diff options
48 files changed, 1630 insertions, 1236 deletions
diff --git a/pcre/AUTHORS b/pcre/AUTHORS index 342417a8a19..291657caef1 100644 --- a/pcre/AUTHORS +++ b/pcre/AUTHORS @@ -8,7 +8,7 @@ Email domain: cam.ac.uk University of Cambridge Computing Service, Cambridge, England. -Copyright (c) 1997-2016 University of Cambridge +Copyright (c) 1997-2017 University of Cambridge All rights reserved @@ -19,7 +19,7 @@ Written by: Zoltan Herczeg Email local part: hzmester Emain domain: freemail.hu -Copyright(c) 2010-2016 Zoltan Herczeg +Copyright(c) 2010-2017 Zoltan Herczeg All rights reserved. @@ -30,7 +30,7 @@ Written by: Zoltan Herczeg Email local part: hzmester Emain domain: freemail.hu -Copyright(c) 2009-2016 Zoltan Herczeg +Copyright(c) 2009-2017 Zoltan Herczeg All rights reserved. diff --git a/pcre/CMakeLists.txt b/pcre/CMakeLists.txt index ce6b1673688..42451ad82fd 100644 --- a/pcre/CMakeLists.txt +++ b/pcre/CMakeLists.txt @@ -66,6 +66,7 @@ # 2013-10-08 PH got rid of the "source" command, which is a bash-ism (use ".") # 2013-11-05 PH added support for PARENS_NEST_LIMIT # 2016-03-01 PH applied Chris Wilson's patch for MSVC static build +# 2016-06-24 PH applied Chris Wilson's revised patch (adds a separate option) PROJECT(PCRE C CXX) @@ -190,6 +191,9 @@ IF (MINGW) ENDIF(MINGW) IF(MSVC) + OPTION(PCRE_STATIC_RUNTIME OFF CACHE BOOL + "ON=Compile against the static runtime (/MT)." + OFF) OPTION(INSTALL_MSVC_PDB "ON=Install .pdb files built by MSVC, if generated" OFF) @@ -573,8 +577,8 @@ ENDIF(MSVC AND NOT PCRE_STATIC) # Fix static compilation with MSVC: https://bugs.exim.org/show_bug.cgi?id=1681 # This code was taken from the CMake wiki, not from WebM. -IF(MSVC AND PCRE_STATIC) - MESSAGE(STATUS "** MSVC and PCRE_STATIC: modifying compiler flags to use static runtime library") +IF(MSVC AND PCRE_STATIC_RUNTIME) + MESSAGE(STATUS "** MSVC and PCRE_STATIC_RUNTIME: modifying compiler flags to use static runtime library") foreach(flag_var CMAKE_C_FLAGS CMAKE_C_FLAGS_DEBUG CMAKE_C_FLAGS_RELEASE CMAKE_C_FLAGS_MINSIZEREL CMAKE_C_FLAGS_RELWITHDEBINFO @@ -582,7 +586,7 @@ IF(MSVC AND PCRE_STATIC) CMAKE_CXX_FLAGS_MINSIZEREL CMAKE_CXX_FLAGS_RELWITHDEBINFO) string(REGEX REPLACE "/MD" "/MT" ${flag_var} "${${flag_var}}") endforeach() -ENDIF(MSVC AND PCRE_STATIC) +ENDIF(MSVC AND PCRE_STATIC_RUNTIME) SET(PCRECPP_HEADERS pcrecpp.h diff --git a/pcre/ChangeLog b/pcre/ChangeLog index a34f845f8a1..01511b1327c 100644 --- a/pcre/ChangeLog +++ b/pcre/ChangeLog @@ -4,6 +4,53 @@ ChangeLog for PCRE Note that the PCRE 8.xx series (PCRE1) is now in a bugfix-only state. All development is happening in the PCRE2 10.xx series. +Version 8.40 11-January-2017 +---------------------------- + +1. Using -o with -M in pcregrep could cause unnecessary repeated output when + the match extended over a line boundary. + +2. Applied Chris Wilson's second patch (Bugzilla #1681) to CMakeLists.txt for + MSVC static compilation, putting the first patch under a new option. + +3. Fix register overwite in JIT when SSE2 acceleration is enabled. + +4. Ignore "show all captures" (/=) for DFA matching. + +5. Fix JIT unaligned accesses on x86. Patch by Marc Mutz. + +6. In any wide-character mode (8-bit UTF or any 16-bit or 32-bit mode), + without PCRE_UCP set, a negative character type such as \D in a positive + class should cause all characters greater than 255 to match, whatever else + is in the class. There was a bug that caused this not to happen if a + Unicode property item was added to such a class, for example [\D\P{Nd}] or + [\W\pL]. + +7. When pcretest was outputing information from a callout, the caret indicator + for the current position in the subject line was incorrect if it was after + an escape sequence for a character whose code point was greater than + \x{ff}. + +8. A pattern such as (?<RA>abc)(?(R)xyz) was incorrectly compiled such that + the conditional was interpreted as a reference to capturing group 1 instead + of a test for recursion. Any group whose name began with R was + misinterpreted in this way. (The reference interpretation should only + happen if the group's name is precisely "R".) + +9. A number of bugs have been mended relating to match start-up optimizations + when the first thing in a pattern is a positive lookahead. These all + applied only when PCRE_NO_START_OPTIMIZE was *not* set: + + (a) A pattern such as (?=.*X)X$ was incorrectly optimized as if it needed + both an initial 'X' and a following 'X'. + (b) Some patterns starting with an assertion that started with .* were + incorrectly optimized as having to match at the start of the subject or + after a newline. There are cases where this is not true, for example, + (?=.*[A-Z])(?=.{8,16})(?!.*[\s]) matches after the start in lines that + start with spaces. Starting .* in an assertion is no longer taken as an + indication of matching at the start (or after a newline). + + Version 8.39 14-June-2016 ------------------------- diff --git a/pcre/LICENCE b/pcre/LICENCE index dd977af971b..dd9071a8dd8 100644 --- a/pcre/LICENCE +++ b/pcre/LICENCE @@ -25,7 +25,7 @@ Email domain: cam.ac.uk University of Cambridge Computing Service, Cambridge, England. -Copyright (c) 1997-2016 University of Cambridge +Copyright (c) 1997-2017 University of Cambridge All rights reserved. @@ -36,7 +36,7 @@ Written by: Zoltan Herczeg Email local part: hzmester Emain domain: freemail.hu -Copyright(c) 2010-2016 Zoltan Herczeg +Copyright(c) 2010-2017 Zoltan Herczeg All rights reserved. @@ -47,7 +47,7 @@ Written by: Zoltan Herczeg Email local part: hzmester Emain domain: freemail.hu -Copyright(c) 2009-2016 Zoltan Herczeg +Copyright(c) 2009-2017 Zoltan Herczeg All rights reserved. diff --git a/pcre/Makefile.in b/pcre/Makefile.in index 6d039125a97..9c8ccecbd87 100644 --- a/pcre/Makefile.in +++ b/pcre/Makefile.in @@ -2832,7 +2832,7 @@ distdir: $(DISTFILES) ! -type d ! -perm -444 -exec $(install_sh) -c -m a+r {} {} \; \ || chmod -R a+r "$(distdir)" dist-gzip: distdir - tardir=$(distdir) && $(am__tar) | GZIP=$(GZIP_ENV) gzip -c >$(distdir).tar.gz + tardir=$(distdir) && $(am__tar) | eval GZIP= gzip $(GZIP_ENV) -c >$(distdir).tar.gz $(am__post_remove_distdir) dist-bzip2: distdir tardir=$(distdir) && $(am__tar) | BZIP2=$${BZIP2--9} bzip2 -c >$(distdir).tar.bz2 @@ -2857,7 +2857,7 @@ dist-shar: distdir @echo WARNING: "Support for shar distribution archives is" \ "deprecated." >&2 @echo WARNING: "It will be removed altogether in Automake 2.0" >&2 - shar $(distdir) | GZIP=$(GZIP_ENV) gzip -c >$(distdir).shar.gz + shar $(distdir) | eval GZIP= gzip $(GZIP_ENV) -c >$(distdir).shar.gz $(am__post_remove_distdir) dist-zip: distdir -rm -f $(distdir).zip @@ -2874,7 +2874,7 @@ dist dist-all: distcheck: dist case '$(DIST_ARCHIVES)' in \ *.tar.gz*) \ - GZIP=$(GZIP_ENV) gzip -dc $(distdir).tar.gz | $(am__untar) ;;\ + eval GZIP= gzip $(GZIP_ENV) -dc $(distdir).tar.gz | $(am__untar) ;;\ *.tar.bz2*) \ bzip2 -dc $(distdir).tar.bz2 | $(am__untar) ;;\ *.tar.lz*) \ @@ -2884,7 +2884,7 @@ distcheck: dist *.tar.Z*) \ uncompress -c $(distdir).tar.Z | $(am__untar) ;;\ *.shar.gz*) \ - GZIP=$(GZIP_ENV) gzip -dc $(distdir).shar.gz | unshar ;;\ + eval GZIP= gzip $(GZIP_ENV) -dc $(distdir).shar.gz | unshar ;;\ *.zip*) \ unzip $(distdir).zip ;;\ esac diff --git a/pcre/NEWS b/pcre/NEWS index 0ca1bab2a4c..b92c4f9605e 100644 --- a/pcre/NEWS +++ b/pcre/NEWS @@ -1,6 +1,12 @@ News about PCRE releases ------------------------ +Release 8.40 11-January-2017 +---------------------------- + +This is a bug-fix release. + + Release 8.39 14-June-2016 ------------------------- diff --git a/pcre/config.h.generic b/pcre/config.h.generic index ccc26dbbba2..f09749060cf 100644 --- a/pcre/config.h.generic +++ b/pcre/config.h.generic @@ -235,7 +235,7 @@ sure both macros are undefined; an emulation function will then be used. */ #define PACKAGE_NAME "PCRE" /* Define to the full name and version of this package. */ -#define PACKAGE_STRING "PCRE 8.39" +#define PACKAGE_STRING "PCRE 8.40" /* Define to the one symbol short name of this package. */ #define PACKAGE_TARNAME "pcre" @@ -244,7 +244,7 @@ sure both macros are undefined; an emulation function will then be used. */ #define PACKAGE_URL "" /* Define to the version of this package. */ -#define PACKAGE_VERSION "8.39" +#define PACKAGE_VERSION "8.40" /* The value of PARENS_NEST_LIMIT specifies the maximum depth of nested parentheses (of any kind) in a pattern. This limits the amount of system @@ -336,7 +336,7 @@ sure both macros are undefined; an emulation function will then be used. */ /* #undef SUPPORT_VALGRIND */ /* Version number of package */ -#define VERSION "8.39" +#define VERSION "8.40" /* Define to empty if `const' does not conform to ANSI C. */ /* #undef const */ diff --git a/pcre/configure b/pcre/configure index 54678cf7d16..42b9638d5ee 100755 --- a/pcre/configure +++ b/pcre/configure @@ -1,6 +1,6 @@ #! /bin/sh # Guess values for system-dependent variables and create Makefiles. -# Generated by GNU Autoconf 2.69 for PCRE 8.39. +# Generated by GNU Autoconf 2.69 for PCRE 8.40. # # # Copyright (C) 1992-1996, 1998-2012 Free Software Foundation, Inc. @@ -587,8 +587,8 @@ MAKEFLAGS= # Identity of this package. PACKAGE_NAME='PCRE' PACKAGE_TARNAME='pcre' -PACKAGE_VERSION='8.39' -PACKAGE_STRING='PCRE 8.39' +PACKAGE_VERSION='8.40' +PACKAGE_STRING='PCRE 8.40' PACKAGE_BUGREPORT='' PACKAGE_URL='' @@ -1418,7 +1418,7 @@ if test "$ac_init_help" = "long"; then # Omit some internal or obsolete options to make the list less imposing. # This message is too long to be a string in the A/UX 3.1 sh. cat <<_ACEOF -\`configure' configures PCRE 8.39 to adapt to many kinds of systems. +\`configure' configures PCRE 8.40 to adapt to many kinds of systems. Usage: $0 [OPTION]... [VAR=VALUE]... @@ -1488,7 +1488,7 @@ fi if test -n "$ac_init_help"; then case $ac_init_help in - short | recursive ) echo "Configuration of PCRE 8.39:";; + short | recursive ) echo "Configuration of PCRE 8.40:";; esac cat <<\_ACEOF @@ -1662,7 +1662,7 @@ fi test -n "$ac_init_help" && exit $ac_status if $ac_init_version; then cat <<\_ACEOF -PCRE configure 8.39 +PCRE configure 8.40 generated by GNU Autoconf 2.69 Copyright (C) 2012 Free Software Foundation, Inc. @@ -2419,7 +2419,7 @@ cat >config.log <<_ACEOF This file contains any messages produced by compilers while running configure, to aid debugging if configure makes a mistake. -It was created by PCRE $as_me 8.39, which was +It was created by PCRE $as_me 8.40, which was generated by GNU Autoconf 2.69. Invocation command line was $ $0 $@ @@ -3283,7 +3283,7 @@ fi # Define the identity of the package. PACKAGE='pcre' - VERSION='8.39' + VERSION='8.40' cat >>confdefs.h <<_ACEOF @@ -17634,9 +17634,9 @@ _ACEOF # Versioning PCRE_MAJOR="8" -PCRE_MINOR="39" +PCRE_MINOR="40" PCRE_PRERELEASE="" -PCRE_DATE="2016-06-14" +PCRE_DATE="2017-01-11" if test "$PCRE_MINOR" = "08" -o "$PCRE_MINOR" = "09" then @@ -19658,13 +19658,13 @@ esac # (Note: The libpcre*_version bits are m4 variables, assigned above) EXTRA_LIBPCRE_LDFLAGS="$EXTRA_LIBPCRE_LDFLAGS \ - $NO_UNDEFINED -version-info 3:7:2" + $NO_UNDEFINED -version-info 3:8:2" EXTRA_LIBPCRE16_LDFLAGS="$EXTRA_LIBPCRE16_LDFLAGS \ - $NO_UNDEFINED -version-info 2:7:2" + $NO_UNDEFINED -version-info 2:8:2" EXTRA_LIBPCRE32_LDFLAGS="$EXTRA_LIBPCRE32_LDFLAGS \ - $NO_UNDEFINED -version-info 0:7:0" + $NO_UNDEFINED -version-info 0:8:0" EXTRA_LIBPCREPOSIX_LDFLAGS="$EXTRA_LIBPCREPOSIX_LDFLAGS \ $NO_UNDEFINED -version-info 0:4:0" @@ -20719,7 +20719,7 @@ cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1 # report actual input values of CONFIG_FILES etc. instead of their # values after options handling. ac_log=" -This file was extended by PCRE $as_me 8.39, which was +This file was extended by PCRE $as_me 8.40, which was generated by GNU Autoconf 2.69. Invocation command line was CONFIG_FILES = $CONFIG_FILES @@ -20785,7 +20785,7 @@ _ACEOF cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1 ac_cs_config="`$as_echo "$ac_configure_args" | sed 's/^ //; s/[\\""\`\$]/\\\\&/g'`" ac_cs_version="\\ -PCRE config.status 8.39 +PCRE config.status 8.40 configured by $0, generated by GNU Autoconf 2.69, with options \\"\$ac_cs_config\\" diff --git a/pcre/configure.ac b/pcre/configure.ac index 3cefaf100f9..24ef7271e05 100644 --- a/pcre/configure.ac +++ b/pcre/configure.ac @@ -9,17 +9,17 @@ dnl The PCRE_PRERELEASE feature is for identifying release candidates. It might dnl be defined as -RC2, for example. For real releases, it should be empty. m4_define(pcre_major, [8]) -m4_define(pcre_minor, [39]) +m4_define(pcre_minor, [40]) m4_define(pcre_prerelease, []) -m4_define(pcre_date, [2016-06-14]) +m4_define(pcre_date, [2017-01-11]) # NOTE: The CMakeLists.txt file searches for the above variables in the first # 50 lines of this file. Please update that if the variables above are moved. # Libtool shared library interface versions (current:revision:age) -m4_define(libpcre_version, [3:7:2]) -m4_define(libpcre16_version, [2:7:2]) -m4_define(libpcre32_version, [0:7:0]) +m4_define(libpcre_version, [3:8:2]) +m4_define(libpcre16_version, [2:8:2]) +m4_define(libpcre32_version, [0:8:0]) m4_define(libpcreposix_version, [0:4:0]) m4_define(libpcrecpp_version, [0:1:0]) diff --git a/pcre/doc/html/pcrecompat.html b/pcre/doc/html/pcrecompat.html index 3e6226692ee..d95570ef179 100644 --- a/pcre/doc/html/pcrecompat.html +++ b/pcre/doc/html/pcrecompat.html @@ -128,7 +128,7 @@ the pattern /^(a(b)?)+$/ in Perl leaves $2 unset, but in PCRE it is set to "b". 14. PCRE's handling of duplicate subpattern numbers and duplicate subpattern names is not as general as Perl's. This is a consequence of the fact the PCRE works internally just with numbers, using an external table to translate -between numbers and names. In particular, a pattern such as (?|(?<a>A)|(?<b)B), +between numbers and names. In particular, a pattern such as (?|(?<a>A)|(?<b>B), where the two capturing parentheses have the same number but different names, is not supported, and causes an error at compile time. If it were allowed, it would not be possible to distinguish which parentheses matched, because both diff --git a/pcre/doc/html/pcrepattern.html b/pcre/doc/html/pcrepattern.html index 55034a7edf6..96fc72986f6 100644 --- a/pcre/doc/html/pcrepattern.html +++ b/pcre/doc/html/pcrepattern.html @@ -358,24 +358,24 @@ When PCRE is compiled in EBCDIC mode, \a, \e, \f, \n, \r, and \t generate the appropriate EBCDIC code values. The \c escape is processed as specified for Perl in the <b>perlebcdic</b> document. The only characters that are allowed after \c are A-Z, a-z, or one of @, [, \, ], ^, _, or ?. Any -other character provokes a compile-time error. The sequence \@ encodes -character code 0; the letters (in either case) encode characters 1-26 (hex 01 -to hex 1A); [, \, ], ^, and _ encode characters 27-31 (hex 1B to hex 1F), and -\? becomes either 255 (hex FF) or 95 (hex 5F). +other character provokes a compile-time error. The sequence \c@ encodes +character code 0; after \c the letters (in either case) encode characters 1-26 +(hex 01 to hex 1A); [, \, ], ^, and _ encode characters 27-31 (hex 1B to hex +1F), and \c? becomes either 255 (hex FF) or 95 (hex 5F). </P> <P> -Thus, apart from \?, these escapes generate the same character code values as +Thus, apart from \c?, these escapes generate the same character code values as they do in an ASCII environment, though the meanings of the values mostly -differ. For example, \G always generates code value 7, which is BEL in ASCII +differ. For example, \cG always generates code value 7, which is BEL in ASCII but DEL in EBCDIC. </P> <P> -The sequence \? generates DEL (127, hex 7F) in an ASCII environment, but +The sequence \c? generates DEL (127, hex 7F) in an ASCII environment, but because 127 is not a control character in EBCDIC, Perl makes it generate the APC character. Unfortunately, there are several variants of EBCDIC. In most of them the APC character has the value 255 (hex FF), but in the one Perl calls POSIX-BC its value is 95 (hex 5F). If certain other characters have POSIX-BC -values, PCRE makes \? generate 95; otherwise it generates 255. +values, PCRE makes \c? generate 95; otherwise it generates 255. </P> <P> After \0 up to two further octal digits are read. If there are fewer than two @@ -1512,13 +1512,8 @@ 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 <b>pcre_fullinfo()</b> function). -</P> -<P> -An option change within a subpattern (see below for a description of -subpatterns) affects only that part of the subpattern that follows it, so +that follows. An option change within a subpattern (see below for a description +of subpatterns) affects only that part of the subpattern that follows it, so <pre> (a(?i)b)c </pre> @@ -2160,6 +2155,14 @@ capturing is carried out only for positive assertions. (Perl sometimes, but not always, does do capturing in negative assertions.) </P> <P> +WARNING: If a positive assertion containing one or more capturing subpatterns +succeeds, but failure to match later in the pattern causes backtracking over +this assertion, the captures within the assertion are reset only if no higher +numbered captures are already set. This is, unfortunately, a fundamental +limitation of the current implementation, and as PCRE1 is now in +maintenance-only status, it is unlikely ever to change. +</P> +<P> For compatibility with Perl, assertion subpatterns may be repeated; though it makes no sense to assert the same thing several times, the side effect of capturing parentheses may occasionally be useful. In practice, there only three @@ -3264,9 +3267,9 @@ Cambridge CB2 3QH, England. </P> <br><a name="SEC30" href="#TOC1">REVISION</a><br> <P> -Last updated: 14 June 2015 +Last updated: 23 October 2016 <br> -Copyright © 1997-2015 University of Cambridge. +Copyright © 1997-2016 University of Cambridge. <br> <p> Return to the <a href="index.html">PCRE index page</a>. diff --git a/pcre/doc/pcre.txt b/pcre/doc/pcre.txt index f5eb347e18a..d68d5033ceb 100644 --- a/pcre/doc/pcre.txt +++ b/pcre/doc/pcre.txt @@ -4640,7 +4640,7 @@ DIFFERENCES BETWEEN PCRE AND PERL pattern names is not as general as Perl's. This is a consequence of the fact the PCRE works internally just with numbers, using an external ta- ble to translate between numbers and names. In particular, a pattern - such as (?|(?<a>A)|(?<b)B), where the two capturing parentheses have + such as (?|(?<a>A)|(?<b>B), where the two capturing parentheses have the same number but different names, is not supported, and causes an error at compile time. If it were allowed, it would not be possible to distinguish which parentheses matched, because both names map to cap- @@ -5028,55 +5028,56 @@ BACKSLASH ate the appropriate EBCDIC code values. The \c escape is processed as specified for Perl in the perlebcdic document. The only characters that are allowed after \c are A-Z, a-z, or one of @, [, \, ], ^, _, or ?. - Any other character provokes a compile-time error. The sequence \@ - encodes character code 0; the letters (in either case) encode charac- - ters 1-26 (hex 01 to hex 1A); [, \, ], ^, and _ encode characters 27-31 - (hex 1B to hex 1F), and \? becomes either 255 (hex FF) or 95 (hex 5F). - - Thus, apart from \?, these escapes generate the same character code - values as they do in an ASCII environment, though the meanings of the - values mostly differ. For example, \G always generates code value 7, + Any other character provokes a compile-time error. The sequence \c@ + encodes character code 0; after \c the letters (in either case) encode + characters 1-26 (hex 01 to hex 1A); [, \, ], ^, and _ encode characters + 27-31 (hex 1B to hex 1F), and \c? becomes either 255 (hex FF) or 95 + (hex 5F). + + Thus, apart from \c?, these escapes generate the same character code + values as they do in an ASCII environment, though the meanings of the + values mostly differ. For example, \cG always generates code value 7, which is BEL in ASCII but DEL in EBCDIC. - The sequence \? generates DEL (127, hex 7F) in an ASCII environment, - but because 127 is not a control character in EBCDIC, Perl makes it - generate the APC character. Unfortunately, there are several variants - of EBCDIC. In most of them the APC character has the value 255 (hex - FF), but in the one Perl calls POSIX-BC its value is 95 (hex 5F). If - certain other characters have POSIX-BC values, PCRE makes \? generate + The sequence \c? generates DEL (127, hex 7F) in an ASCII environment, + but because 127 is not a control character in EBCDIC, Perl makes it + generate the APC character. Unfortunately, there are several variants + of EBCDIC. In most of them the APC character has the value 255 (hex + FF), but in the one Perl calls POSIX-BC its value is 95 (hex 5F). If + certain other characters have POSIX-BC values, PCRE makes \c? generate 95; otherwise it generates 255. - 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 + 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\015 specifies two binary zeros followed by a CR character (code value 13). Make sure you supply two digits after the initial zero if the pattern character that follows is itself an octal digit. - The escape \o must be followed by a sequence of octal digits, enclosed - in braces. An error occurs if this is not the case. This escape is a - recent addition to Perl; it provides way of specifying character code - points as octal numbers greater than 0777, and it also allows octal + The escape \o must be followed by a sequence of octal digits, enclosed + in braces. An error occurs if this is not the case. This escape is a + recent addition to Perl; it provides way of specifying character code + points as octal numbers greater than 0777, and it also allows octal numbers and back references to be unambiguously specified. For greater clarity and unambiguity, it is best to avoid following \ by a digit greater than zero. Instead, use \o{} or \x{} to specify charac- - ter numbers, and \g{} to specify back references. The following para- + ter numbers, and \g{} to specify back references. The following para- graphs describe the old, ambiguous syntax. The handling of a backslash followed by a digit other than 0 is compli- - cated, and Perl has changed in recent releases, causing PCRE also to + cated, and Perl has changed in recent releases, causing PCRE also to change. Outside a character class, PCRE reads the digit and any follow- - ing digits as a decimal number. If the number is less than 8, 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 + ing digits as a decimal number. If the number is less than 8, 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 following \ is + Inside a character class, or if the decimal number following \ is greater than 7 and there have not been that many capturing subpatterns, - PCRE handles \8 and \9 as the literal characters "8" and "9", and oth- + PCRE handles \8 and \9 as the literal characters "8" and "9", and oth- erwise re-reads up to three octal digits following the backslash, using - them to generate a data character. Any subsequent digits stand for + them to generate a data character. Any subsequent digits stand for themselves. For example: \040 is another way of writing an ASCII space @@ -5094,31 +5095,31 @@ BACKSLASH \81 is either a back reference, or the two characters "8" and "1" - Note that octal values of 100 or greater that are specified using this - syntax must not be introduced by a leading zero, because no more than + Note that octal values of 100 or greater that are specified using this + syntax must not be introduced by a leading zero, because no more than three octal digits are ever read. - By default, after \x that is not followed by {, from zero to two hexa- - decimal digits are read (letters can be in upper or lower case). Any + By default, after \x that is not followed by {, from zero to two hexa- + decimal digits are read (letters can be in upper or lower case). Any number of hexadecimal digits may appear between \x{ and }. If a charac- - ter other than a hexadecimal digit appears between \x{ and }, or if + ter other than a hexadecimal digit appears between \x{ and }, or if there is no terminating }, an error occurs. - If the PCRE_JAVASCRIPT_COMPAT option is set, the interpretation of \x - is as just described only when it is followed by two hexadecimal dig- - its. Otherwise, it matches a literal "x" character. In JavaScript + If the PCRE_JAVASCRIPT_COMPAT option is set, the interpretation of \x + is as just described only when it is followed by two hexadecimal dig- + its. Otherwise, it matches a literal "x" character. In JavaScript mode, support for code points greater than 256 is provided by \u, which - must be followed by four hexadecimal digits; otherwise it matches a + must be followed by four hexadecimal digits; otherwise it matches a literal "u" character. Characters whose value is less than 256 can be defined by either of the - two syntaxes for \x (or by \u in JavaScript mode). There is no differ- + two syntaxes for \x (or by \u in JavaScript mode). There is no differ- ence in the way they are handled. For example, \xdc is exactly the same as \x{dc} (or \u00dc in JavaScript mode). Constraints on character values - Characters that are specified using octal or hexadecimal numbers are + Characters that are specified using octal or hexadecimal numbers are limited to certain values, as follows: 8-bit non-UTF mode less than 0x100 @@ -5128,44 +5129,44 @@ BACKSLASH 32-bit non-UTF mode less than 0x100000000 32-bit UTF-32 mode less than 0x10ffff and a valid codepoint - Invalid Unicode codepoints are the range 0xd800 to 0xdfff (the so- + Invalid Unicode codepoints are the range 0xd800 to 0xdfff (the so- called "surrogate" codepoints), and 0xffef. Escape sequences in character classes All the sequences that define a single character value can be used both - inside and outside character classes. In addition, inside a character + inside and outside character classes. In addition, inside a character class, \b is interpreted as the backspace character (hex 08). - \N is not allowed in a character class. \B, \R, and \X are not special - inside a character class. Like other unrecognized escape sequences, - they are treated as the literal characters "B", "R", and "X" by - default, but cause an error if the PCRE_EXTRA option is set. Outside a + \N is not allowed in a character class. \B, \R, and \X are not special + inside a character class. Like other unrecognized escape sequences, + they are treated as the literal characters "B", "R", and "X" by + default, but cause an error if the PCRE_EXTRA option is set. Outside a character class, these sequences have different meanings. Unsupported escape sequences - In Perl, the sequences \l, \L, \u, and \U are recognized by its string - handler and used to modify the case of following characters. By - default, PCRE does not support these escape sequences. However, if the - PCRE_JAVASCRIPT_COMPAT option is set, \U matches a "U" character, and + In Perl, the sequences \l, \L, \u, and \U are recognized by its string + handler and used to modify the case of following characters. By + default, PCRE does not support these escape sequences. However, if the + PCRE_JAVASCRIPT_COMPAT option is set, \U matches a "U" character, and \u can be used to define a character by code point, as described in the previous section. 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 + 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 + 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 + 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 @@ -5184,59 +5185,59 @@ BACKSLASH \W any "non-word" character There is also the single sequence \N, which matches a non-newline char- - acter. This is the same as the "." metacharacter when PCRE_DOTALL is - not set. Perl also uses \N to match characters by name; PCRE does not + acter. This is the same as the "." metacharacter when PCRE_DOTALL is + not set. Perl also uses \N to match characters by name; PCRE does not support this. - Each pair of lower and upper case escape sequences partitions the com- - plete set of characters into two disjoint sets. Any given character - matches one, and only one, of each pair. The 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, because there is no character to + Each pair of lower and upper case escape sequences partitions the com- + plete set of characters into two disjoint sets. Any given character + matches one, and only one, of each pair. The 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, because there is no character to match. - For compatibility with Perl, \s did not used to match the VT character - (code 11), which made it different from the the POSIX "space" class. - However, Perl added VT at release 5.18, and PCRE followed suit at - release 8.34. The default \s characters are now HT (9), LF (10), VT - (11), FF (12), CR (13), and space (32), which are defined as white + For compatibility with Perl, \s did not used to match the VT character + (code 11), which made it different from the the POSIX "space" class. + However, Perl added VT at release 5.18, and PCRE followed suit at + release 8.34. The default \s characters are now HT (9), LF (10), VT + (11), FF (12), CR (13), and space (32), which are defined as white space in the "C" locale. This list may vary if locale-specific matching - is taking place. For example, in some locales the "non-breaking space" - character (\xA0) is recognized as white space, and in others the VT + is taking place. For example, in some locales the "non-breaking space" + character (\xA0) is recognized as white space, and in others the VT character is not. - A "word" character is an underscore or any character that is a letter - or digit. By default, 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 127 - are used for accented letters, and these are then matched by \w. The + A "word" character is an underscore or any character that is a letter + or digit. By default, 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 127 + are used for accented letters, and these are then matched by \w. The use of locales with Unicode is discouraged. - By default, characters whose code points are greater than 127 never + By default, characters whose code points are greater than 127 never match \d, \s, or \w, and always match \D, \S, and \W, although this may - vary for characters in the range 128-255 when locale-specific matching - is happening. These escape sequences retain their original meanings - from before Unicode support was available, mainly for efficiency rea- - sons. If PCRE is compiled with Unicode property support, and the - PCRE_UCP option is set, the behaviour is changed so that Unicode prop- + vary for characters in the range 128-255 when locale-specific matching + is happening. These escape sequences retain their original meanings + from before Unicode support was available, mainly for efficiency rea- + sons. If PCRE is compiled with Unicode property support, and the + PCRE_UCP option is set, the behaviour is changed so that Unicode prop- erties are used to determine character types, as follows: \d any character that matches \p{Nd} (decimal digit) \s any character that matches \p{Z} or \h or \v \w any character that matches \p{L} or \p{N}, plus underscore - The upper case escapes match the inverse sets of characters. Note that - \d matches only decimal digits, whereas \w matches any Unicode digit, - as well as any Unicode letter, and underscore. Note also that PCRE_UCP - affects \b, and \B because they are defined in terms of \w and \W. + The upper case escapes match the inverse sets of characters. Note that + \d matches only decimal digits, whereas \w matches any Unicode digit, + as well as any Unicode letter, and underscore. Note also that PCRE_UCP + affects \b, and \B because they are defined in terms of \w and \W. Matching these sequences is noticeably slower when PCRE_UCP is set. - The sequences \h, \H, \v, and \V are features that were added to Perl - at release 5.10. In contrast to the other sequences, which match only - ASCII characters by default, these always match certain high-valued + The sequences \h, \H, \v, and \V are features that were added to Perl + at release 5.10. In contrast to the other sequences, which match only + ASCII characters by default, these always match certain high-valued code points, whether or not PCRE_UCP is set. The horizontal space char- acters are: @@ -5275,110 +5276,110 @@ BACKSLASH Newline sequences - Outside a character class, by default, the escape sequence \R matches - any Unicode newline sequence. In 8-bit non-UTF-8 mode \R is equivalent + Outside a character class, by default, the escape sequence \R matches + any Unicode newline sequence. In 8-bit 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 + 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 (form feed, U+000C), CR (car- - riage return, U+000D), or NEL (next line, U+0085). The two-character + CR followed by LF, or one of the single characters LF (linefeed, + U+000A), VT (vertical tab, U+000B), FF (form feed, U+000C), CR (car- + riage return, U+000D), or NEL (next line, U+0085). The two-character sequence is treated as a single unit that cannot be split. - In other modes, two additional characters whose codepoints are greater + In other modes, 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 + 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 + 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 + 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 the compiling func- - tion, but they can themselves be overridden by options given to a - matching function. 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 + tion, but they can themselves be overridden by options given to a + matching function. 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) - They can also be combined with the (*UTF8), (*UTF16), (*UTF32), (*UTF) + They can also be combined with the (*UTF8), (*UTF16), (*UTF32), (*UTF) or (*UCP) special sequences. Inside a character class, \R is treated as - an unrecognized escape sequence, and so matches the letter "R" by + an unrecognized escape sequence, and so matches the letter "R" by default, but causes an error if PCRE_EXTRA is set. 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 in 8-bit non-UTF-8 mode, these sequences are of - course limited to testing characters whose codepoints are less than + tional escape sequences that match characters with specific properties + are available. When in 8-bit non-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 a Unicode extended grapheme cluster - The property names represented by xx above are limited to the Unicode + The property names represented by xx above are limited to the Unicode script names, the general category properties, "Any", which matches any - character (including newline), and some special PCRE properties - (described in the next section). Other Perl properties such as "InMu- - sicalSymbols" are not currently supported by PCRE. Note that \P{Any} + character (including newline), and some special PCRE properties + (described in the next section). Other Perl properties such as "InMu- + sicalSymbols" 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. + 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 + Those that are not part of an identified script are lumped together as "Common". The current list of scripts is: - Arabic, Armenian, Avestan, Balinese, Bamum, Bassa_Vah, Batak, Bengali, - Bopomofo, Brahmi, Braille, Buginese, Buhid, Canadian_Aboriginal, Car- + Arabic, Armenian, Avestan, Balinese, Bamum, Bassa_Vah, Batak, Bengali, + Bopomofo, Brahmi, Braille, Buginese, Buhid, Canadian_Aboriginal, Car- ian, Caucasian_Albanian, Chakma, Cham, Cherokee, Common, Coptic, Cunei- form, Cypriot, Cyrillic, Deseret, Devanagari, Duployan, Egyptian_Hiero- glyphs, Elbasan, Ethiopic, Georgian, Glagolitic, Gothic, Grantha, - Greek, Gujarati, Gurmukhi, Han, Hangul, Hanunoo, Hebrew, Hiragana, - Imperial_Aramaic, Inherited, Inscriptional_Pahlavi, Inscrip- - tional_Parthian, Javanese, Kaithi, Kannada, Katakana, Kayah_Li, - Kharoshthi, Khmer, Khojki, Khudawadi, Lao, Latin, Lepcha, Limbu, Lin- - ear_A, Linear_B, Lisu, Lycian, Lydian, Mahajani, Malayalam, Mandaic, - Manichaean, Meetei_Mayek, Mende_Kikakui, Meroitic_Cursive, - Meroitic_Hieroglyphs, Miao, Modi, Mongolian, Mro, Myanmar, Nabataean, - New_Tai_Lue, Nko, Ogham, Ol_Chiki, Old_Italic, Old_North_Arabian, + Greek, Gujarati, Gurmukhi, Han, Hangul, Hanunoo, Hebrew, Hiragana, + Imperial_Aramaic, Inherited, Inscriptional_Pahlavi, Inscrip- + tional_Parthian, Javanese, Kaithi, Kannada, Katakana, Kayah_Li, + Kharoshthi, Khmer, Khojki, Khudawadi, Lao, Latin, Lepcha, Limbu, Lin- + ear_A, Linear_B, Lisu, Lycian, Lydian, Mahajani, Malayalam, Mandaic, + Manichaean, Meetei_Mayek, Mende_Kikakui, Meroitic_Cursive, + Meroitic_Hieroglyphs, Miao, Modi, Mongolian, Mro, Myanmar, Nabataean, + New_Tai_Lue, Nko, Ogham, Ol_Chiki, Old_Italic, Old_North_Arabian, Old_Permic, Old_Persian, Old_South_Arabian, Old_Turkic, Oriya, Osmanya, Pahawh_Hmong, Palmyrene, Pau_Cin_Hau, Phags_Pa, Phoenician, - Psalter_Pahlavi, Rejang, Runic, Samaritan, Saurashtra, Sharada, Sha- - vian, Siddham, Sinhala, Sora_Sompeng, Sundanese, Syloti_Nagri, Syriac, - Tagalog, Tagbanwa, Tai_Le, Tai_Tham, Tai_Viet, Takri, Tamil, Telugu, - Thaana, Thai, Tibetan, Tifinagh, Tirhuta, Ugaritic, Vai, Warang_Citi, + Psalter_Pahlavi, Rejang, Runic, Samaritan, Saurashtra, Sharada, Sha- + vian, Siddham, Sinhala, Sora_Sompeng, Sundanese, Syloti_Nagri, Syriac, + Tagalog, Tagbanwa, Tai_Le, Tai_Tham, Tai_Viet, Takri, Tamil, Telugu, + Thaana, Thai, Tibetan, Tifinagh, Tirhuta, Ugaritic, Vai, Warang_Citi, Yi. Each character has exactly one Unicode general category property, spec- - ified by a two-letter abbreviation. For compatibility with Perl, nega- - tion can be specified by including a circumflex between the opening - brace and the property name. For example, \p{^Lu} is the same as + ified by a two-letter abbreviation. For compatibility with Perl, nega- + tion 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 + 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} @@ -5430,73 +5431,73 @@ BACKSLASH 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 + 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 Unicode strings and - so cannot be tested by PCRE, unless UTF validity checking has been + The Cs (Surrogate) property applies only to characters in the range + U+D800 to U+DFFF. Such characters are not valid in Unicode strings and + so cannot be tested by PCRE, unless UTF validity checking has been turned off (see the discussion of PCRE_NO_UTF8_CHECK, - PCRE_NO_UTF16_CHECK and PCRE_NO_UTF32_CHECK in the pcreapi page). Perl + PCRE_NO_UTF16_CHECK and PCRE_NO_UTF32_CHECK in the pcreapi page). Perl does not support the Cs property. - The long synonyms for property names that Perl supports (such as - \p{Letter}) are not supported by PCRE, nor is it permitted to prefix + The long synonyms for property names 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. This is + Specifying caseless matching does not affect these escape sequences. + For example, \p{Lu} always matches only upper case letters. This is different from the behaviour of current versions of Perl. - Matching characters by Unicode property is not fast, because PCRE has - to do a multistage table lookup in order to find a character's prop- + Matching characters by Unicode property is not fast, because PCRE has + to do a multistage table lookup in order to find a character's prop- erty. That is why the traditional escape sequences such as \d and \w do not use Unicode properties in PCRE by default, though you can make them - do so by setting the PCRE_UCP option or by starting the pattern with + do so by setting the PCRE_UCP option or by starting the pattern with (*UCP). Extended grapheme clusters - The \X escape matches any number of Unicode characters that form an + The \X escape matches any number of Unicode characters that form an "extended grapheme cluster", and treats the sequence as an atomic group - (see below). Up to and including release 8.31, PCRE matched an ear- + (see below). Up to and including release 8.31, PCRE matched an ear- lier, simpler definition that was equivalent to (?>\PM\pM*) - That is, it matched a character without the "mark" property, followed - by zero or more characters with the "mark" property. Characters with - the "mark" property are typically non-spacing accents that affect the + That is, it matched a character without the "mark" property, followed + by zero or more characters with the "mark" property. Characters with + the "mark" property are typically non-spacing accents that affect the preceding character. - This simple definition was extended in Unicode to include more compli- - cated kinds of composite character by giving each character a grapheme - breaking property, and creating rules that use these properties to - define the boundaries of extended grapheme clusters. In releases of + This simple definition was extended in Unicode to include more compli- + cated kinds of composite character by giving each character a grapheme + breaking property, and creating rules that use these properties to + define the boundaries of extended grapheme clusters. In releases of PCRE later than 8.31, \X matches one of these clusters. - \X always matches at least one character. Then it decides whether to + \X always matches at least one character. Then it decides whether to add additional characters according to the following rules for ending a cluster: 1. End at the end of the subject string. - 2. Do not end between CR and LF; otherwise end after any control char- + 2. Do not end between CR and LF; otherwise end after any control char- acter. - 3. Do not break Hangul (a Korean script) syllable sequences. Hangul - characters are of five types: L, V, T, LV, and LVT. An L character may - be followed by an L, V, LV, or LVT character; an LV or V character may + 3. Do not break Hangul (a Korean script) syllable sequences. Hangul + characters are of five types: L, V, T, LV, and LVT. An L character may + be followed by an L, V, LV, or LVT character; an LV or V character may be followed by a V or T character; an LVT or T character may be follwed only by a T character. - 4. Do not end before extending characters or spacing marks. Characters - with the "mark" property always have the "extend" grapheme breaking + 4. Do not end before extending characters or spacing marks. Characters + with the "mark" property always have the "extend" grapheme breaking property. 5. Do not end after prepend characters. @@ -5505,9 +5506,9 @@ BACKSLASH PCRE's additional properties - As well as the standard Unicode properties described above, PCRE sup- - ports four more that make it possible to convert traditional escape - sequences such as \w and \s to use Unicode properties. PCRE uses these + As well as the standard Unicode properties described above, PCRE sup- + ports four more that make it possible to convert traditional escape + sequences such as \w and \s to use Unicode properties. PCRE uses these non-standard, non-Perl properties internally when PCRE_UCP is set. How- ever, they may also be used explicitly. These properties are: @@ -5516,54 +5517,54 @@ BACKSLASH Xsp Any Perl space character Xwd Any Perl "word" character - Xan matches characters that have either the L (letter) or the N (num- - ber) property. Xps matches the characters tab, linefeed, vertical tab, - form feed, or carriage return, and any other character that has the Z - (separator) property. Xsp is the same as Xps; it used to exclude ver- - tical tab, for Perl compatibility, but Perl changed, and so PCRE fol- - lowed at release 8.34. Xwd matches the same characters as Xan, plus + Xan matches characters that have either the L (letter) or the N (num- + ber) property. Xps matches the characters tab, linefeed, vertical tab, + form feed, or carriage return, and any other character that has the Z + (separator) property. Xsp is the same as Xps; it used to exclude ver- + tical tab, for Perl compatibility, but Perl changed, and so PCRE fol- + lowed at release 8.34. Xwd matches the same characters as Xan, plus underscore. - There is another non-standard property, Xuc, which matches any charac- - ter that can be represented by a Universal Character Name in C++ and - other programming languages. These are the characters $, @, ` (grave - accent), and all characters with Unicode code points greater than or - equal to U+00A0, except for the surrogates U+D800 to U+DFFF. Note that - most base (ASCII) characters are excluded. (Universal Character Names - are of the form \uHHHH or \UHHHHHHHH where H is a hexadecimal digit. + There is another non-standard property, Xuc, which matches any charac- + ter that can be represented by a Universal Character Name in C++ and + other programming languages. These are the characters $, @, ` (grave + accent), and all characters with Unicode code points greater than or + equal to U+00A0, except for the surrogates U+D800 to U+DFFF. Note that + most base (ASCII) characters are excluded. (Universal Character Names + are of the form \uHHHH or \UHHHHHHHH where H is a hexadecimal digit. Note that the Xuc property does not match these sequences but the char- acters that they represent.) Resetting the match start - The escape sequence \K causes any previously matched characters not to + The escape sequence \K 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, + 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". - Perl documents that the use of \K within assertions is "not well - defined". In PCRE, \K is acted upon when it occurs inside positive - assertions, but is ignored in negative assertions. Note that when a - pattern such as (?=ab\K) matches, the reported start of the match can + Perl documents that the use of \K within assertions is "not well + defined". In PCRE, \K is acted upon when it occurs inside positive + assertions, but is ignored in negative assertions. Note that when a + pattern such as (?=ab\K) matches, the reported start of the match can be greater than the end of the match. 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 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 @@ -5574,161 +5575,161 @@ BACKSLASH \z matches only at the end of the subject \G matches at the first matching position in the subject - Inside a character class, \b has a different meaning; it matches the - backspace character. If any other of these assertions appears in a - character class, by default it matches the corresponding literal char- + Inside a character class, \b has a different meaning; it matches the + backspace character. If any other of these assertions appears in a + character class, by default it matches the corresponding literal char- acter (for example, \B matches the letter B). However, if the - PCRE_EXTRA option is set, an "invalid escape sequence" error is gener- + PCRE_EXTRA option is set, an "invalid escape sequence" error is gener- ated instead. - 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. In a - UTF mode, the meanings of \w and \W can be changed by setting the - PCRE_UCP option. When this is done, it also affects \b and \B. Neither - PCRE nor Perl has a separate "start of word" or "end of word" metase- - quence. However, whatever follows \b normally determines which it is. + 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. In a + UTF mode, the meanings of \w and \W can be changed by setting the + PCRE_UCP option. When this is done, it also affects \b and \B. Neither + PCRE nor Perl has a separate "start of word" or "end of word" metase- + quence. However, whatever follows \b normally determines which it is. For example, the fragment \ba matches "a" at the start of a word. - The \A, \Z, and \z assertions differ from the traditional circumflex + 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- + 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- + 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 + 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- + 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 + 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 + 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 + 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 - The circumflex and dollar metacharacters are zero-width assertions. - That is, they test for a particular condition being true without con- + The circumflex and dollar metacharacters are zero-width assertions. + That is, they test for a particular condition being true without con- suming any characters from the subject string. 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 + 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 + 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.) - The 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). Note, however, - that it does not actually match the newline. Dollar need not be the + The 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). Note, however, + that it does not actually match the newline. 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. Dol- + but it should be the last item in any branch in which it appears. Dol- lar 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 + 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 + 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 + 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 + 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) AND \N 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- + ter in the subject string except (by default) a character that signi- fies the end of a line. - 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 + 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 + 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 + 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. - The escape sequence \N behaves like a dot, except that it is not - affected by the PCRE_DOTALL option. In other words, it matches any - character except one that signifies the end of a line. Perl also uses + The escape sequence \N behaves like a dot, except that it is not + affected by the PCRE_DOTALL option. In other words, it matches any + character except one that signifies the end of a line. Perl also uses \N to match characters by name; PCRE does not support this. MATCHING A SINGLE DATA UNIT - Outside a character class, the escape sequence \C matches any one data - unit, whether or not a UTF mode is set. In the 8-bit library, one data - unit is one byte; in the 16-bit library it is a 16-bit unit; in the - 32-bit library it is a 32-bit unit. Unlike a dot, \C always matches - line-ending characters. The feature is provided in Perl in order to + Outside a character class, the escape sequence \C matches any one data + unit, whether or not a UTF mode is set. In the 8-bit library, one data + unit is one byte; in the 16-bit library it is a 16-bit unit; in the + 32-bit library it is a 32-bit unit. Unlike a dot, \C always matches + line-ending characters. The feature is provided in Perl in order to match individual bytes in UTF-8 mode, but it is unclear how it can use- - fully be used. Because \C breaks up characters into individual data - units, matching one unit with \C in a UTF mode means that the rest of + fully be used. Because \C breaks up characters into individual data + units, matching one unit with \C in a UTF mode means that the rest of the string may start with a malformed UTF character. This has undefined results, because PCRE assumes that it is dealing with valid UTF strings - (and by default it checks this at the start of processing unless the - PCRE_NO_UTF8_CHECK, PCRE_NO_UTF16_CHECK or PCRE_NO_UTF32_CHECK option + (and by default it checks this at the start of processing unless the + PCRE_NO_UTF8_CHECK, PCRE_NO_UTF16_CHECK or PCRE_NO_UTF32_CHECK option is used). - PCRE does not allow \C to appear in lookbehind assertions (described - below) in a UTF mode, because this would make it impossible to calcu- + PCRE does not allow \C to appear in lookbehind assertions (described + below) in a UTF mode, because this would make it impossible to calcu- late the length of the lookbehind. In general, the \C escape sequence is best avoided. However, one way of - using it that avoids the problem of malformed UTF characters is to use - a lookahead to check the length of the next character, as in this pat- - tern, which could be used with a UTF-8 string (ignore white space and + using it that avoids the problem of malformed UTF characters is to use + a lookahead to check the length of the next character, as in this pat- + tern, which could be used with a UTF-8 string (ignore white space and line breaks): (?| (?=[\x00-\x7f])(\C) | @@ -5736,11 +5737,11 @@ MATCHING A SINGLE DATA UNIT (?=[\x{800}-\x{ffff}])(\C)(\C)(\C) | (?=[\x{10000}-\x{1fffff}])(\C)(\C)(\C)(\C)) - A group that starts with (?| resets the capturing parentheses numbers - in each alternative (see "Duplicate Subpattern Numbers" below). The - assertions at the start of each branch check the next UTF-8 character - for values whose encoding uses 1, 2, 3, or 4 bytes, respectively. The - character's individual bytes are then captured by the appropriate num- + A group that starts with (?| resets the capturing parentheses numbers + in each alternative (see "Duplicate Subpattern Numbers" below). The + assertions at the start of each branch check the next UTF-8 character + for values whose encoding uses 1, 2, 3, or 4 bytes, respectively. The + character's individual bytes are then captured by the appropriate num- ber of groups. @@ -5750,109 +5751,109 @@ SQUARE BRACKETS AND CHARACTER CLASSES closing square bracket. A closing square bracket on its own is not spe- cial by default. However, if the PCRE_JAVASCRIPT_COMPAT option is set, a lone closing square bracket causes a compile-time error. 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 + 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 a UTF - mode, the character may be more than one data unit long. A matched + A character class matches a single character in the subject. In a UTF + mode, the character may be more than one data unit long. 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 + 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 + 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. + 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 + 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 (UTF-16, UTF-32) mode, characters with values greater than 255 - (0xffff) can be included in a class as a literal string of data units, + (0xffff) can be included in a class as a literal string of data units, 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 a UTF 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 in a UTF mode for characters 128 and above, you must - ensure that PCRE is compiled with Unicode property support as well as + 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 a UTF 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 in a UTF mode for characters 128 and above, you must + ensure that PCRE is compiled with Unicode property support as well as with UTF 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 + 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 + 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, or immediately after a range. For - example, [b-d-z] matches letters in the range b to d, a hyphen charac- + example, [b-d-z] matches letters in the range b to d, a hyphen charac- ter, or z. 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 + 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. - An error is generated if a POSIX character class (see below) or an - escape sequence other than one that defines a single character appears - at a point where a range ending character is expected. For example, + An error is generated if a POSIX character class (see below) or an + escape sequence other than one that defines a single character appears + at a point where a range ending character is expected. For example, [z-\xff] is valid, but [A-\d] and [A-[:digit:]] are not. - Ranges operate in the collating sequence of character values. They can - also be used for characters specified numerically, for example - [\000-\037]. Ranges can include any characters that are valid for the + Ranges operate in the collating sequence of character values. They can + also be used for characters specified numerically, for example + [\000-\037]. Ranges can include any characters that are valid for the current mode. 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 a non-UTF mode, if - character tables for a French locale are in use, [\xc8-\xcb] matches - accented E characters in both cases. In UTF modes, PCRE supports the - concept of case for characters with values greater than 128 only when + to [][\\^_`wxyzabc], matched caselessly, and in a non-UTF mode, if + character tables for a French locale are in use, [\xc8-\xcb] matches + accented E characters in both cases. In UTF modes, PCRE supports the + concept of case for characters with values greater than 128 only when it is compiled with Unicode property support. - The character escape sequences \d, \D, \h, \H, \p, \P, \s, \S, \v, \V, + The character escape sequences \d, \D, \h, \H, \p, \P, \s, \S, \v, \V, \w, and \W may appear in a character class, and add the characters that - they match to the class. For example, [\dABCDEF] matches any hexadeci- - mal digit. In UTF modes, the PCRE_UCP option affects the meanings of - \d, \s, \w and their upper case partners, just as it does when they - appear outside a character class, as described in the section entitled + they match to the class. For example, [\dABCDEF] matches any hexadeci- + mal digit. In UTF modes, the PCRE_UCP option affects the meanings of + \d, \s, \w and their upper case partners, just as it does when they + appear outside a character class, as described in the section entitled "Generic character types" above. The escape sequence \b has a different - meaning inside a character class; it matches the backspace character. - The sequences \B, \N, \R, and \X are not special inside a character - class. Like any other unrecognized escape sequences, they are treated - as the literal characters "B", "N", "R", and "X" by default, but cause + meaning inside a character class; it matches the backspace character. + The sequences \B, \N, \R, and \X are not special inside a character + class. Like any other unrecognized escape sequences, they are treated + as the literal characters "B", "N", "R", and "X" by default, but cause an error if the PCRE_EXTRA option is set. - 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 + 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, whereas [\w] includes underscore. A positive character class should be read as "something OR something OR ..." and a negative class as "NOT something AND NOT something AND NOT ...". - 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, or for a - special compatibility feature - see the next two sections), and the + 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, or for a + special compatibility feature - see the next two sections), and the terminating closing square bracket. However, escaping other non- alphanumeric characters does no harm. @@ -5860,7 +5861,7 @@ SQUARE BRACKETS AND CHARACTER CLASSES POSIX CHARACTER CLASSES Perl supports the POSIX notation for character classes. This uses names - enclosed by [: and :] within the enclosing square brackets. PCRE also + enclosed by [: and :] within the enclosing square brackets. PCRE also supports this notation. For example, [01[:alpha:]%] @@ -5883,28 +5884,28 @@ POSIX CHARACTER CLASSES word "word" characters (same as \w) xdigit hexadecimal digits - The default "space" characters are HT (9), LF (10), VT (11), FF (12), - CR (13), and space (32). If locale-specific matching is taking place, - the list of space characters may be different; there may be fewer or + The default "space" characters are HT (9), LF (10), VT (11), FF (12), + CR (13), and space (32). If locale-specific matching is taking place, + the list of space characters may be different; there may be fewer or more of them. "Space" used to be different to \s, which did not include VT, for Perl compatibility. However, Perl changed at release 5.18, and - PCRE followed at release 8.34. "Space" and \s now match the same set + PCRE followed at release 8.34. "Space" and \s now match the same set of characters. - 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 + 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 + 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. By default, characters with values greater than 128 do not match any of - the POSIX character classes. However, if the PCRE_UCP option is passed - to pcre_compile(), some of the classes are changed so that Unicode - character properties are used. This is achieved by replacing certain + the POSIX character classes. However, if the PCRE_UCP option is passed + to pcre_compile(), some of the classes are changed so that Unicode + character properties are used. This is achieved by replacing certain POSIX classes by other sequences, as follows: [:alnum:] becomes \p{Xan} @@ -5916,10 +5917,10 @@ POSIX CHARACTER CLASSES [:upper:] becomes \p{Lu} [:word:] becomes \p{Xwd} - Negated versions, such as [:^alpha:] use \P instead of \p. Three other + Negated versions, such as [:^alpha:] use \P instead of \p. Three other POSIX classes are handled specially in UCP mode: - [:graph:] This matches characters that have glyphs that mark the page + [:graph:] This matches characters that have glyphs that mark the page when printed. In Unicode property terms, it matches all char- acters with the L, M, N, P, S, or Cf properties, except for: @@ -5928,58 +5929,58 @@ POSIX CHARACTER CLASSES U+2066 - U+2069 Various "isolate"s - [:print:] This matches the same characters as [:graph:] plus space - characters that are not controls, that is, characters with + [:print:] This matches the same characters as [:graph:] plus space + characters that are not controls, that is, characters with the Zs property. [:punct:] This matches all characters that have the Unicode P (punctua- - tion) property, plus those characters whose code points are + tion) property, plus those characters whose code points are less than 128 that have the S (Symbol) property. - The other POSIX classes are unchanged, and match only characters with + The other POSIX classes are unchanged, and match only characters with code points less than 128. COMPATIBILITY FEATURE FOR WORD BOUNDARIES - In the POSIX.2 compliant library that was included in 4.4BSD Unix, the - ugly syntax [[:<:]] and [[:>:]] is used for matching "start of word" + In the POSIX.2 compliant library that was included in 4.4BSD Unix, the + ugly syntax [[:<:]] and [[:>:]] is used for matching "start of word" and "end of word". PCRE treats these items as follows: [[:<:]] is converted to \b(?=\w) [[:>:]] is converted to \b(?<=\w) Only these exact character sequences are recognized. A sequence such as - [a[:<:]b] provokes error for an unrecognized POSIX class name. This - support is not compatible with Perl. It is provided to help migrations + [a[:<:]b] provokes error for an unrecognized POSIX class name. This + support is not compatible with Perl. It is provided to help migrations from other environments, and is best not used in any new patterns. Note - that \b matches at the start and the end of a word (see "Simple asser- - tions" above), and in a Perl-style pattern the preceding or following - character normally shows which is wanted, without the need for the - assertions that are used above in order to give exactly the POSIX be- + that \b matches at the start and the end of a word (see "Simple asser- + tions" above), and in a Perl-style pattern the preceding or following + character normally shows which is wanted, without the need for the + assertions that are used above in order to give exactly the POSIX be- haviour. VERTICAL BAR - Vertical bar characters are used to separate alternative patterns. For + 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 + 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 + 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 + 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 @@ -5989,51 +5990,47 @@ INTERNAL OPTION SETTING 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 + 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 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 subpattern that follows it, - so + 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. An option change within a subpattern (see + below for a description of subpatterns) affects only that part of the + subpattern 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 + 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 + 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 compiling or matching 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 are also the (*UTF8), (*UTF16),(*UTF32), and - (*UCP) leading sequences that can be used to set UTF and Unicode prop- - erty modes; they are equivalent to setting the PCRE_UTF8, PCRE_UTF16, - PCRE_UTF32 and the PCRE_UCP options, respectively. The (*UTF) sequence - is a generic version that can be used with any of the libraries. How- - ever, the application can set the PCRE_NEVER_UTF option, which locks + Note: There are other PCRE-specific options that can be set by the + application when the compiling or matching 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 are also the (*UTF8), (*UTF16),(*UTF32), and + (*UCP) leading sequences that can be used to set UTF and Unicode prop- + erty modes; they are equivalent to setting the PCRE_UTF8, PCRE_UTF16, + PCRE_UTF32 and the PCRE_UCP options, respectively. The (*UTF) sequence + is a generic version that can be used with any of the libraries. How- + ever, the application can set the PCRE_NEVER_UTF option, which locks out the use of the (*UTF) sequences. @@ -6046,18 +6043,18 @@ SUBPATTERNS cat(aract|erpillar|) - matches "cataract", "caterpillar", or "cat". Without the parentheses, + matches "cataract", "caterpillar", or "cat". 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 + 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 the matching function. (This applies only to the - traditional matching functions; the DFA matching functions do not sup- + ovector argument of the matching function. (This applies only to the + traditional matching functions; the DFA matching functions do not sup- port capturing.) Opening parentheses are counted from left to right (starting from 1) to - obtain numbers for the capturing subpatterns. For example, if the + obtain numbers for the capturing subpatterns. For example, if the string "the red king" is matched against the pattern the ((red|white) (king|queen)) @@ -6065,12 +6062,12 @@ SUBPATTERNS 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 + 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)) @@ -6078,37 +6075,37 @@ SUBPATTERNS 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 + 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 + 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, + 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 + 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 parentheses that follow the - subpattern start after the highest number used in any branch. The fol- + theses are numbered as usual, but the number is reset at the start of + each branch. The numbers of any capturing parentheses that follow the + subpattern start after the highest number used in any branch. The fol- lowing example is taken from the Perl documentation. The numbers under- neath show in which buffer the captured content will be stored. @@ -6116,58 +6113,58 @@ DUPLICATE SUBPATTERN NUMBERS / ( a ) (?| x ( y ) z | (p (q) r) | (t) u (v) ) ( z ) /x # 1 2 2 3 2 3 4 - A back reference to a numbered subpattern uses the most recent value - that is set for that number by any subpattern. The following pattern + A back reference to a numbered subpattern uses the most recent value + that is set for that number by any subpattern. The following pattern matches "abcabc" or "defdef": /(?|(abc)|(def))\1/ - In contrast, a subroutine call to a numbered subpattern always refers - to the first one in the pattern with the given number. The following + In contrast, a subroutine call to a numbered subpattern always refers + to the first one in the pattern with the given number. The following pattern matches "abcabc" or "defabc": /(?|(abc)|(def))(?1)/ - If a condition test for a subpattern's having matched refers to a non- - unique number, the test is true if any of the subpatterns of that num- + If a condition test for a subpattern's having matched refers to a non- + unique number, the test is true if any of the subpatterns of that num- ber have matched. - An alternative approach to using this "branch reset" feature is to use + 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- + 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. Perl allows identically numbered subpatterns to have different + 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. Perl allows identically numbered subpatterns to have different names, but PCRE does not. - 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 back - references, recursion, and conditions, can be made by name as well as + 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 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, but - must start with a non-digit. 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 + Names consist of up to 32 alphanumeric characters and underscores, but + must start with a non-digit. 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 + 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. (Duplicate names are also always permitted for subpatterns with - the same number, set up as described in the previous section.) Dupli- - cate names 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 + time. (Duplicate names are also always permitted for subpatterns with + the same number, set up as described in the previous section.) Dupli- + cate names 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: @@ -6177,18 +6174,18 @@ NAMED SUBPATTERNS (?<DN>Thu)(?:rsday)?| (?<DN>Sat)(?:urday)? - There are five capturing substrings, but only one is ever set after a + 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 + 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 back reference to a non-unique named subpattern from - elsewhere in the pattern, the subpatterns to which the name refers are - checked in the order in which they appear in the overall pattern. The + If you make a back reference to a non-unique named subpattern from + elsewhere in the pattern, the subpatterns to which the name refers are + checked in the order in which they appear in the overall pattern. The first one that is set is used for the reference. For example, this pat- tern matches both "foofoo" and "barbar" but not "foobar" or "barfoo": @@ -6196,29 +6193,29 @@ NAMED SUBPATTERNS If you make a subroutine call to a non-unique named subpattern, the one - that corresponds to the first occurrence of the name is used. In the + that corresponds to the first occurrence of the name is used. In the absence of duplicate numbers (see the previous section) this is the one with the lowest number. If you use a named reference in a condition test (see the section about conditions below), either to check whether a subpattern has matched, or - to check for recursion, all subpatterns with the same name are tested. - If the condition is true for any one of them, the overall condition is - true. This is the same behaviour as testing by number. For further - details of the interfaces for handling named subpatterns, see the + to check for recursion, all subpatterns with the same name are tested. + If the condition is true for any one of them, the overall condition is + true. This is the same behaviour as testing by number. For further + details of the interfaces for handling named subpatterns, see the pcreapi documentation. Warning: You cannot use different names to distinguish between two sub- - patterns with the same number because PCRE uses only the numbers when + patterns with the same number because PCRE uses only the numbers when matching. For this reason, an error is given at compile time if differ- - ent names are given to subpatterns with the same number. However, you + ent names are given to subpatterns with the same number. However, you can always give the same name to subpatterns with the same number, even when PCRE_DUPNAMES is not set. REPETITION - Repetition is specified by quantifiers, which can follow any of the + Repetition is specified by quantifiers, which can follow any of the following items: a literal data character @@ -6232,17 +6229,17 @@ REPETITION a parenthesized subpattern (including assertions) a subroutine call to a subpattern (recursive or otherwise) - 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, + 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 "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,} @@ -6251,50 +6248,50 @@ REPETITION \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- + 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 modes, quantifiers apply to characters rather than to individual - data units. Thus, for example, \x{100}{2} matches two characters, each + data units. Thus, for example, \x{100}{2} matches two characters, each of which is represented by a two-byte sequence in a UTF-8 string. Simi- - larly, \X{3} matches three Unicode extended grapheme clusters, each of - which may be several data units long (and they may be of different + larly, \X{3} matches three Unicode extended grapheme clusters, each of + which may be several data units 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 + ful for subpatterns that are referenced as subroutines from elsewhere in the pattern (but see also the section entitled "Defining subpatterns - for use by reference only" below). Items other than subpatterns that + for use by reference only" below). 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- + 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 + 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- + 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 + 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 + appear between /* and */ and within the comment, individual * and / + characters may appear. An attempt to match C comments by applying the pattern /\*.*\*/ @@ -6303,19 +6300,19 @@ REPETITION /* first comment */ not comment /* second comment */ - fails, because it matches the entire string owing to the greediness of + 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 + 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 + 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 @@ -6323,45 +6320,45 @@ REPETITION 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 + 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 + 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 + 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- + 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 are some cases where the optimization cannot be used. + However, there are some cases where the optimization cannot be used. When .* is inside capturing parentheses that are the subject of a back reference 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- + If the subject is "xyz123abc123" the match point is the fourth charac- ter. For this reason, such a pattern is not implicitly anchored. - Another case where implicit anchoring is not applied is when the lead- - ing .* is inside an atomic group. Once again, a match at the start may + Another case where implicit anchoring is not applied is when the lead- + ing .* is inside an atomic group. Once again, a match at the start may fail where a later one succeeds. Consider this pattern: (?>.*?a)b - It matches "ab" in the subject "aab". The use of the backtracking con- + It matches "ab" in the subject "aab". The use of the backtracking con- trol verbs (*PRUNE) and (*SKIP) also disable this optimization. When a capturing subpattern is repeated, the value captured is the sub- @@ -6370,8 +6367,8 @@ REPETITION (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- + 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))+/ @@ -6381,53 +6378,53 @@ REPETITION 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 + 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 + 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 + 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 + 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 + 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 + 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 + 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 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 + 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 @@ -6437,45 +6434,45 @@ ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS (abc|xyz){2,3}+ - Possessive quantifiers are always greedy; the setting of the + 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 + 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 + 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 + 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 + 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 + 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 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 + 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+>)*[!?] @@ -6487,28 +6484,28 @@ 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 + 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- + 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. + 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 + 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. This escape + Another way of avoiding the ambiguity inherent in the use of digits + following a backslash is to use the \g escape sequence. This escape must be followed by an unsigned number or a negative number, optionally enclosed in braces. These examples are all identical: @@ -6516,7 +6513,7 @@ BACK REFERENCES (ring), \g1 (ring), \g{1} - An unsigned number specifies an absolute reference without the ambigu- + 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: @@ -6525,33 +6522,33 @@ BACK REFERENCES The sequence \g{-1} is a reference to the most recently started captur- ing subpattern before \g, that is, is it equivalent to \2 in this exam- - ple. 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 + ple. 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 + 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- + 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 + 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 + 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 + and named references, is also supported. We could rewrite the above example in any of the following ways: (?<p1>(?i)rah)\s+\k<p1> @@ -6559,84 +6556,92 @@ BACK REFERENCES (?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 + 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 + 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 by default. For example, the pattern (a|(bc))\2 - always fails if it starts to match "a" rather than "bc". However, if + always fails if it starts to match "a" rather than "bc". However, if the PCRE_JAVASCRIPT_COMPAT option is set at compile time, a back refer- ence to an unset value matches an empty string. - Because there may be many capturing parentheses in a pattern, all dig- - its following a backslash are taken as part of a potential back refer- - ence 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 white space. Otherwise, the + Because there may be many capturing parentheses in a pattern, all dig- + its following a backslash are taken as part of a potential back refer- + ence 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 white space. Otherwise, the \g{ syntax or an empty comment (see "Comments" below) can be used. Recursive back references - 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- + 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 + 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. - Back references of this type cause the group that they reference to be - treated as an atomic group. Once the whole group has been matched, a - subsequent matching failure cannot cause backtracking into the middle + Back references of this type cause the group that they reference to be + treated as an atomic group. Once the whole group has been matched, a + subsequent matching failure cannot cause backtracking into the middle of the group. 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 + 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 + 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. If such an asser- - tion contains capturing subpatterns within it, these are counted for - the purposes of numbering the capturing subpatterns in the whole pat- - tern. However, substring capturing is carried out only for positive + Assertion subpatterns are not capturing subpatterns. If such an asser- + tion contains capturing subpatterns within it, these are counted for + the purposes of numbering the capturing subpatterns in the whole pat- + tern. However, substring capturing is carried out only for positive assertions. (Perl sometimes, but not always, does do capturing in nega- tive assertions.) - For compatibility with Perl, assertion subpatterns may be repeated; - though it makes no sense to assert the same thing several times, the - side effect of capturing parentheses may occasionally be useful. In + WARNING: If a positive assertion containing one or more capturing sub- + patterns succeeds, but failure to match later in the pattern causes + backtracking over this assertion, the captures within the assertion are + reset only if no higher numbered captures are already set. This is, + unfortunately, a fundamental limitation of the current implementation, + and as PCRE1 is now in maintenance-only status, it is unlikely ever to + change. + + For compatibility with Perl, assertion subpatterns may be repeated; + though it makes no sense to assert the same thing several times, the + side effect of capturing parentheses may occasionally be useful. In practice, there only three cases: - (1) If the quantifier is {0}, the assertion is never obeyed during - matching. However, it may contain internal capturing parenthesized + (1) If the quantifier is {0}, the assertion is never obeyed during + matching. However, it may contain internal capturing parenthesized groups that are called from elsewhere via the subroutine mechanism. - (2) If quantifier is {0,n} where n is greater than zero, it is treated - as if it were {0,1}. At run time, the rest of the pattern match is + (2) If quantifier is {0,n} where n is greater than zero, it is treated + as if it were {0,1}. At run time, the rest of the pattern match is tried with and without the assertion, the order depending on the greed- iness of the quantifier. - (3) If the minimum repetition is greater than zero, the quantifier is - ignored. The assertion is obeyed just once when encountered during + (3) If the minimum repetition is greater than zero, the quantifier is + ignored. The assertion is obeyed just once when encountered during matching. Lookahead assertions @@ -6646,38 +6651,38 @@ ASSERTIONS \w+(?=;) - matches a word followed by a semicolon, but does not include the semi- + 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 + 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 + 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 + 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. The backtracking control verb (*FAIL) or (*F) is a synonym for (?!). Lookbehind assertions - Lookbehind assertions start with (?<= for positive assertions and (?<! + 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 + 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 sev- - eral top-level alternatives, they do not all have to have the same + eral top-level alternatives, they do not all have to have the same fixed length. Thus (?<=bullock|donkey) @@ -6686,62 +6691,62 @@ ASSERTIONS (?<!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. + 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, 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 + is not permitted, because its single top-level branch can match two different lengths, but it is acceptable to PCRE if rewritten to use two top-level branches: (?<=abc|abde) - In some cases, the escape sequence \K (see above) can be used instead + In some cases, the escape sequence \K (see above) can be used instead of a lookbehind assertion to get round the fixed-length restriction. - The implementation of lookbehind assertions is, for each alternative, - to temporarily move the current position back by the fixed length and + 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 cur- rent position, the assertion fails. - In a UTF mode, PCRE does not allow the \C escape (which matches a sin- - gle data unit even in a UTF mode) to appear in lookbehind assertions, - because it makes it impossible to calculate the length of the lookbe- - hind. The \X and \R escapes, which can match different numbers of data + In a UTF mode, PCRE does not allow the \C escape (which matches a sin- + gle data unit even in a UTF mode) to appear in lookbehind assertions, + because it makes it impossible to calculate the length of the lookbe- + hind. The \X and \R escapes, which can match different numbers of data units, are also not permitted. - "Subroutine" calls (see below) such as (?2) or (?&X) are permitted in - lookbehinds, as long as the subpattern matches a fixed-length string. + "Subroutine" calls (see below) such as (?2) or (?&X) are permitted in + lookbehinds, as long as the subpattern matches a fixed-length string. Recursion, however, is not supported. - Possessive quantifiers can be used in conjunction with lookbehind + Possessive quantifiers can be used in conjunction with lookbehind assertions to specify efficient matching of fixed-length strings at the end of subject strings. Consider a simple pattern such as abcd$ - when applied to a long string that does not match. Because matching + 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 + 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 + 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, + 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 + 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 @@ -6750,18 +6755,18 @@ ASSERTIONS (?<=\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 + 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" pre- - ceded by six characters, the first of which are digits and the last - three of which are not "999". For example, it doesn't match "123abc- + ceded by six characters, the first of which are digits and the last + three of which are not "999". For example, it doesn't match "123abc- foo". A pattern to do that is (?<=\d{3}...)(?<!999)foo - This time the first assertion looks at the preceding six characters, + 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". @@ -6769,29 +6774,29 @@ ASSERTIONS (?<=(?<!foo)bar)baz - matches an occurrence of "baz" that is preceded by "bar" which in turn + 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 + 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 con- - ditionally or to choose between two alternative subpatterns, depending - on the result of an assertion, or whether a specific capturing subpat- - tern has already been matched. The two possible forms of conditional + It is possible to cause the matching process to obey a subpattern con- + ditionally or to choose between two alternative subpatterns, depending + on the result of an assertion, or whether a specific capturing subpat- + tern has already been matched. 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 alterna- - tives in the subpattern, a compile-time error occurs. Each of the two + If the condition is satisfied, the yes-pattern is used; otherwise the + no-pattern (if present) is used. If there are more than two alterna- + tives in the subpattern, a compile-time error occurs. Each of the two alternatives may itself contain nested subpatterns of any form, includ- ing conditional subpatterns; the restriction to two alternatives applies only at the level of the condition. This pattern fragment is an @@ -6800,68 +6805,68 @@ CONDITIONAL SUBPATTERNS (?(1) (A|B|C) | (D | (?(2)E|F) | E) ) - There are four kinds of condition: references to subpatterns, refer- + There are four kinds of condition: references to subpatterns, refer- ences 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, + If the text between the parentheses consists of a sequence of digits, the condition is true if a capturing subpattern of that number has pre- - viously matched. If there is more than one capturing subpattern with - the same number (see the earlier section about duplicate subpattern - numbers), the condition is true if any of them have matched. An alter- - native 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. Inside loops it can also make sense + viously matched. If there is more than one capturing subpattern with + the same number (see the earlier section about duplicate subpattern + numbers), the condition is true if any of them have matched. An alter- + native 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. Inside loops it can also make sense to refer to subsequent groups. The next parentheses to be opened can be - referenced as (?(+1), and so on. (The value zero in any of these forms + referenced as (?(+1), and so on. (The value zero in any of these forms is not used; it provokes a compile-time error.) - Consider the following pattern, which contains non-significant white + 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 + The first part matches an optional opening parenthesis, and if that character is present, sets it as the first captured substring. The sec- - ond part matches one or more characters that are not parentheses. The - third part is a conditional subpattern that tests whether or not the - first set of parentheses matched. 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. Other- - wise, since no-pattern is not present, the subpattern matches nothing. - In other words, this pattern matches a sequence of non-parentheses, + ond part matches one or more characters that are not parentheses. The + third part is a conditional subpattern that tests whether or not the + first set of parentheses matched. 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. Other- + wise, 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 + 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 + 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 + 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. Rewriting the above example to use a named subpattern gives this: (?<OPEN> \( )? [^()]+ (?(<OPEN>) \) ) - If the name used in a condition of this kind is a duplicate, the test - is applied to all subpatterns of the same name, and is true if any one + If the name used in a condition of this kind is a duplicate, the test + is applied to all subpatterns of the same name, and is true if any one of them has matched. 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 + 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: @@ -6869,51 +6874,51 @@ CONDITIONAL SUBPATTERNS the condition is true if the most recent recursion is into a subpattern whose number or name is given. This condition does not check the entire - recursion stack. If the name used in a condition of this kind is a + recursion stack. If the name used in a condition of this kind is a duplicate, the test is applied to all subpatterns of the same name, and is true if any one of them is the most recent recursion. - At "top level", all these recursion test conditions are false. The + At "top level", all these recursion test conditions are false. The syntax for recursive patterns is 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 refer- - enced from elsewhere. (The use of subroutines is described below.) For - example, a pattern to match an IPv4 address such as "192.168.23.245" + 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 refer- + enced from elsewhere. (The use of subroutines is described below.) For + example, a pattern to match an IPv4 address such as "192.168.23.245" could be written like this (ignore white space 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, insist- + 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, insist- ing 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 + 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 + 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. @@ -6922,41 +6927,41 @@ COMMENTS There are two ways of including comments in patterns that are processed by PCRE. In both cases, the start of the comment must not be in a char- acter class, nor in the middle of any other sequence of related charac- - ters such as (?: or a subpattern name or number. The characters that + ters such as (?: or a subpattern name or number. The characters that make up a comment play no part in the pattern matching. - The sequence (?# marks the start of a comment that continues up to the - next closing parenthesis. Nested parentheses are not permitted. If the + The sequence (?# marks the start of a comment that continues up to the + next closing parenthesis. Nested parentheses are not permitted. If the PCRE_EXTENDED option is set, an unescaped # character also introduces a - comment, which in this case continues to immediately after the next - newline character or character sequence in the pattern. Which charac- + comment, which in this case continues to immediately after the next + newline character or character sequence in the pattern. Which charac- ters are interpreted as newlines is controlled by the options passed to - a compiling function or by a special sequence at the start of the pat- + a compiling function or by a special sequence at the start of the pat- tern, as described in the section entitled "Newline conventions" above. Note that the end of this type of comment is a literal newline sequence - in the pattern; escape sequences that happen to represent a newline do - not count. For example, consider this pattern when PCRE_EXTENDED is + in the pattern; escape sequences that happen to represent a newline do + not count. For example, consider this pattern when PCRE_EXTENDED is set, and the default newline convention is in force: abc #comment \n still comment - On encountering the # character, pcre_compile() skips along, looking - for a newline in the pattern. The sequence \n is still literal at this - stage, so it does not terminate the comment. Only an actual character + On encountering the # character, pcre_compile() skips along, looking + for a newline in the pattern. The sequence \n is still literal at this + stage, so it does not terminate the comment. Only an actual character with the code value 0x0a (the default newline) does so. 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 + 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 + 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: @@ -6966,201 +6971,201 @@ RECURSIVE PATTERNS 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 subsequently introduced + 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 subsequently 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 subroutine call of the - subpattern of the given number, provided that it occurs inside that - subpattern. (If not, it is a non-recursive subroutine call, which is - described in the next section.) The special item (?R) or (?0) is a + A special item that consists of (? followed by a number greater than + zero and a closing parenthesis is a recursive subroutine call of the + subpattern of the given number, provided that it occurs inside that + subpattern. (If not, it is a non-recursive subroutine call, which is + described in the next section.) The special item (?R) or (?0) is a recursive call of the entire regular expression. - This PCRE pattern solves the nested parentheses problem (assume the + 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- + 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. Note the use of a possessive quantifier to avoid backtracking into sequences of non- parentheses. - If this were part of a larger pattern, you would not want to recurse + 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 + 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. Instead + In a larger pattern, keeping track of parenthesis numbers can be + tricky. This is made easier by the use of relative references. 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 + 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 non-recursive subroutine calls, as described in + 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 non-recursive 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 + 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 + 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 + This particular example pattern that we have been looking at contains nested unlimited repeats, and so the use of a possessive quantifier for matching strings of non-parentheses is important when applying the pat- - tern to strings that do not match. For example, when this pattern is + tern to strings that do not match. For example, when this pattern is applied to (aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa() - it yields "no match" quickly. However, if a possessive quantifier 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, + it yields "no match" quickly. However, if a possessive quantifier 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 of capturing parentheses are those - from the outermost level. If you want to obtain intermediate values, a - callout function can be used (see below and the pcrecallout documenta- + At the end of a match, the values of capturing parentheses are those + from the outermost level. If you want to obtain intermediate values, a + callout function can be used (see below and the pcrecallout documenta- tion). If the pattern above is matched against (ab(cd)ef) - the value for the inner capturing parentheses (numbered 2) is "ef", - which is the last value taken on at the top level. If a capturing sub- - pattern is not matched at the top level, its final captured value is - unset, even if it was (temporarily) set at a deeper level during the + the value for the inner capturing parentheses (numbered 2) is "ef", + which is the last value taken on at the top level. If a capturing sub- + pattern is not matched at the top level, its final captured value is + unset, even if it was (temporarily) set at a deeper level during the matching process. - 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 + 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 brack- - ets, allowing for arbitrary nesting. Only digits are allowed in nested - brackets (that is, when recursing), whereas any characters are permit- + 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. + 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. Differences in recursion processing between PCRE and Perl - Recursion processing in PCRE differs from Perl in two important ways. - In PCRE (like Python, but unlike Perl), a recursive subpattern call is + Recursion processing in PCRE differs from Perl in two important ways. + 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 can be - illustrated by the following pattern, which purports to match a palin- - dromic string that contains an odd number of characters (for example, + alternatives and there is a subsequent matching failure. This can be + illustrated by the following pattern, which purports to match a palin- + dromic string that contains an odd number of characters (for example, "a", "aba", "abcba", "abcdcba"): ^(.|(.)(?1)\2)$ The idea is that it either matches a single character, or two identical - characters surrounding a sub-palindrome. In Perl, this pattern works; - in PCRE it does not if the pattern is longer than three characters. + characters surrounding a sub-palindrome. In Perl, this pattern works; + in PCRE it does not if the pattern is longer than three characters. Consider the subject string "abcba": - At the top level, the first character is matched, but as it is not at + At the top level, the first character is matched, but as it is not at the end of the string, the first alternative fails; the second alterna- tive is taken and the recursion kicks in. The recursive call to subpat- - tern 1 successfully matches the next character ("b"). (Note that the + tern 1 successfully matches the next character ("b"). (Note that the beginning and end of line tests are not part of the recursion). - Back at the top level, the next character ("c") is compared with what - subpattern 2 matched, which was "a". This fails. Because the recursion - is treated as an atomic group, there are now no backtracking points, - and so the entire match fails. (Perl is able, at this point, to re- - enter the recursion and try the second alternative.) However, if the + Back at the top level, the next character ("c") is compared with what + subpattern 2 matched, which was "a". This fails. Because the recursion + is treated as an atomic group, there are now no backtracking points, + and so the entire match fails. (Perl is able, at this point, to re- + enter the recursion and try the second alternative.) However, if the pattern is written with the alternatives in the other order, things are different: ^((.)(?1)\2|.)$ - This time, the recursing alternative is tried first, and continues to - recurse until it runs out of characters, at which point the recursion - fails. But this time we do have another alternative to try at the - higher level. That is the big difference: in the previous case the + This time, the recursing alternative is tried first, and continues to + recurse until it runs out of characters, at which point the recursion + fails. But this time we do have another alternative to try at the + higher level. That is the big difference: in the previous case the remaining alternative is at a deeper recursion level, which PCRE cannot use. - To change the pattern so that it matches all palindromic strings, not - just those with an odd number of characters, it is tempting to change + To change the pattern so that it matches all palindromic strings, not + just those with an odd number of characters, it is tempting to change the pattern to this: ^((.)(?1)\2|.?)$ - Again, this works in Perl, but not in PCRE, and for the same reason. - When a deeper recursion has matched a single character, it cannot be - entered again in order to match an empty string. The solution is to - separate the two cases, and write out the odd and even cases as alter- + Again, this works in Perl, but not in PCRE, and for the same reason. + When a deeper recursion has matched a single character, it cannot be + entered again in order to match an empty string. The solution is to + separate the two cases, and write out the odd and even cases as alter- natives at the higher level: ^(?:((.)(?1)\2|)|((.)(?3)\4|.)) - If you want to match typical palindromic phrases, the pattern has to + If you want to match typical palindromic phrases, the pattern has to ignore all non-word characters, which can be done like this: ^\W*+(?:((.)\W*+(?1)\W*+\2|)|((.)\W*+(?3)\W*+\4|\W*+.\W*+))\W*+$ If run with the PCRE_CASELESS option, this pattern matches phrases such as "A man, a plan, a canal: Panama!" and it works well in both PCRE and - Perl. Note the use of the possessive quantifier *+ to avoid backtrack- - ing into sequences of non-word characters. Without this, PCRE takes a - great deal longer (ten times or more) to match typical phrases, and + Perl. Note the use of the possessive quantifier *+ to avoid backtrack- + ing into sequences of non-word characters. Without this, PCRE takes a + great deal longer (ten times or more) to match typical phrases, and Perl takes so long that you think it has gone into a loop. - WARNING: The palindrome-matching patterns above work only if the sub- - ject string does not start with a palindrome that is shorter than the - entire string. For example, although "abcba" is correctly matched, if - the subject is "ababa", PCRE finds the palindrome "aba" at the start, - then fails at top level because the end of the string does not follow. - Once again, it cannot jump back into the recursion to try other alter- + WARNING: The palindrome-matching patterns above work only if the sub- + ject string does not start with a palindrome that is shorter than the + entire string. For example, although "abcba" is correctly matched, if + the subject is "ababa", PCRE finds the palindrome "aba" at the start, + then fails at top level because the end of the string does not follow. + Once again, it cannot jump back into the recursion to try other alter- natives, so the entire match fails. - The second way in which PCRE and Perl differ in their recursion pro- - cessing is in the handling of captured values. In Perl, when a subpat- - tern is called recursively or as a subpattern (see the next section), - it has no access to any values that were captured outside the recur- - sion, whereas in PCRE these values can be referenced. Consider this + The second way in which PCRE and Perl differ in their recursion pro- + cessing is in the handling of captured values. In Perl, when a subpat- + tern is called recursively or as a subpattern (see the next section), + it has no access to any values that were captured outside the recur- + sion, whereas in PCRE these values can be referenced. Consider this pattern: ^(.)(\1|a(?2)) - In PCRE, this pattern matches "bab". The first capturing parentheses - match "b", then in the second group, when the back reference \1 fails - to match "b", the second alternative matches "a" and then recurses. In - the recursion, \1 does now match "b" and so the whole match succeeds. - In Perl, the pattern fails to match because inside the recursive call + In PCRE, this pattern matches "bab". The first capturing parentheses + match "b", then in the second group, when the back reference \1 fails + to match "b", the second alternative matches "a" and then recurses. In + the recursion, \1 does now match "b" and so the whole match succeeds. + In Perl, the pattern fails to match because inside the recursive call \1 cannot access the externally set value. SUBPATTERNS AS SUBROUTINES - If the syntax for a recursive subpattern call (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 + If the syntax for a recursive subpattern call (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)... @@ -7171,79 +7176,79 @@ SUBPATTERNS AS SUBROUTINES (sens|respons)e and \1ibility - matches "sense and sensibility" and "response and responsibility", but + 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 + 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. - All subroutine calls, whether recursive or not, are always treated as - atomic groups. That is, once a subroutine has matched some of the sub- + All subroutine calls, whether recursive or not, are always treated as + atomic groups. That is, once a subroutine has matched some of the sub- ject string, it is never re-entered, even if it contains untried alter- - natives and there is a subsequent matching failure. Any capturing - parentheses that are set during the subroutine call revert to their + natives and there is a subsequent matching failure. Any capturing + parentheses that are set during the subroutine call revert to their previous values afterwards. - Processing options such as case-independence are fixed when a subpat- - tern is defined, so if it is used as a subroutine, such options cannot + Processing options such as case-independence are fixed when a subpat- + tern is defined, so if it is used as a subroutine, such options 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 + 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 + 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- + 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: (?<pn> \( ( (?>[^()]+) | \g<pn> )* \) ) (sens|respons)e and \g'1'ibility - PCRE supports an extension to Oniguruma: if a number is preceded by a + 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 + 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. + 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 (8-bit library) or pcre[16|32]_callout (16-bit or 32-bit - library). By default, this variable contains NULL, which disables all + an external function by putting its entry point in the global variable + pcre_callout (8-bit library) or pcre[16|32]_callout (16-bit or 32-bit + library). 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 + 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 a compiling function, call- - outs are automatically installed before each item in the pattern. They - are all numbered 255. If there is a conditional group in the pattern + If the PCRE_AUTO_CALLOUT flag is passed to a compiling function, call- + outs are automatically installed before each item in the pattern. They + are all numbered 255. If there is a conditional group in the pattern whose condition is an assertion, an additional callout is inserted just before the condition. An explicit callout may also be set at this posi- tion, as in this example: @@ -7253,120 +7258,120 @@ CALLOUTS Note that this applies only to assertion conditions, not to other types of condition. - During matching, when PCRE reaches a callout point, the external func- - tion 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 the matching function. The callout function + During matching, when PCRE reaches a callout point, the external func- + tion 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 the matching function. The callout function may cause matching to proceed, to backtrack, or to fail altogether. - By default, PCRE implements a number of optimizations at compile time - and matching time, and one side-effect is that sometimes callouts are - skipped. If you need all possible callouts to happen, you need to set - options that disable the relevant optimizations. More details, and a - complete description of the interface to the callout function, are + By default, PCRE implements a number of optimizations at compile time + and matching time, and one side-effect is that sometimes callouts are + skipped. If you need all possible callouts to happen, you need to set + options that disable the relevant optimizations. More details, and a + complete description of the interface to the callout function, are given in the pcrecallout documentation. BACKTRACKING CONTROL - Perl 5.10 introduced a number of "Special Backtracking Control Verbs", - which are still 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 + Perl 5.10 introduced a number of "Special Backtracking Control Verbs", + which are still 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. - The new verbs make use of what was previously invalid syntax: an open- + The new verbs make use of what was previously invalid syntax: an open- ing parenthesis followed by an asterisk. They are generally of the form - (*VERB) or (*VERB:NAME). Some may take either form, possibly behaving - differently depending on whether or not a name is present. A name is + (*VERB) or (*VERB:NAME). Some may take either form, possibly behaving + differently depending on whether or not a name is present. A name is any sequence of characters that does not include a closing parenthesis. The maximum length of name is 255 in the 8-bit library and 65535 in the - 16-bit and 32-bit libraries. If the name is empty, that is, if the - closing parenthesis immediately follows the colon, the effect is as if - the colon were not there. Any number of these verbs may occur in a + 16-bit and 32-bit libraries. If the name is empty, that is, if the + closing parenthesis immediately follows the colon, the effect is as if + the colon were not there. Any number of these verbs may occur in a pattern. - Since these verbs are specifically related to backtracking, most of - them can be used only when the pattern is to be matched using one of - the traditional matching functions, because these use a backtracking - algorithm. With the exception of (*FAIL), which behaves like a failing - negative assertion, the backtracking control verbs cause an error if + Since these verbs are specifically related to backtracking, most of + them can be used only when the pattern is to be matched using one of + the traditional matching functions, because these use a backtracking + algorithm. With the exception of (*FAIL), which behaves like a failing + negative assertion, the backtracking control verbs cause an error if encountered by a DFA matching function. - The behaviour of these verbs in repeated groups, assertions, and in + The behaviour of these verbs in repeated groups, assertions, and in subpatterns called as subroutines (whether or not recursively) is docu- mented below. Optimizations that affect backtracking verbs - PCRE contains some optimizations that are used to speed up matching by + PCRE contains some optimizations that are used to speed up matching by running some checks at the start of each match attempt. For example, it - may know the minimum length of matching subject, or that a particular + may know the minimum length of matching subject, or that a particular character must be present. When one of these optimizations bypasses the - running of a match, any included backtracking verbs will not, of + running of a match, any included backtracking verbs will not, of course, be processed. You can suppress the start-of-match optimizations - by setting the PCRE_NO_START_OPTIMIZE option when calling pcre_com- + by setting the PCRE_NO_START_OPTIMIZE option when calling pcre_com- pile() or pcre_exec(), or by starting the pattern with (*NO_START_OPT). There is more discussion of this option in the section entitled "Option bits for pcre_exec()" in the pcreapi documentation. - Experiments with Perl suggest that it too has similar optimizations, + Experiments with Perl suggest that it too has similar optimizations, sometimes leading to anomalous results. Verbs that act immediately - The following verbs act as soon as they are encountered. They may not + The following verbs act as soon as they are encountered. They may not be followed by a name. (*ACCEPT) - This verb causes the match to end successfully, skipping the remainder - of the pattern. However, when it is inside a subpattern that is called - as a subroutine, only that subpattern is ended successfully. Matching + This verb causes the match to end successfully, skipping the remainder + of the pattern. However, when it is inside a subpattern that is called + as a subroutine, only that subpattern is ended successfully. Matching then continues at the outer level. If (*ACCEPT) in triggered in a posi- - tive assertion, the assertion succeeds; in a negative assertion, the + tive assertion, the assertion succeeds; in a negative assertion, the assertion fails. - If (*ACCEPT) is inside capturing parentheses, the data so far is cap- + If (*ACCEPT) is inside capturing parentheses, the data so far is cap- tured. For example: A((?:A|B(*ACCEPT)|C)D) - This matches "AB", "AAD", or "ACD"; when it matches "AB", "B" is cap- + This matches "AB", "AAD", or "ACD"; when it matches "AB", "B" is cap- tured by the outer parentheses. (*FAIL) or (*F) - This verb causes a matching failure, 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- + This verb causes a matching failure, 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 + A match with the string "aaaa" always fails, but the callout is taken before each backtrack happens (in this example, 10 times). Recording which path was taken - There is one verb whose main purpose is to track how a match was - arrived at, though it also has a secondary use in conjunction with + There is one verb whose main purpose is to track how a match was + arrived at, though it also has a secondary use in conjunction with advancing the match starting point (see (*SKIP) below). (*MARK:NAME) or (*:NAME) - A name is always required with this verb. There may be as many - instances of (*MARK) as you like in a pattern, and their names do not + A name is always required with this verb. There may be as many + instances of (*MARK) as you like in a pattern, and their names do not have to be unique. - When a match succeeds, the name of the last-encountered (*MARK:NAME), - (*PRUNE:NAME), or (*THEN:NAME) on the matching path is passed back to - the caller as described in the section entitled "Extra data for - pcre_exec()" in the pcreapi documentation. Here is an example of - pcretest output, where the /K modifier requests the retrieval and out- + When a match succeeds, the name of the last-encountered (*MARK:NAME), + (*PRUNE:NAME), or (*THEN:NAME) on the matching path is passed back to + the caller as described in the section entitled "Extra data for + pcre_exec()" in the pcreapi documentation. Here is an example of + pcretest output, where the /K modifier requests the retrieval and out- putting of (*MARK) data: re> /X(*MARK:A)Y|X(*MARK:B)Z/K @@ -7378,73 +7383,73 @@ BACKTRACKING CONTROL MK: B The (*MARK) name is tagged with "MK:" in this output, and in this exam- - ple it indicates which of the two alternatives matched. This is a more - efficient way of obtaining this information than putting each alterna- + ple it indicates which of the two alternatives matched. This is a more + efficient way of obtaining this information than putting each alterna- tive in its own capturing parentheses. - If a verb with a name is encountered in a positive assertion that is - true, the name is recorded and passed back if it is the last-encoun- + If a verb with a name is encountered in a positive assertion that is + true, the name is recorded and passed back if it is the last-encoun- tered. This does not happen for negative assertions or failing positive assertions. - After a partial match or a failed match, the last encountered name in + After a partial match or a failed match, the last encountered name in the entire match process is returned. For example: re> /X(*MARK:A)Y|X(*MARK:B)Z/K data> XP No match, mark = B - Note that in this unanchored example the mark is retained from the + Note that in this unanchored example the mark is retained from the match attempt that started at the letter "X" in the subject. Subsequent match attempts starting at "P" and then with an empty string do not get as far as the (*MARK) item, but nevertheless do not reset it. - If you are interested in (*MARK) values after failed matches, you - should probably set the PCRE_NO_START_OPTIMIZE option (see above) to + If you are interested in (*MARK) values after failed matches, you + should probably set the PCRE_NO_START_OPTIMIZE option (see above) to ensure that the match is always attempted. 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, causing - a backtrack to the verb, a failure is forced. That is, backtracking - cannot pass to the left of the verb. However, when one of these verbs + tinues with what follows, but if there is no subsequent match, causing + a backtrack to the verb, a failure is forced. That is, backtracking + cannot pass to the left of the verb. However, when one of these verbs appears inside an atomic group or an assertion that is true, its effect - is confined to that group, because once the group has been matched, - there is never any backtracking into it. In this situation, backtrack- - ing can "jump back" to the left of the entire atomic group or asser- - tion. (Remember also, as stated above, that this localization also + is confined to that group, because once the group has been matched, + there is never any backtracking into it. In this situation, backtrack- + ing can "jump back" to the left of the entire atomic group or asser- + tion. (Remember also, as stated above, that this localization also applies in subroutine calls.) - These verbs differ in exactly what kind of failure occurs when back- - tracking reaches them. The behaviour described below is what happens - when the verb is not in a subroutine or an assertion. Subsequent sec- + These verbs differ in exactly what kind of failure occurs when back- + tracking reaches them. The behaviour described below is what happens + when the verb is not in a subroutine or an assertion. Subsequent sec- tions cover these special cases. (*COMMIT) - This verb, which may not be followed by a name, causes the whole match + This verb, which may not be followed by a name, causes the whole match to fail outright if there is a later matching failure that causes back- - tracking to reach it. Even if the pattern is unanchored, no further + tracking to reach it. Even if the pattern is unanchored, no further attempts to find a match by advancing the starting point take place. If - (*COMMIT) is the only backtracking verb that is encountered, once it + (*COMMIT) is the only backtracking verb that is encountered, once it has been passed pcre_exec() is committed to finding a match at the cur- rent 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 + 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." The name of the - most recently passed (*MARK) in the path is passed back when (*COMMIT) + most recently passed (*MARK) in the path is passed back when (*COMMIT) forces a match failure. - If there is more than one backtracking verb in a pattern, a different - one that follows (*COMMIT) may be triggered first, so merely passing + If there is more than one backtracking verb in a pattern, a different + one that follows (*COMMIT) may be triggered first, so merely passing (*COMMIT) during a match does not always guarantee that a match must be at this starting point. - Note that (*COMMIT) at the start of a pattern is not the same as an - anchor, unless PCRE's start-of-match optimizations are turned off, as + Note that (*COMMIT) at the start of a pattern is not the same as an + anchor, unless PCRE's start-of-match optimizations are turned off, as shown in this output from pcretest: re> /(*COMMIT)abc/ @@ -7455,207 +7460,207 @@ BACKTRACKING CONTROL For this pattern, PCRE knows that any match must start with "a", so the optimization skips along the subject to "a" before applying the pattern - to the first set of data. The match attempt then succeeds. In the sec- - ond set of data, the escape sequence \Y is interpreted by the pcretest - program. It causes the PCRE_NO_START_OPTIMIZE option to be set when + to the first set of data. The match attempt then succeeds. In the sec- + ond set of data, the escape sequence \Y is interpreted by the pcretest + program. It causes the PCRE_NO_START_OPTIMIZE option to be set when pcre_exec() is called. This disables the optimization that skips along to the first character. The pattern is now applied starting at "x", and - so the (*COMMIT) causes the match to fail without trying any other + so the (*COMMIT) causes the match to fail without trying any other starting points. (*PRUNE) or (*PRUNE:NAME) - This verb causes the match to fail at the current starting position in + This verb causes the match to fail at the current starting position in the subject if there is a later matching failure that causes backtrack- - ing to reach it. 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), before it is reached, 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 quan- + ing to reach it. 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), before it is reached, 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 quan- tifier, but there are some uses of (*PRUNE) that cannot be expressed in - any other way. In an anchored pattern (*PRUNE) has the same effect as + any other way. In an anchored pattern (*PRUNE) has the same effect as (*COMMIT). The behaviour of (*PRUNE:NAME) is the not the same as - (*MARK:NAME)(*PRUNE). It is like (*MARK:NAME) in that the name is - remembered for passing back to the caller. However, (*SKIP:NAME) + (*MARK:NAME)(*PRUNE). It is like (*MARK:NAME) in that the name is + remembered for passing back to the caller. However, (*SKIP:NAME) searches only for names set with (*MARK). (*SKIP) - This verb, when given without a name, is like (*PRUNE), except that if - the pattern is unanchored, the "bumpalong" advance is not to the next + This verb, when given without a name, 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 encoun- - tered. (*SKIP) signifies that whatever text was matched leading up to + tered. (*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 + 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 as 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 + tifer does not have the same effect as 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". (*SKIP:NAME) When (*SKIP) has an associated name, its behaviour is modified. When it is triggered, the previous path through the pattern is searched for the - most recent (*MARK) that has the same name. If one is found, the + most recent (*MARK) that has the same name. If one is found, the "bumpalong" advance is to the subject position that corresponds to that (*MARK) instead of to where (*SKIP) was encountered. If no (*MARK) with a matching name is found, the (*SKIP) is ignored. - Note that (*SKIP:NAME) searches only for names set by (*MARK:NAME). It + Note that (*SKIP:NAME) searches only for names set by (*MARK:NAME). It ignores names that are set by (*PRUNE:NAME) or (*THEN:NAME). (*THEN) or (*THEN:NAME) - This verb causes a skip to the next innermost alternative when back- - tracking reaches it. That is, it cancels any further backtracking - within the current alternative. Its name comes from the observation + This verb causes a skip to the next innermost alternative when back- + tracking reaches it. That is, it cancels any further backtracking + within the current alternative. 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 that succeeds and BAR fails, COND3 is tried. If subse- - quently BAZ fails, there are no more alternatives, so there is a back- - track to whatever came before the entire group. If (*THEN) is not + 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 that succeeds and BAR fails, COND3 is tried. If subse- + quently BAZ fails, there are no more alternatives, so there is a back- + track to whatever came before the entire group. If (*THEN) is not inside an alternation, it acts like (*PRUNE). - The behaviour of (*THEN:NAME) is the not the same as - (*MARK:NAME)(*THEN). It is like (*MARK:NAME) in that the name is - remembered for passing back to the caller. However, (*SKIP:NAME) + The behaviour of (*THEN:NAME) is the not the same as + (*MARK:NAME)(*THEN). It is like (*MARK:NAME) in that the name is + remembered for passing back to the caller. However, (*SKIP:NAME) searches only for names set with (*MARK). - A subpattern that does not contain a | character is just a part of the - enclosing alternative; it is not a nested alternation with only one - alternative. The effect of (*THEN) extends beyond such a subpattern to - the enclosing alternative. Consider this pattern, where A, B, etc. are - complex pattern fragments that do not contain any | characters at this + A subpattern that does not contain a | character is just a part of the + enclosing alternative; it is not a nested alternation with only one + alternative. The effect of (*THEN) extends beyond such a subpattern to + the enclosing alternative. Consider this pattern, where A, B, etc. are + complex pattern fragments that do not contain any | characters at this level: A (B(*THEN)C) | D - If A and B are matched, but there is a failure in C, matching does not + If A and B are matched, but there is a failure in C, matching does not backtrack into A; instead it moves to the next alternative, that is, D. - However, if the subpattern containing (*THEN) is given an alternative, + However, if the subpattern containing (*THEN) is given an alternative, it behaves differently: A (B(*THEN)C | (*FAIL)) | D - The effect of (*THEN) is now confined to the inner subpattern. After a + The effect of (*THEN) is now confined to the inner subpattern. After a failure in C, matching moves to (*FAIL), which causes the whole subpat- - tern to fail because there are no more alternatives to try. In this + tern to fail because there are no more alternatives to try. In this case, matching does now backtrack into A. - Note that a conditional subpattern is not considered as having two - alternatives, because only one is ever used. In other words, the | + Note that a conditional subpattern is not considered as having two + alternatives, because only one is ever used. In other words, the | character in a conditional subpattern has a different meaning. Ignoring white space, consider: ^.*? (?(?=a) a | b(*THEN)c ) - If the subject is "ba", this pattern does not match. Because .*? is - ungreedy, it initially matches zero characters. The condition (?=a) - then fails, the character "b" is matched, but "c" is not. At this - point, matching does not backtrack to .*? as might perhaps be expected - from the presence of the | character. The conditional subpattern is + If the subject is "ba", this pattern does not match. Because .*? is + ungreedy, it initially matches zero characters. The condition (?=a) + then fails, the character "b" is matched, but "c" is not. At this + point, matching does not backtrack to .*? as might perhaps be expected + from the presence of the | character. The conditional subpattern is part of the single alternative that comprises the whole pattern, and so - the match fails. (If there was a backtrack into .*?, allowing it to + the match fails. (If there was a backtrack into .*?, allowing it to match "b", the match would succeed.) - The verbs just described provide four different "strengths" of control + The verbs just described provide four different "strengths" of control when subsequent matching fails. (*THEN) is the weakest, carrying on the - match at the next alternative. (*PRUNE) comes next, failing the match - at the current starting position, but allowing an advance to the next - character (for an unanchored pattern). (*SKIP) is similar, except that + match at the next alternative. (*PRUNE) comes next, failing the match + at the current starting position, but allowing an advance to the next + character (for an unanchored pattern). (*SKIP) is similar, except that the advance may be more than one character. (*COMMIT) is the strongest, causing the entire match to fail. More than one backtracking verb - If more than one backtracking verb is present in a pattern, the one - that is backtracked onto first acts. For example, consider this pat- + If more than one backtracking verb is present in a pattern, the one + that is backtracked onto first acts. For example, consider this pat- tern, where A, B, etc. are complex pattern fragments: (A(*COMMIT)B(*THEN)C|ABD) - If A matches but B fails, the backtrack to (*COMMIT) causes the entire + If A matches but B fails, the backtrack to (*COMMIT) causes the entire match to fail. However, if A and B match, but C fails, the backtrack to - (*THEN) causes the next alternative (ABD) to be tried. This behaviour - is consistent, but is not always the same as Perl's. It means that if - two or more backtracking verbs appear in succession, all the the last + (*THEN) causes the next alternative (ABD) to be tried. This behaviour + is consistent, but is not always the same as Perl's. It means that if + two or more backtracking verbs appear in succession, all the the last of them has no effect. Consider this example: ...(*COMMIT)(*PRUNE)... If there is a matching failure to the right, backtracking onto (*PRUNE) - causes it to be triggered, and its action is taken. There can never be + causes it to be triggered, and its action is taken. There can never be a backtrack onto (*COMMIT). Backtracking verbs in repeated groups - PCRE differs from Perl in its handling of backtracking verbs in + PCRE differs from Perl in its handling of backtracking verbs in repeated groups. For example, consider: /(a(*COMMIT)b)+ac/ - If the subject is "abac", Perl matches, but PCRE fails because the + If the subject is "abac", Perl matches, but PCRE fails because the (*COMMIT) in the second repeat of the group acts. Backtracking verbs in assertions - (*FAIL) in an assertion has its normal effect: it forces an immediate + (*FAIL) in an assertion has its normal effect: it forces an immediate backtrack. (*ACCEPT) in a positive assertion causes the assertion to succeed with- - out any further processing. In a negative assertion, (*ACCEPT) causes + out any further processing. In a negative assertion, (*ACCEPT) causes the assertion to fail without any further processing. - The other backtracking verbs are not treated specially if they appear - in a positive assertion. In particular, (*THEN) skips to the next - alternative in the innermost enclosing group that has alternations, + The other backtracking verbs are not treated specially if they appear + in a positive assertion. In particular, (*THEN) skips to the next + alternative in the innermost enclosing group that has alternations, whether or not this is within the assertion. - Negative assertions are, however, different, in order to ensure that - changing a positive assertion into a negative assertion changes its + Negative assertions are, however, different, in order to ensure that + changing a positive assertion into a negative assertion changes its result. Backtracking into (*COMMIT), (*SKIP), or (*PRUNE) causes a neg- ative assertion to be true, without considering any further alternative branches in the assertion. Backtracking into (*THEN) causes it to skip - to the next enclosing alternative within the assertion (the normal be- - haviour), but if the assertion does not have such an alternative, + to the next enclosing alternative within the assertion (the normal be- + haviour), but if the assertion does not have such an alternative, (*THEN) behaves like (*PRUNE). Backtracking verbs in subroutines - These behaviours occur whether or not the subpattern is called recur- + These behaviours occur whether or not the subpattern is called recur- sively. Perl's treatment of subroutines is different in some cases. - (*FAIL) in a subpattern called as a subroutine has its normal effect: + (*FAIL) in a subpattern called as a subroutine has its normal effect: it forces an immediate backtrack. - (*ACCEPT) in a subpattern called as a subroutine causes the subroutine - match to succeed without any further processing. Matching then contin- + (*ACCEPT) in a subpattern called as a subroutine causes the subroutine + match to succeed without any further processing. Matching then contin- ues after the subroutine call. (*COMMIT), (*SKIP), and (*PRUNE) in a subpattern called as a subroutine cause the subroutine match to fail. - (*THEN) skips to the next alternative in the innermost enclosing group - within the subpattern that has alternatives. If there is no such group + (*THEN) skips to the next alternative in the innermost enclosing group + within the subpattern that has alternatives. If there is no such group within the subpattern, (*THEN) causes the subroutine match to fail. SEE ALSO - pcreapi(3), pcrecallout(3), pcrematching(3), pcresyntax(3), pcre(3), + pcreapi(3), pcrecallout(3), pcrematching(3), pcresyntax(3), pcre(3), pcre16(3), pcre32(3). @@ -7668,8 +7673,8 @@ AUTHOR REVISION - Last updated: 14 June 2015 - Copyright (c) 1997-2015 University of Cambridge. + Last updated: 23 October 2016 + Copyright (c) 1997-2016 University of Cambridge. ------------------------------------------------------------------------------ diff --git a/pcre/doc/pcrecompat.3 b/pcre/doc/pcrecompat.3 index 0cc40198235..6156e776f53 100644 --- a/pcre/doc/pcrecompat.3 +++ b/pcre/doc/pcrecompat.3 @@ -113,7 +113,7 @@ the pattern /^(a(b)?)+$/ in Perl leaves $2 unset, but in PCRE it is set to "b". 14. PCRE's handling of duplicate subpattern numbers and duplicate subpattern names is not as general as Perl's. This is a consequence of the fact the PCRE works internally just with numbers, using an external table to translate -between numbers and names. In particular, a pattern such as (?|(?<a>A)|(?<b)B), +between numbers and names. In particular, a pattern such as (?|(?<a>A)|(?<b>B), where the two capturing parentheses have the same number but different names, is not supported, and causes an error at compile time. If it were allowed, it would not be possible to distinguish which parentheses matched, because both diff --git a/pcre/doc/pcrepattern.3 b/pcre/doc/pcrepattern.3 index 3b8c6393d21..97df217fdb2 100644 --- a/pcre/doc/pcrepattern.3 +++ b/pcre/doc/pcrepattern.3 @@ -1,4 +1,4 @@ -.TH PCREPATTERN 3 "14 June 2015" "PCRE 8.38" +.TH PCREPATTERN 3 "23 October 2016" "PCRE 8.40" .SH NAME PCRE - Perl-compatible regular expressions .SH "PCRE REGULAR EXPRESSION DETAILS" @@ -336,22 +336,22 @@ When PCRE is compiled in EBCDIC mode, \ea, \ee, \ef, \en, \er, and \et generate the appropriate EBCDIC code values. The \ec escape is processed as specified for Perl in the \fBperlebcdic\fP document. The only characters that are allowed after \ec are A-Z, a-z, or one of @, [, \e, ], ^, _, or ?. Any -other character provokes a compile-time error. The sequence \e@ encodes -character code 0; the letters (in either case) encode characters 1-26 (hex 01 -to hex 1A); [, \e, ], ^, and _ encode characters 27-31 (hex 1B to hex 1F), and -\e? becomes either 255 (hex FF) or 95 (hex 5F). +other character provokes a compile-time error. The sequence \ec@ encodes +character code 0; after \ec the letters (in either case) encode characters 1-26 +(hex 01 to hex 1A); [, \e, ], ^, and _ encode characters 27-31 (hex 1B to hex +1F), and \ec? becomes either 255 (hex FF) or 95 (hex 5F). .P -Thus, apart from \e?, these escapes generate the same character code values as +Thus, apart from \ec?, these escapes generate the same character code values as they do in an ASCII environment, though the meanings of the values mostly -differ. For example, \eG always generates code value 7, which is BEL in ASCII +differ. For example, \ecG always generates code value 7, which is BEL in ASCII but DEL in EBCDIC. .P -The sequence \e? generates DEL (127, hex 7F) in an ASCII environment, but +The sequence \ec? generates DEL (127, hex 7F) in an ASCII environment, but because 127 is not a control character in EBCDIC, Perl makes it generate the APC character. Unfortunately, there are several variants of EBCDIC. In most of them the APC character has the value 255 (hex FF), but in the one Perl calls POSIX-BC its value is 95 (hex 5F). If certain other characters have POSIX-BC -values, PCRE makes \e? generate 95; otherwise it generates 255. +values, PCRE makes \ec? generate 95; otherwise it generates 255. .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\e015 @@ -1511,12 +1511,8 @@ 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 subpattern that follows it, so +that follows. An option change within a subpattern (see below for a description +of subpatterns) affects only that part of the subpattern that follows it, so .sp (a(?i)b)c .sp @@ -2171,6 +2167,13 @@ numbering the capturing subpatterns in the whole pattern. However, substring capturing is carried out only for positive assertions. (Perl sometimes, but not always, does do capturing in negative assertions.) .P +WARNING: If a positive assertion containing one or more capturing subpatterns +succeeds, but failure to match later in the pattern causes backtracking over +this assertion, the captures within the assertion are reset only if no higher +numbered captures are already set. This is, unfortunately, a fundamental +limitation of the current implementation, and as PCRE1 is now in +maintenance-only status, it is unlikely ever to change. +.P For compatibility with Perl, assertion subpatterns may be repeated; though it makes no sense to assert the same thing several times, the side effect of capturing parentheses may occasionally be useful. In practice, there only three @@ -3296,6 +3299,6 @@ Cambridge CB2 3QH, England. .rs .sp .nf -Last updated: 14 June 2015 -Copyright (c) 1997-2015 University of Cambridge. +Last updated: 23 October 2016 +Copyright (c) 1997-2016 University of Cambridge. .fi diff --git a/pcre/pcre.h.generic b/pcre/pcre.h.generic index 70559700654..206f314b87f 100644 --- a/pcre/pcre.h.generic +++ b/pcre/pcre.h.generic @@ -42,9 +42,9 @@ POSSIBILITY OF SUCH DAMAGE. /* The current PCRE version information. */ #define PCRE_MAJOR 8 -#define PCRE_MINOR 39 +#define PCRE_MINOR 40 #define PCRE_PRERELEASE -#define PCRE_DATE 2016-06-14 +#define PCRE_DATE 2017-01-11 /* 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 diff --git a/pcre/pcre_compile.c b/pcre/pcre_compile.c index 7cd39501230..de92313e2f8 100644 --- a/pcre/pcre_compile.c +++ b/pcre/pcre_compile.c @@ -5579,6 +5579,34 @@ for (;; ptr++) #endif #if defined SUPPORT_UTF || !defined COMPILE_PCRE8 { + /* For non-UCP wide characters, in a non-negative class containing \S or + similar (should_flip_negation is set), all characters greater than 255 + must be in the class. */ + + if ( +#if defined COMPILE_PCRE8 + utf && +#endif + should_flip_negation && !negate_class && (options & PCRE_UCP) == 0) + { + *class_uchardata++ = XCL_RANGE; + if (utf) /* Will always be utf in the 8-bit library */ + { + class_uchardata += PRIV(ord2utf)(0x100, class_uchardata); + class_uchardata += PRIV(ord2utf)(0x10ffff, class_uchardata); + } + else /* Can only happen for the 16-bit & 32-bit libraries */ + { +#if defined COMPILE_PCRE16 + *class_uchardata++ = 0x100; + *class_uchardata++ = 0xffffu; +#elif defined COMPILE_PCRE32 + *class_uchardata++ = 0x100; + *class_uchardata++ = 0xffffffffu; +#endif + } + } + *class_uchardata++ = XCL_END; /* Marks the end of extra data */ *code++ = OP_XCLASS; code += LINK_SIZE; @@ -6923,7 +6951,8 @@ for (;; ptr++) slot = cd->name_table; for (i = 0; i < cd->names_found; i++) { - if (STRNCMP_UC_UC(name, slot+IMM2_SIZE, namelen) == 0) break; + if (STRNCMP_UC_UC(name, slot+IMM2_SIZE, namelen) == 0 && + slot[IMM2_SIZE+namelen] == 0) break; slot += cd->name_entry_size; } @@ -7889,15 +7918,17 @@ for (;; ptr++) } } - /* For a forward assertion, we take the reqchar, 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 firstchar - for an assertion, however because it leads to incorrect effect for patterns - such as /(?=a)a.+/ when the "real" "a" would then become a reqchar instead - of a firstchar. This is overcome by a scan at the end if there's no - firstchar, looking for an asserted first char. */ - - else if (bravalue == OP_ASSERT && subreqcharflags >= 0) + /* For a forward assertion, we take the reqchar, if set, provided that the + group has also set a first char. 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 firstchar for an assertion, however + because it leads to incorrect effect for patterns such as /(?=a)a.+/ when + the "real" "a" would then become a reqchar instead of a firstchar. This is + overcome by a scan at the end if there's no firstchar, looking for an + asserted first char. */ + + else if (bravalue == OP_ASSERT && subreqcharflags >= 0 && + subfirstcharflags >= 0) { reqchar = subreqchar; reqcharflags = subreqcharflags; @@ -8686,8 +8717,8 @@ 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. Also, the appearance of .* -inside atomic brackets or in a pattern that contains *PRUNE or *SKIP does not -count, because once again the assumption no longer holds. +inside atomic brackets or in an assertion, or in a pattern that contains *PRUNE +or *SKIP does not count, because once again the assumption no longer holds. Arguments: code points to start of expression (the bracket) @@ -8696,13 +8727,14 @@ Arguments: the less precise approach cd points to the compile data atomcount atomic group level + inassert TRUE if in an assertion Returns: TRUE or FALSE */ static BOOL is_startline(const pcre_uchar *code, unsigned int bracket_map, - compile_data *cd, int atomcount) + compile_data *cd, int atomcount, BOOL inassert) { do { const pcre_uchar *scode = first_significant_code( @@ -8729,7 +8761,7 @@ do { return FALSE; default: /* Assertion */ - if (!is_startline(scode, bracket_map, cd, atomcount)) return FALSE; + if (!is_startline(scode, bracket_map, cd, atomcount, TRUE)) return FALSE; do scode += GET(scode, 1); while (*scode == OP_ALT); scode += 1 + LINK_SIZE; break; @@ -8743,7 +8775,7 @@ do { if (op == OP_BRA || op == OP_BRAPOS || op == OP_SBRA || op == OP_SBRAPOS) { - if (!is_startline(scode, bracket_map, cd, atomcount)) return FALSE; + if (!is_startline(scode, bracket_map, cd, atomcount, inassert)) return FALSE; } /* Capturing brackets */ @@ -8753,33 +8785,33 @@ do { { int n = GET2(scode, 1+LINK_SIZE); int new_map = bracket_map | ((n < 32)? (1 << n) : 1); - if (!is_startline(scode, new_map, cd, atomcount)) return FALSE; + if (!is_startline(scode, new_map, cd, atomcount, inassert)) return FALSE; } /* Positive forward assertions */ else if (op == OP_ASSERT) { - if (!is_startline(scode, bracket_map, cd, atomcount)) return FALSE; + if (!is_startline(scode, bracket_map, cd, atomcount, TRUE)) return FALSE; } /* Atomic brackets */ else if (op == OP_ONCE || op == OP_ONCE_NC) { - if (!is_startline(scode, bracket_map, cd, atomcount + 1)) return FALSE; + if (!is_startline(scode, bracket_map, cd, atomcount + 1, inassert)) return FALSE; } /* .* means "start at start or after \n" if it isn't in atomic brackets or - brackets that may be referenced, as long as the pattern does not contain - *PRUNE or *SKIP, because these break the feature. Consider, for example, - /.*?a(*PRUNE)b/ with the subject "aab", which matches "ab", i.e. not at the - start of a line. */ + brackets that may be referenced or an assertion, as long as the pattern does + not contain *PRUNE or *SKIP, because these break the feature. Consider, for + example, /.*?a(*PRUNE)b/ with the subject "aab", which matches "ab", i.e. + not at the start of a line. */ else if (op == OP_TYPESTAR || op == OP_TYPEMINSTAR || op == OP_TYPEPOSSTAR) { if (scode[1] != OP_ANY || (bracket_map & cd->backref_map) != 0 || - atomcount > 0 || cd->had_pruneorskip) + atomcount > 0 || cd->had_pruneorskip || inassert) return FALSE; } @@ -9634,7 +9666,7 @@ if ((re->options & PCRE_ANCHORED) == 0) re->flags |= PCRE_FIRSTSET; } - else if (is_startline(codestart, 0, cd, 0)) re->flags |= PCRE_STARTLINE; + else if (is_startline(codestart, 0, cd, 0, FALSE)) re->flags |= PCRE_STARTLINE; } } diff --git a/pcre/pcre_jit_compile.c b/pcre/pcre_jit_compile.c index 4f15a27ac28..46ce6c65d54 100644 --- a/pcre/pcre_jit_compile.c +++ b/pcre/pcre_jit_compile.c @@ -4004,12 +4004,12 @@ sljit_emit_op_custom(compiler, instruction, 4); if (load_twice) { - OP1(SLJIT_MOV, TMP3, 0, TMP2, 0); + OP1(SLJIT_MOV, RETURN_ADDR, 0, TMP2, 0); instruction[3] = 0xc0 | (tmp2_ind << 3) | 1; sljit_emit_op_custom(compiler, instruction, 4); OP2(SLJIT_OR, TMP1, 0, TMP1, 0, TMP2, 0); - OP1(SLJIT_MOV, TMP2, 0, TMP3, 0); + OP1(SLJIT_MOV, TMP2, 0, RETURN_ADDR, 0); } OP2(SLJIT_ASHR, TMP1, 0, TMP1, 0, TMP2, 0); diff --git a/pcre/pcre_jit_test.c b/pcre/pcre_jit_test.c index 9b61ec000fa..034cb52697f 100644 --- a/pcre/pcre_jit_test.c +++ b/pcre/pcre_jit_test.c @@ -687,6 +687,7 @@ static struct regression_test_case regression_test_cases[] = { { PCRE_FIRSTLINE | PCRE_NEWLINE_LF | PCRE_DOTALL, 0 | F_NOMATCH, "ab.", "ab" }, { MUA | PCRE_FIRSTLINE, 1 | F_NOMATCH, "^[a-d0-9]", "\nxx\nd" }, { PCRE_NEWLINE_ANY | PCRE_FIRSTLINE | PCRE_DOTALL, 0, "....a", "012\n0a" }, + { MUA | PCRE_FIRSTLINE, 0, "[aC]", "a" }, /* Recurse. */ { MUA, 0, "(a)(?1)", "aa" }, diff --git a/pcre/pcregrep.c b/pcre/pcregrep.c index cd53c648da2..fd2a67622ba 100644 --- a/pcre/pcregrep.c +++ b/pcre/pcregrep.c @@ -1803,6 +1803,12 @@ while (ptr < endptr) match = FALSE; if (line_buffered) fflush(stdout); rc = 0; /* Had some success */ + + /* If the current match ended past the end of the line (only possible + in multiline mode), we are done with this line. */ + + if ((unsigned int)offsets[1] > linelength) goto END_ONE_MATCH; + startoffset = offsets[1]; /* Restart after the match */ if (startoffset <= oldstartoffset) { diff --git a/pcre/pcretest.c b/pcre/pcretest.c index 78ef5177df7..5b73a918075 100644 --- a/pcre/pcretest.c +++ b/pcre/pcretest.c @@ -1982,6 +1982,7 @@ return(result); static int pchar(pcre_uint32 c, FILE *f) { int n = 0; +char tempbuffer[16]; if (PRINTOK(c)) { if (f != NULL) fprintf(f, "%c", c); @@ -2003,6 +2004,8 @@ if (c < 0x100) } if (f != NULL) n = fprintf(f, "\\x{%02x}", c); + else n = sprintf(tempbuffer, "\\x{%02x}", c); + return n >= 0 ? n : 0; } @@ -5042,7 +5045,7 @@ while (!done) if ((all_use_dfa || use_dfa) && find_match_limit) { - printf("**Match limit not relevant for DFA matching: ignored\n"); + printf("** Match limit not relevant for DFA matching: ignored\n"); find_match_limit = 0; } @@ -5255,10 +5258,17 @@ while (!done) if (do_allcaps) { - if (new_info(re, NULL, PCRE_INFO_CAPTURECOUNT, &count) < 0) - goto SKIP_DATA; - count++; /* Allow for full match */ - if (count * 2 > use_size_offsets) count = use_size_offsets/2; + if (all_use_dfa || use_dfa) + { + fprintf(outfile, "** Show all captures ignored after DFA matching\n"); + } + else + { + if (new_info(re, NULL, PCRE_INFO_CAPTURECOUNT, &count) < 0) + goto SKIP_DATA; + count++; /* Allow for full match */ + if (count * 2 > use_size_offsets) count = use_size_offsets/2; + } } /* Output the captured substrings. Note that, for the matched string, diff --git a/pcre/sljit/sljitConfig.h b/pcre/sljit/sljitConfig.h index 1c8a521aa89..eb9c6089f8e 100644 --- a/pcre/sljit/sljitConfig.h +++ b/pcre/sljit/sljitConfig.h @@ -82,7 +82,7 @@ /* --------------------------------------------------------------------- */ /* If SLJIT_STD_MACROS_DEFINED is not defined, the application should - define SLJIT_MALLOC, SLJIT_FREE, SLJIT_MEMMOVE, and NULL. */ + define SLJIT_MALLOC, SLJIT_FREE, SLJIT_MEMCPY, and NULL. */ #ifndef SLJIT_STD_MACROS_DEFINED /* Disabled by default. */ #define SLJIT_STD_MACROS_DEFINED 0 @@ -90,10 +90,20 @@ /* Executable code allocation: If SLJIT_EXECUTABLE_ALLOCATOR is not defined, the application should - define both SLJIT_MALLOC_EXEC and SLJIT_FREE_EXEC. */ + define SLJIT_MALLOC_EXEC, SLJIT_FREE_EXEC, and SLJIT_ENABLE_EXEC. */ #ifndef SLJIT_EXECUTABLE_ALLOCATOR /* Enabled by default. */ #define SLJIT_EXECUTABLE_ALLOCATOR 1 + +/* When SLJIT_PROT_EXECUTABLE_ALLOCATOR is enabled SLJIT uses + an allocator which does not set writable and executable + permission flags at the same time. The trade-of is increased + memory consumption and disabled dynamic code modifications. */ +#ifndef SLJIT_PROT_EXECUTABLE_ALLOCATOR +/* Disabled by default. */ +#define SLJIT_PROT_EXECUTABLE_ALLOCATOR 0 +#endif + #endif /* Force cdecl calling convention even if a better calling diff --git a/pcre/sljit/sljitConfigInternal.h b/pcre/sljit/sljitConfigInternal.h index 9275b149926..4dc452fb54d 100644 --- a/pcre/sljit/sljitConfigInternal.h +++ b/pcre/sljit/sljitConfigInternal.h @@ -210,8 +210,8 @@ #define SLJIT_FREE(ptr, allocator_data) free(ptr) #endif -#ifndef SLJIT_MEMMOVE -#define SLJIT_MEMMOVE(dest, src, len) memmove(dest, src, len) +#ifndef SLJIT_MEMCPY +#define SLJIT_MEMCPY(dest, src, len) memcpy(dest, src, len) #endif #ifndef SLJIT_ZEROMEM @@ -545,6 +545,14 @@ SLJIT_API_FUNC_ATTRIBUTE void sljit_free_exec(void* ptr); SLJIT_API_FUNC_ATTRIBUTE void sljit_free_unused_memory_exec(void); #define SLJIT_MALLOC_EXEC(size) sljit_malloc_exec(size) #define SLJIT_FREE_EXEC(ptr) sljit_free_exec(ptr) + +#if (defined SLJIT_PROT_EXECUTABLE_ALLOCATOR && SLJIT_PROT_EXECUTABLE_ALLOCATOR) +SLJIT_API_FUNC_ATTRIBUTE void sljit_enable_exec(void* from, void *to); +#define SLJIT_ENABLE_EXEC(from, to) sljit_enable_exec((from), (to)) +#else +#define SLJIT_ENABLE_EXEC(from, to) +#endif + #endif /**********************************************/ diff --git a/pcre/sljit/sljitLir.c b/pcre/sljit/sljitLir.c index ec1781e4c7f..a6ecc010288 100644 --- a/pcre/sljit/sljitLir.c +++ b/pcre/sljit/sljitLir.c @@ -242,9 +242,15 @@ #if !(defined SLJIT_CONFIG_UNSUPPORTED && SLJIT_CONFIG_UNSUPPORTED) #if (defined SLJIT_EXECUTABLE_ALLOCATOR && SLJIT_EXECUTABLE_ALLOCATOR) + +#if (defined SLJIT_PROT_EXECUTABLE_ALLOCATOR && SLJIT_PROT_EXECUTABLE_ALLOCATOR) +#include "sljitProtExecAllocator.c" +#else #include "sljitExecAllocator.c" #endif +#endif + /* Argument checking features. */ #if (defined SLJIT_ARGUMENT_CHECKS && SLJIT_ARGUMENT_CHECKS) @@ -283,6 +289,13 @@ } \ } while (0) +#define CHECK_DYN_CODE_MOD(extra_check) \ + if ((extra_check) && !sljit_is_dyn_code_modification_enabled()) \ + { \ + compiler->error = SLJIT_ERR_DYN_CODE_MOD; \ + return NULL; \ + } + #elif (defined SLJIT_DEBUG && SLJIT_DEBUG) /* Assertion failure occures if an invalid argument is passed. */ @@ -295,6 +308,7 @@ #define CHECK(x) x #define CHECK_PTR(x) x #define CHECK_REG_INDEX(x) x +#define CHECK_DYN_CODE_MOD(extra_check) SLJIT_ASSERT(!(extra_check) || sljit_is_dyn_code_modification_enabled()) #elif (defined SLJIT_VERBOSE && SLJIT_VERBOSE) @@ -304,6 +318,7 @@ #define CHECK(x) x #define CHECK_PTR(x) x #define CHECK_REG_INDEX(x) x +#define CHECK_DYN_CODE_MOD(extra_check) #else @@ -311,6 +326,7 @@ #define CHECK(x) #define CHECK_PTR(x) #define CHECK_REG_INDEX(x) +#define CHECK_DYN_CODE_MOD(extra_check) #endif /* SLJIT_ARGUMENT_CHECKS */ @@ -441,6 +457,15 @@ SLJIT_API_FUNC_ATTRIBUTE void sljit_set_compiler_memory_error(struct sljit_compi compiler->error = SLJIT_ERR_ALLOC_FAILED; } +SLJIT_API_FUNC_ATTRIBUTE sljit_s32 sljit_is_dyn_code_modification_enabled(void) +{ +#if (defined SLJIT_EXECUTABLE_ALLOCATOR && SLJIT_EXECUTABLE_ALLOCATOR) \ + && (defined SLJIT_PROT_EXECUTABLE_ALLOCATOR && SLJIT_PROT_EXECUTABLE_ALLOCATOR) + return 0; +#endif + return 1; +} + #if (defined SLJIT_CONFIG_ARM_THUMB2 && SLJIT_CONFIG_ARM_THUMB2) SLJIT_API_FUNC_ATTRIBUTE void sljit_free_code(void* code) { @@ -1601,6 +1626,7 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_jump* sljit_emit_cmp(struct sljit_compiler sljit_sw tmp_srcw; CHECK_ERROR_PTR(); + CHECK_DYN_CODE_MOD(type & SLJIT_REWRITABLE_JUMP); CHECK_PTR(check_sljit_emit_cmp(compiler, type, src1, src1w, src2, src2w)); condition = type & 0xff; @@ -1681,6 +1707,7 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_jump* sljit_emit_fcmp(struct sljit_compile sljit_s32 flags, condition; CHECK_ERROR_PTR(); + CHECK_DYN_CODE_MOD(type & SLJIT_REWRITABLE_JUMP); CHECK_PTR(check_sljit_emit_fcmp(compiler, type, src1, src1w, src2, src2w)); condition = type & 0xff; diff --git a/pcre/sljit/sljitLir.h b/pcre/sljit/sljitLir.h index df69b8656f8..facddb65de7 100644 --- a/pcre/sljit/sljitLir.h +++ b/pcre/sljit/sljitLir.h @@ -99,6 +99,8 @@ of sljitConfigInternal.h */ #define SLJIT_ERR_UNSUPPORTED 4 /* An ivalid argument is passed to any SLJIT function. */ #define SLJIT_ERR_BAD_ARGUMENT 5 +/* Dynamic code modification is not enabled. */ +#define SLJIT_ERR_DYN_CODE_MOD 6 /* --------------------------------------------------------------------- */ /* Registers */ @@ -455,7 +457,19 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_alloc_memory(struct sljit_compiler *compile SLJIT_API_FUNC_ATTRIBUTE void sljit_compiler_verbose(struct sljit_compiler *compiler, FILE* verbose); #endif +/* Returns with non-zero if dynamic code modification is enabled. */ + +SLJIT_API_FUNC_ATTRIBUTE sljit_s32 sljit_is_dyn_code_modification_enabled(void); + +/* + Create executable code from the sljit instruction stream. This is the final step + of the code generation so no more instructions can be added after this call. +*/ + SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compiler); + +/* Free executable code. */ + SLJIT_API_FUNC_ATTRIBUTE void sljit_free_code(void* code); /* diff --git a/pcre/sljit/sljitNativeARM_32.c b/pcre/sljit/sljitNativeARM_32.c index b92808f5268..a756f82933f 100644 --- a/pcre/sljit/sljitNativeARM_32.c +++ b/pcre/sljit/sljitNativeARM_32.c @@ -793,6 +793,7 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil compiler->error = SLJIT_ERR_COMPILED; compiler->executable_size = (code_ptr - code) * sizeof(sljit_uw); + SLJIT_ENABLE_EXEC(code, code_ptr); SLJIT_CACHE_FLUSH(code, code_ptr); return code; } @@ -2402,6 +2403,7 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_jump* sljit_emit_jump(struct sljit_compile struct sljit_jump *jump; CHECK_ERROR_PTR(); + CHECK_DYN_CODE_MOD(type & SLJIT_REWRITABLE_JUMP); CHECK_PTR(check_sljit_emit_jump(compiler, type)); jump = (struct sljit_jump*)ensure_abuf(compiler, sizeof(struct sljit_jump)); @@ -2534,6 +2536,7 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_const* sljit_emit_const(struct sljit_compi sljit_s32 reg; CHECK_ERROR_PTR(); + CHECK_DYN_CODE_MOD(1); CHECK_PTR(check_sljit_emit_const(compiler, dst, dstw, init_value)); ADJUST_LOCAL_OFFSET(dst, dstw); diff --git a/pcre/sljit/sljitNativeARM_64.c b/pcre/sljit/sljitNativeARM_64.c index d9958512c80..75777a8e691 100644 --- a/pcre/sljit/sljitNativeARM_64.c +++ b/pcre/sljit/sljitNativeARM_64.c @@ -309,6 +309,7 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil compiler->error = SLJIT_ERR_COMPILED; compiler->executable_size = (code_ptr - code) * sizeof(sljit_ins); + SLJIT_ENABLE_EXEC(code, code_ptr); SLJIT_CACHE_FLUSH(code, code_ptr); return code; } @@ -1882,6 +1883,7 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_jump* sljit_emit_jump(struct sljit_compile struct sljit_jump *jump; CHECK_ERROR_PTR(); + CHECK_DYN_CODE_MOD(type & SLJIT_REWRITABLE_JUMP); CHECK_PTR(check_sljit_emit_jump(compiler, type)); jump = (struct sljit_jump*)ensure_abuf(compiler, sizeof(struct sljit_jump)); @@ -2020,6 +2022,7 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_const* sljit_emit_const(struct sljit_compi sljit_s32 dst_r; CHECK_ERROR_PTR(); + CHECK_DYN_CODE_MOD(1); CHECK_PTR(check_sljit_emit_const(compiler, dst, dstw, init_value)); ADJUST_LOCAL_OFFSET(dst, dstw); diff --git a/pcre/sljit/sljitNativeARM_T2_32.c b/pcre/sljit/sljitNativeARM_T2_32.c index 1ed44a81303..2952a3eeea4 100644 --- a/pcre/sljit/sljitNativeARM_T2_32.c +++ b/pcre/sljit/sljitNativeARM_T2_32.c @@ -415,6 +415,7 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil compiler->error = SLJIT_ERR_COMPILED; compiler->executable_size = (code_ptr - code) * sizeof(sljit_u16); + SLJIT_ENABLE_EXEC(code, code_ptr); SLJIT_CACHE_FLUSH(code, code_ptr); /* Set thumb mode flag. */ return (void*)((sljit_uw)code | 0x1); @@ -1917,6 +1918,7 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_jump* sljit_emit_jump(struct sljit_compile sljit_ins cc; CHECK_ERROR_PTR(); + CHECK_DYN_CODE_MOD(type & SLJIT_REWRITABLE_JUMP); CHECK_PTR(check_sljit_emit_jump(compiler, type)); jump = (struct sljit_jump*)ensure_abuf(compiler, sizeof(struct sljit_jump)); @@ -2060,6 +2062,7 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_const* sljit_emit_const(struct sljit_compi sljit_s32 dst_r; CHECK_ERROR_PTR(); + CHECK_DYN_CODE_MOD(1); CHECK_PTR(check_sljit_emit_const(compiler, dst, dstw, init_value)); ADJUST_LOCAL_OFFSET(dst, dstw); diff --git a/pcre/sljit/sljitNativeMIPS_common.c b/pcre/sljit/sljitNativeMIPS_common.c index c2c251b1ff4..3d58bb5ee4c 100644 --- a/pcre/sljit/sljitNativeMIPS_common.c +++ b/pcre/sljit/sljitNativeMIPS_common.c @@ -477,6 +477,7 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil compiler->error = SLJIT_ERR_COMPILED; compiler->executable_size = (code_ptr - code) * sizeof(sljit_ins); + SLJIT_ENABLE_EXEC(code, code_ptr); #ifndef __GNUC__ SLJIT_CACHE_FLUSH(code, code_ptr); #else @@ -1625,6 +1626,7 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_jump* sljit_emit_jump(struct sljit_compile sljit_s32 delay_check = UNMOVABLE_INS; CHECK_ERROR_PTR(); + CHECK_DYN_CODE_MOD(type & SLJIT_REWRITABLE_JUMP); CHECK_PTR(check_sljit_emit_jump(compiler, type)); jump = (struct sljit_jump*)ensure_abuf(compiler, sizeof(struct sljit_jump)); @@ -1742,6 +1744,7 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_jump* sljit_emit_cmp(struct sljit_compiler sljit_ins inst; CHECK_ERROR_PTR(); + CHECK_DYN_CODE_MOD(type & SLJIT_REWRITABLE_JUMP); CHECK_PTR(check_sljit_emit_cmp(compiler, type, src1, src1w, src2, src2w)); ADJUST_LOCAL_OFFSET(src1, src1w); ADJUST_LOCAL_OFFSET(src2, src2w); @@ -1863,6 +1866,7 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_jump* sljit_emit_fcmp(struct sljit_compile sljit_s32 if_true; CHECK_ERROR_PTR(); + CHECK_DYN_CODE_MOD(type & SLJIT_REWRITABLE_JUMP); CHECK_PTR(check_sljit_emit_fcmp(compiler, type, src1, src1w, src2, src2w)); compiler->cache_arg = 0; @@ -2121,6 +2125,7 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_const* sljit_emit_const(struct sljit_compi sljit_s32 reg; CHECK_ERROR_PTR(); + CHECK_DYN_CODE_MOD(1); CHECK_PTR(check_sljit_emit_const(compiler, dst, dstw, init_value)); ADJUST_LOCAL_OFFSET(dst, dstw); diff --git a/pcre/sljit/sljitNativePPC_common.c b/pcre/sljit/sljitNativePPC_common.c index a3647327bfe..8621f525e66 100644 --- a/pcre/sljit/sljitNativePPC_common.c +++ b/pcre/sljit/sljitNativePPC_common.c @@ -493,6 +493,7 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil compiler->error = SLJIT_ERR_COMPILED; compiler->executable_size = (code_ptr - code) * sizeof(sljit_ins); + SLJIT_ENABLE_EXEC(code, code_ptr); SLJIT_CACHE_FLUSH(code, code_ptr); #if (defined SLJIT_INDIRECT_CALL && SLJIT_INDIRECT_CALL) @@ -2138,6 +2139,7 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_jump* sljit_emit_jump(struct sljit_compile sljit_ins bo_bi_flags; CHECK_ERROR_PTR(); + CHECK_DYN_CODE_MOD(type & SLJIT_REWRITABLE_JUMP); CHECK_PTR(check_sljit_emit_jump(compiler, type)); bo_bi_flags = get_bo_bi_flags(type & 0xff); @@ -2362,6 +2364,7 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_const* sljit_emit_const(struct sljit_compi sljit_s32 reg; CHECK_ERROR_PTR(); + CHECK_DYN_CODE_MOD(1); CHECK_PTR(check_sljit_emit_const(compiler, dst, dstw, init_value)); ADJUST_LOCAL_OFFSET(dst, dstw); diff --git a/pcre/sljit/sljitNativeSPARC_common.c b/pcre/sljit/sljitNativeSPARC_common.c index f3a33a1097e..ba77c70d521 100644 --- a/pcre/sljit/sljitNativeSPARC_common.c +++ b/pcre/sljit/sljitNativeSPARC_common.c @@ -379,6 +379,7 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil compiler->error = SLJIT_ERR_COMPILED; compiler->executable_size = (code_ptr - code) * sizeof(sljit_ins); + SLJIT_ENABLE_EXEC(code, code_ptr); SLJIT_CACHE_FLUSH(code, code_ptr); return code; } @@ -1295,6 +1296,7 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_jump* sljit_emit_jump(struct sljit_compile struct sljit_jump *jump; CHECK_ERROR_PTR(); + CHECK_DYN_CODE_MOD(type & SLJIT_REWRITABLE_JUMP); CHECK_PTR(check_sljit_emit_jump(compiler, type)); jump = (struct sljit_jump*)ensure_abuf(compiler, sizeof(struct sljit_jump)); @@ -1422,6 +1424,7 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_const* sljit_emit_const(struct sljit_compi struct sljit_const *const_; CHECK_ERROR_PTR(); + CHECK_DYN_CODE_MOD(1); CHECK_PTR(check_sljit_emit_const(compiler, dst, dstw, init_value)); ADJUST_LOCAL_OFFSET(dst, dstw); diff --git a/pcre/sljit/sljitNativeTILEGX_64.c b/pcre/sljit/sljitNativeTILEGX_64.c index 462a8b9cd95..d92b8582b7e 100644 --- a/pcre/sljit/sljitNativeTILEGX_64.c +++ b/pcre/sljit/sljitNativeTILEGX_64.c @@ -1113,6 +1113,7 @@ SLJIT_API_FUNC_ATTRIBUTE void * sljit_generate_code(struct sljit_compiler *compi compiler->error = SLJIT_ERR_COMPILED; compiler->executable_size = (code_ptr - code) * sizeof(sljit_ins); + SLJIT_ENABLE_EXEC(code, code_ptr); SLJIT_CACHE_FLUSH(code, code_ptr); return code; } @@ -2412,6 +2413,7 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_jump * sljit_emit_jump(struct sljit_compil flush_buffer(compiler); CHECK_ERROR_PTR(); + CHECK_DYN_CODE_MOD(type & SLJIT_REWRITABLE_JUMP); CHECK_PTR(check_sljit_emit_jump(compiler, type)); jump = (struct sljit_jump *)ensure_abuf(compiler, sizeof(struct sljit_jump)); @@ -2510,6 +2512,7 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_const * sljit_emit_const(struct sljit_comp flush_buffer(compiler); CHECK_ERROR_PTR(); + CHECK_DYN_CODE_MOD(1); CHECK_PTR(check_sljit_emit_const(compiler, dst, dstw, init_value)); ADJUST_LOCAL_OFFSET(dst, dstw); diff --git a/pcre/sljit/sljitNativeX86_32.c b/pcre/sljit/sljitNativeX86_32.c index cd3c656c664..78f3dcb06f9 100644 --- a/pcre/sljit/sljitNativeX86_32.c +++ b/pcre/sljit/sljitNativeX86_32.c @@ -34,7 +34,7 @@ static sljit_s32 emit_do_imm(struct sljit_compiler *compiler, sljit_u8 opcode, s FAIL_IF(!inst); INC_SIZE(1 + sizeof(sljit_sw)); *inst++ = opcode; - *(sljit_sw*)inst = imm; + sljit_unaligned_store_sw(inst, imm); return SLJIT_SUCCESS; } @@ -57,7 +57,7 @@ static sljit_u8* generate_far_jump_code(struct sljit_jump *jump, sljit_u8 *code_ if (jump->flags & JUMP_LABEL) jump->flags |= PATCH_MW; else - *(sljit_sw*)code_ptr = jump->u.target - (jump->addr + 4); + sljit_unaligned_store_sw(code_ptr, jump->u.target - (jump->addr + 4)); code_ptr += 4; return code_ptr; @@ -151,12 +151,12 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_s32 sljit_emit_enter(struct sljit_compiler *compi inst[1] = MOD_REG | (reg_map[TMP_REG1] << 3) | reg_map[SLJIT_SP]; inst[2] = GROUP_F7; inst[3] = MOD_REG | (0 << 3) | reg_map[SLJIT_SP]; - *(sljit_sw*)(inst + 4) = 0x4; + sljit_unaligned_store_sw(inst + 4, 0x4); inst[8] = JNE_i8; inst[9] = 6; inst[10] = GROUP_BINARY_81; inst[11] = MOD_REG | (5 << 3) | reg_map[SLJIT_SP]; - *(sljit_sw*)(inst + 12) = 0x4; + sljit_unaligned_store_sw(inst + 12, 0x4); inst[16] = PUSH_r + reg_map[TMP_REG1]; } else @@ -406,7 +406,7 @@ static sljit_u8* emit_x86_instruction(struct sljit_compiler *compiler, sljit_s32 if (immb <= 127 && immb >= -128) *buf_ptr++ = immb; /* 8 bit displacement. */ else { - *(sljit_sw*)buf_ptr = immb; /* 32 bit displacement. */ + sljit_unaligned_store_sw(buf_ptr, immb); /* 32 bit displacement. */ buf_ptr += sizeof(sljit_sw); } } @@ -418,7 +418,7 @@ static sljit_u8* emit_x86_instruction(struct sljit_compiler *compiler, sljit_s32 } else { *buf_ptr++ |= 0x05; - *(sljit_sw*)buf_ptr = immb; /* 32 bit displacement. */ + sljit_unaligned_store_sw(buf_ptr, immb); /* 32 bit displacement. */ buf_ptr += sizeof(sljit_sw); } @@ -426,9 +426,9 @@ static sljit_u8* emit_x86_instruction(struct sljit_compiler *compiler, sljit_s32 if (flags & EX86_BYTE_ARG) *buf_ptr = imma; else if (flags & EX86_HALF_ARG) - *(short*)buf_ptr = imma; + sljit_unaligned_store_s16(buf_ptr, imma); else if (!(flags & EX86_SHIFT_INS)) - *(sljit_sw*)buf_ptr = imma; + sljit_unaligned_store_sw(buf_ptr, imma); } return !(flags & EX86_SHIFT_INS) ? inst : (inst + 1); @@ -541,7 +541,7 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_s32 sljit_emit_fast_return(struct sljit_compiler INC_SIZE(5 + 1); *inst++ = PUSH_i32; - *(sljit_sw*)inst = srcw; + sljit_unaligned_store_sw(inst, srcw); inst += sizeof(sljit_sw); } diff --git a/pcre/sljit/sljitNativeX86_64.c b/pcre/sljit/sljitNativeX86_64.c index 6ea27e55131..e88ddedcd1c 100644 --- a/pcre/sljit/sljitNativeX86_64.c +++ b/pcre/sljit/sljitNativeX86_64.c @@ -35,7 +35,7 @@ static sljit_s32 emit_load_imm64(struct sljit_compiler *compiler, sljit_s32 reg, INC_SIZE(2 + sizeof(sljit_sw)); *inst++ = REX_W | ((reg_map[reg] <= 7) ? 0 : REX_B); *inst++ = MOV_r_i32 + (reg_map[reg] & 0x7); - *(sljit_sw*)inst = imm; + sljit_unaligned_store_sw(inst, imm); return SLJIT_SUCCESS; } @@ -55,7 +55,7 @@ static sljit_u8* generate_far_jump_code(struct sljit_jump *jump, sljit_u8 *code_ if (jump->flags & JUMP_LABEL) jump->flags |= PATCH_MD; else - *(sljit_sw*)code_ptr = jump->u.target; + sljit_unaligned_store_sw(code_ptr, jump->u.target); code_ptr += sizeof(sljit_sw); *code_ptr++ = REX_B; @@ -71,13 +71,13 @@ static sljit_u8* generate_fixed_jump(sljit_u8 *code_ptr, sljit_sw addr, sljit_s3 if (delta <= HALFWORD_MAX && delta >= HALFWORD_MIN) { *code_ptr++ = (type == 2) ? CALL_i32 : JMP_i32; - *(sljit_sw*)code_ptr = delta; + sljit_unaligned_store_sw(code_ptr, delta); } else { SLJIT_COMPILE_ASSERT(reg_map[TMP_REG3] == 9, tmp3_is_9_second); *code_ptr++ = REX_W | REX_B; *code_ptr++ = MOV_r_i32 + 1; - *(sljit_sw*)code_ptr = addr; + sljit_unaligned_store_sw(code_ptr, addr); code_ptr += sizeof(sljit_sw); *code_ptr++ = REX_B; *code_ptr++ = GROUP_FF; @@ -193,7 +193,7 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_s32 sljit_emit_enter(struct sljit_compiler *compi *inst++ = REX_W; *inst++ = MOV_rm_i32; *inst++ = MOD_REG | reg_lmap[SLJIT_R0]; - *(sljit_s32*)inst = local_size; + sljit_unaligned_store_s32(inst, local_size); #if (defined SLJIT_VERBOSE && SLJIT_VERBOSE) \ || (defined SLJIT_ARGUMENT_CHECKS && SLJIT_ARGUMENT_CHECKS) compiler->skip_checks = 1; @@ -219,7 +219,7 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_s32 sljit_emit_enter(struct sljit_compiler *compi *inst++ = REX_W; *inst++ = GROUP_BINARY_81; *inst++ = MOD_REG | SUB | 4; - *(sljit_s32*)inst = local_size; + sljit_unaligned_store_s32(inst, local_size); inst += sizeof(sljit_s32); } @@ -230,7 +230,7 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_s32 sljit_emit_enter(struct sljit_compiler *compi FAIL_IF(!inst); INC_SIZE(5); *inst++ = GROUP_0F; - *(sljit_s32*)inst = 0x20247429; + sljit_unaligned_store_s32(inst, 0x20247429); } #endif @@ -271,7 +271,7 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_s32 sljit_emit_return(struct sljit_compiler *comp FAIL_IF(!inst); INC_SIZE(5); *inst++ = GROUP_0F; - *(sljit_s32*)inst = 0x20247428; + sljit_unaligned_store_s32(inst, 0x20247428); } #endif @@ -292,7 +292,7 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_s32 sljit_emit_return(struct sljit_compiler *comp *inst++ = REX_W; *inst++ = GROUP_BINARY_81; *inst++ = MOD_REG | ADD | 4; - *(sljit_s32*)inst = compiler->local_size; + sljit_unaligned_store_s32(inst, compiler->local_size); } tmp = compiler->scratches; @@ -339,7 +339,7 @@ static sljit_s32 emit_do_imm32(struct sljit_compiler *compiler, sljit_u8 rex, sl if (rex) *inst++ = rex; *inst++ = opcode; - *(sljit_s32*)inst = imm; + sljit_unaligned_store_s32(inst, imm); return SLJIT_SUCCESS; } @@ -516,7 +516,7 @@ static sljit_u8* emit_x86_instruction(struct sljit_compiler *compiler, sljit_s32 if (immb <= 127 && immb >= -128) *buf_ptr++ = immb; /* 8 bit displacement. */ else { - *(sljit_s32*)buf_ptr = immb; /* 32 bit displacement. */ + sljit_unaligned_store_s32(buf_ptr, immb); /* 32 bit displacement. */ buf_ptr += sizeof(sljit_s32); } } @@ -533,7 +533,7 @@ static sljit_u8* emit_x86_instruction(struct sljit_compiler *compiler, sljit_s32 else { *buf_ptr++ |= 0x04; *buf_ptr++ = 0x25; - *(sljit_s32*)buf_ptr = immb; /* 32 bit displacement. */ + sljit_unaligned_store_s32(buf_ptr, immb); /* 32 bit displacement. */ buf_ptr += sizeof(sljit_s32); } @@ -541,9 +541,9 @@ static sljit_u8* emit_x86_instruction(struct sljit_compiler *compiler, sljit_s32 if (flags & EX86_BYTE_ARG) *buf_ptr = imma; else if (flags & EX86_HALF_ARG) - *(short*)buf_ptr = imma; + sljit_unaligned_store_s16(buf_ptr, imma); else if (!(flags & EX86_SHIFT_INS)) - *(sljit_s32*)buf_ptr = imma; + sljit_unaligned_store_s32(buf_ptr, imma); } return !(flags & EX86_SHIFT_INS) ? inst : (inst + 1); @@ -676,7 +676,7 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_s32 sljit_emit_fast_return(struct sljit_compiler INC_SIZE(5 + 1); *inst++ = PUSH_i32; - *(sljit_s32*)inst = srcw; + sljit_unaligned_store_s32(inst, srcw); inst += sizeof(sljit_s32); } diff --git a/pcre/sljit/sljitNativeX86_common.c b/pcre/sljit/sljitNativeX86_common.c index 54c3ac7814b..960bdc2d039 100644 --- a/pcre/sljit/sljitNativeX86_common.c +++ b/pcre/sljit/sljitNativeX86_common.c @@ -279,6 +279,29 @@ static sljit_s32 cpu_has_cmov = -1; #include <intrin.h> #endif +/******************************************************/ +/* Unaligned-store functions */ +/******************************************************/ + +static SLJIT_INLINE void sljit_unaligned_store_s16(void *addr, sljit_s16 value) +{ + SLJIT_MEMCPY(addr, &value, sizeof(value)); +} + +static SLJIT_INLINE void sljit_unaligned_store_s32(void *addr, sljit_s32 value) +{ + SLJIT_MEMCPY(addr, &value, sizeof(value)); +} + +static SLJIT_INLINE void sljit_unaligned_store_sw(void *addr, sljit_sw value) +{ + SLJIT_MEMCPY(addr, &value, sizeof(value)); +} + +/******************************************************/ +/* Utility functions */ +/******************************************************/ + static void get_cpu_features(void) { sljit_u32 features; @@ -478,7 +501,7 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil len = *buf_ptr++; if (len > 0) { /* The code is already generated. */ - SLJIT_MEMMOVE(code_ptr, buf_ptr, len); + SLJIT_MEMCPY(code_ptr, buf_ptr, len); code_ptr += len; buf_ptr += len; } @@ -504,7 +527,7 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil #if (defined SLJIT_CONFIG_X86_32 && SLJIT_CONFIG_X86_32) *code_ptr++ = (*buf_ptr == 2) ? CALL_i32 : JMP_i32; buf_ptr++; - *(sljit_sw*)code_ptr = *(sljit_sw*)buf_ptr - ((sljit_sw)code_ptr + sizeof(sljit_sw)); + sljit_unaligned_store_sw(code_ptr, *(sljit_sw*)buf_ptr - ((sljit_sw)code_ptr + sizeof(sljit_sw))); code_ptr += sizeof(sljit_sw); buf_ptr += sizeof(sljit_sw) - 1; #else @@ -531,24 +554,24 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil } else if (jump->flags & PATCH_MW) { if (jump->flags & JUMP_LABEL) { #if (defined SLJIT_CONFIG_X86_32 && SLJIT_CONFIG_X86_32) - *(sljit_sw*)jump->addr = (sljit_sw)(jump->u.label->addr - (jump->addr + sizeof(sljit_sw))); + sljit_unaligned_store_sw((void*)jump->addr, (sljit_sw)(jump->u.label->addr - (jump->addr + sizeof(sljit_sw)))); #else SLJIT_ASSERT((sljit_sw)(jump->u.label->addr - (jump->addr + sizeof(sljit_s32))) >= HALFWORD_MIN && (sljit_sw)(jump->u.label->addr - (jump->addr + sizeof(sljit_s32))) <= HALFWORD_MAX); - *(sljit_s32*)jump->addr = (sljit_s32)(jump->u.label->addr - (jump->addr + sizeof(sljit_s32))); + sljit_unaligned_store_s32((void*)jump->addr, (sljit_s32)(jump->u.label->addr - (jump->addr + sizeof(sljit_s32)))); #endif } else { #if (defined SLJIT_CONFIG_X86_32 && SLJIT_CONFIG_X86_32) - *(sljit_sw*)jump->addr = (sljit_sw)(jump->u.target - (jump->addr + sizeof(sljit_sw))); + sljit_unaligned_store_sw((void*)jump->addr, (sljit_sw)(jump->u.target - (jump->addr + sizeof(sljit_sw)))); #else SLJIT_ASSERT((sljit_sw)(jump->u.target - (jump->addr + sizeof(sljit_s32))) >= HALFWORD_MIN && (sljit_sw)(jump->u.target - (jump->addr + sizeof(sljit_s32))) <= HALFWORD_MAX); - *(sljit_s32*)jump->addr = (sljit_s32)(jump->u.target - (jump->addr + sizeof(sljit_s32))); + sljit_unaligned_store_s32((void*)jump->addr, (sljit_s32)(jump->u.target - (jump->addr + sizeof(sljit_s32)))); #endif } } #if (defined SLJIT_CONFIG_X86_64 && SLJIT_CONFIG_X86_64) else if (jump->flags & PATCH_MD) - *(sljit_sw*)jump->addr = jump->u.label->addr; + sljit_unaligned_store_sw((void*)jump->addr, jump->u.label->addr); #endif jump = jump->next; @@ -558,6 +581,7 @@ SLJIT_API_FUNC_ATTRIBUTE void* sljit_generate_code(struct sljit_compiler *compil SLJIT_ASSERT(code_ptr <= code + compiler->size); compiler->error = SLJIT_ERR_COMPILED; compiler->executable_size = code_ptr - code; + SLJIT_ENABLE_EXEC(code, code_ptr); return (void*)code; } @@ -1699,7 +1723,7 @@ static sljit_s32 emit_mul(struct sljit_compiler *compiler, inst = (sljit_u8*)ensure_buf(compiler, 1 + 4); FAIL_IF(!inst); INC_SIZE(4); - *(sljit_sw*)inst = src1w; + sljit_unaligned_store_sw(inst, src1w); } #else else if (IS_HALFWORD(src1w)) { @@ -1709,7 +1733,7 @@ static sljit_s32 emit_mul(struct sljit_compiler *compiler, inst = (sljit_u8*)ensure_buf(compiler, 1 + 4); FAIL_IF(!inst); INC_SIZE(4); - *(sljit_s32*)inst = (sljit_s32)src1w; + sljit_unaligned_store_s32(inst, (sljit_s32)src1w); } else { EMIT_MOV(compiler, TMP_REG2, 0, SLJIT_IMM, src1w); @@ -1742,7 +1766,7 @@ static sljit_s32 emit_mul(struct sljit_compiler *compiler, inst = (sljit_u8*)ensure_buf(compiler, 1 + 4); FAIL_IF(!inst); INC_SIZE(4); - *(sljit_sw*)inst = src2w; + sljit_unaligned_store_sw(inst, src2w); } #else else if (IS_HALFWORD(src2w)) { @@ -1752,7 +1776,7 @@ static sljit_s32 emit_mul(struct sljit_compiler *compiler, inst = (sljit_u8*)ensure_buf(compiler, 1 + 4); FAIL_IF(!inst); INC_SIZE(4); - *(sljit_s32*)inst = (sljit_s32)src2w; + sljit_unaligned_store_s32(inst, (sljit_s32)src2w); } else { EMIT_MOV(compiler, TMP_REG2, 0, SLJIT_IMM, src2w); @@ -2248,7 +2272,7 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_s32 sljit_emit_op_custom(struct sljit_compiler *c inst = (sljit_u8*)ensure_buf(compiler, 1 + size); FAIL_IF(!inst); INC_SIZE(size); - SLJIT_MEMMOVE(inst, instruction, size); + SLJIT_MEMCPY(inst, instruction, size); return SLJIT_SUCCESS; } @@ -2557,6 +2581,7 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_jump* sljit_emit_jump(struct sljit_compile struct sljit_jump *jump; CHECK_ERROR_PTR(); + CHECK_DYN_CODE_MOD(type & SLJIT_REWRITABLE_JUMP); CHECK_PTR(check_sljit_emit_jump(compiler, type)); if (SLJIT_UNLIKELY(compiler->flags_saved)) { @@ -2885,6 +2910,7 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_const* sljit_emit_const(struct sljit_compi #endif CHECK_ERROR_PTR(); + CHECK_DYN_CODE_MOD(1); CHECK_PTR(check_sljit_emit_const(compiler, dst, dstw, init_value)); ADJUST_LOCAL_OFFSET(dst, dstw); @@ -2926,15 +2952,15 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_const* sljit_emit_const(struct sljit_compi SLJIT_API_FUNC_ATTRIBUTE void sljit_set_jump_addr(sljit_uw addr, sljit_uw new_addr) { #if (defined SLJIT_CONFIG_X86_32 && SLJIT_CONFIG_X86_32) - *(sljit_sw*)addr = new_addr - (addr + 4); + sljit_unaligned_store_sw((void*)addr, new_addr - (addr + 4)); #else - *(sljit_uw*)addr = new_addr; + sljit_unaligned_store_sw((void*)addr, (sljit_sw) new_addr); #endif } SLJIT_API_FUNC_ATTRIBUTE void sljit_set_const(sljit_uw addr, sljit_sw new_constant) { - *(sljit_sw*)addr = new_constant; + sljit_unaligned_store_sw((void*)addr, new_constant); } SLJIT_API_FUNC_ATTRIBUTE sljit_s32 sljit_x86_is_sse2_available(void) diff --git a/pcre/testdata/testinput1 b/pcre/testdata/testinput1 index 8379ce04d5b..93abab3c851 100644 --- a/pcre/testdata/testinput1 +++ b/pcre/testdata/testinput1 @@ -5733,4 +5733,10 @@ AbcdCBefgBhiBqz "(?|(\k'Pm')|(?'Pm'))" abcd +/(?=.*[A-Z])(?=.*[a-z])(?=.*[0-9])(?=.*[,;:])(?=.{8,16})(?!.*[\s])/ + \ Fred:099 + +/(?=.*X)X$/ + \ X + /-- End of testinput1 --/ diff --git a/pcre/testdata/testinput16 b/pcre/testdata/testinput16 index 15419e63fa6..7ccde0a8c80 100644 --- a/pcre/testdata/testinput16 +++ b/pcre/testdata/testinput16 @@ -38,4 +38,30 @@ /s+/i8SI SSss\x{17f} +/[\W\p{Any}]/BZ + abc + 123 + +/[\W\pL]/BZ + abc + ** Failers + 123 + +/[\D]/8 + \x{1d7cf} + +/[\D\P{Nd}]/8 + \x{1d7cf} + +/[^\D]/8 + a9b + ** Failers + \x{1d7cf} + +/[^\D\P{Nd}]/8 + a9b + \x{1d7cf} + ** Failers + \x{10000} + /-- End of testinput16 --/ diff --git a/pcre/testdata/testinput19 b/pcre/testdata/testinput19 index ce45afcb595..dfe8c7befb6 100644 --- a/pcre/testdata/testinput19 +++ b/pcre/testdata/testinput19 @@ -25,4 +25,21 @@ /s+/i8SI SSss\x{17f} +/[\D]/8 + \x{1d7cf} + +/[\D\P{Nd}]/8 + \x{1d7cf} + +/[^\D]/8 + a9b + ** Failers + \x{1d7cf} + +/[^\D\P{Nd}]/8 + a9b + \x{1d7cf} + ** Failers + \x{10000} + /-- End of testinput19 --/ diff --git a/pcre/testdata/testinput2 b/pcre/testdata/testinput2 index 75e402ee9b3..08c6f39a565 100644 --- a/pcre/testdata/testinput2 +++ b/pcre/testdata/testinput2 @@ -4243,4 +4243,10 @@ backtracking verbs. --/ /\N(?(?C)0?!.)*/ +/(?<RA>abc)(?(R)xyz)/BZ + +/(?<R>abc)(?(R)xyz)/BZ + +/(?=.*[A-Z])/I + /-- End of testinput2 --/ diff --git a/pcre/testdata/testinput6 b/pcre/testdata/testinput6 index a178d3d67b4..22ed1e64d57 100644 --- a/pcre/testdata/testinput6 +++ b/pcre/testdata/testinput6 @@ -1562,4 +1562,10 @@ \x{389} \x{20ac} +/(?=.*b)\pL/ + 11bb + +/(?(?=.*b)(?=.*b)\pL|.*c)/ + 11bb + /-- End of testinput6 --/ diff --git a/pcre/testdata/testinput7 b/pcre/testdata/testinput7 index 00b9738a371..f44a810f0f2 100644 --- a/pcre/testdata/testinput7 +++ b/pcre/testdata/testinput7 @@ -838,15 +838,6 @@ of case for anything other than the ASCII letters. --/ /^s?c/mi8I scat -/[\W\p{Any}]/BZ - abc - 123 - -/[\W\pL]/BZ - abc - ** Failers - 123 - /a[[:punct:]b]/WBZ /a[[:punct:]b]/8WBZ diff --git a/pcre/testdata/testinput8 b/pcre/testdata/testinput8 index 931dd717e74..7f8fa8292c5 100644 --- a/pcre/testdata/testinput8 +++ b/pcre/testdata/testinput8 @@ -4841,4 +4841,8 @@ bbb aaa +/()()a+/O= + aaa\D + a\D + /-- End of testinput8 --/ diff --git a/pcre/testdata/testoutput1 b/pcre/testdata/testoutput1 index e852ab9544c..a2b3cffe9d4 100644 --- a/pcre/testdata/testoutput1 +++ b/pcre/testdata/testoutput1 @@ -9434,4 +9434,12 @@ No match 0: 1: +/(?=.*[A-Z])(?=.*[a-z])(?=.*[0-9])(?=.*[,;:])(?=.{8,16})(?!.*[\s])/ + \ Fred:099 + 0: + +/(?=.*X)X$/ + \ X + 0: X + /-- End of testinput1 --/ diff --git a/pcre/testdata/testoutput16 b/pcre/testdata/testoutput16 index fd184cdbeee..e6ba26acfd4 100644 --- a/pcre/testdata/testoutput16 +++ b/pcre/testdata/testoutput16 @@ -138,4 +138,56 @@ Starting chars: S s \xc5 SSss\x{17f} 0: SSss\x{17f} +/[\W\p{Any}]/BZ +------------------------------------------------------------------ + Bra + [\x00-/:-@[-^`{-\xff\p{Any}] + Ket + End +------------------------------------------------------------------ + abc + 0: a + 123 + 0: 1 + +/[\W\pL]/BZ +------------------------------------------------------------------ + Bra + [\x00-/:-@[-^`{-\xff\p{L}] + Ket + End +------------------------------------------------------------------ + abc + 0: a + ** Failers + 0: * + 123 +No match + +/[\D]/8 + \x{1d7cf} + 0: \x{1d7cf} + +/[\D\P{Nd}]/8 + \x{1d7cf} + 0: \x{1d7cf} + +/[^\D]/8 + a9b + 0: 9 + ** Failers +No match + \x{1d7cf} +No match + +/[^\D\P{Nd}]/8 + a9b + 0: 9 + \x{1d7cf} + 0: \x{1d7cf} + ** Failers +No match + \x{10000} +No match + /-- End of testinput16 --/ diff --git a/pcre/testdata/testoutput19 b/pcre/testdata/testoutput19 index eb8a8f6cd34..982bea4c136 100644 --- a/pcre/testdata/testoutput19 +++ b/pcre/testdata/testoutput19 @@ -105,4 +105,30 @@ Starting chars: S s \xff SSss\x{17f} 0: SSss\x{17f} +/[\D]/8 + \x{1d7cf} + 0: \x{1d7cf} + +/[\D\P{Nd}]/8 + \x{1d7cf} + 0: \x{1d7cf} + +/[^\D]/8 + a9b + 0: 9 + ** Failers +No match + \x{1d7cf} +No match + +/[^\D\P{Nd}]/8 + a9b + 0: 9 + \x{1d7cf} + 0: \x{1d7cf} + ** Failers +No match + \x{10000} +No match + /-- End of testinput19 --/ diff --git a/pcre/testdata/testoutput2 b/pcre/testdata/testoutput2 index 5e88d1a7091..811bbefc84c 100644 --- a/pcre/testdata/testoutput2 +++ b/pcre/testdata/testoutput2 @@ -9380,7 +9380,7 @@ No need char /(?(?=.*b).*b|^d)/I Capturing subpattern count = 0 No options -First char at start or follows newline +No first char No need char /xyz/C @@ -14670,4 +14670,39 @@ No match /\N(?(?C)0?!.)*/ Failed: assertion expected after (?( or (?(?C) at offset 4 +/(?<RA>abc)(?(R)xyz)/BZ +------------------------------------------------------------------ + Bra + CBra 1 + abc + Ket + Cond + Cond recurse any + xyz + Ket + Ket + End +------------------------------------------------------------------ + +/(?<R>abc)(?(R)xyz)/BZ +------------------------------------------------------------------ + Bra + CBra 1 + abc + Ket + Cond + 1 Cond ref + xyz + Ket + Ket + End +------------------------------------------------------------------ + +/(?=.*[A-Z])/I +Capturing subpattern count = 0 +May match empty string +No options +No first char +No need char + /-- End of testinput2 --/ diff --git a/pcre/testdata/testoutput6 b/pcre/testdata/testoutput6 index b64dc0dc366..422d3833578 100644 --- a/pcre/testdata/testoutput6 +++ b/pcre/testdata/testoutput6 @@ -2573,4 +2573,12 @@ No match \x{20ac} No match +/(?=.*b)\pL/ + 11bb + 0: b + +/(?(?=.*b)(?=.*b)\pL|.*c)/ + 11bb + 0: b + /-- End of testinput6 --/ diff --git a/pcre/testdata/testoutput7 b/pcre/testdata/testoutput7 index fdfff646d3e..2b167b28d1c 100644 --- a/pcre/testdata/testoutput7 +++ b/pcre/testdata/testoutput7 @@ -2295,32 +2295,6 @@ Need char = 'c' (caseless) scat 0: sc -/[\W\p{Any}]/BZ ------------------------------------------------------------------- - Bra - [\x00-/:-@[-^`{-\xff\p{Any}] - Ket - End ------------------------------------------------------------------- - abc - 0: a - 123 - 0: 1 - -/[\W\pL]/BZ ------------------------------------------------------------------- - Bra - [\x00-/:-@[-^`{-\xff\p{L}] - Ket - End ------------------------------------------------------------------- - abc - 0: a - ** Failers - 0: * - 123 -No match - /a[[:punct:]b]/WBZ ------------------------------------------------------------------ Bra diff --git a/pcre/testdata/testoutput8 b/pcre/testdata/testoutput8 index e4fa4977561..17b667a980c 100644 --- a/pcre/testdata/testoutput8 +++ b/pcre/testdata/testoutput8 @@ -7791,4 +7791,14 @@ Matched, but offsets vector is too small to show all matches aaa No match +/()()a+/O= + aaa\D +** Show all captures ignored after DFA matching + 0: aaa + 1: aa + 2: a + a\D +** Show all captures ignored after DFA matching + 0: a + /-- End of testinput8 --/ |