z STR_p "\0" -#define STRING_Zs0 STR_Z STR_s "\0" - -const char _pcre_utt_names[] = - STRING_Any0 - STRING_Arabic0 - STRING_Armenian0 - STRING_Balinese0 - STRING_Bengali0 - STRING_Bopomofo0 - STRING_Braille0 - STRING_Buginese0 - STRING_Buhid0 - STRING_C0 - STRING_Canadian_Aboriginal0 - STRING_Carian0 - STRING_Cc0 - STRING_Cf0 - STRING_Cham0 - STRING_Cherokee0 - STRING_Cn0 - STRING_Co0 - STRING_Common0 - STRING_Coptic0 - STRING_Cs0 - STRING_Cuneiform0 - STRING_Cypriot0 - STRING_Cyrillic0 - STRING_Deseret0 - STRING_Devanagari0 - STRING_Ethiopic0 - STRING_Georgian0 - STRING_Glagolitic0 - STRING_Gothic0 - STRING_Greek0 - STRING_Gujarati0 - STRING_Gurmukhi0 - STRING_Han0 - STRING_Hangul0 - STRING_Hanunoo0 - STRING_Hebrew0 - STRING_Hiragana0 - STRING_Inherited0 - STRING_Kannada0 - STRING_Katakana0 - STRING_Kayah_Li0 - STRING_Kharoshthi0 - STRING_Khmer0 - STRING_L0 - STRING_L_AMPERSAND0 - STRING_Lao0 - STRING_Latin0 - STRING_Lepcha0 - STRING_Limbu0 - STRING_Linear_B0 - STRING_Ll0 - STRING_Lm0 - STRING_Lo0 - STRING_Lt0 - STRING_Lu0 - STRING_Lycian0 - STRING_Lydian0 - STRING_M0 - STRING_Malayalam0 - STRING_Mc0 - STRING_Me0 - STRING_Mn0 - STRING_Mongolian0 - STRING_Myanmar0 - STRING_N0 - STRING_Nd0 - STRING_New_Tai_Lue0 - STRING_Nko0 - STRING_Nl0 - STRING_No0 - STRING_Ogham0 - STRING_Ol_Chiki0 - STRING_Old_Italic0 - STRING_Old_Persian0 - STRING_Oriya0 - STRING_Osmanya0 - STRING_P0 - STRING_Pc0 - STRING_Pd0 - STRING_Pe0 - STRING_Pf0 - STRING_Phags_Pa0 - STRING_Phoenician0 - STRING_Pi0 - STRING_Po0 - STRING_Ps0 - STRING_Rejang0 - STRING_Runic0 - STRING_S0 - STRING_Saurashtra0 - STRING_Sc0 - STRING_Shavian0 - STRING_Sinhala0 - STRING_Sk0 - STRING_Sm0 - STRING_So0 - STRING_Sundanese0 - STRING_Syloti_Nagri0 - STRING_Syriac0 - STRING_Tagalog0 - STRING_Tagbanwa0 - STRING_Tai_Le0 - STRING_Tamil0 - STRING_Telugu0 - STRING_Thaana0 - STRING_Thai0 - STRING_Tibetan0 - STRING_Tifinagh0 - STRING_Ugaritic0 - STRING_Vai0 - STRING_Yi0 - STRING_Z0 - STRING_Zl0 - STRING_Zp0 - STRING_Zs0; - -const ucp_type_table _pcre_utt[] = { - { 0, PT_ANY, 0 }, - { 4, PT_SC, ucp_Arabic }, - { 11, PT_SC, ucp_Armenian }, - { 20, PT_SC, ucp_Balinese }, - { 29, PT_SC, ucp_Bengali }, - { 37, PT_SC, ucp_Bopomofo }, - { 46, PT_SC, ucp_Braille }, - { 54, PT_SC, ucp_Buginese }, - { 63, PT_SC, ucp_Buhid }, - { 69, PT_GC, ucp_C }, - { 71, PT_SC, ucp_Canadian_Aboriginal }, - { 91, PT_SC, ucp_Carian }, - { 98, PT_PC, ucp_Cc }, - { 101, PT_PC, ucp_Cf }, - { 104, PT_SC, ucp_Cham }, - { 109, PT_SC, ucp_Cherokee }, - { 118, PT_PC, ucp_Cn }, - { 121, PT_PC, ucp_Co }, - { 124, PT_SC, ucp_Common }, - { 131, PT_SC, ucp_Coptic }, - { 138, PT_PC, ucp_Cs }, - { 141, PT_SC, ucp_Cuneiform }, - { 151, PT_SC, ucp_Cypriot }, - { 159, PT_SC, ucp_Cyrillic }, - { 168, PT_SC, ucp_Deseret }, - { 176, PT_SC, ucp_Devanagari }, - { 187, PT_SC, ucp_Ethiopic }, - { 196, PT_SC, ucp_Georgian }, - { 205, PT_SC, ucp_Glagolitic }, - { 216, PT_SC, ucp_Gothic }, - { 223, PT_SC, ucp_Greek }, - { 229, PT_SC, ucp_Gujarati }, - { 238, PT_SC, ucp_Gurmukhi }, - { 247, PT_SC, ucp_Han }, - { 251, PT_SC, ucp_Hangul }, - { 258, PT_SC, ucp_Hanunoo }, - { 266, PT_SC, ucp_Hebrew }, - { 273, PT_SC, ucp_Hiragana }, - { 282, PT_SC, ucp_Inherited }, - { 292, PT_SC, ucp_Kannada }, - { 300, PT_SC, ucp_Katakana }, - { 309, PT_SC, ucp_Kayah_Li }, - { 318, PT_SC, ucp_Kharoshthi }, - { 329, PT_SC, ucp_Khmer }, - { 335, PT_GC, ucp_L }, - { 337, PT_LAMP, 0 }, - { 340, PT_SC, ucp_Lao }, - { 344, PT_SC, ucp_Latin }, - { 350, PT_SC, ucp_Lepcha }, - { 357, PT_SC, ucp_Limbu }, - { 363, PT_SC, ucp_Linear_B }, - { 372, PT_PC, ucp_Ll }, - { 375, PT_PC, ucp_Lm }, - { 378, PT_PC, ucp_Lo }, - { 381, PT_PC, ucp_Lt }, - { 384, PT_PC, ucp_Lu }, - { 387, PT_SC, ucp_Lycian }, - { 394, PT_SC, ucp_Lydian }, - { 401, PT_GC, ucp_M }, - { 403, PT_SC, ucp_Malayalam }, - { 413, PT_PC, ucp_Mc }, - { 416, PT_PC, ucp_Me }, - { 419, PT_PC, ucp_Mn }, - { 422, PT_SC, ucp_Mongolian }, - { 432, PT_SC, ucp_Myanmar }, - { 440, PT_GC, ucp_N }, - { 442, PT_PC, ucp_Nd }, - { 445, PT_SC, ucp_New_Tai_Lue }, - { 457, PT_SC, ucp_Nko }, - { 461, PT_PC, ucp_Nl }, - { 464, PT_PC, ucp_No }, - { 467, PT_SC, ucp_Ogham }, - { 473, PT_SC, ucp_Ol_Chiki }, - { 482, PT_SC, ucp_Old_Italic }, - { 493, PT_SC, ucp_Old_Persian }, - { 505, PT_SC, ucp_Oriya }, - { 511, PT_SC, ucp_Osmanya }, - { 519, PT_GC, ucp_P }, - { 521, PT_PC, ucp_Pc }, - { 524, PT_PC, ucp_Pd }, - { 527, PT_PC, ucp_Pe }, - { 530, PT_PC, ucp_Pf }, - { 533, PT_SC, ucp_Phags_Pa }, - { 542, PT_SC, ucp_Phoenician }, - { 553, PT_PC, ucp_Pi }, - { 556, PT_PC, ucp_Po }, - { 559, PT_PC, ucp_Ps }, - { 562, PT_SC, ucp_Rejang }, - { 569, PT_SC, ucp_Runic }, - { 575, PT_GC, ucp_S }, - { 577, PT_SC, ucp_Saurashtra }, - { 588, PT_PC, ucp_Sc }, - { 591, PT_SC, ucp_Shavian }, - { 599, PT_SC, ucp_Sinhala }, - { 607, PT_PC, ucp_Sk }, - { 610, PT_PC, ucp_Sm }, - { 613, PT_PC, ucp_So }, - { 616, PT_SC, ucp_Sundanese }, - { 626, PT_SC, ucp_Syloti_Nagri }, - { 639, PT_SC, ucp_Syriac }, - { 646, PT_SC, ucp_Tagalog }, - { 654, PT_SC, ucp_Tagbanwa }, - { 663, PT_SC, ucp_Tai_Le }, - { 670, PT_SC, ucp_Tamil }, - { 676, PT_SC, ucp_Telugu }, - { 683, PT_SC, ucp_Thaana }, - { 690, PT_SC, ucp_Thai }, - { 695, PT_SC, ucp_Tibetan }, - { 703, PT_SC, ucp_Tifinagh }, - { 712, PT_SC, ucp_Ugaritic }, - { 721, PT_SC, ucp_Vai }, - { 725, PT_SC, ucp_Yi }, - { 728, PT_GC, ucp_Z }, - { 730, PT_PC, ucp_Zl }, - { 733, PT_PC, ucp_Zp }, - { 736, PT_PC, ucp_Zs } -}; - -const int _pcre_utt_size = sizeof(_pcre_utt)/sizeof(ucp_type_table); - -#endif /* SUPPORT_UTF8 */ - -/* End of pcre_tables.c */ diff --git a/libs/pcre/pcre_try_flipped.c b/libs/pcre/pcre_try_flipped.c deleted file mode 100644 index 0d2f3a2d38..0000000000 --- a/libs/pcre/pcre_try_flipped.c +++ /dev/null @@ -1,137 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2008 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains an internal function that tests a compiled pattern to -see if it was compiled with the opposite endianness. If so, it uses an -auxiliary local function to flip the appropriate bytes. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - - -/************************************************* -* Flip bytes in an integer * -*************************************************/ - -/* This function is called when the magic number in a regex doesn't match, in -order to flip its bytes to see if we are dealing with a pattern that was -compiled on a host of different endianness. If so, this function is used to -flip other byte values. - -Arguments: - value the number to flip - n the number of bytes to flip (assumed to be 2 or 4) - -Returns: the flipped value -*/ - -static unsigned long int -byteflip(unsigned long int value, int n) -{ -if (n == 2) return ((value & 0x00ff) << 8) | ((value & 0xff00) >> 8); -return ((value & 0x000000ff) << 24) | - ((value & 0x0000ff00) << 8) | - ((value & 0x00ff0000) >> 8) | - ((value & 0xff000000) >> 24); -} - - - -/************************************************* -* Test for a byte-flipped compiled regex * -*************************************************/ - -/* This function is called from pcre_exec(), pcre_dfa_exec(), and also from -pcre_fullinfo(). Its job is to test whether the regex is byte-flipped - that -is, it was compiled on a system of opposite endianness. The function is called -only when the native MAGIC_NUMBER test fails. If the regex is indeed flipped, -we flip all the relevant values into a different data block, and return it. - -Arguments: - re points to the regex - study points to study data, or NULL - internal_re points to a new regex block - internal_study points to a new study block - -Returns: the new block if is is indeed a byte-flipped regex - NULL if it is not -*/ - -real_pcre * -_pcre_try_flipped(const real_pcre *re, real_pcre *internal_re, - const pcre_study_data *study, pcre_study_data *internal_study) -{ -if (byteflip(re->magic_number, sizeof(re->magic_number)) != MAGIC_NUMBER) - return NULL; - -*internal_re = *re; /* To copy other fields */ -internal_re->size = byteflip(re->size, sizeof(re->size)); -internal_re->options = byteflip(re->options, sizeof(re->options)); -internal_re->flags = (pcre_uint16)byteflip(re->flags, sizeof(re->flags)); -internal_re->top_bracket = - (pcre_uint16)byteflip(re->top_bracket, sizeof(re->top_bracket)); -internal_re->top_backref = - (pcre_uint16)byteflip(re->top_backref, sizeof(re->top_backref)); -internal_re->first_byte = - (pcre_uint16)byteflip(re->first_byte, sizeof(re->first_byte)); -internal_re->req_byte = - (pcre_uint16)byteflip(re->req_byte, sizeof(re->req_byte)); -internal_re->name_table_offset = - (pcre_uint16)byteflip(re->name_table_offset, sizeof(re->name_table_offset)); -internal_re->name_entry_size = - (pcre_uint16)byteflip(re->name_entry_size, sizeof(re->name_entry_size)); -internal_re->name_count = - (pcre_uint16)byteflip(re->name_count, sizeof(re->name_count)); - -if (study != NULL) - { - *internal_study = *study; /* To copy other fields */ - internal_study->size = byteflip(study->size, sizeof(study->size)); - internal_study->options = byteflip(study->options, sizeof(study->options)); - } - -return internal_re; -} - -/* End of pcre_tryflipped.c */ diff --git a/libs/pcre/pcre_ucd.c b/libs/pcre/pcre_ucd.c deleted file mode 100644 index fafecaa523..0000000000 --- a/libs/pcre/pcre_ucd.c +++ /dev/null @@ -1,2610 +0,0 @@ -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif -#include "pcre_internal.h" - -/* Unicode character database. */ -/* This file was autogenerated by the MultiStage2.py script. */ -/* Total size: 52808 bytes, block size: 128. */ -/* When recompiling tables with a new Unicode version, -please check types in the structure definition from pcre_internal.h: -typedef struct { -uschar property_0; -uschar property_1; -pcre_int32 property_2; -} ucd_record; */ - - -const ucd_record _pcre_ucd_records[] = { /* 3656 bytes, record size 8 */ - { 9, 0, 0, }, /* 0 */ - { 9, 29, 0, }, /* 1 */ - { 9, 21, 0, }, /* 2 */ - { 9, 23, 0, }, /* 3 */ - { 9, 22, 0, }, /* 4 */ - { 9, 18, 0, }, /* 5 */ - { 9, 25, 0, }, /* 6 */ - { 9, 17, 0, }, /* 7 */ - { 9, 13, 0, }, /* 8 */ - { 33, 9, 32, }, /* 9 */ - { 9, 24, 0, }, /* 10 */ - { 9, 16, 0, }, /* 11 */ - { 33, 5, -32, }, /* 12 */ - { 9, 26, 0, }, /* 13 */ - { 33, 5, 0, }, /* 14 */ - { 9, 20, 0, }, /* 15 */ - { 9, 1, 0, }, /* 16 */ - { 9, 15, 0, }, /* 17 */ - { 9, 5, 743, }, /* 18 */ - { 9, 19, 0, }, /* 19 */ - { 33, 5, 121, }, /* 20 */ - { 33, 9, 1, }, /* 21 */ - { 33, 5, -1, }, /* 22 */ - { 33, 9, -199, }, /* 23 */ - { 33, 5, -232, }, /* 24 */ - { 33, 9, -121, }, /* 25 */ - { 33, 5, -300, }, /* 26 */ - { 33, 5, 195, }, /* 27 */ - { 33, 9, 210, }, /* 28 */ - { 33, 9, 206, }, /* 29 */ - { 33, 9, 205, }, /* 30 */ - { 33, 9, 79, }, /* 31 */ - { 33, 9, 202, }, /* 32 */ - { 33, 9, 203, }, /* 33 */ - { 33, 9, 207, }, /* 34 */ - { 33, 5, 97, }, /* 35 */ - { 33, 9, 211, }, /* 36 */ - { 33, 9, 209, }, /* 37 */ - { 33, 5, 163, }, /* 38 */ - { 33, 9, 213, }, /* 39 */ - { 33, 5, 130, }, /* 40 */ - { 33, 9, 214, }, /* 41 */ - { 33, 9, 218, }, /* 42 */ - { 33, 9, 217, }, /* 43 */ - { 33, 9, 219, }, /* 44 */ - { 33, 7, 0, }, /* 45 */ - { 33, 5, 56, }, /* 46 */ - { 33, 9, 2, }, /* 47 */ - { 33, 8, -1, }, /* 48 */ - { 33, 5, -2, }, /* 49 */ - { 33, 5, -79, }, /* 50 */ - { 33, 9, -97, }, /* 51 */ - { 33, 9, -56, }, /* 52 */ - { 33, 9, -130, }, /* 53 */ - { 33, 9, 10795, }, /* 54 */ - { 33, 9, -163, }, /* 55 */ - { 33, 9, 10792, }, /* 56 */ - { 33, 9, -195, }, /* 57 */ - { 33, 9, 69, }, /* 58 */ - { 33, 9, 71, }, /* 59 */ - { 33, 5, 10783, }, /* 60 */ - { 33, 5, 10780, }, /* 61 */ - { 33, 5, -210, }, /* 62 */ - { 33, 5, -206, }, /* 63 */ - { 33, 5, -205, }, /* 64 */ - { 33, 5, -202, }, /* 65 */ - { 33, 5, -203, }, /* 66 */ - { 33, 5, -207, }, /* 67 */ - { 33, 5, -209, }, /* 68 */ - { 33, 5, -211, }, /* 69 */ - { 33, 5, 10743, }, /* 70 */ - { 33, 5, 10749, }, /* 71 */ - { 33, 5, -213, }, /* 72 */ - { 33, 5, -214, }, /* 73 */ - { 33, 5, 10727, }, /* 74 */ - { 33, 5, -218, }, /* 75 */ - { 33, 5, -69, }, /* 76 */ - { 33, 5, -217, }, /* 77 */ - { 33, 5, -71, }, /* 78 */ - { 33, 5, -219, }, /* 79 */ - { 33, 6, 0, }, /* 80 */ - { 9, 6, 0, }, /* 81 */ - { 27, 12, 0, }, /* 82 */ - { 27, 12, 84, }, /* 83 */ - { 19, 9, 1, }, /* 84 */ - { 19, 5, -1, }, /* 85 */ - { 19, 24, 0, }, /* 86 */ - { 9, 2, 0, }, /* 87 */ - { 19, 6, 0, }, /* 88 */ - { 19, 5, 130, }, /* 89 */ - { 19, 9, 38, }, /* 90 */ - { 19, 9, 37, }, /* 91 */ - { 19, 9, 64, }, /* 92 */ - { 19, 9, 63, }, /* 93 */ - { 19, 5, 0, }, /* 94 */ - { 19, 9, 32, }, /* 95 */ - { 19, 5, -38, }, /* 96 */ - { 19, 5, -37, }, /* 97 */ - { 19, 5, -32, }, /* 98 */ - { 19, 5, -31, }, /* 99 */ - { 19, 5, -64, }, /* 100 */ - { 19, 5, -63, }, /* 101 */ - { 19, 9, 8, }, /* 102 */ - { 19, 5, -62, }, /* 103 */ - { 19, 5, -57, }, /* 104 */ - { 19, 9, 0, }, /* 105 */ - { 19, 5, -47, }, /* 106 */ - { 19, 5, -54, }, /* 107 */ - { 19, 5, -8, }, /* 108 */ - { 10, 9, 1, }, /* 109 */ - { 10, 5, -1, }, /* 110 */ - { 19, 5, -86, }, /* 111 */ - { 19, 5, -80, }, /* 112 */ - { 19, 5, 7, }, /* 113 */ - { 19, 9, -60, }, /* 114 */ - { 19, 5, -96, }, /* 115 */ - { 19, 25, 0, }, /* 116 */ - { 19, 9, -7, }, /* 117 */ - { 19, 9, -130, }, /* 118 */ - { 12, 9, 80, }, /* 119 */ - { 12, 9, 32, }, /* 120 */ - { 12, 5, -32, }, /* 121 */ - { 12, 5, -80, }, /* 122 */ - { 12, 9, 1, }, /* 123 */ - { 12, 5, -1, }, /* 124 */ - { 12, 26, 0, }, /* 125 */ - { 12, 12, 0, }, /* 126 */ - { 12, 11, 0, }, /* 127 */ - { 12, 9, 15, }, /* 128 */ - { 12, 5, -15, }, /* 129 */ - { 1, 9, 48, }, /* 130 */ - { 1, 6, 0, }, /* 131 */ - { 1, 21, 0, }, /* 132 */ - { 1, 5, -48, }, /* 133 */ - { 1, 5, 0, }, /* 134 */ - { 1, 17, 0, }, /* 135 */ - { 25, 12, 0, }, /* 136 */ - { 25, 17, 0, }, /* 137 */ - { 25, 21, 0, }, /* 138 */ - { 25, 7, 0, }, /* 139 */ - { 0, 25, 0, }, /* 140 */ - { 0, 21, 0, }, /* 141 */ - { 0, 23, 0, }, /* 142 */ - { 0, 26, 0, }, /* 143 */ - { 0, 12, 0, }, /* 144 */ - { 0, 7, 0, }, /* 145 */ - { 0, 11, 0, }, /* 146 */ - { 0, 6, 0, }, /* 147 */ - { 0, 13, 0, }, /* 148 */ - { 49, 21, 0, }, /* 149 */ - { 49, 1, 0, }, /* 150 */ - { 49, 7, 0, }, /* 151 */ - { 49, 12, 0, }, /* 152 */ - { 55, 7, 0, }, /* 153 */ - { 55, 12, 0, }, /* 154 */ - { 63, 13, 0, }, /* 155 */ - { 63, 7, 0, }, /* 156 */ - { 63, 12, 0, }, /* 157 */ - { 63, 6, 0, }, /* 158 */ - { 63, 26, 0, }, /* 159 */ - { 63, 21, 0, }, /* 160 */ - { 14, 12, 0, }, /* 161 */ - { 14, 10, 0, }, /* 162 */ - { 14, 7, 0, }, /* 163 */ - { 14, 13, 0, }, /* 164 */ - { 14, 6, 0, }, /* 165 */ - { 2, 12, 0, }, /* 166 */ - { 2, 10, 0, }, /* 167 */ - { 2, 7, 0, }, /* 168 */ - { 2, 13, 0, }, /* 169 */ - { 2, 23, 0, }, /* 170 */ - { 2, 15, 0, }, /* 171 */ - { 2, 26, 0, }, /* 172 */ - { 21, 12, 0, }, /* 173 */ - { 21, 10, 0, }, /* 174 */ - { 21, 7, 0, }, /* 175 */ - { 21, 13, 0, }, /* 176 */ - { 20, 12, 0, }, /* 177 */ - { 20, 10, 0, }, /* 178 */ - { 20, 7, 0, }, /* 179 */ - { 20, 13, 0, }, /* 180 */ - { 20, 23, 0, }, /* 181 */ - { 43, 12, 0, }, /* 182 */ - { 43, 10, 0, }, /* 183 */ - { 43, 7, 0, }, /* 184 */ - { 43, 13, 0, }, /* 185 */ - { 43, 26, 0, }, /* 186 */ - { 53, 12, 0, }, /* 187 */ - { 53, 7, 0, }, /* 188 */ - { 53, 10, 0, }, /* 189 */ - { 53, 13, 0, }, /* 190 */ - { 53, 15, 0, }, /* 191 */ - { 53, 26, 0, }, /* 192 */ - { 53, 23, 0, }, /* 193 */ - { 54, 10, 0, }, /* 194 */ - { 54, 7, 0, }, /* 195 */ - { 54, 12, 0, }, /* 196 */ - { 54, 13, 0, }, /* 197 */ - { 54, 15, 0, }, /* 198 */ - { 54, 26, 0, }, /* 199 */ - { 28, 10, 0, }, /* 200 */ - { 28, 7, 0, }, /* 201 */ - { 28, 12, 0, }, /* 202 */ - { 28, 13, 0, }, /* 203 */ - { 36, 10, 0, }, /* 204 */ - { 36, 7, 0, }, /* 205 */ - { 36, 12, 0, }, /* 206 */ - { 36, 13, 0, }, /* 207 */ - { 36, 15, 0, }, /* 208 */ - { 36, 26, 0, }, /* 209 */ - { 47, 10, 0, }, /* 210 */ - { 47, 7, 0, }, /* 211 */ - { 47, 12, 0, }, /* 212 */ - { 47, 21, 0, }, /* 213 */ - { 56, 7, 0, }, /* 214 */ - { 56, 12, 0, }, /* 215 */ - { 56, 6, 0, }, /* 216 */ - { 56, 21, 0, }, /* 217 */ - { 56, 13, 0, }, /* 218 */ - { 32, 7, 0, }, /* 219 */ - { 32, 12, 0, }, /* 220 */ - { 32, 6, 0, }, /* 221 */ - { 32, 13, 0, }, /* 222 */ - { 57, 7, 0, }, /* 223 */ - { 57, 26, 0, }, /* 224 */ - { 57, 21, 0, }, /* 225 */ - { 57, 12, 0, }, /* 226 */ - { 57, 13, 0, }, /* 227 */ - { 57, 15, 0, }, /* 228 */ - { 57, 22, 0, }, /* 229 */ - { 57, 18, 0, }, /* 230 */ - { 57, 10, 0, }, /* 231 */ - { 38, 7, 0, }, /* 232 */ - { 38, 10, 0, }, /* 233 */ - { 38, 12, 0, }, /* 234 */ - { 38, 13, 0, }, /* 235 */ - { 38, 21, 0, }, /* 236 */ - { 38, 26, 0, }, /* 237 */ - { 16, 9, 7264, }, /* 238 */ - { 16, 7, 0, }, /* 239 */ - { 16, 6, 0, }, /* 240 */ - { 23, 7, 0, }, /* 241 */ - { 15, 7, 0, }, /* 242 */ - { 15, 12, 0, }, /* 243 */ - { 15, 26, 0, }, /* 244 */ - { 15, 21, 0, }, /* 245 */ - { 15, 15, 0, }, /* 246 */ - { 8, 7, 0, }, /* 247 */ - { 7, 7, 0, }, /* 248 */ - { 7, 21, 0, }, /* 249 */ - { 40, 29, 0, }, /* 250 */ - { 40, 7, 0, }, /* 251 */ - { 40, 22, 0, }, /* 252 */ - { 40, 18, 0, }, /* 253 */ - { 45, 7, 0, }, /* 254 */ - { 45, 14, 0, }, /* 255 */ - { 50, 7, 0, }, /* 256 */ - { 50, 12, 0, }, /* 257 */ - { 24, 7, 0, }, /* 258 */ - { 24, 12, 0, }, /* 259 */ - { 6, 7, 0, }, /* 260 */ - { 6, 12, 0, }, /* 261 */ - { 51, 7, 0, }, /* 262 */ - { 51, 12, 0, }, /* 263 */ - { 31, 7, 0, }, /* 264 */ - { 31, 1, 0, }, /* 265 */ - { 31, 10, 0, }, /* 266 */ - { 31, 12, 0, }, /* 267 */ - { 31, 21, 0, }, /* 268 */ - { 31, 6, 0, }, /* 269 */ - { 31, 23, 0, }, /* 270 */ - { 31, 13, 0, }, /* 271 */ - { 31, 15, 0, }, /* 272 */ - { 37, 21, 0, }, /* 273 */ - { 37, 17, 0, }, /* 274 */ - { 37, 12, 0, }, /* 275 */ - { 37, 29, 0, }, /* 276 */ - { 37, 13, 0, }, /* 277 */ - { 37, 7, 0, }, /* 278 */ - { 37, 6, 0, }, /* 279 */ - { 34, 7, 0, }, /* 280 */ - { 34, 12, 0, }, /* 281 */ - { 34, 10, 0, }, /* 282 */ - { 34, 26, 0, }, /* 283 */ - { 34, 21, 0, }, /* 284 */ - { 34, 13, 0, }, /* 285 */ - { 52, 7, 0, }, /* 286 */ - { 39, 7, 0, }, /* 287 */ - { 39, 10, 0, }, /* 288 */ - { 39, 13, 0, }, /* 289 */ - { 39, 21, 0, }, /* 290 */ - { 31, 26, 0, }, /* 291 */ - { 5, 7, 0, }, /* 292 */ - { 5, 12, 0, }, /* 293 */ - { 5, 10, 0, }, /* 294 */ - { 5, 21, 0, }, /* 295 */ - { 61, 12, 0, }, /* 296 */ - { 61, 10, 0, }, /* 297 */ - { 61, 7, 0, }, /* 298 */ - { 61, 13, 0, }, /* 299 */ - { 61, 21, 0, }, /* 300 */ - { 61, 26, 0, }, /* 301 */ - { 75, 12, 0, }, /* 302 */ - { 75, 10, 0, }, /* 303 */ - { 75, 7, 0, }, /* 304 */ - { 75, 13, 0, }, /* 305 */ - { 69, 7, 0, }, /* 306 */ - { 69, 10, 0, }, /* 307 */ - { 69, 12, 0, }, /* 308 */ - { 69, 21, 0, }, /* 309 */ - { 69, 13, 0, }, /* 310 */ - { 72, 13, 0, }, /* 311 */ - { 72, 7, 0, }, /* 312 */ - { 72, 6, 0, }, /* 313 */ - { 72, 21, 0, }, /* 314 */ - { 12, 5, 0, }, /* 315 */ - { 12, 6, 0, }, /* 316 */ - { 33, 5, 35332, }, /* 317 */ - { 33, 5, 3814, }, /* 318 */ - { 33, 5, -59, }, /* 319 */ - { 33, 9, -7615, }, /* 320 */ - { 19, 5, 8, }, /* 321 */ - { 19, 9, -8, }, /* 322 */ - { 19, 5, 74, }, /* 323 */ - { 19, 5, 86, }, /* 324 */ - { 19, 5, 100, }, /* 325 */ - { 19, 5, 128, }, /* 326 */ - { 19, 5, 112, }, /* 327 */ - { 19, 5, 126, }, /* 328 */ - { 19, 8, -8, }, /* 329 */ - { 19, 5, 9, }, /* 330 */ - { 19, 9, -74, }, /* 331 */ - { 19, 8, -9, }, /* 332 */ - { 19, 5, -7205, }, /* 333 */ - { 19, 9, -86, }, /* 334 */ - { 19, 9, -100, }, /* 335 */ - { 19, 9, -112, }, /* 336 */ - { 19, 9, -128, }, /* 337 */ - { 19, 9, -126, }, /* 338 */ - { 27, 1, 0, }, /* 339 */ - { 9, 27, 0, }, /* 340 */ - { 9, 28, 0, }, /* 341 */ - { 27, 11, 0, }, /* 342 */ - { 9, 9, 0, }, /* 343 */ - { 9, 5, 0, }, /* 344 */ - { 19, 9, -7517, }, /* 345 */ - { 33, 9, -8383, }, /* 346 */ - { 33, 9, -8262, }, /* 347 */ - { 33, 9, 28, }, /* 348 */ - { 9, 7, 0, }, /* 349 */ - { 33, 5, -28, }, /* 350 */ - { 33, 14, 16, }, /* 351 */ - { 33, 14, -16, }, /* 352 */ - { 33, 14, 0, }, /* 353 */ - { 9, 26, 26, }, /* 354 */ - { 9, 26, -26, }, /* 355 */ - { 4, 26, 0, }, /* 356 */ - { 17, 9, 48, }, /* 357 */ - { 17, 5, -48, }, /* 358 */ - { 33, 9, -10743, }, /* 359 */ - { 33, 9, -3814, }, /* 360 */ - { 33, 9, -10727, }, /* 361 */ - { 33, 5, -10795, }, /* 362 */ - { 33, 5, -10792, }, /* 363 */ - { 33, 9, -10780, }, /* 364 */ - { 33, 9, -10749, }, /* 365 */ - { 33, 9, -10783, }, /* 366 */ - { 10, 5, 0, }, /* 367 */ - { 10, 26, 0, }, /* 368 */ - { 10, 21, 0, }, /* 369 */ - { 10, 15, 0, }, /* 370 */ - { 16, 5, -7264, }, /* 371 */ - { 58, 7, 0, }, /* 372 */ - { 58, 6, 0, }, /* 373 */ - { 22, 26, 0, }, /* 374 */ - { 22, 6, 0, }, /* 375 */ - { 22, 14, 0, }, /* 376 */ - { 26, 7, 0, }, /* 377 */ - { 26, 6, 0, }, /* 378 */ - { 29, 7, 0, }, /* 379 */ - { 29, 6, 0, }, /* 380 */ - { 3, 7, 0, }, /* 381 */ - { 23, 26, 0, }, /* 382 */ - { 29, 26, 0, }, /* 383 */ - { 22, 7, 0, }, /* 384 */ - { 60, 7, 0, }, /* 385 */ - { 60, 6, 0, }, /* 386 */ - { 60, 26, 0, }, /* 387 */ - { 76, 7, 0, }, /* 388 */ - { 76, 6, 0, }, /* 389 */ - { 76, 21, 0, }, /* 390 */ - { 76, 13, 0, }, /* 391 */ - { 12, 7, 0, }, /* 392 */ - { 12, 21, 0, }, /* 393 */ - { 33, 9, -35332, }, /* 394 */ - { 48, 7, 0, }, /* 395 */ - { 48, 12, 0, }, /* 396 */ - { 48, 10, 0, }, /* 397 */ - { 48, 26, 0, }, /* 398 */ - { 64, 7, 0, }, /* 399 */ - { 64, 21, 0, }, /* 400 */ - { 74, 10, 0, }, /* 401 */ - { 74, 7, 0, }, /* 402 */ - { 74, 12, 0, }, /* 403 */ - { 74, 21, 0, }, /* 404 */ - { 74, 13, 0, }, /* 405 */ - { 68, 13, 0, }, /* 406 */ - { 68, 7, 0, }, /* 407 */ - { 68, 12, 0, }, /* 408 */ - { 68, 21, 0, }, /* 409 */ - { 73, 7, 0, }, /* 410 */ - { 73, 12, 0, }, /* 411 */ - { 73, 10, 0, }, /* 412 */ - { 73, 21, 0, }, /* 413 */ - { 67, 7, 0, }, /* 414 */ - { 67, 12, 0, }, /* 415 */ - { 67, 10, 0, }, /* 416 */ - { 67, 13, 0, }, /* 417 */ - { 67, 21, 0, }, /* 418 */ - { 9, 4, 0, }, /* 419 */ - { 9, 3, 0, }, /* 420 */ - { 25, 25, 0, }, /* 421 */ - { 35, 7, 0, }, /* 422 */ - { 19, 14, 0, }, /* 423 */ - { 19, 15, 0, }, /* 424 */ - { 19, 26, 0, }, /* 425 */ - { 70, 7, 0, }, /* 426 */ - { 66, 7, 0, }, /* 427 */ - { 41, 7, 0, }, /* 428 */ - { 41, 15, 0, }, /* 429 */ - { 18, 7, 0, }, /* 430 */ - { 18, 14, 0, }, /* 431 */ - { 59, 7, 0, }, /* 432 */ - { 59, 21, 0, }, /* 433 */ - { 42, 7, 0, }, /* 434 */ - { 42, 21, 0, }, /* 435 */ - { 42, 14, 0, }, /* 436 */ - { 13, 9, 40, }, /* 437 */ - { 13, 5, -40, }, /* 438 */ - { 46, 7, 0, }, /* 439 */ - { 44, 7, 0, }, /* 440 */ - { 44, 13, 0, }, /* 441 */ - { 11, 7, 0, }, /* 442 */ - { 65, 7, 0, }, /* 443 */ - { 65, 15, 0, }, /* 444 */ - { 65, 21, 0, }, /* 445 */ - { 71, 7, 0, }, /* 446 */ - { 71, 21, 0, }, /* 447 */ - { 30, 7, 0, }, /* 448 */ - { 30, 12, 0, }, /* 449 */ - { 30, 15, 0, }, /* 450 */ - { 30, 21, 0, }, /* 451 */ - { 62, 7, 0, }, /* 452 */ - { 62, 14, 0, }, /* 453 */ - { 62, 21, 0, }, /* 454 */ - { 9, 10, 0, }, /* 455 */ - { 19, 12, 0, }, /* 456 */ -}; - -const uschar _pcre_ucd_stage1[] = { /* 8704 bytes */ - 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, /* U+0000 */ - 16, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, /* U+0800 */ - 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 40, 40, 41, 42, 43, 44, /* U+1000 */ - 45, 46, 47, 48, 49, 16, 50, 51, 52, 16, 53, 54, 55, 56, 57, 58, /* U+1800 */ - 59, 60, 61, 62, 63, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, /* U+2000 */ - 74, 74, 63, 75, 63, 63, 76, 16, 77, 78, 79, 80, 81, 82, 83, 84, /* U+2800 */ - 85, 86, 87, 88, 89, 90, 91, 68, 92, 92, 92, 92, 92, 92, 92, 92, /* U+3000 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+3800 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+4000 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 93, 92, 92, 92, 92, /* U+4800 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+5000 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+5800 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+6000 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+6800 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+7000 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+7800 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+8000 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+8800 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+9000 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 94, /* U+9800 */ - 95, 96, 96, 96, 96, 96, 96, 96, 96, 97, 98, 98, 99,100,101,102, /* U+A000 */ -103,104,105, 16,106, 16, 16, 16,107,107,107,107,107,107,107,107, /* U+A800 */ -107,107,107,107,107,107,107,107,107,107,107,107,107,107,107,107, /* U+B000 */ -107,107,107,107,107,107,107,107,107,107,107,107,107,107,107,107, /* U+B800 */ -107,107,107,107,107,107,107,107,107,107,107,107,107,107,107,107, /* U+C000 */ -107,107,107,107,107,107,107,107,107,107,107,107,107,107,107,107, /* U+C800 */ -107,107,107,107,107,107,107,107,107,107,107,107,107,107,107,108, /* U+D000 */ -109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, /* U+D800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+E000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+E800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F000 */ -110,110, 92, 92,111,112,113,114,115,115,116,117,118,119,120,121, /* U+F800 */ -122,123,124,125, 16,126,127,128,129,130, 16, 16, 16, 16, 16, 16, /* U+10000 */ -131, 16,132, 16,133, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+10800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+11000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+11800 */ -134,134,134,134,134,134,135, 16,136, 16, 16, 16, 16, 16, 16, 16, /* U+12000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+12800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+13000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+13800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+14000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+14800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+15000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+15800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+16000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+16800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+17000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+17800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+18000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+18800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+19000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+19800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+1A000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+1A800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+1B000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+1B800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+1C000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+1C800 */ - 68,137,138,139,140, 16,141, 16,142,143,144,145,146,147,148,149, /* U+1D000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+1D800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+1E000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+1E800 */ -150,151, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+1F000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+1F800 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+20000 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+20800 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+21000 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+21800 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+22000 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+22800 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+23000 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+23800 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+24000 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+24800 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+25000 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+25800 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+26000 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+26800 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+27000 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+27800 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+28000 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+28800 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+29000 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, /* U+29800 */ - 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,152, 16, 16, /* U+2A000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+2A800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+2B000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+2B800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+2C000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+2C800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+2D000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+2D800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+2E000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+2E800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+2F000 */ - 92, 92, 92, 92,153, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+2F800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+30000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+30800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+31000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+31800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+32000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+32800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+33000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+33800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+34000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+34800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+35000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+35800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+36000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+36800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+37000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+37800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+38000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+38800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+39000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+39800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+3A000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+3A800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+3B000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+3B800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+3C000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+3C800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+3D000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+3D800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+3E000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+3E800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+3F000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+3F800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+40000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+40800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+41000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+41800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+42000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+42800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+43000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+43800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+44000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+44800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+45000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+45800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+46000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+46800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+47000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+47800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+48000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+48800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+49000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+49800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+4A000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+4A800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+4B000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+4B800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+4C000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+4C800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+4D000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+4D800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+4E000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+4E800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+4F000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+4F800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+50000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+50800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+51000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+51800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+52000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+52800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+53000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+53800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+54000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+54800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+55000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+55800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+56000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+56800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+57000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+57800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+58000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+58800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+59000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+59800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+5A000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+5A800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+5B000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+5B800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+5C000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+5C800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+5D000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+5D800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+5E000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+5E800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+5F000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+5F800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+60000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+60800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+61000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+61800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+62000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+62800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+63000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+63800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+64000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+64800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+65000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+65800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+66000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+66800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+67000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+67800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+68000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+68800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+69000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+69800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+6A000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+6A800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+6B000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+6B800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+6C000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+6C800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+6D000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+6D800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+6E000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+6E800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+6F000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+6F800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+70000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+70800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+71000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+71800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+72000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+72800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+73000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+73800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+74000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+74800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+75000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+75800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+76000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+76800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+77000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+77800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+78000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+78800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+79000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+79800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+7A000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+7A800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+7B000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+7B800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+7C000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+7C800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+7D000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+7D800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+7E000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+7E800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+7F000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+7F800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+80000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+80800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+81000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+81800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+82000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+82800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+83000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+83800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+84000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+84800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+85000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+85800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+86000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+86800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+87000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+87800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+88000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+88800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+89000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+89800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+8A000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+8A800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+8B000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+8B800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+8C000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+8C800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+8D000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+8D800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+8E000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+8E800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+8F000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+8F800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+90000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+90800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+91000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+91800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+92000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+92800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+93000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+93800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+94000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+94800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+95000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+95800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+96000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+96800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+97000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+97800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+98000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+98800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+99000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+99800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+9A000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+9A800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+9B000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+9B800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+9C000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+9C800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+9D000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+9D800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+9E000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+9E800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+9F000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+9F800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A0000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A0800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A1000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A1800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A2000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A2800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A3000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A3800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A4000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A4800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A5000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A5800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A6000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A6800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A7000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A7800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A8000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A8800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A9000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+A9800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+AA000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+AA800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+AB000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+AB800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+AC000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+AC800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+AD000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+AD800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+AE000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+AE800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+AF000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+AF800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B0000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B0800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B1000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B1800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B2000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B2800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B3000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B3800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B4000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B4800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B5000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B5800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B6000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B6800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B7000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B7800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B8000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B8800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B9000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+B9800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+BA000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+BA800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+BB000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+BB800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+BC000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+BC800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+BD000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+BD800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+BE000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+BE800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+BF000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+BF800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C0000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C0800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C1000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C1800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C2000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C2800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C3000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C3800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C4000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C4800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C5000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C5800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C6000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C6800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C7000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C7800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C8000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C8800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C9000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+C9800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+CA000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+CA800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+CB000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+CB800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+CC000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+CC800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+CD000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+CD800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+CE000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+CE800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+CF000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+CF800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D0000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D0800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D1000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D1800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D2000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D2800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D3000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D3800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D4000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D4800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D5000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D5800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D6000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D6800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D7000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D7800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D8000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D8800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D9000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+D9800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+DA000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+DA800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+DB000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+DB800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+DC000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+DC800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+DD000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+DD800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+DE000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+DE800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+DF000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+DF800 */ -154, 16,155,156, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E0000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E0800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E1000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E1800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E2000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E2800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E3000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E3800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E4000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E4800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E5000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E5800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E6000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E6800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E7000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E7800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E8000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E8800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E9000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+E9800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+EA000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+EA800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+EB000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+EB800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+EC000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+EC800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+ED000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+ED800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+EE000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+EE800 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+EF000 */ - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, /* U+EF800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F0000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F0800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F1000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F1800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F2000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F2800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F3000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F3800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F4000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F4800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F5000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F5800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F6000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F6800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F7000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F7800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F8000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F8800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F9000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+F9800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+FA000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+FA800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+FB000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+FB800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+FC000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+FC800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+FD000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+FD800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+FE000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+FE800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+FF000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,157, /* U+FF800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+100000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+100800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+101000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+101800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+102000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+102800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+103000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+103800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+104000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+104800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+105000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+105800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+106000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+106800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+107000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+107800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+108000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+108800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+109000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+109800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+10A000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+10A800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+10B000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+10B800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+10C000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+10C800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+10D000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+10D800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+10E000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+10E800 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,110, /* U+10F000 */ -110,110,110,110,110,110,110,110,110,110,110,110,110,110,110,157, /* U+10F800 */ -}; - -const pcre_uint16 _pcre_ucd_stage2[] = { /* 40448 bytes, block = 128 */ -/* block 0 */ - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 1, 2, 2, 2, 3, 2, 2, 2, 4, 5, 2, 6, 2, 7, 2, 2, - 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 2, 2, 6, 6, 6, 2, - 2, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, - 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 4, 2, 5, 10, 11, - 10, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, - 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 4, 6, 5, 6, 0, - -/* block 1 */ - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 1, 2, 3, 3, 3, 3, 13, 13, 10, 13, 14, 15, 6, 16, 13, 10, - 13, 6, 17, 17, 10, 18, 13, 2, 10, 17, 14, 19, 17, 17, 17, 2, - 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, - 9, 9, 9, 9, 9, 9, 9, 6, 9, 9, 9, 9, 9, 9, 9, 14, - 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, - 12, 12, 12, 12, 12, 12, 12, 6, 12, 12, 12, 12, 12, 12, 12, 20, - -/* block 2 */ - 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, - 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, - 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, - 23, 24, 21, 22, 21, 22, 21, 22, 14, 21, 22, 21, 22, 21, 22, 21, - 22, 21, 22, 21, 22, 21, 22, 21, 22, 14, 21, 22, 21, 22, 21, 22, - 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, - 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, - 21, 22, 21, 22, 21, 22, 21, 22, 25, 21, 22, 21, 22, 21, 22, 26, - -/* block 3 */ - 27, 28, 21, 22, 21, 22, 29, 21, 22, 30, 30, 21, 22, 14, 31, 32, - 33, 21, 22, 30, 34, 35, 36, 37, 21, 22, 38, 14, 36, 39, 40, 41, - 21, 22, 21, 22, 21, 22, 42, 21, 22, 42, 14, 14, 21, 22, 42, 21, - 22, 43, 43, 21, 22, 21, 22, 44, 21, 22, 14, 45, 21, 22, 14, 46, - 45, 45, 45, 45, 47, 48, 49, 47, 48, 49, 47, 48, 49, 21, 22, 21, - 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 50, 21, 22, - 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, - 14, 47, 48, 49, 21, 22, 51, 52, 21, 22, 21, 22, 21, 22, 21, 22, - -/* block 4 */ - 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, - 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, - 53, 14, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, - 21, 22, 21, 22, 14, 14, 14, 14, 14, 14, 54, 21, 22, 55, 56, 14, - 14, 21, 22, 57, 58, 59, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, - 60, 61, 14, 62, 63, 14, 64, 64, 14, 65, 14, 66, 14, 14, 14, 14, - 64, 14, 14, 67, 14, 14, 14, 14, 68, 69, 14, 70, 14, 14, 14, 69, - 14, 71, 72, 14, 14, 73, 14, 14, 14, 14, 14, 14, 14, 74, 14, 14, - -/* block 5 */ - 75, 14, 14, 75, 14, 14, 14, 14, 75, 76, 77, 77, 78, 14, 14, 14, - 14, 14, 79, 14, 45, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, - 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, - 80, 80, 80, 80, 80, 80, 80, 80, 80, 81, 81, 81, 81, 81, 81, 81, - 81, 81, 10, 10, 10, 10, 81, 81, 81, 81, 81, 81, 81, 81, 81, 81, - 81, 81, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, - 80, 80, 80, 80, 80, 10, 10, 10, 10, 10, 10, 10, 81, 10, 81, 10, - 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, - -/* block 6 */ - 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, - 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, - 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, - 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, - 82, 82, 82, 82, 82, 83, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, - 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, - 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, - 84, 85, 84, 85, 81, 86, 84, 85, 87, 87, 88, 89, 89, 89, 2, 87, - -/* block 7 */ - 87, 87, 87, 87, 86, 10, 90, 2, 91, 91, 91, 87, 92, 87, 93, 93, - 94, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, - 95, 95, 87, 95, 95, 95, 95, 95, 95, 95, 95, 95, 96, 97, 97, 97, - 94, 98, 98, 98, 98, 98, 98, 98, 98, 98, 98, 98, 98, 98, 98, 98, - 98, 98, 99, 98, 98, 98, 98, 98, 98, 98, 98, 98,100,101,101,102, -103,104,105,105,105,106,107,108, 84, 85, 84, 85, 84, 85, 84, 85, - 84, 85,109,110,109,110,109,110,109,110,109,110,109,110,109,110, -111,112,113, 94,114,115,116, 84, 85,117, 84, 85, 94,118,118,118, - -/* block 8 */ -119,119,119,119,119,119,119,119,119,119,119,119,119,119,119,119, -120,120,120,120,120,120,120,120,120,120,120,120,120,120,120,120, -120,120,120,120,120,120,120,120,120,120,120,120,120,120,120,120, -121,121,121,121,121,121,121,121,121,121,121,121,121,121,121,121, -121,121,121,121,121,121,121,121,121,121,121,121,121,121,121,121, -122,122,122,122,122,122,122,122,122,122,122,122,122,122,122,122, -123,124,123,124,123,124,123,124,123,124,123,124,123,124,123,124, -123,124,123,124,123,124,123,124,123,124,123,124,123,124,123,124, - -/* block 9 */ -123,124,125,126,126,126,126,126,127,127,123,124,123,124,123,124, -123,124,123,124,123,124,123,124,123,124,123,124,123,124,123,124, -123,124,123,124,123,124,123,124,123,124,123,124,123,124,123,124, -123,124,123,124,123,124,123,124,123,124,123,124,123,124,123,124, -128,123,124,123,124,123,124,123,124,123,124,123,124,123,124,129, -123,124,123,124,123,124,123,124,123,124,123,124,123,124,123,124, -123,124,123,124,123,124,123,124,123,124,123,124,123,124,123,124, -123,124,123,124,123,124,123,124,123,124,123,124,123,124,123,124, - -/* block 10 */ -123,124,123,124,123,124,123,124,123,124,123,124,123,124,123,124, -123,124,123,124,123,124,123,124,123,124,123,124,123,124,123,124, -123,124,123,124, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87,130,130,130,130,130,130,130,130,130,130,130,130,130,130,130, -130,130,130,130,130,130,130,130,130,130,130,130,130,130,130,130, -130,130,130,130,130,130,130, 87, 87,131,132,132,132,132,132,132, - 87,133,133,133,133,133,133,133,133,133,133,133,133,133,133,133, -133,133,133,133,133,133,133,133,133,133,133,133,133,133,133,133, - -/* block 11 */ -133,133,133,133,133,133,133,134, 87, 2,135, 87, 87, 87, 87, 87, - 87,136,136,136,136,136,136,136,136,136,136,136,136,136,136,136, -136,136,136,136,136,136,136,136,136,136,136,136,136,136,136,136, -136,136,136,136,136,136,136,136,136,136,136,136,136,136,137,136, -138,136,136,138,136,136,138,136, 87, 87, 87, 87, 87, 87, 87, 87, -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, -139,139,139,139,139,139,139,139,139,139,139, 87, 87, 87, 87, 87, -139,139,139,138,138, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 12 */ - 16, 16, 16, 16, 87, 87,140,140,140,141,141,142, 2,141,143,143, -144,144,144,144,144,144,144,144,144,144,144, 2, 87, 87,141, 2, - 87,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, - 81,145,145,145,145,145,145,145,145,145,145, 82, 82, 82, 82, 82, - 82, 82, 82, 82, 82, 82,144,144,144,144,144,144,144,144,144, 87, - 8, 8, 8, 8, 8, 8, 8, 8, 8, 8,141,141,141,141,145,145, - 82,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, - -/* block 13 */ -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,141,145,144,144,144,144,144,144,144, 16,146,144, -144,144,144,144,144,147,147,144,144,143,144,144,144,144,145,145, -148,148,148,148,148,148,148,148,148,148,145,145,145,143,143,145, - -/* block 14 */ -149,149,149,149,149,149,149,149,149,149,149,149,149,149, 87,150, -151,152,151,151,151,151,151,151,151,151,151,151,151,151,151,151, -151,151,151,151,151,151,151,151,151,151,151,151,151,151,151,151, -152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152, -152,152,152,152,152,152,152,152,152,152,152, 87, 87,151,151,151, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, - -/* block 15 */ -153,153,153,153,153,153,153,153,153,153,153,153,153,153,153,153, -153,153,153,153,153,153,153,153,153,153,153,153,153,153,153,153, -153,153,153,153,153,153,154,154,154,154,154,154,154,154,154,154, -154,153, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, -155,155,155,155,155,155,155,155,155,155,156,156,156,156,156,156, -156,156,156,156,156,156,156,156,156,156,156,156,156,156,156,156, -156,156,156,156,156,156,156,156,156,156,156,157,157,157,157,157, -157,157,157,157,158,158,159,160,160,160,158, 87, 87, 87, 87, 87, - -/* block 16 */ - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 17 */ - 87,161,161,162,163,163,163,163,163,163,163,163,163,163,163,163, -163,163,163,163,163,163,163,163,163,163,163,163,163,163,163,163, -163,163,163,163,163,163,163,163,163,163,163,163,163,163,163,163, -163,163,163,163,163,163,163,163,163,163, 87, 87,161,163,162,162, -162,161,161,161,161,161,161,161,161,162,162,162,162,161, 87, 87, -163, 82, 82,161,161, 87, 87, 87,163,163,163,163,163,163,163,163, -163,163,161,161, 2, 2,164,164,164,164,164,164,164,164,164,164, - 2,165,163, 87, 87, 87, 87, 87, 87, 87, 87,163,163,163,163,163, - -/* block 18 */ - 87,166,167,167, 87,168,168,168,168,168,168,168,168, 87, 87,168, -168, 87, 87,168,168,168,168,168,168,168,168,168,168,168,168,168, -168,168,168,168,168,168,168,168,168, 87,168,168,168,168,168,168, -168, 87,168, 87, 87, 87,168,168,168,168, 87, 87,166,168,167,167, -167,166,166,166,166, 87, 87,167,167, 87, 87,167,167,166,168, 87, - 87, 87, 87, 87, 87, 87, 87,167, 87, 87, 87, 87,168,168, 87,168, -168,168,166,166, 87, 87,169,169,169,169,169,169,169,169,169,169, -168,168,170,170,171,171,171,171,171,171,172, 87, 87, 87, 87, 87, - -/* block 19 */ - 87,173,173,174, 87,175,175,175,175,175,175, 87, 87, 87, 87,175, -175, 87, 87,175,175,175,175,175,175,175,175,175,175,175,175,175, -175,175,175,175,175,175,175,175,175, 87,175,175,175,175,175,175, -175, 87,175,175, 87,175,175, 87,175,175, 87, 87,173, 87,174,174, -174,173,173, 87, 87, 87, 87,173,173, 87, 87,173,173,173, 87, 87, - 87,173, 87, 87, 87, 87, 87, 87, 87,175,175,175,175, 87,175, 87, - 87, 87, 87, 87, 87, 87,176,176,176,176,176,176,176,176,176,176, -173,173,175,175,175,173, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 20 */ - 87,177,177,178, 87,179,179,179,179,179,179,179,179,179, 87,179, -179,179, 87,179,179,179,179,179,179,179,179,179,179,179,179,179, -179,179,179,179,179,179,179,179,179, 87,179,179,179,179,179,179, -179, 87,179,179, 87,179,179,179,179,179, 87, 87,177,179,178,178, -178,177,177,177,177,177, 87,177,177,178, 87,178,178,177, 87, 87, -179, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, -179,179,177,177, 87, 87,180,180,180,180,180,180,180,180,180,180, - 87,181, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 21 */ - 87,182,183,183, 87,184,184,184,184,184,184,184,184, 87, 87,184, -184, 87, 87,184,184,184,184,184,184,184,184,184,184,184,184,184, -184,184,184,184,184,184,184,184,184, 87,184,184,184,184,184,184, -184, 87,184,184, 87,184,184,184,184,184, 87, 87,182,184,183,182, -183,182,182,182,182, 87, 87,183,183, 87, 87,183,183,182, 87, 87, - 87, 87, 87, 87, 87, 87,182,183, 87, 87, 87, 87,184,184, 87,184, -184,184,182,182, 87, 87,185,185,185,185,185,185,185,185,185,185, -186,184, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 22 */ - 87, 87,187,188, 87,188,188,188,188,188,188, 87, 87, 87,188,188, -188, 87,188,188,188,188, 87, 87, 87,188,188, 87,188, 87,188,188, - 87, 87, 87,188,188, 87, 87, 87,188,188,188, 87, 87, 87,188,188, -188,188,188,188,188,188,188,188,188,188, 87, 87, 87, 87,189,189, -187,189,189, 87, 87, 87,189,189,189, 87,189,189,189,187, 87, 87, -188, 87, 87, 87, 87, 87, 87,189, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87,190,190,190,190,190,190,190,190,190,190, -191,191,191,192,192,192,192,192,192,193,192, 87, 87, 87, 87, 87, - -/* block 23 */ - 87,194,194,194, 87,195,195,195,195,195,195,195,195, 87,195,195, -195, 87,195,195,195,195,195,195,195,195,195,195,195,195,195,195, -195,195,195,195,195,195,195,195,195, 87,195,195,195,195,195,195, -195,195,195,195, 87,195,195,195,195,195, 87, 87, 87,195,196,196, -196,194,194,194,194, 87,196,196,196, 87,196,196,196,196, 87, 87, - 87, 87, 87, 87, 87,196,196, 87,195,195, 87, 87, 87, 87, 87, 87, -195,195,196,196, 87, 87,197,197,197,197,197,197,197,197,197,197, - 87, 87, 87, 87, 87, 87, 87, 87,198,198,198,198,198,198,198,199, - -/* block 24 */ - 87, 87,200,200, 87,201,201,201,201,201,201,201,201, 87,201,201, -201, 87,201,201,201,201,201,201,201,201,201,201,201,201,201,201, -201,201,201,201,201,201,201,201,201, 87,201,201,201,201,201,201, -201,201,201,201, 87,201,201,201,201,201, 87, 87,202,201,200,202, -200,200,200,200,200, 87,202,200,200, 87,200,200,202,202, 87, 87, - 87, 87, 87, 87, 87,200,200, 87, 87, 87, 87, 87, 87, 87,201, 87, -201,201,202,202, 87, 87,203,203,203,203,203,203,203,203,203,203, - 87, 13, 13, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 25 */ - 87, 87,204,204, 87,205,205,205,205,205,205,205,205, 87,205,205, -205, 87,205,205,205,205,205,205,205,205,205,205,205,205,205,205, -205,205,205,205,205,205,205,205,205, 87,205,205,205,205,205,205, -205,205,205,205,205,205,205,205,205,205, 87, 87, 87,205,204,204, -204,206,206,206,206, 87,204,204,204, 87,204,204,204,206, 87, 87, - 87, 87, 87, 87, 87, 87, 87,204, 87, 87, 87, 87, 87, 87, 87, 87, -205,205,206,206, 87, 87,207,207,207,207,207,207,207,207,207,207, -208,208,208,208,208,208, 87, 87, 87,209,205,205,205,205,205,205, - -/* block 26 */ - 87, 87,210,210, 87,211,211,211,211,211,211,211,211,211,211,211, -211,211,211,211,211,211,211, 87, 87, 87,211,211,211,211,211,211, -211,211,211,211,211,211,211,211,211,211,211,211,211,211,211,211, -211,211, 87,211,211,211,211,211,211,211,211,211, 87,211, 87, 87, -211,211,211,211,211,211,211, 87, 87, 87,212, 87, 87, 87, 87,210, -210,210,212,212,212, 87,212, 87,210,210,210,210,210,210,210,210, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87,210,210,213, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 27 */ - 87,214,214,214,214,214,214,214,214,214,214,214,214,214,214,214, -214,214,214,214,214,214,214,214,214,214,214,214,214,214,214,214, -214,214,214,214,214,214,214,214,214,214,214,214,214,214,214,214, -214,215,214,214,215,215,215,215,215,215,215, 87, 87, 87, 87, 3, -214,214,214,214,214,214,216,215,215,215,215,215,215,215,215,217, -218,218,218,218,218,218,218,218,218,218,217,217, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 28 */ - 87,219,219, 87,219, 87, 87,219,219, 87,219, 87, 87,219, 87, 87, - 87, 87, 87, 87,219,219,219,219, 87,219,219,219,219,219,219,219, - 87,219,219,219, 87,219, 87,219, 87, 87,219,219, 87,219,219,219, -219,220,219,219,220,220,220,220,220,220, 87,220,220,219, 87, 87, -219,219,219,219,219, 87,221, 87,220,220,220,220,220,220, 87, 87, -222,222,222,222,222,222,222,222,222,222, 87, 87,219,219, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 29 */ -223,224,224,224,225,225,225,225,225,225,225,225,225,225,225,225, -225,225,225,224,224,224,224,224,226,226,224,224,224,224,224,224, -227,227,227,227,227,227,227,227,227,227,228,228,228,228,228,228, -228,228,228,228,224,226,224,226,224,226,229,230,229,230,231,231, -223,223,223,223,223,223,223,223, 87,223,223,223,223,223,223,223, -223,223,223,223,223,223,223,223,223,223,223,223,223,223,223,223, -223,223,223,223,223,223,223,223,223,223,223,223,223, 87, 87, 87, - 87,226,226,226,226,226,226,226,226,226,226,226,226,226,226,231, - -/* block 30 */ -226,226,226,226,226,225,226,226,223,223,223,223, 87, 87, 87, 87, -226,226,226,226,226,226,226,226, 87,226,226,226,226,226,226,226, -226,226,226,226,226,226,226,226,226,226,226,226,226,226,226,226, -226,226,226,226,226,226,226,226,226,226,226,226,226, 87,224,224, -224,224,224,224,224,224,226,224,224,224,224,224,224, 87,224,224, -225,225,225,225,225, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 31 */ -232,232,232,232,232,232,232,232,232,232,232,232,232,232,232,232, -232,232,232,232,232,232,232,232,232,232,232,232,232,232,232,232, -232,232,232,232,232,232,232,232,232,232,232,233,233,234,234,234, -234,233,234,234,234,234,234,234,233,234,234,233,233,234,234,232, -235,235,235,235,235,235,235,235,235,235,236,236,236,236,236,236, -232,232,232,232,232,232,233,233,234,234,232,232,232,232,234,234, -234,232,233,233,233,232,232,233,233,233,233,233,233,233,232,232, -232,234,234,234,234,232,232,232,232,232,232,232,232,232,232,232, - -/* block 32 */ -232,232,234,233,233,234,234,233,233,233,233,233,233,234,232,233, -235,235,235,235,235,235,235,235,235,235, 87, 87, 87, 87,237,237, -238,238,238,238,238,238,238,238,238,238,238,238,238,238,238,238, -238,238,238,238,238,238,238,238,238,238,238,238,238,238,238,238, -238,238,238,238,238,238, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, -239,239,239,239,239,239,239,239,239,239,239,239,239,239,239,239, -239,239,239,239,239,239,239,239,239,239,239,239,239,239,239,239, -239,239,239,239,239,239,239,239,239,239,239, 2,240, 87, 87, 87, - -/* block 33 */ -241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, -241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, -241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, -241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, -241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, -241,241,241,241,241,241,241,241,241,241, 87, 87, 87, 87, 87,241, -241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, -241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, - -/* block 34 */ -241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, -241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, -241,241,241, 87, 87, 87, 87, 87,241,241,241,241,241,241,241,241, -241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, -241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, -241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, -241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, -241,241,241,241,241,241,241,241,241,241, 87, 87, 87, 87, 87, 87, - -/* block 35 */ -242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, -242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, -242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, -242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, -242,242,242,242,242,242,242,242,242, 87,242,242,242,242, 87, 87, -242,242,242,242,242,242,242, 87,242, 87,242,242,242,242, 87, 87, -242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, -242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, - -/* block 36 */ -242,242,242,242,242,242,242,242,242, 87,242,242,242,242, 87, 87, -242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, -242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, -242, 87,242,242,242,242, 87, 87,242,242,242,242,242,242,242, 87, -242, 87,242,242,242,242, 87, 87,242,242,242,242,242,242,242,242, -242,242,242,242,242,242,242, 87,242,242,242,242,242,242,242,242, -242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, -242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, - -/* block 37 */ -242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, -242, 87,242,242,242,242, 87, 87,242,242,242,242,242,242,242,242, -242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, -242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, -242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, -242,242,242,242,242,242,242,242,242,242,242, 87, 87, 87, 87,243, -244,245,245,245,245,245,245,245,245,246,246,246,246,246,246,246, -246,246,246,246,246,246,246,246,246,246,246,246,246, 87, 87, 87, - -/* block 38 */ -242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, -244,244,244,244,244,244,244,244,244,244, 87, 87, 87, 87, 87, 87, -247,247,247,247,247,247,247,247,247,247,247,247,247,247,247,247, -247,247,247,247,247,247,247,247,247,247,247,247,247,247,247,247, -247,247,247,247,247,247,247,247,247,247,247,247,247,247,247,247, -247,247,247,247,247,247,247,247,247,247,247,247,247,247,247,247, -247,247,247,247,247,247,247,247,247,247,247,247,247,247,247,247, -247,247,247,247,247, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 39 */ - 87,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, -248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, -248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, -248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, -248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, -248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, -248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, -248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, - -/* block 40 */ -248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, -248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, -248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, -248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, -248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, -248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, -248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, -248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, - -/* block 41 */ -248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, -248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, -248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, -248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, -248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, -248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248, -248,248,248,248,248,248,248,248,248,248,248,248,248,249,249,248, -248,248,248,248,248,248,248, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 42 */ -250,251,251,251,251,251,251,251,251,251,251,251,251,251,251,251, -251,251,251,251,251,251,251,251,251,251,251,252,253, 87, 87, 87, -254,254,254,254,254,254,254,254,254,254,254,254,254,254,254,254, -254,254,254,254,254,254,254,254,254,254,254,254,254,254,254,254, -254,254,254,254,254,254,254,254,254,254,254,254,254,254,254,254, -254,254,254,254,254,254,254,254,254,254,254,254,254,254,254,254, -254,254,254,254,254,254,254,254,254,254,254, 2, 2, 2,255,255, -255, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 43 */ -256,256,256,256,256,256,256,256,256,256,256,256,256, 87,256,256, -256,256,257,257,257, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, -258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,258, -258,258,259,259,259, 2, 2, 87, 87, 87, 87, 87, 87, 87, 87, 87, -260,260,260,260,260,260,260,260,260,260,260,260,260,260,260,260, -260,260,261,261, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, -262,262,262,262,262,262,262,262,262,262,262,262,262, 87,262,262, -262, 87,263,263, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 44 */ -264,264,264,264,264,264,264,264,264,264,264,264,264,264,264,264, -264,264,264,264,264,264,264,264,264,264,264,264,264,264,264,264, -264,264,264,264,264,264,264,264,264,264,264,264,264,264,264,264, -264,264,264,264,265,265,266,267,267,267,267,267,267,267,266,266, -266,266,266,266,266,266,267,266,266,267,267,267,267,267,267,267, -267,267,267,267,268,268,268,269,268,268,268,270,264,267, 87, 87, -271,271,271,271,271,271,271,271,271,271, 87, 87, 87, 87, 87, 87, -272,272,272,272,272,272,272,272,272,272, 87, 87, 87, 87, 87, 87, - -/* block 45 */ -273,273, 2, 2,273, 2,274,273,273,273,273,275,275,275,276, 87, -277,277,277,277,277,277,277,277,277,277, 87, 87, 87, 87, 87, 87, -278,278,278,278,278,278,278,278,278,278,278,278,278,278,278,278, -278,278,278,278,278,278,278,278,278,278,278,278,278,278,278,278, -278,278,278,279,278,278,278,278,278,278,278,278,278,278,278,278, -278,278,278,278,278,278,278,278,278,278,278,278,278,278,278,278, -278,278,278,278,278,278,278,278,278,278,278,278,278,278,278,278, -278,278,278,278,278,278,278,278, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 46 */ -278,278,278,278,278,278,278,278,278,278,278,278,278,278,278,278, -278,278,278,278,278,278,278,278,278,278,278,278,278,278,278,278, -278,278,278,278,278,278,278,278,278,275,278, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 47 */ -280,280,280,280,280,280,280,280,280,280,280,280,280,280,280,280, -280,280,280,280,280,280,280,280,280,280,280,280,280, 87, 87, 87, -281,281,281,282,282,282,282,281,281,282,282,282, 87, 87, 87, 87, -282,282,281,282,282,282,282,282,282,281,281,281, 87, 87, 87, 87, -283, 87, 87, 87,284,284,285,285,285,285,285,285,285,285,285,285, -286,286,286,286,286,286,286,286,286,286,286,286,286,286,286,286, -286,286,286,286,286,286,286,286,286,286,286,286,286,286, 87, 87, -286,286,286,286,286, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 48 */ -287,287,287,287,287,287,287,287,287,287,287,287,287,287,287,287, -287,287,287,287,287,287,287,287,287,287,287,287,287,287,287,287, -287,287,287,287,287,287,287,287,287,287, 87, 87, 87, 87, 87, 87, -288,288,288,288,288,288,288,288,288,288,288,288,288,288,288,288, -288,287,287,287,287,287,287,287,288,288, 87, 87, 87, 87, 87, 87, -289,289,289,289,289,289,289,289,289,289, 87, 87, 87, 87,290,290, -291,291,291,291,291,291,291,291,291,291,291,291,291,291,291,291, -291,291,291,291,291,291,291,291,291,291,291,291,291,291,291,291, - -/* block 49 */ -292,292,292,292,292,292,292,292,292,292,292,292,292,292,292,292, -292,292,292,292,292,292,292,293,293,294,294,294, 87, 87,295,295, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 50 */ -296,296,296,296,297,298,298,298,298,298,298,298,298,298,298,298, -298,298,298,298,298,298,298,298,298,298,298,298,298,298,298,298, -298,298,298,298,298,298,298,298,298,298,298,298,298,298,298,298, -298,298,298,298,296,297,296,296,296,296,296,297,296,297,297,297, -297,297,296,297,297,298,298,298,298,298,298,298, 87, 87, 87, 87, -299,299,299,299,299,299,299,299,299,299,300,300,300,300,300,300, -300,301,301,301,301,301,301,301,301,301,301,296,296,296,296,296, -296,296,296,296,301,301,301,301,301,301,301,301,301, 87, 87, 87, - -/* block 51 */ -302,302,303,304,304,304,304,304,304,304,304,304,304,304,304,304, -304,304,304,304,304,304,304,304,304,304,304,304,304,304,304,304, -304,303,302,302,302,302,303,303,302,302,303, 87, 87, 87,304,304, -305,305,305,305,305,305,305,305,305,305, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 52 */ -306,306,306,306,306,306,306,306,306,306,306,306,306,306,306,306, -306,306,306,306,306,306,306,306,306,306,306,306,306,306,306,306, -306,306,306,306,307,307,307,307,307,307,307,307,308,308,308,308, -308,308,308,308,307,307,308,308, 87, 87, 87,309,309,309,309,309, -310,310,310,310,310,310,310,310,310,310, 87, 87, 87,306,306,306, -311,311,311,311,311,311,311,311,311,311,312,312,312,312,312,312, -312,312,312,312,312,312,312,312,312,312,312,312,312,312,312,312, -312,312,312,312,312,312,312,312,313,313,313,313,313,313,314,314, - -/* block 53 */ - 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, - 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, - 14, 14, 14, 14, 14, 14, 94, 94, 94, 94, 94,315, 80, 80, 80, 80, - 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, - 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, - 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 88, 88, 88, - 88, 88, 14, 14, 14, 14, 94, 94, 94, 94, 94, 14, 14, 14, 14, 14, - 14, 14, 14, 14, 14, 14, 14, 14,316,317, 14, 14, 14,318, 14, 14, - -/* block 54 */ - 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, - 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 80, 80, 80, 80, 80, - 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, - 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 88, - 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, - 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, - 82, 82, 82, 82, 82, 82, 82, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 82, 82, - -/* block 55 */ - 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, - 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, - 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, - 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, - 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, - 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, - 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, - 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, - -/* block 56 */ - 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, - 21, 22, 21, 22, 21, 22, 14, 14, 14, 14, 14,319, 14, 14,320, 14, - 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, - 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, - 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, - 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, - 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, - 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, - -/* block 57 */ -321,321,321,321,321,321,321,321,322,322,322,322,322,322,322,322, -321,321,321,321,321,321, 87, 87,322,322,322,322,322,322, 87, 87, -321,321,321,321,321,321,321,321,322,322,322,322,322,322,322,322, -321,321,321,321,321,321,321,321,322,322,322,322,322,322,322,322, -321,321,321,321,321,321, 87, 87,322,322,322,322,322,322, 87, 87, - 94,321, 94,321, 94,321, 94,321, 87,322, 87,322, 87,322, 87,322, -321,321,321,321,321,321,321,321,322,322,322,322,322,322,322,322, -323,323,324,324,324,324,325,325,326,326,327,327,328,328, 87, 87, - -/* block 58 */ -321,321,321,321,321,321,321,321,329,329,329,329,329,329,329,329, -321,321,321,321,321,321,321,321,329,329,329,329,329,329,329,329, -321,321,321,321,321,321,321,321,329,329,329,329,329,329,329,329, -321,321, 94,330, 94, 87, 94, 94,322,322,331,331,332, 86,333, 86, - 86, 86, 94,330, 94, 87, 94, 94,334,334,334,334,332, 86, 86, 86, -321,321, 94, 94, 87, 87, 94, 94,322,322,335,335, 87, 86, 86, 86, -321,321, 94, 94, 94,113, 94, 94,322,322,336,336,117, 86, 86, 86, - 87, 87, 94,330, 94, 87, 94, 94,337,337,338,338,332, 86, 86, 87, - -/* block 59 */ - 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 16,339,339, 16, 16, - 7, 7, 7, 7, 7, 7, 2, 2, 15, 19, 4, 15, 15, 19, 4, 15, - 2, 2, 2, 2, 2, 2, 2, 2,340,341, 16, 16, 16, 16, 16, 1, - 2, 2, 2, 2, 2, 2, 2, 2, 2, 15, 19, 2, 2, 2, 2, 11, - 11, 2, 2, 2, 6, 4, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, - 2, 2, 6, 2, 11, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, - 16, 16, 16, 16, 16, 87, 87, 87, 87, 87, 16, 16, 16, 16, 16, 16, - 17, 14, 87, 87, 17, 17, 17, 17, 17, 17, 6, 6, 6, 4, 5, 14, - -/* block 60 */ - 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 6, 6, 6, 4, 5, 87, - 80, 80, 80, 80, 80, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, - 3, 3, 3, 3, 3, 3, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82,342,342,342, -342, 82,342,342,342, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, - 82, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 61 */ - 13, 13,343, 13, 13, 13, 13,343, 13, 13,344,343,343,343,344,344, -343,343,343,344, 13,343, 13, 13, 13,343,343,343,343,343, 13, 13, - 13, 13, 13, 13,343, 13,345, 13,343, 13,346,347,343,343, 13,344, -343,343,348,343,344,349,349,349,349,344, 13, 13,344,344,343,343, - 6, 6, 6, 6, 6,343,344,344,344,344, 13, 6, 13, 13,350, 13, - 87, 87, 87, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, -351,351,351,351,351,351,351,351,351,351,351,351,351,351,351,351, -352,352,352,352,352,352,352,352,352,352,352,352,352,352,352,352, - -/* block 62 */ -353,353,353, 21, 22,353,353,353,353, 87, 87, 87, 87, 87, 87, 87, - 6, 6, 6, 6, 6, 13, 13, 13, 13, 13, 6, 6, 13, 13, 13, 13, - 6, 13, 13, 6, 13, 13, 6, 13, 13, 13, 13, 13, 13, 13, 6, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 6, 6, - 13, 13, 6, 13, 6, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, - -/* block 63 */ - 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, - 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, - 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, - 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, - 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, - 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, - 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, - 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, - -/* block 64 */ - 13, 13, 13, 13, 13, 13, 13, 13, 6, 6, 6, 6, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 6, 6, 13, 13, 13, 13, 13, 13, 13, 4, 5, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 6, 13, 13, 13, - -/* block 65 */ - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 6, 6, 6, 6, 6, - 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, - 6, 6, 6, 6, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 6, 6, 6, 6, - 6, 6, 13, 13, 13, 13, 13, 13, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 66 */ - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, - 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, - -/* block 67 */ - 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, - 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13,354,354,354,354,354,354,354,354,354,354, -354,354,354,354,354,354,354,354,354,354,354,354,354,354,354,354, -355,355,355,355,355,355,355,355,355,355,355,355,355,355,355,355, -355,355,355,355,355,355,355,355,355,355, 17, 17, 17, 17, 17, 17, - 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, - -/* block 68 */ - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - -/* block 69 */ - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 6, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 6, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 6, 6, 6, 6, 6, 6, 6, 6, - -/* block 70 */ - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 6, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - -/* block 71 */ - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 87, 87, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 87, 87, 87, - 13, 13, 13, 13, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 72 */ - 87, 13, 13, 13, 13, 87, 13, 13, 13, 13, 87, 87, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 87, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 87, 13, 87, 13, - 13, 13, 13, 87, 87, 87, 13, 87, 13, 13, 13, 13, 13, 13, 13, 87, - 87, 13, 13, 13, 13, 13, 13, 13, 4, 5, 4, 5, 4, 5, 4, 5, - 4, 5, 4, 5, 4, 5, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, - -/* block 73 */ - 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, - 17, 17, 17, 17, 13, 87, 87, 87, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 87, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 87, - 6, 6, 6, 6, 6, 4, 5, 6, 6, 6, 6, 87, 6, 87, 87, 87, - 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, - 6, 6, 6, 6, 6, 6, 4, 5, 4, 5, 4, 5, 4, 5, 4, 5, - 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, - -/* block 74 */ -356,356,356,356,356,356,356,356,356,356,356,356,356,356,356,356, -356,356,356,356,356,356,356,356,356,356,356,356,356,356,356,356, -356,356,356,356,356,356,356,356,356,356,356,356,356,356,356,356, -356,356,356,356,356,356,356,356,356,356,356,356,356,356,356,356, -356,356,356,356,356,356,356,356,356,356,356,356,356,356,356,356, -356,356,356,356,356,356,356,356,356,356,356,356,356,356,356,356, -356,356,356,356,356,356,356,356,356,356,356,356,356,356,356,356, -356,356,356,356,356,356,356,356,356,356,356,356,356,356,356,356, - -/* block 75 */ - 6, 6, 6, 4, 5, 4, 5, 4, 5, 4, 5, 4, 5, 4, 5, 4, - 5, 4, 5, 4, 5, 4, 5, 4, 5, 6, 6, 6, 6, 6, 6, 6, - 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, - 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, - 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, - 6, 6, 6, 6, 6, 6, 6, 6, 4, 5, 4, 5, 6, 6, 6, 6, - 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, - 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 4, 5, 6, 6, - -/* block 76 */ - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, - 6, 6, 6, 6, 6, 13, 13, 6, 6, 6, 6, 6, 6, 87, 87, 87, - 13, 13, 13, 13, 13, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 77 */ -357,357,357,357,357,357,357,357,357,357,357,357,357,357,357,357, -357,357,357,357,357,357,357,357,357,357,357,357,357,357,357,357, -357,357,357,357,357,357,357,357,357,357,357,357,357,357,357, 87, -358,358,358,358,358,358,358,358,358,358,358,358,358,358,358,358, -358,358,358,358,358,358,358,358,358,358,358,358,358,358,358,358, -358,358,358,358,358,358,358,358,358,358,358,358,358,358,358, 87, - 21, 22,359,360,361,362,363, 21, 22, 21, 22, 21, 22,364,365,366, - 87, 14, 21, 22, 14, 21, 22, 14, 14, 14, 14, 14, 14, 80, 87, 87, - -/* block 78 */ -109,110,109,110,109,110,109,110,109,110,109,110,109,110,109,110, -109,110,109,110,109,110,109,110,109,110,109,110,109,110,109,110, -109,110,109,110,109,110,109,110,109,110,109,110,109,110,109,110, -109,110,109,110,109,110,109,110,109,110,109,110,109,110,109,110, -109,110,109,110,109,110,109,110,109,110,109,110,109,110,109,110, -109,110,109,110,109,110,109,110,109,110,109,110,109,110,109,110, -109,110,109,110,367,368,368,368,368,368,368, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87,369,369,369,369,370,369,369, - -/* block 79 */ -371,371,371,371,371,371,371,371,371,371,371,371,371,371,371,371, -371,371,371,371,371,371,371,371,371,371,371,371,371,371,371,371, -371,371,371,371,371,371, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, -372,372,372,372,372,372,372,372,372,372,372,372,372,372,372,372, -372,372,372,372,372,372,372,372,372,372,372,372,372,372,372,372, -372,372,372,372,372,372,372,372,372,372,372,372,372,372,372,372, -372,372,372,372,372,372, 87, 87, 87, 87, 87, 87, 87, 87, 87,373, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 80 */ -242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242, -242,242,242,242,242,242,242, 87, 87, 87, 87, 87, 87, 87, 87, 87, -242,242,242,242,242,242,242, 87,242,242,242,242,242,242,242, 87, -242,242,242,242,242,242,242, 87,242,242,242,242,242,242,242, 87, -242,242,242,242,242,242,242, 87,242,242,242,242,242,242,242, 87, -242,242,242,242,242,242,242, 87,242,242,242,242,242,242,242, 87, -126,126,126,126,126,126,126,126,126,126,126,126,126,126,126,126, -126,126,126,126,126,126,126,126,126,126,126,126,126,126,126,126, - -/* block 81 */ - 2, 2, 15, 19, 15, 19, 2, 2, 2, 15, 19, 2, 15, 19, 2, 2, - 2, 2, 2, 2, 2, 2, 2, 7, 2, 2, 7, 2, 15, 19, 2, 2, - 15, 19, 4, 5, 4, 5, 4, 5, 4, 5, 2, 2, 2, 2, 2, 81, - 2, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 82 */ -374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, -374,374,374,374,374,374,374,374,374,374, 87,374,374,374,374,374, -374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, -374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, -374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, -374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, -374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, -374,374,374,374, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 83 */ -374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, -374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, -374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, -374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, -374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, -374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, -374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, -374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, - -/* block 84 */ -374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, -374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, -374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, -374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, -374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374, -374,374,374,374,374,374, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 87, 87, 87, 87, - -/* block 85 */ - 1, 2, 2, 2, 13,375,349,376, 4, 5, 4, 5, 4, 5, 4, 5, - 4, 5, 13, 13, 4, 5, 4, 5, 4, 5, 4, 5, 7, 4, 5, 5, - 13,376,376,376,376,376,376,376,376,376, 82, 82, 82, 82, 82, 82, - 7, 81, 81, 81, 81, 81, 13, 13,376,376,376,375,349, 2, 13, 13, - 87,377,377,377,377,377,377,377,377,377,377,377,377,377,377,377, -377,377,377,377,377,377,377,377,377,377,377,377,377,377,377,377, -377,377,377,377,377,377,377,377,377,377,377,377,377,377,377,377, -377,377,377,377,377,377,377,377,377,377,377,377,377,377,377,377, - -/* block 86 */ -377,377,377,377,377,377,377,377,377,377,377,377,377,377,377,377, -377,377,377,377,377,377,377, 87, 87, 82, 82, 10, 10,378,378,377, - 7,379,379,379,379,379,379,379,379,379,379,379,379,379,379,379, -379,379,379,379,379,379,379,379,379,379,379,379,379,379,379,379, -379,379,379,379,379,379,379,379,379,379,379,379,379,379,379,379, -379,379,379,379,379,379,379,379,379,379,379,379,379,379,379,379, -379,379,379,379,379,379,379,379,379,379,379,379,379,379,379,379, -379,379,379,379,379,379,379,379,379,379,379, 2, 81,380,380,379, - -/* block 87 */ - 87, 87, 87, 87, 87,381,381,381,381,381,381,381,381,381,381,381, -381,381,381,381,381,381,381,381,381,381,381,381,381,381,381,381, -381,381,381,381,381,381,381,381,381,381,381,381,381,381, 87, 87, - 87,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, -241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, -241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, -241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, -241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, - -/* block 88 */ -241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, 87, - 13, 13, 17, 17, 17, 17, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, -381,381,381,381,381,381,381,381,381,381,381,381,381,381,381,381, -381,381,381,381,381,381,381,381, 87, 87, 87, 87, 87, 87, 87, 87, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, -379,379,379,379,379,379,379,379,379,379,379,379,379,379,379,379, - -/* block 89 */ -382,382,382,382,382,382,382,382,382,382,382,382,382,382,382,382, -382,382,382,382,382,382,382,382,382,382,382,382,382,382,382, 87, - 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 13, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, -382,382,382,382,382,382,382,382,382,382,382,382,382,382,382,382, -382,382,382,382,382,382,382,382,382,382,382,382,382,382,382, 13, - -/* block 90 */ - 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, -383,383,383,383,383,383,383,383,383,383,383,383,383,383,383,383, -383,383,383,383,383,383,383,383,383,383,383,383,383,383,383,383, -383,383,383,383,383,383,383,383,383,383,383,383,383,383,383, 87, - -/* block 91 */ -383,383,383,383,383,383,383,383,383,383,383,383,383,383,383,383, -383,383,383,383,383,383,383,383,383,383,383,383,383,383,383,383, -383,383,383,383,383,383,383,383,383,383,383,383,383,383,383,383, -383,383,383,383,383,383,383,383,383,383,383,383,383,383,383,383, -383,383,383,383,383,383,383,383,383,383,383,383,383,383,383,383, -383,383,383,383,383,383,383,383, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - -/* block 92 */ -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, - -/* block 93 */ -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, -384,384,384,384,384,384, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - -/* block 94 */ -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, -384,384,384,384, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 95 */ -385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, -385,385,385,385,385,386,385,385,385,385,385,385,385,385,385,385, -385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, -385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, -385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, -385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, -385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, -385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, - -/* block 96 */ -385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, -385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, -385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, -385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, -385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, -385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, -385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, -385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385, - -/* block 97 */ -385,385,385,385,385,385,385,385,385,385,385,385,385, 87, 87, 87, -387,387,387,387,387,387,387,387,387,387,387,387,387,387,387,387, -387,387,387,387,387,387,387,387,387,387,387,387,387,387,387,387, -387,387,387,387,387,387,387,387,387,387,387,387,387,387,387,387, -387,387,387,387,387,387,387, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 98 */ -388,388,388,388,388,388,388,388,388,388,388,388,388,388,388,388, -388,388,388,388,388,388,388,388,388,388,388,388,388,388,388,388, -388,388,388,388,388,388,388,388,388,388,388,388,388,388,388,388, -388,388,388,388,388,388,388,388,388,388,388,388,388,388,388,388, -388,388,388,388,388,388,388,388,388,388,388,388,388,388,388,388, -388,388,388,388,388,388,388,388,388,388,388,388,388,388,388,388, -388,388,388,388,388,388,388,388,388,388,388,388,388,388,388,388, -388,388,388,388,388,388,388,388,388,388,388,388,388,388,388,388, - -/* block 99 */ -388,388,388,388,388,388,388,388,388,388,388,388,389,390,390,390, -388,388,388,388,388,388,388,388,388,388,388,388,388,388,388,388, -391,391,391,391,391,391,391,391,391,391,388,388, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, -123,124,123,124,123,124,123,124,123,124,123,124,123,124,123,124, -123,124,123,124,123,124,123,124,123,124,123,124,123,124,123,124, - 87, 87,123,124,123,124,123,124,123,124,123,124,123,124,392,126, -127,127,127,393, 87, 87, 87, 87, 87, 87, 87, 87,126,126,393,316, - -/* block 100 */ -123,124,123,124,123,124,123,124,123,124,123,124,123,124,123,124, -123,124,123,124,123,124,123,124, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 101 */ - 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, - 10, 10, 10, 10, 10, 10, 10, 81, 81, 81, 81, 81, 81, 81, 81, 81, - 10, 10, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, - 14, 14, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, - 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, - 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, - 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, 21, 22, - 80, 14, 14, 14, 14, 14, 14, 14, 14, 21, 22, 21, 22,394, 21, 22, - -/* block 102 */ - 21, 22, 21, 22, 21, 22, 21, 22, 81, 10, 10, 21, 22, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 45, 45, 45, 45, 45, - -/* block 103 */ -395,395,396,395,395,395,396,395,395,395,395,396,395,395,395,395, -395,395,395,395,395,395,395,395,395,395,395,395,395,395,395,395, -395,395,395,397,397,396,396,397,398,398,398,398, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, -399,399,399,399,399,399,399,399,399,399,399,399,399,399,399,399, -399,399,399,399,399,399,399,399,399,399,399,399,399,399,399,399, -399,399,399,399,399,399,399,399,399,399,399,399,399,399,399,399, -399,399,399,399,400,400,400,400, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 104 */ -401,401,402,402,402,402,402,402,402,402,402,402,402,402,402,402, -402,402,402,402,402,402,402,402,402,402,402,402,402,402,402,402, -402,402,402,402,402,402,402,402,402,402,402,402,402,402,402,402, -402,402,402,402,401,401,401,401,401,401,401,401,401,401,401,401, -401,401,401,401,403, 87, 87, 87, 87, 87, 87, 87, 87, 87,404,404, -405,405,405,405,405,405,405,405,405,405, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 105 */ -406,406,406,406,406,406,406,406,406,406,407,407,407,407,407,407, -407,407,407,407,407,407,407,407,407,407,407,407,407,407,407,407, -407,407,407,407,407,407,408,408,408,408,408,408,408,408,409,409, -410,410,410,410,410,410,410,410,410,410,410,410,410,410,410,410, -410,410,410,410,410,410,410,411,411,411,411,411,411,411,411,411, -411,411,412,412, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87,413, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 106 */ -414,414,414,414,414,414,414,414,414,414,414,414,414,414,414,414, -414,414,414,414,414,414,414,414,414,414,414,414,414,414,414,414, -414,414,414,414,414,414,414,414,414,415,415,415,415,415,415,416, -416,415,415,416,416,415,415, 87, 87, 87, 87, 87, 87, 87, 87, 87, -414,414,414,415,414,414,414,414,414,414,414,414,415,416, 87, 87, -417,417,417,417,417,417,417,417,417,417, 87, 87,418,418,418,418, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 107 */ -241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, -241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, -241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, -241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, -241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, -241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, -241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, -241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, - -/* block 108 */ -241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, -241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, -241,241,241,241, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 109 */ -419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419, -419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419, -419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419, -419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419, -419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419, -419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419, -419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419, -419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419, - -/* block 110 */ -420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420, -420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420, -420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420, -420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420, -420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420, -420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420, -420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420, -420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420, - -/* block 111 */ -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, -384,384,384,384,384,384,384,384,384,384,384,384,384,384, 87, 87, -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, -384,384,384,384,384,384,384,384,384,384,384, 87, 87, 87, 87, 87, -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, - -/* block 112 */ -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, -384,384,384,384,384,384,384,384,384,384, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 113 */ - 14, 14, 14, 14, 14, 14, 14, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87,134,134,134,134,134, 87, 87, 87, 87, 87,139,136,139, -139,139,139,139,139,139,139,139,139,421,139,139,139,139,139,139, -139,139,139,139,139,139,139, 87,139,139,139,139,139, 87,139, 87, -139,139, 87,139,139, 87,139,139,139,139,139,139,139,139,139,139, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, - -/* block 114 */ -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, - -/* block 115 */ -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, - -/* block 116 */ -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145, 4, 5, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, - -/* block 117 */ -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, - 87, 87,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, -145,145,145,145,145,145,145,145,145,145,145,145,142, 13, 87, 87, - -/* block 118 */ - 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, - 2, 2, 2, 2, 2, 2, 2, 4, 5, 2, 87, 87, 87, 87, 87, 87, - 82, 82, 82, 82, 82, 82, 82, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 2, 7, 7, 11, 11, 4, 5, 4, 5, 4, 5, 4, 5, 4, 5, 4, - 5, 4, 5, 4, 5, 2, 2, 4, 5, 2, 2, 2, 2, 11, 11, 11, - 2, 2, 2, 87, 2, 2, 2, 2, 7, 4, 5, 4, 5, 4, 5, 2, - 2, 2, 6, 7, 6, 6, 6, 87, 2, 3, 2, 2, 87, 87, 87, 87, -145,145,145,145,145, 87,145,145,145,145,145,145,145,145,145,145, - -/* block 119 */ -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145, -145,145,145,145,145,145,145,145,145,145,145,145,145, 87, 87, 16, - -/* block 120 */ - 87, 2, 2, 2, 3, 2, 2, 2, 4, 5, 2, 6, 2, 7, 2, 2, - 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 2, 2, 6, 6, 6, 2, - 2, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, - 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 4, 2, 5, 10, 11, - 10, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, - 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 4, 6, 5, 6, 4, - 5, 2, 4, 5, 2, 2,379,379,379,379,379,379,379,379,379,379, - 81,379,379,379,379,379,379,379,379,379,379,379,379,379,379,379, - -/* block 121 */ -379,379,379,379,379,379,379,379,379,379,379,379,379,379,379,379, -379,379,379,379,379,379,379,379,379,379,379,379,379,379, 81, 81, -241,241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, -241,241,241,241,241,241,241,241,241,241,241,241,241,241,241, 87, - 87, 87,241,241,241,241,241,241, 87, 87,241,241,241,241,241,241, - 87, 87,241,241,241,241,241,241, 87, 87,241,241,241, 87, 87, 87, - 3, 3, 6, 10, 13, 3, 3, 87, 13, 6, 6, 6, 6, 13, 13, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 16, 16, 16, 13, 13, 87, 87, - -/* block 122 */ -422,422,422,422,422,422,422,422,422,422,422,422, 87,422,422,422, -422,422,422,422,422,422,422,422,422,422,422,422,422,422,422,422, -422,422,422,422,422,422,422, 87,422,422,422,422,422,422,422,422, -422,422,422,422,422,422,422,422,422,422,422, 87,422,422, 87,422, -422,422,422,422,422,422,422,422,422,422,422,422,422,422, 87, 87, -422,422,422,422,422,422,422,422,422,422,422,422,422,422, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 123 */ -422,422,422,422,422,422,422,422,422,422,422,422,422,422,422,422, -422,422,422,422,422,422,422,422,422,422,422,422,422,422,422,422, -422,422,422,422,422,422,422,422,422,422,422,422,422,422,422,422, -422,422,422,422,422,422,422,422,422,422,422,422,422,422,422,422, -422,422,422,422,422,422,422,422,422,422,422,422,422,422,422,422, -422,422,422,422,422,422,422,422,422,422,422,422,422,422,422,422, -422,422,422,422,422,422,422,422,422,422,422,422,422,422,422,422, -422,422,422,422,422,422,422,422,422,422,422, 87, 87, 87, 87, 87, - -/* block 124 */ - 2, 2, 13, 87, 87, 87, 87, 17, 17, 17, 17, 17, 17, 17, 17, 17, - 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, - 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, - 17, 17, 17, 17, 87, 87, 87, 13, 13, 13, 13, 13, 13, 13, 13, 13, -423,423,423,423,423,423,423,423,423,423,423,423,423,423,423,423, -423,423,423,423,423,423,423,423,423,423,423,423,423,423,423,423, -423,423,423,423,423,423,423,423,423,423,423,423,423,423,423,423, -423,423,423,423,423,424,424,424,424,425,425,425,425,425,425,425, - -/* block 125 */ -425,425,425,425,425,425,425,425,425,425,424, 87, 87, 87, 87, 87, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 82, 87, 87, - -/* block 126 */ -426,426,426,426,426,426,426,426,426,426,426,426,426,426,426,426, -426,426,426,426,426,426,426,426,426,426,426,426,426, 87, 87, 87, -427,427,427,427,427,427,427,427,427,427,427,427,427,427,427,427, -427,427,427,427,427,427,427,427,427,427,427,427,427,427,427,427, -427,427,427,427,427,427,427,427,427,427,427,427,427,427,427,427, -427, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 127 */ -428,428,428,428,428,428,428,428,428,428,428,428,428,428,428,428, -428,428,428,428,428,428,428,428,428,428,428,428,428,428,428, 87, -429,429,429,429, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, -430,430,430,430,430,430,430,430,430,430,430,430,430,430,430,430, -430,431,430,430,430,430,430,430,430,430,431, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 128 */ -432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,432, -432,432,432,432,432,432,432,432,432,432,432,432,432,432, 87,433, -434,434,434,434,434,434,434,434,434,434,434,434,434,434,434,434, -434,434,434,434,434,434,434,434,434,434,434,434,434,434,434,434, -434,434,434,434, 87, 87, 87, 87,434,434,434,434,434,434,434,434, -435,436,436,436,436,436, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 129 */ -437,437,437,437,437,437,437,437,437,437,437,437,437,437,437,437, -437,437,437,437,437,437,437,437,437,437,437,437,437,437,437,437, -437,437,437,437,437,437,437,437,438,438,438,438,438,438,438,438, -438,438,438,438,438,438,438,438,438,438,438,438,438,438,438,438, -438,438,438,438,438,438,438,438,438,438,438,438,438,438,438,438, -439,439,439,439,439,439,439,439,439,439,439,439,439,439,439,439, -439,439,439,439,439,439,439,439,439,439,439,439,439,439,439,439, -439,439,439,439,439,439,439,439,439,439,439,439,439,439,439,439, - -/* block 130 */ -440,440,440,440,440,440,440,440,440,440,440,440,440,440,440,440, -440,440,440,440,440,440,440,440,440,440,440,440,440,440, 87, 87, -441,441,441,441,441,441,441,441,441,441, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 131 */ -442,442,442,442,442,442, 87, 87,442, 87,442,442,442,442,442,442, -442,442,442,442,442,442,442,442,442,442,442,442,442,442,442,442, -442,442,442,442,442,442,442,442,442,442,442,442,442,442,442,442, -442,442,442,442,442,442, 87,442,442, 87, 87, 87,442, 87, 87,442, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 132 */ -443,443,443,443,443,443,443,443,443,443,443,443,443,443,443,443, -443,443,443,443,443,443,444,444,444,444, 87, 87, 87, 87, 87,445, -446,446,446,446,446,446,446,446,446,446,446,446,446,446,446,446, -446,446,446,446,446,446,446,446,446,446, 87, 87, 87, 87, 87,447, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 133 */ -448,449,449,449, 87,449,449, 87, 87, 87, 87, 87,449,449,449,449, -448,448,448,448, 87,448,448,448, 87,448,448,448,448,448,448,448, -448,448,448,448,448,448,448,448,448,448,448,448,448,448,448,448, -448,448,448,448, 87, 87, 87, 87,449,449,449, 87, 87, 87, 87,449, -450,450,450,450,450,450,450,450, 87, 87, 87, 87, 87, 87, 87, 87, -451,451,451,451,451,451,451,451,451, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 134 */ -452,452,452,452,452,452,452,452,452,452,452,452,452,452,452,452, -452,452,452,452,452,452,452,452,452,452,452,452,452,452,452,452, -452,452,452,452,452,452,452,452,452,452,452,452,452,452,452,452, -452,452,452,452,452,452,452,452,452,452,452,452,452,452,452,452, -452,452,452,452,452,452,452,452,452,452,452,452,452,452,452,452, -452,452,452,452,452,452,452,452,452,452,452,452,452,452,452,452, -452,452,452,452,452,452,452,452,452,452,452,452,452,452,452,452, -452,452,452,452,452,452,452,452,452,452,452,452,452,452,452,452, - -/* block 135 */ -452,452,452,452,452,452,452,452,452,452,452,452,452,452,452,452, -452,452,452,452,452,452,452,452,452,452,452,452,452,452,452,452, -452,452,452,452,452,452,452,452,452,452,452,452,452,452,452,452, -452,452,452,452,452,452,452,452,452,452,452,452,452,452,452,452, -452,452,452,452,452,452,452,452,452,452,452,452,452,452,452,452, -452,452,452,452,452,452,452,452,452,452,452,452,452,452,452,452, -452,452,452,452,452,452,452,452,452,452,452,452,452,452,452, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 136 */ -453,453,453,453,453,453,453,453,453,453,453,453,453,453,453,453, -453,453,453,453,453,453,453,453,453,453,453,453,453,453,453,453, -453,453,453,453,453,453,453,453,453,453,453,453,453,453,453,453, -453,453,453,453,453,453,453,453,453,453,453,453,453,453,453,453, -453,453,453,453,453,453,453,453,453,453,453,453,453,453,453,453, -453,453,453,453,453,453,453,453,453,453,453,453,453,453,453,453, -453,453,453, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, -454,454,454,454, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 137 */ - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 138 */ - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 87, 87, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13,455,455, 82, 82, 82, 13, 13, 13,455,455,455, -455,455,455, 16, 16, 16, 16, 16, 16, 16, 16, 82, 82, 82, 82, 82, - -/* block 139 */ - 82, 82, 82, 13, 13, 82, 82, 82, 82, 82, 82, 82, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 82, 82, 82, 82, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 140 */ -425,425,425,425,425,425,425,425,425,425,425,425,425,425,425,425, -425,425,425,425,425,425,425,425,425,425,425,425,425,425,425,425, -425,425,425,425,425,425,425,425,425,425,425,425,425,425,425,425, -425,425,425,425,425,425,425,425,425,425,425,425,425,425,425,425, -425,425,456,456,456,425, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 141 */ - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, - 17, 17, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 142 */ -343,343,343,343,343,343,343,343,343,343,343,343,343,343,343,343, -343,343,343,343,343,343,343,343,343,343,344,344,344,344,344,344, -344,344,344,344,344,344,344,344,344,344,344,344,344,344,344,344, -344,344,344,344,343,343,343,343,343,343,343,343,343,343,343,343, -343,343,343,343,343,343,343,343,343,343,343,343,343,343,344,344, -344,344,344,344,344, 87,344,344,344,344,344,344,344,344,344,344, -344,344,344,344,344,344,344,344,343,343,343,343,343,343,343,343, -343,343,343,343,343,343,343,343,343,343,343,343,343,343,343,343, - -/* block 143 */ -343,343,344,344,344,344,344,344,344,344,344,344,344,344,344,344, -344,344,344,344,344,344,344,344,344,344,344,344,343, 87,343,343, - 87, 87,343, 87, 87,343,343, 87, 87,343,343,343,343, 87,343,343, -343,343,343,343,343,343,344,344,344,344, 87,344, 87,344,344,344, -344,344,344,344, 87,344,344,344,344,344,344,344,344,344,344,344, -343,343,343,343,343,343,343,343,343,343,343,343,343,343,343,343, -343,343,343,343,343,343,343,343,343,343,344,344,344,344,344,344, -344,344,344,344,344,344,344,344,344,344,344,344,344,344,344,344, - -/* block 144 */ -344,344,344,344,343,343, 87,343,343,343,343, 87, 87,343,343,343, -343,343,343,343,343, 87,343,343,343,343,343,343,343, 87,344,344, -344,344,344,344,344,344,344,344,344,344,344,344,344,344,344,344, -344,344,344,344,344,344,344,344,343,343, 87,343,343,343,343, 87, -343,343,343,343,343, 87,343, 87, 87, 87,343,343,343,343,343,343, -343, 87,344,344,344,344,344,344,344,344,344,344,344,344,344,344, -344,344,344,344,344,344,344,344,344,344,344,344,343,343,343,343, -343,343,343,343,343,343,343,343,343,343,343,343,343,343,343,343, - -/* block 145 */ -343,343,343,343,343,343,344,344,344,344,344,344,344,344,344,344, -344,344,344,344,344,344,344,344,344,344,344,344,344,344,344,344, -343,343,343,343,343,343,343,343,343,343,343,343,343,343,343,343, -343,343,343,343,343,343,343,343,343,343,344,344,344,344,344,344, -344,344,344,344,344,344,344,344,344,344,344,344,344,344,344,344, -344,344,344,344,343,343,343,343,343,343,343,343,343,343,343,343, -343,343,343,343,343,343,343,343,343,343,343,343,343,343,344,344, -344,344,344,344,344,344,344,344,344,344,344,344,344,344,344,344, - -/* block 146 */ -344,344,344,344,344,344,344,344,343,343,343,343,343,343,343,343, -343,343,343,343,343,343,343,343,343,343,343,343,343,343,343,343, -343,343,344,344,344,344,344,344,344,344,344,344,344,344,344,344, -344,344,344,344,344,344,344,344,344,344,344,344,343,343,343,343, -343,343,343,343,343,343,343,343,343,343,343,343,343,343,343,343, -343,343,343,343,343,343,344,344,344,344,344,344,344,344,344,344, -344,344,344,344,344,344,344,344,344,344,344,344,344,344,344,344, -343,343,343,343,343,343,343,343,343,343,343,343,343,343,343,343, - -/* block 147 */ -343,343,343,343,343,343,343,343,343,343,344,344,344,344,344,344, -344,344,344,344,344,344,344,344,344,344,344,344,344,344,344,344, -344,344,344,344,344,344, 87, 87,343,343,343,343,343,343,343,343, -343,343,343,343,343,343,343,343,343,343,343,343,343,343,343,343, -343, 6,344,344,344,344,344,344,344,344,344,344,344,344,344,344, -344,344,344,344,344,344,344,344,344,344,344, 6,344,344,344,344, -344,344,343,343,343,343,343,343,343,343,343,343,343,343,343,343, -343,343,343,343,343,343,343,343,343,343,343, 6,344,344,344,344, - -/* block 148 */ -344,344,344,344,344,344,344,344,344,344,344,344,344,344,344,344, -344,344,344,344,344, 6,344,344,344,344,344,344,343,343,343,343, -343,343,343,343,343,343,343,343,343,343,343,343,343,343,343,343, -343,343,343,343,343, 6,344,344,344,344,344,344,344,344,344,344, -344,344,344,344,344,344,344,344,344,344,344,344,344,344,344, 6, -344,344,344,344,344,344,343,343,343,343,343,343,343,343,343,343, -343,343,343,343,343,343,343,343,343,343,343,343,343,343,343, 6, -344,344,344,344,344,344,344,344,344,344,344,344,344,344,344,344, - -/* block 149 */ -344,344,344,344,344,344,344,344,344, 6,344,344,344,344,344,344, -343,343,343,343,343,343,343,343,343,343,343,343,343,343,343,343, -343,343,343,343,343,343,343,343,343, 6,344,344,344,344,344,344, -344,344,344,344,344,344,344,344,344,344,344,344,344,344,344,344, -344,344,344, 6,344,344,344,344,344,344,343,344, 87, 87, 8, 8, - 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, - 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, - 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, - -/* block 150 */ - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 87, 87, 87, 87, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - -/* block 151 */ - 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, - 13, 13, 13, 13, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 152 */ -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, -384,384,384,384,384,384,384, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 153 */ -384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384, -384,384,384,384,384,384,384,384,384,384,384,384,384,384, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 154 */ - 87, 16, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, - -/* block 155 */ - 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, - 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, - 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, - 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, - 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, - 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, - 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, - 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, - -/* block 156 */ - 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, - 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, - 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, - 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, - 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, - 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, - 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, 82, - 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, - -/* block 157 */ -420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420, -420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420, -420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420, -420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420, -420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420, -420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420, -420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420, -420,420,420,420,420,420,420,420,420,420,420,420,420,420, 87, 87, - -}; - -#if UCD_BLOCK_SIZE != 128 -#error Please correct UCD_BLOCK_SIZE in pcre_internal.h -#endif diff --git a/libs/pcre/pcre_ucp_searchfuncs.c b/libs/pcre/pcre_ucp_searchfuncs.c deleted file mode 100644 index 83ee7ff5a6..0000000000 --- a/libs/pcre/pcre_ucp_searchfuncs.c +++ /dev/null @@ -1,179 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains code for searching the table of Unicode character -properties. */ - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - -#include "ucp.h" /* Category definitions */ -#include "ucpinternal.h" /* Internal table details */ -#include "ucptable.c" /* The table itself */ - - -/* Table to translate from particular type value to the general value. */ - -static int ucp_gentype[] = { - ucp_C, ucp_C, ucp_C, ucp_C, ucp_C, /* Cc, Cf, Cn, Co, Cs */ - ucp_L, ucp_L, ucp_L, ucp_L, ucp_L, /* Ll, Lu, Lm, Lo, Lt */ - ucp_M, ucp_M, ucp_M, /* Mc, Me, Mn */ - ucp_N, ucp_N, ucp_N, /* Nd, Nl, No */ - ucp_P, ucp_P, ucp_P, ucp_P, ucp_P, /* Pc, Pd, Pe, Pf, Pi */ - ucp_P, ucp_P, /* Ps, Po */ - ucp_S, ucp_S, ucp_S, ucp_S, /* Sc, Sk, Sm, So */ - ucp_Z, ucp_Z, ucp_Z /* Zl, Zp, Zs */ -}; - - - -/************************************************* -* Search table and return type * -*************************************************/ - -/* Three values are returned: the category is ucp_C, ucp_L, etc. The detailed -character type is ucp_Lu, ucp_Nd, etc. The script is ucp_Latin, etc. - -Arguments: - c the character value - type_ptr the detailed character type is returned here - script_ptr the script is returned here - -Returns: the character type category -*/ - -int -_pcre_ucp_findprop(const unsigned int c, int *type_ptr, int *script_ptr) -{ -int bot = 0; -int top = sizeof(ucp_table)/sizeof(cnode); -int mid; - -/* The table is searched using a binary chop. You might think that using -intermediate variables to hold some of the common expressions would speed -things up, but tests with gcc 3.4.4 on Linux showed that, on the contrary, it -makes things a lot slower. */ - -for (;;) - { - if (top <= bot) - { - *type_ptr = ucp_Cn; - *script_ptr = ucp_Common; - return ucp_C; - } - mid = (bot + top) >> 1; - if (c == (ucp_table[mid].f0 & f0_charmask)) break; - if (c < (ucp_table[mid].f0 & f0_charmask)) top = mid; - else - { - if ((ucp_table[mid].f0 & f0_rangeflag) != 0 && - c <= (ucp_table[mid].f0 & f0_charmask) + - (ucp_table[mid].f1 & f1_rangemask)) break; - bot = mid + 1; - } - } - -/* Found an entry in the table. Set the script and detailed type values, and -return the general type. */ - -*script_ptr = (ucp_table[mid].f0 & f0_scriptmask) >> f0_scriptshift; -*type_ptr = (ucp_table[mid].f1 & f1_typemask) >> f1_typeshift; - -return ucp_gentype[*type_ptr]; -} - - - -/************************************************* -* Search table and return other case * -*************************************************/ - -/* If the given character is a letter, and there is another case for the -letter, return the other case. Otherwise, return -1. - -Arguments: - c the character value - -Returns: the other case or -1 if none -*/ - -int -_pcre_ucp_othercase(const int c) -{ -int bot = 0; -int top = sizeof(ucp_table)/sizeof(cnode); -int mid, offset; - -/* The table is searched using a binary chop. You might think that using -intermediate variables to hold some of the common expressions would speed -things up, but tests with gcc 3.4.4 on Linux showed that, on the contrary, it -makes things a lot slower. */ - -for (;;) - { - if (top <= bot) return -1; - mid = (bot + top) >> 1; - if (c == (ucp_table[mid].f0 & f0_charmask)) break; - if (c < (int)(ucp_table[mid].f0 & f0_charmask)) top = mid; - else - { - if ((ucp_table[mid].f0 & f0_rangeflag) != 0 && - c <= (int)((ucp_table[mid].f0 & f0_charmask) + - (ucp_table[mid].f1 & f1_rangemask))) break; - bot = mid + 1; - } - } - -/* Found an entry in the table. Return -1 for a range entry. Otherwise return -the other case if there is one, else -1. */ - -if ((ucp_table[mid].f0 & f0_rangeflag) != 0) return -1; - -offset = ucp_table[mid].f1 & f1_casemask; -if ((offset & f1_caseneg) != 0) offset |= f1_caseneg; -return (offset == 0)? -1 : c + offset; -} - - -/* End of pcre_ucp_searchfuncs.c */ diff --git a/libs/pcre/pcre_valid_utf8.c b/libs/pcre/pcre_valid_utf8.c deleted file mode 100644 index d381ad6dab..0000000000 --- a/libs/pcre/pcre_valid_utf8.c +++ /dev/null @@ -1,165 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2009 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains an internal function for validating UTF-8 character -strings. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - - -/************************************************* -* Validate a UTF-8 string * -*************************************************/ - -/* This function is called (optionally) at the start of compile or match, to -validate that a supposed UTF-8 string is actually valid. The early check means -that subsequent code can assume it is dealing with a valid string. The check -can be turned off for maximum performance, but the consequences of supplying -an invalid string are then undefined. - -Originally, this function checked according to RFC 2279, allowing for values in -the range 0 to 0x7fffffff, up to 6 bytes long, but ensuring that they were in -the canonical format. Once somebody had pointed out RFC 3629 to me (it -obsoletes 2279), additional restrictions were applied. The values are now -limited to be between 0 and 0x0010ffff, no more than 4 bytes long, and the -subrange 0xd000 to 0xdfff is excluded. - -Arguments: - string points to the string - length length of string, or -1 if the string is zero-terminated - -Returns: < 0 if the string is a valid UTF-8 string - >= 0 otherwise; the value is the offset of the bad byte -*/ - -int -_pcre_valid_utf8(USPTR string, int length) -{ -#ifdef SUPPORT_UTF8 -register USPTR p; - -if (length < 0) - { - for (p = string; *p != 0; p++); - length = p - string; - } - -for (p = string; length-- > 0; p++) - { - register int ab; - register int c = *p; - if (c < 128) continue; - if (c < 0xc0) return p - string; - ab = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ - if (length < ab || ab > 3) return p - string; - length -= ab; - - /* Check top bits in the second byte */ - if ((*(++p) & 0xc0) != 0x80) return p - string; - - /* Check for overlong sequences for each different length, and for the - excluded range 0xd000 to 0xdfff. */ - - switch (ab) - { - /* Check for xx00 000x (overlong sequence) */ - - case 1: - if ((c & 0x3e) == 0) return p - string; - continue; /* We know there aren't any more bytes to check */ - - /* Check for 1110 0000, xx0x xxxx (overlong sequence) or - 1110 1101, 1010 xxxx (0xd000 - 0xdfff) */ - - case 2: - if ((c == 0xe0 && (*p & 0x20) == 0) || - (c == 0xed && *p >= 0xa0)) - return p - string; - break; - - /* Check for 1111 0000, xx00 xxxx (overlong sequence) or - greater than 0x0010ffff (f4 8f bf bf) */ - - case 3: - if ((c == 0xf0 && (*p & 0x30) == 0) || - (c > 0xf4 ) || - (c == 0xf4 && *p > 0x8f)) - return p - string; - break; - -#if 0 - /* These cases can no longer occur, as we restrict to a maximum of four - bytes nowadays. Leave the code here in case we ever want to add an option - for longer sequences. */ - - /* Check for 1111 1000, xx00 0xxx */ - case 4: - if (c == 0xf8 && (*p & 0x38) == 0) return p - string; - break; - - /* Check for leading 0xfe or 0xff, and then for 1111 1100, xx00 00xx */ - case 5: - if (c == 0xfe || c == 0xff || - (c == 0xfc && (*p & 0x3c) == 0)) return p - string; - break; -#endif - - } - - /* Check for valid bytes after the 2nd, if any; all must start 10 */ - while (--ab > 0) - { - if ((*(++p) & 0xc0) != 0x80) return p - string; - } - } -#else -(void)(string); /* Keep picky compilers happy */ -(void)(length); -#endif - -return -1; -} - -/* End of pcre_valid_utf8.c */ diff --git a/libs/pcre/pcre_version.c b/libs/pcre/pcre_version.c deleted file mode 100644 index 7067cd4aeb..0000000000 --- a/libs/pcre/pcre_version.c +++ /dev/null @@ -1,90 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2008 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains the external function pcre_version(), which returns a -string that identifies the PCRE version that is in use. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - - -/************************************************* -* Return version string * -*************************************************/ - -/* These macros are the standard way of turning unquoted text into C strings. -They allow macros like PCRE_MAJOR to be defined without quotes, which is -convenient for user programs that want to test its value. */ - -#define STRING(a) # a -#define XSTRING(s) STRING(s) - -/* A problem turned up with PCRE_PRERELEASE, which is defined empty for -production releases. Originally, it was used naively in this code: - - return XSTRING(PCRE_MAJOR) - "." XSTRING(PCRE_MINOR) - XSTRING(PCRE_PRERELEASE) - " " XSTRING(PCRE_DATE); - -However, when PCRE_PRERELEASE is empty, this leads to an attempted expansion of -STRING(). The C standard states: "If (before argument substitution) any -argument consists of no preprocessing tokens, the behavior is undefined." It -turns out the gcc treats this case as a single empty string - which is what we -really want - but Visual C grumbles about the lack of an argument for the -macro. Unfortunately, both are within their rights. To cope with both ways of -handling this, I had resort to some messy hackery that does a test at run time. -I could find no way of detecting that a macro is defined as an empty string at -pre-processor time. This hack uses a standard trick for avoiding calling -the STRING macro with an empty argument when doing the test. */ - -PCRE_EXP_DEFN const char * PCRE_CALL_CONVENTION -pcre_version(void) -{ -return (XSTRING(Z PCRE_PRERELEASE)[1] == 0)? - XSTRING(PCRE_MAJOR.PCRE_MINOR PCRE_DATE) : - XSTRING(PCRE_MAJOR.PCRE_MINOR) XSTRING(PCRE_PRERELEASE PCRE_DATE); -} - -/* End of pcre_version.c */ diff --git a/libs/pcre/pcre_xclass.c b/libs/pcre/pcre_xclass.c deleted file mode 100644 index dc67c23d8d..0000000000 --- a/libs/pcre/pcre_xclass.c +++ /dev/null @@ -1,146 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2009 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains an internal function that is used to match an extended -class. It is used by both pcre_exec() and pcre_def_exec(). */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - - -/************************************************* -* Match character against an XCLASS * -*************************************************/ - -/* This function is called to match a character against an extended class that -might contain values > 255 and/or Unicode properties. - -Arguments: - c the character - data points to the flag byte of the XCLASS data - -Returns: TRUE if character matches, else FALSE -*/ - -BOOL -_pcre_xclass(int c, const uschar *data) -{ -int t; -BOOL negated = (*data & XCL_NOT) != 0; - -/* Character values < 256 are matched against a bitmap, if one is present. If -not, we still carry on, because there may be ranges that start below 256 in the -additional data. */ - -if (c < 256) - { - if ((*data & XCL_MAP) != 0 && (data[1 + c/8] & (1 << (c&7))) != 0) - return !negated; /* char found */ - } - -/* First skip the bit map if present. Then match against the list of Unicode -properties or large chars or ranges that end with a large char. We won't ever -encounter XCL_PROP or XCL_NOTPROP when UCP support is not compiled. */ - -if ((*data++ & XCL_MAP) != 0) data += 32; - -while ((t = *data++) != XCL_END) - { - int x, y; - if (t == XCL_SINGLE) - { - GETCHARINC(x, data); - if (c == x) return !negated; - } - else if (t == XCL_RANGE) - { - GETCHARINC(x, data); - GETCHARINC(y, data); - if (c >= x && c <= y) return !negated; - } - -#ifdef SUPPORT_UCP - else /* XCL_PROP & XCL_NOTPROP */ - { - const ucd_record *prop = GET_UCD(c); - - switch(*data) - { - case PT_ANY: - if (t == XCL_PROP) return !negated; - break; - - case PT_LAMP: - if ((prop->chartype == ucp_Lu || prop->chartype == ucp_Ll || prop->chartype == ucp_Lt) == - (t == XCL_PROP)) return !negated; - break; - - case PT_GC: - if ((data[1] == _pcre_ucp_gentype[prop->chartype]) == (t == XCL_PROP)) return !negated; - break; - - case PT_PC: - if ((data[1] == prop->chartype) == (t == XCL_PROP)) return !negated; - break; - - case PT_SC: - if ((data[1] == prop->script) == (t == XCL_PROP)) return !negated; - break; - - /* This should never occur, but compilers may mutter if there is no - default. */ - - default: - return FALSE; - } - - data += 2; - } -#endif /* SUPPORT_UCP */ - } - -return negated; /* char did not match */ -} - -/* End of pcre_xclass.c */ diff --git a/libs/pcre/pcrecpp.cc b/libs/pcre/pcrecpp.cc deleted file mode 100644 index e8e8a12e9f..0000000000 --- a/libs/pcre/pcrecpp.cc +++ /dev/null @@ -1,893 +0,0 @@ -// Copyright (c) 2005, Google Inc. -// All rights reserved. -// -// Redistribution and use in source and binary forms, with or without -// modification, are permitted provided that the following conditions are -// met: -// -// * Redistributions of source code must retain the above copyright -// notice, this list of conditions and the following disclaimer. -// * Redistributions in binary form must reproduce the above -// copyright notice, this list of conditions and the following disclaimer -// in the documentation and/or other materials provided with the -// distribution. -// * Neither the name of Google Inc. nor the names of its -// contributors may be used to endorse or promote products derived from -// this software without specific prior written permission. -// -// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS -// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT -// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR -// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT -// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, -// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT -// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, -// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY -// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT -// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE -// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. -// -// Author: Sanjay Ghemawat - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include -#include -#include -#include /* for SHRT_MIN, USHRT_MAX, etc */ -#include -#include -#include -#include - -#include "pcrecpp_internal.h" -#include "pcre.h" -#include "pcrecpp.h" -#include "pcre_stringpiece.h" - - -namespace pcrecpp { - -// Maximum number of args we can set -static const int kMaxArgs = 16; -static const int kVecSize = (1 + kMaxArgs) * 3; // results + PCRE workspace - -// Special object that stands-in for no argument -Arg RE::no_arg((void*)NULL); - -// This is for ABI compatibility with old versions of pcre (pre-7.6), -// which defined a global no_arg variable instead of putting it in the -// RE class. This works on GCC >= 3, at least. It definitely works -// for ELF, but may not for other object formats (Mach-O, for -// instance, does not support aliases.) We could probably have a more -// inclusive test if we ever needed it. (Note that not only the -// __attribute__ syntax, but also __USER_LABEL_PREFIX__, are -// gnu-specific.) -#if defined(__GNUC__) && __GNUC__ >= 3 && defined(__ELF__) -# define ULP_AS_STRING(x) ULP_AS_STRING_INTERNAL(x) -# define ULP_AS_STRING_INTERNAL(x) #x -# define USER_LABEL_PREFIX_STR ULP_AS_STRING(__USER_LABEL_PREFIX__) -extern Arg no_arg - __attribute__((alias(USER_LABEL_PREFIX_STR "_ZN7pcrecpp2RE6no_argE"))); -#endif - -// If a regular expression has no error, its error_ field points here -static const string empty_string; - -// If the user doesn't ask for any options, we just use this one -static RE_Options default_options; - -void RE::Init(const string& pat, const RE_Options* options) { - pattern_ = pat; - if (options == NULL) { - options_ = default_options; - } else { - options_ = *options; - } - error_ = &empty_string; - re_full_ = NULL; - re_partial_ = NULL; - - re_partial_ = Compile(UNANCHORED); - if (re_partial_ != NULL) { - re_full_ = Compile(ANCHOR_BOTH); - } -} - -void RE::Cleanup() { - if (re_full_ != NULL) (*pcre_free)(re_full_); - if (re_partial_ != NULL) (*pcre_free)(re_partial_); - if (error_ != &empty_string) delete error_; -} - - -RE::~RE() { - Cleanup(); -} - - -pcre* RE::Compile(Anchor anchor) { - // First, convert RE_Options into pcre options - int pcre_options = 0; - pcre_options = options_.all_options(); - - // Special treatment for anchoring. This is needed because at - // runtime pcre only provides an option for anchoring at the - // beginning of a string (unless you use offset). - // - // There are three types of anchoring we want: - // UNANCHORED Compile the original pattern, and use - // a pcre unanchored match. - // ANCHOR_START Compile the original pattern, and use - // a pcre anchored match. - // ANCHOR_BOTH Tack a "\z" to the end of the original pattern - // and use a pcre anchored match. - - const char* compile_error; - int eoffset; - pcre* re; - if (anchor != ANCHOR_BOTH) { - re = pcre_compile(pattern_.c_str(), pcre_options, - &compile_error, &eoffset, NULL); - } else { - // Tack a '\z' at the end of RE. Parenthesize it first so that - // the '\z' applies to all top-level alternatives in the regexp. - string wrapped = "(?:"; // A non-counting grouping operator - wrapped += pattern_; - wrapped += ")\\z"; - re = pcre_compile(wrapped.c_str(), pcre_options, - &compile_error, &eoffset, NULL); - } - if (re == NULL) { - if (error_ == &empty_string) error_ = new string(compile_error); - } - return re; -} - -/***** Matching interfaces *****/ - -bool RE::FullMatch(const StringPiece& text, - const Arg& ptr1, - const Arg& ptr2, - const Arg& ptr3, - const Arg& ptr4, - const Arg& ptr5, - const Arg& ptr6, - const Arg& ptr7, - const Arg& ptr8, - const Arg& ptr9, - const Arg& ptr10, - const Arg& ptr11, - const Arg& ptr12, - const Arg& ptr13, - const Arg& ptr14, - const Arg& ptr15, - const Arg& ptr16) const { - const Arg* args[kMaxArgs]; - int n = 0; - if (&ptr1 == &no_arg) goto done; args[n++] = &ptr1; - if (&ptr2 == &no_arg) goto done; args[n++] = &ptr2; - if (&ptr3 == &no_arg) goto done; args[n++] = &ptr3; - if (&ptr4 == &no_arg) goto done; args[n++] = &ptr4; - if (&ptr5 == &no_arg) goto done; args[n++] = &ptr5; - if (&ptr6 == &no_arg) goto done; args[n++] = &ptr6; - if (&ptr7 == &no_arg) goto done; args[n++] = &ptr7; - if (&ptr8 == &no_arg) goto done; args[n++] = &ptr8; - if (&ptr9 == &no_arg) goto done; args[n++] = &ptr9; - if (&ptr10 == &no_arg) goto done; args[n++] = &ptr10; - if (&ptr11 == &no_arg) goto done; args[n++] = &ptr11; - if (&ptr12 == &no_arg) goto done; args[n++] = &ptr12; - if (&ptr13 == &no_arg) goto done; args[n++] = &ptr13; - if (&ptr14 == &no_arg) goto done; args[n++] = &ptr14; - if (&ptr15 == &no_arg) goto done; args[n++] = &ptr15; - if (&ptr16 == &no_arg) goto done; args[n++] = &ptr16; - done: - - int consumed; - int vec[kVecSize]; - return DoMatchImpl(text, ANCHOR_BOTH, &consumed, args, n, vec, kVecSize); -} - -bool RE::PartialMatch(const StringPiece& text, - const Arg& ptr1, - const Arg& ptr2, - const Arg& ptr3, - const Arg& ptr4, - const Arg& ptr5, - const Arg& ptr6, - const Arg& ptr7, - const Arg& ptr8, - const Arg& ptr9, - const Arg& ptr10, - const Arg& ptr11, - const Arg& ptr12, - const Arg& ptr13, - const Arg& ptr14, - const Arg& ptr15, - const Arg& ptr16) const { - const Arg* args[kMaxArgs]; - int n = 0; - if (&ptr1 == &no_arg) goto done; args[n++] = &ptr1; - if (&ptr2 == &no_arg) goto done; args[n++] = &ptr2; - if (&ptr3 == &no_arg) goto done; args[n++] = &ptr3; - if (&ptr4 == &no_arg) goto done; args[n++] = &ptr4; - if (&ptr5 == &no_arg) goto done; args[n++] = &ptr5; - if (&ptr6 == &no_arg) goto done; args[n++] = &ptr6; - if (&ptr7 == &no_arg) goto done; args[n++] = &ptr7; - if (&ptr8 == &no_arg) goto done; args[n++] = &ptr8; - if (&ptr9 == &no_arg) goto done; args[n++] = &ptr9; - if (&ptr10 == &no_arg) goto done; args[n++] = &ptr10; - if (&ptr11 == &no_arg) goto done; args[n++] = &ptr11; - if (&ptr12 == &no_arg) goto done; args[n++] = &ptr12; - if (&ptr13 == &no_arg) goto done; args[n++] = &ptr13; - if (&ptr14 == &no_arg) goto done; args[n++] = &ptr14; - if (&ptr15 == &no_arg) goto done; args[n++] = &ptr15; - if (&ptr16 == &no_arg) goto done; args[n++] = &ptr16; - done: - - int consumed; - int vec[kVecSize]; - return DoMatchImpl(text, UNANCHORED, &consumed, args, n, vec, kVecSize); -} - -bool RE::Consume(StringPiece* input, - const Arg& ptr1, - const Arg& ptr2, - const Arg& ptr3, - const Arg& ptr4, - const Arg& ptr5, - const Arg& ptr6, - const Arg& ptr7, - const Arg& ptr8, - const Arg& ptr9, - const Arg& ptr10, - const Arg& ptr11, - const Arg& ptr12, - const Arg& ptr13, - const Arg& ptr14, - const Arg& ptr15, - const Arg& ptr16) const { - const Arg* args[kMaxArgs]; - int n = 0; - if (&ptr1 == &no_arg) goto done; args[n++] = &ptr1; - if (&ptr2 == &no_arg) goto done; args[n++] = &ptr2; - if (&ptr3 == &no_arg) goto done; args[n++] = &ptr3; - if (&ptr4 == &no_arg) goto done; args[n++] = &ptr4; - if (&ptr5 == &no_arg) goto done; args[n++] = &ptr5; - if (&ptr6 == &no_arg) goto done; args[n++] = &ptr6; - if (&ptr7 == &no_arg) goto done; args[n++] = &ptr7; - if (&ptr8 == &no_arg) goto done; args[n++] = &ptr8; - if (&ptr9 == &no_arg) goto done; args[n++] = &ptr9; - if (&ptr10 == &no_arg) goto done; args[n++] = &ptr10; - if (&ptr11 == &no_arg) goto done; args[n++] = &ptr11; - if (&ptr12 == &no_arg) goto done; args[n++] = &ptr12; - if (&ptr13 == &no_arg) goto done; args[n++] = &ptr13; - if (&ptr14 == &no_arg) goto done; args[n++] = &ptr14; - if (&ptr15 == &no_arg) goto done; args[n++] = &ptr15; - if (&ptr16 == &no_arg) goto done; args[n++] = &ptr16; - done: - - int consumed; - int vec[kVecSize]; - if (DoMatchImpl(*input, ANCHOR_START, &consumed, - args, n, vec, kVecSize)) { - input->remove_prefix(consumed); - return true; - } else { - return false; - } -} - -bool RE::FindAndConsume(StringPiece* input, - const Arg& ptr1, - const Arg& ptr2, - const Arg& ptr3, - const Arg& ptr4, - const Arg& ptr5, - const Arg& ptr6, - const Arg& ptr7, - const Arg& ptr8, - const Arg& ptr9, - const Arg& ptr10, - const Arg& ptr11, - const Arg& ptr12, - const Arg& ptr13, - const Arg& ptr14, - const Arg& ptr15, - const Arg& ptr16) const { - const Arg* args[kMaxArgs]; - int n = 0; - if (&ptr1 == &no_arg) goto done; args[n++] = &ptr1; - if (&ptr2 == &no_arg) goto done; args[n++] = &ptr2; - if (&ptr3 == &no_arg) goto done; args[n++] = &ptr3; - if (&ptr4 == &no_arg) goto done; args[n++] = &ptr4; - if (&ptr5 == &no_arg) goto done; args[n++] = &ptr5; - if (&ptr6 == &no_arg) goto done; args[n++] = &ptr6; - if (&ptr7 == &no_arg) goto done; args[n++] = &ptr7; - if (&ptr8 == &no_arg) goto done; args[n++] = &ptr8; - if (&ptr9 == &no_arg) goto done; args[n++] = &ptr9; - if (&ptr10 == &no_arg) goto done; args[n++] = &ptr10; - if (&ptr11 == &no_arg) goto done; args[n++] = &ptr11; - if (&ptr12 == &no_arg) goto done; args[n++] = &ptr12; - if (&ptr13 == &no_arg) goto done; args[n++] = &ptr13; - if (&ptr14 == &no_arg) goto done; args[n++] = &ptr14; - if (&ptr15 == &no_arg) goto done; args[n++] = &ptr15; - if (&ptr16 == &no_arg) goto done; args[n++] = &ptr16; - done: - - int consumed; - int vec[kVecSize]; - if (DoMatchImpl(*input, UNANCHORED, &consumed, - args, n, vec, kVecSize)) { - input->remove_prefix(consumed); - return true; - } else { - return false; - } -} - -bool RE::Replace(const StringPiece& rewrite, - string *str) const { - int vec[kVecSize]; - int matches = TryMatch(*str, 0, UNANCHORED, vec, kVecSize); - if (matches == 0) - return false; - - string s; - if (!Rewrite(&s, rewrite, *str, vec, matches)) - return false; - - assert(vec[0] >= 0); - assert(vec[1] >= 0); - str->replace(vec[0], vec[1] - vec[0], s); - return true; -} - -// Returns PCRE_NEWLINE_CRLF, PCRE_NEWLINE_CR, or PCRE_NEWLINE_LF. -// Note that PCRE_NEWLINE_CRLF is defined to be P_N_CR | P_N_LF. -// Modified by PH to add PCRE_NEWLINE_ANY and PCRE_NEWLINE_ANYCRLF. - -static int NewlineMode(int pcre_options) { - // TODO: if we can make it threadsafe, cache this var - int newline_mode = 0; - /* if (newline_mode) return newline_mode; */ // do this once it's cached - if (pcre_options & (PCRE_NEWLINE_CRLF|PCRE_NEWLINE_CR|PCRE_NEWLINE_LF| - PCRE_NEWLINE_ANY|PCRE_NEWLINE_ANYCRLF)) { - newline_mode = (pcre_options & - (PCRE_NEWLINE_CRLF|PCRE_NEWLINE_CR|PCRE_NEWLINE_LF| - PCRE_NEWLINE_ANY|PCRE_NEWLINE_ANYCRLF)); - } else { - int newline; - pcre_config(PCRE_CONFIG_NEWLINE, &newline); - if (newline == 10) - newline_mode = PCRE_NEWLINE_LF; - else if (newline == 13) - newline_mode = PCRE_NEWLINE_CR; - else if (newline == 3338) - newline_mode = PCRE_NEWLINE_CRLF; - else if (newline == -1) - newline_mode = PCRE_NEWLINE_ANY; - else if (newline == -2) - newline_mode = PCRE_NEWLINE_ANYCRLF; - else - assert(NULL == "Unexpected return value from pcre_config(NEWLINE)"); - } - return newline_mode; -} - -int RE::GlobalReplace(const StringPiece& rewrite, - string *str) const { - int count = 0; - int vec[kVecSize]; - string out; - int start = 0; - int lastend = -1; - - while (start <= static_cast(str->length())) { - int matches = TryMatch(*str, start, UNANCHORED, vec, kVecSize); - if (matches <= 0) - break; - int matchstart = vec[0], matchend = vec[1]; - assert(matchstart >= start); - assert(matchend >= matchstart); - if (matchstart == matchend && matchstart == lastend) { - // advance one character if we matched an empty string at the same - // place as the last match occurred - matchend = start + 1; - // If the current char is CR and we're in CRLF mode, skip LF too. - // Note it's better to call pcre_fullinfo() than to examine - // all_options(), since options_ could have changed bewteen - // compile-time and now, but this is simpler and safe enough. - // Modified by PH to add ANY and ANYCRLF. - if (start+1 < static_cast(str->length()) && - (*str)[start] == '\r' && (*str)[start+1] == '\n' && - (NewlineMode(options_.all_options()) == PCRE_NEWLINE_CRLF || - NewlineMode(options_.all_options()) == PCRE_NEWLINE_ANY || - NewlineMode(options_.all_options()) == PCRE_NEWLINE_ANYCRLF) - ) { - matchend++; - } - // We also need to advance more than one char if we're in utf8 mode. -#ifdef SUPPORT_UTF8 - if (options_.utf8()) { - while (matchend < static_cast(str->length()) && - ((*str)[matchend] & 0xc0) == 0x80) - matchend++; - } -#endif - if (matchend <= static_cast(str->length())) - out.append(*str, start, matchend - start); - start = matchend; - } else { - out.append(*str, start, matchstart - start); - Rewrite(&out, rewrite, *str, vec, matches); - start = matchend; - lastend = matchend; - count++; - } - } - - if (count == 0) - return 0; - - if (start < static_cast(str->length())) - out.append(*str, start, str->length() - start); - swap(out, *str); - return count; -} - -bool RE::Extract(const StringPiece& rewrite, - const StringPiece& text, - string *out) const { - int vec[kVecSize]; - int matches = TryMatch(text, 0, UNANCHORED, vec, kVecSize); - if (matches == 0) - return false; - out->erase(); - return Rewrite(out, rewrite, text, vec, matches); -} - -/*static*/ string RE::QuoteMeta(const StringPiece& unquoted) { - string result; - - // Escape any ascii character not in [A-Za-z_0-9]. - // - // Note that it's legal to escape a character even if it has no - // special meaning in a regular expression -- so this function does - // that. (This also makes it identical to the perl function of the - // same name; see `perldoc -f quotemeta`.) The one exception is - // escaping NUL: rather than doing backslash + NUL, like perl does, - // we do '\0', because pcre itself doesn't take embedded NUL chars. - for (int ii = 0; ii < unquoted.size(); ++ii) { - // Note that using 'isalnum' here raises the benchmark time from - // 32ns to 58ns: - if (unquoted[ii] == '\0') { - result += "\\0"; - } else if ((unquoted[ii] < 'a' || unquoted[ii] > 'z') && - (unquoted[ii] < 'A' || unquoted[ii] > 'Z') && - (unquoted[ii] < '0' || unquoted[ii] > '9') && - unquoted[ii] != '_' && - // If this is the part of a UTF8 or Latin1 character, we need - // to copy this byte without escaping. Experimentally this is - // what works correctly with the regexp library. - !(unquoted[ii] & 128)) { - result += '\\'; - result += unquoted[ii]; - } else { - result += unquoted[ii]; - } - } - - return result; -} - -/***** Actual matching and rewriting code *****/ - -int RE::TryMatch(const StringPiece& text, - int startpos, - Anchor anchor, - int *vec, - int vecsize) const { - pcre* re = (anchor == ANCHOR_BOTH) ? re_full_ : re_partial_; - if (re == NULL) { - //fprintf(stderr, "Matching against invalid re: %s\n", error_->c_str()); - return 0; - } - - pcre_extra extra = { 0, 0, 0, 0, 0, 0 }; - if (options_.match_limit() > 0) { - extra.flags |= PCRE_EXTRA_MATCH_LIMIT; - extra.match_limit = options_.match_limit(); - } - if (options_.match_limit_recursion() > 0) { - extra.flags |= PCRE_EXTRA_MATCH_LIMIT_RECURSION; - extra.match_limit_recursion = options_.match_limit_recursion(); - } - int rc = pcre_exec(re, // The regular expression object - &extra, - (text.data() == NULL) ? "" : text.data(), - text.size(), - startpos, - (anchor == UNANCHORED) ? 0 : PCRE_ANCHORED, - vec, - vecsize); - - // Handle errors - if (rc == PCRE_ERROR_NOMATCH) { - return 0; - } else if (rc < 0) { - //fprintf(stderr, "Unexpected return code: %d when matching '%s'\n", - // re, pattern_.c_str()); - return 0; - } else if (rc == 0) { - // pcre_exec() returns 0 as a special case when the number of - // capturing subpatterns exceeds the size of the vector. - // When this happens, there is a match and the output vector - // is filled, but we miss out on the positions of the extra subpatterns. - rc = vecsize / 2; - } - - return rc; -} - -bool RE::DoMatchImpl(const StringPiece& text, - Anchor anchor, - int* consumed, - const Arg* const* args, - int n, - int* vec, - int vecsize) const { - assert((1 + n) * 3 <= vecsize); // results + PCRE workspace - int matches = TryMatch(text, 0, anchor, vec, vecsize); - assert(matches >= 0); // TryMatch never returns negatives - if (matches == 0) - return false; - - *consumed = vec[1]; - - if (n == 0 || args == NULL) { - // We are not interested in results - return true; - } - - if (NumberOfCapturingGroups() < n) { - // RE has fewer capturing groups than number of arg pointers passed in - return false; - } - - // If we got here, we must have matched the whole pattern. - // We do not need (can not do) any more checks on the value of 'matches' here - // -- see the comment for TryMatch. - for (int i = 0; i < n; i++) { - const int start = vec[2*(i+1)]; - const int limit = vec[2*(i+1)+1]; - if (!args[i]->Parse(text.data() + start, limit-start)) { - // TODO: Should we indicate what the error was? - return false; - } - } - - return true; -} - -bool RE::DoMatch(const StringPiece& text, - Anchor anchor, - int* consumed, - const Arg* const args[], - int n) const { - assert(n >= 0); - size_t const vecsize = (1 + n) * 3; // results + PCRE workspace - // (as for kVecSize) - int space[21]; // use stack allocation for small vecsize (common case) - int* vec = vecsize <= 21 ? space : new int[vecsize]; - bool retval = DoMatchImpl(text, anchor, consumed, args, n, vec, vecsize); - if (vec != space) delete [] vec; - return retval; -} - -bool RE::Rewrite(string *out, const StringPiece &rewrite, - const StringPiece &text, int *vec, int veclen) const { - for (const char *s = rewrite.data(), *end = s + rewrite.size(); - s < end; s++) { - int c = *s; - if (c == '\\') { - c = *++s; - if (isdigit(c)) { - int n = (c - '0'); - if (n >= veclen) { - //fprintf(stderr, requested group %d in regexp %.*s\n", - // n, rewrite.size(), rewrite.data()); - return false; - } - int start = vec[2 * n]; - if (start >= 0) - out->append(text.data() + start, vec[2 * n + 1] - start); - } else if (c == '\\') { - *out += '\\'; - } else { - //fprintf(stderr, "invalid rewrite pattern: %.*s\n", - // rewrite.size(), rewrite.data()); - return false; - } - } else { - *out += c; - } - } - return true; -} - -// Return the number of capturing subpatterns, or -1 if the -// regexp wasn't valid on construction. -int RE::NumberOfCapturingGroups() const { - if (re_partial_ == NULL) return -1; - - int result; - int pcre_retval = pcre_fullinfo(re_partial_, // The regular expression object - NULL, // We did not study the pattern - PCRE_INFO_CAPTURECOUNT, - &result); - assert(pcre_retval == 0); - return result; -} - -/***** Parsers for various types *****/ - -bool Arg::parse_null(const char* str, int n, void* dest) { - // We fail if somebody asked us to store into a non-NULL void* pointer - return (dest == NULL); -} - -bool Arg::parse_string(const char* str, int n, void* dest) { - if (dest == NULL) return true; - reinterpret_cast(dest)->assign(str, n); - return true; -} - -bool Arg::parse_stringpiece(const char* str, int n, void* dest) { - if (dest == NULL) return true; - reinterpret_cast(dest)->set(str, n); - return true; -} - -bool Arg::parse_char(const char* str, int n, void* dest) { - if (n != 1) return false; - if (dest == NULL) return true; - *(reinterpret_cast(dest)) = str[0]; - return true; -} - -bool Arg::parse_uchar(const char* str, int n, void* dest) { - if (n != 1) return false; - if (dest == NULL) return true; - *(reinterpret_cast(dest)) = str[0]; - return true; -} - -// Largest number spec that we are willing to parse -static const int kMaxNumberLength = 32; - -// REQUIRES "buf" must have length at least kMaxNumberLength+1 -// REQUIRES "n > 0" -// Copies "str" into "buf" and null-terminates if necessary. -// Returns one of: -// a. "str" if no termination is needed -// b. "buf" if the string was copied and null-terminated -// c. "" if the input was invalid and has no hope of being parsed -static const char* TerminateNumber(char* buf, const char* str, int n) { - if ((n > 0) && isspace(*str)) { - // We are less forgiving than the strtoxxx() routines and do not - // allow leading spaces. - return ""; - } - - // See if the character right after the input text may potentially - // look like a digit. - if (isdigit(str[n]) || - ((str[n] >= 'a') && (str[n] <= 'f')) || - ((str[n] >= 'A') && (str[n] <= 'F'))) { - if (n > kMaxNumberLength) return ""; // Input too big to be a valid number - memcpy(buf, str, n); - buf[n] = '\0'; - return buf; - } else { - // We can parse right out of the supplied string, so return it. - return str; - } -} - -bool Arg::parse_long_radix(const char* str, - int n, - void* dest, - int radix) { - if (n == 0) return false; - char buf[kMaxNumberLength+1]; - str = TerminateNumber(buf, str, n); - char* end; - errno = 0; - long r = strtol(str, &end, radix); - if (end != str + n) return false; // Leftover junk - if (errno) return false; - if (dest == NULL) return true; - *(reinterpret_cast(dest)) = r; - return true; -} - -bool Arg::parse_ulong_radix(const char* str, - int n, - void* dest, - int radix) { - if (n == 0) return false; - char buf[kMaxNumberLength+1]; - str = TerminateNumber(buf, str, n); - if (str[0] == '-') return false; // strtoul() on a negative number?! - char* end; - errno = 0; - unsigned long r = strtoul(str, &end, radix); - if (end != str + n) return false; // Leftover junk - if (errno) return false; - if (dest == NULL) return true; - *(reinterpret_cast(dest)) = r; - return true; -} - -bool Arg::parse_short_radix(const char* str, - int n, - void* dest, - int radix) { - long r; - if (!parse_long_radix(str, n, &r, radix)) return false; // Could not parse - if (r < SHRT_MIN || r > SHRT_MAX) return false; // Out of range - if (dest == NULL) return true; - *(reinterpret_cast(dest)) = static_cast(r); - return true; -} - -bool Arg::parse_ushort_radix(const char* str, - int n, - void* dest, - int radix) { - unsigned long r; - if (!parse_ulong_radix(str, n, &r, radix)) return false; // Could not parse - if (r > USHRT_MAX) return false; // Out of range - if (dest == NULL) return true; - *(reinterpret_cast(dest)) = static_cast(r); - return true; -} - -bool Arg::parse_int_radix(const char* str, - int n, - void* dest, - int radix) { - long r; - if (!parse_long_radix(str, n, &r, radix)) return false; // Could not parse - if (r < INT_MIN || r > INT_MAX) return false; // Out of range - if (dest == NULL) return true; - *(reinterpret_cast(dest)) = r; - return true; -} - -bool Arg::parse_uint_radix(const char* str, - int n, - void* dest, - int radix) { - unsigned long r; - if (!parse_ulong_radix(str, n, &r, radix)) return false; // Could not parse - if (r > UINT_MAX) return false; // Out of range - if (dest == NULL) return true; - *(reinterpret_cast(dest)) = r; - return true; -} - -bool Arg::parse_longlong_radix(const char* str, - int n, - void* dest, - int radix) { -#ifndef HAVE_LONG_LONG - return false; -#else - if (n == 0) return false; - char buf[kMaxNumberLength+1]; - str = TerminateNumber(buf, str, n); - char* end; - errno = 0; -#if defined HAVE_STRTOQ - long long r = strtoq(str, &end, radix); -#elif defined HAVE_STRTOLL - long long r = strtoll(str, &end, radix); -#elif defined HAVE__STRTOI64 - long long r = _strtoi64(str, &end, radix); -#else -#error parse_longlong_radix: cannot convert input to a long-long -#endif - if (end != str + n) return false; // Leftover junk - if (errno) return false; - if (dest == NULL) return true; - *(reinterpret_cast(dest)) = r; - return true; -#endif /* HAVE_LONG_LONG */ -} - -bool Arg::parse_ulonglong_radix(const char* str, - int n, - void* dest, - int radix) { -#ifndef HAVE_UNSIGNED_LONG_LONG - return false; -#else - if (n == 0) return false; - char buf[kMaxNumberLength+1]; - str = TerminateNumber(buf, str, n); - if (str[0] == '-') return false; // strtoull() on a negative number?! - char* end; - errno = 0; -#if defined HAVE_STRTOQ - unsigned long long r = strtouq(str, &end, radix); -#elif defined HAVE_STRTOLL - unsigned long long r = strtoull(str, &end, radix); -#elif defined HAVE__STRTOI64 - unsigned long long r = _strtoui64(str, &end, radix); -#else -#error parse_ulonglong_radix: cannot convert input to a long-long -#endif - if (end != str + n) return false; // Leftover junk - if (errno) return false; - if (dest == NULL) return true; - *(reinterpret_cast(dest)) = r; - return true; -#endif /* HAVE_UNSIGNED_LONG_LONG */ -} - -bool Arg::parse_double(const char* str, int n, void* dest) { - if (n == 0) return false; - static const int kMaxLength = 200; - char buf[kMaxLength]; - if (n >= kMaxLength) return false; - memcpy(buf, str, n); - buf[n] = '\0'; - errno = 0; - char* end; - double r = strtod(buf, &end); - if (end != buf + n) return false; // Leftover junk - if (errno) return false; - if (dest == NULL) return true; - *(reinterpret_cast(dest)) = r; - return true; -} - -bool Arg::parse_float(const char* str, int n, void* dest) { - double r; - if (!parse_double(str, n, &r)) return false; - if (dest == NULL) return true; - *(reinterpret_cast(dest)) = static_cast(r); - return true; -} - - -#define DEFINE_INTEGER_PARSERS(name) \ - bool Arg::parse_##name(const char* str, int n, void* dest) { \ - return parse_##name##_radix(str, n, dest, 10); \ - } \ - bool Arg::parse_##name##_hex(const char* str, int n, void* dest) { \ - return parse_##name##_radix(str, n, dest, 16); \ - } \ - bool Arg::parse_##name##_octal(const char* str, int n, void* dest) { \ - return parse_##name##_radix(str, n, dest, 8); \ - } \ - bool Arg::parse_##name##_cradix(const char* str, int n, void* dest) { \ - return parse_##name##_radix(str, n, dest, 0); \ - } - -DEFINE_INTEGER_PARSERS(short) /* */ -DEFINE_INTEGER_PARSERS(ushort) /* */ -DEFINE_INTEGER_PARSERS(int) /* Don't use semicolons after these */ -DEFINE_INTEGER_PARSERS(uint) /* statements because they can cause */ -DEFINE_INTEGER_PARSERS(long) /* compiler warnings if the checking */ -DEFINE_INTEGER_PARSERS(ulong) /* level is turned up high enough. */ -DEFINE_INTEGER_PARSERS(longlong) /* */ -DEFINE_INTEGER_PARSERS(ulonglong) /* */ - -#undef DEFINE_INTEGER_PARSERS - -} // namespace pcrecpp diff --git a/libs/pcre/pcrecpp.h b/libs/pcre/pcrecpp.h deleted file mode 100644 index 3ee508ff81..0000000000 --- a/libs/pcre/pcrecpp.h +++ /dev/null @@ -1,709 +0,0 @@ -// Copyright (c) 2005, Google Inc. -// All rights reserved. -// -// Redistribution and use in source and binary forms, with or without -// modification, are permitted provided that the following conditions are -// met: -// -// * Redistributions of source code must retain the above copyright -// notice, this list of conditions and the following disclaimer. -// * Redistributions in binary form must reproduce the above -// copyright notice, this list of conditions and the following disclaimer -// in the documentation and/or other materials provided with the -// distribution. -// * Neither the name of Google Inc. nor the names of its -// contributors may be used to endorse or promote products derived from -// this software without specific prior written permission. -// -// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS -// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT -// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR -// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT -// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, -// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT -// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, -// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY -// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT -// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE -// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. -// -// Author: Sanjay Ghemawat -// Support for PCRE_XXX modifiers added by Giuseppe Maxia, July 2005 - -#ifndef _PCRECPP_H -#define _PCRECPP_H - -// C++ interface to the pcre regular-expression library. RE supports -// Perl-style regular expressions (with extensions like \d, \w, \s, -// ...). -// -// ----------------------------------------------------------------------- -// REGEXP SYNTAX: -// -// This module is part of the pcre library and hence supports its syntax -// for regular expressions. -// -// The syntax is pretty similar to Perl's. For those not familiar -// with Perl's regular expressions, here are some examples of the most -// commonly used extensions: -// -// "hello (\\w+) world" -- \w matches a "word" character -// "version (\\d+)" -- \d matches a digit -// "hello\\s+world" -- \s matches any whitespace character -// "\\b(\\w+)\\b" -- \b matches empty string at a word boundary -// "(?i)hello" -- (?i) turns on case-insensitive matching -// "/\\*(.*?)\\*/" -- .*? matches . minimum no. of times possible -// -// ----------------------------------------------------------------------- -// MATCHING INTERFACE: -// -// The "FullMatch" operation checks that supplied text matches a -// supplied pattern exactly. -// -// Example: successful match -// pcrecpp::RE re("h.*o"); -// re.FullMatch("hello"); -// -// Example: unsuccessful match (requires full match): -// pcrecpp::RE re("e"); -// !re.FullMatch("hello"); -// -// Example: creating a temporary RE object: -// pcrecpp::RE("h.*o").FullMatch("hello"); -// -// You can pass in a "const char*" or a "string" for "text". The -// examples below tend to use a const char*. -// -// You can, as in the different examples above, store the RE object -// explicitly in a variable or use a temporary RE object. The -// examples below use one mode or the other arbitrarily. Either -// could correctly be used for any of these examples. -// -// ----------------------------------------------------------------------- -// MATCHING WITH SUB-STRING EXTRACTION: -// -// You can supply extra pointer arguments to extract matched subpieces. -// -// Example: extracts "ruby" into "s" and 1234 into "i" -// int i; -// string s; -// pcrecpp::RE re("(\\w+):(\\d+)"); -// re.FullMatch("ruby:1234", &s, &i); -// -// Example: does not try to extract any extra sub-patterns -// re.FullMatch("ruby:1234", &s); -// -// Example: does not try to extract into NULL -// re.FullMatch("ruby:1234", NULL, &i); -// -// Example: integer overflow causes failure -// !re.FullMatch("ruby:1234567891234", NULL, &i); -// -// Example: fails because there aren't enough sub-patterns: -// !pcrecpp::RE("\\w+:\\d+").FullMatch("ruby:1234", &s); -// -// Example: fails because string cannot be stored in integer -// !pcrecpp::RE("(.*)").FullMatch("ruby", &i); -// -// The provided pointer arguments can be pointers to any scalar numeric -// type, or one of -// string (matched piece is copied to string) -// StringPiece (StringPiece is mutated to point to matched piece) -// T (where "bool T::ParseFrom(const char*, int)" exists) -// NULL (the corresponding matched sub-pattern is not copied) -// -// CAVEAT: An optional sub-pattern that does not exist in the matched -// string is assigned the empty string. Therefore, the following will -// return false (because the empty string is not a valid number): -// int number; -// pcrecpp::RE::FullMatch("abc", "[a-z]+(\\d+)?", &number); -// -// ----------------------------------------------------------------------- -// DO_MATCH -// -// The matching interface supports at most 16 arguments per call. -// If you need more, consider using the more general interface -// pcrecpp::RE::DoMatch(). See pcrecpp.h for the signature for DoMatch. -// -// ----------------------------------------------------------------------- -// PARTIAL MATCHES -// -// You can use the "PartialMatch" operation when you want the pattern -// to match any substring of the text. -// -// Example: simple search for a string: -// pcrecpp::RE("ell").PartialMatch("hello"); -// -// Example: find first number in a string: -// int number; -// pcrecpp::RE re("(\\d+)"); -// re.PartialMatch("x*100 + 20", &number); -// assert(number == 100); -// -// ----------------------------------------------------------------------- -// UTF-8 AND THE MATCHING INTERFACE: -// -// By default, pattern and text are plain text, one byte per character. -// The UTF8 flag, passed to the constructor, causes both pattern -// and string to be treated as UTF-8 text, still a byte stream but -// potentially multiple bytes per character. In practice, the text -// is likelier to be UTF-8 than the pattern, but the match returned -// may depend on the UTF8 flag, so always use it when matching -// UTF8 text. E.g., "." will match one byte normally but with UTF8 -// set may match up to three bytes of a multi-byte character. -// -// Example: -// pcrecpp::RE_Options options; -// options.set_utf8(); -// pcrecpp::RE re(utf8_pattern, options); -// re.FullMatch(utf8_string); -// -// Example: using the convenience function UTF8(): -// pcrecpp::RE re(utf8_pattern, pcrecpp::UTF8()); -// re.FullMatch(utf8_string); -// -// NOTE: The UTF8 option is ignored if pcre was not configured with the -// --enable-utf8 flag. -// -// ----------------------------------------------------------------------- -// PASSING MODIFIERS TO THE REGULAR EXPRESSION ENGINE -// -// PCRE defines some modifiers to change the behavior of the regular -// expression engine. -// The C++ wrapper defines an auxiliary class, RE_Options, as a vehicle -// to pass such modifiers to a RE class. -// -// Currently, the following modifiers are supported -// -// modifier description Perl corresponding -// -// PCRE_CASELESS case insensitive match /i -// PCRE_MULTILINE multiple lines match /m -// PCRE_DOTALL dot matches newlines /s -// PCRE_DOLLAR_ENDONLY $ matches only at end N/A -// PCRE_EXTRA strict escape parsing N/A -// PCRE_EXTENDED ignore whitespaces /x -// PCRE_UTF8 handles UTF8 chars built-in -// PCRE_UNGREEDY reverses * and *? N/A -// PCRE_NO_AUTO_CAPTURE disables matching parens N/A (*) -// -// (For a full account on how each modifier works, please check the -// PCRE API reference manual). -// -// (*) Both Perl and PCRE allow non matching parentheses by means of the -// "?:" modifier within the pattern itself. e.g. (?:ab|cd) does not -// capture, while (ab|cd) does. -// -// For each modifier, there are two member functions whose name is made -// out of the modifier in lowercase, without the "PCRE_" prefix. For -// instance, PCRE_CASELESS is handled by -// bool caseless(), -// which returns true if the modifier is set, and -// RE_Options & set_caseless(bool), -// which sets or unsets the modifier. -// -// Moreover, PCRE_EXTRA_MATCH_LIMIT can be accessed through the -// set_match_limit() and match_limit() member functions. -// Setting match_limit to a non-zero value will limit the executation of -// pcre to keep it from doing bad things like blowing the stack or taking -// an eternity to return a result. A value of 5000 is good enough to stop -// stack blowup in a 2MB thread stack. Setting match_limit to zero will -// disable match limiting. Alternately, you can set match_limit_recursion() -// which uses PCRE_EXTRA_MATCH_LIMIT_RECURSION to limit how much pcre -// recurses. match_limit() caps the number of matches pcre does; -// match_limit_recrusion() caps the depth of recursion. -// -// Normally, to pass one or more modifiers to a RE class, you declare -// a RE_Options object, set the appropriate options, and pass this -// object to a RE constructor. Example: -// -// RE_options opt; -// opt.set_caseless(true); -// -// if (RE("HELLO", opt).PartialMatch("hello world")) ... -// -// RE_options has two constructors. The default constructor takes no -// arguments and creates a set of flags that are off by default. -// -// The optional parameter 'option_flags' is to facilitate transfer -// of legacy code from C programs. This lets you do -// RE(pattern, RE_Options(PCRE_CASELESS|PCRE_MULTILINE)).PartialMatch(str); -// -// But new code is better off doing -// RE(pattern, -// RE_Options().set_caseless(true).set_multiline(true)).PartialMatch(str); -// (See below) -// -// If you are going to pass one of the most used modifiers, there are some -// convenience functions that return a RE_Options class with the -// appropriate modifier already set: -// CASELESS(), UTF8(), MULTILINE(), DOTALL(), EXTENDED() -// -// If you need to set several options at once, and you don't want to go -// through the pains of declaring a RE_Options object and setting several -// options, there is a parallel method that give you such ability on the -// fly. You can concatenate several set_xxxxx member functions, since each -// of them returns a reference to its class object. e.g.: to pass -// PCRE_CASELESS, PCRE_EXTENDED, and PCRE_MULTILINE to a RE with one -// statement, you may write -// -// RE(" ^ xyz \\s+ .* blah$", RE_Options() -// .set_caseless(true) -// .set_extended(true) -// .set_multiline(true)).PartialMatch(sometext); -// -// ----------------------------------------------------------------------- -// SCANNING TEXT INCREMENTALLY -// -// The "Consume" operation may be useful if you want to repeatedly -// match regular expressions at the front of a string and skip over -// them as they match. This requires use of the "StringPiece" type, -// which represents a sub-range of a real string. Like RE, StringPiece -// is defined in the pcrecpp namespace. -// -// Example: read lines of the form "var = value" from a string. -// string contents = ...; // Fill string somehow -// pcrecpp::StringPiece input(contents); // Wrap in a StringPiece -// -// string var; -// int value; -// pcrecpp::RE re("(\\w+) = (\\d+)\n"); -// while (re.Consume(&input, &var, &value)) { -// ...; -// } -// -// Each successful call to "Consume" will set "var/value", and also -// advance "input" so it points past the matched text. -// -// The "FindAndConsume" operation is similar to "Consume" but does not -// anchor your match at the beginning of the string. For example, you -// could extract all words from a string by repeatedly calling -// pcrecpp::RE("(\\w+)").FindAndConsume(&input, &word) -// -// ----------------------------------------------------------------------- -// PARSING HEX/OCTAL/C-RADIX NUMBERS -// -// By default, if you pass a pointer to a numeric value, the -// corresponding text is interpreted as a base-10 number. You can -// instead wrap the pointer with a call to one of the operators Hex(), -// Octal(), or CRadix() to interpret the text in another base. The -// CRadix operator interprets C-style "0" (base-8) and "0x" (base-16) -// prefixes, but defaults to base-10. -// -// Example: -// int a, b, c, d; -// pcrecpp::RE re("(.*) (.*) (.*) (.*)"); -// re.FullMatch("100 40 0100 0x40", -// pcrecpp::Octal(&a), pcrecpp::Hex(&b), -// pcrecpp::CRadix(&c), pcrecpp::CRadix(&d)); -// will leave 64 in a, b, c, and d. -// -// ----------------------------------------------------------------------- -// REPLACING PARTS OF STRINGS -// -// You can replace the first match of "pattern" in "str" with -// "rewrite". Within "rewrite", backslash-escaped digits (\1 to \9) -// can be used to insert text matching corresponding parenthesized -// group from the pattern. \0 in "rewrite" refers to the entire -// matching text. E.g., -// -// string s = "yabba dabba doo"; -// pcrecpp::RE("b+").Replace("d", &s); -// -// will leave "s" containing "yada dabba doo". The result is true if -// the pattern matches and a replacement occurs, or false otherwise. -// -// GlobalReplace() is like Replace(), except that it replaces all -// occurrences of the pattern in the string with the rewrite. -// Replacements are not subject to re-matching. E.g., -// -// string s = "yabba dabba doo"; -// pcrecpp::RE("b+").GlobalReplace("d", &s); -// -// will leave "s" containing "yada dada doo". It returns the number -// of replacements made. -// -// Extract() is like Replace(), except that if the pattern matches, -// "rewrite" is copied into "out" (an additional argument) with -// substitutions. The non-matching portions of "text" are ignored. -// Returns true iff a match occurred and the extraction happened -// successfully. If no match occurs, the string is left unaffected. - - -#include -#include -#include // defines the Arg class -// This isn't technically needed here, but we include it -// anyway so folks who include pcrecpp.h don't have to. -#include - -namespace pcrecpp { - -#define PCRE_SET_OR_CLEAR(b, o) \ - if (b) all_options_ |= (o); else all_options_ &= ~(o); \ - return *this - -#define PCRE_IS_SET(o) \ - (all_options_ & o) == o - -/***** Compiling regular expressions: the RE class *****/ - -// RE_Options allow you to set options to be passed along to pcre, -// along with other options we put on top of pcre. -// Only 9 modifiers, plus match_limit and match_limit_recursion, -// are supported now. -class PCRECPP_EXP_DEFN RE_Options { - public: - // constructor - RE_Options() : match_limit_(0), match_limit_recursion_(0), all_options_(0) {} - - // alternative constructor. - // To facilitate transfer of legacy code from C programs - // - // This lets you do - // RE(pattern, RE_Options(PCRE_CASELESS|PCRE_MULTILINE)).PartialMatch(str); - // But new code is better off doing - // RE(pattern, - // RE_Options().set_caseless(true).set_multiline(true)).PartialMatch(str); - RE_Options(int option_flags) : match_limit_(0), match_limit_recursion_(0), - all_options_(option_flags) {} - // we're fine with the default destructor, copy constructor, etc. - - // accessors and mutators - int match_limit() const { return match_limit_; }; - RE_Options &set_match_limit(int limit) { - match_limit_ = limit; - return *this; - } - - int match_limit_recursion() const { return match_limit_recursion_; }; - RE_Options &set_match_limit_recursion(int limit) { - match_limit_recursion_ = limit; - return *this; - } - - bool caseless() const { - return PCRE_IS_SET(PCRE_CASELESS); - } - RE_Options &set_caseless(bool x) { - PCRE_SET_OR_CLEAR(x, PCRE_CASELESS); - } - - bool multiline() const { - return PCRE_IS_SET(PCRE_MULTILINE); - } - RE_Options &set_multiline(bool x) { - PCRE_SET_OR_CLEAR(x, PCRE_MULTILINE); - } - - bool dotall() const { - return PCRE_IS_SET(PCRE_DOTALL); - } - RE_Options &set_dotall(bool x) { - PCRE_SET_OR_CLEAR(x, PCRE_DOTALL); - } - - bool extended() const { - return PCRE_IS_SET(PCRE_EXTENDED); - } - RE_Options &set_extended(bool x) { - PCRE_SET_OR_CLEAR(x, PCRE_EXTENDED); - } - - bool dollar_endonly() const { - return PCRE_IS_SET(PCRE_DOLLAR_ENDONLY); - } - RE_Options &set_dollar_endonly(bool x) { - PCRE_SET_OR_CLEAR(x, PCRE_DOLLAR_ENDONLY); - } - - bool extra() const { - return PCRE_IS_SET(PCRE_EXTRA); - } - RE_Options &set_extra(bool x) { - PCRE_SET_OR_CLEAR(x, PCRE_EXTRA); - } - - bool ungreedy() const { - return PCRE_IS_SET(PCRE_UNGREEDY); - } - RE_Options &set_ungreedy(bool x) { - PCRE_SET_OR_CLEAR(x, PCRE_UNGREEDY); - } - - bool utf8() const { - return PCRE_IS_SET(PCRE_UTF8); - } - RE_Options &set_utf8(bool x) { - PCRE_SET_OR_CLEAR(x, PCRE_UTF8); - } - - bool no_auto_capture() const { - return PCRE_IS_SET(PCRE_NO_AUTO_CAPTURE); - } - RE_Options &set_no_auto_capture(bool x) { - PCRE_SET_OR_CLEAR(x, PCRE_NO_AUTO_CAPTURE); - } - - RE_Options &set_all_options(int opt) { - all_options_ = opt; - return *this; - } - int all_options() const { - return all_options_ ; - } - - // TODO: add other pcre flags - - private: - int match_limit_; - int match_limit_recursion_; - int all_options_; -}; - -// These functions return some common RE_Options -static inline RE_Options UTF8() { - return RE_Options().set_utf8(true); -} - -static inline RE_Options CASELESS() { - return RE_Options().set_caseless(true); -} -static inline RE_Options MULTILINE() { - return RE_Options().set_multiline(true); -} - -static inline RE_Options DOTALL() { - return RE_Options().set_dotall(true); -} - -static inline RE_Options EXTENDED() { - return RE_Options().set_extended(true); -} - -// Interface for regular expression matching. Also corresponds to a -// pre-compiled regular expression. An "RE" object is safe for -// concurrent use by multiple threads. -class PCRECPP_EXP_DEFN RE { - public: - // We provide implicit conversions from strings so that users can - // pass in a string or a "const char*" wherever an "RE" is expected. - RE(const string& pat) { Init(pat, NULL); } - RE(const string& pat, const RE_Options& option) { Init(pat, &option); } - RE(const char* pat) { Init(pat, NULL); } - RE(const char* pat, const RE_Options& option) { Init(pat, &option); } - RE(const unsigned char* pat) { - Init(reinterpret_cast(pat), NULL); - } - RE(const unsigned char* pat, const RE_Options& option) { - Init(reinterpret_cast(pat), &option); - } - - // Copy constructor & assignment - note that these are expensive - // because they recompile the expression. - RE(const RE& re) { Init(re.pattern_, &re.options_); } - const RE& operator=(const RE& re) { - if (this != &re) { - Cleanup(); - - // This is the code that originally came from Google - // Init(re.pattern_.c_str(), &re.options_); - - // This is the replacement from Ari Pollak - Init(re.pattern_, &re.options_); - } - return *this; - } - - - ~RE(); - - // The string specification for this RE. E.g. - // RE re("ab*c?d+"); - // re.pattern(); // "ab*c?d+" - const string& pattern() const { return pattern_; } - - // If RE could not be created properly, returns an error string. - // Else returns the empty string. - const string& error() const { return *error_; } - - /***** The useful part: the matching interface *****/ - - // This is provided so one can do pattern.ReplaceAll() just as - // easily as ReplaceAll(pattern-text, ....) - - bool FullMatch(const StringPiece& text, - const Arg& ptr1 = no_arg, - const Arg& ptr2 = no_arg, - const Arg& ptr3 = no_arg, - const Arg& ptr4 = no_arg, - const Arg& ptr5 = no_arg, - const Arg& ptr6 = no_arg, - const Arg& ptr7 = no_arg, - const Arg& ptr8 = no_arg, - const Arg& ptr9 = no_arg, - const Arg& ptr10 = no_arg, - const Arg& ptr11 = no_arg, - const Arg& ptr12 = no_arg, - const Arg& ptr13 = no_arg, - const Arg& ptr14 = no_arg, - const Arg& ptr15 = no_arg, - const Arg& ptr16 = no_arg) const; - - bool PartialMatch(const StringPiece& text, - const Arg& ptr1 = no_arg, - const Arg& ptr2 = no_arg, - const Arg& ptr3 = no_arg, - const Arg& ptr4 = no_arg, - const Arg& ptr5 = no_arg, - const Arg& ptr6 = no_arg, - const Arg& ptr7 = no_arg, - const Arg& ptr8 = no_arg, - const Arg& ptr9 = no_arg, - const Arg& ptr10 = no_arg, - const Arg& ptr11 = no_arg, - const Arg& ptr12 = no_arg, - const Arg& ptr13 = no_arg, - const Arg& ptr14 = no_arg, - const Arg& ptr15 = no_arg, - const Arg& ptr16 = no_arg) const; - - bool Consume(StringPiece* input, - const Arg& ptr1 = no_arg, - const Arg& ptr2 = no_arg, - const Arg& ptr3 = no_arg, - const Arg& ptr4 = no_arg, - const Arg& ptr5 = no_arg, - const Arg& ptr6 = no_arg, - const Arg& ptr7 = no_arg, - const Arg& ptr8 = no_arg, - const Arg& ptr9 = no_arg, - const Arg& ptr10 = no_arg, - const Arg& ptr11 = no_arg, - const Arg& ptr12 = no_arg, - const Arg& ptr13 = no_arg, - const Arg& ptr14 = no_arg, - const Arg& ptr15 = no_arg, - const Arg& ptr16 = no_arg) const; - - bool FindAndConsume(StringPiece* input, - const Arg& ptr1 = no_arg, - const Arg& ptr2 = no_arg, - const Arg& ptr3 = no_arg, - const Arg& ptr4 = no_arg, - const Arg& ptr5 = no_arg, - const Arg& ptr6 = no_arg, - const Arg& ptr7 = no_arg, - const Arg& ptr8 = no_arg, - const Arg& ptr9 = no_arg, - const Arg& ptr10 = no_arg, - const Arg& ptr11 = no_arg, - const Arg& ptr12 = no_arg, - const Arg& ptr13 = no_arg, - const Arg& ptr14 = no_arg, - const Arg& ptr15 = no_arg, - const Arg& ptr16 = no_arg) const; - - bool Replace(const StringPiece& rewrite, - string *str) const; - - int GlobalReplace(const StringPiece& rewrite, - string *str) const; - - bool Extract(const StringPiece &rewrite, - const StringPiece &text, - string *out) const; - - // Escapes all potentially meaningful regexp characters in - // 'unquoted'. The returned string, used as a regular expression, - // will exactly match the original string. For example, - // 1.5-2.0? - // may become: - // 1\.5\-2\.0\? - // Note QuoteMeta behaves the same as perl's QuoteMeta function, - // *except* that it escapes the NUL character (\0) as backslash + 0, - // rather than backslash + NUL. - static string QuoteMeta(const StringPiece& unquoted); - - - /***** Generic matching interface *****/ - - // Type of match (TODO: Should be restructured as part of RE_Options) - enum Anchor { - UNANCHORED, // No anchoring - ANCHOR_START, // Anchor at start only - ANCHOR_BOTH // Anchor at start and end - }; - - // General matching routine. Stores the length of the match in - // "*consumed" if successful. - bool DoMatch(const StringPiece& text, - Anchor anchor, - int* consumed, - const Arg* const* args, int n) const; - - // Return the number of capturing subpatterns, or -1 if the - // regexp wasn't valid on construction. - int NumberOfCapturingGroups() const; - - // The default value for an argument, to indicate the end of the argument - // list. This must be used only in optional argument defaults. It should NOT - // be passed explicitly. Some people have tried to use it like this: - // - // FullMatch(x, y, &z, no_arg, &w); - // - // This is a mistake, and will not work. - static Arg no_arg; - - private: - - void Init(const string& pattern, const RE_Options* options); - void Cleanup(); - - // Match against "text", filling in "vec" (up to "vecsize" * 2/3) with - // pairs of integers for the beginning and end positions of matched - // text. The first pair corresponds to the entire matched text; - // subsequent pairs correspond, in order, to parentheses-captured - // matches. Returns the number of pairs (one more than the number of - // the last subpattern with a match) if matching was successful - // and zero if the match failed. - // I.e. for RE("(foo)|(bar)|(baz)") it will return 2, 3, and 4 when matching - // against "foo", "bar", and "baz" respectively. - // When matching RE("(foo)|hello") against "hello", it will return 1. - // But the values for all subpattern are filled in into "vec". - int TryMatch(const StringPiece& text, - int startpos, - Anchor anchor, - int *vec, - int vecsize) const; - - // Append the "rewrite" string, with backslash subsitutions from "text" - // and "vec", to string "out". - bool Rewrite(string *out, - const StringPiece& rewrite, - const StringPiece& text, - int *vec, - int veclen) const; - - // internal implementation for DoMatch - bool DoMatchImpl(const StringPiece& text, - Anchor anchor, - int* consumed, - const Arg* const args[], - int n, - int* vec, - int vecsize) const; - - // Compile the regexp for the specified anchoring mode - pcre* Compile(Anchor anchor); - - string pattern_; - RE_Options options_; - pcre* re_full_; // For full matches - pcre* re_partial_; // For partial matches - const string* error_; // Error indicator (or points to empty string) -}; - -} // namespace pcrecpp - -#endif /* _PCRECPP_H */ diff --git a/libs/pcre/pcrecpp_internal.h b/libs/pcre/pcrecpp_internal.h deleted file mode 100644 index 827f9e04e2..0000000000 --- a/libs/pcre/pcrecpp_internal.h +++ /dev/null @@ -1,71 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* -Copyright (c) 2005, Google Inc. -All rights reserved. - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -#ifndef PCRECPP_INTERNAL_H -#define PCRECPP_INTERNAL_H - -/* When compiling a DLL for Windows, the exported symbols have to be declared -using some MS magic. I found some useful information on this web page: -http://msdn2.microsoft.com/en-us/library/y4h7bcy6(VS.80).aspx. According to the -information there, using __declspec(dllexport) without "extern" we have a -definition; with "extern" we have a declaration. The settings here override the -setting in pcre.h. We use: - - PCRECPP_EXP_DECL for declarations - PCRECPP_EXP_DEFN for definitions of exported functions - -*/ - -#ifndef PCRECPP_EXP_DECL -# ifdef _WIN32 -# ifndef PCRE_STATIC -# define PCRECPP_EXP_DECL extern __declspec(dllexport) -# define PCRECPP_EXP_DEFN __declspec(dllexport) -# else -# define PCRECPP_EXP_DECL extern -# define PCRECPP_EXP_DEFN -# endif -# else -# define PCRECPP_EXP_DECL extern -# define PCRECPP_EXP_DEFN -# endif -#endif - -#endif /* PCRECPP_INTERNAL_H */ - -/* End of pcrecpp_internal.h */ diff --git a/libs/pcre/pcrecpp_unittest.cc b/libs/pcre/pcrecpp_unittest.cc deleted file mode 100644 index 44e0cc9558..0000000000 --- a/libs/pcre/pcrecpp_unittest.cc +++ /dev/null @@ -1,1276 +0,0 @@ -// -*- coding: utf-8 -*- -// -// Copyright (c) 2005 - 2006, Google Inc. -// All rights reserved. -// -// Redistribution and use in source and binary forms, with or without -// modification, are permitted provided that the following conditions are -// met: -// -// * Redistributions of source code must retain the above copyright -// notice, this list of conditions and the following disclaimer. -// * Redistributions in binary form must reproduce the above -// copyright notice, this list of conditions and the following disclaimer -// in the documentation and/or other materials provided with the -// distribution. -// * Neither the name of Google Inc. nor the names of its -// contributors may be used to endorse or promote products derived from -// this software without specific prior written permission. -// -// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS -// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT -// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR -// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT -// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, -// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT -// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, -// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY -// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT -// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE -// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. -// -// Author: Sanjay Ghemawat -// -// TODO: Test extractions for PartialMatch/Consume - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include -#include -#include -#include "pcrecpp.h" - -using pcrecpp::StringPiece; -using pcrecpp::RE; -using pcrecpp::RE_Options; -using pcrecpp::Hex; -using pcrecpp::Octal; -using pcrecpp::CRadix; - -static bool VERBOSE_TEST = false; - -// CHECK dies with a fatal error if condition is not true. It is *not* -// controlled by NDEBUG, so the check will be executed regardless of -// compilation mode. Therefore, it is safe to do things like: -// CHECK_EQ(fp->Write(x), 4) -#define CHECK(condition) do { \ - if (!(condition)) { \ - fprintf(stderr, "%s:%d: Check failed: %s\n", \ - __FILE__, __LINE__, #condition); \ - exit(1); \ - } \ -} while (0) - -#define CHECK_EQ(a, b) CHECK(a == b) - -static void Timing1(int num_iters) { - // Same pattern lots of times - RE pattern("ruby:\\d+"); - StringPiece p("ruby:1234"); - for (int j = num_iters; j > 0; j--) { - CHECK(pattern.FullMatch(p)); - } -} - -static void Timing2(int num_iters) { - // Same pattern lots of times - RE pattern("ruby:(\\d+)"); - int i; - for (int j = num_iters; j > 0; j--) { - CHECK(pattern.FullMatch("ruby:1234", &i)); - CHECK_EQ(i, 1234); - } -} - -static void Timing3(int num_iters) { - string text_string; - for (int j = num_iters; j > 0; j--) { - text_string += "this is another line\n"; - } - - RE line_matcher(".*\n"); - string line; - StringPiece text(text_string); - int counter = 0; - while (line_matcher.Consume(&text)) { - counter++; - } - printf("Matched %d lines\n", counter); -} - -#if 0 // uncomment this if you have a way of defining VirtualProcessSize() - -static void LeakTest() { - // Check for memory leaks - unsigned long long initial_size = 0; - for (int i = 0; i < 100000; i++) { - if (i == 50000) { - initial_size = VirtualProcessSize(); - printf("Size after 50000: %llu\n", initial_size); - } - char buf[100]; // definitely big enough - sprintf(buf, "pat%09d", i); - RE newre(buf); - } - uint64 final_size = VirtualProcessSize(); - printf("Size after 100000: %llu\n", final_size); - const double growth = double(final_size - initial_size) / final_size; - printf("Growth: %0.2f%%", growth * 100); - CHECK(growth < 0.02); // Allow < 2% growth -} - -#endif - -static void RadixTests() { - printf("Testing hex\n"); - -#define CHECK_HEX(type, value) \ - do { \ - type v; \ - CHECK(RE("([0-9a-fA-F]+)[uUlL]*").FullMatch(#value, Hex(&v))); \ - CHECK_EQ(v, 0x ## value); \ - CHECK(RE("([0-9a-fA-FxX]+)[uUlL]*").FullMatch("0x" #value, CRadix(&v))); \ - CHECK_EQ(v, 0x ## value); \ - } while(0) - - CHECK_HEX(short, 2bad); - CHECK_HEX(unsigned short, 2badU); - CHECK_HEX(int, dead); - CHECK_HEX(unsigned int, deadU); - CHECK_HEX(long, 7eadbeefL); - CHECK_HEX(unsigned long, deadbeefUL); -#ifdef HAVE_LONG_LONG - CHECK_HEX(long long, 12345678deadbeefLL); -#endif -#ifdef HAVE_UNSIGNED_LONG_LONG - CHECK_HEX(unsigned long long, cafebabedeadbeefULL); -#endif - -#undef CHECK_HEX - - printf("Testing octal\n"); - -#define CHECK_OCTAL(type, value) \ - do { \ - type v; \ - CHECK(RE("([0-7]+)[uUlL]*").FullMatch(#value, Octal(&v))); \ - CHECK_EQ(v, 0 ## value); \ - CHECK(RE("([0-9a-fA-FxX]+)[uUlL]*").FullMatch("0" #value, CRadix(&v))); \ - CHECK_EQ(v, 0 ## value); \ - } while(0) - - CHECK_OCTAL(short, 77777); - CHECK_OCTAL(unsigned short, 177777U); - CHECK_OCTAL(int, 17777777777); - CHECK_OCTAL(unsigned int, 37777777777U); - CHECK_OCTAL(long, 17777777777L); - CHECK_OCTAL(unsigned long, 37777777777UL); -#ifdef HAVE_LONG_LONG - CHECK_OCTAL(long long, 777777777777777777777LL); -#endif -#ifdef HAVE_UNSIGNED_LONG_LONG - CHECK_OCTAL(unsigned long long, 1777777777777777777777ULL); -#endif - -#undef CHECK_OCTAL - - printf("Testing decimal\n"); - -#define CHECK_DECIMAL(type, value) \ - do { \ - type v; \ - CHECK(RE("(-?[0-9]+)[uUlL]*").FullMatch(#value, &v)); \ - CHECK_EQ(v, value); \ - CHECK(RE("(-?[0-9a-fA-FxX]+)[uUlL]*").FullMatch(#value, CRadix(&v))); \ - CHECK_EQ(v, value); \ - } while(0) - - CHECK_DECIMAL(short, -1); - CHECK_DECIMAL(unsigned short, 9999); - CHECK_DECIMAL(int, -1000); - CHECK_DECIMAL(unsigned int, 12345U); - CHECK_DECIMAL(long, -10000000L); - CHECK_DECIMAL(unsigned long, 3083324652U); -#ifdef HAVE_LONG_LONG - CHECK_DECIMAL(long long, -100000000000000LL); -#endif -#ifdef HAVE_UNSIGNED_LONG_LONG - CHECK_DECIMAL(unsigned long long, 1234567890987654321ULL); -#endif - -#undef CHECK_DECIMAL - -} - -static void TestReplace() { - printf("Testing Replace\n"); - - struct ReplaceTest { - const char *regexp; - const char *rewrite; - const char *original; - const char *single; - const char *global; - int global_count; // the expected return value from ReplaceAll - }; - static const ReplaceTest tests[] = { - { "(qu|[b-df-hj-np-tv-z]*)([a-z]+)", - "\\2\\1ay", - "the quick brown fox jumps over the lazy dogs.", - "ethay quick brown fox jumps over the lazy dogs.", - "ethay ickquay ownbray oxfay umpsjay overay ethay azylay ogsday.", - 9 }, - { "\\w+", - "\\0-NOSPAM", - "paul.haahr@google.com", - "paul-NOSPAM.haahr@google.com", - "paul-NOSPAM.haahr-NOSPAM@google-NOSPAM.com-NOSPAM", - 4 }, - { "^", - "(START)", - "foo", - "(START)foo", - "(START)foo", - 1 }, - { "^", - "(START)", - "", - "(START)", - "(START)", - 1 }, - { "$", - "(END)", - "", - "(END)", - "(END)", - 1 }, - { "b", - "bb", - "ababababab", - "abbabababab", - "abbabbabbabbabb", - 5 }, - { "b", - "bb", - "bbbbbb", - "bbbbbbb", - "bbbbbbbbbbbb", - 6 }, - { "b+", - "bb", - "bbbbbb", - "bb", - "bb", - 1 }, - { "b*", - "bb", - "bbbbbb", - "bb", - "bb", - 1 }, - { "b*", - "bb", - "aaaaa", - "bbaaaaa", - "bbabbabbabbabbabb", - 6 }, - { "b*", - "bb", - "aa\naa\n", - "bbaa\naa\n", - "bbabbabb\nbbabbabb\nbb", - 7 }, - { "b*", - "bb", - "aa\raa\r", - "bbaa\raa\r", - "bbabbabb\rbbabbabb\rbb", - 7 }, - { "b*", - "bb", - "aa\r\naa\r\n", - "bbaa\r\naa\r\n", - "bbabbabb\r\nbbabbabb\r\nbb", - 7 }, -#ifdef SUPPORT_UTF8 - { "b*", - "bb", - "\xE3\x83\x9B\xE3\x83\xBC\xE3\x83\xA0\xE3\x81\xB8", // utf8 - "bb\xE3\x83\x9B\xE3\x83\xBC\xE3\x83\xA0\xE3\x81\xB8", - "bb\xE3\x83\x9B""bb""\xE3\x83\xBC""bb""\xE3\x83\xA0""bb""\xE3\x81\xB8""bb", - 5 }, - { "b*", - "bb", - "\xE3\x83\x9B\r\n\xE3\x83\xBC\r\xE3\x83\xA0\n\xE3\x81\xB8\r\n", // utf8 - "bb\xE3\x83\x9B\r\n\xE3\x83\xBC\r\xE3\x83\xA0\n\xE3\x81\xB8\r\n", - ("bb\xE3\x83\x9B""bb\r\nbb""\xE3\x83\xBC""bb\rbb""\xE3\x83\xA0" - "bb\nbb""\xE3\x81\xB8""bb\r\nbb"), - 9 }, -#endif - { "", NULL, NULL, NULL, NULL, 0 } - }; - -#ifdef SUPPORT_UTF8 - const bool support_utf8 = true; -#else - const bool support_utf8 = false; -#endif - - for (const ReplaceTest *t = tests; t->original != NULL; ++t) { - RE re(t->regexp, RE_Options(PCRE_NEWLINE_CRLF).set_utf8(support_utf8)); - assert(re.error().empty()); - string one(t->original); - CHECK(re.Replace(t->rewrite, &one)); - CHECK_EQ(one, t->single); - string all(t->original); - const int replace_count = re.GlobalReplace(t->rewrite, &all); - CHECK_EQ(all, t->global); - CHECK_EQ(replace_count, t->global_count); - } - - // One final test: test \r\n replacement when we're not in CRLF mode - { - RE re("b*", RE_Options(PCRE_NEWLINE_CR).set_utf8(support_utf8)); - assert(re.error().empty()); - string all("aa\r\naa\r\n"); - CHECK_EQ(re.GlobalReplace("bb", &all), 9); - CHECK_EQ(all, string("bbabbabb\rbb\nbbabbabb\rbb\nbb")); - } - { - RE re("b*", RE_Options(PCRE_NEWLINE_LF).set_utf8(support_utf8)); - assert(re.error().empty()); - string all("aa\r\naa\r\n"); - CHECK_EQ(re.GlobalReplace("bb", &all), 9); - CHECK_EQ(all, string("bbabbabb\rbb\nbbabbabb\rbb\nbb")); - } - // TODO: test what happens when no PCRE_NEWLINE_* flag is set. - // Alas, the answer depends on how pcre was compiled. -} - -static void TestExtract() { - printf("Testing Extract\n"); - - string s; - - CHECK(RE("(.*)@([^.]*)").Extract("\\2!\\1", "boris@kremvax.ru", &s)); - CHECK_EQ(s, "kremvax!boris"); - - // check the RE interface as well - CHECK(RE(".*").Extract("'\\0'", "foo", &s)); - CHECK_EQ(s, "'foo'"); - CHECK(!RE("bar").Extract("'\\0'", "baz", &s)); - CHECK_EQ(s, "'foo'"); -} - -static void TestConsume() { - printf("Testing Consume\n"); - - string word; - - string s(" aaa b!@#$@#$cccc"); - StringPiece input(s); - - RE r("\\s*(\\w+)"); // matches a word, possibly proceeded by whitespace - CHECK(r.Consume(&input, &word)); - CHECK_EQ(word, "aaa"); - CHECK(r.Consume(&input, &word)); - CHECK_EQ(word, "b"); - CHECK(! r.Consume(&input, &word)); -} - -static void TestFindAndConsume() { - printf("Testing FindAndConsume\n"); - - string word; - - string s(" aaa b!@#$@#$cccc"); - StringPiece input(s); - - RE r("(\\w+)"); // matches a word - CHECK(r.FindAndConsume(&input, &word)); - CHECK_EQ(word, "aaa"); - CHECK(r.FindAndConsume(&input, &word)); - CHECK_EQ(word, "b"); - CHECK(r.FindAndConsume(&input, &word)); - CHECK_EQ(word, "cccc"); - CHECK(! r.FindAndConsume(&input, &word)); -} - -static void TestMatchNumberPeculiarity() { - printf("Testing match-number peculiaraity\n"); - - string word1; - string word2; - string word3; - - RE r("(foo)|(bar)|(baz)"); - CHECK(r.PartialMatch("foo", &word1, &word2, &word3)); - CHECK_EQ(word1, "foo"); - CHECK_EQ(word2, ""); - CHECK_EQ(word3, ""); - CHECK(r.PartialMatch("bar", &word1, &word2, &word3)); - CHECK_EQ(word1, ""); - CHECK_EQ(word2, "bar"); - CHECK_EQ(word3, ""); - CHECK(r.PartialMatch("baz", &word1, &word2, &word3)); - CHECK_EQ(word1, ""); - CHECK_EQ(word2, ""); - CHECK_EQ(word3, "baz"); - CHECK(!r.PartialMatch("f", &word1, &word2, &word3)); - - string a; - CHECK(RE("(foo)|hello").FullMatch("hello", &a)); - CHECK_EQ(a, ""); -} - -static void TestRecursion() { - printf("Testing recursion\n"); - - // Get one string that passes (sometimes), one that never does. - string text_good("abcdefghijk"); - string text_bad("acdefghijkl"); - - // According to pcretest, matching text_good against (\w+)*b - // requires match_limit of at least 8192, and match_recursion_limit - // of at least 37. - - RE_Options options_ml; - options_ml.set_match_limit(8192); - RE re("(\\w+)*b", options_ml); - CHECK(re.PartialMatch(text_good) == true); - CHECK(re.PartialMatch(text_bad) == false); - CHECK(re.FullMatch(text_good) == false); - CHECK(re.FullMatch(text_bad) == false); - - options_ml.set_match_limit(1024); - RE re2("(\\w+)*b", options_ml); - CHECK(re2.PartialMatch(text_good) == false); // because of match_limit - CHECK(re2.PartialMatch(text_bad) == false); - CHECK(re2.FullMatch(text_good) == false); - CHECK(re2.FullMatch(text_bad) == false); - - RE_Options options_mlr; - options_mlr.set_match_limit_recursion(50); - RE re3("(\\w+)*b", options_mlr); - CHECK(re3.PartialMatch(text_good) == true); - CHECK(re3.PartialMatch(text_bad) == false); - CHECK(re3.FullMatch(text_good) == false); - CHECK(re3.FullMatch(text_bad) == false); - - options_mlr.set_match_limit_recursion(10); - RE re4("(\\w+)*b", options_mlr); - CHECK(re4.PartialMatch(text_good) == false); - CHECK(re4.PartialMatch(text_bad) == false); - CHECK(re4.FullMatch(text_good) == false); - CHECK(re4.FullMatch(text_bad) == false); -} - -// A meta-quoted string, interpreted as a pattern, should always match -// the original unquoted string. -static void TestQuoteMeta(string unquoted, RE_Options options = RE_Options()) { - string quoted = RE::QuoteMeta(unquoted); - RE re(quoted, options); - CHECK(re.FullMatch(unquoted)); -} - -// A string containing meaningful regexp characters, which is then meta- -// quoted, should not generally match a string the unquoted string does. -static void NegativeTestQuoteMeta(string unquoted, string should_not_match, - RE_Options options = RE_Options()) { - string quoted = RE::QuoteMeta(unquoted); - RE re(quoted, options); - CHECK(!re.FullMatch(should_not_match)); -} - -// Tests that quoted meta characters match their original strings, -// and that a few things that shouldn't match indeed do not. -static void TestQuotaMetaSimple() { - TestQuoteMeta("foo"); - TestQuoteMeta("foo.bar"); - TestQuoteMeta("foo\\.bar"); - TestQuoteMeta("[1-9]"); - TestQuoteMeta("1.5-2.0?"); - TestQuoteMeta("\\d"); - TestQuoteMeta("Who doesn't like ice cream?"); - TestQuoteMeta("((a|b)c?d*e+[f-h]i)"); - TestQuoteMeta("((?!)xxx).*yyy"); - TestQuoteMeta("(["); - TestQuoteMeta(string("foo\0bar", 7)); -} - -static void TestQuoteMetaSimpleNegative() { - NegativeTestQuoteMeta("foo", "bar"); - NegativeTestQuoteMeta("...", "bar"); - NegativeTestQuoteMeta("\\.", "."); - NegativeTestQuoteMeta("\\.", ".."); - NegativeTestQuoteMeta("(a)", "a"); - NegativeTestQuoteMeta("(a|b)", "a"); - NegativeTestQuoteMeta("(a|b)", "(a)"); - NegativeTestQuoteMeta("(a|b)", "a|b"); - NegativeTestQuoteMeta("[0-9]", "0"); - NegativeTestQuoteMeta("[0-9]", "0-9"); - NegativeTestQuoteMeta("[0-9]", "[9]"); - NegativeTestQuoteMeta("((?!)xxx)", "xxx"); -} - -static void TestQuoteMetaLatin1() { - TestQuoteMeta("3\xb2 = 9"); -} - -static void TestQuoteMetaUtf8() { -#ifdef SUPPORT_UTF8 - TestQuoteMeta("Pl\xc3\xa1\x63ido Domingo", pcrecpp::UTF8()); - TestQuoteMeta("xyz", pcrecpp::UTF8()); // No fancy utf8 - TestQuoteMeta("\xc2\xb0", pcrecpp::UTF8()); // 2-byte utf8 (degree symbol) - TestQuoteMeta("27\xc2\xb0 degrees", pcrecpp::UTF8()); // As a middle character - TestQuoteMeta("\xe2\x80\xb3", pcrecpp::UTF8()); // 3-byte utf8 (double prime) - TestQuoteMeta("\xf0\x9d\x85\x9f", pcrecpp::UTF8()); // 4-byte utf8 (music note) - TestQuoteMeta("27\xc2\xb0"); // Interpreted as Latin-1, but should still work - NegativeTestQuoteMeta("27\xc2\xb0", // 2-byte utf (degree symbol) - "27\\\xc2\\\xb0", - pcrecpp::UTF8()); -#endif -} - -static void TestQuoteMetaAll() { - printf("Testing QuoteMeta\n"); - TestQuotaMetaSimple(); - TestQuoteMetaSimpleNegative(); - TestQuoteMetaLatin1(); - TestQuoteMetaUtf8(); -} - -// -// Options tests contributed by -// Giuseppe Maxia, CTO, Stardata s.r.l. -// July 2005 -// -static void GetOneOptionResult( - const char *option_name, - const char *regex, - const char *str, - RE_Options options, - bool full, - string expected) { - - printf("Testing Option <%s>\n", option_name); - if(VERBOSE_TEST) - printf("/%s/ finds \"%s\" within \"%s\" \n", - regex, - expected.c_str(), - str); - string captured(""); - if (full) - RE(regex,options).FullMatch(str, &captured); - else - RE(regex,options).PartialMatch(str, &captured); - CHECK_EQ(captured, expected); -} - -static void TestOneOption( - const char *option_name, - const char *regex, - const char *str, - RE_Options options, - bool full, - bool assertive = true) { - - printf("Testing Option <%s>\n", option_name); - if (VERBOSE_TEST) - printf("'%s' %s /%s/ \n", - str, - (assertive? "matches" : "doesn't match"), - regex); - if (assertive) { - if (full) - CHECK(RE(regex,options).FullMatch(str)); - else - CHECK(RE(regex,options).PartialMatch(str)); - } else { - if (full) - CHECK(!RE(regex,options).FullMatch(str)); - else - CHECK(!RE(regex,options).PartialMatch(str)); - } -} - -static void Test_CASELESS() { - RE_Options options; - RE_Options options2; - - options.set_caseless(true); - TestOneOption("CASELESS (class)", "HELLO", "hello", options, false); - TestOneOption("CASELESS (class2)", "HELLO", "hello", options2.set_caseless(true), false); - TestOneOption("CASELESS (class)", "^[A-Z]+$", "Hello", options, false); - - TestOneOption("CASELESS (function)", "HELLO", "hello", pcrecpp::CASELESS(), false); - TestOneOption("CASELESS (function)", "^[A-Z]+$", "Hello", pcrecpp::CASELESS(), false); - options.set_caseless(false); - TestOneOption("no CASELESS", "HELLO", "hello", options, false, false); -} - -static void Test_MULTILINE() { - RE_Options options; - RE_Options options2; - const char *str = "HELLO\n" "cruel\n" "world\n"; - - options.set_multiline(true); - TestOneOption("MULTILINE (class)", "^cruel$", str, options, false); - TestOneOption("MULTILINE (class2)", "^cruel$", str, options2.set_multiline(true), false); - TestOneOption("MULTILINE (function)", "^cruel$", str, pcrecpp::MULTILINE(), false); - options.set_multiline(false); - TestOneOption("no MULTILINE", "^cruel$", str, options, false, false); -} - -static void Test_DOTALL() { - RE_Options options; - RE_Options options2; - const char *str = "HELLO\n" "cruel\n" "world"; - - options.set_dotall(true); - TestOneOption("DOTALL (class)", "HELLO.*world", str, options, true); - TestOneOption("DOTALL (class2)", "HELLO.*world", str, options2.set_dotall(true), true); - TestOneOption("DOTALL (function)", "HELLO.*world", str, pcrecpp::DOTALL(), true); - options.set_dotall(false); - TestOneOption("no DOTALL", "HELLO.*world", str, options, true, false); -} - -static void Test_DOLLAR_ENDONLY() { - RE_Options options; - RE_Options options2; - const char *str = "HELLO world\n"; - - TestOneOption("no DOLLAR_ENDONLY", "world$", str, options, false); - options.set_dollar_endonly(true); - TestOneOption("DOLLAR_ENDONLY 1", "world$", str, options, false, false); - TestOneOption("DOLLAR_ENDONLY 2", "world$", str, options2.set_dollar_endonly(true), false, false); -} - -static void Test_EXTRA() { - RE_Options options; - const char *str = "HELLO"; - - options.set_extra(true); - TestOneOption("EXTRA 1", "\\HELL\\O", str, options, true, false ); - TestOneOption("EXTRA 2", "\\HELL\\O", str, RE_Options().set_extra(true), true, false ); - options.set_extra(false); - TestOneOption("no EXTRA", "\\HELL\\O", str, options, true ); -} - -static void Test_EXTENDED() { - RE_Options options; - RE_Options options2; - const char *str = "HELLO world"; - - options.set_extended(true); - TestOneOption("EXTENDED (class)", "HELLO world", str, options, false, false); - TestOneOption("EXTENDED (class2)", "HELLO world", str, options2.set_extended(true), false, false); - TestOneOption("EXTENDED (class)", - "^ HE L{2} O " - "\\s+ " - "\\w+ $ ", - str, - options, - false); - - TestOneOption("EXTENDED (function)", "HELLO world", str, pcrecpp::EXTENDED(), false, false); - TestOneOption("EXTENDED (function)", - "^ HE L{2} O " - "\\s+ " - "\\w+ $ ", - str, - pcrecpp::EXTENDED(), - false); - - options.set_extended(false); - TestOneOption("no EXTENDED", "HELLO world", str, options, false); -} - -static void Test_NO_AUTO_CAPTURE() { - RE_Options options; - const char *str = "HELLO world"; - string captured; - - printf("Testing Option \n"); - if (VERBOSE_TEST) - printf("parentheses capture text\n"); - RE re("(world|universe)$", options); - CHECK(re.Extract("\\1", str , &captured)); - CHECK_EQ(captured, "world"); - options.set_no_auto_capture(true); - printf("testing Option \n"); - if (VERBOSE_TEST) - printf("parentheses do not capture text\n"); - re.Extract("\\1",str, &captured ); - CHECK_EQ(captured, "world"); -} - -static void Test_UNGREEDY() { - RE_Options options; - const char *str = "HELLO, 'this' is the 'world'"; - - options.set_ungreedy(true); - GetOneOptionResult("UNGREEDY 1", "('.*')", str, options, false, "'this'" ); - GetOneOptionResult("UNGREEDY 2", "('.*')", str, RE_Options().set_ungreedy(true), false, "'this'" ); - GetOneOptionResult("UNGREEDY", "('.*?')", str, options, false, "'this' is the 'world'" ); - - options.set_ungreedy(false); - GetOneOptionResult("no UNGREEDY", "('.*')", str, options, false, "'this' is the 'world'" ); - GetOneOptionResult("no UNGREEDY", "('.*?')", str, options, false, "'this'" ); -} - -static void Test_all_options() { - const char *str = "HELLO\n" "cruel\n" "world"; - RE_Options options; - options.set_all_options(PCRE_CASELESS | PCRE_DOTALL); - - TestOneOption("all_options (CASELESS|DOTALL)", "^hello.*WORLD", str , options, false); - options.set_all_options(0); - TestOneOption("all_options (0)", "^hello.*WORLD", str , options, false, false); - options.set_all_options(PCRE_MULTILINE | PCRE_EXTENDED); - - TestOneOption("all_options (MULTILINE|EXTENDED)", " ^ c r u e l $ ", str, options, false); - TestOneOption("all_options (MULTILINE|EXTENDED) with constructor", - " ^ c r u e l $ ", - str, - RE_Options(PCRE_MULTILINE | PCRE_EXTENDED), - false); - - TestOneOption("all_options (MULTILINE|EXTENDED) with concatenation", - " ^ c r u e l $ ", - str, - RE_Options() - .set_multiline(true) - .set_extended(true), - false); - - options.set_all_options(0); - TestOneOption("all_options (0)", "^ c r u e l $", str, options, false, false); - -} - -static void TestOptions() { - printf("Testing Options\n"); - Test_CASELESS(); - Test_MULTILINE(); - Test_DOTALL(); - Test_DOLLAR_ENDONLY(); - Test_EXTENDED(); - Test_NO_AUTO_CAPTURE(); - Test_UNGREEDY(); - Test_EXTRA(); - Test_all_options(); -} - -static void TestConstructors() { - printf("Testing constructors\n"); - - RE_Options options; - options.set_dotall(true); - const char *str = "HELLO\n" "cruel\n" "world"; - - RE orig("HELLO.*world", options); - CHECK(orig.FullMatch(str)); - - RE copy1(orig); - CHECK(copy1.FullMatch(str)); - - RE copy2("not a match"); - CHECK(!copy2.FullMatch(str)); - copy2 = copy1; - CHECK(copy2.FullMatch(str)); - copy2 = orig; - CHECK(copy2.FullMatch(str)); - - // Make sure when we assign to ourselves, nothing bad happens - orig = orig; - copy1 = copy1; - copy2 = copy2; - CHECK(orig.FullMatch(str)); - CHECK(copy1.FullMatch(str)); - CHECK(copy2.FullMatch(str)); -} - -int main(int argc, char** argv) { - // Treat any flag as --help - if (argc > 1 && argv[1][0] == '-') { - printf("Usage: %s [timing1|timing2|timing3 num-iters]\n" - " If 'timingX ###' is specified, run the given timing test\n" - " with the given number of iterations, rather than running\n" - " the default corectness test.\n", argv[0]); - return 0; - } - - if (argc > 1) { - if ( argc == 2 || atoi(argv[2]) == 0) { - printf("timing mode needs a num-iters argument\n"); - return 1; - } - if (!strcmp(argv[1], "timing1")) - Timing1(atoi(argv[2])); - else if (!strcmp(argv[1], "timing2")) - Timing2(atoi(argv[2])); - else if (!strcmp(argv[1], "timing3")) - Timing3(atoi(argv[2])); - else - printf("Unknown argument '%s'\n", argv[1]); - return 0; - } - - printf("Testing FullMatch\n"); - - int i; - string s; - - /***** FullMatch with no args *****/ - - CHECK(RE("h.*o").FullMatch("hello")); - CHECK(!RE("h.*o").FullMatch("othello")); // Must be anchored at front - CHECK(!RE("h.*o").FullMatch("hello!")); // Must be anchored at end - CHECK(RE("a*").FullMatch("aaaa")); // Fullmatch with normal op - CHECK(RE("a*?").FullMatch("aaaa")); // Fullmatch with nongreedy op - CHECK(RE("a*?\\z").FullMatch("aaaa")); // Two unusual ops - - /***** FullMatch with args *****/ - - // Zero-arg - CHECK(RE("\\d+").FullMatch("1001")); - - // Single-arg - CHECK(RE("(\\d+)").FullMatch("1001", &i)); - CHECK_EQ(i, 1001); - CHECK(RE("(-?\\d+)").FullMatch("-123", &i)); - CHECK_EQ(i, -123); - CHECK(!RE("()\\d+").FullMatch("10", &i)); - CHECK(!RE("(\\d+)").FullMatch("1234567890123456789012345678901234567890", - &i)); - - // Digits surrounding integer-arg - CHECK(RE("1(\\d*)4").FullMatch("1234", &i)); - CHECK_EQ(i, 23); - CHECK(RE("(\\d)\\d+").FullMatch("1234", &i)); - CHECK_EQ(i, 1); - CHECK(RE("(-\\d)\\d+").FullMatch("-1234", &i)); - CHECK_EQ(i, -1); - CHECK(RE("(\\d)").PartialMatch("1234", &i)); - CHECK_EQ(i, 1); - CHECK(RE("(-\\d)").PartialMatch("-1234", &i)); - CHECK_EQ(i, -1); - - // String-arg - CHECK(RE("h(.*)o").FullMatch("hello", &s)); - CHECK_EQ(s, string("ell")); - - // StringPiece-arg - StringPiece sp; - CHECK(RE("(\\w+):(\\d+)").FullMatch("ruby:1234", &sp, &i)); - CHECK_EQ(sp.size(), 4); - CHECK(memcmp(sp.data(), "ruby", 4) == 0); - CHECK_EQ(i, 1234); - - // Multi-arg - CHECK(RE("(\\w+):(\\d+)").FullMatch("ruby:1234", &s, &i)); - CHECK_EQ(s, string("ruby")); - CHECK_EQ(i, 1234); - - // Ignore non-void* NULL arg - CHECK(RE("he(.*)lo").FullMatch("hello", (char*)NULL)); - CHECK(RE("h(.*)o").FullMatch("hello", (string*)NULL)); - CHECK(RE("h(.*)o").FullMatch("hello", (StringPiece*)NULL)); - CHECK(RE("(.*)").FullMatch("1234", (int*)NULL)); -#ifdef HAVE_LONG_LONG - CHECK(RE("(.*)").FullMatch("1234567890123456", (long long*)NULL)); -#endif - CHECK(RE("(.*)").FullMatch("123.4567890123456", (double*)NULL)); - CHECK(RE("(.*)").FullMatch("123.4567890123456", (float*)NULL)); - - // Fail on non-void* NULL arg if the match doesn't parse for the given type. - CHECK(!RE("h(.*)lo").FullMatch("hello", &s, (char*)NULL)); - CHECK(!RE("(.*)").FullMatch("hello", (int*)NULL)); - CHECK(!RE("(.*)").FullMatch("1234567890123456", (int*)NULL)); - CHECK(!RE("(.*)").FullMatch("hello", (double*)NULL)); - CHECK(!RE("(.*)").FullMatch("hello", (float*)NULL)); - - // Ignored arg - CHECK(RE("(\\w+)(:)(\\d+)").FullMatch("ruby:1234", &s, (void*)NULL, &i)); - CHECK_EQ(s, string("ruby")); - CHECK_EQ(i, 1234); - - // Type tests - { - char c; - CHECK(RE("(H)ello").FullMatch("Hello", &c)); - CHECK_EQ(c, 'H'); - } - { - unsigned char c; - CHECK(RE("(H)ello").FullMatch("Hello", &c)); - CHECK_EQ(c, static_cast('H')); - } - { - short v; - CHECK(RE("(-?\\d+)").FullMatch("100", &v)); CHECK_EQ(v, 100); - CHECK(RE("(-?\\d+)").FullMatch("-100", &v)); CHECK_EQ(v, -100); - CHECK(RE("(-?\\d+)").FullMatch("32767", &v)); CHECK_EQ(v, 32767); - CHECK(RE("(-?\\d+)").FullMatch("-32768", &v)); CHECK_EQ(v, -32768); - CHECK(!RE("(-?\\d+)").FullMatch("-32769", &v)); - CHECK(!RE("(-?\\d+)").FullMatch("32768", &v)); - } - { - unsigned short v; - CHECK(RE("(\\d+)").FullMatch("100", &v)); CHECK_EQ(v, 100); - CHECK(RE("(\\d+)").FullMatch("32767", &v)); CHECK_EQ(v, 32767); - CHECK(RE("(\\d+)").FullMatch("65535", &v)); CHECK_EQ(v, 65535); - CHECK(!RE("(\\d+)").FullMatch("65536", &v)); - } - { - int v; - static const int max_value = 0x7fffffff; - static const int min_value = -max_value - 1; - CHECK(RE("(-?\\d+)").FullMatch("100", &v)); CHECK_EQ(v, 100); - CHECK(RE("(-?\\d+)").FullMatch("-100", &v)); CHECK_EQ(v, -100); - CHECK(RE("(-?\\d+)").FullMatch("2147483647", &v)); CHECK_EQ(v, max_value); - CHECK(RE("(-?\\d+)").FullMatch("-2147483648", &v)); CHECK_EQ(v, min_value); - CHECK(!RE("(-?\\d+)").FullMatch("-2147483649", &v)); - CHECK(!RE("(-?\\d+)").FullMatch("2147483648", &v)); - } - { - unsigned int v; - static const unsigned int max_value = 0xfffffffful; - CHECK(RE("(\\d+)").FullMatch("100", &v)); CHECK_EQ(v, 100); - CHECK(RE("(\\d+)").FullMatch("4294967295", &v)); CHECK_EQ(v, max_value); - CHECK(!RE("(\\d+)").FullMatch("4294967296", &v)); - } -#ifdef HAVE_LONG_LONG -# if defined(__MINGW__) || defined(__MINGW32__) -# define LLD "%I64d" -# define LLU "%I64u" -# else -# define LLD "%lld" -# define LLU "%llu" -# endif - { - long long v; - static const long long max_value = 0x7fffffffffffffffLL; - static const long long min_value = -max_value - 1; - char buf[32]; // definitely big enough for a long long - - CHECK(RE("(-?\\d+)").FullMatch("100", &v)); CHECK_EQ(v, 100); - CHECK(RE("(-?\\d+)").FullMatch("-100",&v)); CHECK_EQ(v, -100); - - sprintf(buf, LLD, max_value); - CHECK(RE("(-?\\d+)").FullMatch(buf,&v)); CHECK_EQ(v, max_value); - - sprintf(buf, LLD, min_value); - CHECK(RE("(-?\\d+)").FullMatch(buf,&v)); CHECK_EQ(v, min_value); - - sprintf(buf, LLD, max_value); - assert(buf[strlen(buf)-1] != '9'); - buf[strlen(buf)-1]++; - CHECK(!RE("(-?\\d+)").FullMatch(buf, &v)); - - sprintf(buf, LLD, min_value); - assert(buf[strlen(buf)-1] != '9'); - buf[strlen(buf)-1]++; - CHECK(!RE("(-?\\d+)").FullMatch(buf, &v)); - } -#endif -#if defined HAVE_UNSIGNED_LONG_LONG && defined HAVE_LONG_LONG - { - unsigned long long v; - long long v2; - static const unsigned long long max_value = 0xffffffffffffffffULL; - char buf[32]; // definitely big enough for a unsigned long long - - CHECK(RE("(-?\\d+)").FullMatch("100",&v)); CHECK_EQ(v, 100); - CHECK(RE("(-?\\d+)").FullMatch("-100",&v2)); CHECK_EQ(v2, -100); - - sprintf(buf, LLU, max_value); - CHECK(RE("(-?\\d+)").FullMatch(buf,&v)); CHECK_EQ(v, max_value); - - assert(buf[strlen(buf)-1] != '9'); - buf[strlen(buf)-1]++; - CHECK(!RE("(-?\\d+)").FullMatch(buf, &v)); - } -#endif - { - float v; - CHECK(RE("(.*)").FullMatch("100", &v)); - CHECK(RE("(.*)").FullMatch("-100.", &v)); - CHECK(RE("(.*)").FullMatch("1e23", &v)); - } - { - double v; - CHECK(RE("(.*)").FullMatch("100", &v)); - CHECK(RE("(.*)").FullMatch("-100.", &v)); - CHECK(RE("(.*)").FullMatch("1e23", &v)); - } - - // Check that matching is fully anchored - CHECK(!RE("(\\d+)").FullMatch("x1001", &i)); - CHECK(!RE("(\\d+)").FullMatch("1001x", &i)); - CHECK(RE("x(\\d+)").FullMatch("x1001", &i)); CHECK_EQ(i, 1001); - CHECK(RE("(\\d+)x").FullMatch("1001x", &i)); CHECK_EQ(i, 1001); - - // Braces - CHECK(RE("[0-9a-f+.-]{5,}").FullMatch("0abcd")); - CHECK(RE("[0-9a-f+.-]{5,}").FullMatch("0abcde")); - CHECK(!RE("[0-9a-f+.-]{5,}").FullMatch("0abc")); - - // Complicated RE - CHECK(RE("foo|bar|[A-Z]").FullMatch("foo")); - CHECK(RE("foo|bar|[A-Z]").FullMatch("bar")); - CHECK(RE("foo|bar|[A-Z]").FullMatch("X")); - CHECK(!RE("foo|bar|[A-Z]").FullMatch("XY")); - - // Check full-match handling (needs '$' tacked on internally) - CHECK(RE("fo|foo").FullMatch("fo")); - CHECK(RE("fo|foo").FullMatch("foo")); - CHECK(RE("fo|foo$").FullMatch("fo")); - CHECK(RE("fo|foo$").FullMatch("foo")); - CHECK(RE("foo$").FullMatch("foo")); - CHECK(!RE("foo\\$").FullMatch("foo$bar")); - CHECK(!RE("fo|bar").FullMatch("fox")); - - // Uncomment the following if we change the handling of '$' to - // prevent it from matching a trailing newline - if (false) { - // Check that we don't get bitten by pcre's special handling of a - // '\n' at the end of the string matching '$' - CHECK(!RE("foo$").PartialMatch("foo\n")); - } - - // Number of args - int a[16]; - CHECK(RE("").FullMatch("")); - - memset(a, 0, sizeof(0)); - CHECK(RE("(\\d){1}").FullMatch("1", - &a[0])); - CHECK_EQ(a[0], 1); - - memset(a, 0, sizeof(0)); - CHECK(RE("(\\d)(\\d)").FullMatch("12", - &a[0], &a[1])); - CHECK_EQ(a[0], 1); - CHECK_EQ(a[1], 2); - - memset(a, 0, sizeof(0)); - CHECK(RE("(\\d)(\\d)(\\d)").FullMatch("123", - &a[0], &a[1], &a[2])); - CHECK_EQ(a[0], 1); - CHECK_EQ(a[1], 2); - CHECK_EQ(a[2], 3); - - memset(a, 0, sizeof(0)); - CHECK(RE("(\\d)(\\d)(\\d)(\\d)").FullMatch("1234", - &a[0], &a[1], &a[2], &a[3])); - CHECK_EQ(a[0], 1); - CHECK_EQ(a[1], 2); - CHECK_EQ(a[2], 3); - CHECK_EQ(a[3], 4); - - memset(a, 0, sizeof(0)); - CHECK(RE("(\\d)(\\d)(\\d)(\\d)(\\d)").FullMatch("12345", - &a[0], &a[1], &a[2], - &a[3], &a[4])); - CHECK_EQ(a[0], 1); - CHECK_EQ(a[1], 2); - CHECK_EQ(a[2], 3); - CHECK_EQ(a[3], 4); - CHECK_EQ(a[4], 5); - - memset(a, 0, sizeof(0)); - CHECK(RE("(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)").FullMatch("123456", - &a[0], &a[1], &a[2], - &a[3], &a[4], &a[5])); - CHECK_EQ(a[0], 1); - CHECK_EQ(a[1], 2); - CHECK_EQ(a[2], 3); - CHECK_EQ(a[3], 4); - CHECK_EQ(a[4], 5); - CHECK_EQ(a[5], 6); - - memset(a, 0, sizeof(0)); - CHECK(RE("(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)").FullMatch("1234567", - &a[0], &a[1], &a[2], &a[3], - &a[4], &a[5], &a[6])); - CHECK_EQ(a[0], 1); - CHECK_EQ(a[1], 2); - CHECK_EQ(a[2], 3); - CHECK_EQ(a[3], 4); - CHECK_EQ(a[4], 5); - CHECK_EQ(a[5], 6); - CHECK_EQ(a[6], 7); - - memset(a, 0, sizeof(0)); - CHECK(RE("(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)" - "(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)").FullMatch( - "1234567890123456", - &a[0], &a[1], &a[2], &a[3], - &a[4], &a[5], &a[6], &a[7], - &a[8], &a[9], &a[10], &a[11], - &a[12], &a[13], &a[14], &a[15])); - CHECK_EQ(a[0], 1); - CHECK_EQ(a[1], 2); - CHECK_EQ(a[2], 3); - CHECK_EQ(a[3], 4); - CHECK_EQ(a[4], 5); - CHECK_EQ(a[5], 6); - CHECK_EQ(a[6], 7); - CHECK_EQ(a[7], 8); - CHECK_EQ(a[8], 9); - CHECK_EQ(a[9], 0); - CHECK_EQ(a[10], 1); - CHECK_EQ(a[11], 2); - CHECK_EQ(a[12], 3); - CHECK_EQ(a[13], 4); - CHECK_EQ(a[14], 5); - CHECK_EQ(a[15], 6); - - /***** PartialMatch *****/ - - printf("Testing PartialMatch\n"); - - CHECK(RE("h.*o").PartialMatch("hello")); - CHECK(RE("h.*o").PartialMatch("othello")); - CHECK(RE("h.*o").PartialMatch("hello!")); - CHECK(RE("((((((((((((((((((((x))))))))))))))))))))").PartialMatch("x")); - - /***** other tests *****/ - - RadixTests(); - TestReplace(); - TestExtract(); - TestConsume(); - TestFindAndConsume(); - TestQuoteMetaAll(); - TestMatchNumberPeculiarity(); - - // Check the pattern() accessor - { - const string kPattern = "http://([^/]+)/.*"; - const RE re(kPattern); - CHECK_EQ(kPattern, re.pattern()); - } - - // Check RE error field. - { - RE re("foo"); - CHECK(re.error().empty()); // Must have no error - } - -#ifdef SUPPORT_UTF8 - // Check UTF-8 handling - { - printf("Testing UTF-8 handling\n"); - - // Three Japanese characters (nihongo) - const unsigned char utf8_string[] = { - 0xe6, 0x97, 0xa5, // 65e5 - 0xe6, 0x9c, 0xac, // 627c - 0xe8, 0xaa, 0x9e, // 8a9e - 0 - }; - const unsigned char utf8_pattern[] = { - '.', - 0xe6, 0x9c, 0xac, // 627c - '.', - 0 - }; - - // Both should match in either mode, bytes or UTF-8 - RE re_test1("........."); - CHECK(re_test1.FullMatch(utf8_string)); - RE re_test2("...", pcrecpp::UTF8()); - CHECK(re_test2.FullMatch(utf8_string)); - - // Check that '.' matches one byte or UTF-8 character - // according to the mode. - string ss; - RE re_test3("(.)"); - CHECK(re_test3.PartialMatch(utf8_string, &ss)); - CHECK_EQ(ss, string("\xe6")); - RE re_test4("(.)", pcrecpp::UTF8()); - CHECK(re_test4.PartialMatch(utf8_string, &ss)); - CHECK_EQ(ss, string("\xe6\x97\xa5")); - - // Check that string matches itself in either mode - RE re_test5(utf8_string); - CHECK(re_test5.FullMatch(utf8_string)); - RE re_test6(utf8_string, pcrecpp::UTF8()); - CHECK(re_test6.FullMatch(utf8_string)); - - // Check that pattern matches string only in UTF8 mode - RE re_test7(utf8_pattern); - CHECK(!re_test7.FullMatch(utf8_string)); - RE re_test8(utf8_pattern, pcrecpp::UTF8()); - CHECK(re_test8.FullMatch(utf8_string)); - } - - // Check that ungreedy, UTF8 regular expressions don't match when they - // oughtn't -- see bug 82246. - { - // This code always worked. - const char* pattern = "\\w+X"; - const string target = "a aX"; - RE match_sentence(pattern); - RE match_sentence_re(pattern, pcrecpp::UTF8()); - - CHECK(!match_sentence.FullMatch(target)); - CHECK(!match_sentence_re.FullMatch(target)); - } - - { - const char* pattern = "(?U)\\w+X"; - const string target = "a aX"; - RE match_sentence(pattern); - RE match_sentence_re(pattern, pcrecpp::UTF8()); - - CHECK(!match_sentence.FullMatch(target)); - CHECK(!match_sentence_re.FullMatch(target)); - } -#endif /* def SUPPORT_UTF8 */ - - printf("Testing error reporting\n"); - - { RE re("a\\1"); CHECK(!re.error().empty()); } - { - RE re("a[x"); - CHECK(!re.error().empty()); - } - { - RE re("a[z-a]"); - CHECK(!re.error().empty()); - } - { - RE re("a[[:foobar:]]"); - CHECK(!re.error().empty()); - } - { - RE re("a(b"); - CHECK(!re.error().empty()); - } - { - RE re("a\\"); - CHECK(!re.error().empty()); - } - - // Test that recursion is stopped - TestRecursion(); - - // Test Options - if (getenv("VERBOSE_TEST") != NULL) - VERBOSE_TEST = true; - TestOptions(); - - // Test the constructors - TestConstructors(); - - // Done - printf("OK\n"); - - return 0; -} diff --git a/libs/pcre/pcrecpparg.h.in b/libs/pcre/pcrecpparg.h.in deleted file mode 100644 index 61bcab5402..0000000000 --- a/libs/pcre/pcrecpparg.h.in +++ /dev/null @@ -1,174 +0,0 @@ -// Copyright (c) 2005, Google Inc. -// All rights reserved. -// -// Redistribution and use in source and binary forms, with or without -// modification, are permitted provided that the following conditions are -// met: -// -// * Redistributions of source code must retain the above copyright -// notice, this list of conditions and the following disclaimer. -// * Redistributions in binary form must reproduce the above -// copyright notice, this list of conditions and the following disclaimer -// in the documentation and/or other materials provided with the -// distribution. -// * Neither the name of Google Inc. nor the names of its -// contributors may be used to endorse or promote products derived from -// this software without specific prior written permission. -// -// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS -// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT -// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR -// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT -// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, -// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT -// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, -// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY -// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT -// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE -// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. -// -// Author: Sanjay Ghemawat - -#ifndef _PCRECPPARG_H -#define _PCRECPPARG_H - -#include // for NULL -#include - -#include - -namespace pcrecpp { - -class StringPiece; - -// Hex/Octal/Binary? - -// Special class for parsing into objects that define a ParseFrom() method -template -class _RE_MatchObject { - public: - static inline bool Parse(const char* str, int n, void* dest) { - if (dest == NULL) return true; - T* object = reinterpret_cast(dest); - return object->ParseFrom(str, n); - } -}; - -class PCRECPP_EXP_DEFN Arg { - public: - // Empty constructor so we can declare arrays of Arg - Arg(); - - // Constructor specially designed for NULL arguments - Arg(void*); - - typedef bool (*Parser)(const char* str, int n, void* dest); - -// Type-specific parsers -#define PCRE_MAKE_PARSER(type,name) \ - Arg(type* p) : arg_(p), parser_(name) { } \ - Arg(type* p, Parser parser) : arg_(p), parser_(parser) { } - - - PCRE_MAKE_PARSER(char, parse_char); - PCRE_MAKE_PARSER(unsigned char, parse_uchar); - PCRE_MAKE_PARSER(short, parse_short); - PCRE_MAKE_PARSER(unsigned short, parse_ushort); - PCRE_MAKE_PARSER(int, parse_int); - PCRE_MAKE_PARSER(unsigned int, parse_uint); - PCRE_MAKE_PARSER(long, parse_long); - PCRE_MAKE_PARSER(unsigned long, parse_ulong); -#if @pcre_have_long_long@ - PCRE_MAKE_PARSER(long long, parse_longlong); -#endif -#if @pcre_have_ulong_long@ - PCRE_MAKE_PARSER(unsigned long long, parse_ulonglong); -#endif - PCRE_MAKE_PARSER(float, parse_float); - PCRE_MAKE_PARSER(double, parse_double); - PCRE_MAKE_PARSER(std::string, parse_string); - PCRE_MAKE_PARSER(StringPiece, parse_stringpiece); - -#undef PCRE_MAKE_PARSER - - // Generic constructor - template Arg(T*, Parser parser); - // Generic constructor template - template Arg(T* p) - : arg_(p), parser_(_RE_MatchObject::Parse) { - } - - // Parse the data - bool Parse(const char* str, int n) const; - - private: - void* arg_; - Parser parser_; - - static bool parse_null (const char* str, int n, void* dest); - static bool parse_char (const char* str, int n, void* dest); - static bool parse_uchar (const char* str, int n, void* dest); - static bool parse_float (const char* str, int n, void* dest); - static bool parse_double (const char* str, int n, void* dest); - static bool parse_string (const char* str, int n, void* dest); - static bool parse_stringpiece (const char* str, int n, void* dest); - -#define PCRE_DECLARE_INTEGER_PARSER(name) \ - private: \ - static bool parse_ ## name(const char* str, int n, void* dest); \ - static bool parse_ ## name ## _radix( \ - const char* str, int n, void* dest, int radix); \ - public: \ - static bool parse_ ## name ## _hex(const char* str, int n, void* dest); \ - static bool parse_ ## name ## _octal(const char* str, int n, void* dest); \ - static bool parse_ ## name ## _cradix(const char* str, int n, void* dest) - - PCRE_DECLARE_INTEGER_PARSER(short); - PCRE_DECLARE_INTEGER_PARSER(ushort); - PCRE_DECLARE_INTEGER_PARSER(int); - PCRE_DECLARE_INTEGER_PARSER(uint); - PCRE_DECLARE_INTEGER_PARSER(long); - PCRE_DECLARE_INTEGER_PARSER(ulong); - PCRE_DECLARE_INTEGER_PARSER(longlong); - PCRE_DECLARE_INTEGER_PARSER(ulonglong); - -#undef PCRE_DECLARE_INTEGER_PARSER -}; - -inline Arg::Arg() : arg_(NULL), parser_(parse_null) { } -inline Arg::Arg(void* p) : arg_(p), parser_(parse_null) { } - -inline bool Arg::Parse(const char* str, int n) const { - return (*parser_)(str, n, arg_); -} - -// This part of the parser, appropriate only for ints, deals with bases -#define MAKE_INTEGER_PARSER(type, name) \ - inline Arg Hex(type* ptr) { \ - return Arg(ptr, Arg::parse_ ## name ## _hex); } \ - inline Arg Octal(type* ptr) { \ - return Arg(ptr, Arg::parse_ ## name ## _octal); } \ - inline Arg CRadix(type* ptr) { \ - return Arg(ptr, Arg::parse_ ## name ## _cradix); } - -MAKE_INTEGER_PARSER(short, short) /* */ -MAKE_INTEGER_PARSER(unsigned short, ushort) /* */ -MAKE_INTEGER_PARSER(int, int) /* Don't use semicolons */ -MAKE_INTEGER_PARSER(unsigned int, uint) /* after these statement */ -MAKE_INTEGER_PARSER(long, long) /* because they can cause */ -MAKE_INTEGER_PARSER(unsigned long, ulong) /* compiler warnings if */ -#if @pcre_have_long_long@ /* the checking level is */ -MAKE_INTEGER_PARSER(long long, longlong) /* turned up high enough. */ -#endif /* */ -#if @pcre_have_ulong_long@ /* */ -MAKE_INTEGER_PARSER(unsigned long long, ulonglong) /* */ -#endif - -#undef PCRE_IS_SET -#undef PCRE_SET_OR_CLEAR -#undef MAKE_INTEGER_PARSER - -} // namespace pcrecpp - - -#endif /* _PCRECPPARG_H */ diff --git a/libs/pcre/pcredemo.c b/libs/pcre/pcredemo.c deleted file mode 100644 index 3647568766..0000000000 --- a/libs/pcre/pcredemo.c +++ /dev/null @@ -1,334 +0,0 @@ -/************************************************* -* PCRE DEMONSTRATION PROGRAM * -*************************************************/ - -/* This is a demonstration program to illustrate the most straightforward ways -of calling the PCRE regular expression library from a C program. See the -pcresample documentation for a short discussion ("man pcresample" if you have -the PCRE man pages installed). - -In Unix-like environments, compile this program thuswise: - - gcc -Wall pcredemo.c -I/usr/local/include -L/usr/local/lib \ - -R/usr/local/lib -lpcre - -Replace "/usr/local/include" and "/usr/local/lib" with wherever the include and -library files for PCRE are installed on your system. You don't need -I and -L -if PCRE is installed in the standard system libraries. Only some operating -systems (e.g. Solaris) use the -R option. - -Building under Windows: - -If you want to statically link this program against a non-dll .a file, you must -define PCRE_STATIC before including pcre.h, otherwise the pcre_malloc() and -pcre_free() exported functions will be declared __declspec(dllimport), with -unwanted results. So in this environment, uncomment the following line. */ - -/* #define PCRE_STATIC */ - -#include -#include -#include - -#define OVECCOUNT 30 /* should be a multiple of 3 */ - - -int main(int argc, char **argv) -{ -pcre *re; -const char *error; -char *pattern; -char *subject; -unsigned char *name_table; -int erroffset; -int find_all; -int namecount; -int name_entry_size; -int ovector[OVECCOUNT]; -int subject_length; -int rc, i; - - -/************************************************************************** -* First, sort out the command line. There is only one possible option at * -* the moment, "-g" to request repeated matching to find all occurrences, * -* like Perl's /g option. We set the variable find_all to a non-zero value * -* if the -g option is present. Apart from that, there must be exactly two * -* arguments. * -**************************************************************************/ - -find_all = 0; -for (i = 1; i < argc; i++) - { - if (strcmp(argv[i], "-g") == 0) find_all = 1; - else break; - } - -/* After the options, we require exactly two arguments, which are the pattern, -and the subject string. */ - -if (argc - i != 2) - { - printf("Two arguments required: a regex and a subject string\n"); - return 1; - } - -pattern = argv[i]; -subject = argv[i+1]; -subject_length = (int)strlen(subject); - - -/************************************************************************* -* Now we are going to compile the regular expression pattern, and handle * -* and errors that are detected. * -*************************************************************************/ - -re = pcre_compile( - pattern, /* the pattern */ - 0, /* default options */ - &error, /* for error message */ - &erroffset, /* for error offset */ - NULL); /* use default character tables */ - -/* Compilation failed: print the error message and exit */ - -if (re == NULL) - { - printf("PCRE compilation failed at offset %d: %s\n", erroffset, error); - return 1; - } - - -/************************************************************************* -* If the compilation succeeded, we call PCRE again, in order to do a * -* pattern match against the subject string. This does just ONE match. If * -* further matching is needed, it will be done below. * -*************************************************************************/ - -rc = pcre_exec( - re, /* the compiled pattern */ - NULL, /* no extra data - we didn't study the pattern */ - subject, /* the subject string */ - subject_length, /* the length of the subject */ - 0, /* start at offset 0 in the subject */ - 0, /* default options */ - ovector, /* output vector for substring information */ - OVECCOUNT); /* number of elements in the output vector */ - -/* Matching failed: handle error cases */ - -if (rc < 0) - { - switch(rc) - { - case PCRE_ERROR_NOMATCH: printf("No match\n"); break; - /* - Handle other special cases if you like - */ - default: printf("Matching error %d\n", rc); break; - } - pcre_free(re); /* Release memory used for the compiled pattern */ - return 1; - } - -/* Match succeded */ - -printf("\nMatch succeeded at offset %d\n", ovector[0]); - - -/************************************************************************* -* We have found the first match within the subject string. If the output * -* vector wasn't big enough, say so. Then output any substrings that were * -* captured. * -*************************************************************************/ - -/* The output vector wasn't big enough */ - -if (rc == 0) - { - rc = OVECCOUNT/3; - printf("ovector only has room for %d captured substrings\n", rc - 1); - } - -/* Show substrings stored in the output vector by number. Obviously, in a real -application you might want to do things other than print them. */ - -for (i = 0; i < rc; i++) - { - char *substring_start = subject + ovector[2*i]; - int substring_length = ovector[2*i+1] - ovector[2*i]; - printf("%2d: %.*s\n", i, substring_length, substring_start); - } - - -/************************************************************************** -* That concludes the basic part of this demonstration program. We have * -* compiled a pattern, and performed a single match. The code that follows * -* shows first how to access named substrings, and then how to code for * -* repeated matches on the same subject. * -**************************************************************************/ - -/* See if there are any named substrings, and if so, show them by name. First -we have to extract the count of named parentheses from the pattern. */ - -(void)pcre_fullinfo( - re, /* the compiled pattern */ - NULL, /* no extra data - we didn't study the pattern */ - PCRE_INFO_NAMECOUNT, /* number of named substrings */ - &namecount); /* where to put the answer */ - -if (namecount <= 0) printf("No named substrings\n"); else - { - unsigned char *tabptr; - printf("Named substrings\n"); - - /* Before we can access the substrings, we must extract the table for - translating names to numbers, and the size of each entry in the table. */ - - (void)pcre_fullinfo( - re, /* the compiled pattern */ - NULL, /* no extra data - we didn't study the pattern */ - PCRE_INFO_NAMETABLE, /* address of the table */ - &name_table); /* where to put the answer */ - - (void)pcre_fullinfo( - re, /* the compiled pattern */ - NULL, /* no extra data - we didn't study the pattern */ - PCRE_INFO_NAMEENTRYSIZE, /* size of each entry in the table */ - &name_entry_size); /* where to put the answer */ - - /* Now we can scan the table and, for each entry, print the number, the name, - and the substring itself. */ - - tabptr = name_table; - for (i = 0; i < namecount; i++) - { - int n = (tabptr[0] << 8) | tabptr[1]; - printf("(%d) %*s: %.*s\n", n, name_entry_size - 3, tabptr + 2, - ovector[2*n+1] - ovector[2*n], subject + ovector[2*n]); - tabptr += name_entry_size; - } - } - - -/************************************************************************* -* If the "-g" option was given on the command line, we want to continue * -* to search for additional matches in the subject string, in a similar * -* way to the /g option in Perl. This turns out to be trickier than you * -* might think because of the possibility of matching an empty string. * -* What happens is as follows: * -* * -* If the previous match was NOT for an empty string, we can just start * -* the next match at the end of the previous one. * -* * -* If the previous match WAS for an empty string, we can't do that, as it * -* would lead to an infinite loop. Instead, a special call of pcre_exec() * -* is made with the PCRE_NOTEMPTY and PCRE_ANCHORED flags set. The first * -* of these tells PCRE that an empty string is not a valid match; other * -* possibilities must be tried. The second flag restricts PCRE to one * -* match attempt at the initial string position. If this match succeeds, * -* an alternative to the empty string match has been found, and we can * -* proceed round the loop. * -*************************************************************************/ - -if (!find_all) - { - pcre_free(re); /* Release the memory used for the compiled pattern */ - return 0; /* Finish unless -g was given */ - } - -/* Loop for second and subsequent matches */ - -for (;;) - { - int options = 0; /* Normally no options */ - int start_offset = ovector[1]; /* Start at end of previous match */ - - /* If the previous match was for an empty string, we are finished if we are - at the end of the subject. Otherwise, arrange to run another match at the - same point to see if a non-empty match can be found. */ - - if (ovector[0] == ovector[1]) - { - if (ovector[0] == subject_length) break; - options = PCRE_NOTEMPTY | PCRE_ANCHORED; - } - - /* Run the next matching operation */ - - rc = pcre_exec( - re, /* the compiled pattern */ - NULL, /* no extra data - we didn't study the pattern */ - subject, /* the subject string */ - subject_length, /* the length of the subject */ - start_offset, /* starting offset in the subject */ - options, /* options */ - ovector, /* output vector for substring information */ - OVECCOUNT); /* number of elements in the output vector */ - - /* This time, a result of NOMATCH isn't an error. If the value in "options" - is zero, it just means we have found all possible matches, so the loop ends. - Otherwise, it means we have failed to find a non-empty-string match at a - point where there was a previous empty-string match. In this case, we do what - Perl does: advance the matching position by one, and continue. We do this by - setting the "end of previous match" offset, because that is picked up at the - top of the loop as the point at which to start again. */ - - if (rc == PCRE_ERROR_NOMATCH) - { - if (options == 0) break; - ovector[1] = start_offset + 1; - continue; /* Go round the loop again */ - } - - /* Other matching errors are not recoverable. */ - - if (rc < 0) - { - printf("Matching error %d\n", rc); - pcre_free(re); /* Release memory used for the compiled pattern */ - return 1; - } - - /* Match succeded */ - - printf("\nMatch succeeded again at offset %d\n", ovector[0]); - - /* The match succeeded, but the output vector wasn't big enough. */ - - if (rc == 0) - { - rc = OVECCOUNT/3; - printf("ovector only has room for %d captured substrings\n", rc - 1); - } - - /* As before, show substrings stored in the output vector by number, and then - also any named substrings. */ - - for (i = 0; i < rc; i++) - { - char *substring_start = subject + ovector[2*i]; - int substring_length = ovector[2*i+1] - ovector[2*i]; - printf("%2d: %.*s\n", i, substring_length, substring_start); - } - - if (namecount <= 0) printf("No named substrings\n"); else - { - unsigned char *tabptr = name_table; - printf("Named substrings\n"); - for (i = 0; i < namecount; i++) - { - int n = (tabptr[0] << 8) | tabptr[1]; - printf("(%d) %*s: %.*s\n", n, name_entry_size - 3, tabptr + 2, - ovector[2*n+1] - ovector[2*n], subject + ovector[2*n]); - tabptr += name_entry_size; - } - } - } /* End of loop to find second and subsequent matches */ - -printf("\n"); -pcre_free(re); /* Release memory used for the compiled pattern */ -return 0; -} - -/* End of pcredemo.c */ diff --git a/libs/pcre/pcregexp.pas b/libs/pcre/pcregexp.pas deleted file mode 100644 index 272a96ea38..0000000000 --- a/libs/pcre/pcregexp.pas +++ /dev/null @@ -1,820 +0,0 @@ -{ - pcRegExp - Perl compatible regular expressions for Virtual Pascal - (c) 2001 Peter S. Voronov aka Chem O'Dun - - Based on PCRE library interface unit for Virtual Pascal. - (c) 2001 Alexander Tokarev - - The current PCRE version is: 3.7 - - This software must be distributed as Freeware. - - The PCRE library is written by: Philip Hazel - Copyright (c) 1997-2004 University of Cambridge - - AngelsHolocaust 4-11-04 updated to use version v5.0 - (INFO: this is regex-directed, NFA) - AH: 9-11-04 - pcre_free: removed var, pcre already gives the ptr, now - everything works as it should (no more crashes) - -> removed CheckRegExp because pcre handles errors perfectly - 10-11-04 - added pcError (errorhandling), pcInit - 13-11-04 - removed the ErrorPos = 0 check -> always print erroroffset - 17-10-05 - support for \1-\9 backreferences in TpcRegExp.GetReplStr - 17-02-06 - added RunTimeOptions: caller can set options while searching - 19-02-06 - added SearchOfs(): let PCRE use the complete string and offset - into the string itself - 20-12-06 - support for version 7.0 - 27.08.08 - support for v7.7 -} - -{$H+} {$DEFINE PCRE_3_7} {$DEFINE PCRE_5_0} {$DEFINE PCRE_7_0} {$DEFINE PCRE_7_7} - -Unit pcregexp; - -Interface - -uses objects; - -Type - PpcRegExp = ^TpcRegExp; -// TpcRegExp = object - TpcRegExp = object(TObject) - MatchesCount: integer; - RegExpC, RegExpExt : Pointer; - Matches:Pointer; - RegExp: shortstring; - SourceLen: integer; - PartialMatch : boolean; - Error : boolean; - ErrorMsg : Pchar; - ErrorPos : integer; - RunTimeOptions: Integer; // options which can be set by the caller - constructor Init(const ARegExp : shortstring; AOptions : integer; ALocale : Pointer); - function Search(AStr: Pchar; ALen : longint) : boolean; virtual; - function SearchNext( AStr: Pchar; ALen : longint) : boolean; virtual; - function SearchOfs ( AStr: Pchar; ALen, AOfs : longint) : boolean; virtual; - function MatchSub(ANom: integer; var Pos, Len : longint) : boolean; virtual; - function MatchFull(var Pos, Len : longint) : boolean; virtual; - function GetSubStr(ANom: integer; AStr: Pchar) : string; virtual; - function GetFullStr(AStr: Pchar) : string; virtual; - function GetReplStr(AStr: Pchar; const ARepl: string) : string; virtual; - function GetPreSubStr(AStr: Pchar) : string; virtual; - function GetPostSubStr(AStr: Pchar) : string; virtual; - function ErrorStr : string; virtual; - destructor Done; virtual; - end; - - function pcGrepMatch(WildCard, aStr: string; AOptions:integer; ALocale : Pointer): Boolean; - function pcGrepSub(WildCard, aStr, aRepl: string; AOptions:integer; ALocale : Pointer): string; - - function pcFastGrepMatch(WildCard, aStr: string): Boolean; - function pcFastGrepSub(WildCard, aStr, aRepl: string): string; - -{$IFDEF PCRE_5_0} - function pcGetVersion : pchar; -{$ENDIF} - - function pcError (var pRegExp : Pointer) : Boolean; - function pcInit (const Pattern: Shortstring; CaseSens: Boolean) : Pointer; - -Const { Options } - PCRE_CASELESS = $0001; - PCRE_MULTILINE = $0002; - PCRE_DOTALL = $0004; - PCRE_EXTENDED = $0008; - PCRE_ANCHORED = $0010; - PCRE_DOLLAR_ENDONLY = $0020; - PCRE_EXTRA = $0040; - PCRE_NOTBOL = $0080; - PCRE_NOTEOL = $0100; - PCRE_UNGREEDY = $0200; - PCRE_NOTEMPTY = $0400; -{$IFDEF PCRE_5_0} - PCRE_UTF8 = $0800; - PCRE_NO_AUTO_CAPTURE = $1000; - PCRE_NO_UTF8_CHECK = $2000; - PCRE_AUTO_CALLOUT = $4000; - PCRE_PARTIAL = $8000; -{$ENDIF} -{$IFDEF PCRE_7_0} - PCRE_DFA_SHORTEST = $00010000; - PCRE_DFA_RESTART = $00020000; - PCRE_FIRSTLINE = $00040000; - PCRE_DUPNAMES = $00080000; - PCRE_NEWLINE_CR = $00100000; - PCRE_NEWLINE_LF = $00200000; - PCRE_NEWLINE_CRLF = $00300000; - PCRE_NEWLINE_ANY = $00400000; - PCRE_NEWLINE_ANYCRLF = $00500000; - - PCRE_NEWLINE_BITS = PCRE_NEWLINE_CR or PCRE_NEWLINE_LF or PCRE_NEWLINE_ANY; - -{$ENDIF} -{$IFDEF PCRE_7_7} - PCRE_BSR_ANYCRLF = $00800000; - PCRE_BSR_UNICODE = $01000000; - PCRE_JAVASCRIPT_COMPAT= $02000000; -{$ENDIF} - - PCRE_COMPILE_ALLOWED_OPTIONS = PCRE_ANCHORED + PCRE_AUTO_CALLOUT + PCRE_CASELESS + - PCRE_DOLLAR_ENDONLY + PCRE_DOTALL + PCRE_EXTENDED + - PCRE_EXTRA + PCRE_MULTILINE + PCRE_NO_AUTO_CAPTURE + - PCRE_UNGREEDY + PCRE_UTF8 + PCRE_NO_UTF8_CHECK - {$IFDEF PCRE_7_0} - + PCRE_DUPNAMES + PCRE_FIRSTLINE + PCRE_NEWLINE_BITS - {$ENDIF} - {$IFDEF PCRE_7_7} - + PCRE_BSR_ANYCRLF + PCRE_BSR_UNICODE + PCRE_JAVASCRIPT_COMPAT - {$ENDIF} - ; - - PCRE_EXEC_ALLOWED_OPTIONS = PCRE_ANCHORED + PCRE_NOTBOL + PCRE_NOTEOL + - PCRE_NOTEMPTY + PCRE_NO_UTF8_CHECK + PCRE_PARTIAL - {$IFDEF PCRE_7_0} - + PCRE_NEWLINE_BITS - {$ENDIF} - {$IFDEF PCRE_7_7} - + PCRE_BSR_ANYCRLF + PCRE_BSR_UNICODE - {$ENDIF} - ; - -{$IFDEF PCRE_7_0} - PCRE_DFA_EXEC_ALLOWED_OPTIONS = PCRE_ANCHORED + PCRE_NOTBOL + PCRE_NOTEOL + - PCRE_NOTEMPTY + PCRE_NO_UTF8_CHECK + PCRE_PARTIAL + - PCRE_DFA_SHORTEST + PCRE_DFA_RESTART + - PCRE_NEWLINE_BITS - {$IFDEF PCRE_7_7} - + PCRE_BSR_ANYCRLF + PCRE_BSR_UNICODE - {$ENDIF} - ; -{$ENDIF} - -{ Exec-time and get/set-time error codes } - PCRE_ERROR_NOMATCH = -1; - PCRE_ERROR_NULL = -2; - PCRE_ERROR_BADOPTION = -3; - PCRE_ERROR_BADMAGIC = -4; - PCRE_ERROR_UNKNOWN_MODE = -5; - PCRE_ERROR_NOMEMORY = -6; - PCRE_ERROR_NOSUBSTRING = -7; -{$IFDEF PCRE_5_0} - PCRE_ERROR_MATCHLIMIT = -8; - PCRE_ERROR_CALLOUT = -9; { Never used by PCRE itself } - PCRE_ERROR_BADUTF8 = -10; - PCRE_ERROR_BADUTF8_OFFSET = -11; - PCRE_ERROR_PARTIAL = -12; - PCRE_ERROR_BADPARTIAL = -13; - PCRE_ERROR_INTERNAL = -14; - PCRE_ERROR_BADCOUNT = -15; -{$ENDIF} -{$IFDEF PCRE_7_0} - PCRE_ERROR_DFA_UITEM = -16; - PCRE_ERROR_DFA_UCOND = -17; - PCRE_ERROR_DFA_UMLIMIT = -18; - PCRE_ERROR_DFA_WSSIZE = -19; - PCRE_ERROR_DFA_RECURSE = -20; - PCRE_ERROR_RECURSIONLIMIT = -21; - PCRE_ERROR_NULLWSLIMIT = -22; - PCRE_ERROR_BADNEWLINE = -23; -{$ENDIF} - -{ Request types for pcre_fullinfo() } - - PCRE_INFO_OPTIONS = 0; - PCRE_INFO_SIZE = 1; - PCRE_INFO_CAPTURECOUNT = 2; - PCRE_INFO_BACKREFMAX = 3; - PCRE_INFO_FIRSTBYTE = 4; - PCRE_INFO_FIRSTCHAR = 4; { For backwards compatibility } - PCRE_INFO_FIRSTTABLE = 5; -{$IFDEF PCRE_5_0} - PCRE_INFO_LASTLITERAL = 6; - PCRE_INFO_NAMEENTRYSIZE = 7; - PCRE_INFO_NAMECOUNT = 8; - PCRE_INFO_NAMETABLE = 9; - PCRE_INFO_STUDYSIZE = 10; - PCRE_INFO_DEFAULT_TABLES = 11; -{$ENDIF PCRE_5_0} -{$IFDEF PCRE_7_7} - PCRE_INFO_OKPARTIAL = 12; - PCRE_INFO_JCHANGED = 13; - PCRE_INFO_HASCRORLF = 14; -{$ENDIF} - -{ Request types for pcre_config() } -{$IFDEF PCRE_5_0} - PCRE_CONFIG_UTF8 = 0; - PCRE_CONFIG_NEWLINE = 1; - PCRE_CONFIG_LINK_SIZE = 2; - PCRE_CONFIG_POSIX_MALLOC_THRESHOLD = 3; - PCRE_CONFIG_MATCH_LIMIT = 4; - PCRE_CONFIG_STACKRECURSE = 5; - PCRE_CONFIG_UNICODE_PROPERTIES = 6; -{$ENDIF PCRE_5_0} -{$IFDEF PCRE_7_0} - PCRE_CONFIG_MATCH_LIMIT_RECURSION = 7; -{$ENDIF} -{$IFDEF PCRE_7_7} - PCRE_CONFIG_BSR = 8; -{$ENDIF} - -{ Bit flags for the pcre_extra structure } -{$IFDEF PCRE_5_0} - PCRE_EXTRA_STUDY_DATA = $0001; - PCRE_EXTRA_MATCH_LIMIT = $0002; - PCRE_EXTRA_CALLOUT_DATA = $0004; - PCRE_EXTRA_TABLES = $0008; -{$ENDIF PCRE_5_0} -{$IFDEF PCRE_7_0} - PCRE_EXTRA_MATCH_LIMIT_RECURSION = $0010; -{$ENDIF} - -Const -// DefaultOptions : integer = 0; - DefaultLocaleTable : pointer = nil; - -{$IFDEF PCRE_5_0} -{ The structure for passing additional data to pcre_exec(). This is defined in -such as way as to be extensible. Always add new fields at the end, in order to -remain compatible. } - -type ppcre_extra = ^tpcre_extra; - tpcre_extra = record - flags : longint; { Bits for which fields are set } - study_data : pointer; { Opaque data from pcre_study() } - match_limit : longint; { Maximum number of calls to match() } - callout_data : pointer; { Data passed back in callouts } - tables : pointer; { Pointer to character tables } - match_limit_recursion: longint; { Max recursive calls to match() } - end; - -type ppcre_callout_block = ^pcre_callout_block; - pcre_callout_block = record - version, - (* ------------------------ Version 0 ------------------------------- *) - callout_number : integer; - offset_vector : pointer; - subject : pchar; - subject_length, start_match, current_position, capture_top, - capture_last : integer; - callout_data : pointer; - (* ------------------- Added for Version 1 -------------------------- *) - pattern_position, next_item_length : integer; - end; -{$ENDIF PCRE_5_0} - -{$OrgName+} -{$IFDEF VIRTUALPASCAL} {&Cdecl+} {$ENDIF VIRTUALPASCAL} - - { local replacement of external pcre memory management functions } - function pcre_malloc( size : integer ) : pointer; - procedure pcre_free( {var} p : pointer ); -{$IFDEF PCRE_5_0} - const pcre_stack_malloc: function ( size : integer ): pointer = pcre_malloc; - pcre_stack_free: procedure ( {var} p : pointer ) = pcre_free; - function pcre_callout(var p : ppcre_callout_block) : integer; -{$ENDIF PCRE_5_0} -{$IFDEF VIRTUALPASCAL} {&Cdecl-} {$ENDIF VIRTUALPASCAL} - -Implementation - -Uses strings, collect, messages, dnapp, commands, advance0, stringsx - {$IFDEF VIRTUALPASCAL} ,vpsyslow {$ENDIF VIRTUALPASCAL}; - -Const - MAGIC_NUMBER = $50435245; { 'PCRE' } - MAX_MATCHES = 90; { changed in 3.5 version; should be divisible by 3, was 64} - -Type - PMatchArray = ^TMatchArray; - TMatchArray = array[0..( MAX_MATCHES * 3 )] of integer; - - PRegExpCollection = ^TRegExpCollection; - TRegExpCollection = object(TSortedCollection) - MaxRegExp : integer; - SearchRegExp : shortstring; - CompareModeInsert : boolean; - constructor Init(AMaxRegExp:integer); - procedure FreeItem(P: Pointer); virtual; - function Compare(P1, P2: Pointer): Integer; virtual; - function Find(ARegExp:shortstring;var P: PpcRegExp):boolean; virtual; - function CheckNew(ARegExp:shortstring):PpcRegExp;virtual; - end; - -Var - PRegExpCache : PRegExpCollection; - - -{$IFDEF VIRTUALPASCAL} {&Cdecl+} {$ENDIF VIRTUALPASCAL} - - { imported original pcre functions } - - function pcre_compile( const pattern : PChar; options : integer; - var errorptr : PChar; var erroroffset : integer; - const tables : PChar ) : pointer {pcre}; external; -{$IFDEF PCRE_7_0} - function pcre_compile2( const pattern : PChar; options : integer; - var errorcodeptr : Integer; - var errorptr : PChar; var erroroffset : integer; - const tables : PChar ) : pointer {pcre}; external; -{$ENDIF} -{$IFDEF PCRE_5_0} - function pcre_config( what : integer; where : pointer) : integer; external; - function pcre_copy_named_substring( const code : pointer {pcre}; - const subject : pchar; - var ovector : integer; - stringcount : integer; - const stringname : pchar; - var buffer : pchar; - size : integer) : integer; external; - function pcre_copy_substring( const subject : pchar; var ovector : integer; - stringcount, stringnumber : integer; - var buffer : pchar; size : integer ) - : integer; external; - function pcre_exec( const argument_re : pointer {pcre}; - const extra_data : pointer {pcre_extra}; -{$ELSE} - function pcre_exec( const external_re : pointer; - const external_extra : pointer; -{$ENDIF} - const subject : PChar; - length, start_offset, options : integer; - offsets : pointer; - offsetcount : integer ) : integer; external; -{$IFDEF PCRE_7_0} - function pcre_dfa_exec( const argument_re : pointer {pcre}; - const extra_data : pointer {pcre_extra}; - const subject : pchar; - length, start_offset, options : integer; - offsets : pointer; - offsetcount : integer; - workspace : pointer; - wscount : integer ) : integer; external; -{$ENDIF} -{$IFDEF PCRE_5_0} - procedure pcre_free_substring( const p : pchar ); external; - procedure pcre_free_substring_list( var p : pchar ); external; - function pcre_fullinfo( const argument_re : pointer {pcre}; - const extra_data : pointer {pcre_extra}; - what : integer; - where : pointer ) : integer; external; - function pcre_get_named_substring( const code : pointer {pcre}; - const subject : pchar; - var ovector : integer; - stringcount : integer; - const stringname : pchar; - var stringptr : pchar ) : integer; external; - function pcre_get_stringnumber( const code : pointer {pcre}; - const stringname : pchar ) : integer; external; - function pcre_get_stringtable_entries( const code : pointer {pcre}; - const stringname : pchar; - var firstptr, - lastptr : pchar ) : integer; external; - function pcre_get_substring( const subject : pchar; var ovector : integer; - stringcount, stringnumber : integer; - var stringptr : pchar ) : integer; external; - function pcre_get_substring_list( const subject : pchar; var ovector : integer; - stringcount : integer; - listptr : pointer {const char ***listptr}) : integer; external; - function pcre_info( const argument_re : pointer {pcre}; - var optptr : integer; - var first_byte : integer ) : integer; external; - function pcre_maketables : pchar; external; -{$ENDIF} -{$IFDEF PCRE_7_0} - function pcre_refcount( const argument_re : pointer {pcre}; - adjust : integer ) : pchar; external; -{$ENDIF} - function pcre_study( const external_re : pointer {pcre}; - options : integer; - var errorptr : PChar ) : pointer {pcre_extra}; external; -{$IFDEF PCRE_5_0} - function pcre_version : pchar; external; -{$ENDIF} - - function pcre_malloc( size : integer ) : pointer; - begin - GetMem( result, size ); - end; - - procedure pcre_free( {var} p : pointer ); - begin - if (p <> nil) then - FreeMem( p, 0 ); - {@p := nil;} - end; - -{$IFDEF PCRE_5_0} -(* Called from PCRE as a result of the (?C) item. We print out where we are in -the match. Yield zero unless more callouts than the fail count, or the callout -data is not zero. *) - - function pcre_callout; - begin - end; -{$ENDIF} - -{$IFDEF VIRTUALPASCAL} {&Cdecl-} {$ENDIF VIRTUALPASCAL} - -// Always include the newest version of the library -{$IFDEF PCRE_7_7} - {$L pcre77.lib} -{$ELSE} - {$IFDEF PCRE_7_0} - {$L pcre70.lib} - {$ELSE} - {$IFDEF PCRE_5_0} - {$L pcre50.lib} - {$ELSE} - {$IFDEF PCRE_3_7} - {$L pcre37.lib} - {$ENDIF PCRE_3_7} - {$ENDIF PCRE_5_0} - {$ENDIF PCRE_7_0} -{$ENDIF PCRE_7_7} - -{TpcRegExp} - - constructor TpcRegExp.Init(const ARegExp:shortstring; AOptions:integer; ALocale : Pointer); - var - pRegExp : PChar; - begin - RegExp:=ARegExp; - RegExpC:=nil; - RegExpExt:=nil; - Matches:=nil; - MatchesCount:=0; - Error:=true; - ErrorMsg:=nil; - ErrorPos:=0; - RunTimeOptions := 0; - if length(RegExp) < 255 then - begin - RegExp[length(RegExp)+1]:=#0; - pRegExp:=@RegExp[1]; - end - else - begin - GetMem(pRegExp,length(RegExp)+1); - pRegExp:=strpcopy(pRegExp,RegExp); - end; - RegExpC := pcre_compile( pRegExp, - AOptions and PCRE_COMPILE_ALLOWED_OPTIONS, - ErrorMsg, ErrorPos, ALocale); - if length(RegExp) = 255 then - StrDispose(pRegExp); - if RegExpC = nil then - exit; - ErrorMsg:=nil; - RegExpExt := pcre_study( RegExpC, 0, ErrorMsg ); - if (RegExpExt = nil) and (ErrorMsg <> nil) then - begin - pcre_free(RegExpC); - exit; - end; - GetMem(Matches,SizeOf(TMatchArray)); - Error:=false; - end; - - destructor TpcRegExp.Done; - begin - if RegExpC <> nil then - pcre_free(RegExpC); - if RegExpExt <> nil then - pcre_free(RegExpExt); - if Matches <> nil then - FreeMem(Matches,SizeOf(TMatchArray)); - end; - - function TpcRegExp.SearchNext( AStr: Pchar; ALen : longint ) : boolean; - var Options: Integer; - begin // must handle PCRE_ERROR_PARTIAL here - Options := (RunTimeOptions or startup.MiscMultiData.cfgRegEx.DefaultOptions) and - PCRE_EXEC_ALLOWED_OPTIONS; - if MatchesCount > 0 then - MatchesCount:=pcre_exec( RegExpC, RegExpExt, AStr, ALen, PMatchArray(Matches)^[1], - Options, Matches, MAX_MATCHES ) else - MatchesCount:=pcre_exec( RegExpC, RegExpExt, AStr, ALen, 0, - Options, Matches, MAX_MATCHES ); -{ if MatchesCount = 0 then - MatchesCount := MatchesCount div 3;} - PartialMatch := MatchesCount = PCRE_ERROR_PARTIAL; - SearchNext := MatchesCount > 0; - end; - - function TpcRegExp.Search( AStr: Pchar; ALen : longint):boolean; - begin - MatchesCount:=0; - Search:=SearchNext(AStr,ALen); - SourceLen:=ALen; - end; - - function TpcRegExp.SearchOfs( AStr: Pchar; ALen, AOfs: longint ) : boolean; - var Options: Integer; - begin - MatchesCount:=0; - Options := (RunTimeOptions or startup.MiscMultiData.cfgRegEx.DefaultOptions) and - PCRE_EXEC_ALLOWED_OPTIONS; - MatchesCount:=pcre_exec( RegExpC, RegExpExt, AStr, ALen, AOfs, - Options, Matches, MAX_MATCHES ); - PartialMatch := MatchesCount = PCRE_ERROR_PARTIAL; - SearchOfs := MatchesCount > 0; - SourceLen := ALen-AOfs; - end; - - function TpcRegExp.MatchSub(ANom:integer; var Pos,Len:longint):boolean; - begin - if (MatchesCount > 0) and (ANom <= (MatchesCount-1)) then - begin - ANom:=ANom*2; - Pos:=PMatchArray(Matches)^[ANom]; - Len:=PMatchArray(Matches)^[ANom+1]-Pos; - MatchSub:=true; - end - else - MatchSub:=false; - end; - - function TpcRegExp.MatchFull(var Pos,Len:longint):boolean; - begin - MatchFull:=MatchSub(0,Pos,Len); - end; - - function TpcRegExp.GetSubStr(ANom: integer; AStr: Pchar):string; - var - s: ansistring; - pos,len: longint; - begin - s:=''; - if MatchSub(ANom, pos, len) then - begin - setlength(s, len); - Move(AStr[pos], s[1], len); - end; - GetSubStr:=s; - end; - - function TpcRegExp.GetPreSubStr(AStr: Pchar):string; - var - s: ansistring; - l: longint; - begin - s:=''; - if (MatchesCount > 0) then - begin - l:=PMatchArray(Matches)^[0]-1; - if l > 0 then - begin - setlength(s,l); - Move(AStr[1],s[1],l); - end; - end; - GetPreSubStr:=s; - end; - - function TpcRegExp.GetPostSubStr(AStr: Pchar):string; - var - s: ansistring; - l: longint; - ANom: integer; - begin - s:=''; - if (MatchesCount > 0) then - begin - ANom:=(MatchesCount-1){*2} shl 1; - l:=SourceLen-PMatchArray(Matches)^[ANom+1]+1; - if l > 0 then - begin - setlength(s,l); - Move(AStr[PMatchArray(Matches)^[ANom+1]],s[1],l); - end; - end; - GetPostSubStr:=s; - end; - - - function TpcRegExp.GetFullStr(AStr: Pchar):string; - var - s: ansistring; - l: longint; - begin - GetFullStr:=GetSubStr(0,AStr); - end; - - function TpcRegExp.GetReplStr(AStr: Pchar; const ARepl: string):string; - var - s: ansistring; - l,i,lasti: longint; - begin - l:=length(ARepl); - i:=1; - lasti:=1; - s:=''; - while i <= l do - begin - case ARepl[i] of - '\' : - begin - if i < l then - begin - s:=s+copy(ARepl,lasti,i-lasti){+ARepl[i+1]}; - {AH 17-10-05 support for POSIX \1-\9 backreferences} - case ARepl[i+1] of - '0' : s:=s+GetFullStr(AStr); - '1'..'9' : s:=s+GetSubStr(ord(ARepl[i+1])-ord('0'),AStr); - else s:=s+ARepl[i+1]; // copy the escaped character - end; - end; - inc(i); - lasti:=i+1; - end; - '$' : - begin - if i < l then - begin - s:=s+copy(ARepl,lasti,i-lasti); - case ARepl[i+1] of - '&' : s:=s+GetFullStr(AStr); - '1'..'9' : s:=s+GetSubStr(ord(ARepl[i+1])-ord('0'),AStr); - '`' : s:=s+GetPreSubStr(AStr); - #39 : s:=s+GetPostSubStr(AStr); - end; - end; - inc(i); - lasti:=i+1; - end; - end; - inc(i); - end; - if lasti <= {AH 25-10-2004 added =, else l==1 won't work} l then - s:=s+copy(ARepl,lasti,l-lasti+1); - GetReplStr:=s; - end; - - function TpcRegExp.ErrorStr:string; - begin - ErrorStr:=StrPas(ErrorMsg); - end; - -{TRegExpCollection} - -constructor TRegExpCollection.Init(AMaxRegExp: integer); -begin - Inherited Init(1,1); - MaxRegExp:=AMaxRegExp; - CompareModeInsert:=true; -end; - -procedure TRegExpCollection.FreeItem(P: Pointer); -begin - if P <> nil then - begin - Dispose(PpcRegExp(P),Done); - end; -end; - -function TRegExpCollection.Compare(P1, P2: Pointer): Integer; -//var -// l,l1,l2,i : byte; -//// wPos: pchar; -begin - if CompareModeInsert then - begin -// l1:=length(PpcRegExp(P1)^.RegExp); -// l2:=length(PpcRegExp(P2)^.RegExp); -// if l1 > l2 then l:=l2 else -// l:=l1; -// for i:=1 to l do -// if PpcRegExp(P1).RegExp[i] <> PpcRegExp(P2).RegExp[i] then break; -// if i <=l then -// Compare:=ord(PpcRegExp(P1).RegExp[i])-ord(PpcRegExp(P2).RegExp[i]) else -// Compare:=l1-l2; - Compare := stringsx.PasStrCmp(PpcRegExp(P1).RegExp, PpcRegExp(P2).RegExp, False); - end - else - begin -// l1:=length(PpcRegExp(P1)^.RegExp); -// l2:=length(SearchRegExp); -// if l1 > l2 then l:=l2 else -// l:=l1; -// for i:=1 to l do -// if PpcRegExp(P1).RegExp[i] <> SearchRegExp[i] then -// begin -// Compare:=ord(PpcRegExp(P1).RegExp[i])-ord(SearchRegExp[i]); -// break; -// end; -// if i > l then Compare:=l1-l2; - Compare := stringsx.PasStrCmp(PpcRegExp(P1).RegExp, SearchRegExp, False); - end; -end; - -function TRegExpCollection.Find(ARegExp:shortstring;var P: PpcRegExp):boolean; -var I : integer; -begin - CompareModeInsert:=false; - SearchRegExp:=ARegExp; - if Search(nil,I) then - begin - P:=PpcRegExp(At(I)); - Find:=true; - end - else - begin - P:=nil; - Find:=false; - end; - CompareModeInsert:=true; -end; - -function TRegExpCollection.CheckNew(ARegExp:shortstring):PpcRegExp; -var - P : PpcRegExp; -begin - if not Find(ARegExp,P) then - begin - if Count = MaxRegExp then - AtFree(0); - P:=New(ppcRegExp,Init(ARegExp,PCRE_CASELESS,nil)); - Insert(P); - end; - CheckNew:=P; -end; - -function pcGrepMatch(WildCard, aStr: string; AOptions:integer; ALocale : Pointer): Boolean; -var - PpcRE:PpcRegExp; -begin - PpcRE:=New(ppcRegExp,Init(WildCard,AOptions,Alocale)); - pcGrepMatch:=PpcRE^.Search(pchar(AStr),Length(AStr)); - Dispose(PpcRE,Done); -end; - -function pcGrepSub(WildCard, aStr, aRepl: string; AOptions:integer; ALocale : Pointer): string; -var - PpcRE:PpcRegExp; -begin - PpcRE:=New(ppcRegExp,Init(WildCard,AOptions,Alocale)); - if PpcRE^.Search(pchar(AStr),Length(AStr)) then - pcGrepSub:=PpcRE^.GetReplStr(pchar(AStr),ARepl) - else - pcGrepSub:=''; - Dispose(PpcRE,Done); -end; - -function pcFastGrepMatch(WildCard, aStr: string): Boolean; -var - PpcRE:PpcRegExp; -begin - PpcRE:=PRegExpCache^.CheckNew(WildCard); - pcFastGrepMatch:=PpcRE^.Search(pchar(AStr),Length(AStr)); -end; - -function pcFastGrepSub(WildCard, aStr, aRepl: string): string; -var - PpcRE:PpcRegExp; -begin - PpcRE:=PRegExpCache^.CheckNew(WildCard); - if PpcRE^.Search(pchar(AStr),Length(AStr)) then - pcFastGrepSub:=PpcRE^.GetReplStr(pchar(AStr),ARepl) - else - pcFastGrepSub:=''; -end; - -{$IFDEF PCRE_5_0} -function pcGetVersion : pchar; assembler; {$FRAME-}{$USES none} -asm - call pcre_version -end; -{$ENDIF PCRE_5_0} - -function pcError; -var P: ppcRegExp absolute pRegExp; -begin - Result := (P = nil) or P^.Error; - If Result and (P <> nil) then - begin -{ if P^.ErrorPos = 0 then - MessageBox(GetString(erRegExpCompile)+'"'+P^.ErrorStr+'"', nil,mfConfirmation+mfOkButton) - else} - MessageBox(GetString(erRegExpCompile)+'"'+P^.ErrorStr+'"'+GetString(erRegExpCompPos), - @P^.ErrorPos,mfConfirmation+mfOkButton); - Dispose(P, Done); - P:=nil; - end; -end; - -function pcInit; -var Options : Integer; -begin - If CaseSens then Options := 0 else Options := PCRE_CASELESS; - Result := New( PpcRegExp, Init( Pattern, - {DefaultOptions} - startup.MiscMultiData.cfgRegEx.DefaultOptions or Options, - DefaultLocaleTable) ); -end; - -Initialization - PRegExpCache:=New(PRegExpCollection,Init(64)); -Finalization - Dispose(PRegExpCache,Done); -End. diff --git a/libs/pcre/pcregrep.c b/libs/pcre/pcregrep.c deleted file mode 100644 index a381f9526a..0000000000 --- a/libs/pcre/pcregrep.c +++ /dev/null @@ -1,2433 +0,0 @@ -/************************************************* -* pcregrep program * -*************************************************/ - -/* This is a grep program that uses the PCRE regular expression library to do -its pattern matching. On a Unix or Win32 system it can recurse into -directories. - - Copyright (c) 1997-2009 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include -#include -#include -#include -#include -#include - -#include -#include - -#ifdef HAVE_UNISTD_H -#include -#endif - -#ifdef SUPPORT_LIBZ -#include -#endif - -#ifdef SUPPORT_LIBBZ2 -#include -#endif - -#include "pcre.h" - -#define FALSE 0 -#define TRUE 1 - -typedef int BOOL; - -#define MAX_PATTERN_COUNT 100 -#define OFFSET_SIZE 99 - -#if BUFSIZ > 8192 -#define MBUFTHIRD BUFSIZ -#else -#define MBUFTHIRD 8192 -#endif - -/* Values for the "filenames" variable, which specifies options for file name -output. The order is important; it is assumed that a file name is wanted for -all values greater than FN_DEFAULT. */ - -enum { FN_NONE, FN_DEFAULT, FN_ONLY, FN_NOMATCH_ONLY, FN_FORCE }; - -/* File reading styles */ - -enum { FR_PLAIN, FR_LIBZ, FR_LIBBZ2 }; - -/* Actions for the -d and -D options */ - -enum { dee_READ, dee_SKIP, dee_RECURSE }; -enum { DEE_READ, DEE_SKIP }; - -/* Actions for special processing options (flag bits) */ - -#define PO_WORD_MATCH 0x0001 -#define PO_LINE_MATCH 0x0002 -#define PO_FIXED_STRINGS 0x0004 - -/* Line ending types */ - -enum { EL_LF, EL_CR, EL_CRLF, EL_ANY, EL_ANYCRLF }; - - - -/************************************************* -* Global variables * -*************************************************/ - -/* Jeffrey Friedl has some debugging requirements that are not part of the -regular code. */ - -#ifdef JFRIEDL_DEBUG -static int S_arg = -1; -static unsigned int jfriedl_XR = 0; /* repeat regex attempt this many times */ -static unsigned int jfriedl_XT = 0; /* replicate text this many times */ -static const char *jfriedl_prefix = ""; -static const char *jfriedl_postfix = ""; -#endif - -static int endlinetype; - -static char *colour_string = (char *)"1;31"; -static char *colour_option = NULL; -static char *dee_option = NULL; -static char *DEE_option = NULL; -static char *newline = NULL; -static char *pattern_filename = NULL; -static char *stdin_name = (char *)"(standard input)"; -static char *locale = NULL; - -static const unsigned char *pcretables = NULL; - -static int pattern_count = 0; -static pcre **pattern_list = NULL; -static pcre_extra **hints_list = NULL; - -static char *include_pattern = NULL; -static char *exclude_pattern = NULL; -static char *include_dir_pattern = NULL; -static char *exclude_dir_pattern = NULL; - -static pcre *include_compiled = NULL; -static pcre *exclude_compiled = NULL; -static pcre *include_dir_compiled = NULL; -static pcre *exclude_dir_compiled = NULL; - -static int after_context = 0; -static int before_context = 0; -static int both_context = 0; -static int dee_action = dee_READ; -static int DEE_action = DEE_READ; -static int error_count = 0; -static int filenames = FN_DEFAULT; -static int process_options = 0; - -static BOOL count_only = FALSE; -static BOOL do_colour = FALSE; -static BOOL file_offsets = FALSE; -static BOOL hyphenpending = FALSE; -static BOOL invert = FALSE; -static BOOL line_offsets = FALSE; -static BOOL multiline = FALSE; -static BOOL number = FALSE; -static BOOL only_matching = FALSE; -static BOOL quiet = FALSE; -static BOOL silent = FALSE; -static BOOL utf8 = FALSE; - -/* Structure for options and list of them */ - -enum { OP_NODATA, OP_STRING, OP_OP_STRING, OP_NUMBER, OP_OP_NUMBER, - OP_PATLIST }; - -typedef struct option_item { - int type; - int one_char; - void *dataptr; - const char *long_name; - const char *help_text; -} option_item; - -/* Options without a single-letter equivalent get a negative value. This can be -used to identify them. */ - -#define N_COLOUR (-1) -#define N_EXCLUDE (-2) -#define N_EXCLUDE_DIR (-3) -#define N_HELP (-4) -#define N_INCLUDE (-5) -#define N_INCLUDE_DIR (-6) -#define N_LABEL (-7) -#define N_LOCALE (-8) -#define N_NULL (-9) -#define N_LOFFSETS (-10) -#define N_FOFFSETS (-11) - -static option_item optionlist[] = { - { OP_NODATA, N_NULL, NULL, "", " terminate options" }, - { OP_NODATA, N_HELP, NULL, "help", "display this help and exit" }, - { OP_NUMBER, 'A', &after_context, "after-context=number", "set number of following context lines" }, - { OP_NUMBER, 'B', &before_context, "before-context=number", "set number of prior context lines" }, - { OP_OP_STRING, N_COLOUR, &colour_option, "color=option", "matched text color option" }, - { OP_NUMBER, 'C', &both_context, "context=number", "set number of context lines, before & after" }, - { OP_NODATA, 'c', NULL, "count", "print only a count of matching lines per FILE" }, - { OP_OP_STRING, N_COLOUR, &colour_option, "colour=option", "matched text colour option" }, - { OP_STRING, 'D', &DEE_option, "devices=action","how to handle devices, FIFOs, and sockets" }, - { OP_STRING, 'd', &dee_option, "directories=action", "how to handle directories" }, - { OP_PATLIST, 'e', NULL, "regex(p)", "specify pattern (may be used more than once)" }, - { OP_NODATA, 'F', NULL, "fixed_strings", "patterns are sets of newline-separated strings" }, - { OP_STRING, 'f', &pattern_filename, "file=path", "read patterns from file" }, - { OP_NODATA, N_FOFFSETS, NULL, "file-offsets", "output file offsets, not text" }, - { OP_NODATA, 'H', NULL, "with-filename", "force the prefixing filename on output" }, - { OP_NODATA, 'h', NULL, "no-filename", "suppress the prefixing filename on output" }, - { OP_NODATA, 'i', NULL, "ignore-case", "ignore case distinctions" }, - { OP_NODATA, 'l', NULL, "files-with-matches", "print only FILE names containing matches" }, - { OP_NODATA, 'L', NULL, "files-without-match","print only FILE names not containing matches" }, - { OP_STRING, N_LABEL, &stdin_name, "label=name", "set name for standard input" }, - { OP_NODATA, N_LOFFSETS, NULL, "line-offsets", "output line numbers and offsets, not text" }, - { OP_STRING, N_LOCALE, &locale, "locale=locale", "use the named locale" }, - { OP_NODATA, 'M', NULL, "multiline", "run in multiline mode" }, - { OP_STRING, 'N', &newline, "newline=type", "set newline type (CR, LF, CRLF, ANYCRLF or ANY)" }, - { OP_NODATA, 'n', NULL, "line-number", "print line number with output lines" }, - { OP_NODATA, 'o', NULL, "only-matching", "show only the part of the line that matched" }, - { OP_NODATA, 'q', NULL, "quiet", "suppress output, just set return code" }, - { OP_NODATA, 'r', NULL, "recursive", "recursively scan sub-directories" }, - { OP_STRING, N_EXCLUDE,&exclude_pattern, "exclude=pattern","exclude matching files when recursing" }, - { OP_STRING, N_INCLUDE,&include_pattern, "include=pattern","include matching files when recursing" }, - { OP_STRING, N_EXCLUDE_DIR,&exclude_dir_pattern, "exclude_dir=pattern","exclude matching directories when recursing" }, - { OP_STRING, N_INCLUDE_DIR,&include_dir_pattern, "include_dir=pattern","include matching directories when recursing" }, -#ifdef JFRIEDL_DEBUG - { OP_OP_NUMBER, 'S', &S_arg, "jeffS", "replace matched (sub)string with X" }, -#endif - { OP_NODATA, 's', NULL, "no-messages", "suppress error messages" }, - { OP_NODATA, 'u', NULL, "utf-8", "use UTF-8 mode" }, - { OP_NODATA, 'V', NULL, "version", "print version information and exit" }, - { OP_NODATA, 'v', NULL, "invert-match", "select non-matching lines" }, - { OP_NODATA, 'w', NULL, "word-regex(p)", "force patterns to match only as words" }, - { OP_NODATA, 'x', NULL, "line-regex(p)", "force patterns to match only whole lines" }, - { OP_NODATA, 0, NULL, NULL, NULL } -}; - -/* Tables for prefixing and suffixing patterns, according to the -w, -x, and -F -options. These set the 1, 2, and 4 bits in process_options, respectively. Note -that the combination of -w and -x has the same effect as -x on its own, so we -can treat them as the same. */ - -static const char *prefix[] = { - "", "\\b", "^(?:", "^(?:", "\\Q", "\\b\\Q", "^(?:\\Q", "^(?:\\Q" }; - -static const char *suffix[] = { - "", "\\b", ")$", ")$", "\\E", "\\E\\b", "\\E)$", "\\E)$" }; - -/* UTF-8 tables - used only when the newline setting is "any". */ - -const int utf8_table3[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01}; - -const char utf8_table4[] = { - 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, - 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, - 2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, - 3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 }; - - - -/************************************************* -* OS-specific functions * -*************************************************/ - -/* These functions are defined so that they can be made system specific, -although at present the only ones are for Unix, Win32, and for "no support". */ - - -/************* Directory scanning in Unix ***********/ - -#if defined HAVE_SYS_STAT_H && defined HAVE_DIRENT_H && defined HAVE_SYS_TYPES_H -#include -#include -#include - -typedef DIR directory_type; - -static int -isdirectory(char *filename) -{ -struct stat statbuf; -if (stat(filename, &statbuf) < 0) - return 0; /* In the expectation that opening as a file will fail */ -return ((statbuf.st_mode & S_IFMT) == S_IFDIR)? '/' : 0; -} - -static directory_type * -opendirectory(char *filename) -{ -return opendir(filename); -} - -static char * -readdirectory(directory_type *dir) -{ -for (;;) - { - struct dirent *dent = readdir(dir); - if (dent == NULL) return NULL; - if (strcmp(dent->d_name, ".") != 0 && strcmp(dent->d_name, "..") != 0) - return dent->d_name; - } -/* Control never reaches here */ -} - -static void -closedirectory(directory_type *dir) -{ -closedir(dir); -} - - -/************* Test for regular file in Unix **********/ - -static int -isregfile(char *filename) -{ -struct stat statbuf; -if (stat(filename, &statbuf) < 0) - return 1; /* In the expectation that opening as a file will fail */ -return (statbuf.st_mode & S_IFMT) == S_IFREG; -} - - -/************* Test stdout for being a terminal in Unix **********/ - -static BOOL -is_stdout_tty(void) -{ -return isatty(fileno(stdout)); -} - - -/************* Directory scanning in Win32 ***********/ - -/* I (Philip Hazel) have no means of testing this code. It was contributed by -Lionel Fourquaux. David Burgess added a patch to define INVALID_FILE_ATTRIBUTES -when it did not exist. David Byron added a patch that moved the #include of - to before the INVALID_FILE_ATTRIBUTES definition rather than after. -*/ - -#elif HAVE_WINDOWS_H - -#ifndef STRICT -# define STRICT -#endif -#ifndef WIN32_LEAN_AND_MEAN -# define WIN32_LEAN_AND_MEAN -#endif - -#include - -#ifndef INVALID_FILE_ATTRIBUTES -#define INVALID_FILE_ATTRIBUTES 0xFFFFFFFF -#endif - -typedef struct directory_type -{ -HANDLE handle; -BOOL first; -WIN32_FIND_DATA data; -} directory_type; - -int -isdirectory(char *filename) -{ -DWORD attr = GetFileAttributes(filename); -if (attr == INVALID_FILE_ATTRIBUTES) - return 0; -return ((attr & FILE_ATTRIBUTE_DIRECTORY) != 0) ? '/' : 0; -} - -directory_type * -opendirectory(char *filename) -{ -size_t len; -char *pattern; -directory_type *dir; -DWORD err; -len = strlen(filename); -pattern = (char *) malloc(len + 3); -dir = (directory_type *) malloc(sizeof(*dir)); -if ((pattern == NULL) || (dir == NULL)) - { - fprintf(stderr, "pcregrep: malloc failed\n"); - exit(2); - } -memcpy(pattern, filename, len); -memcpy(&(pattern[len]), "\\*", 3); -dir->handle = FindFirstFile(pattern, &(dir->data)); -if (dir->handle != INVALID_HANDLE_VALUE) - { - free(pattern); - dir->first = TRUE; - return dir; - } -err = GetLastError(); -free(pattern); -free(dir); -errno = (err == ERROR_ACCESS_DENIED) ? EACCES : ENOENT; -return NULL; -} - -char * -readdirectory(directory_type *dir) -{ -for (;;) - { - if (!dir->first) - { - if (!FindNextFile(dir->handle, &(dir->data))) - return NULL; - } - else - { - dir->first = FALSE; - } - if (strcmp(dir->data.cFileName, ".") != 0 && strcmp(dir->data.cFileName, "..") != 0) - return dir->data.cFileName; - } -#ifndef _MSC_VER -return NULL; /* Keep compiler happy; never executed */ -#endif -} - -void -closedirectory(directory_type *dir) -{ -FindClose(dir->handle); -free(dir); -} - - -/************* Test for regular file in Win32 **********/ - -/* I don't know how to do this, or if it can be done; assume all paths are -regular if they are not directories. */ - -int isregfile(char *filename) -{ -return !isdirectory(filename); -} - - -/************* Test stdout for being a terminal in Win32 **********/ - -/* I don't know how to do this; assume never */ - -static BOOL -is_stdout_tty(void) -{ -return FALSE; -} - - -/************* Directory scanning when we can't do it ***********/ - -/* The type is void, and apart from isdirectory(), the functions do nothing. */ - -#else - -typedef void directory_type; - -int isdirectory(char *filename) { return 0; } -directory_type * opendirectory(char *filename) { return (directory_type*)0;} -char *readdirectory(directory_type *dir) { return (char*)0;} -void closedirectory(directory_type *dir) {} - - -/************* Test for regular when we can't do it **********/ - -/* Assume all files are regular. */ - -int isregfile(char *filename) { return 1; } - - -/************* Test stdout for being a terminal when we can't do it **********/ - -static BOOL -is_stdout_tty(void) -{ -return FALSE; -} - - -#endif - - - -#ifndef HAVE_STRERROR -/************************************************* -* Provide strerror() for non-ANSI libraries * -*************************************************/ - -/* Some old-fashioned systems still around (e.g. SunOS4) don't have strerror() -in their libraries, but can provide the same facility by this simple -alternative function. */ - -extern int sys_nerr; -extern char *sys_errlist[]; - -char * -strerror(int n) -{ -if (n < 0 || n >= sys_nerr) return "unknown error number"; -return sys_errlist[n]; -} -#endif /* HAVE_STRERROR */ - - - -/************************************************* -* Find end of line * -*************************************************/ - -/* The length of the endline sequence that is found is set via lenptr. This may -be zero at the very end of the file if there is no line-ending sequence there. - -Arguments: - p current position in line - endptr end of available data - lenptr where to put the length of the eol sequence - -Returns: pointer to the last byte of the line -*/ - -static char * -end_of_line(char *p, char *endptr, int *lenptr) -{ -switch(endlinetype) - { - default: /* Just in case */ - case EL_LF: - while (p < endptr && *p != '\n') p++; - if (p < endptr) - { - *lenptr = 1; - return p + 1; - } - *lenptr = 0; - return endptr; - - case EL_CR: - while (p < endptr && *p != '\r') p++; - if (p < endptr) - { - *lenptr = 1; - return p + 1; - } - *lenptr = 0; - return endptr; - - case EL_CRLF: - for (;;) - { - while (p < endptr && *p != '\r') p++; - if (++p >= endptr) - { - *lenptr = 0; - return endptr; - } - if (*p == '\n') - { - *lenptr = 2; - return p + 1; - } - } - break; - - case EL_ANYCRLF: - while (p < endptr) - { - int extra = 0; - register int c = *((unsigned char *)p); - - if (utf8 && c >= 0xc0) - { - int gcii, gcss; - extra = utf8_table4[c & 0x3f]; /* Number of additional bytes */ - gcss = 6*extra; - c = (c & utf8_table3[extra]) << gcss; - for (gcii = 1; gcii <= extra; gcii++) - { - gcss -= 6; - c |= (p[gcii] & 0x3f) << gcss; - } - } - - p += 1 + extra; - - switch (c) - { - case 0x0a: /* LF */ - *lenptr = 1; - return p; - - case 0x0d: /* CR */ - if (p < endptr && *p == 0x0a) - { - *lenptr = 2; - p++; - } - else *lenptr = 1; - return p; - - default: - break; - } - } /* End of loop for ANYCRLF case */ - - *lenptr = 0; /* Must have hit the end */ - return endptr; - - case EL_ANY: - while (p < endptr) - { - int extra = 0; - register int c = *((unsigned char *)p); - - if (utf8 && c >= 0xc0) - { - int gcii, gcss; - extra = utf8_table4[c & 0x3f]; /* Number of additional bytes */ - gcss = 6*extra; - c = (c & utf8_table3[extra]) << gcss; - for (gcii = 1; gcii <= extra; gcii++) - { - gcss -= 6; - c |= (p[gcii] & 0x3f) << gcss; - } - } - - p += 1 + extra; - - switch (c) - { - case 0x0a: /* LF */ - case 0x0b: /* VT */ - case 0x0c: /* FF */ - *lenptr = 1; - return p; - - case 0x0d: /* CR */ - if (p < endptr && *p == 0x0a) - { - *lenptr = 2; - p++; - } - else *lenptr = 1; - return p; - - case 0x85: /* NEL */ - *lenptr = utf8? 2 : 1; - return p; - - case 0x2028: /* LS */ - case 0x2029: /* PS */ - *lenptr = 3; - return p; - - default: - break; - } - } /* End of loop for ANY case */ - - *lenptr = 0; /* Must have hit the end */ - return endptr; - } /* End of overall switch */ -} - - - -/************************************************* -* Find start of previous line * -*************************************************/ - -/* This is called when looking back for before lines to print. - -Arguments: - p start of the subsequent line - startptr start of available data - -Returns: pointer to the start of the previous line -*/ - -static char * -previous_line(char *p, char *startptr) -{ -switch(endlinetype) - { - default: /* Just in case */ - case EL_LF: - p--; - while (p > startptr && p[-1] != '\n') p--; - return p; - - case EL_CR: - p--; - while (p > startptr && p[-1] != '\n') p--; - return p; - - case EL_CRLF: - for (;;) - { - p -= 2; - while (p > startptr && p[-1] != '\n') p--; - if (p <= startptr + 1 || p[-2] == '\r') return p; - } - return p; /* But control should never get here */ - - case EL_ANY: - case EL_ANYCRLF: - if (*(--p) == '\n' && p > startptr && p[-1] == '\r') p--; - if (utf8) while ((*p & 0xc0) == 0x80) p--; - - while (p > startptr) - { - register int c; - char *pp = p - 1; - - if (utf8) - { - int extra = 0; - while ((*pp & 0xc0) == 0x80) pp--; - c = *((unsigned char *)pp); - if (c >= 0xc0) - { - int gcii, gcss; - extra = utf8_table4[c & 0x3f]; /* Number of additional bytes */ - gcss = 6*extra; - c = (c & utf8_table3[extra]) << gcss; - for (gcii = 1; gcii <= extra; gcii++) - { - gcss -= 6; - c |= (pp[gcii] & 0x3f) << gcss; - } - } - } - else c = *((unsigned char *)pp); - - if (endlinetype == EL_ANYCRLF) switch (c) - { - case 0x0a: /* LF */ - case 0x0d: /* CR */ - return p; - - default: - break; - } - - else switch (c) - { - case 0x0a: /* LF */ - case 0x0b: /* VT */ - case 0x0c: /* FF */ - case 0x0d: /* CR */ - case 0x85: /* NEL */ - case 0x2028: /* LS */ - case 0x2029: /* PS */ - return p; - - default: - break; - } - - p = pp; /* Back one character */ - } /* End of loop for ANY case */ - - return startptr; /* Hit start of data */ - } /* End of overall switch */ -} - - - - - -/************************************************* -* Print the previous "after" lines * -*************************************************/ - -/* This is called if we are about to lose said lines because of buffer filling, -and at the end of the file. The data in the line is written using fwrite() so -that a binary zero does not terminate it. - -Arguments: - lastmatchnumber the number of the last matching line, plus one - lastmatchrestart where we restarted after the last match - endptr end of available data - printname filename for printing - -Returns: nothing -*/ - -static void do_after_lines(int lastmatchnumber, char *lastmatchrestart, - char *endptr, char *printname) -{ -if (after_context > 0 && lastmatchnumber > 0) - { - int count = 0; - while (lastmatchrestart < endptr && count++ < after_context) - { - int ellength; - char *pp = lastmatchrestart; - if (printname != NULL) fprintf(stdout, "%s-", printname); - if (number) fprintf(stdout, "%d-", lastmatchnumber++); - pp = end_of_line(pp, endptr, &ellength); - fwrite(lastmatchrestart, 1, pp - lastmatchrestart, stdout); - lastmatchrestart = pp; - } - hyphenpending = TRUE; - } -} - - - -/************************************************* -* Apply patterns to subject till one matches * -*************************************************/ - -/* This function is called to run through all patterns, looking for a match. It -is used multiple times for the same subject when colouring is enabled, in order -to find all possible matches. - -Arguments: - matchptr the start of the subject - length the length of the subject to match - offsets the offets vector to fill in - mrc address of where to put the result of pcre_exec() - -Returns: TRUE if there was a match - FALSE if there was no match - invert if there was a non-fatal error -*/ - -static BOOL -match_patterns(char *matchptr, size_t length, int *offsets, int *mrc) -{ -int i; -for (i = 0; i < pattern_count; i++) - { - *mrc = pcre_exec(pattern_list[i], hints_list[i], matchptr, length, 0, - PCRE_NOTEMPTY, offsets, OFFSET_SIZE); - if (*mrc >= 0) return TRUE; - if (*mrc == PCRE_ERROR_NOMATCH) continue; - fprintf(stderr, "pcregrep: pcre_exec() error %d while matching ", *mrc); - if (pattern_count > 1) fprintf(stderr, "pattern number %d to ", i+1); - fprintf(stderr, "this text:\n"); - fwrite(matchptr, 1, length, stderr); /* In case binary zero included */ - fprintf(stderr, "\n"); - if (error_count == 0 && - (*mrc == PCRE_ERROR_MATCHLIMIT || *mrc == PCRE_ERROR_RECURSIONLIMIT)) - { - fprintf(stderr, "pcregrep: error %d means that a resource limit " - "was exceeded\n", *mrc); - fprintf(stderr, "pcregrep: check your regex for nested unlimited loops\n"); - } - if (error_count++ > 20) - { - fprintf(stderr, "pcregrep: too many errors - abandoned\n"); - exit(2); - } - return invert; /* No more matching; don't show the line again */ - } - -return FALSE; /* No match, no errors */ -} - - - -/************************************************* -* Grep an individual file * -*************************************************/ - -/* This is called from grep_or_recurse() below. It uses a buffer that is three -times the value of MBUFTHIRD. The matching point is never allowed to stray into -the top third of the buffer, thus keeping more of the file available for -context printing or for multiline scanning. For large files, the pointer will -be in the middle third most of the time, so the bottom third is available for -"before" context printing. - -Arguments: - handle the fopened FILE stream for a normal file - the gzFile pointer when reading is via libz - the BZFILE pointer when reading is via libbz2 - frtype FR_PLAIN, FR_LIBZ, or FR_LIBBZ2 - printname the file name if it is to be printed for each match - or NULL if the file name is not to be printed - it cannot be NULL if filenames[_nomatch]_only is set - -Returns: 0 if there was at least one match - 1 otherwise (no matches) - 2 if there is a read error on a .bz2 file -*/ - -static int -pcregrep(void *handle, int frtype, char *printname) -{ -int rc = 1; -int linenumber = 1; -int lastmatchnumber = 0; -int count = 0; -int filepos = 0; -int offsets[OFFSET_SIZE]; -char *lastmatchrestart = NULL; -char buffer[3*MBUFTHIRD]; -char *ptr = buffer; -char *endptr; -size_t bufflength; -BOOL endhyphenpending = FALSE; -FILE *in = NULL; /* Ensure initialized */ - -#ifdef SUPPORT_LIBZ -gzFile ingz = NULL; -#endif - -#ifdef SUPPORT_LIBBZ2 -BZFILE *inbz2 = NULL; -#endif - - -/* Do the first read into the start of the buffer and set up the pointer to end -of what we have. In the case of libz, a non-zipped .gz file will be read as a -plain file. However, if a .bz2 file isn't actually bzipped, the first read will -fail. */ - -#ifdef SUPPORT_LIBZ -if (frtype == FR_LIBZ) - { - ingz = (gzFile)handle; - bufflength = gzread (ingz, buffer, 3*MBUFTHIRD); - } -else -#endif - -#ifdef SUPPORT_LIBBZ2 -if (frtype == FR_LIBBZ2) - { - inbz2 = (BZFILE *)handle; - bufflength = BZ2_bzread(inbz2, buffer, 3*MBUFTHIRD); - if ((int)bufflength < 0) return 2; /* Gotcha: bufflength is size_t; */ - } /* without the cast it is unsigned. */ -else -#endif - - { - in = (FILE *)handle; - bufflength = fread(buffer, 1, 3*MBUFTHIRD, in); - } - -endptr = buffer + bufflength; - -/* Loop while the current pointer is not at the end of the file. For large -files, endptr will be at the end of the buffer when we are in the middle of the -file, but ptr will never get there, because as soon as it gets over 2/3 of the -way, the buffer is shifted left and re-filled. */ - -while (ptr < endptr) - { - int endlinelength; - int mrc = 0; - BOOL match; - char *matchptr = ptr; - char *t = ptr; - size_t length, linelength; - - /* At this point, ptr is at the start of a line. We need to find the length - of the subject string to pass to pcre_exec(). In multiline mode, it is the - length remainder of the data in the buffer. Otherwise, it is the length of - the next line, excluding the terminating newline. After matching, we always - advance by the length of the next line. In multiline mode the PCRE_FIRSTLINE - option is used for compiling, so that any match is constrained to be in the - first line. */ - - t = end_of_line(t, endptr, &endlinelength); - linelength = t - ptr - endlinelength; - length = multiline? (size_t)(endptr - ptr) : linelength; - - /* Extra processing for Jeffrey Friedl's debugging. */ - -#ifdef JFRIEDL_DEBUG - if (jfriedl_XT || jfriedl_XR) - { - #include - #include - struct timeval start_time, end_time; - struct timezone dummy; - int i; - - if (jfriedl_XT) - { - unsigned long newlen = length * jfriedl_XT + strlen(jfriedl_prefix) + strlen(jfriedl_postfix); - const char *orig = ptr; - ptr = malloc(newlen + 1); - if (!ptr) { - printf("out of memory"); - exit(2); - } - endptr = ptr; - strcpy(endptr, jfriedl_prefix); endptr += strlen(jfriedl_prefix); - for (i = 0; i < jfriedl_XT; i++) { - strncpy(endptr, orig, length); - endptr += length; - } - strcpy(endptr, jfriedl_postfix); endptr += strlen(jfriedl_postfix); - length = newlen; - } - - if (gettimeofday(&start_time, &dummy) != 0) - perror("bad gettimeofday"); - - - for (i = 0; i < jfriedl_XR; i++) - match = (pcre_exec(pattern_list[0], hints_list[0], ptr, length, 0, - PCRE_NOTEMPTY, offsets, OFFSET_SIZE) >= 0); - - if (gettimeofday(&end_time, &dummy) != 0) - perror("bad gettimeofday"); - - double delta = ((end_time.tv_sec + (end_time.tv_usec / 1000000.0)) - - - (start_time.tv_sec + (start_time.tv_usec / 1000000.0))); - - printf("%s TIMER[%.4f]\n", match ? "MATCH" : "FAIL", delta); - return 0; - } -#endif - - /* We come back here after a match when the -o option (only_matching) is set, - in order to find any further matches in the same line. */ - - ONLY_MATCHING_RESTART: - - /* Run through all the patterns until one matches or there is an error other - than NOMATCH. This code is in a subroutine so that it can be re-used for - finding subsequent matches when colouring matched lines. */ - - match = match_patterns(matchptr, length, offsets, &mrc); - - /* If it's a match or a not-match (as required), do what's wanted. */ - - if (match != invert) - { - BOOL hyphenprinted = FALSE; - - /* We've failed if we want a file that doesn't have any matches. */ - - if (filenames == FN_NOMATCH_ONLY) return 1; - - /* Just count if just counting is wanted. */ - - if (count_only) count++; - - /* If all we want is a file name, there is no need to scan any more lines - in the file. */ - - else if (filenames == FN_ONLY) - { - fprintf(stdout, "%s\n", printname); - return 0; - } - - /* Likewise, if all we want is a yes/no answer. */ - - else if (quiet) return 0; - - /* The --only-matching option prints just the substring that matched, and - the --file-offsets and --line-offsets options output offsets for the - matching substring (they both force --only-matching). None of these options - prints any context. Afterwards, adjust the start and length, and then jump - back to look for further matches in the same line. If we are in invert - mode, however, nothing is printed - this could be still useful because the - return code is set. */ - - else if (only_matching) - { - if (!invert) - { - if (printname != NULL) fprintf(stdout, "%s:", printname); - if (number) fprintf(stdout, "%d:", linenumber); - if (line_offsets) - fprintf(stdout, "%d,%d", (int)(matchptr + offsets[0] - ptr), - offsets[1] - offsets[0]); - else if (file_offsets) - fprintf(stdout, "%d,%d", (int)(filepos + matchptr + offsets[0] - ptr), - offsets[1] - offsets[0]); - else - { - if (do_colour) fprintf(stdout, "%c[%sm", 0x1b, colour_string); - fwrite(matchptr + offsets[0], 1, offsets[1] - offsets[0], stdout); - if (do_colour) fprintf(stdout, "%c[00m", 0x1b); - } - fprintf(stdout, "\n"); - matchptr += offsets[1]; - length -= offsets[1]; - match = FALSE; - goto ONLY_MATCHING_RESTART; - } - } - - /* This is the default case when none of the above options is set. We print - the matching lines(s), possibly preceded and/or followed by other lines of - context. */ - - else - { - /* See if there is a requirement to print some "after" lines from a - previous match. We never print any overlaps. */ - - if (after_context > 0 && lastmatchnumber > 0) - { - int ellength; - int linecount = 0; - char *p = lastmatchrestart; - - while (p < ptr && linecount < after_context) - { - p = end_of_line(p, ptr, &ellength); - linecount++; - } - - /* It is important to advance lastmatchrestart during this printing so - that it interacts correctly with any "before" printing below. Print - each line's data using fwrite() in case there are binary zeroes. */ - - while (lastmatchrestart < p) - { - char *pp = lastmatchrestart; - if (printname != NULL) fprintf(stdout, "%s-", printname); - if (number) fprintf(stdout, "%d-", lastmatchnumber++); - pp = end_of_line(pp, endptr, &ellength); - fwrite(lastmatchrestart, 1, pp - lastmatchrestart, stdout); - lastmatchrestart = pp; - } - if (lastmatchrestart != ptr) hyphenpending = TRUE; - } - - /* If there were non-contiguous lines printed above, insert hyphens. */ - - if (hyphenpending) - { - fprintf(stdout, "--\n"); - hyphenpending = FALSE; - hyphenprinted = TRUE; - } - - /* See if there is a requirement to print some "before" lines for this - match. Again, don't print overlaps. */ - - if (before_context > 0) - { - int linecount = 0; - char *p = ptr; - - while (p > buffer && (lastmatchnumber == 0 || p > lastmatchrestart) && - linecount < before_context) - { - linecount++; - p = previous_line(p, buffer); - } - - if (lastmatchnumber > 0 && p > lastmatchrestart && !hyphenprinted) - fprintf(stdout, "--\n"); - - while (p < ptr) - { - int ellength; - char *pp = p; - if (printname != NULL) fprintf(stdout, "%s-", printname); - if (number) fprintf(stdout, "%d-", linenumber - linecount--); - pp = end_of_line(pp, endptr, &ellength); - fwrite(p, 1, pp - p, stdout); - p = pp; - } - } - - /* Now print the matching line(s); ensure we set hyphenpending at the end - of the file if any context lines are being output. */ - - if (after_context > 0 || before_context > 0) - endhyphenpending = TRUE; - - if (printname != NULL) fprintf(stdout, "%s:", printname); - if (number) fprintf(stdout, "%d:", linenumber); - - /* In multiline mode, we want to print to the end of the line in which - the end of the matched string is found, so we adjust linelength and the - line number appropriately, but only when there actually was a match - (invert not set). Because the PCRE_FIRSTLINE option is set, the start of - the match will always be before the first newline sequence. */ - - if (multiline) - { - int ellength; - char *endmatch = ptr; - if (!invert) - { - endmatch += offsets[1]; - t = ptr; - while (t < endmatch) - { - t = end_of_line(t, endptr, &ellength); - if (t <= endmatch) linenumber++; else break; - } - } - endmatch = end_of_line(endmatch, endptr, &ellength); - linelength = endmatch - ptr - ellength; - } - - /*** NOTE: Use only fwrite() to output the data line, so that binary - zeroes are treated as just another data character. */ - - /* This extra option, for Jeffrey Friedl's debugging requirements, - replaces the matched string, or a specific captured string if it exists, - with X. When this happens, colouring is ignored. */ - -#ifdef JFRIEDL_DEBUG - if (S_arg >= 0 && S_arg < mrc) - { - int first = S_arg * 2; - int last = first + 1; - fwrite(ptr, 1, offsets[first], stdout); - fprintf(stdout, "X"); - fwrite(ptr + offsets[last], 1, linelength - offsets[last], stdout); - } - else -#endif - - /* We have to split the line(s) up if colouring, and search for further - matches. */ - - if (do_colour) - { - int last_offset = 0; - fwrite(ptr, 1, offsets[0], stdout); - fprintf(stdout, "%c[%sm", 0x1b, colour_string); - fwrite(ptr + offsets[0], 1, offsets[1] - offsets[0], stdout); - fprintf(stdout, "%c[00m", 0x1b); - for (;;) - { - last_offset += offsets[1]; - matchptr += offsets[1]; - length -= offsets[1]; - if (!match_patterns(matchptr, length, offsets, &mrc)) break; - fwrite(matchptr, 1, offsets[0], stdout); - fprintf(stdout, "%c[%sm", 0x1b, colour_string); - fwrite(matchptr + offsets[0], 1, offsets[1] - offsets[0], stdout); - fprintf(stdout, "%c[00m", 0x1b); - } - fwrite(ptr + last_offset, 1, (linelength + endlinelength) - last_offset, - stdout); - } - - /* Not colouring; no need to search for further matches */ - - else fwrite(ptr, 1, linelength + endlinelength, stdout); - } - - /* End of doing what has to be done for a match */ - - rc = 0; /* Had some success */ - - /* Remember where the last match happened for after_context. We remember - where we are about to restart, and that line's number. */ - - lastmatchrestart = ptr + linelength + endlinelength; - lastmatchnumber = linenumber + 1; - } - - /* For a match in multiline inverted mode (which of course did not cause - anything to be printed), we have to move on to the end of the match before - proceeding. */ - - if (multiline && invert && match) - { - int ellength; - char *endmatch = ptr + offsets[1]; - t = ptr; - while (t < endmatch) - { - t = end_of_line(t, endptr, &ellength); - if (t <= endmatch) linenumber++; else break; - } - endmatch = end_of_line(endmatch, endptr, &ellength); - linelength = endmatch - ptr - ellength; - } - - /* Advance to after the newline and increment the line number. The file - offset to the current line is maintained in filepos. */ - - ptr += linelength + endlinelength; - filepos += linelength + endlinelength; - linenumber++; - - /* If we haven't yet reached the end of the file (the buffer is full), and - the current point is in the top 1/3 of the buffer, slide the buffer down by - 1/3 and refill it. Before we do this, if some unprinted "after" lines are - about to be lost, print them. */ - - if (bufflength >= sizeof(buffer) && ptr > buffer + 2*MBUFTHIRD) - { - if (after_context > 0 && - lastmatchnumber > 0 && - lastmatchrestart < buffer + MBUFTHIRD) - { - do_after_lines(lastmatchnumber, lastmatchrestart, endptr, printname); - lastmatchnumber = 0; - } - - /* Now do the shuffle */ - - memmove(buffer, buffer + MBUFTHIRD, 2*MBUFTHIRD); - ptr -= MBUFTHIRD; - -#ifdef SUPPORT_LIBZ - if (frtype == FR_LIBZ) - bufflength = 2*MBUFTHIRD + - gzread (ingz, buffer + 2*MBUFTHIRD, MBUFTHIRD); - else -#endif - -#ifdef SUPPORT_LIBBZ2 - if (frtype == FR_LIBBZ2) - bufflength = 2*MBUFTHIRD + - BZ2_bzread(inbz2, buffer + 2*MBUFTHIRD, MBUFTHIRD); - else -#endif - - bufflength = 2*MBUFTHIRD + fread(buffer + 2*MBUFTHIRD, 1, MBUFTHIRD, in); - - endptr = buffer + bufflength; - - /* Adjust any last match point */ - - if (lastmatchnumber > 0) lastmatchrestart -= MBUFTHIRD; - } - } /* Loop through the whole file */ - -/* End of file; print final "after" lines if wanted; do_after_lines sets -hyphenpending if it prints something. */ - -if (!only_matching && !count_only) - { - do_after_lines(lastmatchnumber, lastmatchrestart, endptr, printname); - hyphenpending |= endhyphenpending; - } - -/* Print the file name if we are looking for those without matches and there -were none. If we found a match, we won't have got this far. */ - -if (filenames == FN_NOMATCH_ONLY) - { - fprintf(stdout, "%s\n", printname); - return 0; - } - -/* Print the match count if wanted */ - -if (count_only) - { - if (printname != NULL) fprintf(stdout, "%s:", printname); - fprintf(stdout, "%d\n", count); - } - -return rc; -} - - - -/************************************************* -* Grep a file or recurse into a directory * -*************************************************/ - -/* Given a path name, if it's a directory, scan all the files if we are -recursing; if it's a file, grep it. - -Arguments: - pathname the path to investigate - dir_recurse TRUE if recursing is wanted (-r or -drecurse) - only_one_at_top TRUE if the path is the only one at toplevel - -Returns: 0 if there was at least one match - 1 if there were no matches - 2 there was some kind of error - -However, file opening failures are suppressed if "silent" is set. -*/ - -static int -grep_or_recurse(char *pathname, BOOL dir_recurse, BOOL only_one_at_top) -{ -int rc = 1; -int sep; -int frtype; -int pathlen; -void *handle; -FILE *in = NULL; /* Ensure initialized */ - -#ifdef SUPPORT_LIBZ -gzFile ingz = NULL; -#endif - -#ifdef SUPPORT_LIBBZ2 -BZFILE *inbz2 = NULL; -#endif - -/* If the file name is "-" we scan stdin */ - -if (strcmp(pathname, "-") == 0) - { - return pcregrep(stdin, FR_PLAIN, - (filenames > FN_DEFAULT || (filenames == FN_DEFAULT && !only_one_at_top))? - stdin_name : NULL); - } - -/* If the file is a directory, skip if skipping or if we are recursing, scan -each file and directory within it, subject to any include or exclude patterns -that were set. The scanning code is localized so it can be made -system-specific. */ - -if ((sep = isdirectory(pathname)) != 0) - { - if (dee_action == dee_SKIP) return 1; - if (dee_action == dee_RECURSE) - { - char buffer[1024]; - char *nextfile; - directory_type *dir = opendirectory(pathname); - - if (dir == NULL) - { - if (!silent) - fprintf(stderr, "pcregrep: Failed to open directory %s: %s\n", pathname, - strerror(errno)); - return 2; - } - - while ((nextfile = readdirectory(dir)) != NULL) - { - int frc, nflen; - sprintf(buffer, "%.512s%c%.128s", pathname, sep, nextfile); - nflen = strlen(nextfile); - - if (isdirectory(buffer)) - { - if (exclude_dir_compiled != NULL && - pcre_exec(exclude_dir_compiled, NULL, nextfile, nflen, 0, 0, NULL, 0) >= 0) - continue; - - if (include_dir_compiled != NULL && - pcre_exec(include_dir_compiled, NULL, nextfile, nflen, 0, 0, NULL, 0) < 0) - continue; - } - else - { - if (exclude_compiled != NULL && - pcre_exec(exclude_compiled, NULL, nextfile, nflen, 0, 0, NULL, 0) >= 0) - continue; - - if (include_compiled != NULL && - pcre_exec(include_compiled, NULL, nextfile, nflen, 0, 0, NULL, 0) < 0) - continue; - } - - frc = grep_or_recurse(buffer, dir_recurse, FALSE); - if (frc > 1) rc = frc; - else if (frc == 0 && rc == 1) rc = 0; - } - - closedirectory(dir); - return rc; - } - } - -/* If the file is not a directory and not a regular file, skip it if that's -been requested. */ - -else if (!isregfile(pathname) && DEE_action == DEE_SKIP) return 1; - -/* Control reaches here if we have a regular file, or if we have a directory -and recursion or skipping was not requested, or if we have anything else and -skipping was not requested. The scan proceeds. If this is the first and only -argument at top level, we don't show the file name, unless we are only showing -the file name, or the filename was forced (-H). */ - -pathlen = strlen(pathname); - -/* Open using zlib if it is supported and the file name ends with .gz. */ - -#ifdef SUPPORT_LIBZ -if (pathlen > 3 && strcmp(pathname + pathlen - 3, ".gz") == 0) - { - ingz = gzopen(pathname, "rb"); - if (ingz == NULL) - { - if (!silent) - fprintf(stderr, "pcregrep: Failed to open %s: %s\n", pathname, - strerror(errno)); - return 2; - } - handle = (void *)ingz; - frtype = FR_LIBZ; - } -else -#endif - -/* Otherwise open with bz2lib if it is supported and the name ends with .bz2. */ - -#ifdef SUPPORT_LIBBZ2 -if (pathlen > 4 && strcmp(pathname + pathlen - 4, ".bz2") == 0) - { - inbz2 = BZ2_bzopen(pathname, "rb"); - handle = (void *)inbz2; - frtype = FR_LIBBZ2; - } -else -#endif - -/* Otherwise use plain fopen(). The label is so that we can come back here if -an attempt to read a .bz2 file indicates that it really is a plain file. */ - -#ifdef SUPPORT_LIBBZ2 -PLAIN_FILE: -#endif - { - in = fopen(pathname, "r"); - handle = (void *)in; - frtype = FR_PLAIN; - } - -/* All the opening methods return errno when they fail. */ - -if (handle == NULL) - { - if (!silent) - fprintf(stderr, "pcregrep: Failed to open %s: %s\n", pathname, - strerror(errno)); - return 2; - } - -/* Now grep the file */ - -rc = pcregrep(handle, frtype, (filenames > FN_DEFAULT || - (filenames == FN_DEFAULT && !only_one_at_top))? pathname : NULL); - -/* Close in an appropriate manner. */ - -#ifdef SUPPORT_LIBZ -if (frtype == FR_LIBZ) - gzclose(ingz); -else -#endif - -/* If it is a .bz2 file and the result is 2, it means that the first attempt to -read failed. If the error indicates that the file isn't in fact bzipped, try -again as a normal file. */ - -#ifdef SUPPORT_LIBBZ2 -if (frtype == FR_LIBBZ2) - { - if (rc == 2) - { - int errnum; - const char *err = BZ2_bzerror(inbz2, &errnum); - if (errnum == BZ_DATA_ERROR_MAGIC) - { - BZ2_bzclose(inbz2); - goto PLAIN_FILE; - } - else if (!silent) - fprintf(stderr, "pcregrep: Failed to read %s using bzlib: %s\n", - pathname, err); - } - BZ2_bzclose(inbz2); - } -else -#endif - -/* Normal file close */ - -fclose(in); - -/* Pass back the yield from pcregrep(). */ - -return rc; -} - - - - -/************************************************* -* Usage function * -*************************************************/ - -static int -usage(int rc) -{ -option_item *op; -fprintf(stderr, "Usage: pcregrep [-"); -for (op = optionlist; op->one_char != 0; op++) - { - if (op->one_char > 0) fprintf(stderr, "%c", op->one_char); - } -fprintf(stderr, "] [long options] [pattern] [files]\n"); -fprintf(stderr, "Type `pcregrep --help' for more information and the long " - "options.\n"); -return rc; -} - - - - -/************************************************* -* Help function * -*************************************************/ - -static void -help(void) -{ -option_item *op; - -printf("Usage: pcregrep [OPTION]... [PATTERN] [FILE1 FILE2 ...]\n"); -printf("Search for PATTERN in each FILE or standard input.\n"); -printf("PATTERN must be present if neither -e nor -f is used.\n"); -printf("\"-\" can be used as a file name to mean STDIN.\n"); - -#ifdef SUPPORT_LIBZ -printf("Files whose names end in .gz are read using zlib.\n"); -#endif - -#ifdef SUPPORT_LIBBZ2 -printf("Files whose names end in .bz2 are read using bzlib2.\n"); -#endif - -#if defined SUPPORT_LIBZ || defined SUPPORT_LIBBZ2 -printf("Other files and the standard input are read as plain files.\n\n"); -#else -printf("All files are read as plain files, without any interpretation.\n\n"); -#endif - -printf("Example: pcregrep -i 'hello.*world' menu.h main.c\n\n"); -printf("Options:\n"); - -for (op = optionlist; op->one_char != 0; op++) - { - int n; - char s[4]; - if (op->one_char > 0) sprintf(s, "-%c,", op->one_char); else strcpy(s, " "); - n = 30 - printf(" %s --%s", s, op->long_name); - if (n < 1) n = 1; - printf("%.*s%s\n", n, " ", op->help_text); - } - -printf("\nWhen reading patterns from a file instead of using a command line option,\n"); -printf("trailing white space is removed and blank lines are ignored.\n"); -printf("There is a maximum of %d patterns.\n", MAX_PATTERN_COUNT); - -printf("\nWith no FILEs, read standard input. If fewer than two FILEs given, assume -h.\n"); -printf("Exit status is 0 if any matches, 1 if no matches, and 2 if trouble.\n"); -} - - - - -/************************************************* -* Handle a single-letter, no data option * -*************************************************/ - -static int -handle_option(int letter, int options) -{ -switch(letter) - { - case N_FOFFSETS: file_offsets = TRUE; break; - case N_HELP: help(); exit(0); - case N_LOFFSETS: line_offsets = number = TRUE; break; - case 'c': count_only = TRUE; break; - case 'F': process_options |= PO_FIXED_STRINGS; break; - case 'H': filenames = FN_FORCE; break; - case 'h': filenames = FN_NONE; break; - case 'i': options |= PCRE_CASELESS; break; - case 'l': filenames = FN_ONLY; break; - case 'L': filenames = FN_NOMATCH_ONLY; break; - case 'M': multiline = TRUE; options |= PCRE_MULTILINE|PCRE_FIRSTLINE; break; - case 'n': number = TRUE; break; - case 'o': only_matching = TRUE; break; - case 'q': quiet = TRUE; break; - case 'r': dee_action = dee_RECURSE; break; - case 's': silent = TRUE; break; - case 'u': options |= PCRE_UTF8; utf8 = TRUE; break; - case 'v': invert = TRUE; break; - case 'w': process_options |= PO_WORD_MATCH; break; - case 'x': process_options |= PO_LINE_MATCH; break; - - case 'V': - fprintf(stderr, "pcregrep version %s\n", pcre_version()); - exit(0); - break; - - default: - fprintf(stderr, "pcregrep: Unknown option -%c\n", letter); - exit(usage(2)); - } - -return options; -} - - - - -/************************************************* -* Construct printed ordinal * -*************************************************/ - -/* This turns a number into "1st", "3rd", etc. */ - -static char * -ordin(int n) -{ -static char buffer[8]; -char *p = buffer; -sprintf(p, "%d", n); -while (*p != 0) p++; -switch (n%10) - { - case 1: strcpy(p, "st"); break; - case 2: strcpy(p, "nd"); break; - case 3: strcpy(p, "rd"); break; - default: strcpy(p, "th"); break; - } -return buffer; -} - - - -/************************************************* -* Compile a single pattern * -*************************************************/ - -/* When the -F option has been used, this is called for each substring. -Otherwise it's called for each supplied pattern. - -Arguments: - pattern the pattern string - options the PCRE options - filename the file name, or NULL for a command-line pattern - count 0 if this is the only command line pattern, or - number of the command line pattern, or - linenumber for a pattern from a file - -Returns: TRUE on success, FALSE after an error -*/ - -static BOOL -compile_single_pattern(char *pattern, int options, char *filename, int count) -{ -char buffer[MBUFTHIRD + 16]; -const char *error; -int errptr; - -if (pattern_count >= MAX_PATTERN_COUNT) - { - fprintf(stderr, "pcregrep: Too many %spatterns (max %d)\n", - (filename == NULL)? "command-line " : "", MAX_PATTERN_COUNT); - return FALSE; - } - -sprintf(buffer, "%s%.*s%s", prefix[process_options], MBUFTHIRD, pattern, - suffix[process_options]); -pattern_list[pattern_count] = - pcre_compile(buffer, options, &error, &errptr, pcretables); -if (pattern_list[pattern_count] != NULL) - { - pattern_count++; - return TRUE; - } - -/* Handle compile errors */ - -errptr -= (int)strlen(prefix[process_options]); -if (errptr > (int)strlen(pattern)) errptr = (int)strlen(pattern); - -if (filename == NULL) - { - if (count == 0) - fprintf(stderr, "pcregrep: Error in command-line regex " - "at offset %d: %s\n", errptr, error); - else - fprintf(stderr, "pcregrep: Error in %s command-line regex " - "at offset %d: %s\n", ordin(count), errptr, error); - } -else - { - fprintf(stderr, "pcregrep: Error in regex in line %d of %s " - "at offset %d: %s\n", count, filename, errptr, error); - } - -return FALSE; -} - - - -/************************************************* -* Compile one supplied pattern * -*************************************************/ - -/* When the -F option has been used, each string may be a list of strings, -separated by line breaks. They will be matched literally. - -Arguments: - pattern the pattern string - options the PCRE options - filename the file name, or NULL for a command-line pattern - count 0 if this is the only command line pattern, or - number of the command line pattern, or - linenumber for a pattern from a file - -Returns: TRUE on success, FALSE after an error -*/ - -static BOOL -compile_pattern(char *pattern, int options, char *filename, int count) -{ -if ((process_options & PO_FIXED_STRINGS) != 0) - { - char *eop = pattern + strlen(pattern); - char buffer[MBUFTHIRD]; - for(;;) - { - int ellength; - char *p = end_of_line(pattern, eop, &ellength); - if (ellength == 0) - return compile_single_pattern(pattern, options, filename, count); - sprintf(buffer, "%.*s", (int)(p - pattern - ellength), pattern); - pattern = p; - if (!compile_single_pattern(buffer, options, filename, count)) - return FALSE; - } - } -else return compile_single_pattern(pattern, options, filename, count); -} - - - -/************************************************* -* Main program * -*************************************************/ - -/* Returns 0 if something matched, 1 if nothing matched, 2 after an error. */ - -int -main(int argc, char **argv) -{ -int i, j; -int rc = 1; -int pcre_options = 0; -int cmd_pattern_count = 0; -int hint_count = 0; -int errptr; -BOOL only_one_at_top; -char *patterns[MAX_PATTERN_COUNT]; -const char *locale_from = "--locale"; -const char *error; - -/* Set the default line ending value from the default in the PCRE library; -"lf", "cr", "crlf", and "any" are supported. Anything else is treated as "lf". -Note that the return values from pcre_config(), though derived from the ASCII -codes, are the same in EBCDIC environments, so we must use the actual values -rather than escapes such as as '\r'. */ - -(void)pcre_config(PCRE_CONFIG_NEWLINE, &i); -switch(i) - { - default: newline = (char *)"lf"; break; - case 13: newline = (char *)"cr"; break; - case (13 << 8) | 10: newline = (char *)"crlf"; break; - case -1: newline = (char *)"any"; break; - case -2: newline = (char *)"anycrlf"; break; - } - -/* Process the options */ - -for (i = 1; i < argc; i++) - { - option_item *op = NULL; - char *option_data = (char *)""; /* default to keep compiler happy */ - BOOL longop; - BOOL longopwasequals = FALSE; - - if (argv[i][0] != '-') break; - - /* If we hit an argument that is just "-", it may be a reference to STDIN, - but only if we have previously had -e or -f to define the patterns. */ - - if (argv[i][1] == 0) - { - if (pattern_filename != NULL || pattern_count > 0) break; - else exit(usage(2)); - } - - /* Handle a long name option, or -- to terminate the options */ - - if (argv[i][1] == '-') - { - char *arg = argv[i] + 2; - char *argequals = strchr(arg, '='); - - if (*arg == 0) /* -- terminates options */ - { - i++; - break; /* out of the options-handling loop */ - } - - longop = TRUE; - - /* Some long options have data that follows after =, for example file=name. - Some options have variations in the long name spelling: specifically, we - allow "regexp" because GNU grep allows it, though I personally go along - with Jeffrey Friedl and Larry Wall in preferring "regex" without the "p". - These options are entered in the table as "regex(p)". No option is in both - these categories, fortunately. */ - - for (op = optionlist; op->one_char != 0; op++) - { - char *opbra = strchr(op->long_name, '('); - char *equals = strchr(op->long_name, '='); - if (opbra == NULL) /* Not a (p) case */ - { - if (equals == NULL) /* Not thing=data case */ - { - if (strcmp(arg, op->long_name) == 0) break; - } - else /* Special case xxx=data */ - { - int oplen = equals - op->long_name; - int arglen = (argequals == NULL)? (int)strlen(arg) : argequals - arg; - if (oplen == arglen && strncmp(arg, op->long_name, oplen) == 0) - { - option_data = arg + arglen; - if (*option_data == '=') - { - option_data++; - longopwasequals = TRUE; - } - break; - } - } - } - else /* Special case xxxx(p) */ - { - char buff1[24]; - char buff2[24]; - int baselen = opbra - op->long_name; - sprintf(buff1, "%.*s", baselen, op->long_name); - sprintf(buff2, "%s%.*s", buff1, - (int)strlen(op->long_name) - baselen - 2, opbra + 1); - if (strcmp(arg, buff1) == 0 || strcmp(arg, buff2) == 0) - break; - } - } - - if (op->one_char == 0) - { - fprintf(stderr, "pcregrep: Unknown option %s\n", argv[i]); - exit(usage(2)); - } - } - - - /* Jeffrey Friedl's debugging harness uses these additional options which - are not in the right form for putting in the option table because they use - only one hyphen, yet are more than one character long. By putting them - separately here, they will not get displayed as part of the help() output, - but I don't think Jeffrey will care about that. */ - -#ifdef JFRIEDL_DEBUG - else if (strcmp(argv[i], "-pre") == 0) { - jfriedl_prefix = argv[++i]; - continue; - } else if (strcmp(argv[i], "-post") == 0) { - jfriedl_postfix = argv[++i]; - continue; - } else if (strcmp(argv[i], "-XT") == 0) { - sscanf(argv[++i], "%d", &jfriedl_XT); - continue; - } else if (strcmp(argv[i], "-XR") == 0) { - sscanf(argv[++i], "%d", &jfriedl_XR); - continue; - } -#endif - - - /* One-char options; many that have no data may be in a single argument; we - continue till we hit the last one or one that needs data. */ - - else - { - char *s = argv[i] + 1; - longop = FALSE; - while (*s != 0) - { - for (op = optionlist; op->one_char != 0; op++) - { if (*s == op->one_char) break; } - if (op->one_char == 0) - { - fprintf(stderr, "pcregrep: Unknown option letter '%c' in \"%s\"\n", - *s, argv[i]); - exit(usage(2)); - } - if (op->type != OP_NODATA || s[1] == 0) - { - option_data = s+1; - break; - } - pcre_options = handle_option(*s++, pcre_options); - } - } - - /* At this point we should have op pointing to a matched option. If the type - is NO_DATA, it means that there is no data, and the option might set - something in the PCRE options. */ - - if (op->type == OP_NODATA) - { - pcre_options = handle_option(op->one_char, pcre_options); - continue; - } - - /* If the option type is OP_OP_STRING or OP_OP_NUMBER, it's an option that - either has a value or defaults to something. It cannot have data in a - separate item. At the moment, the only such options are "colo(u)r" and - Jeffrey Friedl's special -S debugging option. */ - - if (*option_data == 0 && - (op->type == OP_OP_STRING || op->type == OP_OP_NUMBER)) - { - switch (op->one_char) - { - case N_COLOUR: - colour_option = (char *)"auto"; - break; -#ifdef JFRIEDL_DEBUG - case 'S': - S_arg = 0; - break; -#endif - } - continue; - } - - /* Otherwise, find the data string for the option. */ - - if (*option_data == 0) - { - if (i >= argc - 1 || longopwasequals) - { - fprintf(stderr, "pcregrep: Data missing after %s\n", argv[i]); - exit(usage(2)); - } - option_data = argv[++i]; - } - - /* If the option type is OP_PATLIST, it's the -e option, which can be called - multiple times to create a list of patterns. */ - - if (op->type == OP_PATLIST) - { - if (cmd_pattern_count >= MAX_PATTERN_COUNT) - { - fprintf(stderr, "pcregrep: Too many command-line patterns (max %d)\n", - MAX_PATTERN_COUNT); - return 2; - } - patterns[cmd_pattern_count++] = option_data; - } - - /* Otherwise, deal with single string or numeric data values. */ - - else if (op->type != OP_NUMBER && op->type != OP_OP_NUMBER) - { - *((char **)op->dataptr) = option_data; - } - else - { - char *endptr; - int n = strtoul(option_data, &endptr, 10); - if (*endptr != 0) - { - if (longop) - { - char *equals = strchr(op->long_name, '='); - int nlen = (equals == NULL)? (int)strlen(op->long_name) : - equals - op->long_name; - fprintf(stderr, "pcregrep: Malformed number \"%s\" after --%.*s\n", - option_data, nlen, op->long_name); - } - else - fprintf(stderr, "pcregrep: Malformed number \"%s\" after -%c\n", - option_data, op->one_char); - exit(usage(2)); - } - *((int *)op->dataptr) = n; - } - } - -/* Options have been decoded. If -C was used, its value is used as a default -for -A and -B. */ - -if (both_context > 0) - { - if (after_context == 0) after_context = both_context; - if (before_context == 0) before_context = both_context; - } - -/* Only one of --only-matching, --file-offsets, or --line-offsets is permitted. -However, the latter two set the only_matching flag. */ - -if ((only_matching && (file_offsets || line_offsets)) || - (file_offsets && line_offsets)) - { - fprintf(stderr, "pcregrep: Cannot mix --only-matching, --file-offsets " - "and/or --line-offsets\n"); - exit(usage(2)); - } - -if (file_offsets || line_offsets) only_matching = TRUE; - -/* If a locale has not been provided as an option, see if the LC_CTYPE or -LC_ALL environment variable is set, and if so, use it. */ - -if (locale == NULL) - { - locale = getenv("LC_ALL"); - locale_from = "LCC_ALL"; - } - -if (locale == NULL) - { - locale = getenv("LC_CTYPE"); - locale_from = "LC_CTYPE"; - } - -/* If a locale has been provided, set it, and generate the tables the PCRE -needs. Otherwise, pcretables==NULL, which causes the use of default tables. */ - -if (locale != NULL) - { - if (setlocale(LC_CTYPE, locale) == NULL) - { - fprintf(stderr, "pcregrep: Failed to set locale %s (obtained from %s)\n", - locale, locale_from); - return 2; - } - pcretables = pcre_maketables(); - } - -/* Sort out colouring */ - -if (colour_option != NULL && strcmp(colour_option, "never") != 0) - { - if (strcmp(colour_option, "always") == 0) do_colour = TRUE; - else if (strcmp(colour_option, "auto") == 0) do_colour = is_stdout_tty(); - else - { - fprintf(stderr, "pcregrep: Unknown colour setting \"%s\"\n", - colour_option); - return 2; - } - if (do_colour) - { - char *cs = getenv("PCREGREP_COLOUR"); - if (cs == NULL) cs = getenv("PCREGREP_COLOR"); - if (cs != NULL) colour_string = cs; - } - } - -/* Interpret the newline type; the default settings are Unix-like. */ - -if (strcmp(newline, "cr") == 0 || strcmp(newline, "CR") == 0) - { - pcre_options |= PCRE_NEWLINE_CR; - endlinetype = EL_CR; - } -else if (strcmp(newline, "lf") == 0 || strcmp(newline, "LF") == 0) - { - pcre_options |= PCRE_NEWLINE_LF; - endlinetype = EL_LF; - } -else if (strcmp(newline, "crlf") == 0 || strcmp(newline, "CRLF") == 0) - { - pcre_options |= PCRE_NEWLINE_CRLF; - endlinetype = EL_CRLF; - } -else if (strcmp(newline, "any") == 0 || strcmp(newline, "ANY") == 0) - { - pcre_options |= PCRE_NEWLINE_ANY; - endlinetype = EL_ANY; - } -else if (strcmp(newline, "anycrlf") == 0 || strcmp(newline, "ANYCRLF") == 0) - { - pcre_options |= PCRE_NEWLINE_ANYCRLF; - endlinetype = EL_ANYCRLF; - } -else - { - fprintf(stderr, "pcregrep: Invalid newline specifier \"%s\"\n", newline); - return 2; - } - -/* Interpret the text values for -d and -D */ - -if (dee_option != NULL) - { - if (strcmp(dee_option, "read") == 0) dee_action = dee_READ; - else if (strcmp(dee_option, "recurse") == 0) dee_action = dee_RECURSE; - else if (strcmp(dee_option, "skip") == 0) dee_action = dee_SKIP; - else - { - fprintf(stderr, "pcregrep: Invalid value \"%s\" for -d\n", dee_option); - return 2; - } - } - -if (DEE_option != NULL) - { - if (strcmp(DEE_option, "read") == 0) DEE_action = DEE_READ; - else if (strcmp(DEE_option, "skip") == 0) DEE_action = DEE_SKIP; - else - { - fprintf(stderr, "pcregrep: Invalid value \"%s\" for -D\n", DEE_option); - return 2; - } - } - -/* Check the values for Jeffrey Friedl's debugging options. */ - -#ifdef JFRIEDL_DEBUG -if (S_arg > 9) - { - fprintf(stderr, "pcregrep: bad value for -S option\n"); - return 2; - } -if (jfriedl_XT != 0 || jfriedl_XR != 0) - { - if (jfriedl_XT == 0) jfriedl_XT = 1; - if (jfriedl_XR == 0) jfriedl_XR = 1; - } -#endif - -/* Get memory to store the pattern and hints lists. */ - -pattern_list = (pcre **)malloc(MAX_PATTERN_COUNT * sizeof(pcre *)); -hints_list = (pcre_extra **)malloc(MAX_PATTERN_COUNT * sizeof(pcre_extra *)); - -if (pattern_list == NULL || hints_list == NULL) - { - fprintf(stderr, "pcregrep: malloc failed\n"); - goto EXIT2; - } - -/* If no patterns were provided by -e, and there is no file provided by -f, -the first argument is the one and only pattern, and it must exist. */ - -if (cmd_pattern_count == 0 && pattern_filename == NULL) - { - if (i >= argc) return usage(2); - patterns[cmd_pattern_count++] = argv[i++]; - } - -/* Compile the patterns that were provided on the command line, either by -multiple uses of -e or as a single unkeyed pattern. */ - -for (j = 0; j < cmd_pattern_count; j++) - { - if (!compile_pattern(patterns[j], pcre_options, NULL, - (j == 0 && cmd_pattern_count == 1)? 0 : j + 1)) - goto EXIT2; - } - -/* Compile the regular expressions that are provided in a file. */ - -if (pattern_filename != NULL) - { - int linenumber = 0; - FILE *f; - char *filename; - char buffer[MBUFTHIRD]; - - if (strcmp(pattern_filename, "-") == 0) - { - f = stdin; - filename = stdin_name; - } - else - { - f = fopen(pattern_filename, "r"); - if (f == NULL) - { - fprintf(stderr, "pcregrep: Failed to open %s: %s\n", pattern_filename, - strerror(errno)); - goto EXIT2; - } - filename = pattern_filename; - } - - while (fgets(buffer, MBUFTHIRD, f) != NULL) - { - char *s = buffer + (int)strlen(buffer); - while (s > buffer && isspace((unsigned char)(s[-1]))) s--; - *s = 0; - linenumber++; - if (buffer[0] == 0) continue; /* Skip blank lines */ - if (!compile_pattern(buffer, pcre_options, filename, linenumber)) - goto EXIT2; - } - - if (f != stdin) fclose(f); - } - -/* Study the regular expressions, as we will be running them many times */ - -for (j = 0; j < pattern_count; j++) - { - hints_list[j] = pcre_study(pattern_list[j], 0, &error); - if (error != NULL) - { - char s[16]; - if (pattern_count == 1) s[0] = 0; else sprintf(s, " number %d", j); - fprintf(stderr, "pcregrep: Error while studying regex%s: %s\n", s, error); - goto EXIT2; - } - hint_count++; - } - -/* If there are include or exclude patterns, compile them. */ - -if (exclude_pattern != NULL) - { - exclude_compiled = pcre_compile(exclude_pattern, 0, &error, &errptr, - pcretables); - if (exclude_compiled == NULL) - { - fprintf(stderr, "pcregrep: Error in 'exclude' regex at offset %d: %s\n", - errptr, error); - goto EXIT2; - } - } - -if (include_pattern != NULL) - { - include_compiled = pcre_compile(include_pattern, 0, &error, &errptr, - pcretables); - if (include_compiled == NULL) - { - fprintf(stderr, "pcregrep: Error in 'include' regex at offset %d: %s\n", - errptr, error); - goto EXIT2; - } - } - -if (exclude_dir_pattern != NULL) - { - exclude_dir_compiled = pcre_compile(exclude_dir_pattern, 0, &error, &errptr, - pcretables); - if (exclude_dir_compiled == NULL) - { - fprintf(stderr, "pcregrep: Error in 'exclude_dir' regex at offset %d: %s\n", - errptr, error); - goto EXIT2; - } - } - -if (include_dir_pattern != NULL) - { - include_dir_compiled = pcre_compile(include_dir_pattern, 0, &error, &errptr, - pcretables); - if (include_dir_compiled == NULL) - { - fprintf(stderr, "pcregrep: Error in 'include_dir' regex at offset %d: %s\n", - errptr, error); - goto EXIT2; - } - } - -/* If there are no further arguments, do the business on stdin and exit. */ - -if (i >= argc) - { - rc = pcregrep(stdin, FR_PLAIN, (filenames > FN_DEFAULT)? stdin_name : NULL); - goto EXIT; - } - -/* Otherwise, work through the remaining arguments as files or directories. -Pass in the fact that there is only one argument at top level - this suppresses -the file name if the argument is not a directory and filenames are not -otherwise forced. */ - -only_one_at_top = i == argc - 1; /* Catch initial value of i */ - -for (; i < argc; i++) - { - int frc = grep_or_recurse(argv[i], dee_action == dee_RECURSE, - only_one_at_top); - if (frc > 1) rc = frc; - else if (frc == 0 && rc == 1) rc = 0; - } - -EXIT: -if (pattern_list != NULL) - { - for (i = 0; i < pattern_count; i++) free(pattern_list[i]); - free(pattern_list); - } -if (hints_list != NULL) - { - for (i = 0; i < hint_count; i++) free(hints_list[i]); - free(hints_list); - } -return rc; - -EXIT2: -rc = 2; -goto EXIT; -} - -/* End of pcregrep */ diff --git a/libs/pcre/pcreposix.c b/libs/pcre/pcreposix.c deleted file mode 100644 index fd63a6f5e3..0000000000 --- a/libs/pcre/pcreposix.c +++ /dev/null @@ -1,357 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2009 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module is a wrapper that provides a POSIX API to the underlying PCRE -functions. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - - -/* Ensure that the PCREPOSIX_EXP_xxx macros are set appropriately for -compiling these functions. This must come before including pcreposix.h, where -they are set for an application (using these functions) if they have not -previously been set. */ - -#if defined(_WIN32) && !defined(PCRE_STATIC) -# define PCREPOSIX_EXP_DECL extern __declspec(dllexport) -# define PCREPOSIX_EXP_DEFN __declspec(dllexport) -#endif - -#include "pcre.h" -#include "pcre_internal.h" -#include "pcreposix.h" - - -/* Table to translate PCRE compile time error codes into POSIX error codes. */ - -static const int eint[] = { - 0, /* no error */ - REG_EESCAPE, /* \ at end of pattern */ - REG_EESCAPE, /* \c at end of pattern */ - REG_EESCAPE, /* unrecognized character follows \ */ - REG_BADBR, /* numbers out of order in {} quantifier */ - REG_BADBR, /* number too big in {} quantifier */ - REG_EBRACK, /* missing terminating ] for character class */ - REG_ECTYPE, /* invalid escape sequence in character class */ - REG_ERANGE, /* range out of order in character class */ - REG_BADRPT, /* nothing to repeat */ - REG_BADRPT, /* operand of unlimited repeat could match the empty string */ - REG_ASSERT, /* internal error: unexpected repeat */ - REG_BADPAT, /* unrecognized character after (? */ - REG_BADPAT, /* POSIX named classes are supported only within a class */ - REG_EPAREN, /* missing ) */ - REG_ESUBREG, /* reference to non-existent subpattern */ - REG_INVARG, /* erroffset passed as NULL */ - REG_INVARG, /* unknown option bit(s) set */ - REG_EPAREN, /* missing ) after comment */ - REG_ESIZE, /* parentheses nested too deeply */ - REG_ESIZE, /* regular expression too large */ - REG_ESPACE, /* failed to get memory */ - REG_EPAREN, /* unmatched brackets */ - REG_ASSERT, /* internal error: code overflow */ - REG_BADPAT, /* unrecognized character after (?< */ - REG_BADPAT, /* lookbehind assertion is not fixed length */ - REG_BADPAT, /* malformed number or name after (?( */ - REG_BADPAT, /* conditional group contains more than two branches */ - REG_BADPAT, /* assertion expected after (?( */ - REG_BADPAT, /* (?R or (?[+-]digits must be followed by ) */ - REG_ECTYPE, /* unknown POSIX class name */ - REG_BADPAT, /* POSIX collating elements are not supported */ - REG_INVARG, /* this version of PCRE is not compiled with PCRE_UTF8 support */ - REG_BADPAT, /* spare error */ - REG_BADPAT, /* character value in \x{...} sequence is too large */ - REG_BADPAT, /* invalid condition (?(0) */ - REG_BADPAT, /* \C not allowed in lookbehind assertion */ - REG_EESCAPE, /* PCRE does not support \L, \l, \N, \U, or \u */ - REG_BADPAT, /* number after (?C is > 255 */ - REG_BADPAT, /* closing ) for (?C expected */ - REG_BADPAT, /* recursive call could loop indefinitely */ - REG_BADPAT, /* unrecognized character after (?P */ - REG_BADPAT, /* syntax error in subpattern name (missing terminator) */ - REG_BADPAT, /* two named subpatterns have the same name */ - REG_BADPAT, /* invalid UTF-8 string */ - REG_BADPAT, /* support for \P, \p, and \X has not been compiled */ - REG_BADPAT, /* malformed \P or \p sequence */ - REG_BADPAT, /* unknown property name after \P or \p */ - REG_BADPAT, /* subpattern name is too long (maximum 32 characters) */ - REG_BADPAT, /* too many named subpatterns (maximum 10,000) */ - REG_BADPAT, /* repeated subpattern is too long */ - REG_BADPAT, /* octal value is greater than \377 (not in UTF-8 mode) */ - REG_BADPAT, /* internal error: overran compiling workspace */ - REG_BADPAT, /* internal error: previously-checked referenced subpattern not found */ - REG_BADPAT, /* DEFINE group contains more than one branch */ - REG_BADPAT, /* repeating a DEFINE group is not allowed */ - REG_INVARG, /* inconsistent NEWLINE options */ - REG_BADPAT, /* \g is not followed followed by an (optionally braced) non-zero number */ - REG_BADPAT, /* (?+ or (?- must be followed by a non-zero number */ - REG_BADPAT, /* number is too big */ - REG_BADPAT, /* subpattern name expected */ - REG_BADPAT, /* digit expected after (?+ */ - REG_BADPAT /* ] is an invalid data character in JavaScript compatibility mode */ -}; - -/* Table of texts corresponding to POSIX error codes */ - -static const char *const pstring[] = { - "", /* Dummy for value 0 */ - "internal error", /* REG_ASSERT */ - "invalid repeat counts in {}", /* BADBR */ - "pattern error", /* BADPAT */ - "? * + invalid", /* BADRPT */ - "unbalanced {}", /* EBRACE */ - "unbalanced []", /* EBRACK */ - "collation error - not relevant", /* ECOLLATE */ - "bad class", /* ECTYPE */ - "bad escape sequence", /* EESCAPE */ - "empty expression", /* EMPTY */ - "unbalanced ()", /* EPAREN */ - "bad range inside []", /* ERANGE */ - "expression too big", /* ESIZE */ - "failed to get memory", /* ESPACE */ - "bad back reference", /* ESUBREG */ - "bad argument", /* INVARG */ - "match failed" /* NOMATCH */ -}; - - - - -/************************************************* -* Translate error code to string * -*************************************************/ - -PCREPOSIX_EXP_DEFN size_t PCRE_CALL_CONVENTION -regerror(int errcode, const regex_t *preg, char *errbuf, size_t errbuf_size) -{ -const char *message, *addmessage; -size_t length, addlength; - -message = (errcode >= (int)(sizeof(pstring)/sizeof(char *)))? - "unknown error code" : pstring[errcode]; -length = strlen(message) + 1; - -addmessage = " at offset "; -addlength = (preg != NULL && (int)preg->re_erroffset != -1)? - strlen(addmessage) + 6 : 0; - -if (errbuf_size > 0) - { - if (addlength > 0 && errbuf_size >= length + addlength) - sprintf(errbuf, "%s%s%-6d", message, addmessage, (int)preg->re_erroffset); - else - { - strncpy(errbuf, message, errbuf_size - 1); - errbuf[errbuf_size-1] = 0; - } - } - -return length + addlength; -} - - - - -/************************************************* -* Free store held by a regex * -*************************************************/ - -PCREPOSIX_EXP_DEFN void PCRE_CALL_CONVENTION -regfree(regex_t *preg) -{ -(pcre_free)(preg->re_pcre); -} - - - - -/************************************************* -* Compile a regular expression * -*************************************************/ - -/* -Arguments: - preg points to a structure for recording the compiled expression - pattern the pattern to compile - cflags compilation flags - -Returns: 0 on success - various non-zero codes on failure -*/ - -PCREPOSIX_EXP_DEFN int PCRE_CALL_CONVENTION -regcomp(regex_t *preg, const char *pattern, int cflags) -{ -const char *errorptr; -int erroffset; -int errorcode; -int options = 0; - -if ((cflags & REG_ICASE) != 0) options |= PCRE_CASELESS; -if ((cflags & REG_NEWLINE) != 0) options |= PCRE_MULTILINE; -if ((cflags & REG_DOTALL) != 0) options |= PCRE_DOTALL; -if ((cflags & REG_NOSUB) != 0) options |= PCRE_NO_AUTO_CAPTURE; -if ((cflags & REG_UTF8) != 0) options |= PCRE_UTF8; - -preg->re_pcre = pcre_compile2(pattern, options, &errorcode, &errorptr, - &erroffset, NULL); -preg->re_erroffset = erroffset; - -if (preg->re_pcre == NULL) return eint[errorcode]; - -preg->re_nsub = pcre_info((const pcre *)preg->re_pcre, NULL, NULL); -return 0; -} - - - - -/************************************************* -* Match a regular expression * -*************************************************/ - -/* Unfortunately, PCRE requires 3 ints of working space for each captured -substring, so we have to get and release working store instead of just using -the POSIX structures as was done in earlier releases when PCRE needed only 2 -ints. However, if the number of possible capturing brackets is small, use a -block of store on the stack, to reduce the use of malloc/free. The threshold is -in a macro that can be changed at configure time. - -If REG_NOSUB was specified at compile time, the PCRE_NO_AUTO_CAPTURE flag will -be set. When this is the case, the nmatch and pmatch arguments are ignored, and -the only result is yes/no/error. */ - -PCREPOSIX_EXP_DEFN int PCRE_CALL_CONVENTION -regexec(const regex_t *preg, const char *string, size_t nmatch, - regmatch_t pmatch[], int eflags) -{ -int rc, so, eo; -int options = 0; -int *ovector = NULL; -int small_ovector[POSIX_MALLOC_THRESHOLD * 3]; -BOOL allocated_ovector = FALSE; -BOOL nosub = - (((const pcre *)preg->re_pcre)->options & PCRE_NO_AUTO_CAPTURE) != 0; - -if ((eflags & REG_NOTBOL) != 0) options |= PCRE_NOTBOL; -if ((eflags & REG_NOTEOL) != 0) options |= PCRE_NOTEOL; -if ((eflags & REG_NOTEMPTY) != 0) options |= PCRE_NOTEMPTY; - -((regex_t *)preg)->re_erroffset = (size_t)(-1); /* Only has meaning after compile */ - -/* When no string data is being returned, ensure that nmatch is zero. -Otherwise, ensure the vector for holding the return data is large enough. */ - -if (nosub) nmatch = 0; - -else if (nmatch > 0) - { - if (nmatch <= POSIX_MALLOC_THRESHOLD) - { - ovector = &(small_ovector[0]); - } - else - { - if (nmatch > INT_MAX/(sizeof(int) * 3)) return REG_ESPACE; - ovector = (int *)malloc(sizeof(int) * nmatch * 3); - if (ovector == NULL) return REG_ESPACE; - allocated_ovector = TRUE; - } - } - -/* REG_STARTEND is a BSD extension, to allow for non-NUL-terminated strings. -The man page from OS X says "REG_STARTEND affects only the location of the -string, not how it is matched". That is why the "so" value is used to bump the -start location rather than being passed as a PCRE "starting offset". */ - -if ((eflags & REG_STARTEND) != 0) - { - so = pmatch[0].rm_so; - eo = pmatch[0].rm_eo; - } -else - { - so = 0; - eo = strlen(string); - } - -rc = pcre_exec((const pcre *)preg->re_pcre, NULL, string + so, (eo - so), - 0, options, ovector, nmatch * 3); - -if (rc == 0) rc = nmatch; /* All captured slots were filled in */ - -if (rc >= 0) - { - size_t i; - if (!nosub) - { - for (i = 0; i < (size_t)rc; i++) - { - pmatch[i].rm_so = ovector[i*2]; - pmatch[i].rm_eo = ovector[i*2+1]; - } - if (allocated_ovector) free(ovector); - for (; i < nmatch; i++) pmatch[i].rm_so = pmatch[i].rm_eo = -1; - } - return 0; - } - -else - { - if (allocated_ovector) free(ovector); - switch(rc) - { - case PCRE_ERROR_NOMATCH: return REG_NOMATCH; - case PCRE_ERROR_NULL: return REG_INVARG; - case PCRE_ERROR_BADOPTION: return REG_INVARG; - case PCRE_ERROR_BADMAGIC: return REG_INVARG; - case PCRE_ERROR_UNKNOWN_NODE: return REG_ASSERT; - case PCRE_ERROR_NOMEMORY: return REG_ESPACE; - case PCRE_ERROR_MATCHLIMIT: return REG_ESPACE; - case PCRE_ERROR_BADUTF8: return REG_INVARG; - case PCRE_ERROR_BADUTF8_OFFSET: return REG_INVARG; - default: return REG_ASSERT; - } - } -} - -/* End of pcreposix.c */ diff --git a/libs/pcre/pcreposix.h b/libs/pcre/pcreposix.h deleted file mode 100644 index 7c5af72437..0000000000 --- a/libs/pcre/pcreposix.h +++ /dev/null @@ -1,144 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -#ifndef _PCREPOSIX_H -#define _PCREPOSIX_H - -/* This is the header for the POSIX wrapper interface to the PCRE Perl- -Compatible Regular Expression library. It defines the things POSIX says should -be there. I hope. - - Copyright (c) 1997-2009 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Have to include stdlib.h in order to ensure that size_t is defined. */ - -#include - -/* Allow for C++ users */ - -#ifdef __cplusplus -extern "C" { -#endif - -/* Options, mostly defined by POSIX, but with a couple of extras. */ - -#define REG_ICASE 0x0001 -#define REG_NEWLINE 0x0002 -#define REG_NOTBOL 0x0004 -#define REG_NOTEOL 0x0008 -#define REG_DOTALL 0x0010 /* NOT defined by POSIX. */ -#define REG_NOSUB 0x0020 -#define REG_UTF8 0x0040 /* NOT defined by POSIX. */ -#define REG_STARTEND 0x0080 /* BSD feature: pass subject string by so,eo */ -#define REG_NOTEMPTY 0x0100 /* NOT defined by POSIX. */ - -/* This is not used by PCRE, but by defining it we make it easier -to slot PCRE into existing programs that make POSIX calls. */ - -#define REG_EXTENDED 0 - -/* Error values. Not all these are relevant or used by the wrapper. */ - -enum { - REG_ASSERT = 1, /* internal error ? */ - REG_BADBR, /* invalid repeat counts in {} */ - REG_BADPAT, /* pattern error */ - REG_BADRPT, /* ? * + invalid */ - REG_EBRACE, /* unbalanced {} */ - REG_EBRACK, /* unbalanced [] */ - REG_ECOLLATE, /* collation error - not relevant */ - REG_ECTYPE, /* bad class */ - REG_EESCAPE, /* bad escape sequence */ - REG_EMPTY, /* empty expression */ - REG_EPAREN, /* unbalanced () */ - REG_ERANGE, /* bad range inside [] */ - REG_ESIZE, /* expression too big */ - REG_ESPACE, /* failed to get memory */ - REG_ESUBREG, /* bad back reference */ - REG_INVARG, /* bad argument */ - REG_NOMATCH /* match failed */ -}; - - -/* The structure representing a compiled regular expression. */ - -typedef struct { - void *re_pcre; - size_t re_nsub; - size_t re_erroffset; -} regex_t; - -/* The structure in which a captured offset is returned. */ - -typedef int regoff_t; - -typedef struct { - regoff_t rm_so; - regoff_t rm_eo; -} regmatch_t; - -/* When an application links to a PCRE DLL in Windows, the symbols that are -imported have to be identified as such. When building PCRE, the appropriate -export settings are needed, and are set in pcreposix.c before including this -file. */ - -#if defined(_WIN32) && !defined(PCRE_STATIC) && !defined(PCREPOSIX_EXP_DECL) -# define PCREPOSIX_EXP_DECL extern __declspec(dllimport) -# define PCREPOSIX_EXP_DEFN __declspec(dllimport) -#endif - -/* By default, we use the standard "extern" declarations. */ - -#ifndef PCREPOSIX_EXP_DECL -# ifdef __cplusplus -# define PCREPOSIX_EXP_DECL extern "C" -# define PCREPOSIX_EXP_DEFN extern "C" -# else -# define PCREPOSIX_EXP_DECL extern -# define PCREPOSIX_EXP_DEFN extern -# endif -#endif - -/* The functions */ - -PCREPOSIX_EXP_DECL int regcomp(regex_t *, const char *, int); -PCREPOSIX_EXP_DECL int regexec(const regex_t *, const char *, size_t, - regmatch_t *, int); -PCREPOSIX_EXP_DECL size_t regerror(int, const regex_t *, char *, size_t); -PCREPOSIX_EXP_DECL void regfree(regex_t *); - -#ifdef __cplusplus -} /* extern "C" */ -#endif - -#endif /* End of pcreposix.h */ diff --git a/libs/pcre/pcretest.c b/libs/pcre/pcretest.c deleted file mode 100644 index 79218a2717..0000000000 --- a/libs/pcre/pcretest.c +++ /dev/null @@ -1,2504 +0,0 @@ -/************************************************* -* PCRE testing program * -*************************************************/ - -/* This program was hacked up as a tester for PCRE. I really should have -written it more tidily in the first place. Will I ever learn? It has grown and -been extended and consequently is now rather, er, *very* untidy in places. - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include -#include -#include -#include -#include -#include -#include - -#ifdef SUPPORT_LIBREADLINE -#ifdef HAVE_UNISTD_H -#include -#endif -#include -#include -#endif - - -/* A number of things vary for Windows builds. Originally, pcretest opened its -input and output without "b"; then I was told that "b" was needed in some -environments, so it was added for release 5.0 to both the input and output. (It -makes no difference on Unix-like systems.) Later I was told that it is wrong -for the input on Windows. I've now abstracted the modes into two macros that -are set here, to make it easier to fiddle with them, and removed "b" from the -input mode under Windows. */ - -#if defined(_WIN32) || defined(WIN32) -#include /* For _setmode() */ -#include /* For _O_BINARY */ -#define INPUT_MODE "r" -#define OUTPUT_MODE "wb" - -#ifndef isatty -#define isatty _isatty /* This is what Windows calls them, I'm told, */ -#endif /* though in some environments they seem to */ - /* be already defined, hence the #ifndefs. */ -#ifndef fileno -#define fileno _fileno -#endif - -#else -#include /* These two includes are needed */ -#include /* for setrlimit(). */ -#define INPUT_MODE "rb" -#define OUTPUT_MODE "wb" -#endif - - -/* We have to include pcre_internal.h because we need the internal info for -displaying the results of pcre_study() and we also need to know about the -internal macros, structures, and other internal data values; pcretest has -"inside information" compared to a program that strictly follows the PCRE API. - -Although pcre_internal.h does itself include pcre.h, we explicitly include it -here before pcre_internal.h so that the PCRE_EXP_xxx macros get set -appropriately for an application, not for building PCRE. */ - -#include "pcre.h" -#include "pcre_internal.h" - -/* We need access to some of the data tables that PCRE uses. So as not to have -to keep two copies, we include the source file here, changing the names of the -external symbols to prevent clashes. */ - -#define _pcre_ucp_gentype ucp_gentype -#define _pcre_utf8_table1 utf8_table1 -#define _pcre_utf8_table1_size utf8_table1_size -#define _pcre_utf8_table2 utf8_table2 -#define _pcre_utf8_table3 utf8_table3 -#define _pcre_utf8_table4 utf8_table4 -#define _pcre_utt utt -#define _pcre_utt_size utt_size -#define _pcre_utt_names utt_names -#define _pcre_OP_lengths OP_lengths - -#include "pcre_tables.c" - -/* We also need the pcre_printint() function for printing out compiled -patterns. This function is in a separate file so that it can be included in -pcre_compile.c when that module is compiled with debugging enabled. - -The definition of the macro PRINTABLE, which determines whether to print an -output character as-is or as a hex value when showing compiled patterns, is -contained in this file. We uses it here also, in cases when the locale has not -been explicitly changed, so as to get consistent output from systems that -differ in their output from isprint() even in the "C" locale. */ - -#include "pcre_printint.src" - -#define PRINTHEX(c) (locale_set? isprint(c) : PRINTABLE(c)) - - -/* It is possible to compile this test program without including support for -testing the POSIX interface, though this is not available via the standard -Makefile. */ - -#if !defined NOPOSIX -#include "pcreposix.h" -#endif - -/* It is also possible, for the benefit of the version currently imported into -Exim, to build pcretest without support for UTF8 (define NOUTF8), without the -interface to the DFA matcher (NODFA), and without the doublecheck of the old -"info" function (define NOINFOCHECK). In fact, we automatically cut out the -UTF8 support if PCRE is built without it. */ - -#ifndef SUPPORT_UTF8 -#ifndef NOUTF8 -#define NOUTF8 -#endif -#endif - - -/* Other parameters */ - -#ifndef CLOCKS_PER_SEC -#ifdef CLK_TCK -#define CLOCKS_PER_SEC CLK_TCK -#else -#define CLOCKS_PER_SEC 100 -#endif -#endif - -/* This is the default loop count for timing. */ - -#define LOOPREPEAT 500000 - -/* Static variables */ - -static FILE *outfile; -static int log_store = 0; -static int callout_count; -static int callout_extra; -static int callout_fail_count; -static int callout_fail_id; -static int debug_lengths; -static int first_callout; -static int locale_set = 0; -static int show_malloc; -static int use_utf8; -static size_t gotten_store; - -/* The buffers grow automatically if very long input lines are encountered. */ - -static int buffer_size = 50000; -static uschar *buffer = NULL; -static uschar *dbuffer = NULL; -static uschar *pbuffer = NULL; - - - -/************************************************* -* Read or extend an input line * -*************************************************/ - -/* Input lines are read into buffer, but both patterns and data lines can be -continued over multiple input lines. In addition, if the buffer fills up, we -want to automatically expand it so as to be able to handle extremely large -lines that are needed for certain stress tests. When the input buffer is -expanded, the other two buffers must also be expanded likewise, and the -contents of pbuffer, which are a copy of the input for callouts, must be -preserved (for when expansion happens for a data line). This is not the most -optimal way of handling this, but hey, this is just a test program! - -Arguments: - f the file to read - start where in buffer to start (this *must* be within buffer) - prompt for stdin or readline() - -Returns: pointer to the start of new data - could be a copy of start, or could be moved - NULL if no data read and EOF reached -*/ - -static uschar * -extend_inputline(FILE *f, uschar *start, const char *prompt) -{ -uschar *here = start; - -for (;;) - { - int rlen = buffer_size - (here - buffer); - - if (rlen > 1000) - { - int dlen; - - /* If libreadline support is required, use readline() to read a line if the - input is a terminal. Note that readline() removes the trailing newline, so - we must put it back again, to be compatible with fgets(). */ - -#ifdef SUPPORT_LIBREADLINE - if (isatty(fileno(f))) - { - size_t len; - char *s = readline(prompt); - if (s == NULL) return (here == start)? NULL : start; - len = strlen(s); - if (len > 0) add_history(s); - if (len > rlen - 1) len = rlen - 1; - memcpy(here, s, len); - here[len] = '\n'; - here[len+1] = 0; - free(s); - } - else -#endif - - /* Read the next line by normal means, prompting if the file is stdin. */ - - { - if (f == stdin) printf(prompt); - if (fgets((char *)here, rlen, f) == NULL) - return (here == start)? NULL : start; - } - - dlen = (int)strlen((char *)here); - if (dlen > 0 && here[dlen - 1] == '\n') return start; - here += dlen; - } - - else - { - int new_buffer_size = 2*buffer_size; - uschar *new_buffer = (unsigned char *)malloc(new_buffer_size); - uschar *new_dbuffer = (unsigned char *)malloc(new_buffer_size); - uschar *new_pbuffer = (unsigned char *)malloc(new_buffer_size); - - if (new_buffer == NULL || new_dbuffer == NULL || new_pbuffer == NULL) - { - fprintf(stderr, "pcretest: malloc(%d) failed\n", new_buffer_size); - exit(1); - } - - memcpy(new_buffer, buffer, buffer_size); - memcpy(new_pbuffer, pbuffer, buffer_size); - - buffer_size = new_buffer_size; - - start = new_buffer + (start - buffer); - here = new_buffer + (here - buffer); - - free(buffer); - free(dbuffer); - free(pbuffer); - - buffer = new_buffer; - dbuffer = new_dbuffer; - pbuffer = new_pbuffer; - } - } - -return NULL; /* Control never gets here */ -} - - - - - - - -/************************************************* -* Read number from string * -*************************************************/ - -/* We don't use strtoul() because SunOS4 doesn't have it. Rather than mess -around with conditional compilation, just do the job by hand. It is only used -for unpicking arguments, so just keep it simple. - -Arguments: - str string to be converted - endptr where to put the end pointer - -Returns: the unsigned long -*/ - -static int -get_value(unsigned char *str, unsigned char **endptr) -{ -int result = 0; -while(*str != 0 && isspace(*str)) str++; -while (isdigit(*str)) result = result * 10 + (int)(*str++ - '0'); -*endptr = str; -return(result); -} - - - - -/************************************************* -* Convert UTF-8 string to value * -*************************************************/ - -/* This function takes one or more bytes that represents a UTF-8 character, -and returns the value of the character. - -Argument: - utf8bytes a pointer to the byte vector - vptr a pointer to an int to receive the value - -Returns: > 0 => the number of bytes consumed - -6 to 0 => malformed UTF-8 character at offset = (-return) -*/ - -#if !defined NOUTF8 - -static int -utf82ord(unsigned char *utf8bytes, int *vptr) -{ -int c = *utf8bytes++; -int d = c; -int i, j, s; - -for (i = -1; i < 6; i++) /* i is number of additional bytes */ - { - if ((d & 0x80) == 0) break; - d <<= 1; - } - -if (i == -1) { *vptr = c; return 1; } /* ascii character */ -if (i == 0 || i == 6) return 0; /* invalid UTF-8 */ - -/* i now has a value in the range 1-5 */ - -s = 6*i; -d = (c & utf8_table3[i]) << s; - -for (j = 0; j < i; j++) - { - c = *utf8bytes++; - if ((c & 0xc0) != 0x80) return -(j+1); - s -= 6; - d |= (c & 0x3f) << s; - } - -/* Check that encoding was the correct unique one */ - -for (j = 0; j < utf8_table1_size; j++) - if (d <= utf8_table1[j]) break; -if (j != i) return -(i+1); - -/* Valid value */ - -*vptr = d; -return i+1; -} - -#endif - - - -/************************************************* -* Convert character value to UTF-8 * -*************************************************/ - -/* This function takes an integer value in the range 0 - 0x7fffffff -and encodes it as a UTF-8 character in 0 to 6 bytes. - -Arguments: - cvalue the character value - utf8bytes pointer to buffer for result - at least 6 bytes long - -Returns: number of characters placed in the buffer -*/ - -#if !defined NOUTF8 - -static int -ord2utf8(int cvalue, uschar *utf8bytes) -{ -register int i, j; -for (i = 0; i < utf8_table1_size; i++) - if (cvalue <= utf8_table1[i]) break; -utf8bytes += i; -for (j = i; j > 0; j--) - { - *utf8bytes-- = 0x80 | (cvalue & 0x3f); - cvalue >>= 6; - } -*utf8bytes = utf8_table2[i] | cvalue; -return i + 1; -} - -#endif - - - -/************************************************* -* Print character string * -*************************************************/ - -/* Character string printing function. Must handle UTF-8 strings in utf8 -mode. Yields number of characters printed. If handed a NULL file, just counts -chars without printing. */ - -static int pchars(unsigned char *p, int length, FILE *f) -{ -int c = 0; -int yield = 0; - -while (length-- > 0) - { -#if !defined NOUTF8 - if (use_utf8) - { - int rc = utf82ord(p, &c); - - if (rc > 0 && rc <= length + 1) /* Mustn't run over the end */ - { - length -= rc - 1; - p += rc; - if (PRINTHEX(c)) - { - if (f != NULL) fprintf(f, "%c", c); - yield++; - } - else - { - int n = 4; - if (f != NULL) fprintf(f, "\\x{%02x}", c); - yield += (n <= 0x000000ff)? 2 : - (n <= 0x00000fff)? 3 : - (n <= 0x0000ffff)? 4 : - (n <= 0x000fffff)? 5 : 6; - } - continue; - } - } -#endif - - /* Not UTF-8, or malformed UTF-8 */ - - c = *p++; - if (PRINTHEX(c)) - { - if (f != NULL) fprintf(f, "%c", c); - yield++; - } - else - { - if (f != NULL) fprintf(f, "\\x%02x", c); - yield += 4; - } - } - -return yield; -} - - - -/************************************************* -* Callout function * -*************************************************/ - -/* Called from PCRE as a result of the (?C) item. We print out where we are in -the match. Yield zero unless more callouts than the fail count, or the callout -data is not zero. */ - -static int callout(pcre_callout_block *cb) -{ -FILE *f = (first_callout | callout_extra)? outfile : NULL; -int i, pre_start, post_start, subject_length; - -if (callout_extra) - { - fprintf(f, "Callout %d: last capture = %d\n", - cb->callout_number, cb->capture_last); - - for (i = 0; i < cb->capture_top * 2; i += 2) - { - if (cb->offset_vector[i] < 0) - fprintf(f, "%2d: \n", i/2); - else - { - fprintf(f, "%2d: ", i/2); - (void)pchars((unsigned char *)cb->subject + cb->offset_vector[i], - cb->offset_vector[i+1] - cb->offset_vector[i], f); - fprintf(f, "\n"); - } - } - } - -/* Re-print the subject in canonical form, the first time or if giving full -datails. On subsequent calls in the same match, we use pchars just to find the -printed lengths of the substrings. */ - -if (f != NULL) fprintf(f, "--->"); - -pre_start = pchars((unsigned char *)cb->subject, cb->start_match, f); -post_start = pchars((unsigned char *)(cb->subject + cb->start_match), - cb->current_position - cb->start_match, f); - -subject_length = pchars((unsigned char *)cb->subject, cb->subject_length, NULL); - -(void)pchars((unsigned char *)(cb->subject + cb->current_position), - cb->subject_length - cb->current_position, f); - -if (f != NULL) fprintf(f, "\n"); - -/* Always print appropriate indicators, with callout number if not already -shown. For automatic callouts, show the pattern offset. */ - -if (cb->callout_number == 255) - { - fprintf(outfile, "%+3d ", cb->pattern_position); - if (cb->pattern_position > 99) fprintf(outfile, "\n "); - } -else - { - if (callout_extra) fprintf(outfile, " "); - else fprintf(outfile, "%3d ", cb->callout_number); - } - -for (i = 0; i < pre_start; i++) fprintf(outfile, " "); -fprintf(outfile, "^"); - -if (post_start > 0) - { - for (i = 0; i < post_start - 1; i++) fprintf(outfile, " "); - fprintf(outfile, "^"); - } - -for (i = 0; i < subject_length - pre_start - post_start + 4; i++) - fprintf(outfile, " "); - -fprintf(outfile, "%.*s", (cb->next_item_length == 0)? 1 : cb->next_item_length, - pbuffer + cb->pattern_position); - -fprintf(outfile, "\n"); -first_callout = 0; - -if (cb->callout_data != NULL) - { - int callout_data = *((int *)(cb->callout_data)); - if (callout_data != 0) - { - fprintf(outfile, "Callout data = %d\n", callout_data); - return callout_data; - } - } - -return (cb->callout_number != callout_fail_id)? 0 : - (++callout_count >= callout_fail_count)? 1 : 0; -} - - -/************************************************* -* Local malloc functions * -*************************************************/ - -/* Alternative malloc function, to test functionality and show the size of the -compiled re. */ - -static void *new_malloc(size_t size) -{ -void *block = malloc(size); -gotten_store = size; -if (show_malloc) - fprintf(outfile, "malloc %3d %p\n", (int)size, block); -return block; -} - -static void new_free(void *block) -{ -if (show_malloc) - fprintf(outfile, "free %p\n", block); -free(block); -} - - -/* For recursion malloc/free, to test stacking calls */ - -static void *stack_malloc(size_t size) -{ -void *block = malloc(size); -if (show_malloc) - fprintf(outfile, "stack_malloc %3d %p\n", (int)size, block); -return block; -} - -static void stack_free(void *block) -{ -if (show_malloc) - fprintf(outfile, "stack_free %p\n", block); -free(block); -} - - -/************************************************* -* Call pcre_fullinfo() * -*************************************************/ - -/* Get one piece of information from the pcre_fullinfo() function */ - -static void new_info(pcre *re, pcre_extra *study, int option, void *ptr) -{ -int rc; -if ((rc = pcre_fullinfo(re, study, option, ptr)) < 0) - fprintf(outfile, "Error %d from pcre_fullinfo(%d)\n", rc, option); -} - - - -/************************************************* -* Byte flipping function * -*************************************************/ - -static unsigned long int -byteflip(unsigned long int value, int n) -{ -if (n == 2) return ((value & 0x00ff) << 8) | ((value & 0xff00) >> 8); -return ((value & 0x000000ff) << 24) | - ((value & 0x0000ff00) << 8) | - ((value & 0x00ff0000) >> 8) | - ((value & 0xff000000) >> 24); -} - - - - -/************************************************* -* Check match or recursion limit * -*************************************************/ - -static int -check_match_limit(pcre *re, pcre_extra *extra, uschar *bptr, int len, - int start_offset, int options, int *use_offsets, int use_size_offsets, - int flag, unsigned long int *limit, int errnumber, const char *msg) -{ -int count; -int min = 0; -int mid = 64; -int max = -1; - -extra->flags |= flag; - -for (;;) - { - *limit = mid; - - count = pcre_exec(re, extra, (char *)bptr, len, start_offset, options, - use_offsets, use_size_offsets); - - if (count == errnumber) - { - /* fprintf(outfile, "Testing %s limit = %d\n", msg, mid); */ - min = mid; - mid = (mid == max - 1)? max : (max > 0)? (min + max)/2 : mid*2; - } - - else if (count >= 0 || count == PCRE_ERROR_NOMATCH || - count == PCRE_ERROR_PARTIAL) - { - if (mid == min + 1) - { - fprintf(outfile, "Minimum %s limit = %d\n", msg, mid); - break; - } - /* fprintf(outfile, "Testing %s limit = %d\n", msg, mid); */ - max = mid; - mid = (min + mid)/2; - } - else break; /* Some other error */ - } - -extra->flags &= ~flag; -return count; -} - - - -/************************************************* -* Case-independent strncmp() function * -*************************************************/ - -/* -Arguments: - s first string - t second string - n number of characters to compare - -Returns: < 0, = 0, or > 0, according to the comparison -*/ - -static int -strncmpic(uschar *s, uschar *t, int n) -{ -while (n--) - { - int c = tolower(*s++) - tolower(*t++); - if (c) return c; - } -return 0; -} - - - -/************************************************* -* Check newline indicator * -*************************************************/ - -/* This is used both at compile and run-time to check for escapes, where -xxx is LF, CR, CRLF, ANYCRLF, or ANY. Print a message and return 0 if there is -no match. - -Arguments: - p points after the leading '<' - f file for error message - -Returns: appropriate PCRE_NEWLINE_xxx flags, or 0 -*/ - -static int -check_newline(uschar *p, FILE *f) -{ -if (strncmpic(p, (uschar *)"cr>", 3) == 0) return PCRE_NEWLINE_CR; -if (strncmpic(p, (uschar *)"lf>", 3) == 0) return PCRE_NEWLINE_LF; -if (strncmpic(p, (uschar *)"crlf>", 5) == 0) return PCRE_NEWLINE_CRLF; -if (strncmpic(p, (uschar *)"anycrlf>", 8) == 0) return PCRE_NEWLINE_ANYCRLF; -if (strncmpic(p, (uschar *)"any>", 4) == 0) return PCRE_NEWLINE_ANY; -if (strncmpic(p, (uschar *)"bsr_anycrlf>", 12) == 0) return PCRE_BSR_ANYCRLF; -if (strncmpic(p, (uschar *)"bsr_unicode>", 12) == 0) return PCRE_BSR_UNICODE; -fprintf(f, "Unknown newline type at: <%s\n", p); -return 0; -} - - - -/************************************************* -* Usage function * -*************************************************/ - -static void -usage(void) -{ -printf("Usage: pcretest [options] [ []]\n\n"); -printf("Input and output default to stdin and stdout.\n"); -#ifdef SUPPORT_LIBREADLINE -printf("If input is a terminal, readline() is used to read from it.\n"); -#else -printf("This version of pcretest is not linked with readline().\n"); -#endif -printf("\nOptions:\n"); -printf(" -b show compiled code (bytecode)\n"); -printf(" -C show PCRE compile-time options and exit\n"); -printf(" -d debug: show compiled code and information (-b and -i)\n"); -#if !defined NODFA -printf(" -dfa force DFA matching for all subjects\n"); -#endif -printf(" -help show usage information\n"); -printf(" -i show information about compiled patterns\n" - " -M find MATCH_LIMIT minimum for each subject\n" - " -m output memory used information\n" - " -o set size of offsets vector to \n"); -#if !defined NOPOSIX -printf(" -p use POSIX interface\n"); -#endif -printf(" -q quiet: do not output PCRE version number at start\n"); -printf(" -S set stack size to megabytes\n"); -printf(" -s output store (memory) used information\n" - " -t time compilation and execution\n"); -printf(" -t time compilation and execution, repeating times\n"); -printf(" -tm time execution (matching) only\n"); -printf(" -tm time execution (matching) only, repeating times\n"); -} - - - -/************************************************* -* Main Program * -*************************************************/ - -/* Read lines from named file or stdin and write to named file or stdout; lines -consist of a regular expression, in delimiters and optionally followed by -options, followed by a set of test data, terminated by an empty line. */ - -int main(int argc, char **argv) -{ -FILE *infile = stdin; -int options = 0; -int study_options = 0; -int default_find_match_limit = FALSE; -int op = 1; -int timeit = 0; -int timeitm = 0; -int showinfo = 0; -int showstore = 0; -int quiet = 0; -int size_offsets = 45; -int size_offsets_max; -int *offsets = NULL; -#if !defined NOPOSIX -int posix = 0; -#endif -int debug = 0; -int done = 0; -int all_use_dfa = 0; -int yield = 0; -int stack_size; - -/* These vectors store, end-to-end, a list of captured substring names. Assume -that 1024 is plenty long enough for the few names we'll be testing. */ - -uschar copynames[1024]; -uschar getnames[1024]; - -uschar *copynamesptr; -uschar *getnamesptr; - -/* Get buffers from malloc() so that Electric Fence will check their misuse -when I am debugging. They grow automatically when very long lines are read. */ - -buffer = (unsigned char *)malloc(buffer_size); -dbuffer = (unsigned char *)malloc(buffer_size); -pbuffer = (unsigned char *)malloc(buffer_size); - -/* The outfile variable is static so that new_malloc can use it. */ - -outfile = stdout; - -/* The following _setmode() stuff is some Windows magic that tells its runtime -library to translate CRLF into a single LF character. At least, that's what -I've been told: never having used Windows I take this all on trust. Originally -it set 0x8000, but then I was advised that _O_BINARY was better. */ - -#if defined(_WIN32) || defined(WIN32) -_setmode( _fileno( stdout ), _O_BINARY ); -#endif - -/* Scan options */ - -while (argc > 1 && argv[op][0] == '-') - { - unsigned char *endptr; - - if (strcmp(argv[op], "-s") == 0 || strcmp(argv[op], "-m") == 0) - showstore = 1; - else if (strcmp(argv[op], "-q") == 0) quiet = 1; - else if (strcmp(argv[op], "-b") == 0) debug = 1; - else if (strcmp(argv[op], "-i") == 0) showinfo = 1; - else if (strcmp(argv[op], "-d") == 0) showinfo = debug = 1; - else if (strcmp(argv[op], "-M") == 0) default_find_match_limit = TRUE; -#if !defined NODFA - else if (strcmp(argv[op], "-dfa") == 0) all_use_dfa = 1; -#endif - else if (strcmp(argv[op], "-o") == 0 && argc > 2 && - ((size_offsets = get_value((unsigned char *)argv[op+1], &endptr)), - *endptr == 0)) - { - op++; - argc--; - } - else if (strcmp(argv[op], "-t") == 0 || strcmp(argv[op], "-tm") == 0) - { - int both = argv[op][2] == 0; - int temp; - if (argc > 2 && (temp = get_value((unsigned char *)argv[op+1], &endptr), - *endptr == 0)) - { - timeitm = temp; - op++; - argc--; - } - else timeitm = LOOPREPEAT; - if (both) timeit = timeitm; - } - else if (strcmp(argv[op], "-S") == 0 && argc > 2 && - ((stack_size = get_value((unsigned char *)argv[op+1], &endptr)), - *endptr == 0)) - { -#if defined(_WIN32) || defined(WIN32) - printf("PCRE: -S not supported on this OS\n"); - exit(1); -#else - int rc; - struct rlimit rlim; - getrlimit(RLIMIT_STACK, &rlim); - rlim.rlim_cur = stack_size * 1024 * 1024; - rc = setrlimit(RLIMIT_STACK, &rlim); - if (rc != 0) - { - printf("PCRE: setrlimit() failed with error %d\n", rc); - exit(1); - } - op++; - argc--; -#endif - } -#if !defined NOPOSIX - else if (strcmp(argv[op], "-p") == 0) posix = 1; -#endif - else if (strcmp(argv[op], "-C") == 0) - { - int rc; - unsigned long int lrc; - printf("PCRE version %s\n", pcre_version()); - printf("Compiled with\n"); - (void)pcre_config(PCRE_CONFIG_UTF8, &rc); - printf(" %sUTF-8 support\n", rc? "" : "No "); - (void)pcre_config(PCRE_CONFIG_UNICODE_PROPERTIES, &rc); - printf(" %sUnicode properties support\n", rc? "" : "No "); - (void)pcre_config(PCRE_CONFIG_NEWLINE, &rc); - /* Note that these values are always the ASCII values, even - in EBCDIC environments. CR is 13 and NL is 10. */ - printf(" Newline sequence is %s\n", (rc == 13)? "CR" : - (rc == 10)? "LF" : (rc == (13<<8 | 10))? "CRLF" : - (rc == -2)? "ANYCRLF" : - (rc == -1)? "ANY" : "???"); - (void)pcre_config(PCRE_CONFIG_BSR, &rc); - printf(" \\R matches %s\n", rc? "CR, LF, or CRLF only" : - "all Unicode newlines"); - (void)pcre_config(PCRE_CONFIG_LINK_SIZE, &rc); - printf(" Internal link size = %d\n", rc); - (void)pcre_config(PCRE_CONFIG_POSIX_MALLOC_THRESHOLD, &rc); - printf(" POSIX malloc threshold = %d\n", rc); - (void)pcre_config(PCRE_CONFIG_MATCH_LIMIT, &lrc); - printf(" Default match limit = %ld\n", lrc); - (void)pcre_config(PCRE_CONFIG_MATCH_LIMIT_RECURSION, &lrc); - printf(" Default recursion depth limit = %ld\n", lrc); - (void)pcre_config(PCRE_CONFIG_STACKRECURSE, &rc); - printf(" Match recursion uses %s\n", rc? "stack" : "heap"); - goto EXIT; - } - else if (strcmp(argv[op], "-help") == 0 || - strcmp(argv[op], "--help") == 0) - { - usage(); - goto EXIT; - } - else - { - printf("** Unknown or malformed option %s\n", argv[op]); - usage(); - yield = 1; - goto EXIT; - } - op++; - argc--; - } - -/* Get the store for the offsets vector, and remember what it was */ - -size_offsets_max = size_offsets; -offsets = (int *)malloc(size_offsets_max * sizeof(int)); -if (offsets == NULL) - { - printf("** Failed to get %d bytes of memory for offsets vector\n", - (int)(size_offsets_max * sizeof(int))); - yield = 1; - goto EXIT; - } - -/* Sort out the input and output files */ - -if (argc > 1) - { - infile = fopen(argv[op], INPUT_MODE); - if (infile == NULL) - { - printf("** Failed to open %s\n", argv[op]); - yield = 1; - goto EXIT; - } - } - -if (argc > 2) - { - outfile = fopen(argv[op+1], OUTPUT_MODE); - if (outfile == NULL) - { - printf("** Failed to open %s\n", argv[op+1]); - yield = 1; - goto EXIT; - } - } - -/* Set alternative malloc function */ - -pcre_malloc = new_malloc; -pcre_free = new_free; -pcre_stack_malloc = stack_malloc; -pcre_stack_free = stack_free; - -/* Heading line unless quiet, then prompt for first regex if stdin */ - -if (!quiet) fprintf(outfile, "PCRE version %s\n\n", pcre_version()); - -/* Main loop */ - -while (!done) - { - pcre *re = NULL; - pcre_extra *extra = NULL; - -#if !defined NOPOSIX /* There are still compilers that require no indent */ - regex_t preg; - int do_posix = 0; -#endif - - const char *error; - unsigned char *p, *pp, *ppp; - unsigned char *to_file = NULL; - const unsigned char *tables = NULL; - unsigned long int true_size, true_study_size = 0; - size_t size, regex_gotten_store; - int do_study = 0; - int do_debug = debug; - int do_G = 0; - int do_g = 0; - int do_showinfo = showinfo; - int do_showrest = 0; - int do_flip = 0; - int erroroffset, len, delimiter, poffset; - - use_utf8 = 0; - debug_lengths = 1; - - if (extend_inputline(infile, buffer, " re> ") == NULL) break; - if (infile != stdin) fprintf(outfile, "%s", (char *)buffer); - fflush(outfile); - - p = buffer; - while (isspace(*p)) p++; - if (*p == 0) continue; - - /* See if the pattern is to be loaded pre-compiled from a file. */ - - if (*p == '<' && strchr((char *)(p+1), '<') == NULL) - { - unsigned long int magic, get_options; - uschar sbuf[8]; - FILE *f; - - p++; - pp = p + (int)strlen((char *)p); - while (isspace(pp[-1])) pp--; - *pp = 0; - - f = fopen((char *)p, "rb"); - if (f == NULL) - { - fprintf(outfile, "Failed to open %s: %s\n", p, strerror(errno)); - continue; - } - - if (fread(sbuf, 1, 8, f) != 8) goto FAIL_READ; - - true_size = - (sbuf[0] << 24) | (sbuf[1] << 16) | (sbuf[2] << 8) | sbuf[3]; - true_study_size = - (sbuf[4] << 24) | (sbuf[5] << 16) | (sbuf[6] << 8) | sbuf[7]; - - re = (real_pcre *)new_malloc(true_size); - regex_gotten_store = gotten_store; - - if (fread(re, 1, true_size, f) != true_size) goto FAIL_READ; - - magic = ((real_pcre *)re)->magic_number; - if (magic != MAGIC_NUMBER) - { - if (byteflip(magic, sizeof(magic)) == MAGIC_NUMBER) - { - do_flip = 1; - } - else - { - fprintf(outfile, "Data in %s is not a compiled PCRE regex\n", p); - fclose(f); - continue; - } - } - - fprintf(outfile, "Compiled regex%s loaded from %s\n", - do_flip? " (byte-inverted)" : "", p); - - /* Need to know if UTF-8 for printing data strings */ - - new_info(re, NULL, PCRE_INFO_OPTIONS, &get_options); - use_utf8 = (get_options & PCRE_UTF8) != 0; - - /* Now see if there is any following study data */ - - if (true_study_size != 0) - { - pcre_study_data *psd; - - extra = (pcre_extra *)new_malloc(sizeof(pcre_extra) + true_study_size); - extra->flags = PCRE_EXTRA_STUDY_DATA; - - psd = (pcre_study_data *)(((char *)extra) + sizeof(pcre_extra)); - extra->study_data = psd; - - if (fread(psd, 1, true_study_size, f) != true_study_size) - { - FAIL_READ: - fprintf(outfile, "Failed to read data from %s\n", p); - if (extra != NULL) new_free(extra); - if (re != NULL) new_free(re); - fclose(f); - continue; - } - fprintf(outfile, "Study data loaded from %s\n", p); - do_study = 1; /* To get the data output if requested */ - } - else fprintf(outfile, "No study data\n"); - - fclose(f); - goto SHOW_INFO; - } - - /* In-line pattern (the usual case). Get the delimiter and seek the end of - the pattern; if is isn't complete, read more. */ - - delimiter = *p++; - - if (isalnum(delimiter) || delimiter == '\\') - { - fprintf(outfile, "** Delimiter must not be alphanumeric or \\\n"); - goto SKIP_DATA; - } - - pp = p; - poffset = p - buffer; - - for(;;) - { - while (*pp != 0) - { - if (*pp == '\\' && pp[1] != 0) pp++; - else if (*pp == delimiter) break; - pp++; - } - if (*pp != 0) break; - if ((pp = extend_inputline(infile, pp, " > ")) == NULL) - { - fprintf(outfile, "** Unexpected EOF\n"); - done = 1; - goto CONTINUE; - } - if (infile != stdin) fprintf(outfile, "%s", (char *)pp); - } - - /* The buffer may have moved while being extended; reset the start of data - pointer to the correct relative point in the buffer. */ - - p = buffer + poffset; - - /* If the first character after the delimiter is backslash, make - the pattern end with backslash. This is purely to provide a way - of testing for the error message when a pattern ends with backslash. */ - - if (pp[1] == '\\') *pp++ = '\\'; - - /* Terminate the pattern at the delimiter, and save a copy of the pattern - for callouts. */ - - *pp++ = 0; - strcpy((char *)pbuffer, (char *)p); - - /* Look for options after final delimiter */ - - options = 0; - study_options = 0; - log_store = showstore; /* default from command line */ - - while (*pp != 0) - { - switch (*pp++) - { - case 'f': options |= PCRE_FIRSTLINE; break; - case 'g': do_g = 1; break; - case 'i': options |= PCRE_CASELESS; break; - case 'm': options |= PCRE_MULTILINE; break; - case 's': options |= PCRE_DOTALL; break; - case 'x': options |= PCRE_EXTENDED; break; - - case '+': do_showrest = 1; break; - case 'A': options |= PCRE_ANCHORED; break; - case 'B': do_debug = 1; break; - case 'C': options |= PCRE_AUTO_CALLOUT; break; - case 'D': do_debug = do_showinfo = 1; break; - case 'E': options |= PCRE_DOLLAR_ENDONLY; break; - case 'F': do_flip = 1; break; - case 'G': do_G = 1; break; - case 'I': do_showinfo = 1; break; - case 'J': options |= PCRE_DUPNAMES; break; - case 'M': log_store = 1; break; - case 'N': options |= PCRE_NO_AUTO_CAPTURE; break; - -#if !defined NOPOSIX - case 'P': do_posix = 1; break; -#endif - - case 'S': do_study = 1; break; - case 'U': options |= PCRE_UNGREEDY; break; - case 'X': options |= PCRE_EXTRA; break; - case 'Z': debug_lengths = 0; break; - case '8': options |= PCRE_UTF8; use_utf8 = 1; break; - case '?': options |= PCRE_NO_UTF8_CHECK; break; - - case 'L': - ppp = pp; - /* The '\r' test here is so that it works on Windows. */ - /* The '0' test is just in case this is an unterminated line. */ - while (*ppp != 0 && *ppp != '\n' && *ppp != '\r' && *ppp != ' ') ppp++; - *ppp = 0; - if (setlocale(LC_CTYPE, (const char *)pp) == NULL) - { - fprintf(outfile, "** Failed to set locale \"%s\"\n", pp); - goto SKIP_DATA; - } - locale_set = 1; - tables = pcre_maketables(); - pp = ppp; - break; - - case '>': - to_file = pp; - while (*pp != 0) pp++; - while (isspace(pp[-1])) pp--; - *pp = 0; - break; - - case '<': - { - if (strncmp((char *)pp, "JS>", 3) == 0) - { - options |= PCRE_JAVASCRIPT_COMPAT; - pp += 3; - } - else - { - int x = check_newline(pp, outfile); - if (x == 0) goto SKIP_DATA; - options |= x; - while (*pp++ != '>'); - } - } - break; - - case '\r': /* So that it works in Windows */ - case '\n': - case ' ': - break; - - default: - fprintf(outfile, "** Unknown option '%c'\n", pp[-1]); - goto SKIP_DATA; - } - } - - /* Handle compiling via the POSIX interface, which doesn't support the - timing, showing, or debugging options, nor the ability to pass over - local character tables. */ - -#if !defined NOPOSIX - if (posix || do_posix) - { - int rc; - int cflags = 0; - - if ((options & PCRE_CASELESS) != 0) cflags |= REG_ICASE; - if ((options & PCRE_MULTILINE) != 0) cflags |= REG_NEWLINE; - if ((options & PCRE_DOTALL) != 0) cflags |= REG_DOTALL; - if ((options & PCRE_NO_AUTO_CAPTURE) != 0) cflags |= REG_NOSUB; - if ((options & PCRE_UTF8) != 0) cflags |= REG_UTF8; - - rc = regcomp(&preg, (char *)p, cflags); - - /* Compilation failed; go back for another re, skipping to blank line - if non-interactive. */ - - if (rc != 0) - { - (void)regerror(rc, &preg, (char *)buffer, buffer_size); - fprintf(outfile, "Failed: POSIX code %d: %s\n", rc, buffer); - goto SKIP_DATA; - } - } - - /* Handle compiling via the native interface */ - - else -#endif /* !defined NOPOSIX */ - - { - unsigned long int get_options; - - if (timeit > 0) - { - register int i; - clock_t time_taken; - clock_t start_time = clock(); - for (i = 0; i < timeit; i++) - { - re = pcre_compile((char *)p, options, &error, &erroroffset, tables); - if (re != NULL) free(re); - } - time_taken = clock() - start_time; - fprintf(outfile, "Compile time %.4f milliseconds\n", - (((double)time_taken * 1000.0) / (double)timeit) / - (double)CLOCKS_PER_SEC); - } - - re = pcre_compile((char *)p, options, &error, &erroroffset, tables); - - /* Compilation failed; go back for another re, skipping to blank line - if non-interactive. */ - - if (re == NULL) - { - fprintf(outfile, "Failed: %s at offset %d\n", error, erroroffset); - SKIP_DATA: - if (infile != stdin) - { - for (;;) - { - if (extend_inputline(infile, buffer, NULL) == NULL) - { - done = 1; - goto CONTINUE; - } - len = (int)strlen((char *)buffer); - while (len > 0 && isspace(buffer[len-1])) len--; - if (len == 0) break; - } - fprintf(outfile, "\n"); - } - goto CONTINUE; - } - - /* Compilation succeeded. It is now possible to set the UTF-8 option from - within the regex; check for this so that we know how to process the data - lines. */ - - new_info(re, NULL, PCRE_INFO_OPTIONS, &get_options); - if ((get_options & PCRE_UTF8) != 0) use_utf8 = 1; - - /* Print information if required. There are now two info-returning - functions. The old one has a limited interface and returns only limited - data. Check that it agrees with the newer one. */ - - if (log_store) - fprintf(outfile, "Memory allocation (code space): %d\n", - (int)(gotten_store - - sizeof(real_pcre) - - ((real_pcre *)re)->name_count * ((real_pcre *)re)->name_entry_size)); - - /* Extract the size for possible writing before possibly flipping it, - and remember the store that was got. */ - - true_size = ((real_pcre *)re)->size; - regex_gotten_store = gotten_store; - - /* If /S was present, study the regexp to generate additional info to - help with the matching. */ - - if (do_study) - { - if (timeit > 0) - { - register int i; - clock_t time_taken; - clock_t start_time = clock(); - for (i = 0; i < timeit; i++) - extra = pcre_study(re, study_options, &error); - time_taken = clock() - start_time; - if (extra != NULL) free(extra); - fprintf(outfile, " Study time %.4f milliseconds\n", - (((double)time_taken * 1000.0) / (double)timeit) / - (double)CLOCKS_PER_SEC); - } - extra = pcre_study(re, study_options, &error); - if (error != NULL) - fprintf(outfile, "Failed to study: %s\n", error); - else if (extra != NULL) - true_study_size = ((pcre_study_data *)(extra->study_data))->size; - } - - /* If the 'F' option was present, we flip the bytes of all the integer - fields in the regex data block and the study block. This is to make it - possible to test PCRE's handling of byte-flipped patterns, e.g. those - compiled on a different architecture. */ - - if (do_flip) - { - real_pcre *rre = (real_pcre *)re; - rre->magic_number = - byteflip(rre->magic_number, sizeof(rre->magic_number)); - rre->size = byteflip(rre->size, sizeof(rre->size)); - rre->options = byteflip(rre->options, sizeof(rre->options)); - rre->flags = (pcre_uint16)byteflip(rre->flags, sizeof(rre->flags)); - rre->top_bracket = - (pcre_uint16)byteflip(rre->top_bracket, sizeof(rre->top_bracket)); - rre->top_backref = - (pcre_uint16)byteflip(rre->top_backref, sizeof(rre->top_backref)); - rre->first_byte = - (pcre_uint16)byteflip(rre->first_byte, sizeof(rre->first_byte)); - rre->req_byte = - (pcre_uint16)byteflip(rre->req_byte, sizeof(rre->req_byte)); - rre->name_table_offset = (pcre_uint16)byteflip(rre->name_table_offset, - sizeof(rre->name_table_offset)); - rre->name_entry_size = (pcre_uint16)byteflip(rre->name_entry_size, - sizeof(rre->name_entry_size)); - rre->name_count = (pcre_uint16)byteflip(rre->name_count, - sizeof(rre->name_count)); - - if (extra != NULL) - { - pcre_study_data *rsd = (pcre_study_data *)(extra->study_data); - rsd->size = byteflip(rsd->size, sizeof(rsd->size)); - rsd->options = byteflip(rsd->options, sizeof(rsd->options)); - } - } - - /* Extract information from the compiled data if required */ - - SHOW_INFO: - - if (do_debug) - { - fprintf(outfile, "------------------------------------------------------------------\n"); - pcre_printint(re, outfile, debug_lengths); - } - - /* We already have the options in get_options (see above) */ - - if (do_showinfo) - { - unsigned long int all_options; -#if !defined NOINFOCHECK - int old_first_char, old_options, old_count; -#endif - int count, backrefmax, first_char, need_char, okpartial, jchanged, - hascrorlf; - int nameentrysize, namecount; - const uschar *nametable; - - new_info(re, NULL, PCRE_INFO_SIZE, &size); - new_info(re, NULL, PCRE_INFO_CAPTURECOUNT, &count); - new_info(re, NULL, PCRE_INFO_BACKREFMAX, &backrefmax); - new_info(re, NULL, PCRE_INFO_FIRSTBYTE, &first_char); - new_info(re, NULL, PCRE_INFO_LASTLITERAL, &need_char); - new_info(re, NULL, PCRE_INFO_NAMEENTRYSIZE, &nameentrysize); - new_info(re, NULL, PCRE_INFO_NAMECOUNT, &namecount); - new_info(re, NULL, PCRE_INFO_NAMETABLE, (void *)&nametable); - new_info(re, NULL, PCRE_INFO_OKPARTIAL, &okpartial); - new_info(re, NULL, PCRE_INFO_JCHANGED, &jchanged); - new_info(re, NULL, PCRE_INFO_HASCRORLF, &hascrorlf); - -#if !defined NOINFOCHECK - old_count = pcre_info(re, &old_options, &old_first_char); - if (count < 0) fprintf(outfile, - "Error %d from pcre_info()\n", count); - else - { - if (old_count != count) fprintf(outfile, - "Count disagreement: pcre_fullinfo=%d pcre_info=%d\n", count, - old_count); - - if (old_first_char != first_char) fprintf(outfile, - "First char disagreement: pcre_fullinfo=%d pcre_info=%d\n", - first_char, old_first_char); - - if (old_options != (int)get_options) fprintf(outfile, - "Options disagreement: pcre_fullinfo=%ld pcre_info=%d\n", - get_options, old_options); - } -#endif - - if (size != regex_gotten_store) fprintf(outfile, - "Size disagreement: pcre_fullinfo=%d call to malloc for %d\n", - (int)size, (int)regex_gotten_store); - - fprintf(outfile, "Capturing subpattern count = %d\n", count); - if (backrefmax > 0) - fprintf(outfile, "Max back reference = %d\n", backrefmax); - - if (namecount > 0) - { - fprintf(outfile, "Named capturing subpatterns:\n"); - while (namecount-- > 0) - { - fprintf(outfile, " %s %*s%3d\n", nametable + 2, - nameentrysize - 3 - (int)strlen((char *)nametable + 2), "", - GET2(nametable, 0)); - nametable += nameentrysize; - } - } - - if (!okpartial) fprintf(outfile, "Partial matching not supported\n"); - if (hascrorlf) fprintf(outfile, "Contains explicit CR or LF match\n"); - - all_options = ((real_pcre *)re)->options; - if (do_flip) all_options = byteflip(all_options, sizeof(all_options)); - - if (get_options == 0) fprintf(outfile, "No options\n"); - else fprintf(outfile, "Options:%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s\n", - ((get_options & PCRE_ANCHORED) != 0)? " anchored" : "", - ((get_options & PCRE_CASELESS) != 0)? " caseless" : "", - ((get_options & PCRE_EXTENDED) != 0)? " extended" : "", - ((get_options & PCRE_MULTILINE) != 0)? " multiline" : "", - ((get_options & PCRE_FIRSTLINE) != 0)? " firstline" : "", - ((get_options & PCRE_DOTALL) != 0)? " dotall" : "", - ((get_options & PCRE_BSR_ANYCRLF) != 0)? " bsr_anycrlf" : "", - ((get_options & PCRE_BSR_UNICODE) != 0)? " bsr_unicode" : "", - ((get_options & PCRE_DOLLAR_ENDONLY) != 0)? " dollar_endonly" : "", - ((get_options & PCRE_EXTRA) != 0)? " extra" : "", - ((get_options & PCRE_UNGREEDY) != 0)? " ungreedy" : "", - ((get_options & PCRE_NO_AUTO_CAPTURE) != 0)? " no_auto_capture" : "", - ((get_options & PCRE_UTF8) != 0)? " utf8" : "", - ((get_options & PCRE_NO_UTF8_CHECK) != 0)? " no_utf8_check" : "", - ((get_options & PCRE_DUPNAMES) != 0)? " dupnames" : ""); - - if (jchanged) fprintf(outfile, "Duplicate name status changes\n"); - - switch (get_options & PCRE_NEWLINE_BITS) - { - case PCRE_NEWLINE_CR: - fprintf(outfile, "Forced newline sequence: CR\n"); - break; - - case PCRE_NEWLINE_LF: - fprintf(outfile, "Forced newline sequence: LF\n"); - break; - - case PCRE_NEWLINE_CRLF: - fprintf(outfile, "Forced newline sequence: CRLF\n"); - break; - - case PCRE_NEWLINE_ANYCRLF: - fprintf(outfile, "Forced newline sequence: ANYCRLF\n"); - break; - - case PCRE_NEWLINE_ANY: - fprintf(outfile, "Forced newline sequence: ANY\n"); - break; - - default: - break; - } - - if (first_char == -1) - { - fprintf(outfile, "First char at start or follows newline\n"); - } - else if (first_char < 0) - { - fprintf(outfile, "No first char\n"); - } - else - { - int ch = first_char & 255; - const char *caseless = ((first_char & REQ_CASELESS) == 0)? - "" : " (caseless)"; - if (PRINTHEX(ch)) - fprintf(outfile, "First char = \'%c\'%s\n", ch, caseless); - else - fprintf(outfile, "First char = %d%s\n", ch, caseless); - } - - if (need_char < 0) - { - fprintf(outfile, "No need char\n"); - } - else - { - int ch = need_char & 255; - const char *caseless = ((need_char & REQ_CASELESS) == 0)? - "" : " (caseless)"; - if (PRINTHEX(ch)) - fprintf(outfile, "Need char = \'%c\'%s\n", ch, caseless); - else - fprintf(outfile, "Need char = %d%s\n", ch, caseless); - } - - /* Don't output study size; at present it is in any case a fixed - value, but it varies, depending on the computer architecture, and - so messes up the test suite. (And with the /F option, it might be - flipped.) */ - - if (do_study) - { - if (extra == NULL) - fprintf(outfile, "Study returned NULL\n"); - else - { - uschar *start_bits = NULL; - new_info(re, extra, PCRE_INFO_FIRSTTABLE, &start_bits); - - if (start_bits == NULL) - fprintf(outfile, "No starting byte set\n"); - else - { - int i; - int c = 24; - fprintf(outfile, "Starting byte set: "); - for (i = 0; i < 256; i++) - { - if ((start_bits[i/8] & (1<<(i&7))) != 0) - { - if (c > 75) - { - fprintf(outfile, "\n "); - c = 2; - } - if (PRINTHEX(i) && i != ' ') - { - fprintf(outfile, "%c ", i); - c += 2; - } - else - { - fprintf(outfile, "\\x%02x ", i); - c += 5; - } - } - } - fprintf(outfile, "\n"); - } - } - } - } - - /* If the '>' option was present, we write out the regex to a file, and - that is all. The first 8 bytes of the file are the regex length and then - the study length, in big-endian order. */ - - if (to_file != NULL) - { - FILE *f = fopen((char *)to_file, "wb"); - if (f == NULL) - { - fprintf(outfile, "Unable to open %s: %s\n", to_file, strerror(errno)); - } - else - { - uschar sbuf[8]; - sbuf[0] = (uschar)((true_size >> 24) & 255); - sbuf[1] = (uschar)((true_size >> 16) & 255); - sbuf[2] = (uschar)((true_size >> 8) & 255); - sbuf[3] = (uschar)((true_size) & 255); - - sbuf[4] = (uschar)((true_study_size >> 24) & 255); - sbuf[5] = (uschar)((true_study_size >> 16) & 255); - sbuf[6] = (uschar)((true_study_size >> 8) & 255); - sbuf[7] = (uschar)((true_study_size) & 255); - - if (fwrite(sbuf, 1, 8, f) < 8 || - fwrite(re, 1, true_size, f) < true_size) - { - fprintf(outfile, "Write error on %s: %s\n", to_file, strerror(errno)); - } - else - { - fprintf(outfile, "Compiled regex written to %s\n", to_file); - if (extra != NULL) - { - if (fwrite(extra->study_data, 1, true_study_size, f) < - true_study_size) - { - fprintf(outfile, "Write error on %s: %s\n", to_file, - strerror(errno)); - } - else fprintf(outfile, "Study data written to %s\n", to_file); - - } - } - fclose(f); - } - - new_free(re); - if (extra != NULL) new_free(extra); - if (tables != NULL) new_free((void *)tables); - continue; /* With next regex */ - } - } /* End of non-POSIX compile */ - - /* Read data lines and test them */ - - for (;;) - { - uschar *q; - uschar *bptr; - int *use_offsets = offsets; - int use_size_offsets = size_offsets; - int callout_data = 0; - int callout_data_set = 0; - int count, c; - int copystrings = 0; - int find_match_limit = default_find_match_limit; - int getstrings = 0; - int getlist = 0; - int gmatched = 0; - int start_offset = 0; - int g_notempty = 0; - int use_dfa = 0; - - options = 0; - - *copynames = 0; - *getnames = 0; - - copynamesptr = copynames; - getnamesptr = getnames; - - pcre_callout = callout; - first_callout = 1; - callout_extra = 0; - callout_count = 0; - callout_fail_count = 999999; - callout_fail_id = -1; - show_malloc = 0; - - if (extra != NULL) extra->flags &= - ~(PCRE_EXTRA_MATCH_LIMIT|PCRE_EXTRA_MATCH_LIMIT_RECURSION); - - len = 0; - for (;;) - { - if (extend_inputline(infile, buffer + len, "data> ") == NULL) - { - if (len > 0) break; - done = 1; - goto CONTINUE; - } - if (infile != stdin) fprintf(outfile, "%s", (char *)buffer); - len = (int)strlen((char *)buffer); - if (buffer[len-1] == '\n') break; - } - - while (len > 0 && isspace(buffer[len-1])) len--; - buffer[len] = 0; - if (len == 0) break; - - p = buffer; - while (isspace(*p)) p++; - - bptr = q = dbuffer; - while ((c = *p++) != 0) - { - int i = 0; - int n = 0; - - if (c == '\\') switch ((c = *p++)) - { - case 'a': c = 7; break; - case 'b': c = '\b'; break; - case 'e': c = 27; break; - case 'f': c = '\f'; break; - case 'n': c = '\n'; break; - case 'r': c = '\r'; break; - case 't': c = '\t'; break; - case 'v': c = '\v'; break; - - case '0': case '1': case '2': case '3': - case '4': case '5': case '6': case '7': - c -= '0'; - while (i++ < 2 && isdigit(*p) && *p != '8' && *p != '9') - c = c * 8 + *p++ - '0'; - -#if !defined NOUTF8 - if (use_utf8 && c > 255) - { - unsigned char buff8[8]; - int ii, utn; - utn = ord2utf8(c, buff8); - for (ii = 0; ii < utn - 1; ii++) *q++ = buff8[ii]; - c = buff8[ii]; /* Last byte */ - } -#endif - break; - - case 'x': - - /* Handle \x{..} specially - new Perl thing for utf8 */ - -#if !defined NOUTF8 - if (*p == '{') - { - unsigned char *pt = p; - c = 0; - while (isxdigit(*(++pt))) - c = c * 16 + tolower(*pt) - ((isdigit(*pt))? '0' : 'W'); - if (*pt == '}') - { - unsigned char buff8[8]; - int ii, utn; - if (use_utf8) - { - utn = ord2utf8(c, buff8); - for (ii = 0; ii < utn - 1; ii++) *q++ = buff8[ii]; - c = buff8[ii]; /* Last byte */ - } - else - { - if (c > 255) - fprintf(outfile, "** Character \\x{%x} is greater than 255 and " - "UTF-8 mode is not enabled.\n" - "** Truncation will probably give the wrong result.\n", c); - } - p = pt + 1; - break; - } - /* Not correct form; fall through */ - } -#endif - - /* Ordinary \x */ - - c = 0; - while (i++ < 2 && isxdigit(*p)) - { - c = c * 16 + tolower(*p) - ((isdigit(*p))? '0' : 'W'); - p++; - } - break; - - case 0: /* \ followed by EOF allows for an empty line */ - p--; - continue; - - case '>': - while(isdigit(*p)) start_offset = start_offset * 10 + *p++ - '0'; - continue; - - case 'A': /* Option setting */ - options |= PCRE_ANCHORED; - continue; - - case 'B': - options |= PCRE_NOTBOL; - continue; - - case 'C': - if (isdigit(*p)) /* Set copy string */ - { - while(isdigit(*p)) n = n * 10 + *p++ - '0'; - copystrings |= 1 << n; - } - else if (isalnum(*p)) - { - uschar *npp = copynamesptr; - while (isalnum(*p)) *npp++ = *p++; - *npp++ = 0; - *npp = 0; - n = pcre_get_stringnumber(re, (char *)copynamesptr); - if (n < 0) - fprintf(outfile, "no parentheses with name \"%s\"\n", copynamesptr); - copynamesptr = npp; - } - else if (*p == '+') - { - callout_extra = 1; - p++; - } - else if (*p == '-') - { - pcre_callout = NULL; - p++; - } - else if (*p == '!') - { - callout_fail_id = 0; - p++; - while(isdigit(*p)) - callout_fail_id = callout_fail_id * 10 + *p++ - '0'; - callout_fail_count = 0; - if (*p == '!') - { - p++; - while(isdigit(*p)) - callout_fail_count = callout_fail_count * 10 + *p++ - '0'; - } - } - else if (*p == '*') - { - int sign = 1; - callout_data = 0; - if (*(++p) == '-') { sign = -1; p++; } - while(isdigit(*p)) - callout_data = callout_data * 10 + *p++ - '0'; - callout_data *= sign; - callout_data_set = 1; - } - continue; - -#if !defined NODFA - case 'D': -#if !defined NOPOSIX - if (posix || do_posix) - printf("** Can't use dfa matching in POSIX mode: \\D ignored\n"); - else -#endif - use_dfa = 1; - continue; - - case 'F': - options |= PCRE_DFA_SHORTEST; - continue; -#endif - - case 'G': - if (isdigit(*p)) - { - while(isdigit(*p)) n = n * 10 + *p++ - '0'; - getstrings |= 1 << n; - } - else if (isalnum(*p)) - { - uschar *npp = getnamesptr; - while (isalnum(*p)) *npp++ = *p++; - *npp++ = 0; - *npp = 0; - n = pcre_get_stringnumber(re, (char *)getnamesptr); - if (n < 0) - fprintf(outfile, "no parentheses with name \"%s\"\n", getnamesptr); - getnamesptr = npp; - } - continue; - - case 'L': - getlist = 1; - continue; - - case 'M': - find_match_limit = 1; - continue; - - case 'N': - options |= PCRE_NOTEMPTY; - continue; - - case 'O': - while(isdigit(*p)) n = n * 10 + *p++ - '0'; - if (n > size_offsets_max) - { - size_offsets_max = n; - free(offsets); - use_offsets = offsets = (int *)malloc(size_offsets_max * sizeof(int)); - if (offsets == NULL) - { - printf("** Failed to get %d bytes of memory for offsets vector\n", - (int)(size_offsets_max * sizeof(int))); - yield = 1; - goto EXIT; - } - } - use_size_offsets = n; - if (n == 0) use_offsets = NULL; /* Ensures it can't write to it */ - continue; - - case 'P': - options |= PCRE_PARTIAL; - continue; - - case 'Q': - while(isdigit(*p)) n = n * 10 + *p++ - '0'; - if (extra == NULL) - { - extra = (pcre_extra *)malloc(sizeof(pcre_extra)); - extra->flags = 0; - } - extra->flags |= PCRE_EXTRA_MATCH_LIMIT_RECURSION; - extra->match_limit_recursion = n; - continue; - - case 'q': - while(isdigit(*p)) n = n * 10 + *p++ - '0'; - if (extra == NULL) - { - extra = (pcre_extra *)malloc(sizeof(pcre_extra)); - extra->flags = 0; - } - extra->flags |= PCRE_EXTRA_MATCH_LIMIT; - extra->match_limit = n; - continue; - -#if !defined NODFA - case 'R': - options |= PCRE_DFA_RESTART; - continue; -#endif - - case 'S': - show_malloc = 1; - continue; - - case 'Y': - options |= PCRE_NO_START_OPTIMIZE; - continue; - - case 'Z': - options |= PCRE_NOTEOL; - continue; - - case '?': - options |= PCRE_NO_UTF8_CHECK; - continue; - - case '<': - { - int x = check_newline(p, outfile); - if (x == 0) goto NEXT_DATA; - options |= x; - while (*p++ != '>'); - } - continue; - } - *q++ = c; - } - *q = 0; - len = q - dbuffer; - - /* Move the data to the end of the buffer so that a read over the end of - the buffer will be seen by valgrind, even if it doesn't cause a crash. If - we are using the POSIX interface, we must include the terminating zero. */ - -#if !defined NOPOSIX - if (posix || do_posix) - { - memmove(bptr + buffer_size - len - 1, bptr, len + 1); - bptr += buffer_size - len - 1; - } - else -#endif - { - memmove(bptr + buffer_size - len, bptr, len); - bptr += buffer_size - len; - } - - if ((all_use_dfa || use_dfa) && find_match_limit) - { - printf("**Match limit not relevant for DFA matching: ignored\n"); - find_match_limit = 0; - } - - /* Handle matching via the POSIX interface, which does not - support timing or playing with the match limit or callout data. */ - -#if !defined NOPOSIX - if (posix || do_posix) - { - int rc; - int eflags = 0; - regmatch_t *pmatch = NULL; - if (use_size_offsets > 0) - pmatch = (regmatch_t *)malloc(sizeof(regmatch_t) * use_size_offsets); - if ((options & PCRE_NOTBOL) != 0) eflags |= REG_NOTBOL; - if ((options & PCRE_NOTEOL) != 0) eflags |= REG_NOTEOL; - if ((options & PCRE_NOTEMPTY) != 0) eflags |= REG_NOTEMPTY; - - rc = regexec(&preg, (const char *)bptr, use_size_offsets, pmatch, eflags); - - if (rc != 0) - { - (void)regerror(rc, &preg, (char *)buffer, buffer_size); - fprintf(outfile, "No match: POSIX code %d: %s\n", rc, buffer); - } - else if ((((const pcre *)preg.re_pcre)->options & PCRE_NO_AUTO_CAPTURE) - != 0) - { - fprintf(outfile, "Matched with REG_NOSUB\n"); - } - else - { - size_t i; - for (i = 0; i < (size_t)use_size_offsets; i++) - { - if (pmatch[i].rm_so >= 0) - { - fprintf(outfile, "%2d: ", (int)i); - (void)pchars(dbuffer + pmatch[i].rm_so, - pmatch[i].rm_eo - pmatch[i].rm_so, outfile); - fprintf(outfile, "\n"); - if (i == 0 && do_showrest) - { - fprintf(outfile, " 0+ "); - (void)pchars(dbuffer + pmatch[i].rm_eo, len - pmatch[i].rm_eo, - outfile); - fprintf(outfile, "\n"); - } - } - } - } - free(pmatch); - } - - /* Handle matching via the native interface - repeats for /g and /G */ - - else -#endif /* !defined NOPOSIX */ - - for (;; gmatched++) /* Loop for /g or /G */ - { - if (timeitm > 0) - { - register int i; - clock_t time_taken; - clock_t start_time = clock(); - -#if !defined NODFA - if (all_use_dfa || use_dfa) - { - int workspace[1000]; - for (i = 0; i < timeitm; i++) - count = pcre_dfa_exec(re, NULL, (char *)bptr, len, start_offset, - options | g_notempty, use_offsets, use_size_offsets, workspace, - sizeof(workspace)/sizeof(int)); - } - else -#endif - - for (i = 0; i < timeitm; i++) - count = pcre_exec(re, extra, (char *)bptr, len, - start_offset, options | g_notempty, use_offsets, use_size_offsets); - - time_taken = clock() - start_time; - fprintf(outfile, "Execute time %.4f milliseconds\n", - (((double)time_taken * 1000.0) / (double)timeitm) / - (double)CLOCKS_PER_SEC); - } - - /* If find_match_limit is set, we want to do repeated matches with - varying limits in order to find the minimum value for the match limit and - for the recursion limit. */ - - if (find_match_limit) - { - if (extra == NULL) - { - extra = (pcre_extra *)malloc(sizeof(pcre_extra)); - extra->flags = 0; - } - - (void)check_match_limit(re, extra, bptr, len, start_offset, - options|g_notempty, use_offsets, use_size_offsets, - PCRE_EXTRA_MATCH_LIMIT, &(extra->match_limit), - PCRE_ERROR_MATCHLIMIT, "match()"); - - count = check_match_limit(re, extra, bptr, len, start_offset, - options|g_notempty, use_offsets, use_size_offsets, - PCRE_EXTRA_MATCH_LIMIT_RECURSION, &(extra->match_limit_recursion), - PCRE_ERROR_RECURSIONLIMIT, "match() recursion"); - } - - /* If callout_data is set, use the interface with additional data */ - - else if (callout_data_set) - { - if (extra == NULL) - { - extra = (pcre_extra *)malloc(sizeof(pcre_extra)); - extra->flags = 0; - } - extra->flags |= PCRE_EXTRA_CALLOUT_DATA; - extra->callout_data = &callout_data; - count = pcre_exec(re, extra, (char *)bptr, len, start_offset, - options | g_notempty, use_offsets, use_size_offsets); - extra->flags &= ~PCRE_EXTRA_CALLOUT_DATA; - } - - /* The normal case is just to do the match once, with the default - value of match_limit. */ - -#if !defined NODFA - else if (all_use_dfa || use_dfa) - { - int workspace[1000]; - count = pcre_dfa_exec(re, NULL, (char *)bptr, len, start_offset, - options | g_notempty, use_offsets, use_size_offsets, workspace, - sizeof(workspace)/sizeof(int)); - if (count == 0) - { - fprintf(outfile, "Matched, but too many subsidiary matches\n"); - count = use_size_offsets/2; - } - } -#endif - - else - { - count = pcre_exec(re, extra, (char *)bptr, len, - start_offset, options | g_notempty, use_offsets, use_size_offsets); - if (count == 0) - { - fprintf(outfile, "Matched, but too many substrings\n"); - count = use_size_offsets/3; - } - } - - /* Matched */ - - if (count >= 0) - { - int i, maxcount; - -#if !defined NODFA - if (all_use_dfa || use_dfa) maxcount = use_size_offsets/2; else -#endif - maxcount = use_size_offsets/3; - - /* This is a check against a lunatic return value. */ - - if (count > maxcount) - { - fprintf(outfile, - "** PCRE error: returned count %d is too big for offset size %d\n", - count, use_size_offsets); - count = use_size_offsets/3; - if (do_g || do_G) - { - fprintf(outfile, "** /%c loop abandoned\n", do_g? 'g' : 'G'); - do_g = do_G = FALSE; /* Break g/G loop */ - } - } - - for (i = 0; i < count * 2; i += 2) - { - if (use_offsets[i] < 0) - fprintf(outfile, "%2d: \n", i/2); - else - { - fprintf(outfile, "%2d: ", i/2); - (void)pchars(bptr + use_offsets[i], - use_offsets[i+1] - use_offsets[i], outfile); - fprintf(outfile, "\n"); - if (i == 0) - { - if (do_showrest) - { - fprintf(outfile, " 0+ "); - (void)pchars(bptr + use_offsets[i+1], len - use_offsets[i+1], - outfile); - fprintf(outfile, "\n"); - } - } - } - } - - for (i = 0; i < 32; i++) - { - if ((copystrings & (1 << i)) != 0) - { - char copybuffer[256]; - int rc = pcre_copy_substring((char *)bptr, use_offsets, count, - i, copybuffer, sizeof(copybuffer)); - if (rc < 0) - fprintf(outfile, "copy substring %d failed %d\n", i, rc); - else - fprintf(outfile, "%2dC %s (%d)\n", i, copybuffer, rc); - } - } - - for (copynamesptr = copynames; - *copynamesptr != 0; - copynamesptr += (int)strlen((char*)copynamesptr) + 1) - { - char copybuffer[256]; - int rc = pcre_copy_named_substring(re, (char *)bptr, use_offsets, - count, (char *)copynamesptr, copybuffer, sizeof(copybuffer)); - if (rc < 0) - fprintf(outfile, "copy substring %s failed %d\n", copynamesptr, rc); - else - fprintf(outfile, " C %s (%d) %s\n", copybuffer, rc, copynamesptr); - } - - for (i = 0; i < 32; i++) - { - if ((getstrings & (1 << i)) != 0) - { - const char *substring; - int rc = pcre_get_substring((char *)bptr, use_offsets, count, - i, &substring); - if (rc < 0) - fprintf(outfile, "get substring %d failed %d\n", i, rc); - else - { - fprintf(outfile, "%2dG %s (%d)\n", i, substring, rc); - pcre_free_substring(substring); - } - } - } - - for (getnamesptr = getnames; - *getnamesptr != 0; - getnamesptr += (int)strlen((char*)getnamesptr) + 1) - { - const char *substring; - int rc = pcre_get_named_substring(re, (char *)bptr, use_offsets, - count, (char *)getnamesptr, &substring); - if (rc < 0) - fprintf(outfile, "copy substring %s failed %d\n", getnamesptr, rc); - else - { - fprintf(outfile, " G %s (%d) %s\n", substring, rc, getnamesptr); - pcre_free_substring(substring); - } - } - - if (getlist) - { - const char **stringlist; - int rc = pcre_get_substring_list((char *)bptr, use_offsets, count, - &stringlist); - if (rc < 0) - fprintf(outfile, "get substring list failed %d\n", rc); - else - { - for (i = 0; i < count; i++) - fprintf(outfile, "%2dL %s\n", i, stringlist[i]); - if (stringlist[i] != NULL) - fprintf(outfile, "string list not terminated by NULL\n"); - /* free((void *)stringlist); */ - pcre_free_substring_list(stringlist); - } - } - } - - /* There was a partial match */ - - else if (count == PCRE_ERROR_PARTIAL) - { - fprintf(outfile, "Partial match"); -#if !defined NODFA - if ((all_use_dfa || use_dfa) && use_size_offsets > 2) - fprintf(outfile, ": %.*s", use_offsets[1] - use_offsets[0], - bptr + use_offsets[0]); -#endif - fprintf(outfile, "\n"); - break; /* Out of the /g loop */ - } - - /* Failed to match. If this is a /g or /G loop and we previously set - g_notempty after a null match, this is not necessarily the end. We want - to advance the start offset, and continue. We won't be at the end of the - string - that was checked before setting g_notempty. - - Complication arises in the case when the newline option is "any" or - "anycrlf". If the previous match was at the end of a line terminated by - CRLF, an advance of one character just passes the \r, whereas we should - prefer the longer newline sequence, as does the code in pcre_exec(). - Fudge the offset value to achieve this. - - Otherwise, in the case of UTF-8 matching, the advance must be one - character, not one byte. */ - - else - { - if (g_notempty != 0) - { - int onechar = 1; - unsigned int obits = ((real_pcre *)re)->options; - use_offsets[0] = start_offset; - if ((obits & PCRE_NEWLINE_BITS) == 0) - { - int d; - (void)pcre_config(PCRE_CONFIG_NEWLINE, &d); - /* Note that these values are always the ASCII ones, even in - EBCDIC environments. CR = 13, NL = 10. */ - obits = (d == 13)? PCRE_NEWLINE_CR : - (d == 10)? PCRE_NEWLINE_LF : - (d == (13<<8 | 10))? PCRE_NEWLINE_CRLF : - (d == -2)? PCRE_NEWLINE_ANYCRLF : - (d == -1)? PCRE_NEWLINE_ANY : 0; - } - if (((obits & PCRE_NEWLINE_BITS) == PCRE_NEWLINE_ANY || - (obits & PCRE_NEWLINE_BITS) == PCRE_NEWLINE_ANYCRLF) - && - start_offset < len - 1 && - bptr[start_offset] == '\r' && - bptr[start_offset+1] == '\n') - onechar++; - else if (use_utf8) - { - while (start_offset + onechar < len) - { - int tb = bptr[start_offset+onechar]; - if (tb <= 127) break; - tb &= 0xc0; - if (tb != 0 && tb != 0xc0) onechar++; - } - } - use_offsets[1] = start_offset + onechar; - } - else - { - if (count == PCRE_ERROR_NOMATCH) - { - if (gmatched == 0) fprintf(outfile, "No match\n"); - } - else fprintf(outfile, "Error %d\n", count); - break; /* Out of the /g loop */ - } - } - - /* If not /g or /G we are done */ - - if (!do_g && !do_G) break; - - /* If we have matched an empty string, first check to see if we are at - the end of the subject. If so, the /g loop is over. Otherwise, mimic - what Perl's /g options does. This turns out to be rather cunning. First - we set PCRE_NOTEMPTY and PCRE_ANCHORED and try the match again at the - same point. If this fails (picked up above) we advance to the next - character. */ - - g_notempty = 0; - - if (use_offsets[0] == use_offsets[1]) - { - if (use_offsets[0] == len) break; - g_notempty = PCRE_NOTEMPTY | PCRE_ANCHORED; - } - - /* For /g, update the start offset, leaving the rest alone */ - - if (do_g) start_offset = use_offsets[1]; - - /* For /G, update the pointer and length */ - - else - { - bptr += use_offsets[1]; - len -= use_offsets[1]; - } - } /* End of loop for /g and /G */ - - NEXT_DATA: continue; - } /* End of loop for data lines */ - - CONTINUE: - -#if !defined NOPOSIX - if (posix || do_posix) regfree(&preg); -#endif - - if (re != NULL) new_free(re); - if (extra != NULL) new_free(extra); - if (tables != NULL) - { - new_free((void *)tables); - setlocale(LC_CTYPE, "C"); - locale_set = 0; - } - } - -if (infile == stdin) fprintf(outfile, "\n"); - -EXIT: - -if (infile != NULL && infile != stdin) fclose(infile); -if (outfile != NULL && outfile != stdout) fclose(outfile); - -free(buffer); -free(dbuffer); -free(pbuffer); -free(offsets); - -return yield; -} - -/* End of pcretest.c */ diff --git a/libs/pcre/perltest b/libs/pcre/perltest deleted file mode 100755 index 9f511656a5..0000000000 --- a/libs/pcre/perltest +++ /dev/null @@ -1,191 +0,0 @@ -#! /usr/bin/perl - -# Program for testing regular expressions with perl to check that PCRE handles -# them the same. This is the version that supports /8 for UTF-8 testing. As it -# stands, it requires at least Perl 5.8 for UTF-8 support. However, it needs to -# have "use utf8" at the start for running the UTF-8 tests, but *not* for the -# other tests. The only way I've found for doing this is to cat this line in -# explicitly in the RunPerlTest script. - -# use locale; # With this included, \x0b matches \s! - -# Function for turning a string into a string of printing chars. There are -# currently problems with UTF-8 strings; this fudges round them. - -sub pchars { -my($t) = ""; - -if ($utf8) - { - @p = unpack('U*', $_[0]); - foreach $c (@p) - { - if ($c >= 32 && $c < 127) { $t .= chr $c; } - else { $t .= sprintf("\\x{%02x}", $c); } - } - } - -else - { - foreach $c (split(//, $_[0])) - { - if (ord $c >= 32 && ord $c < 127) { $t .= $c; } - else { $t .= sprintf("\\x%02x", ord $c); } - } - } - -$t; -} - - -# Read lines from named file or stdin and write to named file or stdout; lines -# consist of a regular expression, in delimiters and optionally followed by -# options, followed by a set of test data, terminated by an empty line. - -# Sort out the input and output files - -if (@ARGV > 0) - { - open(INFILE, "<$ARGV[0]") || die "Failed to open $ARGV[0]\n"; - $infile = "INFILE"; - } -else { $infile = "STDIN"; } - -if (@ARGV > 1) - { - open(OUTFILE, ">$ARGV[1]") || die "Failed to open $ARGV[1]\n"; - $outfile = "OUTFILE"; - } -else { $outfile = "STDOUT"; } - -printf($outfile "Perl $] Regular Expressions\n\n"); - -# Main loop - -NEXT_RE: -for (;;) - { - printf " re> " if $infile eq "STDIN"; - last if ! ($_ = <$infile>); - printf $outfile "$_" if $infile ne "STDIN"; - next if ($_ eq ""); - - $pattern = $_; - - while ($pattern !~ /^\s*(.).*\1/s) - { - printf " > " if $infile eq "STDIN"; - last if ! ($_ = <$infile>); - printf $outfile "$_" if $infile ne "STDIN"; - $pattern .= $_; - } - - chomp($pattern); - $pattern =~ s/\s+$//; - - # The private /+ modifier means "print $' afterwards". - - $showrest = ($pattern =~ s/\+(?=[a-z]*$)//); - - # Remove /8 from a UTF-8 pattern. - - $utf8 = $pattern =~ s/8(?=[a-z]*$)//; - - # Check that the pattern is valid - - eval "\$_ =~ ${pattern}"; - if ($@) - { - printf $outfile "Error: $@"; - next NEXT_RE; - } - - # If the /g modifier is present, we want to put a loop round the matching; - # otherwise just a single "if". - - $cmd = ($pattern =~ /g[a-z]*$/)? "while" : "if"; - - # If the pattern is actually the null string, Perl uses the most recently - # executed (and successfully compiled) regex is used instead. This is a - # nasty trap for the unwary! The PCRE test suite does contain null strings - # in places - if they are allowed through here all sorts of weird and - # unexpected effects happen. To avoid this, we replace such patterns with - # a non-null pattern that has the same effect. - - $pattern = "/(?#)/$2" if ($pattern =~ /^(.)\1(.*)$/); - - # Read data lines and test them - - for (;;) - { - printf "data> " if $infile eq "STDIN"; - last NEXT_RE if ! ($_ = <$infile>); - chomp; - printf $outfile "$_\n" if $infile ne "STDIN"; - - s/\s+$//; - s/^\s+//; - - last if ($_ eq ""); - $x = eval "\"$_\""; # To get escapes processed - - # Empty array for holding results, then do the matching. - - @subs = (); - - $pushes = "push \@subs,\$&;" . - "push \@subs,\$1;" . - "push \@subs,\$2;" . - "push \@subs,\$3;" . - "push \@subs,\$4;" . - "push \@subs,\$5;" . - "push \@subs,\$6;" . - "push \@subs,\$7;" . - "push \@subs,\$8;" . - "push \@subs,\$9;" . - "push \@subs,\$10;" . - "push \@subs,\$11;" . - "push \@subs,\$12;" . - "push \@subs,\$13;" . - "push \@subs,\$14;" . - "push \@subs,\$15;" . - "push \@subs,\$16;" . - "push \@subs,\$'; }"; - - eval "${cmd} (\$x =~ ${pattern}) {" . $pushes; - - if ($@) - { - printf $outfile "Error: $@\n"; - next NEXT_RE; - } - elsif (scalar(@subs) == 0) - { - printf $outfile "No match\n"; - } - else - { - while (scalar(@subs) != 0) - { - printf $outfile (" 0: %s\n", &pchars($subs[0])); - printf $outfile (" 0+ %s\n", &pchars($subs[17])) if $showrest; - $last_printed = 0; - for ($i = 1; $i <= 16; $i++) - { - if (defined $subs[$i]) - { - while ($last_printed++ < $i-1) - { printf $outfile ("%2d: \n", $last_printed); } - printf $outfile ("%2d: %s\n", $i, &pchars($subs[$i])); - $last_printed = $i; - } - } - splice(@subs, 0, 18); - } - } - } - } - -# printf $outfile "\n"; - -# End diff --git a/libs/pcre/perltest.pl b/libs/pcre/perltest.pl deleted file mode 100755 index 0d290c127a..0000000000 --- a/libs/pcre/perltest.pl +++ /dev/null @@ -1,191 +0,0 @@ -#! /usr/bin/env perl - -# Program for testing regular expressions with perl to check that PCRE handles -# them the same. This is the version that supports /8 for UTF-8 testing. As it -# stands, it requires at least Perl 5.8 for UTF-8 support. However, it needs to -# have "use utf8" at the start for running the UTF-8 tests, but *not* for the -# other tests. The only way I've found for doing this is to cat this line in -# explicitly in the RunPerlTest script. - -# use locale; # With this included, \x0b matches \s! - -# Function for turning a string into a string of printing chars. There are -# currently problems with UTF-8 strings; this fudges round them. - -sub pchars { -my($t) = ""; - -if ($utf8) - { - @p = unpack('U*', $_[0]); - foreach $c (@p) - { - if ($c >= 32 && $c < 127) { $t .= chr $c; } - else { $t .= sprintf("\\x{%02x}", $c); } - } - } - -else - { - foreach $c (split(//, $_[0])) - { - if (ord $c >= 32 && ord $c < 127) { $t .= $c; } - else { $t .= sprintf("\\x%02x", ord $c); } - } - } - -$t; -} - - -# Read lines from named file or stdin and write to named file or stdout; lines -# consist of a regular expression, in delimiters and optionally followed by -# options, followed by a set of test data, terminated by an empty line. - -# Sort out the input and output files - -if (@ARGV > 0) - { - open(INFILE, "<$ARGV[0]") || die "Failed to open $ARGV[0]\n"; - $infile = "INFILE"; - } -else { $infile = "STDIN"; } - -if (@ARGV > 1) - { - open(OUTFILE, ">$ARGV[1]") || die "Failed to open $ARGV[1]\n"; - $outfile = "OUTFILE"; - } -else { $outfile = "STDOUT"; } - -printf($outfile "Perl $] Regular Expressions\n\n"); - -# Main loop - -NEXT_RE: -for (;;) - { - printf " re> " if $infile eq "STDIN"; - last if ! ($_ = <$infile>); - printf $outfile "$_" if $infile ne "STDIN"; - next if ($_ eq ""); - - $pattern = $_; - - while ($pattern !~ /^\s*(.).*\1/s) - { - printf " > " if $infile eq "STDIN"; - last if ! ($_ = <$infile>); - printf $outfile "$_" if $infile ne "STDIN"; - $pattern .= $_; - } - - chomp($pattern); - $pattern =~ s/\s+$//; - - # The private /+ modifier means "print $' afterwards". - - $showrest = ($pattern =~ s/\+(?=[a-z]*$)//); - - # Remove /8 from a UTF-8 pattern. - - $utf8 = $pattern =~ s/8(?=[a-z]*$)//; - - # Check that the pattern is valid - - eval "\$_ =~ ${pattern}"; - if ($@) - { - printf $outfile "Error: $@"; - next NEXT_RE; - } - - # If the /g modifier is present, we want to put a loop round the matching; - # otherwise just a single "if". - - $cmd = ($pattern =~ /g[a-z]*$/)? "while" : "if"; - - # If the pattern is actually the null string, Perl uses the most recently - # executed (and successfully compiled) regex is used instead. This is a - # nasty trap for the unwary! The PCRE test suite does contain null strings - # in places - if they are allowed through here all sorts of weird and - # unexpected effects happen. To avoid this, we replace such patterns with - # a non-null pattern that has the same effect. - - $pattern = "/(?#)/$2" if ($pattern =~ /^(.)\1(.*)$/); - - # Read data lines and test them - - for (;;) - { - printf "data> " if $infile eq "STDIN"; - last NEXT_RE if ! ($_ = <$infile>); - chomp; - printf $outfile "$_\n" if $infile ne "STDIN"; - - s/\s+$//; - s/^\s+//; - - last if ($_ eq ""); - $x = eval "\"$_\""; # To get escapes processed - - # Empty array for holding results, then do the matching. - - @subs = (); - - $pushes = "push \@subs,\$&;" . - "push \@subs,\$1;" . - "push \@subs,\$2;" . - "push \@subs,\$3;" . - "push \@subs,\$4;" . - "push \@subs,\$5;" . - "push \@subs,\$6;" . - "push \@subs,\$7;" . - "push \@subs,\$8;" . - "push \@subs,\$9;" . - "push \@subs,\$10;" . - "push \@subs,\$11;" . - "push \@subs,\$12;" . - "push \@subs,\$13;" . - "push \@subs,\$14;" . - "push \@subs,\$15;" . - "push \@subs,\$16;" . - "push \@subs,\$'; }"; - - eval "${cmd} (\$x =~ ${pattern}) {" . $pushes; - - if ($@) - { - printf $outfile "Error: $@\n"; - next NEXT_RE; - } - elsif (scalar(@subs) == 0) - { - printf $outfile "No match\n"; - } - else - { - while (scalar(@subs) != 0) - { - printf $outfile (" 0: %s\n", &pchars($subs[0])); - printf $outfile (" 0+ %s\n", &pchars($subs[17])) if $showrest; - $last_printed = 0; - for ($i = 1; $i <= 16; $i++) - { - if (defined $subs[$i]) - { - while ($last_printed++ < $i-1) - { printf $outfile ("%2d: \n", $last_printed); } - printf $outfile ("%2d: %s\n", $i, &pchars($subs[$i])); - $last_printed = $i; - } - } - splice(@subs, 0, 18); - } - } - } - } - -# printf $outfile "\n"; - -# End diff --git a/libs/pcre/testdata/grepinput b/libs/pcre/testdata/grepinput deleted file mode 100644 index ed33f86d4a..0000000000 --- a/libs/pcre/testdata/grepinput +++ /dev/null @@ -1,609 +0,0 @@ -This is a file of miscellaneous text that is used as test data for checking -that the pcregrep command is working correctly. The file must be more than 24K -long so that it needs more than a single read() call to process it. New -features should be added at the end, because some of the tests involve the -output of line numbers, and we don't want these to change. - -PATTERN at the start of a line. -In the middle of a line, PATTERN appears. - -This pattern is in lower case. - -Here follows a whole lot of stuff that makes the file over 24K long. - -------------------------------------------------------------------------------- -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. - -The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the -lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox -jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick -brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. -------------------------------------------------------------------------------- - -aaaaa0 -aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -bbbbbb -cccccccccccccccccccccccccccccccccccccccccc -aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -eeeee -aaaaa2 -ffffffffff - -This is a line before the binary zero. -This line contains a binary zero here >< for testing. -This is a line after the binary zero. - -ABOVE the elephant -ABOVE -ABOVE theatre -AB.VE -AB.VE the turtle - -PUT NEW DATA ABOVE THIS LINE. -============================= - -Check up on PATTERN near the end. -This is the last line of this file. diff --git a/libs/pcre/testdata/grepinput8 b/libs/pcre/testdata/grepinput8 deleted file mode 100644 index c4b8c440f2..0000000000 --- a/libs/pcre/testdata/grepinput8 +++ /dev/null @@ -1,11 +0,0 @@ -X one -X two X three X four X five -X six -X sevenÂ…X eight
X nine
X ten - -Before 111 -Before 222
Before 333Â…Match -After 111 -After 222
After 333 -And so on and so on -And so on and so on diff --git a/libs/pcre/testdata/grepinputv b/libs/pcre/testdata/grepinputv deleted file mode 100644 index d33d326b01..0000000000 --- a/libs/pcre/testdata/grepinputv +++ /dev/null @@ -1,4 +0,0 @@ -The quick brown -fox jumps -over the lazy dog. -This time it jumps and jumps and jumps. diff --git a/libs/pcre/testdata/grepinputx b/libs/pcre/testdata/grepinputx deleted file mode 100644 index 730cc8a0d0..0000000000 --- a/libs/pcre/testdata/grepinputx +++ /dev/null @@ -1,43 +0,0 @@ -This is a second file of input for the pcregrep tests. - -Here is the pattern again. - -Pattern -That time it was on a line by itself. - -To pat or not to pat, that is the question. - -complete pair -of lines - -That was a complete pair -of lines all by themselves. - -complete pair -of lines - -And there they were again, to check line numbers. - -one -two -three -four -five -six -seven -eight -nine -ten -eleven -twelve -thirteen -fourteen -fifteen -sixteen -seventeen -eighteen -nineteen -twenty - -This line contains pattern not on a line by itself. -This is the last line of this file. diff --git a/libs/pcre/testdata/greplist b/libs/pcre/testdata/greplist deleted file mode 100644 index 1434ae96f6..0000000000 --- a/libs/pcre/testdata/greplist +++ /dev/null @@ -1,7 +0,0 @@ -This is a file of patterns for testing the -f option. Don't include any blank -lines because they will match everything! This is no longer true, so have one. - -pattern -line by itself - -End of the list of patterns. diff --git a/libs/pcre/testdata/grepoutput b/libs/pcre/testdata/grepoutput deleted file mode 100644 index 882344e11f..0000000000 --- a/libs/pcre/testdata/grepoutput +++ /dev/null @@ -1,425 +0,0 @@ ----------------------------- Test 1 ------------------------------ -PATTERN at the start of a line. -In the middle of a line, PATTERN appears. -Check up on PATTERN near the end. ----------------------------- Test 2 ------------------------------ -PATTERN at the start of a line. ----------------------------- Test 3 ------------------------------ -7:PATTERN at the start of a line. -8:In the middle of a line, PATTERN appears. -10:This pattern is in lower case. -608:Check up on PATTERN near the end. ----------------------------- Test 4 ------------------------------ -4 ----------------------------- Test 5 ------------------------------ -./testdata/grepinput:7:PATTERN at the start of a line. -./testdata/grepinput:8:In the middle of a line, PATTERN appears. -./testdata/grepinput:10:This pattern is in lower case. -./testdata/grepinput:608:Check up on PATTERN near the end. -./testdata/grepinputx:3:Here is the pattern again. -./testdata/grepinputx:5:Pattern -./testdata/grepinputx:42:This line contains pattern not on a line by itself. ----------------------------- Test 6 ------------------------------ -7:PATTERN at the start of a line. -8:In the middle of a line, PATTERN appears. -10:This pattern is in lower case. -608:Check up on PATTERN near the end. -3:Here is the pattern again. -5:Pattern -42:This line contains pattern not on a line by itself. ----------------------------- Test 7 ------------------------------ -./testdata/grepinput -./testdata/grepinputx ----------------------------- Test 8 ------------------------------ -./testdata/grepinput ----------------------------- Test 9 ------------------------------ -RC=0 ----------------------------- Test 10 ----------------------------- -RC=1 ----------------------------- Test 11 ----------------------------- -1:This is a second file of input for the pcregrep tests. -2: -4: -5:Pattern -6:That time it was on a line by itself. -7: -8:To pat or not to pat, that is the question. -9: -10:complete pair -11:of lines -12: -13:That was a complete pair -14:of lines all by themselves. -15: -16:complete pair -17:of lines -18: -19:And there they were again, to check line numbers. -20: -21:one -22:two -23:three -24:four -25:five -26:six -27:seven -28:eight -29:nine -30:ten -31:eleven -32:twelve -33:thirteen -34:fourteen -35:fifteen -36:sixteen -37:seventeen -38:eighteen -39:nineteen -40:twenty -41: -43:This is the last line of this file. ----------------------------- Test 12 ----------------------------- -Pattern ----------------------------- Test 13 ----------------------------- -Here is the pattern again. -That time it was on a line by itself. -This line contains pattern not on a line by itself. ----------------------------- Test 14 ----------------------------- -./testdata/grepinputx:To pat or not to pat, that is the question. ----------------------------- Test 15 ----------------------------- -pcregrep: Error in command-line regex at offset 4: nothing to repeat ----------------------------- Test 16 ----------------------------- -pcregrep: Failed to open ./testdata/nonexistfile: No such file or directory ----------------------------- Test 17 ----------------------------- -features should be added at the end, because some of the tests involve the -output of line numbers, and we don't want these to change. ----------------------------- Test 18 ----------------------------- -4:features should be added at the end, because some of the tests involve the -output of line numbers, and we don't want these to change. -583:brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. -------------------------------------------------------------------------------- ----------------------------- Test 19 ----------------------------- -Pattern ----------------------------- Test 20 ----------------------------- -10:complete pair -of lines -16:complete pair -of lines ----------------------------- Test 21 ----------------------------- -24:four -25-five -26-six -27-seven --- -34:fourteen -35-fifteen -36-sixteen -37-seventeen ----------------------------- Test 22 ----------------------------- -21-one -22-two -23-three -24:four --- -31-eleven -32-twelve -33-thirteen -34:fourteen ----------------------------- Test 23 ----------------------------- -one -two -three -four -five -six -seven --- -eleven -twelve -thirteen -fourteen -fifteen -sixteen -seventeen ----------------------------- Test 24 ----------------------------- -four -five -six -seven -eight -nine -ten -eleven -twelve -thirteen -fourteen -fifteen -sixteen -seventeen -eighteen -nineteen -twenty - -This line contains pattern not on a line by itself. -This is the last line of this file. ----------------------------- Test 25 ----------------------------- -15- -16-complete pair -17-of lines -18- -19-And there they were again, to check line numbers. -20- -21-one -22-two -23-three -24:four -25-five -26-six -27-seven -28-eight -29-nine -30-ten -31-eleven -32-twelve -33-thirteen -34:fourteen ----------------------------- Test 26 ----------------------------- - -complete pair -of lines - -And there they were again, to check line numbers. - -one -two -three -four -five -six -seven -eight -nine -ten -eleven -twelve -thirteen -fourteen -fifteen -sixteen -seventeen -eighteen -nineteen -twenty - -This line contains pattern not on a line by itself. -This is the last line of this file. ----------------------------- Test 27 ----------------------------- -four -five -six -seven -eight -nine -ten -eleven -twelve -thirteen -fourteen -fifteen -sixteen -seventeen -eighteen -nineteen -twenty - -This line contains pattern not on a line by itself. -This is the last line of this file. ----------------------------- Test 28 ----------------------------- -14-of lines all by themselves. -15- -16-complete pair -17-of lines -18- -19-And there they were again, to check line numbers. -20- -21-one -22-two -23-three -24:four -25-five -26-six -27-seven -28-eight -29-nine -30-ten -31-eleven -32-twelve -33-thirteen -34:fourteen ----------------------------- Test 29 ----------------------------- -of lines all by themselves. - -complete pair -of lines - -And there they were again, to check line numbers. - -one -two -three -four -five -six -seven -eight -nine -ten -eleven -twelve -thirteen -fourteen -fifteen -sixteen -seventeen -eighteen -nineteen -twenty - -This line contains pattern not on a line by itself. -This is the last line of this file. ----------------------------- Test 30 ----------------------------- -./testdata/grepinput-4-features should be added at the end, because some of the tests involve the -./testdata/grepinput-5-output of line numbers, and we don't want these to change. -./testdata/grepinput-6- -./testdata/grepinput:7:PATTERN at the start of a line. -./testdata/grepinput:8:In the middle of a line, PATTERN appears. -./testdata/grepinput-9- -./testdata/grepinput:10:This pattern is in lower case. --- -./testdata/grepinput-605-PUT NEW DATA ABOVE THIS LINE. -./testdata/grepinput-606-============================= -./testdata/grepinput-607- -./testdata/grepinput:608:Check up on PATTERN near the end. --- -./testdata/grepinputx-1-This is a second file of input for the pcregrep tests. -./testdata/grepinputx-2- -./testdata/grepinputx:3:Here is the pattern again. -./testdata/grepinputx-4- -./testdata/grepinputx:5:Pattern --- -./testdata/grepinputx-39-nineteen -./testdata/grepinputx-40-twenty -./testdata/grepinputx-41- -./testdata/grepinputx:42:This line contains pattern not on a line by itself. ----------------------------- Test 31 ----------------------------- -./testdata/grepinput:7:PATTERN at the start of a line. -./testdata/grepinput:8:In the middle of a line, PATTERN appears. -./testdata/grepinput-9- -./testdata/grepinput:10:This pattern is in lower case. -./testdata/grepinput-11- -./testdata/grepinput-12-Here follows a whole lot of stuff that makes the file over 24K long. -./testdata/grepinput-13- --- -./testdata/grepinput:608:Check up on PATTERN near the end. -./testdata/grepinput-609-This is the last line of this file. --- -./testdata/grepinputx:3:Here is the pattern again. -./testdata/grepinputx-4- -./testdata/grepinputx:5:Pattern -./testdata/grepinputx-6-That time it was on a line by itself. -./testdata/grepinputx-7- -./testdata/grepinputx-8-To pat or not to pat, that is the question. --- -./testdata/grepinputx:42:This line contains pattern not on a line by itself. -./testdata/grepinputx-43-This is the last line of this file. ----------------------------- Test 32 ----------------------------- -./testdata/grepinputx ----------------------------- Test 33 ----------------------------- -pcregrep: Failed to open ./testdata/grepnonexist: No such file or directory -RC=2 ----------------------------- Test 34 ----------------------------- -RC=2 ----------------------------- Test 35 ----------------------------- -./testdata/grepinputx -RC=0 ----------------------------- Test 36 ----------------------------- -./testdata/grepinput8 -./testdata/grepinputx -RC=0 ----------------------------- Test 37 ----------------------------- -aaaaa0 -aaaaa2 -RC=0 -======== STDERR ======== -pcregrep: pcre_exec() error -8 while matching this text: -aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -pcregrep: error -8 means that a resource limit was exceeded -pcregrep: check your regex for nested unlimited loops -pcregrep: pcre_exec() error -8 while matching this text: -aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa ----------------------------- Test 38 ------------------------------ -This line contains a binary zero here >< for testing. ----------------------------- Test 39 ------------------------------ -This is a line before the binary zero. -This line contains a binary zero here >< for testing. ----------------------------- Test 40 ------------------------------ -This line contains a binary zero here >< for testing. -This is a line after the binary zero. ----------------------------- Test 41 ------------------------------ -before the binary zero -after the binary zero ----------------------------- Test 41 ------------------------------ -./testdata/grepinput:595:before the binary zero -./testdata/grepinput:597:after the binary zero ----------------------------- Test 42 ------------------------------ -595:before -595:zero -596:zero -597:after -597:zero ----------------------------- Test 43 ------------------------------ -595:before -595:zero -596:zero -597:zero ----------------------------- Test 44 ------------------------------ -10:pattern -595:binary -596:binary -597:binary ----------------------------- Test 45 ------------------------------ -pcregrep: Error in 2nd command-line regex at offset 9: missing ) ----------------------------- Test 46 ------------------------------ -AB.VE ----------------------------- Test 47 ------------------------------ -ABOVE the elephant -AB.VE -AB.VE the turtle ----------------------------- Test 48 ------------------------------ -ABOVE the elephant -AB.VE -AB.VE the turtle -PUT NEW DATA ABOVE THIS LINE. ----------------------------- Test 49 ------------------------------ ----------------------------- Test 50 ------------------------------ -over the lazy dog. -This time it jumps and jumps and jumps. ----------------------------- Test 51 ------------------------------ -fox jumps -This time it jumps and jumps and jumps. ----------------------------- Test 52 ------------------------------ -36972,6 -36990,4 -37024,4 -37066,5 -37083,4 ----------------------------- Test 53 ------------------------------ -595:15,6 -595:33,4 -596:28,4 -597:15,5 -597:32,4 ----------------------------- Test 54 ----------------------------- -Here is the pattern again. -That time it was on a line by itself. -This line contains pattern not on a line by itself. diff --git a/libs/pcre/testdata/grepoutput8 b/libs/pcre/testdata/grepoutput8 deleted file mode 100644 index 0a8b7ec7bf..0000000000 --- a/libs/pcre/testdata/grepoutput8 +++ /dev/null @@ -1,10 +0,0 @@ ----------------------------- Test U1 ------------------------------ -1:X one -2:X two 3:X three 4:X four 5:X five -6:X six -7:X sevenÂ…8:X eight
9:X nine
10:X ten ----------------------------- Test U2 ------------------------------ -12-Before 111 -13-Before 222
14-Before 333Â…15:Match -16-After 111 -17-After 222
18-After 333 diff --git a/libs/pcre/testdata/grepoutputN b/libs/pcre/testdata/grepoutputN deleted file mode 100644 index 1f9f8801e3..0000000000 --- a/libs/pcre/testdata/grepoutputN +++ /dev/null @@ -1,16 +0,0 @@ ----------------------------- Test N1 ------------------------------ -1:abc 2:def ---------------------------- Test N2 ------------------------------ -1:abc def -2:ghi -jkl---------------------------- Test N3 ------------------------------ -2:def 3: -ghi -jkl---------------------------- Test N4 ------------------------------ -2:ghi -jkl---------------------------- Test N5 ------------------------------ -1:abc 2:def -3:ghi -4:jkl---------------------------- Test N6 ------------------------------ -1:abc 2:def -3:ghi -4:jkl \ No newline at end of file diff --git a/libs/pcre/testdata/testinput1 b/libs/pcre/testdata/testinput1 deleted file mode 100644 index 8b0caa4cc9..0000000000 --- a/libs/pcre/testdata/testinput1 +++ /dev/null @@ -1,4067 +0,0 @@ -/the quick brown fox/ - the quick brown fox - The quick brown FOX - What do you know about the quick brown fox? - What do you know about THE QUICK BROWN FOX? - -/The quick brown fox/i - the quick brown fox - The quick brown FOX - What do you know about the quick brown fox? - What do you know about THE QUICK BROWN FOX? - -/abcd\t\n\r\f\a\e\071\x3b\$\\\?caxyz/ - abcd\t\n\r\f\a\e9;\$\\?caxyz - -/a*abc?xyz+pqr{3}ab{2,}xy{4,5}pq{0,6}AB{0,}zz/ - abxyzpqrrrabbxyyyypqAzz - abxyzpqrrrabbxyyyypqAzz - aabxyzpqrrrabbxyyyypqAzz - aaabxyzpqrrrabbxyyyypqAzz - aaaabxyzpqrrrabbxyyyypqAzz - abcxyzpqrrrabbxyyyypqAzz - aabcxyzpqrrrabbxyyyypqAzz - aaabcxyzpqrrrabbxyyyypAzz - aaabcxyzpqrrrabbxyyyypqAzz - aaabcxyzpqrrrabbxyyyypqqAzz - aaabcxyzpqrrrabbxyyyypqqqAzz - aaabcxyzpqrrrabbxyyyypqqqqAzz - aaabcxyzpqrrrabbxyyyypqqqqqAzz - aaabcxyzpqrrrabbxyyyypqqqqqqAzz - aaaabcxyzpqrrrabbxyyyypqAzz - abxyzzpqrrrabbxyyyypqAzz - aabxyzzzpqrrrabbxyyyypqAzz - aaabxyzzzzpqrrrabbxyyyypqAzz - aaaabxyzzzzpqrrrabbxyyyypqAzz - abcxyzzpqrrrabbxyyyypqAzz - aabcxyzzzpqrrrabbxyyyypqAzz - aaabcxyzzzzpqrrrabbxyyyypqAzz - aaaabcxyzzzzpqrrrabbxyyyypqAzz - aaaabcxyzzzzpqrrrabbbxyyyypqAzz - aaaabcxyzzzzpqrrrabbbxyyyyypqAzz - aaabcxyzpqrrrabbxyyyypABzz - aaabcxyzpqrrrabbxyyyypABBzz - >>>aaabxyzpqrrrabbxyyyypqAzz - >aaaabxyzpqrrrabbxyyyypqAzz - >>>>abcxyzpqrrrabbxyyyypqAzz - *** Failers - abxyzpqrrabbxyyyypqAzz - abxyzpqrrrrabbxyyyypqAzz - abxyzpqrrrabxyyyypqAzz - aaaabcxyzzzzpqrrrabbbxyyyyyypqAzz - aaaabcxyzzzzpqrrrabbbxyyypqAzz - aaabcxyzpqrrrabbxyyyypqqqqqqqAzz - -/^(abc){1,2}zz/ - abczz - abcabczz - *** Failers - zz - abcabcabczz - >>abczz - -/^(b+?|a){1,2}?c/ - bc - bbc - bbbc - bac - bbac - aac - abbbbbbbbbbbc - bbbbbbbbbbbac - *** Failers - aaac - abbbbbbbbbbbac - -/^(b+|a){1,2}c/ - bc - bbc - bbbc - bac - bbac - aac - abbbbbbbbbbbc - bbbbbbbbbbbac - *** Failers - aaac - abbbbbbbbbbbac - -/^(b+|a){1,2}?bc/ - bbc - -/^(b*|ba){1,2}?bc/ - babc - bbabc - bababc - *** Failers - bababbc - babababc - -/^(ba|b*){1,2}?bc/ - babc - bbabc - bababc - *** Failers - bababbc - babababc - -/^\ca\cA\c[\c{\c:/ - \x01\x01\e;z - -/^[ab\]cde]/ - athing - bthing - ]thing - cthing - dthing - ething - *** Failers - fthing - [thing - \\thing - -/^[]cde]/ - ]thing - cthing - dthing - ething - *** Failers - athing - fthing - -/^[^ab\]cde]/ - fthing - [thing - \\thing - *** Failers - athing - bthing - ]thing - cthing - dthing - ething - -/^[^]cde]/ - athing - fthing - *** Failers - ]thing - cthing - dthing - ething - -/^\/ - - -/^ÿ/ - ÿ - -/^[0-9]+$/ - 0 - 1 - 2 - 3 - 4 - 5 - 6 - 7 - 8 - 9 - 10 - 100 - *** Failers - abc - -/^.*nter/ - enter - inter - uponter - -/^xxx[0-9]+$/ - xxx0 - xxx1234 - *** Failers - xxx - -/^.+[0-9][0-9][0-9]$/ - x123 - xx123 - 123456 - *** Failers - 123 - x1234 - -/^.+?[0-9][0-9][0-9]$/ - x123 - xx123 - 123456 - *** Failers - 123 - x1234 - -/^([^!]+)!(.+)=apquxz\.ixr\.zzz\.ac\.uk$/ - abc!pqr=apquxz.ixr.zzz.ac.uk - *** Failers - !pqr=apquxz.ixr.zzz.ac.uk - abc!=apquxz.ixr.zzz.ac.uk - abc!pqr=apquxz:ixr.zzz.ac.uk - abc!pqr=apquxz.ixr.zzz.ac.ukk - -/:/ - Well, we need a colon: somewhere - *** Fail if we don't - -/([\da-f:]+)$/i - 0abc - abc - fed - E - :: - 5f03:12C0::932e - fed def - Any old stuff - *** Failers - 0zzz - gzzz - fed\x20 - Any old rubbish - -/^.*\.(\d{1,3})\.(\d{1,3})\.(\d{1,3})$/ - .1.2.3 - A.12.123.0 - *** Failers - .1.2.3333 - 1.2.3 - 1234.2.3 - -/^(\d+)\s+IN\s+SOA\s+(\S+)\s+(\S+)\s*\(\s*$/ - 1 IN SOA non-sp1 non-sp2( - 1 IN SOA non-sp1 non-sp2 ( - *** Failers - 1IN SOA non-sp1 non-sp2( - -/^[a-zA-Z\d][a-zA-Z\d\-]*(\.[a-zA-Z\d][a-zA-z\d\-]*)*\.$/ - a. - Z. - 2. - ab-c.pq-r. - sxk.zzz.ac.uk. - x-.y-. - *** Failers - -abc.peq. - -/^\*\.[a-z]([a-z\-\d]*[a-z\d]+)?(\.[a-z]([a-z\-\d]*[a-z\d]+)?)*$/ - *.a - *.b0-a - *.c3-b.c - *.c-a.b-c - *** Failers - *.0 - *.a- - *.a-b.c- - *.c-a.0-c - -/^(?=ab(de))(abd)(e)/ - abde - -/^(?!(ab)de|x)(abd)(f)/ - abdf - -/^(?=(ab(cd)))(ab)/ - abcd - -/^[\da-f](\.[\da-f])*$/i - a.b.c.d - A.B.C.D - a.b.c.1.2.3.C - -/^\".*\"\s*(;.*)?$/ - \"1234\" - \"abcd\" ; - \"\" ; rhubarb - *** Failers - \"1234\" : things - -/^$/ - \ - *** Failers - -/ ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/x - ab c - *** Failers - abc - ab cde - -/(?x) ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/ - ab c - *** Failers - abc - ab cde - -/^ a\ b[c ]d $/x - a bcd - a b d - *** Failers - abcd - ab d - -/^(a(b(c)))(d(e(f)))(h(i(j)))(k(l(m)))$/ - abcdefhijklm - -/^(?:a(b(c)))(?:d(e(f)))(?:h(i(j)))(?:k(l(m)))$/ - abcdefhijklm - -/^[\w][\W][\s][\S][\d][\D][\b][\n][\c]][\022]/ - a+ Z0+\x08\n\x1d\x12 - -/^[.^$|()*+?{,}]+/ - .^\$(*+)|{?,?} - -/^a*\w/ - z - az - aaaz - a - aa - aaaa - a+ - aa+ - -/^a*?\w/ - z - az - aaaz - a - aa - aaaa - a+ - aa+ - -/^a+\w/ - az - aaaz - aa - aaaa - aa+ - -/^a+?\w/ - az - aaaz - aa - aaaa - aa+ - -/^\d{8}\w{2,}/ - 1234567890 - 12345678ab - 12345678__ - *** Failers - 1234567 - -/^[aeiou\d]{4,5}$/ - uoie - 1234 - 12345 - aaaaa - *** Failers - 123456 - -/^[aeiou\d]{4,5}?/ - uoie - 1234 - 12345 - aaaaa - 123456 - -/\A(abc|def)=(\1){2,3}\Z/ - abc=abcabc - def=defdefdef - *** Failers - abc=defdef - -/^(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)\11*(\3\4)\1(?#)2$/ - abcdefghijkcda2 - abcdefghijkkkkcda2 - -/(cat(a(ract|tonic)|erpillar)) \1()2(3)/ - cataract cataract23 - catatonic catatonic23 - caterpillar caterpillar23 - - -/^From +([^ ]+) +[a-zA-Z][a-zA-Z][a-zA-Z] +[a-zA-Z][a-zA-Z][a-zA-Z] +[0-9]?[0-9] +[0-9][0-9]:[0-9][0-9]/ - From abcd Mon Sep 01 12:33:02 1997 - -/^From\s+\S+\s+([a-zA-Z]{3}\s+){2}\d{1,2}\s+\d\d:\d\d/ - From abcd Mon Sep 01 12:33:02 1997 - From abcd Mon Sep 1 12:33:02 1997 - *** Failers - From abcd Sep 01 12:33:02 1997 - -/^12.34/s - 12\n34 - 12\r34 - -/\w+(?=\t)/ - the quick brown\t fox - -/foo(?!bar)(.*)/ - foobar is foolish see? - -/(?:(?!foo)...|^.{0,2})bar(.*)/ - foobar crowbar etc - barrel - 2barrel - A barrel - -/^(\D*)(?=\d)(?!123)/ - abc456 - *** Failers - abc123 - -/^1234(?# test newlines - inside)/ - 1234 - -/^1234 #comment in extended re - /x - 1234 - -/#rhubarb - abcd/x - abcd - -/^abcd#rhubarb/x - abcd - -/^(a)\1{2,3}(.)/ - aaab - aaaab - aaaaab - aaaaaab - -/(?!^)abc/ - the abc - *** Failers - abc - -/(?=^)abc/ - abc - *** Failers - the abc - -/^[ab]{1,3}(ab*|b)/ - aabbbbb - -/^[ab]{1,3}?(ab*|b)/ - aabbbbb - -/^[ab]{1,3}?(ab*?|b)/ - aabbbbb - -/^[ab]{1,3}(ab*?|b)/ - aabbbbb - -/ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* # optional leading comment -(?: (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) # initial word -(?: (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) )* # further okay, if led by a period -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* -# address -| # or -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) # one word, optionally followed by.... -(?: -[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] | # atom and space parts, or... -\( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) | # comments, or... - -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -# quoted strings -)* -< (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* # leading < -(?: @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* - -(?: (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* , (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* -)* # further okay, if led by comma -: # closing colon -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* )? # optional route -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) # initial word -(?: (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) )* # further okay, if led by a period -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* -# address spec -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* > # trailing > -# name and address -) (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* # optional trailing comment -/x - Alan Other - - user\@dom.ain - \"A. Other\" (a comment) - A. Other (a comment) - \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay - A missing angle @,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# additional words -)* -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -# address -| # or -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -# leading word -[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] * # "normal" atoms and or spaces -(?: -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -| -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -) # "special" comment or quoted string -[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] * # more "normal" -)* -< -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# < -(?: -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -(?: , -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -)* # additional domains -: -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)? # optional route -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# additional words -)* -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -# address spec -> # > -# name and address -) -/x - Alan Other - - user\@dom.ain - \"A. Other\" (a comment) - A. Other (a comment) - \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay - A missing angle ]{0,})>]{0,})>([\d]{0,}\.)(.*)((
([\w\W\s\d][^<>]{0,})|[\s]{0,}))<\/a><\/TD>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><\/TR>/is - 43.Word Processor
(N-1286)Lega lstaff.comCA - Statewide - -/a[^a]b/ - acb - a\nb - -/a.b/ - acb - *** Failers - a\nb - -/a[^a]b/s - acb - a\nb - -/a.b/s - acb - a\nb - -/^(b+?|a){1,2}?c/ - bac - bbac - bbbac - bbbbac - bbbbbac - -/^(b+|a){1,2}?c/ - bac - bbac - bbbac - bbbbac - bbbbbac - -/(?!\A)x/m - x\nb\n - a\bx\n - -/\x0{ab}/ - \0{ab} - -/(A|B)*?CD/ - CD - -/(A|B)*CD/ - CD - -/(AB)*?\1/ - ABABAB - -/(AB)*\1/ - ABABAB - -/(?.*/)foo" - /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/it/you/see/ - -"(?>.*/)foo" - /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo - -/(?>(\.\d\d[1-9]?))\d+/ - 1.230003938 - 1.875000282 - *** Failers - 1.235 - -/^((?>\w+)|(?>\s+))*$/ - now is the time for all good men to come to the aid of the party - *** Failers - this is not a line with only words and spaces! - -/(\d+)(\w)/ - 12345a - 12345+ - -/((?>\d+))(\w)/ - 12345a - *** Failers - 12345+ - -/(?>a+)b/ - aaab - -/((?>a+)b)/ - aaab - -/(?>(a+))b/ - aaab - -/(?>b)+/ - aaabbbccc - -/(?>a+|b+|c+)*c/ - aaabbbbccccd - -/((?>[^()]+)|\([^()]*\))+/ - ((abc(ade)ufh()()x - -/\(((?>[^()]+)|\([^()]+\))+\)/ - (abc) - (abc(def)xyz) - *** Failers - ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - -/a(?-i)b/i - ab - Ab - *** Failers - aB - AB - -/(a (?x)b c)d e/ - a bcd e - *** Failers - a b cd e - abcd e - a bcde - -/(a b(?x)c d (?-x)e f)/ - a bcde f - *** Failers - abcdef - -/(a(?i)b)c/ - abc - aBc - *** Failers - abC - aBC - Abc - ABc - ABC - AbC - -/a(?i:b)c/ - abc - aBc - *** Failers - ABC - abC - aBC - -/a(?i:b)*c/ - aBc - aBBc - *** Failers - aBC - aBBC - -/a(?=b(?i)c)\w\wd/ - abcd - abCd - *** Failers - aBCd - abcD - -/(?s-i:more.*than).*million/i - more than million - more than MILLION - more \n than Million - *** Failers - MORE THAN MILLION - more \n than \n million - -/(?:(?s-i)more.*than).*million/i - more than million - more than MILLION - more \n than Million - *** Failers - MORE THAN MILLION - more \n than \n million - -/(?>a(?i)b+)+c/ - abc - aBbc - aBBc - *** Failers - Abc - abAb - abbC - -/(?=a(?i)b)\w\wc/ - abc - aBc - *** Failers - Ab - abC - aBC - -/(?<=a(?i)b)(\w\w)c/ - abxxc - aBxxc - *** Failers - Abxxc - ABxxc - abxxC - -/(?:(a)|b)(?(1)A|B)/ - aA - bB - *** Failers - aB - bA - -/^(a)?(?(1)a|b)+$/ - aa - b - bb - *** Failers - ab - -/^(?(?=abc)\w{3}:|\d\d)$/ - abc: - 12 - *** Failers - 123 - xyz - -/^(?(?!abc)\d\d|\w{3}:)$/ - abc: - 12 - *** Failers - 123 - xyz - -/(?(?<=foo)bar|cat)/ - foobar - cat - fcat - focat - *** Failers - foocat - -/(?(?a*)*/ - a - aa - aaaa - -/(abc|)+/ - abc - abcabc - abcabcabc - xyz - -/([a]*)*/ - a - aaaaa - -/([ab]*)*/ - a - b - ababab - aaaabcde - bbbb - -/([^a]*)*/ - b - bbbb - aaa - -/([^ab]*)*/ - cccc - abab - -/([a]*?)*/ - a - aaaa - -/([ab]*?)*/ - a - b - abab - baba - -/([^a]*?)*/ - b - bbbb - aaa - -/([^ab]*?)*/ - c - cccc - baba - -/(?>a*)*/ - a - aaabcde - -/((?>a*))*/ - aaaaa - aabbaa - -/((?>a*?))*/ - aaaaa - aabbaa - -/(?(?=[^a-z]+[a-z]) \d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} ) /x - 12-sep-98 - 12-09-98 - *** Failers - sep-12-98 - -/(?<=(foo))bar\1/ - foobarfoo - foobarfootling - *** Failers - foobar - barfoo - -/(?i:saturday|sunday)/ - saturday - sunday - Saturday - Sunday - SATURDAY - SUNDAY - SunDay - -/(a(?i)bc|BB)x/ - abcx - aBCx - bbx - BBx - *** Failers - abcX - aBCX - bbX - BBX - -/^([ab](?i)[cd]|[ef])/ - ac - aC - bD - elephant - Europe - frog - France - *** Failers - Africa - -/^(ab|a(?i)[b-c](?m-i)d|x(?i)y|z)/ - ab - aBd - xy - xY - zebra - Zambesi - *** Failers - aCD - XY - -/(?<=foo\n)^bar/m - foo\nbar - *** Failers - bar - baz\nbar - -/(?<=(?]&/ - <&OUT - -/^(a\1?){4}$/ - aaaaaaaaaa - *** Failers - AB - aaaaaaaaa - aaaaaaaaaaa - -/^(a(?(1)\1)){4}$/ - aaaaaaaaaa - *** Failers - aaaaaaaaa - aaaaaaaaaaa - -/(?:(f)(o)(o)|(b)(a)(r))*/ - foobar - -/(?<=a)b/ - ab - *** Failers - cb - b - -/(?a+)ab/ - -/(?>a+)b/ - aaab - -/([[:]+)/ - a:[b]: - -/([[=]+)/ - a=[b]= - -/([[.]+)/ - a.[b]. - -/((?>a+)b)/ - aaab - -/(?>(a+))b/ - aaab - -/((?>[^()]+)|\([^()]*\))+/ - ((abc(ade)ufh()()x - -/a\Z/ - *** Failers - aaab - a\nb\n - -/b\Z/ - a\nb\n - -/b\z/ - -/b\Z/ - a\nb - -/b\z/ - a\nb - *** Failers - -/^(?>(?(1)\.|())[^\W_](?>[a-z0-9-]*[^\W_])?)+$/ - a - abc - a-b - 0-9 - a.b - 5.6.7 - the.quick.brown.fox - a100.b200.300c - 12-ab.1245 - *** Failers - \ - .a - -a - a- - a. - a_b - a.- - a.. - ab..bc - the.quick.brown.fox- - the.quick.brown.fox. - the.quick.brown.fox_ - the.quick.brown.fox+ - -/(?>.*)(?<=(abcd|wxyz))/ - alphabetabcd - endingwxyz - *** Failers - a rather long string that doesn't end with one of them - -/word (?>(?:(?!otherword)[a-zA-Z0-9]+ ){0,30})otherword/ - word cat dog elephant mussel cow horse canary baboon snake shark otherword - word cat dog elephant mussel cow horse canary baboon snake shark - -/word (?>[a-zA-Z0-9]+ ){0,30}otherword/ - word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope - -/(?<=\d{3}(?!999))foo/ - 999foo - 123999foo - *** Failers - 123abcfoo - -/(?<=(?!...999)\d{3})foo/ - 999foo - 123999foo - *** Failers - 123abcfoo - -/(?<=\d{3}(?!999)...)foo/ - 123abcfoo - 123456foo - *** Failers - 123999foo - -/(?<=\d{3}...)(?\s*)=(?>\s*) # find Z)+|A)*/ - ZABCDEFG - -/((?>)+|A)*/ - ZABCDEFG - -/a*/g - abbab - -/^[a-\d]/ - abcde - -things - 0digit - *** Failers - bcdef - -/^[\d-a]/ - abcde - -things - 0digit - *** Failers - bcdef - -/[[:space:]]+/ - > \x09\x0a\x0c\x0d\x0b< - -/[[:blank:]]+/ - > \x09\x0a\x0c\x0d\x0b< - -/[\s]+/ - > \x09\x0a\x0c\x0d\x0b< - -/\s+/ - > \x09\x0a\x0c\x0d\x0b< - -/a b/x - ab - -/(?!\A)x/m - a\nxb\n - -/(?!^)x/m - a\nxb\n - -/abc\Qabc\Eabc/ - abcabcabc - -/abc\Q(*+|\Eabc/ - abc(*+|abc - -/ abc\Q abc\Eabc/x - abc abcabc - *** Failers - abcabcabc - -/abc#comment - \Q#not comment - literal\E/x - abc#not comment\n literal - -/abc#comment - \Q#not comment - literal/x - abc#not comment\n literal - -/abc#comment - \Q#not comment - literal\E #more comment - /x - abc#not comment\n literal - -/abc#comment - \Q#not comment - literal\E #more comment/x - abc#not comment\n literal - -/\Qabc\$xyz\E/ - abc\\\$xyz - -/\Qabc\E\$\Qxyz\E/ - abc\$xyz - -/\Gabc/ - abc - *** Failers - xyzabc - -/\Gabc./g - abc1abc2xyzabc3 - -/abc./g - abc1abc2xyzabc3 - -/a(?x: b c )d/ - XabcdY - *** Failers - Xa b c d Y - -/((?x)x y z | a b c)/ - XabcY - AxyzB - -/(?i)AB(?-i)C/ - XabCY - *** Failers - XabcY - -/((?i)AB(?-i)C|D)E/ - abCE - DE - *** Failers - abcE - abCe - dE - De - -/(.*)\d+\1/ - abc123abc - abc123bc - -/(.*)\d+\1/s - abc123abc - abc123bc - -/((.*))\d+\1/ - abc123abc - abc123bc - -/-- This tests for an IPv6 address in the form where it can have up to --/ -/-- eight components, one and only one of which is empty. This must be --/ -/-- an internal component. --/ - -/^(?!:) # colon disallowed at start - (?: # start of item - (?: [0-9a-f]{1,4} | # 1-4 hex digits or - (?(1)0 | () ) ) # if null previously matched, fail; else null - : # followed by colon - ){1,7} # end item; 1-7 of them required - [0-9a-f]{1,4} $ # final hex number at end of string - (?(1)|.) # check that there was an empty component - /xi - a123::a123 - a123:b342::abcd - a123:b342::324e:abcd - a123:ddde:b342::324e:abcd - a123:ddde:b342::324e:dcba:abcd - a123:ddde:9999:b342::324e:dcba:abcd - *** Failers - 1:2:3:4:5:6:7:8 - a123:bce:ddde:9999:b342::324e:dcba:abcd - a123::9999:b342::324e:dcba:abcd - abcde:2:3:4:5:6:7:8 - ::1 - abcd:fee0:123:: - :1 - 1: - -/[z\Qa-d]\E]/ - z - a - - - d - ] - *** Failers - b - -/[\z\C]/ - z - C - -/\M/ - M - -/(a+)*b/ - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - -/(?i)reg(?:ul(?:[aä]|ae)r|ex)/ - REGular - regulaer - Regex - regulär - -/Åæåä[à-ÿÀ-ß]+/ - Åæåäà - Åæåäÿ - ÅæåäÀ - Åæåäß - -/(?<=Z)X./ - \x84XAZXB - -/ab cd (?x) de fg/ - ab cd defg - -/ab cd(?x) de fg/ - ab cddefg - ** Failers - abcddefg - -/(?a|)*\d/ - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 - -/(?:a|)*\d/ - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 - -/\Z/g - abc\n - -/^(?s)(?>.*)(?iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|BM - -|\$\<\.X\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|BM - -/(a(?1)b)/BM - -/(a(?1)+b)/BM - -/a(?Pb|c)d(?Pe)/BM - -/(?:a(?Pc(?Pd)))(?Pa)/BM - -/(?Pa)...(?P=a)bbb(?P>a)d/BM - -/abc(?C255)de(?C)f/BM - -/abcde/CBM - -/\x{100}/8BM - -/\x{1000}/8BM - -/\x{10000}/8BM - -/\x{100000}/8BM - -/\x{1000000}/8BM - -/\x{4000000}/8BM - -/\x{7fffFFFF}/8BM - -/[\x{ff}]/8BM - -/[\x{100}]/8BM - -/\x80/8BM - -/\xff/8BM - -/\x{0041}\x{2262}\x{0391}\x{002e}/D8M - -/\x{D55c}\x{ad6d}\x{C5B4}/D8M - -/\x{65e5}\x{672c}\x{8a9e}/D8M - -/[\x{100}]/8BM - -/[Z\x{100}]/8BM - -/^[\x{100}\E-\Q\E\x{150}]/B8M - -/^[\QÄ€\E-\QÅ\E]/B8M - -/^[\QÄ€\E-\QÅ\E/B8M - -/[\p{L}]/BM - -/[\p{^L}]/BM - -/[\P{L}]/BM - -/[\P{^L}]/BM - -/[abc\p{L}\x{0660}]/8BM - -/[\p{Nd}]/8BM - -/[\p{Nd}+-]+/8BM - -/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8iBM - -/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8BM - -/[\x{105}-\x{109}]/8iBM - -/( ( (?(1)0|) )* )/xBM - -/( (?(1)0|)* )/xBM - -/[a]/BM - -/[a]/8BM - -/[\xaa]/BM - -/[\xaa]/8BM - -/[^a]/BM - -/[^a]/8BM - -/[^\xaa]/BM - -/[^\xaa]/8BM - -/ End of testinput10 / diff --git a/libs/pcre/testdata/testinput2 b/libs/pcre/testdata/testinput2 deleted file mode 100644 index beca157c6a..0000000000 --- a/libs/pcre/testdata/testinput2 +++ /dev/null @@ -1,2776 +0,0 @@ -/(a)b|/I - -/abc/I - abc - defabc - \Aabc - *** Failers - \Adefabc - ABC - -/^abc/I - abc - \Aabc - *** Failers - defabc - \Adefabc - -/a+bc/I - -/a*bc/I - -/a{3}bc/I - -/(abc|a+z)/I - -/^abc$/I - abc - *** Failers - def\nabc - -/ab\idef/X - -/(?X)ab\idef/X - -/x{5,4}/ - -/z{65536}/ - -/[abcd/ - -/(?X)[\B]/ - -/[z-a]/ - -/^*/ - -/(abc/ - -/(?# abc/ - -/(?z)abc/ - -/.*b/I - -/.*?b/I - -/cat|dog|elephant/I - this sentence eventually mentions a cat - this sentences rambles on and on for a while and then reaches elephant - -/cat|dog|elephant/IS - this sentence eventually mentions a cat - this sentences rambles on and on for a while and then reaches elephant - -/cat|dog|elephant/IiS - this sentence eventually mentions a CAT cat - this sentences rambles on and on for a while to elephant ElePhant - -/a|[bcd]/IS - -/(a|[^\dZ])/IS - -/(a|b)*[\s]/IS - -/(ab\2)/ - -/{4,5}abc/ - -/(a)(b)(c)\2/I - abcb - \O0abcb - \O3abcb - \O6abcb - \O9abcb - \O12abcb - -/(a)bc|(a)(b)\2/I - abc - \O0abc - \O3abc - \O6abc - aba - \O0aba - \O3aba - \O6aba - \O9aba - \O12aba - -/abc$/IE - abc - *** Failers - abc\n - abc\ndef - -/(a)(b)(c)(d)(e)\6/ - -/the quick brown fox/I - the quick brown fox - this is a line with the quick brown fox - -/the quick brown fox/IA - the quick brown fox - *** Failers - this is a line with the quick brown fox - -/ab(?z)cd/ - -/^abc|def/I - abcdef - abcdef\B - -/.*((abc)$|(def))/I - defabc - \Zdefabc - -/abc/IP - abc - *** Failers - -/^abc|def/IP - abcdef - abcdef\B - -/.*((abc)$|(def))/IP - defabc - \Zdefabc - -/the quick brown fox/IP - the quick brown fox - *** Failers - The Quick Brown Fox - -/the quick brown fox/IPi - the quick brown fox - The Quick Brown Fox - -/abc.def/IP - *** Failers - abc\ndef - -/abc$/IP - abc - abc\n - -/(abc)\2/IP - -/(abc\1)/IP - abc - -/)/ - -/a[]b/ - -/[^aeiou ]{3,}/I - co-processors, and for - -/<.*>/I - abcghinop - -/<.*?>/I - abcghinop - -/<.*>/IU - abcghinop - -/(?U)<.*>/I - abcghinop - -/<.*?>/IU - abcghinop - -/={3,}/IU - abc========def - -/(?U)={3,}?/I - abc========def - -/(?^abc)/Im - abc - def\nabc - *** Failers - defabc - -/(?<=ab(c+)d)ef/ - -/(?<=ab(?<=c+)d)ef/ - -/(?<=ab(c|de)f)g/ - -/The next three are in testinput2 because they have variable length branches/ - -/(?<=bullock|donkey)-cart/I - the bullock-cart - a donkey-cart race - *** Failers - cart - horse-and-cart - -/(?<=ab(?i)x|y|z)/I - -/(?>.*)(?<=(abcd)|(xyz))/I - alphabetabcd - endingxyz - -/(?<=ab(?i)x(?-i)y|(?i)z|b)ZZ/I - abxyZZ - abXyZZ - ZZZ - zZZ - bZZ - BZZ - *** Failers - ZZ - abXYZZ - zzz - bzz - -/(?[^()]+) # Either a sequence of non-brackets (no backtracking) - | # Or - (?R) # Recurse - i.e. nested bracketed string - )* # Zero or more contents - \) # Closing ) - /Ix - (abcd) - (abcd)xyz - xyz(abcd) - (ab(xy)cd)pqr - (ab(xycd)pqr - () abc () - 12(abcde(fsh)xyz(foo(bar))lmno)89 - *** Failers - abcd - abcd) - (abcd - -/\( ( (?>[^()]+) | (?R) )* \) /Ixg - (ab(xy)cd)pqr - 1(abcd)(x(y)z)pqr - -/\( (?: (?>[^()]+) | (?R) ) \) /Ix - (abcd) - (ab(xy)cd) - (a(b(c)d)e) - ((ab)) - *** Failers - () - -/\( (?: (?>[^()]+) | (?R) )? \) /Ix - () - 12(abcde(fsh)xyz(foo(bar))lmno)89 - -/\( ( (?>[^()]+) | (?R) )* \) /Ix - (ab(xy)cd) - -/\( ( ( (?>[^()]+) | (?R) )* ) \) /Ix - (ab(xy)cd) - -/\( (123)? ( ( (?>[^()]+) | (?R) )* ) \) /Ix - (ab(xy)cd) - (123ab(xy)cd) - -/\( ( (123)? ( (?>[^()]+) | (?R) )* ) \) /Ix - (ab(xy)cd) - (123ab(xy)cd) - -/\( (((((((((( ( (?>[^()]+) | (?R) )* )))))))))) \) /Ix - (ab(xy)cd) - -/\( ( ( (?>[^()<>]+) | ((?>[^()]+)) | (?R) )* ) \) /Ix - (abcd(xyz

qrs)123) - -/\( ( ( (?>[^()]+) | ((?R)) )* ) \) /Ix - (ab(cd)ef) - (ab(cd(ef)gh)ij) - -/^[[:alnum:]]/DZ - -/^[[:^alnum:]]/DZ - -/^[[:alpha:]]/DZ - -/^[[:^alpha:]]/DZ - -/[_[:alpha:]]/IS - -/^[[:ascii:]]/DZ - -/^[[:^ascii:]]/DZ - -/^[[:blank:]]/DZ - -/^[[:^blank:]]/DZ - -/[\n\x0b\x0c\x0d[:blank:]]/IS - -/^[[:cntrl:]]/DZ - -/^[[:digit:]]/DZ - -/^[[:graph:]]/DZ - -/^[[:lower:]]/DZ - -/^[[:print:]]/DZ - -/^[[:punct:]]/DZ - -/^[[:space:]]/DZ - -/^[[:upper:]]/DZ - -/^[[:xdigit:]]/DZ - -/^[[:word:]]/DZ - -/^[[:^cntrl:]]/DZ - -/^[12[:^digit:]]/DZ - -/^[[:^blank:]]/DZ - -/[01[:alpha:]%]/DZ - -/[[.ch.]]/I - -/[[=ch=]]/I - -/[[:rhubarb:]]/I - -/[[:upper:]]/Ii - A - a - -/[[:lower:]]/Ii - A - a - -/((?-i)[[:lower:]])[[:lower:]]/Ii - ab - aB - *** Failers - Ab - AB - -/[\200-\110]/I - -/^(?(0)f|b)oo/I - -/This one's here because of the large output vector needed/I - -/(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\w+)\s+(\270)/I - \O900 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 ABC ABC - -/This one's here because Perl does this differently and PCRE can't at present/I - -/(main(O)?)+/I - mainmain - mainOmain - -/These are all cases where Perl does it differently (nested captures)/I - -/^(a(b)?)+$/I - aba - -/^(aa(bb)?)+$/I - aabbaa - -/^(aa|aa(bb))+$/I - aabbaa - -/^(aa(bb)??)+$/I - aabbaa - -/^(?:aa(bb)?)+$/I - aabbaa - -/^(aa(b(b))?)+$/I - aabbaa - -/^(?:aa(b(b))?)+$/I - aabbaa - -/^(?:aa(b(?:b))?)+$/I - aabbaa - -/^(?:aa(bb(?:b))?)+$/I - aabbbaa - -/^(?:aa(b(?:bb))?)+$/I - aabbbaa - -/^(?:aa(?:b(b))?)+$/I - aabbaa - -/^(?:aa(?:b(bb))?)+$/I - aabbbaa - -/^(aa(b(bb))?)+$/I - aabbbaa - -/^(aa(bb(bb))?)+$/I - aabbbbaa - -/--------------------------------------------------------------------/I - -/#/IxDZ - -/a#/IxDZ - -/[\s]/DZ - -/[\S]/DZ - -/a(?i)b/DZ - ab - aB - *** Failers - AB - -/(a(?i)b)/DZ - ab - aB - *** Failers - AB - -/ (?i)abc/IxDZ - -/#this is a comment - (?i)abc/IxDZ - -/123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/DZ - -/\Q123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/DZ - -/\Q\E/DZ - \ - -/\Q\Ex/DZ - -/ \Q\E/DZ - -/a\Q\E/DZ - abc - bca - bac - -/a\Q\Eb/DZ - abc - -/\Q\Eabc/DZ - -/x*+\w/DZ - *** Failers - xxxxx - -/x?+/DZ - -/x++/DZ - -/x{1,3}+/DZ - -/(x)*+/DZ - -/^(\w++|\s++)*$/I - now is the time for all good men to come to the aid of the party - *** Failers - this is not a line with only words and spaces! - -/(\d++)(\w)/I - 12345a - *** Failers - 12345+ - -/a++b/I - aaab - -/(a++b)/I - aaab - -/(a++)b/I - aaab - -/([^()]++|\([^()]*\))+/I - ((abc(ade)ufh()()x - -/\(([^()]++|\([^()]+\))+\)/I - (abc) - (abc(def)xyz) - *** Failers - ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - -/(abc){1,3}+/DZ - -/a+?+/I - -/a{2,3}?+b/I - -/(?U)a+?+/I - -/a{2,3}?+b/IU - -/x(?U)a++b/DZ - xaaaab - -/(?U)xa++b/DZ - xaaaab - -/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/DZ - -/^x(?U)a+b/DZ - -/^x(?U)(a+)b/DZ - -/[.x.]/I - -/[=x=]/I - -/[:x:]/I - -/\l/I - -/\L/I - -/\N{name}/I - -/\u/I - -/\U/I - -/[/I - -/[a-/I - -/[[:space:]/I - -/[\s]/IDZ - -/[[:space:]]/IDZ - -/[[:space:]abcde]/IDZ - -/< (?: (?(R) \d++ | [^<>]*+) | (?R)) * >/Ix - <> - - hij> - hij> - def> - - *** Failers - iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|IDZ - -|\$\<\.X\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|IDZ - -/(.*)\d+\1/I - -/(.*)\d+/I - -/(.*)\d+\1/Is - -/(.*)\d+/Is - -/(.*(xyz))\d+\2/I - -/((.*))\d+\1/I - abc123bc - -/a[b]/I - -/(?=a).*/I - -/(?=abc).xyz/IiI - -/(?=abc)(?i).xyz/I - -/(?=a)(?=b)/I - -/(?=.)a/I - -/((?=abcda)a)/I - -/((?=abcda)ab)/I - -/()a/I - -/(?(1)ab|ac)(.)/I - -/(?(1)abz|acz)(.)/I - -/(?(1)abz)(.)/I - -/(?(1)abz)(1)23/I - -/(a)+/I - -/(a){2,3}/I - -/(a)*/I - -/[a]/I - -/[ab]/I - -/[ab]/IS - -/[^a]/I - -/\d456/I - -/\d456/IS - -/a^b/I - -/^a/Im - abcde - xy\nabc - *** Failers - xyabc - -/c|abc/I - -/(?i)[ab]/IS - -/[ab](?i)cd/IS - -/abc(?C)def/I - abcdef - 1234abcdef - *** Failers - abcxyz - abcxyzf - -/abc(?C)de(?C1)f/I - 123abcdef - -/(?C1)\dabc(?C2)def/I - 1234abcdef - *** Failers - abcdef - -/(?C255)ab/I - -/(?C256)ab/I - -/(?Cab)xx/I - -/(?C12vr)x/I - -/abc(?C)def/I - *** Failers - \x83\x0\x61bcdef - -/(abc)(?C)de(?C1)f/I - 123abcdef - 123abcdef\C+ - 123abcdef\C- - *** Failers - 123abcdef\C!1 - -/(?C0)(abc(?C1))*/I - abcabcabc - abcabc\C!1!3 - *** Failers - abcabcabc\C!1!3 - -/(\d{3}(?C))*/I - 123\C+ - 123456\C+ - 123456789\C+ - -/((xyz)(?C)p|(?C1)xyzabc)/I - xyzabc\C+ - -/(X)((xyz)(?C)p|(?C1)xyzabc)/I - Xxyzabc\C+ - -/(?=(abc))(?C)abcdef/I - abcdef\C+ - -/(?!(abc)(?C1)d)(?C2)abcxyz/I - abcxyz\C+ - -/(?<=(abc)(?C))xyz/I - abcxyz\C+ - -/a(b+)(c*)(?C1)/I - abbbbbccc\C*1 - -/a(b+?)(c*?)(?C1)/I - abbbbbccc\C*1 - -/(?C)abc/I - -/(?C)^abc/I - -/(?C)a|b/IS - -/(?R)/I - -/(a|(?R))/I - -/(ab|(bc|(de|(?R))))/I - -/x(ab|(bc|(de|(?R))))/I - xab - xbc - xde - xxab - xxxab - *** Failers - xyab - -/(ab|(bc|(de|(?1))))/I - -/x(ab|(bc|(de|(?1)x)x)x)/I - -/^([^()]|\((?1)*\))*$/I - abc - a(b)c - a(b(c))d - *** Failers) - a(b(c)d - -/^>abc>([^()]|\((?1)*\))*abc>123abc>1(2)3abc>(1(2)3)]*+) | (?2)) * >))/Ix - <> - - hij> - hij> - def> - - *** Failers - b|c)d(?Pe)/DZ - abde - acde - -/(?:a(?Pc(?Pd)))(?Pa)/DZ - -/(?Pa)...(?P=a)bbb(?P>a)d/DZ - -/^\W*(?:(?P(?P.)\W*(?P>one)\W*(?P=two)|)|(?P(?P.)\W*(?P>three)\W*(?P=four)|\W*.\W*))\W*$/Ii - 1221 - Satan, oscillate my metallic sonatas! - A man, a plan, a canal: Panama! - Able was I ere I saw Elba. - *** Failers - The quick brown fox - -/((?(R)a|b))\1(?1)?/I - bb - bbaa - -/(.*)a/Is - -/(.*)a\1/Is - -/(.*)a(b)\2/Is - -/((.*)a|(.*)b)z/Is - -/((.*)a|(.*)b)z\1/Is - -/((.*)a|(.*)b)z\2/Is - -/((.*)a|(.*)b)z\3/Is - -/((.*)a|^(.*)b)z\3/Is - -/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a/Is - -/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\31/Is - -/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\32/Is - -/(a)(bc)/INDZ - abc - -/(?Pa)(bc)/INDZ - abc - -/(a)(?Pbc)/INDZ - -/(a+)*zz/I - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaazzbbbbbb\M - aaaaaaaaaaaaaz\M - -/(aaa(?C1)bbb|ab)/I - aaabbb - aaabbb\C*0 - aaabbb\C*1 - aaabbb\C*-1 - -/ab(?Pcd)ef(?Pgh)/I - abcdefgh - abcdefgh\C1\Gtwo - abcdefgh\Cone\Ctwo - abcdefgh\Cthree - -/(?P)(?P)/DZ - -/(?P)(?P)/DZ - -/(?Pzz)(?Paa)/I - zzaa\CZ - zzaa\CA - -/(?Peks)(?Peccs)/I - -/(?Pabc(?Pdef)(?Pxyz))/I - -"\[((?P\d+)(,(?P>elem))*)\]"I - [10,20,30,5,5,4,4,2,43,23,4234] - *** Failers - [] - -"\[((?P\d+)(,(?P>elem))*)?\]"I - [10,20,30,5,5,4,4,2,43,23,4234] - [] - -/(a(b(?2)c))?/DZ - -/(a(b(?2)c))*/DZ - -/(a(b(?2)c)){0,2}/DZ - -/[ab]{1}+/DZ - -/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/Ii - Baby Bjorn Active Carrier - With free SHIPPING!! - -/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/IiS - Baby Bjorn Active Carrier - With free SHIPPING!! - -/a*.*b/ISDZ - -/(a|b)*.?c/ISDZ - -/abc(?C255)de(?C)f/DZ - -/abcde/ICDZ - abcde - abcdfe - -/a*b/ICDZ - ab - aaaab - aaaacb - -/a+b/ICDZ - ab - aaaab - aaaacb - -/(abc|def)x/ICDZ - abcx - defx - abcdefzx - -/(ab|cd){3,4}/IC - ababab - abcdabcd - abcdcdcdcdcd - -/([ab]{,4}c|xy)/ICDZ - Note: that { does NOT introduce a quantifier - -/([ab]{1,4}c|xy){4,5}?123/ICDZ - aacaacaacaacaac123 - -/\b.*/I - ab cd\>1 - -/\b.*/Is - ab cd\>1 - -/(?!.bcd).*/I - Xbcd12345 - -/abcde/I - ab\P - abc\P - abcd\P - abcde\P - the quick brown abc\P - ** Failers\P - the quick brown abxyz fox\P - -"^(0?[1-9]|[12][0-9]|3[01])/(0?[1-9]|1[012])/(20)?\d\d$"I - 13/05/04\P - 13/5/2004\P - 02/05/09\P - 1\P - 1/2\P - 1/2/0\P - 1/2/04\P - 0\P - 02/\P - 02/0\P - 02/1\P - ** Failers\P - \P - 123\P - 33/4/04\P - 3/13/04\P - 0/1/2003\P - 0/\P - 02/0/\P - 02/13\P - -/0{0,2}ABC/I - -/\d{3,}ABC/I - -/\d*ABC/I - -/[abc]+DE/I - -/[abc]?123/I - 123\P - a\P - b\P - c\P - c12\P - c123\P - -/^(?:\d){3,5}X/I - 1\P - 123\P - 123X - 1234\P - 1234X - 12345\P - 12345X - *** Failers - 1X - 123456\P - -/abc/I>testsavedregex -testsavedregex -testsavedregex -testsavedregex -(.)*~smgI - \n\n\nPartner der LCO\nde\nPartner der LINEAS Consulting\nGmbH\nLINEAS Consulting GmbH Hamburg\nPartnerfirmen\n30 days\nindex,follow\n\nja\n3\nPartner\n\n\nLCO\nLINEAS Consulting\n15.10.2003\n\n\n\n\nDie Partnerfirmen der LINEAS Consulting\nGmbH\n\n\n \n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n - -/^a/IF - -/line\nbreak/I - this is a line\nbreak - line one\nthis is a line\nbreak in the second line - -/line\nbreak/If - this is a line\nbreak - ** Failers - line one\nthis is a line\nbreak in the second line - -/line\nbreak/Imf - this is a line\nbreak - ** Failers - line one\nthis is a line\nbreak in the second line - -/ab.cd/IP - ab-cd - ab=cd - ** Failers - ab\ncd - -/ab.cd/IPs - ab-cd - ab=cd - ab\ncd - -/(?i)(?-i)AbCd/I - AbCd - ** Failers - abcd - -/a{11111111111111111111}/I - -/(){64294967295}/I - -/(){2,4294967295}/I - -"(?i:a)(?i:b)(?i:c)(?i:d)(?i:e)(?i:f)(?i:g)(?i:h)(?i:i)(?i:j)(k)(?i:l)A\1B"I - abcdefghijklAkB - -"(?Pa)(?Pb)(?Pc)(?Pd)(?Pe)(?Pf)(?Pg)(?Ph)(?Pi)(?Pj)(?Pk)(?Pl)A\11B"I - abcdefghijklAkB - -"(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)(l)A\11B"I - abcdefghijklAkB - -"(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)"I - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - -"(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)"I - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - -/[^()]*(?:\((?R)\)[^()]*)*/I - (this(and)that - (this(and)that) - (this(and)that)stuff - -/[^()]*(?:\((?>(?R))\)[^()]*)*/I - (this(and)that - (this(and)that) - -/[^()]*(?:\((?R)\))*[^()]*/I - (this(and)that - (this(and)that) - -/(?:\((?R)\))*[^()]*/I - (this(and)that - (this(and)that) - ((this)) - -/(?:\((?R)\))|[^()]*/I - (this(and)that - (this(and)that) - (this) - ((this)) - -/a(b)c/IPN - abc - -/a(?Pb)c/IPN - abc - -/\x{100}/I - -/\x{0000ff}/I - -/^((?Pa1)|(?Pa2)b)/I - -/^((?Pa1)|(?Pa2)b)/IJ - a1b\CA - a2b\CA - ** Failers - a1b\CZ\CA - -/^(?Pa)(?Pb)/IJ - ab\CA - -/^(?Pa)(?Pb)|cd/IJ - ab\CA - cd\CA - -/^(?Pa)(?Pb)|cd(?Pef)(?Pgh)/IJ - cdefgh\CA - -/^((?Pa1)|(?Pa2)b)/IJ - a1b\GA - a2b\GA - ** Failers - a1b\GZ\GA - -/^(?Pa)(?Pb)/IJ - ab\GA - -/^(?Pa)(?Pb)|cd/IJ - ab\GA - cd\GA - -/^(?Pa)(?Pb)|cd(?Pef)(?Pgh)/IJ - cdefgh\GA - -/(?J)^((?Pa1)|(?Pa2)b)/I - a1b\CA - a2b\CA - -/^(?Pa) (?J:(?Pb)(?Pc)) (?Pd)/I - -/ In this next test, J is not set at the outer level; consequently it isn't -set in the pattern's options; consequently pcre_get_named_substring() produces -a random value. /Ix - -/^(?Pa) (?J:(?Pb)(?Pc)) (?Pd)/I - a bc d\CA\CB\CC - -/^(?Pa)?(?(A)a|b)/I - aabc - bc - ** Failers - abc - -/(?:(?(ZZ)a|b)(?PX))+/I - bXaX - -/(?:(?(2y)a|b)(X))+/I - -/(?:(?(ZA)a|b)(?PX))+/I - -/(?:(?(ZZ)a|b)(?(ZZ)a|b)(?PX))+/I - bbXaaX - -/(?:(?(ZZ)a|\(b\))\\(?PX))+/I - (b)\\Xa\\X - -/(?PX|Y))+/I - bXXaYYaY - bXYaXXaX - -/()()()()()()()()()(?:(?(A)(?P=A)a|b)(?PX|Y))+/I - bXXaYYaY - -/\777/I - -/\s*,\s*/IS - \x0b,\x0b - \x0c,\x0d - -/^abc/Im - xyz\nabc - xyz\nabc\ - xyz\r\nabc\ - xyz\rabc\ - xyz\r\nabc\ - ** Failers - xyz\nabc\ - xyz\r\nabc\ - xyz\nabc\ - xyz\rabc\ - xyz\rabc\ - -/abc$/Im - xyzabc - xyzabc\n - xyzabc\npqr - xyzabc\r\ - xyzabc\rpqr\ - xyzabc\r\n\ - xyzabc\r\npqr\ - ** Failers - xyzabc\r - xyzabc\rpqr - xyzabc\r\n - xyzabc\r\npqr - -/^abc/Im - xyz\rabcdef - xyz\nabcdef\ - ** Failers - xyz\nabcdef - -/^abc/Im - xyz\nabcdef - xyz\rabcdef\ - ** Failers - xyz\rabcdef - -/^abc/Im - xyz\r\nabcdef - xyz\rabcdef\ - ** Failers - xyz\rabcdef - -/^abc/Im - -/abc/I - xyz\rabc\ - abc - -/.*/I - abc\ndef - abc\rdef - abc\r\ndef - \abc\ndef - \abc\rdef - \abc\r\ndef - \abc\ndef - \abc\rdef - \abc\r\ndef - -/\w+(.)(.)?def/Is - abc\ndef - abc\rdef - abc\r\ndef - -+((?:\s|//.*\\n|/[*](?:\\n|.)*?[*]/)*)+I - /* this is a C style comment */\M - -/(?P25[0-5]|2[0-4]\d|[01]?\d?\d)(?:\.(?P>B)){3}/I - -/()()()()()()()()()()()()()()()()()()()() - ()()()()()()()()()()()()()()()()()()()() - ()()()()()()()()()()()()()()()()()()()() - ()()()()()()()()()()()()()()()()()()()() - ()()()()()()()()()()()()()()()()()()()() - (.(.))/Ix - XY\O400 - -/(a*b|(?i:c*(?-i)d))/IS - -/()[ab]xyz/IS - -/(|)[ab]xyz/IS - -/(|c)[ab]xyz/IS - -/(|c?)[ab]xyz/IS - -/(d?|c?)[ab]xyz/IS - -/(d?|c)[ab]xyz/IS - -/^a*b\d/DZ - -/^a*+b\d/DZ - -/^a*?b\d/DZ - -/^a+A\d/DZ - aaaA5 - ** Failers - aaaa5 - -/^a*A\d/IiDZ - aaaA5 - aaaa5 - -/(a*|b*)[cd]/IS - -/(a+|b*)[cd]/IS - -/(a*|b+)[cd]/IS - -/(a+|b+)[cd]/IS - -/(((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((( - (((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((( - ((( - a - )))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))) - )))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))) - ))) -/Ix - large nest - -/a*\d/BZ - -/a*\D/BZ - -/0*\d/BZ - -/0*\D/BZ - -/a*\s/BZ - -/a*\S/BZ - -/ *\s/BZ - -/ *\S/BZ - -/a*\w/BZ - -/a*\W/BZ - -/=*\w/BZ - -/=*\W/BZ - -/\d*a/BZ - -/\d*2/BZ - -/\d*\d/BZ - -/\d*\D/BZ - -/\d*\s/BZ - -/\d*\S/BZ - -/\d*\w/BZ - -/\d*\W/BZ - -/\D*a/BZ - -/\D*2/BZ - -/\D*\d/BZ - -/\D*\D/BZ - -/\D*\s/BZ - -/\D*\S/BZ - -/\D*\w/BZ - -/\D*\W/BZ - -/\s*a/BZ - -/\s*2/BZ - -/\s*\d/BZ - -/\s*\D/BZ - -/\s*\s/BZ - -/\s*\S/BZ - -/\s*\w/BZ - -/\s*\W/BZ - -/\S*a/BZ - -/\S*2/BZ - -/\S*\d/BZ - -/\S*\D/BZ - -/\S*\s/BZ - -/\S*\S/BZ - -/\S*\w/BZ - -/\S*\W/BZ - -/\w*a/BZ - -/\w*2/BZ - -/\w*\d/BZ - -/\w*\D/BZ - -/\w*\s/BZ - -/\w*\S/BZ - -/\w*\w/BZ - -/\w*\W/BZ - -/\W*a/BZ - -/\W*2/BZ - -/\W*\d/BZ - -/\W*\D/BZ - -/\W*\s/BZ - -/\W*\S/BZ - -/\W*\w/BZ - -/\W*\W/BZ - -/[^a]+a/BZ - -/[^a]+a/BZi - -/[^a]+A/BZi - -/[^a]+b/BZ - -/[^a]+\d/BZ - -/a*[^a]/BZ - -/(?Px)(?Py)/I - xy\Cabc\Cxyz - -/(?x)(?'xyz'y)/I - xy\Cabc\Cxyz - -/(?x)(?'xyz>y)/I - -/(?P'abc'x)(?Py)/I - -/^(?:(?(ZZ)a|b)(?X))+/ - bXaX - bXbX - ** Failers - aXaX - aXbX - -/^(?P>abc)(?xxx)/ - -/^(?P>abc)(?x|y)/ - xx - xy - yy - yx - -/^(?P>abc)(?Px|y)/ - xx - xy - yy - yx - -/^((?(abc)a|b)(?x|y))+/ - bxay - bxby - ** Failers - axby - -/^(((?P=abc)|X)(?x|y))+/ - XxXxxx - XxXyyx - XxXyxx - ** Failers - x - -/^(?1)(abc)/ - abcabc - -/^(?:(?:\1|X)(a|b))+/ - Xaaa - Xaba - -/^[\E\Qa\E-\Qz\E]+/BZ - -/^[a\Q]bc\E]/BZ - -/^[a-\Q\E]/BZ - -/^(?P>abc)[()](?)/BZ - -/^((?(abc)y)[()](?Px))+/BZ - (xy)x - -/^(?P>abc)\Q()\E(?)/BZ - -/^(?P>abc)[a\Q(]\E(](?)/BZ - -/^(?P>abc) # this is (a comment) - (?)/BZx - -/^\W*(?:(?(?.)\W*(?&one)\W*\k|)|(?(?.)\W*(?&three)\W*\k'four'|\W*.\W*))\W*$/Ii - 1221 - Satan, oscillate my metallic sonatas! - A man, a plan, a canal: Panama! - Able was I ere I saw Elba. - *** Failers - The quick brown fox - -/(?=(\w+))\1:/I - abcd: - -/(?=(?'abc'\w+))\k:/I - abcd: - -/(?'abc'\w+):\k{2}/ - a:aaxyz - ab:ababxyz - ** Failers - a:axyz - ab:abxyz - -/(?'abc'a|b)(?d|e)\k{2}/J - adaa - ** Failers - addd - adbb - -/(?'abc'a|b)(?d|e)(?&abc){2}/J - bdaa - bdab - ** Failers - bddd - -/^(?a)? (?()b|c) (?('ab')d|e)/x - abd - ce - -/(?( (?'B' abc (?(R) (?(R&A)1) (?(R&B)2) X | (?1) (?2) (?R) ))) /x - abcabc1Xabc2XabcXabcabc - -/(? (?'B' abc (?(R) (?(R&1)1) (?(R&B)2) X | (?1) (?2) (?R) ))) /x - -/(?<1> (?'B' abc (?(R) (?(R&1)1) (?(R&B)2) X | (?1) (?2) (?R) ))) /x - abcabc1Xabc2XabcXabcabc - -/^(?(DEFINE) (? a) (? b) ) (?&A) (?&B) /x - abcd - -/(?(?&NAME_PAT))\s+(?(?&ADDRESS_PAT)) - (?(DEFINE) - (?[a-z]+) - (?\d+) - )/x - metcalfe 33 - -/^(?(DEFINE) abc | xyz ) /x - -/(?(DEFINE) abc) xyz/xI - -/(?(DEFINE) abc){3} xyz/x - -/(a|)*\d/ - \O0aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - \O0aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 - -/^a.b/ - a\rb - a\nb\ - a\x85b\ - ** Failers - a\nb - a\nb\ - a\rb\ - a\rb\ - a\x85b\ - a\rb\ - -/^abc./mgx - abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x85abc7 JUNK - -/abc.$/mgx - abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x85 abc7 abc9 - -/a/ - -/a/ - -/^a\Rb/ - a\nb - a\rb - a\r\nb - a\x0bb - a\x0cb - a\x85b - ** Failers - a\n\rb - -/^a\R*b/ - ab - a\nb - a\rb - a\r\nb - a\x0bb - a\x0cb - a\x85b - a\n\rb - a\n\r\x85\x0cb - -/^a\R+b/ - a\nb - a\rb - a\r\nb - a\x0bb - a\x0cb - a\x85b - a\n\rb - a\n\r\x85\x0cb - ** Failers - ab - -/^a\R{1,3}b/ - a\nb - a\n\rb - a\n\r\x85b - a\r\n\r\nb - a\r\n\r\n\r\nb - a\n\r\n\rb - a\n\n\r\nb - ** Failers - a\n\n\n\rb - a\r - -/^a[\R]b/ - aRb - ** Failers - a\nb - -/(?&abc)X(?P)/I - abcPXP123 - -/(?1)X(?P)/I - abcPXP123 - -/(?(DEFINE)(?2[0-4]\d|25[0-5]|1\d\d|[1-9]?\d))\b(?&byte)(\.(?&byte)){3}/ - 1.2.3.4 - 131.111.10.206 - 10.0.0.0 - ** Failers - 10.6 - 455.3.4.5 - -/\b(?&byte)(\.(?&byte)){3}(?(DEFINE)(?2[0-4]\d|25[0-5]|1\d\d|[1-9]?\d))/ - 1.2.3.4 - 131.111.10.206 - 10.0.0.0 - ** Failers - 10.6 - 455.3.4.5 - -/(?:a(?&abc)b)*(?x)/ - 123axbaxbaxbx456 - 123axbaxbaxb456 - -/(?:a(?&abc)b){1,5}(?x)/ - 123axbaxbaxbx456 - -/(?:a(?&abc)b){2,5}(?x)/ - 123axbaxbaxbx456 - -/(?:a(?&abc)b){2,}(?x)/ - 123axbaxbaxbx456 - -/(abc)(?i:(?1))/ - defabcabcxyz - DEFabcABCXYZ - -/(abc)(?:(?i)(?1))/ - defabcabcxyz - DEFabcABCXYZ - -/^(a(b))\1\g1\g{1}\g-1\g{-1}\g{-02}Z/ - ababababbbabZXXXX - -/^(a)\g-2/ - -/^(a)\g/ - -/^(a)\g{0}/ - -/^(a)\g{3/ - -/^(a)\g{4a}/ - -/^a.b/ - a\rb - *** Failers - a\nb - -/.+foo/ - afoo - ** Failers - \r\nfoo - \nfoo - -/.+foo/ - afoo - \nfoo - ** Failers - \r\nfoo - -/.+foo/ - afoo - ** Failers - \nfoo - \r\nfoo - -/.+foo/s - afoo - \r\nfoo - \nfoo - -/^$/mg - abc\r\rxyz - abc\n\rxyz - ** Failers - abc\r\nxyz - -/(?m)^$/g+ - abc\r\n\r\n - -/(?m)^$|^\r\n/g+ - abc\r\n\r\n - -/(?m)$/g+ - abc\r\n\r\n - -/abc.$/mgx - abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x85 abc9 - -/^X/m - XABC - ** Failers - XABC\B - -/(ab|c)(?-1)/BZ - abc - -/xy(?+1)(abc)/BZ - xyabcabc - ** Failers - xyabc - -/x(?-0)y/ - -/x(?-1)y/ - -/x(?+0)y/ - -/x(?+1)y/ - -/^(abc)?(?(-1)X|Y)/BZ - abcX - Y - ** Failers - abcY - -/^((?(+1)X|Y)(abc))+/BZ - YabcXabc - YabcXabcXabc - ** Failers - XabcXabc - -/(?(-1)a)/BZ - -/((?(-1)a))/BZ - -/((?(-2)a))/BZ - -/^(?(+1)X|Y)(.)/BZ - Y! - -/(foo)\Kbar/ - foobar - -/(foo)(\Kbar|baz)/ - foobar - foobaz - -/(foo\Kbar)baz/ - foobarbaz - -/(?tom|bon)-\k{A}/ - tom-tom - bon-bon - ** Failers - tom-bon - -/(?tom|bon)-\g{A}/ - tom-tom - bon-bon - -/\g{A/ - -/(?|(abc)|(xyz))/BZ - >abc< - >xyz< - -/(x)(?|(abc)|(xyz))(x)/BZ - xabcx - xxyzx - -/(x)(?|(abc)(pqr)|(xyz))(x)/BZ - xabcpqrx - xxyzx - -/(?|(abc)|(xyz))\1/ - abcabc - xyzxyz - ** Failers - abcxyz - xyzabc - -/(?|(abc)|(xyz))(?1)/ - abcabc - xyzabc - ** Failers - xyzxyz - -/\H\h\V\v/ - X X\x0a - X\x09X\x0b - ** Failers - \xa0 X\x0a - -/\H*\h+\V?\v{3,4}/ - \x09\x20\xa0X\x0a\x0b\x0c\x0d\x0a - \x09\x20\xa0\x0a\x0b\x0c\x0d\x0a - \x09\x20\xa0\x0a\x0b\x0c - ** Failers - \x09\x20\xa0\x0a\x0b - -/\H{3,4}/ - XY ABCDE - XY PQR ST - -/.\h{3,4}./ - XY AB PQRS - -/\h*X\h?\H+Y\H?Z/ - >XNNNYZ - > X NYQZ - ** Failers - >XYZ - > X NY Z - -/\v*X\v?Y\v+Z\V*\x0a\V+\x0b\V{2,3}\x0c/ - >XY\x0aZ\x0aA\x0bNN\x0c - >\x0a\x0dX\x0aY\x0a\x0bZZZ\x0aAAA\x0bNNN\x0c - -/[\h]/BZ - >\x09< - -/[\h]+/BZ - >\x09\x20\xa0< - -/[\v]/BZ - -/[\H]/BZ - -/[^\h]/BZ - -/[\V]/BZ - -/[\x0a\V]/BZ - -/\H++X/BZ - ** Failers - XXXX - -/\H+\hY/BZ - XXXX Y - -/\H+ Y/BZ - -/\h+A/BZ - -/\v*B/BZ - -/\V+\x0a/BZ - -/A+\h/BZ - -/ *\H/BZ - -/A*\v/BZ - -/\x0b*\V/BZ - -/\d+\h/BZ - -/\d*\v/BZ - -/S+\h\S+\v/BZ - -/\w{3,}\h\w+\v/BZ - -/\h+\d\h+\w\h+\S\h+\H/BZ - -/\v+\d\v+\w\v+\S\v+\V/BZ - -/\H+\h\H+\d/BZ - -/\V+\v\V+\w/BZ - -/\( (?: [^()]* | (?R) )* \)/x -(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(00)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0) - -/[\E]AAA/ - -/[\Q\E]AAA/ - -/[^\E]AAA/ - -/[^\Q\E]AAA/ - -/[\E^]AAA/ - -/[\Q\E^]AAA/ - -/A(*PRUNE)B(*SKIP)C(*THEN)D(*COMMIT)E(*F)F(*FAIL)G(?!)H(*ACCEPT)I/BZ - -/^a+(*FAIL)/ - aaaaaa - -/a+b?c+(*FAIL)/ - aaabccc - -/a+b?(*PRUNE)c+(*FAIL)/ - aaabccc - -/a+b?(*COMMIT)c+(*FAIL)/ - aaabccc - -/a+b?(*SKIP)c+(*FAIL)/ - aaabcccaaabccc - -/^(?:aaa(*THEN)\w{6}|bbb(*THEN)\w{5}|ccc(*THEN)\w{4}|\w{3})/ - aaaxxxxxx - aaa++++++ - bbbxxxxx - bbb+++++ - cccxxxx - ccc++++ - dddddddd - -/^(aaa(*THEN)\w{6}|bbb(*THEN)\w{5}|ccc(*THEN)\w{4}|\w{3})/ - aaaxxxxxx - aaa++++++ - bbbxxxxx - bbb+++++ - cccxxxx - ccc++++ - dddddddd - -/a+b?(*THEN)c+(*FAIL)/ - aaabccc - -/(A (A|B(*ACCEPT)|C) D)(E)/x - ABX - AADE - ACDE - ** Failers - AD - -/^a+(*FAIL)/C - aaaaaa - -/a+b?c+(*FAIL)/C - aaabccc - -/a+b?(*PRUNE)c+(*FAIL)/C - aaabccc - -/a+b?(*COMMIT)c+(*FAIL)/C - aaabccc - -/a+b?(*SKIP)c+(*FAIL)/C - aaabcccaaabccc - -/a+b?(*THEN)c+(*FAIL)/C - aaabccc - -/a(*PRUNE:XXX)b/ - -/a(*MARK)b/ - -/(?i:A{1,}\6666666666)/ - -/\g6666666666/ - -/[\g6666666666]/ - -/(?1)\c[/ - -/.+A/ - \r\nA - -/\nA/ - \r\nA - -/[\r\n]A/ - \r\nA - -/(\r|\n)A/ - \r\nA - -/a(*CR)b/ - -/(*CR)a.b/ - a\nb - ** Failers - a\rb - -/(*CR)a.b/ - a\nb - ** Failers - a\rb - -/(*LF)a.b/ - a\rb - ** Failers - a\nb - -/(*CRLF)a.b/ - a\rb - a\nb - ** Failers - a\r\nb - -/(*ANYCRLF)a.b/ - ** Failers - a\rb - a\nb - a\r\nb - -/(*ANY)a.b/ - ** Failers - a\rb - a\nb - a\r\nb - a\x85b - -/a\Rb/I - a\rb - a\nb - a\r\nb - ** Failers - a\x85b - a\x0bb - -/a\Rb/I - a\rb - a\nb - a\r\nb - a\x85b - a\x0bb - ** Failers - a\x85b\ - a\x0bb\ - -/a\R?b/I - a\rb - a\nb - a\r\nb - ** Failers - a\x85b - a\x0bb - -/a\R?b/I - a\rb - a\nb - a\r\nb - a\x85b - a\x0bb - ** Failers - a\x85b\ - a\x0bb\ - -/a\R{2,4}b/I - a\r\n\nb - a\n\r\rb - a\r\n\r\n\r\n\r\nb - ** Failers - a\x85\85b - a\x0b\0bb - -/a\R{2,4}b/I - a\r\rb - a\n\n\nb - a\r\n\n\r\rb - a\x85\85b - a\x0b\0bb - ** Failers - a\r\r\r\r\rb - a\x85\85b\ - a\x0b\0bb\ - -/(*BSR_ANYCRLF)a\Rb/I - a\nb - a\rb - -/(*BSR_UNICODE)a\Rb/I - a\x85b - -/(*BSR_ANYCRLF)(*CRLF)a\Rb/I - a\nb - a\rb - -/(*CRLF)(*BSR_UNICODE)a\Rb/I - a\x85b - -/(*CRLF)(*BSR_ANYCRLF)(*CR)ab/I - -/(?)(?&)/ - -/(?)(?&a)/ - -/(?)(?&aaaaaaaaaaaaaaaaaaaaaaa)/ - -/(?+-a)/ - -/(?-+a)/ - -/(?(-1))/ - -/(?(+10))/ - -/(?(10))/ - -/(?(+2))()()/ - -/(?(2))()()/ - -/\k''/ - -/\k<>/ - -/\k{}/ - -/(?P=)/ - -/(?P>)/ - -/(?!\w)(?R)/ - -/(?=\w)(?R)/ - -/(?a|b\gc)/ - aaaa - bacxxx - bbaccxxx - bbbacccxx - -/^(?a|b\g'name'c)/ - aaaa - bacxxx - bbaccxxx - bbbacccxx - -/^(a|b\g<1>c)/ - aaaa - bacxxx - bbaccxxx - bbbacccxx - -/^(a|b\g'1'c)/ - aaaa - bacxxx - bbaccxxx - bbbacccxx - -/^(a|b\g'-1'c)/ - aaaa - bacxxx - bbaccxxx - bbbacccxx - -/(^(a|b\g<-1>c))/ - aaaa - bacxxx - bbaccxxx - bbbacccxx - -/(^(a|b\g<-1'c))/ - -/(^(a|b\g{-1}))/ - bacxxx - -/(?-i:\g)(?i:(?a))/ - XaaX - XAAX - -/(?i:\g)(?-i:(?a))/ - XaaX - ** Failers - XAAX - -/(?-i:\g<+1>)(?i:(a))/ - XaaX - XAAX - -/(?=(?(?#simplesyntax)\$(?[a-zA-Z_\x{7f}-\x{ff}][a-zA-Z0-9_\x{7f}-\x{ff}]*)(?:\[(?[a-zA-Z0-9_\x{7f}-\x{ff}]+|\$\g)\]|->\g(\(.*?\))?)?|(?#simple syntax withbraces)\$\{(?:\g(?\[(?:\g|'(?:\\.|[^'\\])*'|"(?:\g|\\.|[^"\\])*")\])?|\g|\$\{\g\})\}|(?#complexsyntax)\{(?\$(?\g(\g*|\(.*?\))?)(?:->\g)*|\$\g|\$\{\g\})\}))\{/ - -/(?a|b|c)\g*/ - abc - accccbbb - -/^(?+1)(?x|y){0}z/ - xzxx - yzyy - ** Failers - xxz - -/(\3)(\1)(a)/ - cat - -/(\3)(\1)(a)/ - cat - -/TA]/ - The ACTA] comes - -/TA]/ - The ACTA] comes - -/(?2)[]a()b](abc)/ - abcbabc - -/(?2)[^]a()b](abc)/ - abcbabc - -/(?1)[]a()b](abc)/ - abcbabc - ** Failers - abcXabc - -/(?1)[^]a()b](abc)/ - abcXabc - ** Failers - abcbabc - -/(?2)[]a()b](abc)(xyz)/ - xyzbabcxyz - -/(?&N)[]a(?)](?abc)/ - abc)](abc)/ - abc - ** Failers - ab - -/a[]+b/ - ** Failers - ab - -/a[]*+b/ - ** Failers - ab - -/a[^]b/ - aXb - a\nb - ** Failers - ab - -/a[^]+b/ - aXb - a\nX\nXb - ** Failers - ab - -/a(?!)+b/ - -/a(*FAIL)+b/ - -/(abc|pqr|123){0}[xyz]/SI - -/(?(?=.*b)b|^)/CI - adc - abc - -/(?(?=b).*b|^d)/I - -/(?(?=.*b).*b|^d)/I - -/a?|b?/P - abc - ** Failers - ddd\N - -/xyz/C - xyz - abcxyz - abcxyz\Y - ** Failers - abc - abc\Y - abcxypqr - abcxypqr\Y - -/^"((?(?=[a])[^"])|b)*"$/C - "ab" - -/^"((?(?=[a])[^"])|b)*"$/ - "ab" - -/^X(?5)(a)(?|(b)|(q))(c)(d)(Y)/ - XYabcdY - -/^X(?5)(a)(?|(b)|(q))(c)(d)Y/ - XYabcdY - -/^X(?&N)(a)(?|(b)|(q))(c)(d)(?Y)/ - XYabcdY - -/^X(?7)(a)(?|(b)|(q)(r)(s))(c)(d)(Y)/ - XYabcdY - -/^X(?7)(a)(?|(b|(r)(s))|(q))(c)(d)(Y)/ - XYabcdY - -/^X(?7)(a)(?|(b|(?|(r)|(t))(s))|(q))(c)(d)(Y)/ - XYabcdY - -/ End of testinput2 / diff --git a/libs/pcre/testdata/testinput3 b/libs/pcre/testdata/testinput3 deleted file mode 100644 index 1376c213b4..0000000000 --- a/libs/pcre/testdata/testinput3 +++ /dev/null @@ -1,91 +0,0 @@ -/^[\w]+/ - *** Failers - École - -/^[\w]+/Lfr_FR - École - -/^[\w]+/ - *** Failers - École - -/^[\W]+/ - École - -/^[\W]+/Lfr_FR - *** Failers - École - -/[\b]/ - \b - *** Failers - a - -/[\b]/Lfr_FR - \b - *** Failers - a - -/^\w+/ - *** Failers - École - -/^\w+/Lfr_FR - École - -/(.+)\b(.+)/ - École - -/(.+)\b(.+)/Lfr_FR - *** Failers - École - -/École/i - École - *** Failers - école - -/École/iLfr_FR - École - école - -/\w/IS - -/\w/ISLfr_FR - -/^[\xc8-\xc9]/iLfr_FR - École - école - -/^[\xc8-\xc9]/Lfr_FR - École - *** Failers - école - -/\W+/Lfr_FR - >>>\xaa<<< - >>>\xba<<< - -/[\W]+/Lfr_FR - >>>\xaa<<< - >>>\xba<<< - -/[^[:alpha:]]+/Lfr_FR - >>>\xaa<<< - >>>\xba<<< - -/\w+/Lfr_FR - >>>\xaa<<< - >>>\xba<<< - -/[\w]+/Lfr_FR - >>>\xaa<<< - >>>\xba<<< - -/[[:alpha:]]+/Lfr_FR - >>>\xaa<<< - >>>\xba<<< - -/[[:alpha:]][[:lower:]][[:upper:]]/DZLfr_FR - -/ End of testinput3 / diff --git a/libs/pcre/testdata/testinput4 b/libs/pcre/testdata/testinput4 deleted file mode 100644 index e5f61946e2..0000000000 --- a/libs/pcre/testdata/testinput4 +++ /dev/null @@ -1,626 +0,0 @@ -/-- Do not use the \x{} construct except with patterns that have the --/ -/-- /8 option set, because PCRE doesn't recognize them as UTF-8 unless --/ -/-- that option is set. However, the latest Perls recognize them always. --/ - -/a.b/8 - acb - a\x7fb - a\x{100}b - *** Failers - a\nb - -/a(.{3})b/8 - a\x{4000}xyb - a\x{4000}\x7fyb - a\x{4000}\x{100}yb - *** Failers - a\x{4000}b - ac\ncb - -/a(.*?)(.)/ - a\xc0\x88b - -/a(.*?)(.)/8 - a\x{100}b - -/a(.*)(.)/ - a\xc0\x88b - -/a(.*)(.)/8 - a\x{100}b - -/a(.)(.)/ - a\xc0\x92bcd - -/a(.)(.)/8 - a\x{240}bcd - -/a(.?)(.)/ - a\xc0\x92bcd - -/a(.?)(.)/8 - a\x{240}bcd - -/a(.??)(.)/ - a\xc0\x92bcd - -/a(.??)(.)/8 - a\x{240}bcd - -/a(.{3})b/8 - a\x{1234}xyb - a\x{1234}\x{4321}yb - a\x{1234}\x{4321}\x{3412}b - *** Failers - a\x{1234}b - ac\ncb - -/a(.{3,})b/8 - a\x{1234}xyb - a\x{1234}\x{4321}yb - a\x{1234}\x{4321}\x{3412}b - axxxxbcdefghijb - a\x{1234}\x{4321}\x{3412}\x{3421}b - *** Failers - a\x{1234}b - -/a(.{3,}?)b/8 - a\x{1234}xyb - a\x{1234}\x{4321}yb - a\x{1234}\x{4321}\x{3412}b - axxxxbcdefghijb - a\x{1234}\x{4321}\x{3412}\x{3421}b - *** Failers - a\x{1234}b - -/a(.{3,5})b/8 - a\x{1234}xyb - a\x{1234}\x{4321}yb - a\x{1234}\x{4321}\x{3412}b - axxxxbcdefghijb - a\x{1234}\x{4321}\x{3412}\x{3421}b - axbxxbcdefghijb - axxxxxbcdefghijb - *** Failers - a\x{1234}b - axxxxxxbcdefghijb - -/a(.{3,5}?)b/8 - a\x{1234}xyb - a\x{1234}\x{4321}yb - a\x{1234}\x{4321}\x{3412}b - axxxxbcdefghijb - a\x{1234}\x{4321}\x{3412}\x{3421}b - axbxxbcdefghijb - axxxxxbcdefghijb - *** Failers - a\x{1234}b - axxxxxxbcdefghijb - -/^[a\x{c0}]/8 - *** Failers - \x{100} - -/(?<=aXb)cd/8 - aXbcd - -/(?<=a\x{100}b)cd/8 - a\x{100}bcd - -/(?<=a\x{100000}b)cd/8 - a\x{100000}bcd - -/(?:\x{100}){3}b/8 - \x{100}\x{100}\x{100}b - *** Failers - \x{100}\x{100}b - -/\x{ab}/8 - \x{ab} - \xc2\xab - *** Failers - \x00{ab} - -/(?<=(.))X/8 - WXYZ - \x{256}XYZ - *** Failers - XYZ - -/X(\C{3})/8 - X\x{1234} - -/X(\C{4})/8 - X\x{1234}YZ - -/X\C*/8 - XYZabcdce - -/X\C*?/8 - XYZabcde - -/X\C{3,5}/8 - Xabcdefg - X\x{1234} - X\x{1234}YZ - X\x{1234}\x{512} - X\x{1234}\x{512}YZ - -/X\C{3,5}?/8 - Xabcdefg - X\x{1234} - X\x{1234}YZ - X\x{1234}\x{512} - -/[^a]+/8g - bcd - \x{100}aY\x{256}Z - -/^[^a]{2}/8 - \x{100}bc - -/^[^a]{2,}/8 - \x{100}bcAa - -/^[^a]{2,}?/8 - \x{100}bca - -/[^a]+/8ig - bcd - \x{100}aY\x{256}Z - -/^[^a]{2}/8i - \x{100}bc - -/^[^a]{2,}/8i - \x{100}bcAa - -/^[^a]{2,}?/8i - \x{100}bca - -/\x{100}{0,0}/8 - abcd - -/\x{100}?/8 - abcd - \x{100}\x{100} - -/\x{100}{0,3}/8 - \x{100}\x{100} - \x{100}\x{100}\x{100}\x{100} - -/\x{100}*/8 - abce - \x{100}\x{100}\x{100}\x{100} - -/\x{100}{1,1}/8 - abcd\x{100}\x{100}\x{100}\x{100} - -/\x{100}{1,3}/8 - abcd\x{100}\x{100}\x{100}\x{100} - -/\x{100}+/8 - abcd\x{100}\x{100}\x{100}\x{100} - -/\x{100}{3}/8 - abcd\x{100}\x{100}\x{100}XX - -/\x{100}{3,5}/8 - abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX - -/\x{100}{3,}/8 - abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX - -/(?<=a\x{100}{2}b)X/8+ - Xyyya\x{100}\x{100}bXzzz - -/\D*/8 - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - -/\D*/8 - \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} - -/\D/8 - 1X2 - 1\x{100}2 - -/>\S/8 - > >X Y - > >\x{100} Y - -/\d/8 - \x{100}3 - -/\s/8 - \x{100} X - -/\D+/8 - 12abcd34 - *** Failers - 1234 - -/\D{2,3}/8 - 12abcd34 - 12ab34 - *** Failers - 1234 - 12a34 - -/\D{2,3}?/8 - 12abcd34 - 12ab34 - *** Failers - 1234 - 12a34 - -/\d+/8 - 12abcd34 - *** Failers - -/\d{2,3}/8 - 12abcd34 - 1234abcd - *** Failers - 1.4 - -/\d{2,3}?/8 - 12abcd34 - 1234abcd - *** Failers - 1.4 - -/\S+/8 - 12abcd34 - *** Failers - \ \ - -/\S{2,3}/8 - 12abcd34 - 1234abcd - *** Failers - \ \ - -/\S{2,3}?/8 - 12abcd34 - 1234abcd - *** Failers - \ \ - -/>\s+ <34 - *** Failers - -/>\s{2,3} \s{2,3}? \xff< - -/[\xff]/8 - >\x{ff}< - -/[^\xFF]/ - XYZ - -/[^\xff]/8 - XYZ - \x{123} - -/^[ac]*b/8 - xb - -/^[ac\x{100}]*b/8 - xb - -/^[^x]*b/8i - xb - -/^[^x]*b/8 - xb - -/^\d*b/8 - xb - -/(|a)/g8 - catac - a\x{256}a - -/^\x{85}$/8i - \x{85} - -/^ሴ/8 - ሴ - -/^\ሴ/8 - ሴ - -"(?s)(.{1,5})"8 - abcdefg - ab - -/a*\x{100}*\w/8 - a - -/\S\S/8g - A\x{a3}BC - -/\S{2}/8g - A\x{a3}BC - -/\W\W/8g - +\x{a3}== - -/\W{2}/8g - +\x{a3}== - -/\S/8g - \x{442}\x{435}\x{441}\x{442} - -/[\S]/8g - \x{442}\x{435}\x{441}\x{442} - -/\D/8g - \x{442}\x{435}\x{441}\x{442} - -/[\D]/8g - \x{442}\x{435}\x{441}\x{442} - -/\W/8g - \x{2442}\x{2435}\x{2441}\x{2442} - -/[\W]/8g - \x{2442}\x{2435}\x{2441}\x{2442} - -/[\S\s]*/8 - abc\n\r\x{442}\x{435}\x{441}\x{442}xyz - -/[\x{41f}\S]/8g - \x{442}\x{435}\x{441}\x{442} - -/.[^\S]./8g - abc def\x{442}\x{443}xyz\npqr - -/.[^\S\n]./8g - abc def\x{442}\x{443}xyz\npqr - -/[[:^alnum:]]/8g - +\x{2442} - -/[[:^alpha:]]/8g - +\x{2442} - -/[[:^ascii:]]/8g - A\x{442} - -/[[:^blank:]]/8g - A\x{442} - -/[[:^cntrl:]]/8g - A\x{442} - -/[[:^digit:]]/8g - A\x{442} - -/[[:^graph:]]/8g - \x19\x{e01ff} - -/[[:^lower:]]/8g - A\x{422} - -/[[:^print:]]/8g - \x{19}\x{e01ff} - -/[[:^punct:]]/8g - A\x{442} - -/[[:^space:]]/8g - A\x{442} - -/[[:^upper:]]/8g - a\x{442} - -/[[:^word:]]/8g - +\x{2442} - -/[[:^xdigit:]]/8g - M\x{442} - -/[^ABCDEFGHIJKLMNOPQRSTUVWXYZÀÃÂÃÄÅÆÇÈÉÊËÌÃÃŽÃÃÑÒÓÔÕÖØÙÚÛÜÃÞĀĂĄĆĈĊČĎÄĒĔĖĘĚĜĞĠĢĤĦĨĪĬĮİIJĴĶĹĻĽĿÅŃŅŇŊŌŎÅŒŔŖŘŚŜŞŠŢŤŦŨŪŬŮŰŲŴŶŸŹŻŽÆƂƄƆƇƉƊƋƎÆÆƑƓƔƖƗƘƜÆƟƠƢƤƦƧƩƬƮƯƱƲƳƵƷƸƼDŽLJNJÇÇǑǓǕǗǙǛǞǠǢǤǦǨǪǬǮDZǴǶǷǸǺǼǾȀȂȄȆȈȊȌȎÈȒȔȖȘȚȜȞȠȢȤȦȨȪȬȮȰȲȺȻȽȾÉΆΈΉΊΌΎÎΑΒΓΔΕΖΗΘΙΚΛΜÎΞΟΠΡΣΤΥΦΧΨΩΪΫϒϓϔϘϚϜϞϠϢϤϦϨϪϬϮϴϷϹϺϽϾϿЀÐЂЃЄЅІЇЈЉЊЋЌÐÐŽÐÐБВГДЕЖЗИЙКЛМÐОПРСТУФХЦЧШЩЪЫЬЭЮЯѠѢѤѦѨѪѬѮѰѲѴѶѸѺѼѾҀҊҌҎÒҒҔҖҘҚҜҞҠҢҤҦҨҪҬҮҰҲҴҶҸҺҼҾӀÓÓƒÓ…Ó‡Ó‰Ó‹ÓÓӒӔӖӘӚӜӞӠӢӤӦӨӪӬӮӰӲӴӶӸԀԂԄԆԈԊԌԎԱԲԳԴԵԶԷԸԹԺԻԼԽԾԿՀÕÕ‚ÕƒÕ„Õ…Õ†Õ‡ÕˆÕ‰ÕŠÕ‹ÕŒÕÕŽÕÕՑՒՓՔՕՖႠႡႢႣႤႥႦႧႨႩႪႫႬႭႮႯႰႱႲႳႴႵႶႷႸႹႺႻႼႽႾႿჀáƒáƒ‚ჃჄჅḀḂḄḆḈḊḌḎá¸á¸’ḔḖḘḚḜḞḠḢḤḦḨḪḬḮḰḲḴḶḸḺḼḾṀṂṄṆṈṊṌṎá¹á¹’ṔṖṘṚṜṞṠṢṤṦṨṪṬṮṰṲṴṶṸṺṼṾẀẂẄẆẈẊẌẎáºáº’ẔẠẢẤẦẨẪẬẮẰẲẴẶẸẺẼẾỀỂỄỆỈỊỌỎá»á»’ỔỖỘỚỜỞỠỢỤỦỨỪỬỮỰỲỴỶỸἈἉἊἋἌá¼á¼Žá¼á¼˜á¼™á¼šá¼›á¼œá¼á¼¨á¼©á¼ªá¼«á¼¬á¼­á¼®á¼¯á¼¸á¼¹á¼ºá¼»á¼¼á¼½á¼¾á¼¿á½ˆá½‰á½Šá½‹á½Œá½á½™á½›á½á½Ÿá½¨á½©á½ªá½«á½¬á½­á½®á½¯á¾¸á¾¹á¾ºá¾»á¿ˆá¿‰á¿Šá¿‹á¿˜á¿™á¿šá¿›á¿¨á¿©á¿ªá¿«á¿¬á¿¸á¿¹á¿ºá¿»abcdefghijklmnopqrstuvwxyzªµºßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿÄăąćĉċÄÄđēĕėęěÄğġģĥħĩīĭįıijĵķĸĺļľŀłńņňʼnŋÅÅőœŕŗřśÅşšţťŧũūŭůűųŵŷźżžſƀƃƅƈƌƃƕƙƚƛƞơƣƥƨƪƫƭưƴƶƹƺƽƾƿdžljnjǎÇǒǔǖǘǚǜÇǟǡǣǥǧǩǫǭǯǰdzǵǹǻǽǿÈȃȅȇȉȋÈÈȑȓȕȗșțÈȟȡȣȥȧȩȫȭȯȱȳȴȵȶȷȸȹȼȿɀÉɑɒɓɔɕɖɗɘəɚɛɜÉɞɟɠɡɢɣɤɥɦɧɨɩɪɫɬɭɮɯɰɱɲɳɴɵɶɷɸɹɺɻɼɽɾɿʀÊʂʃʄʅʆʇʈʉʊʋʌÊÊŽÊÊʑʒʓʔʕʖʗʘʙʚʛʜÊʞʟʠʡʢʣʤʥʦʧʨʩʪʫʬʭʮʯÎάέήίΰαβγδεζηθικλμνξοπÏςστυφχψωϊϋόÏÏŽÏϑϕϖϗϙϛÏϟϡϣϥϧϩϫϭϯϰϱϲϳϵϸϻϼабвгдежзийклмнопрÑтуфхцчшщъыьÑÑŽÑÑёђѓєѕіїјљњћќÑўџѡѣѥѧѩѫѭѯѱѳѵѷѹѻѽѿÒÒ‹ÒÒÒ‘Ò“Ò•Ò—Ò™Ò›ÒҟҡңҥҧҩҫҭүұҳҵҷҹһҽҿӂӄӆӈӊӌӎӑӓӕӗәӛÓÓŸÓ¡Ó£Ó¥Ó§Ó©Ó«Ó­Ó¯Ó±Ó³ÓµÓ·Ó¹ÔÔƒÔ…Ô‡Ô‰Ô‹ÔÔÕ¡Õ¢Õ£Õ¤Õ¥Õ¦Õ§Õ¨Õ©ÕªÕ«Õ¬Õ­Õ®Õ¯Õ°Õ±Õ²Õ³Õ´ÕµÕ¶Õ·Õ¸Õ¹ÕºÕ»Õ¼Õ½Õ¾Õ¿Ö€Öւփքօֆևᴀá´á´‚ᴃᴄᴅᴆᴇᴈᴉᴊᴋᴌá´á´Žá´á´á´‘ᴒᴓᴔᴕᴖᴗᴘᴙᴚᴛᴜá´á´žá´Ÿá´ á´¡á´¢á´£á´¤á´¥á´¦á´§á´¨á´©á´ªá´«áµ¢áµ£áµ¤áµ¥áµ¦áµ§áµ¨áµ©áµªáµ«áµ¬áµ­áµ®áµ¯áµ°áµ±áµ²áµ³áµ´áµµáµ¶áµ·áµ¹áµºáµ»áµ¼áµ½áµ¾áµ¿á¶€á¶á¶‚ᶃᶄᶅᶆᶇᶈᶉᶊᶋᶌá¶á¶Žá¶á¶á¶‘ᶒᶓᶔᶕᶖᶗᶘᶙᶚá¸á¸ƒá¸…ḇḉḋá¸á¸á¸‘ḓḕḗḙḛá¸á¸Ÿá¸¡á¸£á¸¥á¸§á¸©á¸«á¸­á¸¯á¸±á¸³á¸µá¸·á¸¹á¸»á¸½á¸¿á¹á¹ƒá¹…ṇṉṋá¹á¹á¹‘ṓṕṗṙṛá¹á¹Ÿá¹¡á¹£á¹¥á¹§á¹©á¹«á¹­á¹¯á¹±á¹³á¹µá¹·á¹¹á¹»á¹½á¹¿áºáºƒáº…ẇẉẋáºáºáº‘ẓẕẖẗẘẙẚẛạảấầẩẫậắằẳẵặẹẻẽếá»á»ƒá»…ệỉịá»á»á»‘ồổỗộớá»á»Ÿá»¡á»£á»¥á»§á»©á»«á»­á»¯á»±á»³á»µá»·á»¹á¼€á¼á¼‚ἃἄἅἆἇá¼á¼‘ἒἓἔἕἠἡἢἣἤἥἦἧἰἱἲἳἴἵἶἷὀá½á½‚ὃὄὅá½á½‘ὒὓὔὕὖὗὠὡὢὣὤὥὦὧὰάὲέὴήὶίὸόὺύὼώᾀá¾á¾‚ᾃᾄᾅᾆᾇá¾á¾‘ᾒᾓᾔᾕᾖᾗᾠᾡᾢᾣᾤᾥᾦᾧᾰᾱᾲᾳᾴᾶᾷιῂῃῄῆῇá¿á¿‘ῒΐῖῗῠῡῢΰῤῥῦῧῲῳῴῶῷâ²â²ƒâ²…ⲇⲉⲋâ²â²â²‘ⲓⲕⲗⲙⲛâ²â²Ÿâ²¡â²£â²¥â²§â²©â²«â²­â²¯â²±â²³â²µâ²·â²¹â²»â²½â²¿â³â³ƒâ³…ⳇⳉⳋâ³â³â³‘ⳓⳕⳗⳙⳛâ³â³Ÿâ³¡â³£â³¤â´€â´â´‚ⴃⴄⴅⴆⴇⴈⴉⴊⴋⴌâ´â´Žâ´â´â´‘ⴒⴓⴔⴕⴖⴗⴘⴙⴚⴛⴜâ´â´žâ´Ÿâ´ â´¡â´¢â´£â´¤â´¥ï¬€ï¬ï¬‚ffifflſtstﬓﬔﬕﬖﬗ\d-_^]/8 - -/^[^d]*?$/ - abc - -/^[^d]*?$/8 - abc - -/^[^d]*?$/i - abc - -/^[^d]*?$/8i - abc - -/(?i)[\xc3\xa9\xc3\xbd]|[\xc3\xa9\xc3\xbdA]/8 - -/ End of testinput4 / diff --git a/libs/pcre/testdata/testinput5 b/libs/pcre/testdata/testinput5 deleted file mode 100644 index 38e22b8c01..0000000000 --- a/libs/pcre/testdata/testinput5 +++ /dev/null @@ -1,488 +0,0 @@ -/\x{100}/8DZ - -/\x{1000}/8DZ - -/\x{10000}/8DZ - -/\x{100000}/8DZ - -/\x{1000000}/8DZ - -/\x{4000000}/8DZ - -/\x{7fffFFFF}/8DZ - -/[\x{ff}]/8DZ - -/[\x{100}]/8DZ - -/\x{ffffffff}/8 - -/\x{100000000}/8 - -/^\x{100}a\x{1234}/8 - \x{100}a\x{1234}bcd - -/\x80/8DZ - -/\xff/8DZ - -/\x{0041}\x{2262}\x{0391}\x{002e}/DZ8 - \x{0041}\x{2262}\x{0391}\x{002e} - -/\x{D55c}\x{ad6d}\x{C5B4}/DZ8 - \x{D55c}\x{ad6d}\x{C5B4} - -/\x{65e5}\x{672c}\x{8a9e}/DZ8 - \x{65e5}\x{672c}\x{8a9e} - -/\x{80}/DZ8 - -/\x{084}/DZ8 - -/\x{104}/DZ8 - -/\x{861}/DZ8 - -/\x{212ab}/DZ8 - -/.{3,5}X/DZ8 - \x{212ab}\x{212ab}\x{212ab}\x{861}X - - -/.{3,5}?/DZ8 - \x{212ab}\x{212ab}\x{212ab}\x{861} - -/-- These tests are here rather than in testinput4 because Perl 5.6 has some -problems with UTF-8 support, in the area of \x{..} where the value is < 255. -It grumbles about invalid UTF-8 strings. --/ - -/^[a\x{c0}]b/8 - \x{c0}b - -/^([a\x{c0}]*?)aa/8 - a\x{c0}aaaa/ - -/^([a\x{c0}]*?)aa/8 - a\x{c0}aaaa/ - a\x{c0}a\x{c0}aaa/ - -/^([a\x{c0}]*)aa/8 - a\x{c0}aaaa/ - a\x{c0}a\x{c0}aaa/ - -/^([a\x{c0}]*)a\x{c0}/8 - a\x{c0}aaaa/ - a\x{c0}a\x{c0}aaa/ - -/-- --/ - -/(?<=\C)X/8 - Should produce an error diagnostic - -/-- This one is here not because it's different to Perl, but because the way -the captured single-byte is displayed. (In Perl it becomes a character, and you -can't tell the difference.) --/ - -/X(\C)(.*)/8 - X\x{1234} - X\nabc - -/^[ab]/8DZ - bar - *** Failers - c - \x{ff} - \x{100} - -/^[^ab]/8DZ - c - \x{ff} - \x{100} - *** Failers - aaa - -/[^ab\xC0-\xF0]/8SDZ - \x{f1} - \x{bf} - \x{100} - \x{1000} - *** Failers - \x{c0} - \x{f0} - -/Ä€{3,4}/8SDZ - \x{100}\x{100}\x{100}\x{100\x{100} - -/(\x{100}+|x)/8SDZ - -/(\x{100}*a|x)/8SDZ - -/(\x{100}{0,2}a|x)/8SDZ - -/(\x{100}{1,2}a|x)/8SDZ - -/\x{100}*(\d+|"(?1)")/8 - 1234 - "1234" - \x{100}1234 - "\x{100}1234" - \x{100}\x{100}12ab - \x{100}\x{100}"12" - *** Failers - \x{100}\x{100}abcd - -/\x{100}/8DZ - -/\x{100}*/8DZ - -/a\x{100}*/8DZ - -/ab\x{100}*/8DZ - -/a\x{100}\x{101}*/8DZ - -/a\x{100}\x{101}+/8DZ - -/\x{100}*A/8DZ - A - -/\x{100}*\d(?R)/8DZ - -/[^\x{c4}]/DZ - -/[^\x{c4}]/8DZ - -/[\x{100}]/8DZ - \x{100} - Z\x{100} - \x{100}Z - *** Failers - -/[Z\x{100}]/8DZ - Z\x{100} - \x{100} - \x{100}Z - *** Failers - -/[\x{200}-\x{100}]/8 - -/[Ä€-Ä„]/8 - \x{100} - \x{104} - *** Failers - \x{105} - \x{ff} - -/[z-\x{100}]/8DZ - -/[z\Qa-d]Ä€\E]/8DZ - \x{100} - Ä€ - -/[\xFF]/DZ - >\xff< - -/[\xff]/DZ8 - >\x{ff}< - -/[^\xFF]/DZ - -/[^\xff]/8DZ - -/[Ä-Ãœ]/8 - Ö # Matches without Study - \x{d6} - -/[Ä-Ãœ]/8S - Ö <-- Same with Study - \x{d6} - -/[\x{c4}-\x{dc}]/8 - Ö # Matches without Study - \x{d6} - -/[\x{c4}-\x{dc}]/8S - Ö <-- Same with Study - \x{d6} - -/[Ã]/8 - -/Ã/8 - -/ÃÃÃxxx/8 - -/ÃÃÃxxx/8?DZ - -/abc/8 - Ã] - à - ÃÃà - ÃÃÃ\? - -/anything/8 - \xc0\x80 - \xc1\x8f - \xe0\x9f\x80 - \xf0\x8f\x80\x80 - \xf8\x87\x80\x80\x80 - \xfc\x83\x80\x80\x80\x80 - \xfe\x80\x80\x80\x80\x80 - \xff\x80\x80\x80\x80\x80 - \xc3\x8f - \xe0\xaf\x80 - \xe1\x80\x80 - \xf0\x9f\x80\x80 - \xf1\x8f\x80\x80 - \xf8\x88\x80\x80\x80 - \xf9\x87\x80\x80\x80 - \xfc\x84\x80\x80\x80\x80 - \xfd\x83\x80\x80\x80\x80 - \?\xf8\x88\x80\x80\x80 - \?\xf9\x87\x80\x80\x80 - \?\xfc\x84\x80\x80\x80\x80 - \?\xfd\x83\x80\x80\x80\x80 - -/\x{100}abc(xyz(?1))/8DZ - -/[^\x{100}]abc(xyz(?1))/8DZ - -/[ab\x{100}]abc(xyz(?1))/8DZ - -/(\x{100}(b(?2)c))?/DZ8 - -/(\x{100}(b(?2)c)){0,2}/DZ8 - -/(\x{100}(b(?1)c))?/DZ8 - -/(\x{100}(b(?1)c)){0,2}/DZ8 - -/\W/8 - A.B - A\x{100}B - -/\w/8 - \x{100}X - -/a\x{1234}b/P8 - a\x{1234}b - -/^\ሴ/8DZ - -/\777/I - -/\777/8I - \x{1ff} - \777 - -/\x{100}*\d/8DZ - -/\x{100}*\s/8DZ - -/\x{100}*\w/8DZ - -/\x{100}*\D/8DZ - -/\x{100}*\S/8DZ - -/\x{100}*\W/8DZ - -/\x{100}+\x{200}/8DZ - -/\x{100}+X/8DZ - -/X+\x{200}/8DZ - -/()()()()()()()()()() - ()()()()()()()()()() - ()()()()()()()()()() - ()()()()()()()()()() - A (x) (?41) B/8x - AxxB - -/^[\x{100}\E-\Q\E\x{150}]/BZ8 - -/^[\QÄ€\E-\QÅ\E]/BZ8 - -/^[\QÄ€\E-\QÅ\E/BZ8 - -/^abc./mgx8 - abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x{0085}abc7 \x{2028}abc8 \x{2029}abc9 JUNK - -/abc.$/mgx8 - abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x{0085} abc7\x{2028} abc8\x{2029} abc9 - -/^a\Rb/8 - a\nb - a\rb - a\r\nb - a\x0bb - a\x0cb - a\x{85}b - a\x{2028}b - a\x{2029}b - ** Failers - a\n\rb - -/^a\R*b/8 - ab - a\nb - a\rb - a\r\nb - a\x0bb - a\x0c\x{2028}\x{2029}b - a\x{85}b - a\n\rb - a\n\r\x{85}\x0cb - -/^a\R+b/8 - a\nb - a\rb - a\r\nb - a\x0bb - a\x0c\x{2028}\x{2029}b - a\x{85}b - a\n\rb - a\n\r\x{85}\x0cb - ** Failers - ab - -/^a\R{1,3}b/8 - a\nb - a\n\rb - a\n\r\x{85}b - a\r\n\r\nb - a\r\n\r\n\r\nb - a\n\r\n\rb - a\n\n\r\nb - ** Failers - a\n\n\n\rb - a\r - -/\H\h\V\v/8 - X X\x0a - X\x09X\x0b - ** Failers - \x{a0} X\x0a - -/\H*\h+\V?\v{3,4}/8 - \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a - \x09\x20\x{a0}\x0a\x0b\x0c\x0d\x0a - \x09\x20\x{a0}\x0a\x0b\x0c - ** Failers - \x09\x20\x{a0}\x0a\x0b - -/\H\h\V\v/8 - \x{3001}\x{3000}\x{2030}\x{2028} - X\x{180e}X\x{85} - ** Failers - \x{2009} X\x0a - -/\H*\h+\V?\v{3,4}/8 - \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x0c\x0d\x0a - \x09\x{205f}\x{a0}\x0a\x{2029}\x0c\x{2028}\x0a - \x09\x20\x{202f}\x0a\x0b\x0c - ** Failers - \x09\x{200a}\x{a0}\x{2028}\x0b - -/[\h]/8BZ - >\x{1680} - -/[\h]{3,}/8BZ - >\x{1680}\x{180e}\x{2000}\x{2003}\x{200a}\x{202f}\x{205f}\x{3000}< - -/[\v]/8BZ - -/[\H]/8BZ - -/[\V]/8BZ - -/.*$/8 - \x{1ec5} - -/-- This tests the stricter UTF-8 check according to RFC 3629. --/ - -/X/8 - \x{0}\x{d7ff}\x{e000}\x{10ffff} - \x{d800} - \x{d800}\? - \x{da00} - \x{da00}\? - \x{dfff} - \x{dfff}\? - \x{110000} - \x{110000}\? - \x{2000000} - \x{2000000}\? - \x{7fffffff} - \x{7fffffff}\? - -/a\Rb/I8 - a\rb - a\nb - a\r\nb - ** Failers - a\x{85}b - a\x0bb - -/a\Rb/I8 - a\rb - a\nb - a\r\nb - a\x{85}b - a\x0bb - ** Failers - a\x{85}b\ - a\x0bb\ - -/a\R?b/I8 - a\rb - a\nb - a\r\nb - ** Failers - a\x{85}b - a\x0bb - -/a\R?b/I8 - a\rb - a\nb - a\r\nb - a\x{85}b - a\x0bb - ** Failers - a\x{85}b\ - a\x0bb\ - -/.*a.*=.b.*/8 - QQQ\x{2029}ABCaXYZ=!bPQR - ** Failers - a\x{2029}b - \x61\xe2\x80\xa9\x62 - -/[[:a\x{100}b:]]/8 - -/a[^]b/8 - a\x{1234}b - a\nb - ** Failers - ab - -/a[^]+b/8 - aXb - a\nX\nX\x{1234}b - ** Failers - ab - -/(\x{de})\1/ - \x{de}\x{de} - \x{123} - -/X/8f - A\x{1ec5}ABCXYZ - -/(*UTF8)\x{1234}/ - abcd\x{1234}pqr - -/(*CRLF)(*UTF8)(*BSR_UNICODE)a\Rb/I - -/ End of testinput5 / diff --git a/libs/pcre/testdata/testinput6 b/libs/pcre/testdata/testinput6 deleted file mode 100644 index 628646d7d3..0000000000 --- a/libs/pcre/testdata/testinput6 +++ /dev/null @@ -1,954 +0,0 @@ -/^\pC\pL\pM\pN\pP\pS\pZ3 - *** Failers - xyzabc - xyzabc\>2 - -/x\dy\Dz/ - x9yzz - x0y+z - *** Failers - xyz - xxy0z - -/x\sy\Sz/ - x yzz - x y+z - *** Failers - xyz - xxyyz - -/x\wy\Wz/ - xxy+z - *** Failers - xxy0z - x+y+z - -/x.y/ - x+y - x-y - *** Failers - x\ny - -/x.y/s - x+y - x-y - x\ny - -/(a.b(?s)c.d|x.y)p.q/ - a+bc+dp+q - a+bc\ndp+q - x\nyp+q - *** Failers - a\nbc\ndp+q - a+bc\ndp\nq - x\nyp\nq - -/a\d\z/ - ba0 - *** Failers - ba0\n - ba0\ncd - -/a\d\z/m - ba0 - *** Failers - ba0\n - ba0\ncd - -/a\d\Z/ - ba0 - ba0\n - *** Failers - ba0\ncd - -/a\d\Z/m - ba0 - ba0\n - *** Failers - ba0\ncd - -/a\d$/ - ba0 - ba0\n - *** Failers - ba0\ncd - -/a\d$/m - ba0 - ba0\n - ba0\ncd - *** Failers - -/abc/i - abc - aBc - ABC - -/[^a]/ - abcd - -/ab?\w/ - abz - abbz - azz - -/x{0,3}yz/ - ayzq - axyzq - axxyz - axxxyzq - axxxxyzq - *** Failers - ax - axx - -/x{3}yz/ - axxxyzq - axxxxyzq - *** Failers - ax - axx - ayzq - axyzq - axxyz - -/x{2,3}yz/ - axxyz - axxxyzq - axxxxyzq - *** Failers - ax - axx - ayzq - axyzq - -/[^a]+/ - bac - bcdefax - *** Failers - aaaaa - -/[^a]*/ - bac - bcdefax - *** Failers - aaaaa - -/[^a]{3,5}/ - xyz - awxyza - abcdefa - abcdefghijk - *** Failers - axya - axa - aaaaa - -/\d*/ - 1234b567 - xyz - -/\D*/ - a1234b567 - xyz - -/\d+/ - ab1234c56 - *** Failers - xyz - -/\D+/ - ab123c56 - *** Failers - 789 - -/\d?A/ - 045ABC - ABC - *** Failers - XYZ - -/\D?A/ - ABC - BAC - 9ABC - *** Failers - -/a+/ - aaaa - -/^.*xyz/ - xyz - ggggggggxyz - -/^.+xyz/ - abcdxyz - axyz - *** Failers - xyz - -/^.?xyz/ - xyz - cxyz - -/^\d{2,3}X/ - 12X - 123X - *** Failers - X - 1X - 1234X - -/^[abcd]\d/ - a45 - b93 - c99z - d04 - *** Failers - e45 - abcd - abcd1234 - 1234 - -/^[abcd]*\d/ - a45 - b93 - c99z - d04 - abcd1234 - 1234 - *** Failers - e45 - abcd - -/^[abcd]+\d/ - a45 - b93 - c99z - d04 - abcd1234 - *** Failers - 1234 - e45 - abcd - -/^a+X/ - aX - aaX - -/^[abcd]?\d/ - a45 - b93 - c99z - d04 - 1234 - *** Failers - abcd1234 - e45 - -/^[abcd]{2,3}\d/ - ab45 - bcd93 - *** Failers - 1234 - a36 - abcd1234 - ee45 - -/^(abc)*\d/ - abc45 - abcabcabc45 - 42xyz - *** Failers - -/^(abc)+\d/ - abc45 - abcabcabc45 - *** Failers - 42xyz - -/^(abc)?\d/ - abc45 - 42xyz - *** Failers - abcabcabc45 - -/^(abc){2,3}\d/ - abcabc45 - abcabcabc45 - *** Failers - abcabcabcabc45 - abc45 - 42xyz - -/1(abc|xyz)2(?1)3/ - 1abc2abc3456 - 1abc2xyz3456 - -/^(a*\w|ab)=(a*\w|ab)/ - ab=ab - -/^(a*\w|ab)=(?1)/ - ab=ab - -/^([^()]|\((?1)*\))*$/ - abc - a(b)c - a(b(c))d - *** Failers) - a(b(c)d - -/^>abc>([^()]|\((?1)*\))*abc>123abc>1(2)3abc>(1(2)3)a*)\d/ - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa9876 - *** Failers - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - -/< (?: (?(R) \d++ | [^<>]*+) | (?R)) * >/x - <> - - hij> - hij> - def> - - *** Failers - 3 - *** Failers - defabcxyz - -/^abcdef/ - ab\P - abcde\P - abcdef\P - *** Failers - abx\P - -/^a{2,4}\d+z/ - a\P - aa\P - aa2\P - aaa\P - aaa23\P - aaaa12345\P - aa0z\P - aaaa4444444444444z\P - *** Failers - az\P - aaaaa\P - a56\P - -/^abcdef/ - abc\P - def\R - -/(?<=foo)bar/ - xyzfo\P - foob\P\>2 - foobar...\R\P\>4 - xyzfo\P - foobar\>2 - *** Failers - xyzfo\P - obar\R - -/(ab*(cd|ef))+X/ - adfadadaklhlkalkajhlkjahdfasdfasdfladsfjkj\P\Z - lkjhlkjhlkjhlkjhabbbbbbcdaefabbbbbbbefa\P\B\Z - cdabbbbbbbb\P\R\B\Z - efabbbbbbbbbbbbbbbb\P\R\B\Z - bbbbbbbbbbbbcdXyasdfadf\P\R\B\Z - -/(a|b)/SF>testsavedregex ->>aaabxyzpqrrrabbxyyyypqAzz - >aaaabxyzpqrrrabbxyyyypqAzz - >>>>abcxyzpqrrrabbxyyyypqAzz - *** Failers - abxyzpqrrabbxyyyypqAzz - abxyzpqrrrrabbxyyyypqAzz - abxyzpqrrrabxyyyypqAzz - aaaabcxyzzzzpqrrrabbbxyyyyyypqAzz - aaaabcxyzzzzpqrrrabbbxyyypqAzz - aaabcxyzpqrrrabbxyyyypqqqqqqqAzz - -/^(abc){1,2}zz/ - abczz - abcabczz - *** Failers - zz - abcabcabczz - >>abczz - -/^(b+?|a){1,2}?c/ - bc - bbc - bbbc - bac - bbac - aac - abbbbbbbbbbbc - bbbbbbbbbbbac - *** Failers - aaac - abbbbbbbbbbbac - -/^(b+|a){1,2}c/ - bc - bbc - bbbc - bac - bbac - aac - abbbbbbbbbbbc - bbbbbbbbbbbac - *** Failers - aaac - abbbbbbbbbbbac - -/^(b+|a){1,2}?bc/ - bbc - -/^(b*|ba){1,2}?bc/ - babc - bbabc - bababc - *** Failers - bababbc - babababc - -/^(ba|b*){1,2}?bc/ - babc - bbabc - bababc - *** Failers - bababbc - babababc - -/^\ca\cA\c[\c{\c:/ - \x01\x01\e;z - -/^[ab\]cde]/ - athing - bthing - ]thing - cthing - dthing - ething - *** Failers - fthing - [thing - \\thing - -/^[]cde]/ - ]thing - cthing - dthing - ething - *** Failers - athing - fthing - -/^[^ab\]cde]/ - fthing - [thing - \\thing - *** Failers - athing - bthing - ]thing - cthing - dthing - ething - -/^[^]cde]/ - athing - fthing - *** Failers - ]thing - cthing - dthing - ething - -/^\/ - - -/^ÿ/ - ÿ - -/^[0-9]+$/ - 0 - 1 - 2 - 3 - 4 - 5 - 6 - 7 - 8 - 9 - 10 - 100 - *** Failers - abc - -/^.*nter/ - enter - inter - uponter - -/^xxx[0-9]+$/ - xxx0 - xxx1234 - *** Failers - xxx - -/^.+[0-9][0-9][0-9]$/ - x123 - xx123 - 123456 - *** Failers - 123 - x1234 - -/^.+?[0-9][0-9][0-9]$/ - x123 - xx123 - 123456 - *** Failers - 123 - x1234 - -/^([^!]+)!(.+)=apquxz\.ixr\.zzz\.ac\.uk$/ - abc!pqr=apquxz.ixr.zzz.ac.uk - *** Failers - !pqr=apquxz.ixr.zzz.ac.uk - abc!=apquxz.ixr.zzz.ac.uk - abc!pqr=apquxz:ixr.zzz.ac.uk - abc!pqr=apquxz.ixr.zzz.ac.ukk - -/:/ - Well, we need a colon: somewhere - *** Fail if we don't - -/([\da-f:]+)$/i - 0abc - abc - fed - E - :: - 5f03:12C0::932e - fed def - Any old stuff - *** Failers - 0zzz - gzzz - fed\x20 - Any old rubbish - -/^.*\.(\d{1,3})\.(\d{1,3})\.(\d{1,3})$/ - .1.2.3 - A.12.123.0 - *** Failers - .1.2.3333 - 1.2.3 - 1234.2.3 - -/^(\d+)\s+IN\s+SOA\s+(\S+)\s+(\S+)\s*\(\s*$/ - 1 IN SOA non-sp1 non-sp2( - 1 IN SOA non-sp1 non-sp2 ( - *** Failers - 1IN SOA non-sp1 non-sp2( - -/^[a-zA-Z\d][a-zA-Z\d\-]*(\.[a-zA-Z\d][a-zA-z\d\-]*)*\.$/ - a. - Z. - 2. - ab-c.pq-r. - sxk.zzz.ac.uk. - x-.y-. - *** Failers - -abc.peq. - -/^\*\.[a-z]([a-z\-\d]*[a-z\d]+)?(\.[a-z]([a-z\-\d]*[a-z\d]+)?)*$/ - *.a - *.b0-a - *.c3-b.c - *.c-a.b-c - *** Failers - *.0 - *.a- - *.a-b.c- - *.c-a.0-c - -/^(?=ab(de))(abd)(e)/ - abde - -/^(?!(ab)de|x)(abd)(f)/ - abdf - -/^(?=(ab(cd)))(ab)/ - abcd - -/^[\da-f](\.[\da-f])*$/i - a.b.c.d - A.B.C.D - a.b.c.1.2.3.C - -/^\".*\"\s*(;.*)?$/ - \"1234\" - \"abcd\" ; - \"\" ; rhubarb - *** Failers - \"1234\" : things - -/^$/ - \ - *** Failers - -/ ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/x - ab c - *** Failers - abc - ab cde - -/(?x) ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/ - ab c - *** Failers - abc - ab cde - -/^ a\ b[c ]d $/x - a bcd - a b d - *** Failers - abcd - ab d - -/^(a(b(c)))(d(e(f)))(h(i(j)))(k(l(m)))$/ - abcdefhijklm - -/^(?:a(b(c)))(?:d(e(f)))(?:h(i(j)))(?:k(l(m)))$/ - abcdefhijklm - -/^[\w][\W][\s][\S][\d][\D][\b][\n][\c]][\022]/ - a+ Z0+\x08\n\x1d\x12 - -/^[.^$|()*+?{,}]+/ - .^\$(*+)|{?,?} - -/^a*\w/ - z - az - aaaz - a - aa - aaaa - a+ - aa+ - -/^a*?\w/ - z - az - aaaz - a - aa - aaaa - a+ - aa+ - -/^a+\w/ - az - aaaz - aa - aaaa - aa+ - -/^a+?\w/ - az - aaaz - aa - aaaa - aa+ - -/^\d{8}\w{2,}/ - 1234567890 - 12345678ab - 12345678__ - *** Failers - 1234567 - -/^[aeiou\d]{4,5}$/ - uoie - 1234 - 12345 - aaaaa - *** Failers - 123456 - -/^[aeiou\d]{4,5}?/ - uoie - 1234 - 12345 - aaaaa - 123456 - -/^From +([^ ]+) +[a-zA-Z][a-zA-Z][a-zA-Z] +[a-zA-Z][a-zA-Z][a-zA-Z] +[0-9]?[0-9] +[0-9][0-9]:[0-9][0-9]/ - From abcd Mon Sep 01 12:33:02 1997 - -/^From\s+\S+\s+([a-zA-Z]{3}\s+){2}\d{1,2}\s+\d\d:\d\d/ - From abcd Mon Sep 01 12:33:02 1997 - From abcd Mon Sep 1 12:33:02 1997 - *** Failers - From abcd Sep 01 12:33:02 1997 - -/^12.34/s - 12\n34 - 12\r34 - -/\w+(?=\t)/ - the quick brown\t fox - -/foo(?!bar)(.*)/ - foobar is foolish see? - -/(?:(?!foo)...|^.{0,2})bar(.*)/ - foobar crowbar etc - barrel - 2barrel - A barrel - -/^(\D*)(?=\d)(?!123)/ - abc456 - *** Failers - abc123 - -/^1234(?# test newlines - inside)/ - 1234 - -/^1234 #comment in extended re - /x - 1234 - -/#rhubarb - abcd/x - abcd - -/^abcd#rhubarb/x - abcd - -/(?!^)abc/ - the abc - *** Failers - abc - -/(?=^)abc/ - abc - *** Failers - the abc - -/^[ab]{1,3}(ab*|b)/ - aabbbbb - -/^[ab]{1,3}?(ab*|b)/ - aabbbbb - -/^[ab]{1,3}?(ab*?|b)/ - aabbbbb - -/^[ab]{1,3}(ab*?|b)/ - aabbbbb - -/ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* # optional leading comment -(?: (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) # initial word -(?: (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) )* # further okay, if led by a period -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* -# address -| # or -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) # one word, optionally followed by.... -(?: -[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] | # atom and space parts, or... -\( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) | # comments, or... - -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -# quoted strings -)* -< (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* # leading < -(?: @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* - -(?: (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* , (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* -)* # further okay, if led by comma -: # closing colon -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* )? # optional route -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) # initial word -(?: (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) )* # further okay, if led by a period -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* -# address spec -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* > # trailing > -# name and address -) (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* # optional trailing comment -/x - Alan Other - - user\@dom.ain - \"A. Other\" (a comment) - A. Other (a comment) - \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay - A missing angle @,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# additional words -)* -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -# address -| # or -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -# leading word -[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] * # "normal" atoms and or spaces -(?: -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -| -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -) # "special" comment or quoted string -[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] * # more "normal" -)* -< -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# < -(?: -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -(?: , -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -)* # additional domains -: -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)? # optional route -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# additional words -)* -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -# address spec -> # > -# name and address -) -/x - Alan Other - - user\@dom.ain - \"A. Other\" (a comment) - A. Other (a comment) - \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay - A missing angle - a\rb - *** Failers - a\nb - -/abc$/ - abc - abc\n - *** Failers - abc\ndef - -/(abc)\123/ - abc\x53 - -/(abc)\223/ - abc\x93 - -/(abc)\323/ - abc\xd3 - -/(abc)\100/ - abc\x40 - abc\100 - -/(abc)\1000/ - abc\x400 - abc\x40\x30 - abc\1000 - abc\100\x30 - abc\100\060 - abc\100\60 - -/abc\81/ - abc\081 - abc\0\x38\x31 - -/abc\91/ - abc\091 - abc\0\x39\x31 - -/(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)\12\123/ - abcdefghijk\12S - -/ab\idef/ - abidef - -/a{0}bc/ - bc - -/(a|(bc)){0,0}?xyz/ - xyz - -/abc[\10]de/ - abc\010de - -/abc[\1]de/ - abc\1de - -/(abc)[\1]de/ - abc\1de - -/(?s)a.b/ - a\nb - -/^([^a])([^\b])([^c]*)([^d]{3,4})/ - baNOTccccd - baNOTcccd - baNOTccd - bacccd - *** Failers - anything - b\bc - baccd - -/[^a]/ - Abc - -/[^a]/i - Abc - -/[^a]+/ - AAAaAbc - -/[^a]+/i - AAAaAbc - -/[^a]+/ - bbb\nccc - -/[^k]$/ - abc - *** Failers - abk - -/[^k]{2,3}$/ - abc - kbc - kabc - *** Failers - abk - akb - akk - -/^\d{8,}\@.+[^k]$/ - 12345678\@a.b.c.d - 123456789\@x.y.z - *** Failers - 12345678\@x.y.uk - 1234567\@a.b.c.d - -/[^a]/ - aaaabcd - aaAabcd - -/[^a]/i - aaaabcd - aaAabcd - -/[^az]/ - aaaabcd - aaAabcd - -/[^az]/i - aaaabcd - aaAabcd - -/\000\001\002\003\004\005\006\007\010\011\012\013\014\015\016\017\020\021\022\023\024\025\026\027\030\031\032\033\034\035\036\037\040\041\042\043\044\045\046\047\050\051\052\053\054\055\056\057\060\061\062\063\064\065\066\067\070\071\072\073\074\075\076\077\100\101\102\103\104\105\106\107\110\111\112\113\114\115\116\117\120\121\122\123\124\125\126\127\130\131\132\133\134\135\136\137\140\141\142\143\144\145\146\147\150\151\152\153\154\155\156\157\160\161\162\163\164\165\166\167\170\171\172\173\174\175\176\177\200\201\202\203\204\205\206\207\210\211\212\213\214\215\216\217\220\221\222\223\224\225\226\227\230\231\232\233\234\235\236\237\240\241\242\243\244\245\246\247\250\251\252\253\254\255\256\257\260\261\262\263\264\265\266\267\270\271\272\273\274\275\276\277\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337\340\341\342\343\344\345\346\347\350\351\352\353\354\355\356\357\360\361\362\363\364\365\366\367\370\371\372\373\374\375\376\377/ - \000\001\002\003\004\005\006\007\010\011\012\013\014\015\016\017\020\021\022\023\024\025\026\027\030\031\032\033\034\035\036\037\040\041\042\043\044\045\046\047\050\051\052\053\054\055\056\057\060\061\062\063\064\065\066\067\070\071\072\073\074\075\076\077\100\101\102\103\104\105\106\107\110\111\112\113\114\115\116\117\120\121\122\123\124\125\126\127\130\131\132\133\134\135\136\137\140\141\142\143\144\145\146\147\150\151\152\153\154\155\156\157\160\161\162\163\164\165\166\167\170\171\172\173\174\175\176\177\200\201\202\203\204\205\206\207\210\211\212\213\214\215\216\217\220\221\222\223\224\225\226\227\230\231\232\233\234\235\236\237\240\241\242\243\244\245\246\247\250\251\252\253\254\255\256\257\260\261\262\263\264\265\266\267\270\271\272\273\274\275\276\277\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337\340\341\342\343\344\345\346\347\350\351\352\353\354\355\356\357\360\361\362\363\364\365\366\367\370\371\372\373\374\375\376\377 - -/P[^*]TAIRE[^*]{1,6}?LL/ - xxxxxxxxxxxPSTAIREISLLxxxxxxxxx - -/P[^*]TAIRE[^*]{1,}?LL/ - xxxxxxxxxxxPSTAIREISLLxxxxxxxxx - -/(\.\d\d[1-9]?)\d+/ - 1.230003938 - 1.875000282 - 1.235 - -/(\.\d\d((?=0)|\d(?=\d)))/ - 1.230003938 - 1.875000282 - *** Failers - 1.235 - -/a(?)b/ - ab - -/\b(foo)\s+(\w+)/i - Food is on the foo table - -/foo(.*)bar/ - The food is under the bar in the barn. - -/foo(.*?)bar/ - The food is under the bar in the barn. - -/(.*)(\d*)/ - I have 2 numbers: 53147 - -/(.*)(\d+)/ - I have 2 numbers: 53147 - -/(.*?)(\d*)/ - I have 2 numbers: 53147 - -/(.*?)(\d+)/ - I have 2 numbers: 53147 - -/(.*)(\d+)$/ - I have 2 numbers: 53147 - -/(.*?)(\d+)$/ - I have 2 numbers: 53147 - -/(.*)\b(\d+)$/ - I have 2 numbers: 53147 - -/(.*\D)(\d+)$/ - I have 2 numbers: 53147 - -/^\D*(?!123)/ - ABC123 - -/^(\D*)(?=\d)(?!123)/ - ABC445 - *** Failers - ABC123 - -/^[W-]46]/ - W46]789 - -46]789 - *** Failers - Wall - Zebra - 42 - [abcd] - ]abcd[ - -/^[W-\]46]/ - W46]789 - Wall - Zebra - Xylophone - 42 - [abcd] - ]abcd[ - \\backslash - *** Failers - -46]789 - well - -/\d\d\/\d\d\/\d\d\d\d/ - 01/01/2000 - -/word (?:[a-zA-Z0-9]+ ){0,10}otherword/ - word cat dog elephant mussel cow horse canary baboon snake shark otherword - word cat dog elephant mussel cow horse canary baboon snake shark - -/word (?:[a-zA-Z0-9]+ ){0,300}otherword/ - word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope - -/^(a){0,0}/ - bcd - abc - aab - -/^(a){0,1}/ - bcd - abc - aab - -/^(a){0,2}/ - bcd - abc - aab - -/^(a){0,3}/ - bcd - abc - aab - aaa - -/^(a){0,}/ - bcd - abc - aab - aaa - aaaaaaaa - -/^(a){1,1}/ - bcd - abc - aab - -/^(a){1,2}/ - bcd - abc - aab - -/^(a){1,3}/ - bcd - abc - aab - aaa - -/^(a){1,}/ - bcd - abc - aab - aaa - aaaaaaaa - -/.*\.gif/ - borfle\nbib.gif\nno - -/.{0,}\.gif/ - borfle\nbib.gif\nno - -/.*\.gif/m - borfle\nbib.gif\nno - -/.*\.gif/s - borfle\nbib.gif\nno - -/.*\.gif/ms - borfle\nbib.gif\nno - -/.*$/ - borfle\nbib.gif\nno - -/.*$/m - borfle\nbib.gif\nno - -/.*$/s - borfle\nbib.gif\nno - -/.*$/ms - borfle\nbib.gif\nno - -/.*$/ - borfle\nbib.gif\nno\n - -/.*$/m - borfle\nbib.gif\nno\n - -/.*$/s - borfle\nbib.gif\nno\n - -/.*$/ms - borfle\nbib.gif\nno\n - -/(.*X|^B)/ - abcde\n1234Xyz - BarFoo - *** Failers - abcde\nBar - -/(.*X|^B)/m - abcde\n1234Xyz - BarFoo - abcde\nBar - -/(.*X|^B)/s - abcde\n1234Xyz - BarFoo - *** Failers - abcde\nBar - -/(.*X|^B)/ms - abcde\n1234Xyz - BarFoo - abcde\nBar - -/(?s)(.*X|^B)/ - abcde\n1234Xyz - BarFoo - *** Failers - abcde\nBar - -/(?s:.*X|^B)/ - abcde\n1234Xyz - BarFoo - *** Failers - abcde\nBar - -/^.*B/ - **** Failers - abc\nB - -/(?s)^.*B/ - abc\nB - -/(?m)^.*B/ - abc\nB - -/(?ms)^.*B/ - abc\nB - -/(?ms)^B/ - abc\nB - -/(?s)B$/ - B\n - -/^[0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9]/ - 123456654321 - -/^\d\d\d\d\d\d\d\d\d\d\d\d/ - 123456654321 - -/^[\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d]/ - 123456654321 - -/^[abc]{12}/ - abcabcabcabc - -/^[a-c]{12}/ - abcabcabcabc - -/^(a|b|c){12}/ - abcabcabcabc - -/^[abcdefghijklmnopqrstuvwxy0123456789]/ - n - *** Failers - z - -/abcde{0,0}/ - abcd - *** Failers - abce - -/ab[cd]{0,0}e/ - abe - *** Failers - abcde - -/ab(c){0,0}d/ - abd - *** Failers - abcd - -/a(b*)/ - a - ab - abbbb - *** Failers - bbbbb - -/ab\d{0}e/ - abe - *** Failers - ab1e - -/"([^\\"]+|\\.)*"/ - the \"quick\" brown fox - \"the \\\"quick\\\" brown fox\" - -/.*?/g+ - abc - -/\b/g+ - abc - -/\b/+g - abc - -//g - abc - -/]{0,})>]{0,})>([\d]{0,}\.)(.*)((
([\w\W\s\d][^<>]{0,})|[\s]{0,}))<\/a><\/TD>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><\/TR>/is - 43.Word Processor
(N-1286)Lega lstaff.comCA - Statewide - -/a[^a]b/ - acb - a\nb - -/a.b/ - acb - *** Failers - a\nb - -/a[^a]b/s - acb - a\nb - -/a.b/s - acb - a\nb - -/^(b+?|a){1,2}?c/ - bac - bbac - bbbac - bbbbac - bbbbbac - -/^(b+|a){1,2}?c/ - bac - bbac - bbbac - bbbbac - bbbbbac - -/(?!\A)x/m - x\nb\n - a\bx\n - -/\x0{ab}/ - \0{ab} - -/(A|B)*?CD/ - CD - -/(A|B)*CD/ - CD - -/(?.*/)foo" - /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/it/you/see/ - -"(?>.*/)foo" - /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo - -/(?>(\.\d\d[1-9]?))\d+/ - 1.230003938 - 1.875000282 - *** Failers - 1.235 - -/^((?>\w+)|(?>\s+))*$/ - now is the time for all good men to come to the aid of the party - *** Failers - this is not a line with only words and spaces! - -/(\d+)(\w)/ - 12345a - 12345+ - -/((?>\d+))(\w)/ - 12345a - *** Failers - 12345+ - -/(?>a+)b/ - aaab - -/((?>a+)b)/ - aaab - -/(?>(a+))b/ - aaab - -/(?>b)+/ - aaabbbccc - -/(?>a+|b+|c+)*c/ - aaabbbbccccd - -/(a+|b+|c+)*c/ - aaabbbbccccd - -/((?>[^()]+)|\([^()]*\))+/ - ((abc(ade)ufh()()x - -/\(((?>[^()]+)|\([^()]+\))+\)/ - (abc) - (abc(def)xyz) - *** Failers - ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - -/a(?-i)b/i - ab - Ab - *** Failers - aB - AB - -/(a (?x)b c)d e/ - a bcd e - *** Failers - a b cd e - abcd e - a bcde - -/(a b(?x)c d (?-x)e f)/ - a bcde f - *** Failers - abcdef - -/(a(?i)b)c/ - abc - aBc - *** Failers - abC - aBC - Abc - ABc - ABC - AbC - -/a(?i:b)c/ - abc - aBc - *** Failers - ABC - abC - aBC - -/a(?i:b)*c/ - aBc - aBBc - *** Failers - aBC - aBBC - -/a(?=b(?i)c)\w\wd/ - abcd - abCd - *** Failers - aBCd - abcD - -/(?s-i:more.*than).*million/i - more than million - more than MILLION - more \n than Million - *** Failers - MORE THAN MILLION - more \n than \n million - -/(?:(?s-i)more.*than).*million/i - more than million - more than MILLION - more \n than Million - *** Failers - MORE THAN MILLION - more \n than \n million - -/(?>a(?i)b+)+c/ - abc - aBbc - aBBc - *** Failers - Abc - abAb - abbC - -/(?=a(?i)b)\w\wc/ - abc - aBc - *** Failers - Ab - abC - aBC - -/(?<=a(?i)b)(\w\w)c/ - abxxc - aBxxc - *** Failers - Abxxc - ABxxc - abxxC - -/^(?(?=abc)\w{3}:|\d\d)$/ - abc: - 12 - *** Failers - 123 - xyz - -/^(?(?!abc)\d\d|\w{3}:)$/ - abc: - 12 - *** Failers - 123 - xyz - -/(?(?<=foo)bar|cat)/ - foobar - cat - fcat - focat - *** Failers - foocat - -/(?(?a*)*/ - a - aa - aaaa - -/(abc|)+/ - abc - abcabc - abcabcabc - xyz - -/([a]*)*/ - a - aaaaa - -/([ab]*)*/ - a - b - ababab - aaaabcde - bbbb - -/([^a]*)*/ - b - bbbb - aaa - -/([^ab]*)*/ - cccc - abab - -/([a]*?)*/ - a - aaaa - -/([ab]*?)*/ - a - b - abab - baba - -/([^a]*?)*/ - b - bbbb - aaa - -/([^ab]*?)*/ - c - cccc - baba - -/(?>a*)*/ - a - aaabcde - -/((?>a*))*/ - aaaaa - aabbaa - -/((?>a*?))*/ - aaaaa - aabbaa - -/(?(?=[^a-z]+[a-z]) \d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} ) /x - 12-sep-98 - 12-09-98 - *** Failers - sep-12-98 - -/(?i:saturday|sunday)/ - saturday - sunday - Saturday - Sunday - SATURDAY - SUNDAY - SunDay - -/(a(?i)bc|BB)x/ - abcx - aBCx - bbx - BBx - *** Failers - abcX - aBCX - bbX - BBX - -/^([ab](?i)[cd]|[ef])/ - ac - aC - bD - elephant - Europe - frog - France - *** Failers - Africa - -/^(ab|a(?i)[b-c](?m-i)d|x(?i)y|z)/ - ab - aBd - xy - xY - zebra - Zambesi - *** Failers - aCD - XY - -/(?<=foo\n)^bar/m - foo\nbar - *** Failers - bar - baz\nbar - -/(?<=(?]&/ - <&OUT - -/(?:(f)(o)(o)|(b)(a)(r))*/ - foobar - -/(?<=a)b/ - ab - *** Failers - cb - b - -/(?a+)ab/ - -/(?>a+)b/ - aaab - -/([[:]+)/ - a:[b]: - -/([[=]+)/ - a=[b]= - -/([[.]+)/ - a.[b]. - -/((?>a+)b)/ - aaab - -/(?>(a+))b/ - aaab - -/((?>[^()]+)|\([^()]*\))+/ - ((abc(ade)ufh()()x - -/a\Z/ - *** Failers - aaab - a\nb\n - -/b\Z/ - a\nb\n - -/b\z/ - -/b\Z/ - a\nb - -/b\z/ - a\nb - *** Failers - -/(?>.*)(?<=(abcd|wxyz))/ - alphabetabcd - endingwxyz - *** Failers - a rather long string that doesn't end with one of them - -/word (?>(?:(?!otherword)[a-zA-Z0-9]+ ){0,30})otherword/ - word cat dog elephant mussel cow horse canary baboon snake shark otherword - word cat dog elephant mussel cow horse canary baboon snake shark - -/word (?>[a-zA-Z0-9]+ ){0,30}otherword/ - word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope - -/(?<=\d{3}(?!999))foo/ - 999foo - 123999foo - *** Failers - 123abcfoo - -/(?<=(?!...999)\d{3})foo/ - 999foo - 123999foo - *** Failers - 123abcfoo - -/(?<=\d{3}(?!999)...)foo/ - 123abcfoo - 123456foo - *** Failers - 123999foo - -/(?<=\d{3}...)(?Z)+|A)*/ - ZABCDEFG - -/((?>)+|A)*/ - ZABCDEFG - -/a*/g - abbab - -/^[a-\d]/ - abcde - -things - 0digit - *** Failers - bcdef - -/^[\d-a]/ - abcde - -things - 0digit - *** Failers - bcdef - -/[[:space:]]+/ - > \x09\x0a\x0c\x0d\x0b< - -/[[:blank:]]+/ - > \x09\x0a\x0c\x0d\x0b< - -/[\s]+/ - > \x09\x0a\x0c\x0d\x0b< - -/\s+/ - > \x09\x0a\x0c\x0d\x0b< - -/a b/x - ab - -/(?!\A)x/m - a\nxb\n - -/(?!^)x/m - a\nxb\n - -/abc\Qabc\Eabc/ - abcabcabc - -/abc\Q(*+|\Eabc/ - abc(*+|abc - -/ abc\Q abc\Eabc/x - abc abcabc - *** Failers - abcabcabc - -/abc#comment - \Q#not comment - literal\E/x - abc#not comment\n literal - -/abc#comment - \Q#not comment - literal/x - abc#not comment\n literal - -/abc#comment - \Q#not comment - literal\E #more comment - /x - abc#not comment\n literal - -/abc#comment - \Q#not comment - literal\E #more comment/x - abc#not comment\n literal - -/\Qabc\$xyz\E/ - abc\\\$xyz - -/\Qabc\E\$\Qxyz\E/ - abc\$xyz - -/\Gabc/ - abc - *** Failers - xyzabc - -/\Gabc./g - abc1abc2xyzabc3 - -/abc./g - abc1abc2xyzabc3 - -/a(?x: b c )d/ - XabcdY - *** Failers - Xa b c d Y - -/((?x)x y z | a b c)/ - XabcY - AxyzB - -/(?i)AB(?-i)C/ - XabCY - *** Failers - XabcY - -/((?i)AB(?-i)C|D)E/ - abCE - DE - *** Failers - abcE - abCe - dE - De - -/[z\Qa-d]\E]/ - z - a - - - d - ] - *** Failers - b - -/[\z\C]/ - z - C - -/\M/ - M - -/(a+)*b/ - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - -/(?i)reg(?:ul(?:[aä]|ae)r|ex)/ - REGular - regulaer - Regex - regulär - -/Åæåä[à-ÿÀ-ß]+/ - Åæåäà - Åæåäÿ - ÅæåäÀ - Åæåäß - -/(?<=Z)X./ - \x84XAZXB - -/^(?(2)a|(1)(2))+$/ - 123a - -/(?<=a|bbbb)c/ - ac - bbbbc - -/abc/>testsavedregex -testsavedregex -testsavedregex -testsavedregex - - xyz\r\nabc\ - xyz\rabc\ - xyz\r\nabc\ - ** Failers - xyz\nabc\ - xyz\r\nabc\ - xyz\nabc\ - xyz\rabc\ - xyz\rabc\ - -/abc$/m - xyzabc - xyzabc\n - xyzabc\npqr - xyzabc\r\ - xyzabc\rpqr\ - xyzabc\r\n\ - xyzabc\r\npqr\ - ** Failers - xyzabc\r - xyzabc\rpqr - xyzabc\r\n - xyzabc\r\npqr - -/^abc/m - xyz\rabcdef - xyz\nabcdef\ - ** Failers - xyz\nabcdef - -/^abc/m - xyz\nabcdef - xyz\rabcdef\ - ** Failers - xyz\rabcdef - -/^abc/m - xyz\r\nabcdef - xyz\rabcdef\ - ** Failers - xyz\rabcdef - -/.*/ - abc\ndef - abc\rdef - abc\r\ndef - \abc\ndef - \abc\rdef - \abc\r\ndef - \abc\ndef - \abc\rdef - \abc\r\ndef - -/\w+(.)(.)?def/s - abc\ndef - abc\rdef - abc\r\ndef - -/^\w+=.*(\\\n.*)*/ - abc=xyz\\\npqr - -/^(a()*)*/ - aaaa - -/^(?:a(?:(?:))*)*/ - aaaa - -/^(a()+)+/ - aaaa - -/^(?:a(?:(?:))+)+/ - aaaa - -/(a|)*\d/ - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 - -/(?>a|)*\d/ - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 - -/(?:a|)*\d/ - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 - -/^a.b/ - a\rb - a\nb\ - ** Failers - a\nb - a\nb\ - a\rb\ - a\rb\ - -/^abc./mgx - abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x85abc7 JUNK - -/abc.$/mgx - abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x85 abc9 - -/^a\Rb/ - a\nb - a\rb - a\r\nb - a\x0bb - a\x0cb - a\x85b - ** Failers - a\n\rb - -/^a\R*b/ - ab - a\nb - a\rb - a\r\nb - a\x0bb - a\x0cb - a\x85b - a\n\rb - a\n\r\x85\x0cb - -/^a\R+b/ - a\nb - a\rb - a\r\nb - a\x0bb - a\x0cb - a\x85b - a\n\rb - a\n\r\x85\x0cb - ** Failers - ab - -/^a\R{1,3}b/ - a\nb - a\n\rb - a\n\r\x85b - a\r\n\r\nb - a\r\n\r\n\r\nb - a\n\r\n\rb - a\n\n\r\nb - ** Failers - a\n\n\n\rb - a\r - -/^a[\R]b/ - aRb - ** Failers - a\nb - -/.+foo/ - afoo - ** Failers - \r\nfoo - \nfoo - -/.+foo/ - afoo - \nfoo - ** Failers - \r\nfoo - -/.+foo/ - afoo - ** Failers - \nfoo - \r\nfoo - -/.+foo/s - afoo - \r\nfoo - \nfoo - -/^$/mg - abc\r\rxyz - abc\n\rxyz - ** Failers - abc\r\nxyz - -/^X/m - XABC - ** Failers - XABC\B - -/(?m)^$/g+ - abc\r\n\r\n - -/(?m)^$|^\r\n/g+ - abc\r\n\r\n - -/(?m)$/g+ - abc\r\n\r\n - -/(?|(abc)|(xyz))/ - >abc< - >xyz< - -/(x)(?|(abc)|(xyz))(x)/ - xabcx - xxyzx - -/(x)(?|(abc)(pqr)|(xyz))(x)/ - xabcpqrx - xxyzx - -/(?|(abc)|(xyz))(?1)/ - abcabc - xyzabc - ** Failers - xyzxyz - -/\H\h\V\v/ - X X\x0a - X\x09X\x0b - ** Failers - \xa0 X\x0a - -/\H*\h+\V?\v{3,4}/ - \x09\x20\xa0X\x0a\x0b\x0c\x0d\x0a - \x09\x20\xa0\x0a\x0b\x0c\x0d\x0a - \x09\x20\xa0\x0a\x0b\x0c - ** Failers - \x09\x20\xa0\x0a\x0b - -/\H{3,4}/ - XY ABCDE - XY PQR ST - -/.\h{3,4}./ - XY AB PQRS - -/\h*X\h?\H+Y\H?Z/ - >XNNNYZ - > X NYQZ - ** Failers - >XYZ - > X NY Z - -/\v*X\v?Y\v+Z\V*\x0a\V+\x0b\V{2,3}\x0c/ - >XY\x0aZ\x0aA\x0bNN\x0c - >\x0a\x0dX\x0aY\x0a\x0bZZZ\x0aAAA\x0bNNN\x0c - -/.+A/ - \r\nA - -/\nA/ - \r\nA - -/[\r\n]A/ - \r\nA - -/(\r|\n)A/ - \r\nA - -/a\Rb/I - a\rb - a\nb - a\r\nb - ** Failers - a\x85b - a\x0bb - -/a\Rb/I - a\rb - a\nb - a\r\nb - a\x85b - a\x0bb - ** Failers - a\x85b\ - a\x0bb\ - -/a\R?b/I - a\rb - a\nb - a\r\nb - ** Failers - a\x85b - a\x0bb - -/a\R?b/I - a\rb - a\nb - a\r\nb - a\x85b - a\x0bb - ** Failers - a\x85b\ - a\x0bb\ - -/a\R{2,4}b/I - a\r\n\nb - a\n\r\rb - a\r\n\r\n\r\n\r\nb - ** Failers - a\x85\85b - a\x0b\0bb - -/a\R{2,4}b/I - a\r\rb - a\n\n\nb - a\r\n\n\r\rb - a\x85\85b - a\x0b\0bb - ** Failers - a\r\r\r\r\rb - a\x85\85b\ - a\x0b\0bb\ - -/a(?!)|\wbc/ - abc - -/a[]b/ - ** Failers - ab - -/a[]+b/ - ** Failers - ab - -/a[]*+b/ - ** Failers - ab - -/a[^]b/ - aXb - a\nb - ** Failers - ab - -/a[^]+b/ - aXb - a\nX\nXb - ** Failers - ab - -/X$/E - X - ** Failers - X\n - -/X$/ - X - X\n - -/xyz/C - xyz - abcxyz - abcxyz\Y - ** Failers - abc - abc\Y - abcxypqr - abcxypqr\Y - -/(?C)ab/ - ab - \C-ab - -/ab/C - ab - \C-ab - -/^"((?(?=[a])[^"])|b)*"$/C - "ab" - \C-"ab" - -/ End of testinput7 / diff --git a/libs/pcre/testdata/testinput8 b/libs/pcre/testdata/testinput8 deleted file mode 100644 index 11884adf65..0000000000 --- a/libs/pcre/testdata/testinput8 +++ /dev/null @@ -1,670 +0,0 @@ -/-- Do not use the \x{} construct except with patterns that have the --/ -/-- /8 option set, because PCRE doesn't recognize them as UTF-8 unless --/ -/-- that option is set. However, the latest Perls recognize them always. --/ - -/\x{100}ab/8 - \x{100}ab - -/a\x{100}*b/8 - ab - a\x{100}b - a\x{100}\x{100}b - -/a\x{100}+b/8 - a\x{100}b - a\x{100}\x{100}b - *** Failers - ab - -/\bX/8 - Xoanon - +Xoanon - \x{300}Xoanon - *** Failers - YXoanon - -/\BX/8 - YXoanon - *** Failers - Xoanon - +Xoanon - \x{300}Xoanon - -/X\b/8 - X+oanon - ZX\x{300}oanon - FAX - *** Failers - Xoanon - -/X\B/8 - Xoanon - *** Failers - X+oanon - ZX\x{300}oanon - FAX - -/[^a]/8 - abcd - a\x{100} - -/^[abc\x{123}\x{400}-\x{402}]{2,3}\d/8 - ab99 - \x{123}\x{123}45 - \x{400}\x{401}\x{402}6 - *** Failers - d99 - \x{123}\x{122}4 - \x{400}\x{403}6 - \x{400}\x{401}\x{402}\x{402}6 - -/abc/8 - Ã] - à - ÃÃà - ÃÃÃ\? - -/a.b/8 - acb - a\x7fb - a\x{100}b - *** Failers - a\nb - -/a(.{3})b/8 - a\x{4000}xyb - a\x{4000}\x7fyb - a\x{4000}\x{100}yb - *** Failers - a\x{4000}b - ac\ncb - -/a(.*?)(.)/ - a\xc0\x88b - -/a(.*?)(.)/8 - a\x{100}b - -/a(.*)(.)/ - a\xc0\x88b - -/a(.*)(.)/8 - a\x{100}b - -/a(.)(.)/ - a\xc0\x92bcd - -/a(.)(.)/8 - a\x{240}bcd - -/a(.?)(.)/ - a\xc0\x92bcd - -/a(.?)(.)/8 - a\x{240}bcd - -/a(.??)(.)/ - a\xc0\x92bcd - -/a(.??)(.)/8 - a\x{240}bcd - -/a(.{3})b/8 - a\x{1234}xyb - a\x{1234}\x{4321}yb - a\x{1234}\x{4321}\x{3412}b - *** Failers - a\x{1234}b - ac\ncb - -/a(.{3,})b/8 - a\x{1234}xyb - a\x{1234}\x{4321}yb - a\x{1234}\x{4321}\x{3412}b - axxxxbcdefghijb - a\x{1234}\x{4321}\x{3412}\x{3421}b - *** Failers - a\x{1234}b - -/a(.{3,}?)b/8 - a\x{1234}xyb - a\x{1234}\x{4321}yb - a\x{1234}\x{4321}\x{3412}b - axxxxbcdefghijb - a\x{1234}\x{4321}\x{3412}\x{3421}b - *** Failers - a\x{1234}b - -/a(.{3,5})b/8 - a\x{1234}xyb - a\x{1234}\x{4321}yb - a\x{1234}\x{4321}\x{3412}b - axxxxbcdefghijb - a\x{1234}\x{4321}\x{3412}\x{3421}b - axbxxbcdefghijb - axxxxxbcdefghijb - *** Failers - a\x{1234}b - axxxxxxbcdefghijb - -/a(.{3,5}?)b/8 - a\x{1234}xyb - a\x{1234}\x{4321}yb - a\x{1234}\x{4321}\x{3412}b - axxxxbcdefghijb - a\x{1234}\x{4321}\x{3412}\x{3421}b - axbxxbcdefghijb - axxxxxbcdefghijb - *** Failers - a\x{1234}b - axxxxxxbcdefghijb - -/^[a\x{c0}]/8 - *** Failers - \x{100} - -/(?<=aXb)cd/8 - aXbcd - -/(?<=a\x{100}b)cd/8 - a\x{100}bcd - -/(?<=a\x{100000}b)cd/8 - a\x{100000}bcd - -/(?:\x{100}){3}b/8 - \x{100}\x{100}\x{100}b - *** Failers - \x{100}\x{100}b - -/\x{ab}/8 - \x{ab} - \xc2\xab - *** Failers - \x00{ab} - -/(?<=(.))X/8 - WXYZ - \x{256}XYZ - *** Failers - XYZ - -/[^a]+/8g - bcd - \x{100}aY\x{256}Z - -/^[^a]{2}/8 - \x{100}bc - -/^[^a]{2,}/8 - \x{100}bcAa - -/^[^a]{2,}?/8 - \x{100}bca - -/[^a]+/8ig - bcd - \x{100}aY\x{256}Z - -/^[^a]{2}/8i - \x{100}bc - -/^[^a]{2,}/8i - \x{100}bcAa - -/^[^a]{2,}?/8i - \x{100}bca - -/\x{100}{0,0}/8 - abcd - -/\x{100}?/8 - abcd - \x{100}\x{100} - -/\x{100}{0,3}/8 - \x{100}\x{100} - \x{100}\x{100}\x{100}\x{100} - -/\x{100}*/8 - abce - \x{100}\x{100}\x{100}\x{100} - -/\x{100}{1,1}/8 - abcd\x{100}\x{100}\x{100}\x{100} - -/\x{100}{1,3}/8 - abcd\x{100}\x{100}\x{100}\x{100} - -/\x{100}+/8 - abcd\x{100}\x{100}\x{100}\x{100} - -/\x{100}{3}/8 - abcd\x{100}\x{100}\x{100}XX - -/\x{100}{3,5}/8 - abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX - -/\x{100}{3,}/8 - abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX - -/(?<=a\x{100}{2}b)X/8 - Xyyya\x{100}\x{100}bXzzz - -/\D*/8 - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - -/\D*/8 - \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} - -/\D/8 - 1X2 - 1\x{100}2 - -/>\S/8 - > >X Y - > >\x{100} Y - -/\d/8 - \x{100}3 - -/\s/8 - \x{100} X - -/\D+/8 - 12abcd34 - *** Failers - 1234 - -/\D{2,3}/8 - 12abcd34 - 12ab34 - *** Failers - 1234 - 12a34 - -/\D{2,3}?/8 - 12abcd34 - 12ab34 - *** Failers - 1234 - 12a34 - -/\d+/8 - 12abcd34 - *** Failers - -/\d{2,3}/8 - 12abcd34 - 1234abcd - *** Failers - 1.4 - -/\d{2,3}?/8 - 12abcd34 - 1234abcd - *** Failers - 1.4 - -/\S+/8 - 12abcd34 - *** Failers - \ \ - -/\S{2,3}/8 - 12abcd34 - 1234abcd - *** Failers - \ \ - -/\S{2,3}?/8 - 12abcd34 - 1234abcd - *** Failers - \ \ - -/>\s+ <34 - *** Failers - -/>\s{2,3} \s{2,3}? \xff< - -/[\xff]/8 - >\x{ff}< - -/[^\xFF]/ - XYZ - -/[^\xff]/8 - XYZ - \x{123} - -/^[ac]*b/8 - xb - -/^[ac\x{100}]*b/8 - xb - -/^[^x]*b/8i - xb - -/^[^x]*b/8 - xb - -/^\d*b/8 - xb - -/(|a)/g8 - catac - a\x{256}a - -/^\x{85}$/8i - \x{85} - -/^abc./mgx8 - abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x{0085}abc7 \x{2028}abc8 \x{2029}abc9 JUNK - -/abc.$/mgx8 - abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x{0085} abc7\x{2028} abc8\x{2029} abc9 - -/^a\Rb/8 - a\nb - a\rb - a\r\nb - a\x0bb - a\x0cb - a\x{85}b - a\x{2028}b - a\x{2029}b - ** Failers - a\n\rb - -/^a\R*b/8 - ab - a\nb - a\rb - a\r\nb - a\x0bb - a\x0c\x{2028}\x{2029}b - a\x{85}b - a\n\rb - a\n\r\x{85}\x0cb - -/^a\R+b/8 - a\nb - a\rb - a\r\nb - a\x0bb - a\x0c\x{2028}\x{2029}b - a\x{85}b - a\n\rb - a\n\r\x{85}\x0cb - ** Failers - ab - -/^a\R{1,3}b/8 - a\nb - a\n\rb - a\n\r\x{85}b - a\r\n\r\nb - a\r\n\r\n\r\nb - a\n\r\n\rb - a\n\n\r\nb - ** Failers - a\n\n\n\rb - a\r - -/\h+\V?\v{3,4}/8 - \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a - -/\V?\v{3,4}/8 - \x20\x{a0}X\x0a\x0b\x0c\x0d\x0a - -/\h+\V?\v{3,4}/8 - >\x09\x20\x{a0}X\x0a\x0a\x0a< - -/\V?\v{3,4}/8 - >\x09\x20\x{a0}X\x0a\x0a\x0a< - -/\H\h\V\v/8 - X X\x0a - X\x09X\x0b - ** Failers - \x{a0} X\x0a - -/\H*\h+\V?\v{3,4}/8 - \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a - \x09\x20\x{a0}\x0a\x0b\x0c\x0d\x0a - \x09\x20\x{a0}\x0a\x0b\x0c - ** Failers - \x09\x20\x{a0}\x0a\x0b - -/\H\h\V\v/8 - \x{3001}\x{3000}\x{2030}\x{2028} - X\x{180e}X\x{85} - ** Failers - \x{2009} X\x0a - -/\H*\h+\V?\v{3,4}/8 - \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x0c\x0d\x0a - \x09\x{205f}\x{a0}\x0a\x{2029}\x0c\x{2028}\x0a - \x09\x20\x{202f}\x0a\x0b\x0c - ** Failers - \x09\x{200a}\x{a0}\x{2028}\x0b - -/a\Rb/I8 - a\rb - a\nb - a\r\nb - ** Failers - a\x{85}b - a\x0bb - -/a\Rb/I8 - a\rb - a\nb - a\r\nb - a\x{85}b - a\x0bb - ** Failers - a\x{85}b\ - a\x0bb\ - -/a\R?b/I8 - a\rb - a\nb - a\r\nb - ** Failers - a\x{85}b - a\x0bb - -/a\R?b/I8 - a\rb - a\nb - a\r\nb - a\x{85}b - a\x0bb - ** Failers - a\x{85}b\ - a\x0bb\ - -/X/8f - A\x{1ec5}ABCXYZ - -/ End of testinput 8 / diff --git a/libs/pcre/testdata/testinput9 b/libs/pcre/testdata/testinput9 deleted file mode 100644 index ab044558d1..0000000000 --- a/libs/pcre/testdata/testinput9 +++ /dev/null @@ -1,846 +0,0 @@ -/\pL\P{Nd}/8 - AB - *** Failers - A0 - 00 - -/\X./8 - AB - A\x{300}BC - A\x{300}\x{301}\x{302}BC - *** Failers - \x{300} - -/\X\X/8 - ABC - A\x{300}B\x{300}\x{301}C - A\x{300}\x{301}\x{302}BC - *** Failers - \x{300} - -/^\pL+/8 - abcd - a - *** Failers - -/^\PL+/8 - 1234 - = - *** Failers - abcd - -/^\X+/8 - abcdA\x{300}\x{301}\x{302} - A\x{300}\x{301}\x{302} - A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302} - a - *** Failers - \x{300}\x{301}\x{302} - -/\X?abc/8 - abc - A\x{300}abc - A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz - \x{300}abc - *** Failers - -/^\X?abc/8 - abc - A\x{300}abc - *** Failers - A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz - \x{300}abc - -/\X*abc/8 - abc - A\x{300}abc - A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz - \x{300}abc - *** Failers - -/^\X*abc/8 - abc - A\x{300}abc - A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz - *** Failers - \x{300}abc - -/^\pL?=./8 - A=b - =c - *** Failers - 1=2 - AAAA=b - -/^\pL*=./8 - AAAA=b - =c - *** Failers - 1=2 - -/^\X{2,3}X/8 - A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X - A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X - *** Failers - X - A\x{300}\x{301}\x{302}X - A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X - -/^\pC\pL\pM\pN\pP\pS\pZ>>aaabxyzpqrrrabbxyyyypqAzz - 0: aaabxyzpqrrrabbxyyyypqAzz - >aaaabxyzpqrrrabbxyyyypqAzz - 0: aaaabxyzpqrrrabbxyyyypqAzz - >>>>abcxyzpqrrrabbxyyyypqAzz - 0: abcxyzpqrrrabbxyyyypqAzz - *** Failers -No match - abxyzpqrrabbxyyyypqAzz -No match - abxyzpqrrrrabbxyyyypqAzz -No match - abxyzpqrrrabxyyyypqAzz -No match - aaaabcxyzzzzpqrrrabbbxyyyyyypqAzz -No match - aaaabcxyzzzzpqrrrabbbxyyypqAzz -No match - aaabcxyzpqrrrabbxyyyypqqqqqqqAzz -No match - -/^(abc){1,2}zz/ - abczz - 0: abczz - 1: abc - abcabczz - 0: abcabczz - 1: abc - *** Failers -No match - zz -No match - abcabcabczz -No match - >>abczz -No match - -/^(b+?|a){1,2}?c/ - bc - 0: bc - 1: b - bbc - 0: bbc - 1: b - bbbc - 0: bbbc - 1: bb - bac - 0: bac - 1: a - bbac - 0: bbac - 1: a - aac - 0: aac - 1: a - abbbbbbbbbbbc - 0: abbbbbbbbbbbc - 1: bbbbbbbbbbb - bbbbbbbbbbbac - 0: bbbbbbbbbbbac - 1: a - *** Failers -No match - aaac -No match - abbbbbbbbbbbac -No match - -/^(b+|a){1,2}c/ - bc - 0: bc - 1: b - bbc - 0: bbc - 1: bb - bbbc - 0: bbbc - 1: bbb - bac - 0: bac - 1: a - bbac - 0: bbac - 1: a - aac - 0: aac - 1: a - abbbbbbbbbbbc - 0: abbbbbbbbbbbc - 1: bbbbbbbbbbb - bbbbbbbbbbbac - 0: bbbbbbbbbbbac - 1: a - *** Failers -No match - aaac -No match - abbbbbbbbbbbac -No match - -/^(b+|a){1,2}?bc/ - bbc - 0: bbc - 1: b - -/^(b*|ba){1,2}?bc/ - babc - 0: babc - 1: ba - bbabc - 0: bbabc - 1: ba - bababc - 0: bababc - 1: ba - *** Failers -No match - bababbc -No match - babababc -No match - -/^(ba|b*){1,2}?bc/ - babc - 0: babc - 1: ba - bbabc - 0: bbabc - 1: ba - bababc - 0: bababc - 1: ba - *** Failers -No match - bababbc -No match - babababc -No match - -/^\ca\cA\c[\c{\c:/ - \x01\x01\e;z - 0: \x01\x01\x1b;z - -/^[ab\]cde]/ - athing - 0: a - bthing - 0: b - ]thing - 0: ] - cthing - 0: c - dthing - 0: d - ething - 0: e - *** Failers -No match - fthing -No match - [thing -No match - \\thing -No match - -/^[]cde]/ - ]thing - 0: ] - cthing - 0: c - dthing - 0: d - ething - 0: e - *** Failers -No match - athing -No match - fthing -No match - -/^[^ab\]cde]/ - fthing - 0: f - [thing - 0: [ - \\thing - 0: \ - *** Failers - 0: * - athing -No match - bthing -No match - ]thing -No match - cthing -No match - dthing -No match - ething -No match - -/^[^]cde]/ - athing - 0: a - fthing - 0: f - *** Failers - 0: * - ]thing -No match - cthing -No match - dthing -No match - ething -No match - -/^\/ - - 0: \x81 - -/^ÿ/ - ÿ - 0: \xff - -/^[0-9]+$/ - 0 - 0: 0 - 1 - 0: 1 - 2 - 0: 2 - 3 - 0: 3 - 4 - 0: 4 - 5 - 0: 5 - 6 - 0: 6 - 7 - 0: 7 - 8 - 0: 8 - 9 - 0: 9 - 10 - 0: 10 - 100 - 0: 100 - *** Failers -No match - abc -No match - -/^.*nter/ - enter - 0: enter - inter - 0: inter - uponter - 0: uponter - -/^xxx[0-9]+$/ - xxx0 - 0: xxx0 - xxx1234 - 0: xxx1234 - *** Failers -No match - xxx -No match - -/^.+[0-9][0-9][0-9]$/ - x123 - 0: x123 - xx123 - 0: xx123 - 123456 - 0: 123456 - *** Failers -No match - 123 -No match - x1234 - 0: x1234 - -/^.+?[0-9][0-9][0-9]$/ - x123 - 0: x123 - xx123 - 0: xx123 - 123456 - 0: 123456 - *** Failers -No match - 123 -No match - x1234 - 0: x1234 - -/^([^!]+)!(.+)=apquxz\.ixr\.zzz\.ac\.uk$/ - abc!pqr=apquxz.ixr.zzz.ac.uk - 0: abc!pqr=apquxz.ixr.zzz.ac.uk - 1: abc - 2: pqr - *** Failers -No match - !pqr=apquxz.ixr.zzz.ac.uk -No match - abc!=apquxz.ixr.zzz.ac.uk -No match - abc!pqr=apquxz:ixr.zzz.ac.uk -No match - abc!pqr=apquxz.ixr.zzz.ac.ukk -No match - -/:/ - Well, we need a colon: somewhere - 0: : - *** Fail if we don't -No match - -/([\da-f:]+)$/i - 0abc - 0: 0abc - 1: 0abc - abc - 0: abc - 1: abc - fed - 0: fed - 1: fed - E - 0: E - 1: E - :: - 0: :: - 1: :: - 5f03:12C0::932e - 0: 5f03:12C0::932e - 1: 5f03:12C0::932e - fed def - 0: def - 1: def - Any old stuff - 0: ff - 1: ff - *** Failers -No match - 0zzz -No match - gzzz -No match - fed\x20 -No match - Any old rubbish -No match - -/^.*\.(\d{1,3})\.(\d{1,3})\.(\d{1,3})$/ - .1.2.3 - 0: .1.2.3 - 1: 1 - 2: 2 - 3: 3 - A.12.123.0 - 0: A.12.123.0 - 1: 12 - 2: 123 - 3: 0 - *** Failers -No match - .1.2.3333 -No match - 1.2.3 -No match - 1234.2.3 -No match - -/^(\d+)\s+IN\s+SOA\s+(\S+)\s+(\S+)\s*\(\s*$/ - 1 IN SOA non-sp1 non-sp2( - 0: 1 IN SOA non-sp1 non-sp2( - 1: 1 - 2: non-sp1 - 3: non-sp2 - 1 IN SOA non-sp1 non-sp2 ( - 0: 1 IN SOA non-sp1 non-sp2 ( - 1: 1 - 2: non-sp1 - 3: non-sp2 - *** Failers -No match - 1IN SOA non-sp1 non-sp2( -No match - -/^[a-zA-Z\d][a-zA-Z\d\-]*(\.[a-zA-Z\d][a-zA-z\d\-]*)*\.$/ - a. - 0: a. - Z. - 0: Z. - 2. - 0: 2. - ab-c.pq-r. - 0: ab-c.pq-r. - 1: .pq-r - sxk.zzz.ac.uk. - 0: sxk.zzz.ac.uk. - 1: .uk - x-.y-. - 0: x-.y-. - 1: .y- - *** Failers -No match - -abc.peq. -No match - -/^\*\.[a-z]([a-z\-\d]*[a-z\d]+)?(\.[a-z]([a-z\-\d]*[a-z\d]+)?)*$/ - *.a - 0: *.a - *.b0-a - 0: *.b0-a - 1: 0-a - *.c3-b.c - 0: *.c3-b.c - 1: 3-b - 2: .c - *.c-a.b-c - 0: *.c-a.b-c - 1: -a - 2: .b-c - 3: -c - *** Failers -No match - *.0 -No match - *.a- -No match - *.a-b.c- -No match - *.c-a.0-c -No match - -/^(?=ab(de))(abd)(e)/ - abde - 0: abde - 1: de - 2: abd - 3: e - -/^(?!(ab)de|x)(abd)(f)/ - abdf - 0: abdf - 1: - 2: abd - 3: f - -/^(?=(ab(cd)))(ab)/ - abcd - 0: ab - 1: abcd - 2: cd - 3: ab - -/^[\da-f](\.[\da-f])*$/i - a.b.c.d - 0: a.b.c.d - 1: .d - A.B.C.D - 0: A.B.C.D - 1: .D - a.b.c.1.2.3.C - 0: a.b.c.1.2.3.C - 1: .C - -/^\".*\"\s*(;.*)?$/ - \"1234\" - 0: "1234" - \"abcd\" ; - 0: "abcd" ; - 1: ; - \"\" ; rhubarb - 0: "" ; rhubarb - 1: ; rhubarb - *** Failers -No match - \"1234\" : things -No match - -/^$/ - \ - 0: - *** Failers -No match - -/ ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/x - ab c - 0: ab c - *** Failers -No match - abc -No match - ab cde -No match - -/(?x) ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/ - ab c - 0: ab c - *** Failers -No match - abc -No match - ab cde -No match - -/^ a\ b[c ]d $/x - a bcd - 0: a bcd - a b d - 0: a b d - *** Failers -No match - abcd -No match - ab d -No match - -/^(a(b(c)))(d(e(f)))(h(i(j)))(k(l(m)))$/ - abcdefhijklm - 0: abcdefhijklm - 1: abc - 2: bc - 3: c - 4: def - 5: ef - 6: f - 7: hij - 8: ij - 9: j -10: klm -11: lm -12: m - -/^(?:a(b(c)))(?:d(e(f)))(?:h(i(j)))(?:k(l(m)))$/ - abcdefhijklm - 0: abcdefhijklm - 1: bc - 2: c - 3: ef - 4: f - 5: ij - 6: j - 7: lm - 8: m - -/^[\w][\W][\s][\S][\d][\D][\b][\n][\c]][\022]/ - a+ Z0+\x08\n\x1d\x12 - 0: a+ Z0+\x08\x0a\x1d\x12 - -/^[.^$|()*+?{,}]+/ - .^\$(*+)|{?,?} - 0: .^$(*+)|{?,?} - -/^a*\w/ - z - 0: z - az - 0: az - aaaz - 0: aaaz - a - 0: a - aa - 0: aa - aaaa - 0: aaaa - a+ - 0: a - aa+ - 0: aa - -/^a*?\w/ - z - 0: z - az - 0: a - aaaz - 0: a - a - 0: a - aa - 0: a - aaaa - 0: a - a+ - 0: a - aa+ - 0: a - -/^a+\w/ - az - 0: az - aaaz - 0: aaaz - aa - 0: aa - aaaa - 0: aaaa - aa+ - 0: aa - -/^a+?\w/ - az - 0: az - aaaz - 0: aa - aa - 0: aa - aaaa - 0: aa - aa+ - 0: aa - -/^\d{8}\w{2,}/ - 1234567890 - 0: 1234567890 - 12345678ab - 0: 12345678ab - 12345678__ - 0: 12345678__ - *** Failers -No match - 1234567 -No match - -/^[aeiou\d]{4,5}$/ - uoie - 0: uoie - 1234 - 0: 1234 - 12345 - 0: 12345 - aaaaa - 0: aaaaa - *** Failers -No match - 123456 -No match - -/^[aeiou\d]{4,5}?/ - uoie - 0: uoie - 1234 - 0: 1234 - 12345 - 0: 1234 - aaaaa - 0: aaaa - 123456 - 0: 1234 - -/\A(abc|def)=(\1){2,3}\Z/ - abc=abcabc - 0: abc=abcabc - 1: abc - 2: abc - def=defdefdef - 0: def=defdefdef - 1: def - 2: def - *** Failers -No match - abc=defdef -No match - -/^(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)\11*(\3\4)\1(?#)2$/ - abcdefghijkcda2 - 0: abcdefghijkcda2 - 1: a - 2: b - 3: c - 4: d - 5: e - 6: f - 7: g - 8: h - 9: i -10: j -11: k -12: cd - abcdefghijkkkkcda2 - 0: abcdefghijkkkkcda2 - 1: a - 2: b - 3: c - 4: d - 5: e - 6: f - 7: g - 8: h - 9: i -10: j -11: k -12: cd - -/(cat(a(ract|tonic)|erpillar)) \1()2(3)/ - cataract cataract23 - 0: cataract cataract23 - 1: cataract - 2: aract - 3: ract - 4: - 5: 3 - catatonic catatonic23 - 0: catatonic catatonic23 - 1: catatonic - 2: atonic - 3: tonic - 4: - 5: 3 - caterpillar caterpillar23 - 0: caterpillar caterpillar23 - 1: caterpillar - 2: erpillar - 3: - 4: - 5: 3 - - -/^From +([^ ]+) +[a-zA-Z][a-zA-Z][a-zA-Z] +[a-zA-Z][a-zA-Z][a-zA-Z] +[0-9]?[0-9] +[0-9][0-9]:[0-9][0-9]/ - From abcd Mon Sep 01 12:33:02 1997 - 0: From abcd Mon Sep 01 12:33 - 1: abcd - -/^From\s+\S+\s+([a-zA-Z]{3}\s+){2}\d{1,2}\s+\d\d:\d\d/ - From abcd Mon Sep 01 12:33:02 1997 - 0: From abcd Mon Sep 01 12:33 - 1: Sep - From abcd Mon Sep 1 12:33:02 1997 - 0: From abcd Mon Sep 1 12:33 - 1: Sep - *** Failers -No match - From abcd Sep 01 12:33:02 1997 -No match - -/^12.34/s - 12\n34 - 0: 12\x0a34 - 12\r34 - 0: 12\x0d34 - -/\w+(?=\t)/ - the quick brown\t fox - 0: brown - -/foo(?!bar)(.*)/ - foobar is foolish see? - 0: foolish see? - 1: lish see? - -/(?:(?!foo)...|^.{0,2})bar(.*)/ - foobar crowbar etc - 0: rowbar etc - 1: etc - barrel - 0: barrel - 1: rel - 2barrel - 0: 2barrel - 1: rel - A barrel - 0: A barrel - 1: rel - -/^(\D*)(?=\d)(?!123)/ - abc456 - 0: abc - 1: abc - *** Failers -No match - abc123 -No match - -/^1234(?# test newlines - inside)/ - 1234 - 0: 1234 - -/^1234 #comment in extended re - /x - 1234 - 0: 1234 - -/#rhubarb - abcd/x - abcd - 0: abcd - -/^abcd#rhubarb/x - abcd - 0: abcd - -/^(a)\1{2,3}(.)/ - aaab - 0: aaab - 1: a - 2: b - aaaab - 0: aaaab - 1: a - 2: b - aaaaab - 0: aaaaa - 1: a - 2: a - aaaaaab - 0: aaaaa - 1: a - 2: a - -/(?!^)abc/ - the abc - 0: abc - *** Failers -No match - abc -No match - -/(?=^)abc/ - abc - 0: abc - *** Failers -No match - the abc -No match - -/^[ab]{1,3}(ab*|b)/ - aabbbbb - 0: aabb - 1: b - -/^[ab]{1,3}?(ab*|b)/ - aabbbbb - 0: aabbbbb - 1: abbbbb - -/^[ab]{1,3}?(ab*?|b)/ - aabbbbb - 0: aa - 1: a - -/^[ab]{1,3}(ab*?|b)/ - aabbbbb - 0: aabb - 1: b - -/ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* # optional leading comment -(?: (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) # initial word -(?: (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) )* # further okay, if led by a period -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* -# address -| # or -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) # one word, optionally followed by.... -(?: -[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] | # atom and space parts, or... -\( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) | # comments, or... - -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -# quoted strings -)* -< (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* # leading < -(?: @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* - -(?: (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* , (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* -)* # further okay, if led by comma -: # closing colon -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* )? # optional route -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) # initial word -(?: (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) )* # further okay, if led by a period -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* -# address spec -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* > # trailing > -# name and address -) (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* # optional trailing comment -/x - Alan Other - 0: Alan Other - - 0: user@dom.ain - user\@dom.ain - 0: user@dom.ain - \"A. Other\" (a comment) - 0: "A. Other" (a comment) - A. Other (a comment) - 0: Other (a comment) - \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay - 0: "/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/"@x400-re.lay - A missing angle @,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# additional words -)* -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -# address -| # or -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -# leading word -[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] * # "normal" atoms and or spaces -(?: -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -| -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -) # "special" comment or quoted string -[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] * # more "normal" -)* -< -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# < -(?: -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -(?: , -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -)* # additional domains -: -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)? # optional route -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# additional words -)* -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -# address spec -> # > -# name and address -) -/x - Alan Other - 0: Alan Other - - 0: user@dom.ain - user\@dom.ain - 0: user@dom.ain - \"A. Other\" (a comment) - 0: "A. Other" - A. Other (a comment) - 0: Other - \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay - 0: "/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/"@x400-re.lay - A missing angle ?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x7f\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff - -/P[^*]TAIRE[^*]{1,6}?LL/ - xxxxxxxxxxxPSTAIREISLLxxxxxxxxx - 0: PSTAIREISLL - -/P[^*]TAIRE[^*]{1,}?LL/ - xxxxxxxxxxxPSTAIREISLLxxxxxxxxx - 0: PSTAIREISLL - -/(\.\d\d[1-9]?)\d+/ - 1.230003938 - 0: .230003938 - 1: .23 - 1.875000282 - 0: .875000282 - 1: .875 - 1.235 - 0: .235 - 1: .23 - -/(\.\d\d((?=0)|\d(?=\d)))/ - 1.230003938 - 0: .23 - 1: .23 - 2: - 1.875000282 - 0: .875 - 1: .875 - 2: 5 - *** Failers -No match - 1.235 -No match - -/a(?)b/ - ab - 0: ab - -/\b(foo)\s+(\w+)/i - Food is on the foo table - 0: foo table - 1: foo - 2: table - -/foo(.*)bar/ - The food is under the bar in the barn. - 0: food is under the bar in the bar - 1: d is under the bar in the - -/foo(.*?)bar/ - The food is under the bar in the barn. - 0: food is under the bar - 1: d is under the - -/(.*)(\d*)/ - I have 2 numbers: 53147 - 0: I have 2 numbers: 53147 - 1: I have 2 numbers: 53147 - 2: - -/(.*)(\d+)/ - I have 2 numbers: 53147 - 0: I have 2 numbers: 53147 - 1: I have 2 numbers: 5314 - 2: 7 - -/(.*?)(\d*)/ - I have 2 numbers: 53147 - 0: - 1: - 2: - -/(.*?)(\d+)/ - I have 2 numbers: 53147 - 0: I have 2 - 1: I have - 2: 2 - -/(.*)(\d+)$/ - I have 2 numbers: 53147 - 0: I have 2 numbers: 53147 - 1: I have 2 numbers: 5314 - 2: 7 - -/(.*?)(\d+)$/ - I have 2 numbers: 53147 - 0: I have 2 numbers: 53147 - 1: I have 2 numbers: - 2: 53147 - -/(.*)\b(\d+)$/ - I have 2 numbers: 53147 - 0: I have 2 numbers: 53147 - 1: I have 2 numbers: - 2: 53147 - -/(.*\D)(\d+)$/ - I have 2 numbers: 53147 - 0: I have 2 numbers: 53147 - 1: I have 2 numbers: - 2: 53147 - -/^\D*(?!123)/ - ABC123 - 0: AB - -/^(\D*)(?=\d)(?!123)/ - ABC445 - 0: ABC - 1: ABC - *** Failers -No match - ABC123 -No match - -/^[W-]46]/ - W46]789 - 0: W46] - -46]789 - 0: -46] - *** Failers -No match - Wall -No match - Zebra -No match - 42 -No match - [abcd] -No match - ]abcd[ -No match - -/^[W-\]46]/ - W46]789 - 0: W - Wall - 0: W - Zebra - 0: Z - Xylophone - 0: X - 42 - 0: 4 - [abcd] - 0: [ - ]abcd[ - 0: ] - \\backslash - 0: \ - *** Failers -No match - -46]789 -No match - well -No match - -/\d\d\/\d\d\/\d\d\d\d/ - 01/01/2000 - 0: 01/01/2000 - -/word (?:[a-zA-Z0-9]+ ){0,10}otherword/ - word cat dog elephant mussel cow horse canary baboon snake shark otherword - 0: word cat dog elephant mussel cow horse canary baboon snake shark otherword - word cat dog elephant mussel cow horse canary baboon snake shark -No match - -/word (?:[a-zA-Z0-9]+ ){0,300}otherword/ - word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope -No match - -/^(a){0,0}/ - bcd - 0: - abc - 0: - aab - 0: - -/^(a){0,1}/ - bcd - 0: - abc - 0: a - 1: a - aab - 0: a - 1: a - -/^(a){0,2}/ - bcd - 0: - abc - 0: a - 1: a - aab - 0: aa - 1: a - -/^(a){0,3}/ - bcd - 0: - abc - 0: a - 1: a - aab - 0: aa - 1: a - aaa - 0: aaa - 1: a - -/^(a){0,}/ - bcd - 0: - abc - 0: a - 1: a - aab - 0: aa - 1: a - aaa - 0: aaa - 1: a - aaaaaaaa - 0: aaaaaaaa - 1: a - -/^(a){1,1}/ - bcd -No match - abc - 0: a - 1: a - aab - 0: a - 1: a - -/^(a){1,2}/ - bcd -No match - abc - 0: a - 1: a - aab - 0: aa - 1: a - -/^(a){1,3}/ - bcd -No match - abc - 0: a - 1: a - aab - 0: aa - 1: a - aaa - 0: aaa - 1: a - -/^(a){1,}/ - bcd -No match - abc - 0: a - 1: a - aab - 0: aa - 1: a - aaa - 0: aaa - 1: a - aaaaaaaa - 0: aaaaaaaa - 1: a - -/.*\.gif/ - borfle\nbib.gif\nno - 0: bib.gif - -/.{0,}\.gif/ - borfle\nbib.gif\nno - 0: bib.gif - -/.*\.gif/m - borfle\nbib.gif\nno - 0: bib.gif - -/.*\.gif/s - borfle\nbib.gif\nno - 0: borfle\x0abib.gif - -/.*\.gif/ms - borfle\nbib.gif\nno - 0: borfle\x0abib.gif - -/.*$/ - borfle\nbib.gif\nno - 0: no - -/.*$/m - borfle\nbib.gif\nno - 0: borfle - -/.*$/s - borfle\nbib.gif\nno - 0: borfle\x0abib.gif\x0ano - -/.*$/ms - borfle\nbib.gif\nno - 0: borfle\x0abib.gif\x0ano - -/.*$/ - borfle\nbib.gif\nno\n - 0: no - -/.*$/m - borfle\nbib.gif\nno\n - 0: borfle - -/.*$/s - borfle\nbib.gif\nno\n - 0: borfle\x0abib.gif\x0ano\x0a - -/.*$/ms - borfle\nbib.gif\nno\n - 0: borfle\x0abib.gif\x0ano\x0a - -/(.*X|^B)/ - abcde\n1234Xyz - 0: 1234X - 1: 1234X - BarFoo - 0: B - 1: B - *** Failers -No match - abcde\nBar -No match - -/(.*X|^B)/m - abcde\n1234Xyz - 0: 1234X - 1: 1234X - BarFoo - 0: B - 1: B - abcde\nBar - 0: B - 1: B - -/(.*X|^B)/s - abcde\n1234Xyz - 0: abcde\x0a1234X - 1: abcde\x0a1234X - BarFoo - 0: B - 1: B - *** Failers -No match - abcde\nBar -No match - -/(.*X|^B)/ms - abcde\n1234Xyz - 0: abcde\x0a1234X - 1: abcde\x0a1234X - BarFoo - 0: B - 1: B - abcde\nBar - 0: B - 1: B - -/(?s)(.*X|^B)/ - abcde\n1234Xyz - 0: abcde\x0a1234X - 1: abcde\x0a1234X - BarFoo - 0: B - 1: B - *** Failers -No match - abcde\nBar -No match - -/(?s:.*X|^B)/ - abcde\n1234Xyz - 0: abcde\x0a1234X - BarFoo - 0: B - *** Failers -No match - abcde\nBar -No match - -/^.*B/ - **** Failers -No match - abc\nB -No match - -/(?s)^.*B/ - abc\nB - 0: abc\x0aB - -/(?m)^.*B/ - abc\nB - 0: B - -/(?ms)^.*B/ - abc\nB - 0: abc\x0aB - -/(?ms)^B/ - abc\nB - 0: B - -/(?s)B$/ - B\n - 0: B - -/^[0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9]/ - 123456654321 - 0: 123456654321 - -/^\d\d\d\d\d\d\d\d\d\d\d\d/ - 123456654321 - 0: 123456654321 - -/^[\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d]/ - 123456654321 - 0: 123456654321 - -/^[abc]{12}/ - abcabcabcabc - 0: abcabcabcabc - -/^[a-c]{12}/ - abcabcabcabc - 0: abcabcabcabc - -/^(a|b|c){12}/ - abcabcabcabc - 0: abcabcabcabc - 1: c - -/^[abcdefghijklmnopqrstuvwxy0123456789]/ - n - 0: n - *** Failers -No match - z -No match - -/abcde{0,0}/ - abcd - 0: abcd - *** Failers -No match - abce -No match - -/ab[cd]{0,0}e/ - abe - 0: abe - *** Failers -No match - abcde -No match - -/ab(c){0,0}d/ - abd - 0: abd - *** Failers -No match - abcd -No match - -/a(b*)/ - a - 0: a - 1: - ab - 0: ab - 1: b - abbbb - 0: abbbb - 1: bbbb - *** Failers - 0: a - 1: - bbbbb -No match - -/ab\d{0}e/ - abe - 0: abe - *** Failers -No match - ab1e -No match - -/"([^\\"]+|\\.)*"/ - the \"quick\" brown fox - 0: "quick" - 1: quick - \"the \\\"quick\\\" brown fox\" - 0: "the \"quick\" brown fox" - 1: brown fox - -/.*?/g+ - abc - 0: - 0+ abc - 0: a - 0+ bc - 0: - 0+ bc - 0: b - 0+ c - 0: - 0+ c - 0: c - 0+ - 0: - 0+ - -/\b/g+ - abc - 0: - 0+ abc - 0: - 0+ - -/\b/+g - abc - 0: - 0+ abc - 0: - 0+ - -//g - abc - 0: - 0: - 0: - 0: - -/]{0,})>]{0,})>([\d]{0,}\.)(.*)((
([\w\W\s\d][^<>]{0,})|[\s]{0,}))<\/a><\/TD>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><\/TR>/is - 43.Word Processor
(N-1286)Lega lstaff.comCA - Statewide - 0: 43.Word Processor
(N-1286)Lega lstaff.comCA - Statewide - 1: BGCOLOR='#DBE9E9' - 2: align=left valign=top - 3: 43. - 4: Word Processor
(N-1286) - 5: - 6: - 7: - 8: align=left valign=top - 9: Lega lstaff.com -10: align=left valign=top -11: CA - Statewide - -/a[^a]b/ - acb - 0: acb - a\nb - 0: a\x0ab - -/a.b/ - acb - 0: acb - *** Failers -No match - a\nb -No match - -/a[^a]b/s - acb - 0: acb - a\nb - 0: a\x0ab - -/a.b/s - acb - 0: acb - a\nb - 0: a\x0ab - -/^(b+?|a){1,2}?c/ - bac - 0: bac - 1: a - bbac - 0: bbac - 1: a - bbbac - 0: bbbac - 1: a - bbbbac - 0: bbbbac - 1: a - bbbbbac - 0: bbbbbac - 1: a - -/^(b+|a){1,2}?c/ - bac - 0: bac - 1: a - bbac - 0: bbac - 1: a - bbbac - 0: bbbac - 1: a - bbbbac - 0: bbbbac - 1: a - bbbbbac - 0: bbbbbac - 1: a - -/(?!\A)x/m - x\nb\n -No match - a\bx\n - 0: x - -/\x0{ab}/ - \0{ab} - 0: \x00{ab} - -/(A|B)*?CD/ - CD - 0: CD - -/(A|B)*CD/ - CD - 0: CD - -/(AB)*?\1/ - ABABAB - 0: ABAB - 1: AB - -/(AB)*\1/ - ABABAB - 0: ABABAB - 1: AB - -/(?.*/)foo" - /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/it/you/see/ -No match - -"(?>.*/)foo" - /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo - 0: /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo - -/(?>(\.\d\d[1-9]?))\d+/ - 1.230003938 - 0: .230003938 - 1: .23 - 1.875000282 - 0: .875000282 - 1: .875 - *** Failers -No match - 1.235 -No match - -/^((?>\w+)|(?>\s+))*$/ - now is the time for all good men to come to the aid of the party - 0: now is the time for all good men to come to the aid of the party - 1: party - *** Failers -No match - this is not a line with only words and spaces! -No match - -/(\d+)(\w)/ - 12345a - 0: 12345a - 1: 12345 - 2: a - 12345+ - 0: 12345 - 1: 1234 - 2: 5 - -/((?>\d+))(\w)/ - 12345a - 0: 12345a - 1: 12345 - 2: a - *** Failers -No match - 12345+ -No match - -/(?>a+)b/ - aaab - 0: aaab - -/((?>a+)b)/ - aaab - 0: aaab - 1: aaab - -/(?>(a+))b/ - aaab - 0: aaab - 1: aaa - -/(?>b)+/ - aaabbbccc - 0: bbb - -/(?>a+|b+|c+)*c/ - aaabbbbccccd - 0: aaabbbbc - -/((?>[^()]+)|\([^()]*\))+/ - ((abc(ade)ufh()()x - 0: abc(ade)ufh()()x - 1: x - -/\(((?>[^()]+)|\([^()]+\))+\)/ - (abc) - 0: (abc) - 1: abc - (abc(def)xyz) - 0: (abc(def)xyz) - 1: xyz - *** Failers -No match - ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -No match - -/a(?-i)b/i - ab - 0: ab - Ab - 0: Ab - *** Failers -No match - aB -No match - AB -No match - -/(a (?x)b c)d e/ - a bcd e - 0: a bcd e - 1: a bc - *** Failers -No match - a b cd e -No match - abcd e -No match - a bcde -No match - -/(a b(?x)c d (?-x)e f)/ - a bcde f - 0: a bcde f - 1: a bcde f - *** Failers -No match - abcdef -No match - -/(a(?i)b)c/ - abc - 0: abc - 1: ab - aBc - 0: aBc - 1: aB - *** Failers -No match - abC -No match - aBC -No match - Abc -No match - ABc -No match - ABC -No match - AbC -No match - -/a(?i:b)c/ - abc - 0: abc - aBc - 0: aBc - *** Failers -No match - ABC -No match - abC -No match - aBC -No match - -/a(?i:b)*c/ - aBc - 0: aBc - aBBc - 0: aBBc - *** Failers -No match - aBC -No match - aBBC -No match - -/a(?=b(?i)c)\w\wd/ - abcd - 0: abcd - abCd - 0: abCd - *** Failers -No match - aBCd -No match - abcD -No match - -/(?s-i:more.*than).*million/i - more than million - 0: more than million - more than MILLION - 0: more than MILLION - more \n than Million - 0: more \x0a than Million - *** Failers -No match - MORE THAN MILLION -No match - more \n than \n million -No match - -/(?:(?s-i)more.*than).*million/i - more than million - 0: more than million - more than MILLION - 0: more than MILLION - more \n than Million - 0: more \x0a than Million - *** Failers -No match - MORE THAN MILLION -No match - more \n than \n million -No match - -/(?>a(?i)b+)+c/ - abc - 0: abc - aBbc - 0: aBbc - aBBc - 0: aBBc - *** Failers -No match - Abc -No match - abAb -No match - abbC -No match - -/(?=a(?i)b)\w\wc/ - abc - 0: abc - aBc - 0: aBc - *** Failers -No match - Ab -No match - abC -No match - aBC -No match - -/(?<=a(?i)b)(\w\w)c/ - abxxc - 0: xxc - 1: xx - aBxxc - 0: xxc - 1: xx - *** Failers -No match - Abxxc -No match - ABxxc -No match - abxxC -No match - -/(?:(a)|b)(?(1)A|B)/ - aA - 0: aA - 1: a - bB - 0: bB - *** Failers -No match - aB -No match - bA -No match - -/^(a)?(?(1)a|b)+$/ - aa - 0: aa - 1: a - b - 0: b - bb - 0: bb - *** Failers -No match - ab -No match - -/^(?(?=abc)\w{3}:|\d\d)$/ - abc: - 0: abc: - 12 - 0: 12 - *** Failers -No match - 123 -No match - xyz -No match - -/^(?(?!abc)\d\d|\w{3}:)$/ - abc: - 0: abc: - 12 - 0: 12 - *** Failers -No match - 123 -No match - xyz -No match - -/(?(?<=foo)bar|cat)/ - foobar - 0: bar - cat - 0: cat - fcat - 0: cat - focat - 0: cat - *** Failers -No match - foocat -No match - -/(?(?a*)*/ - a - 0: a - aa - 0: aa - aaaa - 0: aaaa - -/(abc|)+/ - abc - 0: abc - 1: - abcabc - 0: abcabc - 1: - abcabcabc - 0: abcabcabc - 1: - xyz - 0: - 1: - -/([a]*)*/ - a - 0: a - 1: - aaaaa - 0: aaaaa - 1: - -/([ab]*)*/ - a - 0: a - 1: - b - 0: b - 1: - ababab - 0: ababab - 1: - aaaabcde - 0: aaaab - 1: - bbbb - 0: bbbb - 1: - -/([^a]*)*/ - b - 0: b - 1: - bbbb - 0: bbbb - 1: - aaa - 0: - 1: - -/([^ab]*)*/ - cccc - 0: cccc - 1: - abab - 0: - 1: - -/([a]*?)*/ - a - 0: - 1: - aaaa - 0: - 1: - -/([ab]*?)*/ - a - 0: - 1: - b - 0: - 1: - abab - 0: - 1: - baba - 0: - 1: - -/([^a]*?)*/ - b - 0: - 1: - bbbb - 0: - 1: - aaa - 0: - 1: - -/([^ab]*?)*/ - c - 0: - 1: - cccc - 0: - 1: - baba - 0: - 1: - -/(?>a*)*/ - a - 0: a - aaabcde - 0: aaa - -/((?>a*))*/ - aaaaa - 0: aaaaa - 1: - aabbaa - 0: aa - 1: - -/((?>a*?))*/ - aaaaa - 0: - 1: - aabbaa - 0: - 1: - -/(?(?=[^a-z]+[a-z]) \d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} ) /x - 12-sep-98 - 0: 12-sep-98 - 12-09-98 - 0: 12-09-98 - *** Failers -No match - sep-12-98 -No match - -/(?<=(foo))bar\1/ - foobarfoo - 0: barfoo - 1: foo - foobarfootling - 0: barfoo - 1: foo - *** Failers -No match - foobar -No match - barfoo -No match - -/(?i:saturday|sunday)/ - saturday - 0: saturday - sunday - 0: sunday - Saturday - 0: Saturday - Sunday - 0: Sunday - SATURDAY - 0: SATURDAY - SUNDAY - 0: SUNDAY - SunDay - 0: SunDay - -/(a(?i)bc|BB)x/ - abcx - 0: abcx - 1: abc - aBCx - 0: aBCx - 1: aBC - bbx - 0: bbx - 1: bb - BBx - 0: BBx - 1: BB - *** Failers -No match - abcX -No match - aBCX -No match - bbX -No match - BBX -No match - -/^([ab](?i)[cd]|[ef])/ - ac - 0: ac - 1: ac - aC - 0: aC - 1: aC - bD - 0: bD - 1: bD - elephant - 0: e - 1: e - Europe - 0: E - 1: E - frog - 0: f - 1: f - France - 0: F - 1: F - *** Failers -No match - Africa -No match - -/^(ab|a(?i)[b-c](?m-i)d|x(?i)y|z)/ - ab - 0: ab - 1: ab - aBd - 0: aBd - 1: aBd - xy - 0: xy - 1: xy - xY - 0: xY - 1: xY - zebra - 0: z - 1: z - Zambesi - 0: Z - 1: Z - *** Failers -No match - aCD -No match - XY -No match - -/(?<=foo\n)^bar/m - foo\nbar - 0: bar - *** Failers -No match - bar -No match - baz\nbar -No match - -/(?<=(?]&/ - <&OUT - 0: <& - -/^(a\1?){4}$/ - aaaaaaaaaa - 0: aaaaaaaaaa - 1: aaaa - *** Failers -No match - AB -No match - aaaaaaaaa -No match - aaaaaaaaaaa -No match - -/^(a(?(1)\1)){4}$/ - aaaaaaaaaa - 0: aaaaaaaaaa - 1: aaaa - *** Failers -No match - aaaaaaaaa -No match - aaaaaaaaaaa -No match - -/(?:(f)(o)(o)|(b)(a)(r))*/ - foobar - 0: foobar - 1: f - 2: o - 3: o - 4: b - 5: a - 6: r - -/(?<=a)b/ - ab - 0: b - *** Failers -No match - cb -No match - b -No match - -/(? - 2: abcd - xy:z:::abcd - 0: xy:z:::abcd - 1: xy:z::: - 2: abcd - -/^[^bcd]*(c+)/ - aexycd - 0: aexyc - 1: c - -/(a*)b+/ - caab - 0: aab - 1: aa - -/([\w:]+::)?(\w+)$/ - abcd - 0: abcd - 1: - 2: abcd - xy:z:::abcd - 0: xy:z:::abcd - 1: xy:z::: - 2: abcd - *** Failers - 0: Failers - 1: - 2: Failers - abcd: -No match - abcd: -No match - -/^[^bcd]*(c+)/ - aexycd - 0: aexyc - 1: c - -/(>a+)ab/ - -/(?>a+)b/ - aaab - 0: aaab - -/([[:]+)/ - a:[b]: - 0: :[ - 1: :[ - -/([[=]+)/ - a=[b]= - 0: =[ - 1: =[ - -/([[.]+)/ - a.[b]. - 0: .[ - 1: .[ - -/((?>a+)b)/ - aaab - 0: aaab - 1: aaab - -/(?>(a+))b/ - aaab - 0: aaab - 1: aaa - -/((?>[^()]+)|\([^()]*\))+/ - ((abc(ade)ufh()()x - 0: abc(ade)ufh()()x - 1: x - -/a\Z/ - *** Failers -No match - aaab -No match - a\nb\n -No match - -/b\Z/ - a\nb\n - 0: b - -/b\z/ - -/b\Z/ - a\nb - 0: b - -/b\z/ - a\nb - 0: b - *** Failers -No match - -/^(?>(?(1)\.|())[^\W_](?>[a-z0-9-]*[^\W_])?)+$/ - a - 0: a - 1: - abc - 0: abc - 1: - a-b - 0: a-b - 1: - 0-9 - 0: 0-9 - 1: - a.b - 0: a.b - 1: - 5.6.7 - 0: 5.6.7 - 1: - the.quick.brown.fox - 0: the.quick.brown.fox - 1: - a100.b200.300c - 0: a100.b200.300c - 1: - 12-ab.1245 - 0: 12-ab.1245 - 1: - *** Failers -No match - \ -No match - .a -No match - -a -No match - a- -No match - a. -No match - a_b -No match - a.- -No match - a.. -No match - ab..bc -No match - the.quick.brown.fox- -No match - the.quick.brown.fox. -No match - the.quick.brown.fox_ -No match - the.quick.brown.fox+ -No match - -/(?>.*)(?<=(abcd|wxyz))/ - alphabetabcd - 0: alphabetabcd - 1: abcd - endingwxyz - 0: endingwxyz - 1: wxyz - *** Failers -No match - a rather long string that doesn't end with one of them -No match - -/word (?>(?:(?!otherword)[a-zA-Z0-9]+ ){0,30})otherword/ - word cat dog elephant mussel cow horse canary baboon snake shark otherword - 0: word cat dog elephant mussel cow horse canary baboon snake shark otherword - word cat dog elephant mussel cow horse canary baboon snake shark -No match - -/word (?>[a-zA-Z0-9]+ ){0,30}otherword/ - word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope -No match - -/(?<=\d{3}(?!999))foo/ - 999foo - 0: foo - 123999foo - 0: foo - *** Failers -No match - 123abcfoo -No match - -/(?<=(?!...999)\d{3})foo/ - 999foo - 0: foo - 123999foo - 0: foo - *** Failers -No match - 123abcfoo -No match - -/(?<=\d{3}(?!999)...)foo/ - 123abcfoo - 0: foo - 123456foo - 0: foo - *** Failers -No match - 123999foo -No match - -/(?<=\d{3}...)(? - 2: - 3: abcd - - 2: - 3: abcd - \s*)=(?>\s*) # find - 2: - 3: abcd - Z)+|A)*/ - ZABCDEFG - 0: ZA - 1: A - -/((?>)+|A)*/ - ZABCDEFG - 0: - 1: - -/a*/g - abbab - 0: a - 0: - 0: - 0: a - 0: - 0: - -/^[a-\d]/ - abcde - 0: a - -things - 0: - - 0digit - 0: 0 - *** Failers -No match - bcdef -No match - -/^[\d-a]/ - abcde - 0: a - -things - 0: - - 0digit - 0: 0 - *** Failers -No match - bcdef -No match - -/[[:space:]]+/ - > \x09\x0a\x0c\x0d\x0b< - 0: \x09\x0a\x0c\x0d\x0b - -/[[:blank:]]+/ - > \x09\x0a\x0c\x0d\x0b< - 0: \x09 - -/[\s]+/ - > \x09\x0a\x0c\x0d\x0b< - 0: \x09\x0a\x0c\x0d - -/\s+/ - > \x09\x0a\x0c\x0d\x0b< - 0: \x09\x0a\x0c\x0d - -/a b/x - ab -No match - -/(?!\A)x/m - a\nxb\n - 0: x - -/(?!^)x/m - a\nxb\n -No match - -/abc\Qabc\Eabc/ - abcabcabc - 0: abcabcabc - -/abc\Q(*+|\Eabc/ - abc(*+|abc - 0: abc(*+|abc - -/ abc\Q abc\Eabc/x - abc abcabc - 0: abc abcabc - *** Failers -No match - abcabcabc -No match - -/abc#comment - \Q#not comment - literal\E/x - abc#not comment\n literal - 0: abc#not comment\x0a literal - -/abc#comment - \Q#not comment - literal/x - abc#not comment\n literal - 0: abc#not comment\x0a literal - -/abc#comment - \Q#not comment - literal\E #more comment - /x - abc#not comment\n literal - 0: abc#not comment\x0a literal - -/abc#comment - \Q#not comment - literal\E #more comment/x - abc#not comment\n literal - 0: abc#not comment\x0a literal - -/\Qabc\$xyz\E/ - abc\\\$xyz - 0: abc\$xyz - -/\Qabc\E\$\Qxyz\E/ - abc\$xyz - 0: abc$xyz - -/\Gabc/ - abc - 0: abc - *** Failers -No match - xyzabc -No match - -/\Gabc./g - abc1abc2xyzabc3 - 0: abc1 - 0: abc2 - -/abc./g - abc1abc2xyzabc3 - 0: abc1 - 0: abc2 - 0: abc3 - -/a(?x: b c )d/ - XabcdY - 0: abcd - *** Failers -No match - Xa b c d Y -No match - -/((?x)x y z | a b c)/ - XabcY - 0: abc - 1: abc - AxyzB - 0: xyz - 1: xyz - -/(?i)AB(?-i)C/ - XabCY - 0: abC - *** Failers -No match - XabcY -No match - -/((?i)AB(?-i)C|D)E/ - abCE - 0: abCE - 1: abC - DE - 0: DE - 1: D - *** Failers -No match - abcE -No match - abCe -No match - dE -No match - De -No match - -/(.*)\d+\1/ - abc123abc - 0: abc123abc - 1: abc - abc123bc - 0: bc123bc - 1: bc - -/(.*)\d+\1/s - abc123abc - 0: abc123abc - 1: abc - abc123bc - 0: bc123bc - 1: bc - -/((.*))\d+\1/ - abc123abc - 0: abc123abc - 1: abc - 2: abc - abc123bc - 0: bc123bc - 1: bc - 2: bc - -/-- This tests for an IPv6 address in the form where it can have up to --/ -/-- eight components, one and only one of which is empty. This must be --/ -No match -/-- an internal component. --/ -No match - -/^(?!:) # colon disallowed at start - (?: # start of item - (?: [0-9a-f]{1,4} | # 1-4 hex digits or - (?(1)0 | () ) ) # if null previously matched, fail; else null - : # followed by colon - ){1,7} # end item; 1-7 of them required - [0-9a-f]{1,4} $ # final hex number at end of string - (?(1)|.) # check that there was an empty component - /xi - a123::a123 - 0: a123::a123 - 1: - a123:b342::abcd - 0: a123:b342::abcd - 1: - a123:b342::324e:abcd - 0: a123:b342::324e:abcd - 1: - a123:ddde:b342::324e:abcd - 0: a123:ddde:b342::324e:abcd - 1: - a123:ddde:b342::324e:dcba:abcd - 0: a123:ddde:b342::324e:dcba:abcd - 1: - a123:ddde:9999:b342::324e:dcba:abcd - 0: a123:ddde:9999:b342::324e:dcba:abcd - 1: - *** Failers -No match - 1:2:3:4:5:6:7:8 -No match - a123:bce:ddde:9999:b342::324e:dcba:abcd -No match - a123::9999:b342::324e:dcba:abcd -No match - abcde:2:3:4:5:6:7:8 -No match - ::1 -No match - abcd:fee0:123:: -No match - :1 -No match - 1: -No match - -/[z\Qa-d]\E]/ - z - 0: z - a - 0: a - - - 0: - - d - 0: d - ] - 0: ] - *** Failers - 0: a - b -No match - -/[\z\C]/ - z - 0: z - C - 0: C - -/\M/ - M - 0: M - -/(a+)*b/ - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -No match - -/(?i)reg(?:ul(?:[aä]|ae)r|ex)/ - REGular - 0: REGular - regulaer - 0: regulaer - Regex - 0: Regex - regulär - 0: regul\xe4r - -/Åæåä[à-ÿÀ-ß]+/ - Åæåäà - 0: \xc5\xe6\xe5\xe4\xe0 - Åæåäÿ - 0: \xc5\xe6\xe5\xe4\xff - ÅæåäÀ - 0: \xc5\xe6\xe5\xe4\xc0 - Åæåäß - 0: \xc5\xe6\xe5\xe4\xdf - -/(?<=Z)X./ - \x84XAZXB - 0: XB - -/ab cd (?x) de fg/ - ab cd defg - 0: ab cd defg - -/ab cd(?x) de fg/ - ab cddefg - 0: ab cddefg - ** Failers -No match - abcddefg -No match - -/(? - 2: - D - 0: D - 1: - 2: - -/(a|)*\d/ - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -No match - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 - 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 - 1: - -/(?>a|)*\d/ - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -No match - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 - 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 - -/(?:a|)*\d/ - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -No match - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 - 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 - -/\Z/g - abc\n - 0: - 0: - -/^(?s)(?>.*)(?iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|BM -Memory allocation (code space): 826 ------------------------------------------------------------------- - 0 822 Bra - 3 8J$WE<.rX+ix[d1b!H#?vV0vrK:ZH1=2M>iV;?aPhFB<*vW@QW@sO9}cfZA-i'w%hKd6gt1UJP,15_#QY$M^Mss_U/]&LK9[5vQub^w[KDDqmj;2}YWFdYx.Ap]hjCPTP(n28k+3;o&WXqs/gOXdr$:r'do0;b4c(f_Gr="\4)[01T7ajQJvL$W~mL_sS/4h:x*[ZN=KLs&L5zX//>it,o:aU(;Z>pW&T7oP'2K^E:x9'c[%z-,64JQ5AeH_G#KijUKghQw^\vea3a?kka_G$8#`*kynsxzBLru']k_[7FrVx}^=$blx>s-N%j;D*aZDnsw:YKZ%Q.Kne9#hP?+b3(SOvL,^;&u5@?5C5Bhb=m-vEh_L15Jl]U)0RP6{q%L^_z5E'Dw6X -821 \b -822 822 Ket -825 End ------------------------------------------------------------------- - -|\$\<\.X\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|BM -Memory allocation (code space): 816 ------------------------------------------------------------------- - 0 812 Bra - 3 $<.X+ix[d1b!H#?vV0vrK:ZH1=2M>iV;?aPhFB<*vW@QW@sO9}cfZA-i'w%hKd6gt1UJP,15_#QY$M^Mss_U/]&LK9[5vQub^w[KDDqmj;2}YWFdYx.Ap]hjCPTP(n28k+3;o&WXqs/gOXdr$:r'do0;b4c(f_Gr="\4)[01T7ajQJvL$W~mL_sS/4h:x*[ZN=KLs&L5zX//>it,o:aU(;Z>pW&T7oP'2K^E:x9'c[%z-,64JQ5AeH_G#KijUKghQw^\vea3a?kka_G$8#`*kynsxzBLru']k_[7FrVx}^=$blx>s-N%j;D*aZDnsw:YKZ%Q.Kne9#hP?+b3(SOvL,^;&u5@?5C5Bhb=m-vEh_L15Jl]U)0RP6{q%L^_z5E'Dw6X -811 \b -812 812 Ket -815 End ------------------------------------------------------------------- - -/(a(?1)b)/BM -Memory allocation (code space): 28 ------------------------------------------------------------------- - 0 24 Bra - 3 18 CBra 1 - 8 a - 10 6 Once - 13 3 Recurse - 16 6 Ket - 19 b - 21 18 Ket - 24 24 Ket - 27 End ------------------------------------------------------------------- - -/(a(?1)+b)/BM -Memory allocation (code space): 28 ------------------------------------------------------------------- - 0 24 Bra - 3 18 CBra 1 - 8 a - 10 6 Once - 13 3 Recurse - 16 6 KetRmax - 19 b - 21 18 Ket - 24 24 Ket - 27 End ------------------------------------------------------------------- - -/a(?Pb|c)d(?Pe)/BM -Memory allocation (code space): 42 ------------------------------------------------------------------- - 0 32 Bra - 3 a - 5 7 CBra 1 - 10 b - 12 5 Alt - 15 c - 17 12 Ket - 20 d - 22 7 CBra 2 - 27 e - 29 7 Ket - 32 32 Ket - 35 End ------------------------------------------------------------------- - -/(?:a(?Pc(?Pd)))(?Pa)/BM -Memory allocation (code space): 54 ------------------------------------------------------------------- - 0 41 Bra - 3 25 Bra - 6 a - 8 17 CBra 1 - 13 c - 15 7 CBra 2 - 20 d - 22 7 Ket - 25 17 Ket - 28 25 Ket - 31 7 CBra 3 - 36 a - 38 7 Ket - 41 41 Ket - 44 End ------------------------------------------------------------------- - -/(?Pa)...(?P=a)bbb(?P>a)d/BM -Memory allocation (code space): 43 ------------------------------------------------------------------- - 0 36 Bra - 3 7 CBra 1 - 8 a - 10 7 Ket - 13 Any - 14 Any - 15 Any - 16 \1 - 19 bbb - 25 6 Once - 28 3 Recurse - 31 6 Ket - 34 d - 36 36 Ket - 39 End ------------------------------------------------------------------- - -/abc(?C255)de(?C)f/BM -Memory allocation (code space): 31 ------------------------------------------------------------------- - 0 27 Bra - 3 abc - 9 Callout 255 10 1 - 15 de - 19 Callout 0 16 1 - 25 f - 27 27 Ket - 30 End ------------------------------------------------------------------- - -/abcde/CBM -Memory allocation (code space): 53 ------------------------------------------------------------------- - 0 49 Bra - 3 Callout 255 0 1 - 9 a - 11 Callout 255 1 1 - 17 b - 19 Callout 255 2 1 - 25 c - 27 Callout 255 3 1 - 33 d - 35 Callout 255 4 1 - 41 e - 43 Callout 255 5 0 - 49 49 Ket - 52 End ------------------------------------------------------------------- - -/\x{100}/8BM -Memory allocation (code space): 10 ------------------------------------------------------------------- - 0 6 Bra - 3 \x{100} - 6 6 Ket - 9 End ------------------------------------------------------------------- - -/\x{1000}/8BM -Memory allocation (code space): 11 ------------------------------------------------------------------- - 0 7 Bra - 3 \x{1000} - 7 7 Ket - 10 End ------------------------------------------------------------------- - -/\x{10000}/8BM -Memory allocation (code space): 12 ------------------------------------------------------------------- - 0 8 Bra - 3 \x{10000} - 8 8 Ket - 11 End ------------------------------------------------------------------- - -/\x{100000}/8BM -Memory allocation (code space): 12 ------------------------------------------------------------------- - 0 8 Bra - 3 \x{100000} - 8 8 Ket - 11 End ------------------------------------------------------------------- - -/\x{1000000}/8BM -Memory allocation (code space): 13 ------------------------------------------------------------------- - 0 9 Bra - 3 \x{1000000} - 9 9 Ket - 12 End ------------------------------------------------------------------- - -/\x{4000000}/8BM -Memory allocation (code space): 14 ------------------------------------------------------------------- - 0 10 Bra - 3 \x{4000000} - 10 10 Ket - 13 End ------------------------------------------------------------------- - -/\x{7fffFFFF}/8BM -Memory allocation (code space): 14 ------------------------------------------------------------------- - 0 10 Bra - 3 \x{7fffffff} - 10 10 Ket - 13 End ------------------------------------------------------------------- - -/[\x{ff}]/8BM -Memory allocation (code space): 10 ------------------------------------------------------------------- - 0 6 Bra - 3 \x{ff} - 6 6 Ket - 9 End ------------------------------------------------------------------- - -/[\x{100}]/8BM -Memory allocation (code space): 15 ------------------------------------------------------------------- - 0 11 Bra - 3 [\x{100}] - 11 11 Ket - 14 End ------------------------------------------------------------------- - -/\x80/8BM -Memory allocation (code space): 10 ------------------------------------------------------------------- - 0 6 Bra - 3 \x{80} - 6 6 Ket - 9 End ------------------------------------------------------------------- - -/\xff/8BM -Memory allocation (code space): 10 ------------------------------------------------------------------- - 0 6 Bra - 3 \x{ff} - 6 6 Ket - 9 End ------------------------------------------------------------------- - -/\x{0041}\x{2262}\x{0391}\x{002e}/D8M -Memory allocation (code space): 18 ------------------------------------------------------------------- - 0 14 Bra - 3 A\x{2262}\x{391}. - 14 14 Ket - 17 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 'A' -Need char = '.' - -/\x{D55c}\x{ad6d}\x{C5B4}/D8M -Memory allocation (code space): 19 ------------------------------------------------------------------- - 0 15 Bra - 3 \x{d55c}\x{ad6d}\x{c5b4} - 15 15 Ket - 18 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 237 -Need char = 180 - -/\x{65e5}\x{672c}\x{8a9e}/D8M -Memory allocation (code space): 19 ------------------------------------------------------------------- - 0 15 Bra - 3 \x{65e5}\x{672c}\x{8a9e} - 15 15 Ket - 18 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 230 -Need char = 158 - -/[\x{100}]/8BM -Memory allocation (code space): 15 ------------------------------------------------------------------- - 0 11 Bra - 3 [\x{100}] - 11 11 Ket - 14 End ------------------------------------------------------------------- - -/[Z\x{100}]/8BM -Memory allocation (code space): 47 ------------------------------------------------------------------- - 0 43 Bra - 3 [Z\x{100}] - 43 43 Ket - 46 End ------------------------------------------------------------------- - -/^[\x{100}\E-\Q\E\x{150}]/B8M -Memory allocation (code space): 18 ------------------------------------------------------------------- - 0 14 Bra - 3 ^ - 4 [\x{100}-\x{150}] - 14 14 Ket - 17 End ------------------------------------------------------------------- - -/^[\QÄ€\E-\QÅ\E]/B8M -Memory allocation (code space): 18 ------------------------------------------------------------------- - 0 14 Bra - 3 ^ - 4 [\x{100}-\x{150}] - 14 14 Ket - 17 End ------------------------------------------------------------------- - -/^[\QÄ€\E-\QÅ\E/B8M -Failed: missing terminating ] for character class at offset 15 - -/[\p{L}]/BM -Memory allocation (code space): 15 ------------------------------------------------------------------- - 0 11 Bra - 3 [\p{L}] - 11 11 Ket - 14 End ------------------------------------------------------------------- - -/[\p{^L}]/BM -Memory allocation (code space): 15 ------------------------------------------------------------------- - 0 11 Bra - 3 [\P{L}] - 11 11 Ket - 14 End ------------------------------------------------------------------- - -/[\P{L}]/BM -Memory allocation (code space): 15 ------------------------------------------------------------------- - 0 11 Bra - 3 [\P{L}] - 11 11 Ket - 14 End ------------------------------------------------------------------- - -/[\P{^L}]/BM -Memory allocation (code space): 15 ------------------------------------------------------------------- - 0 11 Bra - 3 [\p{L}] - 11 11 Ket - 14 End ------------------------------------------------------------------- - -/[abc\p{L}\x{0660}]/8BM -Memory allocation (code space): 50 ------------------------------------------------------------------- - 0 46 Bra - 3 [a-c\p{L}\x{660}] - 46 46 Ket - 49 End ------------------------------------------------------------------- - -/[\p{Nd}]/8BM -Memory allocation (code space): 15 ------------------------------------------------------------------- - 0 11 Bra - 3 [\p{Nd}] - 11 11 Ket - 14 End ------------------------------------------------------------------- - -/[\p{Nd}+-]+/8BM -Memory allocation (code space): 48 ------------------------------------------------------------------- - 0 44 Bra - 3 [+\-\p{Nd}]+ - 44 44 Ket - 47 End ------------------------------------------------------------------- - -/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8iBM -Memory allocation (code space): 25 ------------------------------------------------------------------- - 0 21 Bra - 3 NC A\x{391}\x{10427}\x{ff3a}\x{1fb0} - 21 21 Ket - 24 End ------------------------------------------------------------------- - -/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8BM -Memory allocation (code space): 25 ------------------------------------------------------------------- - 0 21 Bra - 3 A\x{391}\x{10427}\x{ff3a}\x{1fb0} - 21 21 Ket - 24 End ------------------------------------------------------------------- - -/[\x{105}-\x{109}]/8iBM -Memory allocation (code space): 17 ------------------------------------------------------------------- - 0 13 Bra - 3 [\x{104}-\x{109}] - 13 13 Ket - 16 End ------------------------------------------------------------------- - -/( ( (?(1)0|) )* )/xBM -Memory allocation (code space): 38 ------------------------------------------------------------------- - 0 34 Bra - 3 28 CBra 1 - 8 Brazero - 9 19 SCBra 2 - 14 8 Cond - 17 1 Cond ref - 20 0 - 22 3 Alt - 25 11 Ket - 28 19 KetRmax - 31 28 Ket - 34 34 Ket - 37 End ------------------------------------------------------------------- - -/( (?(1)0|)* )/xBM -Memory allocation (code space): 30 ------------------------------------------------------------------- - 0 26 Bra - 3 20 CBra 1 - 8 Brazero - 9 8 SCond - 12 1 Cond ref - 15 0 - 17 3 Alt - 20 11 KetRmax - 23 20 Ket - 26 26 Ket - 29 End ------------------------------------------------------------------- - -/[a]/BM -Memory allocation (code space): 9 ------------------------------------------------------------------- - 0 5 Bra - 3 a - 5 5 Ket - 8 End ------------------------------------------------------------------- - -/[a]/8BM -Memory allocation (code space): 9 ------------------------------------------------------------------- - 0 5 Bra - 3 a - 5 5 Ket - 8 End ------------------------------------------------------------------- - -/[\xaa]/BM -Memory allocation (code space): 9 ------------------------------------------------------------------- - 0 5 Bra - 3 \xaa - 5 5 Ket - 8 End ------------------------------------------------------------------- - -/[\xaa]/8BM -Memory allocation (code space): 10 ------------------------------------------------------------------- - 0 6 Bra - 3 \x{aa} - 6 6 Ket - 9 End ------------------------------------------------------------------- - -/[^a]/BM -Memory allocation (code space): 9 ------------------------------------------------------------------- - 0 5 Bra - 3 [^a] - 5 5 Ket - 8 End ------------------------------------------------------------------- - -/[^a]/8BM -Memory allocation (code space): 9 ------------------------------------------------------------------- - 0 5 Bra - 3 [^a] - 5 5 Ket - 8 End ------------------------------------------------------------------- - -/[^\xaa]/BM -Memory allocation (code space): 9 ------------------------------------------------------------------- - 0 5 Bra - 3 [^\xaa] - 5 5 Ket - 8 End ------------------------------------------------------------------- - -/[^\xaa]/8BM -Memory allocation (code space): 40 ------------------------------------------------------------------- - 0 36 Bra - 3 [\x00-\xa9\xab-\xff] (neg) - 36 36 Ket - 39 End ------------------------------------------------------------------- - -/ End of testinput10 / diff --git a/libs/pcre/testdata/testoutput2 b/libs/pcre/testdata/testoutput2 deleted file mode 100644 index 420e75dc40..0000000000 --- a/libs/pcre/testdata/testoutput2 +++ /dev/null @@ -1,9843 +0,0 @@ -/(a)b|/I -Capturing subpattern count = 1 -No options -No first char -No need char - -/abc/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' - abc - 0: abc - defabc - 0: abc - \Aabc - 0: abc - *** Failers -No match - \Adefabc -No match - ABC -No match - -/^abc/I -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - abc - 0: abc - \Aabc - 0: abc - *** Failers -No match - defabc -No match - \Adefabc -No match - -/a+bc/I -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'a' -Need char = 'c' - -/a*bc/I -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -Need char = 'c' - -/a{3}bc/I -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'a' -Need char = 'c' - -/(abc|a+z)/I -Capturing subpattern count = 1 -Partial matching not supported -No options -First char = 'a' -No need char - -/^abc$/I -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - abc - 0: abc - *** Failers -No match - def\nabc -No match - -/ab\idef/X -Failed: unrecognized character follows \ at offset 3 - -/(?X)ab\idef/X -Failed: unrecognized character follows \ at offset 7 - -/x{5,4}/ -Failed: numbers out of order in {} quantifier at offset 5 - -/z{65536}/ -Failed: number too big in {} quantifier at offset 7 - -/[abcd/ -Failed: missing terminating ] for character class at offset 5 - -/(?X)[\B]/ -Failed: invalid escape sequence in character class at offset 6 - -/[z-a]/ -Failed: range out of order in character class at offset 3 - -/^*/ -Failed: nothing to repeat at offset 1 - -/(abc/ -Failed: missing ) at offset 4 - -/(?# abc/ -Failed: missing ) after comment at offset 7 - -/(?z)abc/ -Failed: unrecognized character after (? or (?- at offset 2 - -/.*b/I -Capturing subpattern count = 0 -Partial matching not supported -No options -First char at start or follows newline -Need char = 'b' - -/.*?b/I -Capturing subpattern count = 0 -Partial matching not supported -No options -First char at start or follows newline -Need char = 'b' - -/cat|dog|elephant/I -Capturing subpattern count = 0 -No options -No first char -No need char - this sentence eventually mentions a cat - 0: cat - this sentences rambles on and on for a while and then reaches elephant - 0: elephant - -/cat|dog|elephant/IS -Capturing subpattern count = 0 -No options -No first char -No need char -Starting byte set: c d e - this sentence eventually mentions a cat - 0: cat - this sentences rambles on and on for a while and then reaches elephant - 0: elephant - -/cat|dog|elephant/IiS -Capturing subpattern count = 0 -Options: caseless -No first char -No need char -Starting byte set: C D E c d e - this sentence eventually mentions a CAT cat - 0: CAT - this sentences rambles on and on for a while to elephant ElePhant - 0: elephant - -/a|[bcd]/IS -Capturing subpattern count = 0 -No options -No first char -No need char -Starting byte set: a b c d - -/(a|[^\dZ])/IS -Capturing subpattern count = 1 -No options -No first char -No need char -Starting byte set: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a - \x0b \x0c \x0d \x0e \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 - \x1a \x1b \x1c \x1d \x1e \x1f \x20 ! " # $ % & ' ( ) * + , - . / : ; < = > - ? @ A B C D E F G H I J K L M N O P Q R S T U V W X Y [ \ ] ^ _ ` a b c d - e f g h i j k l m n o p q r s t u v w x y z { | } ~ \x7f \x80 \x81 \x82 \x83 - \x84 \x85 \x86 \x87 \x88 \x89 \x8a \x8b \x8c \x8d \x8e \x8f \x90 \x91 \x92 - \x93 \x94 \x95 \x96 \x97 \x98 \x99 \x9a \x9b \x9c \x9d \x9e \x9f \xa0 \xa1 - \xa2 \xa3 \xa4 \xa5 \xa6 \xa7 \xa8 \xa9 \xaa \xab \xac \xad \xae \xaf \xb0 - \xb1 \xb2 \xb3 \xb4 \xb5 \xb6 \xb7 \xb8 \xb9 \xba \xbb \xbc \xbd \xbe \xbf - \xc0 \xc1 \xc2 \xc3 \xc4 \xc5 \xc6 \xc7 \xc8 \xc9 \xca \xcb \xcc \xcd \xce - \xcf \xd0 \xd1 \xd2 \xd3 \xd4 \xd5 \xd6 \xd7 \xd8 \xd9 \xda \xdb \xdc \xdd - \xde \xdf \xe0 \xe1 \xe2 \xe3 \xe4 \xe5 \xe6 \xe7 \xe8 \xe9 \xea \xeb \xec - \xed \xee \xef \xf0 \xf1 \xf2 \xf3 \xf4 \xf5 \xf6 \xf7 \xf8 \xf9 \xfa \xfb - \xfc \xfd \xfe \xff - -/(a|b)*[\s]/IS -Capturing subpattern count = 1 -No options -No first char -No need char -Starting byte set: \x09 \x0a \x0c \x0d \x20 a b - -/(ab\2)/ -Failed: reference to non-existent subpattern at offset 6 - -/{4,5}abc/ -Failed: nothing to repeat at offset 4 - -/(a)(b)(c)\2/I -Capturing subpattern count = 3 -Max back reference = 2 -No options -First char = 'a' -Need char = 'c' - abcb - 0: abcb - 1: a - 2: b - 3: c - \O0abcb -Matched, but too many substrings - \O3abcb -Matched, but too many substrings - 0: abcb - \O6abcb -Matched, but too many substrings - 0: abcb - 1: a - \O9abcb -Matched, but too many substrings - 0: abcb - 1: a - 2: b - \O12abcb - 0: abcb - 1: a - 2: b - 3: c - -/(a)bc|(a)(b)\2/I -Capturing subpattern count = 3 -Max back reference = 2 -No options -First char = 'a' -No need char - abc - 0: abc - 1: a - \O0abc -Matched, but too many substrings - \O3abc -Matched, but too many substrings - 0: abc - \O6abc - 0: abc - 1: a - aba - 0: aba - 1: - 2: a - 3: b - \O0aba -Matched, but too many substrings - \O3aba -Matched, but too many substrings - 0: aba - \O6aba -Matched, but too many substrings - 0: aba - 1: - \O9aba -Matched, but too many substrings - 0: aba - 1: - 2: a - \O12aba - 0: aba - 1: - 2: a - 3: b - -/abc$/IE -Capturing subpattern count = 0 -Options: dollar_endonly -First char = 'a' -Need char = 'c' - abc - 0: abc - *** Failers -No match - abc\n -No match - abc\ndef -No match - -/(a)(b)(c)(d)(e)\6/ -Failed: reference to non-existent subpattern at offset 17 - -/the quick brown fox/I -Capturing subpattern count = 0 -No options -First char = 't' -Need char = 'x' - the quick brown fox - 0: the quick brown fox - this is a line with the quick brown fox - 0: the quick brown fox - -/the quick brown fox/IA -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - the quick brown fox - 0: the quick brown fox - *** Failers -No match - this is a line with the quick brown fox -No match - -/ab(?z)cd/ -Failed: unrecognized character after (? or (?- at offset 4 - -/^abc|def/I -Capturing subpattern count = 0 -No options -No first char -No need char - abcdef - 0: abc - abcdef\B - 0: def - -/.*((abc)$|(def))/I -Capturing subpattern count = 3 -Partial matching not supported -No options -First char at start or follows newline -No need char - defabc - 0: defabc - 1: abc - 2: abc - \Zdefabc - 0: def - 1: def - 2: - 3: def - -/abc/IP - abc - 0: abc - *** Failers -No match: POSIX code 17: match failed - -/^abc|def/IP - abcdef - 0: abc - abcdef\B - 0: def - -/.*((abc)$|(def))/IP - defabc - 0: defabc - 1: abc - 2: abc - \Zdefabc - 0: def - 1: def - 3: def - -/the quick brown fox/IP - the quick brown fox - 0: the quick brown fox - *** Failers -No match: POSIX code 17: match failed - The Quick Brown Fox -No match: POSIX code 17: match failed - -/the quick brown fox/IPi - the quick brown fox - 0: the quick brown fox - The Quick Brown Fox - 0: The Quick Brown Fox - -/abc.def/IP - *** Failers -No match: POSIX code 17: match failed - abc\ndef -No match: POSIX code 17: match failed - -/abc$/IP - abc - 0: abc - abc\n - 0: abc - -/(abc)\2/IP -Failed: POSIX code 15: bad back reference at offset 7 - -/(abc\1)/IP - abc -No match: POSIX code 17: match failed - -/)/ -Failed: unmatched parentheses at offset 0 - -/a[]b/ -Failed: missing terminating ] for character class at offset 4 - -/[^aeiou ]{3,}/I -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -No need char - co-processors, and for - 0: -pr - -/<.*>/I -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = '<' -Need char = '>' - abcghinop - 0: ghi - -/<.*?>/I -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = '<' -Need char = '>' - abcghinop - 0: - -/<.*>/IU -Capturing subpattern count = 0 -Partial matching not supported -Options: ungreedy -First char = '<' -Need char = '>' - abcghinop - 0: - -/(?U)<.*>/I -Capturing subpattern count = 0 -Partial matching not supported -Options: ungreedy -First char = '<' -Need char = '>' - abcghinop - 0: - -/<.*?>/IU -Capturing subpattern count = 0 -Partial matching not supported -Options: ungreedy -First char = '<' -Need char = '>' - abcghinop - 0: ghi - -/={3,}/IU -Capturing subpattern count = 0 -Partial matching not supported -Options: ungreedy -First char = '=' -Need char = '=' - abc========def - 0: === - -/(?U)={3,}?/I -Capturing subpattern count = 0 -Partial matching not supported -Options: ungreedy -First char = '=' -Need char = '=' - abc========def - 0: ======== - -/(?^abc)/Im -Capturing subpattern count = 0 -Options: multiline -First char at start or follows newline -Need char = 'c' - abc - 0: abc - def\nabc - 0: abc - *** Failers -No match - defabc -No match - -/(?<=ab(c+)d)ef/ -Failed: lookbehind assertion is not fixed length at offset 11 - -/(?<=ab(?<=c+)d)ef/ -Failed: lookbehind assertion is not fixed length at offset 12 - -/(?<=ab(c|de)f)g/ -Failed: lookbehind assertion is not fixed length at offset 13 - -/The next three are in testinput2 because they have variable length branches/ - -/(?<=bullock|donkey)-cart/I -Capturing subpattern count = 0 -No options -First char = '-' -Need char = 't' - the bullock-cart - 0: -cart - a donkey-cart race - 0: -cart - *** Failers -No match - cart -No match - horse-and-cart -No match - -/(?<=ab(?i)x|y|z)/I -Capturing subpattern count = 0 -No options -No first char -No need char - -/(?>.*)(?<=(abcd)|(xyz))/I -Capturing subpattern count = 2 -Partial matching not supported -No options -First char at start or follows newline -No need char - alphabetabcd - 0: alphabetabcd - 1: abcd - endingxyz - 0: endingxyz - 1: - 2: xyz - -/(?<=ab(?i)x(?-i)y|(?i)z|b)ZZ/I -Capturing subpattern count = 0 -No options -First char = 'Z' -Need char = 'Z' - abxyZZ - 0: ZZ - abXyZZ - 0: ZZ - ZZZ - 0: ZZ - zZZ - 0: ZZ - bZZ - 0: ZZ - BZZ - 0: ZZ - *** Failers -No match - ZZ -No match - abXYZZ -No match - zzz -No match - bzz -No match - -/(? - 3: f - 1G a (1) - 2G (0) - 3G f (1) -get substring 4 failed -7 - 0L adef - 1L a - 2L - 3L f - bcdef\G1\G2\G3\G4\L - 0: bcdef - 1: bc - 2: bc - 3: f - 1G bc (2) - 2G bc (2) - 3G f (1) -get substring 4 failed -7 - 0L bcdef - 1L bc - 2L bc - 3L f - adefghijk\C0 - 0: adef - 1: a - 2: - 3: f - 0C adef (4) - -/^abc\00def/I -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - abc\00def\L\C0 - 0: abc\x00def - 0C abc (7) - 0L abc - -/word ((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ -)((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ -)?)?)?)?)?)?)?)?)?otherword/I -Capturing subpattern count = 8 -Partial matching not supported -Contains explicit CR or LF match -No options -First char = 'w' -Need char = 'd' - -/.*X/IDZ ------------------------------------------------------------------- - Bra - Any* - X - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -No options -First char at start or follows newline -Need char = 'X' - -/.*X/IDZs ------------------------------------------------------------------- - Bra - AllAny* - X - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: anchored dotall -No first char -Need char = 'X' - -/(.*X|^B)/IDZ ------------------------------------------------------------------- - Bra - CBra 1 - Any* - X - Alt - ^ - B - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Partial matching not supported -No options -First char at start or follows newline -No need char - -/(.*X|^B)/IDZs ------------------------------------------------------------------- - Bra - CBra 1 - AllAny* - X - Alt - ^ - B - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Partial matching not supported -Options: anchored dotall -No first char -No need char - -/(?s)(.*X|^B)/IDZ ------------------------------------------------------------------- - Bra - CBra 1 - AllAny* - X - Alt - ^ - B - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Partial matching not supported -Options: anchored dotall -No first char -No need char - -/(?s:.*X|^B)/IDZ ------------------------------------------------------------------- - Bra - Bra - 04 Opt - AllAny* - X - Alt - 04 Opt - ^ - B - Ket - 00 Opt - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: anchored -No first char -No need char - -/\Biss\B/I+ -Capturing subpattern count = 0 -No options -First char = 'i' -Need char = 's' - Mississippi - 0: iss - 0+ issippi - -/\Biss\B/I+P - Mississippi - 0: iss - 0+ issippi - -/iss/IG+ -Capturing subpattern count = 0 -No options -First char = 'i' -Need char = 's' - Mississippi - 0: iss - 0+ issippi - 0: iss - 0+ ippi - -/\Biss\B/IG+ -Capturing subpattern count = 0 -No options -First char = 'i' -Need char = 's' - Mississippi - 0: iss - 0+ issippi - -/\Biss\B/Ig+ -Capturing subpattern count = 0 -No options -First char = 'i' -Need char = 's' - Mississippi - 0: iss - 0+ issippi - 0: iss - 0+ ippi - *** Failers -No match - Mississippi\A -No match - -/(?<=[Ms])iss/Ig+ -Capturing subpattern count = 0 -No options -First char = 'i' -Need char = 's' - Mississippi - 0: iss - 0+ issippi - 0: iss - 0+ ippi - -/(?<=[Ms])iss/IG+ -Capturing subpattern count = 0 -No options -First char = 'i' -Need char = 's' - Mississippi - 0: iss - 0+ issippi - -/^iss/Ig+ -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - ississippi - 0: iss - 0+ issippi - -/.*iss/Ig+ -Capturing subpattern count = 0 -Partial matching not supported -No options -First char at start or follows newline -Need char = 's' - abciss\nxyzisspqr - 0: abciss - 0+ \x0axyzisspqr - 0: xyziss - 0+ pqr - -/.i./I+g -Capturing subpattern count = 0 -No options -No first char -Need char = 'i' - Mississippi - 0: Mis - 0+ sissippi - 0: sis - 0+ sippi - 0: sip - 0+ pi - Mississippi\A - 0: Mis - 0+ sissippi - 0: sis - 0+ sippi - 0: sip - 0+ pi - Missouri river - 0: Mis - 0+ souri river - 0: ri - 0+ river - 0: riv - 0+ er - Missouri river\A - 0: Mis - 0+ souri river - -/^.is/I+g -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - Mississippi - 0: Mis - 0+ sissippi - -/^ab\n/Ig+ -Capturing subpattern count = 0 -Contains explicit CR or LF match -Options: anchored -No first char -No need char - ab\nab\ncd - 0: ab\x0a - 0+ ab\x0acd - -/^ab\n/Img+ -Capturing subpattern count = 0 -Contains explicit CR or LF match -Options: multiline -First char at start or follows newline -Need char = 10 - ab\nab\ncd - 0: ab\x0a - 0+ ab\x0acd - 0: ab\x0a - 0+ cd - -/abc/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' - -/abc|bac/I -Capturing subpattern count = 0 -No options -No first char -Need char = 'c' - -/(abc|bac)/I -Capturing subpattern count = 1 -No options -No first char -Need char = 'c' - -/(abc|(c|dc))/I -Capturing subpattern count = 2 -No options -No first char -Need char = 'c' - -/(abc|(d|de)c)/I -Capturing subpattern count = 2 -No options -No first char -Need char = 'c' - -/a*/I -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -No need char - -/a+/I -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'a' -No need char - -/(baa|a+)/I -Capturing subpattern count = 1 -Partial matching not supported -No options -No first char -Need char = 'a' - -/a{0,3}/I -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -No need char - -/baa{3,}/I -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'b' -Need char = 'a' - -/"([^\\"]+|\\.)*"/I -Capturing subpattern count = 1 -Partial matching not supported -No options -First char = '"' -Need char = '"' - -/(abc|ab[cd])/I -Capturing subpattern count = 1 -No options -First char = 'a' -No need char - -/(a|.)/I -Capturing subpattern count = 1 -No options -No first char -No need char - -/a|ba|\w/I -Capturing subpattern count = 0 -No options -No first char -No need char - -/abc(?=pqr)/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'r' - -/...(?<=abc)/I -Capturing subpattern count = 0 -No options -No first char -No need char - -/abc(?!pqr)/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' - -/ab./I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - -/ab[xyz]/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - -/abc*/I -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'a' -Need char = 'b' - -/ab.c*/I -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'a' -Need char = 'b' - -/a.c*/I -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'a' -No need char - -/.c*/I -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -No need char - -/ac*/I -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'a' -No need char - -/(a.c*|b.c*)/I -Capturing subpattern count = 1 -Partial matching not supported -No options -No first char -No need char - -/a.c*|aba/I -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'a' -No need char - -/.+a/I -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -Need char = 'a' - -/(?=abcda)a.*/I -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'a' -Need char = 'a' - -/(?=a)a.*/I -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'a' -No need char - -/a(b)*/I -Capturing subpattern count = 1 -No options -First char = 'a' -No need char - -/a\d*/I -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'a' -No need char - -/ab\d*/I -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'a' -Need char = 'b' - -/a(\d)*/I -Capturing subpattern count = 1 -No options -First char = 'a' -No need char - -/abcde{0,0}/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'd' - -/ab\d+/I -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'a' -Need char = 'b' - -/a(?(1)b)(.)/I -Capturing subpattern count = 1 -No options -First char = 'a' -No need char - -/a(?(1)bag|big)(.)/I -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'g' - -/a(?(1)bag|big)*(.)/I -Capturing subpattern count = 1 -No options -First char = 'a' -No need char - -/a(?(1)bag|big)+(.)/I -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'g' - -/a(?(1)b..|b..)(.)/I -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'b' - -/ab\d{0}e/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'e' - -/a?b?/I -Capturing subpattern count = 0 -No options -No first char -No need char - a - 0: a - b - 0: b - ab - 0: ab - \ - 0: - *** Failers - 0: - \N -No match - -/|-/I -Capturing subpattern count = 0 -No options -No first char -No need char - abcd - 0: - -abc - 0: - \Nab-c - 0: - - *** Failers - 0: - \Nabc -No match - -/a*(b+)(z)(z)/IP - aaaabbbbzzzz - 0: aaaabbbbzz - 1: bbbb - 2: z - 3: z - aaaabbbbzzzz\O0 - aaaabbbbzzzz\O1 - 0: aaaabbbbzz - aaaabbbbzzzz\O2 - 0: aaaabbbbzz - 1: bbbb - aaaabbbbzzzz\O3 - 0: aaaabbbbzz - 1: bbbb - 2: z - aaaabbbbzzzz\O4 - 0: aaaabbbbzz - 1: bbbb - 2: z - 3: z - aaaabbbbzzzz\O5 - 0: aaaabbbbzz - 1: bbbb - 2: z - 3: z - -/^.?abcd/IS -Capturing subpattern count = 0 -Options: anchored -No first char -Need char = 'd' -Study returned NULL - -/\( # ( at start - (?: # Non-capturing bracket - (?>[^()]+) # Either a sequence of non-brackets (no backtracking) - | # Or - (?R) # Recurse - i.e. nested bracketed string - )* # Zero or more contents - \) # Closing ) - /Ix -Capturing subpattern count = 0 -Partial matching not supported -Options: extended -First char = '(' -Need char = ')' - (abcd) - 0: (abcd) - (abcd)xyz - 0: (abcd) - xyz(abcd) - 0: (abcd) - (ab(xy)cd)pqr - 0: (ab(xy)cd) - (ab(xycd)pqr - 0: (xycd) - () abc () - 0: () - 12(abcde(fsh)xyz(foo(bar))lmno)89 - 0: (abcde(fsh)xyz(foo(bar))lmno) - *** Failers -No match - abcd -No match - abcd) -No match - (abcd -No match - -/\( ( (?>[^()]+) | (?R) )* \) /Ixg -Capturing subpattern count = 1 -Partial matching not supported -Options: extended -First char = '(' -Need char = ')' - (ab(xy)cd)pqr - 0: (ab(xy)cd) - 1: cd - 1(abcd)(x(y)z)pqr - 0: (abcd) - 1: abcd - 0: (x(y)z) - 1: z - -/\( (?: (?>[^()]+) | (?R) ) \) /Ix -Capturing subpattern count = 0 -Partial matching not supported -Options: extended -First char = '(' -Need char = ')' - (abcd) - 0: (abcd) - (ab(xy)cd) - 0: (xy) - (a(b(c)d)e) - 0: (c) - ((ab)) - 0: ((ab)) - *** Failers -No match - () -No match - -/\( (?: (?>[^()]+) | (?R) )? \) /Ix -Capturing subpattern count = 0 -Partial matching not supported -Options: extended -First char = '(' -Need char = ')' - () - 0: () - 12(abcde(fsh)xyz(foo(bar))lmno)89 - 0: (fsh) - -/\( ( (?>[^()]+) | (?R) )* \) /Ix -Capturing subpattern count = 1 -Partial matching not supported -Options: extended -First char = '(' -Need char = ')' - (ab(xy)cd) - 0: (ab(xy)cd) - 1: cd - -/\( ( ( (?>[^()]+) | (?R) )* ) \) /Ix -Capturing subpattern count = 2 -Partial matching not supported -Options: extended -First char = '(' -Need char = ')' - (ab(xy)cd) - 0: (ab(xy)cd) - 1: ab(xy)cd - 2: cd - -/\( (123)? ( ( (?>[^()]+) | (?R) )* ) \) /Ix -Capturing subpattern count = 3 -Partial matching not supported -Options: extended -First char = '(' -Need char = ')' - (ab(xy)cd) - 0: (ab(xy)cd) - 1: - 2: ab(xy)cd - 3: cd - (123ab(xy)cd) - 0: (123ab(xy)cd) - 1: 123 - 2: ab(xy)cd - 3: cd - -/\( ( (123)? ( (?>[^()]+) | (?R) )* ) \) /Ix -Capturing subpattern count = 3 -Partial matching not supported -Options: extended -First char = '(' -Need char = ')' - (ab(xy)cd) - 0: (ab(xy)cd) - 1: ab(xy)cd - 2: - 3: cd - (123ab(xy)cd) - 0: (123ab(xy)cd) - 1: 123ab(xy)cd - 2: 123 - 3: cd - -/\( (((((((((( ( (?>[^()]+) | (?R) )* )))))))))) \) /Ix -Capturing subpattern count = 11 -Partial matching not supported -Options: extended -First char = '(' -Need char = ')' - (ab(xy)cd) - 0: (ab(xy)cd) - 1: ab(xy)cd - 2: ab(xy)cd - 3: ab(xy)cd - 4: ab(xy)cd - 5: ab(xy)cd - 6: ab(xy)cd - 7: ab(xy)cd - 8: ab(xy)cd - 9: ab(xy)cd -10: ab(xy)cd -11: cd - -/\( ( ( (?>[^()<>]+) | ((?>[^()]+)) | (?R) )* ) \) /Ix -Capturing subpattern count = 3 -Partial matching not supported -Options: extended -First char = '(' -Need char = ')' - (abcd(xyz

qrs)123) - 0: (abcd(xyz

qrs)123) - 1: abcd(xyz

qrs)123 - 2: 123 - 3: - -/\( ( ( (?>[^()]+) | ((?R)) )* ) \) /Ix -Capturing subpattern count = 3 -Partial matching not supported -Options: extended -First char = '(' -Need char = ')' - (ab(cd)ef) - 0: (ab(cd)ef) - 1: ab(cd)ef - 2: ef - 3: (cd) - (ab(cd(ef)gh)ij) - 0: (ab(cd(ef)gh)ij) - 1: ab(cd(ef)gh)ij - 2: ij - 3: (cd(ef)gh) - -/^[[:alnum:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [0-9A-Za-z] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:^alnum:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [\x00-/:-@[-`{-\xff] (neg) - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:alpha:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [A-Za-z] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:^alpha:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [\x00-@[-`{-\xff] (neg) - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/[_[:alpha:]]/IS -Capturing subpattern count = 0 -No options -No first char -No need char -Starting byte set: A B C D E F G H I J K L M N O P Q R S T U V W X Y Z - _ a b c d e f g h i j k l m n o p q r s t u v w x y z - -/^[[:ascii:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [\x00-\x7f] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:^ascii:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [\x80-\xff] (neg) - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:blank:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [\x09 ] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:^blank:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [\x00-\x08\x0a-\x1f!-\xff] (neg) - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/[\n\x0b\x0c\x0d[:blank:]]/IS -Capturing subpattern count = 0 -Contains explicit CR or LF match -No options -No first char -No need char -Starting byte set: \x09 \x0a \x0b \x0c \x0d \x20 - -/^[[:cntrl:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [\x00-\x1f\x7f] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:digit:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [0-9] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:graph:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [!-~] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:lower:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [a-z] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:print:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [ -~] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:punct:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [!-/:-@[-`{-~] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:space:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [\x09-\x0d ] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:upper:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [A-Z] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:xdigit:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [0-9A-Fa-f] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:word:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [0-9A-Z_a-z] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:^cntrl:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [ -~\x80-\xff] (neg) - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[12[:^digit:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [\x00-/12:-\xff] (neg) - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:^blank:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [\x00-\x08\x0a-\x1f!-\xff] (neg) - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/[01[:alpha:]%]/DZ ------------------------------------------------------------------- - Bra - [%01A-Za-z] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/[[.ch.]]/I -Failed: POSIX collating elements are not supported at offset 1 - -/[[=ch=]]/I -Failed: POSIX collating elements are not supported at offset 1 - -/[[:rhubarb:]]/I -Failed: unknown POSIX class name at offset 3 - -/[[:upper:]]/Ii -Capturing subpattern count = 0 -Options: caseless -No first char -No need char - A - 0: A - a - 0: a - -/[[:lower:]]/Ii -Capturing subpattern count = 0 -Options: caseless -No first char -No need char - A - 0: A - a - 0: a - -/((?-i)[[:lower:]])[[:lower:]]/Ii -Capturing subpattern count = 1 -Options: caseless -No first char -No need char - ab - 0: ab - 1: a - aB - 0: aB - 1: a - *** Failers - 0: ai - 1: a - Ab -No match - AB -No match - -/[\200-\110]/I -Failed: range out of order in character class at offset 9 - -/^(?(0)f|b)oo/I -Failed: invalid condition (?(0) at offset 6 - -/This one's here because of the large output vector needed/I -Capturing subpattern count = 0 -No options -First char = 'T' -Need char = 'd' - -/(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\w+)\s+(\270)/I -Capturing subpattern count = 271 -Max back reference = 270 -Partial matching not supported -No options -No first char -No need char - \O900 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 ABC ABC - 0: 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 ABC ABC - 1: 1 - 2: 2 - 3: 3 - 4: 4 - 5: 5 - 6: 6 - 7: 7 - 8: 8 - 9: 9 -10: 10 -11: 11 -12: 12 -13: 13 -14: 14 -15: 15 -16: 16 -17: 17 -18: 18 -19: 19 -20: 20 -21: 21 -22: 22 -23: 23 -24: 24 -25: 25 -26: 26 -27: 27 -28: 28 -29: 29 -30: 30 -31: 31 -32: 32 -33: 33 -34: 34 -35: 35 -36: 36 -37: 37 -38: 38 -39: 39 -40: 40 -41: 41 -42: 42 -43: 43 -44: 44 -45: 45 -46: 46 -47: 47 -48: 48 -49: 49 -50: 50 -51: 51 -52: 52 -53: 53 -54: 54 -55: 55 -56: 56 -57: 57 -58: 58 -59: 59 -60: 60 -61: 61 -62: 62 -63: 63 -64: 64 -65: 65 -66: 66 -67: 67 -68: 68 -69: 69 -70: 70 -71: 71 -72: 72 -73: 73 -74: 74 -75: 75 -76: 76 -77: 77 -78: 78 -79: 79 -80: 80 -81: 81 -82: 82 -83: 83 -84: 84 -85: 85 -86: 86 -87: 87 -88: 88 -89: 89 -90: 90 -91: 91 -92: 92 -93: 93 -94: 94 -95: 95 -96: 96 -97: 97 -98: 98 -99: 99 -100: 100 -101: 101 -102: 102 -103: 103 -104: 104 -105: 105 -106: 106 -107: 107 -108: 108 -109: 109 -110: 110 -111: 111 -112: 112 -113: 113 -114: 114 -115: 115 -116: 116 -117: 117 -118: 118 -119: 119 -120: 120 -121: 121 -122: 122 -123: 123 -124: 124 -125: 125 -126: 126 -127: 127 -128: 128 -129: 129 -130: 130 -131: 131 -132: 132 -133: 133 -134: 134 -135: 135 -136: 136 -137: 137 -138: 138 -139: 139 -140: 140 -141: 141 -142: 142 -143: 143 -144: 144 -145: 145 -146: 146 -147: 147 -148: 148 -149: 149 -150: 150 -151: 151 -152: 152 -153: 153 -154: 154 -155: 155 -156: 156 -157: 157 -158: 158 -159: 159 -160: 160 -161: 161 -162: 162 -163: 163 -164: 164 -165: 165 -166: 166 -167: 167 -168: 168 -169: 169 -170: 170 -171: 171 -172: 172 -173: 173 -174: 174 -175: 175 -176: 176 -177: 177 -178: 178 -179: 179 -180: 180 -181: 181 -182: 182 -183: 183 -184: 184 -185: 185 -186: 186 -187: 187 -188: 188 -189: 189 -190: 190 -191: 191 -192: 192 -193: 193 -194: 194 -195: 195 -196: 196 -197: 197 -198: 198 -199: 199 -200: 200 -201: 201 -202: 202 -203: 203 -204: 204 -205: 205 -206: 206 -207: 207 -208: 208 -209: 209 -210: 210 -211: 211 -212: 212 -213: 213 -214: 214 -215: 215 -216: 216 -217: 217 -218: 218 -219: 219 -220: 220 -221: 221 -222: 222 -223: 223 -224: 224 -225: 225 -226: 226 -227: 227 -228: 228 -229: 229 -230: 230 -231: 231 -232: 232 -233: 233 -234: 234 -235: 235 -236: 236 -237: 237 -238: 238 -239: 239 -240: 240 -241: 241 -242: 242 -243: 243 -244: 244 -245: 245 -246: 246 -247: 247 -248: 248 -249: 249 -250: 250 -251: 251 -252: 252 -253: 253 -254: 254 -255: 255 -256: 256 -257: 257 -258: 258 -259: 259 -260: 260 -261: 261 -262: 262 -263: 263 -264: 264 -265: 265 -266: 266 -267: 267 -268: 268 -269: 269 -270: ABC -271: ABC - -/This one's here because Perl does this differently and PCRE can't at present/I -Capturing subpattern count = 0 -No options -First char = 'T' -Need char = 't' - -/(main(O)?)+/I -Capturing subpattern count = 2 -No options -First char = 'm' -Need char = 'n' - mainmain - 0: mainmain - 1: main - mainOmain - 0: mainOmain - 1: main - 2: O - -/These are all cases where Perl does it differently (nested captures)/I -Capturing subpattern count = 1 -No options -First char = 'T' -Need char = 's' - -/^(a(b)?)+$/I -Capturing subpattern count = 2 -Options: anchored -No first char -No need char - aba - 0: aba - 1: a - 2: b - -/^(aa(bb)?)+$/I -Capturing subpattern count = 2 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: aa - 2: bb - -/^(aa|aa(bb))+$/I -Capturing subpattern count = 2 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: aa - 2: bb - -/^(aa(bb)??)+$/I -Capturing subpattern count = 2 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: aa - 2: bb - -/^(?:aa(bb)?)+$/I -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: bb - -/^(aa(b(b))?)+$/I -Capturing subpattern count = 3 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: aa - 2: bb - 3: b - -/^(?:aa(b(b))?)+$/I -Capturing subpattern count = 2 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: bb - 2: b - -/^(?:aa(b(?:b))?)+$/I -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: bb - -/^(?:aa(bb(?:b))?)+$/I -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - aabbbaa - 0: aabbbaa - 1: bbb - -/^(?:aa(b(?:bb))?)+$/I -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - aabbbaa - 0: aabbbaa - 1: bbb - -/^(?:aa(?:b(b))?)+$/I -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: b - -/^(?:aa(?:b(bb))?)+$/I -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - aabbbaa - 0: aabbbaa - 1: bb - -/^(aa(b(bb))?)+$/I -Capturing subpattern count = 3 -Options: anchored -No first char -No need char - aabbbaa - 0: aabbbaa - 1: aa - 2: bbb - 3: bb - -/^(aa(bb(bb))?)+$/I -Capturing subpattern count = 3 -Options: anchored -No first char -No need char - aabbbbaa - 0: aabbbbaa - 1: aa - 2: bbbb - 3: bb - -/--------------------------------------------------------------------/I -Capturing subpattern count = 0 -No options -First char = '-' -Need char = '-' - -/#/IxDZ ------------------------------------------------------------------- - Bra - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: extended -No first char -No need char - -/a#/IxDZ ------------------------------------------------------------------- - Bra - a - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: extended -First char = 'a' -No need char - -/[\s]/DZ ------------------------------------------------------------------- - Bra - [\x09\x0a\x0c\x0d ] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/[\S]/DZ ------------------------------------------------------------------- - Bra - [\x00-\x08\x0b\x0e-\x1f!-\xff] (neg) - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/a(?i)b/DZ ------------------------------------------------------------------- - Bra - a - 01 Opt - NC b - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' (caseless) - ab - 0: ab - aB - 0: aB - *** Failers -No match - AB -No match - -/(a(?i)b)/DZ ------------------------------------------------------------------- - Bra - CBra 1 - a - 01 Opt - NC b - Ket - 00 Opt - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'b' (caseless) - ab - 0: ab - 1: ab - aB - 0: aB - 1: aB - *** Failers -No match - AB -No match - -/ (?i)abc/IxDZ ------------------------------------------------------------------- - Bra - NC abc - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: caseless extended -First char = 'a' (caseless) -Need char = 'c' (caseless) - -/#this is a comment - (?i)abc/IxDZ ------------------------------------------------------------------- - Bra - NC abc - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: caseless extended -First char = 'a' (caseless) -Need char = 'c' (caseless) - -/123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/DZ ------------------------------------------------------------------- - Bra - 123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890 - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = '1' -Need char = '0' - -/\Q123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/DZ ------------------------------------------------------------------- - Bra - 123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890 - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = '1' -Need char = '0' - -/\Q\E/DZ ------------------------------------------------------------------- - Bra - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - \ - 0: - -/\Q\Ex/DZ ------------------------------------------------------------------- - Bra - x - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = 'x' -No need char - -/ \Q\E/DZ ------------------------------------------------------------------- - Bra - - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = ' ' -No need char - -/a\Q\E/DZ ------------------------------------------------------------------- - Bra - a - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - abc - 0: a - bca - 0: a - bac - 0: a - -/a\Q\Eb/DZ ------------------------------------------------------------------- - Bra - ab - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - abc - 0: ab - -/\Q\Eabc/DZ ------------------------------------------------------------------- - Bra - abc - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' - -/x*+\w/DZ ------------------------------------------------------------------- - Bra - x*+ - \w - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -No need char - *** Failers - 0: F - xxxxx -No match - -/x?+/DZ ------------------------------------------------------------------- - Bra - x?+ - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/x++/DZ ------------------------------------------------------------------- - Bra - x++ - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'x' -No need char - -/x{1,3}+/DZ ------------------------------------------------------------------- - Bra - Once - x - x{0,2} - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'x' -No need char - -/(x)*+/DZ ------------------------------------------------------------------- - Bra - Once - Brazero - CBra 1 - x - KetRmax - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -No options -No first char -No need char - -/^(\w++|\s++)*$/I -Capturing subpattern count = 1 -Partial matching not supported -Options: anchored -No first char -No need char - now is the time for all good men to come to the aid of the party - 0: now is the time for all good men to come to the aid of the party - 1: party - *** Failers -No match - this is not a line with only words and spaces! -No match - -/(\d++)(\w)/I -Capturing subpattern count = 2 -Partial matching not supported -No options -No first char -No need char - 12345a - 0: 12345a - 1: 12345 - 2: a - *** Failers -No match - 12345+ -No match - -/a++b/I -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'a' -Need char = 'b' - aaab - 0: aaab - -/(a++b)/I -Capturing subpattern count = 1 -Partial matching not supported -No options -First char = 'a' -Need char = 'b' - aaab - 0: aaab - 1: aaab - -/(a++)b/I -Capturing subpattern count = 1 -Partial matching not supported -No options -First char = 'a' -Need char = 'b' - aaab - 0: aaab - 1: aaa - -/([^()]++|\([^()]*\))+/I -Capturing subpattern count = 1 -Partial matching not supported -No options -No first char -No need char - ((abc(ade)ufh()()x - 0: abc(ade)ufh()()x - 1: x - -/\(([^()]++|\([^()]+\))+\)/I -Capturing subpattern count = 1 -Partial matching not supported -No options -First char = '(' -Need char = ')' - (abc) - 0: (abc) - 1: abc - (abc(def)xyz) - 0: (abc(def)xyz) - 1: xyz - *** Failers -No match - ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -No match - -/(abc){1,3}+/DZ ------------------------------------------------------------------- - Bra - Once - CBra 1 - abc - Ket - Brazero - Bra - CBra 1 - abc - Ket - Brazero - CBra 1 - abc - Ket - Ket - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'c' - -/a+?+/I -Failed: nothing to repeat at offset 3 - -/a{2,3}?+b/I -Failed: nothing to repeat at offset 7 - -/(?U)a+?+/I -Failed: nothing to repeat at offset 7 - -/a{2,3}?+b/IU -Failed: nothing to repeat at offset 7 - -/x(?U)a++b/DZ ------------------------------------------------------------------- - Bra - x - a++ - b - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'x' -Need char = 'b' - xaaaab - 0: xaaaab - -/(?U)xa++b/DZ ------------------------------------------------------------------- - Bra - x - a++ - b - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: ungreedy -First char = 'x' -Need char = 'b' - xaaaab - 0: xaaaab - -/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/DZ ------------------------------------------------------------------- - Bra - ^ - CBra 1 - CBra 2 - a+ - Ket - CBra 3 - [ab]+? - Ket - CBra 4 - [bc]+ - Ket - CBra 5 - \w* - Ket - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 5 -Partial matching not supported -Options: anchored -No first char -No need char - -/^x(?U)a+b/DZ ------------------------------------------------------------------- - Bra - ^ - x - a++ - b - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: anchored -No first char -Need char = 'b' - -/^x(?U)(a+)b/DZ ------------------------------------------------------------------- - Bra - ^ - x - CBra 1 - a+? - Ket - b - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Partial matching not supported -Options: anchored -No first char -Need char = 'b' - -/[.x.]/I -Failed: POSIX collating elements are not supported at offset 0 - -/[=x=]/I -Failed: POSIX collating elements are not supported at offset 0 - -/[:x:]/I -Failed: POSIX named classes are supported only within a class at offset 0 - -/\l/I -Failed: PCRE does not support \L, \l, \N, \U, or \u at offset 1 - -/\L/I -Failed: PCRE does not support \L, \l, \N, \U, or \u at offset 1 - -/\N{name}/I -Failed: PCRE does not support \L, \l, \N, \U, or \u at offset 1 - -/\u/I -Failed: PCRE does not support \L, \l, \N, \U, or \u at offset 1 - -/\U/I -Failed: PCRE does not support \L, \l, \N, \U, or \u at offset 1 - -/[/I -Failed: missing terminating ] for character class at offset 1 - -/[a-/I -Failed: missing terminating ] for character class at offset 3 - -/[[:space:]/I -Failed: missing terminating ] for character class at offset 10 - -/[\s]/IDZ ------------------------------------------------------------------- - Bra - [\x09\x0a\x0c\x0d ] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/[[:space:]]/IDZ ------------------------------------------------------------------- - Bra - [\x09-\x0d ] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/[[:space:]abcde]/IDZ ------------------------------------------------------------------- - Bra - [\x09-\x0d a-e] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/< (?: (?(R) \d++ | [^<>]*+) | (?R)) * >/Ix -Capturing subpattern count = 0 -Partial matching not supported -Options: extended -First char = '<' -Need char = '>' - <> - 0: <> - - 0: - hij> - 0: hij> - hij> - 0: - def> - 0: def> - - 0: <> - *** Failers -No match - iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|IDZ ------------------------------------------------------------------- - Bra - 8J$WE<.rX+ix[d1b!H#?vV0vrK:ZH1=2M>iV;?aPhFB<*vW@QW@sO9}cfZA-i'w%hKd6gt1UJP,15_#QY$M^Mss_U/]&LK9[5vQub^w[KDDqmj;2}YWFdYx.Ap]hjCPTP(n28k+3;o&WXqs/gOXdr$:r'do0;b4c(f_Gr="\4)[01T7ajQJvL$W~mL_sS/4h:x*[ZN=KLs&L5zX//>it,o:aU(;Z>pW&T7oP'2K^E:x9'c[%z-,64JQ5AeH_G#KijUKghQw^\vea3a?kka_G$8#`*kynsxzBLru']k_[7FrVx}^=$blx>s-N%j;D*aZDnsw:YKZ%Q.Kne9#hP?+b3(SOvL,^;&u5@?5C5Bhb=m-vEh_L15Jl]U)0RP6{q%L^_z5E'Dw6X - \b - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = '8' -Need char = 'X' - -|\$\<\.X\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|IDZ ------------------------------------------------------------------- - Bra - $<.X+ix[d1b!H#?vV0vrK:ZH1=2M>iV;?aPhFB<*vW@QW@sO9}cfZA-i'w%hKd6gt1UJP,15_#QY$M^Mss_U/]&LK9[5vQub^w[KDDqmj;2}YWFdYx.Ap]hjCPTP(n28k+3;o&WXqs/gOXdr$:r'do0;b4c(f_Gr="\4)[01T7ajQJvL$W~mL_sS/4h:x*[ZN=KLs&L5zX//>it,o:aU(;Z>pW&T7oP'2K^E:x9'c[%z-,64JQ5AeH_G#KijUKghQw^\vea3a?kka_G$8#`*kynsxzBLru']k_[7FrVx}^=$blx>s-N%j;D*aZDnsw:YKZ%Q.Kne9#hP?+b3(SOvL,^;&u5@?5C5Bhb=m-vEh_L15Jl]U)0RP6{q%L^_z5E'Dw6X - \b - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = '$' -Need char = 'X' - -/(.*)\d+\1/I -Capturing subpattern count = 1 -Max back reference = 1 -Partial matching not supported -No options -No first char -No need char - -/(.*)\d+/I -Capturing subpattern count = 1 -Partial matching not supported -No options -First char at start or follows newline -No need char - -/(.*)\d+\1/Is -Capturing subpattern count = 1 -Max back reference = 1 -Partial matching not supported -Options: dotall -No first char -No need char - -/(.*)\d+/Is -Capturing subpattern count = 1 -Partial matching not supported -Options: anchored dotall -No first char -No need char - -/(.*(xyz))\d+\2/I -Capturing subpattern count = 2 -Max back reference = 2 -Partial matching not supported -No options -First char at start or follows newline -Need char = 'z' - -/((.*))\d+\1/I -Capturing subpattern count = 2 -Max back reference = 1 -Partial matching not supported -No options -No first char -No need char - abc123bc - 0: bc123bc - 1: bc - 2: bc - -/a[b]/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - -/(?=a).*/I -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'a' -No need char - -/(?=abc).xyz/IiI -Capturing subpattern count = 0 -Options: caseless -First char = 'a' (caseless) -Need char = 'z' (caseless) - -/(?=abc)(?i).xyz/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'z' (caseless) - -/(?=a)(?=b)/I -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - -/(?=.)a/I -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - -/((?=abcda)a)/I -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'a' - -/((?=abcda)ab)/I -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'b' - -/()a/I -Capturing subpattern count = 1 -No options -No first char -Need char = 'a' - -/(?(1)ab|ac)(.)/I -Capturing subpattern count = 1 -No options -First char = 'a' -No need char - -/(?(1)abz|acz)(.)/I -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'z' - -/(?(1)abz)(.)/I -Capturing subpattern count = 1 -No options -No first char -No need char - -/(?(1)abz)(1)23/I -Capturing subpattern count = 1 -No options -No first char -Need char = '3' - -/(a)+/I -Capturing subpattern count = 1 -No options -First char = 'a' -No need char - -/(a){2,3}/I -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'a' - -/(a)*/I -Capturing subpattern count = 1 -No options -No first char -No need char - -/[a]/I -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - -/[ab]/I -Capturing subpattern count = 0 -No options -No first char -No need char - -/[ab]/IS -Capturing subpattern count = 0 -No options -No first char -No need char -Starting byte set: a b - -/[^a]/I -Capturing subpattern count = 0 -No options -No first char -No need char - -/\d456/I -Capturing subpattern count = 0 -No options -No first char -Need char = '6' - -/\d456/IS -Capturing subpattern count = 0 -No options -No first char -Need char = '6' -Starting byte set: 0 1 2 3 4 5 6 7 8 9 - -/a^b/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - -/^a/Im -Capturing subpattern count = 0 -Options: multiline -First char at start or follows newline -Need char = 'a' - abcde - 0: a - xy\nabc - 0: a - *** Failers -No match - xyabc -No match - -/c|abc/I -Capturing subpattern count = 0 -No options -No first char -Need char = 'c' - -/(?i)[ab]/IS -Capturing subpattern count = 0 -Options: caseless -No first char -No need char -Starting byte set: A B a b - -/[ab](?i)cd/IS -Capturing subpattern count = 0 -No options -No first char -Need char = 'd' (caseless) -Starting byte set: a b - -/abc(?C)def/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'f' - abcdef ---->abcdef - 0 ^ ^ d - 0: abcdef - 1234abcdef ---->1234abcdef - 0 ^ ^ d - 0: abcdef - *** Failers -No match - abcxyz -No match - abcxyzf ---->abcxyzf - 0 ^ ^ d -No match - -/abc(?C)de(?C1)f/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'f' - 123abcdef ---->123abcdef - 0 ^ ^ d - 1 ^ ^ f - 0: abcdef - -/(?C1)\dabc(?C2)def/I -Capturing subpattern count = 0 -No options -No first char -Need char = 'f' - 1234abcdef ---->1234abcdef - 1 ^ \d - 1 ^ \d - 1 ^ \d - 1 ^ \d - 2 ^ ^ d - 0: 4abcdef - *** Failers -No match - abcdef ---->abcdef - 1 ^ \d - 1 ^ \d - 1 ^ \d - 1 ^ \d - 1 ^ \d - 1 ^ \d -No match - -/(?C255)ab/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - -/(?C256)ab/I -Failed: number after (?C is > 255 at offset 6 - -/(?Cab)xx/I -Failed: closing ) for (?C expected at offset 3 - -/(?C12vr)x/I -Failed: closing ) for (?C expected at offset 5 - -/abc(?C)def/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'f' - *** Failers -No match - \x83\x0\x61bcdef ---->\x83\x00abcdef - 0 ^ ^ d - 0: abcdef - -/(abc)(?C)de(?C1)f/I -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'f' - 123abcdef ---->123abcdef - 0 ^ ^ d - 1 ^ ^ f - 0: abcdef - 1: abc - 123abcdef\C+ -Callout 0: last capture = 1 - 0: - 1: abc ---->123abcdef - ^ ^ d -Callout 1: last capture = 1 - 0: - 1: abc ---->123abcdef - ^ ^ f - 0: abcdef - 1: abc - 123abcdef\C- - 0: abcdef - 1: abc - *** Failers -No match - 123abcdef\C!1 ---->123abcdef - 0 ^ ^ d - 1 ^ ^ f -No match - -/(?C0)(abc(?C1))*/I -Capturing subpattern count = 1 -No options -No first char -No need char - abcabcabc ---->abcabcabc - 0 ^ (abc(?C1))* - 1 ^ ^ ) - 1 ^ ^ ) - 1 ^ ^ ) - 0: abcabcabc - 1: abc - abcabc\C!1!3 ---->abcabc - 0 ^ (abc(?C1))* - 1 ^ ^ ) - 1 ^ ^ ) - 0: abcabc - 1: abc - *** Failers ---->*** Failers - 0 ^ (abc(?C1))* - 0: - abcabcabc\C!1!3 ---->abcabcabc - 0 ^ (abc(?C1))* - 1 ^ ^ ) - 1 ^ ^ ) - 1 ^ ^ ) - 0: abcabc - 1: abc - -/(\d{3}(?C))*/I -Capturing subpattern count = 1 -Partial matching not supported -No options -No first char -No need char - 123\C+ -Callout 0: last capture = -1 - 0: ---->123 - ^ ^ ) - 0: 123 - 1: 123 - 123456\C+ -Callout 0: last capture = -1 - 0: ---->123456 - ^ ^ ) -Callout 0: last capture = 1 - 0: - 1: 123 ---->123456 - ^ ^ ) - 0: 123456 - 1: 456 - 123456789\C+ -Callout 0: last capture = -1 - 0: ---->123456789 - ^ ^ ) -Callout 0: last capture = 1 - 0: - 1: 123 ---->123456789 - ^ ^ ) -Callout 0: last capture = 1 - 0: - 1: 456 ---->123456789 - ^ ^ ) - 0: 123456789 - 1: 789 - -/((xyz)(?C)p|(?C1)xyzabc)/I -Capturing subpattern count = 2 -No options -First char = 'x' -No need char - xyzabc\C+ -Callout 0: last capture = 2 - 0: - 1: - 2: xyz ---->xyzabc - ^ ^ p -Callout 1: last capture = -1 - 0: ---->xyzabc - ^ x - 0: xyzabc - 1: xyzabc - -/(X)((xyz)(?C)p|(?C1)xyzabc)/I -Capturing subpattern count = 3 -No options -First char = 'X' -Need char = 'x' - Xxyzabc\C+ -Callout 0: last capture = 3 - 0: - 1: X - 2: - 3: xyz ---->Xxyzabc - ^ ^ p -Callout 1: last capture = 1 - 0: - 1: X ---->Xxyzabc - ^^ x - 0: Xxyzabc - 1: X - 2: xyzabc - -/(?=(abc))(?C)abcdef/I -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'f' - abcdef\C+ -Callout 0: last capture = 1 - 0: - 1: abc ---->abcdef - ^ a - 0: abcdef - 1: abc - -/(?!(abc)(?C1)d)(?C2)abcxyz/I -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'z' - abcxyz\C+ -Callout 1: last capture = 1 - 0: - 1: abc ---->abcxyz - ^ ^ d -Callout 2: last capture = -1 - 0: ---->abcxyz - ^ a - 0: abcxyz - -/(?<=(abc)(?C))xyz/I -Capturing subpattern count = 1 -No options -First char = 'x' -Need char = 'z' - abcxyz\C+ -Callout 0: last capture = 1 - 0: - 1: abc ---->abcxyz - ^ ) - 0: xyz - 1: abc - -/a(b+)(c*)(?C1)/I -Capturing subpattern count = 2 -Partial matching not supported -No options -First char = 'a' -Need char = 'b' - abbbbbccc\C*1 ---->abbbbbccc - 1 ^ ^ -Callout data = 1 - 1 ^ ^ -Callout data = 1 - 1 ^ ^ -Callout data = 1 - 1 ^ ^ -Callout data = 1 - 1 ^ ^ -Callout data = 1 - 1 ^ ^ -Callout data = 1 - 1 ^ ^ -Callout data = 1 - 1 ^ ^ -Callout data = 1 -No match - -/a(b+?)(c*?)(?C1)/I -Capturing subpattern count = 2 -Partial matching not supported -No options -First char = 'a' -Need char = 'b' - abbbbbccc\C*1 ---->abbbbbccc - 1 ^ ^ -Callout data = 1 - 1 ^ ^ -Callout data = 1 - 1 ^ ^ -Callout data = 1 - 1 ^ ^ -Callout data = 1 - 1 ^ ^ -Callout data = 1 - 1 ^ ^ -Callout data = 1 - 1 ^ ^ -Callout data = 1 - 1 ^ ^ -Callout data = 1 -No match - -/(?C)abc/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' - -/(?C)^abc/I -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/(?C)a|b/IS -Capturing subpattern count = 0 -No options -No first char -No need char -Starting byte set: a b - -/(?R)/I -Failed: recursive call could loop indefinitely at offset 3 - -/(a|(?R))/I -Failed: recursive call could loop indefinitely at offset 6 - -/(ab|(bc|(de|(?R))))/I -Failed: recursive call could loop indefinitely at offset 15 - -/x(ab|(bc|(de|(?R))))/I -Capturing subpattern count = 3 -No options -First char = 'x' -No need char - xab - 0: xab - 1: ab - xbc - 0: xbc - 1: bc - 2: bc - xde - 0: xde - 1: de - 2: de - 3: de - xxab - 0: xxab - 1: xab - 2: xab - 3: xab - xxxab - 0: xxxab - 1: xxab - 2: xxab - 3: xxab - *** Failers -No match - xyab -No match - -/(ab|(bc|(de|(?1))))/I -Failed: recursive call could loop indefinitely at offset 15 - -/x(ab|(bc|(de|(?1)x)x)x)/I -Failed: recursive call could loop indefinitely at offset 16 - -/^([^()]|\((?1)*\))*$/I -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - abc - 0: abc - 1: c - a(b)c - 0: a(b)c - 1: c - a(b(c))d - 0: a(b(c))d - 1: d - *** Failers) -No match - a(b(c)d -No match - -/^>abc>([^()]|\((?1)*\))*abc>123abc>123abc>1(2)3abc>1(2)3abc>(1(2)3)abc>(1(2)3) - 2: - 3: Satan, oscillate my metallic sonatas - 4: S - A man, a plan, a canal: Panama! - 0: A man, a plan, a canal: Panama! - 1: - 2: - 3: A man, a plan, a canal: Panama - 4: A - Able was I ere I saw Elba. - 0: Able was I ere I saw Elba. - 1: - 2: - 3: Able was I ere I saw Elba - 4: A - *** Failers -No match - The quick brown fox -No match - -/^(\d+|\((?1)([+*-])(?1)\)|-(?1))$/I -Capturing subpattern count = 2 -Partial matching not supported -Options: anchored -No first char -No need char - 12 - 0: 12 - 1: 12 - (((2+2)*-3)-7) - 0: (((2+2)*-3)-7) - 1: (((2+2)*-3)-7) - 2: - - -12 - 0: -12 - 1: -12 - *** Failers -No match - ((2+2)*-3)-7) -No match - -/^(x(y|(?1){2})z)/I -Capturing subpattern count = 2 -Options: anchored -No first char -No need char - xyz - 0: xyz - 1: xyz - 2: y - xxyzxyzz - 0: xxyzxyzz - 1: xxyzxyzz - 2: xyzxyz - *** Failers -No match - xxyzz -No match - xxyzxyzxyzz -No match - -/((< (?: (?(R) \d++ | [^<>]*+) | (?2)) * >))/Ix -Capturing subpattern count = 2 -Partial matching not supported -Options: extended -First char = '<' -Need char = '>' - <> - 0: <> - 1: <> - 2: <> - - 0: - 1: - 2: - hij> - 0: hij> - 1: hij> - 2: hij> - hij> - 0: - 1: - 2: - def> - 0: def> - 1: def> - 2: def> - - 0: <> - 1: <> - 2: <> - *** Failers -No match - b|c)d(?Pe)/DZ ------------------------------------------------------------------- - Bra - a - CBra 1 - b - Alt - c - Ket - d - CBra 2 - e - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 2 -Named capturing subpatterns: - longername2 2 - name1 1 -No options -First char = 'a' -Need char = 'e' - abde - 0: abde - 1: b - 2: e - acde - 0: acde - 1: c - 2: e - -/(?:a(?Pc(?Pd)))(?Pa)/DZ ------------------------------------------------------------------- - Bra - Bra - a - CBra 1 - c - CBra 2 - d - Ket - Ket - Ket - CBra 3 - a - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 3 -Named capturing subpatterns: - a 3 - c 1 - d 2 -No options -First char = 'a' -Need char = 'a' - -/(?Pa)...(?P=a)bbb(?P>a)d/DZ ------------------------------------------------------------------- - Bra - CBra 1 - a - Ket - Any - Any - Any - \1 - bbb - Once - Recurse - Ket - d - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Max back reference = 1 -Named capturing subpatterns: - a 1 -No options -First char = 'a' -Need char = 'd' - -/^\W*(?:(?P(?P.)\W*(?P>one)\W*(?P=two)|)|(?P(?P.)\W*(?P>three)\W*(?P=four)|\W*.\W*))\W*$/Ii -Capturing subpattern count = 4 -Max back reference = 4 -Named capturing subpatterns: - four 4 - one 1 - three 3 - two 2 -Partial matching not supported -Options: anchored caseless -No first char -No need char - 1221 - 0: 1221 - 1: 1221 - 2: 1 - Satan, oscillate my metallic sonatas! - 0: Satan, oscillate my metallic sonatas! - 1: - 2: - 3: Satan, oscillate my metallic sonatas - 4: S - A man, a plan, a canal: Panama! - 0: A man, a plan, a canal: Panama! - 1: - 2: - 3: A man, a plan, a canal: Panama - 4: A - Able was I ere I saw Elba. - 0: Able was I ere I saw Elba. - 1: - 2: - 3: Able was I ere I saw Elba - 4: A - *** Failers -No match - The quick brown fox -No match - -/((?(R)a|b))\1(?1)?/I -Capturing subpattern count = 1 -Max back reference = 1 -No options -No first char -No need char - bb - 0: bb - 1: b - bbaa - 0: bba - 1: b - -/(.*)a/Is -Capturing subpattern count = 1 -Partial matching not supported -Options: anchored dotall -No first char -Need char = 'a' - -/(.*)a\1/Is -Capturing subpattern count = 1 -Max back reference = 1 -Partial matching not supported -Options: dotall -No first char -Need char = 'a' - -/(.*)a(b)\2/Is -Capturing subpattern count = 2 -Max back reference = 2 -Partial matching not supported -Options: anchored dotall -No first char -Need char = 'b' - -/((.*)a|(.*)b)z/Is -Capturing subpattern count = 3 -Partial matching not supported -Options: anchored dotall -No first char -Need char = 'z' - -/((.*)a|(.*)b)z\1/Is -Capturing subpattern count = 3 -Max back reference = 1 -Partial matching not supported -Options: dotall -No first char -Need char = 'z' - -/((.*)a|(.*)b)z\2/Is -Capturing subpattern count = 3 -Max back reference = 2 -Partial matching not supported -Options: dotall -No first char -Need char = 'z' - -/((.*)a|(.*)b)z\3/Is -Capturing subpattern count = 3 -Max back reference = 3 -Partial matching not supported -Options: dotall -No first char -Need char = 'z' - -/((.*)a|^(.*)b)z\3/Is -Capturing subpattern count = 3 -Max back reference = 3 -Partial matching not supported -Options: anchored dotall -No first char -Need char = 'z' - -/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a/Is -Capturing subpattern count = 31 -Partial matching not supported -Options: anchored dotall -No first char -No need char - -/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\31/Is -Capturing subpattern count = 31 -Max back reference = 31 -Partial matching not supported -Options: dotall -No first char -No need char - -/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\32/Is -Capturing subpattern count = 32 -Max back reference = 32 -Partial matching not supported -Options: dotall -No first char -No need char - -/(a)(bc)/INDZ ------------------------------------------------------------------- - Bra - Bra - a - Ket - Bra - bc - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: no_auto_capture -First char = 'a' -Need char = 'c' - abc - 0: abc - -/(?Pa)(bc)/INDZ ------------------------------------------------------------------- - Bra - CBra 1 - a - Ket - Bra - bc - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Named capturing subpatterns: - one 1 -Options: no_auto_capture -First char = 'a' -Need char = 'c' - abc - 0: abc - 1: a - -/(a)(?Pbc)/INDZ ------------------------------------------------------------------- - Bra - Bra - a - Ket - CBra 1 - bc - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Named capturing subpatterns: - named 1 -Options: no_auto_capture -First char = 'a' -Need char = 'c' - -/(a+)*zz/I -Capturing subpattern count = 1 -Partial matching not supported -No options -No first char -Need char = 'z' - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaazzbbbbbb\M -Minimum match() limit = 8 -Minimum match() recursion limit = 6 - 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaazz - 1: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - aaaaaaaaaaaaaz\M -Minimum match() limit = 32768 -Minimum match() recursion limit = 42 -No match - -/(aaa(?C1)bbb|ab)/I -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'b' - aaabbb ---->aaabbb - 1 ^ ^ b - 0: aaabbb - 1: aaabbb - aaabbb\C*0 ---->aaabbb - 1 ^ ^ b - 0: aaabbb - 1: aaabbb - aaabbb\C*1 ---->aaabbb - 1 ^ ^ b -Callout data = 1 - 0: ab - 1: ab - aaabbb\C*-1 ---->aaabbb - 1 ^ ^ b -Callout data = -1 -No match - -/ab(?Pcd)ef(?Pgh)/I -Capturing subpattern count = 2 -Named capturing subpatterns: - one 1 - two 2 -No options -First char = 'a' -Need char = 'h' - abcdefgh - 0: abcdefgh - 1: cd - 2: gh - abcdefgh\C1\Gtwo - 0: abcdefgh - 1: cd - 2: gh - 1C cd (2) - G gh (2) two - abcdefgh\Cone\Ctwo - 0: abcdefgh - 1: cd - 2: gh - C cd (2) one - C gh (2) two - abcdefgh\Cthree -no parentheses with name "three" - 0: abcdefgh - 1: cd - 2: gh -copy substring three failed -7 - -/(?P)(?P)/DZ ------------------------------------------------------------------- - Bra - CBra 1 - Ket - CBra 2 - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 2 -Named capturing subpatterns: - Tes 1 - Test 2 -No options -No first char -No need char - -/(?P)(?P)/DZ ------------------------------------------------------------------- - Bra - CBra 1 - Ket - CBra 2 - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 2 -Named capturing subpatterns: - Tes 2 - Test 1 -No options -No first char -No need char - -/(?Pzz)(?Paa)/I -Capturing subpattern count = 2 -Named capturing subpatterns: - A 2 - Z 1 -No options -First char = 'z' -Need char = 'a' - zzaa\CZ - 0: zzaa - 1: zz - 2: aa - C zz (2) Z - zzaa\CA - 0: zzaa - 1: zz - 2: aa - C aa (2) A - -/(?Peks)(?Peccs)/I -Failed: two named subpatterns have the same name at offset 15 - -/(?Pabc(?Pdef)(?Pxyz))/I -Failed: two named subpatterns have the same name at offset 30 - -"\[((?P\d+)(,(?P>elem))*)\]"I -Capturing subpattern count = 3 -Named capturing subpatterns: - elem 2 -Partial matching not supported -No options -First char = '[' -Need char = ']' - [10,20,30,5,5,4,4,2,43,23,4234] - 0: [10,20,30,5,5,4,4,2,43,23,4234] - 1: 10,20,30,5,5,4,4,2,43,23,4234 - 2: 10 - 3: ,4234 - *** Failers -No match - [] -No match - -"\[((?P\d+)(,(?P>elem))*)?\]"I -Capturing subpattern count = 3 -Named capturing subpatterns: - elem 2 -Partial matching not supported -No options -First char = '[' -Need char = ']' - [10,20,30,5,5,4,4,2,43,23,4234] - 0: [10,20,30,5,5,4,4,2,43,23,4234] - 1: 10,20,30,5,5,4,4,2,43,23,4234 - 2: 10 - 3: ,4234 - [] - 0: [] - -/(a(b(?2)c))?/DZ ------------------------------------------------------------------- - Bra - Brazero - CBra 1 - a - CBra 2 - b - Once - Recurse - Ket - c - Ket - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 2 -No options -No first char -No need char - -/(a(b(?2)c))*/DZ ------------------------------------------------------------------- - Bra - Brazero - CBra 1 - a - CBra 2 - b - Once - Recurse - Ket - c - Ket - KetRmax - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 2 -No options -No first char -No need char - -/(a(b(?2)c)){0,2}/DZ ------------------------------------------------------------------- - Bra - Brazero - Bra - CBra 1 - a - CBra 2 - b - Once - Recurse - Ket - c - Ket - Ket - Brazero - CBra 1 - a - CBra 2 - b - Once - Recurse - Ket - c - Ket - Ket - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 2 -No options -No first char -No need char - -/[ab]{1}+/DZ ------------------------------------------------------------------- - Bra - Once - [ab]{1,1} - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/Ii -Capturing subpattern count = 3 -Partial matching not supported -Options: caseless -No first char -Need char = 'g' (caseless) - Baby Bjorn Active Carrier - With free SHIPPING!! - 0: Baby Bjorn Active Carrier - With free SHIPPING!! - 1: Baby Bjorn Active Carrier - With free SHIPPING!! - -/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/IiS -Capturing subpattern count = 3 -Partial matching not supported -Options: caseless -No first char -Need char = 'g' (caseless) -Study returned NULL - Baby Bjorn Active Carrier - With free SHIPPING!! - 0: Baby Bjorn Active Carrier - With free SHIPPING!! - 1: Baby Bjorn Active Carrier - With free SHIPPING!! - -/a*.*b/ISDZ ------------------------------------------------------------------- - Bra - a* - Any* - b - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -Need char = 'b' -Study returned NULL - -/(a|b)*.?c/ISDZ ------------------------------------------------------------------- - Bra - Brazero - CBra 1 - a - Alt - b - KetRmax - Any? - c - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -No options -No first char -Need char = 'c' -Study returned NULL - -/abc(?C255)de(?C)f/DZ ------------------------------------------------------------------- - Bra - abc - Callout 255 10 1 - de - Callout 0 16 1 - f - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'f' - -/abcde/ICDZ ------------------------------------------------------------------- - Bra - Callout 255 0 1 - a - Callout 255 1 1 - b - Callout 255 2 1 - c - Callout 255 3 1 - d - Callout 255 4 1 - e - Callout 255 5 0 - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: -First char = 'a' -Need char = 'e' - abcde ---->abcde - +0 ^ a - +1 ^^ b - +2 ^ ^ c - +3 ^ ^ d - +4 ^ ^ e - +5 ^ ^ - 0: abcde - abcdfe ---->abcdfe - +0 ^ a - +1 ^^ b - +2 ^ ^ c - +3 ^ ^ d - +4 ^ ^ e -No match - -/a*b/ICDZ ------------------------------------------------------------------- - Bra - Callout 255 0 2 - a*+ - Callout 255 2 1 - b - Callout 255 3 0 - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: -No first char -Need char = 'b' - ab ---->ab - +0 ^ a* - +2 ^^ b - +3 ^ ^ - 0: ab - aaaab ---->aaaab - +0 ^ a* - +2 ^ ^ b - +3 ^ ^ - 0: aaaab - aaaacb ---->aaaacb - +0 ^ a* - +2 ^ ^ b - +0 ^ a* - +2 ^ ^ b - +0 ^ a* - +2 ^ ^ b - +0 ^ a* - +2 ^^ b - +0 ^ a* - +2 ^ b - +0 ^ a* - +2 ^ b - +3 ^^ - 0: b - -/a+b/ICDZ ------------------------------------------------------------------- - Bra - Callout 255 0 2 - a++ - Callout 255 2 1 - b - Callout 255 3 0 - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: -First char = 'a' -Need char = 'b' - ab ---->ab - +0 ^ a+ - +2 ^^ b - +3 ^ ^ - 0: ab - aaaab ---->aaaab - +0 ^ a+ - +2 ^ ^ b - +3 ^ ^ - 0: aaaab - aaaacb ---->aaaacb - +0 ^ a+ - +2 ^ ^ b - +0 ^ a+ - +2 ^ ^ b - +0 ^ a+ - +2 ^ ^ b - +0 ^ a+ - +2 ^^ b -No match - -/(abc|def)x/ICDZ ------------------------------------------------------------------- - Bra - Callout 255 0 9 - CBra 1 - Callout 255 1 1 - a - Callout 255 2 1 - b - Callout 255 3 1 - c - Callout 255 4 0 - Alt - Callout 255 5 1 - d - Callout 255 6 1 - e - Callout 255 7 1 - f - Callout 255 8 0 - Ket - Callout 255 9 1 - x - Callout 255 10 0 - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Options: -No first char -Need char = 'x' - abcx ---->abcx - +0 ^ (abc|def) - +1 ^ a - +2 ^^ b - +3 ^ ^ c - +4 ^ ^ | - +9 ^ ^ x -+10 ^ ^ - 0: abcx - 1: abc - defx ---->defx - +0 ^ (abc|def) - +1 ^ a - +5 ^ d - +6 ^^ e - +7 ^ ^ f - +8 ^ ^ ) - +9 ^ ^ x -+10 ^ ^ - 0: defx - 1: def - abcdefzx ---->abcdefzx - +0 ^ (abc|def) - +1 ^ a - +2 ^^ b - +3 ^ ^ c - +4 ^ ^ | - +9 ^ ^ x - +5 ^ d - +0 ^ (abc|def) - +1 ^ a - +5 ^ d - +0 ^ (abc|def) - +1 ^ a - +5 ^ d - +0 ^ (abc|def) - +1 ^ a - +5 ^ d - +6 ^^ e - +7 ^ ^ f - +8 ^ ^ ) - +9 ^ ^ x - +0 ^ (abc|def) - +1 ^ a - +5 ^ d - +0 ^ (abc|def) - +1 ^ a - +5 ^ d - +0 ^ (abc|def) - +1 ^ a - +5 ^ d - +0 ^ (abc|def) - +1 ^ a - +5 ^ d -No match - -/(ab|cd){3,4}/IC -Capturing subpattern count = 1 -Options: -No first char -No need char - ababab ---->ababab - +0 ^ (ab|cd){3,4} - +1 ^ a - +2 ^^ b - +3 ^ ^ | - +1 ^ ^ a - +2 ^ ^ b - +3 ^ ^ | - +1 ^ ^ a - +2 ^ ^ b - +3 ^ ^ | - +1 ^ ^ a - +4 ^ ^ c -+12 ^ ^ - 0: ababab - 1: ab - abcdabcd ---->abcdabcd - +0 ^ (ab|cd){3,4} - +1 ^ a - +2 ^^ b - +3 ^ ^ | - +1 ^ ^ a - +4 ^ ^ c - +5 ^ ^ d - +6 ^ ^ ) - +1 ^ ^ a - +2 ^ ^ b - +3 ^ ^ | - +1 ^ ^ a - +4 ^ ^ c - +5 ^ ^ d - +6 ^ ^ ) -+12 ^ ^ - 0: abcdabcd - 1: cd - abcdcdcdcdcd ---->abcdcdcdcdcd - +0 ^ (ab|cd){3,4} - +1 ^ a - +2 ^^ b - +3 ^ ^ | - +1 ^ ^ a - +4 ^ ^ c - +5 ^ ^ d - +6 ^ ^ ) - +1 ^ ^ a - +4 ^ ^ c - +5 ^ ^ d - +6 ^ ^ ) - +1 ^ ^ a - +4 ^ ^ c - +5 ^ ^ d - +6 ^ ^ ) -+12 ^ ^ - 0: abcdcdcd - 1: cd - -/([ab]{,4}c|xy)/ICDZ ------------------------------------------------------------------- - Bra - Callout 255 0 14 - CBra 1 - Callout 255 1 4 - [ab] - Callout 255 5 1 - { - Callout 255 6 1 - , - Callout 255 7 1 - 4 - Callout 255 8 1 - } - Callout 255 9 1 - c - Callout 255 10 0 - Alt - Callout 255 11 1 - x - Callout 255 12 1 - y - Callout 255 13 0 - Ket - Callout 255 14 0 - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Options: -No first char -No need char - Note: that { does NOT introduce a quantifier ---->Note: that { does NOT introduce a quantifier - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] - +5 ^^ { -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] - +5 ^^ { -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] - +5 ^^ { -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x -No match - -/([ab]{1,4}c|xy){4,5}?123/ICDZ ------------------------------------------------------------------- - Bra - Callout 255 0 21 - CBra 1 - Callout 255 1 9 - [ab]{1,4} - Callout 255 10 1 - c - Callout 255 11 0 - Alt - Callout 255 12 1 - x - Callout 255 13 1 - y - Callout 255 14 0 - Ket - CBra 1 - Callout 255 1 9 - [ab]{1,4} - Callout 255 10 1 - c - Callout 255 11 0 - Alt - Callout 255 12 1 - x - Callout 255 13 1 - y - Callout 255 14 0 - Ket - CBra 1 - Callout 255 1 9 - [ab]{1,4} - Callout 255 10 1 - c - Callout 255 11 0 - Alt - Callout 255 12 1 - x - Callout 255 13 1 - y - Callout 255 14 0 - Ket - CBra 1 - Callout 255 1 9 - [ab]{1,4} - Callout 255 10 1 - c - Callout 255 11 0 - Alt - Callout 255 12 1 - x - Callout 255 13 1 - y - Callout 255 14 0 - Ket - Braminzero - CBra 1 - Callout 255 1 9 - [ab]{1,4} - Callout 255 10 1 - c - Callout 255 11 0 - Alt - Callout 255 12 1 - x - Callout 255 13 1 - y - Callout 255 14 0 - Ket - Callout 255 21 1 - 1 - Callout 255 22 1 - 2 - Callout 255 23 1 - 3 - Callout 255 24 0 - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Partial matching not supported -Options: -No first char -Need char = '3' - aacaacaacaacaac123 ---->aacaacaacaacaac123 - +0 ^ ([ab]{1,4}c|xy){4,5}? - +1 ^ [ab]{1,4} -+10 ^ ^ c -+11 ^ ^ | - +1 ^ ^ [ab]{1,4} -+10 ^ ^ c -+11 ^ ^ | - +1 ^ ^ [ab]{1,4} -+10 ^ ^ c -+11 ^ ^ | - +1 ^ ^ [ab]{1,4} -+10 ^ ^ c -+11 ^ ^ | -+21 ^ ^ 1 - +1 ^ ^ [ab]{1,4} -+10 ^ ^ c -+11 ^ ^ | -+21 ^ ^ 1 -+22 ^ ^ 2 -+23 ^ ^ 3 -+24 ^ ^ - 0: aacaacaacaacaac123 - 1: aac - -/\b.*/I -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -No need char - ab cd\>1 - 0: cd - -/\b.*/Is -Capturing subpattern count = 0 -Partial matching not supported -Options: dotall -No first char -No need char - ab cd\>1 - 0: cd - -/(?!.bcd).*/I -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -No need char - Xbcd12345 - 0: bcd12345 - -/abcde/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'e' - ab\P -Partial match - abc\P -Partial match - abcd\P -Partial match - abcde\P - 0: abcde - the quick brown abc\P -Partial match - ** Failers\P -No match - the quick brown abxyz fox\P -No match - -"^(0?[1-9]|[12][0-9]|3[01])/(0?[1-9]|1[012])/(20)?\d\d$"I -Capturing subpattern count = 3 -Options: anchored -No first char -Need char = '/' - 13/05/04\P - 0: 13/05/04 - 1: 13 - 2: 05 - 13/5/2004\P - 0: 13/5/2004 - 1: 13 - 2: 5 - 3: 20 - 02/05/09\P - 0: 02/05/09 - 1: 02 - 2: 05 - 1\P -Partial match - 1/2\P -Partial match - 1/2/0\P -Partial match - 1/2/04\P - 0: 1/2/04 - 1: 1 - 2: 2 - 0\P -Partial match - 02/\P -Partial match - 02/0\P -Partial match - 02/1\P -Partial match - ** Failers\P -No match - \P -No match - 123\P -No match - 33/4/04\P -No match - 3/13/04\P -No match - 0/1/2003\P -No match - 0/\P -No match - 02/0/\P -No match - 02/13\P -No match - -/0{0,2}ABC/I -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -Need char = 'C' - -/\d{3,}ABC/I -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -Need char = 'C' - -/\d*ABC/I -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -Need char = 'C' - -/[abc]+DE/I -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -Need char = 'E' - -/[abc]?123/I -Capturing subpattern count = 0 -No options -No first char -Need char = '3' - 123\P - 0: 123 - a\P -Partial match - b\P -Partial match - c\P -Partial match - c12\P -Partial match - c123\P - 0: c123 - -/^(?:\d){3,5}X/I -Capturing subpattern count = 0 -Options: anchored -No first char -Need char = 'X' - 1\P -Partial match - 123\P -Partial match - 123X - 0: 123X - 1234\P -Partial match - 1234X - 0: 1234X - 12345\P -Partial match - 12345X - 0: 12345X - *** Failers -No match - 1X -No match - 123456\P -No match - -/abc/I>testsavedregex -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' -Compiled regex written to testsavedregex -testsavedregex -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' -Compiled regex written to testsavedregex -testsavedregex -Capturing subpattern count = 1 -No options -No first char -No need char -Starting byte set: a b -Compiled regex written to testsavedregex -Study data written to testsavedregex -testsavedregex -Capturing subpattern count = 1 -No options -No first char -No need char -Starting byte set: a b -Compiled regex written to testsavedregex -Study data written to testsavedregex -(.)*~smgI -Capturing subpattern count = 3 -Max back reference = 1 -Partial matching not supported -Options: multiline dotall -First char = '<' -Need char = '>' - \n\n\nPartner der LCO\nde\nPartner der LINEAS Consulting\nGmbH\nLINEAS Consulting GmbH Hamburg\nPartnerfirmen\n30 days\nindex,follow\n\nja\n3\nPartner\n\n\nLCO\nLINEAS Consulting\n15.10.2003\n\n\n\n\nDie Partnerfirmen der LINEAS Consulting\nGmbH\n\n\n \n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n - 0: \x0a\x0aPartner der LCO\x0ade\x0aPartner der LINEAS Consulting\x0aGmbH\x0aLINEAS Consulting GmbH Hamburg\x0aPartnerfirmen\x0a30 days\x0aindex,follow\x0a\x0aja\x0a3\x0aPartner\x0a\x0a\x0aLCO\x0aLINEAS Consulting\x0a15.10.2003\x0a\x0a\x0a\x0a\x0aDie Partnerfirmen der LINEAS Consulting\x0aGmbH\x0a\x0a\x0a \x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a - 1: seite - 2: \x0a - 3: seite - -/^a/IF -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/line\nbreak/I -Capturing subpattern count = 0 -Contains explicit CR or LF match -No options -First char = 'l' -Need char = 'k' - this is a line\nbreak - 0: line\x0abreak - line one\nthis is a line\nbreak in the second line - 0: line\x0abreak - -/line\nbreak/If -Capturing subpattern count = 0 -Contains explicit CR or LF match -Options: firstline -First char = 'l' -Need char = 'k' - this is a line\nbreak - 0: line\x0abreak - ** Failers -No match - line one\nthis is a line\nbreak in the second line -No match - -/line\nbreak/Imf -Capturing subpattern count = 0 -Contains explicit CR or LF match -Options: multiline firstline -First char = 'l' -Need char = 'k' - this is a line\nbreak - 0: line\x0abreak - ** Failers -No match - line one\nthis is a line\nbreak in the second line -No match - -/ab.cd/IP - ab-cd - 0: ab-cd - ab=cd - 0: ab=cd - ** Failers -No match: POSIX code 17: match failed - ab\ncd -No match: POSIX code 17: match failed - -/ab.cd/IPs - ab-cd - 0: ab-cd - ab=cd - 0: ab=cd - ab\ncd - 0: ab\x0acd - -/(?i)(?-i)AbCd/I -Capturing subpattern count = 0 -No options -First char = 'A' -Need char = 'd' - AbCd - 0: AbCd - ** Failers -No match - abcd -No match - -/a{11111111111111111111}/I -Failed: number too big in {} quantifier at offset 22 - -/(){64294967295}/I -Failed: number too big in {} quantifier at offset 14 - -/(){2,4294967295}/I -Failed: number too big in {} quantifier at offset 15 - -"(?i:a)(?i:b)(?i:c)(?i:d)(?i:e)(?i:f)(?i:g)(?i:h)(?i:i)(?i:j)(k)(?i:l)A\1B"I -Capturing subpattern count = 1 -Max back reference = 1 -No options -First char = 'a' (caseless) -Need char = 'B' - abcdefghijklAkB - 0: abcdefghijklAkB - 1: k - -"(?Pa)(?Pb)(?Pc)(?Pd)(?Pe)(?Pf)(?Pg)(?Ph)(?Pi)(?Pj)(?Pk)(?Pl)A\11B"I -Capturing subpattern count = 12 -Max back reference = 11 -Named capturing subpatterns: - n0 1 - n1 2 - n10 11 - n11 12 - n2 3 - n3 4 - n4 5 - n5 6 - n6 7 - n7 8 - n8 9 - n9 10 -No options -First char = 'a' -Need char = 'B' - abcdefghijklAkB - 0: abcdefghijklAkB - 1: a - 2: b - 3: c - 4: d - 5: e - 6: f - 7: g - 8: h - 9: i -10: j -11: k -12: l - -"(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)(l)A\11B"I -Capturing subpattern count = 12 -Max back reference = 11 -No options -First char = 'a' -Need char = 'B' - abcdefghijklAkB - 0: abcdefghijklAkB - 1: a - 2: b - 3: c - 4: d - 5: e - 6: f - 7: g - 8: h - 9: i -10: j -11: k -12: l - -"(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)"I -Capturing subpattern count = 101 -Named capturing subpatterns: - name0 1 - name1 2 - name10 11 - name100 101 - name11 12 - name12 13 - name13 14 - name14 15 - name15 16 - name16 17 - name17 18 - name18 19 - name19 20 - name2 3 - name20 21 - name21 22 - name22 23 - name23 24 - name24 25 - name25 26 - name26 27 - name27 28 - name28 29 - name29 30 - name3 4 - name30 31 - name31 32 - name32 33 - name33 34 - name34 35 - name35 36 - name36 37 - name37 38 - name38 39 - name39 40 - name4 5 - name40 41 - name41 42 - name42 43 - name43 44 - name44 45 - name45 46 - name46 47 - name47 48 - name48 49 - name49 50 - name5 6 - name50 51 - name51 52 - name52 53 - name53 54 - name54 55 - name55 56 - name56 57 - name57 58 - name58 59 - name59 60 - name6 7 - name60 61 - name61 62 - name62 63 - name63 64 - name64 65 - name65 66 - name66 67 - name67 68 - name68 69 - name69 70 - name7 8 - name70 71 - name71 72 - name72 73 - name73 74 - name74 75 - name75 76 - name76 77 - name77 78 - name78 79 - name79 80 - name8 9 - name80 81 - name81 82 - name82 83 - name83 84 - name84 85 - name85 86 - name86 87 - name87 88 - name88 89 - name89 90 - name9 10 - name90 91 - name91 92 - name92 93 - name93 94 - name94 95 - name95 96 - name96 97 - name97 98 - name98 99 - name99 100 -No options -First char = 'a' -Need char = 'a' - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -Matched, but too many substrings - 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - 1: a - 2: a - 3: a - 4: a - 5: a - 6: a - 7: a - 8: a - 9: a -10: a -11: a -12: a -13: a -14: a - -"(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)"I -Capturing subpattern count = 101 -No options -First char = 'a' -Need char = 'a' - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -Matched, but too many substrings - 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - 1: a - 2: a - 3: a - 4: a - 5: a - 6: a - 7: a - 8: a - 9: a -10: a -11: a -12: a -13: a -14: a - -/[^()]*(?:\((?R)\)[^()]*)*/I -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -No need char - (this(and)that - 0: - (this(and)that) - 0: (this(and)that) - (this(and)that)stuff - 0: (this(and)that)stuff - -/[^()]*(?:\((?>(?R))\)[^()]*)*/I -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -No need char - (this(and)that - 0: - (this(and)that) - 0: (this(and)that) - -/[^()]*(?:\((?R)\))*[^()]*/I -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -No need char - (this(and)that - 0: - (this(and)that) - 0: (this(and)that) - -/(?:\((?R)\))*[^()]*/I -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -No need char - (this(and)that - 0: - (this(and)that) - 0: - ((this)) - 0: ((this)) - -/(?:\((?R)\))|[^()]*/I -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -No need char - (this(and)that - 0: - (this(and)that) - 0: - (this) - 0: (this) - ((this)) - 0: ((this)) - -/a(b)c/IPN - abc -Matched with REG_NOSUB - -/a(?Pb)c/IPN - abc -Matched with REG_NOSUB - -/\x{100}/I -Failed: character value in \x{...} sequence is too large at offset 6 - -/\x{0000ff}/I -Capturing subpattern count = 0 -No options -First char = 255 -No need char - -/^((?Pa1)|(?Pa2)b)/I -Failed: two named subpatterns have the same name at offset 17 - -/^((?Pa1)|(?Pa2)b)/IJ -Capturing subpattern count = 3 -Named capturing subpatterns: - A 2 - A 3 -Options: anchored dupnames -No first char -No need char - a1b\CA - 0: a1 - 1: a1 - 2: a1 - C a1 (2) A - a2b\CA - 0: a2b - 1: a2b - 2: - 3: a2 - C a2 (2) A - ** Failers -No match - a1b\CZ\CA -no parentheses with name "Z" - 0: a1 - 1: a1 - 2: a1 -copy substring Z failed -7 - C a1 (2) A - -/^(?Pa)(?Pb)/IJ -Capturing subpattern count = 2 -Named capturing subpatterns: - A 1 - A 2 -Options: anchored dupnames -No first char -No need char - ab\CA - 0: ab - 1: a - 2: b - C a (1) A - -/^(?Pa)(?Pb)|cd/IJ -Capturing subpattern count = 2 -Named capturing subpatterns: - A 1 - A 2 -Options: dupnames -No first char -No need char - ab\CA - 0: ab - 1: a - 2: b - C a (1) A - cd\CA - 0: cd -copy substring A failed -7 - -/^(?Pa)(?Pb)|cd(?Pef)(?Pgh)/IJ -Capturing subpattern count = 4 -Named capturing subpatterns: - A 1 - A 2 - A 3 - A 4 -Options: dupnames -No first char -No need char - cdefgh\CA - 0: cdefgh - 1: - 2: - 3: ef - 4: gh - C ef (2) A - -/^((?Pa1)|(?Pa2)b)/IJ -Capturing subpattern count = 3 -Named capturing subpatterns: - A 2 - A 3 -Options: anchored dupnames -No first char -No need char - a1b\GA - 0: a1 - 1: a1 - 2: a1 - G a1 (2) A - a2b\GA - 0: a2b - 1: a2b - 2: - 3: a2 - G a2 (2) A - ** Failers -No match - a1b\GZ\GA -no parentheses with name "Z" - 0: a1 - 1: a1 - 2: a1 -copy substring Z failed -7 - G a1 (2) A - -/^(?Pa)(?Pb)/IJ -Capturing subpattern count = 2 -Named capturing subpatterns: - A 1 - A 2 -Options: anchored dupnames -No first char -No need char - ab\GA - 0: ab - 1: a - 2: b - G a (1) A - -/^(?Pa)(?Pb)|cd/IJ -Capturing subpattern count = 2 -Named capturing subpatterns: - A 1 - A 2 -Options: dupnames -No first char -No need char - ab\GA - 0: ab - 1: a - 2: b - G a (1) A - cd\GA - 0: cd -copy substring A failed -7 - -/^(?Pa)(?Pb)|cd(?Pef)(?Pgh)/IJ -Capturing subpattern count = 4 -Named capturing subpatterns: - A 1 - A 2 - A 3 - A 4 -Options: dupnames -No first char -No need char - cdefgh\GA - 0: cdefgh - 1: - 2: - 3: ef - 4: gh - G ef (2) A - -/(?J)^((?Pa1)|(?Pa2)b)/I -Capturing subpattern count = 3 -Named capturing subpatterns: - A 2 - A 3 -Options: anchored dupnames -Duplicate name status changes -No first char -No need char - a1b\CA - 0: a1 - 1: a1 - 2: a1 - C a1 (2) A - a2b\CA - 0: a2b - 1: a2b - 2: - 3: a2 - C a2 (2) A - -/^(?Pa) (?J:(?Pb)(?Pc)) (?Pd)/I -Failed: two named subpatterns have the same name at offset 37 - -/ In this next test, J is not set at the outer level; consequently it isn't -set in the pattern's options; consequently pcre_get_named_substring() produces -a random value. /Ix -Capturing subpattern count = 1 -Options: extended -First char = 'I' -Need char = 'e' - -/^(?Pa) (?J:(?Pb)(?Pc)) (?Pd)/I -Capturing subpattern count = 4 -Named capturing subpatterns: - A 1 - B 2 - B 3 - C 4 -Options: anchored -Duplicate name status changes -No first char -No need char - a bc d\CA\CB\CC - 0: a bc d - 1: a - 2: b - 3: c - 4: d - C a (1) A - C b (1) B - C d (1) C - -/^(?Pa)?(?(A)a|b)/I -Capturing subpattern count = 1 -Named capturing subpatterns: - A 1 -Options: anchored -No first char -No need char - aabc - 0: aa - 1: a - bc - 0: b - ** Failers -No match - abc -No match - -/(?:(?(ZZ)a|b)(?PX))+/I -Capturing subpattern count = 1 -Named capturing subpatterns: - ZZ 1 -No options -No first char -Need char = 'X' - bXaX - 0: bXaX - 1: X - -/(?:(?(2y)a|b)(X))+/I -Failed: reference to non-existent subpattern at offset 9 - -/(?:(?(ZA)a|b)(?PX))+/I -Failed: reference to non-existent subpattern at offset 9 - -/(?:(?(ZZ)a|b)(?(ZZ)a|b)(?PX))+/I -Capturing subpattern count = 1 -Named capturing subpatterns: - ZZ 1 -No options -No first char -Need char = 'X' - bbXaaX - 0: bbXaaX - 1: X - -/(?:(?(ZZ)a|\(b\))\\(?PX))+/I -Capturing subpattern count = 1 -Named capturing subpatterns: - ZZ 1 -No options -No first char -Need char = 'X' - (b)\\Xa\\X - 0: (b)\Xa\X - 1: X - -/(?PX|Y))+/I -Capturing subpattern count = 1 -Max back reference = 1 -Named capturing subpatterns: - A 1 -No options -No first char -No need char - bXXaYYaY - 0: bXXaYYaY - 1: Y - bXYaXXaX - 0: bX - 1: X - -/()()()()()()()()()(?:(?(A)(?P=A)a|b)(?PX|Y))+/I -Capturing subpattern count = 10 -Max back reference = 10 -Named capturing subpatterns: - A 10 -No options -No first char -No need char - bXXaYYaY - 0: bXXaYYaY - 1: - 2: - 3: - 4: - 5: - 6: - 7: - 8: - 9: -10: Y - -/\777/I -Failed: octal value is greater than \377 (not in UTF-8 mode) at offset 3 - -/\s*,\s*/IS -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -Need char = ',' -Starting byte set: \x09 \x0a \x0c \x0d \x20 , - \x0b,\x0b - 0: , - \x0c,\x0d - 0: \x0c,\x0d - -/^abc/Im -Capturing subpattern count = 0 -Options: multiline -First char at start or follows newline -Need char = 'c' - xyz\nabc - 0: abc - xyz\nabc\ - 0: abc - xyz\r\nabc\ - 0: abc - xyz\rabc\ - 0: abc - xyz\r\nabc\ - 0: abc - ** Failers -No match - xyz\nabc\ -No match - xyz\r\nabc\ -No match - xyz\nabc\ -No match - xyz\rabc\ -No match - xyz\rabc\ -No match - -/abc$/Im -Capturing subpattern count = 0 -Options: multiline -Forced newline sequence: LF -First char = 'a' -Need char = 'c' - xyzabc - 0: abc - xyzabc\n - 0: abc - xyzabc\npqr - 0: abc - xyzabc\r\ - 0: abc - xyzabc\rpqr\ - 0: abc - xyzabc\r\n\ - 0: abc - xyzabc\r\npqr\ - 0: abc - ** Failers -No match - xyzabc\r -No match - xyzabc\rpqr -No match - xyzabc\r\n -No match - xyzabc\r\npqr -No match - -/^abc/Im -Capturing subpattern count = 0 -Options: multiline -Forced newline sequence: CR -First char at start or follows newline -Need char = 'c' - xyz\rabcdef - 0: abc - xyz\nabcdef\ - 0: abc - ** Failers -No match - xyz\nabcdef -No match - -/^abc/Im -Capturing subpattern count = 0 -Options: multiline -Forced newline sequence: LF -First char at start or follows newline -Need char = 'c' - xyz\nabcdef - 0: abc - xyz\rabcdef\ - 0: abc - ** Failers -No match - xyz\rabcdef -No match - -/^abc/Im -Capturing subpattern count = 0 -Options: multiline -Forced newline sequence: CRLF -First char at start or follows newline -Need char = 'c' - xyz\r\nabcdef - 0: abc - xyz\rabcdef\ - 0: abc - ** Failers -No match - xyz\rabcdef -No match - -/^abc/Im -Unknown newline type at: - - -/abc/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' - xyz\rabc\ -Unknown newline type at: - abc - 0: abc - -/.*/I -Capturing subpattern count = 0 -Partial matching not supported -Options: -Forced newline sequence: LF -First char at start or follows newline -No need char - abc\ndef - 0: abc - abc\rdef - 0: abc\x0ddef - abc\r\ndef - 0: abc\x0d - \abc\ndef - 0: abc\x0adef - \abc\rdef - 0: abc - \abc\r\ndef - 0: abc - \abc\ndef - 0: abc\x0adef - \abc\rdef - 0: abc\x0ddef - \abc\r\ndef - 0: abc - -/\w+(.)(.)?def/Is -Capturing subpattern count = 2 -Partial matching not supported -Options: dotall -No first char -Need char = 'f' - abc\ndef - 0: abc\x0adef - 1: \x0a - abc\rdef - 0: abc\x0ddef - 1: \x0d - abc\r\ndef - 0: abc\x0d\x0adef - 1: \x0d - 2: \x0a - -+((?:\s|//.*\\n|/[*](?:\\n|.)*?[*]/)*)+I -Capturing subpattern count = 1 -Partial matching not supported -No options -No first char -No need char - /* this is a C style comment */\M -Minimum match() limit = 120 -Minimum match() recursion limit = 6 - 0: /* this is a C style comment */ - 1: /* this is a C style comment */ - -/(?P25[0-5]|2[0-4]\d|[01]?\d?\d)(?:\.(?P>B)){3}/I -Capturing subpattern count = 1 -Named capturing subpatterns: - B 1 -No options -No first char -Need char = '.' - -/()()()()()()()()()()()()()()()()()()()() - ()()()()()()()()()()()()()()()()()()()() - ()()()()()()()()()()()()()()()()()()()() - ()()()()()()()()()()()()()()()()()()()() - ()()()()()()()()()()()()()()()()()()()() - (.(.))/Ix -Capturing subpattern count = 102 -Options: extended -No first char -No need char - XY\O400 - 0: XY - 1: - 2: - 3: - 4: - 5: - 6: - 7: - 8: - 9: -10: -11: -12: -13: -14: -15: -16: -17: -18: -19: -20: -21: -22: -23: -24: -25: -26: -27: -28: -29: -30: -31: -32: -33: -34: -35: -36: -37: -38: -39: -40: -41: -42: -43: -44: -45: -46: -47: -48: -49: -50: -51: -52: -53: -54: -55: -56: -57: -58: -59: -60: -61: -62: -63: -64: -65: -66: -67: -68: -69: -70: -71: -72: -73: -74: -75: -76: -77: -78: -79: -80: -81: -82: -83: -84: -85: -86: -87: -88: -89: -90: -91: -92: -93: -94: -95: -96: -97: -98: -99: -100: -101: XY -102: Y - -/(a*b|(?i:c*(?-i)d))/IS -Capturing subpattern count = 1 -Partial matching not supported -No options -No first char -No need char -Starting byte set: C a b c d - -/()[ab]xyz/IS -Capturing subpattern count = 1 -No options -No first char -Need char = 'z' -Starting byte set: a b - -/(|)[ab]xyz/IS -Capturing subpattern count = 1 -No options -No first char -Need char = 'z' -Starting byte set: a b - -/(|c)[ab]xyz/IS -Capturing subpattern count = 1 -No options -No first char -Need char = 'z' -Starting byte set: a b c - -/(|c?)[ab]xyz/IS -Capturing subpattern count = 1 -No options -No first char -Need char = 'z' -Starting byte set: a b c - -/(d?|c?)[ab]xyz/IS -Capturing subpattern count = 1 -No options -No first char -Need char = 'z' -Starting byte set: a b c d - -/(d?|c)[ab]xyz/IS -Capturing subpattern count = 1 -No options -No first char -Need char = 'z' -Starting byte set: a b c d - -/^a*b\d/DZ ------------------------------------------------------------------- - Bra - ^ - a*+ - b - \d - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: anchored -No first char -Need char = 'b' - -/^a*+b\d/DZ ------------------------------------------------------------------- - Bra - ^ - a*+ - b - \d - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: anchored -No first char -Need char = 'b' - -/^a*?b\d/DZ ------------------------------------------------------------------- - Bra - ^ - a*+ - b - \d - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: anchored -No first char -Need char = 'b' - -/^a+A\d/DZ ------------------------------------------------------------------- - Bra - ^ - a++ - A - \d - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: anchored -No first char -Need char = 'A' - aaaA5 - 0: aaaA5 - ** Failers -No match - aaaa5 -No match - -/^a*A\d/IiDZ ------------------------------------------------------------------- - Bra - ^ - a* - NC A - \d - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: anchored caseless -No first char -Need char = 'A' (caseless) - aaaA5 - 0: aaaA5 - aaaa5 - 0: aaaa5 - -/(a*|b*)[cd]/IS -Capturing subpattern count = 1 -Partial matching not supported -No options -No first char -No need char -Starting byte set: a b c d - -/(a+|b*)[cd]/IS -Capturing subpattern count = 1 -Partial matching not supported -No options -No first char -No need char -Starting byte set: a b c d - -/(a*|b+)[cd]/IS -Capturing subpattern count = 1 -Partial matching not supported -No options -No first char -No need char -Starting byte set: a b c d - -/(a+|b+)[cd]/IS -Capturing subpattern count = 1 -Partial matching not supported -No options -No first char -No need char -Starting byte set: a b - -/(((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((( - (((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((( - ((( - a - )))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))) - )))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))) - ))) -/Ix -Capturing subpattern count = 203 -Options: extended -First char = 'a' -No need char - large nest -Matched, but too many substrings - 0: a - 1: a - 2: a - 3: a - 4: a - 5: a - 6: a - 7: a - 8: a - 9: a -10: a -11: a -12: a -13: a -14: a - -/a*\d/BZ ------------------------------------------------------------------- - Bra - a*+ - \d - Ket - End ------------------------------------------------------------------- - -/a*\D/BZ ------------------------------------------------------------------- - Bra - a* - \D - Ket - End ------------------------------------------------------------------- - -/0*\d/BZ ------------------------------------------------------------------- - Bra - 0* - \d - Ket - End ------------------------------------------------------------------- - -/0*\D/BZ ------------------------------------------------------------------- - Bra - 0*+ - \D - Ket - End ------------------------------------------------------------------- - -/a*\s/BZ ------------------------------------------------------------------- - Bra - a*+ - \s - Ket - End ------------------------------------------------------------------- - -/a*\S/BZ ------------------------------------------------------------------- - Bra - a* - \S - Ket - End ------------------------------------------------------------------- - -/ *\s/BZ ------------------------------------------------------------------- - Bra - * - \s - Ket - End ------------------------------------------------------------------- - -/ *\S/BZ ------------------------------------------------------------------- - Bra - *+ - \S - Ket - End ------------------------------------------------------------------- - -/a*\w/BZ ------------------------------------------------------------------- - Bra - a* - \w - Ket - End ------------------------------------------------------------------- - -/a*\W/BZ ------------------------------------------------------------------- - Bra - a*+ - \W - Ket - End ------------------------------------------------------------------- - -/=*\w/BZ ------------------------------------------------------------------- - Bra - =*+ - \w - Ket - End ------------------------------------------------------------------- - -/=*\W/BZ ------------------------------------------------------------------- - Bra - =* - \W - Ket - End ------------------------------------------------------------------- - -/\d*a/BZ ------------------------------------------------------------------- - Bra - \d*+ - a - Ket - End ------------------------------------------------------------------- - -/\d*2/BZ ------------------------------------------------------------------- - Bra - \d* - 2 - Ket - End ------------------------------------------------------------------- - -/\d*\d/BZ ------------------------------------------------------------------- - Bra - \d* - \d - Ket - End ------------------------------------------------------------------- - -/\d*\D/BZ ------------------------------------------------------------------- - Bra - \d*+ - \D - Ket - End ------------------------------------------------------------------- - -/\d*\s/BZ ------------------------------------------------------------------- - Bra - \d*+ - \s - Ket - End ------------------------------------------------------------------- - -/\d*\S/BZ ------------------------------------------------------------------- - Bra - \d* - \S - Ket - End ------------------------------------------------------------------- - -/\d*\w/BZ ------------------------------------------------------------------- - Bra - \d* - \w - Ket - End ------------------------------------------------------------------- - -/\d*\W/BZ ------------------------------------------------------------------- - Bra - \d*+ - \W - Ket - End ------------------------------------------------------------------- - -/\D*a/BZ ------------------------------------------------------------------- - Bra - \D* - a - Ket - End ------------------------------------------------------------------- - -/\D*2/BZ ------------------------------------------------------------------- - Bra - \D*+ - 2 - Ket - End ------------------------------------------------------------------- - -/\D*\d/BZ ------------------------------------------------------------------- - Bra - \D*+ - \d - Ket - End ------------------------------------------------------------------- - -/\D*\D/BZ ------------------------------------------------------------------- - Bra - \D* - \D - Ket - End ------------------------------------------------------------------- - -/\D*\s/BZ ------------------------------------------------------------------- - Bra - \D* - \s - Ket - End ------------------------------------------------------------------- - -/\D*\S/BZ ------------------------------------------------------------------- - Bra - \D* - \S - Ket - End ------------------------------------------------------------------- - -/\D*\w/BZ ------------------------------------------------------------------- - Bra - \D* - \w - Ket - End ------------------------------------------------------------------- - -/\D*\W/BZ ------------------------------------------------------------------- - Bra - \D* - \W - Ket - End ------------------------------------------------------------------- - -/\s*a/BZ ------------------------------------------------------------------- - Bra - \s*+ - a - Ket - End ------------------------------------------------------------------- - -/\s*2/BZ ------------------------------------------------------------------- - Bra - \s*+ - 2 - Ket - End ------------------------------------------------------------------- - -/\s*\d/BZ ------------------------------------------------------------------- - Bra - \s*+ - \d - Ket - End ------------------------------------------------------------------- - -/\s*\D/BZ ------------------------------------------------------------------- - Bra - \s* - \D - Ket - End ------------------------------------------------------------------- - -/\s*\s/BZ ------------------------------------------------------------------- - Bra - \s* - \s - Ket - End ------------------------------------------------------------------- - -/\s*\S/BZ ------------------------------------------------------------------- - Bra - \s*+ - \S - Ket - End ------------------------------------------------------------------- - -/\s*\w/BZ ------------------------------------------------------------------- - Bra - \s*+ - \w - Ket - End ------------------------------------------------------------------- - -/\s*\W/BZ ------------------------------------------------------------------- - Bra - \s* - \W - Ket - End ------------------------------------------------------------------- - -/\S*a/BZ ------------------------------------------------------------------- - Bra - \S* - a - Ket - End ------------------------------------------------------------------- - -/\S*2/BZ ------------------------------------------------------------------- - Bra - \S* - 2 - Ket - End ------------------------------------------------------------------- - -/\S*\d/BZ ------------------------------------------------------------------- - Bra - \S* - \d - Ket - End ------------------------------------------------------------------- - -/\S*\D/BZ ------------------------------------------------------------------- - Bra - \S* - \D - Ket - End ------------------------------------------------------------------- - -/\S*\s/BZ ------------------------------------------------------------------- - Bra - \S*+ - \s - Ket - End ------------------------------------------------------------------- - -/\S*\S/BZ ------------------------------------------------------------------- - Bra - \S* - \S - Ket - End ------------------------------------------------------------------- - -/\S*\w/BZ ------------------------------------------------------------------- - Bra - \S* - \w - Ket - End ------------------------------------------------------------------- - -/\S*\W/BZ ------------------------------------------------------------------- - Bra - \S* - \W - Ket - End ------------------------------------------------------------------- - -/\w*a/BZ ------------------------------------------------------------------- - Bra - \w* - a - Ket - End ------------------------------------------------------------------- - -/\w*2/BZ ------------------------------------------------------------------- - Bra - \w* - 2 - Ket - End ------------------------------------------------------------------- - -/\w*\d/BZ ------------------------------------------------------------------- - Bra - \w* - \d - Ket - End ------------------------------------------------------------------- - -/\w*\D/BZ ------------------------------------------------------------------- - Bra - \w* - \D - Ket - End ------------------------------------------------------------------- - -/\w*\s/BZ ------------------------------------------------------------------- - Bra - \w*+ - \s - Ket - End ------------------------------------------------------------------- - -/\w*\S/BZ ------------------------------------------------------------------- - Bra - \w* - \S - Ket - End ------------------------------------------------------------------- - -/\w*\w/BZ ------------------------------------------------------------------- - Bra - \w* - \w - Ket - End ------------------------------------------------------------------- - -/\w*\W/BZ ------------------------------------------------------------------- - Bra - \w*+ - \W - Ket - End ------------------------------------------------------------------- - -/\W*a/BZ ------------------------------------------------------------------- - Bra - \W*+ - a - Ket - End ------------------------------------------------------------------- - -/\W*2/BZ ------------------------------------------------------------------- - Bra - \W*+ - 2 - Ket - End ------------------------------------------------------------------- - -/\W*\d/BZ ------------------------------------------------------------------- - Bra - \W*+ - \d - Ket - End ------------------------------------------------------------------- - -/\W*\D/BZ ------------------------------------------------------------------- - Bra - \W* - \D - Ket - End ------------------------------------------------------------------- - -/\W*\s/BZ ------------------------------------------------------------------- - Bra - \W* - \s - Ket - End ------------------------------------------------------------------- - -/\W*\S/BZ ------------------------------------------------------------------- - Bra - \W* - \S - Ket - End ------------------------------------------------------------------- - -/\W*\w/BZ ------------------------------------------------------------------- - Bra - \W*+ - \w - Ket - End ------------------------------------------------------------------- - -/\W*\W/BZ ------------------------------------------------------------------- - Bra - \W* - \W - Ket - End ------------------------------------------------------------------- - -/[^a]+a/BZ ------------------------------------------------------------------- - Bra - [^a]++ - a - Ket - End ------------------------------------------------------------------- - -/[^a]+a/BZi ------------------------------------------------------------------- - Bra - [^A]++ - NC a - Ket - End ------------------------------------------------------------------- - -/[^a]+A/BZi ------------------------------------------------------------------- - Bra - [^A]++ - NC A - Ket - End ------------------------------------------------------------------- - -/[^a]+b/BZ ------------------------------------------------------------------- - Bra - [^a]+ - b - Ket - End ------------------------------------------------------------------- - -/[^a]+\d/BZ ------------------------------------------------------------------- - Bra - [^a]+ - \d - Ket - End ------------------------------------------------------------------- - -/a*[^a]/BZ ------------------------------------------------------------------- - Bra - a* - [^a] - Ket - End ------------------------------------------------------------------- - -/(?Px)(?Py)/I -Capturing subpattern count = 2 -Named capturing subpatterns: - abc 1 - xyz 2 -No options -First char = 'x' -Need char = 'y' - xy\Cabc\Cxyz - 0: xy - 1: x - 2: y - C x (1) abc - C y (1) xyz - -/(?x)(?'xyz'y)/I -Capturing subpattern count = 2 -Named capturing subpatterns: - abc 1 - xyz 2 -No options -First char = 'x' -Need char = 'y' - xy\Cabc\Cxyz - 0: xy - 1: x - 2: y - C x (1) abc - C y (1) xyz - -/(?x)(?'xyz>y)/I -Failed: syntax error in subpattern name (missing terminator) at offset 15 - -/(?P'abc'x)(?Py)/I -Failed: unrecognized character after (?P at offset 3 - -/^(?:(?(ZZ)a|b)(?X))+/ - bXaX - 0: bXaX - 1: X - bXbX - 0: bX - 1: X - ** Failers -No match - aXaX -No match - aXbX -No match - -/^(?P>abc)(?xxx)/ -Failed: reference to non-existent subpattern at offset 8 - -/^(?P>abc)(?x|y)/ - xx - 0: xx - 1: x - xy - 0: xy - 1: y - yy - 0: yy - 1: y - yx - 0: yx - 1: x - -/^(?P>abc)(?Px|y)/ - xx - 0: xx - 1: x - xy - 0: xy - 1: y - yy - 0: yy - 1: y - yx - 0: yx - 1: x - -/^((?(abc)a|b)(?x|y))+/ - bxay - 0: bxay - 1: ay - 2: y - bxby - 0: bx - 1: bx - 2: x - ** Failers -No match - axby -No match - -/^(((?P=abc)|X)(?x|y))+/ - XxXxxx - 0: XxXxxx - 1: xx - 2: x - 3: x - XxXyyx - 0: XxXyyx - 1: yx - 2: y - 3: x - XxXyxx - 0: XxXy - 1: Xy - 2: X - 3: y - ** Failers -No match - x -No match - -/^(?1)(abc)/ - abcabc - 0: abcabc - 1: abc - -/^(?:(?:\1|X)(a|b))+/ - Xaaa - 0: Xaaa - 1: a - Xaba - 0: Xa - 1: a - -/^[\E\Qa\E-\Qz\E]+/BZ ------------------------------------------------------------------- - Bra - ^ - [a-z]+ - Ket - End ------------------------------------------------------------------- - -/^[a\Q]bc\E]/BZ ------------------------------------------------------------------- - Bra - ^ - [\]a-c] - Ket - End ------------------------------------------------------------------- - -/^[a-\Q\E]/BZ ------------------------------------------------------------------- - Bra - ^ - [\-a] - Ket - End ------------------------------------------------------------------- - -/^(?P>abc)[()](?)/BZ ------------------------------------------------------------------- - Bra - ^ - Once - Recurse - Ket - [()] - CBra 1 - Ket - Ket - End ------------------------------------------------------------------- - -/^((?(abc)y)[()](?Px))+/BZ ------------------------------------------------------------------- - Bra - ^ - CBra 1 - Cond - 2 Cond ref - y - Ket - [()] - CBra 2 - x - Ket - KetRmax - Ket - End ------------------------------------------------------------------- - (xy)x - 0: (xy)x - 1: y)x - 2: x - -/^(?P>abc)\Q()\E(?)/BZ ------------------------------------------------------------------- - Bra - ^ - Once - Recurse - Ket - () - CBra 1 - Ket - Ket - End ------------------------------------------------------------------- - -/^(?P>abc)[a\Q(]\E(](?)/BZ ------------------------------------------------------------------- - Bra - ^ - Once - Recurse - Ket - [(\]a] - CBra 1 - Ket - Ket - End ------------------------------------------------------------------- - -/^(?P>abc) # this is (a comment) - (?)/BZx ------------------------------------------------------------------- - Bra - ^ - Once - Recurse - Ket - CBra 1 - Ket - Ket - End ------------------------------------------------------------------- - -/^\W*(?:(?(?.)\W*(?&one)\W*\k|)|(?(?.)\W*(?&three)\W*\k'four'|\W*.\W*))\W*$/Ii -Capturing subpattern count = 4 -Max back reference = 4 -Named capturing subpatterns: - four 4 - one 1 - three 3 - two 2 -Partial matching not supported -Options: anchored caseless -No first char -No need char - 1221 - 0: 1221 - 1: 1221 - 2: 1 - Satan, oscillate my metallic sonatas! - 0: Satan, oscillate my metallic sonatas! - 1: - 2: - 3: Satan, oscillate my metallic sonatas - 4: S - A man, a plan, a canal: Panama! - 0: A man, a plan, a canal: Panama! - 1: - 2: - 3: A man, a plan, a canal: Panama - 4: A - Able was I ere I saw Elba. - 0: Able was I ere I saw Elba. - 1: - 2: - 3: Able was I ere I saw Elba - 4: A - *** Failers -No match - The quick brown fox -No match - -/(?=(\w+))\1:/I -Capturing subpattern count = 1 -Max back reference = 1 -Partial matching not supported -No options -No first char -Need char = ':' - abcd: - 0: abcd: - 1: abcd - -/(?=(?'abc'\w+))\k:/I -Capturing subpattern count = 1 -Max back reference = 1 -Named capturing subpatterns: - abc 1 -Partial matching not supported -No options -No first char -Need char = ':' - abcd: - 0: abcd: - 1: abcd - -/(?'abc'\w+):\k{2}/ - a:aaxyz - 0: a:aa - 1: a - ab:ababxyz - 0: ab:abab - 1: ab - ** Failers -No match - a:axyz -No match - ab:abxyz -No match - -/(?'abc'a|b)(?d|e)\k{2}/J - adaa - 0: adaa - 1: a - 2: d - ** Failers -No match - addd -No match - adbb -No match - -/(?'abc'a|b)(?d|e)(?&abc){2}/J - bdaa - 0: bdaa - 1: b - 2: d - bdab - 0: bdab - 1: b - 2: d - ** Failers -No match - bddd -No match - -/^(?a)? (?()b|c) (?('ab')d|e)/x - abd - 0: abd - 1: a - ce - 0: ce - -/(?( (?'B' abc (?(R) (?(R&A)1) (?(R&B)2) X | (?1) (?2) (?R) ))) /x - abcabc1Xabc2XabcXabcabc - 0: abcabc1Xabc2XabcX - 1: abcabc1Xabc2XabcX - 2: abcabc1Xabc2XabcX - -/(? (?'B' abc (?(R) (?(R&1)1) (?(R&B)2) X | (?1) (?2) (?R) ))) /x -Failed: reference to non-existent subpattern at offset 29 - -/(?<1> (?'B' abc (?(R) (?(R&1)1) (?(R&B)2) X | (?1) (?2) (?R) ))) /x - abcabc1Xabc2XabcXabcabc - 0: abcabc1Xabc2XabcX - 1: abcabc1Xabc2XabcX - 2: abcabc1Xabc2XabcX - -/^(?(DEFINE) (? a) (? b) ) (?&A) (?&B) /x - abcd - 0: ab - 1: - 2: - -/(?(?&NAME_PAT))\s+(?(?&ADDRESS_PAT)) - (?(DEFINE) - (?[a-z]+) - (?\d+) - )/x - metcalfe 33 - 0: metcalfe 33 - 1: metcalfe - 2: 33 - 3: - 4: - -/^(?(DEFINE) abc | xyz ) /x -Failed: DEFINE group contains more than one branch at offset 22 - -/(?(DEFINE) abc) xyz/xI -Capturing subpattern count = 0 -Options: extended -First char = 'x' -Need char = 'z' - -/(?(DEFINE) abc){3} xyz/x -Failed: repeating a DEFINE group is not allowed at offset 17 - -/(a|)*\d/ - \O0aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -No match - \O0aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 -Matched, but too many substrings - -/^a.b/ - a\rb - 0: a\x0db - a\nb\ - 0: a\x0ab - a\x85b\ - 0: a\x85b - ** Failers -No match - a\nb -No match - a\nb\ -No match - a\rb\ -No match - a\rb\ -No match - a\x85b\ -No match - a\rb\ -No match - -/^abc./mgx - abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x85abc7 JUNK - 0: abc1 - 0: abc2 - 0: abc3 - 0: abc4 - 0: abc5 - 0: abc6 - 0: abc7 - -/abc.$/mgx - abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x85 abc7 abc9 - 0: abc1 - 0: abc2 - 0: abc3 - 0: abc4 - 0: abc5 - 0: abc6 - 0: abc9 - -/a/ - -/a/ -Failed: inconsistent NEWLINE options at offset 0 - -/^a\Rb/ - a\nb - 0: a\x0ab - a\rb - 0: a\x0db - a\r\nb - 0: a\x0d\x0ab - a\x0bb - 0: a\x0bb - a\x0cb - 0: a\x0cb - a\x85b - 0: a\x85b - ** Failers -No match - a\n\rb -No match - -/^a\R*b/ - ab - 0: ab - a\nb - 0: a\x0ab - a\rb - 0: a\x0db - a\r\nb - 0: a\x0d\x0ab - a\x0bb - 0: a\x0bb - a\x0cb - 0: a\x0cb - a\x85b - 0: a\x85b - a\n\rb - 0: a\x0a\x0db - a\n\r\x85\x0cb - 0: a\x0a\x0d\x85\x0cb - -/^a\R+b/ - a\nb - 0: a\x0ab - a\rb - 0: a\x0db - a\r\nb - 0: a\x0d\x0ab - a\x0bb - 0: a\x0bb - a\x0cb - 0: a\x0cb - a\x85b - 0: a\x85b - a\n\rb - 0: a\x0a\x0db - a\n\r\x85\x0cb - 0: a\x0a\x0d\x85\x0cb - ** Failers -No match - ab -No match - -/^a\R{1,3}b/ - a\nb - 0: a\x0ab - a\n\rb - 0: a\x0a\x0db - a\n\r\x85b - 0: a\x0a\x0d\x85b - a\r\n\r\nb - 0: a\x0d\x0a\x0d\x0ab - a\r\n\r\n\r\nb - 0: a\x0d\x0a\x0d\x0a\x0d\x0ab - a\n\r\n\rb - 0: a\x0a\x0d\x0a\x0db - a\n\n\r\nb - 0: a\x0a\x0a\x0d\x0ab - ** Failers -No match - a\n\n\n\rb -No match - a\r -No match - -/^a[\R]b/ - aRb - 0: aRb - ** Failers -No match - a\nb -No match - -/(?&abc)X(?P)/I -Capturing subpattern count = 1 -Named capturing subpatterns: - abc 1 -No options -No first char -Need char = 'P' - abcPXP123 - 0: PXP - 1: P - -/(?1)X(?P)/I -Capturing subpattern count = 1 -Named capturing subpatterns: - abc 1 -No options -No first char -Need char = 'P' - abcPXP123 - 0: PXP - 1: P - -/(?(DEFINE)(?2[0-4]\d|25[0-5]|1\d\d|[1-9]?\d))\b(?&byte)(\.(?&byte)){3}/ - 1.2.3.4 - 0: 1.2.3.4 - 1: - 2: .4 - 131.111.10.206 - 0: 131.111.10.206 - 1: - 2: .206 - 10.0.0.0 - 0: 10.0.0.0 - 1: - 2: .0 - ** Failers -No match - 10.6 -No match - 455.3.4.5 -No match - -/\b(?&byte)(\.(?&byte)){3}(?(DEFINE)(?2[0-4]\d|25[0-5]|1\d\d|[1-9]?\d))/ - 1.2.3.4 - 0: 1.2.3.4 - 1: .4 - 2: - 131.111.10.206 - 0: 131.111.10.206 - 1: .206 - 2: - 10.0.0.0 - 0: 10.0.0.0 - 1: .0 - 2: - ** Failers -No match - 10.6 -No match - 455.3.4.5 -No match - -/(?:a(?&abc)b)*(?x)/ - 123axbaxbaxbx456 - 0: axbaxbaxbx - 1: x - 123axbaxbaxb456 - 0: x - 1: x - -/(?:a(?&abc)b){1,5}(?x)/ - 123axbaxbaxbx456 - 0: axbaxbaxbx - 1: x - -/(?:a(?&abc)b){2,5}(?x)/ - 123axbaxbaxbx456 - 0: axbaxbaxbx - 1: x - -/(?:a(?&abc)b){2,}(?x)/ - 123axbaxbaxbx456 - 0: axbaxbaxbx - 1: x - -/(abc)(?i:(?1))/ - defabcabcxyz - 0: abcabc - 1: abc - DEFabcABCXYZ -No match - -/(abc)(?:(?i)(?1))/ - defabcabcxyz - 0: abcabc - 1: abc - DEFabcABCXYZ -No match - -/^(a(b))\1\g1\g{1}\g-1\g{-1}\g{-02}Z/ - ababababbbabZXXXX - 0: ababababbbabZ - 1: ab - 2: b - -/^(a)\g-2/ -Failed: reference to non-existent subpattern at offset 7 - -/^(a)\g/ -Failed: a numbered reference must not be zero at offset 5 - -/^(a)\g{0}/ -Failed: a numbered reference must not be zero at offset 8 - -/^(a)\g{3/ -Failed: \g is not followed by a braced, angle-bracketed, or quoted name/number or by a plain number at offset 8 - -/^(a)\g{4a}/ -Failed: reference to non-existent subpattern at offset 9 - -/^a.b/ - a\rb - 0: a\x0db - *** Failers -No match - a\nb -No match - -/.+foo/ - afoo - 0: afoo - ** Failers -No match - \r\nfoo -No match - \nfoo -No match - -/.+foo/ - afoo - 0: afoo - \nfoo - 0: \x0afoo - ** Failers -No match - \r\nfoo -No match - -/.+foo/ - afoo - 0: afoo - ** Failers -No match - \nfoo -No match - \r\nfoo -No match - -/.+foo/s - afoo - 0: afoo - \r\nfoo - 0: \x0d\x0afoo - \nfoo - 0: \x0afoo - -/^$/mg - abc\r\rxyz - 0: - abc\n\rxyz - 0: - ** Failers -No match - abc\r\nxyz -No match - -/(?m)^$/g+ - abc\r\n\r\n - 0: - 0+ \x0d\x0a - -/(?m)^$|^\r\n/g+ - abc\r\n\r\n - 0: - 0+ \x0d\x0a - 0: \x0d\x0a - 0+ - -/(?m)$/g+ - abc\r\n\r\n - 0: - 0+ \x0d\x0a\x0d\x0a - 0: - 0+ \x0d\x0a - 0: - 0+ - -/abc.$/mgx - abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x85 abc9 - 0: abc1 - 0: abc4 - 0: abc5 - 0: abc9 - -/^X/m - XABC - 0: X - ** Failers -No match - XABC\B -No match - -/(ab|c)(?-1)/BZ ------------------------------------------------------------------- - Bra - CBra 1 - ab - Alt - c - Ket - Once - Recurse - Ket - Ket - End ------------------------------------------------------------------- - abc - 0: abc - 1: ab - -/xy(?+1)(abc)/BZ ------------------------------------------------------------------- - Bra - xy - Once - Recurse - Ket - CBra 1 - abc - Ket - Ket - End ------------------------------------------------------------------- - xyabcabc - 0: xyabcabc - 1: abc - ** Failers -No match - xyabc -No match - -/x(?-0)y/ -Failed: a numbered reference must not be zero at offset 5 - -/x(?-1)y/ -Failed: reference to non-existent subpattern at offset 5 - -/x(?+0)y/ -Failed: a numbered reference must not be zero at offset 5 - -/x(?+1)y/ -Failed: reference to non-existent subpattern at offset 5 - -/^(abc)?(?(-1)X|Y)/BZ ------------------------------------------------------------------- - Bra - ^ - Brazero - CBra 1 - abc - Ket - Cond - 1 Cond ref - X - Alt - Y - Ket - Ket - End ------------------------------------------------------------------- - abcX - 0: abcX - 1: abc - Y - 0: Y - ** Failers -No match - abcY -No match - -/^((?(+1)X|Y)(abc))+/BZ ------------------------------------------------------------------- - Bra - ^ - CBra 1 - Cond - 2 Cond ref - X - Alt - Y - Ket - CBra 2 - abc - Ket - KetRmax - Ket - End ------------------------------------------------------------------- - YabcXabc - 0: YabcXabc - 1: Xabc - 2: abc - YabcXabcXabc - 0: YabcXabcXabc - 1: Xabc - 2: abc - ** Failers -No match - XabcXabc -No match - -/(?(-1)a)/BZ -Failed: reference to non-existent subpattern at offset 6 - -/((?(-1)a))/BZ ------------------------------------------------------------------- - Bra - CBra 1 - Cond - 1 Cond ref - a - Ket - Ket - Ket - End ------------------------------------------------------------------- - -/((?(-2)a))/BZ -Failed: reference to non-existent subpattern at offset 7 - -/^(?(+1)X|Y)(.)/BZ ------------------------------------------------------------------- - Bra - ^ - Cond - 1 Cond ref - X - Alt - Y - Ket - CBra 1 - Any - Ket - Ket - End ------------------------------------------------------------------- - Y! - 0: Y! - 1: ! - -/(foo)\Kbar/ - foobar - 0: bar - 1: foo - -/(foo)(\Kbar|baz)/ - foobar - 0: bar - 1: foo - 2: bar - foobaz - 0: foobaz - 1: foo - 2: baz - -/(foo\Kbar)baz/ - foobarbaz - 0: barbaz - 1: foobar - -/(?tom|bon)-\k{A}/ - tom-tom - 0: tom-tom - 1: tom - bon-bon - 0: bon-bon - 1: bon - ** Failers -No match - tom-bon -No match - -/(?tom|bon)-\g{A}/ - tom-tom - 0: tom-tom - 1: tom - bon-bon - 0: bon-bon - 1: bon - -/\g{A/ -Failed: syntax error in subpattern name (missing terminator) at offset 4 - -/(?|(abc)|(xyz))/BZ ------------------------------------------------------------------- - Bra - Bra - CBra 1 - abc - Ket - Alt - CBra 1 - xyz - Ket - Ket - Ket - End ------------------------------------------------------------------- - >abc< - 0: abc - 1: abc - >xyz< - 0: xyz - 1: xyz - -/(x)(?|(abc)|(xyz))(x)/BZ ------------------------------------------------------------------- - Bra - CBra 1 - x - Ket - Bra - CBra 2 - abc - Ket - Alt - CBra 2 - xyz - Ket - Ket - CBra 3 - x - Ket - Ket - End ------------------------------------------------------------------- - xabcx - 0: xabcx - 1: x - 2: abc - 3: x - xxyzx - 0: xxyzx - 1: x - 2: xyz - 3: x - -/(x)(?|(abc)(pqr)|(xyz))(x)/BZ ------------------------------------------------------------------- - Bra - CBra 1 - x - Ket - Bra - CBra 2 - abc - Ket - CBra 3 - pqr - Ket - Alt - CBra 2 - xyz - Ket - Ket - CBra 4 - x - Ket - Ket - End ------------------------------------------------------------------- - xabcpqrx - 0: xabcpqrx - 1: x - 2: abc - 3: pqr - 4: x - xxyzx - 0: xxyzx - 1: x - 2: xyz - 3: - 4: x - -/(?|(abc)|(xyz))\1/ - abcabc - 0: abcabc - 1: abc - xyzxyz - 0: xyzxyz - 1: xyz - ** Failers -No match - abcxyz -No match - xyzabc -No match - -/(?|(abc)|(xyz))(?1)/ - abcabc - 0: abcabc - 1: abc - xyzabc - 0: xyzabc - 1: xyz - ** Failers -No match - xyzxyz -No match - -/\H\h\V\v/ - X X\x0a - 0: X X\x0a - X\x09X\x0b - 0: X\x09X\x0b - ** Failers -No match - \xa0 X\x0a -No match - -/\H*\h+\V?\v{3,4}/ - \x09\x20\xa0X\x0a\x0b\x0c\x0d\x0a - 0: \x09 \xa0X\x0a\x0b\x0c\x0d - \x09\x20\xa0\x0a\x0b\x0c\x0d\x0a - 0: \x09 \xa0\x0a\x0b\x0c\x0d - \x09\x20\xa0\x0a\x0b\x0c - 0: \x09 \xa0\x0a\x0b\x0c - ** Failers -No match - \x09\x20\xa0\x0a\x0b -No match - -/\H{3,4}/ - XY ABCDE - 0: ABCD - XY PQR ST - 0: PQR - -/.\h{3,4}./ - XY AB PQRS - 0: B P - -/\h*X\h?\H+Y\H?Z/ - >XNNNYZ - 0: XNNNYZ - > X NYQZ - 0: X NYQZ - ** Failers -No match - >XYZ -No match - > X NY Z -No match - -/\v*X\v?Y\v+Z\V*\x0a\V+\x0b\V{2,3}\x0c/ - >XY\x0aZ\x0aA\x0bNN\x0c - 0: XY\x0aZ\x0aA\x0bNN\x0c - >\x0a\x0dX\x0aY\x0a\x0bZZZ\x0aAAA\x0bNNN\x0c - 0: \x0a\x0dX\x0aY\x0a\x0bZZZ\x0aAAA\x0bNNN\x0c - -/[\h]/BZ ------------------------------------------------------------------- - Bra - [\x09 \xa0] - Ket - End ------------------------------------------------------------------- - >\x09< - 0: \x09 - -/[\h]+/BZ ------------------------------------------------------------------- - Bra - [\x09 \xa0]+ - Ket - End ------------------------------------------------------------------- - >\x09\x20\xa0< - 0: \x09 \xa0 - -/[\v]/BZ ------------------------------------------------------------------- - Bra - [\x0a-\x0d\x85] - Ket - End ------------------------------------------------------------------- - -/[\H]/BZ ------------------------------------------------------------------- - Bra - [\x00-\x08\x0a-\x1f!-\x9f\xa1-\xff] - Ket - End ------------------------------------------------------------------- - -/[^\h]/BZ ------------------------------------------------------------------- - Bra - [\x00-\x08\x0a-\x1f!-\x9f\xa1-\xff] (neg) - Ket - End ------------------------------------------------------------------- - -/[\V]/BZ ------------------------------------------------------------------- - Bra - [\x00-\x09\x0e-\x84\x86-\xff] - Ket - End ------------------------------------------------------------------- - -/[\x0a\V]/BZ ------------------------------------------------------------------- - Bra - [\x00-\x0a\x0e-\x84\x86-\xff] - Ket - End ------------------------------------------------------------------- - -/\H++X/BZ ------------------------------------------------------------------- - Bra - \H++ - X - Ket - End ------------------------------------------------------------------- - ** Failers -No match - XXXX -No match - -/\H+\hY/BZ ------------------------------------------------------------------- - Bra - \H++ - \h - Y - Ket - End ------------------------------------------------------------------- - XXXX Y - 0: XXXX Y - -/\H+ Y/BZ ------------------------------------------------------------------- - Bra - \H++ - Y - Ket - End ------------------------------------------------------------------- - -/\h+A/BZ ------------------------------------------------------------------- - Bra - \h++ - A - Ket - End ------------------------------------------------------------------- - -/\v*B/BZ ------------------------------------------------------------------- - Bra - \v*+ - B - Ket - End ------------------------------------------------------------------- - -/\V+\x0a/BZ ------------------------------------------------------------------- - Bra - \V++ - \x0a - Ket - End ------------------------------------------------------------------- - -/A+\h/BZ ------------------------------------------------------------------- - Bra - A++ - \h - Ket - End ------------------------------------------------------------------- - -/ *\H/BZ ------------------------------------------------------------------- - Bra - *+ - \H - Ket - End ------------------------------------------------------------------- - -/A*\v/BZ ------------------------------------------------------------------- - Bra - A*+ - \v - Ket - End ------------------------------------------------------------------- - -/\x0b*\V/BZ ------------------------------------------------------------------- - Bra - \x0b*+ - \V - Ket - End ------------------------------------------------------------------- - -/\d+\h/BZ ------------------------------------------------------------------- - Bra - \d++ - \h - Ket - End ------------------------------------------------------------------- - -/\d*\v/BZ ------------------------------------------------------------------- - Bra - \d*+ - \v - Ket - End ------------------------------------------------------------------- - -/S+\h\S+\v/BZ ------------------------------------------------------------------- - Bra - S++ - \h - \S++ - \v - Ket - End ------------------------------------------------------------------- - -/\w{3,}\h\w+\v/BZ ------------------------------------------------------------------- - Bra - \w{3} - \w*+ - \h - \w++ - \v - Ket - End ------------------------------------------------------------------- - -/\h+\d\h+\w\h+\S\h+\H/BZ ------------------------------------------------------------------- - Bra - \h++ - \d - \h++ - \w - \h++ - \S - \h++ - \H - Ket - End ------------------------------------------------------------------- - -/\v+\d\v+\w\v+\S\v+\V/BZ ------------------------------------------------------------------- - Bra - \v++ - \d - \v++ - \w - \v+ - \S - \v++ - \V - Ket - End ------------------------------------------------------------------- - -/\H+\h\H+\d/BZ ------------------------------------------------------------------- - Bra - \H++ - \h - \H+ - \d - Ket - End ------------------------------------------------------------------- - -/\V+\v\V+\w/BZ ------------------------------------------------------------------- - Bra - \V++ - \v - \V+ - \w - Ket - End ------------------------------------------------------------------- - -/\( (?: [^()]* | (?R) )* \)/x -(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(00)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0) - 0: (0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(00)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0) - -/[\E]AAA/ -Failed: missing terminating ] for character class at offset 7 - -/[\Q\E]AAA/ -Failed: missing terminating ] for character class at offset 9 - -/[^\E]AAA/ -Failed: missing terminating ] for character class at offset 8 - -/[^\Q\E]AAA/ -Failed: missing terminating ] for character class at offset 10 - -/[\E^]AAA/ -Failed: missing terminating ] for character class at offset 8 - -/[\Q\E^]AAA/ -Failed: missing terminating ] for character class at offset 10 - -/A(*PRUNE)B(*SKIP)C(*THEN)D(*COMMIT)E(*F)F(*FAIL)G(?!)H(*ACCEPT)I/BZ ------------------------------------------------------------------- - Bra - A - *PRUNE - B - *SKIP - C - *THEN - D - *COMMIT - E - *FAIL - F - *FAIL - G - *FAIL - H - *ACCEPT - I - Ket - End ------------------------------------------------------------------- - -/^a+(*FAIL)/ - aaaaaa -No match - -/a+b?c+(*FAIL)/ - aaabccc -No match - -/a+b?(*PRUNE)c+(*FAIL)/ - aaabccc -No match - -/a+b?(*COMMIT)c+(*FAIL)/ - aaabccc -No match - -/a+b?(*SKIP)c+(*FAIL)/ - aaabcccaaabccc -No match - -/^(?:aaa(*THEN)\w{6}|bbb(*THEN)\w{5}|ccc(*THEN)\w{4}|\w{3})/ - aaaxxxxxx - 0: aaaxxxxxx - aaa++++++ - 0: aaa - bbbxxxxx - 0: bbbxxxxx - bbb+++++ - 0: bbb - cccxxxx - 0: cccxxxx - ccc++++ - 0: ccc - dddddddd - 0: ddd - -/^(aaa(*THEN)\w{6}|bbb(*THEN)\w{5}|ccc(*THEN)\w{4}|\w{3})/ - aaaxxxxxx - 0: aaaxxxxxx - 1: aaaxxxxxx - aaa++++++ - 0: aaa - 1: aaa - bbbxxxxx - 0: bbbxxxxx - 1: bbbxxxxx - bbb+++++ - 0: bbb - 1: bbb - cccxxxx - 0: cccxxxx - 1: cccxxxx - ccc++++ - 0: ccc - 1: ccc - dddddddd - 0: ddd - 1: ddd - -/a+b?(*THEN)c+(*FAIL)/ - aaabccc -No match - -/(A (A|B(*ACCEPT)|C) D)(E)/x - ABX - 0: AB - AADE - 0: AADE - 1: AAD - 2: A - 3: E - ACDE - 0: ACDE - 1: ACD - 2: C - 3: E - ** Failers -No match - AD -No match - -/^a+(*FAIL)/C - aaaaaa ---->aaaaaa - +0 ^ ^ - +1 ^ a+ - +3 ^ ^ (*FAIL) - +3 ^ ^ (*FAIL) - +3 ^ ^ (*FAIL) - +3 ^ ^ (*FAIL) - +3 ^ ^ (*FAIL) - +3 ^^ (*FAIL) -No match - -/a+b?c+(*FAIL)/C - aaabccc ---->aaabccc - +0 ^ a+ - +2 ^ ^ b? - +4 ^ ^ c+ - +6 ^ ^ (*FAIL) - +6 ^ ^ (*FAIL) - +6 ^ ^ (*FAIL) - +4 ^ ^ c+ - +2 ^ ^ b? - +4 ^ ^ c+ - +2 ^^ b? - +4 ^^ c+ - +0 ^ a+ - +2 ^ ^ b? - +4 ^ ^ c+ - +6 ^ ^ (*FAIL) - +6 ^ ^ (*FAIL) - +6 ^ ^ (*FAIL) - +4 ^ ^ c+ - +2 ^^ b? - +4 ^^ c+ - +0 ^ a+ - +2 ^^ b? - +4 ^ ^ c+ - +6 ^ ^ (*FAIL) - +6 ^ ^ (*FAIL) - +6 ^ ^ (*FAIL) - +4 ^^ c+ -No match - -/a+b?(*PRUNE)c+(*FAIL)/C - aaabccc ---->aaabccc - +0 ^ a+ - +2 ^ ^ b? - +4 ^ ^ (*PRUNE) -+12 ^ ^ c+ -+14 ^ ^ (*FAIL) -+14 ^ ^ (*FAIL) -+14 ^ ^ (*FAIL) - +0 ^ a+ - +2 ^ ^ b? - +4 ^ ^ (*PRUNE) -+12 ^ ^ c+ -+14 ^ ^ (*FAIL) -+14 ^ ^ (*FAIL) -+14 ^ ^ (*FAIL) - +0 ^ a+ - +2 ^^ b? - +4 ^ ^ (*PRUNE) -+12 ^ ^ c+ -+14 ^ ^ (*FAIL) -+14 ^ ^ (*FAIL) -+14 ^ ^ (*FAIL) -No match - -/a+b?(*COMMIT)c+(*FAIL)/C - aaabccc ---->aaabccc - +0 ^ a+ - +2 ^ ^ b? - +4 ^ ^ (*COMMIT) -+13 ^ ^ c+ -+15 ^ ^ (*FAIL) -+15 ^ ^ (*FAIL) -+15 ^ ^ (*FAIL) -No match - -/a+b?(*SKIP)c+(*FAIL)/C - aaabcccaaabccc ---->aaabcccaaabccc - +0 ^ a+ - +2 ^ ^ b? - +4 ^ ^ (*SKIP) -+11 ^ ^ c+ -+13 ^ ^ (*FAIL) -+13 ^ ^ (*FAIL) -+13 ^ ^ (*FAIL) - +0 ^ a+ - +2 ^ ^ b? - +4 ^ ^ (*SKIP) -+11 ^ ^ c+ -+13 ^ ^ (*FAIL) -+13 ^ ^ (*FAIL) -+13 ^ ^ (*FAIL) -No match - -/a+b?(*THEN)c+(*FAIL)/C - aaabccc ---->aaabccc - +0 ^ a+ - +2 ^ ^ b? - +4 ^ ^ (*THEN) -+11 ^ ^ c+ -+13 ^ ^ (*FAIL) -+13 ^ ^ (*FAIL) -+13 ^ ^ (*FAIL) - +0 ^ a+ - +2 ^ ^ b? - +4 ^ ^ (*THEN) -+11 ^ ^ c+ -+13 ^ ^ (*FAIL) -+13 ^ ^ (*FAIL) -+13 ^ ^ (*FAIL) - +0 ^ a+ - +2 ^^ b? - +4 ^ ^ (*THEN) -+11 ^ ^ c+ -+13 ^ ^ (*FAIL) -+13 ^ ^ (*FAIL) -+13 ^ ^ (*FAIL) -No match - -/a(*PRUNE:XXX)b/ -Failed: (*VERB) with an argument is not supported at offset 8 - -/a(*MARK)b/ -Failed: (*VERB) not recognized at offset 7 - -/(?i:A{1,}\6666666666)/ -Failed: number is too big at offset 19 - -/\g6666666666/ -Failed: number is too big at offset 11 - -/[\g6666666666]/ -Failed: number is too big at offset 12 - -/(?1)\c[/ -Failed: reference to non-existent subpattern at offset 3 - -/.+A/ - \r\nA -No match - -/\nA/ - \r\nA - 0: \x0aA - -/[\r\n]A/ - \r\nA - 0: \x0aA - -/(\r|\n)A/ - \r\nA - 0: \x0aA - 1: \x0a - -/a(*CR)b/ -Failed: (*VERB) not recognized at offset 5 - -/(*CR)a.b/ - a\nb - 0: a\x0ab - ** Failers -No match - a\rb -No match - -/(*CR)a.b/ - a\nb - 0: a\x0ab - ** Failers -No match - a\rb -No match - -/(*LF)a.b/ - a\rb - 0: a\x0db - ** Failers -No match - a\nb -No match - -/(*CRLF)a.b/ - a\rb - 0: a\x0db - a\nb - 0: a\x0ab - ** Failers -No match - a\r\nb -No match - -/(*ANYCRLF)a.b/ - ** Failers -No match - a\rb -No match - a\nb -No match - a\r\nb -No match - -/(*ANY)a.b/ - ** Failers -No match - a\rb -No match - a\nb -No match - a\r\nb -No match - a\x85b -No match - -/a\Rb/I -Capturing subpattern count = 0 -Options: bsr_anycrlf -First char = 'a' -Need char = 'b' - a\rb - 0: a\x0db - a\nb - 0: a\x0ab - a\r\nb - 0: a\x0d\x0ab - ** Failers -No match - a\x85b -No match - a\x0bb -No match - -/a\Rb/I -Capturing subpattern count = 0 -Options: bsr_unicode -First char = 'a' -Need char = 'b' - a\rb - 0: a\x0db - a\nb - 0: a\x0ab - a\r\nb - 0: a\x0d\x0ab - a\x85b - 0: a\x85b - a\x0bb - 0: a\x0bb - ** Failers -No match - a\x85b\ -No match - a\x0bb\ -No match - -/a\R?b/I -Capturing subpattern count = 0 -Options: bsr_anycrlf -First char = 'a' -Need char = 'b' - a\rb - 0: a\x0db - a\nb - 0: a\x0ab - a\r\nb - 0: a\x0d\x0ab - ** Failers -No match - a\x85b -No match - a\x0bb -No match - -/a\R?b/I -Capturing subpattern count = 0 -Options: bsr_unicode -First char = 'a' -Need char = 'b' - a\rb - 0: a\x0db - a\nb - 0: a\x0ab - a\r\nb - 0: a\x0d\x0ab - a\x85b - 0: a\x85b - a\x0bb - 0: a\x0bb - ** Failers -No match - a\x85b\ -No match - a\x0bb\ -No match - -/a\R{2,4}b/I -Capturing subpattern count = 0 -Partial matching not supported -Options: bsr_anycrlf -First char = 'a' -Need char = 'b' - a\r\n\nb - 0: a\x0d\x0a\x0ab - a\n\r\rb - 0: a\x0a\x0d\x0db - a\r\n\r\n\r\n\r\nb - 0: a\x0d\x0a\x0d\x0a\x0d\x0a\x0d\x0ab - ** Failers -No match - a\x85\85b -No match - a\x0b\0bb -No match - -/a\R{2,4}b/I -Capturing subpattern count = 0 -Partial matching not supported -Options: bsr_unicode -First char = 'a' -Need char = 'b' - a\r\rb - 0: a\x0d\x0db - a\n\n\nb - 0: a\x0a\x0a\x0ab - a\r\n\n\r\rb - 0: a\x0d\x0a\x0a\x0d\x0db - a\x85\85b -No match - a\x0b\0bb -No match - ** Failers -No match - a\r\r\r\r\rb -No match - a\x85\85b\ -No match - a\x0b\0bb\ -No match - -/(*BSR_ANYCRLF)a\Rb/I -Capturing subpattern count = 0 -Options: bsr_anycrlf -First char = 'a' -Need char = 'b' - a\nb - 0: a\x0ab - a\rb - 0: a\x0db - -/(*BSR_UNICODE)a\Rb/I -Capturing subpattern count = 0 -Options: bsr_unicode -First char = 'a' -Need char = 'b' - a\x85b - 0: a\x85b - -/(*BSR_ANYCRLF)(*CRLF)a\Rb/I -Capturing subpattern count = 0 -Options: bsr_anycrlf -Forced newline sequence: CRLF -First char = 'a' -Need char = 'b' - a\nb - 0: a\x0ab - a\rb - 0: a\x0db - -/(*CRLF)(*BSR_UNICODE)a\Rb/I -Capturing subpattern count = 0 -Options: bsr_unicode -Forced newline sequence: CRLF -First char = 'a' -Need char = 'b' - a\x85b - 0: a\x85b - -/(*CRLF)(*BSR_ANYCRLF)(*CR)ab/I -Capturing subpattern count = 0 -Options: bsr_anycrlf -Forced newline sequence: CR -First char = 'a' -Need char = 'b' - -/(?)(?&)/ -Failed: subpattern name expected at offset 9 - -/(?)(?&a)/ -Failed: reference to non-existent subpattern at offset 12 - -/(?)(?&aaaaaaaaaaaaaaaaaaaaaaa)/ -Failed: reference to non-existent subpattern at offset 32 - -/(?+-a)/ -Failed: digit expected after (?+ at offset 3 - -/(?-+a)/ -Failed: unrecognized character after (? or (?- at offset 3 - -/(?(-1))/ -Failed: reference to non-existent subpattern at offset 6 - -/(?(+10))/ -Failed: reference to non-existent subpattern at offset 7 - -/(?(10))/ -Failed: reference to non-existent subpattern at offset 6 - -/(?(+2))()()/ - -/(?(2))()()/ - -/\k''/ -Failed: subpattern name expected at offset 3 - -/\k<>/ -Failed: subpattern name expected at offset 3 - -/\k{}/ -Failed: subpattern name expected at offset 3 - -/(?P=)/ -Failed: subpattern name expected at offset 4 - -/(?P>)/ -Failed: subpattern name expected at offset 4 - -/(?!\w)(?R)/ -Failed: recursive call could loop indefinitely at offset 9 - -/(?=\w)(?R)/ -Failed: recursive call could loop indefinitely at offset 9 - -/(?a|b\gc)/ - aaaa - 0: a - 1: a - bacxxx - 0: bac - 1: bac - bbaccxxx - 0: bbacc - 1: bbacc - bbbacccxx - 0: bbbaccc - 1: bbbaccc - -/^(?a|b\g'name'c)/ - aaaa - 0: a - 1: a - bacxxx - 0: bac - 1: bac - bbaccxxx - 0: bbacc - 1: bbacc - bbbacccxx - 0: bbbaccc - 1: bbbaccc - -/^(a|b\g<1>c)/ - aaaa - 0: a - 1: a - bacxxx - 0: bac - 1: bac - bbaccxxx - 0: bbacc - 1: bbacc - bbbacccxx - 0: bbbaccc - 1: bbbaccc - -/^(a|b\g'1'c)/ - aaaa - 0: a - 1: a - bacxxx - 0: bac - 1: bac - bbaccxxx - 0: bbacc - 1: bbacc - bbbacccxx - 0: bbbaccc - 1: bbbaccc - -/^(a|b\g'-1'c)/ - aaaa - 0: a - 1: a - bacxxx - 0: bac - 1: bac - bbaccxxx - 0: bbacc - 1: bbacc - bbbacccxx - 0: bbbaccc - 1: bbbaccc - -/(^(a|b\g<-1>c))/ - aaaa - 0: a - 1: a - 2: a - bacxxx - 0: bac - 1: bac - 2: bac - bbaccxxx - 0: bbacc - 1: bbacc - 2: bbacc - bbbacccxx - 0: bbbaccc - 1: bbbaccc - 2: bbbaccc - -/(^(a|b\g<-1'c))/ -Failed: \g is not followed by a braced, angle-bracketed, or quoted name/number or by a plain number at offset 15 - -/(^(a|b\g{-1}))/ - bacxxx -No match - -/(?-i:\g)(?i:(?a))/ - XaaX - 0: aa - 1: a - XAAX - 0: AA - 1: A - -/(?i:\g)(?-i:(?a))/ - XaaX - 0: aa - 1: a - ** Failers -No match - XAAX -No match - -/(?-i:\g<+1>)(?i:(a))/ - XaaX - 0: aa - 1: a - XAAX - 0: AA - 1: A - -/(?=(?(?#simplesyntax)\$(?[a-zA-Z_\x{7f}-\x{ff}][a-zA-Z0-9_\x{7f}-\x{ff}]*)(?:\[(?[a-zA-Z0-9_\x{7f}-\x{ff}]+|\$\g)\]|->\g(\(.*?\))?)?|(?#simple syntax withbraces)\$\{(?:\g(?\[(?:\g|'(?:\\.|[^'\\])*'|"(?:\g|\\.|[^"\\])*")\])?|\g|\$\{\g\})\}|(?#complexsyntax)\{(?\$(?\g(\g*|\(.*?\))?)(?:->\g)*|\$\g|\$\{\g\})\}))\{/ - -/(?a|b|c)\g*/ - abc - 0: abc - 1: a - accccbbb - 0: accccbbb - 1: a - -/^(?+1)(?x|y){0}z/ - xzxx - 0: xz - 1: - yzyy - 0: yz - 1: - ** Failers -No match - xxz -No match - -/(\3)(\1)(a)/ - cat -No match - -/(\3)(\1)(a)/ - cat - 0: a - 1: - 2: - 3: a - -/TA]/ - The ACTA] comes - 0: TA] - -/TA]/ -Failed: ] is an invalid data character in JavaScript compatibility mode at offset 2 - -/(?2)[]a()b](abc)/ -Failed: reference to non-existent subpattern at offset 3 - -/(?2)[^]a()b](abc)/ -Failed: reference to non-existent subpattern at offset 3 - -/(?1)[]a()b](abc)/ - abcbabc - 0: abcbabc - 1: abc - ** Failers -No match - abcXabc -No match - -/(?1)[^]a()b](abc)/ - abcXabc - 0: abcXabc - 1: abc - ** Failers -No match - abcbabc -No match - -/(?2)[]a()b](abc)(xyz)/ - xyzbabcxyz - 0: xyzbabcxyz - 1: abc - 2: xyz - -/(?&N)[]a(?)](?abc)/ -Failed: reference to non-existent subpattern at offset 4 - -/(?&N)[]a(?)](abc)/ -Failed: reference to non-existent subpattern at offset 4 - -/a[]b/ -Failed: missing terminating ] for character class at offset 4 - -/a[^]b/ -Failed: missing terminating ] for character class at offset 5 - -/a[]b/ - ** Failers -No match - ab -No match - -/a[]+b/ - ** Failers -No match - ab -No match - -/a[]*+b/ - ** Failers -No match - ab -No match - -/a[^]b/ - aXb - 0: aXb - a\nb - 0: a\x0ab - ** Failers -No match - ab -No match - -/a[^]+b/ - aXb - 0: aXb - a\nX\nXb - 0: a\x0aX\x0aXb - ** Failers -No match - ab -No match - -/a(?!)+b/ -Failed: nothing to repeat at offset 5 - -/a(*FAIL)+b/ -Failed: nothing to repeat at offset 8 - -/(abc|pqr|123){0}[xyz]/SI -Capturing subpattern count = 1 -No options -No first char -No need char -Starting byte set: x y z - -/(?(?=.*b)b|^)/CI -Capturing subpattern count = 0 -Partial matching not supported -Options: -No first char -No need char - adc ---->adc - +0 ^ (?(?=.*b)b|^) - +2 ^ (?=.*b) - +5 ^ .* - +7 ^ ^ b - +7 ^ ^ b - +7 ^^ b - +7 ^ b -+12 ^ ) -+13 ^ - 0: - abc ---->abc - +0 ^ (?(?=.*b)b|^) - +2 ^ (?=.*b) - +5 ^ .* - +7 ^ ^ b - +7 ^ ^ b - +7 ^^ b - +8 ^ ^ ) - +9 ^ b - +0 ^ (?(?=.*b)b|^) - +2 ^ (?=.*b) - +5 ^ .* - +7 ^ ^ b - +7 ^^ b - +7 ^ b - +8 ^^ ) - +9 ^ b -+10 ^^ | -+13 ^^ - 0: b - -/(?(?=b).*b|^d)/I -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -No need char - -/(?(?=.*b).*b|^d)/I -Capturing subpattern count = 0 -Partial matching not supported -No options -First char at start or follows newline -No need char - -/a?|b?/P - abc - 0: a - ** Failers - 0: - ddd\N -No match: POSIX code 17: match failed - -/xyz/C - xyz ---->xyz - +0 ^ x - +1 ^^ y - +2 ^ ^ z - +3 ^ ^ - 0: xyz - abcxyz ---->abcxyz - +0 ^ x - +1 ^^ y - +2 ^ ^ z - +3 ^ ^ - 0: xyz - abcxyz\Y ---->abcxyz - +0 ^ x - +0 ^ x - +0 ^ x - +0 ^ x - +1 ^^ y - +2 ^ ^ z - +3 ^ ^ - 0: xyz - ** Failers -No match - abc -No match - abc\Y ---->abc - +0 ^ x - +0 ^ x - +0 ^ x - +0 ^ x -No match - abcxypqr -No match - abcxypqr\Y ---->abcxypqr - +0 ^ x - +0 ^ x - +0 ^ x - +0 ^ x - +1 ^^ y - +2 ^ ^ z - +0 ^ x - +0 ^ x - +0 ^ x - +0 ^ x - +0 ^ x -No match - -/^"((?(?=[a])[^"])|b)*"$/C - "ab" ---->"ab" - +0 ^ ^ - +1 ^ " - +2 ^^ ((?(?=[a])[^"])|b)* - +3 ^^ (?(?=[a])[^"]) - +5 ^^ (?=[a]) - +8 ^^ [a] -+11 ^ ^ ) -+12 ^^ [^"] -+16 ^ ^ ) -+17 ^ ^ | - +3 ^ ^ (?(?=[a])[^"]) - +5 ^ ^ (?=[a]) - +8 ^ ^ [a] -+21 ^ ^ " -+18 ^ ^ b -+19 ^ ^ ) - +3 ^ ^ (?(?=[a])[^"]) - +5 ^ ^ (?=[a]) - +8 ^ ^ [a] -+21 ^ ^ " -+22 ^ ^ $ -+23 ^ ^ - 0: "ab" - 1: - -/^"((?(?=[a])[^"])|b)*"$/ - "ab" - 0: "ab" - 1: - -/^X(?5)(a)(?|(b)|(q))(c)(d)(Y)/ - XYabcdY - 0: XYabcdY - 1: a - 2: b - 3: c - 4: d - 5: Y - -/^X(?5)(a)(?|(b)|(q))(c)(d)Y/ -Failed: reference to non-existent subpattern at offset 5 - -/^X(?&N)(a)(?|(b)|(q))(c)(d)(?Y)/ - XYabcdY - 0: XYabcdY - 1: a - 2: b - 3: c - 4: d - 5: Y - -/^X(?7)(a)(?|(b)|(q)(r)(s))(c)(d)(Y)/ - XYabcdY - 0: XYabcdY - 1: a - 2: b - 3: - 4: - 5: c - 6: d - 7: Y - -/^X(?7)(a)(?|(b|(r)(s))|(q))(c)(d)(Y)/ - XYabcdY - 0: XYabcdY - 1: a - 2: b - 3: - 4: - 5: c - 6: d - 7: Y - -/^X(?7)(a)(?|(b|(?|(r)|(t))(s))|(q))(c)(d)(Y)/ - XYabcdY - 0: XYabcdY - 1: a - 2: b - 3: - 4: - 5: c - 6: d - 7: Y - -/ End of testinput2 / diff --git a/libs/pcre/testdata/testoutput3 b/libs/pcre/testdata/testoutput3 deleted file mode 100644 index 28b1c3aaaf..0000000000 --- a/libs/pcre/testdata/testoutput3 +++ /dev/null @@ -1,163 +0,0 @@ -/^[\w]+/ - *** Failers -No match - École -No match - -/^[\w]+/Lfr_FR - École - 0: École - -/^[\w]+/ - *** Failers -No match - École -No match - -/^[\W]+/ - École - 0: \xc9 - -/^[\W]+/Lfr_FR - *** Failers - 0: *** - École -No match - -/[\b]/ - \b - 0: \x08 - *** Failers -No match - a -No match - -/[\b]/Lfr_FR - \b - 0: \x08 - *** Failers -No match - a -No match - -/^\w+/ - *** Failers -No match - École -No match - -/^\w+/Lfr_FR - École - 0: École - -/(.+)\b(.+)/ - École - 0: \xc9cole - 1: \xc9 - 2: cole - -/(.+)\b(.+)/Lfr_FR - *** Failers - 0: *** Failers - 1: *** - 2: Failers - École -No match - -/École/i - École - 0: \xc9cole - *** Failers -No match - école -No match - -/École/iLfr_FR - École - 0: École - école - 0: école - -/\w/IS -Capturing subpattern count = 0 -No options -No first char -No need char -Starting byte set: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P - Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z - -/\w/ISLfr_FR -Capturing subpattern count = 0 -No options -No first char -No need char -Starting byte set: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P - Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z - ª µ º À Á Â Ã Ä Å Æ Ç È É Ê Ë Ì Í Î Ï Ð Ñ Ò Ó Ô Õ Ö Ø Ù Ú Û Ü Ý Þ ß à á â - ã ä å æ ç è é ê ë ì í î ï ð ñ ò ó ô õ ö ø ù ú û ü ý þ ÿ - -/^[\xc8-\xc9]/iLfr_FR - École - 0: É - école - 0: é - -/^[\xc8-\xc9]/Lfr_FR - École - 0: É - *** Failers -No match - école -No match - -/\W+/Lfr_FR - >>>\xaa<<< - 0: >>> - >>>\xba<<< - 0: >>> - -/[\W]+/Lfr_FR - >>>\xaa<<< - 0: >>> - >>>\xba<<< - 0: >>> - -/[^[:alpha:]]+/Lfr_FR - >>>\xaa<<< - 0: >>> - >>>\xba<<< - 0: >>> - -/\w+/Lfr_FR - >>>\xaa<<< - 0: ª - >>>\xba<<< - 0: º - -/[\w]+/Lfr_FR - >>>\xaa<<< - 0: ª - >>>\xba<<< - 0: º - -/[[:alpha:]]+/Lfr_FR - >>>\xaa<<< - 0: ª - >>>\xba<<< - 0: º - -/[[:alpha:]][[:lower:]][[:upper:]]/DZLfr_FR ------------------------------------------------------------------- - Bra - [A-Za-z\xaa\xb5\xba\xc0-\xd6\xd8-\xf6\xf8-\xff] - [a-z\xb5\xdf-\xf6\xf8-\xff] - [A-Z\xc0-\xd6\xd8-\xde] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/ End of testinput3 / diff --git a/libs/pcre/testdata/testoutput4 b/libs/pcre/testdata/testoutput4 deleted file mode 100644 index e67a95895f..0000000000 --- a/libs/pcre/testdata/testoutput4 +++ /dev/null @@ -1,1092 +0,0 @@ -/-- Do not use the \x{} construct except with patterns that have the --/ -/-- /8 option set, because PCRE doesn't recognize them as UTF-8 unless --/ -No match -/-- that option is set. However, the latest Perls recognize them always. --/ -No match - -/a.b/8 - acb - 0: acb - a\x7fb - 0: a\x{7f}b - a\x{100}b - 0: a\x{100}b - *** Failers -No match - a\nb -No match - -/a(.{3})b/8 - a\x{4000}xyb - 0: a\x{4000}xyb - 1: \x{4000}xy - a\x{4000}\x7fyb - 0: a\x{4000}\x{7f}yb - 1: \x{4000}\x{7f}y - a\x{4000}\x{100}yb - 0: a\x{4000}\x{100}yb - 1: \x{4000}\x{100}y - *** Failers -No match - a\x{4000}b -No match - ac\ncb -No match - -/a(.*?)(.)/ - a\xc0\x88b - 0: a\xc0 - 1: - 2: \xc0 - -/a(.*?)(.)/8 - a\x{100}b - 0: a\x{100} - 1: - 2: \x{100} - -/a(.*)(.)/ - a\xc0\x88b - 0: a\xc0\x88b - 1: \xc0\x88 - 2: b - -/a(.*)(.)/8 - a\x{100}b - 0: a\x{100}b - 1: \x{100} - 2: b - -/a(.)(.)/ - a\xc0\x92bcd - 0: a\xc0\x92 - 1: \xc0 - 2: \x92 - -/a(.)(.)/8 - a\x{240}bcd - 0: a\x{240}b - 1: \x{240} - 2: b - -/a(.?)(.)/ - a\xc0\x92bcd - 0: a\xc0\x92 - 1: \xc0 - 2: \x92 - -/a(.?)(.)/8 - a\x{240}bcd - 0: a\x{240}b - 1: \x{240} - 2: b - -/a(.??)(.)/ - a\xc0\x92bcd - 0: a\xc0 - 1: - 2: \xc0 - -/a(.??)(.)/8 - a\x{240}bcd - 0: a\x{240} - 1: - 2: \x{240} - -/a(.{3})b/8 - a\x{1234}xyb - 0: a\x{1234}xyb - 1: \x{1234}xy - a\x{1234}\x{4321}yb - 0: a\x{1234}\x{4321}yb - 1: \x{1234}\x{4321}y - a\x{1234}\x{4321}\x{3412}b - 0: a\x{1234}\x{4321}\x{3412}b - 1: \x{1234}\x{4321}\x{3412} - *** Failers -No match - a\x{1234}b -No match - ac\ncb -No match - -/a(.{3,})b/8 - a\x{1234}xyb - 0: a\x{1234}xyb - 1: \x{1234}xy - a\x{1234}\x{4321}yb - 0: a\x{1234}\x{4321}yb - 1: \x{1234}\x{4321}y - a\x{1234}\x{4321}\x{3412}b - 0: a\x{1234}\x{4321}\x{3412}b - 1: \x{1234}\x{4321}\x{3412} - axxxxbcdefghijb - 0: axxxxbcdefghijb - 1: xxxxbcdefghij - a\x{1234}\x{4321}\x{3412}\x{3421}b - 0: a\x{1234}\x{4321}\x{3412}\x{3421}b - 1: \x{1234}\x{4321}\x{3412}\x{3421} - *** Failers -No match - a\x{1234}b -No match - -/a(.{3,}?)b/8 - a\x{1234}xyb - 0: a\x{1234}xyb - 1: \x{1234}xy - a\x{1234}\x{4321}yb - 0: a\x{1234}\x{4321}yb - 1: \x{1234}\x{4321}y - a\x{1234}\x{4321}\x{3412}b - 0: a\x{1234}\x{4321}\x{3412}b - 1: \x{1234}\x{4321}\x{3412} - axxxxbcdefghijb - 0: axxxxb - 1: xxxx - a\x{1234}\x{4321}\x{3412}\x{3421}b - 0: a\x{1234}\x{4321}\x{3412}\x{3421}b - 1: \x{1234}\x{4321}\x{3412}\x{3421} - *** Failers -No match - a\x{1234}b -No match - -/a(.{3,5})b/8 - a\x{1234}xyb - 0: a\x{1234}xyb - 1: \x{1234}xy - a\x{1234}\x{4321}yb - 0: a\x{1234}\x{4321}yb - 1: \x{1234}\x{4321}y - a\x{1234}\x{4321}\x{3412}b - 0: a\x{1234}\x{4321}\x{3412}b - 1: \x{1234}\x{4321}\x{3412} - axxxxbcdefghijb - 0: axxxxb - 1: xxxx - a\x{1234}\x{4321}\x{3412}\x{3421}b - 0: a\x{1234}\x{4321}\x{3412}\x{3421}b - 1: \x{1234}\x{4321}\x{3412}\x{3421} - axbxxbcdefghijb - 0: axbxxb - 1: xbxx - axxxxxbcdefghijb - 0: axxxxxb - 1: xxxxx - *** Failers -No match - a\x{1234}b -No match - axxxxxxbcdefghijb -No match - -/a(.{3,5}?)b/8 - a\x{1234}xyb - 0: a\x{1234}xyb - 1: \x{1234}xy - a\x{1234}\x{4321}yb - 0: a\x{1234}\x{4321}yb - 1: \x{1234}\x{4321}y - a\x{1234}\x{4321}\x{3412}b - 0: a\x{1234}\x{4321}\x{3412}b - 1: \x{1234}\x{4321}\x{3412} - axxxxbcdefghijb - 0: axxxxb - 1: xxxx - a\x{1234}\x{4321}\x{3412}\x{3421}b - 0: a\x{1234}\x{4321}\x{3412}\x{3421}b - 1: \x{1234}\x{4321}\x{3412}\x{3421} - axbxxbcdefghijb - 0: axbxxb - 1: xbxx - axxxxxbcdefghijb - 0: axxxxxb - 1: xxxxx - *** Failers -No match - a\x{1234}b -No match - axxxxxxbcdefghijb -No match - -/^[a\x{c0}]/8 - *** Failers -No match - \x{100} -No match - -/(?<=aXb)cd/8 - aXbcd - 0: cd - -/(?<=a\x{100}b)cd/8 - a\x{100}bcd - 0: cd - -/(?<=a\x{100000}b)cd/8 - a\x{100000}bcd - 0: cd - -/(?:\x{100}){3}b/8 - \x{100}\x{100}\x{100}b - 0: \x{100}\x{100}\x{100}b - *** Failers -No match - \x{100}\x{100}b -No match - -/\x{ab}/8 - \x{ab} - 0: \x{ab} - \xc2\xab - 0: \x{ab} - *** Failers -No match - \x00{ab} -No match - -/(?<=(.))X/8 - WXYZ - 0: X - 1: W - \x{256}XYZ - 0: X - 1: \x{256} - *** Failers -No match - XYZ -No match - -/X(\C{3})/8 - X\x{1234} - 0: X\x{1234} - 1: \x{1234} - -/X(\C{4})/8 - X\x{1234}YZ - 0: X\x{1234}Y - 1: \x{1234}Y - -/X\C*/8 - XYZabcdce - 0: XYZabcdce - -/X\C*?/8 - XYZabcde - 0: X - -/X\C{3,5}/8 - Xabcdefg - 0: Xabcde - X\x{1234} - 0: X\x{1234} - X\x{1234}YZ - 0: X\x{1234}YZ - X\x{1234}\x{512} - 0: X\x{1234}\x{512} - X\x{1234}\x{512}YZ - 0: X\x{1234}\x{512} - -/X\C{3,5}?/8 - Xabcdefg - 0: Xabc - X\x{1234} - 0: X\x{1234} - X\x{1234}YZ - 0: X\x{1234} - X\x{1234}\x{512} - 0: X\x{1234} - -/[^a]+/8g - bcd - 0: bcd - \x{100}aY\x{256}Z - 0: \x{100} - 0: Y\x{256}Z - -/^[^a]{2}/8 - \x{100}bc - 0: \x{100}b - -/^[^a]{2,}/8 - \x{100}bcAa - 0: \x{100}bcA - -/^[^a]{2,}?/8 - \x{100}bca - 0: \x{100}b - -/[^a]+/8ig - bcd - 0: bcd - \x{100}aY\x{256}Z - 0: \x{100} - 0: Y\x{256}Z - -/^[^a]{2}/8i - \x{100}bc - 0: \x{100}b - -/^[^a]{2,}/8i - \x{100}bcAa - 0: \x{100}bc - -/^[^a]{2,}?/8i - \x{100}bca - 0: \x{100}b - -/\x{100}{0,0}/8 - abcd - 0: - -/\x{100}?/8 - abcd - 0: - \x{100}\x{100} - 0: \x{100} - -/\x{100}{0,3}/8 - \x{100}\x{100} - 0: \x{100}\x{100} - \x{100}\x{100}\x{100}\x{100} - 0: \x{100}\x{100}\x{100} - -/\x{100}*/8 - abce - 0: - \x{100}\x{100}\x{100}\x{100} - 0: \x{100}\x{100}\x{100}\x{100} - -/\x{100}{1,1}/8 - abcd\x{100}\x{100}\x{100}\x{100} - 0: \x{100} - -/\x{100}{1,3}/8 - abcd\x{100}\x{100}\x{100}\x{100} - 0: \x{100}\x{100}\x{100} - -/\x{100}+/8 - abcd\x{100}\x{100}\x{100}\x{100} - 0: \x{100}\x{100}\x{100}\x{100} - -/\x{100}{3}/8 - abcd\x{100}\x{100}\x{100}XX - 0: \x{100}\x{100}\x{100} - -/\x{100}{3,5}/8 - abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX - 0: \x{100}\x{100}\x{100}\x{100}\x{100} - -/\x{100}{3,}/8 - abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX - 0: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} - -/(?<=a\x{100}{2}b)X/8+ - Xyyya\x{100}\x{100}bXzzz - 0: X - 0+ zzz - -/\D*/8 - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - -/\D*/8 - \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} - 0: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} - -/\D/8 - 1X2 - 0: X - 1\x{100}2 - 0: \x{100} - -/>\S/8 - > >X Y - 0: >X - > >\x{100} Y - 0: >\x{100} - -/\d/8 - \x{100}3 - 0: 3 - -/\s/8 - \x{100} X - 0: - -/\D+/8 - 12abcd34 - 0: abcd - *** Failers - 0: *** Failers - 1234 -No match - -/\D{2,3}/8 - 12abcd34 - 0: abc - 12ab34 - 0: ab - *** Failers - 0: *** - 1234 -No match - 12a34 -No match - -/\D{2,3}?/8 - 12abcd34 - 0: ab - 12ab34 - 0: ab - *** Failers - 0: ** - 1234 -No match - 12a34 -No match - -/\d+/8 - 12abcd34 - 0: 12 - *** Failers -No match - -/\d{2,3}/8 - 12abcd34 - 0: 12 - 1234abcd - 0: 123 - *** Failers -No match - 1.4 -No match - -/\d{2,3}?/8 - 12abcd34 - 0: 12 - 1234abcd - 0: 12 - *** Failers -No match - 1.4 -No match - -/\S+/8 - 12abcd34 - 0: 12abcd34 - *** Failers - 0: *** - \ \ -No match - -/\S{2,3}/8 - 12abcd34 - 0: 12a - 1234abcd - 0: 123 - *** Failers - 0: *** - \ \ -No match - -/\S{2,3}?/8 - 12abcd34 - 0: 12 - 1234abcd - 0: 12 - *** Failers - 0: ** - \ \ -No match - -/>\s+ <34 - 0: > < - 0+ 34 - *** Failers -No match - -/>\s{2,3} < - 0+ cd - ab> < - 0+ ce - *** Failers -No match - ab> \s{2,3}? < - 0+ cd - ab> < - 0+ ce - *** Failers -No match - ab> \xff< - 0: \xff - -/[\xff]/8 - >\x{ff}< - 0: \x{ff} - -/[^\xFF]/ - XYZ - 0: X - -/[^\xff]/8 - XYZ - 0: X - \x{123} - 0: \x{123} - -/^[ac]*b/8 - xb -No match - -/^[ac\x{100}]*b/8 - xb -No match - -/^[^x]*b/8i - xb -No match - -/^[^x]*b/8 - xb -No match - -/^\d*b/8 - xb -No match - -/(|a)/g8 - catac - 0: - 1: - 0: - 1: - 0: a - 1: a - 0: - 1: - 0: - 1: - 0: a - 1: a - 0: - 1: - 0: - 1: - a\x{256}a - 0: - 1: - 0: a - 1: a - 0: - 1: - 0: - 1: - 0: a - 1: a - 0: - 1: - -/^\x{85}$/8i - \x{85} - 0: \x{85} - -/^ሴ/8 - ሴ - 0: \x{1234} - -/^\ሴ/8 - ሴ - 0: \x{1234} - -"(?s)(.{1,5})"8 - abcdefg - 0: abcde - 1: abcde - ab - 0: ab - 1: ab - -/a*\x{100}*\w/8 - a - 0: a - -/\S\S/8g - A\x{a3}BC - 0: A\x{a3} - 0: BC - -/\S{2}/8g - A\x{a3}BC - 0: A\x{a3} - 0: BC - -/\W\W/8g - +\x{a3}== - 0: +\x{a3} - 0: == - -/\W{2}/8g - +\x{a3}== - 0: +\x{a3} - 0: == - -/\S/8g - \x{442}\x{435}\x{441}\x{442} - 0: \x{442} - 0: \x{435} - 0: \x{441} - 0: \x{442} - -/[\S]/8g - \x{442}\x{435}\x{441}\x{442} - 0: \x{442} - 0: \x{435} - 0: \x{441} - 0: \x{442} - -/\D/8g - \x{442}\x{435}\x{441}\x{442} - 0: \x{442} - 0: \x{435} - 0: \x{441} - 0: \x{442} - -/[\D]/8g - \x{442}\x{435}\x{441}\x{442} - 0: \x{442} - 0: \x{435} - 0: \x{441} - 0: \x{442} - -/\W/8g - \x{2442}\x{2435}\x{2441}\x{2442} - 0: \x{2442} - 0: \x{2435} - 0: \x{2441} - 0: \x{2442} - -/[\W]/8g - \x{2442}\x{2435}\x{2441}\x{2442} - 0: \x{2442} - 0: \x{2435} - 0: \x{2441} - 0: \x{2442} - -/[\S\s]*/8 - abc\n\r\x{442}\x{435}\x{441}\x{442}xyz - 0: abc\x{0a}\x{0d}\x{442}\x{435}\x{441}\x{442}xyz - -/[\x{41f}\S]/8g - \x{442}\x{435}\x{441}\x{442} - 0: \x{442} - 0: \x{435} - 0: \x{441} - 0: \x{442} - -/.[^\S]./8g - abc def\x{442}\x{443}xyz\npqr - 0: c d - 0: z\x{0a}p - -/.[^\S\n]./8g - abc def\x{442}\x{443}xyz\npqr - 0: c d - -/[[:^alnum:]]/8g - +\x{2442} - 0: + - 0: \x{2442} - -/[[:^alpha:]]/8g - +\x{2442} - 0: + - 0: \x{2442} - -/[[:^ascii:]]/8g - A\x{442} - 0: \x{442} - -/[[:^blank:]]/8g - A\x{442} - 0: A - 0: \x{442} - -/[[:^cntrl:]]/8g - A\x{442} - 0: A - 0: \x{442} - -/[[:^digit:]]/8g - A\x{442} - 0: A - 0: \x{442} - -/[[:^graph:]]/8g - \x19\x{e01ff} - 0: \x{19} - 0: \x{e01ff} - -/[[:^lower:]]/8g - A\x{422} - 0: A - 0: \x{422} - -/[[:^print:]]/8g - \x{19}\x{e01ff} - 0: \x{19} - 0: \x{e01ff} - -/[[:^punct:]]/8g - A\x{442} - 0: A - 0: \x{442} - -/[[:^space:]]/8g - A\x{442} - 0: A - 0: \x{442} - -/[[:^upper:]]/8g - a\x{442} - 0: a - 0: \x{442} - -/[[:^word:]]/8g - +\x{2442} - 0: + - 0: \x{2442} - -/[[:^xdigit:]]/8g - M\x{442} - 0: M - 0: \x{442} - -/[^ABCDEFGHIJKLMNOPQRSTUVWXYZÀÃÂÃÄÅÆÇÈÉÊËÌÃÃŽÃÃÑÒÓÔÕÖØÙÚÛÜÃÞĀĂĄĆĈĊČĎÄĒĔĖĘĚĜĞĠĢĤĦĨĪĬĮİIJĴĶĹĻĽĿÅŃŅŇŊŌŎÅŒŔŖŘŚŜŞŠŢŤŦŨŪŬŮŰŲŴŶŸŹŻŽÆƂƄƆƇƉƊƋƎÆÆƑƓƔƖƗƘƜÆƟƠƢƤƦƧƩƬƮƯƱƲƳƵƷƸƼDŽLJNJÇÇǑǓǕǗǙǛǞǠǢǤǦǨǪǬǮDZǴǶǷǸǺǼǾȀȂȄȆȈȊȌȎÈȒȔȖȘȚȜȞȠȢȤȦȨȪȬȮȰȲȺȻȽȾÉΆΈΉΊΌΎÎΑΒΓΔΕΖΗΘΙΚΛΜÎΞΟΠΡΣΤΥΦΧΨΩΪΫϒϓϔϘϚϜϞϠϢϤϦϨϪϬϮϴϷϹϺϽϾϿЀÐЂЃЄЅІЇЈЉЊЋЌÐÐŽÐÐБВГДЕЖЗИЙКЛМÐОПРСТУФХЦЧШЩЪЫЬЭЮЯѠѢѤѦѨѪѬѮѰѲѴѶѸѺѼѾҀҊҌҎÒҒҔҖҘҚҜҞҠҢҤҦҨҪҬҮҰҲҴҶҸҺҼҾӀÓÓƒÓ…Ó‡Ó‰Ó‹ÓÓӒӔӖӘӚӜӞӠӢӤӦӨӪӬӮӰӲӴӶӸԀԂԄԆԈԊԌԎԱԲԳԴԵԶԷԸԹԺԻԼԽԾԿՀÕÕ‚ÕƒÕ„Õ…Õ†Õ‡ÕˆÕ‰ÕŠÕ‹ÕŒÕÕŽÕÕՑՒՓՔՕՖႠႡႢႣႤႥႦႧႨႩႪႫႬႭႮႯႰႱႲႳႴႵႶႷႸႹႺႻႼႽႾႿჀáƒáƒ‚ჃჄჅḀḂḄḆḈḊḌḎá¸á¸’ḔḖḘḚḜḞḠḢḤḦḨḪḬḮḰḲḴḶḸḺḼḾṀṂṄṆṈṊṌṎá¹á¹’ṔṖṘṚṜṞṠṢṤṦṨṪṬṮṰṲṴṶṸṺṼṾẀẂẄẆẈẊẌẎáºáº’ẔẠẢẤẦẨẪẬẮẰẲẴẶẸẺẼẾỀỂỄỆỈỊỌỎá»á»’ỔỖỘỚỜỞỠỢỤỦỨỪỬỮỰỲỴỶỸἈἉἊἋἌá¼á¼Žá¼á¼˜á¼™á¼šá¼›á¼œá¼á¼¨á¼©á¼ªá¼«á¼¬á¼­á¼®á¼¯á¼¸á¼¹á¼ºá¼»á¼¼á¼½á¼¾á¼¿á½ˆá½‰á½Šá½‹á½Œá½á½™á½›á½á½Ÿá½¨á½©á½ªá½«á½¬á½­á½®á½¯á¾¸á¾¹á¾ºá¾»á¿ˆá¿‰á¿Šá¿‹á¿˜á¿™á¿šá¿›á¿¨á¿©á¿ªá¿«á¿¬á¿¸á¿¹á¿ºá¿»abcdefghijklmnopqrstuvwxyzªµºßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿÄăąćĉċÄÄđēĕėęěÄğġģĥħĩīĭįıijĵķĸĺļľŀłńņňʼnŋÅÅőœŕŗřśÅşšţťŧũūŭůűųŵŷźżžſƀƃƅƈƌƃƕƙƚƛƞơƣƥƨƪƫƭưƴƶƹƺƽƾƿdžljnjǎÇǒǔǖǘǚǜÇǟǡǣǥǧǩǫǭǯǰdzǵǹǻǽǿÈȃȅȇȉȋÈÈȑȓȕȗșțÈȟȡȣȥȧȩȫȭȯȱȳȴȵȶȷȸȹȼȿɀÉɑɒɓɔɕɖɗɘəɚɛɜÉɞɟɠɡɢɣɤɥɦɧɨɩɪɫɬɭɮɯɰɱɲɳɴɵɶɷɸɹɺɻɼɽɾɿʀÊʂʃʄʅʆʇʈʉʊʋʌÊÊŽÊÊʑʒʓʔʕʖʗʘʙʚʛʜÊʞʟʠʡʢʣʤʥʦʧʨʩʪʫʬʭʮʯÎάέήίΰαβγδεζηθικλμνξοπÏςστυφχψωϊϋόÏÏŽÏϑϕϖϗϙϛÏϟϡϣϥϧϩϫϭϯϰϱϲϳϵϸϻϼабвгдежзийклмнопрÑтуфхцчшщъыьÑÑŽÑÑёђѓєѕіїјљњћќÑўџѡѣѥѧѩѫѭѯѱѳѵѷѹѻѽѿÒÒ‹ÒÒÒ‘Ò“Ò•Ò—Ò™Ò›ÒҟҡңҥҧҩҫҭүұҳҵҷҹһҽҿӂӄӆӈӊӌӎӑӓӕӗәӛÓÓŸÓ¡Ó£Ó¥Ó§Ó©Ó«Ó­Ó¯Ó±Ó³ÓµÓ·Ó¹ÔÔƒÔ…Ô‡Ô‰Ô‹ÔÔÕ¡Õ¢Õ£Õ¤Õ¥Õ¦Õ§Õ¨Õ©ÕªÕ«Õ¬Õ­Õ®Õ¯Õ°Õ±Õ²Õ³Õ´ÕµÕ¶Õ·Õ¸Õ¹ÕºÕ»Õ¼Õ½Õ¾Õ¿Ö€Öւփքօֆևᴀá´á´‚ᴃᴄᴅᴆᴇᴈᴉᴊᴋᴌá´á´Žá´á´á´‘ᴒᴓᴔᴕᴖᴗᴘᴙᴚᴛᴜá´á´žá´Ÿá´ á´¡á´¢á´£á´¤á´¥á´¦á´§á´¨á´©á´ªá´«áµ¢áµ£áµ¤áµ¥áµ¦áµ§áµ¨áµ©áµªáµ«áµ¬áµ­áµ®áµ¯áµ°áµ±áµ²áµ³áµ´áµµáµ¶áµ·áµ¹áµºáµ»áµ¼áµ½áµ¾áµ¿á¶€á¶á¶‚ᶃᶄᶅᶆᶇᶈᶉᶊᶋᶌá¶á¶Žá¶á¶á¶‘ᶒᶓᶔᶕᶖᶗᶘᶙᶚá¸á¸ƒá¸…ḇḉḋá¸á¸á¸‘ḓḕḗḙḛá¸á¸Ÿá¸¡á¸£á¸¥á¸§á¸©á¸«á¸­á¸¯á¸±á¸³á¸µá¸·á¸¹á¸»á¸½á¸¿á¹á¹ƒá¹…ṇṉṋá¹á¹á¹‘ṓṕṗṙṛá¹á¹Ÿá¹¡á¹£á¹¥á¹§á¹©á¹«á¹­á¹¯á¹±á¹³á¹µá¹·á¹¹á¹»á¹½á¹¿áºáºƒáº…ẇẉẋáºáºáº‘ẓẕẖẗẘẙẚẛạảấầẩẫậắằẳẵặẹẻẽếá»á»ƒá»…ệỉịá»á»á»‘ồổỗộớá»á»Ÿá»¡á»£á»¥á»§á»©á»«á»­á»¯á»±á»³á»µá»·á»¹á¼€á¼á¼‚ἃἄἅἆἇá¼á¼‘ἒἓἔἕἠἡἢἣἤἥἦἧἰἱἲἳἴἵἶἷὀá½á½‚ὃὄὅá½á½‘ὒὓὔὕὖὗὠὡὢὣὤὥὦὧὰάὲέὴήὶίὸόὺύὼώᾀá¾á¾‚ᾃᾄᾅᾆᾇá¾á¾‘ᾒᾓᾔᾕᾖᾗᾠᾡᾢᾣᾤᾥᾦᾧᾰᾱᾲᾳᾴᾶᾷιῂῃῄῆῇá¿á¿‘ῒΐῖῗῠῡῢΰῤῥῦῧῲῳῴῶῷâ²â²ƒâ²…ⲇⲉⲋâ²â²â²‘ⲓⲕⲗⲙⲛâ²â²Ÿâ²¡â²£â²¥â²§â²©â²«â²­â²¯â²±â²³â²µâ²·â²¹â²»â²½â²¿â³â³ƒâ³…ⳇⳉⳋâ³â³â³‘ⳓⳕⳗⳙⳛâ³â³Ÿâ³¡â³£â³¤â´€â´â´‚ⴃⴄⴅⴆⴇⴈⴉⴊⴋⴌâ´â´Žâ´â´â´‘ⴒⴓⴔⴕⴖⴗⴘⴙⴚⴛⴜâ´â´žâ´Ÿâ´ â´¡â´¢â´£â´¤â´¥ï¬€ï¬ï¬‚ffifflſtstﬓﬔﬕﬖﬗ\d-_^]/8 - -/^[^d]*?$/ - abc - 0: abc - -/^[^d]*?$/8 - abc - 0: abc - -/^[^d]*?$/i - abc - 0: abc - -/^[^d]*?$/8i - abc - 0: abc - -/(?i)[\xc3\xa9\xc3\xbd]|[\xc3\xa9\xc3\xbdA]/8 - -/ End of testinput4 / diff --git a/libs/pcre/testdata/testoutput5 b/libs/pcre/testdata/testoutput5 deleted file mode 100644 index 75630b4500..0000000000 --- a/libs/pcre/testdata/testoutput5 +++ /dev/null @@ -1,1655 +0,0 @@ -/\x{100}/8DZ ------------------------------------------------------------------- - Bra - \x{100} - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 196 -Need char = 128 - -/\x{1000}/8DZ ------------------------------------------------------------------- - Bra - \x{1000} - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 225 -Need char = 128 - -/\x{10000}/8DZ ------------------------------------------------------------------- - Bra - \x{10000} - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 240 -Need char = 128 - -/\x{100000}/8DZ ------------------------------------------------------------------- - Bra - \x{100000} - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 244 -Need char = 128 - -/\x{1000000}/8DZ ------------------------------------------------------------------- - Bra - \x{1000000} - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 249 -Need char = 128 - -/\x{4000000}/8DZ ------------------------------------------------------------------- - Bra - \x{4000000} - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 252 -Need char = 128 - -/\x{7fffFFFF}/8DZ ------------------------------------------------------------------- - Bra - \x{7fffffff} - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 253 -Need char = 191 - -/[\x{ff}]/8DZ ------------------------------------------------------------------- - Bra - \x{ff} - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 195 -Need char = 191 - -/[\x{100}]/8DZ ------------------------------------------------------------------- - Bra - [\x{100}] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -No need char - -/\x{ffffffff}/8 -Failed: character value in \x{...} sequence is too large at offset 11 - -/\x{100000000}/8 -Failed: character value in \x{...} sequence is too large at offset 12 - -/^\x{100}a\x{1234}/8 - \x{100}a\x{1234}bcd - 0: \x{100}a\x{1234} - -/\x80/8DZ ------------------------------------------------------------------- - Bra - \x{80} - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 194 -Need char = 128 - -/\xff/8DZ ------------------------------------------------------------------- - Bra - \x{ff} - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 195 -Need char = 191 - -/\x{0041}\x{2262}\x{0391}\x{002e}/DZ8 ------------------------------------------------------------------- - Bra - A\x{2262}\x{391}. - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 'A' -Need char = '.' - \x{0041}\x{2262}\x{0391}\x{002e} - 0: A\x{2262}\x{391}. - -/\x{D55c}\x{ad6d}\x{C5B4}/DZ8 ------------------------------------------------------------------- - Bra - \x{d55c}\x{ad6d}\x{c5b4} - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 237 -Need char = 180 - \x{D55c}\x{ad6d}\x{C5B4} - 0: \x{d55c}\x{ad6d}\x{c5b4} - -/\x{65e5}\x{672c}\x{8a9e}/DZ8 ------------------------------------------------------------------- - Bra - \x{65e5}\x{672c}\x{8a9e} - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 230 -Need char = 158 - \x{65e5}\x{672c}\x{8a9e} - 0: \x{65e5}\x{672c}\x{8a9e} - -/\x{80}/DZ8 ------------------------------------------------------------------- - Bra - \x{80} - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 194 -Need char = 128 - -/\x{084}/DZ8 ------------------------------------------------------------------- - Bra - \x{84} - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 194 -Need char = 132 - -/\x{104}/DZ8 ------------------------------------------------------------------- - Bra - \x{104} - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 196 -Need char = 132 - -/\x{861}/DZ8 ------------------------------------------------------------------- - Bra - \x{861} - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 224 -Need char = 161 - -/\x{212ab}/DZ8 ------------------------------------------------------------------- - Bra - \x{212ab} - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 240 -Need char = 171 - -/.{3,5}X/DZ8 ------------------------------------------------------------------- - Bra - Any{3} - Any{0,2} - X - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: utf8 -No first char -Need char = 'X' - \x{212ab}\x{212ab}\x{212ab}\x{861}X - 0: \x{212ab}\x{212ab}\x{212ab}\x{861}X - - -/.{3,5}?/DZ8 ------------------------------------------------------------------- - Bra - Any{3} - Any{0,2}? - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: utf8 -No first char -No need char - \x{212ab}\x{212ab}\x{212ab}\x{861} - 0: \x{212ab}\x{212ab}\x{212ab} - -/-- These tests are here rather than in testinput4 because Perl 5.6 has some -problems with UTF-8 support, in the area of \x{..} where the value is < 255. -It grumbles about invalid UTF-8 strings. --/ - -/^[a\x{c0}]b/8 - \x{c0}b - 0: \x{c0}b - -/^([a\x{c0}]*?)aa/8 - a\x{c0}aaaa/ - 0: a\x{c0}aa - 1: a\x{c0} - -/^([a\x{c0}]*?)aa/8 - a\x{c0}aaaa/ - 0: a\x{c0}aa - 1: a\x{c0} - a\x{c0}a\x{c0}aaa/ - 0: a\x{c0}a\x{c0}aa - 1: a\x{c0}a\x{c0} - -/^([a\x{c0}]*)aa/8 - a\x{c0}aaaa/ - 0: a\x{c0}aaaa - 1: a\x{c0}aa - a\x{c0}a\x{c0}aaa/ - 0: a\x{c0}a\x{c0}aaa - 1: a\x{c0}a\x{c0}a - -/^([a\x{c0}]*)a\x{c0}/8 - a\x{c0}aaaa/ - 0: a\x{c0} - 1: - a\x{c0}a\x{c0}aaa/ - 0: a\x{c0}a\x{c0} - 1: a\x{c0} - -/-- --/ - -/(?<=\C)X/8 -Failed: \C not allowed in lookbehind assertion at offset 6 - -/-- This one is here not because it's different to Perl, but because the way -the captured single-byte is displayed. (In Perl it becomes a character, and you -can't tell the difference.) --/ - -/X(\C)(.*)/8 - X\x{1234} - 0: X\x{1234} - 1: \xe1 - 2: \x88\xb4 - X\nabc - 0: X\x{0a}abc - 1: \x{0a} - 2: abc - -/^[ab]/8DZ ------------------------------------------------------------------- - Bra - ^ - [ab] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored utf8 -No first char -No need char - bar - 0: b - *** Failers -No match - c -No match - \x{ff} -No match - \x{100} -No match - -/^[^ab]/8DZ ------------------------------------------------------------------- - Bra - ^ - [\x00-`c-\xff] (neg) - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored utf8 -No first char -No need char - c - 0: c - \x{ff} - 0: \x{ff} - \x{100} - 0: \x{100} - *** Failers - 0: * - aaa -No match - -/[^ab\xC0-\xF0]/8SDZ ------------------------------------------------------------------- - Bra - [\x00-`c-\xbf\xf1-\xff] (neg) - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -No need char -Starting byte set: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a - \x0b \x0c \x0d \x0e \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 - \x1a \x1b \x1c \x1d \x1e \x1f \x20 ! " # $ % & ' ( ) * + , - . / 0 1 2 3 4 - 5 6 7 8 9 : ; < = > ? @ A B C D E F G H I J K L M N O P Q R S T U V W X Y - Z [ \ ] ^ _ ` c d e f g h i j k l m n o p q r s t u v w x y z { | } ~ \x7f - \xc2 \xc3 \xc4 \xc5 \xc6 \xc7 \xc8 \xc9 \xca \xcb \xcc \xcd \xce \xcf \xd0 - \xd1 \xd2 \xd3 \xd4 \xd5 \xd6 \xd7 \xd8 \xd9 \xda \xdb \xdc \xdd \xde \xdf - \xe0 \xe1 \xe2 \xe3 \xe4 \xe5 \xe6 \xe7 \xe8 \xe9 \xea \xeb \xec \xed \xee - \xef \xf0 \xf1 \xf2 \xf3 \xf4 \xf5 \xf6 \xf7 \xf8 \xf9 \xfa \xfb \xfc \xfd - \xfe \xff - \x{f1} - 0: \x{f1} - \x{bf} - 0: \x{bf} - \x{100} - 0: \x{100} - \x{1000} - 0: \x{1000} - *** Failers - 0: * - \x{c0} -No match - \x{f0} -No match - -/Ä€{3,4}/8SDZ ------------------------------------------------------------------- - Bra - \x{100}{3} - \x{100}? - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: utf8 -First char = 196 -Need char = 128 -Study returned NULL - \x{100}\x{100}\x{100}\x{100\x{100} - 0: \x{100}\x{100}\x{100} - -/(\x{100}+|x)/8SDZ ------------------------------------------------------------------- - Bra - CBra 1 - \x{100}+ - Alt - x - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Partial matching not supported -Options: utf8 -No first char -No need char -Starting byte set: x \xc4 - -/(\x{100}*a|x)/8SDZ ------------------------------------------------------------------- - Bra - CBra 1 - \x{100}*+ - a - Alt - x - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Partial matching not supported -Options: utf8 -No first char -No need char -Starting byte set: a x \xc4 - -/(\x{100}{0,2}a|x)/8SDZ ------------------------------------------------------------------- - Bra - CBra 1 - \x{100}{0,2} - a - Alt - x - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Partial matching not supported -Options: utf8 -No first char -No need char -Starting byte set: a x \xc4 - -/(\x{100}{1,2}a|x)/8SDZ ------------------------------------------------------------------- - Bra - CBra 1 - \x{100} - \x{100}{0,1} - a - Alt - x - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Partial matching not supported -Options: utf8 -No first char -No need char -Starting byte set: x \xc4 - -/\x{100}*(\d+|"(?1)")/8 - 1234 - 0: 1234 - 1: 1234 - "1234" - 0: "1234" - 1: "1234" - \x{100}1234 - 0: \x{100}1234 - 1: 1234 - "\x{100}1234" - 0: \x{100}1234 - 1: 1234 - \x{100}\x{100}12ab - 0: \x{100}\x{100}12 - 1: 12 - \x{100}\x{100}"12" - 0: \x{100}\x{100}"12" - 1: "12" - *** Failers -No match - \x{100}\x{100}abcd -No match - -/\x{100}/8DZ ------------------------------------------------------------------- - Bra - \x{100} - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 196 -Need char = 128 - -/\x{100}*/8DZ ------------------------------------------------------------------- - Bra - \x{100}* - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: utf8 -No first char -No need char - -/a\x{100}*/8DZ ------------------------------------------------------------------- - Bra - a - \x{100}* - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: utf8 -First char = 'a' -No need char - -/ab\x{100}*/8DZ ------------------------------------------------------------------- - Bra - ab - \x{100}* - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: utf8 -First char = 'a' -Need char = 'b' - -/a\x{100}\x{101}*/8DZ ------------------------------------------------------------------- - Bra - a\x{100} - \x{101}* - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: utf8 -First char = 'a' -Need char = 128 - -/a\x{100}\x{101}+/8DZ ------------------------------------------------------------------- - Bra - a\x{100} - \x{101}+ - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: utf8 -First char = 'a' -Need char = 129 - -/\x{100}*A/8DZ ------------------------------------------------------------------- - Bra - \x{100}*+ - A - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: utf8 -No first char -Need char = 'A' - A - 0: A - -/\x{100}*\d(?R)/8DZ ------------------------------------------------------------------- - Bra - \x{100}*+ - \d - Once - Recurse - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: utf8 -No first char -No need char - -/[^\x{c4}]/DZ ------------------------------------------------------------------- - Bra - [^\xc4] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/[^\x{c4}]/8DZ ------------------------------------------------------------------- - Bra - [\x00-\xc3\xc5-\xff] (neg) - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -No need char - -/[\x{100}]/8DZ ------------------------------------------------------------------- - Bra - [\x{100}] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -No need char - \x{100} - 0: \x{100} - Z\x{100} - 0: \x{100} - \x{100}Z - 0: \x{100} - *** Failers -No match - -/[Z\x{100}]/8DZ ------------------------------------------------------------------- - Bra - [Z\x{100}] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -No need char - Z\x{100} - 0: Z - \x{100} - 0: \x{100} - \x{100}Z - 0: \x{100} - *** Failers -No match - -/[\x{200}-\x{100}]/8 -Failed: range out of order in character class at offset 15 - -/[Ä€-Ä„]/8 - \x{100} - 0: \x{100} - \x{104} - 0: \x{104} - *** Failers -No match - \x{105} -No match - \x{ff} -No match - -/[z-\x{100}]/8DZ ------------------------------------------------------------------- - Bra - [z-\x{100}] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -No need char - -/[z\Qa-d]Ä€\E]/8DZ ------------------------------------------------------------------- - Bra - [\-\]adz\x{100}] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -No need char - \x{100} - 0: \x{100} - Ä€ - 0: \x{100} - -/[\xFF]/DZ ------------------------------------------------------------------- - Bra - \xff - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = 255 -No need char - >\xff< - 0: \xff - -/[\xff]/DZ8 ------------------------------------------------------------------- - Bra - \x{ff} - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 195 -Need char = 191 - >\x{ff}< - 0: \x{ff} - -/[^\xFF]/DZ ------------------------------------------------------------------- - Bra - [^\xff] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/[^\xff]/8DZ ------------------------------------------------------------------- - Bra - [\x00-\xfe] (neg) - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -No need char - -/[Ä-Ãœ]/8 - Ö # Matches without Study - 0: \x{d6} - \x{d6} - 0: \x{d6} - -/[Ä-Ãœ]/8S - Ö <-- Same with Study - 0: \x{d6} - \x{d6} - 0: \x{d6} - -/[\x{c4}-\x{dc}]/8 - Ö # Matches without Study - 0: \x{d6} - \x{d6} - 0: \x{d6} - -/[\x{c4}-\x{dc}]/8S - Ö <-- Same with Study - 0: \x{d6} - \x{d6} - 0: \x{d6} - -/[Ã]/8 -Failed: invalid UTF-8 string at offset 2 - -/Ã/8 -Failed: invalid UTF-8 string at offset 0 - -/ÃÃÃxxx/8 -Failed: invalid UTF-8 string at offset 1 - -/ÃÃÃxxx/8?DZ ------------------------------------------------------------------- - Bra - \X{c0}\X{c0}\X{c0}xxx - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 no_utf8_check -First char = 195 -Need char = 'x' - -/abc/8 - Ã] -Error -10 - à -Error -10 - ÃÃà -Error -10 - ÃÃÃ\? -No match - -/anything/8 - \xc0\x80 -Error -10 - \xc1\x8f -Error -10 - \xe0\x9f\x80 -Error -10 - \xf0\x8f\x80\x80 -Error -10 - \xf8\x87\x80\x80\x80 -Error -10 - \xfc\x83\x80\x80\x80\x80 -Error -10 - \xfe\x80\x80\x80\x80\x80 -Error -10 - \xff\x80\x80\x80\x80\x80 -Error -10 - \xc3\x8f -No match - \xe0\xaf\x80 -No match - \xe1\x80\x80 -No match - \xf0\x9f\x80\x80 -No match - \xf1\x8f\x80\x80 -No match - \xf8\x88\x80\x80\x80 -Error -10 - \xf9\x87\x80\x80\x80 -Error -10 - \xfc\x84\x80\x80\x80\x80 -Error -10 - \xfd\x83\x80\x80\x80\x80 -Error -10 - \?\xf8\x88\x80\x80\x80 -No match - \?\xf9\x87\x80\x80\x80 -No match - \?\xfc\x84\x80\x80\x80\x80 -No match - \?\xfd\x83\x80\x80\x80\x80 -No match - -/\x{100}abc(xyz(?1))/8DZ ------------------------------------------------------------------- - Bra - \x{100}abc - CBra 1 - xyz - Once - Recurse - Ket - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Options: utf8 -First char = 196 -Need char = 'z' - -/[^\x{100}]abc(xyz(?1))/8DZ ------------------------------------------------------------------- - Bra - [^\x{100}] - abc - CBra 1 - xyz - Once - Recurse - Ket - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Options: utf8 -No first char -Need char = 'z' - -/[ab\x{100}]abc(xyz(?1))/8DZ ------------------------------------------------------------------- - Bra - [ab\x{100}] - abc - CBra 1 - xyz - Once - Recurse - Ket - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Options: utf8 -No first char -Need char = 'z' - -/(\x{100}(b(?2)c))?/DZ8 ------------------------------------------------------------------- - Bra - Brazero - CBra 1 - \x{100} - CBra 2 - b - Once - Recurse - Ket - c - Ket - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 2 -Options: utf8 -No first char -No need char - -/(\x{100}(b(?2)c)){0,2}/DZ8 ------------------------------------------------------------------- - Bra - Brazero - Bra - CBra 1 - \x{100} - CBra 2 - b - Once - Recurse - Ket - c - Ket - Ket - Brazero - CBra 1 - \x{100} - CBra 2 - b - Once - Recurse - Ket - c - Ket - Ket - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 2 -Options: utf8 -No first char -No need char - -/(\x{100}(b(?1)c))?/DZ8 ------------------------------------------------------------------- - Bra - Brazero - CBra 1 - \x{100} - CBra 2 - b - Once - Recurse - Ket - c - Ket - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 2 -Options: utf8 -No first char -No need char - -/(\x{100}(b(?1)c)){0,2}/DZ8 ------------------------------------------------------------------- - Bra - Brazero - Bra - CBra 1 - \x{100} - CBra 2 - b - Once - Recurse - Ket - c - Ket - Ket - Brazero - CBra 1 - \x{100} - CBra 2 - b - Once - Recurse - Ket - c - Ket - Ket - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 2 -Options: utf8 -No first char -No need char - -/\W/8 - A.B - 0: . - A\x{100}B - 0: \x{100} - -/\w/8 - \x{100}X - 0: X - -/a\x{1234}b/P8 - a\x{1234}b - 0: a\x{1234}b - -/^\ሴ/8DZ ------------------------------------------------------------------- - Bra - ^ - \x{1234} - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored utf8 -No first char -No need char - -/\777/I -Failed: octal value is greater than \377 (not in UTF-8 mode) at offset 3 - -/\777/8I -Capturing subpattern count = 0 -Options: utf8 -First char = 199 -Need char = 191 - \x{1ff} - 0: \x{1ff} - \777 - 0: \x{1ff} - -/\x{100}*\d/8DZ ------------------------------------------------------------------- - Bra - \x{100}*+ - \d - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: utf8 -No first char -No need char - -/\x{100}*\s/8DZ ------------------------------------------------------------------- - Bra - \x{100}*+ - \s - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: utf8 -No first char -No need char - -/\x{100}*\w/8DZ ------------------------------------------------------------------- - Bra - \x{100}*+ - \w - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: utf8 -No first char -No need char - -/\x{100}*\D/8DZ ------------------------------------------------------------------- - Bra - \x{100}* - \D - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: utf8 -No first char -No need char - -/\x{100}*\S/8DZ ------------------------------------------------------------------- - Bra - \x{100}* - \S - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: utf8 -No first char -No need char - -/\x{100}*\W/8DZ ------------------------------------------------------------------- - Bra - \x{100}* - \W - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: utf8 -No first char -No need char - -/\x{100}+\x{200}/8DZ ------------------------------------------------------------------- - Bra - \x{100}++ - \x{200} - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: utf8 -First char = 196 -Need char = 128 - -/\x{100}+X/8DZ ------------------------------------------------------------------- - Bra - \x{100}++ - X - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: utf8 -First char = 196 -Need char = 'X' - -/X+\x{200}/8DZ ------------------------------------------------------------------- - Bra - X++ - \x{200} - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: utf8 -First char = 'X' -Need char = 128 - -/()()()()()()()()()() - ()()()()()()()()()() - ()()()()()()()()()() - ()()()()()()()()()() - A (x) (?41) B/8x - AxxB -Matched, but too many substrings - 0: AxxB - 1: - 2: - 3: - 4: - 5: - 6: - 7: - 8: - 9: -10: -11: -12: -13: -14: - -/^[\x{100}\E-\Q\E\x{150}]/BZ8 ------------------------------------------------------------------- - Bra - ^ - [\x{100}-\x{150}] - Ket - End ------------------------------------------------------------------- - -/^[\QÄ€\E-\QÅ\E]/BZ8 ------------------------------------------------------------------- - Bra - ^ - [\x{100}-\x{150}] - Ket - End ------------------------------------------------------------------- - -/^[\QÄ€\E-\QÅ\E/BZ8 -Failed: missing terminating ] for character class at offset 15 - -/^abc./mgx8 - abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x{0085}abc7 \x{2028}abc8 \x{2029}abc9 JUNK - 0: abc1 - 0: abc2 - 0: abc3 - 0: abc4 - 0: abc5 - 0: abc6 - 0: abc7 - 0: abc8 - 0: abc9 - -/abc.$/mgx8 - abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x{0085} abc7\x{2028} abc8\x{2029} abc9 - 0: abc1 - 0: abc2 - 0: abc3 - 0: abc4 - 0: abc5 - 0: abc6 - 0: abc7 - 0: abc8 - 0: abc9 - -/^a\Rb/8 - a\nb - 0: a\x{0a}b - a\rb - 0: a\x{0d}b - a\r\nb - 0: a\x{0d}\x{0a}b - a\x0bb - 0: a\x{0b}b - a\x0cb - 0: a\x{0c}b - a\x{85}b - 0: a\x{85}b - a\x{2028}b - 0: a\x{2028}b - a\x{2029}b - 0: a\x{2029}b - ** Failers -No match - a\n\rb -No match - -/^a\R*b/8 - ab - 0: ab - a\nb - 0: a\x{0a}b - a\rb - 0: a\x{0d}b - a\r\nb - 0: a\x{0d}\x{0a}b - a\x0bb - 0: a\x{0b}b - a\x0c\x{2028}\x{2029}b - 0: a\x{0c}\x{2028}\x{2029}b - a\x{85}b - 0: a\x{85}b - a\n\rb - 0: a\x{0a}\x{0d}b - a\n\r\x{85}\x0cb - 0: a\x{0a}\x{0d}\x{85}\x{0c}b - -/^a\R+b/8 - a\nb - 0: a\x{0a}b - a\rb - 0: a\x{0d}b - a\r\nb - 0: a\x{0d}\x{0a}b - a\x0bb - 0: a\x{0b}b - a\x0c\x{2028}\x{2029}b - 0: a\x{0c}\x{2028}\x{2029}b - a\x{85}b - 0: a\x{85}b - a\n\rb - 0: a\x{0a}\x{0d}b - a\n\r\x{85}\x0cb - 0: a\x{0a}\x{0d}\x{85}\x{0c}b - ** Failers -No match - ab -No match - -/^a\R{1,3}b/8 - a\nb - 0: a\x{0a}b - a\n\rb - 0: a\x{0a}\x{0d}b - a\n\r\x{85}b - 0: a\x{0a}\x{0d}\x{85}b - a\r\n\r\nb - 0: a\x{0d}\x{0a}\x{0d}\x{0a}b - a\r\n\r\n\r\nb - 0: a\x{0d}\x{0a}\x{0d}\x{0a}\x{0d}\x{0a}b - a\n\r\n\rb - 0: a\x{0a}\x{0d}\x{0a}\x{0d}b - a\n\n\r\nb - 0: a\x{0a}\x{0a}\x{0d}\x{0a}b - ** Failers -No match - a\n\n\n\rb -No match - a\r -No match - -/\H\h\V\v/8 - X X\x0a - 0: X X\x{0a} - X\x09X\x0b - 0: X\x{09}X\x{0b} - ** Failers -No match - \x{a0} X\x0a -No match - -/\H*\h+\V?\v{3,4}/8 - \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a - 0: \x{09} \x{a0}X\x{0a}\x{0b}\x{0c}\x{0d} - \x09\x20\x{a0}\x0a\x0b\x0c\x0d\x0a - 0: \x{09} \x{a0}\x{0a}\x{0b}\x{0c}\x{0d} - \x09\x20\x{a0}\x0a\x0b\x0c - 0: \x{09} \x{a0}\x{0a}\x{0b}\x{0c} - ** Failers -No match - \x09\x20\x{a0}\x0a\x0b -No match - -/\H\h\V\v/8 - \x{3001}\x{3000}\x{2030}\x{2028} - 0: \x{3001}\x{3000}\x{2030}\x{2028} - X\x{180e}X\x{85} - 0: X\x{180e}X\x{85} - ** Failers -No match - \x{2009} X\x0a -No match - -/\H*\h+\V?\v{3,4}/8 - \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x0c\x0d\x0a - 0: \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x{0c}\x{0d} - \x09\x{205f}\x{a0}\x0a\x{2029}\x0c\x{2028}\x0a - 0: \x{09}\x{205f}\x{a0}\x{0a}\x{2029}\x{0c}\x{2028} - \x09\x20\x{202f}\x0a\x0b\x0c - 0: \x{09} \x{202f}\x{0a}\x{0b}\x{0c} - ** Failers -No match - \x09\x{200a}\x{a0}\x{2028}\x0b -No match - -/[\h]/8BZ ------------------------------------------------------------------- - Bra - [\x09 \xa0\x{1680}\x{180e}\x{2000}-\x{200a}\x{202f}\x{205f}\x{3000}] - Ket - End ------------------------------------------------------------------- - >\x{1680} - 0: \x{1680} - -/[\h]{3,}/8BZ ------------------------------------------------------------------- - Bra - [\x09 \xa0\x{1680}\x{180e}\x{2000}-\x{200a}\x{202f}\x{205f}\x{3000}]{3,} - Ket - End ------------------------------------------------------------------- - >\x{1680}\x{180e}\x{2000}\x{2003}\x{200a}\x{202f}\x{205f}\x{3000}< - 0: \x{1680}\x{180e}\x{2000}\x{2003}\x{200a}\x{202f}\x{205f}\x{3000} - -/[\v]/8BZ ------------------------------------------------------------------- - Bra - [\x0a-\x0d\x85\x{2028}-\x{2029}] - Ket - End ------------------------------------------------------------------- - -/[\H]/8BZ ------------------------------------------------------------------- - Bra - [\x00-\x08\x0a-\x1f!-\x9f\xa1-\xff\x{100}-\x{167f}\x{1681}-\x{180d}\x{180f}-\x{1fff}\x{200b}-\x{202e}\x{2030}-\x{205e}\x{2060}-\x{2fff}\x{3001}-\x{7fffffff}] - Ket - End ------------------------------------------------------------------- - -/[\V]/8BZ ------------------------------------------------------------------- - Bra - [\x00-\x09\x0e-\x84\x86-\xff\x{100}-\x{2027}\x{2029}-\x{7fffffff}] - Ket - End ------------------------------------------------------------------- - -/.*$/8 - \x{1ec5} - 0: \x{1ec5} - -/-- This tests the stricter UTF-8 check according to RFC 3629. --/ - -/X/8 - \x{0}\x{d7ff}\x{e000}\x{10ffff} -No match - \x{d800} -Error -10 - \x{d800}\? -No match - \x{da00} -Error -10 - \x{da00}\? -No match - \x{dfff} -Error -10 - \x{dfff}\? -No match - \x{110000} -Error -10 - \x{110000}\? -No match - \x{2000000} -Error -10 - \x{2000000}\? -No match - \x{7fffffff} -Error -10 - \x{7fffffff}\? -No match - -/a\Rb/I8 -Capturing subpattern count = 0 -Options: bsr_anycrlf utf8 -First char = 'a' -Need char = 'b' - a\rb - 0: a\x{0d}b - a\nb - 0: a\x{0a}b - a\r\nb - 0: a\x{0d}\x{0a}b - ** Failers -No match - a\x{85}b -No match - a\x0bb -No match - -/a\Rb/I8 -Capturing subpattern count = 0 -Options: bsr_unicode utf8 -First char = 'a' -Need char = 'b' - a\rb - 0: a\x{0d}b - a\nb - 0: a\x{0a}b - a\r\nb - 0: a\x{0d}\x{0a}b - a\x{85}b - 0: a\x{85}b - a\x0bb - 0: a\x{0b}b - ** Failers -No match - a\x{85}b\ -No match - a\x0bb\ -No match - -/a\R?b/I8 -Capturing subpattern count = 0 -Options: bsr_anycrlf utf8 -First char = 'a' -Need char = 'b' - a\rb - 0: a\x{0d}b - a\nb - 0: a\x{0a}b - a\r\nb - 0: a\x{0d}\x{0a}b - ** Failers -No match - a\x{85}b -No match - a\x0bb -No match - -/a\R?b/I8 -Capturing subpattern count = 0 -Options: bsr_unicode utf8 -First char = 'a' -Need char = 'b' - a\rb - 0: a\x{0d}b - a\nb - 0: a\x{0a}b - a\r\nb - 0: a\x{0d}\x{0a}b - a\x{85}b - 0: a\x{85}b - a\x0bb - 0: a\x{0b}b - ** Failers -No match - a\x{85}b\ -No match - a\x0bb\ -No match - -/.*a.*=.b.*/8 - QQQ\x{2029}ABCaXYZ=!bPQR - 0: ABCaXYZ=!bPQR - ** Failers -No match - a\x{2029}b -No match - \x61\xe2\x80\xa9\x62 -No match - -/[[:a\x{100}b:]]/8 -Failed: unknown POSIX class name at offset 3 - -/a[^]b/8 - a\x{1234}b - 0: a\x{1234}b - a\nb - 0: a\x{0a}b - ** Failers -No match - ab -No match - -/a[^]+b/8 - aXb - 0: aXb - a\nX\nX\x{1234}b - 0: a\x{0a}X\x{0a}X\x{1234}b - ** Failers -No match - ab -No match - -/(\x{de})\1/ - \x{de}\x{de} - 0: \xde\xde - 1: \xde - \x{123} -** Character \x{123} is greater than 255 and UTF-8 mode is not enabled. -** Truncation will probably give the wrong result. -No match - -/X/8f - A\x{1ec5}ABCXYZ - 0: X - -/(*UTF8)\x{1234}/ - abcd\x{1234}pqr - 0: \x{1234} - -/(*CRLF)(*UTF8)(*BSR_UNICODE)a\Rb/I -Capturing subpattern count = 0 -Options: bsr_unicode utf8 -Forced newline sequence: CRLF -First char = 'a' -Need char = 'b' - -/ End of testinput5 / diff --git a/libs/pcre/testdata/testoutput6 b/libs/pcre/testdata/testoutput6 deleted file mode 100644 index cb6f7d55ca..0000000000 --- a/libs/pcre/testdata/testoutput6 +++ /dev/null @@ -1,1760 +0,0 @@ -/^\pC\pL\pM\pN\pP\pS\pZ3 - 0: abc - *** Failers -No match - xyzabc -No match - xyzabc\>2 -No match - -/x\dy\Dz/ - x9yzz - 0: x9yzz - x0y+z - 0: x0y+z - *** Failers -No match - xyz -No match - xxy0z -No match - -/x\sy\Sz/ - x yzz - 0: x yzz - x y+z - 0: x y+z - *** Failers -No match - xyz -No match - xxyyz -No match - -/x\wy\Wz/ - xxy+z - 0: xxy+z - *** Failers -No match - xxy0z -No match - x+y+z -No match - -/x.y/ - x+y - 0: x+y - x-y - 0: x-y - *** Failers -No match - x\ny -No match - -/x.y/s - x+y - 0: x+y - x-y - 0: x-y - x\ny - 0: x\x0ay - -/(a.b(?s)c.d|x.y)p.q/ - a+bc+dp+q - 0: a+bc+dp+q - a+bc\ndp+q - 0: a+bc\x0adp+q - x\nyp+q - 0: x\x0ayp+q - *** Failers -No match - a\nbc\ndp+q -No match - a+bc\ndp\nq -No match - x\nyp\nq -No match - -/a\d\z/ - ba0 - 0: a0 - *** Failers -No match - ba0\n -No match - ba0\ncd -No match - -/a\d\z/m - ba0 - 0: a0 - *** Failers -No match - ba0\n -No match - ba0\ncd -No match - -/a\d\Z/ - ba0 - 0: a0 - ba0\n - 0: a0 - *** Failers -No match - ba0\ncd -No match - -/a\d\Z/m - ba0 - 0: a0 - ba0\n - 0: a0 - *** Failers -No match - ba0\ncd -No match - -/a\d$/ - ba0 - 0: a0 - ba0\n - 0: a0 - *** Failers -No match - ba0\ncd -No match - -/a\d$/m - ba0 - 0: a0 - ba0\n - 0: a0 - ba0\ncd - 0: a0 - *** Failers -No match - -/abc/i - abc - 0: abc - aBc - 0: aBc - ABC - 0: ABC - -/[^a]/ - abcd - 0: b - -/ab?\w/ - abz - 0: abz - 1: ab - abbz - 0: abb - 1: ab - azz - 0: az - -/x{0,3}yz/ - ayzq - 0: yz - axyzq - 0: xyz - axxyz - 0: xxyz - axxxyzq - 0: xxxyz - axxxxyzq - 0: xxxyz - *** Failers -No match - ax -No match - axx -No match - -/x{3}yz/ - axxxyzq - 0: xxxyz - axxxxyzq - 0: xxxyz - *** Failers -No match - ax -No match - axx -No match - ayzq -No match - axyzq -No match - axxyz -No match - -/x{2,3}yz/ - axxyz - 0: xxyz - axxxyzq - 0: xxxyz - axxxxyzq - 0: xxxyz - *** Failers -No match - ax -No match - axx -No match - ayzq -No match - axyzq -No match - -/[^a]+/ - bac - 0: b - bcdefax - 0: bcdef - 1: bcde - 2: bcd - 3: bc - 4: b - *** Failers - 0: *** F - 1: *** - 2: *** - 3: ** - 4: * - aaaaa -No match - -/[^a]*/ - bac - 0: b - 1: - bcdefax - 0: bcdef - 1: bcde - 2: bcd - 3: bc - 4: b - 5: - *** Failers - 0: *** F - 1: *** - 2: *** - 3: ** - 4: * - 5: - aaaaa - 0: - -/[^a]{3,5}/ - xyz - 0: xyz - awxyza - 0: wxyz - 1: wxy - abcdefa - 0: bcdef - 1: bcde - 2: bcd - abcdefghijk - 0: bcdef - 1: bcde - 2: bcd - *** Failers - 0: *** F - 1: *** - 2: *** - axya -No match - axa -No match - aaaaa -No match - -/\d*/ - 1234b567 - 0: 1234 - 1: 123 - 2: 12 - 3: 1 - 4: - xyz - 0: - -/\D*/ - a1234b567 - 0: a - 1: - xyz - 0: xyz - 1: xy - 2: x - 3: - -/\d+/ - ab1234c56 - 0: 1234 - 1: 123 - 2: 12 - 3: 1 - *** Failers -No match - xyz -No match - -/\D+/ - ab123c56 - 0: ab - 1: a - *** Failers - 0: *** Failers - 1: *** Failer - 2: *** Faile - 3: *** Fail - 4: *** Fai - 5: *** Fa - 6: *** F - 7: *** - 8: *** - 9: ** -10: * - 789 -No match - -/\d?A/ - 045ABC - 0: 5A - ABC - 0: A - *** Failers -No match - XYZ -No match - -/\D?A/ - ABC - 0: A - BAC - 0: BA - 9ABC - 0: A - *** Failers -No match - -/a+/ - aaaa - 0: aaaa - 1: aaa - 2: aa - 3: a - -/^.*xyz/ - xyz - 0: xyz - ggggggggxyz - 0: ggggggggxyz - -/^.+xyz/ - abcdxyz - 0: abcdxyz - axyz - 0: axyz - *** Failers -No match - xyz -No match - -/^.?xyz/ - xyz - 0: xyz - cxyz - 0: cxyz - -/^\d{2,3}X/ - 12X - 0: 12X - 123X - 0: 123X - *** Failers -No match - X -No match - 1X -No match - 1234X -No match - -/^[abcd]\d/ - a45 - 0: a4 - b93 - 0: b9 - c99z - 0: c9 - d04 - 0: d0 - *** Failers -No match - e45 -No match - abcd -No match - abcd1234 -No match - 1234 -No match - -/^[abcd]*\d/ - a45 - 0: a4 - b93 - 0: b9 - c99z - 0: c9 - d04 - 0: d0 - abcd1234 - 0: abcd1 - 1234 - 0: 1 - *** Failers -No match - e45 -No match - abcd -No match - -/^[abcd]+\d/ - a45 - 0: a4 - b93 - 0: b9 - c99z - 0: c9 - d04 - 0: d0 - abcd1234 - 0: abcd1 - *** Failers -No match - 1234 -No match - e45 -No match - abcd -No match - -/^a+X/ - aX - 0: aX - aaX - 0: aaX - -/^[abcd]?\d/ - a45 - 0: a4 - b93 - 0: b9 - c99z - 0: c9 - d04 - 0: d0 - 1234 - 0: 1 - *** Failers -No match - abcd1234 -No match - e45 -No match - -/^[abcd]{2,3}\d/ - ab45 - 0: ab4 - bcd93 - 0: bcd9 - *** Failers -No match - 1234 -No match - a36 -No match - abcd1234 -No match - ee45 -No match - -/^(abc)*\d/ - abc45 - 0: abc4 - abcabcabc45 - 0: abcabcabc4 - 42xyz - 0: 4 - *** Failers -No match - -/^(abc)+\d/ - abc45 - 0: abc4 - abcabcabc45 - 0: abcabcabc4 - *** Failers -No match - 42xyz -No match - -/^(abc)?\d/ - abc45 - 0: abc4 - 42xyz - 0: 4 - *** Failers -No match - abcabcabc45 -No match - -/^(abc){2,3}\d/ - abcabc45 - 0: abcabc4 - abcabcabc45 - 0: abcabcabc4 - *** Failers -No match - abcabcabcabc45 -No match - abc45 -No match - 42xyz -No match - -/1(abc|xyz)2(?1)3/ - 1abc2abc3456 - 0: 1abc2abc3 - 1abc2xyz3456 - 0: 1abc2xyz3 - -/^(a*\w|ab)=(a*\w|ab)/ - ab=ab - 0: ab=ab - 1: ab=a - -/^(a*\w|ab)=(?1)/ - ab=ab - 0: ab=ab - -/^([^()]|\((?1)*\))*$/ - abc - 0: abc - a(b)c - 0: a(b)c - a(b(c))d - 0: a(b(c))d - *** Failers) -No match - a(b(c)d -No match - -/^>abc>([^()]|\((?1)*\))*abc>123abc>123abc>1(2)3abc>1(2)3abc>(1(2)3)abc>(1(2)3)a*)\d/ - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa9876 - 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa9 - *** Failers -No match - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -No match - -/< (?: (?(R) \d++ | [^<>]*+) | (?R)) * >/x - <> - 0: <> - - 0: - hij> - 0: hij> - hij> - 0: - def> - 0: def> - - 0: <> - *** Failers -No match - abcxyz - 1 ^ ^ x - 0: abcxyz - 123abcxyz999 ---->123abcxyz999 - 1 ^ ^ x - 0: abcxyz - -/(ab|cd){3,4}/C - ababab ---->ababab - +0 ^ (ab|cd){3,4} - +1 ^ a - +4 ^ c - +2 ^^ b - +3 ^ ^ | - +1 ^ ^ a - +4 ^ ^ c - +2 ^ ^ b - +3 ^ ^ | - +1 ^ ^ a - +4 ^ ^ c - +2 ^ ^ b - +3 ^ ^ | -+12 ^ ^ - +1 ^ ^ a - +4 ^ ^ c - 0: ababab - abcdabcd ---->abcdabcd - +0 ^ (ab|cd){3,4} - +1 ^ a - +4 ^ c - +2 ^^ b - +3 ^ ^ | - +1 ^ ^ a - +4 ^ ^ c - +5 ^ ^ d - +6 ^ ^ ) - +1 ^ ^ a - +4 ^ ^ c - +2 ^ ^ b - +3 ^ ^ | -+12 ^ ^ - +1 ^ ^ a - +4 ^ ^ c - +5 ^ ^ d - +6 ^ ^ ) -+12 ^ ^ - 0: abcdabcd - 1: abcdab - abcdcdcdcdcd ---->abcdcdcdcdcd - +0 ^ (ab|cd){3,4} - +1 ^ a - +4 ^ c - +2 ^^ b - +3 ^ ^ | - +1 ^ ^ a - +4 ^ ^ c - +5 ^ ^ d - +6 ^ ^ ) - +1 ^ ^ a - +4 ^ ^ c - +5 ^ ^ d - +6 ^ ^ ) -+12 ^ ^ - +1 ^ ^ a - +4 ^ ^ c - +5 ^ ^ d - +6 ^ ^ ) -+12 ^ ^ - 0: abcdcdcd - 1: abcdcd - -/^abc/ - abcdef - 0: abc - *** Failers -No match - abcdef\B -No match - -/^(a*|xyz)/ - bcd - 0: - aaabcd - 0: aaa - 1: aa - 2: a - 3: - xyz - 0: xyz - 1: - xyz\N - 0: xyz - *** Failers - 0: - bcd\N -No match - -/xyz$/ - xyz - 0: xyz - xyz\n - 0: xyz - *** Failers -No match - xyz\Z -No match - xyz\n\Z -No match - -/xyz$/m - xyz - 0: xyz - xyz\n - 0: xyz - abcxyz\npqr - 0: xyz - abcxyz\npqr\Z - 0: xyz - xyz\n\Z - 0: xyz - *** Failers -No match - xyz\Z -No match - -/\Gabc/ - abcdef - 0: abc - defabcxyz\>3 - 0: abc - *** Failers -No match - defabcxyz -No match - -/^abcdef/ - ab\P -Partial match: ab - abcde\P -Partial match: abcde - abcdef\P - 0: abcdef - *** Failers -No match - abx\P -No match - -/^a{2,4}\d+z/ - a\P -Partial match: a - aa\P -Partial match: aa - aa2\P -Partial match: aa2 - aaa\P -Partial match: aaa - aaa23\P -Partial match: aaa23 - aaaa12345\P -Partial match: aaaa12345 - aa0z\P - 0: aa0z - aaaa4444444444444z\P - 0: aaaa4444444444444z - *** Failers -No match - az\P -No match - aaaaa\P -No match - a56\P -No match - -/^abcdef/ - abc\P -Partial match: abc - def\R - 0: def - -/(?<=foo)bar/ - xyzfo\P -No match - foob\P\>2 -Partial match: b - foobar...\R\P\>4 - 0: ar - xyzfo\P -No match - foobar\>2 - 0: bar - *** Failers -No match - xyzfo\P -No match - obar\R -No match - -/(ab*(cd|ef))+X/ - adfadadaklhlkalkajhlkjahdfasdfasdfladsfjkj\P\Z -No match - lkjhlkjhlkjhlkjhabbbbbbcdaefabbbbbbbefa\P\B\Z -Partial match: abbbbbbcdaefabbbbbbbefa - cdabbbbbbbb\P\R\B\Z -Partial match: cdabbbbbbbb - efabbbbbbbbbbbbbbbb\P\R\B\Z -Partial match: efabbbbbbbbbbbbbbbb - bbbbbbbbbbbbcdXyasdfadf\P\R\B\Z - 0: bbbbbbbbbbbbcdX - -/(a|b)/SF>testsavedregex -Compiled regex written to testsavedregex -Study data written to testsavedregex ->>aaabxyzpqrrrabbxyyyypqAzz - 0: aaabxyzpqrrrabbxyyyypqAzz - >aaaabxyzpqrrrabbxyyyypqAzz - 0: aaaabxyzpqrrrabbxyyyypqAzz - >>>>abcxyzpqrrrabbxyyyypqAzz - 0: abcxyzpqrrrabbxyyyypqAzz - *** Failers -No match - abxyzpqrrabbxyyyypqAzz -No match - abxyzpqrrrrabbxyyyypqAzz -No match - abxyzpqrrrabxyyyypqAzz -No match - aaaabcxyzzzzpqrrrabbbxyyyyyypqAzz -No match - aaaabcxyzzzzpqrrrabbbxyyypqAzz -No match - aaabcxyzpqrrrabbxyyyypqqqqqqqAzz -No match - -/^(abc){1,2}zz/ - abczz - 0: abczz - abcabczz - 0: abcabczz - *** Failers -No match - zz -No match - abcabcabczz -No match - >>abczz -No match - -/^(b+?|a){1,2}?c/ - bc - 0: bc - bbc - 0: bbc - bbbc - 0: bbbc - bac - 0: bac - bbac - 0: bbac - aac - 0: aac - abbbbbbbbbbbc - 0: abbbbbbbbbbbc - bbbbbbbbbbbac - 0: bbbbbbbbbbbac - *** Failers -No match - aaac -No match - abbbbbbbbbbbac -No match - -/^(b+|a){1,2}c/ - bc - 0: bc - bbc - 0: bbc - bbbc - 0: bbbc - bac - 0: bac - bbac - 0: bbac - aac - 0: aac - abbbbbbbbbbbc - 0: abbbbbbbbbbbc - bbbbbbbbbbbac - 0: bbbbbbbbbbbac - *** Failers -No match - aaac -No match - abbbbbbbbbbbac -No match - -/^(b+|a){1,2}?bc/ - bbc - 0: bbc - -/^(b*|ba){1,2}?bc/ - babc - 0: babc - bbabc - 0: bbabc - bababc - 0: bababc - *** Failers -No match - bababbc -No match - babababc -No match - -/^(ba|b*){1,2}?bc/ - babc - 0: babc - bbabc - 0: bbabc - bababc - 0: bababc - *** Failers -No match - bababbc -No match - babababc -No match - -/^\ca\cA\c[\c{\c:/ - \x01\x01\e;z - 0: \x01\x01\x1b;z - -/^[ab\]cde]/ - athing - 0: a - bthing - 0: b - ]thing - 0: ] - cthing - 0: c - dthing - 0: d - ething - 0: e - *** Failers -No match - fthing -No match - [thing -No match - \\thing -No match - -/^[]cde]/ - ]thing - 0: ] - cthing - 0: c - dthing - 0: d - ething - 0: e - *** Failers -No match - athing -No match - fthing -No match - -/^[^ab\]cde]/ - fthing - 0: f - [thing - 0: [ - \\thing - 0: \ - *** Failers - 0: * - athing -No match - bthing -No match - ]thing -No match - cthing -No match - dthing -No match - ething -No match - -/^[^]cde]/ - athing - 0: a - fthing - 0: f - *** Failers - 0: * - ]thing -No match - cthing -No match - dthing -No match - ething -No match - -/^\/ - - 0: \x81 - -/^ÿ/ - ÿ - 0: \xff - -/^[0-9]+$/ - 0 - 0: 0 - 1 - 0: 1 - 2 - 0: 2 - 3 - 0: 3 - 4 - 0: 4 - 5 - 0: 5 - 6 - 0: 6 - 7 - 0: 7 - 8 - 0: 8 - 9 - 0: 9 - 10 - 0: 10 - 100 - 0: 100 - *** Failers -No match - abc -No match - -/^.*nter/ - enter - 0: enter - inter - 0: inter - uponter - 0: uponter - -/^xxx[0-9]+$/ - xxx0 - 0: xxx0 - xxx1234 - 0: xxx1234 - *** Failers -No match - xxx -No match - -/^.+[0-9][0-9][0-9]$/ - x123 - 0: x123 - xx123 - 0: xx123 - 123456 - 0: 123456 - *** Failers -No match - 123 -No match - x1234 - 0: x1234 - -/^.+?[0-9][0-9][0-9]$/ - x123 - 0: x123 - xx123 - 0: xx123 - 123456 - 0: 123456 - *** Failers -No match - 123 -No match - x1234 - 0: x1234 - -/^([^!]+)!(.+)=apquxz\.ixr\.zzz\.ac\.uk$/ - abc!pqr=apquxz.ixr.zzz.ac.uk - 0: abc!pqr=apquxz.ixr.zzz.ac.uk - *** Failers -No match - !pqr=apquxz.ixr.zzz.ac.uk -No match - abc!=apquxz.ixr.zzz.ac.uk -No match - abc!pqr=apquxz:ixr.zzz.ac.uk -No match - abc!pqr=apquxz.ixr.zzz.ac.ukk -No match - -/:/ - Well, we need a colon: somewhere - 0: : - *** Fail if we don't -No match - -/([\da-f:]+)$/i - 0abc - 0: 0abc - abc - 0: abc - fed - 0: fed - E - 0: E - :: - 0: :: - 5f03:12C0::932e - 0: 5f03:12C0::932e - fed def - 0: def - Any old stuff - 0: ff - *** Failers -No match - 0zzz -No match - gzzz -No match - fed\x20 -No match - Any old rubbish -No match - -/^.*\.(\d{1,3})\.(\d{1,3})\.(\d{1,3})$/ - .1.2.3 - 0: .1.2.3 - A.12.123.0 - 0: A.12.123.0 - *** Failers -No match - .1.2.3333 -No match - 1.2.3 -No match - 1234.2.3 -No match - -/^(\d+)\s+IN\s+SOA\s+(\S+)\s+(\S+)\s*\(\s*$/ - 1 IN SOA non-sp1 non-sp2( - 0: 1 IN SOA non-sp1 non-sp2( - 1 IN SOA non-sp1 non-sp2 ( - 0: 1 IN SOA non-sp1 non-sp2 ( - *** Failers -No match - 1IN SOA non-sp1 non-sp2( -No match - -/^[a-zA-Z\d][a-zA-Z\d\-]*(\.[a-zA-Z\d][a-zA-z\d\-]*)*\.$/ - a. - 0: a. - Z. - 0: Z. - 2. - 0: 2. - ab-c.pq-r. - 0: ab-c.pq-r. - sxk.zzz.ac.uk. - 0: sxk.zzz.ac.uk. - x-.y-. - 0: x-.y-. - *** Failers -No match - -abc.peq. -No match - -/^\*\.[a-z]([a-z\-\d]*[a-z\d]+)?(\.[a-z]([a-z\-\d]*[a-z\d]+)?)*$/ - *.a - 0: *.a - *.b0-a - 0: *.b0-a - *.c3-b.c - 0: *.c3-b.c - *.c-a.b-c - 0: *.c-a.b-c - *** Failers -No match - *.0 -No match - *.a- -No match - *.a-b.c- -No match - *.c-a.0-c -No match - -/^(?=ab(de))(abd)(e)/ - abde - 0: abde - -/^(?!(ab)de|x)(abd)(f)/ - abdf - 0: abdf - -/^(?=(ab(cd)))(ab)/ - abcd - 0: ab - -/^[\da-f](\.[\da-f])*$/i - a.b.c.d - 0: a.b.c.d - A.B.C.D - 0: A.B.C.D - a.b.c.1.2.3.C - 0: a.b.c.1.2.3.C - -/^\".*\"\s*(;.*)?$/ - \"1234\" - 0: "1234" - \"abcd\" ; - 0: "abcd" ; - \"\" ; rhubarb - 0: "" ; rhubarb - *** Failers -No match - \"1234\" : things -No match - -/^$/ - \ - 0: - *** Failers -No match - -/ ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/x - ab c - 0: ab c - *** Failers -No match - abc -No match - ab cde -No match - -/(?x) ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/ - ab c - 0: ab c - *** Failers -No match - abc -No match - ab cde -No match - -/^ a\ b[c ]d $/x - a bcd - 0: a bcd - a b d - 0: a b d - *** Failers -No match - abcd -No match - ab d -No match - -/^(a(b(c)))(d(e(f)))(h(i(j)))(k(l(m)))$/ - abcdefhijklm - 0: abcdefhijklm - -/^(?:a(b(c)))(?:d(e(f)))(?:h(i(j)))(?:k(l(m)))$/ - abcdefhijklm - 0: abcdefhijklm - -/^[\w][\W][\s][\S][\d][\D][\b][\n][\c]][\022]/ - a+ Z0+\x08\n\x1d\x12 - 0: a+ Z0+\x08\x0a\x1d\x12 - -/^[.^$|()*+?{,}]+/ - .^\$(*+)|{?,?} - 0: .^$(*+)|{?,?} - 1: .^$(*+)|{?,? - 2: .^$(*+)|{?, - 3: .^$(*+)|{? - 4: .^$(*+)|{ - 5: .^$(*+)| - 6: .^$(*+) - 7: .^$(*+ - 8: .^$(* - 9: .^$( -10: .^$ -11: .^ -12: . - -/^a*\w/ - z - 0: z - az - 0: az - 1: a - aaaz - 0: aaaz - 1: aaa - 2: aa - 3: a - a - 0: a - aa - 0: aa - 1: a - aaaa - 0: aaaa - 1: aaa - 2: aa - 3: a - a+ - 0: a - aa+ - 0: aa - 1: a - -/^a*?\w/ - z - 0: z - az - 0: az - 1: a - aaaz - 0: aaaz - 1: aaa - 2: aa - 3: a - a - 0: a - aa - 0: aa - 1: a - aaaa - 0: aaaa - 1: aaa - 2: aa - 3: a - a+ - 0: a - aa+ - 0: aa - 1: a - -/^a+\w/ - az - 0: az - aaaz - 0: aaaz - 1: aaa - 2: aa - aa - 0: aa - aaaa - 0: aaaa - 1: aaa - 2: aa - aa+ - 0: aa - -/^a+?\w/ - az - 0: az - aaaz - 0: aaaz - 1: aaa - 2: aa - aa - 0: aa - aaaa - 0: aaaa - 1: aaa - 2: aa - aa+ - 0: aa - -/^\d{8}\w{2,}/ - 1234567890 - 0: 1234567890 - 12345678ab - 0: 12345678ab - 12345678__ - 0: 12345678__ - *** Failers -No match - 1234567 -No match - -/^[aeiou\d]{4,5}$/ - uoie - 0: uoie - 1234 - 0: 1234 - 12345 - 0: 12345 - aaaaa - 0: aaaaa - *** Failers -No match - 123456 -No match - -/^[aeiou\d]{4,5}?/ - uoie - 0: uoie - 1234 - 0: 1234 - 12345 - 0: 12345 - 1: 1234 - aaaaa - 0: aaaaa - 1: aaaa - 123456 - 0: 12345 - 1: 1234 - -/^From +([^ ]+) +[a-zA-Z][a-zA-Z][a-zA-Z] +[a-zA-Z][a-zA-Z][a-zA-Z] +[0-9]?[0-9] +[0-9][0-9]:[0-9][0-9]/ - From abcd Mon Sep 01 12:33:02 1997 - 0: From abcd Mon Sep 01 12:33 - -/^From\s+\S+\s+([a-zA-Z]{3}\s+){2}\d{1,2}\s+\d\d:\d\d/ - From abcd Mon Sep 01 12:33:02 1997 - 0: From abcd Mon Sep 01 12:33 - From abcd Mon Sep 1 12:33:02 1997 - 0: From abcd Mon Sep 1 12:33 - *** Failers -No match - From abcd Sep 01 12:33:02 1997 -No match - -/^12.34/s - 12\n34 - 0: 12\x0a34 - 12\r34 - 0: 12\x0d34 - -/\w+(?=\t)/ - the quick brown\t fox - 0: brown - -/foo(?!bar)(.*)/ - foobar is foolish see? - 0: foolish see? - 1: foolish see - 2: foolish se - 3: foolish s - 4: foolish - 5: foolish - 6: foolis - 7: fooli - 8: fool - 9: foo - -/(?:(?!foo)...|^.{0,2})bar(.*)/ - foobar crowbar etc - 0: rowbar etc - 1: rowbar et - 2: rowbar e - 3: rowbar - 4: rowbar - barrel - 0: barrel - 1: barre - 2: barr - 3: bar - 2barrel - 0: 2barrel - 1: 2barre - 2: 2barr - 3: 2bar - A barrel - 0: A barrel - 1: A barre - 2: A barr - 3: A bar - -/^(\D*)(?=\d)(?!123)/ - abc456 - 0: abc - *** Failers -No match - abc123 -No match - -/^1234(?# test newlines - inside)/ - 1234 - 0: 1234 - -/^1234 #comment in extended re - /x - 1234 - 0: 1234 - -/#rhubarb - abcd/x - abcd - 0: abcd - -/^abcd#rhubarb/x - abcd - 0: abcd - -/(?!^)abc/ - the abc - 0: abc - *** Failers -No match - abc -No match - -/(?=^)abc/ - abc - 0: abc - *** Failers -No match - the abc -No match - -/^[ab]{1,3}(ab*|b)/ - aabbbbb - 0: aabbbbb - 1: aabbbb - 2: aabbb - 3: aabb - 4: aab - 5: aa - -/^[ab]{1,3}?(ab*|b)/ - aabbbbb - 0: aabbbbb - 1: aabbbb - 2: aabbb - 3: aabb - 4: aab - 5: aa - -/^[ab]{1,3}?(ab*?|b)/ - aabbbbb - 0: aabbbbb - 1: aabbbb - 2: aabbb - 3: aabb - 4: aab - 5: aa - -/^[ab]{1,3}(ab*?|b)/ - aabbbbb - 0: aabbbbb - 1: aabbbb - 2: aabbb - 3: aabb - 4: aab - 5: aa - -/ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* # optional leading comment -(?: (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) # initial word -(?: (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) )* # further okay, if led by a period -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* -# address -| # or -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) # one word, optionally followed by.... -(?: -[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] | # atom and space parts, or... -\( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) | # comments, or... - -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -# quoted strings -)* -< (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* # leading < -(?: @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* - -(?: (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* , (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* -)* # further okay, if led by comma -: # closing colon -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* )? # optional route -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) # initial word -(?: (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) )* # further okay, if led by a period -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* -# address spec -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* > # trailing > -# name and address -) (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* # optional trailing comment -/x - Alan Other - 0: Alan Other - - 0: user@dom.ain - 1: user@dom - user\@dom.ain - 0: user@dom.ain - 1: user@dom - \"A. Other\" (a comment) - 0: "A. Other" (a comment) - 1: "A. Other" - 2: "A. Other" - A. Other (a comment) - 0: Other (a comment) - 1: Other - 2: Other - \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay - 0: "/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/"@x400-re.lay - 1: "/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/"@x400-re - A missing angle @,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# additional words -)* -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -# address -| # or -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -# leading word -[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] * # "normal" atoms and or spaces -(?: -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -| -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -) # "special" comment or quoted string -[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] * # more "normal" -)* -< -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# < -(?: -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -(?: , -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -)* # additional domains -: -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)? # optional route -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# additional words -)* -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -# address spec -> # > -# name and address -) -/x - Alan Other - 0: Alan Other - - 0: user@dom.ain - 1: user@dom - user\@dom.ain - 0: user@dom.ain - 1: user@dom - \"A. Other\" (a comment) - 0: "A. Other" - A. Other (a comment) - 0: Other - \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay - 0: "/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/"@x400-re.lay - 1: "/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/"@x400-re - A missing angle - a\rb - 0: a\x0db - *** Failers -No match - a\nb -No match - -/abc$/ - abc - 0: abc - abc\n - 0: abc - *** Failers -No match - abc\ndef -No match - -/(abc)\123/ - abc\x53 - 0: abcS - -/(abc)\223/ - abc\x93 - 0: abc\x93 - -/(abc)\323/ - abc\xd3 - 0: abc\xd3 - -/(abc)\100/ - abc\x40 - 0: abc@ - abc\100 - 0: abc@ - -/(abc)\1000/ - abc\x400 - 0: abc@0 - abc\x40\x30 - 0: abc@0 - abc\1000 - 0: abc@0 - abc\100\x30 - 0: abc@0 - abc\100\060 - 0: abc@0 - abc\100\60 - 0: abc@0 - -/abc\81/ - abc\081 - 0: abc\x0081 - abc\0\x38\x31 - 0: abc\x0081 - -/abc\91/ - abc\091 - 0: abc\x0091 - abc\0\x39\x31 - 0: abc\x0091 - -/(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)\12\123/ - abcdefghijk\12S - 0: abcdefghijk\x0aS - -/ab\idef/ - abidef - 0: abidef - -/a{0}bc/ - bc - 0: bc - -/(a|(bc)){0,0}?xyz/ - xyz - 0: xyz - -/abc[\10]de/ - abc\010de - 0: abc\x08de - -/abc[\1]de/ - abc\1de - 0: abc\x01de - -/(abc)[\1]de/ - abc\1de - 0: abc\x01de - -/(?s)a.b/ - a\nb - 0: a\x0ab - -/^([^a])([^\b])([^c]*)([^d]{3,4})/ - baNOTccccd - 0: baNOTcccc - 1: baNOTccc - 2: baNOTcc - 3: baNOTc - 4: baNOT - baNOTcccd - 0: baNOTccc - 1: baNOTcc - 2: baNOTc - 3: baNOT - baNOTccd - 0: baNOTcc - 1: baNOTc - 2: baNOT - bacccd - 0: baccc - *** Failers - 0: *** Failers - 1: *** Failer - 2: *** Faile - 3: *** Fail - 4: *** Fai - 5: *** Fa - 6: *** F - anything -No match - b\bc -No match - baccd -No match - -/[^a]/ - Abc - 0: A - -/[^a]/i - Abc - 0: b - -/[^a]+/ - AAAaAbc - 0: AAA - 1: AA - 2: A - -/[^a]+/i - AAAaAbc - 0: bc - 1: b - -/[^a]+/ - bbb\nccc - 0: bbb\x0accc - 1: bbb\x0acc - 2: bbb\x0ac - 3: bbb\x0a - 4: bbb - 5: bb - 6: b - -/[^k]$/ - abc - 0: c - *** Failers - 0: s - abk -No match - -/[^k]{2,3}$/ - abc - 0: abc - kbc - 0: bc - kabc - 0: abc - *** Failers - 0: ers - abk -No match - akb -No match - akk -No match - -/^\d{8,}\@.+[^k]$/ - 12345678\@a.b.c.d - 0: 12345678@a.b.c.d - 123456789\@x.y.z - 0: 123456789@x.y.z - *** Failers -No match - 12345678\@x.y.uk -No match - 1234567\@a.b.c.d -No match - -/[^a]/ - aaaabcd - 0: b - aaAabcd - 0: A - -/[^a]/i - aaaabcd - 0: b - aaAabcd - 0: b - -/[^az]/ - aaaabcd - 0: b - aaAabcd - 0: A - -/[^az]/i - aaaabcd - 0: b - aaAabcd - 0: b - -/\000\001\002\003\004\005\006\007\010\011\012\013\014\015\016\017\020\021\022\023\024\025\026\027\030\031\032\033\034\035\036\037\040\041\042\043\044\045\046\047\050\051\052\053\054\055\056\057\060\061\062\063\064\065\066\067\070\071\072\073\074\075\076\077\100\101\102\103\104\105\106\107\110\111\112\113\114\115\116\117\120\121\122\123\124\125\126\127\130\131\132\133\134\135\136\137\140\141\142\143\144\145\146\147\150\151\152\153\154\155\156\157\160\161\162\163\164\165\166\167\170\171\172\173\174\175\176\177\200\201\202\203\204\205\206\207\210\211\212\213\214\215\216\217\220\221\222\223\224\225\226\227\230\231\232\233\234\235\236\237\240\241\242\243\244\245\246\247\250\251\252\253\254\255\256\257\260\261\262\263\264\265\266\267\270\271\272\273\274\275\276\277\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337\340\341\342\343\344\345\346\347\350\351\352\353\354\355\356\357\360\361\362\363\364\365\366\367\370\371\372\373\374\375\376\377/ - \000\001\002\003\004\005\006\007\010\011\012\013\014\015\016\017\020\021\022\023\024\025\026\027\030\031\032\033\034\035\036\037\040\041\042\043\044\045\046\047\050\051\052\053\054\055\056\057\060\061\062\063\064\065\066\067\070\071\072\073\074\075\076\077\100\101\102\103\104\105\106\107\110\111\112\113\114\115\116\117\120\121\122\123\124\125\126\127\130\131\132\133\134\135\136\137\140\141\142\143\144\145\146\147\150\151\152\153\154\155\156\157\160\161\162\163\164\165\166\167\170\171\172\173\174\175\176\177\200\201\202\203\204\205\206\207\210\211\212\213\214\215\216\217\220\221\222\223\224\225\226\227\230\231\232\233\234\235\236\237\240\241\242\243\244\245\246\247\250\251\252\253\254\255\256\257\260\261\262\263\264\265\266\267\270\271\272\273\274\275\276\277\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337\340\341\342\343\344\345\346\347\350\351\352\353\354\355\356\357\360\361\362\363\364\365\366\367\370\371\372\373\374\375\376\377 - 0: \x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f !"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x7f\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff - -/P[^*]TAIRE[^*]{1,6}?LL/ - xxxxxxxxxxxPSTAIREISLLxxxxxxxxx - 0: PSTAIREISLL - -/P[^*]TAIRE[^*]{1,}?LL/ - xxxxxxxxxxxPSTAIREISLLxxxxxxxxx - 0: PSTAIREISLL - -/(\.\d\d[1-9]?)\d+/ - 1.230003938 - 0: .230003938 - 1: .23000393 - 2: .2300039 - 3: .230003 - 4: .23000 - 5: .2300 - 6: .230 - 1.875000282 - 0: .875000282 - 1: .87500028 - 2: .8750002 - 3: .875000 - 4: .87500 - 5: .8750 - 6: .875 - 1.235 - 0: .235 - -/(\.\d\d((?=0)|\d(?=\d)))/ - 1.230003938 - 0: .230 - 1: .23 - 1.875000282 - 0: .875 - *** Failers -No match - 1.235 -No match - -/a(?)b/ - ab - 0: ab - -/\b(foo)\s+(\w+)/i - Food is on the foo table - 0: foo table - 1: foo tabl - 2: foo tab - 3: foo ta - 4: foo t - -/foo(.*)bar/ - The food is under the bar in the barn. - 0: food is under the bar in the bar - 1: food is under the bar - -/foo(.*?)bar/ - The food is under the bar in the barn. - 0: food is under the bar in the bar - 1: food is under the bar - -/(.*)(\d*)/ - I have 2 numbers: 53147 -Matched, but too many subsidiary matches - 0: I have 2 numbers: 53147 - 1: I have 2 numbers: 5314 - 2: I have 2 numbers: 531 - 3: I have 2 numbers: 53 - 4: I have 2 numbers: 5 - 5: I have 2 numbers: - 6: I have 2 numbers: - 7: I have 2 numbers - 8: I have 2 number - 9: I have 2 numbe -10: I have 2 numb -11: I have 2 num -12: I have 2 nu -13: I have 2 n -14: I have 2 -15: I have 2 -16: I have -17: I have -18: I hav -19: I ha -20: I h -21: I - -/(.*)(\d+)/ - I have 2 numbers: 53147 - 0: I have 2 numbers: 53147 - 1: I have 2 numbers: 5314 - 2: I have 2 numbers: 531 - 3: I have 2 numbers: 53 - 4: I have 2 numbers: 5 - 5: I have 2 - -/(.*?)(\d*)/ - I have 2 numbers: 53147 -Matched, but too many subsidiary matches - 0: I have 2 numbers: 53147 - 1: I have 2 numbers: 5314 - 2: I have 2 numbers: 531 - 3: I have 2 numbers: 53 - 4: I have 2 numbers: 5 - 5: I have 2 numbers: - 6: I have 2 numbers: - 7: I have 2 numbers - 8: I have 2 number - 9: I have 2 numbe -10: I have 2 numb -11: I have 2 num -12: I have 2 nu -13: I have 2 n -14: I have 2 -15: I have 2 -16: I have -17: I have -18: I hav -19: I ha -20: I h -21: I - -/(.*?)(\d+)/ - I have 2 numbers: 53147 - 0: I have 2 numbers: 53147 - 1: I have 2 numbers: 5314 - 2: I have 2 numbers: 531 - 3: I have 2 numbers: 53 - 4: I have 2 numbers: 5 - 5: I have 2 - -/(.*)(\d+)$/ - I have 2 numbers: 53147 - 0: I have 2 numbers: 53147 - -/(.*?)(\d+)$/ - I have 2 numbers: 53147 - 0: I have 2 numbers: 53147 - -/(.*)\b(\d+)$/ - I have 2 numbers: 53147 - 0: I have 2 numbers: 53147 - -/(.*\D)(\d+)$/ - I have 2 numbers: 53147 - 0: I have 2 numbers: 53147 - -/^\D*(?!123)/ - ABC123 - 0: AB - 1: A - 2: - -/^(\D*)(?=\d)(?!123)/ - ABC445 - 0: ABC - *** Failers -No match - ABC123 -No match - -/^[W-]46]/ - W46]789 - 0: W46] - -46]789 - 0: -46] - *** Failers -No match - Wall -No match - Zebra -No match - 42 -No match - [abcd] -No match - ]abcd[ -No match - -/^[W-\]46]/ - W46]789 - 0: W - Wall - 0: W - Zebra - 0: Z - Xylophone - 0: X - 42 - 0: 4 - [abcd] - 0: [ - ]abcd[ - 0: ] - \\backslash - 0: \ - *** Failers -No match - -46]789 -No match - well -No match - -/\d\d\/\d\d\/\d\d\d\d/ - 01/01/2000 - 0: 01/01/2000 - -/word (?:[a-zA-Z0-9]+ ){0,10}otherword/ - word cat dog elephant mussel cow horse canary baboon snake shark otherword - 0: word cat dog elephant mussel cow horse canary baboon snake shark otherword - word cat dog elephant mussel cow horse canary baboon snake shark -No match - -/word (?:[a-zA-Z0-9]+ ){0,300}otherword/ - word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope -No match - -/^(a){0,0}/ - bcd - 0: - abc - 0: - aab - 0: - -/^(a){0,1}/ - bcd - 0: - abc - 0: a - 1: - aab - 0: a - 1: - -/^(a){0,2}/ - bcd - 0: - abc - 0: a - 1: - aab - 0: aa - 1: a - 2: - -/^(a){0,3}/ - bcd - 0: - abc - 0: a - 1: - aab - 0: aa - 1: a - 2: - aaa - 0: aaa - 1: aa - 2: a - 3: - -/^(a){0,}/ - bcd - 0: - abc - 0: a - 1: - aab - 0: aa - 1: a - 2: - aaa - 0: aaa - 1: aa - 2: a - 3: - aaaaaaaa - 0: aaaaaaaa - 1: aaaaaaa - 2: aaaaaa - 3: aaaaa - 4: aaaa - 5: aaa - 6: aa - 7: a - 8: - -/^(a){1,1}/ - bcd -No match - abc - 0: a - aab - 0: a - -/^(a){1,2}/ - bcd -No match - abc - 0: a - aab - 0: aa - 1: a - -/^(a){1,3}/ - bcd -No match - abc - 0: a - aab - 0: aa - 1: a - aaa - 0: aaa - 1: aa - 2: a - -/^(a){1,}/ - bcd -No match - abc - 0: a - aab - 0: aa - 1: a - aaa - 0: aaa - 1: aa - 2: a - aaaaaaaa - 0: aaaaaaaa - 1: aaaaaaa - 2: aaaaaa - 3: aaaaa - 4: aaaa - 5: aaa - 6: aa - 7: a - -/.*\.gif/ - borfle\nbib.gif\nno - 0: bib.gif - -/.{0,}\.gif/ - borfle\nbib.gif\nno - 0: bib.gif - -/.*\.gif/m - borfle\nbib.gif\nno - 0: bib.gif - -/.*\.gif/s - borfle\nbib.gif\nno - 0: borfle\x0abib.gif - -/.*\.gif/ms - borfle\nbib.gif\nno - 0: borfle\x0abib.gif - -/.*$/ - borfle\nbib.gif\nno - 0: no - -/.*$/m - borfle\nbib.gif\nno - 0: borfle - -/.*$/s - borfle\nbib.gif\nno - 0: borfle\x0abib.gif\x0ano - -/.*$/ms - borfle\nbib.gif\nno - 0: borfle\x0abib.gif\x0ano - 1: borfle\x0abib.gif - 2: borfle - -/.*$/ - borfle\nbib.gif\nno\n - 0: no - -/.*$/m - borfle\nbib.gif\nno\n - 0: borfle - -/.*$/s - borfle\nbib.gif\nno\n - 0: borfle\x0abib.gif\x0ano\x0a - 1: borfle\x0abib.gif\x0ano - -/.*$/ms - borfle\nbib.gif\nno\n - 0: borfle\x0abib.gif\x0ano\x0a - 1: borfle\x0abib.gif\x0ano - 2: borfle\x0abib.gif - 3: borfle - -/(.*X|^B)/ - abcde\n1234Xyz - 0: 1234X - BarFoo - 0: B - *** Failers -No match - abcde\nBar -No match - -/(.*X|^B)/m - abcde\n1234Xyz - 0: 1234X - BarFoo - 0: B - abcde\nBar - 0: B - -/(.*X|^B)/s - abcde\n1234Xyz - 0: abcde\x0a1234X - BarFoo - 0: B - *** Failers -No match - abcde\nBar -No match - -/(.*X|^B)/ms - abcde\n1234Xyz - 0: abcde\x0a1234X - BarFoo - 0: B - abcde\nBar - 0: B - -/(?s)(.*X|^B)/ - abcde\n1234Xyz - 0: abcde\x0a1234X - BarFoo - 0: B - *** Failers -No match - abcde\nBar -No match - -/(?s:.*X|^B)/ - abcde\n1234Xyz - 0: abcde\x0a1234X - BarFoo - 0: B - *** Failers -No match - abcde\nBar -No match - -/^.*B/ - **** Failers -No match - abc\nB -No match - -/(?s)^.*B/ - abc\nB - 0: abc\x0aB - -/(?m)^.*B/ - abc\nB - 0: B - -/(?ms)^.*B/ - abc\nB - 0: abc\x0aB - -/(?ms)^B/ - abc\nB - 0: B - -/(?s)B$/ - B\n - 0: B - -/^[0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9]/ - 123456654321 - 0: 123456654321 - -/^\d\d\d\d\d\d\d\d\d\d\d\d/ - 123456654321 - 0: 123456654321 - -/^[\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d]/ - 123456654321 - 0: 123456654321 - -/^[abc]{12}/ - abcabcabcabc - 0: abcabcabcabc - -/^[a-c]{12}/ - abcabcabcabc - 0: abcabcabcabc - -/^(a|b|c){12}/ - abcabcabcabc - 0: abcabcabcabc - -/^[abcdefghijklmnopqrstuvwxy0123456789]/ - n - 0: n - *** Failers -No match - z -No match - -/abcde{0,0}/ - abcd - 0: abcd - *** Failers -No match - abce -No match - -/ab[cd]{0,0}e/ - abe - 0: abe - *** Failers -No match - abcde -No match - -/ab(c){0,0}d/ - abd - 0: abd - *** Failers -No match - abcd -No match - -/a(b*)/ - a - 0: a - ab - 0: ab - 1: a - abbbb - 0: abbbb - 1: abbb - 2: abb - 3: ab - 4: a - *** Failers - 0: a - bbbbb -No match - -/ab\d{0}e/ - abe - 0: abe - *** Failers -No match - ab1e -No match - -/"([^\\"]+|\\.)*"/ - the \"quick\" brown fox - 0: "quick" - \"the \\\"quick\\\" brown fox\" - 0: "the \"quick\" brown fox" - -/.*?/g+ - abc - 0: abc - 0+ - 1: ab - 2: a - 3: - 0: - 0+ - -/\b/g+ - abc - 0: - 0+ abc - 0: - 0+ - -/\b/+g - abc - 0: - 0+ abc - 0: - 0+ - -//g - abc - 0: - 0: - 0: - 0: - -/]{0,})>]{0,})>([\d]{0,}\.)(.*)((
([\w\W\s\d][^<>]{0,})|[\s]{0,}))<\/a><\/TD>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><\/TR>/is - 43.Word Processor
(N-1286)Lega lstaff.comCA - Statewide - 0: 43.Word Processor
(N-1286)Lega lstaff.comCA - Statewide - -/a[^a]b/ - acb - 0: acb - a\nb - 0: a\x0ab - -/a.b/ - acb - 0: acb - *** Failers -No match - a\nb -No match - -/a[^a]b/s - acb - 0: acb - a\nb - 0: a\x0ab - -/a.b/s - acb - 0: acb - a\nb - 0: a\x0ab - -/^(b+?|a){1,2}?c/ - bac - 0: bac - bbac - 0: bbac - bbbac - 0: bbbac - bbbbac - 0: bbbbac - bbbbbac - 0: bbbbbac - -/^(b+|a){1,2}?c/ - bac - 0: bac - bbac - 0: bbac - bbbac - 0: bbbac - bbbbac - 0: bbbbac - bbbbbac - 0: bbbbbac - -/(?!\A)x/m - x\nb\n -No match - a\bx\n - 0: x - -/\x0{ab}/ - \0{ab} - 0: \x00{ab} - -/(A|B)*?CD/ - CD - 0: CD - -/(A|B)*CD/ - CD - 0: CD - -/(?.*/)foo" - /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/it/you/see/ -No match - -"(?>.*/)foo" - /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo - 0: /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo - -/(?>(\.\d\d[1-9]?))\d+/ - 1.230003938 - 0: .230003938 - 1: .23000393 - 2: .2300039 - 3: .230003 - 4: .23000 - 5: .2300 - 6: .230 - 1.875000282 - 0: .875000282 - 1: .87500028 - 2: .8750002 - 3: .875000 - 4: .87500 - 5: .8750 - *** Failers -No match - 1.235 -No match - -/^((?>\w+)|(?>\s+))*$/ - now is the time for all good men to come to the aid of the party - 0: now is the time for all good men to come to the aid of the party - *** Failers -No match - this is not a line with only words and spaces! -No match - -/(\d+)(\w)/ - 12345a - 0: 12345a - 1: 12345 - 2: 1234 - 3: 123 - 4: 12 - 12345+ - 0: 12345 - 1: 1234 - 2: 123 - 3: 12 - -/((?>\d+))(\w)/ - 12345a - 0: 12345a - *** Failers -No match - 12345+ -No match - -/(?>a+)b/ - aaab - 0: aaab - -/((?>a+)b)/ - aaab - 0: aaab - -/(?>(a+))b/ - aaab - 0: aaab - -/(?>b)+/ - aaabbbccc - 0: bbb - 1: bb - 2: b - -/(?>a+|b+|c+)*c/ - aaabbbbccccd - 0: aaabbbbcccc - 1: aaabbbbc - -/(a+|b+|c+)*c/ - aaabbbbccccd - 0: aaabbbbcccc - 1: aaabbbbccc - 2: aaabbbbcc - 3: aaabbbbc - -/((?>[^()]+)|\([^()]*\))+/ - ((abc(ade)ufh()()x - 0: abc(ade)ufh()()x - 1: abc(ade)ufh()() - 2: abc(ade)ufh() - 3: abc(ade)ufh - 4: abc(ade) - 5: abc - -/\(((?>[^()]+)|\([^()]+\))+\)/ - (abc) - 0: (abc) - (abc(def)xyz) - 0: (abc(def)xyz) - *** Failers -No match - ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -No match - -/a(?-i)b/i - ab - 0: ab - Ab - 0: Ab - *** Failers -No match - aB -No match - AB -No match - -/(a (?x)b c)d e/ - a bcd e - 0: a bcd e - *** Failers -No match - a b cd e -No match - abcd e -No match - a bcde -No match - -/(a b(?x)c d (?-x)e f)/ - a bcde f - 0: a bcde f - *** Failers -No match - abcdef -No match - -/(a(?i)b)c/ - abc - 0: abc - aBc - 0: aBc - *** Failers -No match - abC -No match - aBC -No match - Abc -No match - ABc -No match - ABC -No match - AbC -No match - -/a(?i:b)c/ - abc - 0: abc - aBc - 0: aBc - *** Failers -No match - ABC -No match - abC -No match - aBC -No match - -/a(?i:b)*c/ - aBc - 0: aBc - aBBc - 0: aBBc - *** Failers -No match - aBC -No match - aBBC -No match - -/a(?=b(?i)c)\w\wd/ - abcd - 0: abcd - abCd - 0: abCd - *** Failers -No match - aBCd -No match - abcD -No match - -/(?s-i:more.*than).*million/i - more than million - 0: more than million - more than MILLION - 0: more than MILLION - more \n than Million - 0: more \x0a than Million - *** Failers -No match - MORE THAN MILLION -No match - more \n than \n million -No match - -/(?:(?s-i)more.*than).*million/i - more than million - 0: more than million - more than MILLION - 0: more than MILLION - more \n than Million - 0: more \x0a than Million - *** Failers -No match - MORE THAN MILLION -No match - more \n than \n million -No match - -/(?>a(?i)b+)+c/ - abc - 0: abc - aBbc - 0: aBbc - aBBc - 0: aBBc - *** Failers -No match - Abc -No match - abAb -No match - abbC -No match - -/(?=a(?i)b)\w\wc/ - abc - 0: abc - aBc - 0: aBc - *** Failers -No match - Ab -No match - abC -No match - aBC -No match - -/(?<=a(?i)b)(\w\w)c/ - abxxc - 0: xxc - aBxxc - 0: xxc - *** Failers -No match - Abxxc -No match - ABxxc -No match - abxxC -No match - -/^(?(?=abc)\w{3}:|\d\d)$/ - abc: - 0: abc: - 12 - 0: 12 - *** Failers -No match - 123 -No match - xyz -No match - -/^(?(?!abc)\d\d|\w{3}:)$/ - abc: - 0: abc: - 12 - 0: 12 - *** Failers -No match - 123 -No match - xyz -No match - -/(?(?<=foo)bar|cat)/ - foobar - 0: bar - cat - 0: cat - fcat - 0: cat - focat - 0: cat - *** Failers -No match - foocat -No match - -/(?(?a*)*/ - a - 0: a - 1: - aa - 0: aa - 1: - aaaa - 0: aaaa - 1: - -/(abc|)+/ - abc - 0: abc - 1: - abcabc - 0: abcabc - 1: abc - 2: - abcabcabc - 0: abcabcabc - 1: abcabc - 2: abc - 3: - xyz - 0: - -/([a]*)*/ - a - 0: a - 1: - aaaaa - 0: aaaaa - 1: aaaa - 2: aaa - 3: aa - 4: a - 5: - -/([ab]*)*/ - a - 0: a - 1: - b - 0: b - 1: - ababab - 0: ababab - 1: ababa - 2: abab - 3: aba - 4: ab - 5: a - 6: - aaaabcde - 0: aaaab - 1: aaaa - 2: aaa - 3: aa - 4: a - 5: - bbbb - 0: bbbb - 1: bbb - 2: bb - 3: b - 4: - -/([^a]*)*/ - b - 0: b - 1: - bbbb - 0: bbbb - 1: bbb - 2: bb - 3: b - 4: - aaa - 0: - -/([^ab]*)*/ - cccc - 0: cccc - 1: ccc - 2: cc - 3: c - 4: - abab - 0: - -/([a]*?)*/ - a - 0: a - 1: - aaaa - 0: aaaa - 1: aaa - 2: aa - 3: a - 4: - -/([ab]*?)*/ - a - 0: a - 1: - b - 0: b - 1: - abab - 0: abab - 1: aba - 2: ab - 3: a - 4: - baba - 0: baba - 1: bab - 2: ba - 3: b - 4: - -/([^a]*?)*/ - b - 0: b - 1: - bbbb - 0: bbbb - 1: bbb - 2: bb - 3: b - 4: - aaa - 0: - -/([^ab]*?)*/ - c - 0: c - 1: - cccc - 0: cccc - 1: ccc - 2: cc - 3: c - 4: - baba - 0: - -/(?>a*)*/ - a - 0: a - 1: - aaabcde - 0: aaa - 1: - -/((?>a*))*/ - aaaaa - 0: aaaaa - 1: - aabbaa - 0: aa - 1: - -/((?>a*?))*/ - aaaaa - 0: aaaaa - 1: - aabbaa - 0: aa - 1: - -/(?(?=[^a-z]+[a-z]) \d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} ) /x - 12-sep-98 - 0: 12-sep-98 - 12-09-98 - 0: 12-09-98 - *** Failers -No match - sep-12-98 -No match - -/(?i:saturday|sunday)/ - saturday - 0: saturday - sunday - 0: sunday - Saturday - 0: Saturday - Sunday - 0: Sunday - SATURDAY - 0: SATURDAY - SUNDAY - 0: SUNDAY - SunDay - 0: SunDay - -/(a(?i)bc|BB)x/ - abcx - 0: abcx - aBCx - 0: aBCx - bbx - 0: bbx - BBx - 0: BBx - *** Failers -No match - abcX -No match - aBCX -No match - bbX -No match - BBX -No match - -/^([ab](?i)[cd]|[ef])/ - ac - 0: ac - aC - 0: aC - bD - 0: bD - elephant - 0: e - Europe - 0: E - frog - 0: f - France - 0: F - *** Failers -No match - Africa -No match - -/^(ab|a(?i)[b-c](?m-i)d|x(?i)y|z)/ - ab - 0: ab - aBd - 0: aBd - xy - 0: xy - xY - 0: xY - zebra - 0: z - Zambesi - 0: Z - *** Failers -No match - aCD -No match - XY -No match - -/(?<=foo\n)^bar/m - foo\nbar - 0: bar - *** Failers -No match - bar -No match - baz\nbar -No match - -/(?<=(?]&/ - <&OUT - 0: <& - -/(?:(f)(o)(o)|(b)(a)(r))*/ - foobar - 0: foobar - 1: foo - 2: - -/(?<=a)b/ - ab - 0: b - *** Failers -No match - cb -No match - b -No match - -/(?a+)ab/ - -/(?>a+)b/ - aaab - 0: aaab - -/([[:]+)/ - a:[b]: - 0: :[ - 1: : - -/([[=]+)/ - a=[b]= - 0: =[ - 1: = - -/([[.]+)/ - a.[b]. - 0: .[ - 1: . - -/((?>a+)b)/ - aaab - 0: aaab - -/(?>(a+))b/ - aaab - 0: aaab - -/((?>[^()]+)|\([^()]*\))+/ - ((abc(ade)ufh()()x - 0: abc(ade)ufh()()x - 1: abc(ade)ufh()() - 2: abc(ade)ufh() - 3: abc(ade)ufh - 4: abc(ade) - 5: abc - -/a\Z/ - *** Failers -No match - aaab -No match - a\nb\n -No match - -/b\Z/ - a\nb\n - 0: b - -/b\z/ - -/b\Z/ - a\nb - 0: b - -/b\z/ - a\nb - 0: b - *** Failers -No match - -/(?>.*)(?<=(abcd|wxyz))/ - alphabetabcd - 0: alphabetabcd - endingwxyz - 0: endingwxyz - *** Failers -No match - a rather long string that doesn't end with one of them -No match - -/word (?>(?:(?!otherword)[a-zA-Z0-9]+ ){0,30})otherword/ - word cat dog elephant mussel cow horse canary baboon snake shark otherword - 0: word cat dog elephant mussel cow horse canary baboon snake shark otherword - word cat dog elephant mussel cow horse canary baboon snake shark -No match - -/word (?>[a-zA-Z0-9]+ ){0,30}otherword/ - word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope -No match - -/(?<=\d{3}(?!999))foo/ - 999foo - 0: foo - 123999foo - 0: foo - *** Failers -No match - 123abcfoo -No match - -/(?<=(?!...999)\d{3})foo/ - 999foo - 0: foo - 123999foo - 0: foo - *** Failers -No match - 123abcfoo -No match - -/(?<=\d{3}(?!999)...)foo/ - 123abcfoo - 0: foo - 123456foo - 0: foo - *** Failers -No match - 123999foo -No match - -/(?<=\d{3}...)(?Z)+|A)*/ - ZABCDEFG - 0: ZA - 1: Z - 2: - -/((?>)+|A)*/ - ZABCDEFG - 0: - -/a*/g - abbab - 0: a - 1: - 0: - 0: - 0: a - 1: - 0: - 0: - -/^[a-\d]/ - abcde - 0: a - -things - 0: - - 0digit - 0: 0 - *** Failers -No match - bcdef -No match - -/^[\d-a]/ - abcde - 0: a - -things - 0: - - 0digit - 0: 0 - *** Failers -No match - bcdef -No match - -/[[:space:]]+/ - > \x09\x0a\x0c\x0d\x0b< - 0: \x09\x0a\x0c\x0d\x0b - 1: \x09\x0a\x0c\x0d - 2: \x09\x0a\x0c - 3: \x09\x0a - 4: \x09 - 5: - -/[[:blank:]]+/ - > \x09\x0a\x0c\x0d\x0b< - 0: \x09 - 1: - -/[\s]+/ - > \x09\x0a\x0c\x0d\x0b< - 0: \x09\x0a\x0c\x0d - 1: \x09\x0a\x0c - 2: \x09\x0a - 3: \x09 - 4: - -/\s+/ - > \x09\x0a\x0c\x0d\x0b< - 0: \x09\x0a\x0c\x0d - 1: \x09\x0a\x0c - 2: \x09\x0a - 3: \x09 - 4: - -/a b/x - ab -No match - -/(?!\A)x/m - a\nxb\n - 0: x - -/(?!^)x/m - a\nxb\n -No match - -/abc\Qabc\Eabc/ - abcabcabc - 0: abcabcabc - -/abc\Q(*+|\Eabc/ - abc(*+|abc - 0: abc(*+|abc - -/ abc\Q abc\Eabc/x - abc abcabc - 0: abc abcabc - *** Failers -No match - abcabcabc -No match - -/abc#comment - \Q#not comment - literal\E/x - abc#not comment\n literal - 0: abc#not comment\x0a literal - -/abc#comment - \Q#not comment - literal/x - abc#not comment\n literal - 0: abc#not comment\x0a literal - -/abc#comment - \Q#not comment - literal\E #more comment - /x - abc#not comment\n literal - 0: abc#not comment\x0a literal - -/abc#comment - \Q#not comment - literal\E #more comment/x - abc#not comment\n literal - 0: abc#not comment\x0a literal - -/\Qabc\$xyz\E/ - abc\\\$xyz - 0: abc\$xyz - -/\Qabc\E\$\Qxyz\E/ - abc\$xyz - 0: abc$xyz - -/\Gabc/ - abc - 0: abc - *** Failers -No match - xyzabc -No match - -/\Gabc./g - abc1abc2xyzabc3 - 0: abc1 - 0: abc2 - -/abc./g - abc1abc2xyzabc3 - 0: abc1 - 0: abc2 - 0: abc3 - -/a(?x: b c )d/ - XabcdY - 0: abcd - *** Failers -No match - Xa b c d Y -No match - -/((?x)x y z | a b c)/ - XabcY - 0: abc - AxyzB - 0: xyz - -/(?i)AB(?-i)C/ - XabCY - 0: abC - *** Failers -No match - XabcY -No match - -/((?i)AB(?-i)C|D)E/ - abCE - 0: abCE - DE - 0: DE - *** Failers -No match - abcE -No match - abCe -No match - dE -No match - De -No match - -/[z\Qa-d]\E]/ - z - 0: z - a - 0: a - - - 0: - - d - 0: d - ] - 0: ] - *** Failers - 0: a - b -No match - -/[\z\C]/ - z - 0: z - C - 0: C - -/\M/ - M - 0: M - -/(a+)*b/ - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -No match - -/(?i)reg(?:ul(?:[aä]|ae)r|ex)/ - REGular - 0: REGular - regulaer - 0: regulaer - Regex - 0: Regex - regulär - 0: regul\xe4r - -/Åæåä[à-ÿÀ-ß]+/ - Åæåäà - 0: \xc5\xe6\xe5\xe4\xe0 - Åæåäÿ - 0: \xc5\xe6\xe5\xe4\xff - ÅæåäÀ - 0: \xc5\xe6\xe5\xe4\xc0 - Åæåäß - 0: \xc5\xe6\xe5\xe4\xdf - -/(?<=Z)X./ - \x84XAZXB - 0: XB - -/^(?(2)a|(1)(2))+$/ - 123a -Error -17 - -/(?<=a|bbbb)c/ - ac - 0: c - bbbbc - 0: c - -/abc/>testsavedregex -Compiled regex written to testsavedregex -testsavedregex -Compiled regex written to testsavedregex -testsavedregex -Compiled regex written to testsavedregex -Study data written to testsavedregex -testsavedregex -Compiled regex written to testsavedregex -Study data written to testsavedregex - - 0: abc - xyz\r\nabc\ - 0: abc - xyz\rabc\ - 0: abc - xyz\r\nabc\ - 0: abc - ** Failers -No match - xyz\nabc\ -No match - xyz\r\nabc\ -No match - xyz\nabc\ -No match - xyz\rabc\ -No match - xyz\rabc\ -No match - -/abc$/m - xyzabc - 0: abc - xyzabc\n - 0: abc - xyzabc\npqr - 0: abc - xyzabc\r\ - 0: abc - xyzabc\rpqr\ - 0: abc - xyzabc\r\n\ - 0: abc - xyzabc\r\npqr\ - 0: abc - ** Failers -No match - xyzabc\r -No match - xyzabc\rpqr -No match - xyzabc\r\n -No match - xyzabc\r\npqr -No match - -/^abc/m - xyz\rabcdef - 0: abc - xyz\nabcdef\ - 0: abc - ** Failers -No match - xyz\nabcdef -No match - -/^abc/m - xyz\nabcdef - 0: abc - xyz\rabcdef\ - 0: abc - ** Failers -No match - xyz\rabcdef -No match - -/^abc/m - xyz\r\nabcdef - 0: abc - xyz\rabcdef\ - 0: abc - ** Failers -No match - xyz\rabcdef -No match - -/.*/ - abc\ndef - 0: abc - 1: ab - 2: a - 3: - abc\rdef - 0: abc\x0ddef - 1: abc\x0dde - 2: abc\x0dd - 3: abc\x0d - 4: abc - 5: ab - 6: a - 7: - abc\r\ndef - 0: abc\x0d - 1: abc - 2: ab - 3: a - 4: - \abc\ndef - 0: abc\x0adef - 1: abc\x0ade - 2: abc\x0ad - 3: abc\x0a - 4: abc - 5: ab - 6: a - 7: - \abc\rdef - 0: abc - 1: ab - 2: a - 3: - \abc\r\ndef - 0: abc - 1: ab - 2: a - 3: - \abc\ndef - 0: abc\x0adef - 1: abc\x0ade - 2: abc\x0ad - 3: abc\x0a - 4: abc - 5: ab - 6: a - 7: - \abc\rdef - 0: abc\x0ddef - 1: abc\x0dde - 2: abc\x0dd - 3: abc\x0d - 4: abc - 5: ab - 6: a - 7: - \abc\r\ndef - 0: abc - 1: ab - 2: a - 3: - -/\w+(.)(.)?def/s - abc\ndef - 0: abc\x0adef - abc\rdef - 0: abc\x0ddef - abc\r\ndef - 0: abc\x0d\x0adef - -/^\w+=.*(\\\n.*)*/ - abc=xyz\\\npqr - 0: abc=xyz\\x0apqr - 1: abc=xyz\\x0apq - 2: abc=xyz\\x0ap - 3: abc=xyz\\x0a - 4: abc=xyz\ - 5: abc=xyz - 6: abc=xy - 7: abc=x - 8: abc= - -/^(a()*)*/ - aaaa - 0: aaaa - 1: aaa - 2: aa - 3: a - 4: - -/^(?:a(?:(?:))*)*/ - aaaa - 0: aaaa - 1: aaa - 2: aa - 3: a - 4: - -/^(a()+)+/ - aaaa - 0: aaaa - 1: aaa - 2: aa - 3: a - -/^(?:a(?:(?:))+)+/ - aaaa - 0: aaaa - 1: aaa - 2: aa - 3: a - -/(a|)*\d/ - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -No match - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 - 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 - -/(?>a|)*\d/ - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -No match - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 - 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 - -/(?:a|)*\d/ - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -No match - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 - 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 - -/^a.b/ - a\rb - 0: a\x0db - a\nb\ - 0: a\x0ab - ** Failers -No match - a\nb -No match - a\nb\ -No match - a\rb\ -No match - a\rb\ -No match - -/^abc./mgx - abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x85abc7 JUNK - 0: abc1 - 0: abc2 - 0: abc3 - 0: abc4 - 0: abc5 - 0: abc6 - 0: abc7 - -/abc.$/mgx - abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x85 abc9 - 0: abc1 - 0: abc2 - 0: abc3 - 0: abc4 - 0: abc5 - 0: abc6 - 0: abc9 - -/^a\Rb/ - a\nb - 0: a\x0ab - a\rb - 0: a\x0db - a\r\nb - 0: a\x0d\x0ab - a\x0bb - 0: a\x0bb - a\x0cb - 0: a\x0cb - a\x85b - 0: a\x85b - ** Failers -No match - a\n\rb -No match - -/^a\R*b/ - ab - 0: ab - a\nb - 0: a\x0ab - a\rb - 0: a\x0db - a\r\nb - 0: a\x0d\x0ab - a\x0bb - 0: a\x0bb - a\x0cb - 0: a\x0cb - a\x85b - 0: a\x85b - a\n\rb - 0: a\x0a\x0db - a\n\r\x85\x0cb - 0: a\x0a\x0d\x85\x0cb - -/^a\R+b/ - a\nb - 0: a\x0ab - a\rb - 0: a\x0db - a\r\nb - 0: a\x0d\x0ab - a\x0bb - 0: a\x0bb - a\x0cb - 0: a\x0cb - a\x85b - 0: a\x85b - a\n\rb - 0: a\x0a\x0db - a\n\r\x85\x0cb - 0: a\x0a\x0d\x85\x0cb - ** Failers -No match - ab -No match - -/^a\R{1,3}b/ - a\nb - 0: a\x0ab - a\n\rb - 0: a\x0a\x0db - a\n\r\x85b - 0: a\x0a\x0d\x85b - a\r\n\r\nb - 0: a\x0d\x0a\x0d\x0ab - a\r\n\r\n\r\nb - 0: a\x0d\x0a\x0d\x0a\x0d\x0ab - a\n\r\n\rb - 0: a\x0a\x0d\x0a\x0db - a\n\n\r\nb - 0: a\x0a\x0a\x0d\x0ab - ** Failers -No match - a\n\n\n\rb -No match - a\r -No match - -/^a[\R]b/ - aRb - 0: aRb - ** Failers -No match - a\nb -No match - -/.+foo/ - afoo - 0: afoo - ** Failers -No match - \r\nfoo -No match - \nfoo -No match - -/.+foo/ - afoo - 0: afoo - \nfoo - 0: \x0afoo - ** Failers -No match - \r\nfoo -No match - -/.+foo/ - afoo - 0: afoo - ** Failers -No match - \nfoo -No match - \r\nfoo -No match - -/.+foo/s - afoo - 0: afoo - \r\nfoo - 0: \x0d\x0afoo - \nfoo - 0: \x0afoo - -/^$/mg - abc\r\rxyz - 0: - abc\n\rxyz - 0: - ** Failers -No match - abc\r\nxyz -No match - -/^X/m - XABC - 0: X - ** Failers -No match - XABC\B -No match - -/(?m)^$/g+ - abc\r\n\r\n - 0: - 0+ \x0d\x0a - -/(?m)^$|^\r\n/g+ - abc\r\n\r\n - 0: \x0d\x0a - 0+ - 1: - -/(?m)$/g+ - abc\r\n\r\n - 0: - 0+ \x0d\x0a\x0d\x0a - 0: - 0+ \x0d\x0a - 0: - 0+ - -/(?|(abc)|(xyz))/ - >abc< - 0: abc - >xyz< - 0: xyz - -/(x)(?|(abc)|(xyz))(x)/ - xabcx - 0: xabcx - xxyzx - 0: xxyzx - -/(x)(?|(abc)(pqr)|(xyz))(x)/ - xabcpqrx - 0: xabcpqrx - xxyzx - 0: xxyzx - -/(?|(abc)|(xyz))(?1)/ - abcabc - 0: abcabc - xyzabc - 0: xyzabc - ** Failers -No match - xyzxyz -No match - -/\H\h\V\v/ - X X\x0a - 0: X X\x0a - X\x09X\x0b - 0: X\x09X\x0b - ** Failers -No match - \xa0 X\x0a -No match - -/\H*\h+\V?\v{3,4}/ - \x09\x20\xa0X\x0a\x0b\x0c\x0d\x0a - 0: \x09 \xa0X\x0a\x0b\x0c\x0d - 1: \x09 \xa0X\x0a\x0b\x0c - \x09\x20\xa0\x0a\x0b\x0c\x0d\x0a - 0: \x09 \xa0\x0a\x0b\x0c\x0d - 1: \x09 \xa0\x0a\x0b\x0c - \x09\x20\xa0\x0a\x0b\x0c - 0: \x09 \xa0\x0a\x0b\x0c - ** Failers -No match - \x09\x20\xa0\x0a\x0b -No match - -/\H{3,4}/ - XY ABCDE - 0: ABCD - 1: ABC - XY PQR ST - 0: PQR - -/.\h{3,4}./ - XY AB PQRS - 0: B P - 1: B - -/\h*X\h?\H+Y\H?Z/ - >XNNNYZ - 0: XNNNYZ - > X NYQZ - 0: X NYQZ - ** Failers -No match - >XYZ -No match - > X NY Z -No match - -/\v*X\v?Y\v+Z\V*\x0a\V+\x0b\V{2,3}\x0c/ - >XY\x0aZ\x0aA\x0bNN\x0c - 0: XY\x0aZ\x0aA\x0bNN\x0c - >\x0a\x0dX\x0aY\x0a\x0bZZZ\x0aAAA\x0bNNN\x0c - 0: \x0a\x0dX\x0aY\x0a\x0bZZZ\x0aAAA\x0bNNN\x0c - -/.+A/ - \r\nA -No match - -/\nA/ - \r\nA - 0: \x0aA - -/[\r\n]A/ - \r\nA - 0: \x0aA - -/(\r|\n)A/ - \r\nA - 0: \x0aA - -/a\Rb/I -Capturing subpattern count = 0 -Options: bsr_anycrlf -First char = 'a' -Need char = 'b' - a\rb - 0: a\x0db - a\nb - 0: a\x0ab - a\r\nb - 0: a\x0d\x0ab - ** Failers -No match - a\x85b -No match - a\x0bb -No match - -/a\Rb/I -Capturing subpattern count = 0 -Options: bsr_unicode -First char = 'a' -Need char = 'b' - a\rb - 0: a\x0db - a\nb - 0: a\x0ab - a\r\nb - 0: a\x0d\x0ab - a\x85b - 0: a\x85b - a\x0bb - 0: a\x0bb - ** Failers -No match - a\x85b\ -No match - a\x0bb\ -No match - -/a\R?b/I -Capturing subpattern count = 0 -Options: bsr_anycrlf -First char = 'a' -Need char = 'b' - a\rb - 0: a\x0db - a\nb - 0: a\x0ab - a\r\nb - 0: a\x0d\x0ab - ** Failers -No match - a\x85b -No match - a\x0bb -No match - -/a\R?b/I -Capturing subpattern count = 0 -Options: bsr_unicode -First char = 'a' -Need char = 'b' - a\rb - 0: a\x0db - a\nb - 0: a\x0ab - a\r\nb - 0: a\x0d\x0ab - a\x85b - 0: a\x85b - a\x0bb - 0: a\x0bb - ** Failers -No match - a\x85b\ -No match - a\x0bb\ -No match - -/a\R{2,4}b/I -Capturing subpattern count = 0 -Partial matching not supported -Options: bsr_anycrlf -First char = 'a' -Need char = 'b' - a\r\n\nb - 0: a\x0d\x0a\x0ab - a\n\r\rb - 0: a\x0a\x0d\x0db - a\r\n\r\n\r\n\r\nb - 0: a\x0d\x0a\x0d\x0a\x0d\x0a\x0d\x0ab - ** Failers -No match - a\x85\85b -No match - a\x0b\0bb -No match - -/a\R{2,4}b/I -Capturing subpattern count = 0 -Partial matching not supported -Options: bsr_unicode -First char = 'a' -Need char = 'b' - a\r\rb - 0: a\x0d\x0db - a\n\n\nb - 0: a\x0a\x0a\x0ab - a\r\n\n\r\rb - 0: a\x0d\x0a\x0a\x0d\x0db - a\x85\85b -No match - a\x0b\0bb -No match - ** Failers -No match - a\r\r\r\r\rb -No match - a\x85\85b\ -No match - a\x0b\0bb\ -No match - -/a(?!)|\wbc/ - abc - 0: abc - -/a[]b/ - ** Failers -No match - ab -No match - -/a[]+b/ - ** Failers -No match - ab -No match - -/a[]*+b/ - ** Failers -No match - ab -No match - -/a[^]b/ - aXb - 0: aXb - a\nb - 0: a\x0ab - ** Failers -No match - ab -No match - -/a[^]+b/ - aXb - 0: aXb - a\nX\nXb - 0: a\x0aX\x0aXb - ** Failers -No match - ab -No match - -/X$/E - X - 0: X - ** Failers -No match - X\n -No match - -/X$/ - X - 0: X - X\n - 0: X - -/xyz/C - xyz ---->xyz - +0 ^ x - +1 ^^ y - +2 ^ ^ z - +3 ^ ^ - 0: xyz - abcxyz ---->abcxyz - +0 ^ x - +1 ^^ y - +2 ^ ^ z - +3 ^ ^ - 0: xyz - abcxyz\Y ---->abcxyz - +0 ^ x - +0 ^ x - +0 ^ x - +0 ^ x - +1 ^^ y - +2 ^ ^ z - +3 ^ ^ - 0: xyz - ** Failers -No match - abc -No match - abc\Y ---->abc - +0 ^ x - +0 ^ x - +0 ^ x - +0 ^ x -No match - abcxypqr -No match - abcxypqr\Y ---->abcxypqr - +0 ^ x - +0 ^ x - +0 ^ x - +0 ^ x - +1 ^^ y - +2 ^ ^ z - +0 ^ x - +0 ^ x - +0 ^ x - +0 ^ x - +0 ^ x -No match - -/(?C)ab/ - ab ---->ab - 0 ^ a - 0: ab - \C-ab - 0: ab - -/ab/C - ab ---->ab - +0 ^ a - +1 ^^ b - +2 ^ ^ - 0: ab - \C-ab - 0: ab - -/^"((?(?=[a])[^"])|b)*"$/C - "ab" ---->"ab" - +0 ^ ^ - +1 ^ " - +2 ^^ ((?(?=[a])[^"])|b)* -+21 ^^ " - +3 ^^ (?(?=[a])[^"]) -+18 ^^ b - +5 ^^ (?=[a]) - +8 ^ [a] -+11 ^^ ) -+12 ^^ [^"] -+16 ^ ^ ) -+17 ^ ^ | -+21 ^ ^ " - +3 ^ ^ (?(?=[a])[^"]) -+18 ^ ^ b - +5 ^ ^ (?=[a]) - +8 ^ [a] -+19 ^ ^ ) -+21 ^ ^ " - +3 ^ ^ (?(?=[a])[^"]) -+18 ^ ^ b - +5 ^ ^ (?=[a]) - +8 ^ [a] -+17 ^ ^ | -+22 ^ ^ $ -+23 ^ ^ - 0: "ab" - \C-"ab" - 0: "ab" - -/ End of testinput7 / diff --git a/libs/pcre/testdata/testoutput8 b/libs/pcre/testdata/testoutput8 deleted file mode 100644 index af10c4ae7d..0000000000 --- a/libs/pcre/testdata/testoutput8 +++ /dev/null @@ -1,1291 +0,0 @@ -/-- Do not use the \x{} construct except with patterns that have the --/ -/-- /8 option set, because PCRE doesn't recognize them as UTF-8 unless --/ -No match -/-- that option is set. However, the latest Perls recognize them always. --/ -No match - -/\x{100}ab/8 - \x{100}ab - 0: \x{100}ab - -/a\x{100}*b/8 - ab - 0: ab - a\x{100}b - 0: a\x{100}b - a\x{100}\x{100}b - 0: a\x{100}\x{100}b - -/a\x{100}+b/8 - a\x{100}b - 0: a\x{100}b - a\x{100}\x{100}b - 0: a\x{100}\x{100}b - *** Failers -No match - ab -No match - -/\bX/8 - Xoanon - 0: X - +Xoanon - 0: X - \x{300}Xoanon - 0: X - *** Failers -No match - YXoanon -No match - -/\BX/8 - YXoanon - 0: X - *** Failers -No match - Xoanon -No match - +Xoanon -No match - \x{300}Xoanon -No match - -/X\b/8 - X+oanon - 0: X - ZX\x{300}oanon - 0: X - FAX - 0: X - *** Failers -No match - Xoanon -No match - -/X\B/8 - Xoanon - 0: X - *** Failers -No match - X+oanon -No match - ZX\x{300}oanon -No match - FAX -No match - -/[^a]/8 - abcd - 0: b - a\x{100} - 0: \x{100} - -/^[abc\x{123}\x{400}-\x{402}]{2,3}\d/8 - ab99 - 0: ab9 - \x{123}\x{123}45 - 0: \x{123}\x{123}4 - \x{400}\x{401}\x{402}6 - 0: \x{400}\x{401}\x{402}6 - *** Failers -No match - d99 -No match - \x{123}\x{122}4 -No match - \x{400}\x{403}6 -No match - \x{400}\x{401}\x{402}\x{402}6 -No match - -/abc/8 - Ã] -Error -10 - à -Error -10 - ÃÃà -Error -10 - ÃÃÃ\? -No match - -/a.b/8 - acb - 0: acb - a\x7fb - 0: a\x{7f}b - a\x{100}b - 0: a\x{100}b - *** Failers -No match - a\nb -No match - -/a(.{3})b/8 - a\x{4000}xyb - 0: a\x{4000}xyb - a\x{4000}\x7fyb - 0: a\x{4000}\x{7f}yb - a\x{4000}\x{100}yb - 0: a\x{4000}\x{100}yb - *** Failers -No match - a\x{4000}b -No match - ac\ncb -No match - -/a(.*?)(.)/ - a\xc0\x88b - 0: a\xc0\x88b - 1: a\xc0\x88 - 2: a\xc0 - -/a(.*?)(.)/8 - a\x{100}b - 0: a\x{100}b - 1: a\x{100} - -/a(.*)(.)/ - a\xc0\x88b - 0: a\xc0\x88b - 1: a\xc0\x88 - 2: a\xc0 - -/a(.*)(.)/8 - a\x{100}b - 0: a\x{100}b - 1: a\x{100} - -/a(.)(.)/ - a\xc0\x92bcd - 0: a\xc0\x92 - -/a(.)(.)/8 - a\x{240}bcd - 0: a\x{240}b - -/a(.?)(.)/ - a\xc0\x92bcd - 0: a\xc0\x92 - 1: a\xc0 - -/a(.?)(.)/8 - a\x{240}bcd - 0: a\x{240}b - 1: a\x{240} - -/a(.??)(.)/ - a\xc0\x92bcd - 0: a\xc0\x92 - 1: a\xc0 - -/a(.??)(.)/8 - a\x{240}bcd - 0: a\x{240}b - 1: a\x{240} - -/a(.{3})b/8 - a\x{1234}xyb - 0: a\x{1234}xyb - a\x{1234}\x{4321}yb - 0: a\x{1234}\x{4321}yb - a\x{1234}\x{4321}\x{3412}b - 0: a\x{1234}\x{4321}\x{3412}b - *** Failers -No match - a\x{1234}b -No match - ac\ncb -No match - -/a(.{3,})b/8 - a\x{1234}xyb - 0: a\x{1234}xyb - a\x{1234}\x{4321}yb - 0: a\x{1234}\x{4321}yb - a\x{1234}\x{4321}\x{3412}b - 0: a\x{1234}\x{4321}\x{3412}b - axxxxbcdefghijb - 0: axxxxbcdefghijb - 1: axxxxb - a\x{1234}\x{4321}\x{3412}\x{3421}b - 0: a\x{1234}\x{4321}\x{3412}\x{3421}b - *** Failers -No match - a\x{1234}b -No match - -/a(.{3,}?)b/8 - a\x{1234}xyb - 0: a\x{1234}xyb - a\x{1234}\x{4321}yb - 0: a\x{1234}\x{4321}yb - a\x{1234}\x{4321}\x{3412}b - 0: a\x{1234}\x{4321}\x{3412}b - axxxxbcdefghijb - 0: axxxxbcdefghijb - 1: axxxxb - a\x{1234}\x{4321}\x{3412}\x{3421}b - 0: a\x{1234}\x{4321}\x{3412}\x{3421}b - *** Failers -No match - a\x{1234}b -No match - -/a(.{3,5})b/8 - a\x{1234}xyb - 0: a\x{1234}xyb - a\x{1234}\x{4321}yb - 0: a\x{1234}\x{4321}yb - a\x{1234}\x{4321}\x{3412}b - 0: a\x{1234}\x{4321}\x{3412}b - axxxxbcdefghijb - 0: axxxxb - a\x{1234}\x{4321}\x{3412}\x{3421}b - 0: a\x{1234}\x{4321}\x{3412}\x{3421}b - axbxxbcdefghijb - 0: axbxxb - axxxxxbcdefghijb - 0: axxxxxb - *** Failers -No match - a\x{1234}b -No match - axxxxxxbcdefghijb -No match - -/a(.{3,5}?)b/8 - a\x{1234}xyb - 0: a\x{1234}xyb - a\x{1234}\x{4321}yb - 0: a\x{1234}\x{4321}yb - a\x{1234}\x{4321}\x{3412}b - 0: a\x{1234}\x{4321}\x{3412}b - axxxxbcdefghijb - 0: axxxxb - a\x{1234}\x{4321}\x{3412}\x{3421}b - 0: a\x{1234}\x{4321}\x{3412}\x{3421}b - axbxxbcdefghijb - 0: axbxxb - axxxxxbcdefghijb - 0: axxxxxb - *** Failers -No match - a\x{1234}b -No match - axxxxxxbcdefghijb -No match - -/^[a\x{c0}]/8 - *** Failers -No match - \x{100} -No match - -/(?<=aXb)cd/8 - aXbcd - 0: cd - -/(?<=a\x{100}b)cd/8 - a\x{100}bcd - 0: cd - -/(?<=a\x{100000}b)cd/8 - a\x{100000}bcd - 0: cd - -/(?:\x{100}){3}b/8 - \x{100}\x{100}\x{100}b - 0: \x{100}\x{100}\x{100}b - *** Failers -No match - \x{100}\x{100}b -No match - -/\x{ab}/8 - \x{ab} - 0: \x{ab} - \xc2\xab - 0: \x{ab} - *** Failers -No match - \x00{ab} -No match - -/(?<=(.))X/8 - WXYZ - 0: X - \x{256}XYZ - 0: X - *** Failers -No match - XYZ -No match - -/[^a]+/8g - bcd - 0: bcd - 1: bc - 2: b - \x{100}aY\x{256}Z - 0: \x{100} - 0: Y\x{256}Z - 1: Y\x{256} - 2: Y - -/^[^a]{2}/8 - \x{100}bc - 0: \x{100}b - -/^[^a]{2,}/8 - \x{100}bcAa - 0: \x{100}bcA - 1: \x{100}bc - 2: \x{100}b - -/^[^a]{2,}?/8 - \x{100}bca - 0: \x{100}bc - 1: \x{100}b - -/[^a]+/8ig - bcd - 0: bcd - 1: bc - 2: b - \x{100}aY\x{256}Z - 0: \x{100} - 0: Y\x{256}Z - 1: Y\x{256} - 2: Y - -/^[^a]{2}/8i - \x{100}bc - 0: \x{100}b - -/^[^a]{2,}/8i - \x{100}bcAa - 0: \x{100}bc - 1: \x{100}b - -/^[^a]{2,}?/8i - \x{100}bca - 0: \x{100}bc - 1: \x{100}b - -/\x{100}{0,0}/8 - abcd - 0: - -/\x{100}?/8 - abcd - 0: - \x{100}\x{100} - 0: \x{100} - 1: - -/\x{100}{0,3}/8 - \x{100}\x{100} - 0: \x{100}\x{100} - 1: \x{100} - 2: - \x{100}\x{100}\x{100}\x{100} - 0: \x{100}\x{100}\x{100} - 1: \x{100}\x{100} - 2: \x{100} - 3: - -/\x{100}*/8 - abce - 0: - \x{100}\x{100}\x{100}\x{100} - 0: \x{100}\x{100}\x{100}\x{100} - 1: \x{100}\x{100}\x{100} - 2: \x{100}\x{100} - 3: \x{100} - 4: - -/\x{100}{1,1}/8 - abcd\x{100}\x{100}\x{100}\x{100} - 0: \x{100} - -/\x{100}{1,3}/8 - abcd\x{100}\x{100}\x{100}\x{100} - 0: \x{100}\x{100}\x{100} - 1: \x{100}\x{100} - 2: \x{100} - -/\x{100}+/8 - abcd\x{100}\x{100}\x{100}\x{100} - 0: \x{100}\x{100}\x{100}\x{100} - 1: \x{100}\x{100}\x{100} - 2: \x{100}\x{100} - 3: \x{100} - -/\x{100}{3}/8 - abcd\x{100}\x{100}\x{100}XX - 0: \x{100}\x{100}\x{100} - -/\x{100}{3,5}/8 - abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX - 0: \x{100}\x{100}\x{100}\x{100}\x{100} - 1: \x{100}\x{100}\x{100}\x{100} - 2: \x{100}\x{100}\x{100} - -/\x{100}{3,}/8 - abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX - 0: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} - 1: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100} - 2: \x{100}\x{100}\x{100}\x{100}\x{100} - 3: \x{100}\x{100}\x{100}\x{100} - 4: \x{100}\x{100}\x{100} - -/(?<=a\x{100}{2}b)X/8 - Xyyya\x{100}\x{100}bXzzz - 0: X - -/\D*/8 - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -Matched, but too many subsidiary matches - 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - 1: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - 2: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - 3: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - 4: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - 5: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - 6: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - 7: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - 8: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - 9: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -10: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -11: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -12: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -13: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -14: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -15: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -16: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -17: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -18: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -19: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -20: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -21: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - -/\D*/8 - \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} -Matched, but too many subsidiary matches - 0: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} - 1: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} - 2: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} - 3: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} - 4: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} - 5: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} - 6: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} - 7: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} - 8: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} - 9: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} -10: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} -11: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} -12: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} -13: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} -14: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} -15: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} -16: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} -17: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} -18: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} -19: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} -20: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} -21: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} - -/\D/8 - 1X2 - 0: X - 1\x{100}2 - 0: \x{100} - -/>\S/8 - > >X Y - 0: >X - > >\x{100} Y - 0: >\x{100} - -/\d/8 - \x{100}3 - 0: 3 - -/\s/8 - \x{100} X - 0: - -/\D+/8 - 12abcd34 - 0: abcd - 1: abc - 2: ab - 3: a - *** Failers - 0: *** Failers - 1: *** Failer - 2: *** Faile - 3: *** Fail - 4: *** Fai - 5: *** Fa - 6: *** F - 7: *** - 8: *** - 9: ** -10: * - 1234 -No match - -/\D{2,3}/8 - 12abcd34 - 0: abc - 1: ab - 12ab34 - 0: ab - *** Failers - 0: *** - 1: ** - 1234 -No match - 12a34 -No match - -/\D{2,3}?/8 - 12abcd34 - 0: abc - 1: ab - 12ab34 - 0: ab - *** Failers - 0: *** - 1: ** - 1234 -No match - 12a34 -No match - -/\d+/8 - 12abcd34 - 0: 12 - 1: 1 - *** Failers -No match - -/\d{2,3}/8 - 12abcd34 - 0: 12 - 1234abcd - 0: 123 - 1: 12 - *** Failers -No match - 1.4 -No match - -/\d{2,3}?/8 - 12abcd34 - 0: 12 - 1234abcd - 0: 123 - 1: 12 - *** Failers -No match - 1.4 -No match - -/\S+/8 - 12abcd34 - 0: 12abcd34 - 1: 12abcd3 - 2: 12abcd - 3: 12abc - 4: 12ab - 5: 12a - 6: 12 - 7: 1 - *** Failers - 0: *** - 1: ** - 2: * - \ \ -No match - -/\S{2,3}/8 - 12abcd34 - 0: 12a - 1: 12 - 1234abcd - 0: 123 - 1: 12 - *** Failers - 0: *** - 1: ** - \ \ -No match - -/\S{2,3}?/8 - 12abcd34 - 0: 12a - 1: 12 - 1234abcd - 0: 123 - 1: 12 - *** Failers - 0: *** - 1: ** - \ \ -No match - -/>\s+ <34 - 0: > < - *** Failers -No match - -/>\s{2,3} < - ab> < - *** Failers -No match - ab> \s{2,3}? < - ab> < - *** Failers -No match - ab> \xff< - 0: \xff - -/[\xff]/8 - >\x{ff}< - 0: \x{ff} - -/[^\xFF]/ - XYZ - 0: X - -/[^\xff]/8 - XYZ - 0: X - \x{123} - 0: \x{123} - -/^[ac]*b/8 - xb -No match - -/^[ac\x{100}]*b/8 - xb -No match - -/^[^x]*b/8i - xb -No match - -/^[^x]*b/8 - xb -No match - -/^\d*b/8 - xb -No match - -/(|a)/g8 - catac - 0: - 0: a - 1: - 0: - 0: a - 1: - 0: - 0: - a\x{256}a - 0: a - 1: - 0: - 0: a - 1: - 0: - -/^\x{85}$/8i - \x{85} - 0: \x{85} - -/^abc./mgx8 - abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x{0085}abc7 \x{2028}abc8 \x{2029}abc9 JUNK - 0: abc1 - 0: abc2 - 0: abc3 - 0: abc4 - 0: abc5 - 0: abc6 - 0: abc7 - 0: abc8 - 0: abc9 - -/abc.$/mgx8 - abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x{0085} abc7\x{2028} abc8\x{2029} abc9 - 0: abc1 - 0: abc2 - 0: abc3 - 0: abc4 - 0: abc5 - 0: abc6 - 0: abc7 - 0: abc8 - 0: abc9 - -/^a\Rb/8 - a\nb - 0: a\x{0a}b - a\rb - 0: a\x{0d}b - a\r\nb - 0: a\x{0d}\x{0a}b - a\x0bb - 0: a\x{0b}b - a\x0cb - 0: a\x{0c}b - a\x{85}b - 0: a\x{85}b - a\x{2028}b - 0: a\x{2028}b - a\x{2029}b - 0: a\x{2029}b - ** Failers -No match - a\n\rb -No match - -/^a\R*b/8 - ab - 0: ab - a\nb - 0: a\x{0a}b - a\rb - 0: a\x{0d}b - a\r\nb - 0: a\x{0d}\x{0a}b - a\x0bb - 0: a\x{0b}b - a\x0c\x{2028}\x{2029}b - 0: a\x{0c}\x{2028}\x{2029}b - a\x{85}b - 0: a\x{85}b - a\n\rb - 0: a\x{0a}\x{0d}b - a\n\r\x{85}\x0cb - 0: a\x{0a}\x{0d}\x{85}\x{0c}b - -/^a\R+b/8 - a\nb - 0: a\x{0a}b - a\rb - 0: a\x{0d}b - a\r\nb - 0: a\x{0d}\x{0a}b - a\x0bb - 0: a\x{0b}b - a\x0c\x{2028}\x{2029}b - 0: a\x{0c}\x{2028}\x{2029}b - a\x{85}b - 0: a\x{85}b - a\n\rb - 0: a\x{0a}\x{0d}b - a\n\r\x{85}\x0cb - 0: a\x{0a}\x{0d}\x{85}\x{0c}b - ** Failers -No match - ab -No match - -/^a\R{1,3}b/8 - a\nb - 0: a\x{0a}b - a\n\rb - 0: a\x{0a}\x{0d}b - a\n\r\x{85}b - 0: a\x{0a}\x{0d}\x{85}b - a\r\n\r\nb - 0: a\x{0d}\x{0a}\x{0d}\x{0a}b - a\r\n\r\n\r\nb - 0: a\x{0d}\x{0a}\x{0d}\x{0a}\x{0d}\x{0a}b - a\n\r\n\rb - 0: a\x{0a}\x{0d}\x{0a}\x{0d}b - a\n\n\r\nb - 0: a\x{0a}\x{0a}\x{0d}\x{0a}b - ** Failers -No match - a\n\n\n\rb -No match - a\r -No match - -/\h+\V?\v{3,4}/8 - \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a - 0: \x{09} \x{a0}X\x{0a}\x{0b}\x{0c}\x{0d} - 1: \x{09} \x{a0}X\x{0a}\x{0b}\x{0c} - -/\V?\v{3,4}/8 - \x20\x{a0}X\x0a\x0b\x0c\x0d\x0a - 0: X\x{0a}\x{0b}\x{0c}\x{0d} - 1: X\x{0a}\x{0b}\x{0c} - -/\h+\V?\v{3,4}/8 - >\x09\x20\x{a0}X\x0a\x0a\x0a< - 0: \x{09} \x{a0}X\x{0a}\x{0a}\x{0a} - -/\V?\v{3,4}/8 - >\x09\x20\x{a0}X\x0a\x0a\x0a< - 0: X\x{0a}\x{0a}\x{0a} - -/\H\h\V\v/8 - X X\x0a - 0: X X\x{0a} - X\x09X\x0b - 0: X\x{09}X\x{0b} - ** Failers -No match - \x{a0} X\x0a -No match - -/\H*\h+\V?\v{3,4}/8 - \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a - 0: \x{09} \x{a0}X\x{0a}\x{0b}\x{0c}\x{0d} - 1: \x{09} \x{a0}X\x{0a}\x{0b}\x{0c} - \x09\x20\x{a0}\x0a\x0b\x0c\x0d\x0a - 0: \x{09} \x{a0}\x{0a}\x{0b}\x{0c}\x{0d} - 1: \x{09} \x{a0}\x{0a}\x{0b}\x{0c} - \x09\x20\x{a0}\x0a\x0b\x0c - 0: \x{09} \x{a0}\x{0a}\x{0b}\x{0c} - ** Failers -No match - \x09\x20\x{a0}\x0a\x0b -No match - -/\H\h\V\v/8 - \x{3001}\x{3000}\x{2030}\x{2028} - 0: \x{3001}\x{3000}\x{2030}\x{2028} - X\x{180e}X\x{85} - 0: X\x{180e}X\x{85} - ** Failers -No match - \x{2009} X\x0a -No match - -/\H*\h+\V?\v{3,4}/8 - \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x0c\x0d\x0a - 0: \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x{0c}\x{0d} - 1: \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x{0c} - \x09\x{205f}\x{a0}\x0a\x{2029}\x0c\x{2028}\x0a - 0: \x{09}\x{205f}\x{a0}\x{0a}\x{2029}\x{0c}\x{2028} - 1: \x{09}\x{205f}\x{a0}\x{0a}\x{2029}\x{0c} - \x09\x20\x{202f}\x0a\x0b\x0c - 0: \x{09} \x{202f}\x{0a}\x{0b}\x{0c} - ** Failers -No match - \x09\x{200a}\x{a0}\x{2028}\x0b -No match - -/a\Rb/I8 -Capturing subpattern count = 0 -Options: bsr_anycrlf utf8 -First char = 'a' -Need char = 'b' - a\rb - 0: a\x{0d}b - a\nb - 0: a\x{0a}b - a\r\nb - 0: a\x{0d}\x{0a}b - ** Failers -No match - a\x{85}b -No match - a\x0bb -No match - -/a\Rb/I8 -Capturing subpattern count = 0 -Options: bsr_unicode utf8 -First char = 'a' -Need char = 'b' - a\rb - 0: a\x{0d}b - a\nb - 0: a\x{0a}b - a\r\nb - 0: a\x{0d}\x{0a}b - a\x{85}b - 0: a\x{85}b - a\x0bb - 0: a\x{0b}b - ** Failers -No match - a\x{85}b\ -No match - a\x0bb\ -No match - -/a\R?b/I8 -Capturing subpattern count = 0 -Options: bsr_anycrlf utf8 -First char = 'a' -Need char = 'b' - a\rb - 0: a\x{0d}b - a\nb - 0: a\x{0a}b - a\r\nb - 0: a\x{0d}\x{0a}b - ** Failers -No match - a\x{85}b -No match - a\x0bb -No match - -/a\R?b/I8 -Capturing subpattern count = 0 -Options: bsr_unicode utf8 -First char = 'a' -Need char = 'b' - a\rb - 0: a\x{0d}b - a\nb - 0: a\x{0a}b - a\r\nb - 0: a\x{0d}\x{0a}b - a\x{85}b - 0: a\x{85}b - a\x0bb - 0: a\x{0b}b - ** Failers -No match - a\x{85}b\ -No match - a\x0bb\ -No match - -/X/8f - A\x{1ec5}ABCXYZ - 0: X - -/ End of testinput 8 / diff --git a/libs/pcre/testdata/testoutput9 b/libs/pcre/testdata/testoutput9 deleted file mode 100644 index 04e3873bb8..0000000000 --- a/libs/pcre/testdata/testoutput9 +++ /dev/null @@ -1,1673 +0,0 @@ -/\pL\P{Nd}/8 - AB - 0: AB - *** Failers - 0: Fa - A0 -No match - 00 -No match - -/\X./8 - AB - 0: AB - A\x{300}BC - 0: A\x{300}B - A\x{300}\x{301}\x{302}BC - 0: A\x{300}\x{301}\x{302}B - *** Failers - 0: ** - \x{300} -No match - -/\X\X/8 - ABC - 0: AB - A\x{300}B\x{300}\x{301}C - 0: A\x{300}B\x{300}\x{301} - A\x{300}\x{301}\x{302}BC - 0: A\x{300}\x{301}\x{302}B - *** Failers - 0: ** - \x{300} -No match - -/^\pL+/8 - abcd - 0: abcd - 1: abc - 2: ab - 3: a - a - 0: a - *** Failers -No match - -/^\PL+/8 - 1234 - 0: 1234 - 1: 123 - 2: 12 - 3: 1 - = - 0: = - *** Failers - 0: *** - 1: *** - 2: ** - 3: * - abcd -No match - -/^\X+/8 - abcdA\x{300}\x{301}\x{302} - 0: abcdA\x{300}\x{301}\x{302} - 1: abcd - 2: abc - 3: ab - 4: a - A\x{300}\x{301}\x{302} - 0: A\x{300}\x{301}\x{302} - A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302} - 0: A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302} - 1: A\x{300}\x{301}\x{302} - a - 0: a - *** Failers - 0: *** Failers - 1: *** Failer - 2: *** Faile - 3: *** Fail - 4: *** Fai - 5: *** Fa - 6: *** F - 7: *** - 8: *** - 9: ** -10: * - \x{300}\x{301}\x{302} -No match - -/\X?abc/8 - abc - 0: abc - A\x{300}abc - 0: A\x{300}abc - A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz - 0: A\x{300}abc - \x{300}abc - 0: abc - *** Failers -No match - -/^\X?abc/8 - abc - 0: abc - A\x{300}abc - 0: A\x{300}abc - *** Failers -No match - A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz -No match - \x{300}abc -No match - -/\X*abc/8 - abc - 0: abc - A\x{300}abc - 0: A\x{300}abc - A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz - 0: A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abc - \x{300}abc - 0: abc - *** Failers -No match - -/^\X*abc/8 - abc - 0: abc - A\x{300}abc - 0: A\x{300}abc - A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz - 0: A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abc - *** Failers -No match - \x{300}abc -No match - -/^\pL?=./8 - A=b - 0: A=b - =c - 0: =c - *** Failers -No match - 1=2 -No match - AAAA=b -No match - -/^\pL*=./8 - AAAA=b - 0: AAAA=b - =c - 0: =c - *** Failers -No match - 1=2 -No match - -/^\X{2,3}X/8 - A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X - 0: A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X - A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X - 0: A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X - *** Failers -No match - X -No match - A\x{300}\x{301}\x{302}X -No match - A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X -No match - -/^\pC\pL\pM\pN\pP\pS\pZ>>\xaa<<< - >>>\xba<<< - -/[\W]+/Lfrench - >>>\xaa<<< - >>>\xba<<< - -/[^[:alpha:]]+/Lfrench - >>>\xaa<<< - >>>\xba<<< - -/\w+/Lfrench - >>>\xaa<<< - >>>\xba<<< - -/[\w]+/Lfrench - >>>\xaa<<< - >>>\xba<<< - -/[[:alpha:]]+/Lfrench - >>>\xaa<<< - >>>\xba<<< - -/[[:alpha:]][[:lower:]][[:upper:]]/DZLfrench - -/ End of testinput3 / diff --git a/libs/pcre/testdata/wintestoutput3 b/libs/pcre/testdata/wintestoutput3 deleted file mode 100644 index df9dfee10b..0000000000 --- a/libs/pcre/testdata/wintestoutput3 +++ /dev/null @@ -1,164 +0,0 @@ -/^[\w]+/ - *** Failers -No match - École -No match - -/^[\w]+/Lfrench - École - 0: École - -/^[\w]+/ - *** Failers -No match - École -No match - -/^[\W]+/ - École - 0: \xc9 - -/^[\W]+/Lfrench - *** Failers - 0: *** - École -No match - -/[\b]/ - \b - 0: \x08 - *** Failers -No match - a -No match - -/[\b]/Lfrench - \b - 0: \x08 - *** Failers -No match - a -No match - -/^\w+/ - *** Failers -No match - École -No match - -/^\w+/Lfrench - École - 0: École - -/(.+)\b(.+)/ - École - 0: \xc9cole - 1: \xc9 - 2: cole - -/(.+)\b(.+)/Lfrench - *** Failers - 0: *** Failers - 1: *** - 2: Failers - École -No match - -/École/i - École - 0: \xc9cole - *** Failers -No match - école -No match - -/École/iLfrench - École - 0: École - école - 0: école - -/\w/IS -Capturing subpattern count = 0 -No options -No first char -No need char -Starting byte set: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P - Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z - -/\w/ISLfrench -Capturing subpattern count = 0 -No options -No first char -No need char -Starting byte set: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P - Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z - ƒ Š Œ Ž š œ ž Ÿ ª ² ³ µ ¹ º À Á Â Ã Ä Å Æ Ç È É Ê Ë Ì Í Î Ï Ð Ñ Ò Ó Ô Õ Ö - Ø Ù Ú Û Ü Ý Þ ß à á â ã ä å æ ç è é ê ë ì í î ï ð ñ ò ó ô õ ö ø ù ú û ü ý - þ ÿ - -/^[\xc8-\xc9]/iLfrench - École - 0: É - école - 0: é - -/^[\xc8-\xc9]/Lfrench - École - 0: É - *** Failers -No match - école -No match - -/\W+/Lfrench - >>>\xaa<<< - 0: >>> - >>>\xba<<< - 0: >>> - -/[\W]+/Lfrench - >>>\xaa<<< - 0: >>> - >>>\xba<<< - 0: >>> - -/[^[:alpha:]]+/Lfrench - >>>\xaa<<< - 0: >>> - >>>\xba<<< - 0: >>> - -/\w+/Lfrench - >>>\xaa<<< - 0: ª - >>>\xba<<< - 0: º - -/[\w]+/Lfrench - >>>\xaa<<< - 0: ª - >>>\xba<<< - 0: º - -/[[:alpha:]]+/Lfrench - >>>\xaa<<< - 0: ª - >>>\xba<<< - 0: º - -/[[:alpha:]][[:lower:]][[:upper:]]/DZLfrench ------------------------------------------------------------------- - Bra - [A-Za-z\x83\x8a\x8c\x8e\x9a\x9c\x9e\x9f\xaa\xb5\xba\xc0-\xd6\xd8-\xf6\xf8-\xff] - [a-z\x83\x9a\x9c\x9e\xaa\xb5\xba\xdf-\xf6\xf8-\xff] - [A-Z\x8a\x8c\x8e\x9f\xc0-\xd6\xd8-\xde] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/ End of testinput3 / diff --git a/libs/pcre/ucp.h b/libs/pcre/ucp.h deleted file mode 100644 index ef62e40583..0000000000 --- a/libs/pcre/ucp.h +++ /dev/null @@ -1,145 +0,0 @@ -/************************************************* -* Unicode Property Table handler * -*************************************************/ - -#ifndef _UCP_H -#define _UCP_H - -/* This file contains definitions of the property values that are returned by -the UCD access macros. New values that are added for new releases of Unicode -should always be at the end of each enum, for backwards compatibility. */ - -/* These are the general character categories. */ - -enum { - ucp_C, /* Other */ - ucp_L, /* Letter */ - ucp_M, /* Mark */ - ucp_N, /* Number */ - ucp_P, /* Punctuation */ - ucp_S, /* Symbol */ - ucp_Z /* Separator */ -}; - -/* These are the particular character types. */ - -enum { - ucp_Cc, /* Control */ - ucp_Cf, /* Format */ - ucp_Cn, /* Unassigned */ - ucp_Co, /* Private use */ - ucp_Cs, /* Surrogate */ - ucp_Ll, /* Lower case letter */ - ucp_Lm, /* Modifier letter */ - ucp_Lo, /* Other letter */ - ucp_Lt, /* Title case letter */ - ucp_Lu, /* Upper case letter */ - ucp_Mc, /* Spacing mark */ - ucp_Me, /* Enclosing mark */ - ucp_Mn, /* Non-spacing mark */ - ucp_Nd, /* Decimal number */ - ucp_Nl, /* Letter number */ - ucp_No, /* Other number */ - ucp_Pc, /* Connector punctuation */ - ucp_Pd, /* Dash punctuation */ - ucp_Pe, /* Close punctuation */ - ucp_Pf, /* Final punctuation */ - ucp_Pi, /* Initial punctuation */ - ucp_Po, /* Other punctuation */ - ucp_Ps, /* Open punctuation */ - ucp_Sc, /* Currency symbol */ - ucp_Sk, /* Modifier symbol */ - ucp_Sm, /* Mathematical symbol */ - ucp_So, /* Other symbol */ - ucp_Zl, /* Line separator */ - ucp_Zp, /* Paragraph separator */ - ucp_Zs /* Space separator */ -}; - -/* These are the script identifications. */ - -enum { - ucp_Arabic, - ucp_Armenian, - ucp_Bengali, - ucp_Bopomofo, - ucp_Braille, - ucp_Buginese, - ucp_Buhid, - ucp_Canadian_Aboriginal, - ucp_Cherokee, - ucp_Common, - ucp_Coptic, - ucp_Cypriot, - ucp_Cyrillic, - ucp_Deseret, - ucp_Devanagari, - ucp_Ethiopic, - ucp_Georgian, - ucp_Glagolitic, - ucp_Gothic, - ucp_Greek, - ucp_Gujarati, - ucp_Gurmukhi, - ucp_Han, - ucp_Hangul, - ucp_Hanunoo, - ucp_Hebrew, - ucp_Hiragana, - ucp_Inherited, - ucp_Kannada, - ucp_Katakana, - ucp_Kharoshthi, - ucp_Khmer, - ucp_Lao, - ucp_Latin, - ucp_Limbu, - ucp_Linear_B, - ucp_Malayalam, - ucp_Mongolian, - ucp_Myanmar, - ucp_New_Tai_Lue, - ucp_Ogham, - ucp_Old_Italic, - ucp_Old_Persian, - ucp_Oriya, - ucp_Osmanya, - ucp_Runic, - ucp_Shavian, - ucp_Sinhala, - ucp_Syloti_Nagri, - ucp_Syriac, - ucp_Tagalog, - ucp_Tagbanwa, - ucp_Tai_Le, - ucp_Tamil, - ucp_Telugu, - ucp_Thaana, - ucp_Thai, - ucp_Tibetan, - ucp_Tifinagh, - ucp_Ugaritic, - ucp_Yi, - /* New for Unicode 5.0: */ - ucp_Balinese, - ucp_Cuneiform, - ucp_Nko, - ucp_Phags_Pa, - ucp_Phoenician, - /* New for Unicode 5.1: */ - ucp_Carian, - ucp_Cham, - ucp_Kayah_Li, - ucp_Lepcha, - ucp_Lycian, - ucp_Lydian, - ucp_Ol_Chiki, - ucp_Rejang, - ucp_Saurashtra, - ucp_Sundanese, - ucp_Vai -}; - -#endif - -/* End of ucp.h */ diff --git a/libs/pcre/ucpinternal.h b/libs/pcre/ucpinternal.h deleted file mode 100644 index 16dfbe9b0f..0000000000 --- a/libs/pcre/ucpinternal.h +++ /dev/null @@ -1,87 +0,0 @@ -/************************************************* -* Unicode Property Table handler * -*************************************************/ - -/* Internal header file defining the layout of the bits in each pair of 32-bit -words that form a data item in the table. */ - -typedef struct cnode { - pcre_uint32 f0; - pcre_uint32 f1; -} cnode; - -/* Things for the f0 field */ - -#define f0_scriptmask 0xff000000 /* Mask for script field */ -#define f0_scriptshift 24 /* Shift for script value */ -#define f0_rangeflag 0x00f00000 /* Flag for a range item */ -#define f0_charmask 0x001fffff /* Mask for code point value */ - -/* Things for the f1 field */ - -#define f1_typemask 0xfc000000 /* Mask for char type field */ -#define f1_typeshift 26 /* Shift for the type field */ -#define f1_rangemask 0x0000ffff /* Mask for a range offset */ -#define f1_casemask 0x0000ffff /* Mask for a case offset */ -#define f1_caseneg 0xffff8000 /* Bits for negation */ - -/* The data consists of a vector of structures of type cnode. The two unsigned -32-bit integers are used as follows: - -(f0) (1) The most significant byte holds the script number. The numbers are - defined by the enum in ucp.h. - - (2) The 0x00800000 bit is set if this entry defines a range of characters. - It is not set if this entry defines a single character - - (3) The 0x00600000 bits are spare. - - (4) The 0x001fffff bits contain the code point. No Unicode code point will - ever be greater than 0x0010ffff, so this should be OK for ever. - -(f1) (1) The 0xfc000000 bits contain the character type number. The numbers are - defined by an enum in ucp.h. - - (2) The 0x03ff0000 bits are spare. - - (3) The 0x0000ffff bits contain EITHER the unsigned offset to the top of - range if this entry defines a range, OR the *signed* offset to the - character's "other case" partner if this entry defines a single - character. There is no partner if the value is zero. - -------------------------------------------------------------------------------- -| script (8) |.|.|.| codepoint (21) || type (6) |.|.| spare (8) | offset (16) | -------------------------------------------------------------------------------- - | | | | | - | | |-> spare | |-> spare - | | | - | |-> spare |-> spare - | - |-> range flag - -The upper/lower casing information is set only for characters that come in -pairs. The non-one-to-one mappings in the Unicode data are ignored. - -When searching the data, proceed as follows: - -(1) Set up for a binary chop search. - -(2) If the top is not greater than the bottom, the character is not in the - table. Its type must therefore be "Cn" ("Undefined"). - -(3) Find the middle vector element. - -(4) Extract the code point and compare. If equal, we are done. - -(5) If the test character is smaller, set the top to the current point, and - goto (2). - -(6) If the current entry defines a range, compute the last character by adding - the offset, and see if the test character is within the range. If it is, - we are done. - -(7) Otherwise, set the bottom to one element past the current point and goto - (2). -*/ - -/* End of ucpinternal.h */ diff --git a/libs/pcre/ucptable.c b/libs/pcre/ucptable.c deleted file mode 100644 index ae665b3760..0000000000 --- a/libs/pcre/ucptable.c +++ /dev/null @@ -1,2968 +0,0 @@ -/* This source module is automatically generated from the Unicode -property table. See ucpinternal.h for a description of the layout. */ - -static cnode ucp_table[] = { - { 0x09800000, 0x0000001f }, - { 0x09000020, 0x74000000 }, - { 0x09800021, 0x54000002 }, - { 0x09000024, 0x5c000000 }, - { 0x09800025, 0x54000002 }, - { 0x09000028, 0x58000000 }, - { 0x09000029, 0x48000000 }, - { 0x0900002a, 0x54000000 }, - { 0x0900002b, 0x64000000 }, - { 0x0900002c, 0x54000000 }, - { 0x0900002d, 0x44000000 }, - { 0x0980002e, 0x54000001 }, - { 0x09800030, 0x34000009 }, - { 0x0980003a, 0x54000001 }, - { 0x0980003c, 0x64000002 }, - { 0x0980003f, 0x54000001 }, - { 0x21000041, 0x24000020 }, - { 0x21000042, 0x24000020 }, - { 0x21000043, 0x24000020 }, - { 0x21000044, 0x24000020 }, - { 0x21000045, 0x24000020 }, - { 0x21000046, 0x24000020 }, - { 0x21000047, 0x24000020 }, - { 0x21000048, 0x24000020 }, - { 0x21000049, 0x24000020 }, - { 0x2100004a, 0x24000020 }, - { 0x2100004b, 0x24000020 }, - { 0x2100004c, 0x24000020 }, - { 0x2100004d, 0x24000020 }, - { 0x2100004e, 0x24000020 }, - { 0x2100004f, 0x24000020 }, - { 0x21000050, 0x24000020 }, - { 0x21000051, 0x24000020 }, - { 0x21000052, 0x24000020 }, - { 0x21000053, 0x24000020 }, - { 0x21000054, 0x24000020 }, - { 0x21000055, 0x24000020 }, - { 0x21000056, 0x24000020 }, - { 0x21000057, 0x24000020 }, - { 0x21000058, 0x24000020 }, - { 0x21000059, 0x24000020 }, - { 0x2100005a, 0x24000020 }, - { 0x0900005b, 0x58000000 }, - { 0x0900005c, 0x54000000 }, - { 0x0900005d, 0x48000000 }, - { 0x0900005e, 0x60000000 }, - { 0x0900005f, 0x40000000 }, - { 0x09000060, 0x60000000 }, - { 0x21000061, 0x1400ffe0 }, - { 0x21000062, 0x1400ffe0 }, - { 0x21000063, 0x1400ffe0 }, - { 0x21000064, 0x1400ffe0 }, - { 0x21000065, 0x1400ffe0 }, - { 0x21000066, 0x1400ffe0 }, - { 0x21000067, 0x1400ffe0 }, - { 0x21000068, 0x1400ffe0 }, - { 0x21000069, 0x1400ffe0 }, - { 0x2100006a, 0x1400ffe0 }, - { 0x2100006b, 0x1400ffe0 }, - { 0x2100006c, 0x1400ffe0 }, - { 0x2100006d, 0x1400ffe0 }, - { 0x2100006e, 0x1400ffe0 }, - { 0x2100006f, 0x1400ffe0 }, - { 0x21000070, 0x1400ffe0 }, - { 0x21000071, 0x1400ffe0 }, - { 0x21000072, 0x1400ffe0 }, - { 0x21000073, 0x1400ffe0 }, - { 0x21000074, 0x1400ffe0 }, - { 0x21000075, 0x1400ffe0 }, - { 0x21000076, 0x1400ffe0 }, - { 0x21000077, 0x1400ffe0 }, - { 0x21000078, 0x1400ffe0 }, - { 0x21000079, 0x1400ffe0 }, - { 0x2100007a, 0x1400ffe0 }, - { 0x0900007b, 0x58000000 }, - { 0x0900007c, 0x64000000 }, - { 0x0900007d, 0x48000000 }, - { 0x0900007e, 0x64000000 }, - { 0x0980007f, 0x00000020 }, - { 0x090000a0, 0x74000000 }, - { 0x090000a1, 0x54000000 }, - { 0x098000a2, 0x5c000003 }, - { 0x098000a6, 0x68000001 }, - { 0x090000a8, 0x60000000 }, - { 0x090000a9, 0x68000000 }, - { 0x210000aa, 0x14000000 }, - { 0x090000ab, 0x50000000 }, - { 0x090000ac, 0x64000000 }, - { 0x090000ad, 0x04000000 }, - { 0x090000ae, 0x68000000 }, - { 0x090000af, 0x60000000 }, - { 0x090000b0, 0x68000000 }, - { 0x090000b1, 0x64000000 }, - { 0x098000b2, 0x3c000001 }, - { 0x090000b4, 0x60000000 }, - { 0x090000b5, 0x140002e7 }, - { 0x090000b6, 0x68000000 }, - { 0x090000b7, 0x54000000 }, - { 0x090000b8, 0x60000000 }, - { 0x090000b9, 0x3c000000 }, - { 0x210000ba, 0x14000000 }, - { 0x090000bb, 0x4c000000 }, - { 0x098000bc, 0x3c000002 }, - { 0x090000bf, 0x54000000 }, - { 0x210000c0, 0x24000020 }, - { 0x210000c1, 0x24000020 }, - { 0x210000c2, 0x24000020 }, - { 0x210000c3, 0x24000020 }, - { 0x210000c4, 0x24000020 }, - { 0x210000c5, 0x24000020 }, - { 0x210000c6, 0x24000020 }, - { 0x210000c7, 0x24000020 }, - { 0x210000c8, 0x24000020 }, - { 0x210000c9, 0x24000020 }, - { 0x210000ca, 0x24000020 }, - { 0x210000cb, 0x24000020 }, - { 0x210000cc, 0x24000020 }, - { 0x210000cd, 0x24000020 }, - { 0x210000ce, 0x24000020 }, - { 0x210000cf, 0x24000020 }, - { 0x210000d0, 0x24000020 }, - { 0x210000d1, 0x24000020 }, - { 0x210000d2, 0x24000020 }, - { 0x210000d3, 0x24000020 }, - { 0x210000d4, 0x24000020 }, - { 0x210000d5, 0x24000020 }, - { 0x210000d6, 0x24000020 }, - { 0x090000d7, 0x64000000 }, - { 0x210000d8, 0x24000020 }, - { 0x210000d9, 0x24000020 }, - { 0x210000da, 0x24000020 }, - { 0x210000db, 0x24000020 }, - { 0x210000dc, 0x24000020 }, - { 0x210000dd, 0x24000020 }, - { 0x210000de, 0x24000020 }, - { 0x210000df, 0x14000000 }, - { 0x210000e0, 0x1400ffe0 }, - { 0x210000e1, 0x1400ffe0 }, - { 0x210000e2, 0x1400ffe0 }, - { 0x210000e3, 0x1400ffe0 }, - { 0x210000e4, 0x1400ffe0 }, - { 0x210000e5, 0x1400ffe0 }, - { 0x210000e6, 0x1400ffe0 }, - { 0x210000e7, 0x1400ffe0 }, - { 0x210000e8, 0x1400ffe0 }, - { 0x210000e9, 0x1400ffe0 }, - { 0x210000ea, 0x1400ffe0 }, - { 0x210000eb, 0x1400ffe0 }, - { 0x210000ec, 0x1400ffe0 }, - { 0x210000ed, 0x1400ffe0 }, - { 0x210000ee, 0x1400ffe0 }, - { 0x210000ef, 0x1400ffe0 }, - { 0x210000f0, 0x1400ffe0 }, - { 0x210000f1, 0x1400ffe0 }, - { 0x210000f2, 0x1400ffe0 }, - { 0x210000f3, 0x1400ffe0 }, - { 0x210000f4, 0x1400ffe0 }, - { 0x210000f5, 0x1400ffe0 }, - { 0x210000f6, 0x1400ffe0 }, - { 0x090000f7, 0x64000000 }, - { 0x210000f8, 0x1400ffe0 }, - { 0x210000f9, 0x1400ffe0 }, - { 0x210000fa, 0x1400ffe0 }, - { 0x210000fb, 0x1400ffe0 }, - { 0x210000fc, 0x1400ffe0 }, - { 0x210000fd, 0x1400ffe0 }, - { 0x210000fe, 0x1400ffe0 }, - { 0x210000ff, 0x14000079 }, - { 0x21000100, 0x24000001 }, - { 0x21000101, 0x1400ffff }, - { 0x21000102, 0x24000001 }, - { 0x21000103, 0x1400ffff }, - { 0x21000104, 0x24000001 }, - { 0x21000105, 0x1400ffff }, - { 0x21000106, 0x24000001 }, - { 0x21000107, 0x1400ffff }, - { 0x21000108, 0x24000001 }, - { 0x21000109, 0x1400ffff }, - { 0x2100010a, 0x24000001 }, - { 0x2100010b, 0x1400ffff }, - { 0x2100010c, 0x24000001 }, - { 0x2100010d, 0x1400ffff }, - { 0x2100010e, 0x24000001 }, - { 0x2100010f, 0x1400ffff }, - { 0x21000110, 0x24000001 }, - { 0x21000111, 0x1400ffff }, - { 0x21000112, 0x24000001 }, - { 0x21000113, 0x1400ffff }, - { 0x21000114, 0x24000001 }, - { 0x21000115, 0x1400ffff }, - { 0x21000116, 0x24000001 }, - { 0x21000117, 0x1400ffff }, - { 0x21000118, 0x24000001 }, - { 0x21000119, 0x1400ffff }, - { 0x2100011a, 0x24000001 }, - { 0x2100011b, 0x1400ffff }, - { 0x2100011c, 0x24000001 }, - { 0x2100011d, 0x1400ffff }, - { 0x2100011e, 0x24000001 }, - { 0x2100011f, 0x1400ffff }, - { 0x21000120, 0x24000001 }, - { 0x21000121, 0x1400ffff }, - { 0x21000122, 0x24000001 }, - { 0x21000123, 0x1400ffff }, - { 0x21000124, 0x24000001 }, - { 0x21000125, 0x1400ffff }, - { 0x21000126, 0x24000001 }, - { 0x21000127, 0x1400ffff }, - { 0x21000128, 0x24000001 }, - { 0x21000129, 0x1400ffff }, - { 0x2100012a, 0x24000001 }, - { 0x2100012b, 0x1400ffff }, - { 0x2100012c, 0x24000001 }, - { 0x2100012d, 0x1400ffff }, - { 0x2100012e, 0x24000001 }, - { 0x2100012f, 0x1400ffff }, - { 0x21000130, 0x2400ff39 }, - { 0x21000131, 0x1400ff18 }, - { 0x21000132, 0x24000001 }, - { 0x21000133, 0x1400ffff }, - { 0x21000134, 0x24000001 }, - { 0x21000135, 0x1400ffff }, - { 0x21000136, 0x24000001 }, - { 0x21000137, 0x1400ffff }, - { 0x21000138, 0x14000000 }, - { 0x21000139, 0x24000001 }, - { 0x2100013a, 0x1400ffff }, - { 0x2100013b, 0x24000001 }, - { 0x2100013c, 0x1400ffff }, - { 0x2100013d, 0x24000001 }, - { 0x2100013e, 0x1400ffff }, - { 0x2100013f, 0x24000001 }, - { 0x21000140, 0x1400ffff }, - { 0x21000141, 0x24000001 }, - { 0x21000142, 0x1400ffff }, - { 0x21000143, 0x24000001 }, - { 0x21000144, 0x1400ffff }, - { 0x21000145, 0x24000001 }, - { 0x21000146, 0x1400ffff }, - { 0x21000147, 0x24000001 }, - { 0x21000148, 0x1400ffff }, - { 0x21000149, 0x14000000 }, - { 0x2100014a, 0x24000001 }, - { 0x2100014b, 0x1400ffff }, - { 0x2100014c, 0x24000001 }, - { 0x2100014d, 0x1400ffff }, - { 0x2100014e, 0x24000001 }, - { 0x2100014f, 0x1400ffff }, - { 0x21000150, 0x24000001 }, - { 0x21000151, 0x1400ffff }, - { 0x21000152, 0x24000001 }, - { 0x21000153, 0x1400ffff }, - { 0x21000154, 0x24000001 }, - { 0x21000155, 0x1400ffff }, - { 0x21000156, 0x24000001 }, - { 0x21000157, 0x1400ffff }, - { 0x21000158, 0x24000001 }, - { 0x21000159, 0x1400ffff }, - { 0x2100015a, 0x24000001 }, - { 0x2100015b, 0x1400ffff }, - { 0x2100015c, 0x24000001 }, - { 0x2100015d, 0x1400ffff }, - { 0x2100015e, 0x24000001 }, - { 0x2100015f, 0x1400ffff }, - { 0x21000160, 0x24000001 }, - { 0x21000161, 0x1400ffff }, - { 0x21000162, 0x24000001 }, - { 0x21000163, 0x1400ffff }, - { 0x21000164, 0x24000001 }, - { 0x21000165, 0x1400ffff }, - { 0x21000166, 0x24000001 }, - { 0x21000167, 0x1400ffff }, - { 0x21000168, 0x24000001 }, - { 0x21000169, 0x1400ffff }, - { 0x2100016a, 0x24000001 }, - { 0x2100016b, 0x1400ffff }, - { 0x2100016c, 0x24000001 }, - { 0x2100016d, 0x1400ffff }, - { 0x2100016e, 0x24000001 }, - { 0x2100016f, 0x1400ffff }, - { 0x21000170, 0x24000001 }, - { 0x21000171, 0x1400ffff }, - { 0x21000172, 0x24000001 }, - { 0x21000173, 0x1400ffff }, - { 0x21000174, 0x24000001 }, - { 0x21000175, 0x1400ffff }, - { 0x21000176, 0x24000001 }, - { 0x21000177, 0x1400ffff }, - { 0x21000178, 0x2400ff87 }, - { 0x21000179, 0x24000001 }, - { 0x2100017a, 0x1400ffff }, - { 0x2100017b, 0x24000001 }, - { 0x2100017c, 0x1400ffff }, - { 0x2100017d, 0x24000001 }, - { 0x2100017e, 0x1400ffff }, - { 0x2100017f, 0x1400fed4 }, - { 0x21000180, 0x14000000 }, - { 0x21000181, 0x240000d2 }, - { 0x21000182, 0x24000001 }, - { 0x21000183, 0x1400ffff }, - { 0x21000184, 0x24000001 }, - { 0x21000185, 0x1400ffff }, - { 0x21000186, 0x240000ce }, - { 0x21000187, 0x24000001 }, - { 0x21000188, 0x1400ffff }, - { 0x21000189, 0x240000cd }, - { 0x2100018a, 0x240000cd }, - { 0x2100018b, 0x24000001 }, - { 0x2100018c, 0x1400ffff }, - { 0x2100018d, 0x14000000 }, - { 0x2100018e, 0x2400004f }, - { 0x2100018f, 0x240000ca }, - { 0x21000190, 0x240000cb }, - { 0x21000191, 0x24000001 }, - { 0x21000192, 0x1400ffff }, - { 0x21000193, 0x240000cd }, - { 0x21000194, 0x240000cf }, - { 0x21000195, 0x14000061 }, - { 0x21000196, 0x240000d3 }, - { 0x21000197, 0x240000d1 }, - { 0x21000198, 0x24000001 }, - { 0x21000199, 0x1400ffff }, - { 0x2100019a, 0x140000a3 }, - { 0x2100019b, 0x14000000 }, - { 0x2100019c, 0x240000d3 }, - { 0x2100019d, 0x240000d5 }, - { 0x2100019e, 0x14000082 }, - { 0x2100019f, 0x240000d6 }, - { 0x210001a0, 0x24000001 }, - { 0x210001a1, 0x1400ffff }, - { 0x210001a2, 0x24000001 }, - { 0x210001a3, 0x1400ffff }, - { 0x210001a4, 0x24000001 }, - { 0x210001a5, 0x1400ffff }, - { 0x210001a6, 0x240000da }, - { 0x210001a7, 0x24000001 }, - { 0x210001a8, 0x1400ffff }, - { 0x210001a9, 0x240000da }, - { 0x218001aa, 0x14000001 }, - { 0x210001ac, 0x24000001 }, - { 0x210001ad, 0x1400ffff }, - { 0x210001ae, 0x240000da }, - { 0x210001af, 0x24000001 }, - { 0x210001b0, 0x1400ffff }, - { 0x210001b1, 0x240000d9 }, - { 0x210001b2, 0x240000d9 }, - { 0x210001b3, 0x24000001 }, - { 0x210001b4, 0x1400ffff }, - { 0x210001b5, 0x24000001 }, - { 0x210001b6, 0x1400ffff }, - { 0x210001b7, 0x240000db }, - { 0x210001b8, 0x24000001 }, - { 0x210001b9, 0x1400ffff }, - { 0x210001ba, 0x14000000 }, - { 0x210001bb, 0x1c000000 }, - { 0x210001bc, 0x24000001 }, - { 0x210001bd, 0x1400ffff }, - { 0x210001be, 0x14000000 }, - { 0x210001bf, 0x14000038 }, - { 0x218001c0, 0x1c000003 }, - { 0x210001c4, 0x24000002 }, - { 0x210001c5, 0x2000ffff }, - { 0x210001c6, 0x1400fffe }, - { 0x210001c7, 0x24000002 }, - { 0x210001c8, 0x2000ffff }, - { 0x210001c9, 0x1400fffe }, - { 0x210001ca, 0x24000002 }, - { 0x210001cb, 0x2000ffff }, - { 0x210001cc, 0x1400fffe }, - { 0x210001cd, 0x24000001 }, - { 0x210001ce, 0x1400ffff }, - { 0x210001cf, 0x24000001 }, - { 0x210001d0, 0x1400ffff }, - { 0x210001d1, 0x24000001 }, - { 0x210001d2, 0x1400ffff }, - { 0x210001d3, 0x24000001 }, - { 0x210001d4, 0x1400ffff }, - { 0x210001d5, 0x24000001 }, - { 0x210001d6, 0x1400ffff }, - { 0x210001d7, 0x24000001 }, - { 0x210001d8, 0x1400ffff }, - { 0x210001d9, 0x24000001 }, - { 0x210001da, 0x1400ffff }, - { 0x210001db, 0x24000001 }, - { 0x210001dc, 0x1400ffff }, - { 0x210001dd, 0x1400ffb1 }, - { 0x210001de, 0x24000001 }, - { 0x210001df, 0x1400ffff }, - { 0x210001e0, 0x24000001 }, - { 0x210001e1, 0x1400ffff }, - { 0x210001e2, 0x24000001 }, - { 0x210001e3, 0x1400ffff }, - { 0x210001e4, 0x24000001 }, - { 0x210001e5, 0x1400ffff }, - { 0x210001e6, 0x24000001 }, - { 0x210001e7, 0x1400ffff }, - { 0x210001e8, 0x24000001 }, - { 0x210001e9, 0x1400ffff }, - { 0x210001ea, 0x24000001 }, - { 0x210001eb, 0x1400ffff }, - { 0x210001ec, 0x24000001 }, - { 0x210001ed, 0x1400ffff }, - { 0x210001ee, 0x24000001 }, - { 0x210001ef, 0x1400ffff }, - { 0x210001f0, 0x14000000 }, - { 0x210001f1, 0x24000002 }, - { 0x210001f2, 0x2000ffff }, - { 0x210001f3, 0x1400fffe }, - { 0x210001f4, 0x24000001 }, - { 0x210001f5, 0x1400ffff }, - { 0x210001f6, 0x2400ff9f }, - { 0x210001f7, 0x2400ffc8 }, - { 0x210001f8, 0x24000001 }, - { 0x210001f9, 0x1400ffff }, - { 0x210001fa, 0x24000001 }, - { 0x210001fb, 0x1400ffff }, - { 0x210001fc, 0x24000001 }, - { 0x210001fd, 0x1400ffff }, - { 0x210001fe, 0x24000001 }, - { 0x210001ff, 0x1400ffff }, - { 0x21000200, 0x24000001 }, - { 0x21000201, 0x1400ffff }, - { 0x21000202, 0x24000001 }, - { 0x21000203, 0x1400ffff }, - { 0x21000204, 0x24000001 }, - { 0x21000205, 0x1400ffff }, - { 0x21000206, 0x24000001 }, - { 0x21000207, 0x1400ffff }, - { 0x21000208, 0x24000001 }, - { 0x21000209, 0x1400ffff }, - { 0x2100020a, 0x24000001 }, - { 0x2100020b, 0x1400ffff }, - { 0x2100020c, 0x24000001 }, - { 0x2100020d, 0x1400ffff }, - { 0x2100020e, 0x24000001 }, - { 0x2100020f, 0x1400ffff }, - { 0x21000210, 0x24000001 }, - { 0x21000211, 0x1400ffff }, - { 0x21000212, 0x24000001 }, - { 0x21000213, 0x1400ffff }, - { 0x21000214, 0x24000001 }, - { 0x21000215, 0x1400ffff }, - { 0x21000216, 0x24000001 }, - { 0x21000217, 0x1400ffff }, - { 0x21000218, 0x24000001 }, - { 0x21000219, 0x1400ffff }, - { 0x2100021a, 0x24000001 }, - { 0x2100021b, 0x1400ffff }, - { 0x2100021c, 0x24000001 }, - { 0x2100021d, 0x1400ffff }, - { 0x2100021e, 0x24000001 }, - { 0x2100021f, 0x1400ffff }, - { 0x21000220, 0x2400ff7e }, - { 0x21000221, 0x14000000 }, - { 0x21000222, 0x24000001 }, - { 0x21000223, 0x1400ffff }, - { 0x21000224, 0x24000001 }, - { 0x21000225, 0x1400ffff }, - { 0x21000226, 0x24000001 }, - { 0x21000227, 0x1400ffff }, - { 0x21000228, 0x24000001 }, - { 0x21000229, 0x1400ffff }, - { 0x2100022a, 0x24000001 }, - { 0x2100022b, 0x1400ffff }, - { 0x2100022c, 0x24000001 }, - { 0x2100022d, 0x1400ffff }, - { 0x2100022e, 0x24000001 }, - { 0x2100022f, 0x1400ffff }, - { 0x21000230, 0x24000001 }, - { 0x21000231, 0x1400ffff }, - { 0x21000232, 0x24000001 }, - { 0x21000233, 0x1400ffff }, - { 0x21800234, 0x14000005 }, - { 0x2100023a, 0x24000000 }, - { 0x2100023b, 0x24000001 }, - { 0x2100023c, 0x1400ffff }, - { 0x2100023d, 0x2400ff5d }, - { 0x2100023e, 0x24000000 }, - { 0x2180023f, 0x14000001 }, - { 0x21000241, 0x24000053 }, - { 0x21800250, 0x14000002 }, - { 0x21000253, 0x1400ff2e }, - { 0x21000254, 0x1400ff32 }, - { 0x21000255, 0x14000000 }, - { 0x21000256, 0x1400ff33 }, - { 0x21000257, 0x1400ff33 }, - { 0x21000258, 0x14000000 }, - { 0x21000259, 0x1400ff36 }, - { 0x2100025a, 0x14000000 }, - { 0x2100025b, 0x1400ff35 }, - { 0x2180025c, 0x14000003 }, - { 0x21000260, 0x1400ff33 }, - { 0x21800261, 0x14000001 }, - { 0x21000263, 0x1400ff31 }, - { 0x21800264, 0x14000003 }, - { 0x21000268, 0x1400ff2f }, - { 0x21000269, 0x1400ff2d }, - { 0x2180026a, 0x14000004 }, - { 0x2100026f, 0x1400ff2d }, - { 0x21800270, 0x14000001 }, - { 0x21000272, 0x1400ff2b }, - { 0x21800273, 0x14000001 }, - { 0x21000275, 0x1400ff2a }, - { 0x21800276, 0x14000009 }, - { 0x21000280, 0x1400ff26 }, - { 0x21800281, 0x14000001 }, - { 0x21000283, 0x1400ff26 }, - { 0x21800284, 0x14000003 }, - { 0x21000288, 0x1400ff26 }, - { 0x21000289, 0x14000000 }, - { 0x2100028a, 0x1400ff27 }, - { 0x2100028b, 0x1400ff27 }, - { 0x2180028c, 0x14000005 }, - { 0x21000292, 0x1400ff25 }, - { 0x21000293, 0x14000000 }, - { 0x21000294, 0x1400ffad }, - { 0x21800295, 0x1400001a }, - { 0x218002b0, 0x18000011 }, - { 0x098002c2, 0x60000003 }, - { 0x098002c6, 0x1800000b }, - { 0x098002d2, 0x6000000d }, - { 0x218002e0, 0x18000004 }, - { 0x098002e5, 0x60000008 }, - { 0x090002ee, 0x18000000 }, - { 0x098002ef, 0x60000010 }, - { 0x1b800300, 0x30000044 }, - { 0x1b000345, 0x30000054 }, - { 0x1b800346, 0x30000029 }, - { 0x13800374, 0x60000001 }, - { 0x1300037a, 0x18000000 }, - { 0x0900037e, 0x54000000 }, - { 0x13800384, 0x60000001 }, - { 0x13000386, 0x24000026 }, - { 0x09000387, 0x54000000 }, - { 0x13000388, 0x24000025 }, - { 0x13000389, 0x24000025 }, - { 0x1300038a, 0x24000025 }, - { 0x1300038c, 0x24000040 }, - { 0x1300038e, 0x2400003f }, - { 0x1300038f, 0x2400003f }, - { 0x13000390, 0x14000000 }, - { 0x13000391, 0x24000020 }, - { 0x13000392, 0x24000020 }, - { 0x13000393, 0x24000020 }, - { 0x13000394, 0x24000020 }, - { 0x13000395, 0x24000020 }, - { 0x13000396, 0x24000020 }, - { 0x13000397, 0x24000020 }, - { 0x13000398, 0x24000020 }, - { 0x13000399, 0x24000020 }, - { 0x1300039a, 0x24000020 }, - { 0x1300039b, 0x24000020 }, - { 0x1300039c, 0x24000020 }, - { 0x1300039d, 0x24000020 }, - { 0x1300039e, 0x24000020 }, - { 0x1300039f, 0x24000020 }, - { 0x130003a0, 0x24000020 }, - { 0x130003a1, 0x24000020 }, - { 0x130003a3, 0x24000020 }, - { 0x130003a4, 0x24000020 }, - { 0x130003a5, 0x24000020 }, - { 0x130003a6, 0x24000020 }, - { 0x130003a7, 0x24000020 }, - { 0x130003a8, 0x24000020 }, - { 0x130003a9, 0x24000020 }, - { 0x130003aa, 0x24000020 }, - { 0x130003ab, 0x24000020 }, - { 0x130003ac, 0x1400ffda }, - { 0x130003ad, 0x1400ffdb }, - { 0x130003ae, 0x1400ffdb }, - { 0x130003af, 0x1400ffdb }, - { 0x130003b0, 0x14000000 }, - { 0x130003b1, 0x1400ffe0 }, - { 0x130003b2, 0x1400ffe0 }, - { 0x130003b3, 0x1400ffe0 }, - { 0x130003b4, 0x1400ffe0 }, - { 0x130003b5, 0x1400ffe0 }, - { 0x130003b6, 0x1400ffe0 }, - { 0x130003b7, 0x1400ffe0 }, - { 0x130003b8, 0x1400ffe0 }, - { 0x130003b9, 0x1400ffe0 }, - { 0x130003ba, 0x1400ffe0 }, - { 0x130003bb, 0x1400ffe0 }, - { 0x130003bc, 0x1400ffe0 }, - { 0x130003bd, 0x1400ffe0 }, - { 0x130003be, 0x1400ffe0 }, - { 0x130003bf, 0x1400ffe0 }, - { 0x130003c0, 0x1400ffe0 }, - { 0x130003c1, 0x1400ffe0 }, - { 0x130003c2, 0x1400ffe1 }, - { 0x130003c3, 0x1400ffe0 }, - { 0x130003c4, 0x1400ffe0 }, - { 0x130003c5, 0x1400ffe0 }, - { 0x130003c6, 0x1400ffe0 }, - { 0x130003c7, 0x1400ffe0 }, - { 0x130003c8, 0x1400ffe0 }, - { 0x130003c9, 0x1400ffe0 }, - { 0x130003ca, 0x1400ffe0 }, - { 0x130003cb, 0x1400ffe0 }, - { 0x130003cc, 0x1400ffc0 }, - { 0x130003cd, 0x1400ffc1 }, - { 0x130003ce, 0x1400ffc1 }, - { 0x130003d0, 0x1400ffc2 }, - { 0x130003d1, 0x1400ffc7 }, - { 0x138003d2, 0x24000002 }, - { 0x130003d5, 0x1400ffd1 }, - { 0x130003d6, 0x1400ffca }, - { 0x130003d7, 0x14000000 }, - { 0x130003d8, 0x24000001 }, - { 0x130003d9, 0x1400ffff }, - { 0x130003da, 0x24000001 }, - { 0x130003db, 0x1400ffff }, - { 0x130003dc, 0x24000001 }, - { 0x130003dd, 0x1400ffff }, - { 0x130003de, 0x24000001 }, - { 0x130003df, 0x1400ffff }, - { 0x130003e0, 0x24000001 }, - { 0x130003e1, 0x1400ffff }, - { 0x0a0003e2, 0x24000001 }, - { 0x0a0003e3, 0x1400ffff }, - { 0x0a0003e4, 0x24000001 }, - { 0x0a0003e5, 0x1400ffff }, - { 0x0a0003e6, 0x24000001 }, - { 0x0a0003e7, 0x1400ffff }, - { 0x0a0003e8, 0x24000001 }, - { 0x0a0003e9, 0x1400ffff }, - { 0x0a0003ea, 0x24000001 }, - { 0x0a0003eb, 0x1400ffff }, - { 0x0a0003ec, 0x24000001 }, - { 0x0a0003ed, 0x1400ffff }, - { 0x0a0003ee, 0x24000001 }, - { 0x0a0003ef, 0x1400ffff }, - { 0x130003f0, 0x1400ffaa }, - { 0x130003f1, 0x1400ffb0 }, - { 0x130003f2, 0x14000007 }, - { 0x130003f3, 0x14000000 }, - { 0x130003f4, 0x2400ffc4 }, - { 0x130003f5, 0x1400ffa0 }, - { 0x130003f6, 0x64000000 }, - { 0x130003f7, 0x24000001 }, - { 0x130003f8, 0x1400ffff }, - { 0x130003f9, 0x2400fff9 }, - { 0x130003fa, 0x24000001 }, - { 0x130003fb, 0x1400ffff }, - { 0x130003fc, 0x14000000 }, - { 0x138003fd, 0x24000002 }, - { 0x0c000400, 0x24000050 }, - { 0x0c000401, 0x24000050 }, - { 0x0c000402, 0x24000050 }, - { 0x0c000403, 0x24000050 }, - { 0x0c000404, 0x24000050 }, - { 0x0c000405, 0x24000050 }, - { 0x0c000406, 0x24000050 }, - { 0x0c000407, 0x24000050 }, - { 0x0c000408, 0x24000050 }, - { 0x0c000409, 0x24000050 }, - { 0x0c00040a, 0x24000050 }, - { 0x0c00040b, 0x24000050 }, - { 0x0c00040c, 0x24000050 }, - { 0x0c00040d, 0x24000050 }, - { 0x0c00040e, 0x24000050 }, - { 0x0c00040f, 0x24000050 }, - { 0x0c000410, 0x24000020 }, - { 0x0c000411, 0x24000020 }, - { 0x0c000412, 0x24000020 }, - { 0x0c000413, 0x24000020 }, - { 0x0c000414, 0x24000020 }, - { 0x0c000415, 0x24000020 }, - { 0x0c000416, 0x24000020 }, - { 0x0c000417, 0x24000020 }, - { 0x0c000418, 0x24000020 }, - { 0x0c000419, 0x24000020 }, - { 0x0c00041a, 0x24000020 }, - { 0x0c00041b, 0x24000020 }, - { 0x0c00041c, 0x24000020 }, - { 0x0c00041d, 0x24000020 }, - { 0x0c00041e, 0x24000020 }, - { 0x0c00041f, 0x24000020 }, - { 0x0c000420, 0x24000020 }, - { 0x0c000421, 0x24000020 }, - { 0x0c000422, 0x24000020 }, - { 0x0c000423, 0x24000020 }, - { 0x0c000424, 0x24000020 }, - { 0x0c000425, 0x24000020 }, - { 0x0c000426, 0x24000020 }, - { 0x0c000427, 0x24000020 }, - { 0x0c000428, 0x24000020 }, - { 0x0c000429, 0x24000020 }, - { 0x0c00042a, 0x24000020 }, - { 0x0c00042b, 0x24000020 }, - { 0x0c00042c, 0x24000020 }, - { 0x0c00042d, 0x24000020 }, - { 0x0c00042e, 0x24000020 }, - { 0x0c00042f, 0x24000020 }, - { 0x0c000430, 0x1400ffe0 }, - { 0x0c000431, 0x1400ffe0 }, - { 0x0c000432, 0x1400ffe0 }, - { 0x0c000433, 0x1400ffe0 }, - { 0x0c000434, 0x1400ffe0 }, - { 0x0c000435, 0x1400ffe0 }, - { 0x0c000436, 0x1400ffe0 }, - { 0x0c000437, 0x1400ffe0 }, - { 0x0c000438, 0x1400ffe0 }, - { 0x0c000439, 0x1400ffe0 }, - { 0x0c00043a, 0x1400ffe0 }, - { 0x0c00043b, 0x1400ffe0 }, - { 0x0c00043c, 0x1400ffe0 }, - { 0x0c00043d, 0x1400ffe0 }, - { 0x0c00043e, 0x1400ffe0 }, - { 0x0c00043f, 0x1400ffe0 }, - { 0x0c000440, 0x1400ffe0 }, - { 0x0c000441, 0x1400ffe0 }, - { 0x0c000442, 0x1400ffe0 }, - { 0x0c000443, 0x1400ffe0 }, - { 0x0c000444, 0x1400ffe0 }, - { 0x0c000445, 0x1400ffe0 }, - { 0x0c000446, 0x1400ffe0 }, - { 0x0c000447, 0x1400ffe0 }, - { 0x0c000448, 0x1400ffe0 }, - { 0x0c000449, 0x1400ffe0 }, - { 0x0c00044a, 0x1400ffe0 }, - { 0x0c00044b, 0x1400ffe0 }, - { 0x0c00044c, 0x1400ffe0 }, - { 0x0c00044d, 0x1400ffe0 }, - { 0x0c00044e, 0x1400ffe0 }, - { 0x0c00044f, 0x1400ffe0 }, - { 0x0c000450, 0x1400ffb0 }, - { 0x0c000451, 0x1400ffb0 }, - { 0x0c000452, 0x1400ffb0 }, - { 0x0c000453, 0x1400ffb0 }, - { 0x0c000454, 0x1400ffb0 }, - { 0x0c000455, 0x1400ffb0 }, - { 0x0c000456, 0x1400ffb0 }, - { 0x0c000457, 0x1400ffb0 }, - { 0x0c000458, 0x1400ffb0 }, - { 0x0c000459, 0x1400ffb0 }, - { 0x0c00045a, 0x1400ffb0 }, - { 0x0c00045b, 0x1400ffb0 }, - { 0x0c00045c, 0x1400ffb0 }, - { 0x0c00045d, 0x1400ffb0 }, - { 0x0c00045e, 0x1400ffb0 }, - { 0x0c00045f, 0x1400ffb0 }, - { 0x0c000460, 0x24000001 }, - { 0x0c000461, 0x1400ffff }, - { 0x0c000462, 0x24000001 }, - { 0x0c000463, 0x1400ffff }, - { 0x0c000464, 0x24000001 }, - { 0x0c000465, 0x1400ffff }, - { 0x0c000466, 0x24000001 }, - { 0x0c000467, 0x1400ffff }, - { 0x0c000468, 0x24000001 }, - { 0x0c000469, 0x1400ffff }, - { 0x0c00046a, 0x24000001 }, - { 0x0c00046b, 0x1400ffff }, - { 0x0c00046c, 0x24000001 }, - { 0x0c00046d, 0x1400ffff }, - { 0x0c00046e, 0x24000001 }, - { 0x0c00046f, 0x1400ffff }, - { 0x0c000470, 0x24000001 }, - { 0x0c000471, 0x1400ffff }, - { 0x0c000472, 0x24000001 }, - { 0x0c000473, 0x1400ffff }, - { 0x0c000474, 0x24000001 }, - { 0x0c000475, 0x1400ffff }, - { 0x0c000476, 0x24000001 }, - { 0x0c000477, 0x1400ffff }, - { 0x0c000478, 0x24000001 }, - { 0x0c000479, 0x1400ffff }, - { 0x0c00047a, 0x24000001 }, - { 0x0c00047b, 0x1400ffff }, - { 0x0c00047c, 0x24000001 }, - { 0x0c00047d, 0x1400ffff }, - { 0x0c00047e, 0x24000001 }, - { 0x0c00047f, 0x1400ffff }, - { 0x0c000480, 0x24000001 }, - { 0x0c000481, 0x1400ffff }, - { 0x0c000482, 0x68000000 }, - { 0x0c800483, 0x30000003 }, - { 0x0c800488, 0x2c000001 }, - { 0x0c00048a, 0x24000001 }, - { 0x0c00048b, 0x1400ffff }, - { 0x0c00048c, 0x24000001 }, - { 0x0c00048d, 0x1400ffff }, - { 0x0c00048e, 0x24000001 }, - { 0x0c00048f, 0x1400ffff }, - { 0x0c000490, 0x24000001 }, - { 0x0c000491, 0x1400ffff }, - { 0x0c000492, 0x24000001 }, - { 0x0c000493, 0x1400ffff }, - { 0x0c000494, 0x24000001 }, - { 0x0c000495, 0x1400ffff }, - { 0x0c000496, 0x24000001 }, - { 0x0c000497, 0x1400ffff }, - { 0x0c000498, 0x24000001 }, - { 0x0c000499, 0x1400ffff }, - { 0x0c00049a, 0x24000001 }, - { 0x0c00049b, 0x1400ffff }, - { 0x0c00049c, 0x24000001 }, - { 0x0c00049d, 0x1400ffff }, - { 0x0c00049e, 0x24000001 }, - { 0x0c00049f, 0x1400ffff }, - { 0x0c0004a0, 0x24000001 }, - { 0x0c0004a1, 0x1400ffff }, - { 0x0c0004a2, 0x24000001 }, - { 0x0c0004a3, 0x1400ffff }, - { 0x0c0004a4, 0x24000001 }, - { 0x0c0004a5, 0x1400ffff }, - { 0x0c0004a6, 0x24000001 }, - { 0x0c0004a7, 0x1400ffff }, - { 0x0c0004a8, 0x24000001 }, - { 0x0c0004a9, 0x1400ffff }, - { 0x0c0004aa, 0x24000001 }, - { 0x0c0004ab, 0x1400ffff }, - { 0x0c0004ac, 0x24000001 }, - { 0x0c0004ad, 0x1400ffff }, - { 0x0c0004ae, 0x24000001 }, - { 0x0c0004af, 0x1400ffff }, - { 0x0c0004b0, 0x24000001 }, - { 0x0c0004b1, 0x1400ffff }, - { 0x0c0004b2, 0x24000001 }, - { 0x0c0004b3, 0x1400ffff }, - { 0x0c0004b4, 0x24000001 }, - { 0x0c0004b5, 0x1400ffff }, - { 0x0c0004b6, 0x24000001 }, - { 0x0c0004b7, 0x1400ffff }, - { 0x0c0004b8, 0x24000001 }, - { 0x0c0004b9, 0x1400ffff }, - { 0x0c0004ba, 0x24000001 }, - { 0x0c0004bb, 0x1400ffff }, - { 0x0c0004bc, 0x24000001 }, - { 0x0c0004bd, 0x1400ffff }, - { 0x0c0004be, 0x24000001 }, - { 0x0c0004bf, 0x1400ffff }, - { 0x0c0004c0, 0x24000000 }, - { 0x0c0004c1, 0x24000001 }, - { 0x0c0004c2, 0x1400ffff }, - { 0x0c0004c3, 0x24000001 }, - { 0x0c0004c4, 0x1400ffff }, - { 0x0c0004c5, 0x24000001 }, - { 0x0c0004c6, 0x1400ffff }, - { 0x0c0004c7, 0x24000001 }, - { 0x0c0004c8, 0x1400ffff }, - { 0x0c0004c9, 0x24000001 }, - { 0x0c0004ca, 0x1400ffff }, - { 0x0c0004cb, 0x24000001 }, - { 0x0c0004cc, 0x1400ffff }, - { 0x0c0004cd, 0x24000001 }, - { 0x0c0004ce, 0x1400ffff }, - { 0x0c0004d0, 0x24000001 }, - { 0x0c0004d1, 0x1400ffff }, - { 0x0c0004d2, 0x24000001 }, - { 0x0c0004d3, 0x1400ffff }, - { 0x0c0004d4, 0x24000001 }, - { 0x0c0004d5, 0x1400ffff }, - { 0x0c0004d6, 0x24000001 }, - { 0x0c0004d7, 0x1400ffff }, - { 0x0c0004d8, 0x24000001 }, - { 0x0c0004d9, 0x1400ffff }, - { 0x0c0004da, 0x24000001 }, - { 0x0c0004db, 0x1400ffff }, - { 0x0c0004dc, 0x24000001 }, - { 0x0c0004dd, 0x1400ffff }, - { 0x0c0004de, 0x24000001 }, - { 0x0c0004df, 0x1400ffff }, - { 0x0c0004e0, 0x24000001 }, - { 0x0c0004e1, 0x1400ffff }, - { 0x0c0004e2, 0x24000001 }, - { 0x0c0004e3, 0x1400ffff }, - { 0x0c0004e4, 0x24000001 }, - { 0x0c0004e5, 0x1400ffff }, - { 0x0c0004e6, 0x24000001 }, - { 0x0c0004e7, 0x1400ffff }, - { 0x0c0004e8, 0x24000001 }, - { 0x0c0004e9, 0x1400ffff }, - { 0x0c0004ea, 0x24000001 }, - { 0x0c0004eb, 0x1400ffff }, - { 0x0c0004ec, 0x24000001 }, - { 0x0c0004ed, 0x1400ffff }, - { 0x0c0004ee, 0x24000001 }, - { 0x0c0004ef, 0x1400ffff }, - { 0x0c0004f0, 0x24000001 }, - { 0x0c0004f1, 0x1400ffff }, - { 0x0c0004f2, 0x24000001 }, - { 0x0c0004f3, 0x1400ffff }, - { 0x0c0004f4, 0x24000001 }, - { 0x0c0004f5, 0x1400ffff }, - { 0x0c0004f6, 0x24000001 }, - { 0x0c0004f7, 0x1400ffff }, - { 0x0c0004f8, 0x24000001 }, - { 0x0c0004f9, 0x1400ffff }, - { 0x0c000500, 0x24000001 }, - { 0x0c000501, 0x1400ffff }, - { 0x0c000502, 0x24000001 }, - { 0x0c000503, 0x1400ffff }, - { 0x0c000504, 0x24000001 }, - { 0x0c000505, 0x1400ffff }, - { 0x0c000506, 0x24000001 }, - { 0x0c000507, 0x1400ffff }, - { 0x0c000508, 0x24000001 }, - { 0x0c000509, 0x1400ffff }, - { 0x0c00050a, 0x24000001 }, - { 0x0c00050b, 0x1400ffff }, - { 0x0c00050c, 0x24000001 }, - { 0x0c00050d, 0x1400ffff }, - { 0x0c00050e, 0x24000001 }, - { 0x0c00050f, 0x1400ffff }, - { 0x01000531, 0x24000030 }, - { 0x01000532, 0x24000030 }, - { 0x01000533, 0x24000030 }, - { 0x01000534, 0x24000030 }, - { 0x01000535, 0x24000030 }, - { 0x01000536, 0x24000030 }, - { 0x01000537, 0x24000030 }, - { 0x01000538, 0x24000030 }, - { 0x01000539, 0x24000030 }, - { 0x0100053a, 0x24000030 }, - { 0x0100053b, 0x24000030 }, - { 0x0100053c, 0x24000030 }, - { 0x0100053d, 0x24000030 }, - { 0x0100053e, 0x24000030 }, - { 0x0100053f, 0x24000030 }, - { 0x01000540, 0x24000030 }, - { 0x01000541, 0x24000030 }, - { 0x01000542, 0x24000030 }, - { 0x01000543, 0x24000030 }, - { 0x01000544, 0x24000030 }, - { 0x01000545, 0x24000030 }, - { 0x01000546, 0x24000030 }, - { 0x01000547, 0x24000030 }, - { 0x01000548, 0x24000030 }, - { 0x01000549, 0x24000030 }, - { 0x0100054a, 0x24000030 }, - { 0x0100054b, 0x24000030 }, - { 0x0100054c, 0x24000030 }, - { 0x0100054d, 0x24000030 }, - { 0x0100054e, 0x24000030 }, - { 0x0100054f, 0x24000030 }, - { 0x01000550, 0x24000030 }, - { 0x01000551, 0x24000030 }, - { 0x01000552, 0x24000030 }, - { 0x01000553, 0x24000030 }, - { 0x01000554, 0x24000030 }, - { 0x01000555, 0x24000030 }, - { 0x01000556, 0x24000030 }, - { 0x01000559, 0x18000000 }, - { 0x0180055a, 0x54000005 }, - { 0x01000561, 0x1400ffd0 }, - { 0x01000562, 0x1400ffd0 }, - { 0x01000563, 0x1400ffd0 }, - { 0x01000564, 0x1400ffd0 }, - { 0x01000565, 0x1400ffd0 }, - { 0x01000566, 0x1400ffd0 }, - { 0x01000567, 0x1400ffd0 }, - { 0x01000568, 0x1400ffd0 }, - { 0x01000569, 0x1400ffd0 }, - { 0x0100056a, 0x1400ffd0 }, - { 0x0100056b, 0x1400ffd0 }, - { 0x0100056c, 0x1400ffd0 }, - { 0x0100056d, 0x1400ffd0 }, - { 0x0100056e, 0x1400ffd0 }, - { 0x0100056f, 0x1400ffd0 }, - { 0x01000570, 0x1400ffd0 }, - { 0x01000571, 0x1400ffd0 }, - { 0x01000572, 0x1400ffd0 }, - { 0x01000573, 0x1400ffd0 }, - { 0x01000574, 0x1400ffd0 }, - { 0x01000575, 0x1400ffd0 }, - { 0x01000576, 0x1400ffd0 }, - { 0x01000577, 0x1400ffd0 }, - { 0x01000578, 0x1400ffd0 }, - { 0x01000579, 0x1400ffd0 }, - { 0x0100057a, 0x1400ffd0 }, - { 0x0100057b, 0x1400ffd0 }, - { 0x0100057c, 0x1400ffd0 }, - { 0x0100057d, 0x1400ffd0 }, - { 0x0100057e, 0x1400ffd0 }, - { 0x0100057f, 0x1400ffd0 }, - { 0x01000580, 0x1400ffd0 }, - { 0x01000581, 0x1400ffd0 }, - { 0x01000582, 0x1400ffd0 }, - { 0x01000583, 0x1400ffd0 }, - { 0x01000584, 0x1400ffd0 }, - { 0x01000585, 0x1400ffd0 }, - { 0x01000586, 0x1400ffd0 }, - { 0x01000587, 0x14000000 }, - { 0x09000589, 0x54000000 }, - { 0x0100058a, 0x44000000 }, - { 0x19800591, 0x30000028 }, - { 0x198005bb, 0x30000002 }, - { 0x190005be, 0x54000000 }, - { 0x190005bf, 0x30000000 }, - { 0x190005c0, 0x54000000 }, - { 0x198005c1, 0x30000001 }, - { 0x190005c3, 0x54000000 }, - { 0x198005c4, 0x30000001 }, - { 0x190005c6, 0x54000000 }, - { 0x190005c7, 0x30000000 }, - { 0x198005d0, 0x1c00001a }, - { 0x198005f0, 0x1c000002 }, - { 0x198005f3, 0x54000001 }, - { 0x09800600, 0x04000003 }, - { 0x0000060b, 0x5c000000 }, - { 0x0980060c, 0x54000001 }, - { 0x0080060e, 0x68000001 }, - { 0x00800610, 0x30000005 }, - { 0x0900061b, 0x54000000 }, - { 0x0080061e, 0x54000001 }, - { 0x00800621, 0x1c000019 }, - { 0x09000640, 0x18000000 }, - { 0x00800641, 0x1c000009 }, - { 0x1b80064b, 0x30000013 }, - { 0x09800660, 0x34000009 }, - { 0x0080066a, 0x54000003 }, - { 0x0080066e, 0x1c000001 }, - { 0x1b000670, 0x30000000 }, - { 0x00800671, 0x1c000062 }, - { 0x000006d4, 0x54000000 }, - { 0x000006d5, 0x1c000000 }, - { 0x008006d6, 0x30000006 }, - { 0x090006dd, 0x04000000 }, - { 0x000006de, 0x2c000000 }, - { 0x008006df, 0x30000005 }, - { 0x008006e5, 0x18000001 }, - { 0x008006e7, 0x30000001 }, - { 0x000006e9, 0x68000000 }, - { 0x008006ea, 0x30000003 }, - { 0x008006ee, 0x1c000001 }, - { 0x008006f0, 0x34000009 }, - { 0x008006fa, 0x1c000002 }, - { 0x008006fd, 0x68000001 }, - { 0x000006ff, 0x1c000000 }, - { 0x31800700, 0x5400000d }, - { 0x3100070f, 0x04000000 }, - { 0x31000710, 0x1c000000 }, - { 0x31000711, 0x30000000 }, - { 0x31800712, 0x1c00001d }, - { 0x31800730, 0x3000001a }, - { 0x3180074d, 0x1c000020 }, - { 0x37800780, 0x1c000025 }, - { 0x378007a6, 0x3000000a }, - { 0x370007b1, 0x1c000000 }, - { 0x0e800901, 0x30000001 }, - { 0x0e000903, 0x28000000 }, - { 0x0e800904, 0x1c000035 }, - { 0x0e00093c, 0x30000000 }, - { 0x0e00093d, 0x1c000000 }, - { 0x0e80093e, 0x28000002 }, - { 0x0e800941, 0x30000007 }, - { 0x0e800949, 0x28000003 }, - { 0x0e00094d, 0x30000000 }, - { 0x0e000950, 0x1c000000 }, - { 0x0e800951, 0x30000003 }, - { 0x0e800958, 0x1c000009 }, - { 0x0e800962, 0x30000001 }, - { 0x09800964, 0x54000001 }, - { 0x0e800966, 0x34000009 }, - { 0x09000970, 0x54000000 }, - { 0x0e00097d, 0x1c000000 }, - { 0x02000981, 0x30000000 }, - { 0x02800982, 0x28000001 }, - { 0x02800985, 0x1c000007 }, - { 0x0280098f, 0x1c000001 }, - { 0x02800993, 0x1c000015 }, - { 0x028009aa, 0x1c000006 }, - { 0x020009b2, 0x1c000000 }, - { 0x028009b6, 0x1c000003 }, - { 0x020009bc, 0x30000000 }, - { 0x020009bd, 0x1c000000 }, - { 0x028009be, 0x28000002 }, - { 0x028009c1, 0x30000003 }, - { 0x028009c7, 0x28000001 }, - { 0x028009cb, 0x28000001 }, - { 0x020009cd, 0x30000000 }, - { 0x020009ce, 0x1c000000 }, - { 0x020009d7, 0x28000000 }, - { 0x028009dc, 0x1c000001 }, - { 0x028009df, 0x1c000002 }, - { 0x028009e2, 0x30000001 }, - { 0x028009e6, 0x34000009 }, - { 0x028009f0, 0x1c000001 }, - { 0x028009f2, 0x5c000001 }, - { 0x028009f4, 0x3c000005 }, - { 0x020009fa, 0x68000000 }, - { 0x15800a01, 0x30000001 }, - { 0x15000a03, 0x28000000 }, - { 0x15800a05, 0x1c000005 }, - { 0x15800a0f, 0x1c000001 }, - { 0x15800a13, 0x1c000015 }, - { 0x15800a2a, 0x1c000006 }, - { 0x15800a32, 0x1c000001 }, - { 0x15800a35, 0x1c000001 }, - { 0x15800a38, 0x1c000001 }, - { 0x15000a3c, 0x30000000 }, - { 0x15800a3e, 0x28000002 }, - { 0x15800a41, 0x30000001 }, - { 0x15800a47, 0x30000001 }, - { 0x15800a4b, 0x30000002 }, - { 0x15800a59, 0x1c000003 }, - { 0x15000a5e, 0x1c000000 }, - { 0x15800a66, 0x34000009 }, - { 0x15800a70, 0x30000001 }, - { 0x15800a72, 0x1c000002 }, - { 0x14800a81, 0x30000001 }, - { 0x14000a83, 0x28000000 }, - { 0x14800a85, 0x1c000008 }, - { 0x14800a8f, 0x1c000002 }, - { 0x14800a93, 0x1c000015 }, - { 0x14800aaa, 0x1c000006 }, - { 0x14800ab2, 0x1c000001 }, - { 0x14800ab5, 0x1c000004 }, - { 0x14000abc, 0x30000000 }, - { 0x14000abd, 0x1c000000 }, - { 0x14800abe, 0x28000002 }, - { 0x14800ac1, 0x30000004 }, - { 0x14800ac7, 0x30000001 }, - { 0x14000ac9, 0x28000000 }, - { 0x14800acb, 0x28000001 }, - { 0x14000acd, 0x30000000 }, - { 0x14000ad0, 0x1c000000 }, - { 0x14800ae0, 0x1c000001 }, - { 0x14800ae2, 0x30000001 }, - { 0x14800ae6, 0x34000009 }, - { 0x14000af1, 0x5c000000 }, - { 0x2b000b01, 0x30000000 }, - { 0x2b800b02, 0x28000001 }, - { 0x2b800b05, 0x1c000007 }, - { 0x2b800b0f, 0x1c000001 }, - { 0x2b800b13, 0x1c000015 }, - { 0x2b800b2a, 0x1c000006 }, - { 0x2b800b32, 0x1c000001 }, - { 0x2b800b35, 0x1c000004 }, - { 0x2b000b3c, 0x30000000 }, - { 0x2b000b3d, 0x1c000000 }, - { 0x2b000b3e, 0x28000000 }, - { 0x2b000b3f, 0x30000000 }, - { 0x2b000b40, 0x28000000 }, - { 0x2b800b41, 0x30000002 }, - { 0x2b800b47, 0x28000001 }, - { 0x2b800b4b, 0x28000001 }, - { 0x2b000b4d, 0x30000000 }, - { 0x2b000b56, 0x30000000 }, - { 0x2b000b57, 0x28000000 }, - { 0x2b800b5c, 0x1c000001 }, - { 0x2b800b5f, 0x1c000002 }, - { 0x2b800b66, 0x34000009 }, - { 0x2b000b70, 0x68000000 }, - { 0x2b000b71, 0x1c000000 }, - { 0x35000b82, 0x30000000 }, - { 0x35000b83, 0x1c000000 }, - { 0x35800b85, 0x1c000005 }, - { 0x35800b8e, 0x1c000002 }, - { 0x35800b92, 0x1c000003 }, - { 0x35800b99, 0x1c000001 }, - { 0x35000b9c, 0x1c000000 }, - { 0x35800b9e, 0x1c000001 }, - { 0x35800ba3, 0x1c000001 }, - { 0x35800ba8, 0x1c000002 }, - { 0x35800bae, 0x1c00000b }, - { 0x35800bbe, 0x28000001 }, - { 0x35000bc0, 0x30000000 }, - { 0x35800bc1, 0x28000001 }, - { 0x35800bc6, 0x28000002 }, - { 0x35800bca, 0x28000002 }, - { 0x35000bcd, 0x30000000 }, - { 0x35000bd7, 0x28000000 }, - { 0x35800be6, 0x34000009 }, - { 0x35800bf0, 0x3c000002 }, - { 0x35800bf3, 0x68000005 }, - { 0x35000bf9, 0x5c000000 }, - { 0x35000bfa, 0x68000000 }, - { 0x36800c01, 0x28000002 }, - { 0x36800c05, 0x1c000007 }, - { 0x36800c0e, 0x1c000002 }, - { 0x36800c12, 0x1c000016 }, - { 0x36800c2a, 0x1c000009 }, - { 0x36800c35, 0x1c000004 }, - { 0x36800c3e, 0x30000002 }, - { 0x36800c41, 0x28000003 }, - { 0x36800c46, 0x30000002 }, - { 0x36800c4a, 0x30000003 }, - { 0x36800c55, 0x30000001 }, - { 0x36800c60, 0x1c000001 }, - { 0x36800c66, 0x34000009 }, - { 0x1c800c82, 0x28000001 }, - { 0x1c800c85, 0x1c000007 }, - { 0x1c800c8e, 0x1c000002 }, - { 0x1c800c92, 0x1c000016 }, - { 0x1c800caa, 0x1c000009 }, - { 0x1c800cb5, 0x1c000004 }, - { 0x1c000cbc, 0x30000000 }, - { 0x1c000cbd, 0x1c000000 }, - { 0x1c000cbe, 0x28000000 }, - { 0x1c000cbf, 0x30000000 }, - { 0x1c800cc0, 0x28000004 }, - { 0x1c000cc6, 0x30000000 }, - { 0x1c800cc7, 0x28000001 }, - { 0x1c800cca, 0x28000001 }, - { 0x1c800ccc, 0x30000001 }, - { 0x1c800cd5, 0x28000001 }, - { 0x1c000cde, 0x1c000000 }, - { 0x1c800ce0, 0x1c000001 }, - { 0x1c800ce6, 0x34000009 }, - { 0x24800d02, 0x28000001 }, - { 0x24800d05, 0x1c000007 }, - { 0x24800d0e, 0x1c000002 }, - { 0x24800d12, 0x1c000016 }, - { 0x24800d2a, 0x1c00000f }, - { 0x24800d3e, 0x28000002 }, - { 0x24800d41, 0x30000002 }, - { 0x24800d46, 0x28000002 }, - { 0x24800d4a, 0x28000002 }, - { 0x24000d4d, 0x30000000 }, - { 0x24000d57, 0x28000000 }, - { 0x24800d60, 0x1c000001 }, - { 0x24800d66, 0x34000009 }, - { 0x2f800d82, 0x28000001 }, - { 0x2f800d85, 0x1c000011 }, - { 0x2f800d9a, 0x1c000017 }, - { 0x2f800db3, 0x1c000008 }, - { 0x2f000dbd, 0x1c000000 }, - { 0x2f800dc0, 0x1c000006 }, - { 0x2f000dca, 0x30000000 }, - { 0x2f800dcf, 0x28000002 }, - { 0x2f800dd2, 0x30000002 }, - { 0x2f000dd6, 0x30000000 }, - { 0x2f800dd8, 0x28000007 }, - { 0x2f800df2, 0x28000001 }, - { 0x2f000df4, 0x54000000 }, - { 0x38800e01, 0x1c00002f }, - { 0x38000e31, 0x30000000 }, - { 0x38800e32, 0x1c000001 }, - { 0x38800e34, 0x30000006 }, - { 0x09000e3f, 0x5c000000 }, - { 0x38800e40, 0x1c000005 }, - { 0x38000e46, 0x18000000 }, - { 0x38800e47, 0x30000007 }, - { 0x38000e4f, 0x54000000 }, - { 0x38800e50, 0x34000009 }, - { 0x38800e5a, 0x54000001 }, - { 0x20800e81, 0x1c000001 }, - { 0x20000e84, 0x1c000000 }, - { 0x20800e87, 0x1c000001 }, - { 0x20000e8a, 0x1c000000 }, - { 0x20000e8d, 0x1c000000 }, - { 0x20800e94, 0x1c000003 }, - { 0x20800e99, 0x1c000006 }, - { 0x20800ea1, 0x1c000002 }, - { 0x20000ea5, 0x1c000000 }, - { 0x20000ea7, 0x1c000000 }, - { 0x20800eaa, 0x1c000001 }, - { 0x20800ead, 0x1c000003 }, - { 0x20000eb1, 0x30000000 }, - { 0x20800eb2, 0x1c000001 }, - { 0x20800eb4, 0x30000005 }, - { 0x20800ebb, 0x30000001 }, - { 0x20000ebd, 0x1c000000 }, - { 0x20800ec0, 0x1c000004 }, - { 0x20000ec6, 0x18000000 }, - { 0x20800ec8, 0x30000005 }, - { 0x20800ed0, 0x34000009 }, - { 0x20800edc, 0x1c000001 }, - { 0x39000f00, 0x1c000000 }, - { 0x39800f01, 0x68000002 }, - { 0x39800f04, 0x5400000e }, - { 0x39800f13, 0x68000004 }, - { 0x39800f18, 0x30000001 }, - { 0x39800f1a, 0x68000005 }, - { 0x39800f20, 0x34000009 }, - { 0x39800f2a, 0x3c000009 }, - { 0x39000f34, 0x68000000 }, - { 0x39000f35, 0x30000000 }, - { 0x39000f36, 0x68000000 }, - { 0x39000f37, 0x30000000 }, - { 0x39000f38, 0x68000000 }, - { 0x39000f39, 0x30000000 }, - { 0x39000f3a, 0x58000000 }, - { 0x39000f3b, 0x48000000 }, - { 0x39000f3c, 0x58000000 }, - { 0x39000f3d, 0x48000000 }, - { 0x39800f3e, 0x28000001 }, - { 0x39800f40, 0x1c000007 }, - { 0x39800f49, 0x1c000021 }, - { 0x39800f71, 0x3000000d }, - { 0x39000f7f, 0x28000000 }, - { 0x39800f80, 0x30000004 }, - { 0x39000f85, 0x54000000 }, - { 0x39800f86, 0x30000001 }, - { 0x39800f88, 0x1c000003 }, - { 0x39800f90, 0x30000007 }, - { 0x39800f99, 0x30000023 }, - { 0x39800fbe, 0x68000007 }, - { 0x39000fc6, 0x30000000 }, - { 0x39800fc7, 0x68000005 }, - { 0x39000fcf, 0x68000000 }, - { 0x39800fd0, 0x54000001 }, - { 0x26801000, 0x1c000021 }, - { 0x26801023, 0x1c000004 }, - { 0x26801029, 0x1c000001 }, - { 0x2600102c, 0x28000000 }, - { 0x2680102d, 0x30000003 }, - { 0x26001031, 0x28000000 }, - { 0x26001032, 0x30000000 }, - { 0x26801036, 0x30000001 }, - { 0x26001038, 0x28000000 }, - { 0x26001039, 0x30000000 }, - { 0x26801040, 0x34000009 }, - { 0x2680104a, 0x54000005 }, - { 0x26801050, 0x1c000005 }, - { 0x26801056, 0x28000001 }, - { 0x26801058, 0x30000001 }, - { 0x100010a0, 0x24001c60 }, - { 0x100010a1, 0x24001c60 }, - { 0x100010a2, 0x24001c60 }, - { 0x100010a3, 0x24001c60 }, - { 0x100010a4, 0x24001c60 }, - { 0x100010a5, 0x24001c60 }, - { 0x100010a6, 0x24001c60 }, - { 0x100010a7, 0x24001c60 }, - { 0x100010a8, 0x24001c60 }, - { 0x100010a9, 0x24001c60 }, - { 0x100010aa, 0x24001c60 }, - { 0x100010ab, 0x24001c60 }, - { 0x100010ac, 0x24001c60 }, - { 0x100010ad, 0x24001c60 }, - { 0x100010ae, 0x24001c60 }, - { 0x100010af, 0x24001c60 }, - { 0x100010b0, 0x24001c60 }, - { 0x100010b1, 0x24001c60 }, - { 0x100010b2, 0x24001c60 }, - { 0x100010b3, 0x24001c60 }, - { 0x100010b4, 0x24001c60 }, - { 0x100010b5, 0x24001c60 }, - { 0x100010b6, 0x24001c60 }, - { 0x100010b7, 0x24001c60 }, - { 0x100010b8, 0x24001c60 }, - { 0x100010b9, 0x24001c60 }, - { 0x100010ba, 0x24001c60 }, - { 0x100010bb, 0x24001c60 }, - { 0x100010bc, 0x24001c60 }, - { 0x100010bd, 0x24001c60 }, - { 0x100010be, 0x24001c60 }, - { 0x100010bf, 0x24001c60 }, - { 0x100010c0, 0x24001c60 }, - { 0x100010c1, 0x24001c60 }, - { 0x100010c2, 0x24001c60 }, - { 0x100010c3, 0x24001c60 }, - { 0x100010c4, 0x24001c60 }, - { 0x100010c5, 0x24001c60 }, - { 0x108010d0, 0x1c00002a }, - { 0x090010fb, 0x54000000 }, - { 0x100010fc, 0x18000000 }, - { 0x17801100, 0x1c000059 }, - { 0x1780115f, 0x1c000043 }, - { 0x178011a8, 0x1c000051 }, - { 0x0f801200, 0x1c000048 }, - { 0x0f80124a, 0x1c000003 }, - { 0x0f801250, 0x1c000006 }, - { 0x0f001258, 0x1c000000 }, - { 0x0f80125a, 0x1c000003 }, - { 0x0f801260, 0x1c000028 }, - { 0x0f80128a, 0x1c000003 }, - { 0x0f801290, 0x1c000020 }, - { 0x0f8012b2, 0x1c000003 }, - { 0x0f8012b8, 0x1c000006 }, - { 0x0f0012c0, 0x1c000000 }, - { 0x0f8012c2, 0x1c000003 }, - { 0x0f8012c8, 0x1c00000e }, - { 0x0f8012d8, 0x1c000038 }, - { 0x0f801312, 0x1c000003 }, - { 0x0f801318, 0x1c000042 }, - { 0x0f00135f, 0x30000000 }, - { 0x0f001360, 0x68000000 }, - { 0x0f801361, 0x54000007 }, - { 0x0f801369, 0x3c000013 }, - { 0x0f801380, 0x1c00000f }, - { 0x0f801390, 0x68000009 }, - { 0x088013a0, 0x1c000054 }, - { 0x07801401, 0x1c00026b }, - { 0x0780166d, 0x54000001 }, - { 0x0780166f, 0x1c000007 }, - { 0x28001680, 0x74000000 }, - { 0x28801681, 0x1c000019 }, - { 0x2800169b, 0x58000000 }, - { 0x2800169c, 0x48000000 }, - { 0x2d8016a0, 0x1c00004a }, - { 0x098016eb, 0x54000002 }, - { 0x2d8016ee, 0x38000002 }, - { 0x32801700, 0x1c00000c }, - { 0x3280170e, 0x1c000003 }, - { 0x32801712, 0x30000002 }, - { 0x18801720, 0x1c000011 }, - { 0x18801732, 0x30000002 }, - { 0x09801735, 0x54000001 }, - { 0x06801740, 0x1c000011 }, - { 0x06801752, 0x30000001 }, - { 0x33801760, 0x1c00000c }, - { 0x3380176e, 0x1c000002 }, - { 0x33801772, 0x30000001 }, - { 0x1f801780, 0x1c000033 }, - { 0x1f8017b4, 0x04000001 }, - { 0x1f0017b6, 0x28000000 }, - { 0x1f8017b7, 0x30000006 }, - { 0x1f8017be, 0x28000007 }, - { 0x1f0017c6, 0x30000000 }, - { 0x1f8017c7, 0x28000001 }, - { 0x1f8017c9, 0x3000000a }, - { 0x1f8017d4, 0x54000002 }, - { 0x1f0017d7, 0x18000000 }, - { 0x1f8017d8, 0x54000002 }, - { 0x1f0017db, 0x5c000000 }, - { 0x1f0017dc, 0x1c000000 }, - { 0x1f0017dd, 0x30000000 }, - { 0x1f8017e0, 0x34000009 }, - { 0x1f8017f0, 0x3c000009 }, - { 0x25801800, 0x54000005 }, - { 0x25001806, 0x44000000 }, - { 0x25801807, 0x54000003 }, - { 0x2580180b, 0x30000002 }, - { 0x2500180e, 0x74000000 }, - { 0x25801810, 0x34000009 }, - { 0x25801820, 0x1c000022 }, - { 0x25001843, 0x18000000 }, - { 0x25801844, 0x1c000033 }, - { 0x25801880, 0x1c000028 }, - { 0x250018a9, 0x30000000 }, - { 0x22801900, 0x1c00001c }, - { 0x22801920, 0x30000002 }, - { 0x22801923, 0x28000003 }, - { 0x22801927, 0x30000001 }, - { 0x22801929, 0x28000002 }, - { 0x22801930, 0x28000001 }, - { 0x22001932, 0x30000000 }, - { 0x22801933, 0x28000005 }, - { 0x22801939, 0x30000002 }, - { 0x22001940, 0x68000000 }, - { 0x22801944, 0x54000001 }, - { 0x22801946, 0x34000009 }, - { 0x34801950, 0x1c00001d }, - { 0x34801970, 0x1c000004 }, - { 0x27801980, 0x1c000029 }, - { 0x278019b0, 0x28000010 }, - { 0x278019c1, 0x1c000006 }, - { 0x278019c8, 0x28000001 }, - { 0x278019d0, 0x34000009 }, - { 0x278019de, 0x54000001 }, - { 0x1f8019e0, 0x6800001f }, - { 0x05801a00, 0x1c000016 }, - { 0x05801a17, 0x30000001 }, - { 0x05801a19, 0x28000002 }, - { 0x05801a1e, 0x54000001 }, - { 0x21801d00, 0x1400002b }, - { 0x21801d2c, 0x18000035 }, - { 0x21801d62, 0x14000015 }, - { 0x0c001d78, 0x18000000 }, - { 0x21801d79, 0x14000021 }, - { 0x21801d9b, 0x18000024 }, - { 0x1b801dc0, 0x30000003 }, - { 0x21001e00, 0x24000001 }, - { 0x21001e01, 0x1400ffff }, - { 0x21001e02, 0x24000001 }, - { 0x21001e03, 0x1400ffff }, - { 0x21001e04, 0x24000001 }, - { 0x21001e05, 0x1400ffff }, - { 0x21001e06, 0x24000001 }, - { 0x21001e07, 0x1400ffff }, - { 0x21001e08, 0x24000001 }, - { 0x21001e09, 0x1400ffff }, - { 0x21001e0a, 0x24000001 }, - { 0x21001e0b, 0x1400ffff }, - { 0x21001e0c, 0x24000001 }, - { 0x21001e0d, 0x1400ffff }, - { 0x21001e0e, 0x24000001 }, - { 0x21001e0f, 0x1400ffff }, - { 0x21001e10, 0x24000001 }, - { 0x21001e11, 0x1400ffff }, - { 0x21001e12, 0x24000001 }, - { 0x21001e13, 0x1400ffff }, - { 0x21001e14, 0x24000001 }, - { 0x21001e15, 0x1400ffff }, - { 0x21001e16, 0x24000001 }, - { 0x21001e17, 0x1400ffff }, - { 0x21001e18, 0x24000001 }, - { 0x21001e19, 0x1400ffff }, - { 0x21001e1a, 0x24000001 }, - { 0x21001e1b, 0x1400ffff }, - { 0x21001e1c, 0x24000001 }, - { 0x21001e1d, 0x1400ffff }, - { 0x21001e1e, 0x24000001 }, - { 0x21001e1f, 0x1400ffff }, - { 0x21001e20, 0x24000001 }, - { 0x21001e21, 0x1400ffff }, - { 0x21001e22, 0x24000001 }, - { 0x21001e23, 0x1400ffff }, - { 0x21001e24, 0x24000001 }, - { 0x21001e25, 0x1400ffff }, - { 0x21001e26, 0x24000001 }, - { 0x21001e27, 0x1400ffff }, - { 0x21001e28, 0x24000001 }, - { 0x21001e29, 0x1400ffff }, - { 0x21001e2a, 0x24000001 }, - { 0x21001e2b, 0x1400ffff }, - { 0x21001e2c, 0x24000001 }, - { 0x21001e2d, 0x1400ffff }, - { 0x21001e2e, 0x24000001 }, - { 0x21001e2f, 0x1400ffff }, - { 0x21001e30, 0x24000001 }, - { 0x21001e31, 0x1400ffff }, - { 0x21001e32, 0x24000001 }, - { 0x21001e33, 0x1400ffff }, - { 0x21001e34, 0x24000001 }, - { 0x21001e35, 0x1400ffff }, - { 0x21001e36, 0x24000001 }, - { 0x21001e37, 0x1400ffff }, - { 0x21001e38, 0x24000001 }, - { 0x21001e39, 0x1400ffff }, - { 0x21001e3a, 0x24000001 }, - { 0x21001e3b, 0x1400ffff }, - { 0x21001e3c, 0x24000001 }, - { 0x21001e3d, 0x1400ffff }, - { 0x21001e3e, 0x24000001 }, - { 0x21001e3f, 0x1400ffff }, - { 0x21001e40, 0x24000001 }, - { 0x21001e41, 0x1400ffff }, - { 0x21001e42, 0x24000001 }, - { 0x21001e43, 0x1400ffff }, - { 0x21001e44, 0x24000001 }, - { 0x21001e45, 0x1400ffff }, - { 0x21001e46, 0x24000001 }, - { 0x21001e47, 0x1400ffff }, - { 0x21001e48, 0x24000001 }, - { 0x21001e49, 0x1400ffff }, - { 0x21001e4a, 0x24000001 }, - { 0x21001e4b, 0x1400ffff }, - { 0x21001e4c, 0x24000001 }, - { 0x21001e4d, 0x1400ffff }, - { 0x21001e4e, 0x24000001 }, - { 0x21001e4f, 0x1400ffff }, - { 0x21001e50, 0x24000001 }, - { 0x21001e51, 0x1400ffff }, - { 0x21001e52, 0x24000001 }, - { 0x21001e53, 0x1400ffff }, - { 0x21001e54, 0x24000001 }, - { 0x21001e55, 0x1400ffff }, - { 0x21001e56, 0x24000001 }, - { 0x21001e57, 0x1400ffff }, - { 0x21001e58, 0x24000001 }, - { 0x21001e59, 0x1400ffff }, - { 0x21001e5a, 0x24000001 }, - { 0x21001e5b, 0x1400ffff }, - { 0x21001e5c, 0x24000001 }, - { 0x21001e5d, 0x1400ffff }, - { 0x21001e5e, 0x24000001 }, - { 0x21001e5f, 0x1400ffff }, - { 0x21001e60, 0x24000001 }, - { 0x21001e61, 0x1400ffff }, - { 0x21001e62, 0x24000001 }, - { 0x21001e63, 0x1400ffff }, - { 0x21001e64, 0x24000001 }, - { 0x21001e65, 0x1400ffff }, - { 0x21001e66, 0x24000001 }, - { 0x21001e67, 0x1400ffff }, - { 0x21001e68, 0x24000001 }, - { 0x21001e69, 0x1400ffff }, - { 0x21001e6a, 0x24000001 }, - { 0x21001e6b, 0x1400ffff }, - { 0x21001e6c, 0x24000001 }, - { 0x21001e6d, 0x1400ffff }, - { 0x21001e6e, 0x24000001 }, - { 0x21001e6f, 0x1400ffff }, - { 0x21001e70, 0x24000001 }, - { 0x21001e71, 0x1400ffff }, - { 0x21001e72, 0x24000001 }, - { 0x21001e73, 0x1400ffff }, - { 0x21001e74, 0x24000001 }, - { 0x21001e75, 0x1400ffff }, - { 0x21001e76, 0x24000001 }, - { 0x21001e77, 0x1400ffff }, - { 0x21001e78, 0x24000001 }, - { 0x21001e79, 0x1400ffff }, - { 0x21001e7a, 0x24000001 }, - { 0x21001e7b, 0x1400ffff }, - { 0x21001e7c, 0x24000001 }, - { 0x21001e7d, 0x1400ffff }, - { 0x21001e7e, 0x24000001 }, - { 0x21001e7f, 0x1400ffff }, - { 0x21001e80, 0x24000001 }, - { 0x21001e81, 0x1400ffff }, - { 0x21001e82, 0x24000001 }, - { 0x21001e83, 0x1400ffff }, - { 0x21001e84, 0x24000001 }, - { 0x21001e85, 0x1400ffff }, - { 0x21001e86, 0x24000001 }, - { 0x21001e87, 0x1400ffff }, - { 0x21001e88, 0x24000001 }, - { 0x21001e89, 0x1400ffff }, - { 0x21001e8a, 0x24000001 }, - { 0x21001e8b, 0x1400ffff }, - { 0x21001e8c, 0x24000001 }, - { 0x21001e8d, 0x1400ffff }, - { 0x21001e8e, 0x24000001 }, - { 0x21001e8f, 0x1400ffff }, - { 0x21001e90, 0x24000001 }, - { 0x21001e91, 0x1400ffff }, - { 0x21001e92, 0x24000001 }, - { 0x21001e93, 0x1400ffff }, - { 0x21001e94, 0x24000001 }, - { 0x21001e95, 0x1400ffff }, - { 0x21801e96, 0x14000004 }, - { 0x21001e9b, 0x1400ffc5 }, - { 0x21001ea0, 0x24000001 }, - { 0x21001ea1, 0x1400ffff }, - { 0x21001ea2, 0x24000001 }, - { 0x21001ea3, 0x1400ffff }, - { 0x21001ea4, 0x24000001 }, - { 0x21001ea5, 0x1400ffff }, - { 0x21001ea6, 0x24000001 }, - { 0x21001ea7, 0x1400ffff }, - { 0x21001ea8, 0x24000001 }, - { 0x21001ea9, 0x1400ffff }, - { 0x21001eaa, 0x24000001 }, - { 0x21001eab, 0x1400ffff }, - { 0x21001eac, 0x24000001 }, - { 0x21001ead, 0x1400ffff }, - { 0x21001eae, 0x24000001 }, - { 0x21001eaf, 0x1400ffff }, - { 0x21001eb0, 0x24000001 }, - { 0x21001eb1, 0x1400ffff }, - { 0x21001eb2, 0x24000001 }, - { 0x21001eb3, 0x1400ffff }, - { 0x21001eb4, 0x24000001 }, - { 0x21001eb5, 0x1400ffff }, - { 0x21001eb6, 0x24000001 }, - { 0x21001eb7, 0x1400ffff }, - { 0x21001eb8, 0x24000001 }, - { 0x21001eb9, 0x1400ffff }, - { 0x21001eba, 0x24000001 }, - { 0x21001ebb, 0x1400ffff }, - { 0x21001ebc, 0x24000001 }, - { 0x21001ebd, 0x1400ffff }, - { 0x21001ebe, 0x24000001 }, - { 0x21001ebf, 0x1400ffff }, - { 0x21001ec0, 0x24000001 }, - { 0x21001ec1, 0x1400ffff }, - { 0x21001ec2, 0x24000001 }, - { 0x21001ec3, 0x1400ffff }, - { 0x21001ec4, 0x24000001 }, - { 0x21001ec5, 0x1400ffff }, - { 0x21001ec6, 0x24000001 }, - { 0x21001ec7, 0x1400ffff }, - { 0x21001ec8, 0x24000001 }, - { 0x21001ec9, 0x1400ffff }, - { 0x21001eca, 0x24000001 }, - { 0x21001ecb, 0x1400ffff }, - { 0x21001ecc, 0x24000001 }, - { 0x21001ecd, 0x1400ffff }, - { 0x21001ece, 0x24000001 }, - { 0x21001ecf, 0x1400ffff }, - { 0x21001ed0, 0x24000001 }, - { 0x21001ed1, 0x1400ffff }, - { 0x21001ed2, 0x24000001 }, - { 0x21001ed3, 0x1400ffff }, - { 0x21001ed4, 0x24000001 }, - { 0x21001ed5, 0x1400ffff }, - { 0x21001ed6, 0x24000001 }, - { 0x21001ed7, 0x1400ffff }, - { 0x21001ed8, 0x24000001 }, - { 0x21001ed9, 0x1400ffff }, - { 0x21001eda, 0x24000001 }, - { 0x21001edb, 0x1400ffff }, - { 0x21001edc, 0x24000001 }, - { 0x21001edd, 0x1400ffff }, - { 0x21001ede, 0x24000001 }, - { 0x21001edf, 0x1400ffff }, - { 0x21001ee0, 0x24000001 }, - { 0x21001ee1, 0x1400ffff }, - { 0x21001ee2, 0x24000001 }, - { 0x21001ee3, 0x1400ffff }, - { 0x21001ee4, 0x24000001 }, - { 0x21001ee5, 0x1400ffff }, - { 0x21001ee6, 0x24000001 }, - { 0x21001ee7, 0x1400ffff }, - { 0x21001ee8, 0x24000001 }, - { 0x21001ee9, 0x1400ffff }, - { 0x21001eea, 0x24000001 }, - { 0x21001eeb, 0x1400ffff }, - { 0x21001eec, 0x24000001 }, - { 0x21001eed, 0x1400ffff }, - { 0x21001eee, 0x24000001 }, - { 0x21001eef, 0x1400ffff }, - { 0x21001ef0, 0x24000001 }, - { 0x21001ef1, 0x1400ffff }, - { 0x21001ef2, 0x24000001 }, - { 0x21001ef3, 0x1400ffff }, - { 0x21001ef4, 0x24000001 }, - { 0x21001ef5, 0x1400ffff }, - { 0x21001ef6, 0x24000001 }, - { 0x21001ef7, 0x1400ffff }, - { 0x21001ef8, 0x24000001 }, - { 0x21001ef9, 0x1400ffff }, - { 0x13001f00, 0x14000008 }, - { 0x13001f01, 0x14000008 }, - { 0x13001f02, 0x14000008 }, - { 0x13001f03, 0x14000008 }, - { 0x13001f04, 0x14000008 }, - { 0x13001f05, 0x14000008 }, - { 0x13001f06, 0x14000008 }, - { 0x13001f07, 0x14000008 }, - { 0x13001f08, 0x2400fff8 }, - { 0x13001f09, 0x2400fff8 }, - { 0x13001f0a, 0x2400fff8 }, - { 0x13001f0b, 0x2400fff8 }, - { 0x13001f0c, 0x2400fff8 }, - { 0x13001f0d, 0x2400fff8 }, - { 0x13001f0e, 0x2400fff8 }, - { 0x13001f0f, 0x2400fff8 }, - { 0x13001f10, 0x14000008 }, - { 0x13001f11, 0x14000008 }, - { 0x13001f12, 0x14000008 }, - { 0x13001f13, 0x14000008 }, - { 0x13001f14, 0x14000008 }, - { 0x13001f15, 0x14000008 }, - { 0x13001f18, 0x2400fff8 }, - { 0x13001f19, 0x2400fff8 }, - { 0x13001f1a, 0x2400fff8 }, - { 0x13001f1b, 0x2400fff8 }, - { 0x13001f1c, 0x2400fff8 }, - { 0x13001f1d, 0x2400fff8 }, - { 0x13001f20, 0x14000008 }, - { 0x13001f21, 0x14000008 }, - { 0x13001f22, 0x14000008 }, - { 0x13001f23, 0x14000008 }, - { 0x13001f24, 0x14000008 }, - { 0x13001f25, 0x14000008 }, - { 0x13001f26, 0x14000008 }, - { 0x13001f27, 0x14000008 }, - { 0x13001f28, 0x2400fff8 }, - { 0x13001f29, 0x2400fff8 }, - { 0x13001f2a, 0x2400fff8 }, - { 0x13001f2b, 0x2400fff8 }, - { 0x13001f2c, 0x2400fff8 }, - { 0x13001f2d, 0x2400fff8 }, - { 0x13001f2e, 0x2400fff8 }, - { 0x13001f2f, 0x2400fff8 }, - { 0x13001f30, 0x14000008 }, - { 0x13001f31, 0x14000008 }, - { 0x13001f32, 0x14000008 }, - { 0x13001f33, 0x14000008 }, - { 0x13001f34, 0x14000008 }, - { 0x13001f35, 0x14000008 }, - { 0x13001f36, 0x14000008 }, - { 0x13001f37, 0x14000008 }, - { 0x13001f38, 0x2400fff8 }, - { 0x13001f39, 0x2400fff8 }, - { 0x13001f3a, 0x2400fff8 }, - { 0x13001f3b, 0x2400fff8 }, - { 0x13001f3c, 0x2400fff8 }, - { 0x13001f3d, 0x2400fff8 }, - { 0x13001f3e, 0x2400fff8 }, - { 0x13001f3f, 0x2400fff8 }, - { 0x13001f40, 0x14000008 }, - { 0x13001f41, 0x14000008 }, - { 0x13001f42, 0x14000008 }, - { 0x13001f43, 0x14000008 }, - { 0x13001f44, 0x14000008 }, - { 0x13001f45, 0x14000008 }, - { 0x13001f48, 0x2400fff8 }, - { 0x13001f49, 0x2400fff8 }, - { 0x13001f4a, 0x2400fff8 }, - { 0x13001f4b, 0x2400fff8 }, - { 0x13001f4c, 0x2400fff8 }, - { 0x13001f4d, 0x2400fff8 }, - { 0x13001f50, 0x14000000 }, - { 0x13001f51, 0x14000008 }, - { 0x13001f52, 0x14000000 }, - { 0x13001f53, 0x14000008 }, - { 0x13001f54, 0x14000000 }, - { 0x13001f55, 0x14000008 }, - { 0x13001f56, 0x14000000 }, - { 0x13001f57, 0x14000008 }, - { 0x13001f59, 0x2400fff8 }, - { 0x13001f5b, 0x2400fff8 }, - { 0x13001f5d, 0x2400fff8 }, - { 0x13001f5f, 0x2400fff8 }, - { 0x13001f60, 0x14000008 }, - { 0x13001f61, 0x14000008 }, - { 0x13001f62, 0x14000008 }, - { 0x13001f63, 0x14000008 }, - { 0x13001f64, 0x14000008 }, - { 0x13001f65, 0x14000008 }, - { 0x13001f66, 0x14000008 }, - { 0x13001f67, 0x14000008 }, - { 0x13001f68, 0x2400fff8 }, - { 0x13001f69, 0x2400fff8 }, - { 0x13001f6a, 0x2400fff8 }, - { 0x13001f6b, 0x2400fff8 }, - { 0x13001f6c, 0x2400fff8 }, - { 0x13001f6d, 0x2400fff8 }, - { 0x13001f6e, 0x2400fff8 }, - { 0x13001f6f, 0x2400fff8 }, - { 0x13001f70, 0x1400004a }, - { 0x13001f71, 0x1400004a }, - { 0x13001f72, 0x14000056 }, - { 0x13001f73, 0x14000056 }, - { 0x13001f74, 0x14000056 }, - { 0x13001f75, 0x14000056 }, - { 0x13001f76, 0x14000064 }, - { 0x13001f77, 0x14000064 }, - { 0x13001f78, 0x14000080 }, - { 0x13001f79, 0x14000080 }, - { 0x13001f7a, 0x14000070 }, - { 0x13001f7b, 0x14000070 }, - { 0x13001f7c, 0x1400007e }, - { 0x13001f7d, 0x1400007e }, - { 0x13001f80, 0x14000008 }, - { 0x13001f81, 0x14000008 }, - { 0x13001f82, 0x14000008 }, - { 0x13001f83, 0x14000008 }, - { 0x13001f84, 0x14000008 }, - { 0x13001f85, 0x14000008 }, - { 0x13001f86, 0x14000008 }, - { 0x13001f87, 0x14000008 }, - { 0x13001f88, 0x2000fff8 }, - { 0x13001f89, 0x2000fff8 }, - { 0x13001f8a, 0x2000fff8 }, - { 0x13001f8b, 0x2000fff8 }, - { 0x13001f8c, 0x2000fff8 }, - { 0x13001f8d, 0x2000fff8 }, - { 0x13001f8e, 0x2000fff8 }, - { 0x13001f8f, 0x2000fff8 }, - { 0x13001f90, 0x14000008 }, - { 0x13001f91, 0x14000008 }, - { 0x13001f92, 0x14000008 }, - { 0x13001f93, 0x14000008 }, - { 0x13001f94, 0x14000008 }, - { 0x13001f95, 0x14000008 }, - { 0x13001f96, 0x14000008 }, - { 0x13001f97, 0x14000008 }, - { 0x13001f98, 0x2000fff8 }, - { 0x13001f99, 0x2000fff8 }, - { 0x13001f9a, 0x2000fff8 }, - { 0x13001f9b, 0x2000fff8 }, - { 0x13001f9c, 0x2000fff8 }, - { 0x13001f9d, 0x2000fff8 }, - { 0x13001f9e, 0x2000fff8 }, - { 0x13001f9f, 0x2000fff8 }, - { 0x13001fa0, 0x14000008 }, - { 0x13001fa1, 0x14000008 }, - { 0x13001fa2, 0x14000008 }, - { 0x13001fa3, 0x14000008 }, - { 0x13001fa4, 0x14000008 }, - { 0x13001fa5, 0x14000008 }, - { 0x13001fa6, 0x14000008 }, - { 0x13001fa7, 0x14000008 }, - { 0x13001fa8, 0x2000fff8 }, - { 0x13001fa9, 0x2000fff8 }, - { 0x13001faa, 0x2000fff8 }, - { 0x13001fab, 0x2000fff8 }, - { 0x13001fac, 0x2000fff8 }, - { 0x13001fad, 0x2000fff8 }, - { 0x13001fae, 0x2000fff8 }, - { 0x13001faf, 0x2000fff8 }, - { 0x13001fb0, 0x14000008 }, - { 0x13001fb1, 0x14000008 }, - { 0x13001fb2, 0x14000000 }, - { 0x13001fb3, 0x14000009 }, - { 0x13001fb4, 0x14000000 }, - { 0x13801fb6, 0x14000001 }, - { 0x13001fb8, 0x2400fff8 }, - { 0x13001fb9, 0x2400fff8 }, - { 0x13001fba, 0x2400ffb6 }, - { 0x13001fbb, 0x2400ffb6 }, - { 0x13001fbc, 0x2000fff7 }, - { 0x13001fbd, 0x60000000 }, - { 0x13001fbe, 0x1400e3db }, - { 0x13801fbf, 0x60000002 }, - { 0x13001fc2, 0x14000000 }, - { 0x13001fc3, 0x14000009 }, - { 0x13001fc4, 0x14000000 }, - { 0x13801fc6, 0x14000001 }, - { 0x13001fc8, 0x2400ffaa }, - { 0x13001fc9, 0x2400ffaa }, - { 0x13001fca, 0x2400ffaa }, - { 0x13001fcb, 0x2400ffaa }, - { 0x13001fcc, 0x2000fff7 }, - { 0x13801fcd, 0x60000002 }, - { 0x13001fd0, 0x14000008 }, - { 0x13001fd1, 0x14000008 }, - { 0x13801fd2, 0x14000001 }, - { 0x13801fd6, 0x14000001 }, - { 0x13001fd8, 0x2400fff8 }, - { 0x13001fd9, 0x2400fff8 }, - { 0x13001fda, 0x2400ff9c }, - { 0x13001fdb, 0x2400ff9c }, - { 0x13801fdd, 0x60000002 }, - { 0x13001fe0, 0x14000008 }, - { 0x13001fe1, 0x14000008 }, - { 0x13801fe2, 0x14000002 }, - { 0x13001fe5, 0x14000007 }, - { 0x13801fe6, 0x14000001 }, - { 0x13001fe8, 0x2400fff8 }, - { 0x13001fe9, 0x2400fff8 }, - { 0x13001fea, 0x2400ff90 }, - { 0x13001feb, 0x2400ff90 }, - { 0x13001fec, 0x2400fff9 }, - { 0x13801fed, 0x60000002 }, - { 0x13001ff2, 0x14000000 }, - { 0x13001ff3, 0x14000009 }, - { 0x13001ff4, 0x14000000 }, - { 0x13801ff6, 0x14000001 }, - { 0x13001ff8, 0x2400ff80 }, - { 0x13001ff9, 0x2400ff80 }, - { 0x13001ffa, 0x2400ff82 }, - { 0x13001ffb, 0x2400ff82 }, - { 0x13001ffc, 0x2000fff7 }, - { 0x13801ffd, 0x60000001 }, - { 0x09802000, 0x7400000a }, - { 0x0980200b, 0x04000004 }, - { 0x09802010, 0x44000005 }, - { 0x09802016, 0x54000001 }, - { 0x09002018, 0x50000000 }, - { 0x09002019, 0x4c000000 }, - { 0x0900201a, 0x58000000 }, - { 0x0980201b, 0x50000001 }, - { 0x0900201d, 0x4c000000 }, - { 0x0900201e, 0x58000000 }, - { 0x0900201f, 0x50000000 }, - { 0x09802020, 0x54000007 }, - { 0x09002028, 0x6c000000 }, - { 0x09002029, 0x70000000 }, - { 0x0980202a, 0x04000004 }, - { 0x0900202f, 0x74000000 }, - { 0x09802030, 0x54000008 }, - { 0x09002039, 0x50000000 }, - { 0x0900203a, 0x4c000000 }, - { 0x0980203b, 0x54000003 }, - { 0x0980203f, 0x40000001 }, - { 0x09802041, 0x54000002 }, - { 0x09002044, 0x64000000 }, - { 0x09002045, 0x58000000 }, - { 0x09002046, 0x48000000 }, - { 0x09802047, 0x5400000a }, - { 0x09002052, 0x64000000 }, - { 0x09002053, 0x54000000 }, - { 0x09002054, 0x40000000 }, - { 0x09802055, 0x54000009 }, - { 0x0900205f, 0x74000000 }, - { 0x09802060, 0x04000003 }, - { 0x0980206a, 0x04000005 }, - { 0x09002070, 0x3c000000 }, - { 0x21002071, 0x14000000 }, - { 0x09802074, 0x3c000005 }, - { 0x0980207a, 0x64000002 }, - { 0x0900207d, 0x58000000 }, - { 0x0900207e, 0x48000000 }, - { 0x2100207f, 0x14000000 }, - { 0x09802080, 0x3c000009 }, - { 0x0980208a, 0x64000002 }, - { 0x0900208d, 0x58000000 }, - { 0x0900208e, 0x48000000 }, - { 0x21802090, 0x18000004 }, - { 0x098020a0, 0x5c000015 }, - { 0x1b8020d0, 0x3000000c }, - { 0x1b8020dd, 0x2c000003 }, - { 0x1b0020e1, 0x30000000 }, - { 0x1b8020e2, 0x2c000002 }, - { 0x1b8020e5, 0x30000006 }, - { 0x09802100, 0x68000001 }, - { 0x09002102, 0x24000000 }, - { 0x09802103, 0x68000003 }, - { 0x09002107, 0x24000000 }, - { 0x09802108, 0x68000001 }, - { 0x0900210a, 0x14000000 }, - { 0x0980210b, 0x24000002 }, - { 0x0980210e, 0x14000001 }, - { 0x09802110, 0x24000002 }, - { 0x09002113, 0x14000000 }, - { 0x09002114, 0x68000000 }, - { 0x09002115, 0x24000000 }, - { 0x09802116, 0x68000002 }, - { 0x09802119, 0x24000004 }, - { 0x0980211e, 0x68000005 }, - { 0x09002124, 0x24000000 }, - { 0x09002125, 0x68000000 }, - { 0x13002126, 0x2400e2a3 }, - { 0x09002127, 0x68000000 }, - { 0x09002128, 0x24000000 }, - { 0x09002129, 0x68000000 }, - { 0x2100212a, 0x2400df41 }, - { 0x2100212b, 0x2400dfba }, - { 0x0980212c, 0x24000001 }, - { 0x0900212e, 0x68000000 }, - { 0x0900212f, 0x14000000 }, - { 0x09802130, 0x24000001 }, - { 0x09002132, 0x68000000 }, - { 0x09002133, 0x24000000 }, - { 0x09002134, 0x14000000 }, - { 0x09802135, 0x1c000003 }, - { 0x09002139, 0x14000000 }, - { 0x0980213a, 0x68000001 }, - { 0x0980213c, 0x14000001 }, - { 0x0980213e, 0x24000001 }, - { 0x09802140, 0x64000004 }, - { 0x09002145, 0x24000000 }, - { 0x09802146, 0x14000003 }, - { 0x0900214a, 0x68000000 }, - { 0x0900214b, 0x64000000 }, - { 0x0900214c, 0x68000000 }, - { 0x09802153, 0x3c00000c }, - { 0x09002160, 0x38000010 }, - { 0x09002161, 0x38000010 }, - { 0x09002162, 0x38000010 }, - { 0x09002163, 0x38000010 }, - { 0x09002164, 0x38000010 }, - { 0x09002165, 0x38000010 }, - { 0x09002166, 0x38000010 }, - { 0x09002167, 0x38000010 }, - { 0x09002168, 0x38000010 }, - { 0x09002169, 0x38000010 }, - { 0x0900216a, 0x38000010 }, - { 0x0900216b, 0x38000010 }, - { 0x0900216c, 0x38000010 }, - { 0x0900216d, 0x38000010 }, - { 0x0900216e, 0x38000010 }, - { 0x0900216f, 0x38000010 }, - { 0x09002170, 0x3800fff0 }, - { 0x09002171, 0x3800fff0 }, - { 0x09002172, 0x3800fff0 }, - { 0x09002173, 0x3800fff0 }, - { 0x09002174, 0x3800fff0 }, - { 0x09002175, 0x3800fff0 }, - { 0x09002176, 0x3800fff0 }, - { 0x09002177, 0x3800fff0 }, - { 0x09002178, 0x3800fff0 }, - { 0x09002179, 0x3800fff0 }, - { 0x0900217a, 0x3800fff0 }, - { 0x0900217b, 0x3800fff0 }, - { 0x0900217c, 0x3800fff0 }, - { 0x0900217d, 0x3800fff0 }, - { 0x0900217e, 0x3800fff0 }, - { 0x0900217f, 0x3800fff0 }, - { 0x09802180, 0x38000003 }, - { 0x09802190, 0x64000004 }, - { 0x09802195, 0x68000004 }, - { 0x0980219a, 0x64000001 }, - { 0x0980219c, 0x68000003 }, - { 0x090021a0, 0x64000000 }, - { 0x098021a1, 0x68000001 }, - { 0x090021a3, 0x64000000 }, - { 0x098021a4, 0x68000001 }, - { 0x090021a6, 0x64000000 }, - { 0x098021a7, 0x68000006 }, - { 0x090021ae, 0x64000000 }, - { 0x098021af, 0x6800001e }, - { 0x098021ce, 0x64000001 }, - { 0x098021d0, 0x68000001 }, - { 0x090021d2, 0x64000000 }, - { 0x090021d3, 0x68000000 }, - { 0x090021d4, 0x64000000 }, - { 0x098021d5, 0x6800001e }, - { 0x098021f4, 0x6400010b }, - { 0x09802300, 0x68000007 }, - { 0x09802308, 0x64000003 }, - { 0x0980230c, 0x68000013 }, - { 0x09802320, 0x64000001 }, - { 0x09802322, 0x68000006 }, - { 0x09002329, 0x58000000 }, - { 0x0900232a, 0x48000000 }, - { 0x0980232b, 0x68000050 }, - { 0x0900237c, 0x64000000 }, - { 0x0980237d, 0x6800001d }, - { 0x0980239b, 0x64000018 }, - { 0x090023b4, 0x58000000 }, - { 0x090023b5, 0x48000000 }, - { 0x090023b6, 0x54000000 }, - { 0x098023b7, 0x68000024 }, - { 0x09802400, 0x68000026 }, - { 0x09802440, 0x6800000a }, - { 0x09802460, 0x3c00003b }, - { 0x0980249c, 0x68000019 }, - { 0x090024b6, 0x6800001a }, - { 0x090024b7, 0x6800001a }, - { 0x090024b8, 0x6800001a }, - { 0x090024b9, 0x6800001a }, - { 0x090024ba, 0x6800001a }, - { 0x090024bb, 0x6800001a }, - { 0x090024bc, 0x6800001a }, - { 0x090024bd, 0x6800001a }, - { 0x090024be, 0x6800001a }, - { 0x090024bf, 0x6800001a }, - { 0x090024c0, 0x6800001a }, - { 0x090024c1, 0x6800001a }, - { 0x090024c2, 0x6800001a }, - { 0x090024c3, 0x6800001a }, - { 0x090024c4, 0x6800001a }, - { 0x090024c5, 0x6800001a }, - { 0x090024c6, 0x6800001a }, - { 0x090024c7, 0x6800001a }, - { 0x090024c8, 0x6800001a }, - { 0x090024c9, 0x6800001a }, - { 0x090024ca, 0x6800001a }, - { 0x090024cb, 0x6800001a }, - { 0x090024cc, 0x6800001a }, - { 0x090024cd, 0x6800001a }, - { 0x090024ce, 0x6800001a }, - { 0x090024cf, 0x6800001a }, - { 0x090024d0, 0x6800ffe6 }, - { 0x090024d1, 0x6800ffe6 }, - { 0x090024d2, 0x6800ffe6 }, - { 0x090024d3, 0x6800ffe6 }, - { 0x090024d4, 0x6800ffe6 }, - { 0x090024d5, 0x6800ffe6 }, - { 0x090024d6, 0x6800ffe6 }, - { 0x090024d7, 0x6800ffe6 }, - { 0x090024d8, 0x6800ffe6 }, - { 0x090024d9, 0x6800ffe6 }, - { 0x090024da, 0x6800ffe6 }, - { 0x090024db, 0x6800ffe6 }, - { 0x090024dc, 0x6800ffe6 }, - { 0x090024dd, 0x6800ffe6 }, - { 0x090024de, 0x6800ffe6 }, - { 0x090024df, 0x6800ffe6 }, - { 0x090024e0, 0x6800ffe6 }, - { 0x090024e1, 0x6800ffe6 }, - { 0x090024e2, 0x6800ffe6 }, - { 0x090024e3, 0x6800ffe6 }, - { 0x090024e4, 0x6800ffe6 }, - { 0x090024e5, 0x6800ffe6 }, - { 0x090024e6, 0x6800ffe6 }, - { 0x090024e7, 0x6800ffe6 }, - { 0x090024e8, 0x6800ffe6 }, - { 0x090024e9, 0x6800ffe6 }, - { 0x098024ea, 0x3c000015 }, - { 0x09802500, 0x680000b6 }, - { 0x090025b7, 0x64000000 }, - { 0x098025b8, 0x68000008 }, - { 0x090025c1, 0x64000000 }, - { 0x098025c2, 0x68000035 }, - { 0x098025f8, 0x64000007 }, - { 0x09802600, 0x6800006e }, - { 0x0900266f, 0x64000000 }, - { 0x09802670, 0x6800002c }, - { 0x098026a0, 0x68000011 }, - { 0x09802701, 0x68000003 }, - { 0x09802706, 0x68000003 }, - { 0x0980270c, 0x6800001b }, - { 0x09802729, 0x68000022 }, - { 0x0900274d, 0x68000000 }, - { 0x0980274f, 0x68000003 }, - { 0x09002756, 0x68000000 }, - { 0x09802758, 0x68000006 }, - { 0x09802761, 0x68000006 }, - { 0x09002768, 0x58000000 }, - { 0x09002769, 0x48000000 }, - { 0x0900276a, 0x58000000 }, - { 0x0900276b, 0x48000000 }, - { 0x0900276c, 0x58000000 }, - { 0x0900276d, 0x48000000 }, - { 0x0900276e, 0x58000000 }, - { 0x0900276f, 0x48000000 }, - { 0x09002770, 0x58000000 }, - { 0x09002771, 0x48000000 }, - { 0x09002772, 0x58000000 }, - { 0x09002773, 0x48000000 }, - { 0x09002774, 0x58000000 }, - { 0x09002775, 0x48000000 }, - { 0x09802776, 0x3c00001d }, - { 0x09002794, 0x68000000 }, - { 0x09802798, 0x68000017 }, - { 0x098027b1, 0x6800000d }, - { 0x098027c0, 0x64000004 }, - { 0x090027c5, 0x58000000 }, - { 0x090027c6, 0x48000000 }, - { 0x098027d0, 0x64000015 }, - { 0x090027e6, 0x58000000 }, - { 0x090027e7, 0x48000000 }, - { 0x090027e8, 0x58000000 }, - { 0x090027e9, 0x48000000 }, - { 0x090027ea, 0x58000000 }, - { 0x090027eb, 0x48000000 }, - { 0x098027f0, 0x6400000f }, - { 0x04802800, 0x680000ff }, - { 0x09802900, 0x64000082 }, - { 0x09002983, 0x58000000 }, - { 0x09002984, 0x48000000 }, - { 0x09002985, 0x58000000 }, - { 0x09002986, 0x48000000 }, - { 0x09002987, 0x58000000 }, - { 0x09002988, 0x48000000 }, - { 0x09002989, 0x58000000 }, - { 0x0900298a, 0x48000000 }, - { 0x0900298b, 0x58000000 }, - { 0x0900298c, 0x48000000 }, - { 0x0900298d, 0x58000000 }, - { 0x0900298e, 0x48000000 }, - { 0x0900298f, 0x58000000 }, - { 0x09002990, 0x48000000 }, - { 0x09002991, 0x58000000 }, - { 0x09002992, 0x48000000 }, - { 0x09002993, 0x58000000 }, - { 0x09002994, 0x48000000 }, - { 0x09002995, 0x58000000 }, - { 0x09002996, 0x48000000 }, - { 0x09002997, 0x58000000 }, - { 0x09002998, 0x48000000 }, - { 0x09802999, 0x6400003e }, - { 0x090029d8, 0x58000000 }, - { 0x090029d9, 0x48000000 }, - { 0x090029da, 0x58000000 }, - { 0x090029db, 0x48000000 }, - { 0x098029dc, 0x6400001f }, - { 0x090029fc, 0x58000000 }, - { 0x090029fd, 0x48000000 }, - { 0x098029fe, 0x64000101 }, - { 0x09802b00, 0x68000013 }, - { 0x11002c00, 0x24000030 }, - { 0x11002c01, 0x24000030 }, - { 0x11002c02, 0x24000030 }, - { 0x11002c03, 0x24000030 }, - { 0x11002c04, 0x24000030 }, - { 0x11002c05, 0x24000030 }, - { 0x11002c06, 0x24000030 }, - { 0x11002c07, 0x24000030 }, - { 0x11002c08, 0x24000030 }, - { 0x11002c09, 0x24000030 }, - { 0x11002c0a, 0x24000030 }, - { 0x11002c0b, 0x24000030 }, - { 0x11002c0c, 0x24000030 }, - { 0x11002c0d, 0x24000030 }, - { 0x11002c0e, 0x24000030 }, - { 0x11002c0f, 0x24000030 }, - { 0x11002c10, 0x24000030 }, - { 0x11002c11, 0x24000030 }, - { 0x11002c12, 0x24000030 }, - { 0x11002c13, 0x24000030 }, - { 0x11002c14, 0x24000030 }, - { 0x11002c15, 0x24000030 }, - { 0x11002c16, 0x24000030 }, - { 0x11002c17, 0x24000030 }, - { 0x11002c18, 0x24000030 }, - { 0x11002c19, 0x24000030 }, - { 0x11002c1a, 0x24000030 }, - { 0x11002c1b, 0x24000030 }, - { 0x11002c1c, 0x24000030 }, - { 0x11002c1d, 0x24000030 }, - { 0x11002c1e, 0x24000030 }, - { 0x11002c1f, 0x24000030 }, - { 0x11002c20, 0x24000030 }, - { 0x11002c21, 0x24000030 }, - { 0x11002c22, 0x24000030 }, - { 0x11002c23, 0x24000030 }, - { 0x11002c24, 0x24000030 }, - { 0x11002c25, 0x24000030 }, - { 0x11002c26, 0x24000030 }, - { 0x11002c27, 0x24000030 }, - { 0x11002c28, 0x24000030 }, - { 0x11002c29, 0x24000030 }, - { 0x11002c2a, 0x24000030 }, - { 0x11002c2b, 0x24000030 }, - { 0x11002c2c, 0x24000030 }, - { 0x11002c2d, 0x24000030 }, - { 0x11002c2e, 0x24000030 }, - { 0x11002c30, 0x1400ffd0 }, - { 0x11002c31, 0x1400ffd0 }, - { 0x11002c32, 0x1400ffd0 }, - { 0x11002c33, 0x1400ffd0 }, - { 0x11002c34, 0x1400ffd0 }, - { 0x11002c35, 0x1400ffd0 }, - { 0x11002c36, 0x1400ffd0 }, - { 0x11002c37, 0x1400ffd0 }, - { 0x11002c38, 0x1400ffd0 }, - { 0x11002c39, 0x1400ffd0 }, - { 0x11002c3a, 0x1400ffd0 }, - { 0x11002c3b, 0x1400ffd0 }, - { 0x11002c3c, 0x1400ffd0 }, - { 0x11002c3d, 0x1400ffd0 }, - { 0x11002c3e, 0x1400ffd0 }, - { 0x11002c3f, 0x1400ffd0 }, - { 0x11002c40, 0x1400ffd0 }, - { 0x11002c41, 0x1400ffd0 }, - { 0x11002c42, 0x1400ffd0 }, - { 0x11002c43, 0x1400ffd0 }, - { 0x11002c44, 0x1400ffd0 }, - { 0x11002c45, 0x1400ffd0 }, - { 0x11002c46, 0x1400ffd0 }, - { 0x11002c47, 0x1400ffd0 }, - { 0x11002c48, 0x1400ffd0 }, - { 0x11002c49, 0x1400ffd0 }, - { 0x11002c4a, 0x1400ffd0 }, - { 0x11002c4b, 0x1400ffd0 }, - { 0x11002c4c, 0x1400ffd0 }, - { 0x11002c4d, 0x1400ffd0 }, - { 0x11002c4e, 0x1400ffd0 }, - { 0x11002c4f, 0x1400ffd0 }, - { 0x11002c50, 0x1400ffd0 }, - { 0x11002c51, 0x1400ffd0 }, - { 0x11002c52, 0x1400ffd0 }, - { 0x11002c53, 0x1400ffd0 }, - { 0x11002c54, 0x1400ffd0 }, - { 0x11002c55, 0x1400ffd0 }, - { 0x11002c56, 0x1400ffd0 }, - { 0x11002c57, 0x1400ffd0 }, - { 0x11002c58, 0x1400ffd0 }, - { 0x11002c59, 0x1400ffd0 }, - { 0x11002c5a, 0x1400ffd0 }, - { 0x11002c5b, 0x1400ffd0 }, - { 0x11002c5c, 0x1400ffd0 }, - { 0x11002c5d, 0x1400ffd0 }, - { 0x11002c5e, 0x1400ffd0 }, - { 0x0a002c80, 0x24000001 }, - { 0x0a002c81, 0x1400ffff }, - { 0x0a002c82, 0x24000001 }, - { 0x0a002c83, 0x1400ffff }, - { 0x0a002c84, 0x24000001 }, - { 0x0a002c85, 0x1400ffff }, - { 0x0a002c86, 0x24000001 }, - { 0x0a002c87, 0x1400ffff }, - { 0x0a002c88, 0x24000001 }, - { 0x0a002c89, 0x1400ffff }, - { 0x0a002c8a, 0x24000001 }, - { 0x0a002c8b, 0x1400ffff }, - { 0x0a002c8c, 0x24000001 }, - { 0x0a002c8d, 0x1400ffff }, - { 0x0a002c8e, 0x24000001 }, - { 0x0a002c8f, 0x1400ffff }, - { 0x0a002c90, 0x24000001 }, - { 0x0a002c91, 0x1400ffff }, - { 0x0a002c92, 0x24000001 }, - { 0x0a002c93, 0x1400ffff }, - { 0x0a002c94, 0x24000001 }, - { 0x0a002c95, 0x1400ffff }, - { 0x0a002c96, 0x24000001 }, - { 0x0a002c97, 0x1400ffff }, - { 0x0a002c98, 0x24000001 }, - { 0x0a002c99, 0x1400ffff }, - { 0x0a002c9a, 0x24000001 }, - { 0x0a002c9b, 0x1400ffff }, - { 0x0a002c9c, 0x24000001 }, - { 0x0a002c9d, 0x1400ffff }, - { 0x0a002c9e, 0x24000001 }, - { 0x0a002c9f, 0x1400ffff }, - { 0x0a002ca0, 0x24000001 }, - { 0x0a002ca1, 0x1400ffff }, - { 0x0a002ca2, 0x24000001 }, - { 0x0a002ca3, 0x1400ffff }, - { 0x0a002ca4, 0x24000001 }, - { 0x0a002ca5, 0x1400ffff }, - { 0x0a002ca6, 0x24000001 }, - { 0x0a002ca7, 0x1400ffff }, - { 0x0a002ca8, 0x24000001 }, - { 0x0a002ca9, 0x1400ffff }, - { 0x0a002caa, 0x24000001 }, - { 0x0a002cab, 0x1400ffff }, - { 0x0a002cac, 0x24000001 }, - { 0x0a002cad, 0x1400ffff }, - { 0x0a002cae, 0x24000001 }, - { 0x0a002caf, 0x1400ffff }, - { 0x0a002cb0, 0x24000001 }, - { 0x0a002cb1, 0x1400ffff }, - { 0x0a002cb2, 0x24000001 }, - { 0x0a002cb3, 0x1400ffff }, - { 0x0a002cb4, 0x24000001 }, - { 0x0a002cb5, 0x1400ffff }, - { 0x0a002cb6, 0x24000001 }, - { 0x0a002cb7, 0x1400ffff }, - { 0x0a002cb8, 0x24000001 }, - { 0x0a002cb9, 0x1400ffff }, - { 0x0a002cba, 0x24000001 }, - { 0x0a002cbb, 0x1400ffff }, - { 0x0a002cbc, 0x24000001 }, - { 0x0a002cbd, 0x1400ffff }, - { 0x0a002cbe, 0x24000001 }, - { 0x0a002cbf, 0x1400ffff }, - { 0x0a002cc0, 0x24000001 }, - { 0x0a002cc1, 0x1400ffff }, - { 0x0a002cc2, 0x24000001 }, - { 0x0a002cc3, 0x1400ffff }, - { 0x0a002cc4, 0x24000001 }, - { 0x0a002cc5, 0x1400ffff }, - { 0x0a002cc6, 0x24000001 }, - { 0x0a002cc7, 0x1400ffff }, - { 0x0a002cc8, 0x24000001 }, - { 0x0a002cc9, 0x1400ffff }, - { 0x0a002cca, 0x24000001 }, - { 0x0a002ccb, 0x1400ffff }, - { 0x0a002ccc, 0x24000001 }, - { 0x0a002ccd, 0x1400ffff }, - { 0x0a002cce, 0x24000001 }, - { 0x0a002ccf, 0x1400ffff }, - { 0x0a002cd0, 0x24000001 }, - { 0x0a002cd1, 0x1400ffff }, - { 0x0a002cd2, 0x24000001 }, - { 0x0a002cd3, 0x1400ffff }, - { 0x0a002cd4, 0x24000001 }, - { 0x0a002cd5, 0x1400ffff }, - { 0x0a002cd6, 0x24000001 }, - { 0x0a002cd7, 0x1400ffff }, - { 0x0a002cd8, 0x24000001 }, - { 0x0a002cd9, 0x1400ffff }, - { 0x0a002cda, 0x24000001 }, - { 0x0a002cdb, 0x1400ffff }, - { 0x0a002cdc, 0x24000001 }, - { 0x0a002cdd, 0x1400ffff }, - { 0x0a002cde, 0x24000001 }, - { 0x0a002cdf, 0x1400ffff }, - { 0x0a002ce0, 0x24000001 }, - { 0x0a002ce1, 0x1400ffff }, - { 0x0a002ce2, 0x24000001 }, - { 0x0a002ce3, 0x1400ffff }, - { 0x0a002ce4, 0x14000000 }, - { 0x0a802ce5, 0x68000005 }, - { 0x0a802cf9, 0x54000003 }, - { 0x0a002cfd, 0x3c000000 }, - { 0x0a802cfe, 0x54000001 }, - { 0x10002d00, 0x1400e3a0 }, - { 0x10002d01, 0x1400e3a0 }, - { 0x10002d02, 0x1400e3a0 }, - { 0x10002d03, 0x1400e3a0 }, - { 0x10002d04, 0x1400e3a0 }, - { 0x10002d05, 0x1400e3a0 }, - { 0x10002d06, 0x1400e3a0 }, - { 0x10002d07, 0x1400e3a0 }, - { 0x10002d08, 0x1400e3a0 }, - { 0x10002d09, 0x1400e3a0 }, - { 0x10002d0a, 0x1400e3a0 }, - { 0x10002d0b, 0x1400e3a0 }, - { 0x10002d0c, 0x1400e3a0 }, - { 0x10002d0d, 0x1400e3a0 }, - { 0x10002d0e, 0x1400e3a0 }, - { 0x10002d0f, 0x1400e3a0 }, - { 0x10002d10, 0x1400e3a0 }, - { 0x10002d11, 0x1400e3a0 }, - { 0x10002d12, 0x1400e3a0 }, - { 0x10002d13, 0x1400e3a0 }, - { 0x10002d14, 0x1400e3a0 }, - { 0x10002d15, 0x1400e3a0 }, - { 0x10002d16, 0x1400e3a0 }, - { 0x10002d17, 0x1400e3a0 }, - { 0x10002d18, 0x1400e3a0 }, - { 0x10002d19, 0x1400e3a0 }, - { 0x10002d1a, 0x1400e3a0 }, - { 0x10002d1b, 0x1400e3a0 }, - { 0x10002d1c, 0x1400e3a0 }, - { 0x10002d1d, 0x1400e3a0 }, - { 0x10002d1e, 0x1400e3a0 }, - { 0x10002d1f, 0x1400e3a0 }, - { 0x10002d20, 0x1400e3a0 }, - { 0x10002d21, 0x1400e3a0 }, - { 0x10002d22, 0x1400e3a0 }, - { 0x10002d23, 0x1400e3a0 }, - { 0x10002d24, 0x1400e3a0 }, - { 0x10002d25, 0x1400e3a0 }, - { 0x3a802d30, 0x1c000035 }, - { 0x3a002d6f, 0x18000000 }, - { 0x0f802d80, 0x1c000016 }, - { 0x0f802da0, 0x1c000006 }, - { 0x0f802da8, 0x1c000006 }, - { 0x0f802db0, 0x1c000006 }, - { 0x0f802db8, 0x1c000006 }, - { 0x0f802dc0, 0x1c000006 }, - { 0x0f802dc8, 0x1c000006 }, - { 0x0f802dd0, 0x1c000006 }, - { 0x0f802dd8, 0x1c000006 }, - { 0x09802e00, 0x54000001 }, - { 0x09002e02, 0x50000000 }, - { 0x09002e03, 0x4c000000 }, - { 0x09002e04, 0x50000000 }, - { 0x09002e05, 0x4c000000 }, - { 0x09802e06, 0x54000002 }, - { 0x09002e09, 0x50000000 }, - { 0x09002e0a, 0x4c000000 }, - { 0x09002e0b, 0x54000000 }, - { 0x09002e0c, 0x50000000 }, - { 0x09002e0d, 0x4c000000 }, - { 0x09802e0e, 0x54000008 }, - { 0x09002e17, 0x44000000 }, - { 0x09002e1c, 0x50000000 }, - { 0x09002e1d, 0x4c000000 }, - { 0x16802e80, 0x68000019 }, - { 0x16802e9b, 0x68000058 }, - { 0x16802f00, 0x680000d5 }, - { 0x09802ff0, 0x6800000b }, - { 0x09003000, 0x74000000 }, - { 0x09803001, 0x54000002 }, - { 0x09003004, 0x68000000 }, - { 0x16003005, 0x18000000 }, - { 0x09003006, 0x1c000000 }, - { 0x16003007, 0x38000000 }, - { 0x09003008, 0x58000000 }, - { 0x09003009, 0x48000000 }, - { 0x0900300a, 0x58000000 }, - { 0x0900300b, 0x48000000 }, - { 0x0900300c, 0x58000000 }, - { 0x0900300d, 0x48000000 }, - { 0x0900300e, 0x58000000 }, - { 0x0900300f, 0x48000000 }, - { 0x09003010, 0x58000000 }, - { 0x09003011, 0x48000000 }, - { 0x09803012, 0x68000001 }, - { 0x09003014, 0x58000000 }, - { 0x09003015, 0x48000000 }, - { 0x09003016, 0x58000000 }, - { 0x09003017, 0x48000000 }, - { 0x09003018, 0x58000000 }, - { 0x09003019, 0x48000000 }, - { 0x0900301a, 0x58000000 }, - { 0x0900301b, 0x48000000 }, - { 0x0900301c, 0x44000000 }, - { 0x0900301d, 0x58000000 }, - { 0x0980301e, 0x48000001 }, - { 0x09003020, 0x68000000 }, - { 0x16803021, 0x38000008 }, - { 0x1b80302a, 0x30000005 }, - { 0x09003030, 0x44000000 }, - { 0x09803031, 0x18000004 }, - { 0x09803036, 0x68000001 }, - { 0x16803038, 0x38000002 }, - { 0x1600303b, 0x18000000 }, - { 0x0900303c, 0x1c000000 }, - { 0x0900303d, 0x54000000 }, - { 0x0980303e, 0x68000001 }, - { 0x1a803041, 0x1c000055 }, - { 0x1b803099, 0x30000001 }, - { 0x0980309b, 0x60000001 }, - { 0x1a80309d, 0x18000001 }, - { 0x1a00309f, 0x1c000000 }, - { 0x090030a0, 0x44000000 }, - { 0x1d8030a1, 0x1c000059 }, - { 0x090030fb, 0x54000000 }, - { 0x098030fc, 0x18000002 }, - { 0x1d0030ff, 0x1c000000 }, - { 0x03803105, 0x1c000027 }, - { 0x17803131, 0x1c00005d }, - { 0x09803190, 0x68000001 }, - { 0x09803192, 0x3c000003 }, - { 0x09803196, 0x68000009 }, - { 0x038031a0, 0x1c000017 }, - { 0x098031c0, 0x6800000f }, - { 0x1d8031f0, 0x1c00000f }, - { 0x17803200, 0x6800001e }, - { 0x09803220, 0x3c000009 }, - { 0x0980322a, 0x68000019 }, - { 0x09003250, 0x68000000 }, - { 0x09803251, 0x3c00000e }, - { 0x17803260, 0x6800001f }, - { 0x09803280, 0x3c000009 }, - { 0x0980328a, 0x68000026 }, - { 0x098032b1, 0x3c00000e }, - { 0x098032c0, 0x6800003e }, - { 0x09803300, 0x680000ff }, - { 0x16803400, 0x1c0019b5 }, - { 0x09804dc0, 0x6800003f }, - { 0x16804e00, 0x1c0051bb }, - { 0x3c80a000, 0x1c000014 }, - { 0x3c00a015, 0x18000000 }, - { 0x3c80a016, 0x1c000476 }, - { 0x3c80a490, 0x68000036 }, - { 0x0980a700, 0x60000016 }, - { 0x3080a800, 0x1c000001 }, - { 0x3000a802, 0x28000000 }, - { 0x3080a803, 0x1c000002 }, - { 0x3000a806, 0x30000000 }, - { 0x3080a807, 0x1c000003 }, - { 0x3000a80b, 0x30000000 }, - { 0x3080a80c, 0x1c000016 }, - { 0x3080a823, 0x28000001 }, - { 0x3080a825, 0x30000001 }, - { 0x3000a827, 0x28000000 }, - { 0x3080a828, 0x68000003 }, - { 0x1780ac00, 0x1c002ba3 }, - { 0x0980d800, 0x1000037f }, - { 0x0980db80, 0x1000007f }, - { 0x0980dc00, 0x100003ff }, - { 0x0980e000, 0x0c0018ff }, - { 0x1680f900, 0x1c00012d }, - { 0x1680fa30, 0x1c00003a }, - { 0x1680fa70, 0x1c000069 }, - { 0x2180fb00, 0x14000006 }, - { 0x0180fb13, 0x14000004 }, - { 0x1900fb1d, 0x1c000000 }, - { 0x1900fb1e, 0x30000000 }, - { 0x1980fb1f, 0x1c000009 }, - { 0x1900fb29, 0x64000000 }, - { 0x1980fb2a, 0x1c00000c }, - { 0x1980fb38, 0x1c000004 }, - { 0x1900fb3e, 0x1c000000 }, - { 0x1980fb40, 0x1c000001 }, - { 0x1980fb43, 0x1c000001 }, - { 0x1980fb46, 0x1c00006b }, - { 0x0080fbd3, 0x1c00016a }, - { 0x0900fd3e, 0x58000000 }, - { 0x0900fd3f, 0x48000000 }, - { 0x0080fd50, 0x1c00003f }, - { 0x0080fd92, 0x1c000035 }, - { 0x0080fdf0, 0x1c00000b }, - { 0x0000fdfc, 0x5c000000 }, - { 0x0900fdfd, 0x68000000 }, - { 0x1b80fe00, 0x3000000f }, - { 0x0980fe10, 0x54000006 }, - { 0x0900fe17, 0x58000000 }, - { 0x0900fe18, 0x48000000 }, - { 0x0900fe19, 0x54000000 }, - { 0x1b80fe20, 0x30000003 }, - { 0x0900fe30, 0x54000000 }, - { 0x0980fe31, 0x44000001 }, - { 0x0980fe33, 0x40000001 }, - { 0x0900fe35, 0x58000000 }, - { 0x0900fe36, 0x48000000 }, - { 0x0900fe37, 0x58000000 }, - { 0x0900fe38, 0x48000000 }, - { 0x0900fe39, 0x58000000 }, - { 0x0900fe3a, 0x48000000 }, - { 0x0900fe3b, 0x58000000 }, - { 0x0900fe3c, 0x48000000 }, - { 0x0900fe3d, 0x58000000 }, - { 0x0900fe3e, 0x48000000 }, - { 0x0900fe3f, 0x58000000 }, - { 0x0900fe40, 0x48000000 }, - { 0x0900fe41, 0x58000000 }, - { 0x0900fe42, 0x48000000 }, - { 0x0900fe43, 0x58000000 }, - { 0x0900fe44, 0x48000000 }, - { 0x0980fe45, 0x54000001 }, - { 0x0900fe47, 0x58000000 }, - { 0x0900fe48, 0x48000000 }, - { 0x0980fe49, 0x54000003 }, - { 0x0980fe4d, 0x40000002 }, - { 0x0980fe50, 0x54000002 }, - { 0x0980fe54, 0x54000003 }, - { 0x0900fe58, 0x44000000 }, - { 0x0900fe59, 0x58000000 }, - { 0x0900fe5a, 0x48000000 }, - { 0x0900fe5b, 0x58000000 }, - { 0x0900fe5c, 0x48000000 }, - { 0x0900fe5d, 0x58000000 }, - { 0x0900fe5e, 0x48000000 }, - { 0x0980fe5f, 0x54000002 }, - { 0x0900fe62, 0x64000000 }, - { 0x0900fe63, 0x44000000 }, - { 0x0980fe64, 0x64000002 }, - { 0x0900fe68, 0x54000000 }, - { 0x0900fe69, 0x5c000000 }, - { 0x0980fe6a, 0x54000001 }, - { 0x0080fe70, 0x1c000004 }, - { 0x0080fe76, 0x1c000086 }, - { 0x0900feff, 0x04000000 }, - { 0x0980ff01, 0x54000002 }, - { 0x0900ff04, 0x5c000000 }, - { 0x0980ff05, 0x54000002 }, - { 0x0900ff08, 0x58000000 }, - { 0x0900ff09, 0x48000000 }, - { 0x0900ff0a, 0x54000000 }, - { 0x0900ff0b, 0x64000000 }, - { 0x0900ff0c, 0x54000000 }, - { 0x0900ff0d, 0x44000000 }, - { 0x0980ff0e, 0x54000001 }, - { 0x0980ff10, 0x34000009 }, - { 0x0980ff1a, 0x54000001 }, - { 0x0980ff1c, 0x64000002 }, - { 0x0980ff1f, 0x54000001 }, - { 0x2100ff21, 0x24000020 }, - { 0x2100ff22, 0x24000020 }, - { 0x2100ff23, 0x24000020 }, - { 0x2100ff24, 0x24000020 }, - { 0x2100ff25, 0x24000020 }, - { 0x2100ff26, 0x24000020 }, - { 0x2100ff27, 0x24000020 }, - { 0x2100ff28, 0x24000020 }, - { 0x2100ff29, 0x24000020 }, - { 0x2100ff2a, 0x24000020 }, - { 0x2100ff2b, 0x24000020 }, - { 0x2100ff2c, 0x24000020 }, - { 0x2100ff2d, 0x24000020 }, - { 0x2100ff2e, 0x24000020 }, - { 0x2100ff2f, 0x24000020 }, - { 0x2100ff30, 0x24000020 }, - { 0x2100ff31, 0x24000020 }, - { 0x2100ff32, 0x24000020 }, - { 0x2100ff33, 0x24000020 }, - { 0x2100ff34, 0x24000020 }, - { 0x2100ff35, 0x24000020 }, - { 0x2100ff36, 0x24000020 }, - { 0x2100ff37, 0x24000020 }, - { 0x2100ff38, 0x24000020 }, - { 0x2100ff39, 0x24000020 }, - { 0x2100ff3a, 0x24000020 }, - { 0x0900ff3b, 0x58000000 }, - { 0x0900ff3c, 0x54000000 }, - { 0x0900ff3d, 0x48000000 }, - { 0x0900ff3e, 0x60000000 }, - { 0x0900ff3f, 0x40000000 }, - { 0x0900ff40, 0x60000000 }, - { 0x2100ff41, 0x1400ffe0 }, - { 0x2100ff42, 0x1400ffe0 }, - { 0x2100ff43, 0x1400ffe0 }, - { 0x2100ff44, 0x1400ffe0 }, - { 0x2100ff45, 0x1400ffe0 }, - { 0x2100ff46, 0x1400ffe0 }, - { 0x2100ff47, 0x1400ffe0 }, - { 0x2100ff48, 0x1400ffe0 }, - { 0x2100ff49, 0x1400ffe0 }, - { 0x2100ff4a, 0x1400ffe0 }, - { 0x2100ff4b, 0x1400ffe0 }, - { 0x2100ff4c, 0x1400ffe0 }, - { 0x2100ff4d, 0x1400ffe0 }, - { 0x2100ff4e, 0x1400ffe0 }, - { 0x2100ff4f, 0x1400ffe0 }, - { 0x2100ff50, 0x1400ffe0 }, - { 0x2100ff51, 0x1400ffe0 }, - { 0x2100ff52, 0x1400ffe0 }, - { 0x2100ff53, 0x1400ffe0 }, - { 0x2100ff54, 0x1400ffe0 }, - { 0x2100ff55, 0x1400ffe0 }, - { 0x2100ff56, 0x1400ffe0 }, - { 0x2100ff57, 0x1400ffe0 }, - { 0x2100ff58, 0x1400ffe0 }, - { 0x2100ff59, 0x1400ffe0 }, - { 0x2100ff5a, 0x1400ffe0 }, - { 0x0900ff5b, 0x58000000 }, - { 0x0900ff5c, 0x64000000 }, - { 0x0900ff5d, 0x48000000 }, - { 0x0900ff5e, 0x64000000 }, - { 0x0900ff5f, 0x58000000 }, - { 0x0900ff60, 0x48000000 }, - { 0x0900ff61, 0x54000000 }, - { 0x0900ff62, 0x58000000 }, - { 0x0900ff63, 0x48000000 }, - { 0x0980ff64, 0x54000001 }, - { 0x1d80ff66, 0x1c000009 }, - { 0x0900ff70, 0x18000000 }, - { 0x1d80ff71, 0x1c00002c }, - { 0x0980ff9e, 0x18000001 }, - { 0x1780ffa0, 0x1c00001e }, - { 0x1780ffc2, 0x1c000005 }, - { 0x1780ffca, 0x1c000005 }, - { 0x1780ffd2, 0x1c000005 }, - { 0x1780ffda, 0x1c000002 }, - { 0x0980ffe0, 0x5c000001 }, - { 0x0900ffe2, 0x64000000 }, - { 0x0900ffe3, 0x60000000 }, - { 0x0900ffe4, 0x68000000 }, - { 0x0980ffe5, 0x5c000001 }, - { 0x0900ffe8, 0x68000000 }, - { 0x0980ffe9, 0x64000003 }, - { 0x0980ffed, 0x68000001 }, - { 0x0980fff9, 0x04000002 }, - { 0x0980fffc, 0x68000001 }, - { 0x23810000, 0x1c00000b }, - { 0x2381000d, 0x1c000019 }, - { 0x23810028, 0x1c000012 }, - { 0x2381003c, 0x1c000001 }, - { 0x2381003f, 0x1c00000e }, - { 0x23810050, 0x1c00000d }, - { 0x23810080, 0x1c00007a }, - { 0x09810100, 0x54000001 }, - { 0x09010102, 0x68000000 }, - { 0x09810107, 0x3c00002c }, - { 0x09810137, 0x68000008 }, - { 0x13810140, 0x38000034 }, - { 0x13810175, 0x3c000003 }, - { 0x13810179, 0x68000010 }, - { 0x1301018a, 0x3c000000 }, - { 0x29810300, 0x1c00001e }, - { 0x29810320, 0x3c000003 }, - { 0x12810330, 0x1c000019 }, - { 0x1201034a, 0x38000000 }, - { 0x3b810380, 0x1c00001d }, - { 0x3b01039f, 0x54000000 }, - { 0x2a8103a0, 0x1c000023 }, - { 0x2a8103c8, 0x1c000007 }, - { 0x2a0103d0, 0x68000000 }, - { 0x2a8103d1, 0x38000004 }, - { 0x0d010400, 0x24000028 }, - { 0x0d010401, 0x24000028 }, - { 0x0d010402, 0x24000028 }, - { 0x0d010403, 0x24000028 }, - { 0x0d010404, 0x24000028 }, - { 0x0d010405, 0x24000028 }, - { 0x0d010406, 0x24000028 }, - { 0x0d010407, 0x24000028 }, - { 0x0d010408, 0x24000028 }, - { 0x0d010409, 0x24000028 }, - { 0x0d01040a, 0x24000028 }, - { 0x0d01040b, 0x24000028 }, - { 0x0d01040c, 0x24000028 }, - { 0x0d01040d, 0x24000028 }, - { 0x0d01040e, 0x24000028 }, - { 0x0d01040f, 0x24000028 }, - { 0x0d010410, 0x24000028 }, - { 0x0d010411, 0x24000028 }, - { 0x0d010412, 0x24000028 }, - { 0x0d010413, 0x24000028 }, - { 0x0d010414, 0x24000028 }, - { 0x0d010415, 0x24000028 }, - { 0x0d010416, 0x24000028 }, - { 0x0d010417, 0x24000028 }, - { 0x0d010418, 0x24000028 }, - { 0x0d010419, 0x24000028 }, - { 0x0d01041a, 0x24000028 }, - { 0x0d01041b, 0x24000028 }, - { 0x0d01041c, 0x24000028 }, - { 0x0d01041d, 0x24000028 }, - { 0x0d01041e, 0x24000028 }, - { 0x0d01041f, 0x24000028 }, - { 0x0d010420, 0x24000028 }, - { 0x0d010421, 0x24000028 }, - { 0x0d010422, 0x24000028 }, - { 0x0d010423, 0x24000028 }, - { 0x0d010424, 0x24000028 }, - { 0x0d010425, 0x24000028 }, - { 0x0d010426, 0x24000028 }, - { 0x0d010427, 0x24000028 }, - { 0x0d010428, 0x1400ffd8 }, - { 0x0d010429, 0x1400ffd8 }, - { 0x0d01042a, 0x1400ffd8 }, - { 0x0d01042b, 0x1400ffd8 }, - { 0x0d01042c, 0x1400ffd8 }, - { 0x0d01042d, 0x1400ffd8 }, - { 0x0d01042e, 0x1400ffd8 }, - { 0x0d01042f, 0x1400ffd8 }, - { 0x0d010430, 0x1400ffd8 }, - { 0x0d010431, 0x1400ffd8 }, - { 0x0d010432, 0x1400ffd8 }, - { 0x0d010433, 0x1400ffd8 }, - { 0x0d010434, 0x1400ffd8 }, - { 0x0d010435, 0x1400ffd8 }, - { 0x0d010436, 0x1400ffd8 }, - { 0x0d010437, 0x1400ffd8 }, - { 0x0d010438, 0x1400ffd8 }, - { 0x0d010439, 0x1400ffd8 }, - { 0x0d01043a, 0x1400ffd8 }, - { 0x0d01043b, 0x1400ffd8 }, - { 0x0d01043c, 0x1400ffd8 }, - { 0x0d01043d, 0x1400ffd8 }, - { 0x0d01043e, 0x1400ffd8 }, - { 0x0d01043f, 0x1400ffd8 }, - { 0x0d010440, 0x1400ffd8 }, - { 0x0d010441, 0x1400ffd8 }, - { 0x0d010442, 0x1400ffd8 }, - { 0x0d010443, 0x1400ffd8 }, - { 0x0d010444, 0x1400ffd8 }, - { 0x0d010445, 0x1400ffd8 }, - { 0x0d010446, 0x1400ffd8 }, - { 0x0d010447, 0x1400ffd8 }, - { 0x0d010448, 0x1400ffd8 }, - { 0x0d010449, 0x1400ffd8 }, - { 0x0d01044a, 0x1400ffd8 }, - { 0x0d01044b, 0x1400ffd8 }, - { 0x0d01044c, 0x1400ffd8 }, - { 0x0d01044d, 0x1400ffd8 }, - { 0x0d01044e, 0x1400ffd8 }, - { 0x0d01044f, 0x1400ffd8 }, - { 0x2e810450, 0x1c00004d }, - { 0x2c8104a0, 0x34000009 }, - { 0x0b810800, 0x1c000005 }, - { 0x0b010808, 0x1c000000 }, - { 0x0b81080a, 0x1c00002b }, - { 0x0b810837, 0x1c000001 }, - { 0x0b01083c, 0x1c000000 }, - { 0x0b01083f, 0x1c000000 }, - { 0x1e010a00, 0x1c000000 }, - { 0x1e810a01, 0x30000002 }, - { 0x1e810a05, 0x30000001 }, - { 0x1e810a0c, 0x30000003 }, - { 0x1e810a10, 0x1c000003 }, - { 0x1e810a15, 0x1c000002 }, - { 0x1e810a19, 0x1c00001a }, - { 0x1e810a38, 0x30000002 }, - { 0x1e010a3f, 0x30000000 }, - { 0x1e810a40, 0x3c000007 }, - { 0x1e810a50, 0x54000008 }, - { 0x0981d000, 0x680000f5 }, - { 0x0981d100, 0x68000026 }, - { 0x0981d12a, 0x6800003a }, - { 0x0981d165, 0x28000001 }, - { 0x1b81d167, 0x30000002 }, - { 0x0981d16a, 0x68000002 }, - { 0x0981d16d, 0x28000005 }, - { 0x0981d173, 0x04000007 }, - { 0x1b81d17b, 0x30000007 }, - { 0x0981d183, 0x68000001 }, - { 0x1b81d185, 0x30000006 }, - { 0x0981d18c, 0x6800001d }, - { 0x1b81d1aa, 0x30000003 }, - { 0x0981d1ae, 0x6800002f }, - { 0x1381d200, 0x68000041 }, - { 0x1381d242, 0x30000002 }, - { 0x1301d245, 0x68000000 }, - { 0x0981d300, 0x68000056 }, - { 0x0981d400, 0x24000019 }, - { 0x0981d41a, 0x14000019 }, - { 0x0981d434, 0x24000019 }, - { 0x0981d44e, 0x14000006 }, - { 0x0981d456, 0x14000011 }, - { 0x0981d468, 0x24000019 }, - { 0x0981d482, 0x14000019 }, - { 0x0901d49c, 0x24000000 }, - { 0x0981d49e, 0x24000001 }, - { 0x0901d4a2, 0x24000000 }, - { 0x0981d4a5, 0x24000001 }, - { 0x0981d4a9, 0x24000003 }, - { 0x0981d4ae, 0x24000007 }, - { 0x0981d4b6, 0x14000003 }, - { 0x0901d4bb, 0x14000000 }, - { 0x0981d4bd, 0x14000006 }, - { 0x0981d4c5, 0x1400000a }, - { 0x0981d4d0, 0x24000019 }, - { 0x0981d4ea, 0x14000019 }, - { 0x0981d504, 0x24000001 }, - { 0x0981d507, 0x24000003 }, - { 0x0981d50d, 0x24000007 }, - { 0x0981d516, 0x24000006 }, - { 0x0981d51e, 0x14000019 }, - { 0x0981d538, 0x24000001 }, - { 0x0981d53b, 0x24000003 }, - { 0x0981d540, 0x24000004 }, - { 0x0901d546, 0x24000000 }, - { 0x0981d54a, 0x24000006 }, - { 0x0981d552, 0x14000019 }, - { 0x0981d56c, 0x24000019 }, - { 0x0981d586, 0x14000019 }, - { 0x0981d5a0, 0x24000019 }, - { 0x0981d5ba, 0x14000019 }, - { 0x0981d5d4, 0x24000019 }, - { 0x0981d5ee, 0x14000019 }, - { 0x0981d608, 0x24000019 }, - { 0x0981d622, 0x14000019 }, - { 0x0981d63c, 0x24000019 }, - { 0x0981d656, 0x14000019 }, - { 0x0981d670, 0x24000019 }, - { 0x0981d68a, 0x1400001b }, - { 0x0981d6a8, 0x24000018 }, - { 0x0901d6c1, 0x64000000 }, - { 0x0981d6c2, 0x14000018 }, - { 0x0901d6db, 0x64000000 }, - { 0x0981d6dc, 0x14000005 }, - { 0x0981d6e2, 0x24000018 }, - { 0x0901d6fb, 0x64000000 }, - { 0x0981d6fc, 0x14000018 }, - { 0x0901d715, 0x64000000 }, - { 0x0981d716, 0x14000005 }, - { 0x0981d71c, 0x24000018 }, - { 0x0901d735, 0x64000000 }, - { 0x0981d736, 0x14000018 }, - { 0x0901d74f, 0x64000000 }, - { 0x0981d750, 0x14000005 }, - { 0x0981d756, 0x24000018 }, - { 0x0901d76f, 0x64000000 }, - { 0x0981d770, 0x14000018 }, - { 0x0901d789, 0x64000000 }, - { 0x0981d78a, 0x14000005 }, - { 0x0981d790, 0x24000018 }, - { 0x0901d7a9, 0x64000000 }, - { 0x0981d7aa, 0x14000018 }, - { 0x0901d7c3, 0x64000000 }, - { 0x0981d7c4, 0x14000005 }, - { 0x0981d7ce, 0x34000031 }, - { 0x16820000, 0x1c00a6d6 }, - { 0x1682f800, 0x1c00021d }, - { 0x090e0001, 0x04000000 }, - { 0x098e0020, 0x0400005f }, - { 0x1b8e0100, 0x300000ef }, - { 0x098f0000, 0x0c00fffd }, - { 0x09900000, 0x0c00fffd }, -}; diff --git a/src/mod/event_handlers/mod_rayo/Makefile.am b/src/mod/event_handlers/mod_rayo/Makefile.am index 493e5c0835..abaa612e67 100644 --- a/src/mod/event_handlers/mod_rayo/Makefile.am +++ b/src/mod/event_handlers/mod_rayo/Makefile.am @@ -3,24 +3,17 @@ MODNAME=mod_rayo IKS_DIR=$(switch_srcdir)/libs/iksemel IKS_BUILDDIR=$(switch_builddir)/libs/iksemel -PCRE_DIR=$(switch_srcdir)/libs/pcre -PCRE_BUILDDIR=$(switch_builddir)/libs/pcre IKS_LA=$(IKS_BUILDDIR)/src/libiksemel.la -PCRE_LA=$(PCRE_BUILDDIR)/libpcre.la mod_LTLIBRARIES = mod_rayo.la mod_rayo_la_SOURCES = mod_rayo.c iks_helpers.c nlsml.c rayo_components.c rayo_cpa_component.c rayo_cpa_detector.c rayo_elements.c rayo_fax_components.c mod_rayo_la_SOURCES += rayo_input_component.c rayo_output_component.c rayo_prompt_component.c rayo_record_component.c sasl.c srgs.c xmpp_streams.c -mod_rayo_la_CFLAGS = $(AM_CFLAGS) -I$(IKS_DIR)/include -I$(switch_srcdir)/libs/pcre -mod_rayo_la_LIBADD = $(switch_builddir)/libfreeswitch.la $(IKS_LA) $(PCRE_LA) +mod_rayo_la_CFLAGS = $(AM_CFLAGS) -I$(IKS_DIR)/include $(PCRE_CFLAGS) +mod_rayo_la_LIBADD = $(switch_builddir)/libfreeswitch.la $(IKS_LA) $(PCRE_LIBS) mod_rayo_la_LDFLAGS = -avoid-version -module -no-undefined -shared -BUILT_SOURCES=$(IKS_LA) $(PCRE_LA) +BUILT_SOURCES=$(IKS_LA) $(IKS_LA): $(IKS_BUILDDIR) $(IKS_DIR) $(IKS_DIR)/.update @cd $(IKS_BUILDDIR) && $(MAKE) @$(TOUCH_TARGET) - -$(PCRE_LA): $(PCRE_BUILDDIR) $(PCRE_DIR) $(PCRE_DIR)/.update - @cd $(PCRE_BUILDDIR) && $(MAKE) - @$(TOUCH_TARGET)