diff options
| author | ph10 <ph10@2f5784b3-3f2a-0410-8824-cb99058d5e15> | 2012-10-31 17:42:29 +0000 |
|---|---|---|
| committer | ph10 <ph10@2f5784b3-3f2a-0410-8824-cb99058d5e15> | 2012-10-31 17:42:29 +0000 |
| commit | 7aee104a4b40242e323b6a7291e8b82533446557 (patch) | |
| tree | 46fa468bf10d082967f52386fd8a93178b048149 | |
| parent | 30c38b72f7c232b1b2fadd66f4da75e5117f91a3 (diff) | |
| download | pcre-7aee104a4b40242e323b6a7291e8b82533446557.tar.gz | |
More documentation updates
git-svn-id: svn://vcs.exim.org/pcre/code/trunk@1194 2f5784b3-3f2a-0410-8824-cb99058d5e15
57 files changed, 5808 insertions, 3358 deletions
diff --git a/Makefile.am b/Makefile.am index 004034e..dcf51f0 100644 --- a/Makefile.am +++ b/Makefile.am @@ -36,6 +36,7 @@ dist_html_DATA = \ doc/html/pcre_get_stringtable_entries.html \ doc/html/pcre_get_substring.html \ doc/html/pcre_get_substring_list.html \ + doc/html/pcre_jit_exec.html \ doc/html/pcre_jit_stack_alloc.html \ doc/html/pcre_jit_stack_free.html \ doc/html/pcre_maketables.html \ @@ -140,8 +141,8 @@ pcre.h.generic: pcre.h.in configure.ac # It is more complicated for config.h.generic. We need the version that results # from a default configuration. We can get this by doing a configure in a -# temporary directory. It has to be entirely done using files in that -# directory, because the source directory may already be configured. If you +# temporary directory. It has to be entirely done using files in that +# directory, because the source directory may already be configured. If you # just try running configure in a new directory, it complains that the source # directory is already configured. config.h.generic: configure.ac @@ -663,6 +664,7 @@ dist_man_MANS = \ doc/pcre_get_stringtable_entries.3 \ doc/pcre_get_substring.3 \ doc/pcre_get_substring_list.3 \ + doc/pcre_jit_exec.3 \ doc/pcre_jit_stack_alloc.3 \ doc/pcre_jit_stack_free.3 \ doc/pcre_maketables.3 \ @@ -710,6 +712,7 @@ install-data-hook: ln -sf pcre_get_stringtable_entries.3 $(DESTDIR)$(man3dir)/pcre16_get_stringtable_entries.3 ln -sf pcre_get_substring.3 $(DESTDIR)$(man3dir)/pcre16_get_substring.3 ln -sf pcre_get_substring_list.3 $(DESTDIR)$(man3dir)/pcre16_get_substring_list.3 + ln -sf pcre_jit_exec.3 $(DESTDIR)$(man3dir)/pcre16_jit_exec.3 ln -sf pcre_jit_stack_alloc.3 $(DESTDIR)$(man3dir)/pcre16_jit_stack_alloc.3 ln -sf pcre_jit_stack_free.3 $(DESTDIR)$(man3dir)/pcre16_jit_stack_free.3 ln -sf pcre_maketables.3 $(DESTDIR)$(man3dir)/pcre16_maketables.3 @@ -735,6 +738,7 @@ install-data-hook: ln -sf pcre_get_stringtable_entries.3 $(DESTDIR)$(man3dir)/pcre32_get_stringtable_entries.3 ln -sf pcre_get_substring.3 $(DESTDIR)$(man3dir)/pcre32_get_substring.3 ln -sf pcre_get_substring_list.3 $(DESTDIR)$(man3dir)/pcre32_get_substring_list.3 + ln -sf pcre_jit_exec.3 $(DESTDIR)$(man3dir)/pcre32_jit_exec.3 ln -sf pcre_jit_stack_alloc.3 $(DESTDIR)$(man3dir)/pcre32_jit_stack_alloc.3 ln -sf pcre_jit_stack_free.3 $(DESTDIR)$(man3dir)/pcre32_jit_stack_free.3 ln -sf pcre_maketables.3 $(DESTDIR)$(man3dir)/pcre32_maketables.3 diff --git a/doc/html/index.html b/doc/html/index.html index 739f7a5..c7bc196 100644 --- a/doc/html/index.html +++ b/doc/html/index.html @@ -1,10 +1,10 @@ <html> -<!-- This is a manually maintained file that is the root of the HTML version of - the PCRE documentation. When the HTML documents are built from the man - page versions, the entire doc/html directory is emptied, this file is then - copied into doc/html/index.html, and the remaining files therein are +<!-- This is a manually maintained file that is the root of the HTML version of + the PCRE documentation. When the HTML documents are built from the man + page versions, the entire doc/html directory is emptied, this file is then + copied into doc/html/index.html, and the remaining files therein are created by the 132html script. ---> +--> <head> <title>PCRE specification</title> </head> @@ -21,6 +21,9 @@ The HTML documentation for PCRE comprises the following pages: <tr><td><a href="pcre16.html">pcre16</a></td> <td> Discussion of the 16-bit PCRE library</td></tr> +<tr><td><a href="pcre32.html">pcre32</a></td> + <td> Discussion of the 32-bit PCRE library</td></tr> + <tr><td><a href="pcre-config.html">pcre-config</a></td> <td> Information about the installation configuration</td></tr> @@ -82,15 +85,16 @@ The HTML documentation for PCRE comprises the following pages: <td> The <b>pcretest</b> command for testing PCRE</td></tr> <tr><td><a href="pcreunicode.html">pcreunicode</a></td> - <td> Discussion of Unicode and UTF-8/UTF-16 support</td></tr> + <td> Discussion of Unicode and UTF-8/UTF-16/UTF-32 support</td></tr> </table> <p> There are also individual pages that summarize the interface for each function -in the library. There is a single page for each pair of 8-bit/16-bit functions. +in the library. There is a single page for each triple of 8-bit/16-bit/32-bit +functions. </p> -<table> +<table> <tr><td><a href="pcre_assign_jit_stack.html">pcre_assign_jit_stack</a></td> <td> Assign stack for JIT matching</td></tr> @@ -153,7 +157,7 @@ in the library. There is a single page for each pair of 8-bit/16-bit functions. <tr><td><a href="pcre_maketables.html">pcre_maketables</a></td> <td> Build character tables in current locale</td></tr> - + <tr><td><a href="pcre_pattern_to_host_byte_order.html">pcre_pattern_to_host_byte_order</a></td> <td> Convert compiled pattern to host byte order if necessary</td></tr> @@ -166,6 +170,9 @@ in the library. There is a single page for each pair of 8-bit/16-bit functions. <tr><td><a href="pcre_utf16_to_host_byte_order.html">pcre_utf16_to_host_byte_order</a></td> <td> Convert UTF-16 string to host byte order if necessary</td></tr> +<tr><td><a href="pcre_utf32_to_host_byte_order.html">pcre_utf32_to_host_byte_order</a></td> + <td> Convert UTF-32 string to host byte order if necessary</td></tr> + <tr><td><a href="pcre_version.html">pcre_version</a></td> <td> Return PCRE version and release date</td></tr> </table> diff --git a/doc/html/pcre-config.html b/doc/html/pcre-config.html index 87c874d..3df7ff4 100644 --- a/doc/html/pcre-config.html +++ b/doc/html/pcre-config.html @@ -23,14 +23,15 @@ man page, in case the conversion went wrong. <br><a name="SEC1" href="#TOC1">SYNOPSIS</a><br> <P> <b>pcre-config [--prefix] [--exec-prefix] [--version] [--libs]</b> -<b>[--libs16] [--libs-cpp] [--libs-posix] [--cflags]</b> -<b>[--cflags-posix]</b> +<b>[--libs16] [--libs32] [--libs-cpp] [--libs-posix]</b> +<b>[--cflags] [--cflags-posix]</b> </P> <br><a name="SEC2" href="#TOC1">DESCRIPTION</a><br> <P> <b>pcre-config</b> returns the configuration of the installed PCRE libraries and the options required to compile a program to use them. Some of -the options apply only to the 8-bit or 16-bit libraries, respectively, and are +the options apply only to the 8-bit, or 16-bit, or 32-bit libraries, +respectively, and are not available if only one of those libraries has been built. If an unavailable option is encountered, the "usage" information is output. </P> @@ -62,6 +63,11 @@ Writes to the standard output the command line options required to link with the 16-bit PCRE library (<b>-lpcre16</b> on many systems). </P> <P> +<b>--libs32</b> +Writes to the standard output the command line options required to link +with the 32-bit PCRE library (<b>-lpcre32</b> on many systems). +</P> +<P> <b>--libs-cpp</b> Writes to the standard output the command line options required to link with PCRE's C++ wrapper library (<b>-lpcrecpp</b> <b>-lpcre</b> on many @@ -96,7 +102,7 @@ system. It has been subsequently revised as a generic PCRE man page. </P> <br><a name="SEC6" href="#TOC1">REVISION</a><br> <P> -Last updated: 01 January 2012 +Last updated: 24 June 2012 <br> <p> Return to the <a href="index.html">PCRE index page</a>. diff --git a/doc/html/pcre.html b/doc/html/pcre.html index ff5202f..f05e08c 100644 --- a/doc/html/pcre.html +++ b/doc/html/pcre.html @@ -14,9 +14,10 @@ man page, in case the conversion went wrong. <br> <ul> <li><a name="TOC1" href="#SEC1">INTRODUCTION</a> -<li><a name="TOC2" href="#SEC2">USER DOCUMENTATION</a> -<li><a name="TOC3" href="#SEC3">AUTHOR</a> -<li><a name="TOC4" href="#SEC4">REVISION</a> +<li><a name="TOC2" href="#SEC2">SECURITY CONSIDERATIONS</a> +<li><a name="TOC3" href="#SEC3">USER DOCUMENTATION</a> +<li><a name="TOC4" href="#SEC4">AUTHOR</a> +<li><a name="TOC5" href="#SEC5">REVISION</a> </ul> <br><a name="SEC1" href="#TOC1">INTRODUCTION</a><br> <P> @@ -36,21 +37,32 @@ built. The majority of the work to make this possible was done by Zoltan Herczeg. </P> <P> -The two libraries contain identical sets of functions, except that the names in -the 16-bit library start with <b>pcre16_</b> instead of <b>pcre_</b>. To avoid -over-complication and reduce the documentation maintenance load, most of the -documentation describes the 8-bit library, with the differences for the 16-bit -library described separately in the +Starting with release 8.32 it is possible to compile a third separate PCRE +library, which supports 32-bit character strings (including +UTF-32 strings). The build process allows any set of the 8-, 16- and 32-bit +libraries. The work to make this possible was done by Christian Persch. +</P> +<P> +The three libraries contain identical sets of functions, except that the names +in the 16-bit library start with <b>pcre16_</b> instead of <b>pcre_</b>, and the +names in the 32-bit library start with <b>pcre32_</b> instead of <b>pcre_</b>. To +avoid over-complication and reduce the documentation maintenance load, most of +the documentation describes the 8-bit library, with the differences for the +16-bit and 32-bit libraries described separately in the <a href="pcre16.html"><b>pcre16</b></a> -page. References to functions or structures of the form <i>pcre[16]_xxx</i> -should be read as meaning "<i>pcre_xxx</i> when using the 8-bit library and -<i>pcre16_xxx</i> when using the 16-bit library". +and +<a href="pcre32.html"><b>pcre32</b></a> +pages. References to functions or structures of the form <i>pcre[16|32]_xxx</i> +should be read as meaning "<i>pcre_xxx</i> when using the 8-bit library, +<i>pcre16_xxx</i> when using the 16-bit library, or <i>pcre32_xxx</i> when using +the 32-bit library". </P> <P> The current implementation of PCRE corresponds approximately with Perl 5.12, -including support for UTF-8/16 encoded strings and Unicode general category -properties. However, UTF-8/16 and Unicode support has to be explicitly enabled; -it is not the default. The Unicode tables correspond to Unicode release 6.0.0. +including support for UTF-8/16/32 encoded strings and Unicode general category +properties. However, UTF-8/16/32 and Unicode support has to be explicitly +enabled; it is not the default. The Unicode tables correspond to Unicode +release 6.2.0. </P> <P> In addition to the Perl-compatible matching function, PCRE contains an @@ -88,19 +100,48 @@ function makes it possible for a client to discover which features are available. The features themselves are described in the <a href="pcrebuild.html"><b>pcrebuild</b></a> page. Documentation about building PCRE for various operating systems can be -found in the <b>README</b> and <b>NON-UNIX-USE</b> files in the source +found in the <b>README</b> and <b>NON-AUTOTOOLS_BUILD</b> files in the source distribution. </P> <P> The libraries contains a number of undocumented internal functions and data tables that are used by more than one of the exported external functions, but which are not intended for use by external callers. Their names all begin with -"_pcre_" or "_pcre16_", which hopefully will not provoke any name clashes. In -some environments, it is possible to control which external symbols are -exported when a shared library is built, and in these cases the undocumented -symbols are not exported. +"_pcre_" or "_pcre16_" or "_pcre32_", which hopefully will not provoke any name +clashes. In some environments, it is possible to control which external symbols +are exported when a shared library is built, and in these cases the +undocumented symbols are not exported. +</P> +<br><a name="SEC2" href="#TOC1">SECURITY CONSIDERATIONS</a><br> +<P> +If you are using PCRE in a non-UTF application that permits users to supply +arbitrary patterns for compilation, you should be aware of a feature that +allows users to turn on UTF support from within a pattern, provided that PCRE +was built with UTF support. For example, an 8-bit pattern that begins with +"(*UTF8)" turns on UTF-8 mode. This causes both the pattern and any data +against which it is matched to be checked for UTF-8 validity. If the data +string is very long, such a check might use sufficiently many resources as to +cause your application to lose performance. +</P> +<P> +The best way of guarding against this possibility is to use the +<b>pcre_fullinfo()</b> function to check the compiled pattern's options for UTF. +</P> +<P> +If your application is one that supports UTF, be aware that validity checking +can take time. If the same data string is to be matched many times, you can use +the PCRE_NO_UTF[8|16|32]_CHECK option for the second and subsequent matches to +save redundant checks. +</P> +<P> +Another way that performance can be hit is by running a pattern that has a very +large search tree against a string that will never match. Nested unlimited +repeats in a pattern are a common example. PCRE provides some protection +against this: see the PCRE_EXTRA_MATCH_LIMIT feature in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page. </P> -<br><a name="SEC2" href="#TOC1">USER DOCUMENTATION</a><br> +<br><a name="SEC3" href="#TOC1">USER DOCUMENTATION</a><br> <P> The user documentation for PCRE comprises a number of different sections. In the "man" format, each of these is a separate "man page". In the HTML format, @@ -110,6 +151,7 @@ of searching. The sections are as follows: <pre> pcre this document pcre16 details of the 16-bit library + pcre32 details of the 32-bit library pcre-config show PCRE installation configuration information pcreapi details of PCRE's native C API pcrebuild options for building PCRE @@ -130,12 +172,12 @@ of searching. The sections are as follows: pcrestack discussion of stack usage pcresyntax quick syntax reference pcretest description of the <b>pcretest</b> testing command - pcreunicode discussion of Unicode and UTF-8/16 support + pcreunicode discussion of Unicode and UTF-8/16/32 support </pre> In addition, in the "man" and HTML formats, there is a short page for each -8-bit C library function, listing its arguments and results. +C library function, listing its arguments and results. </P> -<br><a name="SEC3" href="#TOC1">AUTHOR</a><br> +<br><a name="SEC4" href="#TOC1">AUTHOR</a><br> <P> Philip Hazel <br> @@ -149,9 +191,9 @@ Putting an actual email address here seems to have been a spam magnet, so I've taken it away. If you want to email me, use my two initials, followed by the two digits 10, at the domain cam.ac.uk. </P> -<br><a name="SEC4" href="#TOC1">REVISION</a><br> +<br><a name="SEC5" href="#TOC1">REVISION</a><br> <P> -Last updated: 10 January 2012 +Last updated: 30 October 2012 <br> Copyright © 1997-2012 University of Cambridge. <br> diff --git a/doc/html/pcre16.html b/doc/html/pcre16.html index c996eeb..06388ed 100644 --- a/doc/html/pcre16.html +++ b/doc/html/pcre16.html @@ -283,8 +283,9 @@ page. <P> For the <b>pcre16_config()</b> function there is an option PCRE_CONFIG_UTF16 that returns 1 if UTF-16 support is configured, otherwise 0. If this option is -given to <b>pcre_config()</b>, or if the PCRE_CONFIG_UTF8 option is given to -<b>pcre16_config()</b>, the result is the PCRE_ERROR_BADOPTION error. +given to <b>pcre_config()</b> or <b>pcre32_config()</b>, or if the +PCRE_CONFIG_UTF8 or PCRE_CONFIG_UTF32 option is given to <b>pcre16_config()</b>, +the result is the PCRE_ERROR_BADOPTION error. </P> <br><a name="SEC15" href="#TOC1">CHARACTER CODES</a><br> <P> @@ -327,7 +328,7 @@ page. The UTF-16 errors are: PCRE_UTF16_ERR1 Missing low surrogate at end of string PCRE_UTF16_ERR2 Invalid low surrogate follows high surrogate PCRE_UTF16_ERR3 Isolated low surrogate - PCRE_UTF16_ERR4 Invalid character 0xfffe + PCRE_UTF16_ERR4 Non-character </PRE> </P> <br><a name="SEC17" href="#TOC1">ERROR TEXTS</a><br> @@ -348,13 +349,13 @@ files, but it can be used for testing the 16-bit library. If it is run with the command line option <b>-16</b>, patterns and subject strings are converted from 8-bit to 16-bit before being passed to PCRE, and the 16-bit library functions are used instead of the 8-bit ones. Returned 16-bit strings are converted to -8-bit for output. If the 8-bit library was not compiled, <b>pcretest</b> -defaults to 16-bit and the <b>-16</b> option is ignored. +8-bit for output. If both the 8-bit and the 32-bit libraries were not compiled, +<b>pcretest</b> defaults to 16-bit and the <b>-16</b> option is ignored. </P> <P> When PCRE is being built, the <b>RunTest</b> script that is called by "make -check" uses the <b>pcretest</b> <b>-C</b> option to discover which of the 8-bit -and 16-bit libraries has been built, and runs the tests appropriately. +check" uses the <b>pcretest</b> <b>-C</b> option to discover which of the 8-bit, +16-bit and 32-bit libraries has been built, and runs the tests appropriately. </P> <br><a name="SEC20" href="#TOC1">NOT SUPPORTED IN 16-BIT MODE</a><br> <P> diff --git a/doc/html/pcre32.html b/doc/html/pcre32.html new file mode 100644 index 0000000..f170adf --- /dev/null +++ b/doc/html/pcre32.html @@ -0,0 +1,382 @@ +<html> +<head> +<title>pcre32 specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre32 man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<ul> +<li><a name="TOC1" href="#SEC1">PCRE 32-BIT API BASIC FUNCTIONS</a> +<li><a name="TOC2" href="#SEC2">PCRE 32-BIT API STRING EXTRACTION FUNCTIONS</a> +<li><a name="TOC3" href="#SEC3">PCRE 32-BIT API AUXILIARY FUNCTIONS</a> +<li><a name="TOC4" href="#SEC4">PCRE 32-BIT API INDIRECTED FUNCTIONS</a> +<li><a name="TOC5" href="#SEC5">PCRE 32-BIT API 32-BIT-ONLY FUNCTION</a> +<li><a name="TOC6" href="#SEC6">THE PCRE 32-BIT LIBRARY</a> +<li><a name="TOC7" href="#SEC7">THE HEADER FILE</a> +<li><a name="TOC8" href="#SEC8">THE LIBRARY NAME</a> +<li><a name="TOC9" href="#SEC9">STRING TYPES</a> +<li><a name="TOC10" href="#SEC10">STRUCTURE TYPES</a> +<li><a name="TOC11" href="#SEC11">32-BIT FUNCTIONS</a> +<li><a name="TOC12" href="#SEC12">SUBJECT STRING OFFSETS</a> +<li><a name="TOC13" href="#SEC13">NAMED SUBPATTERNS</a> +<li><a name="TOC14" href="#SEC14">OPTION NAMES</a> +<li><a name="TOC15" href="#SEC15">CHARACTER CODES</a> +<li><a name="TOC16" href="#SEC16">ERROR NAMES</a> +<li><a name="TOC17" href="#SEC17">ERROR TEXTS</a> +<li><a name="TOC18" href="#SEC18">CALLOUTS</a> +<li><a name="TOC19" href="#SEC19">TESTING</a> +<li><a name="TOC20" href="#SEC20">NOT SUPPORTED IN 32-BIT MODE</a> +<li><a name="TOC21" href="#SEC21">AUTHOR</a> +<li><a name="TOC22" href="#SEC22">REVISION</a> +</ul> +<P> +<b>#include <pcre.h></b> +</P> +<br><a name="SEC1" href="#TOC1">PCRE 32-BIT API BASIC FUNCTIONS</a><br> +<P> +<b>pcre32 *pcre32_compile(PCRE_SPTR32 <i>pattern</i>, int <i>options</i>,</b> +<b>const char **<i>errptr</i>, int *<i>erroffset</i>,</b> +<b>const unsigned char *<i>tableptr</i>);</b> +</P> +<P> +<b>pcre32 *pcre32_compile2(PCRE_SPTR32 <i>pattern</i>, int <i>options</i>,</b> +<b>int *<i>errorcodeptr</i>,</b> +<b>const char **<i>errptr</i>, int *<i>erroffset</i>,</b> +<b>const unsigned char *<i>tableptr</i>);</b> +</P> +<P> +<b>pcre32_extra *pcre32_study(const pcre32 *<i>code</i>, int <i>options</i>,</b> +<b>const char **<i>errptr</i>);</b> +</P> +<P> +<b>void pcre32_free_study(pcre32_extra *<i>extra</i>);</b> +</P> +<P> +<b>int pcre32_exec(const pcre32 *<i>code</i>, const pcre32_extra *<i>extra</i>,</b> +<b>PCRE_SPTR32 <i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b> +<b>int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>);</b> +</P> +<P> +<b>int pcre32_dfa_exec(const pcre32 *<i>code</i>, const pcre32_extra *<i>extra</i>,</b> +<b>PCRE_SPTR32 <i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b> +<b>int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b> +<b>int *<i>workspace</i>, int <i>wscount</i>);</b> +</P> +<br><a name="SEC2" href="#TOC1">PCRE 32-BIT API STRING EXTRACTION FUNCTIONS</a><br> +<P> +<b>int pcre32_copy_named_substring(const pcre32 *<i>code</i>,</b> +<b>PCRE_SPTR32 <i>subject</i>, int *<i>ovector</i>,</b> +<b>int <i>stringcount</i>, PCRE_SPTR32 <i>stringname</i>,</b> +<b>PCRE_UCHAR32 *<i>buffer</i>, int <i>buffersize</i>);</b> +</P> +<P> +<b>int pcre32_copy_substring(PCRE_SPTR32 <i>subject</i>, int *<i>ovector</i>,</b> +<b>int <i>stringcount</i>, int <i>stringnumber</i>, PCRE_UCHAR32 *<i>buffer</i>,</b> +<b>int <i>buffersize</i>);</b> +</P> +<P> +<b>int pcre32_get_named_substring(const pcre32 *<i>code</i>,</b> +<b>PCRE_SPTR32 <i>subject</i>, int *<i>ovector</i>,</b> +<b>int <i>stringcount</i>, PCRE_SPTR32 <i>stringname</i>,</b> +<b>PCRE_SPTR32 *<i>stringptr</i>);</b> +</P> +<P> +<b>int pcre32_get_stringnumber(const pcre32 *<i>code</i>,</b> +<b>PCRE_SPTR32 <i>name</i>);</b> +</P> +<P> +<b>int pcre32_get_stringtable_entries(const pcre32 *<i>code</i>,</b> +<b>PCRE_SPTR32 <i>name</i>, PCRE_UCHAR32 **<i>first</i>, PCRE_UCHAR32 **<i>last</i>);</b> +</P> +<P> +<b>int pcre32_get_substring(PCRE_SPTR32 <i>subject</i>, int *<i>ovector</i>,</b> +<b>int <i>stringcount</i>, int <i>stringnumber</i>,</b> +<b>PCRE_SPTR32 *<i>stringptr</i>);</b> +</P> +<P> +<b>int pcre32_get_substring_list(PCRE_SPTR32 <i>subject</i>,</b> +<b>int *<i>ovector</i>, int <i>stringcount</i>, PCRE_SPTR32 **<i>listptr</i>);</b> +</P> +<P> +<b>void pcre32_free_substring(PCRE_SPTR32 <i>stringptr</i>);</b> +</P> +<P> +<b>void pcre32_free_substring_list(PCRE_SPTR32 *<i>stringptr</i>);</b> +</P> +<br><a name="SEC3" href="#TOC1">PCRE 32-BIT API AUXILIARY FUNCTIONS</a><br> +<P> +<b>pcre32_jit_stack *pcre32_jit_stack_alloc(int <i>startsize</i>, int <i>maxsize</i>);</b> +</P> +<P> +<b>void pcre32_jit_stack_free(pcre32_jit_stack *<i>stack</i>);</b> +</P> +<P> +<b>void pcre32_assign_jit_stack(pcre32_extra *<i>extra</i>,</b> +<b>pcre32_jit_callback <i>callback</i>, void *<i>data</i>);</b> +</P> +<P> +<b>const unsigned char *pcre32_maketables(void);</b> +</P> +<P> +<b>int pcre32_fullinfo(const pcre32 *<i>code</i>, const pcre32_extra *<i>extra</i>,</b> +<b>int <i>what</i>, void *<i>where</i>);</b> +</P> +<P> +<b>int pcre32_refcount(pcre32 *<i>code</i>, int <i>adjust</i>);</b> +</P> +<P> +<b>int pcre32_config(int <i>what</i>, void *<i>where</i>);</b> +</P> +<P> +<b>const char *pcre32_version(void);</b> +</P> +<P> +<b>int pcre32_pattern_to_host_byte_order(pcre32 *<i>code</i>,</b> +<b>pcre32_extra *<i>extra</i>, const unsigned char *<i>tables</i>);</b> +</P> +<br><a name="SEC4" href="#TOC1">PCRE 32-BIT API INDIRECTED FUNCTIONS</a><br> +<P> +<b>void *(*pcre32_malloc)(size_t);</b> +</P> +<P> +<b>void (*pcre32_free)(void *);</b> +</P> +<P> +<b>void *(*pcre32_stack_malloc)(size_t);</b> +</P> +<P> +<b>void (*pcre32_stack_free)(void *);</b> +</P> +<P> +<b>int (*pcre32_callout)(pcre32_callout_block *);</b> +</P> +<br><a name="SEC5" href="#TOC1">PCRE 32-BIT API 32-BIT-ONLY FUNCTION</a><br> +<P> +<b>int pcre32_utf32_to_host_byte_order(PCRE_UCHAR32 *<i>output</i>,</b> +<b>PCRE_SPTR32 <i>input</i>, int <i>length</i>, int *<i>byte_order</i>,</b> +<b>int <i>keep_boms</i>);</b> +</P> +<br><a name="SEC6" href="#TOC1">THE PCRE 32-BIT LIBRARY</a><br> +<P> +Starting with release 8.32, it is possible to compile a PCRE library that +supports 32-bit character strings, including UTF-32 strings, as well as or +instead of the original 8-bit library. This work was done by Christian Persch, +based on the work done by Zoltan Herczeg for the 16-bit library. All three +libraries contain identical sets of functions, used in exactly the same way. +Only the names of the functions and the data types of their arguments and +results are different. To avoid over-complication and reduce the documentation +maintenance load, most of the PCRE documentation describes the 8-bit library, +with only occasional references to the 16-bit and 32-bit libraries. This page +describes what is different when you use the 32-bit library. +</P> +<P> +WARNING: A single application can be linked with all or any of the three +libraries, but you must take care when processing any particular pattern +to use functions from just one library. For example, if you want to study +a pattern that was compiled with <b>pcre32_compile()</b>, you must do so +with <b>pcre32_study()</b>, not <b>pcre_study()</b>, and you must free the +study data with <b>pcre32_free_study()</b>. +</P> +<br><a name="SEC7" href="#TOC1">THE HEADER FILE</a><br> +<P> +There is only one header file, <b>pcre.h</b>. It contains prototypes for all the +functions in both libraries, as well as definitions of flags, structures, error +codes, etc. +</P> +<br><a name="SEC8" href="#TOC1">THE LIBRARY NAME</a><br> +<P> +In Unix-like systems, the 32-bit library is called <b>libpcre32</b>, and can +normally be accesss by adding <b>-lpcre32</b> to the command for linking an +application that uses PCRE. +</P> +<br><a name="SEC9" href="#TOC1">STRING TYPES</a><br> +<P> +In the 8-bit library, strings are passed to PCRE library functions as vectors +of bytes with the C type "char *". In the 32-bit library, strings are passed as +vectors of unsigned 32-bit quantities. The macro PCRE_UCHAR32 specifies an +appropriate data type, and PCRE_SPTR32 is defined as "const PCRE_UCHAR32 *". In +very many environments, "unsigned int" is a 32-bit data type. When PCRE is built, +it defines PCRE_UCHAR32 as "unsigned int", but checks that it really is a 32-bit +data type. If it is not, the build fails with an error message telling the +maintainer to modify the definition appropriately. +</P> +<br><a name="SEC10" href="#TOC1">STRUCTURE TYPES</a><br> +<P> +The types of the opaque structures that are used for compiled 32-bit patterns +and JIT stacks are <b>pcre32</b> and <b>pcre32_jit_stack</b> respectively. The +type of the user-accessible structure that is returned by <b>pcre32_study()</b> +is <b>pcre32_extra</b>, and the type of the structure that is used for passing +data to a callout function is <b>pcre32_callout_block</b>. These structures +contain the same fields, with the same names, as their 8-bit counterparts. The +only difference is that pointers to character strings are 32-bit instead of +8-bit types. +</P> +<br><a name="SEC11" href="#TOC1">32-BIT FUNCTIONS</a><br> +<P> +For every function in the 8-bit library there is a corresponding function in +the 32-bit library with a name that starts with <b>pcre32_</b> instead of +<b>pcre_</b>. The prototypes are listed above. In addition, there is one extra +function, <b>pcre32_utf32_to_host_byte_order()</b>. This is a utility function +that converts a UTF-32 character string to host byte order if necessary. The +other 32-bit functions expect the strings they are passed to be in host byte +order. +</P> +<P> +The <i>input</i> and <i>output</i> arguments of +<b>pcre32_utf32_to_host_byte_order()</b> may point to the same address, that is, +conversion in place is supported. The output buffer must be at least as long as +the input. +</P> +<P> +The <i>length</i> argument specifies the number of 32-bit data units in the +input string; a negative value specifies a zero-terminated string. +</P> +<P> +If <i>byte_order</i> is NULL, it is assumed that the string starts off in host +byte order. This may be changed by byte-order marks (BOMs) anywhere in the +string (commonly as the first character). +</P> +<P> +If <i>byte_order</i> is not NULL, a non-zero value of the integer to which it +points means that the input starts off in host byte order, otherwise the +opposite order is assumed. Again, BOMs in the string can change this. The final +byte order is passed back at the end of processing. +</P> +<P> +If <i>keep_boms</i> is not zero, byte-order mark characters (0xfeff) are copied +into the output string. Otherwise they are discarded. +</P> +<P> +The result of the function is the number of 32-bit units placed into the output +buffer, including the zero terminator if the string was zero-terminated. +</P> +<br><a name="SEC12" href="#TOC1">SUBJECT STRING OFFSETS</a><br> +<P> +The offsets within subject strings that are returned by the matching functions +are in 32-bit units rather than bytes. +</P> +<br><a name="SEC13" href="#TOC1">NAMED SUBPATTERNS</a><br> +<P> +The name-to-number translation table that is maintained for named subpatterns +uses 32-bit characters. The <b>pcre32_get_stringtable_entries()</b> function +returns the length of each entry in the table as the number of 32-bit data +units. +</P> +<br><a name="SEC14" href="#TOC1">OPTION NAMES</a><br> +<P> +There are two new general option names, PCRE_UTF32 and PCRE_NO_UTF32_CHECK, +which correspond to PCRE_UTF8 and PCRE_NO_UTF8_CHECK in the 8-bit library. In +fact, these new options define the same bits in the options word. There is a +discussion about the +<a href="pcreunicode.html#utf32strings">validity of UTF-32 strings</a> +in the +<a href="pcreunicode.html"><b>pcreunicode</b></a> +page. +</P> +<P> +For the <b>pcre32_config()</b> function there is an option PCRE_CONFIG_UTF32 +that returns 1 if UTF-32 support is configured, otherwise 0. If this option is +given to <b>pcre_config()</b> or <b>pcre16_config()</b>, or if the +PCRE_CONFIG_UTF8 or PCRE_CONFIG_UTF16 option is given to <b>pcre32_config()</b>, +the result is the PCRE_ERROR_BADOPTION error. +</P> +<br><a name="SEC15" href="#TOC1">CHARACTER CODES</a><br> +<P> +In 32-bit mode, when PCRE_UTF32 is not set, character values are treated in the +same way as in 8-bit, non UTF-8 mode, except, of course, that they can range +from 0 to 0x7fffffff instead of 0 to 0xff. Character types for characters less +than 0xff can therefore be influenced by the locale in the same way as before. +Characters greater than 0xff have only one case, and no "type" (such as letter +or digit). +</P> +<P> +In UTF-32 mode, the character code is Unicode, in the range 0 to 0x10ffff, with +the exception of values in the range 0xd800 to 0xdfff because those are +"surrogate" values that are ill-formed in UTF-32. +</P> +<P> +A UTF-32 string can indicate its endianness by special code knows as a +byte-order mark (BOM). The PCRE functions do not handle this, expecting strings +to be in host byte order. A utility function called +<b>pcre32_utf32_to_host_byte_order()</b> is provided to help with this (see +above). +</P> +<br><a name="SEC16" href="#TOC1">ERROR NAMES</a><br> +<P> +The error PCRE_ERROR_BADUTF32 corresponds to its 8-bit counterpart. +The error PCRE_ERROR_BADMODE is given when a compiled +pattern is passed to a function that processes patterns in the other +mode, for example, if a pattern compiled with <b>pcre_compile()</b> is passed to +<b>pcre32_exec()</b>. +</P> +<P> +There are new error codes whose names begin with PCRE_UTF32_ERR for invalid +UTF-32 strings, corresponding to the PCRE_UTF8_ERR codes for UTF-8 strings that +are described in the section entitled +<a href="pcreapi.html#badutf8reasons">"Reason codes for invalid UTF-8 strings"</a> +in the main +<a href="pcreapi.html"><b>pcreapi</b></a> +page. The UTF-32 errors are: +<pre> + PCRE_UTF32_ERR1 Surrogate character (range from 0xd800 to 0xdfff) + PCRE_UTF32_ERR2 Non-character + PCRE_UTF32_ERR3 Character > 0x10ffff +</PRE> +</P> +<br><a name="SEC17" href="#TOC1">ERROR TEXTS</a><br> +<P> +If there is an error while compiling a pattern, the error text that is passed +back by <b>pcre32_compile()</b> or <b>pcre32_compile2()</b> is still an 8-bit +character string, zero-terminated. +</P> +<br><a name="SEC18" href="#TOC1">CALLOUTS</a><br> +<P> +The <i>subject</i> and <i>mark</i> fields in the callout block that is passed to +a callout function point to 32-bit vectors. +</P> +<br><a name="SEC19" href="#TOC1">TESTING</a><br> +<P> +The <b>pcretest</b> program continues to operate with 8-bit input and output +files, but it can be used for testing the 32-bit library. If it is run with the +command line option <b>-32</b>, patterns and subject strings are converted from +8-bit to 32-bit before being passed to PCRE, and the 32-bit library functions +are used instead of the 8-bit ones. Returned 32-bit strings are converted to +8-bit for output. If both the 8-bit and the 16-bit libraries were not compiled, +<b>pcretest</b> defaults to 32-bit and the <b>-32</b> option is ignored. +</P> +<P> +When PCRE is being built, the <b>RunTest</b> script that is called by "make +check" uses the <b>pcretest</b> <b>-C</b> option to discover which of the 8-bit, +16-bit and 32-bit libraries has been built, and runs the tests appropriately. +</P> +<br><a name="SEC20" href="#TOC1">NOT SUPPORTED IN 32-BIT MODE</a><br> +<P> +Not all the features of the 8-bit library are available with the 32-bit +library. The C++ and POSIX wrapper functions support only the 8-bit library, +and the <b>pcregrep</b> program is at present 8-bit only. +</P> +<br><a name="SEC21" href="#TOC1">AUTHOR</a><br> +<P> +Philip Hazel +<br> +University Computing Service +<br> +Cambridge CB2 3QH, England. +<br> +</P> +<br><a name="SEC22" href="#TOC1">REVISION</a><br> +<P> +Last updated: 24 June 2012 +<br> +Copyright © 1997-2012 University of Cambridge. +<br> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/doc/html/pcre_assign_jit_stack.html b/doc/html/pcre_assign_jit_stack.html index 8dca1e7..d77d4e1 100644 --- a/doc/html/pcre_assign_jit_stack.html +++ b/doc/html/pcre_assign_jit_stack.html @@ -26,15 +26,19 @@ SYNOPSIS <b>void pcre16_assign_jit_stack(pcre16_extra *<i>extra</i>,</b> <b>pcre16_jit_callback <i>callback</i>, void *<i>data</i>);</b> </P> +<P> +<b>void pcre32_assign_jit_stack(pcre32_extra *<i>extra</i>,</b> +<b>pcre32_jit_callback <i>callback</i>, void *<i>data</i>);</b> +</P> <br><b> DESCRIPTION </b><br> <P> This function provides control over the memory used as a stack at run-time by a -call to <b>pcre[16]_exec()</b> with a pattern that has been successfully +call to <b>pcre[16|32]_exec()</b> with a pattern that has been successfully compiled with JIT optimization. The arguments are: <pre> - extra the data pointer returned by <b>pcre[16]_study()</b> + extra the data pointer returned by <b>pcre[16|32]_study()</b> callback a callback function data a JIT stack or a value to be passed to the callback function @@ -46,13 +50,13 @@ the machine stack is used. </P> <P> If <i>callback</i> is NULL and <i>data</i> is not NULL, <i>data</i> must -be a valid JIT stack, the result of calling <b>pcre[16]_jit_stack_alloc()</b>. +be a valid JIT stack, the result of calling <b>pcre[16|32]_jit_stack_alloc()</b>. </P> <P> If <i>callback</i> not NULL, it is called with <i>data</i> as an argument at the start of matching, in order to set up a JIT stack. If the result is NULL, the internal 32K stack is used; otherwise the return value must be a valid JIT -stack, the result of calling <b>pcre[16]_jit_stack_alloc()</b>. +stack, the result of calling <b>pcre[16|32]_jit_stack_alloc()</b>. </P> <P> You may safely assign the same JIT stack to multiple patterns, as long as they diff --git a/doc/html/pcre_compile.html b/doc/html/pcre_compile.html index fd48b44..0121475 100644 --- a/doc/html/pcre_compile.html +++ b/doc/html/pcre_compile.html @@ -28,12 +28,17 @@ SYNOPSIS <b>const char **<i>errptr</i>, int *<i>erroffset</i>,</b> <b>const unsigned char *<i>tableptr</i>);</b> </P> +<P> +<b>pcre32 *pcre32_compile(PCRE_SPTR32 <i>pattern</i>, int <i>options</i>,</b> +<b>const char **<i>errptr</i>, int *<i>erroffset</i>,</b> +<b>const unsigned char *<i>tableptr</i>);</b> +</P> <br><b> DESCRIPTION </b><br> <P> This function compiles a regular expression into an internal form. It is the -same as <b>pcre[16]_compile2()</b>, except for the absence of the +same as <b>pcre[16|32]_compile2()</b>, except for the absence of the <i>errorcodeptr</i> argument. Its arguments are: <pre> <i>pattern</i> A zero-terminated string containing the @@ -71,16 +76,20 @@ The option bits are: PCRE_NO_UTF16_CHECK Do not check the pattern for UTF-16 validity (only relevant if PCRE_UTF16 is set) + PCRE_NO_UTF32_CHECK Do not check the pattern for UTF-32 + validity (only relevant if + PCRE_UTF32 is set) PCRE_NO_UTF8_CHECK Do not check the pattern for UTF-8 validity (only relevant if PCRE_UTF8 is set) PCRE_UCP Use Unicode properties for \d, \w, etc. PCRE_UNGREEDY Invert greediness of quantifiers PCRE_UTF16 Run in <b>pcre16_compile()</b> UTF-16 mode + PCRE_UTF32 Run in <b>pcre32_compile()</b> UTF-32 mode PCRE_UTF8 Run in <b>pcre_compile()</b> UTF-8 mode </pre> -PCRE must be built with UTF support in order to use PCRE_UTF8/16 and -PCRE_NO_UTF8/16_CHECK, and with UCP support if PCRE_UCP is used. +PCRE must be built with UTF support in order to use PCRE_UTF8/16/32 and +PCRE_NO_UTF8/16/32_CHECK, and with UCP support if PCRE_UCP is used. </P> <P> The yield of the function is a pointer to a private data structure that diff --git a/doc/html/pcre_compile2.html b/doc/html/pcre_compile2.html index 9c177b6..7d76bd9 100644 --- a/doc/html/pcre_compile2.html +++ b/doc/html/pcre_compile2.html @@ -30,12 +30,18 @@ SYNOPSIS <b>const char **<i>errptr</i>, int *<i>erroffset</i>,</b> <b>const unsigned char *<i>tableptr</i>);</b> </P> +<P> +<b>pcre32 *pcre32_compile2(PCRE_SPTR32 <i>pattern</i>, int <i>options</i>,</b> +<b>int *<i>errorcodeptr</i>,</b> +<b>const char **<i>errptr</i>, int *<i>erroffset</i>,</b> +<b>const unsigned char *<i>tableptr</i>);</b> +</P> <br><b> DESCRIPTION </b><br> <P> This function compiles a regular expression into an internal form. It is the -same as <b>pcre[16]_compile()</b>, except for the addition of the +same as <b>pcre[16|32]_compile()</b>, except for the addition of the <i>errorcodeptr</i> argument. The arguments are: <pre> <i>pattern</i> A zero-terminated string containing the @@ -74,16 +80,20 @@ The option bits are: PCRE_NO_UTF16_CHECK Do not check the pattern for UTF-16 validity (only relevant if PCRE_UTF16 is set) + PCRE_NO_UTF32_CHECK Do not check the pattern for UTF-32 + validity (only relevant if + PCRE_UTF32 is set) PCRE_NO_UTF8_CHECK Do not check the pattern for UTF-8 validity (only relevant if PCRE_UTF8 is set) PCRE_UCP Use Unicode properties for \d, \w, etc. PCRE_UNGREEDY Invert greediness of quantifiers PCRE_UTF16 Run <b>pcre16_compile()</b> in UTF-16 mode + PCRE_UTF32 Run <b>pcre32_compile()</b> in UTF-32 mode PCRE_UTF8 Run <b>pcre_compile()</b> in UTF-8 mode </pre> -PCRE must be built with UTF support in order to use PCRE_UTF8/16 and -PCRE_NO_UTF8/16_CHECK, and with UCP support if PCRE_UCP is used. +PCRE must be built with UTF support in order to use PCRE_UTF8/16/32 and +PCRE_NO_UTF8/16/32_CHECK, and with UCP support if PCRE_UCP is used. </P> <P> The yield of the function is a pointer to a private data structure that diff --git a/doc/html/pcre_config.html b/doc/html/pcre_config.html index dcfb831..fc10d18 100644 --- a/doc/html/pcre_config.html +++ b/doc/html/pcre_config.html @@ -24,6 +24,9 @@ SYNOPSIS <P> <b>int pcre16_config(int <i>what</i>, void *<i>where</i>);</b> </P> +<P> +<b>int pcre32_config(int <i>what</i>, void *<i>where</i>);</b> +</P> <br><b> DESCRIPTION </b><br> @@ -63,6 +66,8 @@ point to an unsigned long integer. The available codes are: PCRE_CONFIG_STACKRECURSE Recursion implementation (1=stack 0=heap) PCRE_CONFIG_UTF16 Availability of UTF-16 support (1=yes 0=no); option for <b>pcre16_config()</b> + PCRE_CONFIG_UTF32 Availability of UTF-32 support (1=yes + 0=no); option for <b>pcre32_config()</b> PCRE_CONFIG_UTF8 Availability of UTF-8 support (1=yes 0=no); option for <b>pcre_config()</b> PCRE_CONFIG_UNICODE_PROPERTIES @@ -70,8 +75,10 @@ point to an unsigned long integer. The available codes are: (1=yes 0=no) </pre> The function yields 0 on success or PCRE_ERROR_BADOPTION otherwise. That error -is also given if PCRE_CONFIG_UTF16 is passed to <b>pcre_config()</b> or if -PCRE_CONFIG_UTF8 is passed to <b>pcre16_config()</b>. +is also given if PCRE_CONFIG_UTF16 or PCRE_CONFIG_UTF32 is passed to +<b>pcre_config()</b>, if PCRE_CONFIG_UTF8 or PCRE_CONFIG_UTF32 is passed to +<b>pcre16_config()</b>, or if PCRE_CONFIG_UTF8 or PCRE_CONFIG_UTF16 is passed to +<b>pcre32_config()</b>. </P> <P> There is a complete description of the PCRE native API in the diff --git a/doc/html/pcre_copy_named_substring.html b/doc/html/pcre_copy_named_substring.html index 40293e5..ae4f690 100644 --- a/doc/html/pcre_copy_named_substring.html +++ b/doc/html/pcre_copy_named_substring.html @@ -30,6 +30,12 @@ SYNOPSIS <b>int <i>stringcount</i>, PCRE_SPTR16 <i>stringname</i>,</b> <b>PCRE_UCHAR16 *<i>buffer</i>, int <i>buffersize</i>);</b> </P> +<P> +<b>int pcre32_copy_named_substring(const pcre32 *<i>code</i>,</b> +<b>PCRE_SPTR32 <i>subject</i>, int *<i>ovector</i>,</b> +<b>int <i>stringcount</i>, PCRE_SPTR32 <i>stringname</i>,</b> +<b>PCRE_UCHAR32 *<i>buffer</i>, int <i>buffersize</i>);</b> +</P> <br><b> DESCRIPTION </b><br> @@ -39,8 +45,8 @@ by name, into a given buffer. The arguments are: <pre> <i>code</i> Pattern that was successfully matched <i>subject</i> Subject that has been successfully matched - <i>ovector</i> Offset vector that <b>pcre[16]_exec()</b> used - <i>stringcount</i> Value returned by <b>pcre[16]_exec()</b> + <i>ovector</i> Offset vector that <b>pcre[16|32]_exec()</b> used + <i>stringcount</i> Value returned by <b>pcre[16|32]_exec()</b> <i>stringname</i> Name of the required substring <i>buffer</i> Buffer to receive the string <i>buffersize</i> Size of buffer diff --git a/doc/html/pcre_copy_substring.html b/doc/html/pcre_copy_substring.html index 12a5db4..12bfb63 100644 --- a/doc/html/pcre_copy_substring.html +++ b/doc/html/pcre_copy_substring.html @@ -28,6 +28,11 @@ SYNOPSIS <b>int <i>stringcount</i>, int <i>stringnumber</i>, PCRE_UCHAR16 *<i>buffer</i>,</b> <b>int <i>buffersize</i>);</b> </P> +<P> +<b>int pcre32_copy_substring(PCRE_SPTR32 <i>subject</i>, int *<i>ovector</i>,</b> +<b>int <i>stringcount</i>, int <i>stringnumber</i>, PCRE_UCHAR32 *<i>buffer</i>,</b> +<b>int <i>buffersize</i>);</b> +</P> <br><b> DESCRIPTION </b><br> @@ -36,8 +41,8 @@ This is a convenience function for extracting a captured substring into a given buffer. The arguments are: <pre> <i>subject</i> Subject that has been successfully matched - <i>ovector</i> Offset vector that <b>pcre[16]_exec()</b> used - <i>stringcount</i> Value returned by <b>pcre[16]_exec()</b> + <i>ovector</i> Offset vector that <b>pcre[16|32]_exec()</b> used + <i>stringcount</i> Value returned by <b>pcre[16|32]_exec()</b> <i>stringnumber</i> Number of the required substring <i>buffer</i> Buffer to receive the string <i>buffersize</i> Size of buffer diff --git a/doc/html/pcre_dfa_exec.html b/doc/html/pcre_dfa_exec.html index 76a1baa..663e1d0 100644 --- a/doc/html/pcre_dfa_exec.html +++ b/doc/html/pcre_dfa_exec.html @@ -30,6 +30,12 @@ SYNOPSIS <b>int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b> <b>int *<i>workspace</i>, int <i>wscount</i>);</b> </P> +<P> +<b>int pcre32_dfa_exec(const pcre32 *<i>code</i>, const pcre32_extra *<i>extra</i>,</b> +<b>PCRE_SPTR32 <i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b> +<b>int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b> +<b>int *<i>workspace</i>, int <i>wscount</i>);</b> +</P> <br><b> DESCRIPTION </b><br> @@ -37,11 +43,11 @@ DESCRIPTION This function matches a compiled regular expression against a given subject string, using an alternative matching algorithm that scans the subject string just once (<i>not</i> Perl-compatible). Note that the main, Perl-compatible, -matching function is <b>pcre[16]_exec()</b>. The arguments for this function +matching function is <b>pcre[16|32]_exec()</b>. The arguments for this function are: <pre> <i>code</i> Points to the compiled pattern - <i>extra</i> Points to an associated <b>pcre[16]_extra</b> structure, + <i>extra</i> Points to an associated <b>pcre[16|32]_extra</b> structure, or is NULL <i>subject</i> Points to the subject string <i>length</i> Length of the subject string, in bytes @@ -72,6 +78,9 @@ The options are: PCRE_NO_UTF16_CHECK Do not check the subject for UTF-16 validity (only relevant if PCRE_UTF16 was set at compile time) + PCRE_NO_UTF32_CHECK Do not check the subject for UTF-32 + validity (only relevant if PCRE_UTF32 + was set at compile time) PCRE_NO_UTF8_CHECK Do not check the subject for UTF-8 validity (only relevant if PCRE_UTF8 was set at compile time) @@ -90,10 +99,10 @@ documentation. For details of partial matching, see the page. </P> <P> -A <b>pcre[16]_extra</b> structure contains the following fields: +A <b>pcre[16|32]_extra</b> structure contains the following fields: <pre> <i>flags</i> Bits indicating which fields are set - <i>study_data</i> Opaque data from <b>pcre[16]_study()</b> + <i>study_data</i> Opaque data from <b>pcre[16|32]_study()</b> <i>match_limit</i> Limit on internal resource use <i>match_limit_recursion</i> Limit on internal recursion depth <i>callout_data</i> Opaque data passed back to callouts diff --git a/doc/html/pcre_exec.html b/doc/html/pcre_exec.html index 98f742f..e4ddf9a 100644 --- a/doc/html/pcre_exec.html +++ b/doc/html/pcre_exec.html @@ -28,6 +28,11 @@ SYNOPSIS <b>PCRE_SPTR16 <i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b> <b>int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>);</b> </P> +<P> +<b>int pcre32_exec(const pcre32 *<i>code</i>, const pcre32_extra *<i>extra</i>,</b> +<b>PCRE_SPTR32 <i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b> +<b>int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>);</b> +</P> <br><b> DESCRIPTION </b><br> @@ -37,7 +42,7 @@ string, using a matching algorithm that is similar to Perl's. It returns offsets to captured substrings. Its arguments are: <pre> <i>code</i> Points to the compiled pattern - <i>extra</i> Points to an associated <b>pcre[16]_extra</b> structure, + <i>extra</i> Points to an associated <b>pcre[16|32]_extra</b> structure, or is NULL <i>subject</i> Points to the subject string <i>length</i> Length of the subject string, in bytes @@ -66,6 +71,9 @@ The options are: PCRE_NO_UTF16_CHECK Do not check the subject for UTF-16 validity (only relevant if PCRE_UTF16 was set at compile time) + PCRE_NO_UTF32_CHECK Do not check the subject for UTF-32 + validity (only relevant if PCRE_UTF32 + was set at compile time) PCRE_NO_UTF8_CHECK Do not check the subject for UTF-8 validity (only relevant if PCRE_UTF8 was set at compile time) @@ -79,7 +87,7 @@ For details of partial matching, see the page. A <b>pcre_extra</b> structure contains the following fields: <pre> <i>flags</i> Bits indicating which fields are set - <i>study_data</i> Opaque data from <b>pcre[16]_study()</b> + <i>study_data</i> Opaque data from <b>pcre[16|32]_study()</b> <i>match_limit</i> Limit on internal resource use <i>match_limit_recursion</i> Limit on internal recursion depth <i>callout_data</i> Opaque data passed back to callouts diff --git a/doc/html/pcre_free_study.html b/doc/html/pcre_free_study.html index 1bbcffe..7f9e10e 100644 --- a/doc/html/pcre_free_study.html +++ b/doc/html/pcre_free_study.html @@ -24,12 +24,15 @@ SYNOPSIS <P> <b>void pcre16_free_study(pcre16_extra *<i>extra</i>);</b> </P> +<P> +<b>void pcre32_free_study(pcre32_extra *<i>extra</i>);</b> +</P> <br><b> DESCRIPTION </b><br> <P> This function is used to free the memory used for the data generated by a call -to <b>pcre[16]_study()</b> when it is no longer needed. The argument must be the +to <b>pcre[16|32]_study()</b> when it is no longer needed. The argument must be the result of such a call. </P> <P> diff --git a/doc/html/pcre_free_substring.html b/doc/html/pcre_free_substring.html index d820745..1fe6610 100644 --- a/doc/html/pcre_free_substring.html +++ b/doc/html/pcre_free_substring.html @@ -24,12 +24,15 @@ SYNOPSIS <P> <b>void pcre16_free_substring(PCRE_SPTR16 <i>stringptr</i>);</b> </P> +<P> +<b>void pcre32_free_substring(PCRE_SPTR32 <i>stringptr</i>);</b> +</P> <br><b> DESCRIPTION </b><br> <P> This is a convenience function for freeing the store obtained by a previous -call to <b>pcre[16]_get_substring()</b> or <b>pcre[16]_get_named_substring()</b>. +call to <b>pcre[16|32]_get_substring()</b> or <b>pcre[16|32]_get_named_substring()</b>. Its only argument is a pointer to the string. </P> <P> diff --git a/doc/html/pcre_free_substring_list.html b/doc/html/pcre_free_substring_list.html index 26e2daf..c086178 100644 --- a/doc/html/pcre_free_substring_list.html +++ b/doc/html/pcre_free_substring_list.html @@ -24,12 +24,15 @@ SYNOPSIS <P> <b>void pcre16_free_substring_list(PCRE_SPTR16 *<i>stringptr</i>);</b> </P> +<P> +<b>void pcre32_free_substring_list(PCRE_SPTR32 *<i>stringptr</i>);</b> +</P> <br><b> DESCRIPTION </b><br> <P> This is a convenience function for freeing the store obtained by a previous -call to <b>pcre[16]_get_substring_list()</b>. Its only argument is a pointer to +call to <b>pcre[16|32]_get_substring_list()</b>. Its only argument is a pointer to the list of string pointers. </P> <P> diff --git a/doc/html/pcre_fullinfo.html b/doc/html/pcre_fullinfo.html index edb6eb7..d353432 100644 --- a/doc/html/pcre_fullinfo.html +++ b/doc/html/pcre_fullinfo.html @@ -26,6 +26,10 @@ SYNOPSIS <b>int pcre16_fullinfo(const pcre16 *<i>code</i>, const pcre16_extra *<i>extra</i>,</b> <b>int <i>what</i>, void *<i>where</i>);</b> </P> +<P> +<b>int pcre32_fullinfo(const pcre32 *<i>code</i>, const pcre32_extra *<i>extra</i>,</b> +<b>int <i>what</i>, void *<i>where</i>);</b> +</P> <br><b> DESCRIPTION </b><br> @@ -33,7 +37,7 @@ DESCRIPTION This function returns information about a compiled pattern. Its arguments are: <pre> <i>code</i> Compiled regular expression - <i>extra</i> Result of <b>pcre[16]_study()</b> or NULL + <i>extra</i> Result of <b>pcre[16|32]_study()</b> or NULL <i>what</i> What information is required <i>where</i> Where to put the information </pre> @@ -61,6 +65,16 @@ The following information is available: PCRE_INFO_OPTIONS Option bits used for compilation PCRE_INFO_SIZE Size of compiled pattern PCRE_INFO_STUDYSIZE Size of study data + PCRE_INFO_FIRSTCHARACTER Fixed first data unit for a match + PCRE_INFO_FIRSTCHARACTERFLAGS Returns + 1 if there is a first data character set, which can + then be retrieved using PCRE_INFO_FIRSTCHARACTER, + 2 if the first character is at the start of the data + string or after a newline, and + 0 otherwise + PCRE_INFO_REQUIREDCHAR Literal last data unit required + PCRE_INFO_REQUIREDCHARFLAGS Returns 1 if the last data character is set (which can then + be retrieved using PCRE_INFO_REQUIREDCHAR); 0 otherwise </pre> The <i>where</i> argument must point to an integer variable, except for the following <i>what</i> values: @@ -68,9 +82,12 @@ following <i>what</i> values: PCRE_INFO_DEFAULT_TABLES const unsigned char * PCRE_INFO_FIRSTTABLE const unsigned char * PCRE_INFO_NAMETABLE PCRE_SPTR16 (16-bit library) + PCRE_INFO_NAMETABLE PCRE_SPTR32 (32-bit library) PCRE_INFO_NAMETABLE const unsigned char * (8-bit library) PCRE_INFO_OPTIONS unsigned long int PCRE_INFO_SIZE size_t + PCRE_INFO_FIRSTCHARACTER uint32_t + PCRE_INFO_REQUIREDCHAR uint32_t </pre> The yield of the function is zero on success or: <pre> diff --git a/doc/html/pcre_get_named_substring.html b/doc/html/pcre_get_named_substring.html index 5eea87c..6150ad7 100644 --- a/doc/html/pcre_get_named_substring.html +++ b/doc/html/pcre_get_named_substring.html @@ -30,6 +30,12 @@ SYNOPSIS <b>int <i>stringcount</i>, PCRE_SPTR16 <i>stringname</i>,</b> <b>PCRE_SPTR16 *<i>stringptr</i>);</b> </P> +<P> +<b>int pcre32_get_named_substring(const pcre32 *<i>code</i>,</b> +<b>PCRE_SPTR32 <i>subject</i>, int *<i>ovector</i>,</b> +<b>int <i>stringcount</i>, PCRE_SPTR32 <i>stringname</i>,</b> +<b>PCRE_SPTR32 *<i>stringptr</i>);</b> +</P> <br><b> DESCRIPTION </b><br> @@ -39,14 +45,14 @@ arguments are: <pre> <i>code</i> Compiled pattern <i>subject</i> Subject that has been successfully matched - <i>ovector</i> Offset vector that <b>pcre[16]_exec()</b> used - <i>stringcount</i> Value returned by <b>pcre[16]_exec()</b> + <i>ovector</i> Offset vector that <b>pcre[16|32]_exec()</b> used + <i>stringcount</i> Value returned by <b>pcre[16|32]_exec()</b> <i>stringname</i> Name of the required substring <i>stringptr</i> Where to put the string pointer </pre> The memory in which the substring is placed is obtained by calling -<b>pcre[16]_malloc()</b>. The convenience function -<b>pcre[16]_free_substring()</b> can be used to free it when it is no longer +<b>pcre[16|32]_malloc()</b>. The convenience function +<b>pcre[16|32]_free_substring()</b> can be used to free it when it is no longer needed. The yield of the function is the length of the extracted substring, PCRE_ERROR_NOMEMORY if sufficient memory could not be obtained, or PCRE_ERROR_NOSUBSTRING if the string name is invalid. diff --git a/doc/html/pcre_get_stringnumber.html b/doc/html/pcre_get_stringnumber.html index 1c9483a..08967de 100644 --- a/doc/html/pcre_get_stringnumber.html +++ b/doc/html/pcre_get_stringnumber.html @@ -26,6 +26,10 @@ SYNOPSIS <b>int pcre16_get_stringnumber(const pcre16 *<i>code</i>,</b> <b>PCRE_SPTR16 <i>name</i>);</b> </P> +<P> +<b>int pcre32_get_stringnumber(const pcre32 *<i>code</i>,</b> +<b>PCRE_SPTR32 <i>name</i>);</b> +</P> <br><b> DESCRIPTION </b><br> @@ -39,8 +43,8 @@ parenthesis in a compiled pattern. Its arguments are: The yield of the function is the number of the parenthesis if the name is found, or PCRE_ERROR_NOSUBSTRING otherwise. When duplicate names are allowed (PCRE_DUPNAMES is set), it is not defined which of the numbers is returned by -<b>pcre[16]_get_stringnumber()</b>. You can obtain the complete list by calling -<b>pcre[16]_get_stringtable_entries()</b>. +<b>pcre[16|32]_get_stringnumber()</b>. You can obtain the complete list by calling +<b>pcre[16|32]_get_stringtable_entries()</b>. </P> <P> There is a complete description of the PCRE native API in the diff --git a/doc/html/pcre_get_stringtable_entries.html b/doc/html/pcre_get_stringtable_entries.html index 954fb5b..38f9c0c 100644 --- a/doc/html/pcre_get_stringtable_entries.html +++ b/doc/html/pcre_get_stringtable_entries.html @@ -26,6 +26,10 @@ SYNOPSIS <b>int pcre16_get_stringtable_entries(const pcre16 *<i>code</i>,</b> <b>PCRE_SPTR16 <i>name</i>, PCRE_UCHAR16 **<i>first</i>, PCRE_UCHAR16 **<i>last</i>);</b> </P> +<P> +<b>int pcre32_get_stringtable_entries(const pcre32 *<i>code</i>,</b> +<b>PCRE_SPTR32 <i>name</i>, PCRE_UCHAR32 **<i>first</i>, PCRE_UCHAR32 **<i>last</i>);</b> +</P> <br><b> DESCRIPTION </b><br> @@ -33,7 +37,7 @@ DESCRIPTION This convenience function finds, for a compiled pattern, the first and last entries for a given name in the table that translates capturing parenthesis names into numbers. When names are required to be unique (PCRE_DUPNAMES is -<i>not</i> set), it is usually easier to use <b>pcre[16]_get_stringnumber()</b> +<i>not</i> set), it is usually easier to use <b>pcre[16|32]_get_stringnumber()</b> instead. <pre> <i>code</i> Compiled regular expression diff --git a/doc/html/pcre_get_substring.html b/doc/html/pcre_get_substring.html index 279cee6..2a5a610 100644 --- a/doc/html/pcre_get_substring.html +++ b/doc/html/pcre_get_substring.html @@ -28,6 +28,11 @@ SYNOPSIS <b>int <i>stringcount</i>, int <i>stringnumber</i>,</b> <b>PCRE_SPTR16 *<i>stringptr</i>);</b> </P> +<P> +<b>int pcre32_get_substring(PCRE_SPTR32 <i>subject</i>, int *<i>ovector</i>,</b> +<b>int <i>stringcount</i>, int <i>stringnumber</i>,</b> +<b>PCRE_SPTR32 *<i>stringptr</i>);</b> +</P> <br><b> DESCRIPTION </b><br> @@ -36,14 +41,14 @@ This is a convenience function for extracting a captured substring. The arguments are: <pre> <i>subject</i> Subject that has been successfully matched - <i>ovector</i> Offset vector that <b>pcre[16]_exec()</b> used - <i>stringcount</i> Value returned by <b>pcre[16]_exec()</b> + <i>ovector</i> Offset vector that <b>pcre[16|32]_exec()</b> used + <i>stringcount</i> Value returned by <b>pcre[16|32]_exec()</b> <i>stringnumber</i> Number of the required substring <i>stringptr</i> Where to put the string pointer </pre> The memory in which the substring is placed is obtained by calling -<b>pcre[16]_malloc()</b>. The convenience function -<b>pcre[16]_free_substring()</b> can be used to free it when it is no longer +<b>pcre[16|32]_malloc()</b>. The convenience function +<b>pcre[16|32]_free_substring()</b> can be used to free it when it is no longer needed. The yield of the function is the length of the substring, PCRE_ERROR_NOMEMORY if sufficient memory could not be obtained, or PCRE_ERROR_NOSUBSTRING if the string number is invalid. diff --git a/doc/html/pcre_get_substring_list.html b/doc/html/pcre_get_substring_list.html index 178b22e..85edef4 100644 --- a/doc/html/pcre_get_substring_list.html +++ b/doc/html/pcre_get_substring_list.html @@ -26,6 +26,10 @@ SYNOPSIS <b>int pcre16_get_substring_list(PCRE_SPTR16 <i>subject</i>,</b> <b>int *<i>ovector</i>, int <i>stringcount</i>, PCRE_SPTR16 **<i>listptr</i>);</b> </P> +<P> +<b>int pcre32_get_substring_list(PCRE_SPTR32 <i>subject</i>,</b> +<b>int *<i>ovector</i>, int <i>stringcount</i>, PCRE_SPTR32 **<i>listptr</i>);</b> +</P> <br><b> DESCRIPTION </b><br> @@ -34,13 +38,13 @@ This is a convenience function for extracting a list of all the captured substrings. The arguments are: <pre> <i>subject</i> Subject that has been successfully matched - <i>ovector</i> Offset vector that <b>pcre[16]_exec</b> used - <i>stringcount</i> Value returned by <b>pcre[16]_exec</b> + <i>ovector</i> Offset vector that <b>pcre[16|32]_exec</b> used + <i>stringcount</i> Value returned by <b>pcre[16|32]_exec</b> <i>listptr</i> Where to put a pointer to the list </pre> The memory in which the substrings and the list are placed is obtained by -calling <b>pcre[16]_malloc()</b>. The convenience function -<b>pcre[16]_free_substring_list()</b> can be used to free it when it is no +calling <b>pcre[16|32]_malloc()</b>. The convenience function +<b>pcre[16|32]_free_substring_list()</b> can be used to free it when it is no longer needed. A pointer to a list of pointers is put in the variable whose address is in <i>listptr</i>. The list is terminated by a NULL pointer. The yield of the function is zero on success or PCRE_ERROR_NOMEMORY if sufficient diff --git a/doc/html/pcre_jit_exec.html b/doc/html/pcre_jit_exec.html new file mode 100644 index 0000000..4f6dfbb --- /dev/null +++ b/doc/html/pcre_jit_exec.html @@ -0,0 +1,108 @@ +<html> +<head> +<title>pcre_jit_exec specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre_jit_exec man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +SYNOPSIS +</b><br> +<P> +<b>#include <pcre.h></b> +</P> +<P> +<b>int pcre_jit_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b> +<b>const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b> +<b>int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b> +<b>pcre_jit_stack *<i>jstack</i>);</b> +</P> +<P> +<b>int pcre16_jit_exec(const pcre16 *<i>code</i>, const pcre16_extra *<i>extra</i>,</b> +<b>PCRE_SPTR16 <i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b> +<b>int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b> +<b>pcre_jit_stack *<i>jstack</i>);</b> +</P> +<P> +<b>int pcre32_jit_exec(const pcre32 *<i>code</i>, const pcre32_extra *<i>extra</i>,</b> +<b>PCRE_SPTR32 <i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b> +<b>int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b> +<b>pcre_jit_stack *<i>jstack</i>);</b> +</P> +<br><b> +DESCRIPTION +</b><br> +<P> +This function matches a compiled regular expression that has been successfully +studied with one of the JIT options against a given subject string, using a +matching algorithm that is similar to Perl's. It is a "fast path" interface to +JIT, and it bypasses some of the sanity checks that <b>pcre_exec()</b> applies. +It returns offsets to captured substrings. Its arguments are: +<pre> + <i>code</i> Points to the compiled pattern + <i>extra</i> Points to an associated <b>pcre[16|32]_extra</b> structure, + or is NULL + <i>subject</i> Points to the subject string + <i>length</i> Length of the subject string, in bytes + <i>startoffset</i> Offset in bytes in the subject at which to + start matching + <i>options</i> Option bits + <i>ovector</i> Points to a vector of ints for result offsets + <i>ovecsize</i> Number of elements in the vector (a multiple of 3) + <i>jstack</i> Pointer to a JIT stack +</pre> +The allowed options are: +<pre> + PCRE_NOTBOL Subject string is not the beginning of a line + PCRE_NOTEOL Subject string is not the end of a line + PCRE_NOTEMPTY An empty string is not a valid match + PCRE_NOTEMPTY_ATSTART An empty string at the start of the subject + is not a valid match + PCRE_NO_UTF16_CHECK Do not check the subject for UTF-16 + validity (only relevant if PCRE_UTF16 + was set at compile time) + PCRE_NO_UTF32_CHECK Do not check the subject for UTF-32 + validity (only relevant if PCRE_UTF32 + was set at compile time) + PCRE_NO_UTF8_CHECK Do not check the subject for UTF-8 + validity (only relevant if PCRE_UTF8 + was set at compile time) + PCRE_PARTIAL ) Return PCRE_ERROR_PARTIAL for a partial + PCRE_PARTIAL_SOFT ) match if no full matches are found + PCRE_PARTIAL_HARD Return PCRE_ERROR_PARTIAL for a partial match + if that is found before a full match +</pre> +However, the PCRE_NO_UTF[8|16|32]_CHECK options have no effect, as this check +is never applied. For details of partial matching, see the +<a href="pcrepartial.html"><b>pcrepartial</b></a> +page. A <b>pcre_extra</b> structure contains the following fields: +<pre> + <i>flags</i> Bits indicating which fields are set + <i>study_data</i> Opaque data from <b>pcre[16|32]_study()</b> + <i>match_limit</i> Limit on internal resource use + <i>match_limit_recursion</i> Limit on internal recursion depth + <i>callout_data</i> Opaque data passed back to callouts + <i>tables</i> Points to character tables or is NULL + <i>mark</i> For passing back a *MARK pointer + <i>executable_jit</i> Opaque data from JIT compilation +</pre> +The flag bits are PCRE_EXTRA_STUDY_DATA, PCRE_EXTRA_MATCH_LIMIT, +PCRE_EXTRA_MATCH_LIMIT_RECURSION, PCRE_EXTRA_CALLOUT_DATA, +PCRE_EXTRA_TABLES, PCRE_EXTRA_MARK and PCRE_EXTRA_EXECUTABLE_JIT. +</P> +<P> +There is a complete description of the PCRE native API in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page and a description of the JIT API in the +<a href="pcrejit.html"><b>pcrejit</b></a> +page. +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/doc/html/pcre_jit_stack_alloc.html b/doc/html/pcre_jit_stack_alloc.html index a3a939f..4153ee5 100644 --- a/doc/html/pcre_jit_stack_alloc.html +++ b/doc/html/pcre_jit_stack_alloc.html @@ -26,14 +26,18 @@ SYNOPSIS <b>pcre16_jit_stack *pcre16_jit_stack_alloc(int <i>startsize</i>,</b> <b>int <i>maxsize</i>);</b> </P> +<P> +<b>pcre32_jit_stack *pcre32_jit_stack_alloc(int <i>startsize</i>,</b> +<b>int <i>maxsize</i>);</b> +</P> <br><b> DESCRIPTION </b><br> <P> This function is used to create a stack for use by the code compiled by the JIT -optimization of <b>pcre[16]_study()</b>. The arguments are a starting size for +optimization of <b>pcre[16|32]_study()</b>. The arguments are a starting size for the stack, and a maximum size to which it is allowed to grow. The result can be -passed to the JIT run-time code by <b>pcre[16]_assign_jit_stack()</b>, or that +passed to the JIT run-time code by <b>pcre[16|32]_assign_jit_stack()</b>, or that function can set up a callback for obtaining a stack. A maximum stack size of 512K to 1M should be more than enough for any pattern. For more details, see the diff --git a/doc/html/pcre_jit_stack_free.html b/doc/html/pcre_jit_stack_free.html index ecbf5d0..8bd06e4 100644 --- a/doc/html/pcre_jit_stack_free.html +++ b/doc/html/pcre_jit_stack_free.html @@ -24,12 +24,15 @@ SYNOPSIS <P> <b>void pcre16_jit_stack_free(pcre16_jit_stack *<i>stack</i>);</b> </P> +<P> +<b>void pcre32_jit_stack_free(pcre32_jit_stack *<i>stack</i>);</b> +</P> <br><b> DESCRIPTION </b><br> <P> This function is used to free a JIT stack that was created by -<b>pcre[16]_jit_stack_alloc()</b> when it is no longer needed. For more details, +<b>pcre[16|32]_jit_stack_alloc()</b> when it is no longer needed. For more details, see the <a href="pcrejit.html"><b>pcrejit</b></a> page. diff --git a/doc/html/pcre_maketables.html b/doc/html/pcre_maketables.html index a4be6b1..3a7b5eb 100644 --- a/doc/html/pcre_maketables.html +++ b/doc/html/pcre_maketables.html @@ -24,13 +24,16 @@ SYNOPSIS <P> <b>const unsigned char *pcre16_maketables(void);</b> </P> +<P> +<b>const unsigned char *pcre32_maketables(void);</b> +</P> <br><b> DESCRIPTION </b><br> <P> This function builds a set of character tables for character values less than -256. These can be passed to <b>pcre[16]_compile()</b> to override PCRE's -internal, built-in tables (which were made by <b>pcre[16]_maketables()</b> when +256. These can be passed to <b>pcre[16|32]_compile()</b> to override PCRE's +internal, built-in tables (which were made by <b>pcre[16|32]_maketables()</b> when PCRE was compiled). You might want to do this if you are using a non-standard locale. The function yields a pointer to the tables. </P> diff --git a/doc/html/pcre_pattern_to_host_byte_order.html b/doc/html/pcre_pattern_to_host_byte_order.html index 2fb7f10..68d6f5a 100644 --- a/doc/html/pcre_pattern_to_host_byte_order.html +++ b/doc/html/pcre_pattern_to_host_byte_order.html @@ -26,6 +26,10 @@ SYNOPSIS <b>int pcre16_pattern_to_host_byte_order(pcre16 *<i>code</i>,</b> <b>pcre16_extra *<i>extra</i>, const unsigned char *<i>tables</i>);</b> </P> +<P> +<b>int pcre32_pattern_to_host_byte_order(pcre32 *<i>code</i>,</b> +<b>pcre32_extra *<i>extra</i>, const unsigned char *<i>tables</i>);</b> +</P> <br><b> DESCRIPTION </b><br> @@ -36,7 +40,7 @@ pattern that has been compiled on one host is transferred to another that might have different endianness. The arguments are: <pre> <i>code</i> A compiled regular expression - <i>extra</i> Points to an associated <b>pcre[16]_extra</b> structure, + <i>extra</i> Points to an associated <b>pcre[16|32]_extra</b> structure, or is NULL <i>tables</i> Pointer to character tables, or NULL to set the built-in default diff --git a/doc/html/pcre_refcount.html b/doc/html/pcre_refcount.html index a2af821..bfb92e6 100644 --- a/doc/html/pcre_refcount.html +++ b/doc/html/pcre_refcount.html @@ -24,6 +24,9 @@ SYNOPSIS <P> <b>int pcre16_refcount(pcre16 *<i>code</i>, int <i>adjust</i>);</b> </P> +<P> +<b>int pcre32_refcount(pcre32 *<i>code</i>, int <i>adjust</i>);</b> +</P> <br><b> DESCRIPTION </b><br> diff --git a/doc/html/pcre_study.html b/doc/html/pcre_study.html index ab56c62..2baf54c 100644 --- a/doc/html/pcre_study.html +++ b/doc/html/pcre_study.html @@ -26,6 +26,10 @@ SYNOPSIS <b>pcre16_extra *pcre16_study(const pcre16 *<i>code</i>, int <i>options</i>,</b> <b>const char **<i>errptr</i>);</b> </P> +<P> +<b>pcre32_extra *pcre32_study(const pcre32 *<i>code</i>, int <i>options</i>,</b> +<b>const char **<i>errptr</i>);</b> +</P> <br><b> DESCRIPTION </b><br> @@ -34,11 +38,11 @@ This function studies a compiled pattern, to see if additional information can be extracted that might speed up matching. Its arguments are: <pre> <i>code</i> A compiled regular expression - <i>options</i> Options for <b>pcre[16]_study()</b> + <i>options</i> Options for <b>pcre[16|32]_study()</b> <i>errptr</i> Where to put an error message </pre> If the function succeeds, it returns a value that can be passed to -<b>pcre[16]_exec()</b> or <b>pcre[16]_dfa_exec()</b> via their <i>extra</i> +<b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b> via their <i>extra</i> arguments. </P> <P> diff --git a/doc/html/pcre_utf32_to_host_byte_order.html b/doc/html/pcre_utf32_to_host_byte_order.html new file mode 100644 index 0000000..967c00d --- /dev/null +++ b/doc/html/pcre_utf32_to_host_byte_order.html @@ -0,0 +1,57 @@ +<html> +<head> +<title>pcre_utf32_to_host_byte_order specification</title> +</head> +<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> +<h1>pcre_utf32_to_host_byte_order man page</h1> +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> +<p> +This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +<br> +<br><b> +SYNOPSIS +</b><br> +<P> +<b>#include <pcre.h></b> +</P> +<P> +<b>int pcre32_utf32_to_host_byte_order(PCRE_UCHAR32 *<i>output</i>,</b> +<b>PCRE_SPTR32 <i>input</i>, int <i>length</i>, int *<i>host_byte_order</i>,</b> +<b>int <i>keep_boms</i>);</b> +</P> +<br><b> +DESCRIPTION +</b><br> +<P> +This function, which exists only in the 32-bit library, converts a UTF-32 +string to the correct order for the current host, taking account of any byte +order marks (BOMs) within the string. Its arguments are: +<pre> + <i>output</i> pointer to output buffer, may be the same as <i>input</i> + <i>input</i> pointer to input buffer + <i>length</i> number of 32-bit units in the input, or negative for + a zero-terminated string + <i>host_byte_order</i> a NULL value or a non-zero value pointed to means + start in host byte order + <i>keep_boms</i> if non-zero, BOMs are copied to the output string +</pre> +The result of the function is the number of 32-bit units placed into the output +buffer, including the zero terminator if the string was zero-terminated. +</P> +<P> +If <i>host_byte_order</i> is not NULL, it is set to indicate the byte order that +is current at the end of the string. +</P> +<P> +There is a complete description of the PCRE native API in the +<a href="pcreapi.html"><b>pcreapi</b></a> +page and a description of the POSIX API in the +<a href="pcreposix.html"><b>pcreposix</b></a> +page. +<p> +Return to the <a href="index.html">PCRE index page</a>. +</p> diff --git a/doc/html/pcre_version.html b/doc/html/pcre_version.html index 6b6a8ab..d33e718 100644 --- a/doc/html/pcre_version.html +++ b/doc/html/pcre_version.html @@ -24,13 +24,16 @@ SYNOPSIS <P> <b>const char *pcre16_version(void);</b> </P> +<P> +<b>const char *pcre32_version(void);</b> +</P> <br><b> DESCRIPTION </b><br> <P> -This function (even in the 16-bit library) returns a zero-terminated, 8-bit -character string that gives the version number of the PCRE library and the date -of its release. +This function (even in the 16-bit and 32-bit libraries) returns a +zero-terminated, 8-bit character string that gives the version number of the +PCRE library and the date of its release. </P> <P> There is a complete description of the PCRE native API in the diff --git a/doc/html/pcreapi.html b/doc/html/pcreapi.html index 87f7f64..742f61a 100644 --- a/doc/html/pcreapi.html +++ b/doc/html/pcreapi.html @@ -17,7 +17,7 @@ man page, in case the conversion went wrong. <li><a name="TOC2" href="#SEC2">PCRE NATIVE API STRING EXTRACTION FUNCTIONS</a> <li><a name="TOC3" href="#SEC3">PCRE NATIVE API AUXILIARY FUNCTIONS</a> <li><a name="TOC4" href="#SEC4">PCRE NATIVE API INDIRECTED FUNCTIONS</a> -<li><a name="TOC5" href="#SEC5">PCRE 8-BIT AND 16-BIT LIBRARIES</a> +<li><a name="TOC5" href="#SEC5">PCRE 8-BIT, 16-BIT AND 32-BIT LIBRARIES</a> <li><a name="TOC6" href="#SEC6">PCRE API OVERVIEW</a> <li><a name="TOC7" href="#SEC7">NEWLINES</a> <li><a name="TOC8" href="#SEC8">MULTITHREADING</a> @@ -116,6 +116,12 @@ man page, in case the conversion went wrong. </P> <br><a name="SEC3" href="#TOC1">PCRE NATIVE API AUXILIARY FUNCTIONS</a><br> <P> +<b>int pcre_jit_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b> +<b>const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b> +<b>int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b> +<b>pcre_jit_stack *<i>jstack</i>);</b> +</P> +<P> <b>pcre_jit_stack *pcre_jit_stack_alloc(int <i>startsize</i>, int <i>maxsize</i>);</b> </P> <P> @@ -161,29 +167,34 @@ man page, in case the conversion went wrong. <P> <b>int (*pcre_callout)(pcre_callout_block *);</b> </P> -<br><a name="SEC5" href="#TOC1">PCRE 8-BIT AND 16-BIT LIBRARIES</a><br> +<br><a name="SEC5" href="#TOC1">PCRE 8-BIT, 16-BIT AND 32-BIT LIBRARIES</a><br> <P> From release 8.30, PCRE can be compiled as a library for handling 16-bit character strings as well as, or instead of, the original library that handles -8-bit character strings. To avoid too much complication, this document -describes the 8-bit versions of the functions, with only occasional references -to the 16-bit library. +8-bit character strings. From release 8.32, PCRE can also be compiled as a +library for handling 32-bit character strings. To avoid too much complication, +this document describes the 8-bit versions of the functions, with only +occasional references to the 16-bit and 32-bit libraries. </P> <P> -The 16-bit functions operate in the same way as their 8-bit counterparts; they -just use different data types for their arguments and results, and their names -start with <b>pcre16_</b> instead of <b>pcre_</b>. For every option that has UTF8 -in its name (for example, PCRE_UTF8), there is a corresponding 16-bit name with -UTF8 replaced by UTF16. This facility is in fact just cosmetic; the 16-bit -option names define the same bit values. +The 16-bit and 32-bit functions operate in the same way as their 8-bit +counterparts; they just use different data types for their arguments and +results, and their names start with <b>pcre16_</b> or <b>pcre32_</b> instead of +<b>pcre_</b>. For every option that has UTF8 in its name (for example, +PCRE_UTF8), there are corresponding 16-bit and 32-bit names with UTF8 replaced +by UTF16 or UTF32, respectively. This facility is in fact just cosmetic; the +16-bit and 32-bit option names define the same bit values. </P> <P> References to bytes and UTF-8 in this document should be read as references to -16-bit data quantities and UTF-16 when using the 16-bit library, unless -specified otherwise. More details of the specific differences for the 16-bit -library are given in the +16-bit data quantities and UTF-16 when using the 16-bit library, or 32-bit data +quantities and UTF-32 when using the 32-bit library, unless specified +otherwise. More details of the specific differences for the 16-bit and 32-bit +libraries are given in the <a href="pcre16.html"><b>pcre16</b></a> -page. +and +<a href="pcre32.html"><b>pcre32</b></a> +pages. </P> <br><a name="SEC6" href="#TOC1">PCRE API OVERVIEW</a><br> <P> @@ -233,7 +244,10 @@ used if available, by setting an option that is ignored when it is not relevant. More complicated programs might need to make use of the functions <b>pcre_jit_stack_alloc()</b>, <b>pcre_jit_stack_free()</b>, and <b>pcre_assign_jit_stack()</b> in order to control the JIT code's memory usage. -These functions are discussed in the +</P> +<P> +From release 8.32 there is also a direct interface for JIT execution, which +gives improved performance. The JIT-specific functions are discussed in the <a href="pcrejit.html"><b>pcrejit</b></a> documentation. </P> @@ -398,15 +412,23 @@ not recognized. The following information is available: PCRE_CONFIG_UTF8 </pre> The output is an integer that is set to one if UTF-8 support is available; -otherwise it is set to zero. If this option is given to the 16-bit version of -this function, <b>pcre16_config()</b>, the result is PCRE_ERROR_BADOPTION. +otherwise it is set to zero. This value should normally be given to the 8-bit +version of this function, <b>pcre_config()</b>. If it is given to the 16-bit +or 32-bit version of this function, the result is PCRE_ERROR_BADOPTION. <pre> PCRE_CONFIG_UTF16 </pre> The output is an integer that is set to one if UTF-16 support is available; otherwise it is set to zero. This value should normally be given to the 16-bit version of this function, <b>pcre16_config()</b>. If it is given to the 8-bit -version of this function, the result is PCRE_ERROR_BADOPTION. +or 32-bit version of this function, the result is PCRE_ERROR_BADOPTION. +<pre> + PCRE_CONFIG_UTF32 +</pre> +The output is an integer that is set to one if UTF-32 support is available; +otherwise it is set to zero. This value should normally be given to the 32-bit +version of this function, <b>pcre32_config()</b>. If it is given to the 8-bit +or 16-bit version of this function, the result is PCRE_ERROR_BADOPTION. <pre> PCRE_CONFIG_UNICODE_PROPERTIES </pre> @@ -428,11 +450,13 @@ unaligned)". If JIT support is not available, the result is NULL. PCRE_CONFIG_NEWLINE </pre> The output is an integer whose value specifies the default character sequence -that is recognized as meaning "newline". The four values that are supported -are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, and -1 for ANY. -Though they are derived from ASCII, the same values are returned in EBCDIC -environments. The default should normally correspond to the standard sequence -for your operating system. +that is recognized as meaning "newline". The values that are supported in +ASCII/Unicode environments are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for +ANYCRLF, and -1 for ANY. In EBCDIC environments, CR, ANYCRLF, and ANY yield the +same values. However, the value for LF is normally 21, though some EBCDIC +environments use 37. The corresponding values for CRLF are 3349 and 3365. The +default should normally correspond to the standard sequence for your operating +system. <pre> PCRE_CONFIG_BSR </pre> @@ -446,10 +470,11 @@ or CRLF. The default can be overridden when a pattern is compiled or matched. The output is an integer that contains the number of bytes used for internal linkage in compiled regular expressions. For the 8-bit library, the value can be 2, 3, or 4. For the 16-bit library, the value is either 2 or 4 and is still -a number of bytes. The default value of 2 is sufficient for all but the most -massive patterns, since it allows the compiled pattern to be up to 64K in size. -Larger values allow larger regular expressions to be compiled, at the expense -of slower matching. +a number of bytes. For the 32-bit library, the value is either 2 or 4 and is +still a number of bytes. The default value of 2 is sufficient for all but the +most massive patterns, since it allows the compiled pattern to be up to 64K in +size. Larger values allow larger regular expressions to be compiled, at the +expense of slower matching. <pre> PCRE_CONFIG_POSIX_MALLOC_THRESHOLD </pre> @@ -743,11 +768,23 @@ indicated by a single character (CR or LF, respectively). Setting PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies -that any Unicode newline sequence should be recognized. The Unicode newline -sequences are the three just mentioned, plus the single characters VT (vertical -tab, U+000B), FF (form feed, U+000C), NEL (next line, U+0085), LS (line -separator, U+2028), and PS (paragraph separator, U+2029). For the 8-bit -library, the last two are recognized only in UTF-8 mode. +that any Unicode newline sequence should be recognized. +</P> +<P> +In an ASCII/Unicode environment, the Unicode newline sequences are the three +just mentioned, plus the single characters VT (vertical tab, U+000B), FF (form +feed, U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS +(paragraph separator, U+2029). For the 8-bit library, the last two are +recognized only in UTF-8 mode. +</P> +<P> +When PCRE is compiled to run in an EBCDIC (mainframe) environment, the code for +CR is 0x0d, the same as ASCII. However, the character code for LF is normally +0x15, though in some EBCDIC environments 0x25 is used. Whichever of these is +not LF is made to correspond to Unicode's NEL character. EBCDIC codes are all +less than 256. For more details, see the +<a href="pcrebuild.html"><b>pcrebuild</b></a> +documentation. </P> <P> The newline setting in the options word uses three bits that are treated @@ -816,8 +853,8 @@ page. <pre> PCRE_NO_UTF8_CHECK </pre> -When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 -string is automatically checked. There is a discussion about the +When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is +automatically checked. There is a discussion about the <a href="pcreunicode.html#utf8strings">validity of UTF-8 strings</a> in the <a href="pcreunicode.html"><b>pcreunicode</b></a> @@ -827,15 +864,17 @@ this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid UTF-8 string as a pattern is undefined. It may cause your program to crash. Note that this option can also be passed to <b>pcre_exec()</b> and <b>pcre_dfa_exec()</b>, to suppress the -validity checking of subject strings. +validity checking of subject strings only. If the same string is being matched +many times, the option can be safely set for the second and subsequent +matchings to improve performance. </P> <br><a name="SEC12" href="#TOC1">COMPILATION ERROR CODES</a><br> <P> The following table lists the error codes than may be returned by <b>pcre_compile2()</b>, along with the error messages that may be returned by both compiling functions. Note that error messages are always 8-bit ASCII -strings, even in 16-bit mode. As PCRE has developed, some error codes have -fallen out of use. To avoid confusion, they have not been re-used. +strings, even in 16-bit or 32-bit mode. As PCRE has developed, some error codes +have fallen out of use. To avoid confusion, they have not been re-used. <pre> 0 no error 1 \ at end of pattern @@ -918,6 +957,7 @@ fallen out of use. To avoid confusion, they have not been re-used. 74 invalid UTF-16 string (specifically UTF-16) 75 name is too long in (*MARK), (*PRUNE), (*SKIP), or (*THEN) 76 character value in \u.... sequence is too large + 77 invalid UTF-32 string (specifically UTF-32) </pre> The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may be used if the limits were changed when PCRE was built. @@ -946,13 +986,17 @@ in the section on matching a pattern. </P> <P> If studying the pattern does not produce any useful information, -<b>pcre_study()</b> returns NULL. In that circumstance, if the calling program -wants to pass any of the other fields to <b>pcre_exec()</b> or -<b>pcre_dfa_exec()</b>, it must set up its own <b>pcre_extra</b> block. +<b>pcre_study()</b> returns NULL by default. In that circumstance, if the +calling program wants to pass any of the other fields to <b>pcre_exec()</b> or +<b>pcre_dfa_exec()</b>, it must set up its own <b>pcre_extra</b> block. However, +if <b>pcre_study()</b> is called with the PCRE_STUDY_EXTRA_NEEDED option, it +returns a <b>pcre_extra</b> block even if studying did not find any additional +information. It may still return NULL, however, if an error occurs in +<b>pcre_study()</b>. </P> <P> The second argument of <b>pcre_study()</b> contains option bits. There are three -options: +further options in addition to PCRE_STUDY_EXTRA_NEEDED: <pre> PCRE_STUDY_JIT_COMPILE PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE @@ -961,7 +1005,7 @@ options: If any of these are set, and the just-in-time compiler is available, the pattern is further compiled into machine code that executes much faster than the <b>pcre_exec()</b> interpretive matching function. If the just-in-time -compiler is not available, these options are ignored. All other bits in the +compiler is not available, these options are ignored. All undefined bits in the <i>options</i> argument must be zero. </P> <P> @@ -1011,16 +1055,16 @@ real application there should be tests for errors): Studying a pattern does two things: first, a lower bound for the length of subject string that is needed to match the pattern is computed. This does not mean that there are any strings of that length that match, but it does -guarantee that no shorter strings match. The value is used by -<b>pcre_exec()</b> and <b>pcre_dfa_exec()</b> to avoid wasting time by trying to -match strings that are shorter than the lower bound. You can find out the value -in a calling program via the <b>pcre_fullinfo()</b> function. +guarantee that no shorter strings match. The value is used to avoid wasting +time by trying to match strings that are shorter than the lower bound. You can +find out the value in a calling program via the <b>pcre_fullinfo()</b> function. </P> <P> Studying a pattern is also useful for non-anchored patterns that do not have a single fixed starting character. A bitmap of possible starting bytes is created. This speeds up finding a position in the subject at which to start -matching. (In 16-bit mode, the bitmap is used for 16-bit values less than 256.) +matching. (In 16-bit mode, the bitmap is used for 16-bit values less than 256. +In 32-bit mode, the bitmap is used for 32-bit values less than 256.) </P> <P> These two optimizations apply to both <b>pcre_exec()</b> and @@ -1165,8 +1209,8 @@ variable. <P> If there is a fixed first value, for example, the letter "c" from a pattern such as (cat|cow|coyote), its value is returned. In the 8-bit library, the -value is always less than 256; in the 16-bit library the value can be up to -0xffff. +value is always less than 256. In the 16-bit library the value can be up to +0xffff. In the 32-bit library the value can be up to 0x10ffff. </P> <P> If there is no fixed first value, and if either @@ -1183,6 +1227,12 @@ starts with "^", or -1 is returned, indicating that the pattern matches only at the start of a subject string or after any newline within the string. Otherwise -2 is returned. For anchored patterns, -2 is returned. +</P> +<P> +Since for the 32-bit library using the non-UTF-32 mode, this function is unable +to return the full 32-bit range of the character, this value is deprecated; +instead the PCRE_INFO_FIRSTCHARACTERFLAGS and PCRE_INFO_FIRSTCHARACTER values +should be used. <pre> PCRE_INFO_FIRSTTABLE </pre> @@ -1228,6 +1278,12 @@ value, -1 is returned. For anchored patterns, a last literal value is recorded only if it follows something of variable length. For example, for the pattern /^a\d+z\d+/ the returned value is "z", but for /^a\dz\d/ the returned value is -1. +</P> +<P> +Since for the 32-bit library using the non-UTF-32 mode, this function is unable +to return the full 32-bit range of the character, this value is deprecated; +instead the PCRE_INFO_REQUIREDCHARFLAGS and PCRE_INFO_REQUIREDCHAR values should +be used. <pre> PCRE_INFO_MAXLOOKBEHIND </pre> @@ -1268,7 +1324,9 @@ length of the longest name. PCRE_INFO_NAMETABLE returns a pointer to the first entry of the table. This is a pointer to <b>char</b> in the 8-bit library, where the first two bytes of each entry are the number of the capturing parenthesis, most significant byte first. In the 16-bit library, the pointer points to -16-bit data units, the first of which contains the parenthesis number. The rest +16-bit data units, the first of which contains the parenthesis number. +In the 32-bit library, the pointer points to 32-bit data units, the first of +which contains the parenthesis number. The rest of the entry is the corresponding name, zero terminated. </P> <P> @@ -1357,6 +1415,80 @@ above). The format of the <i>study_data</i> block is private, but its length is made available via this option so that it can be saved and restored (see the <a href="pcreprecompile.html"><b>pcreprecompile</b></a> documentation for details). +<pre> + PCRE_INFO_FIRSTCHARACTERFLAGS +</pre> +Return information about the first data unit of any matched string, for a +non-anchored pattern. The fourth argument should point to an <b>int</b> +variable. +</P> +<P> +If there is a fixed first value, for example, the letter "c" from a pattern +such as (cat|cow|coyote), 1 is returned, and the character value can be +retrieved using PCRE_INFO_FIRSTCHARACTER. +</P> +<P> +If there is no fixed first value, and if either +<br> +<br> +(a) the pattern was compiled with the PCRE_MULTILINE option, and every branch +starts with "^", or +<br> +<br> +(b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set +(if it were set, the pattern would be anchored), +<br> +<br> +2 is returned, indicating that the pattern matches only at the start of a +subject string or after any newline within the string. Otherwise 0 is +returned. For anchored patterns, 0 is returned. +<pre> + PCRE_INFO_FIRSTCHARACTER +</pre> +Return the fixed first character value, if PCRE_INFO_FIRSTCHARACTERFLAGS +returned 1; otherwise returns 0. The fourth argument should point to an +<b>uint_t</b> variable. +</P> +<P> +In the 8-bit library, the value is always less than 256. In the 16-bit library +the value can be up to 0xffff. In the 32-bit library in UTF-32 mode the value +can be up to 0x10ffff, and up to 0xffffffff when not using UTF-32 mode. +</P> +<P> +If there is no fixed first value, and if either +<br> +<br> +(a) the pattern was compiled with the PCRE_MULTILINE option, and every branch +starts with "^", or +<br> +<br> +(b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set +(if it were set, the pattern would be anchored), +<br> +<br> +-1 is returned, indicating that the pattern matches only at the start of a +subject string or after any newline within the string. Otherwise -2 is +returned. For anchored patterns, -2 is returned. +<pre> + PCRE_INFO_REQUIREDCHARFLAGS +</pre> +Returns 1 if there is a rightmost literal data unit that must exist in any +matched string, other than at its start. The fourth argument should point to +an <b>int</b> variable. If there is no such value, 0 is returned. If returning +1, the character value itself can be retrieved using PCRE_INFO_REQUIREDCHAR. +</P> +<P> +For anchored patterns, a last literal value is recorded only if it follows +something of variable length. For example, for the pattern /^a\d+z\d+/ the +returned value 1 (with "z" returned from PCRE_INFO_REQUIREDCHAR), but for +/^a\dz\d/ the returned value is 0. +<pre> + PCRE_INFO_REQUIREDCHAR +</pre> +Return the value of the rightmost literal data unit that must exist in any +matched string, other than at its start, if such a value has been recorded. The +fourth argument should point to an <b>uint32_t</b> variable. If there is no such +value, 0 is returned. </P> <br><a name="SEC16" href="#TOC1">REFERENCE COUNTS</a><br> <P> @@ -1449,6 +1581,10 @@ fields (not necessarily in this order): </pre> In the 16-bit version of this structure, the <i>mark</i> field has type "PCRE_UCHAR16 **". +<br> +<br> +In the 32-bit version of this structure, the <i>mark</i> field has type +"PCRE_UCHAR32 **". </P> <P> The <i>flags</i> field is used to specify which of the other fields are set. The @@ -2089,7 +2225,7 @@ documentation for more details. PCRE_ERROR_BADMODE (-28) </pre> This error is given if a pattern that was compiled by the 8-bit library is -passed to a 16-bit library function, or vice versa. +passed to a 16-bit or 32-bit library function, or vice versa. <pre> PCRE_ERROR_BADENDIANNESS (-29) </pre> @@ -2097,9 +2233,23 @@ This error is given if a pattern that was compiled and saved is reloaded on a host with different endianness. The utility function <b>pcre_pattern_to_host_byte_order()</b> can be used to convert such a pattern so that it runs on the new host. +<pre> + PCRE_ERROR_JIT_BADOPTION +</pre> +This error is returned when a pattern that was successfully studied using a JIT +compile option is being matched, but the matching mode (partial or complete +match) does not correspond to any JIT compilation mode. When the JIT fast path +function is used, this error may be also given for invalid options. See the +<a href="pcrejit.html"><b>pcrejit</b></a> +documentation for more details. +<pre> + PCRE_ERROR_BADLENGTH (-32) +</pre> +This error is given if <b>pcre_exec()</b> is called with a negative value for +the <i>length</i> argument. </P> <P> -Error numbers -16 to -20, -22, and -30 are not used by <b>pcre_exec()</b>. +Error numbers -16 to -20, -22, and 30 are not used by <b>pcre_exec()</b>. <a name="badutf8reasons"></a></P> <br><b> Reason codes for invalid UTF-8 strings @@ -2108,6 +2258,8 @@ Reason codes for invalid UTF-8 strings This section applies only to the 8-bit library. The corresponding information for the 16-bit library is given in the <a href="pcre16.html"><b>pcre16</b></a> +page. The corresponding information for the 32-bit library is given in the +<a href="pcre32.html"><b>pcre32</b></a> page. </P> <P> @@ -2179,6 +2331,11 @@ character. </pre> The first byte of a character has the value 0xfe or 0xff. These values can never occur in a valid UTF-8 string. +<pre> + PCRE_UTF8_ERR2 +</pre> +Non-character. These are the last two characters in each plane (0xfffe, 0xffff, +0x1fffe, 0x1ffff .. 0x10fffe, 0x10ffff), and the characters 0xfdd0..0xfdef. </P> <br><a name="SEC18" href="#TOC1">EXTRACTING CAPTURED SUBSTRINGS BY NUMBER</a><br> <P> @@ -2604,9 +2761,10 @@ fail, this error is given. </P> <br><a name="SEC24" href="#TOC1">SEE ALSO</a><br> <P> -<b>pcre16</b>(3), <b>pcrebuild</b>(3), <b>pcrecallout</b>(3), <b>pcrecpp(3)</b>(3), -<b>pcrematching</b>(3), <b>pcrepartial</b>(3), <b>pcreposix</b>(3), -<b>pcreprecompile</b>(3), <b>pcresample</b>(3), <b>pcrestack</b>(3). +<b>pcre16</b>(3), <b>pcre32</b>(3), <b>pcrebuild</b>(3), <b>pcrecallout</b>(3), +<b>pcrecpp(3)</b>(3), <b>pcrematching</b>(3), <b>pcrepartial</b>(3), +<b>pcreposix</b>(3), <b>pcreprecompile</b>(3), <b>pcresample</b>(3), +<b>pcrestack</b>(3). </P> <br><a name="SEC25" href="#TOC1">AUTHOR</a><br> <P> @@ -2619,7 +2777,7 @@ Cambridge CB2 3QH, England. </P> <br><a name="SEC26" href="#TOC1">REVISION</a><br> <P> -Last updated: 17 June 2012 +Last updated: 31 October 2012 <br> Copyright © 1997-2012 University of Cambridge. <br> diff --git a/doc/html/pcrebuild.html b/doc/html/pcrebuild.html index 2906c3d..d6fa8f4 100644 --- a/doc/html/pcrebuild.html +++ b/doc/html/pcrebuild.html @@ -14,10 +14,10 @@ man page, in case the conversion went wrong. <br> <ul> <li><a name="TOC1" href="#SEC1">PCRE BUILD-TIME OPTIONS</a> -<li><a name="TOC2" href="#SEC2">BUILDING 8-BIT and 16-BIT LIBRARIES</a> +<li><a name="TOC2" href="#SEC2">BUILDING 8-BIT, 16-BIT AND 32-BIT LIBRARIES</a> <li><a name="TOC3" href="#SEC3">BUILDING SHARED AND STATIC LIBRARIES</a> <li><a name="TOC4" href="#SEC4">C++ SUPPORT</a> -<li><a name="TOC5" href="#SEC5">UTF-8 and UTF-16 SUPPORT</a> +<li><a name="TOC5" href="#SEC5">UTF-8, UTF-16 AND UTF-32 SUPPORT</a> <li><a name="TOC6" href="#SEC6">UNICODE CHARACTER PROPERTY SUPPORT</a> <li><a name="TOC7" href="#SEC7">JUST-IN-TIME COMPILER SUPPORT</a> <li><a name="TOC8" href="#SEC8">CODE VALUE OF NEWLINE</a> @@ -31,9 +31,11 @@ man page, in case the conversion went wrong. <li><a name="TOC16" href="#SEC16">PCREGREP OPTIONS FOR COMPRESSED FILE SUPPORT</a> <li><a name="TOC17" href="#SEC17">PCREGREP BUFFER SIZE</a> <li><a name="TOC18" href="#SEC18">PCRETEST OPTION FOR LIBREADLINE SUPPORT</a> -<li><a name="TOC19" href="#SEC19">SEE ALSO</a> -<li><a name="TOC20" href="#SEC20">AUTHOR</a> -<li><a name="TOC21" href="#SEC21">REVISION</a> +<li><a name="TOC19" href="#SEC19">DEBUGGING WITH VALGRIND SUPPORT</a> +<li><a name="TOC20" href="#SEC20">CODE COVERAGE REPORTING</a> +<li><a name="TOC21" href="#SEC21">SEE ALSO</a> +<li><a name="TOC22" href="#SEC22">AUTHOR</a> +<li><a name="TOC23" href="#SEC23">REVISION</a> </ul> <br><a name="SEC1" href="#TOC1">PCRE BUILD-TIME OPTIONS</a><br> <P> @@ -46,8 +48,9 @@ the GUI facility of <b>cmake-gui</b> if you are using <b>CMake</b> instead of <b>configure</b> to build PCRE. </P> <P> -There is a lot more information about building PCRE in non-Unix-like -environments in the file called <i>NON_UNIX_USE</i>, which is part of the PCRE +There is a lot more information about building PCRE without using +<b>configure</b> (including information about using <b>CMake</b> or building "by +hand") in the file called <i>NON-AUTOTOOLS-BUILD</i>, which is part of the PCRE distribution. You should consult this file as well as the <i>README</i> file if you are building in a non-Unix-like environment. </P> @@ -64,7 +67,7 @@ The following sections include descriptions of options whose names begin with --enable and --disable always come in pairs, so the complementary option always exists as well, but as it specifies the default, it is not described. </P> -<br><a name="SEC2" href="#TOC1">BUILDING 8-BIT and 16-BIT LIBRARIES</a><br> +<br><a name="SEC2" href="#TOC1">BUILDING 8-BIT, 16-BIT AND 32-BIT LIBRARIES</a><br> <P> By default, a library called <b>libpcre</b> is built, containing functions that take string arguments contained in vectors of bytes, either as single-byte @@ -75,13 +78,21 @@ strings, by adding <pre> --enable-pcre16 </pre> +to the <b>configure</b> command. You can also build a separate +library, called <b>libpcre32</b>, in which strings are contained in vectors of +32-bit data units and interpreted either as single-unit characters or UTF-32 +strings, by adding +<pre> + --enable-pcre32 +</pre> to the <b>configure</b> command. If you do not want the 8-bit library, add <pre> --disable-pcre8 </pre> -as well. At least one of the two libraries must be built. Note that the C++ and -POSIX wrappers are for the 8-bit library only, and that <b>pcregrep</b> is an -8-bit program. None of these are built if you select only the 16-bit library. +as well. At least one of the three libraries must be built. Note that the C++ +and POSIX wrappers are for the 8-bit library only, and that <b>pcregrep</b> is +an 8-bit program. None of these are built if you select only the 16-bit or +32-bit libraries. </P> <br><a name="SEC3" href="#TOC1">BUILDING SHARED AND STATIC LIBRARIES</a><br> <P> @@ -104,26 +115,26 @@ strings). You can disable this by adding </pre> to the <b>configure</b> command. </P> -<br><a name="SEC5" href="#TOC1">UTF-8 and UTF-16 SUPPORT</a><br> +<br><a name="SEC5" href="#TOC1">UTF-8, UTF-16 AND UTF-32 SUPPORT</a><br> <P> To build PCRE with support for UTF Unicode character strings, add <pre> --enable-utf </pre> -to the <b>configure</b> command. This setting applies to both libraries, adding -support for UTF-8 to the 8-bit library and support for UTF-16 to the 16-bit -library. There are no separate options for enabling UTF-8 and UTF-16 -independently because that would allow ridiculous settings such as requesting -UTF-16 support while building only the 8-bit library. It is not possible to -build one library with UTF support and the other without in the same -configuration. (For backwards compatibility, --enable-utf8 is a synonym of ---enable-utf.) +to the <b>configure</b> command. This setting applies to all three libraries, +adding support for UTF-8 to the 8-bit library, support for UTF-16 to the 16-bit +library, and support for UTF-32 to the to the 32-bit library. There are no +separate options for enabling UTF-8, UTF-16 and UTF-32 independently because +that would allow ridiculous settings such as requesting UTF-16 support while +building only the 8-bit library. It is not possible to build one library with +UTF support and another without in the same configuration. (For backwards +compatibility, --enable-utf8 is a synonym of --enable-utf.) </P> <P> -Of itself, this setting does not make PCRE treat strings as UTF-8 or UTF-16. As -well as compiling PCRE with this option, you also have have to set the -PCRE_UTF8 or PCRE_UTF16 option when you call one of the pattern compiling -functions. +Of itself, this setting does not make PCRE treat strings as UTF-8, UTF-16 or +UTF-32. As well as compiling PCRE with this option, you also have have to set +the PCRE_UTF8, PCRE_UTF16 or PCRE_UTF32 option (as appropriate) when you call +one of the pattern compiling functions. </P> <P> If you set --enable-utf when compiling in an EBCDIC environment, PCRE expects @@ -233,18 +244,20 @@ to the <b>configure</b> command. <P> Within a compiled pattern, offset values are used to point from one part to another (for example, from an opening parenthesis to an alternation -metacharacter). By default, two-byte values are used for these offsets, leading -to a maximum size for a compiled pattern of around 64K. This is sufficient to -handle all but the most gigantic patterns. Nevertheless, some people do want to -process truly enormous patterns, so it is possible to compile PCRE to use -three-byte or four-byte offsets by adding a setting such as +metacharacter). By default, in the 8-bit and 16-bit libraries, two-byte values +are used for these offsets, leading to a maximum size for a compiled pattern of +around 64K. This is sufficient to handle all but the most gigantic patterns. +Nevertheless, some people do want to process truly enormous patterns, so it is +possible to compile PCRE to use three-byte or four-byte offsets by adding a +setting such as <pre> --with-link-size=3 </pre> to the <b>configure</b> command. The value given must be 2, 3, or 4. For the -16-bit library, a value of 3 is rounded up to 4. Using longer offsets slows -down the operation of PCRE because it has to load additional data when handling -them. +16-bit library, a value of 3 is rounded up to 4. In these libraries, using +longer offsets slows down the operation of PCRE because it has to load +additional data when handling them. For the 32-bit library the value is always +4 and cannot be overridden; the value of --with-link-size is ignored. </P> <br><a name="SEC12" href="#TOC1">AVOIDING EXCESSIVE STACK USAGE</a><br> <P> @@ -337,6 +350,23 @@ to the <b>configure</b> command. This setting implies an EBCDIC environment (for example, an IBM mainframe operating system). The --enable-ebcdic option is incompatible with --enable-utf. </P> +<P> +The EBCDIC character that corresponds to an ASCII LF is assumed to have the +value 0x15 by default. However, in some EBCDIC environments, 0x25 is used. In +such an environment you should use +<pre> + --enable-ebcdic-nl25 +</pre> +as well as, or instead of, --enable-ebcdic. The EBCDIC character for CR has the +same value as in ASCII, namely, 0x0d. Whichever of 0x15 and 0x25 is <i>not</i> +chosen as LF is made to correspond to the Unicode NEL character (which, in +Unicode, is 0x85). +</P> +<P> +The options that select newline behaviour, such as --enable-newline-is-cr, +and equivalent run-time options, refer to these character values in an EBCDIC +environment. +</P> <br><a name="SEC16" href="#TOC1">PCREGREP OPTIONS FOR COMPRESSED FILE SUPPORT</a><br> <P> By default, <b>pcregrep</b> reads all files as plain text. You can build it so @@ -396,11 +426,78 @@ automatically included, you may need to add something like </pre> immediately before the <b>configure</b> command. </P> -<br><a name="SEC19" href="#TOC1">SEE ALSO</a><br> +<br><a name="SEC19" href="#TOC1">DEBUGGING WITH VALGRIND SUPPORT</a><br> +<P> +By adding the +<pre> + --enable-valgrind +</pre> +option to to the <b>configure</b> command, PCRE will use valgrind annotations +to mark certain memory regions as unaddressable. This allows it to detect +invalid memory accesses, and is mostly useful for debugging PCRE itself. +</P> +<br><a name="SEC20" href="#TOC1">CODE COVERAGE REPORTING</a><br> +<P> +If your C compiler is gcc, you can build a version of PCRE that can generate a +code coverage report for its test suite. To enable this, you must install +<b>lcov</b> version 1.6 or above. Then specify +<pre> + --enable-coverage +</pre> +to the <b>configure</b> command and build PCRE in the usual way. +</P> +<P> +Note that using <b>ccache</b> (a caching C compiler) is incompatible with code +coverage reporting. If you have configured <b>ccache</b> to run automatically +on your system, you must set the environment variable +<pre> + CCACHE_DISABLE=1 +</pre> +before running <b>make</b> to build PCRE, so that <b>ccache</b> is not used. +</P> +<P> +When --enable-coverage is used, the following addition targets are added to the +<i>Makefile</i>: +<pre> + make coverage +</pre> +This creates a fresh coverage report for the PCRE test suite. It is equivalent +to running "make coverage-reset", "make coverage-baseline", "make check", and +then "make coverage-report". +<pre> + make coverage-reset +</pre> +This zeroes the coverage counters, but does nothing else. +<pre> + make coverage-baseline +</pre> +This captures baseline coverage information. +<pre> + make coverage-report +</pre> +This creates the coverage report. +<pre> + make coverage-clean-report +</pre> +This removes the generated coverage report without cleaning the coverage data +itself. +<pre> + make coverage-clean-data +</pre> +This removes the captured coverage data without removing the coverage files +created at compile time (*.gcno). +<pre> + make coverage-clean +</pre> +This cleans all coverage data including the generated coverage report. For more +information about code coverage, see the <b>gcov</b> and <b>lcov</b> +documentation. +</P> +<br><a name="SEC21" href="#TOC1">SEE ALSO</a><br> <P> -<b>pcreapi</b>(3), <b>pcre16</b>, <b>pcre_config</b>(3). +<b>pcreapi</b>(3), <b>pcre16</b>, <b>pcre32</b>, <b>pcre_config</b>(3). </P> -<br><a name="SEC20" href="#TOC1">AUTHOR</a><br> +<br><a name="SEC22" href="#TOC1">AUTHOR</a><br> <P> Philip Hazel <br> @@ -409,9 +506,9 @@ University Computing Service Cambridge CB2 3QH, England. <br> </P> -<br><a name="SEC21" href="#TOC1">REVISION</a><br> +<br><a name="SEC23" href="#TOC1">REVISION</a><br> <P> -Last updated: 07 January 2012 +Last updated: 30 October 2012 <br> Copyright © 1997-2012 University of Cambridge. <br> diff --git a/doc/html/pcrecallout.html b/doc/html/pcrecallout.html index 8076cee..b28e347 100644 --- a/doc/html/pcrecallout.html +++ b/doc/html/pcrecallout.html @@ -13,14 +13,18 @@ from the original man page. If there is any nonsense in it, please consult the man page, in case the conversion went wrong. <br> <ul> -<li><a name="TOC1" href="#SEC1">PCRE CALLOUTS</a> -<li><a name="TOC2" href="#SEC2">MISSING CALLOUTS</a> -<li><a name="TOC3" href="#SEC3">THE CALLOUT INTERFACE</a> -<li><a name="TOC4" href="#SEC4">RETURN VALUES</a> -<li><a name="TOC5" href="#SEC5">AUTHOR</a> -<li><a name="TOC6" href="#SEC6">REVISION</a> +<li><a name="TOC1" href="#SEC1">SYNOPSIS</a> +<li><a name="TOC2" href="#SEC2">DESCRIPTION</a> +<li><a name="TOC3" href="#SEC3">MISSING CALLOUTS</a> +<li><a name="TOC4" href="#SEC4">THE CALLOUT INTERFACE</a> +<li><a name="TOC5" href="#SEC5">RETURN VALUES</a> +<li><a name="TOC6" href="#SEC6">AUTHOR</a> +<li><a name="TOC7" href="#SEC7">REVISION</a> </ul> -<br><a name="SEC1" href="#TOC1">PCRE CALLOUTS</a><br> +<br><a name="SEC1" href="#TOC1">SYNOPSIS</a><br> +<P> +<b>#include <pcre.h></b> +</P> <P> <b>int (*pcre_callout)(pcre_callout_block *);</b> </P> @@ -28,12 +32,16 @@ man page, in case the conversion went wrong. <b>int (*pcre16_callout)(pcre16_callout_block *);</b> </P> <P> +<b>int (*pcre32_callout)(pcre32_callout_block *);</b> +</P> +<br><a name="SEC2" href="#TOC1">DESCRIPTION</a><br> +<P> PCRE provides a feature called "callout", which is a means of temporarily passing control to the caller of PCRE in the middle of pattern matching. The caller of PCRE provides an external function by putting its entry point in the global variable <i>pcre_callout</i> (<i>pcre16_callout</i> for the 16-bit -library). By default, this variable contains NULL, which disables all calling -out. +library, <i>pcre32_callout</i> for the 32-bit library). By default, this +variable contains NULL, which disables all calling out. </P> <P> Within a regular expression, (?C) indicates the points at which the external @@ -68,7 +76,7 @@ The use of callouts in a pattern makes it ineligible for optimization by the just-in-time compiler. Studying such a pattern with the PCRE_STUDY_JIT_COMPILE option always fails. </P> -<br><a name="SEC2" href="#TOC1">MISSING CALLOUTS</a><br> +<br><a name="SEC3" href="#TOC1">MISSING CALLOUTS</a><br> <P> You should be aware that, because of optimizations in the way PCRE matches patterns by default, callouts sometimes do not happen. For example, if the @@ -93,12 +101,13 @@ option to the matching function, or by starting the pattern with (*NO_START_OPT). This slows down the matching process, but does ensure that callouts such as the example above are obeyed. </P> -<br><a name="SEC3" href="#TOC1">THE CALLOUT INTERFACE</a><br> +<br><a name="SEC4" href="#TOC1">THE CALLOUT INTERFACE</a><br> <P> During matching, when PCRE reaches a callout point, the external function -defined by <i>pcre_callout</i> or <i>pcre16_callout</i> is called (if it is set). -This applies to both normal and DFA matching. The only argument to the callout -function is a pointer to a <b>pcre_callout</b> or <b>pcre16_callout</b> block. +defined by <i>pcre_callout</i> or <i>pcre[16|32]_callout</i> is called +(if it is set). This applies to both normal and DFA matching. The only +argument to the callout function is a pointer to a <b>pcre_callout</b> +or <b>pcre[16|32]_callout</b> block. These structures contains the following fields: <pre> int <i>version</i>; @@ -106,6 +115,7 @@ These structures contains the following fields: int *<i>offset_vector</i>; const char *<i>subject</i>; (8-bit version) PCRE_SPTR16 <i>subject</i>; (16-bit version) + PCRE_SPTR32 <i>subject</i>; (32-bit version) int <i>subject_length</i>; int <i>start_match</i>; int <i>current_position</i>; @@ -116,6 +126,7 @@ These structures contains the following fields: int <i>next_item_length</i>; const unsigned char *<i>mark</i>; (8-bit version) const PCRE_UCHAR16 *<i>mark</i>; (16-bit version) + const PCRE_UCHAR32 *<i>mark</i>; (32-bit version) </pre> The <i>version</i> field is an integer containing the version number of the block format. The initial version was 0; the current version is 2. The version @@ -130,7 +141,7 @@ automatically generated callouts). <P> The <i>offset_vector</i> field is a pointer to the vector of offsets that was passed by the caller to the matching function. When <b>pcre_exec()</b> or -<b>pcre16_exec()</b> is used, the contents can be inspected, in order to extract +<b>pcre[16|32]_exec()</b> is used, the contents can be inspected, in order to extract substrings that have been matched so far, in the same way as for extracting substrings after a match has completed. For the DFA matching functions, this field is not useful. @@ -152,7 +163,7 @@ The <i>current_position</i> field contains the offset within the subject of the current match pointer. </P> <P> -When the <b>pcre_exec()</b> or <b>pcre16_exec()</b> is used, the +When the <b>pcre_exec()</b> or <b>pcre[16|32]_exec()</b> is used, the <i>capture_top</i> field contains one more than the number of the highest numbered captured substring so far. If no substrings have been captured, the value of <i>capture_top</i> is one. This is always the case when the DFA @@ -166,7 +177,7 @@ the case for the DFA matching functions. <P> The <i>callout_data</i> field contains a value that is passed to a matching function specifically so that it can be passed back in callouts. It is passed -in the <i>callout_data</i> field of a <b>pcre_extra</b> or <b>pcre16_extra</b> +in the <i>callout_data</i> field of a <b>pcre_extra</b> or <b>pcre[16|32]_extra</b> data structure. If no such data was passed, the value of <i>callout_data</i> in a callout block is NULL. There is a description of the <b>pcre_extra</b> structure in the @@ -192,13 +203,13 @@ same callout number. However, they are set for all callouts. </P> <P> The <i>mark</i> field is present from version 2 of the callout structure. In -callouts from <b>pcre_exec()</b> or <b>pcre16_exec()</b> it contains a pointer to +callouts from <b>pcre_exec()</b> or <b>pcre[16|32]_exec()</b> it contains a pointer to the zero-terminated name of the most recently passed (*MARK), (*PRUNE), or (*THEN) item in the match, or NULL if no such items have been passed. Instances of (*PRUNE) or (*THEN) without a name do not obliterate a previous (*MARK). In callouts from the DFA matching functions this field always contains NULL. </P> -<br><a name="SEC4" href="#TOC1">RETURN VALUES</a><br> +<br><a name="SEC5" href="#TOC1">RETURN VALUES</a><br> <P> The external callout function returns an integer to PCRE. If the value is zero, matching proceeds as normal. If the value is greater than zero, matching fails @@ -212,7 +223,7 @@ values. In particular, PCRE_ERROR_NOMATCH forces a standard "no match" failure. The error number PCRE_ERROR_CALLOUT is reserved for use by callout functions; it will never be used by PCRE itself. </P> -<br><a name="SEC5" href="#TOC1">AUTHOR</a><br> +<br><a name="SEC6" href="#TOC1">AUTHOR</a><br> <P> Philip Hazel <br> @@ -221,9 +232,9 @@ University Computing Service Cambridge CB2 3QH, England. <br> </P> -<br><a name="SEC6" href="#TOC1">REVISION</a><br> +<br><a name="SEC7" href="#TOC1">REVISION</a><br> <P> -Last updated: 08 Janurary 2012 +Last updated: 24 June 2012 <br> Copyright © 1997-2012 University of Cambridge. <br> diff --git a/doc/html/pcrecompat.html b/doc/html/pcrecompat.html index 3f7f98f..0637781 100644 --- a/doc/html/pcrecompat.html +++ b/doc/html/pcrecompat.html @@ -67,12 +67,7 @@ the internal representation of Unicode characters, there is no need to implement the somewhat messy concept of surrogates." </P> <P> -7. PCRE implements a simpler version of \X than Perl, which changed to make -\X match what Unicode calls an "extended grapheme cluster". This is more -complicated than an extended Unicode sequence, which is what PCRE matches. -</P> -<P> -8. PCRE does support the \Q...\E escape for quoting substrings. Characters in +7. PCRE does support the \Q...\E escape for quoting substrings. Characters in between are treated as literals. This is slightly different from Perl in that $ and @ are also handled as literals inside the quotes. In Perl, they cause variable interpolation (but of course PCRE does not have variables). Note the @@ -87,7 +82,7 @@ following examples: The \Q...\E sequence is recognized both inside and outside character classes. </P> <P> -9. Fairly obviously, PCRE does not support the (?{code}) and (??{code}) +8. Fairly obviously, PCRE does not support the (?{code}) and (??{code}) constructions. However, there is support for recursive patterns. This is not available in Perl 5.8, but it is in Perl 5.10. Also, the PCRE "callout" feature allows an external function to be called during pattern matching. See @@ -96,7 +91,7 @@ the documentation for details. </P> <P> -10. Subpatterns that are called as subroutines (whether or not recursively) are +9. Subpatterns that are called as subroutines (whether or not recursively) are always treated as atomic groups in PCRE. This is like Python, but unlike Perl. Captured values that are set outside a subroutine call can be reference from inside in PCRE, but not in Perl. There is a discussion that explains these @@ -107,7 +102,7 @@ in the page. </P> <P> -11. If any of the backtracking control verbs are used in an assertion or in a +10. If any of the backtracking control verbs are used in an assertion or in a subpattern that is called as a subroutine (whether or not recursively), their effect is confined to that subpattern; it does not extend to the surrounding pattern. This is not always the case in Perl. In particular, if (*THEN) is @@ -119,12 +114,12 @@ match succeeds (compare capturing parentheses in assertions). Note that such subpatterns are processed as anchored at the point where they are tested. </P> <P> -12. There are some differences that are concerned with the settings of captured +11. There are some differences that are concerned with the settings of captured strings when part of a pattern is repeated. For example, matching "aba" against the pattern /^(a(b)?)+$/ in Perl leaves $2 unset, but in PCRE it is set to "b". </P> <P> -13. PCRE's handling of duplicate subpattern numbers and duplicate subpattern +12. 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), @@ -135,13 +130,13 @@ names map to capturing subpattern number 1. To avoid this confusing situation, an error is given at compile time. </P> <P> -14. Perl recognizes comments in some places that PCRE does not, for example, +13. Perl recognizes comments in some places that PCRE does not, for example, between the ( and ? at the start of a subpattern. If the /x modifier is set, Perl allows white space between ( and ? but PCRE never does, even if the PCRE_EXTENDED option is set. </P> <P> -15. PCRE provides some extensions to the Perl regular expression facilities. +14. PCRE provides some extensions to the Perl regular expression facilities. Perl 5.10 includes new features that are not in earlier versions of Perl, some of which (such as named parentheses) have been in PCRE for some time. This list is with respect to Perl 5.10: @@ -189,8 +184,9 @@ different hosts that have the other endianness. However, this does not apply to optimized data created by the just-in-time compiler. <br> <br> -(k) The alternative matching functions (<b>pcre_dfa_exec()</b> and -<b>pcre16_dfa_exec()</b>) match in a different way and are not Perl-compatible. +(k) The alternative matching functions (<b>pcre_dfa_exec()</b>, +<b>pcre16_dfa_exec()</b> and <b>pcre32_dfa_exec()</b>,) match in a different way +and are not Perl-compatible. <br> <br> (l) PCRE recognizes some special sequences such as (*CR) at the start of @@ -211,7 +207,7 @@ Cambridge CB2 3QH, England. REVISION </b><br> <P> -Last updated: 01 June 2012 +Last updated: 25 August 2012 <br> Copyright © 1997-2012 University of Cambridge. <br> diff --git a/doc/html/pcrecpp.html b/doc/html/pcrecpp.html index 48e0656..b7eac3a 100644 --- a/doc/html/pcrecpp.html +++ b/doc/html/pcrecpp.html @@ -36,7 +36,7 @@ The C++ wrapper for PCRE was provided by Google Inc. Some additional functionality was added by Giuseppe Maxia. This brief man page was constructed from the notes in the <i>pcrecpp.h</i> file, which should be consulted for further details. Note that the C++ wrapper supports only the original 8-bit -PCRE library. There is no 16-bit support at present. +PCRE library. There is no 16-bit or 32-bit support at present. </P> <br><a name="SEC3" href="#TOC1">MATCHING INTERFACE</a><br> <P> diff --git a/doc/html/pcregrep.html b/doc/html/pcregrep.html index f23060c..bac8f9a 100644 --- a/doc/html/pcregrep.html +++ b/doc/html/pcregrep.html @@ -50,7 +50,7 @@ without delimiters. For example: If you attempt to use delimiters (for example, by surrounding a pattern with slashes, as is common in Perl scripts), they are interpreted as part of the pattern. Quotes can of course be used to delimit patterns on the command line -because they are interpreted by the shell, and indeed they are required if a +because they are interpreted by the shell, and indeed quotes are required if a pattern contains white space or shell metacharacters. </P> <P> @@ -83,27 +83,28 @@ used (to allow for buffering "before" and "after" lines). An error occurs if a line overflows the buffer. </P> <P> -Patterns are limited to 8K or BUFSIZ bytes, whichever is the greater. BUFSIZ is -defined in <b><stdio.h></b>. When there is more than one pattern (specified by -the use of <b>-e</b> and/or <b>-f</b>), each pattern is applied to each line in -the order in which they are defined, except that all the <b>-e</b> patterns are -tried before the <b>-f</b> patterns. +Patterns can be no longer than 8K or BUFSIZ bytes, whichever is the greater. +BUFSIZ is defined in <b><stdio.h></b>. When there is more than one pattern +(specified by the use of <b>-e</b> and/or <b>-f</b>), each pattern is applied to +each line in the order in which they are defined, except that all the <b>-e</b> +patterns are tried before the <b>-f</b> patterns. </P> <P> -By default, as soon as one pattern matches (or fails to match when <b>-v</b> is -used), no further patterns are considered. However, if <b>--colour</b> (or -<b>--color</b>) is used to colour the matching substrings, or if -<b>--only-matching</b>, <b>--file-offsets</b>, or <b>--line-offsets</b> is used to -output only the part of the line that matched (either shown literally, or as an -offset), scanning resumes immediately following the match, so that further -matches on the same line can be found. If there are multiple patterns, they are -all tried on the remainder of the line, but patterns that follow the one that -matched are not tried on the earlier part of the line. +By default, as soon as one pattern matches a line, no further patterns are +considered. However, if <b>--colour</b> (or <b>--color</b>) is used to colour the +matching substrings, or if <b>--only-matching</b>, <b>--file-offsets</b>, or +<b>--line-offsets</b> is used to output only the part of the line that matched +(either shown literally, or as an offset), scanning resumes immediately +following the match, so that further matches on the same line can be found. If +there are multiple patterns, they are all tried on the remainder of the line, +but patterns that follow the one that matched are not tried on the earlier part +of the line. </P> <P> -This is the same behaviour as GNU grep, but it does mean that the order in -which multiple patterns are specified can affect the output when one of the -above options is used. +This behaviour means that the order in which multiple patterns are specified +can affect the output when one of the above options is used. This is no longer +the same behaviour as GNU grep, which now manages to display earlier matches +for later patterns (as long as there is no overlap). </P> <P> Patterns that can match an empty string are accepted, but empty string @@ -138,8 +139,9 @@ for a means of changing the way binary files are handled. The order in which some of the options appear can affect the output. For example, both the <b>-h</b> and <b>-l</b> options affect the printing of file names. Whichever comes later in the command line will be the one that takes -effect. Numerical values for options may be followed by K or M, to signify -multiplication by 1024 or 1024*1024 respectively. +effect. Similarly, except where noted below, if an option is given twice, the +later setting is used. Numerical values for options may be followed by K or M, +to signify multiplication by 1024 or 1024*1024 respectively. </P> <P> <b>--</b> @@ -235,10 +237,12 @@ it is to be processed. Valid values are "read" (the default) or "skip" <P> <b>-d</b> <i>action</i>, <b>--directories=</b><i>action</i> If an input path is a directory, "action" specifies how it is to be processed. -Valid values are "read" (the default), "recurse" (equivalent to the <b>-r</b> -option), or "skip" (silently skip the path). In the default case, directories -are read as if they were ordinary files. In some operating systems the effect -of reading a directory like this is an immediate end-of-file. +Valid values are "read" (the default in non-Windows environments, for +compatibility with GNU grep), "recurse" (equivalent to the <b>-r</b> option), or +"skip" (silently skip the path, the default in Windows environments). In the +"read" case, directories are read as if they were ordinary files. In some +operating systems the effect of reading a directory like this is an immediate +end-of-file; in others it may provoke an error. </P> <P> <b>-e</b> <i>pattern</i>, <b>--regex=</b><i>pattern</i>, <b>--regexp=</b><i>pattern</i> @@ -246,70 +250,94 @@ Specify a pattern to be matched. This option can be used multiple times in order to specify several patterns. It can also be used as a way of specifying a single pattern that starts with a hyphen. When <b>-e</b> is used, no argument pattern is taken from the command line; all arguments are treated as file -names. There is an overall maximum of 100 patterns. They are applied to each -line in the order in which they are defined until one matches (or fails to -match if <b>-v</b> is used). If <b>-f</b> is used with <b>-e</b>, the command line -patterns are matched first, followed by the patterns from the file, independent -of the order in which these options are specified. Note that multiple use of -<b>-e</b> is not the same as a single pattern with alternatives. For example, -X|Y finds the first character in a line that is X or Y, whereas if the two -patterns are given separately, <b>pcregrep</b> finds X if it is present, even if -it follows Y in the line. It finds Y only if there is no X in the line. This -really matters only if you are using <b>-o</b> to show the part(s) of the line -that matched. +names. There is no limit to the number of patterns. They are applied to each +line in the order in which they are defined until one matches. +<br> +<br> +If <b>-f</b> is used with <b>-e</b>, the command line patterns are matched first, +followed by the patterns from the file(s), independent of the order in which +these options are specified. Note that multiple use of <b>-e</b> is not the same +as a single pattern with alternatives. For example, X|Y finds the first +character in a line that is X or Y, whereas if the two patterns are given +separately, with X first, <b>pcregrep</b> finds X if it is present, even if it +follows Y in the line. It finds Y only if there is no X in the line. This +matters only if you are using <b>-o</b> or <b>--colo(u)r</b> to show the part(s) +of the line that matched. </P> <P> <b>--exclude</b>=<i>pattern</i> -When <b>pcregrep</b> is searching the files in a directory as a consequence of -the <b>-r</b> (recursive search) option, any regular files whose names match the -pattern are excluded. Subdirectories are not excluded by this option; they are -searched recursively, subject to the <b>--exclude-dir</b> and -<b>--include_dir</b> options. The pattern is a PCRE regular expression, and is -matched against the final component of the file name (not the entire path). If -a file name matches both <b>--include</b> and <b>--exclude</b>, it is excluded. -There is no short form for this option. +Files (but not directories) whose names match the pattern are skipped without +being processed. This applies to all files, whether listed on the command line, +obtained from <b>--file-list</b>, or by scanning a directory. The pattern is a +PCRE regular expression, and is matched against the final component of the file +name, not the entire path. The <b>-F</b>, <b>-w</b>, and <b>-x</b> options do not +apply to this pattern. The option may be given any number of times in order to +specify multiple patterns. If a file name matches both an <b>--include</b> +and an <b>--exclude</b> pattern, it is excluded. There is no short form for this +option. +</P> +<P> +<b>--exclude-from=</b><i>filename</i> +Treat each non-empty line of the file as the data for an <b>--exclude</b> +option. What constitutes a newline when reading the file is the operating +system's default. The <b>--newline</b> option has no effect on this option. This +option may be given more than once in order to specify a number of files to +read. </P> <P> <b>--exclude-dir</b>=<i>pattern</i> -When <b>pcregrep</b> is searching the contents of a directory as a consequence -of the <b>-r</b> (recursive search) option, any subdirectories whose names match -the pattern are excluded. (Note that the \fP--exclude\fP option does not affect -subdirectories.) The pattern is a PCRE regular expression, and is matched -against the final component of the name (not the entire path). If a -subdirectory name matches both <b>--include-dir</b> and <b>--exclude-dir</b>, it -is excluded. There is no short form for this option. +Directories whose names match the pattern are skipped without being processed, +whatever the setting of the <b>--recursive</b> option. This applies to all +directories, whether listed on the command line, obtained from +<b>--file-list</b>, or by scanning a parent directory. The pattern is a PCRE +regular expression, and is matched against the final component of the directory +name, not the entire path. The <b>-F</b>, <b>-w</b>, and <b>-x</b> options do not +apply to this pattern. The option may be given any number of times in order to +specify more than one pattern. If a directory matches both <b>--include-dir</b> +and <b>--exclude-dir</b>, it is excluded. There is no short form for this +option. </P> <P> <b>-F</b>, <b>--fixed-strings</b> -Interpret each pattern as a list of fixed strings, separated by newlines, -instead of as a regular expression. The <b>-w</b> (match as a word) and <b>-x</b> -(match whole line) options can be used with <b>-F</b>. They apply to each of the -fixed strings. A line is selected if any of the fixed strings are found in it -(subject to <b>-w</b> or <b>-x</b>, if present). +Interpret each data-matching pattern as a list of fixed strings, separated by +newlines, instead of as a regular expression. What constitutes a newline for +this purpose is controlled by the <b>--newline</b> option. The <b>-w</b> (match +as a word) and <b>-x</b> (match whole line) options can be used with <b>-F</b>. +They apply to each of the fixed strings. A line is selected if any of the fixed +strings are found in it (subject to <b>-w</b> or <b>-x</b>, if present). This +option applies only to the patterns that are matched against the contents of +files; it does not apply to patterns specified by any of the <b>--include</b> or +<b>--exclude</b> options. </P> <P> <b>-f</b> <i>filename</i>, <b>--file=</b><i>filename</i> -Read a number of patterns from the file, one per line, and match them against -each line of input. A data line is output if any of the patterns match it. The -filename can be given as "-" to refer to the standard input. When <b>-f</b> is -used, patterns specified on the command line using <b>-e</b> may also be -present; they are tested before the file's patterns. However, no other pattern -is taken from the command line; all arguments are treated as the names of paths -to be searched. There is an overall maximum of 100 patterns. Trailing white -space is removed from each line, and blank lines are ignored. An empty file -contains no patterns and therefore matches nothing. See also the comments about -multiple patterns versus a single pattern with alternatives in the description -of <b>-e</b> above. +Read patterns from the file, one per line, and match them against +each line of input. What constitutes a newline when reading the file is the +operating system's default. The <b>--newline</b> option has no effect on this +option. Trailing white space is removed from each line, and blank lines are +ignored. An empty file contains no patterns and therefore matches nothing. See +also the comments about multiple patterns versus a single pattern with +alternatives in the description of <b>-e</b> above. +<br> +<br> +If this option is given more than once, all the specified files are +read. A data line is output if any of the patterns match it. A filename can +be given as "-" to refer to the standard input. When <b>-f</b> is used, patterns +specified on the command line using <b>-e</b> may also be present; they are +tested before the file's patterns. However, no other pattern is taken from the +command line; all arguments are treated as the names of paths to be searched. </P> <P> <b>--file-list</b>=<i>filename</i> -Read a list of files to be searched from the given file, one per line. Trailing -white space is removed from each line, and blank lines are ignored. These files -are searched before any others that may be listed on the command line. The -filename can be given as "-" to refer to the standard input. If <b>--file</b> -and <b>--file-list</b> are both specified as "-", patterns are read first. This -is useful only when the standard input is a terminal, from which further lines -(the list of files) can be read after an end-of-file indication. +Read a list of files and/or directories that are to be scanned from the given +file, one per line. Trailing white space is removed from each line, and blank +lines are ignored. These paths are processed before any that are listed on the +command line. The filename can be given as "-" to refer to the standard input. +If <b>--file</b> and <b>--file-list</b> are both specified as "-", patterns are +read first. This is useful only when the standard input is a terminal, from +which further lines (the list of files) can be read after an end-of-file +indication. If this option is given more than once, all the specified files are +read. </P> <P> <b>--file-offsets</b> @@ -338,7 +366,8 @@ If a line number is also being output, it follows the file name. <P> <b>--help</b> Output a help message, giving brief details of the command options and file -type support, and then exit. +type support, and then exit. Anything else on the command line is +ignored. </P> <P> <b>-I</b> @@ -351,24 +380,35 @@ Ignore upper/lower case distinctions during comparisons. </P> <P> <b>--include</b>=<i>pattern</i> -When <b>pcregrep</b> is searching the files in a directory as a consequence of -the <b>-r</b> (recursive search) option, only those regular files whose names -match the pattern are included. Subdirectories are always included and searched -recursively, subject to the \fP--include-dir\fP and <b>--exclude-dir</b> -options. The pattern is a PCRE regular expression, and is matched against the -final component of the file name (not the entire path). If a file name matches -both <b>--include</b> and <b>--exclude</b>, it is excluded. There is no short -form for this option. +If any <b>--include</b> patterns are specified, the only files that are +processed are those that match one of the patterns (and do not match an +<b>--exclude</b> pattern). This option does not affect directories, but it +applies to all files, whether listed on the command line, obtained from +<b>--file-list</b>, or by scanning a directory. The pattern is a PCRE regular +expression, and is matched against the final component of the file name, not +the entire path. The <b>-F</b>, <b>-w</b>, and <b>-x</b> options do not apply to +this pattern. The option may be given any number of times. If a file name +matches both an <b>--include</b> and an <b>--exclude</b> pattern, it is excluded. +There is no short form for this option. +</P> +<P> +<b>--include-from=</b><i>filename</i> +Treat each non-empty line of the file as the data for an <b>--include</b> +option. What constitutes a newline for this purpose is the operating system's +default. The <b>--newline</b> option has no effect on this option. This option +may be given any number of times; all the files are read. </P> <P> <b>--include-dir</b>=<i>pattern</i> -When <b>pcregrep</b> is searching the contents of a directory as a consequence -of the <b>-r</b> (recursive search) option, only those subdirectories whose -names match the pattern are included. (Note that the <b>--include</b> option -does not affect subdirectories.) The pattern is a PCRE regular expression, and -is matched against the final component of the name (not the entire path). If a -subdirectory name matches both <b>--include-dir</b> and <b>--exclude-dir</b>, it -is excluded. There is no short form for this option. +If any <b>--include-dir</b> patterns are specified, the only directories that +are processed are those that match one of the patterns (and do not match an +<b>--exclude-dir</b> pattern). This applies to all directories, whether listed +on the command line, obtained from <b>--file-list</b>, or by scanning a parent +directory. The pattern is a PCRE regular expression, and is matched against the +final component of the directory name, not the entire path. The <b>-F</b>, +<b>-w</b>, and <b>-x</b> options do not apply to this pattern. The option may be +given any number of times. If a directory matches both <b>--include-dir</b> and +<b>--exclude-dir</b>, it is excluded. There is no short form for this option. </P> <P> <b>-L</b>, <b>--files-without-match</b> @@ -397,7 +437,7 @@ short form for this option. When this option is given, input is read and processed line by line, and the output is flushed after each write. By default, input is read in large chunks, unless <b>pcregrep</b> can determine that it is reading from a terminal (which -is currently possible only in Unix environments). Output to terminal is +is currently possible only in Unix-like environments). Output to terminal is normally automatically flushed by the operating system. This option can be useful when the input or output is attached to a pipe and you do not want <b>pcregrep</b> to buffer up large amounts of data. However, its use will affect @@ -484,10 +524,13 @@ When the PCRE library is built, a default line-ending sequence is specified. This is normally the standard sequence for the operating system. Unless otherwise specified by this option, <b>pcregrep</b> uses the library's default. The possible values for this option are CR, LF, CRLF, ANYCRLF, or ANY. This -makes it possible to use <b>pcregrep</b> on files that have come from other +makes it possible to use <b>pcregrep</b> to scan files that have come from other environments without having to modify their line endings. If the data that is being scanned does not agree with the convention set by this option, -<b>pcregrep</b> may behave in strange ways. +<b>pcregrep</b> may behave in strange ways. Note that this option does not +apply to files specified by the <b>-f</b>, <b>--exclude-from</b>, or +<b>--include-from</b> options, which are expected to use the operating system's +standard newline sequence. </P> <P> <b>-n</b>, <b>--line-number</b> @@ -519,13 +562,24 @@ exclusive with <b>--file-offsets</b> and <b>--line-offsets</b>. <P> <b>-o</b><i>number</i>, <b>--only-matching</b>=<i>number</i> Show only the part of the line that matched the capturing parentheses of the -given number. Up to 32 capturing parentheses are supported. Because these -options can be given without an argument (see above), if an argument is -present, it must be given in the same shell item, for example, -o3 or ---only-matching=2. The comments given for the non-argument case above also -apply to this case. If the specified capturing parentheses do not exist in the -pattern, or were not set in the match, nothing is output unless the file name -or line number are being printed. +given number. Up to 32 capturing parentheses are supported, and -o0 is +equivalent to <b>-o</b> without a number. Because these options can be given +without an argument (see above), if an argument is present, it must be given in +the same shell item, for example, -o3 or --only-matching=2. The comments given +for the non-argument case above also apply to this case. If the specified +capturing parentheses do not exist in the pattern, or were not set in the +match, nothing is output unless the file name or line number are being printed. +<br> +<br> +If this option is given multiple times, multiple substrings are output, in the +order the options are given. For example, -o3 -o1 -o3 causes the substrings +matched by capturing parentheses 3 and 1 and then 3 again to be output. By +default, there is no separator (but see the next option). +</P> +<P> +<b>--om-separator</b>=<i>text</i> +Specify a separating string for multiple occurrences of <b>-o</b>. The default +is an empty string. Separating strings are never coloured. </P> <P> <b>-q</b>, <b>--quiet</b> @@ -553,13 +607,15 @@ found in other files. <P> <b>-u</b>, <b>--utf-8</b> Operate in UTF-8 mode. This option is available only if PCRE has been compiled -with UTF-8 support. Both patterns and subject lines must be valid strings of -UTF-8 characters. +with UTF-8 support. All patterns (including those for any <b>--exclude</b> and +<b>--include</b> options) and all subject lines that are scanned must be valid +strings of UTF-8 characters. </P> <P> <b>-V</b>, <b>--version</b> -Write the version numbers of <b>pcregrep</b> and the PCRE library that is being -used to the standard error stream. +Write the version numbers of <b>pcregrep</b> and the PCRE library to the +standard output and then exit. Anything else on the command line is +ignored. </P> <P> <b>-v</b>, <b>--invert-match</b> @@ -569,14 +625,18 @@ the patterns are the ones that are found. <P> <b>-w</b>, <b>--word-regex</b>, <b>--word-regexp</b> Force the patterns to match only whole words. This is equivalent to having \b -at the start and end of the pattern. +at the start and end of the pattern. This option applies only to the patterns +that are matched against the contents of files; it does not apply to patterns +specified by any of the <b>--include</b> or <b>--exclude</b> options. </P> <P> <b>-x</b>, <b>--line-regex</b>, <b>--line-regexp</b> Force the patterns to be anchored (each must start matching at the beginning of -a line) and in addition, require them to match entire lines. This is -equivalent to having ^ and $ characters at the start and end of each -alternative branch in every pattern. +a line) and in addition, require them to match entire lines. This is equivalent +to having ^ and $ characters at the start and end of each alternative branch in +every pattern. This option applies only to the patterns that are matched +against the contents of files; it does not apply to patterns specified by any +of the <b>--include</b> or <b>--exclude</b> options. </P> <br><a name="SEC6" href="#TOC1">ENVIRONMENT VARIABLES</a><br> <P> @@ -588,11 +648,15 @@ by the <b>--locale</b> option. If no locale is set, the PCRE library's default <br><a name="SEC7" href="#TOC1">NEWLINES</a><br> <P> The <b>-N</b> (<b>--newline</b>) option allows <b>pcregrep</b> to scan files with -different newline conventions from the default. However, the setting of this -option does not affect the way in which <b>pcregrep</b> writes information to -the standard error and output streams. It uses the string "\n" in C -<b>printf()</b> calls to indicate newlines, relying on the C I/O library to -convert this to an appropriate sequence if the output is sent to a file. +different newline conventions from the default. Any parts of the input files +that are written to the standard output are copied identically, with whatever +newline sequences they have in the input. However, the setting of this option +does not affect the interpretation of files specified by the <b>-f</b>, +<b>--exclude-from</b>, or <b>--include-from</b> options, which are assumed to use +the operating system's standard newline sequence, nor does it affect the way in +which <b>pcregrep</b> writes informational messages to the standard error and +output streams. For these it uses the string "\n" to indicate newlines, +relying on the C I/O library to convert this to an appropriate sequence. </P> <br><a name="SEC8" href="#TOC1">OPTIONS COMPATIBILITY</a><br> <P> @@ -601,7 +665,7 @@ as in the GNU <b>grep</b> program. Any long option of the form <b>--xxx-regexp</b> (GNU terminology) is also available as <b>--xxx-regex</b> (PCRE terminology). However, the <b>--file-list</b>, <b>--file-offsets</b>, <b>--include-dir</b>, <b>--line-offsets</b>, <b>--locale</b>, <b>--match-limit</b>, -<b>-M</b>, <b>--multiline</b>, <b>-N</b>, <b>--newline</b>, +<b>-M</b>, <b>--multiline</b>, <b>-N</b>, <b>--newline</b>, <b>--om-separator</b>, <b>--recursion-limit</b>, <b>-u</b>, and <b>--utf-8</b> options are specific to <b>pcregrep</b>, as is the use of the <b>--only-matching</b> option with a capturing parentheses number. @@ -671,7 +735,7 @@ affect the return code. </P> <br><a name="SEC12" href="#TOC1">SEE ALSO</a><br> <P> -<b>pcrepattern</b>(3), <b>pcretest</b>(1). +<b>pcrepattern</b>(3), <b>pcresyntax</b>(3), <b>pcretest</b>(1). </P> <br><a name="SEC13" href="#TOC1">AUTHOR</a><br> <P> @@ -684,7 +748,7 @@ Cambridge CB2 3QH, England. </P> <br><a name="SEC14" href="#TOC1">REVISION</a><br> <P> -Last updated: 04 March 2012 +Last updated: 13 September 2012 <br> Copyright © 1997-2012 University of Cambridge. <br> diff --git a/doc/html/pcrejit.html b/doc/html/pcrejit.html index ea1c6cc..7161e71 100644 --- a/doc/html/pcrejit.html +++ b/doc/html/pcrejit.html @@ -14,7 +14,7 @@ man page, in case the conversion went wrong. <br> <ul> <li><a name="TOC1" href="#SEC1">PCRE JUST-IN-TIME COMPILER SUPPORT</a> -<li><a name="TOC2" href="#SEC2">8-BIT and 16-BIT SUPPORT</a> +<li><a name="TOC2" href="#SEC2">8-BIT, 16-BIT AND 32-BIT SUPPORT</a> <li><a name="TOC3" href="#SEC3">AVAILABILITY OF JIT SUPPORT</a> <li><a name="TOC4" href="#SEC4">SIMPLE USE OF JIT</a> <li><a name="TOC5" href="#SEC5">UNSUPPORTED OPTIONS AND PATTERN ITEMS</a> @@ -23,9 +23,10 @@ man page, in case the conversion went wrong. <li><a name="TOC8" href="#SEC8">CONTROLLING THE JIT STACK</a> <li><a name="TOC9" href="#SEC9">JIT STACK FAQ</a> <li><a name="TOC10" href="#SEC10">EXAMPLE CODE</a> -<li><a name="TOC11" href="#SEC11">SEE ALSO</a> -<li><a name="TOC12" href="#SEC12">AUTHOR</a> -<li><a name="TOC13" href="#SEC13">REVISION</a> +<li><a name="TOC11" href="#SEC11">JIT FAST PATH API</a> +<li><a name="TOC12" href="#SEC12">SEE ALSO</a> +<li><a name="TOC13" href="#SEC13">AUTHOR</a> +<li><a name="TOC14" href="#SEC14">REVISION</a> </ul> <br><a name="SEC1" href="#TOC1">PCRE JUST-IN-TIME COMPILER SUPPORT</a><br> <P> @@ -43,13 +44,15 @@ JIT support applies only to the traditional Perl-compatible matching function. It does not apply when the DFA matching function is being used. The code for this support was written by Zoltan Herczeg. </P> -<br><a name="SEC2" href="#TOC1">8-BIT and 16-BIT SUPPORT</a><br> +<br><a name="SEC2" href="#TOC1">8-BIT, 16-BIT AND 32-BIT SUPPORT</a><br> <P> -JIT support is available for both the 8-bit and 16-bit PCRE libraries. To keep -this documentation simple, only the 8-bit interface is described in what -follows. If you are using the 16-bit library, substitute the 16-bit functions -and 16-bit structures (for example, <i>pcre16_jit_stack</i> instead of -<i>pcre_jit_stack</i>). +JIT support is available for all of the 8-bit, 16-bit and 32-bit PCRE +libraries. To keep this documentation simple, only the 8-bit interface is +described in what follows. If you are using the 16-bit library, substitute the +16-bit functions and 16-bit structures (for example, <i>pcre16_jit_stack</i> +instead of <i>pcre_jit_stack</i>). If you are using the 32-bit library, +substitute the 32-bit functions and 32-bit structures (for example, +<i>pcre32_jit_stack</i> instead of <i>pcre_jit_stack</i>). </P> <br><a name="SEC3" href="#TOC1">AVAILABILITY OF JIT SUPPORT</a><br> <P> @@ -61,6 +64,7 @@ JIT. The support is limited to the following hardware platforms: Intel x86 32-bit and 64-bit MIPS 32-bit Power PC 32-bit and 64-bit + SPARC 32-bit (experimental) </pre> If --enable-jit is set on an unsupported platform, compilation fails. </P> @@ -68,8 +72,10 @@ If --enable-jit is set on an unsupported platform, compilation fails. A program that is linked with PCRE 8.20 or later can tell if JIT support is available by calling <b>pcre_config()</b> with the PCRE_CONFIG_JIT option. The result is 1 when JIT is available, and 0 otherwise. However, a simple program -does not need to check this in order to use JIT. The API is implemented in a -way that falls back to the interpretive code if JIT is not available. +does not need to check this in order to use JIT. The normal API is implemented +in a way that falls back to the interpretive code if JIT is not available. For +programs that need the best possible performance, there is also a "fast path" +API that is JIT-specific. </P> <P> If your program may sometimes be linked with versions of PCRE that are older @@ -86,8 +92,8 @@ You have to do two things to make use of the JIT support in the simplest way: <b>pcre_exec()</b>. (2) Use <b>pcre_free_study()</b> to free the <b>pcre_extra</b> block when it is - no longer needed, instead of just freeing it yourself. This - ensures that any JIT data is also freed. + no longer needed, instead of just freeing it yourself. This ensures that + any JIT data is also freed. </pre> For a program that may be linked with pre-8.20 versions of PCRE, you can insert <pre> @@ -161,8 +167,9 @@ times as you like for matching different subject strings. <br><a name="SEC5" href="#TOC1">UNSUPPORTED OPTIONS AND PATTERN ITEMS</a><br> <P> The only <b>pcre_exec()</b> options that are supported for JIT execution are -PCRE_NO_UTF8_CHECK, PCRE_NO_UTF16_CHECK, PCRE_NOTBOL, PCRE_NOTEOL, -PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART, PCRE_PARTIAL_HARD, and PCRE_PARTIAL_SOFT. +PCRE_NO_UTF8_CHECK, PCRE_NO_UTF16_CHECK, PCRE_NO_UTF32_CHECK, PCRE_NOTBOL, +PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART, PCRE_PARTIAL_HARD, and +PCRE_PARTIAL_SOFT. </P> <P> The unsupported pattern items are: @@ -350,7 +357,7 @@ replacement. <br> No, because this is too costly in terms of resources. However, you could implement some clever idea which release the stack if it is not used in let's -say two minutes. The JIT callback can help to achive this without keeping a +say two minutes. The JIT callback can help to achieve this without keeping a list of the currently JIT studied patterns. </P> <P> @@ -398,11 +405,40 @@ callback. </PRE> </P> -<br><a name="SEC11" href="#TOC1">SEE ALSO</a><br> +<br><a name="SEC11" href="#TOC1">JIT FAST PATH API</a><br> +<P> +Because the API described above falls back to interpreted execution when JIT is +not available, it is convenient for programs that are written for general use +in many environments. However, calling JIT via <b>pcre_exec()</b> does have a +performance impact. Programs that are written for use where JIT is known to be +available, and which need the best possible performance, can instead use a +"fast path" API to call JIT execution directly instead of calling +<b>pcre_exec()</b> (obviously only for patterns that have been successfully +studied by JIT). +</P> +<P> +The fast path function is called <b>pcre_jit_exec()</b>, and it takes exactly +the same arguments as <b>pcre_exec()</b>, plus one additional argument that +must point to a JIT stack. The JIT stack arrangements described above do not +apply. The return values are the same as for <b>pcre_exec()</b>. +</P> +<P> +When you call <b>pcre_exec()</b>, as well as testing for invalid options, a +number of other sanity checks are performed on the arguments. For example, if +the subject pointer is NULL, or its length is negative, an immediate error is +given. Also, unless PCRE_NO_UTF[8|16|32] is set, a UTF subject string is tested +for validity. In the interests of speed, these checks do not happen on the JIT +fast path, and if invalid data is passed, the result is undefined. +</P> +<P> +Bypassing the sanity checks and the <b>pcre_exec()</b> wrapping can give +speedups of more than 10%. +</P> +<br><a name="SEC12" href="#TOC1">SEE ALSO</a><br> <P> <b>pcreapi</b>(3) </P> -<br><a name="SEC12" href="#TOC1">AUTHOR</a><br> +<br><a name="SEC13" href="#TOC1">AUTHOR</a><br> <P> Philip Hazel (FAQ by Zoltan Herczeg) <br> @@ -411,9 +447,9 @@ University Computing Service Cambridge CB2 3QH, England. <br> </P> -<br><a name="SEC13" href="#TOC1">REVISION</a><br> +<br><a name="SEC14" href="#TOC1">REVISION</a><br> <P> -Last updated: 04 May 2012 +Last updated: 31 October 2012 <br> Copyright © 1997-2012 University of Cambridge. <br> diff --git a/doc/html/pcrelimits.html b/doc/html/pcrelimits.html index 10920c1..b83a801 100644 --- a/doc/html/pcrelimits.html +++ b/doc/html/pcrelimits.html @@ -21,11 +21,12 @@ practice be relevant. </P> <P> The maximum length of a compiled pattern is approximately 64K data units (bytes -for the 8-bit library, 16-bit units for the 16-bit library) if PCRE is compiled -with the default internal linkage size of 2 bytes. If you want to process -regular expressions that are truly enormous, you can compile PCRE with an -internal linkage size of 3 or 4 (when building the 16-bit library, 3 is rounded -up to 4). See the <b>README</b> file in the source distribution and the +for the 8-bit library, 32-bit units for the 32-bit library, and 32-bit units for +the 32-bit library) if PCRE is compiled with the default internal linkage size +of 2 bytes. If you want to process regular expressions that are truly enormous, +you can compile PCRE with an internal linkage size of 3 or 4 (when building the +16-bit or 32-bit library, 3 is rounded up to 4). See the <b>README</b> file in +the source distribution and the <a href="pcrebuild.html"><b>pcrebuild</b></a> documentation for details. In these cases the limit is substantially larger. However, the speed of execution is slower. @@ -49,7 +50,7 @@ maximum number of named subpatterns is 10000. </P> <P> The maximum length of a name in a (*MARK), (*PRUNE), (*SKIP), or (*THEN) verb -is 255 for the 8-bit library and 65535 for the 16-bit library. +is 255 for the 8-bit library and 65535 for the 16-bit and 32-bit library. </P> <P> The maximum length of a subject string is the largest positive number that an diff --git a/doc/html/pcrematching.html b/doc/html/pcrematching.html index 6abd17e..f185431 100644 --- a/doc/html/pcrematching.html +++ b/doc/html/pcrematching.html @@ -26,18 +26,19 @@ man page, in case the conversion went wrong. <P> This document describes the two different algorithms that are available in PCRE for matching a compiled regular expression against a given subject string. The -"standard" algorithm is the one provided by the <b>pcre_exec()</b> and -<b>pcre16_exec()</b> functions. These work in the same was as Perl's matching -function, and provide a Perl-compatible matching operation. The just-in-time -(JIT) optimization that is described in the +"standard" algorithm is the one provided by the <b>pcre_exec()</b>, +<b>pcre16_exec()</b> and <b>pcre32_exec()</b> functions. These work in the same +as as Perl's matching function, and provide a Perl-compatible matching operation. +The just-in-time (JIT) optimization that is described in the <a href="pcrejit.html"><b>pcrejit</b></a> documentation is compatible with these functions. </P> <P> -An alternative algorithm is provided by the <b>pcre_dfa_exec()</b> and -<b>pcre16_dfa_exec()</b> functions; they operate in a different way, and are not -Perl-compatible. This alternative has advantages and disadvantages compared -with the standard algorithm, and these are described below. +An alternative algorithm is provided by the <b>pcre_dfa_exec()</b>, +<b>pcre16_dfa_exec()</b> and <b>pcre32_dfa_exec()</b> functions; they operate in +a different way, and are not Perl-compatible. This alternative has advantages +and disadvantages compared with the standard algorithm, and these are described +below. </P> <P> When there is only one possible way in which a given subject string can match a @@ -167,9 +168,9 @@ always 1, and the value of the <i>capture_last</i> field is always -1. </P> <P> 7. The \C escape sequence, which (in the standard algorithm) always matches a -single data unit, even in UTF-8 or UTF-16 modes, is not supported in these -modes, because the alternative algorithm moves through the subject string one -character (not data unit) at a time, for all active paths through the tree. +single data unit, even in UTF-8, UTF-16 or UTF-32 modes, is not supported in +these modes, because the alternative algorithm moves through the subject string +one character (not data unit) at a time, for all active paths through the tree. </P> <P> 8. Except for (*FAIL), the backtracking control verbs such as (*PRUNE) are not diff --git a/doc/html/pcrepartial.html b/doc/html/pcrepartial.html index 35c4d2d..298f92e 100644 --- a/doc/html/pcrepartial.html +++ b/doc/html/pcrepartial.html @@ -14,13 +14,13 @@ man page, in case the conversion went wrong. <br> <ul> <li><a name="TOC1" href="#SEC1">PARTIAL MATCHING IN PCRE</a> -<li><a name="TOC2" href="#SEC2">PARTIAL MATCHING USING pcre_exec() OR pcre16_exec()</a> -<li><a name="TOC3" href="#SEC3">PARTIAL MATCHING USING pcre_dfa_exec() OR pcre16_dfa_exec()</a> +<li><a name="TOC2" href="#SEC2">PARTIAL MATCHING USING pcre_exec() OR pcre[16|32]_exec()</a> +<li><a name="TOC3" href="#SEC3">PARTIAL MATCHING USING pcre_dfa_exec() OR pcre[16|32]_dfa_exec()</a> <li><a name="TOC4" href="#SEC4">PARTIAL MATCHING AND WORD BOUNDARIES</a> <li><a name="TOC5" href="#SEC5">FORMERLY RESTRICTED PATTERNS</a> <li><a name="TOC6" href="#SEC6">EXAMPLE OF PARTIAL MATCHING USING PCRETEST</a> -<li><a name="TOC7" href="#SEC7">MULTI-SEGMENT MATCHING WITH pcre_dfa_exec() OR pcre16_dfa_exec()</a> -<li><a name="TOC8" href="#SEC8">MULTI-SEGMENT MATCHING WITH pcre_exec() OR pcre16_exec()</a> +<li><a name="TOC7" href="#SEC7">MULTI-SEGMENT MATCHING WITH pcre_dfa_exec() OR pcre[16|32]_dfa_exec()</a> +<li><a name="TOC8" href="#SEC8">MULTI-SEGMENT MATCHING WITH pcre_exec() OR pcre[16|32]_exec()</a> <li><a name="TOC9" href="#SEC9">ISSUES WITH MULTI-SEGMENT MATCHING</a> <li><a name="TOC10" href="#SEC10">AUTHOR</a> <li><a name="TOC11" href="#SEC11">REVISION</a> @@ -59,8 +59,8 @@ are set, PCRE_PARTIAL_HARD takes precedence. </P> <P> If you want to use partial matching with just-in-time optimized code, you must -call <b>pcre_study()</b> or <b>pcre16_study()</b> with one or both of these -options: +call <b>pcre_study()</b>, <b>pcre16_study()</b> or <b>pcre32_study()</b> with one +or both of these options: <pre> PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE @@ -78,10 +78,10 @@ partially. If the pattern was studied, PCRE knows the minimum length of a matching string, and does not bother to run the matching function on shorter strings. This optimization is also disabled for partial matching. </P> -<br><a name="SEC2" href="#TOC1">PARTIAL MATCHING USING pcre_exec() OR pcre16_exec()</a><br> +<br><a name="SEC2" href="#TOC1">PARTIAL MATCHING USING pcre_exec() OR pcre[16|32]_exec()</a><br> <P> A partial match occurs during a call to <b>pcre_exec()</b> or -<b>pcre16_exec()</b> when the end of the subject string is reached successfully, +<b>pcre[16|32]_exec()</b> when the end of the subject string is reached successfully, but matching cannot continue because more characters are needed. However, at least one character in the subject must have been inspected. This character need not form part of the final matched string; lookbehind assertions and the @@ -114,10 +114,10 @@ What happens when a partial match is identified depends on which of the two partial matching options are set. </P> <br><b> -PCRE_PARTIAL_SOFT WITH pcre_exec() OR pcre16_exec() +PCRE_PARTIAL_SOFT WITH pcre_exec() OR pcre[16|32]_exec() </b><br> <P> -If PCRE_PARTIAL_SOFT is set when <b>pcre_exec()</b> or <b>pcre16_exec()</b> +If PCRE_PARTIAL_SOFT is set when <b>pcre_exec()</b> or <b>pcre[16|32]_exec()</b> identifies a partial match, the partial match is remembered, but matching continues as normal, and other alternatives in the pattern are tried. If no complete match can be found, PCRE_ERROR_PARTIAL is returned instead of @@ -144,10 +144,10 @@ example, there are two partial matches, because "dog" on its own partially matches the second alternative.) </P> <br><b> -PCRE_PARTIAL_HARD WITH pcre_exec() OR pcre16_exec() +PCRE_PARTIAL_HARD WITH pcre_exec() OR pcre[16|32]_exec() </b><br> <P> -If PCRE_PARTIAL_HARD is set for <b>pcre_exec()</b> or <b>pcre16_exec()</b>, +If PCRE_PARTIAL_HARD is set for <b>pcre_exec()</b> or <b>pcre[16|32]_exec()</b>, PCRE_ERROR_PARTIAL is returned as soon as a partial match is found, without continuing to search for possible complete matches. This option is "hard" because it prefers an earlier partial match over a later complete match. For @@ -192,7 +192,7 @@ to follow this explanation by thinking of the two patterns like this: The second pattern will never match "dogsbody", because it will always find the shorter match first. </P> -<br><a name="SEC3" href="#TOC1">PARTIAL MATCHING USING pcre_dfa_exec() OR pcre16_dfa_exec()</a><br> +<br><a name="SEC3" href="#TOC1">PARTIAL MATCHING USING pcre_dfa_exec() OR pcre[16|32]_dfa_exec()</a><br> <P> The DFA functions move along the subject string character by character, without backtracking, searching for all possible matches simultaneously. If the end of @@ -280,7 +280,7 @@ if DFA matching is used. If the escape sequence \P is present more than once in a <b>pcretest</b> data line, the PCRE_PARTIAL_HARD option is set for the match. </P> -<br><a name="SEC7" href="#TOC1">MULTI-SEGMENT MATCHING WITH pcre_dfa_exec() OR pcre16_dfa_exec()</a><br> +<br><a name="SEC7" href="#TOC1">MULTI-SEGMENT MATCHING WITH pcre_dfa_exec() OR pcre[16|32]_dfa_exec()</a><br> <P> When a partial match has been found using a DFA matching function, it is possible to continue the match by providing additional subject data and calling @@ -308,7 +308,7 @@ PCRE_DFA_RESTART to continue partial matching over multiple segments. This facility can be used to pass very long subject strings to the DFA matching functions. </P> -<br><a name="SEC8" href="#TOC1">MULTI-SEGMENT MATCHING WITH pcre_exec() OR pcre16_exec()</a><br> +<br><a name="SEC8" href="#TOC1">MULTI-SEGMENT MATCHING WITH pcre_exec() OR pcre[16|32]_exec()</a><br> <P> From release 8.00, the standard matching functions can also be used to do multi-segment matching. Unlike the DFA functions, it is not possible to @@ -356,7 +356,7 @@ includes the effect of PCRE_NOTEOL. offsets that are returned for a partial match. However a lookbehind assertion later in the pattern could require even earlier characters to be inspected. You can handle this case by using the PCRE_INFO_MAXLOOKBEHIND option of the -<b>pcre_fullinfo()</b> or <b>pcre16_fullinfo()</b> functions to obtain the length +<b>pcre_fullinfo()</b> or <b>pcre[16|32]_fullinfo()</b> functions to obtain the length of the largest lookbehind in the pattern. This length is given in characters, not bytes. If you always retain at least that many characters before the partially matched string, all should be well. (Of course, near the start of the @@ -465,7 +465,7 @@ Cambridge CB2 3QH, England. </P> <br><a name="SEC11" href="#TOC1">REVISION</a><br> <P> -Last updated: 24 February 2012 +Last updated: 24 June 2012 <br> Copyright © 1997-2012 University of Cambridge. <br> diff --git a/doc/html/pcrepattern.html b/doc/html/pcrepattern.html index 59619cc..93c3e1f 100644 --- a/doc/html/pcrepattern.html +++ b/doc/html/pcrepattern.html @@ -14,33 +14,34 @@ man page, in case the conversion went wrong. <br> <ul> <li><a name="TOC1" href="#SEC1">PCRE REGULAR EXPRESSION DETAILS</a> -<li><a name="TOC2" href="#SEC2">NEWLINE CONVENTIONS</a> -<li><a name="TOC3" href="#SEC3">CHARACTERS AND METACHARACTERS</a> -<li><a name="TOC4" href="#SEC4">BACKSLASH</a> -<li><a name="TOC5" href="#SEC5">CIRCUMFLEX AND DOLLAR</a> -<li><a name="TOC6" href="#SEC6">FULL STOP (PERIOD, DOT) AND \N</a> -<li><a name="TOC7" href="#SEC7">MATCHING A SINGLE DATA UNIT</a> -<li><a name="TOC8" href="#SEC8">SQUARE BRACKETS AND CHARACTER CLASSES</a> -<li><a name="TOC9" href="#SEC9">POSIX CHARACTER CLASSES</a> -<li><a name="TOC10" href="#SEC10">VERTICAL BAR</a> -<li><a name="TOC11" href="#SEC11">INTERNAL OPTION SETTING</a> -<li><a name="TOC12" href="#SEC12">SUBPATTERNS</a> -<li><a name="TOC13" href="#SEC13">DUPLICATE SUBPATTERN NUMBERS</a> -<li><a name="TOC14" href="#SEC14">NAMED SUBPATTERNS</a> -<li><a name="TOC15" href="#SEC15">REPETITION</a> -<li><a name="TOC16" href="#SEC16">ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS</a> -<li><a name="TOC17" href="#SEC17">BACK REFERENCES</a> -<li><a name="TOC18" href="#SEC18">ASSERTIONS</a> -<li><a name="TOC19" href="#SEC19">CONDITIONAL SUBPATTERNS</a> -<li><a name="TOC20" href="#SEC20">COMMENTS</a> -<li><a name="TOC21" href="#SEC21">RECURSIVE PATTERNS</a> -<li><a name="TOC22" href="#SEC22">SUBPATTERNS AS SUBROUTINES</a> -<li><a name="TOC23" href="#SEC23">ONIGURUMA SUBROUTINE SYNTAX</a> -<li><a name="TOC24" href="#SEC24">CALLOUTS</a> -<li><a name="TOC25" href="#SEC25">BACKTRACKING CONTROL</a> -<li><a name="TOC26" href="#SEC26">SEE ALSO</a> -<li><a name="TOC27" href="#SEC27">AUTHOR</a> -<li><a name="TOC28" href="#SEC28">REVISION</a> +<li><a name="TOC2" href="#SEC2">EBCDIC CHARACTER CODES</a> +<li><a name="TOC3" href="#SEC3">NEWLINE CONVENTIONS</a> +<li><a name="TOC4" href="#SEC4">CHARACTERS AND METACHARACTERS</a> +<li><a name="TOC5" href="#SEC5">BACKSLASH</a> +<li><a name="TOC6" href="#SEC6">CIRCUMFLEX AND DOLLAR</a> +<li><a name="TOC7" href="#SEC7">FULL STOP (PERIOD, DOT) AND \N</a> +<li><a name="TOC8" href="#SEC8">MATCHING A SINGLE DATA UNIT</a> +<li><a name="TOC9" href="#SEC9">SQUARE BRACKETS AND CHARACTER CLASSES</a> +<li><a name="TOC10" href="#SEC10">POSIX CHARACTER CLASSES</a> +<li><a name="TOC11" href="#SEC11">VERTICAL BAR</a> +<li><a name="TOC12" href="#SEC12">INTERNAL OPTION SETTING</a> +<li><a name="TOC13" href="#SEC13">SUBPATTERNS</a> +<li><a name="TOC14" href="#SEC14">DUPLICATE SUBPATTERN NUMBERS</a> +<li><a name="TOC15" href="#SEC15">NAMED SUBPATTERNS</a> +<li><a name="TOC16" href="#SEC16">REPETITION</a> +<li><a name="TOC17" href="#SEC17">ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS</a> +<li><a name="TOC18" href="#SEC18">BACK REFERENCES</a> +<li><a name="TOC19" href="#SEC19">ASSERTIONS</a> +<li><a name="TOC20" href="#SEC20">CONDITIONAL SUBPATTERNS</a> +<li><a name="TOC21" href="#SEC21">COMMENTS</a> +<li><a name="TOC22" href="#SEC22">RECURSIVE PATTERNS</a> +<li><a name="TOC23" href="#SEC23">SUBPATTERNS AS SUBROUTINES</a> +<li><a name="TOC24" href="#SEC24">ONIGURUMA SUBROUTINE SYNTAX</a> +<li><a name="TOC25" href="#SEC25">CALLOUTS</a> +<li><a name="TOC26" href="#SEC26">BACKTRACKING CONTROL</a> +<li><a name="TOC27" href="#SEC27">SEE ALSO</a> +<li><a name="TOC28" href="#SEC28">AUTHOR</a> +<li><a name="TOC29" href="#SEC29">REVISION</a> </ul> <br><a name="SEC1" href="#TOC1">PCRE REGULAR EXPRESSION DETAILS</a><br> <P> @@ -61,15 +62,17 @@ description of PCRE's regular expressions is intended as reference material. </P> <P> The original operation of PCRE was on strings of one-byte characters. However, -there is now also support for UTF-8 strings in the original library, and a -second library that supports 16-bit and UTF-16 character strings. To use these +there is now also support for UTF-8 strings in the original library, an +extra library that supports 16-bit and UTF-16 character strings, and an +extra library that supports 32-bit and UTF-32 character strings. To use these features, PCRE must be built to include appropriate support. When using UTF -strings you must either call the compiling function with the PCRE_UTF8 or -PCRE_UTF16 option, or the pattern must start with one of these special -sequences: +strings you must either call the compiling function with the PCRE_UTF8, +PCRE_UTF16 or PCRE_UTF32 option, or the pattern must start with one of +these special sequences: <pre> (*UTF8) (*UTF16) + (*UTF32) </pre> Starting a pattern with such a sequence is equivalent to setting the relevant option. This feature is not Perl-compatible. How setting a UTF mode affects @@ -80,7 +83,7 @@ page. </P> <P> Another special sequence that may appear at the start of a pattern or in -combination with (*UTF8) or (*UTF16) is: +combination with (*UTF8) or (*UTF16) or (*UTF32) is: <pre> (*UCP) </pre> @@ -98,16 +101,24 @@ of newlines; they are described below. <P> The remainder of this document discusses the patterns that are supported by PCRE when one its main matching functions, <b>pcre_exec()</b> (8-bit) or -<b>pcre16_exec()</b> (16-bit), is used. PCRE also has alternative matching -functions, <b>pcre_dfa_exec()</b> and <b>pcre16_dfa_exec()</b>, which match using -a different algorithm that is not Perl-compatible. Some of the features -discussed below are not available when DFA matching is used. The advantages and -disadvantages of the alternative functions, and how they differ from the normal -functions, are discussed in the +<b>pcre[16|32]_exec()</b> (16- or 32-bit), is used. PCRE also has alternative +matching functions, <b>pcre_dfa_exec()</b> and <b>pcre[16|32_dfa_exec()</b>, +which match using a different algorithm that is not Perl-compatible. Some of +the features discussed below are not available when DFA matching is used. The +advantages and disadvantages of the alternative functions, and how they differ +from the normal functions, are discussed in the <a href="pcrematching.html"><b>pcrematching</b></a> page. +</P> +<br><a name="SEC2" href="#TOC1">EBCDIC CHARACTER CODES</a><br> +<P> +PCRE can be compiled to run in an environment that uses EBCDIC as its character +code rather than ASCII or Unicode (typically a mainframe system). In the +sections below, character code values are ASCII or Unicode; in an EBCDIC +environment these characters may have different code values, and there are no +code points greater than 255. <a name="newlines"></a></P> -<br><a name="SEC2" href="#TOC1">NEWLINE CONVENTIONS</a><br> +<br><a name="SEC3" href="#TOC1">NEWLINE CONVENTIONS</a><br> <P> PCRE supports five different conventions for indicating line breaks in strings: a single CR (carriage return) character, a single LF (linefeed) @@ -150,7 +161,7 @@ description of \R in the section entitled below. A change of \R setting can be combined with a change of newline convention. </P> -<br><a name="SEC3" href="#TOC1">CHARACTERS AND METACHARACTERS</a><br> +<br><a name="SEC4" href="#TOC1">CHARACTERS AND METACHARACTERS</a><br> <P> A regular expression is a pattern that is matched against a subject string from left to right. Most characters stand for themselves in a pattern, and match the @@ -207,7 +218,7 @@ a character class the only metacharacters are: </pre> The following sections describe the use of each of the metacharacters. </P> -<br><a name="SEC4" href="#TOC1">BACKSLASH</a><br> +<br><a name="SEC5" href="#TOC1">BACKSLASH</a><br> <P> The backslash character has several uses. Firstly, if it is followed by a character that is not a number or a letter, it takes away any special meaning @@ -273,14 +284,22 @@ one of the following escape sequences than the binary character it represents: \x{hhh..} character with hex code hhh.. (non-JavaScript mode) \uhhhh character with hex code hhhh (JavaScript mode only) </pre> -The precise effect of \cx is as follows: if x is a lower case letter, it -is converted to upper case. Then bit 6 of the character (hex 40) is inverted. -Thus \cz becomes hex 1A (z is 7A), but \c{ becomes hex 3B ({ is 7B), while -\c; becomes hex 7B (; is 3B). If the byte following \c has a value greater -than 127, a compile-time error occurs. This locks out non-ASCII characters in -all modes. (When PCRE is compiled in EBCDIC mode, all byte values are valid. A -lower case letter is converted to upper case, and then the 0xc0 bits are -flipped.) +The precise effect of \cx on ASCII characters is as follows: if x is a lower +case letter, it is converted to upper case. Then bit 6 of the character (hex +40) is inverted. Thus \cA to \cZ become hex 01 to hex 1A (A is 41, Z is 5A), +but \c{ becomes hex 3B ({ is 7B), and \c; becomes hex 7B (; is 3B). If the +data item (byte or 16-bit value) following \c has a value greater than 127, a +compile-time error occurs. This locks out non-ASCII characters in all modes. +</P> +<P> +The \c facility was designed for use with ASCII characters, but with the +extension to Unicode it is even less useful than it once was. It is, however, +recognized when PCRE is compiled in EBCDIC mode, where data items are always +bytes. In this mode, all values are valid after \c. If the next character is a +lower case letter, it is converted to upper case. Then the 0xc0 bits of the +byte are inverted. Thus \cA becomes hex 01, as in ASCII (A is C1), but because +the EBCDIC letters are disjoint, \cZ becomes hex 29 (Z is E9), and other +characters also generate different values. </P> <P> By default, after \x, from zero to two hexadecimal digits are read (letters @@ -291,9 +310,11 @@ between \x{ and }, but the character code is constrained as follows: 8-bit UTF-8 mode less than 0x10ffff and a valid codepoint 16-bit non-UTF mode less than 0x10000 16-bit UTF-16 mode less than 0x10ffff and a valid codepoint + 32-bit non-UTF mode less than 0x80000000 + 32-bit UTF-32 mode less than 0x10ffff and a valid codepoint </pre> Invalid Unicode codepoints are the range 0xd800 to 0xdfff (the so-called -"surrogate" codepoints). +"surrogate" codepoints), and 0xffef. </P> <P> If characters other than hexadecimal digits appear between \x{ and }, or if @@ -341,7 +362,7 @@ subsequent digits stand for themselves. The value of the character is constrained in the same way as characters specified in hexadecimal. For example: <pre> - \040 is another way of writing a space + \040 is another way of writing an ASCII space \40 is the same, provided there are fewer than 40 previous capturing subpatterns \7 is always a back reference \11 might be a back reference, or another way of writing a tab @@ -475,7 +496,7 @@ release 5.10. In contrast to the other sequences, which match only ASCII characters by default, these always match certain high-valued codepoints, whether or not PCRE_UCP is set. The horizontal space characters are: <pre> - U+0009 Horizontal tab + U+0009 Horizontal tab (HT) U+0020 Space U+00A0 Non-break space U+1680 Ogham space mark @@ -497,11 +518,11 @@ whether or not PCRE_UCP is set. The horizontal space characters are: </pre> The vertical space characters are: <pre> - U+000A Linefeed - U+000B Vertical tab - U+000C Form feed - U+000D Carriage return - U+0085 Next line + U+000A Linefeed (LF) + U+000B Vertical tab (VT) + U+000C Form feed (FF) + U+000D Carriage return (CR) + U+0085 Next line (NEL) U+2028 Line separator U+2029 Paragraph separator </pre> @@ -553,7 +574,7 @@ change of newline convention; for example, a pattern can start with: <pre> (*ANY)(*BSR_ANYCRLF) </pre> -They can also be combined with the (*UTF8), (*UTF16), or (*UCP) special +They can also be combined with the (*UTF8), (*UTF16), (*UTF32) or (*UCP) special sequences. Inside a character class, \R is treated as an unrecognized escape sequence, and so matches the letter "R" by default, but causes an error if PCRE_EXTRA is set. @@ -570,7 +591,7 @@ The extra escape sequences are: <pre> \p{<i>xx</i>} a character with the <i>xx</i> property \P{<i>xx</i>} a character without the <i>xx</i> property - \X an extended Unicode sequence + \X a Unicode extended grapheme cluster </pre> The property names represented by <i>xx</i> above are limited to the Unicode script names, the general category properties, "Any", which matches any @@ -765,7 +786,8 @@ 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 turned off -(see the discussion of PCRE_NO_UTF8_CHECK and PCRE_NO_UTF16_CHECK in the +(see the discussion of PCRE_NO_UTF8_CHECK, PCRE_NO_UTF16_CHECK and +PCRE_NO_UTF32_CHECK in the <a href="pcreapi.html"><b>pcreapi</b></a> page). Perl does not support the Cs property. </P> @@ -784,39 +806,69 @@ Specifying caseless matching does not affect these escape sequences. For example, \p{Lu} always matches only upper case letters. </P> <P> -The \X escape matches any number of Unicode characters that form an extended -Unicode sequence. \X is equivalent to +Matching characters by Unicode property is not fast, because PCRE has to do a +multistage table lookup in order to find a character's property. 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 (*UCP). +</P> +<br><b> +Extended grapheme clusters +</b><br> +<P> +The \X escape matches any number of Unicode characters that form an "extended +grapheme cluster", and treats the sequence as an atomic group +<a href="#atomicgroup">(see below).</a> +Up to and including release 8.31, PCRE matched an earlier, simpler definition +that was equivalent to <pre> (?>\PM\pM*) </pre> -That is, it matches a character without the "mark" property, followed by zero -or more characters with the "mark" property, and treats the sequence as an -atomic group -<a href="#atomicgroup">(see below).</a> -Characters with the "mark" property are typically accents that affect the -preceding character. None of them have codepoints less than 256, so in -8-bit non-UTF-8 mode \X matches any one character. +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. </P> <P> -Note that recent versions of Perl have changed \X to match what Unicode calls -an "extended grapheme cluster", which has a more complicated definition. +This simple definition was extended in Unicode to include more complicated +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. </P> <P> -Matching characters by Unicode property is not fast, because PCRE has to search -a structure that contains data for over fifteen thousand characters. That is -why the traditional escape sequences such as \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 (*UCP). +\X always matches at least one character. Then it decides whether to add +additional characters according to the following rules for ending a cluster: +</P> +<P> +1. End at the end of the subject string. +</P> +<P> +2. Do not end between CR and LF; otherwise end after any control character. +</P> +<P> +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. +</P> +<P> +4. Do not end before extending characters or spacing marks. Characters with +the "mark" property always have the "extend" grapheme breaking property. +</P> +<P> +5. Do not end after prepend characters. +</P> +<P> +6. Otherwise, end the cluster. <a name="extraprops"></a></P> <br><b> PCRE's additional properties </b><br> <P> -As well as the standard Unicode properties described in the previous -section, PCRE supports four more that make it possible to convert traditional -escape sequences such as \w and \s and POSIX character classes to use Unicode -properties. PCRE uses these non-standard, non-Perl properties internally when -PCRE_UCP is set. They are: +As well as the standard Unicode properties described above, PCRE supports four +more that make it possible to convert traditional escape sequences such as \w +and \s and POSIX character classes to use Unicode properties. PCRE uses these +non-standard, non-Perl properties internally when PCRE_UCP is set. They are: <pre> Xan Any alphanumeric character Xps Any POSIX space character @@ -924,7 +976,7 @@ 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. </P> -<br><a name="SEC5" href="#TOC1">CIRCUMFLEX AND DOLLAR</a><br> +<br><a name="SEC6" href="#TOC1">CIRCUMFLEX AND DOLLAR</a><br> <P> 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 @@ -978,7 +1030,7 @@ 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. <a name="fullstopdot"></a></P> -<br><a name="SEC6" href="#TOC1">FULL STOP (PERIOD, DOT) AND \N</a><br> +<br><a name="SEC7" href="#TOC1">FULL STOP (PERIOD, DOT) AND \N</a><br> <P> Outside a character class, a dot in the pattern matches any one character in the subject string except (by default) a character that signifies the end of a @@ -1009,19 +1061,20 @@ 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. </P> -<br><a name="SEC7" href="#TOC1">MATCHING A SINGLE DATA UNIT</a><br> +<br><a name="SEC8" href="#TOC1">MATCHING A SINGLE DATA UNIT</a><br> <P> 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. Unlike a dot, \C always +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 usefully 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 or PCRE_NO_UTF16_CHECK option -is used). +start of processing unless the PCRE_NO_UTF8_CHECK, PCRE_NO_UTF16_CHECK or +PCRE_NO_UTF32_CHECK option is used). </P> <P> PCRE does not allow \C to appear in lookbehind assertions @@ -1048,7 +1101,7 @@ character for values whose encoding uses 1, 2, 3, or 4 bytes, respectively. The character's individual bytes are then captured by the appropriate number of groups. <a name="characterclass"></a></P> -<br><a name="SEC8" href="#TOC1">SQUARE BRACKETS AND CHARACTER CLASSES</a><br> +<br><a name="SEC9" href="#TOC1">SQUARE BRACKETS AND CHARACTER CLASSES</a><br> <P> An opening square bracket introduces a character class, terminated by a closing square bracket. A closing square bracket on its own is not special by default. @@ -1076,9 +1129,9 @@ string, and therefore it fails if the current pointer is at the end of the string. </P> <P> -In UTF-8 (UTF-16) mode, characters with values greater than 255 (0xffff) can be -included in a class as a literal string of data units, or by using the \x{ -escaping mechanism. +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, or by using the +\x{ escaping mechanism. </P> <P> When caseless matching is set, any letters in a class represent both their @@ -1158,7 +1211,7 @@ introducing a POSIX class name - see the next section), and the terminating closing square bracket. However, escaping other non-alphanumeric characters does no harm. </P> -<br><a name="SEC9" href="#TOC1">POSIX CHARACTER CLASSES</a><br> +<br><a name="SEC10" href="#TOC1">POSIX CHARACTER CLASSES</a><br> <P> Perl supports the POSIX notation for character classes. This uses names enclosed by [: and :] within the enclosing square brackets. PCRE also supports @@ -1220,7 +1273,7 @@ Negated versions, such as [:^alpha:] use \P instead of \p. The other POSIX classes are unchanged, and match only characters with code points less than 128. </P> -<br><a name="SEC10" href="#TOC1">VERTICAL BAR</a><br> +<br><a name="SEC11" href="#TOC1">VERTICAL BAR</a><br> <P> Vertical bar characters are used to separate alternative patterns. For example, the pattern @@ -1235,7 +1288,7 @@ that succeeds is used. If the alternatives are within a subpattern "succeeds" means matching the rest of the main pattern as well as the alternative in the subpattern. </P> -<br><a name="SEC11" href="#TOC1">INTERNAL OPTION SETTING</a><br> +<br><a name="SEC12" href="#TOC1">INTERNAL OPTION SETTING</a><br> <P> The settings of the PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, and PCRE_EXTENDED options (which are Perl-compatible) can be changed from within @@ -1291,11 +1344,12 @@ 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 <a href="#newlineseq">"Newline sequences"</a> -above. There are also the (*UTF8), (*UTF16), and (*UCP) leading sequences that -can be used to set UTF and Unicode property modes; they are equivalent to -setting the PCRE_UTF8, PCRE_UTF16, and the PCRE_UCP options, respectively. +above. There are also the (*UTF8), (*UTF16),(*UTF32) and (*UCP) leading +sequences that can be used to set UTF and Unicode property modes; they are +equivalent to setting the PCRE_UTF8, PCRE_UTF16, PCRE_UTF32 and the PCRE_UCP +options, respectively. <a name="subpattern"></a></P> -<br><a name="SEC12" href="#TOC1">SUBPATTERNS</a><br> +<br><a name="SEC13" href="#TOC1">SUBPATTERNS</a><br> <P> Subpatterns are delimited by parentheses (round brackets), which can be nested. Turning part of a pattern into a subpattern does two things: @@ -1351,7 +1405,7 @@ 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". <a name="dupsubpatternnumber"></a></P> -<br><a name="SEC13" href="#TOC1">DUPLICATE SUBPATTERN NUMBERS</a><br> +<br><a name="SEC14" href="#TOC1">DUPLICATE SUBPATTERN NUMBERS</a><br> <P> 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 @@ -1395,7 +1449,7 @@ true if any of the subpatterns of that number have matched. An alternative approach to using this "branch reset" feature is to use duplicate named subpatterns, as described in the next section. </P> -<br><a name="SEC14" href="#TOC1">NAMED SUBPATTERNS</a><br> +<br><a name="SEC15" href="#TOC1">NAMED SUBPATTERNS</a><br> <P> Identifying capturing parentheses by number is simple, but it can be very hard to keep track of the numbers in complicated regular expressions. Furthermore, @@ -1470,7 +1524,7 @@ matching. For this reason, an error is given at compile time if different names are given to subpatterns with the same number. However, you can give the same name to subpatterns with the same number, even when PCRE_DUPNAMES is not set. </P> -<br><a name="SEC15" href="#TOC1">REPETITION</a><br> +<br><a name="SEC16" href="#TOC1">REPETITION</a><br> <P> Repetition is specified by quantifiers, which can follow any of the following items: @@ -1513,8 +1567,8 @@ 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 of which is represented by a two-byte sequence in a UTF-8 string. Similarly, -\X{3} matches three Unicode extended sequences, each of which may be several -data units long (and they may be of different lengths). +\X{3} matches three Unicode extended grapheme clusters, each of which may be +several data units long (and they may be of different lengths). </P> <P> The quantifier {0} is permitted, causing the expression to behave as if the @@ -1603,7 +1657,7 @@ worth setting PCRE_DOTALL in order to obtain this optimization, or alternatively using ^ to indicate anchoring explicitly. </P> <P> -However, there is one situation where the optimization cannot be used. When .* +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: @@ -1614,6 +1668,16 @@ If the subject is "xyz123abc123" the match point is the fourth character. For this reason, such a pattern is not implicitly anchored. </P> <P> +Another case where implicit anchoring is not applied is when the leading .* is +inside an atomic group. Once again, a match at the start may fail where a later +one succeeds. Consider this pattern: +<pre> + (?>.*?a)b +</pre> +It matches "ab" in the subject "aab". The use of the backtracking control verbs +(*PRUNE) and (*SKIP) also disable this optimization. +</P> +<P> When a capturing subpattern is repeated, the value captured is the substring that matched the final iteration. For example, after <pre> @@ -1628,7 +1692,7 @@ example, after </pre> matches "aba" the value of the second captured substring is "b". <a name="atomicgroup"></a></P> -<br><a name="SEC16" href="#TOC1">ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS</a><br> +<br><a name="SEC17" href="#TOC1">ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS</a><br> <P> With both maximizing ("greedy") and minimizing ("ungreedy" or "lazy") repetition, failure of what follows normally causes the repeated item to be @@ -1732,7 +1796,7 @@ an atomic group, like this: </pre> sequences of non-digits cannot be broken, and failure happens quickly. <a name="backreferences"></a></P> -<br><a name="SEC17" href="#TOC1">BACK REFERENCES</a><br> +<br><a name="SEC18" href="#TOC1">BACK REFERENCES</a><br> <P> Outside a character class, a backslash followed by a digit greater than 0 (and possibly further digits) is a back reference to a capturing subpattern earlier @@ -1860,7 +1924,7 @@ as an Once the whole group has been matched, a subsequent matching failure cannot cause backtracking into the middle of the group. <a name="bigassertions"></a></P> -<br><a name="SEC18" href="#TOC1">ASSERTIONS</a><br> +<br><a name="SEC19" href="#TOC1">ASSERTIONS</a><br> <P> An assertion is a test on the characters following or preceding the current matching point that does not actually consume any characters. The simple @@ -2050,7 +2114,7 @@ preceded by "foo", while is another pattern that matches "foo" preceded by three digits and any three characters that are not "999". <a name="conditions"></a></P> -<br><a name="SEC19" href="#TOC1">CONDITIONAL SUBPATTERNS</a><br> +<br><a name="SEC20" href="#TOC1">CONDITIONAL SUBPATTERNS</a><br> <P> It is possible to cause the matching process to obey a subpattern conditionally or to choose between two alternative subpatterns, depending on @@ -2205,7 +2269,7 @@ 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. <a name="comments"></a></P> -<br><a name="SEC20" href="#TOC1">COMMENTS</a><br> +<br><a name="SEC21" href="#TOC1">COMMENTS</a><br> <P> 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 character class, @@ -2234,7 +2298,7 @@ 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. <a name="recursion"></a></P> -<br><a name="SEC21" href="#TOC1">RECURSIVE PATTERNS</a><br> +<br><a name="SEC22" href="#TOC1">RECURSIVE PATTERNS</a><br> <P> Consider the problem of matching a string in parentheses, allowing for unlimited nested parentheses. Without the use of recursion, the best that can @@ -2449,7 +2513,7 @@ 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. <a name="subpatternsassubroutines"></a></P> -<br><a name="SEC22" href="#TOC1">SUBPATTERNS AS SUBROUTINES</a><br> +<br><a name="SEC23" href="#TOC1">SUBPATTERNS AS SUBROUTINES</a><br> <P> 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 @@ -2490,7 +2554,7 @@ different calls. For example, consider this pattern: It matches "abcabc". It does not match "abcABC" because the change of processing option does not affect the called subpattern. <a name="onigurumasubroutines"></a></P> -<br><a name="SEC23" href="#TOC1">ONIGURUMA SUBROUTINE SYNTAX</a><br> +<br><a name="SEC24" href="#TOC1">ONIGURUMA SUBROUTINE SYNTAX</a><br> <P> 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 @@ -2508,7 +2572,7 @@ plus or a minus sign it is taken as a relative reference. For example: Note that \g{...} (Perl syntax) and \g<...> (Oniguruma syntax) are <i>not</i> synonymous. The former is a back reference; the latter is a subroutine call. </P> -<br><a name="SEC24" href="#TOC1">CALLOUTS</a><br> +<br><a name="SEC25" href="#TOC1">CALLOUTS</a><br> <P> Perl has a feature whereby using the sequence (?{...}) causes arbitrary Perl code to be obeyed in the middle of matching a regular expression. This makes it @@ -2519,8 +2583,8 @@ same pair of parentheses when there is a repetition. PCRE provides a similar feature, but of course it cannot obey arbitrary Perl code. The feature is called "callout". The caller of PCRE provides an external function by putting its entry point in the global variable <i>pcre_callout</i> -(8-bit library) or <i>pcre16_callout</i> (16-bit library). By default, this -variable contains NULL, which disables all calling out. +(8-bit library) or <i>pcre[16|32]_callout</i> (16-bit or 32-bit library). +By default, this variable contains NULL, which disables all calling out. </P> <P> Within a regular expression, (?C) indicates the points at which the external @@ -2544,7 +2608,7 @@ the callout function is given in the <a href="pcrecallout.html"><b>pcrecallout</b></a> documentation. <a name="backtrackcontrol"></a></P> -<br><a name="SEC25" href="#TOC1">BACKTRACKING CONTROL</a><br> +<br><a name="SEC26" href="#TOC1">BACKTRACKING CONTROL</a><br> <P> Perl 5.10 introduced a number of "Special Backtracking Control Verbs", which are described in the Perl documentation as "experimental and subject to change @@ -2575,10 +2639,10 @@ parenthesis followed by an asterisk. They are generally of the form (*VERB) or (*VERB:NAME). Some may take either form, with differing behaviour, depending on whether or not an argument 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 library. 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. +name is 255 in the 8-bit library and 65535 in the 16-bit and 32-bit library. +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. <a name="nooptimize"></a></P> <br><b> Optimizations that affect backtracking verbs @@ -2855,12 +2919,12 @@ position. If subsequently B matches, but C does not, the normal (*THEN) action of trying the next alternative (that is, D) does not happen because (*COMMIT) overrides. </P> -<br><a name="SEC26" href="#TOC1">SEE ALSO</a><br> +<br><a name="SEC27" href="#TOC1">SEE ALSO</a><br> <P> <b>pcreapi</b>(3), <b>pcrecallout</b>(3), <b>pcrematching</b>(3), -<b>pcresyntax</b>(3), <b>pcre</b>(3), <b>pcre16(3)</b>. +<b>pcresyntax</b>(3), <b>pcre</b>(3), <b>pcre16(3)</b>, <b>pcre32(3)</b>. </P> -<br><a name="SEC27" href="#TOC1">AUTHOR</a><br> +<br><a name="SEC28" href="#TOC1">AUTHOR</a><br> <P> Philip Hazel <br> @@ -2869,9 +2933,9 @@ University Computing Service Cambridge CB2 3QH, England. <br> </P> -<br><a name="SEC28" href="#TOC1">REVISION</a><br> +<br><a name="SEC29" href="#TOC1">REVISION</a><br> <P> -Last updated: 17 June 2012 +Last updated: 10 September 2012 <br> Copyright © 1997-2012 University of Cambridge. <br> diff --git a/doc/html/pcreperform.html b/doc/html/pcreperform.html index f7c8595..dda207f 100644 --- a/doc/html/pcreperform.html +++ b/doc/html/pcreperform.html @@ -77,7 +77,7 @@ that PCRE cannot otherwise handle. STACK USAGE AT RUN TIME </b><br> <P> -When <b>pcre_exec()</b> or <b>pcre16_exec()</b> is used for matching, certain +When <b>pcre_exec()</b> or <b>pcre[16|32]_exec()</b> is used for matching, certain kinds of pattern can cause it to use large amounts of the process stack. In some environments the default process stack is quite small, and if it runs out the result is often SIGSEGV. This issue is probably the most frequently raised @@ -99,10 +99,9 @@ contains a few observations about PCRE. </P> <P> Using Unicode character properties (the \p, \P, and \X escapes) is slow, -because PCRE has to scan a structure that contains data for over fifteen -thousand characters whenever it needs a character's property. If you can find -an alternative pattern that does not use character properties, it will probably -be faster. +because PCRE has to use a multi-stage table lookup whenever it needs a +character's property. If you can find an alternative pattern that does not use +character properties, it will probably be faster. </P> <P> By default, the escape sequences \b, \d, \s, and \w, and the POSIX @@ -187,7 +186,7 @@ Cambridge CB2 3QH, England. REVISION </b><br> <P> -Last updated: 09 January 2012 +Last updated: 25 August 2012 <br> Copyright © 1997-2012 University of Cambridge. <br> diff --git a/doc/html/pcreposix.html b/doc/html/pcreposix.html index 9aa699a..0e5b296 100644 --- a/doc/html/pcreposix.html +++ b/doc/html/pcreposix.html @@ -49,7 +49,7 @@ expression 8-bit library. See the <a href="pcreapi.html"><b>pcreapi</b></a> documentation for a description of PCRE's native API, which contains much additional functionality. There is no POSIX-style wrapper for PCRE's 16-bit -library. +and 32-bit library. </P> <P> The functions described here are just wrapper functions that ultimately call diff --git a/doc/html/pcreprecompile.html b/doc/html/pcreprecompile.html index 8361b7a..beb9e24 100644 --- a/doc/html/pcreprecompile.html +++ b/doc/html/pcreprecompile.html @@ -35,7 +35,7 @@ JIT data. <P> If you save compiled patterns to a file, you can copy them to a different host and run them there. If the two hosts have different endianness (byte order), -you should run the <b>pcre[16]_pattern_to_host_byte_order()</b> function on the +you should run the <b>pcre[16|32]_pattern_to_host_byte_order()</b> function on the new host before trying to match the pattern. The matching functions return PCRE_ERROR_BADENDIANNESS if they detect a pattern with the wrong endianness. </P> @@ -46,9 +46,9 @@ restoring a compiled pattern loses any JIT optimization data. </P> <br><a name="SEC2" href="#TOC1">SAVING A COMPILED PATTERN</a><br> <P> -The value returned by <b>pcre[16]_compile()</b> points to a single block of +The value returned by <b>pcre[16|32]_compile()</b> points to a single block of memory that holds the compiled pattern and associated data. You can find the -length of this block in bytes by calling <b>pcre[16]_fullinfo()</b> with an +length of this block in bytes by calling <b>pcre[16|32]_fullinfo()</b> with an argument of PCRE_INFO_SIZE. You can then save the data in any appropriate manner. Here is sample code for the 8-bit library that compiles a pattern and writes it to a file. It assumes that the variable <i>fd</i> refers to a file @@ -87,31 +87,31 @@ If the pattern has been studied, it is also possible to save the normal study data in a similar way to the compiled pattern itself. However, if the PCRE_STUDY_JIT_COMPILE was used, the just-in-time data that is created cannot be saved because it is too dependent on the current environment. When studying -generates additional information, <b>pcre[16]_study()</b> returns a pointer to a -<b>pcre[16]_extra</b> data block. Its format is defined in the +generates additional information, <b>pcre[16|32]_study()</b> returns a pointer to a +<b>pcre[16|32]_extra</b> data block. Its format is defined in the <a href="pcreapi.html#extradata">section on matching a pattern</a> in the <a href="pcreapi.html"><b>pcreapi</b></a> documentation. The <i>study_data</i> field points to the binary study data, and -this is what you must save (not the <b>pcre[16]_extra</b> block itself). The -length of the study data can be obtained by calling <b>pcre[16]_fullinfo()</b> +this is what you must save (not the <b>pcre[16|32]_extra</b> block itself). The +length of the study data can be obtained by calling <b>pcre[16|32]_fullinfo()</b> with an argument of PCRE_INFO_STUDYSIZE. Remember to check that -<b>pcre[16]_study()</b> did return a non-NULL value before trying to save the +<b>pcre[16|32]_study()</b> did return a non-NULL value before trying to save the study data. </P> <br><a name="SEC3" href="#TOC1">RE-USING A PRECOMPILED PATTERN</a><br> <P> Re-using a precompiled pattern is straightforward. Having reloaded it into main -memory, called <b>pcre[16]_pattern_to_host_byte_order()</b> if necessary, -you pass its pointer to <b>pcre[16]_exec()</b> or <b>pcre[16]_dfa_exec()</b> in +memory, called <b>pcre[16|32]_pattern_to_host_byte_order()</b> if necessary, +you pass its pointer to <b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b> in the usual way. </P> <P> However, if you passed a pointer to custom character tables when the pattern -was compiled (the <i>tableptr</i> argument of <b>pcre[16]_compile()</b>), you -must now pass a similar pointer to <b>pcre[16]_exec()</b> or -<b>pcre[16]_dfa_exec()</b>, because the value saved with the compiled pattern -will obviously be nonsense. A field in a <b>pcre[16]_extra()</b> block is used +was compiled (the <i>tableptr</i> argument of <b>pcre[16|32]_compile()</b>), you +must now pass a similar pointer to <b>pcre[16|32]_exec()</b> or +<b>pcre[16|32]_dfa_exec()</b>, because the value saved with the compiled pattern +will obviously be nonsense. A field in a <b>pcre[16|32]_extra()</b> block is used to pass this data, as described in the <a href="pcreapi.html#extradata">section on matching a pattern</a> in the @@ -126,10 +126,10 @@ special action at run time in this case. </P> <P> If you saved study data with the compiled pattern, you need to create your own -<b>pcre[16]_extra</b> data block and set the <i>study_data</i> field to point to the +<b>pcre[16|32]_extra</b> data block and set the <i>study_data</i> field to point to the reloaded study data. You must also set the PCRE_EXTRA_STUDY_DATA bit in the <i>flags</i> field to indicate that study data is present. Then pass the -<b>pcre[16]_extra</b> block to the matching function in the usual way. If the +<b>pcre[16|32]_extra</b> block to the matching function in the usual way. If the pattern was studied for just-in-time optimization, that data cannot be saved, and so is lost by a save/restore cycle. </P> @@ -149,7 +149,7 @@ Cambridge CB2 3QH, England. </P> <br><a name="SEC6" href="#TOC1">REVISION</a><br> <P> -Last updated: 10 January 2012 +Last updated: 24 June 2012 <br> Copyright © 1997-2012 University of Cambridge. <br> diff --git a/doc/html/pcrestack.html b/doc/html/pcrestack.html index 76101b3..af6406d 100644 --- a/doc/html/pcrestack.html +++ b/doc/html/pcrestack.html @@ -16,7 +16,7 @@ man page, in case the conversion went wrong. PCRE DISCUSSION OF STACK USAGE </b><br> <P> -When you call <b>pcre[16]_exec()</b>, it makes use of an internal function +When you call <b>pcre[16|32]_exec()</b>, it makes use of an internal function called <b>match()</b>. This calls itself recursively at branch points in the pattern, in order to remember the state of the match so that it can back up and try a different alternative if the first one fails. As matching proceeds deeper @@ -33,32 +33,32 @@ the recursive call would immediately be passed back as the result of the current call (a "tail recursion"), the function is just restarted instead. </P> <P> -The above comments apply when <b>pcre[16]_exec()</b> is run in its normal +The above comments apply when <b>pcre[16|32]_exec()</b> is run in its normal interpretive manner. If the pattern was studied with the PCRE_STUDY_JIT_COMPILE option, and just-in-time compiling was successful, and -the options passed to <b>pcre[16]_exec()</b> were not incompatible, the matching +the options passed to <b>pcre[16|32]_exec()</b> were not incompatible, the matching process uses the JIT-compiled code instead of the <b>match()</b> function. In this case, the memory requirements are handled entirely differently. See the <a href="pcrejit.html"><b>pcrejit</b></a> documentation for details. </P> <P> -The <b>pcre[16]_dfa_exec()</b> function operates in an entirely different way, +The <b>pcre[16|32]_dfa_exec()</b> function operates in an entirely different way, and uses recursion only when there is a regular expression recursion or subroutine call in the pattern. This includes the processing of assertion and "once-only" subpatterns, which are handled like subroutine calls. Normally, these are never very deep, and the limit on the complexity of -<b>pcre[16]_dfa_exec()</b> is controlled by the amount of workspace it is given. +<b>pcre[16|32]_dfa_exec()</b> is controlled by the amount of workspace it is given. However, it is possible to write patterns with runaway infinite recursions; -such patterns will cause <b>pcre[16]_dfa_exec()</b> to run out of stack. At +such patterns will cause <b>pcre[16|32]_dfa_exec()</b> to run out of stack. At present, there is no protection against this. </P> <P> -The comments that follow do NOT apply to <b>pcre[16]_dfa_exec()</b>; they are -relevant only for <b>pcre[16]_exec()</b> without the JIT optimization. +The comments that follow do NOT apply to <b>pcre[16|32]_dfa_exec()</b>; they are +relevant only for <b>pcre[16|32]_exec()</b> without the JIT optimization. </P> <br><b> -Reducing <b>pcre[16]_exec()</b>'s stack usage +Reducing <b>pcre[16|32]_exec()</b>'s stack usage </b><br> <P> Each time that <b>match()</b> is actually called recursively, it uses memory @@ -94,17 +94,17 @@ subject strings is to write repeated parenthesized subpatterns to match more than one character whenever possible. </P> <br><b> -Compiling PCRE to use heap instead of stack for <b>pcre[16]_exec()</b> +Compiling PCRE to use heap instead of stack for <b>pcre[16|32]_exec()</b> </b><br> <P> In environments where stack memory is constrained, you might want to compile PCRE to use heap memory instead of stack for remembering back-up points when -<b>pcre[16]_exec()</b> is running. This makes it run a lot more slowly, however. +<b>pcre[16|32]_exec()</b> is running. This makes it run a lot more slowly, however. Details of how to do this are given in the <a href="pcrebuild.html"><b>pcrebuild</b></a> documentation. When built in this way, instead of using the stack, PCRE obtains and frees memory by calling the functions that are pointed to by the -<b>pcre[16]_stack_malloc</b> and <b>pcre[16]_stack_free</b> variables. By +<b>pcre[16|32]_stack_malloc</b> and <b>pcre[16|32]_stack_free</b> variables. By default, these point to <b>malloc()</b> and <b>free()</b>, but you can replace the pointers to cause PCRE to use your own functions. Since the block sizes are always the same, and are always freed in reverse order, it may be possible to @@ -112,18 +112,18 @@ implement customized memory handlers that are more efficient than the standard functions. </P> <br><b> -Limiting <b>pcre[16]_exec()</b>'s stack usage +Limiting <b>pcre[16|32]_exec()</b>'s stack usage </b><br> <P> You can set limits on the number of times that <b>match()</b> is called, both in -total and recursively. If a limit is exceeded, <b>pcre[16]_exec()</b> returns an +total and recursively. If a limit is exceeded, <b>pcre[16|32]_exec()</b> returns an error code. Setting suitable limits should prevent it from running out of stack. The default values of the limits are very large, and unlikely ever to operate. They can be changed when PCRE is built, and they can also be set when -<b>pcre[16]_exec()</b> is called. For details of these interfaces, see the +<b>pcre[16|32]_exec()</b> is called. For details of these interfaces, see the <a href="pcrebuild.html"><b>pcrebuild</b></a> documentation and the -<a href="pcreapi.html#extradata">section on extra data for <b>pcre[16]_exec()</b></a> +<a href="pcreapi.html#extradata">section on extra data for <b>pcre[16|32]_exec()</b></a> in the <a href="pcreapi.html"><b>pcreapi</b></a> documentation. @@ -139,7 +139,7 @@ In Unix-like environments, the <b>pcretest</b> test program has a command line option (<b>-S</b>) that can be used to increase the size of its stack. As long as the stack is large enough, another option (<b>-M</b>) can be used to find the smallest limits that allow a particular pattern to match a given subject -string. This is done by calling <b>pcre[16]_exec()</b> repeatedly with different +string. This is done by calling <b>pcre[16|32]_exec()</b> repeatedly with different limits. </P> <br><b> @@ -190,7 +190,7 @@ limit on stack size by code such as this: </pre> This reads the current limits (soft and hard) using <b>getrlimit()</b>, then attempts to increase the soft limit to 100Mb using <b>setrlimit()</b>. You must -do this before calling <b>pcre[16]_exec()</b>. +do this before calling <b>pcre[16|32]_exec()</b>. </P> <br><b> Changing stack size in Mac OS X @@ -216,7 +216,7 @@ Cambridge CB2 3QH, England. REVISION </b><br> <P> -Last updated: 21 January 2012 +Last updated: 24 June 2012 <br> Copyright © 1997-2012 University of Cambridge. <br> diff --git a/doc/html/pcresyntax.html b/doc/html/pcresyntax.html index 1d58392..09fe80a 100644 --- a/doc/html/pcresyntax.html +++ b/doc/html/pcresyntax.html @@ -90,7 +90,7 @@ documentation. This document contains a quick-reference summary of the syntax. \V a character that is not a vertical white space character \w a "word" character \W a "non-word" character - \X an extended Unicode sequence + \X a Unicode extended grapheme cluster </pre> In PCRE, by default, \d, \D, \s, \S, \w, and \W recognize only ASCII characters, even in a UTF mode. However, this can be changed by setting the @@ -378,6 +378,7 @@ newline-setting options with similar syntax: (*NO_START_OPT) no start-match optimization (PCRE_NO_START_OPTIMIZE) (*UTF8) set UTF-8 mode: 8-bit library (PCRE_UTF8) (*UTF16) set UTF-16 mode: 16-bit library (PCRE_UTF16) + (*UTF32) set UTF-32 mode: 32-bit library (PCRE_UTF32) (*UCP) set PCRE_UCP (use Unicode properties for \d etc) </PRE> </P> @@ -469,7 +470,7 @@ pattern is not anchored. <br><a name="SEC22" href="#TOC1">NEWLINE CONVENTIONS</a><br> <P> These are recognized only at the very start of the pattern or after a -(*BSR_...), (*UTF8), (*UTF16) or (*UCP) option. +(*BSR_...), (*UTF8), (*UTF16), (*UTF32) or (*UCP) option. <pre> (*CR) carriage return only (*LF) linefeed only @@ -510,7 +511,7 @@ Cambridge CB2 3QH, England. </P> <br><a name="SEC27" href="#TOC1">REVISION</a><br> <P> -Last updated: 10 January 2012 +Last updated: 25 August 2012 <br> Copyright © 1997-2012 University of Cambridge. <br> diff --git a/doc/html/pcretest.html b/doc/html/pcretest.html index 0c6195f..905d7ff 100644 --- a/doc/html/pcretest.html +++ b/doc/html/pcretest.html @@ -14,7 +14,7 @@ man page, in case the conversion went wrong. <br> <ul> <li><a name="TOC1" href="#SEC1">SYNOPSIS</a> -<li><a name="TOC2" href="#SEC2">PCRE's 8-BIT and 16-BIT LIBRARIES</a> +<li><a name="TOC2" href="#SEC2">PCRE's 8-BIT, 16-BIT AND 32-BIT LIBRARIES</a> <li><a name="TOC3" href="#SEC3">COMMAND LINE OPTIONS</a> <li><a name="TOC4" href="#SEC4">DESCRIPTION</a> <li><a name="TOC5" href="#SEC5">PATTERN MODIFIERS</a> @@ -43,38 +43,66 @@ details of the regular expressions themselves, see the documentation. For details of the PCRE library function calls and their options, see the <a href="pcreapi.html"><b>pcreapi</b></a> -and +, <a href="pcre16.html"><b>pcre16</b></a> -documentation. The input for <b>pcretest</b> is a sequence of regular expression -patterns and strings to be matched, as described below. The output shows the -result of each match. Options on the command line and the patterns control PCRE -options and exactly what is output. +and +<a href="pcre32.html"><b>pcre32</b></a> +documentation. +</P> +<P> +The input for <b>pcretest</b> is a sequence of regular expression patterns and +strings to be matched, as described below. The output shows the result of each +match. Options on the command line and the patterns control PCRE options and +exactly what is output. </P> -<br><a name="SEC2" href="#TOC1">PCRE's 8-BIT and 16-BIT LIBRARIES</a><br> +<P> +As PCRE has evolved, it has acquired many different features, and as a result, +<b>pcretest</b> now has rather a lot of obscure options for testing every +possible feature. Some of these options are specifically designed for use in +conjunction with the test script and data files that are distributed as part of +PCRE, and are unlikely to be of use otherwise. They are all documented here, +but without much justification. +</P> +<br><a name="SEC2" href="#TOC1">PCRE's 8-BIT, 16-BIT AND 32-BIT LIBRARIES</a><br> <P> From release 8.30, two separate PCRE libraries can be built. The original one supports 8-bit character strings, whereas the newer 16-bit library supports -character strings encoded in 16-bit units. The <b>pcretest</b> program can be -used to test both libraries. However, it is itself still an 8-bit program, -reading 8-bit input and writing 8-bit output. When testing the 16-bit library, -the patterns and data strings are converted to 16-bit format before being -passed to the PCRE library functions. Results are converted to 8-bit for -output. +character strings encoded in 16-bit units. From release 8.32, a third +library can be built, supporting character strings encoded in 32-bit units. +The <b>pcretest</b> program can be +used to test all three libraries. However, it is itself still an 8-bit program, +reading 8-bit input and writing 8-bit output. When testing the 16-bit or 32-bit +library, the patterns and data strings are converted to 16- or 32-bit format +before being passed to the PCRE library functions. Results are converted to +8-bit for output. </P> <P> -References to functions and structures of the form <b>pcre[16]_xx</b> below +References to functions and structures of the form <b>pcre[16|32]_xx</b> below mean "<b>pcre_xx</b> when using the 8-bit library or <b>pcre16_xx</b> when using the 16-bit library". </P> <br><a name="SEC3" href="#TOC1">COMMAND LINE OPTIONS</a><br> <P> -<b>-16</b> -If both the 8-bit and the 16-bit libraries have been built, this option causes -the 16-bit library to be used. If only the 16-bit library has been built, this -is the default (so has no effect). If only the 8-bit library has been built, +<b>-8</b> +If both the 8-bit library has been built, this option causes the 8-bit library +to be used (which is the default); if the 8-bit library has not been built, this option causes an error. </P> <P> +<b>-16</b> +If both the 8-bit or the 32-bit, and the 16-bit libraries have been built, this +option causes the 16-bit library to be used. If only the 16-bit library has been +built, this is the default (so has no effect). If only the 8-bit or the 32-bit +library has been built, this option causes an error. +</P> +<P> +<b>-32</b> +If both the 8-bit or the 16-bit, and the 32-bit libraries have been built, this +option causes the 32-bit library to be used. If only the 32-bit library has been +built, this is the default (so has no effect). If only the 8-bit or the 16-bit +library has been built, this option causes an error. +</P> +<P> <b>-b</b> Behave as if each pattern has the <b>/B</b> (show byte code) modifier; the internal form is output after compilation. @@ -91,17 +119,22 @@ Output information about a specific build-time option, then exit. This functionality is intended for use in scripts such as <b>RunTest</b>. The following options output the value indicated: <pre> + ebcdic-nl the code for LF (= NL) in an EBCDIC environment: + 0x15 or 0x25 + 0 if used in an ASCII environment linksize the internal link size (2, 3, or 4) newline the default newline setting: CR, LF, CRLF, ANYCRLF, or ANY </pre> The following options output 1 for true or zero for false: <pre> + ebcdic compiled for an EBCDIC environment jit just-in-time support is available pcre16 the 16-bit library was built + pcre32 the 32-bit library was built pcre8 the 8-bit library was built ucp Unicode property support is available - utf UTF-8 and/or UTF-16 support is available + utf UTF-8 and/or UTF-16 and/or UTF-32 support is available </PRE> </P> <P> @@ -113,8 +146,8 @@ form and information about the compiled pattern is output after compilation; <P> <b>-dfa</b> Behave as if each data line contains the \D escape sequence; this causes the -alternative matching function, <b>pcre[16]_dfa_exec()</b>, to be used instead of -the standard <b>pcre[16]_exec()</b> function (more detail is given below). +alternative matching function, <b>pcre[16|32]_dfa_exec()</b>, to be used instead +of the standard <b>pcre[16|32]_exec()</b> function (more detail is given below). </P> <P> <b>-help</b> @@ -129,7 +162,7 @@ compiled pattern is given after compilation. <b>-M</b> Behave as if each data line contains the \M escape sequence; this causes PCRE to discover the minimum MATCH_LIMIT and MATCH_LIMIT_RECURSION settings by -calling <b>pcre[16]_exec()</b> repeatedly with different limits. +calling <b>pcre[16|32]_exec()</b> repeatedly with different limits. </P> <P> <b>-m</b> @@ -140,9 +173,10 @@ bytes for both libraries. <P> <b>-o</b> <i>osize</i> Set the number of elements in the output vector that is used when calling -<b>pcre[16]_exec()</b> or <b>pcre[16]_dfa_exec()</b> to be <i>osize</i>. The +<b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b> to be <i>osize</i>. The default value is 45, which is enough for 14 capturing subexpressions for -<b>pcre[16]_exec()</b> or 22 different matches for <b>pcre[16]_dfa_exec()</b>. +<b>pcre[16|32]_exec()</b> or 22 different matches for +<b>pcre[16|32]_dfa_exec()</b>. The vector size can be changed for individual matching calls by including \O in the data line (see below). </P> @@ -165,7 +199,7 @@ megabytes. <b>-s</b> or <b>-s+</b> Behave as if each pattern has the <b>/S</b> modifier; in other words, force each pattern to be studied. If <b>-s+</b> is used, all the JIT compile options are -passed to <b>pcre[16]_study()</b>, causing just-in-time optimization to be set +passed to <b>pcre[16|32]_study()</b>, causing just-in-time optimization to be set up if it is available, for both full and partial matching. Specific JIT compile options can be selected by following <b>-s+</b> with a digit in the range 1 to 7, which selects the JIT compile modes as follows: @@ -180,8 +214,12 @@ options can be selected by following <b>-s+</b> with a digit in the range 1 to If <b>-s++</b> is used instead of <b>-s+</b> (with or without a following digit), the text "(JIT)" is added to the first output line after a match or no match when JIT-compiled code was actually used. -</P> -<P> +<br> +<br> +Note that there are pattern options that can override <b>-s</b>, either +specifying no studying at all, or suppressing JIT compilation. +<br> +<br> If the <b>/I</b> or <b>/D</b> option is present on a pattern (requesting output about the compiled pattern), information about the result of studying is not included when studying is caused only by <b>-s</b> and neither <b>-i</b> nor @@ -275,20 +313,76 @@ pcretest to read the next line as a continuation of the regular expression. <br><a name="SEC5" href="#TOC1">PATTERN MODIFIERS</a><br> <P> A pattern may be followed by any number of modifiers, which are mostly single -characters. Following Perl usage, these are referred to below as, for example, -"the <b>/i</b> modifier", even though the delimiter of the pattern need not -always be a slash, and no slash is used when writing modifiers. White space may -appear between the final pattern delimiter and the first modifier, and between -the modifiers themselves. +characters, though some of these can be qualified by further characters. +Following Perl usage, these are referred to below as, for example, "the +<b>/i</b> modifier", even though the delimiter of the pattern need not always be +a slash, and no slash is used when writing modifiers. White space may appear +between the final pattern delimiter and the first modifier, and between the +modifiers themselves. For reference, here is a complete list of modifiers. They +fall into several groups that are described in detail in the following +sections. +<pre> + <b>/8</b> set UTF mode + <b>/?</b> disable UTF validity check + <b>/+</b> show remainder of subject after match + <b>/=</b> show all captures (not just those that are set) + + <b>/A</b> set PCRE_ANCHORED + <b>/B</b> show compiled code + <b>/C</b> set PCRE_AUTO_CALLOUT + <b>/D</b> same as <b>/B</b> plus <b>/I</b> + <b>/E</b> set PCRE_DOLLAR_ENDONLY + <b>/F</b> flip byte order in compiled pattern + <b>/f</b> set PCRE_FIRSTLINE + <b>/G</b> find all matches (shorten string) + <b>/g</b> find all matches (use startoffset) + <b>/I</b> show information about pattern + <b>/i</b> set PCRE_CASELESS + <b>/J</b> set PCRE_DUPNAMES + <b>/K</b> show backtracking control names + <b>/L</b> set locale + <b>/M</b> show compiled memory size + <b>/m</b> set PCRE_MULTILINE + <b>/N</b> set PCRE_NO_AUTO_CAPTURE + <b>/P</b> use the POSIX wrapper + <b>/S</b> study the pattern after compilation + <b>/s</b> set PCRE_DOTALL + <b>/T</b> select character tables + <b>/U</b> set PCRE_UNGREEDY + <b>/W</b> set PCRE_UCP + <b>/X</b> set PCRE_EXTRA + <b>/x</b> set PCRE_EXTENDED + <b>/Y</b> set PCRE_NO_START_OPTIMIZE + <b>/Z</b> don't show lengths in <b>/B</b> output + + <b>/<any></b> set PCRE_NEWLINE_ANY + <b>/<anycrlf></b> set PCRE_NEWLINE_ANYCRLF + <b>/<cr></b> set PCRE_NEWLINE_CR + <b>/<crlf></b> set PCRE_NEWLINE_CRLF + <b>/<lf></b> set PCRE_NEWLINE_LF + <b>/<bsr_anycrlf></b> set PCRE_BSR_ANYCRLF + <b>/<bsr_unicode></b> set PCRE_BSR_UNICODE + <b>/<JS></b> set PCRE_JAVASCRIPT_COMPAT + +</PRE> </P> +<br><b> +Perl-compatible modifiers +</b><br> <P> The <b>/i</b>, <b>/m</b>, <b>/s</b>, and <b>/x</b> modifiers set the PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, or PCRE_EXTENDED options, respectively, when -<b>pcre[16]_compile()</b> is called. These four modifier letters have the same +<b>pcre[16|32]_compile()</b> is called. These four modifier letters have the same effect as they do in Perl. For example: <pre> /caseless/i -</pre> + +</PRE> +</P> +<br><b> +Modifiers for other PCRE options +</b><br> +<P> The following table shows additional modifiers for setting PCRE compile-time options that do not correspond to anything in Perl: <pre> @@ -298,6 +392,9 @@ options that do not correspond to anything in Perl: <b>/8</b> PCRE_UTF16 ) when using the 16-bit <b>/?</b> PCRE_NO_UTF16_CHECK ) library + <b>/8</b> PCRE_UTF32 ) when using the 32-bit + <b>/?</b> PCRE_NO_UTF32_CHECK ) library + <b>/A</b> PCRE_ANCHORED <b>/C</b> PCRE_AUTO_CALLOUT <b>/E</b> PCRE_DOLLAR_ENDONLY @@ -308,14 +405,14 @@ options that do not correspond to anything in Perl: <b>/W</b> PCRE_UCP <b>/X</b> PCRE_EXTRA <b>/Y</b> PCRE_NO_START_OPTIMIZE - <b>/<JS></b> PCRE_JAVASCRIPT_COMPAT + <b>/<any></b> PCRE_NEWLINE_ANY + <b>/<anycrlf></b> PCRE_NEWLINE_ANYCRLF <b>/<cr></b> PCRE_NEWLINE_CR - <b>/<lf></b> PCRE_NEWLINE_LF <b>/<crlf></b> PCRE_NEWLINE_CRLF - <b>/<anycrlf></b> PCRE_NEWLINE_ANYCRLF - <b>/<any></b> PCRE_NEWLINE_ANY + <b>/<lf></b> PCRE_NEWLINE_LF <b>/<bsr_anycrlf></b> PCRE_BSR_ANYCRLF <b>/<bsr_unicode></b> PCRE_BSR_UNICODE + <b>/<JS></b> PCRE_JAVASCRIPT_COMPAT </pre> The modifiers that are enclosed in angle brackets are literal strings as shown, including the angle brackets, but the letters within can be in either case. @@ -323,7 +420,7 @@ This example sets multiline matching with CRLF as the line ending sequence: <pre> /^abc/m<CRLF> </pre> -As well as turning on the PCRE_UTF8/16 option, the <b>/8</b> modifier causes +As well as turning on the PCRE_UTF8/16/32 option, the <b>/8</b> modifier causes all non-printing characters in output strings to be printed using the \x{hh...} notation. Otherwise, those less than 0x100 are output in hex without the curly brackets. @@ -341,13 +438,13 @@ Searching for all possible matches within each subject string can be requested by the <b>/g</b> or <b>/G</b> modifier. After finding a match, PCRE is called again to search the remainder of the subject string. The difference between <b>/g</b> and <b>/G</b> is that the former uses the <i>startoffset</i> argument to -<b>pcre[16]_exec()</b> to start searching at a new point within the entire +<b>pcre[16|32]_exec()</b> to start searching at a new point within the entire string (which is in effect what Perl does), whereas the latter passes over a shortened substring. This makes a difference to the matching process if the pattern begins with a lookbehind assertion (including \b or \B). </P> <P> -If any call to <b>pcre[16]_exec()</b> in a <b>/g</b> or <b>/G</b> sequence matches +If any call to <b>pcre[16|32]_exec()</b> in a <b>/g</b> or <b>/G</b> sequence matches an empty string, the next call is done with the PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED flags set in order to search for another, non-empty, match at the same point. If this second match fails, the start offset is advanced, and the @@ -378,7 +475,7 @@ modifier because /S+ and /S++ have other meanings. The <b>/=</b> modifier requests that the values of all potential captured parentheses be output after a match. By default, only those up to the highest one actually used in the match are output (corresponding to the return code -from <b>pcre[16]_exec()</b>). Values in the offsets vector corresponding to +from <b>pcre[16|32]_exec()</b>). Values in the offsets vector corresponding to higher numbers should be set to -1, and these are output as "<unset>". This modifier gives a way of checking that this is happening. </P> @@ -406,16 +503,16 @@ below. <P> The <b>/I</b> modifier requests that <b>pcretest</b> output information about the compiled pattern (whether it is anchored, has a fixed first character, and -so on). It does this by calling <b>pcre[16]_fullinfo()</b> after compiling a +so on). It does this by calling <b>pcre[16|32]_fullinfo()</b> after compiling a pattern. If the pattern is studied, the results of that are also output. </P> <P> The <b>/K</b> modifier requests <b>pcretest</b> to show names from backtracking -control verbs that are returned from calls to <b>pcre[16]_exec()</b>. It causes -<b>pcretest</b> to create a <b>pcre[16]_extra</b> block if one has not already -been created by a call to <b>pcre[16]_study()</b>, and to set the +control verbs that are returned from calls to <b>pcre[16|32]_exec()</b>. It causes +<b>pcretest</b> to create a <b>pcre[16|32]_extra</b> block if one has not already +been created by a call to <b>pcre[16|32]_study()</b>, and to set the PCRE_EXTRA_MARK flag and the <b>mark</b> field within it, every time that -<b>pcre[16]_exec()</b> is called. If the variable that the <b>mark</b> field +<b>pcre[16|32]_exec()</b> is called. If the variable that the <b>mark</b> field points to is non-NULL for a match, non-match, or partial match, <b>pcretest</b> prints the string to which it points. For a match, this is shown on a line by itself, tagged with "MK:". For a non-match it is added to the message. @@ -427,8 +524,8 @@ example, /pattern/Lfr_FR </pre> For this reason, it must be the last modifier. The given locale is set, -<b>pcre[16]_maketables()</b> is called to build a set of character tables for -the locale, and this is then passed to <b>pcre[16]_compile()</b> when compiling +<b>pcre[16|32]_maketables()</b> is called to build a set of character tables for +the locale, and this is then passed to <b>pcre[16|32]_compile()</b> when compiling the regular expression. Without an <b>/L</b> (or <b>/T</b>) modifier, NULL is passed as the tables pointer; that is, <b>/L</b> applies only to the expression on which it appears. @@ -436,22 +533,31 @@ on which it appears. <P> The <b>/M</b> modifier causes the size in bytes of the memory block used to hold the compiled pattern to be output. This does not include the size of the -<b>pcre[16]</b> block; it is just the actual compiled data. If the pattern is +<b>pcre[16|32]</b> block; it is just the actual compiled data. If the pattern is successfully studied with the PCRE_STUDY_JIT_COMPILE option, the size of the JIT compiled code is also output. </P> <P> -If the <b>/S</b> modifier appears once, it causes <b>pcre[16]_study()</b> to be -called after the expression has been compiled, and the results used when the -expression is matched. If <b>/S</b> appears twice, it suppresses studying, even +The <b>/S</b> modifier causes <b>pcre[16|32]_study()</b> to be called after the +expression has been compiled, and the results used when the expression is +matched. There are a number of qualifying characters that may follow <b>/S</b>. +They may appear in any order. +</P> +<P> +If <b>S</b> is followed by an exclamation mark, <b>pcre[16|32]_study()</b> is called +with the PCRE_STUDY_EXTRA_NEEDED option, causing it always to return a +<b>pcre_extra</b> block, even when studying discovers no useful information. +</P> +<P> +If <b>/S</b> is followed by a second S character, it suppresses studying, even if it was requested externally by the <b>-s</b> command line option. This makes it possible to specify that certain patterns are always studied, and others are never studied, independently of <b>-s</b>. This feature is used in the test files in a few cases where the output is different when the pattern is studied. </P> <P> -If the <b>/S</b> modifier is immediately followed by a + character, the call to -<b>pcre[16]_study()</b> is made with all the JIT study options, requesting +If the <b>/S</b> modifier is followed by a + character, the call to +<b>pcre[16|32]_study()</b> is made with all the JIT study options, requesting just-in-time optimization support if it is available, for both normal and partial matching. If you want to restrict the JIT compiling modes, you can follow <b>/S+</b> with a digit in the range 1 to 7: @@ -473,15 +579,21 @@ immediately after <b>/S</b> or <b>/S+</b> because this will be misinterpreted. </P> <P> If JIT studying is successful, the compiled JIT code will automatically be used -when <b>pcre[16]_exec()</b> is run, except when incompatible run-time options +when <b>pcre[16|32]_exec()</b> is run, except when incompatible run-time options are specified. For more details, see the <a href="pcrejit.html"><b>pcrejit</b></a> documentation. See also the <b>\J</b> escape sequence below for a way of setting the size of the JIT stack. </P> <P> +Finally, if <b>/S</b> is followed by a minus character, JIT compilation is +suppressed, even if it was requested externally by the <b>-s</b> command line +option. This makes it possible to specify that JIT is never to be used for +certain patterns. +</P> +<P> The <b>/T</b> modifier must be followed by a single digit. It causes a specific -set of built-in character tables to be passed to <b>pcre[16]_compile()</b>. It +set of built-in character tables to be passed to <b>pcre[16|32]_compile()</b>. It is used in the standard PCRE tests to check behaviour with different character tables. The digit specifies the tables as follows: <pre> @@ -514,7 +626,7 @@ ignored. </P> <br><a name="SEC6" href="#TOC1">DATA LINES</a><br> <P> -Before each data line is passed to <b>pcre[16]_exec()</b>, leading and trailing +Before each data line is passed to <b>pcre[16|32]_exec()</b>, leading and trailing white space is removed, and it is then scanned for \ escapes. Some of these are pretty esoteric features, intended for checking out some of the more complicated features of PCRE. If you are just testing "ordinary" regular @@ -531,45 +643,45 @@ recognized: \t tab (\x09) \v vertical tab (\x0b) \nnn octal character (up to 3 octal digits); always - a byte unless > 255 in UTF-8 or 16-bit mode + a byte unless > 255 in UTF-8 or 16-bit or 32-bit mode \xhh hexadecimal byte (up to 2 hex digits) \x{hh...} hexadecimal character (any number of hex digits) - \A pass the PCRE_ANCHORED option to <b>pcre[16]_exec()</b> or <b>pcre[16]_dfa_exec()</b> - \B pass the PCRE_NOTBOL option to <b>pcre[16]_exec()</b> or <b>pcre[16]_dfa_exec()</b> - \Cdd call pcre[16]_copy_substring() for substring dd after a successful match (number less than 32) - \Cname call pcre[16]_copy_named_substring() for substring "name" after a successful match (name termin- + \A pass the PCRE_ANCHORED option to <b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b> + \B pass the PCRE_NOTBOL option to <b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b> + \Cdd call pcre[16|32]_copy_substring() for substring dd after a successful match (number less than 32) + \Cname call pcre[16|32]_copy_named_substring() for substring "name" after a successful match (name termin- ated by next non alphanumeric character) \C+ show the current captured substrings at callout time \C- do not supply a callout function \C!n return 1 instead of 0 when callout number n is reached \C!n!m return 1 instead of 0 when callout number n is reached for the nth time \C*n pass the number n (may be negative) as callout data; this is used as the callout return value - \D use the <b>pcre[16]_dfa_exec()</b> match function - \F only shortest match for <b>pcre[16]_dfa_exec()</b> - \Gdd call pcre[16]_get_substring() for substring dd after a successful match (number less than 32) - \Gname call pcre[16]_get_named_substring() for substring "name" after a successful match (name termin- + \D use the <b>pcre[16|32]_dfa_exec()</b> match function + \F only shortest match for <b>pcre[16|32]_dfa_exec()</b> + \Gdd call pcre[16|32]_get_substring() for substring dd after a successful match (number less than 32) + \Gname call pcre[16|32]_get_named_substring() for substring "name" after a successful match (name termin- ated by next non-alphanumeric character) \Jdd set up a JIT stack of dd kilobytes maximum (any number of digits) - \L call pcre[16]_get_substringlist() after a successful match + \L call pcre[16|32]_get_substringlist() after a successful match \M discover the minimum MATCH_LIMIT and MATCH_LIMIT_RECURSION settings - \N pass the PCRE_NOTEMPTY option to <b>pcre[16]_exec()</b> or <b>pcre[16]_dfa_exec()</b>; if used twice, pass the + \N pass the PCRE_NOTEMPTY option to <b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b>; if used twice, pass the PCRE_NOTEMPTY_ATSTART option - \Odd set the size of the output vector passed to <b>pcre[16]_exec()</b> to dd (any number of digits) - \P pass the PCRE_PARTIAL_SOFT option to <b>pcre[16]_exec()</b> or <b>pcre[16]_dfa_exec()</b>; if used twice, pass the + \Odd set the size of the output vector passed to <b>pcre[16|32]_exec()</b> to dd (any number of digits) + \P pass the PCRE_PARTIAL_SOFT option to <b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b>; if used twice, pass the PCRE_PARTIAL_HARD option \Qdd set the PCRE_MATCH_LIMIT_RECURSION limit to dd (any number of digits) - \R pass the PCRE_DFA_RESTART option to <b>pcre[16]_dfa_exec()</b> + \R pass the PCRE_DFA_RESTART option to <b>pcre[16|32]_dfa_exec()</b> \S output details of memory get/free calls during matching - \Y pass the PCRE_NO_START_OPTIMIZE option to <b>pcre[16]_exec()</b> or <b>pcre[16]_dfa_exec()</b> - \Z pass the PCRE_NOTEOL option to <b>pcre[16]_exec()</b> or <b>pcre[16]_dfa_exec()</b> - \? pass the PCRE_NO_UTF[8|16]_CHECK option to <b>pcre[16]_exec()</b> or <b>pcre[16]_dfa_exec()</b> + \Y pass the PCRE_NO_START_OPTIMIZE option to <b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b> + \Z pass the PCRE_NOTEOL option to <b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b> + \? pass the PCRE_NO_UTF[8|16|32]_CHECK option to <b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b> \>dd start the match at offset dd (optional "-"; then any number of digits); this sets the <i>startoffset</i> - argument for <b>pcre[16]_exec()</b> or <b>pcre[16]_dfa_exec()</b> - \<cr> pass the PCRE_NEWLINE_CR option to <b>pcre[16]_exec()</b> or <b>pcre[16]_dfa_exec()</b> - \<lf> pass the PCRE_NEWLINE_LF option to <b>pcre[16]_exec()</b> or <b>pcre[16]_dfa_exec()</b> - \<crlf> pass the PCRE_NEWLINE_CRLF option to <b>pcre[16]_exec()</b> or <b>pcre[16]_dfa_exec()</b> - \<anycrlf> pass the PCRE_NEWLINE_ANYCRLF option to <b>pcre[16]_exec()</b> or <b>pcre[16]_dfa_exec()</b> - \<any> pass the PCRE_NEWLINE_ANY option to <b>pcre[16]_exec()</b> or <b>pcre[16]_dfa_exec()</b> + argument for <b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b> + \<cr> pass the PCRE_NEWLINE_CR option to <b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b> + \<lf> pass the PCRE_NEWLINE_LF option to <b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b> + \<crlf> pass the PCRE_NEWLINE_CRLF option to <b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b> + \<anycrlf> pass the PCRE_NEWLINE_ANYCRLF option to <b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b> + \<any> pass the PCRE_NEWLINE_ANY option to <b>pcre[16|32]_exec()</b> or <b>pcre[16|32]_dfa_exec()</b> </pre> The use of \x{hh...} is not dependent on the use of the <b>/8</b> modifier on the pattern. It is recognized always. There may be any number of hexadecimal @@ -588,6 +700,10 @@ In UTF-16 mode, all 4-digit \x{hhhh} values are accepted. This makes it possible to construct invalid UTF-16 sequences for testing purposes. </P> <P> +In UTF-32 mode, all 4- to 8-digit \x{...} values are accepted. This makes it +possible to construct invalid UTF-32 sequences for testing purposes. +</P> +<P> The escapes that specify line ending sequences are literal strings, exactly as shown. No more than one newline setting should be present in any data line. </P> @@ -604,12 +720,12 @@ is not being used. Providing a stack that is larger than the default 32K is necessary only for very complicated patterns. </P> <P> -If \M is present, <b>pcretest</b> calls <b>pcre[16]_exec()</b> several times, +If \M is present, <b>pcretest</b> calls <b>pcre[16|32]_exec()</b> several times, with different values in the <i>match_limit</i> and <i>match_limit_recursion</i> -fields of the <b>pcre[16]_extra</b> data structure, until it finds the minimum -numbers for each parameter that allow <b>pcre[16]_exec()</b> to complete without +fields of the <b>pcre[16|32]_extra</b> data structure, until it finds the minimum +numbers for each parameter that allow <b>pcre[16|32]_exec()</b> to complete without error. Because this is testing a specific feature of the normal interpretive -<b>pcre[16]_exec()</b> execution, the use of any JIT optimization that might +<b>pcre[16|32]_exec()</b> execution, the use of any JIT optimization that might have been set up by the <b>/S+</b> qualifier of <b>-s+</b> option is disabled. </P> <P> @@ -624,7 +740,7 @@ needed to complete the match attempt. <P> When \O is used, the value specified may be higher or lower than the size set by the <b>-O</b> command line option (or defaulted to 45); \O applies only to -the call of <b>pcre[16]_exec()</b> for the line in which it appears. +the call of <b>pcre[16|32]_exec()</b> for the line in which it appears. </P> <P> If the <b>/P</b> modifier was present on the pattern, causing the POSIX wrapper @@ -635,8 +751,8 @@ to be passed to <b>regexec()</b>. <br><a name="SEC7" href="#TOC1">THE ALTERNATIVE MATCHING FUNCTION</a><br> <P> By default, <b>pcretest</b> uses the standard PCRE matching function, -<b>pcre[16]_exec()</b> to match each data line. PCRE also supports an -alternative matching function, <b>pcre[16]_dfa_test()</b>, which operates in a +<b>pcre[16|32]_exec()</b> to match each data line. PCRE also supports an +alternative matching function, <b>pcre[16|32]_dfa_test()</b>, which operates in a different way, and has some restrictions. The differences between the two functions are described in the <a href="pcrematching.html"><b>pcrematching</b></a> @@ -652,14 +768,14 @@ found. This is always the shortest possible match. <br><a name="SEC8" href="#TOC1">DEFAULT OUTPUT FROM PCRETEST</a><br> <P> This section describes the output when the normal matching function, -<b>pcre[16]_exec()</b>, is being used. +<b>pcre[16|32]_exec()</b>, is being used. </P> <P> When a match succeeds, <b>pcretest</b> outputs the list of captured substrings -that <b>pcre[16]_exec()</b> returns, starting with number 0 for the string that +that <b>pcre[16|32]_exec()</b> returns, starting with number 0 for the string that matched the whole pattern. Otherwise, it outputs "No match" when the return is PCRE_ERROR_NOMATCH, and "Partial match:" followed by the partially matching -substring when <b>pcre[16]_exec()</b> returns PCRE_ERROR_PARTIAL. (Note that +substring when <b>pcre[16|32]_exec()</b> returns PCRE_ERROR_PARTIAL. (Note that this is the entire substring that was inspected during the partial match; it may include characters before the actual match start if a lookbehind assertion, \K, \b, or \B was involved.) For any other return, <b>pcretest</b> outputs @@ -679,7 +795,7 @@ at least two. Here is an example of an interactive <b>pcretest</b> run. No match </pre> Unset capturing substrings that are not followed by one that is set are not -returned by <b>pcre[16]_exec()</b>, and are not shown by <b>pcretest</b>. In the +returned by <b>pcre[16|32]_exec()</b>, and are not shown by <b>pcretest</b>. In the following example, there are two capturing substrings, but when the first data line is matched, the second, unset substring is not shown. An "internal" unset substring is shown as "<unset>", as for the second data line. @@ -742,7 +858,7 @@ the newline sequence setting). </P> <br><a name="SEC9" href="#TOC1">OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION</a><br> <P> -When the alternative matching function, <b>pcre[16]_dfa_exec()</b>, is used (by +When the alternative matching function, <b>pcre[16|32]_dfa_exec()</b>, is used (by means of the \D escape sequence or the <b>-dfa</b> command line option), the output consists of a list of all the matches that start at the first point in the subject where there is at least one match. For example: @@ -941,7 +1057,8 @@ result is undefined. </P> <br><a name="SEC14" href="#TOC1">SEE ALSO</a><br> <P> -<b>pcre</b>(3), <b>pcre16</b>(3), <b>pcreapi</b>(3), <b>pcrecallout</b>(3), +<b>pcre</b>(3), <b>pcre16</b>(3), <b>pcre32</b>(3), <b>pcreapi</b>(3), +<b>pcrecallout</b>(3), <b>pcrejit</b>, <b>pcrematching</b>(3), <b>pcrepartial</b>(d), <b>pcrepattern</b>(3), <b>pcreprecompile</b>(3). </P> @@ -956,7 +1073,7 @@ Cambridge CB2 3QH, England. </P> <br><a name="SEC16" href="#TOC1">REVISION</a><br> <P> -Last updated: 21 February 2012 +Last updated: 10 September 2012 <br> Copyright © 1997-2012 University of Cambridge. <br> diff --git a/doc/html/pcreunicode.html b/doc/html/pcreunicode.html index 6b5c022..63b8746 100644 --- a/doc/html/pcreunicode.html +++ b/doc/html/pcreunicode.html @@ -20,6 +20,11 @@ From Release 8.30, in addition to its previous UTF-8 support, PCRE also supports UTF-16 by means of a separate 16-bit library. This can be built as well as, or instead of, the 8-bit library. </P> +<P> +From Release 8.32, in addition to its previous UTF-8 and UTF-16 support, +PCRE also supports UTF-32 by means of a separate 32-bit library. This can be +built as well as, or instead of, the 8-bit and 16-bit libraries. +</P> <br><b> UTF-8 SUPPORT </b><br> @@ -45,12 +50,24 @@ strings that are matched against it are treated as UTF-16 strings instead of strings of 16-bit characters. </P> <br><b> +UTF-32 SUPPORT +</b><br> +<P> +In order process UTF-32 strings, you must build PCRE's 32-bit library with UTF +support, and, in addition, you must call +<a href="pcre_compile.html"><b>pcre32_compile()</b></a> +with the PCRE_UTF32 option flag, or the pattern must start with the sequence +(*UTF32). When either of these is the case, both the pattern and any subject +strings that are matched against it are treated as UTF-32 strings instead of +strings of 32-bit characters. +</P> +<br><b> UTF SUPPORT OVERHEAD </b><br> <P> If you compile PCRE with UTF support, but do not use it at run time, the library will be a bit bigger, but the additional run time overhead is limited -to testing the PCRE_UTF8/16 flag occasionally, so should not be very big. +to testing the PCRE_UTF[8|16|32] flag occasionally, so should not be very big. </P> <br><b> UNICODE PROPERTY SUPPORT @@ -79,16 +96,20 @@ place. From release 7.3 of PCRE, the check is according the rules of RFC 3629, which are themselves derived from the Unicode specification. Earlier releases of PCRE followed the rules of RFC 2279, which allows the full range of 31-bit values (0 to 0x7FFFFFFF). The current check allows only values in the range U+0 -to U+10FFFF, excluding U+D800 to U+DFFF. +to U+10FFFF, excluding the surrogate area, and the non-characters. </P> <P> -The excluded code points are the "Surrogate Area" of Unicode. They are reserved +Excluded code points are the "Surrogate Area" of Unicode. They are reserved for use by UTF-16, where they are used in pairs to encode codepoints with values greater than 0xFFFF. The code points that are encoded by UTF-16 pairs are available independently in the UTF-8 encoding. (In other words, the whole surrogate thing is a fudge for UTF-16 which unfortunately messes up UTF-8.) </P> <P> +Also excluded are the "Non-Characters" code points, which are U+FDD0 to U+FDEF +and the last two code points in each plane, U+??FFFE and U+??FFFF. +</P> +<P> If an invalid UTF-8 string is passed to PCRE, an error return is given. At compile time, the only additional information is the offset to the first byte of the failing character. The run-time functions <b>pcre_exec()</b> and @@ -134,6 +155,10 @@ U+D800 to U+DFFF are independent code points. Values in the surrogate range must be used in pairs in the correct manner. </P> <P> +Excluded are the "Non-Characters" code points, which are U+FDD0 to U+FDEF +and the last two code points in each plane, U+??FFFE and U+??FFFF. +</P> +<P> If an invalid UTF-16 string is passed to PCRE, an error return is given. At compile time, the only additional information is the offset to the first data unit of the failing character. The run-time functions <b>pcre16_exec()</b> and @@ -146,6 +171,42 @@ therefore want to skip these checks in order to improve performance. If you set the PCRE_NO_UTF16_CHECK flag at compile time or at run time, PCRE assumes that the pattern or subject it is given (respectively) contains only valid UTF-16 sequences. In this case, it does not diagnose an invalid UTF-16 string. +<a name="utf32strings"></a></P> +<br><b> +Validity of UTF-32 strings +</b><br> +<P> +When you set the PCRE_UTF32 flag, the strings of 32-bit data units that are +passed as patterns and subjects are (by default) checked for validity on entry +to the relevant functions. This check allows only values in the range U+0 +to U+10FFFF, excluding the surrogate area U+D800 to U+DFFF, and the +"Non-Characters" code points, which are U+FDD0 to U+FDEF and the last two +characters in each plane, U+??FFFE and U+??FFFF. +</P> +<P> +If an invalid UTF-32 string is passed to PCRE, an error return is given. At +compile time, the only additional information is the offset to the first data +unit of the failing character. The run-time functions <b>pcre32_exec()</b> and +<b>pcre32_dfa_exec()</b> also pass back this information, as well as a more +detailed reason code if the caller has provided memory in which to do this. +</P> +<P> +In some situations, you may already know that your strings are valid, and +therefore want to skip these checks in order to improve performance. If you set +the PCRE_NO_UTF32_CHECK flag at compile time or at run time, PCRE assumes that +the pattern or subject it is given (respectively) contains only valid UTF-32 +sequences. In this case, it does not diagnose an invalid UTF-32 string. +</P> +<P> +UTF-32 only uses the lowest 21 bits of the 32 bit characters, and the +application may use the upper bits for internal purposes. To allow you to +pass these strings to PCRE unmodified (thus avoiding the costly operation of +creating a copy of the string with the upper bits masked), PCRE accepts +these 32-bit character strings as-is, but only uses the lowest 21 bits for +matching, if you pass the PCRE_NO_UTF32_CHECK flag to <b>pcre32_exec()</b> and +<b>pcre32_dfa_exec()</b>. However, in this situation, you will have to apply +your own validity check, and avoid the use of JIT optimization. +(The latter restriction may be lifter in a later version of PCRE.) </P> <br><b> General comments about UTF modes @@ -169,13 +230,13 @@ unit. </P> <P> 5. The escape sequence \C can be used to match a single byte in UTF-8 mode, or -a single 16-bit data unit in UTF-16 mode, but its use can lead to some strange -effects because it breaks up multi-unit characters (see the description of \C -in the +a single 16-bit data unit in UTF-16 mode, or a single 32-bit data unit in +UTF-32 mode, but its use can lead to some strange effects because it breaks up +multi-unit characters (see the description of \C in the <a href="pcrepattern.html"><b>pcrepattern</b></a> documentation). The use of \C is not supported in the alternative matching -function <b>pcre[16]_dfa_exec()</b>, nor is it supported in UTF mode by the JIT -optimization of <b>pcre[16]_exec()</b>. If JIT optimization is requested for a +function <b>pcre[16|32]_dfa_exec()</b>, nor is it supported in UTF mode by the JIT +optimization of <b>pcre[16|32]_exec()</b>. If JIT optimization is requested for a UTF pattern that contains \C, it will not succeed, and so the matching will be carried out by the normal interpretive function. </P> @@ -208,13 +269,11 @@ PCRE_UCP is set. </P> <P> 9. Case-insensitive matching applies only to characters whose values are less -than 128, unless PCRE is built with Unicode property support. Even when Unicode -property support is available, PCRE still uses its own character tables when -checking the case of low-valued characters, so as not to degrade performance. -The Unicode property information is used only for characters with higher -values. Furthermore, PCRE supports case-insensitive matching only when there is -a one-to-one mapping between a letter's cases. There are a small number of -many-to-one mappings in Unicode; these are not supported by PCRE. +than 128, unless PCRE is built with Unicode property support. A few Unicode +characters such as Greek sigma have more than two codepoints that are +case-equivalent. Up to and including PCRE release 8.31, only one-to-one case +mappings were supported, but later releases (with Unicode property support) do +treat as case-equivalent all versions of characters such as Greek sigma. </P> <br><b> AUTHOR @@ -231,7 +290,7 @@ Cambridge CB2 3QH, England. REVISION </b><br> <P> -Last updated: 14 April 2012 +Last updated: 25 September 2012 <br> Copyright © 1997-2012 University of Cambridge. <br> diff --git a/doc/pcre-config.txt b/doc/pcre-config.txt index ec89b32..3ee9777 100644 --- a/doc/pcre-config.txt +++ b/doc/pcre-config.txt @@ -8,59 +8,64 @@ NAME SYNOPSIS pcre-config [--prefix] [--exec-prefix] [--version] [--libs] - [--libs16] [--libs-cpp] [--libs-posix] [--cflags] - [--cflags-posix] + [--libs16] [--libs32] [--libs-cpp] [--libs-posix] + [--cflags] [--cflags-posix] DESCRIPTION pcre-config returns the configuration of the installed PCRE libraries and the options required to compile a program to use them. Some of the - options apply only to the 8-bit or 16-bit libraries, respectively, and - are not available if only one of those libraries has been built. If an - unavailable option is encountered, the "usage" information is output. + options apply only to the 8-bit, or 16-bit, or 32-bit libraries, + respectively, and are not available if only one of those libraries has + been built. If an unavailable option is encountered, the "usage" infor- + mation is output. OPTIONS --prefix Writes the directory prefix used in the PCRE installation for - architecture independent files (/usr on many systems, + architecture independent files (/usr on many systems, /usr/local on some systems) to the standard output. --exec-prefix Writes the directory prefix used in the PCRE installation for - architecture dependent files (normally the same as --prefix) + architecture dependent files (normally the same as --prefix) to the standard output. - --version Writes the version number of the installed PCRE libraries to + --version Writes the version number of the installed PCRE libraries to the standard output. - --libs Writes to the standard output the command line options - required to link with the 8-bit PCRE library (-lpcre on many + --libs Writes to the standard output the command line options + required to link with the 8-bit PCRE library (-lpcre on many systems). - --libs16 Writes to the standard output the command line options - required to link with the 16-bit PCRE library (-lpcre16 on + --libs16 Writes to the standard output the command line options + required to link with the 16-bit PCRE library (-lpcre16 on + many systems). + + --libs32 Writes to the standard output the command line options + required to link with the 32-bit PCRE library (-lpcre32 on many systems). --libs-cpp - Writes to the standard output the command line options - required to link with PCRE's C++ wrapper library (-lpcrecpp + Writes to the standard output the command line options + required to link with PCRE's C++ wrapper library (-lpcrecpp -lpcre on many systems). --libs-posix - Writes to the standard output the command line options - required to link with PCRE's POSIX API wrapper library + Writes to the standard output the command line options + required to link with PCRE's POSIX API wrapper library (-lpcreposix -lpcre on many systems). - --cflags Writes to the standard output the command line options - required to compile files that use PCRE (this may include + --cflags Writes to the standard output the command line options + required to compile files that use PCRE (this may include some -I options, but is blank on many systems). --cflags-posix - Writes to the standard output the command line options - required to compile files that use PCRE's POSIX API wrapper - library (this may include some -I options, but is blank on + Writes to the standard output the command line options + required to compile files that use PCRE's POSIX API wrapper + library (this may include some -I options, but is blank on many systems). @@ -71,11 +76,11 @@ SEE ALSO AUTHOR - This manual page was originally written by Mark Baker for the Debian - GNU/Linux system. It has been subsequently revised as a generic PCRE + This manual page was originally written by Mark Baker for the Debian + GNU/Linux system. It has been subsequently revised as a generic PCRE man page. REVISION - Last updated: 01 January 2012 + Last updated: 24 June 2012 diff --git a/doc/pcre.txt b/doc/pcre.txt index 19f04f2..de5dfab 100644 --- a/doc/pcre.txt +++ b/doc/pcre.txt @@ -32,69 +32,106 @@ INTRODUCTION either one or both to be built. The majority of the work to make this possible was done by Zoltan Herczeg. - The two libraries contain identical sets of functions, except that the - names in the 16-bit library start with pcre16_ instead of pcre_. To - avoid over-complication and reduce the documentation maintenance load, - most of the documentation describes the 8-bit library, with the differ- - ences for the 16-bit library described separately in the pcre16 page. - References to functions or structures of the form pcre[16]_xxx should - be read as meaning "pcre_xxx when using the 8-bit library and - pcre16_xxx when using the 16-bit library". - - The current implementation of PCRE corresponds approximately with Perl - 5.12, including support for UTF-8/16 encoded strings and Unicode gen- - eral category properties. However, UTF-8/16 and Unicode support has to - be explicitly enabled; it is not the default. The Unicode tables corre- - spond to Unicode release 6.0.0. - - In addition to the Perl-compatible matching function, PCRE contains an - alternative function that matches the same compiled patterns in a dif- + Starting with release 8.32 it is possible to compile a third separate + PCRE library, which supports 32-bit character strings (including UTF-32 + strings). The build process allows any set of the 8-, 16- and 32-bit + libraries. The work to make this possible was done by Christian Persch. + + The three libraries contain identical sets of functions, except that + the names in the 16-bit library start with pcre16_ instead of pcre_, + and the names in the 32-bit library start with pcre32_ instead of + pcre_. To avoid over-complication and reduce the documentation mainte- + nance load, most of the documentation describes the 8-bit library, with + the differences for the 16-bit and 32-bit libraries described sepa- + rately in the pcre16 and pcre32 pages. References to functions or + structures of the form pcre[16|32]_xxx should be read as meaning + "pcre_xxx when using the 8-bit library, pcre16_xxx when using the + 16-bit library, or pcre32_xxx when using the 32-bit library". + + The current implementation of PCRE corresponds approximately with Perl + 5.12, including support for UTF-8/16/32 encoded strings and Unicode + general category properties. However, UTF-8/16/32 and Unicode support + has to be explicitly enabled; it is not the default. The Unicode tables + correspond to Unicode release 6.2.0. + + In addition to the Perl-compatible matching function, PCRE contains an + alternative function that matches the same compiled patterns in a dif- ferent way. In certain circumstances, the alternative function has some - advantages. For a discussion of the two matching algorithms, see the + advantages. For a discussion of the two matching algorithms, see the pcrematching page. - PCRE is written in C and released as a C library. A number of people - have written wrappers and interfaces of various kinds. In particular, - Google Inc. have provided a comprehensive C++ wrapper for the 8-bit - library. This is now included as part of the PCRE distribution. The - pcrecpp page has details of this interface. Other people's contribu- - tions can be found in the Contrib directory at the primary FTP site, + PCRE is written in C and released as a C library. A number of people + have written wrappers and interfaces of various kinds. In particular, + Google Inc. have provided a comprehensive C++ wrapper for the 8-bit + library. This is now included as part of the PCRE distribution. The + pcrecpp page has details of this interface. Other people's contribu- + tions can be found in the Contrib directory at the primary FTP site, which is: ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre - Details of exactly which Perl regular expression features are and are + Details of exactly which Perl regular expression features are and are not supported by PCRE are given in separate documents. See the pcrepat- - tern and pcrecompat pages. There is a syntax summary in the pcresyntax + tern and pcrecompat pages. There is a syntax summary in the pcresyntax page. - Some features of PCRE can be included, excluded, or changed when the - library is built. The pcre_config() function makes it possible for a - client to discover which features are available. The features them- - selves are described in the pcrebuild page. Documentation about build- - ing PCRE for various operating systems can be found in the README and - NON-UNIX-USE files in the source distribution. - - The libraries contains a number of undocumented internal functions and - data tables that are used by more than one of the exported external - functions, but which are not intended for use by external callers. - Their names all begin with "_pcre_" or "_pcre16_", which hopefully will - not provoke any name clashes. In some environments, it is possible to - control which external symbols are exported when a shared library is - built, and in these cases the undocumented symbols are not exported. + Some features of PCRE can be included, excluded, or changed when the + library is built. The pcre_config() function makes it possible for a + client to discover which features are available. The features them- + selves are described in the pcrebuild page. Documentation about build- + ing PCRE for various operating systems can be found in the README and + NON-AUTOTOOLS_BUILD files in the source distribution. + + The libraries contains a number of undocumented internal functions and + data tables that are used by more than one of the exported external + functions, but which are not intended for use by external callers. + Their names all begin with "_pcre_" or "_pcre16_" or "_pcre32_", which + hopefully will not provoke any name clashes. In some environments, it + is possible to control which external symbols are exported when a + shared library is built, and in these cases the undocumented symbols + are not exported. + + +SECURITY CONSIDERATIONS + + If you are using PCRE in a non-UTF application that permits users to + supply arbitrary patterns for compilation, you should be aware of a + feature that allows users to turn on UTF support from within a pattern, + provided that PCRE was built with UTF support. For example, an 8-bit + pattern that begins with "(*UTF8)" turns on UTF-8 mode. This causes + both the pattern and any data against which it is matched to be checked + for UTF-8 validity. If the data string is very long, such a check might + use sufficiently many resources as to cause your application to lose + performance. + + The best way of guarding against this possibility is to use the + pcre_fullinfo() function to check the compiled pattern's options for + UTF. + + If your application is one that supports UTF, be aware that validity + checking can take time. If the same data string is to be matched many + times, you can use the PCRE_NO_UTF[8|16|32]_CHECK option for the second + and subsequent matches to save redundant checks. + + Another way that performance can be hit is by running a pattern that + has a very large search tree against a string that will never match. + Nested unlimited repeats in a pattern are a common example. PCRE pro- + vides some protection against this: see the PCRE_EXTRA_MATCH_LIMIT fea- + ture in the pcreapi page. USER DOCUMENTATION - The user documentation for PCRE comprises a number of different sec- - tions. In the "man" format, each of these is a separate "man page". In - the HTML format, each is a separate page, linked from the index page. - In the plain text format, all the sections, except the pcredemo sec- + The user documentation for PCRE comprises a number of different sec- + tions. In the "man" format, each of these is a separate "man page". In + the HTML format, each is a separate page, linked from the index page. + In the plain text format, all the sections, except the pcredemo sec- tion, are concatenated, for ease of searching. The sections are as fol- lows: pcre this document pcre16 details of the 16-bit library + pcre32 details of the 32-bit library pcre-config show PCRE installation configuration information pcreapi details of PCRE's native C API pcrebuild options for building PCRE @@ -116,10 +153,10 @@ USER DOCUMENTATION pcrestack discussion of stack usage pcresyntax quick syntax reference pcretest description of the pcretest testing command - pcreunicode discussion of Unicode and UTF-8/16 support + pcreunicode discussion of Unicode and UTF-8/16/32 support - In addition, in the "man" and HTML formats, there is a short page for - each 8-bit C library function, listing its arguments and results. + In addition, in the "man" and HTML formats, there is a short page for + each C library function, listing its arguments and results. AUTHOR @@ -128,18 +165,18 @@ AUTHOR University Computing Service Cambridge CB2 3QH, England. - Putting an actual email address here seems to have been a spam magnet, - so I've taken it away. If you want to email me, use my two initials, + Putting an actual email address here seems to have been a spam magnet, + so I've taken it away. If you want to email me, use my two initials, followed by the two digits 10, at the domain cam.ac.uk. REVISION - Last updated: 10 January 2012 + Last updated: 30 October 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE(3) PCRE(3) @@ -372,83 +409,86 @@ OPTION NAMES For the pcre16_config() function there is an option PCRE_CONFIG_UTF16 that returns 1 if UTF-16 support is configured, otherwise 0. If this - option is given to pcre_config(), or if the PCRE_CONFIG_UTF8 option is - given to pcre16_config(), the result is the PCRE_ERROR_BADOPTION error. + option is given to pcre_config() or pcre32_config(), or if the + PCRE_CONFIG_UTF8 or PCRE_CONFIG_UTF32 option is given to pcre16_con- + fig(), the result is the PCRE_ERROR_BADOPTION error. CHARACTER CODES - In 16-bit mode, when PCRE_UTF16 is not set, character values are + In 16-bit mode, when PCRE_UTF16 is not set, character values are treated in the same way as in 8-bit, non UTF-8 mode, except, of course, - that they can range from 0 to 0xffff instead of 0 to 0xff. Character - types for characters less than 0xff can therefore be influenced by the - locale in the same way as before. Characters greater than 0xff have + that they can range from 0 to 0xffff instead of 0 to 0xff. Character + types for characters less than 0xff can therefore be influenced by the + locale in the same way as before. Characters greater than 0xff have only one case, and no "type" (such as letter or digit). - In UTF-16 mode, the character code is Unicode, in the range 0 to - 0x10ffff, with the exception of values in the range 0xd800 to 0xdfff - because those are "surrogate" values that are used in pairs to encode + In UTF-16 mode, the character code is Unicode, in the range 0 to + 0x10ffff, with the exception of values in the range 0xd800 to 0xdfff + because those are "surrogate" values that are used in pairs to encode values greater than 0xffff. - A UTF-16 string can indicate its endianness by special code knows as a + A UTF-16 string can indicate its endianness by special code knows as a byte-order mark (BOM). The PCRE functions do not handle this, expecting - strings to be in host byte order. A utility function called - pcre16_utf16_to_host_byte_order() is provided to help with this (see + strings to be in host byte order. A utility function called + pcre16_utf16_to_host_byte_order() is provided to help with this (see above). ERROR NAMES - The errors PCRE_ERROR_BADUTF16_OFFSET and PCRE_ERROR_SHORTUTF16 corre- - spond to their 8-bit counterparts. The error PCRE_ERROR_BADMODE is - given when a compiled pattern is passed to a function that processes - patterns in the other mode, for example, if a pattern compiled with + The errors PCRE_ERROR_BADUTF16_OFFSET and PCRE_ERROR_SHORTUTF16 corre- + spond to their 8-bit counterparts. The error PCRE_ERROR_BADMODE is + given when a compiled pattern is passed to a function that processes + patterns in the other mode, for example, if a pattern compiled with pcre_compile() is passed to pcre16_exec(). - There are new error codes whose names begin with PCRE_UTF16_ERR for - invalid UTF-16 strings, corresponding to the PCRE_UTF8_ERR codes for - UTF-8 strings that are described in the section entitled "Reason codes - for invalid UTF-8 strings" in the main pcreapi page. The UTF-16 errors + There are new error codes whose names begin with PCRE_UTF16_ERR for + invalid UTF-16 strings, corresponding to the PCRE_UTF8_ERR codes for + UTF-8 strings that are described in the section entitled "Reason codes + for invalid UTF-8 strings" in the main pcreapi page. The UTF-16 errors are: PCRE_UTF16_ERR1 Missing low surrogate at end of string PCRE_UTF16_ERR2 Invalid low surrogate follows high surrogate PCRE_UTF16_ERR3 Isolated low surrogate - PCRE_UTF16_ERR4 Invalid character 0xfffe + PCRE_UTF16_ERR4 Non-character ERROR TEXTS - If there is an error while compiling a pattern, the error text that is - passed back by pcre16_compile() or pcre16_compile2() is still an 8-bit + If there is an error while compiling a pattern, the error text that is + passed back by pcre16_compile() or pcre16_compile2() is still an 8-bit character string, zero-terminated. CALLOUTS - The subject and mark fields in the callout block that is passed to a + The subject and mark fields in the callout block that is passed to a callout function point to 16-bit vectors. TESTING - The pcretest program continues to operate with 8-bit input and output - files, but it can be used for testing the 16-bit library. If it is run + The pcretest program continues to operate with 8-bit input and output + files, but it can be used for testing the 16-bit library. If it is run with the command line option -16, patterns and subject strings are con- verted from 8-bit to 16-bit before being passed to PCRE, and the 16-bit - library functions are used instead of the 8-bit ones. Returned 16-bit - strings are converted to 8-bit for output. If the 8-bit library was not - compiled, pcretest defaults to 16-bit and the -16 option is ignored. + library functions are used instead of the 8-bit ones. Returned 16-bit + strings are converted to 8-bit for output. If both the 8-bit and the + 32-bit libraries were not compiled, pcretest defaults to 16-bit and the + -16 option is ignored. When PCRE is being built, the RunTest script that is called by "make - check" uses the pcretest -C option to discover which of the 8-bit and - 16-bit libraries has been built, and runs the tests appropriately. + check" uses the pcretest -C option to discover which of the 8-bit, + 16-bit and 32-bit libraries has been built, and runs the tests appro- + priately. NOT SUPPORTED IN 16-BIT MODE Not all the features of the 8-bit library are available with the 16-bit - library. The C++ and POSIX wrapper functions support only the 8-bit + library. The C++ and POSIX wrapper functions support only the 8-bit library, and the pcregrep program is at present 8-bit only. @@ -464,8 +504,334 @@ REVISION Last updated: 14 April 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ + + +PCRE(3) PCRE(3) + + +NAME + PCRE - Perl-compatible regular expressions + + #include <pcre.h> +PCRE 32-BIT API BASIC FUNCTIONS + + pcre32 *pcre32_compile(PCRE_SPTR32 pattern, int options, + const char **errptr, int *erroffset, + const unsigned char *tableptr); + + pcre32 *pcre32_compile2(PCRE_SPTR32 pattern, int options, + int *errorcodeptr, + const char **errptr, int *erroffset, + const unsigned char *tableptr); + + pcre32_extra *pcre32_study(const pcre32 *code, int options, + const char **errptr); + + void pcre32_free_study(pcre32_extra *extra); + + int pcre32_exec(const pcre32 *code, const pcre32_extra *extra, + PCRE_SPTR32 subject, int length, int startoffset, + int options, int *ovector, int ovecsize); + + int pcre32_dfa_exec(const pcre32 *code, const pcre32_extra *extra, + PCRE_SPTR32 subject, int length, int startoffset, + int options, int *ovector, int ovecsize, + int *workspace, int wscount); + + +PCRE 32-BIT API STRING EXTRACTION FUNCTIONS + + int pcre32_copy_named_substring(const pcre32 *code, + PCRE_SPTR32 subject, int *ovector, + int stringcount, PCRE_SPTR32 stringname, + PCRE_UCHAR32 *buffer, int buffersize); + + int pcre32_copy_substring(PCRE_SPTR32 subject, int *ovector, + int stringcount, int stringnumber, PCRE_UCHAR32 *buffer, + int buffersize); + + int pcre32_get_named_substring(const pcre32 *code, + PCRE_SPTR32 subject, int *ovector, + int stringcount, PCRE_SPTR32 stringname, + PCRE_SPTR32 *stringptr); + + int pcre32_get_stringnumber(const pcre32 *code, + PCRE_SPTR32 name); + + int pcre32_get_stringtable_entries(const pcre32 *code, + PCRE_SPTR32 name, PCRE_UCHAR32 **first, PCRE_UCHAR32 **last); + + int pcre32_get_substring(PCRE_SPTR32 subject, int *ovector, + int stringcount, int stringnumber, + PCRE_SPTR32 *stringptr); + + int pcre32_get_substring_list(PCRE_SPTR32 subject, + int *ovector, int stringcount, PCRE_SPTR32 **listptr); + + void pcre32_free_substring(PCRE_SPTR32 stringptr); + + void pcre32_free_substring_list(PCRE_SPTR32 *stringptr); + + +PCRE 32-BIT API AUXILIARY FUNCTIONS + + pcre32_jit_stack *pcre32_jit_stack_alloc(int startsize, int maxsize); + + void pcre32_jit_stack_free(pcre32_jit_stack *stack); + + void pcre32_assign_jit_stack(pcre32_extra *extra, + pcre32_jit_callback callback, void *data); + + const unsigned char *pcre32_maketables(void); + + int pcre32_fullinfo(const pcre32 *code, const pcre32_extra *extra, + int what, void *where); + + int pcre32_refcount(pcre32 *code, int adjust); + + int pcre32_config(int what, void *where); + + const char *pcre32_version(void); + + int pcre32_pattern_to_host_byte_order(pcre32 *code, + pcre32_extra *extra, const unsigned char *tables); + + +PCRE 32-BIT API INDIRECTED FUNCTIONS + + void *(*pcre32_malloc)(size_t); + + void (*pcre32_free)(void *); + + void *(*pcre32_stack_malloc)(size_t); + + void (*pcre32_stack_free)(void *); + + int (*pcre32_callout)(pcre32_callout_block *); + + +PCRE 32-BIT API 32-BIT-ONLY FUNCTION + + int pcre32_utf32_to_host_byte_order(PCRE_UCHAR32 *output, + PCRE_SPTR32 input, int length, int *byte_order, + int keep_boms); + + +THE PCRE 32-BIT LIBRARY + + Starting with release 8.32, it is possible to compile a PCRE library + that supports 32-bit character strings, including UTF-32 strings, as + well as or instead of the original 8-bit library. This work was done by + Christian Persch, based on the work done by Zoltan Herczeg for the + 16-bit library. All three libraries contain identical sets of func- + tions, used in exactly the same way. Only the names of the functions + and the data types of their arguments and results are different. To + avoid over-complication and reduce the documentation maintenance load, + most of the PCRE documentation describes the 8-bit library, with only + occasional references to the 16-bit and 32-bit libraries. This page + describes what is different when you use the 32-bit library. + + WARNING: A single application can be linked with all or any of the + three libraries, but you must take care when processing any particular + pattern to use functions from just one library. For example, if you + want to study a pattern that was compiled with pcre32_compile(), you + must do so with pcre32_study(), not pcre_study(), and you must free the + study data with pcre32_free_study(). + + +THE HEADER FILE + + There is only one header file, pcre.h. It contains prototypes for all + the functions in both libraries, as well as definitions of flags, + structures, error codes, etc. + + +THE LIBRARY NAME + + In Unix-like systems, the 32-bit library is called libpcre32, and can + normally be accesss by adding -lpcre32 to the command for linking an + application that uses PCRE. + + +STRING TYPES + + In the 8-bit library, strings are passed to PCRE library functions as + vectors of bytes with the C type "char *". In the 32-bit library, + strings are passed as vectors of unsigned 32-bit quantities. The macro + PCRE_UCHAR32 specifies an appropriate data type, and PCRE_SPTR32 is + defined as "const PCRE_UCHAR32 *". In very many environments, "unsigned + int" is a 32-bit data type. When PCRE is built, it defines PCRE_UCHAR32 + as "unsigned int", but checks that it really is a 32-bit data type. If + it is not, the build fails with an error message telling the maintainer + to modify the definition appropriately. + + +STRUCTURE TYPES + + The types of the opaque structures that are used for compiled 32-bit + patterns and JIT stacks are pcre32 and pcre32_jit_stack respectively. + The type of the user-accessible structure that is returned by + pcre32_study() is pcre32_extra, and the type of the structure that is + used for passing data to a callout function is pcre32_callout_block. + These structures contain the same fields, with the same names, as their + 8-bit counterparts. The only difference is that pointers to character + strings are 32-bit instead of 8-bit types. + + +32-BIT FUNCTIONS + + For every function in the 8-bit library there is a corresponding func- + tion in the 32-bit library with a name that starts with pcre32_ instead + of pcre_. The prototypes are listed above. In addition, there is one + extra function, pcre32_utf32_to_host_byte_order(). This is a utility + function that converts a UTF-32 character string to host byte order if + necessary. The other 32-bit functions expect the strings they are + passed to be in host byte order. + + The input and output arguments of pcre32_utf32_to_host_byte_order() may + point to the same address, that is, conversion in place is supported. + The output buffer must be at least as long as the input. + + The length argument specifies the number of 32-bit data units in the + input string; a negative value specifies a zero-terminated string. + + If byte_order is NULL, it is assumed that the string starts off in host + byte order. This may be changed by byte-order marks (BOMs) anywhere in + the string (commonly as the first character). + + If byte_order is not NULL, a non-zero value of the integer to which it + points means that the input starts off in host byte order, otherwise + the opposite order is assumed. Again, BOMs in the string can change + this. The final byte order is passed back at the end of processing. + + If keep_boms is not zero, byte-order mark characters (0xfeff) are + copied into the output string. Otherwise they are discarded. + + The result of the function is the number of 32-bit units placed into + the output buffer, including the zero terminator if the string was + zero-terminated. + + +SUBJECT STRING OFFSETS + + The offsets within subject strings that are returned by the matching + functions are in 32-bit units rather than bytes. + + +NAMED SUBPATTERNS + + The name-to-number translation table that is maintained for named sub- + patterns uses 32-bit characters. The pcre32_get_stringtable_entries() + function returns the length of each entry in the table as the number of + 32-bit data units. + + +OPTION NAMES + + There are two new general option names, PCRE_UTF32 and + PCRE_NO_UTF32_CHECK, which correspond to PCRE_UTF8 and + PCRE_NO_UTF8_CHECK in the 8-bit library. In fact, these new options + define the same bits in the options word. There is a discussion about + the validity of UTF-32 strings in the pcreunicode page. + + For the pcre32_config() function there is an option PCRE_CONFIG_UTF32 + that returns 1 if UTF-32 support is configured, otherwise 0. If this + option is given to pcre_config() or pcre16_config(), or if the + PCRE_CONFIG_UTF8 or PCRE_CONFIG_UTF16 option is given to pcre32_con- + fig(), the result is the PCRE_ERROR_BADOPTION error. + + +CHARACTER CODES + + In 32-bit mode, when PCRE_UTF32 is not set, character values are + treated in the same way as in 8-bit, non UTF-8 mode, except, of course, + that they can range from 0 to 0x7fffffff instead of 0 to 0xff. Charac- + ter types for characters less than 0xff can therefore be influenced by + the locale in the same way as before. Characters greater than 0xff + have only one case, and no "type" (such as letter or digit). + + In UTF-32 mode, the character code is Unicode, in the range 0 to + 0x10ffff, with the exception of values in the range 0xd800 to 0xdfff + because those are "surrogate" values that are ill-formed in UTF-32. + + A UTF-32 string can indicate its endianness by special code knows as a + byte-order mark (BOM). The PCRE functions do not handle this, expecting + strings to be in host byte order. A utility function called + pcre32_utf32_to_host_byte_order() is provided to help with this (see + above). + + +ERROR NAMES + + The error PCRE_ERROR_BADUTF32 corresponds to its 8-bit counterpart. + The error PCRE_ERROR_BADMODE is given when a compiled pattern is passed + to a function that processes patterns in the other mode, for example, + if a pattern compiled with pcre_compile() is passed to pcre32_exec(). + + There are new error codes whose names begin with PCRE_UTF32_ERR for + invalid UTF-32 strings, corresponding to the PCRE_UTF8_ERR codes for + UTF-8 strings that are described in the section entitled "Reason codes + for invalid UTF-8 strings" in the main pcreapi page. The UTF-32 errors + are: + + PCRE_UTF32_ERR1 Surrogate character (range from 0xd800 to 0xdfff) + PCRE_UTF32_ERR2 Non-character + PCRE_UTF32_ERR3 Character > 0x10ffff + + +ERROR TEXTS + + If there is an error while compiling a pattern, the error text that is + passed back by pcre32_compile() or pcre32_compile2() is still an 8-bit + character string, zero-terminated. + + +CALLOUTS + + The subject and mark fields in the callout block that is passed to a + callout function point to 32-bit vectors. + + +TESTING + + The pcretest program continues to operate with 8-bit input and output + files, but it can be used for testing the 32-bit library. If it is run + with the command line option -32, patterns and subject strings are con- + verted from 8-bit to 32-bit before being passed to PCRE, and the 32-bit + library functions are used instead of the 8-bit ones. Returned 32-bit + strings are converted to 8-bit for output. If both the 8-bit and the + 16-bit libraries were not compiled, pcretest defaults to 32-bit and the + -32 option is ignored. + + When PCRE is being built, the RunTest script that is called by "make + check" uses the pcretest -C option to discover which of the 8-bit, + 16-bit and 32-bit libraries has been built, and runs the tests appro- + priately. + + +NOT SUPPORTED IN 32-BIT MODE + + Not all the features of the 8-bit library are available with the 32-bit + library. The C++ and POSIX wrapper functions support only the 8-bit + library, and the pcregrep program is at present 8-bit only. + + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION + + Last updated: 24 June 2012 + Copyright (c) 1997-2012 University of Cambridge. +------------------------------------------------------------------------------ + + PCREBUILD(3) PCREBUILD(3) @@ -483,44 +849,52 @@ PCRE BUILD-TIME OPTIONS environments using the GUI facility of cmake-gui if you are using CMake instead of configure to build PCRE. - There is a lot more information about building PCRE in non-Unix-like - environments in the file called NON_UNIX_USE, which is part of the PCRE - distribution. You should consult this file as well as the README file - if you are building in a non-Unix-like environment. + There is a lot more information about building PCRE without using con- + figure (including information about using CMake or building "by hand") + in the file called NON-AUTOTOOLS-BUILD, which is part of the PCRE dis- + tribution. You should consult this file as well as the README file if + you are building in a non-Unix-like environment. The complete list of options for configure (which includes the standard - ones such as the selection of the installation directory) can be + ones such as the selection of the installation directory) can be obtained by running ./configure --help - The following sections include descriptions of options whose names + The following sections include descriptions of options whose names begin with --enable or --disable. These settings specify changes to the - defaults for the configure command. Because of the way that configure - works, --enable and --disable always come in pairs, so the complemen- - tary option always exists as well, but as it specifies the default, it + defaults for the configure command. Because of the way that configure + works, --enable and --disable always come in pairs, so the complemen- + tary option always exists as well, but as it specifies the default, it is not described. -BUILDING 8-BIT and 16-BIT LIBRARIES +BUILDING 8-BIT, 16-BIT AND 32-BIT LIBRARIES - By default, a library called libpcre is built, containing functions - that take string arguments contained in vectors of bytes, either as - single-byte characters, or interpreted as UTF-8 strings. You can also - build a separate library, called libpcre16, in which strings are con- - tained in vectors of 16-bit data units and interpreted either as sin- + By default, a library called libpcre is built, containing functions + that take string arguments contained in vectors of bytes, either as + single-byte characters, or interpreted as UTF-8 strings. You can also + build a separate library, called libpcre16, in which strings are con- + tained in vectors of 16-bit data units and interpreted either as sin- gle-unit characters or UTF-16 strings, by adding --enable-pcre16 + to the configure command. You can also build a separate library, called + libpcre32, in which strings are contained in vectors of 32-bit data + units and interpreted either as single-unit characters or UTF-32 + strings, by adding + + --enable-pcre32 + to the configure command. If you do not want the 8-bit library, add --disable-pcre8 - as well. At least one of the two libraries must be built. Note that the - C++ and POSIX wrappers are for the 8-bit library only, and that pcre- - grep is an 8-bit program. None of these are built if you select only - the 16-bit library. + as well. At least one of the three libraries must be built. Note that + the C++ and POSIX wrappers are for the 8-bit library only, and that + pcregrep is an 8-bit program. None of these are built if you select + only the 16-bit or 32-bit libraries. BUILDING SHARED AND STATIC LIBRARIES @@ -547,48 +921,49 @@ C++ SUPPORT to the configure command. -UTF-8 and UTF-16 SUPPORT +UTF-8, UTF-16 AND UTF-32 SUPPORT To build PCRE with support for UTF Unicode character strings, add --enable-utf - to the configure command. This setting applies to both libraries, - adding support for UTF-8 to the 8-bit library and support for UTF-16 to - the 16-bit library. There are no separate options for enabling UTF-8 - and UTF-16 independently because that would allow ridiculous settings - such as requesting UTF-16 support while building only the 8-bit - library. It is not possible to build one library with UTF support and - the other without in the same configuration. (For backwards compatibil- - ity, --enable-utf8 is a synonym of --enable-utf.) - - Of itself, this setting does not make PCRE treat strings as UTF-8 or - UTF-16. As well as compiling PCRE with this option, you also have have - to set the PCRE_UTF8 or PCRE_UTF16 option when you call one of the pat- - tern compiling functions. - - If you set --enable-utf when compiling in an EBCDIC environment, PCRE - expects its input to be either ASCII or UTF-8 (depending on the run- + to the configure command. This setting applies to all three libraries, + adding support for UTF-8 to the 8-bit library, support for UTF-16 to + the 16-bit library, and support for UTF-32 to the to the 32-bit + library. There are no separate options for enabling UTF-8, UTF-16 and + UTF-32 independently because that would allow ridiculous settings such + as requesting UTF-16 support while building only the 8-bit library. It + is not possible to build one library with UTF support and another with- + out in the same configuration. (For backwards compatibility, --enable- + utf8 is a synonym of --enable-utf.) + + Of itself, this setting does not make PCRE treat strings as UTF-8, + UTF-16 or UTF-32. As well as compiling PCRE with this option, you also + have have to set the PCRE_UTF8, PCRE_UTF16 or PCRE_UTF32 option (as + appropriate) when you call one of the pattern compiling functions. + + If you set --enable-utf when compiling in an EBCDIC environment, PCRE + expects its input to be either ASCII or UTF-8 (depending on the run- time option). It is not possible to support both EBCDIC and UTF-8 codes - in the same version of the library. Consequently, --enable-utf and + in the same version of the library. Consequently, --enable-utf and --enable-ebcdic are mutually exclusive. UNICODE CHARACTER PROPERTY SUPPORT - UTF support allows the libraries to process character codepoints up to - 0x10ffff in the strings that they handle. On its own, however, it does + UTF support allows the libraries to process character codepoints up to + 0x10ffff in the strings that they handle. On its own, however, it does not provide any facilities for accessing the properties of such charac- ters. If you want to be able to use the pattern escapes \P, \p, and \X, which refer to Unicode character properties, you must add --enable-unicode-properties - to the configure command. This implies UTF support, even if you have + to the configure command. This implies UTF support, even if you have not explicitly requested it. - Including Unicode property support adds around 30K of tables to the - PCRE library. Only the general category properties such as Lu and Nd + Including Unicode property support adds around 30K of tables to the + PCRE library. Only the general category properties such as Lu and Nd are supported. Details are given in the pcrepattern documentation. @@ -598,9 +973,9 @@ JUST-IN-TIME COMPILER SUPPORT --enable-jit - This support is available only for certain hardware architectures. If - this option is set for an unsupported architecture, a compile time - error occurs. See the pcrejit documentation for a discussion of JIT + This support is available only for certain hardware architectures. If + this option is set for an unsupported architecture, a compile time + error occurs. See the pcrejit documentation for a discussion of JIT usage. When JIT support is enabled, pcregrep automatically makes use of it, unless you add @@ -611,14 +986,14 @@ JUST-IN-TIME COMPILER SUPPORT CODE VALUE OF NEWLINE - By default, PCRE interprets the linefeed (LF) character as indicating - the end of a line. This is the normal newline character on Unix-like - systems. You can compile PCRE to use carriage return (CR) instead, by + By default, PCRE interprets the linefeed (LF) character as indicating + the end of a line. This is the normal newline character on Unix-like + systems. You can compile PCRE to use carriage return (CR) instead, by adding --enable-newline-is-cr - to the configure command. There is also a --enable-newline-is-lf + to the configure command. There is also a --enable-newline-is-lf option, which explicitly specifies linefeed as the newline character. Alternatively, you can specify that line endings are to be indicated by @@ -630,40 +1005,40 @@ CODE VALUE OF NEWLINE --enable-newline-is-anycrlf - which causes PCRE to recognize any of the three sequences CR, LF, or + which causes PCRE to recognize any of the three sequences CR, LF, or CRLF as indicating a line ending. Finally, a fifth option, specified by --enable-newline-is-any causes PCRE to recognize any Unicode newline sequence. - Whatever line ending convention is selected when PCRE is built can be - overridden when the library functions are called. At build time it is + Whatever line ending convention is selected when PCRE is built can be + overridden when the library functions are called. At build time it is conventional to use the standard for your operating system. WHAT \R MATCHES - By default, the sequence \R in a pattern matches any Unicode newline - sequence, whatever has been selected as the line ending sequence. If + By default, the sequence \R in a pattern matches any Unicode newline + sequence, whatever has been selected as the line ending sequence. If you specify --enable-bsr-anycrlf - the default is changed so that \R matches only CR, LF, or CRLF. What- - ever is selected when PCRE is built can be overridden when the library + the default is changed so that \R matches only CR, LF, or CRLF. What- + ever is selected when PCRE is built can be overridden when the library functions are called. POSIX MALLOC USAGE - When the 8-bit library is called through the POSIX interface (see the - pcreposix documentation), additional working storage is required for - holding the pointers to capturing substrings, because PCRE requires + When the 8-bit library is called through the POSIX interface (see the + pcreposix documentation), additional working storage is required for + holding the pointers to capturing substrings, because PCRE requires three integers per substring, whereas the POSIX interface provides only - two. If the number of expected substrings is small, the wrapper func- - tion uses space on the stack, because this is faster than using mal- - loc() for each call. The default threshold above which the stack is no + two. If the number of expected substrings is small, the wrapper func- + tion uses space on the stack, because this is faster than using mal- + loc() for each call. The default threshold above which the stack is no longer used is 10; it can be changed by adding a setting such as --with-posix-malloc-threshold=20 @@ -673,114 +1048,131 @@ POSIX MALLOC USAGE HANDLING VERY LARGE PATTERNS - Within a compiled pattern, offset values are used to point from one - part to another (for example, from an opening parenthesis to an alter- - nation metacharacter). By default, two-byte values are used for these - offsets, leading to a maximum size for a compiled pattern of around - 64K. This is sufficient to handle all but the most gigantic patterns. - Nevertheless, some people do want to process truly enormous patterns, - so it is possible to compile PCRE to use three-byte or four-byte off- - sets by adding a setting such as + Within a compiled pattern, offset values are used to point from one + part to another (for example, from an opening parenthesis to an alter- + nation metacharacter). By default, in the 8-bit and 16-bit libraries, + two-byte values are used for these offsets, leading to a maximum size + for a compiled pattern of around 64K. This is sufficient to handle all + but the most gigantic patterns. Nevertheless, some people do want to + process truly enormous patterns, so it is possible to compile PCRE to + use three-byte or four-byte offsets by adding a setting such as --with-link-size=3 - to the configure command. The value given must be 2, 3, or 4. For the - 16-bit library, a value of 3 is rounded up to 4. Using longer offsets - slows down the operation of PCRE because it has to load additional data - when handling them. + to the configure command. The value given must be 2, 3, or 4. For the + 16-bit library, a value of 3 is rounded up to 4. In these libraries, + using longer offsets slows down the operation of PCRE because it has to + load additional data when handling them. For the 32-bit library the + value is always 4 and cannot be overridden; the value of --with-link- + size is ignored. AVOIDING EXCESSIVE STACK USAGE When matching with the pcre_exec() function, PCRE implements backtrack- - ing by making recursive calls to an internal function called match(). - In environments where the size of the stack is limited, this can se- - verely limit PCRE's operation. (The Unix environment does not usually + ing by making recursive calls to an internal function called match(). + In environments where the size of the stack is limited, this can se- + verely limit PCRE's operation. (The Unix environment does not usually suffer from this problem, but it may sometimes be necessary to increase - the maximum stack size. There is a discussion in the pcrestack docu- - mentation.) An alternative approach to recursion that uses memory from - the heap to remember data, instead of using recursive function calls, - has been implemented to work round the problem of limited stack size. + the maximum stack size. There is a discussion in the pcrestack docu- + mentation.) An alternative approach to recursion that uses memory from + the heap to remember data, instead of using recursive function calls, + has been implemented to work round the problem of limited stack size. If you want to build a version of PCRE that works this way, add --disable-stack-for-recursion - to the configure command. With this configuration, PCRE will use the - pcre_stack_malloc and pcre_stack_free variables to call memory manage- - ment functions. By default these point to malloc() and free(), but you + to the configure command. With this configuration, PCRE will use the + pcre_stack_malloc and pcre_stack_free variables to call memory manage- + ment functions. By default these point to malloc() and free(), but you can replace the pointers so that your own functions are used instead. - Separate functions are provided rather than using pcre_malloc and - pcre_free because the usage is very predictable: the block sizes - requested are always the same, and the blocks are always freed in - reverse order. A calling program might be able to implement optimized - functions that perform better than malloc() and free(). PCRE runs + Separate functions are provided rather than using pcre_malloc and + pcre_free because the usage is very predictable: the block sizes + requested are always the same, and the blocks are always freed in + reverse order. A calling program might be able to implement optimized + functions that perform better than malloc() and free(). PCRE runs noticeably more slowly when built in this way. This option affects only the pcre_exec() function; it is not relevant for pcre_dfa_exec(). LIMITING PCRE RESOURCE USAGE - Internally, PCRE has a function called match(), which it calls repeat- - edly (sometimes recursively) when matching a pattern with the - pcre_exec() function. By controlling the maximum number of times this - function may be called during a single matching operation, a limit can - be placed on the resources used by a single call to pcre_exec(). The - limit can be changed at run time, as described in the pcreapi documen- - tation. The default is 10 million, but this can be changed by adding a + Internally, PCRE has a function called match(), which it calls repeat- + edly (sometimes recursively) when matching a pattern with the + pcre_exec() function. By controlling the maximum number of times this + function may be called during a single matching operation, a limit can + be placed on the resources used by a single call to pcre_exec(). The + limit can be changed at run time, as described in the pcreapi documen- + tation. The default is 10 million, but this can be changed by adding a setting such as --with-match-limit=500000 - to the configure command. This setting has no effect on the + to the configure command. This setting has no effect on the pcre_dfa_exec() matching function. - In some environments it is desirable to limit the depth of recursive + In some environments it is desirable to limit the depth of recursive calls of match() more strictly than the total number of calls, in order - to restrict the maximum amount of stack (or heap, if --disable-stack- + to restrict the maximum amount of stack (or heap, if --disable-stack- for-recursion is specified) that is used. A second limit controls this; - it defaults to the value that is set for --with-match-limit, which - imposes no additional constraints. However, you can set a lower limit + it defaults to the value that is set for --with-match-limit, which + imposes no additional constraints. However, you can set a lower limit by adding, for example, --with-match-limit-recursion=10000 - to the configure command. This value can also be overridden at run + to the configure command. This value can also be overridden at run time. CREATING CHARACTER TABLES AT BUILD TIME - PCRE uses fixed tables for processing characters whose code values are - less than 256. By default, PCRE is built with a set of tables that are - distributed in the file pcre_chartables.c.dist. These tables are for + PCRE uses fixed tables for processing characters whose code values are + less than 256. By default, PCRE is built with a set of tables that are + distributed in the file pcre_chartables.c.dist. These tables are for ASCII codes only. If you add --enable-rebuild-chartables - to the configure command, the distributed tables are no longer used. - Instead, a program called dftables is compiled and run. This outputs + to the configure command, the distributed tables are no longer used. + Instead, a program called dftables is compiled and run. This outputs the source for new set of tables, created in the default locale of your - C run-time system. (This method of replacing the tables does not work - if you are cross compiling, because dftables is run on the local host. + C run-time system. (This method of replacing the tables does not work + if you are cross compiling, because dftables is run on the local host. If you need to create alternative tables when cross compiling, you will have to do so "by hand".) USING EBCDIC CODE - PCRE assumes by default that it will run in an environment where the - character code is ASCII (or Unicode, which is a superset of ASCII). - This is the case for most computer operating systems. PCRE can, how- + PCRE assumes by default that it will run in an environment where the + character code is ASCII (or Unicode, which is a superset of ASCII). + This is the case for most computer operating systems. PCRE can, how- ever, be compiled to run in an EBCDIC environment by adding --enable-ebcdic to the configure command. This setting implies --enable-rebuild-charta- - bles. You should only use it if you know that you are in an EBCDIC - environment (for example, an IBM mainframe operating system). The + bles. You should only use it if you know that you are in an EBCDIC + environment (for example, an IBM mainframe operating system). The --enable-ebcdic option is incompatible with --enable-utf. + The EBCDIC character that corresponds to an ASCII LF is assumed to have + the value 0x15 by default. However, in some EBCDIC environments, 0x25 + is used. In such an environment you should use + + --enable-ebcdic-nl25 + + as well as, or instead of, --enable-ebcdic. The EBCDIC character for CR + has the same value as in ASCII, namely, 0x0d. Whichever of 0x15 and + 0x25 is not chosen as LF is made to correspond to the Unicode NEL char- + acter (which, in Unicode, is 0x85). + + The options that select newline behaviour, such as --enable-newline-is- + cr, and equivalent run-time options, refer to these character values in + an EBCDIC environment. + PCREGREP OPTIONS FOR COMPRESSED FILE SUPPORT @@ -843,9 +1235,77 @@ PCRETEST OPTION FOR LIBREADLINE SUPPORT immediately before the configure command. +DEBUGGING WITH VALGRIND SUPPORT + + By adding the + + --enable-valgrind + + option to to the configure command, PCRE will use valgrind annotations + to mark certain memory regions as unaddressable. This allows it to + detect invalid memory accesses, and is mostly useful for debugging PCRE + itself. + + +CODE COVERAGE REPORTING + + If your C compiler is gcc, you can build a version of PCRE that can + generate a code coverage report for its test suite. To enable this, you + must install lcov version 1.6 or above. Then specify + + --enable-coverage + + to the configure command and build PCRE in the usual way. + + Note that using ccache (a caching C compiler) is incompatible with code + coverage reporting. If you have configured ccache to run automatically + on your system, you must set the environment variable + + CCACHE_DISABLE=1 + + before running make to build PCRE, so that ccache is not used. + + When --enable-coverage is used, the following addition targets are + added to the Makefile: + + make coverage + + This creates a fresh coverage report for the PCRE test suite. It is + equivalent to running "make coverage-reset", "make coverage-baseline", + "make check", and then "make coverage-report". + + make coverage-reset + + This zeroes the coverage counters, but does nothing else. + + make coverage-baseline + + This captures baseline coverage information. + + make coverage-report + + This creates the coverage report. + + make coverage-clean-report + + This removes the generated coverage report without cleaning the cover- + age data itself. + + make coverage-clean-data + + This removes the captured coverage data without removing the coverage + files created at compile time (*.gcno). + + make coverage-clean + + This cleans all coverage data including the generated coverage report. + For more information about code coverage, see the gcov and lcov docu- + mentation. + + SEE ALSO - pcreapi(3), pcre16, pcre_config(3). + pcreapi(3), pcre16, pcre32, pcre_config(3). AUTHOR @@ -857,11 +1317,11 @@ AUTHOR REVISION - Last updated: 07 January 2012 + Last updated: 30 October 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCREMATCHING(3) PCREMATCHING(3) @@ -874,15 +1334,17 @@ PCRE MATCHING ALGORITHMS This document describes the two different algorithms that are available in PCRE for matching a compiled regular expression against a given sub- ject string. The "standard" algorithm is the one provided by the - pcre_exec() and pcre16_exec() functions. These work in the same was as - Perl's matching function, and provide a Perl-compatible matching opera- - tion. The just-in-time (JIT) optimization that is described in the - pcrejit documentation is compatible with these functions. - - An alternative algorithm is provided by the pcre_dfa_exec() and - pcre16_dfa_exec() functions; they operate in a different way, and are - not Perl-compatible. This alternative has advantages and disadvantages - compared with the standard algorithm, and these are described below. + pcre_exec(), pcre16_exec() and pcre32_exec() functions. These work in + the same as as Perl's matching function, and provide a Perl-compatible + matching operation. The just-in-time (JIT) optimization that is + described in the pcrejit documentation is compatible with these func- + tions. + + An alternative algorithm is provided by the pcre_dfa_exec(), + pcre16_dfa_exec() and pcre32_dfa_exec() functions; they operate in a + different way, and are not Perl-compatible. This alternative has advan- + tages and disadvantages compared with the standard algorithm, and these + are described below. When there is only one possible way in which a given subject string can match a pattern, the two algorithms give the same answer. A difference @@ -1011,10 +1473,10 @@ THE ALTERNATIVE MATCHING ALGORITHM always 1, and the value of the capture_last field is always -1. 7. The \C escape sequence, which (in the standard algorithm) always - matches a single data unit, even in UTF-8 or UTF-16 modes, is not sup- - ported in these modes, because the alternative algorithm moves through - the subject string one character (not data unit) at a time, for all - active paths through the tree. + matches a single data unit, even in UTF-8, UTF-16 or UTF-32 modes, is + not supported in these modes, because the alternative algorithm moves + through the subject string one character (not data unit) at a time, for + all active paths through the tree. 8. Except for (*FAIL), the backtracking control verbs such as (*PRUNE) are not supported. (*FAIL) is supported, and behaves like a failing @@ -1067,8 +1529,8 @@ REVISION Last updated: 08 January 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCREAPI(3) PCREAPI(3) @@ -1140,6 +1602,11 @@ PCRE NATIVE API STRING EXTRACTION FUNCTIONS PCRE NATIVE API AUXILIARY FUNCTIONS + int pcre_jit_exec(const pcre *code, const pcre_extra *extra, + const char *subject, int length, int startoffset, + int options, int *ovector, int ovecsize, + pcre_jit_stack *jstack); + pcre_jit_stack *pcre_jit_stack_alloc(int startsize, int maxsize); void pcre_jit_stack_free(pcre_jit_stack *stack); @@ -1175,69 +1642,77 @@ PCRE NATIVE API INDIRECTED FUNCTIONS int (*pcre_callout)(pcre_callout_block *); -PCRE 8-BIT AND 16-BIT LIBRARIES +PCRE 8-BIT, 16-BIT AND 32-BIT LIBRARIES From release 8.30, PCRE can be compiled as a library for handling 16-bit character strings as well as, or instead of, the original - library that handles 8-bit character strings. To avoid too much compli- - cation, this document describes the 8-bit versions of the functions, - with only occasional references to the 16-bit library. - - The 16-bit functions operate in the same way as their 8-bit counter- - parts; they just use different data types for their arguments and - results, and their names start with pcre16_ instead of pcre_. For every - option that has UTF8 in its name (for example, PCRE_UTF8), there is a - corresponding 16-bit name with UTF8 replaced by UTF16. This facility is - in fact just cosmetic; the 16-bit option names define the same bit val- + library that handles 8-bit character strings. From release 8.32, PCRE + can also be compiled as a library for handling 32-bit character + strings. To avoid too much complication, this document describes the + 8-bit versions of the functions, with only occasional references to the + 16-bit and 32-bit libraries. + + The 16-bit and 32-bit functions operate in the same way as their 8-bit + counterparts; they just use different data types for their arguments + and results, and their names start with pcre16_ or pcre32_ instead of + pcre_. For every option that has UTF8 in its name (for example, + PCRE_UTF8), there are corresponding 16-bit and 32-bit names with UTF8 + replaced by UTF16 or UTF32, respectively. This facility is in fact just + cosmetic; the 16-bit and 32-bit option names define the same bit val- ues. References to bytes and UTF-8 in this document should be read as refer- - ences to 16-bit data quantities and UTF-16 when using the 16-bit + ences to 16-bit data quantities and UTF-16 when using the 16-bit + library, or 32-bit data quantities and UTF-32 when using the 32-bit library, unless specified otherwise. More details of the specific dif- - ferences for the 16-bit library are given in the pcre16 page. + ferences for the 16-bit and 32-bit libraries are given in the pcre16 + and pcre32 pages. PCRE API OVERVIEW PCRE has its own native API, which is described in this document. There - are also some wrapper functions (for the 8-bit library only) that cor- - respond to the POSIX regular expression API, but they do not give - access to all the functionality. They are described in the pcreposix - documentation. Both of these APIs define a set of C function calls. A + are also some wrapper functions (for the 8-bit library only) that cor- + respond to the POSIX regular expression API, but they do not give + access to all the functionality. They are described in the pcreposix + documentation. Both of these APIs define a set of C function calls. A C++ wrapper (again for the 8-bit library only) is also distributed with PCRE. It is documented in the pcrecpp page. - The native API C function prototypes are defined in the header file - pcre.h, and on Unix-like systems the (8-bit) library itself is called - libpcre. It can normally be accessed by adding -lpcre to the command - for linking an application that uses PCRE. The header file defines the + The native API C function prototypes are defined in the header file + pcre.h, and on Unix-like systems the (8-bit) library itself is called + libpcre. It can normally be accessed by adding -lpcre to the command + for linking an application that uses PCRE. The header file defines the macros PCRE_MAJOR and PCRE_MINOR to contain the major and minor release - numbers for the library. Applications can use these to include support + numbers for the library. Applications can use these to include support for different releases of PCRE. In a Windows environment, if you want to statically link an application - program against a non-dll pcre.a file, you must define PCRE_STATIC - before including pcre.h or pcrecpp.h, because otherwise the pcre_mal- + program against a non-dll pcre.a file, you must define PCRE_STATIC + before including pcre.h or pcrecpp.h, because otherwise the pcre_mal- loc() and pcre_free() exported functions will be declared __declspec(dllimport), with unwanted results. - The functions pcre_compile(), pcre_compile2(), pcre_study(), and - pcre_exec() are used for compiling and matching regular expressions in - a Perl-compatible manner. A sample program that demonstrates the sim- - plest way of using them is provided in the file called pcredemo.c in + The functions pcre_compile(), pcre_compile2(), pcre_study(), and + pcre_exec() are used for compiling and matching regular expressions in + a Perl-compatible manner. A sample program that demonstrates the sim- + plest way of using them is provided in the file called pcredemo.c in the PCRE source distribution. A listing of this program is given in the - pcredemo documentation, and the pcresample documentation describes how + pcredemo documentation, and the pcresample documentation describes how to compile and run it. - Just-in-time compiler support is an optional feature of PCRE that can + Just-in-time compiler support is an optional feature of PCRE that can be built in appropriate hardware environments. It greatly speeds up the - matching performance of many patterns. Simple programs can easily - request that it be used if available, by setting an option that is - ignored when it is not relevant. More complicated programs might need - to make use of the functions pcre_jit_stack_alloc(), - pcre_jit_stack_free(), and pcre_assign_jit_stack() in order to control - the JIT code's memory usage. These functions are discussed in the - pcrejit documentation. + matching performance of many patterns. Simple programs can easily + request that it be used if available, by setting an option that is + ignored when it is not relevant. More complicated programs might need + to make use of the functions pcre_jit_stack_alloc(), + pcre_jit_stack_free(), and pcre_assign_jit_stack() in order to control + the JIT code's memory usage. + + From release 8.32 there is also a direct interface for JIT execution, + which gives improved performance. The JIT-specific functions are dis- + cussed in the pcrejit documentation. A second matching function, pcre_dfa_exec(), which is not Perl-compati- ble, is also provided. This uses a different algorithm for the match- @@ -1384,21 +1859,30 @@ CHECKING BUILD-TIME OPTIONS PCRE_CONFIG_UTF8 The output is an integer that is set to one if UTF-8 support is avail- - able; otherwise it is set to zero. If this option is given to the - 16-bit version of this function, pcre16_config(), the result is + able; otherwise it is set to zero. This value should normally be given + to the 8-bit version of this function, pcre_config(). If it is given to + the 16-bit or 32-bit version of this function, the result is PCRE_ERROR_BADOPTION. PCRE_CONFIG_UTF16 The output is an integer that is set to one if UTF-16 support is avail- - able; otherwise it is set to zero. This value should normally be given + able; otherwise it is set to zero. This value should normally be given to the 16-bit version of this function, pcre16_config(). If it is given - to the 8-bit version of this function, the result is PCRE_ERROR_BADOP- - TION. + to the 8-bit or 32-bit version of this function, the result is + PCRE_ERROR_BADOPTION. + + PCRE_CONFIG_UTF32 + + The output is an integer that is set to one if UTF-32 support is avail- + able; otherwise it is set to zero. This value should normally be given + to the 32-bit version of this function, pcre32_config(). If it is given + to the 8-bit or 16-bit version of this function, the result is + PCRE_ERROR_BADOPTION. PCRE_CONFIG_UNICODE_PROPERTIES - The output is an integer that is set to one if support for Unicode + The output is an integer that is set to one if support for Unicode character properties is available; otherwise it is set to zero. PCRE_CONFIG_JIT @@ -1408,39 +1892,42 @@ CHECKING BUILD-TIME OPTIONS PCRE_CONFIG_JITTARGET - The output is a pointer to a zero-terminated "const char *" string. If + The output is a pointer to a zero-terminated "const char *" string. If JIT support is available, the string contains the name of the architec- - ture for which the JIT compiler is configured, for example "x86 32bit - (little endian + unaligned)". If JIT support is not available, the + ture for which the JIT compiler is configured, for example "x86 32bit + (little endian + unaligned)". If JIT support is not available, the result is NULL. PCRE_CONFIG_NEWLINE - The output is an integer whose value specifies the default character - sequence that is recognized as meaning "newline". The four values that - are supported are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, - and -1 for ANY. Though they are derived from ASCII, the same values - are returned in EBCDIC environments. The default should normally corre- + The output is an integer whose value specifies the default character + sequence that is recognized as meaning "newline". The values that are + supported in ASCII/Unicode environments are: 10 for LF, 13 for CR, 3338 + for CRLF, -2 for ANYCRLF, and -1 for ANY. In EBCDIC environments, CR, + ANYCRLF, and ANY yield the same values. However, the value for LF is + normally 21, though some EBCDIC environments use 37. The corresponding + values for CRLF are 3349 and 3365. The default should normally corre- spond to the standard sequence for your operating system. PCRE_CONFIG_BSR The output is an integer whose value indicates what character sequences - the \R escape sequence matches by default. A value of 0 means that \R - matches any Unicode line ending sequence; a value of 1 means that \R + the \R escape sequence matches by default. A value of 0 means that \R + matches any Unicode line ending sequence; a value of 1 means that \R matches only CR, LF, or CRLF. The default can be overridden when a pat- tern is compiled or matched. PCRE_CONFIG_LINK_SIZE - The output is an integer that contains the number of bytes used for + The output is an integer that contains the number of bytes used for internal linkage in compiled regular expressions. For the 8-bit library, the value can be 2, 3, or 4. For the 16-bit library, the value - is either 2 or 4 and is still a number of bytes. The default value of 2 - is sufficient for all but the most massive patterns, since it allows - the compiled pattern to be up to 64K in size. Larger values allow - larger regular expressions to be compiled, at the expense of slower - matching. + is either 2 or 4 and is still a number of bytes. For the 32-bit + library, the value is either 2 or 4 and is still a number of bytes. The + default value of 2 is sufficient for all but the most massive patterns, + since it allows the compiled pattern to be up to 64K in size. Larger + values allow larger regular expressions to be compiled, at the expense + of slower matching. PCRE_CONFIG_POSIX_MALLOC_THRESHOLD @@ -1726,25 +2213,34 @@ COMPILING A PATTERN two-character CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies that any Unicode newline sequence should be - recognized. The Unicode newline sequences are the three just mentioned, - plus the single characters VT (vertical tab, U+000B), FF (form feed, - U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS - (paragraph separator, U+2029). For the 8-bit library, the last two are - recognized only in UTF-8 mode. - - The newline setting in the options word uses three bits that are + recognized. + + In an ASCII/Unicode environment, the Unicode newline sequences are the + three just mentioned, plus the single characters VT (vertical tab, + U+000B), FF (form feed, U+000C), NEL (next line, U+0085), LS (line sep- + arator, U+2028), and PS (paragraph separator, U+2029). For the 8-bit + library, the last two are recognized only in UTF-8 mode. + + When PCRE is compiled to run in an EBCDIC (mainframe) environment, the + code for CR is 0x0d, the same as ASCII. However, the character code for + LF is normally 0x15, though in some EBCDIC environments 0x25 is used. + Whichever of these is not LF is made to correspond to Unicode's NEL + character. EBCDIC codes are all less than 256. For more details, see + the pcrebuild documentation. + + The newline setting in the options word uses three bits that are treated as a number, giving eight possibilities. Currently only six are - used (default plus the five values above). This means that if you set - more than one newline option, the combination may or may not be sensi- + used (default plus the five values above). This means that if you set + more than one newline option, the combination may or may not be sensi- ble. For example, PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to - PCRE_NEWLINE_CRLF, but other combinations may yield unused numbers and + PCRE_NEWLINE_CRLF, but other combinations may yield unused numbers and cause an error. - The only time that a line break in a pattern is specially recognized - when compiling is when PCRE_EXTENDED is set. CR and LF are white space - characters, and so are ignored in this mode. Also, an unescaped # out- - side a character class indicates a comment that lasts until after the - next line break sequence. In other circumstances, line break sequences + The only time that a line break in a pattern is specially recognized + when compiling is when PCRE_EXTENDED is set. CR and LF are white space + characters, and so are ignored in this mode. Also, an unescaped # out- + side a character class indicates a comment that lasts until after the + next line break sequence. In other circumstances, line break sequences in patterns are treated as literal data. The newline option that is set at compile time becomes the default that @@ -1753,67 +2249,69 @@ COMPILING A PATTERN PCRE_NO_AUTO_CAPTURE If this option is set, it disables the use of numbered capturing paren- - theses in the pattern. Any opening parenthesis that is not followed by - ? behaves as if it were followed by ?: but named parentheses can still - be used for capturing (and they acquire numbers in the usual way). + theses in the pattern. Any opening parenthesis that is not followed by + ? behaves as if it were followed by ?: but named parentheses can still + be used for capturing (and they acquire numbers in the usual way). There is no equivalent of this option in Perl. NO_START_OPTIMIZE - This is an option that acts at matching time; that is, it is really an - option for pcre_exec() or pcre_dfa_exec(). If it is set at compile - time, it is remembered with the compiled pattern and assumed at match- - ing time. For details see the discussion of PCRE_NO_START_OPTIMIZE + This is an option that acts at matching time; that is, it is really an + option for pcre_exec() or pcre_dfa_exec(). If it is set at compile + time, it is remembered with the compiled pattern and assumed at match- + ing time. For details see the discussion of PCRE_NO_START_OPTIMIZE below. PCRE_UCP - This option changes the way PCRE processes \B, \b, \D, \d, \S, \s, \W, - \w, and some of the POSIX character classes. By default, only ASCII - characters are recognized, but if PCRE_UCP is set, Unicode properties - are used instead to classify characters. More details are given in the - section on generic character types in the pcrepattern page. If you set - PCRE_UCP, matching one of the items it affects takes much longer. The - option is available only if PCRE has been compiled with Unicode prop- + This option changes the way PCRE processes \B, \b, \D, \d, \S, \s, \W, + \w, and some of the POSIX character classes. By default, only ASCII + characters are recognized, but if PCRE_UCP is set, Unicode properties + are used instead to classify characters. More details are given in the + section on generic character types in the pcrepattern page. If you set + PCRE_UCP, matching one of the items it affects takes much longer. The + option is available only if PCRE has been compiled with Unicode prop- erty support. PCRE_UNGREEDY - This option inverts the "greediness" of the quantifiers so that they - are not greedy by default, but become greedy if followed by "?". It is - not compatible with Perl. It can also be set by a (?U) option setting + This option inverts the "greediness" of the quantifiers so that they + are not greedy by default, but become greedy if followed by "?". It is + not compatible with Perl. It can also be set by a (?U) option setting within the pattern. PCRE_UTF8 - This option causes PCRE to regard both the pattern and the subject as + This option causes PCRE to regard both the pattern and the subject as strings of UTF-8 characters instead of single-byte strings. However, it - is available only when PCRE is built to include UTF support. If not, - the use of this option provokes an error. Details of how this option + is available only when PCRE is built to include UTF support. If not, + the use of this option provokes an error. Details of how this option changes the behaviour of PCRE are given in the pcreunicode page. PCRE_NO_UTF8_CHECK When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is - automatically checked. There is a discussion about the validity of - UTF-8 strings in the pcreunicode page. If an invalid UTF-8 sequence is - found, pcre_compile() returns an error. If you already know that your - pattern is valid, and you want to skip this check for performance rea- - sons, you can set the PCRE_NO_UTF8_CHECK option. When it is set, the + automatically checked. There is a discussion about the validity of + UTF-8 strings in the pcreunicode page. If an invalid UTF-8 sequence is + found, pcre_compile() returns an error. If you already know that your + pattern is valid, and you want to skip this check for performance rea- + sons, you can set the PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid UTF-8 string as a pattern is undefined. It - may cause your program to crash. Note that this option can also be - passed to pcre_exec() and pcre_dfa_exec(), to suppress the validity - checking of subject strings. + may cause your program to crash. Note that this option can also be + passed to pcre_exec() and pcre_dfa_exec(), to suppress the validity + checking of subject strings only. If the same string is being matched + many times, the option can be safely set for the second and subsequent + matchings to improve performance. COMPILATION ERROR CODES - The following table lists the error codes than may be returned by - pcre_compile2(), along with the error messages that may be returned by - both compiling functions. Note that error messages are always 8-bit - ASCII strings, even in 16-bit mode. As PCRE has developed, some error - codes have fallen out of use. To avoid confusion, they have not been - re-used. + The following table lists the error codes than may be returned by + pcre_compile2(), along with the error messages that may be returned by + both compiling functions. Note that error messages are always 8-bit + ASCII strings, even in 16-bit or 32-bit mode. As PCRE has developed, + some error codes have fallen out of use. To avoid confusion, they have + not been re-used. 0 no error 1 \ at end of pattern @@ -1896,8 +2394,9 @@ COMPILATION ERROR CODES 74 invalid UTF-16 string (specifically UTF-16) 75 name is too long in (*MARK), (*PRUNE), (*SKIP), or (*THEN) 76 character value in \u.... sequence is too large + 77 invalid UTF-32 string (specifically UTF-32) - The numbers 32 and 10000 in errors 48 and 49 are defaults; different + The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may be used if the limits were changed when PCRE was built. @@ -1906,60 +2405,64 @@ STUDYING A PATTERN pcre_extra *pcre_study(const pcre *code, int options const char **errptr); - If a compiled pattern is going to be used several times, it is worth + If a compiled pattern is going to be used several times, it is worth spending more time analyzing it in order to speed up the time taken for - matching. The function pcre_study() takes a pointer to a compiled pat- + matching. The function pcre_study() takes a pointer to a compiled pat- tern as its first argument. If studying the pattern produces additional - information that will help speed up matching, pcre_study() returns a - pointer to a pcre_extra block, in which the study_data field points to + information that will help speed up matching, pcre_study() returns a + pointer to a pcre_extra block, in which the study_data field points to the results of the study. The returned value from pcre_study() can be passed directly to - pcre_exec() or pcre_dfa_exec(). However, a pcre_extra block also con- - tains other fields that can be set by the caller before the block is + pcre_exec() or pcre_dfa_exec(). However, a pcre_extra block also con- + tains other fields that can be set by the caller before the block is passed; these are described below in the section on matching a pattern. - If studying the pattern does not produce any useful information, - pcre_study() returns NULL. In that circumstance, if the calling program - wants to pass any of the other fields to pcre_exec() or - pcre_dfa_exec(), it must set up its own pcre_extra block. + If studying the pattern does not produce any useful information, + pcre_study() returns NULL by default. In that circumstance, if the + calling program wants to pass any of the other fields to pcre_exec() or + pcre_dfa_exec(), it must set up its own pcre_extra block. However, if + pcre_study() is called with the PCRE_STUDY_EXTRA_NEEDED option, it + returns a pcre_extra block even if studying did not find any additional + information. It may still return NULL, however, if an error occurs in + pcre_study(). - The second argument of pcre_study() contains option bits. There are - three options: + The second argument of pcre_study() contains option bits. There are + three further options in addition to PCRE_STUDY_EXTRA_NEEDED: PCRE_STUDY_JIT_COMPILE PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE - If any of these are set, and the just-in-time compiler is available, - the pattern is further compiled into machine code that executes much - faster than the pcre_exec() interpretive matching function. If the - just-in-time compiler is not available, these options are ignored. All - other bits in the options argument must be zero. + If any of these are set, and the just-in-time compiler is available, + the pattern is further compiled into machine code that executes much + faster than the pcre_exec() interpretive matching function. If the + just-in-time compiler is not available, these options are ignored. All + undefined bits in the options argument must be zero. - JIT compilation is a heavyweight optimization. It can take some time - for patterns to be analyzed, and for one-off matches and simple pat- - terns the benefit of faster execution might be offset by a much slower + JIT compilation is a heavyweight optimization. It can take some time + for patterns to be analyzed, and for one-off matches and simple pat- + terns the benefit of faster execution might be offset by a much slower study time. Not all patterns can be optimized by the JIT compiler. For - those that cannot be handled, matching automatically falls back to the - pcre_exec() interpreter. For more details, see the pcrejit documenta- + those that cannot be handled, matching automatically falls back to the + pcre_exec() interpreter. For more details, see the pcrejit documenta- tion. - The third argument for pcre_study() is a pointer for an error message. - If studying succeeds (even if no data is returned), the variable it - points to is set to NULL. Otherwise it is set to point to a textual + The third argument for pcre_study() is a pointer for an error message. + If studying succeeds (even if no data is returned), the variable it + points to is set to NULL. Otherwise it is set to point to a textual error message. This is a static string that is part of the library. You - must not try to free it. You should test the error pointer for NULL + must not try to free it. You should test the error pointer for NULL after calling pcre_study(), to be sure that it has run successfully. - When you are finished with a pattern, you can free the memory used for + When you are finished with a pattern, you can free the memory used for the study data by calling pcre_free_study(). This function was added to - the API for release 8.20. For earlier versions, the memory could be - freed with pcre_free(), just like the pattern itself. This will still - work in cases where JIT optimization is not used, but it is advisable + the API for release 8.20. For earlier versions, the memory could be + freed with pcre_free(), just like the pattern itself. This will still + work in cases where JIT optimization is not used, but it is advisable to change to the new function when convenient. - This is a typical way in which pcre_study() is used (except that in a + This is a typical way in which pcre_study() is used (except that in a real application there should be tests for errors): int rc; @@ -1979,15 +2482,16 @@ STUDYING A PATTERN Studying a pattern does two things: first, a lower bound for the length of subject string that is needed to match the pattern is computed. This does not mean that there are any strings of that length that match, but - it does guarantee that no shorter strings match. The value is used by - pcre_exec() and pcre_dfa_exec() to avoid wasting time by trying to - match strings that are shorter than the lower bound. You can find out - the value in a calling program via the pcre_fullinfo() function. + it does guarantee that no shorter strings match. The value is used to + avoid wasting time by trying to match strings that are shorter than the + lower bound. You can find out the value in a calling program via the + pcre_fullinfo() function. Studying a pattern is also useful for non-anchored patterns that do not - have a single fixed starting character. A bitmap of possible starting - bytes is created. This speeds up finding a position in the subject at + have a single fixed starting character. A bitmap of possible starting + bytes is created. This speeds up finding a position in the subject at which to start matching. (In 16-bit mode, the bitmap is used for 16-bit + values less than 256. In 32-bit mode, the bitmap is used for 32-bit values less than 256.) These two optimizations apply to both pcre_exec() and pcre_dfa_exec(), @@ -2126,21 +2630,27 @@ INFORMATION ABOUT A PATTERN If there is a fixed first value, for example, the letter "c" from a pattern such as (cat|cow|coyote), its value is returned. In the 8-bit - library, the value is always less than 256; in the 16-bit library the - value can be up to 0xffff. + library, the value is always less than 256. In the 16-bit library the + value can be up to 0xffff. In the 32-bit library the value can be up to + 0x10ffff. If there is no fixed first value, and if either - (a) the pattern was compiled with the PCRE_MULTILINE option, and every + (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch starts with "^", or (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set (if it were set, the pattern would be anchored), - -1 is returned, indicating that the pattern matches only at the start - of a subject string or after any newline within the string. Otherwise + -1 is returned, indicating that the pattern matches only at the start + of a subject string or after any newline within the string. Otherwise -2 is returned. For anchored patterns, -2 is returned. + Since for the 32-bit library using the non-UTF-32 mode, this function + is unable to return the full 32-bit range of the character, this value + is deprecated; instead the PCRE_INFO_FIRSTCHARACTERFLAGS and + PCRE_INFO_FIRSTCHARACTER values should be used. + PCRE_INFO_FIRSTTABLE If the pattern was studied, and this resulted in the construction of a @@ -2188,68 +2698,75 @@ INFORMATION ABOUT A PATTERN example, for the pattern /^a\d+z\d+/ the returned value is "z", but for /^a\dz\d/ the returned value is -1. + Since for the 32-bit library using the non-UTF-32 mode, this function + is unable to return the full 32-bit range of the character, this value + is deprecated; instead the PCRE_INFO_REQUIREDCHARFLAGS and + PCRE_INFO_REQUIREDCHAR values should be used. + PCRE_INFO_MAXLOOKBEHIND - Return the number of characters (NB not bytes) in the longest lookbe- - hind assertion in the pattern. Note that the simple assertions \b and - \B require a one-character lookbehind. This information is useful when + Return the number of characters (NB not bytes) in the longest lookbe- + hind assertion in the pattern. Note that the simple assertions \b and + \B require a one-character lookbehind. This information is useful when doing multi-segment matching using the partial matching facilities. PCRE_INFO_MINLENGTH - If the pattern was studied and a minimum length for matching subject - strings was computed, its value is returned. Otherwise the returned - value is -1. The value is a number of characters, which in UTF-8 mode - may be different from the number of bytes. The fourth argument should - point to an int variable. A non-negative value is a lower bound to the - length of any matching string. There may not be any strings of that - length that do actually match, but every string that does match is at + If the pattern was studied and a minimum length for matching subject + strings was computed, its value is returned. Otherwise the returned + value is -1. The value is a number of characters, which in UTF-8 mode + may be different from the number of bytes. The fourth argument should + point to an int variable. A non-negative value is a lower bound to the + length of any matching string. There may not be any strings of that + length that do actually match, but every string that does match is at least that long. PCRE_INFO_NAMECOUNT PCRE_INFO_NAMEENTRYSIZE PCRE_INFO_NAMETABLE - PCRE supports the use of named as well as numbered capturing parenthe- - ses. The names are just an additional way of identifying the parenthe- + PCRE supports the use of named as well as numbered capturing parenthe- + ses. The names are just an additional way of identifying the parenthe- ses, which still acquire numbers. Several convenience functions such as - pcre_get_named_substring() are provided for extracting captured sub- - strings by name. It is also possible to extract the data directly, by - first converting the name to a number in order to access the correct + pcre_get_named_substring() are provided for extracting captured sub- + strings by name. It is also possible to extract the data directly, by + first converting the name to a number in order to access the correct pointers in the output vector (described with pcre_exec() below). To do - the conversion, you need to use the name-to-number map, which is + the conversion, you need to use the name-to-number map, which is described by these three values. The map consists of a number of fixed-size entries. PCRE_INFO_NAMECOUNT gives the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size - of each entry; both of these return an int value. The entry size - depends on the length of the longest name. PCRE_INFO_NAMETABLE returns + of each entry; both of these return an int value. The entry size + depends on the length of the longest name. PCRE_INFO_NAMETABLE returns a pointer to the first entry of the table. This is a pointer to char in the 8-bit library, where the first two bytes of each entry are the num- - ber of the capturing parenthesis, most significant byte first. In the - 16-bit library, the pointer points to 16-bit data units, the first of - which contains the parenthesis number. The rest of the entry is the - corresponding name, zero terminated. - - The names are in alphabetical order. Duplicate names may appear if (?| + ber of the capturing parenthesis, most significant byte first. In the + 16-bit library, the pointer points to 16-bit data units, the first of + which contains the parenthesis number. In the 32-bit library, the + pointer points to 32-bit data units, the first of which contains the + parenthesis number. The rest of the entry is the corresponding name, + zero terminated. + + The names are in alphabetical order. Duplicate names may appear if (?| is used to create multiple groups with the same number, as described in - the section on duplicate subpattern numbers in the pcrepattern page. - Duplicate names for subpatterns with different numbers are permitted - only if PCRE_DUPNAMES is set. In all cases of duplicate names, they - appear in the table in the order in which they were found in the pat- - tern. In the absence of (?| this is the order of increasing number; + the section on duplicate subpattern numbers in the pcrepattern page. + Duplicate names for subpatterns with different numbers are permitted + only if PCRE_DUPNAMES is set. In all cases of duplicate names, they + appear in the table in the order in which they were found in the pat- + tern. In the absence of (?| this is the order of increasing number; when (?| is used this is not necessarily the case because later subpat- terns may have lower numbers. - As a simple example of the name/number table, consider the following + As a simple example of the name/number table, consider the following pattern after compilation by the 8-bit library (assume PCRE_EXTENDED is set, so white space - including newlines - is ignored): (?<date> (?<year>(\d\d)?\d\d) - (?<month>\d\d) - (?<day>\d\d) ) - There are four named subpatterns, so the table has four entries, and - each entry in the table is eight bytes long. The table is as follows, + There are four named subpatterns, so the table has four entries, and + each entry in the table is eight bytes long. The table is as follows, with non-printing bytes shows in hexadecimal, and undefined bytes shown as ??: @@ -2258,31 +2775,31 @@ INFORMATION ABOUT A PATTERN 00 04 m o n t h 00 00 02 y e a r 00 ?? - When writing code to extract data from named subpatterns using the - name-to-number map, remember that the length of the entries is likely + When writing code to extract data from named subpatterns using the + name-to-number map, remember that the length of the entries is likely to be different for each compiled pattern. PCRE_INFO_OKPARTIAL - Return 1 if the pattern can be used for partial matching with - pcre_exec(), otherwise 0. The fourth argument should point to an int - variable. From release 8.00, this always returns 1, because the - restrictions that previously applied to partial matching have been - lifted. The pcrepartial documentation gives details of partial match- + Return 1 if the pattern can be used for partial matching with + pcre_exec(), otherwise 0. The fourth argument should point to an int + variable. From release 8.00, this always returns 1, because the + restrictions that previously applied to partial matching have been + lifted. The pcrepartial documentation gives details of partial match- ing. PCRE_INFO_OPTIONS - Return a copy of the options with which the pattern was compiled. The - fourth argument should point to an unsigned long int variable. These + Return a copy of the options with which the pattern was compiled. The + fourth argument should point to an unsigned long int variable. These option bits are those specified in the call to pcre_compile(), modified by any top-level option settings at the start of the pattern itself. In - other words, they are the options that will be in force when matching - starts. For example, if the pattern /(?im)abc(?-i)d/ is compiled with - the PCRE_EXTENDED option, the result is PCRE_CASELESS, PCRE_MULTILINE, + other words, they are the options that will be in force when matching + starts. For example, if the pattern /(?im)abc(?-i)d/ is compiled with + the PCRE_EXTENDED option, the result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED. - A pattern is automatically anchored by PCRE if all of its top-level + A pattern is automatically anchored by PCRE if all of its top-level alternatives begin with one of the following: ^ unless PCRE_MULTILINE is set @@ -2296,27 +2813,92 @@ INFORMATION ABOUT A PATTERN PCRE_INFO_SIZE - Return the size of the compiled pattern in bytes (for both libraries). - The fourth argument should point to a size_t variable. This value does - not include the size of the pcre structure that is returned by - pcre_compile(). The value that is passed as the argument to pcre_mal- - loc() when pcre_compile() is getting memory in which to place the com- - piled data is the value returned by this option plus the size of the - pcre structure. Studying a compiled pattern, with or without JIT, does + Return the size of the compiled pattern in bytes (for both libraries). + The fourth argument should point to a size_t variable. This value does + not include the size of the pcre structure that is returned by + pcre_compile(). The value that is passed as the argument to pcre_mal- + loc() when pcre_compile() is getting memory in which to place the com- + piled data is the value returned by this option plus the size of the + pcre structure. Studying a compiled pattern, with or without JIT, does not alter the value returned by this option. PCRE_INFO_STUDYSIZE Return the size in bytes of the data block pointed to by the study_data - field in a pcre_extra block. If pcre_extra is NULL, or there is no - study data, zero is returned. The fourth argument should point to a - size_t variable. The study_data field is set by pcre_study() to record - information that will speed up matching (see the section entitled + field in a pcre_extra block. If pcre_extra is NULL, or there is no + study data, zero is returned. The fourth argument should point to a + size_t variable. The study_data field is set by pcre_study() to record + information that will speed up matching (see the section entitled "Studying a pattern" above). The format of the study_data block is pri- - vate, but its length is made available via this option so that it can + vate, but its length is made available via this option so that it can be saved and restored (see the pcreprecompile documentation for details). + PCRE_INFO_FIRSTCHARACTERFLAGS + + Return information about the first data unit of any matched string, for + a non-anchored pattern. The fourth argument should point to an int + variable. + + If there is a fixed first value, for example, the letter "c" from a + pattern such as (cat|cow|coyote), 1 is returned, and the character + value can be retrieved using PCRE_INFO_FIRSTCHARACTER. + + If there is no fixed first value, and if either + + (a) the pattern was compiled with the PCRE_MULTILINE option, and every + branch starts with "^", or + + (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not + set (if it were set, the pattern would be anchored), + + 2 is returned, indicating that the pattern matches only at the start of + a subject string or after any newline within the string. Otherwise 0 is + returned. For anchored patterns, 0 is returned. + + PCRE_INFO_FIRSTCHARACTER + + Return the fixed first character value, if PCRE_INFO_FIRSTCHARACTER- + FLAGS returned 1; otherwise returns 0. The fourth argument should point + to an uint_t variable. + + In the 8-bit library, the value is always less than 256. In the 16-bit + library the value can be up to 0xffff. In the 32-bit library in UTF-32 + mode the value can be up to 0x10ffff, and up to 0xffffffff when not + using UTF-32 mode. + + If there is no fixed first value, and if either + + (a) the pattern was compiled with the PCRE_MULTILINE option, and every + branch starts with "^", or + + (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not + set (if it were set, the pattern would be anchored), + + -1 is returned, indicating that the pattern matches only at the start + of a subject string or after any newline within the string. Otherwise + -2 is returned. For anchored patterns, -2 is returned. + + PCRE_INFO_REQUIREDCHARFLAGS + + Returns 1 if there is a rightmost literal data unit that must exist in + any matched string, other than at its start. The fourth argument should + point to an int variable. If there is no such value, 0 is returned. If + returning 1, the character value itself can be retrieved using + PCRE_INFO_REQUIREDCHAR. + + For anchored patterns, a last literal value is recorded only if it fol- + lows something of variable length. For example, for the pattern + /^a\d+z\d+/ the returned value 1 (with "z" returned from + PCRE_INFO_REQUIREDCHAR), but for /^a\dz\d/ the returned value is 0. + + PCRE_INFO_REQUIREDCHAR + + Return the value of the rightmost literal data unit that must exist in + any matched string, other than at its start, if such a value has been + recorded. The fourth argument should point to an uint32_t variable. If + there is no such value, 0 is returned. + REFERENCE COUNTS @@ -2398,7 +2980,10 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION In the 16-bit version of this structure, the mark field has type "PCRE_UCHAR16 **". - The flags field is used to specify which of the other fields are set. + In the 32-bit version of this structure, the mark field has type + "PCRE_UCHAR32 **". + + The flags field is used to specify which of the other fields are set. The flag bits are: PCRE_EXTRA_CALLOUT_DATA @@ -2409,112 +2994,112 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION PCRE_EXTRA_STUDY_DATA PCRE_EXTRA_TABLES - Other flag bits should be set to zero. The study_data field and some- - times the executable_jit field are set in the pcre_extra block that is - returned by pcre_study(), together with the appropriate flag bits. You - should not set these yourself, but you may add to the block by setting + Other flag bits should be set to zero. The study_data field and some- + times the executable_jit field are set in the pcre_extra block that is + returned by pcre_study(), together with the appropriate flag bits. You + should not set these yourself, but you may add to the block by setting other fields and their corresponding flag bits. The match_limit field provides a means of preventing PCRE from using up - a vast amount of resources when running patterns that are not going to - match, but which have a very large number of possibilities in their - search trees. The classic example is a pattern that uses nested unlim- + a vast amount of resources when running patterns that are not going to + match, but which have a very large number of possibilities in their + search trees. The classic example is a pattern that uses nested unlim- ited repeats. - Internally, pcre_exec() uses a function called match(), which it calls - repeatedly (sometimes recursively). The limit set by match_limit is - imposed on the number of times this function is called during a match, - which has the effect of limiting the amount of backtracking that can + Internally, pcre_exec() uses a function called match(), which it calls + repeatedly (sometimes recursively). The limit set by match_limit is + imposed on the number of times this function is called during a match, + which has the effect of limiting the amount of backtracking that can take place. For patterns that are not anchored, the count restarts from zero for each position in the subject string. When pcre_exec() is called with a pattern that was successfully studied - with a JIT option, the way that the matching is executed is entirely + with a JIT option, the way that the matching is executed is entirely different. However, there is still the possibility of runaway matching that goes on for a very long time, and so the match_limit value is also used in this case (but in a different way) to limit how long the match- ing can continue. - The default value for the limit can be set when PCRE is built; the - default default is 10 million, which handles all but the most extreme - cases. You can override the default by suppling pcre_exec() with a - pcre_extra block in which match_limit is set, and - PCRE_EXTRA_MATCH_LIMIT is set in the flags field. If the limit is + The default value for the limit can be set when PCRE is built; the + default default is 10 million, which handles all but the most extreme + cases. You can override the default by suppling pcre_exec() with a + pcre_extra block in which match_limit is set, and + PCRE_EXTRA_MATCH_LIMIT is set in the flags field. If the limit is exceeded, pcre_exec() returns PCRE_ERROR_MATCHLIMIT. - The match_limit_recursion field is similar to match_limit, but instead + The match_limit_recursion field is similar to match_limit, but instead of limiting the total number of times that match() is called, it limits - the depth of recursion. The recursion depth is a smaller number than - the total number of calls, because not all calls to match() are recur- + the depth of recursion. The recursion depth is a smaller number than + the total number of calls, because not all calls to match() are recur- sive. This limit is of use only if it is set smaller than match_limit. - Limiting the recursion depth limits the amount of machine stack that - can be used, or, when PCRE has been compiled to use memory on the heap - instead of the stack, the amount of heap memory that can be used. This - limit is not relevant, and is ignored, when matching is done using JIT + Limiting the recursion depth limits the amount of machine stack that + can be used, or, when PCRE has been compiled to use memory on the heap + instead of the stack, the amount of heap memory that can be used. This + limit is not relevant, and is ignored, when matching is done using JIT compiled code. - The default value for match_limit_recursion can be set when PCRE is - built; the default default is the same value as the default for - match_limit. You can override the default by suppling pcre_exec() with - a pcre_extra block in which match_limit_recursion is set, and - PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the flags field. If the + The default value for match_limit_recursion can be set when PCRE is + built; the default default is the same value as the default for + match_limit. You can override the default by suppling pcre_exec() with + a pcre_extra block in which match_limit_recursion is set, and + PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the flags field. If the limit is exceeded, pcre_exec() returns PCRE_ERROR_RECURSIONLIMIT. - The callout_data field is used in conjunction with the "callout" fea- + The callout_data field is used in conjunction with the "callout" fea- ture, and is described in the pcrecallout documentation. - The tables field is used to pass a character tables pointer to - pcre_exec(); this overrides the value that is stored with the compiled - pattern. A non-NULL value is stored with the compiled pattern only if - custom tables were supplied to pcre_compile() via its tableptr argu- + The tables field is used to pass a character tables pointer to + pcre_exec(); this overrides the value that is stored with the compiled + pattern. A non-NULL value is stored with the compiled pattern only if + custom tables were supplied to pcre_compile() via its tableptr argu- ment. If NULL is passed to pcre_exec() using this mechanism, it forces - PCRE's internal tables to be used. This facility is helpful when re- - using patterns that have been saved after compiling with an external - set of tables, because the external tables might be at a different - address when pcre_exec() is called. See the pcreprecompile documenta- + PCRE's internal tables to be used. This facility is helpful when re- + using patterns that have been saved after compiling with an external + set of tables, because the external tables might be at a different + address when pcre_exec() is called. See the pcreprecompile documenta- tion for a discussion of saving compiled patterns for later use. - If PCRE_EXTRA_MARK is set in the flags field, the mark field must be - set to point to a suitable variable. If the pattern contains any back- - tracking control verbs such as (*MARK:NAME), and the execution ends up - with a name to pass back, a pointer to the name string (zero termi- - nated) is placed in the variable pointed to by the mark field. The - names are within the compiled pattern; if you wish to retain such a - name you must copy it before freeing the memory of a compiled pattern. - If there is no name to pass back, the variable pointed to by the mark - field is set to NULL. For details of the backtracking control verbs, + If PCRE_EXTRA_MARK is set in the flags field, the mark field must be + set to point to a suitable variable. If the pattern contains any back- + tracking control verbs such as (*MARK:NAME), and the execution ends up + with a name to pass back, a pointer to the name string (zero termi- + nated) is placed in the variable pointed to by the mark field. The + names are within the compiled pattern; if you wish to retain such a + name you must copy it before freeing the memory of a compiled pattern. + If there is no name to pass back, the variable pointed to by the mark + field is set to NULL. For details of the backtracking control verbs, see the section entitled "Backtracking control" in the pcrepattern doc- umentation. Option bits for pcre_exec() - The unused bits of the options argument for pcre_exec() must be zero. - The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_xxx, - PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART, - PCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_HARD, and + The unused bits of the options argument for pcre_exec() must be zero. + The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_xxx, + PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART, + PCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_HARD, and PCRE_PARTIAL_SOFT. - If the pattern was successfully studied with one of the just-in-time + If the pattern was successfully studied with one of the just-in-time (JIT) compile options, the only supported options for JIT execution are - PCRE_NO_UTF8_CHECK, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, - PCRE_NOTEMPTY_ATSTART, PCRE_PARTIAL_HARD, and PCRE_PARTIAL_SOFT. If an - unsupported option is used, JIT execution is disabled and the normal + PCRE_NO_UTF8_CHECK, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, + PCRE_NOTEMPTY_ATSTART, PCRE_PARTIAL_HARD, and PCRE_PARTIAL_SOFT. If an + unsupported option is used, JIT execution is disabled and the normal interpretive code in pcre_exec() is run. PCRE_ANCHORED - The PCRE_ANCHORED option limits pcre_exec() to matching at the first - matching position. If a pattern was compiled with PCRE_ANCHORED, or - turned out to be anchored by virtue of its contents, it cannot be made + The PCRE_ANCHORED option limits pcre_exec() to matching at the first + matching position. If a pattern was compiled with PCRE_ANCHORED, or + turned out to be anchored by virtue of its contents, it cannot be made unachored at matching time. PCRE_BSR_ANYCRLF PCRE_BSR_UNICODE These options (which are mutually exclusive) control what the \R escape - sequence matches. The choice is either to match only CR, LF, or CRLF, - or to match any Unicode newline sequence. These options override the + sequence matches. The choice is either to match only CR, LF, or CRLF, + or to match any Unicode newline sequence. These options override the choice that was made or defaulted when the pattern was compiled. PCRE_NEWLINE_CR @@ -2523,337 +3108,337 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION PCRE_NEWLINE_ANYCRLF PCRE_NEWLINE_ANY - These options override the newline definition that was chosen or - defaulted when the pattern was compiled. For details, see the descrip- - tion of pcre_compile() above. During matching, the newline choice - affects the behaviour of the dot, circumflex, and dollar metacharac- - ters. It may also alter the way the match position is advanced after a + These options override the newline definition that was chosen or + defaulted when the pattern was compiled. For details, see the descrip- + tion of pcre_compile() above. During matching, the newline choice + affects the behaviour of the dot, circumflex, and dollar metacharac- + ters. It may also alter the way the match position is advanced after a match failure for an unanchored pattern. - When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is - set, and a match attempt for an unanchored pattern fails when the cur- - rent position is at a CRLF sequence, and the pattern contains no - explicit matches for CR or LF characters, the match position is + When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is + set, and a match attempt for an unanchored pattern fails when the cur- + rent position is at a CRLF sequence, and the pattern contains no + explicit matches for CR or LF characters, the match position is advanced by two characters instead of one, in other words, to after the CRLF. The above rule is a compromise that makes the most common cases work as - expected. For example, if the pattern is .+A (and the PCRE_DOTALL + expected. For example, if the pattern is .+A (and the PCRE_DOTALL option is not set), it does not match the string "\r\nA" because, after - failing at the start, it skips both the CR and the LF before retrying. - However, the pattern [\r\n]A does match that string, because it con- + failing at the start, it skips both the CR and the LF before retrying. + However, the pattern [\r\n]A does match that string, because it con- tains an explicit CR or LF reference, and so advances only by one char- acter after the first failure. An explicit match for CR of LF is either a literal appearance of one of - those characters, or one of the \r or \n escape sequences. Implicit - matches such as [^X] do not count, nor does \s (which includes CR and + those characters, or one of the \r or \n escape sequences. Implicit + matches such as [^X] do not count, nor does \s (which includes CR and LF in the characters that it matches). - Notwithstanding the above, anomalous effects may still occur when CRLF + Notwithstanding the above, anomalous effects may still occur when CRLF is a valid newline sequence and explicit \r or \n escapes appear in the pattern. PCRE_NOTBOL This option specifies that first character of the subject string is not - the beginning of a line, so the circumflex metacharacter should not - match before it. Setting this without PCRE_MULTILINE (at compile time) - causes circumflex never to match. This option affects only the behav- + the beginning of a line, so the circumflex metacharacter should not + match before it. Setting this without PCRE_MULTILINE (at compile time) + causes circumflex never to match. This option affects only the behav- iour of the circumflex metacharacter. It does not affect \A. PCRE_NOTEOL This option specifies that the end of the subject string is not the end - of a line, so the dollar metacharacter should not match it nor (except - in multiline mode) a newline immediately before it. Setting this with- + of a line, so the dollar metacharacter should not match it nor (except + in multiline mode) a newline immediately before it. Setting this with- out PCRE_MULTILINE (at compile time) causes dollar never to match. This - option affects only the behaviour of the dollar metacharacter. It does + option affects only the behaviour of the dollar metacharacter. It does not affect \Z or \z. PCRE_NOTEMPTY An empty string is not considered to be a valid match if this option is - set. If there are alternatives in the pattern, they are tried. If all - the alternatives match the empty string, the entire match fails. For + set. If there are alternatives in the pattern, they are tried. If all + the alternatives match the empty string, the entire match fails. For example, if the pattern a?b? - is applied to a string not beginning with "a" or "b", it matches an - empty string at the start of the subject. With PCRE_NOTEMPTY set, this + is applied to a string not beginning with "a" or "b", it matches an + empty string at the start of the subject. With PCRE_NOTEMPTY set, this match is not valid, so PCRE searches further into the string for occur- rences of "a" or "b". PCRE_NOTEMPTY_ATSTART - This is like PCRE_NOTEMPTY, except that an empty string match that is - not at the start of the subject is permitted. If the pattern is + This is like PCRE_NOTEMPTY, except that an empty string match that is + not at the start of the subject is permitted. If the pattern is anchored, such a match can occur only if the pattern contains \K. - Perl has no direct equivalent of PCRE_NOTEMPTY or - PCRE_NOTEMPTY_ATSTART, but it does make a special case of a pattern - match of the empty string within its split() function, and when using - the /g modifier. It is possible to emulate Perl's behaviour after + Perl has no direct equivalent of PCRE_NOTEMPTY or + PCRE_NOTEMPTY_ATSTART, but it does make a special case of a pattern + match of the empty string within its split() function, and when using + the /g modifier. It is possible to emulate Perl's behaviour after matching a null string by first trying the match again at the same off- - set with PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED, and then if that + set with PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED, and then if that fails, by advancing the starting offset (see below) and trying an ordi- - nary match again. There is some code that demonstrates how to do this - in the pcredemo sample program. In the most general case, you have to - check to see if the newline convention recognizes CRLF as a newline, - and if so, and the current character is CR followed by LF, advance the + nary match again. There is some code that demonstrates how to do this + in the pcredemo sample program. In the most general case, you have to + check to see if the newline convention recognizes CRLF as a newline, + and if so, and the current character is CR followed by LF, advance the starting offset by two characters instead of one. PCRE_NO_START_OPTIMIZE - There are a number of optimizations that pcre_exec() uses at the start - of a match, in order to speed up the process. For example, if it is + There are a number of optimizations that pcre_exec() uses at the start + of a match, in order to speed up the process. For example, if it is known that an unanchored match must start with a specific character, it - searches the subject for that character, and fails immediately if it - cannot find it, without actually running the main matching function. + searches the subject for that character, and fails immediately if it + cannot find it, without actually running the main matching function. This means that a special item such as (*COMMIT) at the start of a pat- - tern is not considered until after a suitable starting point for the - match has been found. When callouts or (*MARK) items are in use, these + tern is not considered until after a suitable starting point for the + match has been found. When callouts or (*MARK) items are in use, these "start-up" optimizations can cause them to be skipped if the pattern is - never actually used. The start-up optimizations are in effect a pre- + never actually used. The start-up optimizations are in effect a pre- scan of the subject that takes place before the pattern is run. - The PCRE_NO_START_OPTIMIZE option disables the start-up optimizations, - possibly causing performance to suffer, but ensuring that in cases - where the result is "no match", the callouts do occur, and that items + The PCRE_NO_START_OPTIMIZE option disables the start-up optimizations, + possibly causing performance to suffer, but ensuring that in cases + where the result is "no match", the callouts do occur, and that items such as (*COMMIT) and (*MARK) are considered at every possible starting - position in the subject string. If PCRE_NO_START_OPTIMIZE is set at - compile time, it cannot be unset at matching time. The use of + position in the subject string. If PCRE_NO_START_OPTIMIZE is set at + compile time, it cannot be unset at matching time. The use of PCRE_NO_START_OPTIMIZE disables JIT execution; when it is set, matching is always done using interpretively. - Setting PCRE_NO_START_OPTIMIZE can change the outcome of a matching + Setting PCRE_NO_START_OPTIMIZE can change the outcome of a matching operation. Consider the pattern (*COMMIT)ABC - When this is compiled, PCRE records the fact that a match must start - with the character "A". Suppose the subject string is "DEFABC". The - start-up optimization scans along the subject, finds "A" and runs the - first match attempt from there. The (*COMMIT) item means that the pat- - tern must match the current starting position, which in this case, it - does. However, if the same match is run with PCRE_NO_START_OPTIMIZE - set, the initial scan along the subject string does not happen. The - first match attempt is run starting from "D" and when this fails, - (*COMMIT) prevents any further matches being tried, so the overall - result is "no match". If the pattern is studied, more start-up opti- - mizations may be used. For example, a minimum length for the subject + When this is compiled, PCRE records the fact that a match must start + with the character "A". Suppose the subject string is "DEFABC". The + start-up optimization scans along the subject, finds "A" and runs the + first match attempt from there. The (*COMMIT) item means that the pat- + tern must match the current starting position, which in this case, it + does. However, if the same match is run with PCRE_NO_START_OPTIMIZE + set, the initial scan along the subject string does not happen. The + first match attempt is run starting from "D" and when this fails, + (*COMMIT) prevents any further matches being tried, so the overall + result is "no match". If the pattern is studied, more start-up opti- + mizations may be used. For example, a minimum length for the subject may be recorded. Consider the pattern (*MARK:A)(X|Y) - The minimum length for a match is one character. If the subject is - "ABC", there will be attempts to match "ABC", "BC", "C", and then - finally an empty string. If the pattern is studied, the final attempt - does not take place, because PCRE knows that the subject is too short, - and so the (*MARK) is never encountered. In this case, studying the - pattern does not affect the overall match result, which is still "no + The minimum length for a match is one character. If the subject is + "ABC", there will be attempts to match "ABC", "BC", "C", and then + finally an empty string. If the pattern is studied, the final attempt + does not take place, because PCRE knows that the subject is too short, + and so the (*MARK) is never encountered. In this case, studying the + pattern does not affect the overall match result, which is still "no match", but it does affect the auxiliary information that is returned. PCRE_NO_UTF8_CHECK When PCRE_UTF8 is set at compile time, the validity of the subject as a - UTF-8 string is automatically checked when pcre_exec() is subsequently + UTF-8 string is automatically checked when pcre_exec() is subsequently called. The entire string is checked before any other processing takes - place. The value of startoffset is also checked to ensure that it - points to the start of a UTF-8 character. There is a discussion about - the validity of UTF-8 strings in the pcreunicode page. If an invalid - sequence of bytes is found, pcre_exec() returns the error + place. The value of startoffset is also checked to ensure that it + points to the start of a UTF-8 character. There is a discussion about + the validity of UTF-8 strings in the pcreunicode page. If an invalid + sequence of bytes is found, pcre_exec() returns the error PCRE_ERROR_BADUTF8 or, if PCRE_PARTIAL_HARD is set and the problem is a truncated character at the end of the subject, PCRE_ERROR_SHORTUTF8. In - both cases, information about the precise nature of the error may also - be returned (see the descriptions of these errors in the section enti- - tled Error return values from pcre_exec() below). If startoffset con- + both cases, information about the precise nature of the error may also + be returned (see the descriptions of these errors in the section enti- + tled Error return values from pcre_exec() below). If startoffset con- tains a value that does not point to the start of a UTF-8 character (or to the end of the subject), PCRE_ERROR_BADUTF8_OFFSET is returned. - If you already know that your subject is valid, and you want to skip - these checks for performance reasons, you can set the - PCRE_NO_UTF8_CHECK option when calling pcre_exec(). You might want to - do this for the second and subsequent calls to pcre_exec() if you are - making repeated calls to find all the matches in a single subject - string. However, you should be sure that the value of startoffset - points to the start of a character (or the end of the subject). When + If you already know that your subject is valid, and you want to skip + these checks for performance reasons, you can set the + PCRE_NO_UTF8_CHECK option when calling pcre_exec(). You might want to + do this for the second and subsequent calls to pcre_exec() if you are + making repeated calls to find all the matches in a single subject + string. However, you should be sure that the value of startoffset + points to the start of a character (or the end of the subject). When PCRE_NO_UTF8_CHECK is set, the effect of passing an invalid string as a - subject or an invalid value of startoffset is undefined. Your program + subject or an invalid value of startoffset is undefined. Your program may crash. PCRE_PARTIAL_HARD PCRE_PARTIAL_SOFT - These options turn on the partial matching feature. For backwards com- - patibility, PCRE_PARTIAL is a synonym for PCRE_PARTIAL_SOFT. A partial - match occurs if the end of the subject string is reached successfully, - but there are not enough subject characters to complete the match. If + These options turn on the partial matching feature. For backwards com- + patibility, PCRE_PARTIAL is a synonym for PCRE_PARTIAL_SOFT. A partial + match occurs if the end of the subject string is reached successfully, + but there are not enough subject characters to complete the match. If this happens when PCRE_PARTIAL_SOFT (but not PCRE_PARTIAL_HARD) is set, - matching continues by testing any remaining alternatives. Only if no - complete match can be found is PCRE_ERROR_PARTIAL returned instead of - PCRE_ERROR_NOMATCH. In other words, PCRE_PARTIAL_SOFT says that the - caller is prepared to handle a partial match, but only if no complete + matching continues by testing any remaining alternatives. Only if no + complete match can be found is PCRE_ERROR_PARTIAL returned instead of + PCRE_ERROR_NOMATCH. In other words, PCRE_PARTIAL_SOFT says that the + caller is prepared to handle a partial match, but only if no complete match can be found. - If PCRE_PARTIAL_HARD is set, it overrides PCRE_PARTIAL_SOFT. In this - case, if a partial match is found, pcre_exec() immediately returns - PCRE_ERROR_PARTIAL, without considering any other alternatives. In - other words, when PCRE_PARTIAL_HARD is set, a partial match is consid- + If PCRE_PARTIAL_HARD is set, it overrides PCRE_PARTIAL_SOFT. In this + case, if a partial match is found, pcre_exec() immediately returns + PCRE_ERROR_PARTIAL, without considering any other alternatives. In + other words, when PCRE_PARTIAL_HARD is set, a partial match is consid- ered to be more important that an alternative complete match. - In both cases, the portion of the string that was inspected when the + In both cases, the portion of the string that was inspected when the partial match was found is set as the first matching string. There is a - more detailed discussion of partial and multi-segment matching, with + more detailed discussion of partial and multi-segment matching, with examples, in the pcrepartial documentation. The string to be matched by pcre_exec() - The subject string is passed to pcre_exec() as a pointer in subject, a - length in bytes in length, and a starting byte offset in startoffset. - If this is negative or greater than the length of the subject, - pcre_exec() returns PCRE_ERROR_BADOFFSET. When the starting offset is - zero, the search for a match starts at the beginning of the subject, + The subject string is passed to pcre_exec() as a pointer in subject, a + length in bytes in length, and a starting byte offset in startoffset. + If this is negative or greater than the length of the subject, + pcre_exec() returns PCRE_ERROR_BADOFFSET. When the starting offset is + zero, the search for a match starts at the beginning of the subject, and this is by far the most common case. In UTF-8 mode, the byte offset - must point to the start of a UTF-8 character (or the end of the sub- - ject). Unlike the pattern string, the subject may contain binary zero + must point to the start of a UTF-8 character (or the end of the sub- + ject). Unlike the pattern string, the subject may contain binary zero bytes. - A non-zero starting offset is useful when searching for another match - in the same subject by calling pcre_exec() again after a previous suc- - cess. Setting startoffset differs from just passing over a shortened - string and setting PCRE_NOTBOL in the case of a pattern that begins + A non-zero starting offset is useful when searching for another match + in the same subject by calling pcre_exec() again after a previous suc- + cess. Setting startoffset differs from just passing over a shortened + string and setting PCRE_NOTBOL in the case of a pattern that begins with any kind of lookbehind. For example, consider the pattern \Biss\B - which finds occurrences of "iss" in the middle of words. (\B matches - only if the current position in the subject is not a word boundary.) - When applied to the string "Mississipi" the first call to pcre_exec() - finds the first occurrence. If pcre_exec() is called again with just - the remainder of the subject, namely "issipi", it does not match, + which finds occurrences of "iss" in the middle of words. (\B matches + only if the current position in the subject is not a word boundary.) + When applied to the string "Mississipi" the first call to pcre_exec() + finds the first occurrence. If pcre_exec() is called again with just + the remainder of the subject, namely "issipi", it does not match, because \B is always false at the start of the subject, which is deemed - to be a word boundary. However, if pcre_exec() is passed the entire + to be a word boundary. However, if pcre_exec() is passed the entire string again, but with startoffset set to 4, it finds the second occur- - rence of "iss" because it is able to look behind the starting point to + rence of "iss" because it is able to look behind the starting point to discover that it is preceded by a letter. - Finding all the matches in a subject is tricky when the pattern can + Finding all the matches in a subject is tricky when the pattern can match an empty string. It is possible to emulate Perl's /g behaviour by - first trying the match again at the same offset, with the - PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED options, and then if that - fails, advancing the starting offset and trying an ordinary match + first trying the match again at the same offset, with the + PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED options, and then if that + fails, advancing the starting offset and trying an ordinary match again. There is some code that demonstrates how to do this in the pcre- demo sample program. In the most general case, you have to check to see - if the newline convention recognizes CRLF as a newline, and if so, and + if the newline convention recognizes CRLF as a newline, and if so, and the current character is CR followed by LF, advance the starting offset by two characters instead of one. - If a non-zero starting offset is passed when the pattern is anchored, + If a non-zero starting offset is passed when the pattern is anchored, one attempt to match at the given offset is made. This can only succeed - if the pattern does not require the match to be at the start of the + if the pattern does not require the match to be at the start of the subject. How pcre_exec() returns captured substrings - In general, a pattern matches a certain portion of the subject, and in - addition, further substrings from the subject may be picked out by - parts of the pattern. Following the usage in Jeffrey Friedl's book, - this is called "capturing" in what follows, and the phrase "capturing - subpattern" is used for a fragment of a pattern that picks out a sub- - string. PCRE supports several other kinds of parenthesized subpattern + In general, a pattern matches a certain portion of the subject, and in + addition, further substrings from the subject may be picked out by + parts of the pattern. Following the usage in Jeffrey Friedl's book, + this is called "capturing" in what follows, and the phrase "capturing + subpattern" is used for a fragment of a pattern that picks out a sub- + string. PCRE supports several other kinds of parenthesized subpattern that do not cause substrings to be captured. Captured substrings are returned to the caller via a vector of integers - whose address is passed in ovector. The number of elements in the vec- - tor is passed in ovecsize, which must be a non-negative number. Note: + whose address is passed in ovector. The number of elements in the vec- + tor is passed in ovecsize, which must be a non-negative number. Note: this argument is NOT the size of ovector in bytes. - The first two-thirds of the vector is used to pass back captured sub- - strings, each substring using a pair of integers. The remaining third - of the vector is used as workspace by pcre_exec() while matching cap- - turing subpatterns, and is not available for passing back information. - The number passed in ovecsize should always be a multiple of three. If + The first two-thirds of the vector is used to pass back captured sub- + strings, each substring using a pair of integers. The remaining third + of the vector is used as workspace by pcre_exec() while matching cap- + turing subpatterns, and is not available for passing back information. + The number passed in ovecsize should always be a multiple of three. If it is not, it is rounded down. - When a match is successful, information about captured substrings is - returned in pairs of integers, starting at the beginning of ovector, - and continuing up to two-thirds of its length at the most. The first - element of each pair is set to the byte offset of the first character - in a substring, and the second is set to the byte offset of the first - character after the end of a substring. Note: these values are always + When a match is successful, information about captured substrings is + returned in pairs of integers, starting at the beginning of ovector, + and continuing up to two-thirds of its length at the most. The first + element of each pair is set to the byte offset of the first character + in a substring, and the second is set to the byte offset of the first + character after the end of a substring. Note: these values are always byte offsets, even in UTF-8 mode. They are not character counts. - The first pair of integers, ovector[0] and ovector[1], identify the - portion of the subject string matched by the entire pattern. The next - pair is used for the first capturing subpattern, and so on. The value + The first pair of integers, ovector[0] and ovector[1], identify the + portion of the subject string matched by the entire pattern. The next + pair is used for the first capturing subpattern, and so on. The value returned by pcre_exec() is one more than the highest numbered pair that - has been set. For example, if two substrings have been captured, the - returned value is 3. If there are no capturing subpatterns, the return + has been set. For example, if two substrings have been captured, the + returned value is 3. If there are no capturing subpatterns, the return value from a successful match is 1, indicating that just the first pair of offsets has been set. If a capturing subpattern is matched repeatedly, it is the last portion of the string that it matched that is returned. - If the vector is too small to hold all the captured substring offsets, + If the vector is too small to hold all the captured substring offsets, it is used as far as possible (up to two-thirds of its length), and the - function returns a value of zero. If neither the actual string matched - nor any captured substrings are of interest, pcre_exec() may be called - with ovector passed as NULL and ovecsize as zero. However, if the pat- - tern contains back references and the ovector is not big enough to - remember the related substrings, PCRE has to get additional memory for - use during matching. Thus it is usually advisable to supply an ovector + function returns a value of zero. If neither the actual string matched + nor any captured substrings are of interest, pcre_exec() may be called + with ovector passed as NULL and ovecsize as zero. However, if the pat- + tern contains back references and the ovector is not big enough to + remember the related substrings, PCRE has to get additional memory for + use during matching. Thus it is usually advisable to supply an ovector of reasonable size. - There are some cases where zero is returned (indicating vector over- - flow) when in fact the vector is exactly the right size for the final + There are some cases where zero is returned (indicating vector over- + flow) when in fact the vector is exactly the right size for the final match. For example, consider the pattern (a)(?:(b)c|bd) - If a vector of 6 elements (allowing for only 1 captured substring) is + If a vector of 6 elements (allowing for only 1 captured substring) is given with subject string "abd", pcre_exec() will try to set the second captured string, thereby recording a vector overflow, before failing to - match "c" and backing up to try the second alternative. The zero - return, however, does correctly indicate that the maximum number of + match "c" and backing up to try the second alternative. The zero + return, however, does correctly indicate that the maximum number of slots (namely 2) have been filled. In similar cases where there is tem- - porary overflow, but the final number of used slots is actually less + porary overflow, but the final number of used slots is actually less than the maximum, a non-zero value is returned. The pcre_fullinfo() function can be used to find out how many capturing - subpatterns there are in a compiled pattern. The smallest size for - ovector that will allow for n captured substrings, in addition to the + subpatterns there are in a compiled pattern. The smallest size for + ovector that will allow for n captured substrings, in addition to the offsets of the substring matched by the whole pattern, is (n+1)*3. - It is possible for capturing subpattern number n+1 to match some part + It is possible for capturing subpattern number n+1 to match some part of the subject when subpattern n has not been used at all. For example, - if the string "abc" is matched against the pattern (a|(z))(bc) the + if the string "abc" is matched against the pattern (a|(z))(bc) the return from the function is 4, and subpatterns 1 and 3 are matched, but - 2 is not. When this happens, both values in the offset pairs corre- + 2 is not. When this happens, both values in the offset pairs corre- sponding to unused subpatterns are set to -1. - Offset values that correspond to unused subpatterns at the end of the - expression are also set to -1. For example, if the string "abc" is - matched against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not - matched. The return from the function is 2, because the highest used - capturing subpattern number is 1, and the offsets for for the second - and third capturing subpatterns (assuming the vector is large enough, + Offset values that correspond to unused subpatterns at the end of the + expression are also set to -1. For example, if the string "abc" is + matched against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not + matched. The return from the function is 2, because the highest used + capturing subpattern number is 1, and the offsets for for the second + and third capturing subpatterns (assuming the vector is large enough, of course) are set to -1. - Note: Elements in the first two-thirds of ovector that do not corre- - spond to capturing parentheses in the pattern are never changed. That - is, if a pattern contains n capturing parentheses, no more than ovec- - tor[0] to ovector[2n+1] are set by pcre_exec(). The other elements (in + Note: Elements in the first two-thirds of ovector that do not corre- + spond to capturing parentheses in the pattern are never changed. That + is, if a pattern contains n capturing parentheses, no more than ovec- + tor[0] to ovector[2n+1] are set by pcre_exec(). The other elements (in the first two-thirds) retain whatever values they previously had. - Some convenience functions are provided for extracting the captured + Some convenience functions are provided for extracting the captured substrings as separate strings. These are described below. Error return values from pcre_exec() - If pcre_exec() fails, it returns a negative number. The following are + If pcre_exec() fails, it returns a negative number. The following are defined in the header file: PCRE_ERROR_NOMATCH (-1) @@ -2862,7 +3447,7 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION PCRE_ERROR_NULL (-2) - Either code or subject was passed as NULL, or ovector was NULL and + Either code or subject was passed as NULL, or ovector was NULL and ovecsize was not zero. PCRE_ERROR_BADOPTION (-3) @@ -2871,82 +3456,82 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION PCRE_ERROR_BADMAGIC (-4) - PCRE stores a 4-byte "magic number" at the start of the compiled code, + PCRE stores a 4-byte "magic number" at the start of the compiled code, to catch the case when it is passed a junk pointer and to detect when a pattern that was compiled in an environment of one endianness is run in - an environment with the other endianness. This is the error that PCRE + an environment with the other endianness. This is the error that PCRE gives when the magic number is not present. PCRE_ERROR_UNKNOWN_OPCODE (-5) While running the pattern match, an unknown item was encountered in the - compiled pattern. This error could be caused by a bug in PCRE or by + compiled pattern. This error could be caused by a bug in PCRE or by overwriting of the compiled pattern. PCRE_ERROR_NOMEMORY (-6) - If a pattern contains back references, but the ovector that is passed + If a pattern contains back references, but the ovector that is passed to pcre_exec() is not big enough to remember the referenced substrings, - PCRE gets a block of memory at the start of matching to use for this - purpose. If the call via pcre_malloc() fails, this error is given. The + PCRE gets a block of memory at the start of matching to use for this + purpose. If the call via pcre_malloc() fails, this error is given. The memory is automatically freed at the end of matching. - This error is also given if pcre_stack_malloc() fails in pcre_exec(). - This can happen only when PCRE has been compiled with --disable-stack- + This error is also given if pcre_stack_malloc() fails in pcre_exec(). + This can happen only when PCRE has been compiled with --disable-stack- for-recursion. PCRE_ERROR_NOSUBSTRING (-7) - This error is used by the pcre_copy_substring(), pcre_get_substring(), + This error is used by the pcre_copy_substring(), pcre_get_substring(), and pcre_get_substring_list() functions (see below). It is never returned by pcre_exec(). PCRE_ERROR_MATCHLIMIT (-8) - The backtracking limit, as specified by the match_limit field in a - pcre_extra structure (or defaulted) was reached. See the description + The backtracking limit, as specified by the match_limit field in a + pcre_extra structure (or defaulted) was reached. See the description above. PCRE_ERROR_CALLOUT (-9) This error is never generated by pcre_exec() itself. It is provided for - use by callout functions that want to yield a distinctive error code. + use by callout functions that want to yield a distinctive error code. See the pcrecallout documentation for details. PCRE_ERROR_BADUTF8 (-10) - A string that contains an invalid UTF-8 byte sequence was passed as a - subject, and the PCRE_NO_UTF8_CHECK option was not set. If the size of - the output vector (ovecsize) is at least 2, the byte offset to the - start of the the invalid UTF-8 character is placed in the first ele- - ment, and a reason code is placed in the second element. The reason + A string that contains an invalid UTF-8 byte sequence was passed as a + subject, and the PCRE_NO_UTF8_CHECK option was not set. If the size of + the output vector (ovecsize) is at least 2, the byte offset to the + start of the the invalid UTF-8 character is placed in the first ele- + ment, and a reason code is placed in the second element. The reason codes are listed in the following section. For backward compatibility, - if PCRE_PARTIAL_HARD is set and the problem is a truncated UTF-8 char- - acter at the end of the subject (reason codes 1 to 5), + if PCRE_PARTIAL_HARD is set and the problem is a truncated UTF-8 char- + acter at the end of the subject (reason codes 1 to 5), PCRE_ERROR_SHORTUTF8 is returned instead of PCRE_ERROR_BADUTF8. PCRE_ERROR_BADUTF8_OFFSET (-11) - The UTF-8 byte sequence that was passed as a subject was checked and - found to be valid (the PCRE_NO_UTF8_CHECK option was not set), but the - value of startoffset did not point to the beginning of a UTF-8 charac- + The UTF-8 byte sequence that was passed as a subject was checked and + found to be valid (the PCRE_NO_UTF8_CHECK option was not set), but the + value of startoffset did not point to the beginning of a UTF-8 charac- ter or the end of the subject. PCRE_ERROR_PARTIAL (-12) - The subject string did not match, but it did match partially. See the + The subject string did not match, but it did match partially. See the pcrepartial documentation for details of partial matching. PCRE_ERROR_BADPARTIAL (-13) - This code is no longer in use. It was formerly returned when the - PCRE_PARTIAL option was used with a compiled pattern containing items - that were not supported for partial matching. From release 8.00 + This code is no longer in use. It was formerly returned when the + PCRE_PARTIAL option was used with a compiled pattern containing items + that were not supported for partial matching. From release 8.00 onwards, there are no restrictions on partial matching. PCRE_ERROR_INTERNAL (-14) - An unexpected internal error has occurred. This error could be caused + An unexpected internal error has occurred. This error could be caused by a bug in PCRE or by overwriting of the compiled pattern. PCRE_ERROR_BADCOUNT (-15) @@ -2956,7 +3541,7 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION PCRE_ERROR_RECURSIONLIMIT (-21) The internal recursion limit, as specified by the match_limit_recursion - field in a pcre_extra structure (or defaulted) was reached. See the + field in a pcre_extra structure (or defaulted) was reached. See the description above. PCRE_ERROR_BADNEWLINE (-23) @@ -2970,55 +3555,71 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION PCRE_ERROR_SHORTUTF8 (-25) - This error is returned instead of PCRE_ERROR_BADUTF8 when the subject - string ends with a truncated UTF-8 character and the PCRE_PARTIAL_HARD - option is set. Information about the failure is returned as for - PCRE_ERROR_BADUTF8. It is in fact sufficient to detect this case, but - this special error code for PCRE_PARTIAL_HARD precedes the implementa- - tion of returned information; it is retained for backwards compatibil- + This error is returned instead of PCRE_ERROR_BADUTF8 when the subject + string ends with a truncated UTF-8 character and the PCRE_PARTIAL_HARD + option is set. Information about the failure is returned as for + PCRE_ERROR_BADUTF8. It is in fact sufficient to detect this case, but + this special error code for PCRE_PARTIAL_HARD precedes the implementa- + tion of returned information; it is retained for backwards compatibil- ity. PCRE_ERROR_RECURSELOOP (-26) This error is returned when pcre_exec() detects a recursion loop within - the pattern. Specifically, it means that either the whole pattern or a - subpattern has been called recursively for the second time at the same + the pattern. Specifically, it means that either the whole pattern or a + subpattern has been called recursively for the second time at the same position in the subject string. Some simple patterns that might do this - are detected and faulted at compile time, but more complicated cases, + are detected and faulted at compile time, but more complicated cases, in particular mutual recursions between two different subpatterns, can- not be detected until run time. PCRE_ERROR_JIT_STACKLIMIT (-27) - This error is returned when a pattern that was successfully studied - using a JIT compile option is being matched, but the memory available - for the just-in-time processing stack is not large enough. See the + This error is returned when a pattern that was successfully studied + using a JIT compile option is being matched, but the memory available + for the just-in-time processing stack is not large enough. See the pcrejit documentation for more details. PCRE_ERROR_BADMODE (-28) This error is given if a pattern that was compiled by the 8-bit library - is passed to a 16-bit library function, or vice versa. + is passed to a 16-bit or 32-bit library function, or vice versa. PCRE_ERROR_BADENDIANNESS (-29) - This error is given if a pattern that was compiled and saved is - reloaded on a host with different endianness. The utility function + This error is given if a pattern that was compiled and saved is + reloaded on a host with different endianness. The utility function pcre_pattern_to_host_byte_order() can be used to convert such a pattern so that it runs on the new host. - Error numbers -16 to -20, -22, and -30 are not used by pcre_exec(). + PCRE_ERROR_JIT_BADOPTION + + This error is returned when a pattern that was successfully studied + using a JIT compile option is being matched, but the matching mode + (partial or complete match) does not correspond to any JIT compilation + mode. When the JIT fast path function is used, this error may be also + given for invalid options. See the pcrejit documentation for more + details. + + PCRE_ERROR_BADLENGTH (-32) + + This error is given if pcre_exec() is called with a negative value for + the length argument. + + Error numbers -16 to -20, -22, and 30 are not used by pcre_exec(). Reason codes for invalid UTF-8 strings - This section applies only to the 8-bit library. The corresponding - information for the 16-bit library is given in the pcre16 page. + This section applies only to the 8-bit library. The corresponding + information for the 16-bit library is given in the pcre16 page. The + corresponding information for the 32-bit library is given in the pcre32 + page. When pcre_exec() returns either PCRE_ERROR_BADUTF8 or PCRE_ERROR_SHORT- - UTF8, and the size of the output vector (ovecsize) is at least 2, the - offset of the start of the invalid UTF-8 character is placed in the + UTF8, and the size of the output vector (ovecsize) is at least 2, the + offset of the start of the invalid UTF-8 character is placed in the first output vector element (ovector[0]) and a reason code is placed in - the second element (ovector[1]). The reason codes are given names in + the second element (ovector[1]). The reason codes are given names in the pcre.h header file: PCRE_UTF8_ERR1 @@ -3027,10 +3628,10 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION PCRE_UTF8_ERR4 PCRE_UTF8_ERR5 - The string ends with a truncated UTF-8 character; the code specifies - how many bytes are missing (1 to 5). Although RFC 3629 restricts UTF-8 - characters to be no longer than 4 bytes, the encoding scheme (origi- - nally defined by RFC 2279) allows for up to 6 bytes, and this is + The string ends with a truncated UTF-8 character; the code specifies + how many bytes are missing (1 to 5). Although RFC 3629 restricts UTF-8 + characters to be no longer than 4 bytes, the encoding scheme (origi- + nally defined by RFC 2279) allows for up to 6 bytes, and this is checked first; hence the possibility of 4 or 5 missing bytes. PCRE_UTF8_ERR6 @@ -3040,24 +3641,24 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION PCRE_UTF8_ERR10 The two most significant bits of the 2nd, 3rd, 4th, 5th, or 6th byte of - the character do not have the binary value 0b10 (that is, either the + the character do not have the binary value 0b10 (that is, either the most significant bit is 0, or the next bit is 1). PCRE_UTF8_ERR11 PCRE_UTF8_ERR12 - A character that is valid by the RFC 2279 rules is either 5 or 6 bytes + A character that is valid by the RFC 2279 rules is either 5 or 6 bytes long; these code points are excluded by RFC 3629. PCRE_UTF8_ERR13 - A 4-byte character has a value greater than 0x10fff; these code points + A 4-byte character has a value greater than 0x10fff; these code points are excluded by RFC 3629. PCRE_UTF8_ERR14 - A 3-byte character has a value in the range 0xd800 to 0xdfff; this - range of code points are reserved by RFC 3629 for use with UTF-16, and + A 3-byte character has a value in the range 0xd800 to 0xdfff; this + range of code points are reserved by RFC 3629 for use with UTF-16, and so are excluded from UTF-8. PCRE_UTF8_ERR15 @@ -3066,23 +3667,29 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION PCRE_UTF8_ERR18 PCRE_UTF8_ERR19 - A 2-, 3-, 4-, 5-, or 6-byte character is "overlong", that is, it codes - for a value that can be represented by fewer bytes, which is invalid. - For example, the two bytes 0xc0, 0xae give the value 0x2e, whose cor- + A 2-, 3-, 4-, 5-, or 6-byte character is "overlong", that is, it codes + for a value that can be represented by fewer bytes, which is invalid. + For example, the two bytes 0xc0, 0xae give the value 0x2e, whose cor- rect coding uses just one byte. PCRE_UTF8_ERR20 The two most significant bits of the first byte of a character have the - binary value 0b10 (that is, the most significant bit is 1 and the sec- - ond is 0). Such a byte can only validly occur as the second or subse- + binary value 0b10 (that is, the most significant bit is 1 and the sec- + ond is 0). Such a byte can only validly occur as the second or subse- quent byte of a multi-byte character. PCRE_UTF8_ERR21 - The first byte of a character has the value 0xfe or 0xff. These values + The first byte of a character has the value 0xfe or 0xff. These values can never occur in a valid UTF-8 string. + PCRE_UTF8_ERR2 + + Non-character. These are the last two characters in each plane (0xfffe, + 0xffff, 0x1fffe, 0x1ffff .. 0x10fffe, 0x10ffff), and the characters + 0xfdd0..0xfdef. + EXTRACTING CAPTURED SUBSTRINGS BY NUMBER @@ -3097,78 +3704,78 @@ EXTRACTING CAPTURED SUBSTRINGS BY NUMBER int pcre_get_substring_list(const char *subject, int *ovector, int stringcount, const char ***listptr); - Captured substrings can be accessed directly by using the offsets - returned by pcre_exec() in ovector. For convenience, the functions + Captured substrings can be accessed directly by using the offsets + returned by pcre_exec() in ovector. For convenience, the functions pcre_copy_substring(), pcre_get_substring(), and pcre_get_sub- - string_list() are provided for extracting captured substrings as new, - separate, zero-terminated strings. These functions identify substrings - by number. The next section describes functions for extracting named + string_list() are provided for extracting captured substrings as new, + separate, zero-terminated strings. These functions identify substrings + by number. The next section describes functions for extracting named substrings. - A substring that contains a binary zero is correctly extracted and has - a further zero added on the end, but the result is not, of course, a C - string. However, you can process such a string by referring to the - length that is returned by pcre_copy_substring() and pcre_get_sub- + A substring that contains a binary zero is correctly extracted and has + a further zero added on the end, but the result is not, of course, a C + string. However, you can process such a string by referring to the + length that is returned by pcre_copy_substring() and pcre_get_sub- string(). Unfortunately, the interface to pcre_get_substring_list() is - not adequate for handling strings containing binary zeros, because the + not adequate for handling strings containing binary zeros, because the end of the final string is not independently indicated. - The first three arguments are the same for all three of these func- - tions: subject is the subject string that has just been successfully + The first three arguments are the same for all three of these func- + tions: subject is the subject string that has just been successfully matched, ovector is a pointer to the vector of integer offsets that was passed to pcre_exec(), and stringcount is the number of substrings that - were captured by the match, including the substring that matched the + were captured by the match, including the substring that matched the entire regular expression. This is the value returned by pcre_exec() if - it is greater than zero. If pcre_exec() returned zero, indicating that - it ran out of space in ovector, the value passed as stringcount should + it is greater than zero. If pcre_exec() returned zero, indicating that + it ran out of space in ovector, the value passed as stringcount should be the number of elements in the vector divided by three. - The functions pcre_copy_substring() and pcre_get_substring() extract a - single substring, whose number is given as stringnumber. A value of - zero extracts the substring that matched the entire pattern, whereas - higher values extract the captured substrings. For pcre_copy_sub- - string(), the string is placed in buffer, whose length is given by - buffersize, while for pcre_get_substring() a new block of memory is - obtained via pcre_malloc, and its address is returned via stringptr. - The yield of the function is the length of the string, not including + The functions pcre_copy_substring() and pcre_get_substring() extract a + single substring, whose number is given as stringnumber. A value of + zero extracts the substring that matched the entire pattern, whereas + higher values extract the captured substrings. For pcre_copy_sub- + string(), the string is placed in buffer, whose length is given by + buffersize, while for pcre_get_substring() a new block of memory is + obtained via pcre_malloc, and its address is returned via stringptr. + The yield of the function is the length of the string, not including the terminating zero, or one of these error codes: PCRE_ERROR_NOMEMORY (-6) - The buffer was too small for pcre_copy_substring(), or the attempt to + The buffer was too small for pcre_copy_substring(), or the attempt to get memory failed for pcre_get_substring(). PCRE_ERROR_NOSUBSTRING (-7) There is no substring whose number is stringnumber. - The pcre_get_substring_list() function extracts all available sub- - strings and builds a list of pointers to them. All this is done in a + The pcre_get_substring_list() function extracts all available sub- + strings and builds a list of pointers to them. All this is done in a single block of memory that is obtained via pcre_malloc. The address of - the memory block is returned via listptr, which is also the start of - the list of string pointers. The end of the list is marked by a NULL - pointer. The yield of the function is zero if all went well, or the + the memory block is returned via listptr, which is also the start of + the list of string pointers. The end of the list is marked by a NULL + pointer. The yield of the function is zero if all went well, or the error code PCRE_ERROR_NOMEMORY (-6) if the attempt to get the memory block failed. - When any of these functions encounter a substring that is unset, which - can happen when capturing subpattern number n+1 matches some part of - the subject, but subpattern n has not been used at all, they return an + When any of these functions encounter a substring that is unset, which + can happen when capturing subpattern number n+1 matches some part of + the subject, but subpattern n has not been used at all, they return an empty string. This can be distinguished from a genuine zero-length sub- - string by inspecting the appropriate offset in ovector, which is nega- + string by inspecting the appropriate offset in ovector, which is nega- tive for unset substrings. - The two convenience functions pcre_free_substring() and pcre_free_sub- - string_list() can be used to free the memory returned by a previous + The two convenience functions pcre_free_substring() and pcre_free_sub- + string_list() can be used to free the memory returned by a previous call of pcre_get_substring() or pcre_get_substring_list(), respec- - tively. They do nothing more than call the function pointed to by - pcre_free, which of course could be called directly from a C program. - However, PCRE is used in some situations where it is linked via a spe- - cial interface to another programming language that cannot use - pcre_free directly; it is for these cases that the functions are pro- + tively. They do nothing more than call the function pointed to by + pcre_free, which of course could be called directly from a C program. + However, PCRE is used in some situations where it is linked via a spe- + cial interface to another programming language that cannot use + pcre_free directly; it is for these cases that the functions are pro- vided. @@ -3187,7 +3794,7 @@ EXTRACTING CAPTURED SUBSTRINGS BY NAME int stringcount, const char *stringname, const char **stringptr); - To extract a substring by name, you first have to find associated num- + To extract a substring by name, you first have to find associated num- ber. For example, for this pattern (a+)b(?<xxx>\d+)... @@ -3196,35 +3803,35 @@ EXTRACTING CAPTURED SUBSTRINGS BY NAME be unique (PCRE_DUPNAMES was not set), you can find the number from the name by calling pcre_get_stringnumber(). The first argument is the com- piled pattern, and the second is the name. The yield of the function is - the subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no + the subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no subpattern of that name. Given the number, you can extract the substring directly, or use one of the functions described in the previous section. For convenience, there are also two functions that do the whole job. - Most of the arguments of pcre_copy_named_substring() and - pcre_get_named_substring() are the same as those for the similarly - named functions that extract by number. As these are described in the - previous section, they are not re-described here. There are just two + Most of the arguments of pcre_copy_named_substring() and + pcre_get_named_substring() are the same as those for the similarly + named functions that extract by number. As these are described in the + previous section, they are not re-described here. There are just two differences: - First, instead of a substring number, a substring name is given. Sec- + First, instead of a substring number, a substring name is given. Sec- ond, there is an extra argument, given at the start, which is a pointer - to the compiled pattern. This is needed in order to gain access to the + to the compiled pattern. This is needed in order to gain access to the name-to-number translation table. - These functions call pcre_get_stringnumber(), and if it succeeds, they - then call pcre_copy_substring() or pcre_get_substring(), as appropri- - ate. NOTE: If PCRE_DUPNAMES is set and there are duplicate names, the + These functions call pcre_get_stringnumber(), and if it succeeds, they + then call pcre_copy_substring() or pcre_get_substring(), as appropri- + ate. NOTE: If PCRE_DUPNAMES is set and there are duplicate names, the behaviour may not be what you want (see the next section). Warning: If the pattern uses the (?| feature to set up multiple subpat- - terns with the same number, as described in the section on duplicate - subpattern numbers in the pcrepattern page, you cannot use names to - distinguish the different subpatterns, because names are not included - in the compiled code. The matching process uses only numbers. For this - reason, the use of different names for subpatterns of the same number + terns with the same number, as described in the section on duplicate + subpattern numbers in the pcrepattern page, you cannot use names to + distinguish the different subpatterns, because names are not included + in the compiled code. The matching process uses only numbers. For this + reason, the use of different names for subpatterns of the same number causes an error at compile time. @@ -3233,76 +3840,76 @@ DUPLICATE SUBPATTERN NAMES int pcre_get_stringtable_entries(const pcre *code, const char *name, char **first, char **last); - When a pattern is compiled with the PCRE_DUPNAMES option, names for - subpatterns are not required to be unique. (Duplicate names are always - allowed for subpatterns with the same number, created by using the (?| - feature. Indeed, if such subpatterns are named, they are required to + When a pattern is compiled with the PCRE_DUPNAMES option, names for + subpatterns are not required to be unique. (Duplicate names are always + allowed for subpatterns with the same number, created by using the (?| + feature. Indeed, if such subpatterns are named, they are required to use the same names.) Normally, patterns with duplicate names are such that in any one match, - only one of the named subpatterns participates. An example is shown in + only one of the named subpatterns participates. An example is shown in the pcrepattern documentation. - When duplicates are present, pcre_copy_named_substring() and - pcre_get_named_substring() return the first substring corresponding to - the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING - (-7) is returned; no data is returned. The pcre_get_stringnumber() - function returns one of the numbers that are associated with the name, + When duplicates are present, pcre_copy_named_substring() and + pcre_get_named_substring() return the first substring corresponding to + the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING + (-7) is returned; no data is returned. The pcre_get_stringnumber() + function returns one of the numbers that are associated with the name, but it is not defined which it is. - If you want to get full details of all captured substrings for a given - name, you must use the pcre_get_stringtable_entries() function. The + If you want to get full details of all captured substrings for a given + name, you must use the pcre_get_stringtable_entries() function. The first argument is the compiled pattern, and the second is the name. The - third and fourth are pointers to variables which are updated by the + third and fourth are pointers to variables which are updated by the function. After it has run, they point to the first and last entries in - the name-to-number table for the given name. The function itself - returns the length of each entry, or PCRE_ERROR_NOSUBSTRING (-7) if - there are none. The format of the table is described above in the sec- - tion entitled Information about a pattern above. Given all the rele- - vant entries for the name, you can extract each of their numbers, and + the name-to-number table for the given name. The function itself + returns the length of each entry, or PCRE_ERROR_NOSUBSTRING (-7) if + there are none. The format of the table is described above in the sec- + tion entitled Information about a pattern above. Given all the rele- + vant entries for the name, you can extract each of their numbers, and hence the captured data, if any. FINDING ALL POSSIBLE MATCHES - The traditional matching function uses a similar algorithm to Perl, + The traditional matching function uses a similar algorithm to Perl, which stops when it finds the first match, starting at a given point in - the subject. If you want to find all possible matches, or the longest - possible match, consider using the alternative matching function (see - below) instead. If you cannot use the alternative function, but still - need to find all possible matches, you can kludge it up by making use + the subject. If you want to find all possible matches, or the longest + possible match, consider using the alternative matching function (see + below) instead. If you cannot use the alternative function, but still + need to find all possible matches, you can kludge it up by making use of the callout facility, which is described in the pcrecallout documen- tation. What you have to do is to insert a callout right at the end of the pat- - tern. When your callout function is called, extract and save the cur- - rent matched substring. Then return 1, which forces pcre_exec() to - backtrack and try other alternatives. Ultimately, when it runs out of + tern. When your callout function is called, extract and save the cur- + rent matched substring. Then return 1, which forces pcre_exec() to + backtrack and try other alternatives. Ultimately, when it runs out of matches, pcre_exec() will yield PCRE_ERROR_NOMATCH. OBTAINING AN ESTIMATE OF STACK USAGE - Matching certain patterns using pcre_exec() can use a lot of process - stack, which in certain environments can be rather limited in size. - Some users find it helpful to have an estimate of the amount of stack - that is used by pcre_exec(), to help them set recursion limits, as - described in the pcrestack documentation. The estimate that is output + Matching certain patterns using pcre_exec() can use a lot of process + stack, which in certain environments can be rather limited in size. + Some users find it helpful to have an estimate of the amount of stack + that is used by pcre_exec(), to help them set recursion limits, as + described in the pcrestack documentation. The estimate that is output by pcretest when called with the -m and -C options is obtained by call- - ing pcre_exec with the values NULL, NULL, NULL, -999, and -999 for its + ing pcre_exec with the values NULL, NULL, NULL, -999, and -999 for its first five arguments. - Normally, if its first argument is NULL, pcre_exec() immediately - returns the negative error code PCRE_ERROR_NULL, but with this special - combination of arguments, it returns instead a negative number whose - absolute value is the approximate stack frame size in bytes. (A nega- - tive number is used so that it is clear that no match has happened.) - The value is approximate because in some cases, recursive calls to + Normally, if its first argument is NULL, pcre_exec() immediately + returns the negative error code PCRE_ERROR_NULL, but with this special + combination of arguments, it returns instead a negative number whose + absolute value is the approximate stack frame size in bytes. (A nega- + tive number is used so that it is clear that no match has happened.) + The value is approximate because in some cases, recursive calls to pcre_exec() occur when there are one or two additional variables on the stack. - If PCRE has been compiled to use the heap instead of the stack for - recursion, the value returned is the size of each block that is + If PCRE has been compiled to use the heap instead of the stack for + recursion, the value returned is the size of each block that is obtained from the heap. @@ -3313,26 +3920,26 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION int options, int *ovector, int ovecsize, int *workspace, int wscount); - The function pcre_dfa_exec() is called to match a subject string - against a compiled pattern, using a matching algorithm that scans the - subject string just once, and does not backtrack. This has different - characteristics to the normal algorithm, and is not compatible with - Perl. Some of the features of PCRE patterns are not supported. Never- - theless, there are times when this kind of matching can be useful. For - a discussion of the two matching algorithms, and a list of features - that pcre_dfa_exec() does not support, see the pcrematching documenta- + The function pcre_dfa_exec() is called to match a subject string + against a compiled pattern, using a matching algorithm that scans the + subject string just once, and does not backtrack. This has different + characteristics to the normal algorithm, and is not compatible with + Perl. Some of the features of PCRE patterns are not supported. Never- + theless, there are times when this kind of matching can be useful. For + a discussion of the two matching algorithms, and a list of features + that pcre_dfa_exec() does not support, see the pcrematching documenta- tion. - The arguments for the pcre_dfa_exec() function are the same as for + The arguments for the pcre_dfa_exec() function are the same as for pcre_exec(), plus two extras. The ovector argument is used in a differ- - ent way, and this is described below. The other common arguments are - used in the same way as for pcre_exec(), so their description is not + ent way, and this is described below. The other common arguments are + used in the same way as for pcre_exec(), so their description is not repeated here. - The two additional arguments provide workspace for the function. The - workspace vector should contain at least 20 elements. It is used for + The two additional arguments provide workspace for the function. The + workspace vector should contain at least 20 elements. It is used for keeping track of multiple paths through the pattern tree. More - workspace will be needed for patterns and subjects where there are a + workspace will be needed for patterns and subjects where there are a lot of potential matches. Here is an example of a simple call to pcre_dfa_exec(): @@ -3354,55 +3961,55 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION Option bits for pcre_dfa_exec() - The unused bits of the options argument for pcre_dfa_exec() must be - zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEW- + The unused bits of the options argument for pcre_dfa_exec() must be + zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEW- LINE_xxx, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, - PCRE_NOTEMPTY_ATSTART, PCRE_NO_UTF8_CHECK, PCRE_BSR_ANYCRLF, - PCRE_BSR_UNICODE, PCRE_NO_START_OPTIMIZE, PCRE_PARTIAL_HARD, PCRE_PAR- - TIAL_SOFT, PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last - four of these are exactly the same as for pcre_exec(), so their + PCRE_NOTEMPTY_ATSTART, PCRE_NO_UTF8_CHECK, PCRE_BSR_ANYCRLF, + PCRE_BSR_UNICODE, PCRE_NO_START_OPTIMIZE, PCRE_PARTIAL_HARD, PCRE_PAR- + TIAL_SOFT, PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last + four of these are exactly the same as for pcre_exec(), so their description is not repeated here. PCRE_PARTIAL_HARD PCRE_PARTIAL_SOFT - These have the same general effect as they do for pcre_exec(), but the - details are slightly different. When PCRE_PARTIAL_HARD is set for - pcre_dfa_exec(), it returns PCRE_ERROR_PARTIAL if the end of the sub- - ject is reached and there is still at least one matching possibility + These have the same general effect as they do for pcre_exec(), but the + details are slightly different. When PCRE_PARTIAL_HARD is set for + pcre_dfa_exec(), it returns PCRE_ERROR_PARTIAL if the end of the sub- + ject is reached and there is still at least one matching possibility that requires additional characters. This happens even if some complete matches have also been found. When PCRE_PARTIAL_SOFT is set, the return code PCRE_ERROR_NOMATCH is converted into PCRE_ERROR_PARTIAL if the end - of the subject is reached, there have been no complete matches, but - there is still at least one matching possibility. The portion of the - string that was inspected when the longest partial match was found is - set as the first matching string in both cases. There is a more - detailed discussion of partial and multi-segment matching, with exam- + of the subject is reached, there have been no complete matches, but + there is still at least one matching possibility. The portion of the + string that was inspected when the longest partial match was found is + set as the first matching string in both cases. There is a more + detailed discussion of partial and multi-segment matching, with exam- ples, in the pcrepartial documentation. PCRE_DFA_SHORTEST - Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to + Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to stop as soon as it has found one match. Because of the way the alterna- - tive algorithm works, this is necessarily the shortest possible match + tive algorithm works, this is necessarily the shortest possible match at the first possible matching point in the subject string. PCRE_DFA_RESTART When pcre_dfa_exec() returns a partial match, it is possible to call it - again, with additional subject characters, and have it continue with - the same match. The PCRE_DFA_RESTART option requests this action; when - it is set, the workspace and wscount options must reference the same - vector as before because data about the match so far is left in them + again, with additional subject characters, and have it continue with + the same match. The PCRE_DFA_RESTART option requests this action; when + it is set, the workspace and wscount options must reference the same + vector as before because data about the match so far is left in them after a partial match. There is more discussion of this facility in the pcrepartial documentation. Successful returns from pcre_dfa_exec() - When pcre_dfa_exec() succeeds, it may have matched more than one sub- + When pcre_dfa_exec() succeeds, it may have matched more than one sub- string in the subject. Note, however, that all the matches from one run - of the function start at the same point in the subject. The shorter - matches are all initial substrings of the longer matches. For example, + of the function start at the same point in the subject. The shorter + matches are all initial substrings of the longer matches. For example, if the pattern <.*> @@ -3417,72 +4024,72 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION <something> <something else> <something> <something else> <something further> - On success, the yield of the function is a number greater than zero, - which is the number of matched substrings. The substrings themselves - are returned in ovector. Each string uses two elements; the first is - the offset to the start, and the second is the offset to the end. In - fact, all the strings have the same start offset. (Space could have - been saved by giving this only once, but it was decided to retain some - compatibility with the way pcre_exec() returns data, even though the + On success, the yield of the function is a number greater than zero, + which is the number of matched substrings. The substrings themselves + are returned in ovector. Each string uses two elements; the first is + the offset to the start, and the second is the offset to the end. In + fact, all the strings have the same start offset. (Space could have + been saved by giving this only once, but it was decided to retain some + compatibility with the way pcre_exec() returns data, even though the meaning of the strings is different.) The strings are returned in reverse order of length; that is, the long- - est matching string is given first. If there were too many matches to - fit into ovector, the yield of the function is zero, and the vector is - filled with the longest matches. Unlike pcre_exec(), pcre_dfa_exec() + est matching string is given first. If there were too many matches to + fit into ovector, the yield of the function is zero, and the vector is + filled with the longest matches. Unlike pcre_exec(), pcre_dfa_exec() can use the entire ovector for returning matched strings. Error returns from pcre_dfa_exec() - The pcre_dfa_exec() function returns a negative number when it fails. - Many of the errors are the same as for pcre_exec(), and these are - described above. There are in addition the following errors that are + The pcre_dfa_exec() function returns a negative number when it fails. + Many of the errors are the same as for pcre_exec(), and these are + described above. There are in addition the following errors that are specific to pcre_dfa_exec(): PCRE_ERROR_DFA_UITEM (-16) - This return is given if pcre_dfa_exec() encounters an item in the pat- - tern that it does not support, for instance, the use of \C or a back + This return is given if pcre_dfa_exec() encounters an item in the pat- + tern that it does not support, for instance, the use of \C or a back reference. PCRE_ERROR_DFA_UCOND (-17) - This return is given if pcre_dfa_exec() encounters a condition item - that uses a back reference for the condition, or a test for recursion + This return is given if pcre_dfa_exec() encounters a condition item + that uses a back reference for the condition, or a test for recursion in a specific group. These are not supported. PCRE_ERROR_DFA_UMLIMIT (-18) - This return is given if pcre_dfa_exec() is called with an extra block - that contains a setting of the match_limit or match_limit_recursion - fields. This is not supported (these fields are meaningless for DFA + This return is given if pcre_dfa_exec() is called with an extra block + that contains a setting of the match_limit or match_limit_recursion + fields. This is not supported (these fields are meaningless for DFA matching). PCRE_ERROR_DFA_WSSIZE (-19) - This return is given if pcre_dfa_exec() runs out of space in the + This return is given if pcre_dfa_exec() runs out of space in the workspace vector. PCRE_ERROR_DFA_RECURSE (-20) - When a recursive subpattern is processed, the matching function calls - itself recursively, using private vectors for ovector and workspace. - This error is given if the output vector is not large enough. This + When a recursive subpattern is processed, the matching function calls + itself recursively, using private vectors for ovector and workspace. + This error is given if the output vector is not large enough. This should be extremely rare, as a vector of size 1000 is used. PCRE_ERROR_DFA_BADRESTART (-30) - When pcre_dfa_exec() is called with the PCRE_DFA_RESTART option, some - plausibility checks are made on the contents of the workspace, which - should contain data about the previous partial match. If any of these + When pcre_dfa_exec() is called with the PCRE_DFA_RESTART option, some + plausibility checks are made on the contents of the workspace, which + should contain data about the previous partial match. If any of these checks fail, this error is given. SEE ALSO - pcre16(3), pcrebuild(3), pcrecallout(3), pcrecpp(3)(3), pcrematch- - ing(3), pcrepartial(3), pcreposix(3), pcreprecompile(3), pcresample(3), - pcrestack(3). + pcre16(3), pcre32(3), pcrebuild(3), pcrecallout(3), pcrecpp(3)(3), + pcrematching(3), pcrepartial(3), pcreposix(3), pcreprecompile(3), pcre- + sample(3), pcrestack(3). AUTHOR @@ -3494,11 +4101,11 @@ AUTHOR REVISION - Last updated: 17 June 2012 + Last updated: 31 October 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRECALLOUT(3) PCRECALLOUT(3) @@ -3506,18 +4113,25 @@ NAME PCRE - Perl-compatible regular expressions -PCRE CALLOUTS +SYNOPSIS + + #include <pcre.h> int (*pcre_callout)(pcre_callout_block *); int (*pcre16_callout)(pcre16_callout_block *); + int (*pcre32_callout)(pcre32_callout_block *); + + +DESCRIPTION + PCRE provides a feature called "callout", which is a means of temporar- ily passing control to the caller of PCRE in the middle of pattern matching. The caller of PCRE provides an external function by putting its entry point in the global variable pcre_callout (pcre16_callout for - the 16-bit library). By default, this variable contains NULL, which - disables all calling out. + the 16-bit library, pcre32_callout for the 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. Different callout points can be @@ -3577,16 +4191,18 @@ MISSING CALLOUTS THE CALLOUT INTERFACE During matching, when PCRE reaches a callout point, the external func- - tion defined by pcre_callout or pcre16_callout is called (if it is - set). This applies to both normal and DFA matching. The only argument - to the callout function is a pointer to a pcre_callout or pcre16_call- - out block. These structures contains the following fields: + tion defined by pcre_callout or pcre[16|32]_callout is called (if it is + set). This applies to both normal and DFA matching. The only argument + to the callout function is a pointer to a pcre_callout or + pcre[16|32]_callout block. These structures contains the following + fields: int version; int callout_number; int *offset_vector; const char *subject; (8-bit version) PCRE_SPTR16 subject; (16-bit version) + PCRE_SPTR32 subject; (32-bit version) int subject_length; int start_match; int current_position; @@ -3597,90 +4213,91 @@ THE CALLOUT INTERFACE int next_item_length; const unsigned char *mark; (8-bit version) const PCRE_UCHAR16 *mark; (16-bit version) + const PCRE_UCHAR32 *mark; (32-bit version) - The version field is an integer containing the version number of the - block format. The initial version was 0; the current version is 2. The - version number will change again in future if additional fields are + The version field is an integer containing the version number of the + block format. The initial version was 0; the current version is 2. The + version number will change again in future if additional fields are added, but the intention is never to remove any of the existing fields. - The callout_number field contains the number of the callout, as com- - piled into the pattern (that is, the number after ?C for manual call- + The callout_number field contains the number of the callout, as com- + piled into the pattern (that is, the number after ?C for manual call- outs, and 255 for automatically generated callouts). - The offset_vector field is a pointer to the vector of offsets that was - passed by the caller to the matching function. When pcre_exec() or - pcre16_exec() is used, the contents can be inspected, in order to - extract substrings that have been matched so far, in the same way as - for extracting substrings after a match has completed. For the DFA + The offset_vector field is a pointer to the vector of offsets that was + passed by the caller to the matching function. When pcre_exec() or + pcre[16|32]_exec() is used, the contents can be inspected, in order to + extract substrings that have been matched so far, in the same way as + for extracting substrings after a match has completed. For the DFA matching functions, this field is not useful. The subject and subject_length fields contain copies of the values that were passed to the matching function. - The start_match field normally contains the offset within the subject - at which the current match attempt started. However, if the escape - sequence \K has been encountered, this value is changed to reflect the - modified starting point. If the pattern is not anchored, the callout + The start_match field normally contains the offset within the subject + at which the current match attempt started. However, if the escape + sequence \K has been encountered, this value is changed to reflect the + modified starting point. If the pattern is not anchored, the callout function may be called several times from the same point in the pattern for different starting points in the subject. - The current_position field contains the offset within the subject of + The current_position field contains the offset within the subject of the current match pointer. - When the pcre_exec() or pcre16_exec() is used, the capture_top field - contains one more than the number of the highest numbered captured sub- - string so far. If no substrings have been captured, the value of cap- - ture_top is one. This is always the case when the DFA functions are - used, because they do not support captured substrings. + When the pcre_exec() or pcre[16|32]_exec() is used, the capture_top + field contains one more than the number of the highest numbered cap- + tured substring so far. If no substrings have been captured, the value + of capture_top is one. This is always the case when the DFA functions + are used, because they do not support captured substrings. - The capture_last field contains the number of the most recently cap- - tured substring. If no substrings have been captured, its value is -1. + The capture_last field contains the number of the most recently cap- + tured substring. If no substrings have been captured, its value is -1. This is always the case for the DFA matching functions. - The callout_data field contains a value that is passed to a matching - function specifically so that it can be passed back in callouts. It is - passed in the callout_data field of a pcre_extra or pcre16_extra data - structure. If no such data was passed, the value of callout_data in a - callout block is NULL. There is a description of the pcre_extra struc- - ture in the pcreapi documentation. + The callout_data field contains a value that is passed to a matching + function specifically so that it can be passed back in callouts. It is + passed in the callout_data field of a pcre_extra or pcre[16|32]_extra + data structure. If no such data was passed, the value of callout_data + in a callout block is NULL. There is a description of the pcre_extra + structure in the pcreapi documentation. - The pattern_position field is present from version 1 of the callout + The pattern_position field is present from version 1 of the callout structure. It contains the offset to the next item to be matched in the pattern string. - The next_item_length field is present from version 1 of the callout + The next_item_length field is present from version 1 of the callout structure. It contains the length of the next item to be matched in the - pattern string. When the callout immediately precedes an alternation - bar, a closing parenthesis, or the end of the pattern, the length is - zero. When the callout precedes an opening parenthesis, the length is + pattern string. When the callout immediately precedes an alternation + bar, a closing parenthesis, or the end of the pattern, the length is + zero. When the callout precedes an opening parenthesis, the length is that of the entire subpattern. - The pattern_position and next_item_length fields are intended to help - in distinguishing between different automatic callouts, which all have + The pattern_position and next_item_length fields are intended to help + in distinguishing between different automatic callouts, which all have the same callout number. However, they are set for all callouts. - The mark field is present from version 2 of the callout structure. In - callouts from pcre_exec() or pcre16_exec() it contains a pointer to the - zero-terminated name of the most recently passed (*MARK), (*PRUNE), or - (*THEN) item in the match, or NULL if no such items have been passed. - Instances of (*PRUNE) or (*THEN) without a name do not obliterate a - previous (*MARK). In callouts from the DFA matching functions this - field always contains NULL. + The mark field is present from version 2 of the callout structure. In + callouts from pcre_exec() or pcre[16|32]_exec() it contains a pointer + to the zero-terminated name of the most recently passed (*MARK), + (*PRUNE), or (*THEN) item in the match, or NULL if no such items have + been passed. Instances of (*PRUNE) or (*THEN) without a name do not + obliterate a previous (*MARK). In callouts from the DFA matching func- + tions this field always contains NULL. RETURN VALUES - The external callout function returns an integer to PCRE. If the value - is zero, matching proceeds as normal. If the value is greater than - zero, matching fails at the current point, but the testing of other + The external callout function returns an integer to PCRE. If the value + is zero, matching proceeds as normal. If the value is greater than + zero, matching fails at the current point, but the testing of other matching possibilities goes ahead, just as if a lookahead assertion had - failed. If the value is less than zero, the match is abandoned, the + failed. If the value is less than zero, the match is abandoned, the matching function returns the negative value. - Negative values should normally be chosen from the set of + Negative values should normally be chosen from the set of PCRE_ERROR_xxx values. In particular, PCRE_ERROR_NOMATCH forces a stan- - dard "no match" failure. The error number PCRE_ERROR_CALLOUT is - reserved for use by callout functions; it will never be used by PCRE + dard "no match" failure. The error number PCRE_ERROR_CALLOUT is + reserved for use by callout functions; it will never be used by PCRE itself. @@ -3693,11 +4310,11 @@ AUTHOR REVISION - Last updated: 08 Janurary 2012 + Last updated: 24 June 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRECOMPAT(3) PCRECOMPAT(3) @@ -3752,15 +4369,10 @@ DIFFERENCES BETWEEN PCRE AND PERL tion of Unicode characters, there is no need to implement the somewhat messy concept of surrogates." - 7. PCRE implements a simpler version of \X than Perl, which changed to - make \X match what Unicode calls an "extended grapheme cluster". This - is more complicated than an extended Unicode sequence, which is what - PCRE matches. - - 8. PCRE does support the \Q...\E escape for quoting substrings. Charac- - ters in between are treated as literals. This is slightly different - from Perl in that $ and @ are also handled as literals inside the - quotes. In Perl, they cause variable interpolation (but of course PCRE + 7. PCRE does support the \Q...\E escape for quoting substrings. Charac- + ters in between are treated as literals. This is slightly different + from Perl in that $ and @ are also handled as literals inside the + quotes. In Perl, they cause variable interpolation (but of course PCRE does not have variables). Note the following examples: Pattern PCRE matches Perl matches @@ -3770,73 +4382,73 @@ DIFFERENCES BETWEEN PCRE AND PERL \Qabc\$xyz\E abc\$xyz abc\$xyz \Qabc\E\$\Qxyz\E abc$xyz abc$xyz - The \Q...\E sequence is recognized both inside and outside character + The \Q...\E sequence is recognized both inside and outside character classes. - 9. Fairly obviously, PCRE does not support the (?{code}) and (??{code}) - constructions. However, there is support for recursive patterns. This - is not available in Perl 5.8, but it is in Perl 5.10. Also, the PCRE - "callout" feature allows an external function to be called during pat- + 8. Fairly obviously, PCRE does not support the (?{code}) and (??{code}) + constructions. However, there is support for recursive patterns. This + is not available in Perl 5.8, but it is in Perl 5.10. Also, the PCRE + "callout" feature allows an external function to be called during pat- tern matching. See the pcrecallout documentation for details. - 10. Subpatterns that are called as subroutines (whether or not recur- - sively) are always treated as atomic groups in PCRE. This is like - Python, but unlike Perl. Captured values that are set outside a sub- - routine call can be reference from inside in PCRE, but not in Perl. + 9. Subpatterns that are called as subroutines (whether or not recur- + sively) are always treated as atomic groups in PCRE. This is like + Python, but unlike Perl. Captured values that are set outside a sub- + routine call can be reference from inside in PCRE, but not in Perl. There is a discussion that explains these differences in more detail in the section on recursion differences from Perl in the pcrepattern page. - 11. If any of the backtracking control verbs are used in an assertion - or in a subpattern that is called as a subroutine (whether or not - recursively), their effect is confined to that subpattern; it does not + 10. If any of the backtracking control verbs are used in an assertion + or in a subpattern that is called as a subroutine (whether or not + recursively), their effect is confined to that subpattern; it does not extend to the surrounding pattern. This is not always the case in Perl. - In particular, if (*THEN) is present in a group that is called as a + In particular, if (*THEN) is present in a group that is called as a subroutine, its action is limited to that group, even if the group does - not contain any | characters. There is one exception to this: the name - from a *(MARK), (*PRUNE), or (*THEN) that is encountered in a success- - ful positive assertion is passed back when a match succeeds (compare - capturing parentheses in assertions). Note that such subpatterns are + not contain any | characters. There is one exception to this: the name + from a *(MARK), (*PRUNE), or (*THEN) that is encountered in a success- + ful positive assertion is passed back when a match succeeds (compare + capturing parentheses in assertions). Note that such subpatterns are processed as anchored at the point where they are tested. - 12. There are some differences that are concerned with the settings of - captured strings when part of a pattern is repeated. For example, - matching "aba" against the pattern /^(a(b)?)+$/ in Perl leaves $2 + 11. There are some differences that are concerned with the settings of + captured strings when part of a pattern is repeated. For example, + matching "aba" against the pattern /^(a(b)?)+$/ in Perl leaves $2 unset, but in PCRE it is set to "b". - 13. PCRE's handling of duplicate subpattern numbers and duplicate sub- + 12. PCRE's handling of duplicate subpattern numbers and duplicate sub- 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 - 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- + ble to translate 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 names map to cap- turing subpattern number 1. To avoid this confusing situation, an error is given at compile time. - 14. Perl recognizes comments in some places that PCRE does not, for - example, between the ( and ? at the start of a subpattern. If the /x + 13. Perl recognizes comments in some places that PCRE does not, for + example, between the ( and ? at the start of a subpattern. If the /x modifier is set, Perl allows white space between ( and ? but PCRE never does, even if the PCRE_EXTENDED option is set. - 15. PCRE provides some extensions to the Perl regular expression facil- - ities. Perl 5.10 includes new features that are not in earlier ver- - sions of Perl, some of which (such as named parentheses) have been in + 14. PCRE provides some extensions to the Perl regular expression facil- + ities. Perl 5.10 includes new features that are not in earlier ver- + sions of Perl, some of which (such as named parentheses) have been in PCRE for some time. This list is with respect to Perl 5.10: - (a) Although lookbehind assertions in PCRE must match fixed length - strings, each alternative branch of a lookbehind assertion can match a - different length of string. Perl requires them all to have the same + (a) Although lookbehind assertions in PCRE must match fixed length + strings, each alternative branch of a lookbehind assertion can match a + different length of string. Perl requires them all to have the same length. - (b) If PCRE_DOLLAR_ENDONLY is set and PCRE_MULTILINE is not set, the $ + (b) If PCRE_DOLLAR_ENDONLY is set and PCRE_MULTILINE is not set, the $ meta-character matches only at the very end of the string. (c) If PCRE_EXTRA is set, a backslash followed by a letter with no spe- cial meaning is faulted. Otherwise, like Perl, the backslash is quietly ignored. (Perl can be made to issue a warning.) - (d) If PCRE_UNGREEDY is set, the greediness of the repetition quanti- + (d) If PCRE_UNGREEDY is set, the greediness of the repetition quanti- fiers is inverted, that is, by default they are not greedy, but if fol- lowed by a question mark they are. @@ -3844,10 +4456,10 @@ DIFFERENCES BETWEEN PCRE AND PERL tried only at the first matching position in the subject string. (f) The PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART, - and PCRE_NO_AUTO_CAPTURE options for pcre_exec() have no Perl equiva- + and PCRE_NO_AUTO_CAPTURE options for pcre_exec() have no Perl equiva- lents. - (g) The \R escape sequence can be restricted to match only CR, LF, or + (g) The \R escape sequence can be restricted to match only CR, LF, or CRLF by the PCRE_BSR_ANYCRLF option. (h) The callout facility is PCRE-specific. @@ -3855,14 +4467,14 @@ DIFFERENCES BETWEEN PCRE AND PERL (i) The partial matching facility is PCRE-specific. (j) Patterns compiled by PCRE can be saved and re-used at a later time, - even on different hosts that have the other endianness. However, this + even on different hosts that have the other endianness. However, this does not apply to optimized data created by the just-in-time compiler. - (k) The alternative matching functions (pcre_dfa_exec() and - pcre16_dfa_exec()) match in a different way and are not Perl-compati- - ble. + (k) The alternative matching functions (pcre_dfa_exec(), + pcre16_dfa_exec() and pcre32_dfa_exec(),) match in a different way and + are not Perl-compatible. - (l) PCRE recognizes some special sequences such as (*CR) at the start + (l) PCRE recognizes some special sequences such as (*CR) at the start of a pattern that set overall options that cannot be changed within the pattern. @@ -3876,11 +4488,11 @@ AUTHOR REVISION - Last updated: 01 June 2012 + Last updated: 25 August 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCREPATTERN(3) PCREPATTERN(3) @@ -3907,56 +4519,67 @@ PCRE REGULAR EXPRESSION DETAILS The original operation of PCRE was on strings of one-byte characters. However, there is now also support for UTF-8 strings in the original - library, and a second library that supports 16-bit and UTF-16 character + library, an extra library that supports 16-bit and UTF-16 character + strings, and an extra library that supports 32-bit and UTF-32 character strings. To use these features, PCRE must be built to include appropri- - ate support. When using UTF strings you must either call the compiling - function with the PCRE_UTF8 or PCRE_UTF16 option, or the pattern must - start with one of these special sequences: + ate support. When using UTF strings you must either call the compiling + function with the PCRE_UTF8, PCRE_UTF16 or PCRE_UTF32 option, or the + pattern must start with one of these special sequences: (*UTF8) (*UTF16) + (*UTF32) - Starting a pattern with such a sequence is equivalent to setting the + Starting a pattern with such a sequence is equivalent to setting the relevant option. This feature is not Perl-compatible. How setting a UTF - mode affects pattern matching is mentioned in several places below. + mode affects pattern matching is mentioned in several places below. There is also a summary of features in the pcreunicode page. - Another special sequence that may appear at the start of a pattern or - in combination with (*UTF8) or (*UTF16) is: + Another special sequence that may appear at the start of a pattern or + in combination with (*UTF8) or (*UTF16) or (*UTF32) is: (*UCP) - This has the same effect as setting the PCRE_UCP option: it causes - sequences such as \d and \w to use Unicode properties to determine + This has the same effect as setting the PCRE_UCP option: it causes + sequences such as \d and \w to use Unicode properties to determine character types, instead of recognizing only characters with codes less than 128 via a lookup table. - If a pattern starts with (*NO_START_OPT), it has the same effect as + If a pattern starts with (*NO_START_OPT), it has the same effect as setting the PCRE_NO_START_OPTIMIZE option either at compile or matching time. There are also some more of these special sequences that are con- cerned with the handling of newlines; they are described below. - The remainder of this document discusses the patterns that are sup- - ported by PCRE when one its main matching functions, pcre_exec() - (8-bit) or pcre16_exec() (16-bit), is used. PCRE also has alternative - matching functions, pcre_dfa_exec() and pcre16_dfa_exec(), which match - using a different algorithm that is not Perl-compatible. Some of the - features discussed below are not available when DFA matching is used. - The advantages and disadvantages of the alternative functions, and how - they differ from the normal functions, are discussed in the pcrematch- - ing page. + The remainder of this document discusses the patterns that are sup- + ported by PCRE when one its main matching functions, pcre_exec() + (8-bit) or pcre[16|32]_exec() (16- or 32-bit), is used. PCRE also has + alternative matching functions, pcre_dfa_exec() and + pcre[16|32_dfa_exec(), which match using a different algorithm that is + not Perl-compatible. Some of the features discussed below are not + available when DFA matching is used. The advantages and disadvantages + of the alternative functions, and how they differ from the normal func- + tions, are discussed in the pcrematching page. + + +EBCDIC CHARACTER CODES + + PCRE can be compiled to run in an environment that uses EBCDIC as its + character code rather than ASCII or Unicode (typically a mainframe sys- + tem). In the sections below, character code values are ASCII or Uni- + code; in an EBCDIC environment these characters may have different code + values, and there are no code points greater than 255. NEWLINE CONVENTIONS - PCRE supports five different conventions for indicating line breaks in - strings: a single CR (carriage return) character, a single LF (line- + PCRE supports five different conventions for indicating line breaks in + strings: a single CR (carriage return) character, a single LF (line- feed) character, the two-character sequence CRLF, any of the three pre- - ceding, or any Unicode newline sequence. The pcreapi page has further - discussion about newlines, and shows how to set the newline convention + ceding, or any Unicode newline sequence. The pcreapi page has further + discussion about newlines, and shows how to set the newline convention in the options arguments for the compiling and matching functions. - It is also possible to specify a newline convention by starting a pat- + It is also possible to specify a newline convention by starting a pat- tern string with one of the following five sequences: (*CR) carriage return @@ -3966,53 +4589,53 @@ NEWLINE CONVENTIONS (*ANY) all Unicode newline sequences These override the default and the options given to the compiling func- - tion. For example, on a Unix system where LF is the default newline + tion. For example, on a Unix system where LF is the default newline sequence, the pattern (*CR)a.b changes the convention to CR. That pattern matches "a\nb" because LF is - no longer a newline. Note that these special settings, which are not - Perl-compatible, are recognized only at the very start of a pattern, - and that they must be in upper case. If more than one of them is + no longer a newline. Note that these special settings, which are not + Perl-compatible, are recognized only at the very start of a pattern, + and that they must be in upper case. If more than one of them is present, the last one is used. - The newline convention affects the interpretation of the dot metachar- - acter when PCRE_DOTALL is not set, and also the behaviour of \N. How- - ever, it does not affect what the \R escape sequence matches. By - default, this is any Unicode newline sequence, for Perl compatibility. - However, this can be changed; see the description of \R in the section - entitled "Newline sequences" below. A change of \R setting can be com- + The newline convention affects the interpretation of the dot metachar- + acter when PCRE_DOTALL is not set, and also the behaviour of \N. How- + ever, it does not affect what the \R escape sequence matches. By + default, this is any Unicode newline sequence, for Perl compatibility. + However, this can be changed; see the description of \R in the section + entitled "Newline sequences" below. A change of \R setting can be com- bined with a change of newline convention. CHARACTERS AND METACHARACTERS - A regular expression is a pattern that is matched against a subject - string from left to right. Most characters stand for themselves in a - pattern, and match the corresponding characters in the subject. As a + A regular expression is a pattern that is matched against a subject + string from left to right. Most characters stand for themselves in a + pattern, and match the corresponding characters in the subject. As a trivial example, the pattern The quick brown fox matches a portion of a subject string that is identical to itself. When - caseless matching is specified (the PCRE_CASELESS option), letters are - matched independently of case. In 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 val- - ues, the concept of case is supported if PCRE is compiled with Unicode - property support, but not otherwise. If you want to use caseless - matching for characters 128 and above, you must ensure that PCRE is + caseless matching is specified (the PCRE_CASELESS option), letters are + matched independently of case. 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 val- + ues, the concept of case is supported if PCRE is compiled with Unicode + property support, but not otherwise. If you want to use caseless + matching for characters 128 and above, you must ensure that PCRE is compiled with Unicode property support as well as with UTF support. - The power of regular expressions comes from the ability to include - alternatives and repetitions in the pattern. These are encoded in the + The power of regular expressions comes from the ability to include + alternatives and repetitions in the pattern. These are encoded in the pattern by the use of metacharacters, which do not stand for themselves but instead are interpreted in some special way. - There are two different sets of metacharacters: those that are recog- - nized anywhere in the pattern except within square brackets, and those - that are recognized within square brackets. Outside square brackets, + There are two different sets of metacharacters: those that are recog- + nized anywhere in the pattern except within square brackets, and those + that are recognized within square brackets. Outside square brackets, the metacharacters are as follows: \ general escape character with several uses @@ -4031,7 +4654,7 @@ CHARACTERS AND METACHARACTERS also "possessive quantifier" { start min/max quantifier - Part of a pattern that is in square brackets is called a "character + Part of a pattern that is in square brackets is called a "character class". In a character class the only metacharacters are: \ general escape character @@ -4048,30 +4671,30 @@ BACKSLASH The backslash character has several uses. Firstly, if it is followed by a character that is not a number or a letter, it takes away any special - meaning that character may have. This use of backslash as an escape + meaning that character may have. This use of backslash as an escape character applies both inside and outside character classes. - For example, if you want to match a * character, you write \* in the - pattern. This escaping action applies whether or not the following - character would otherwise be interpreted as a metacharacter, so it is - always safe to precede a non-alphanumeric with backslash to specify - that it stands for itself. In particular, if you want to match a back- + For example, if you want to match a * character, you write \* in the + pattern. This escaping action applies whether or not the following + character would otherwise be interpreted as a metacharacter, so it is + always safe to precede a non-alphanumeric with backslash to specify + that it stands for itself. In particular, if you want to match a back- slash, you write \\. - In a UTF mode, only ASCII numbers and letters have any special meaning - after a backslash. All other characters (in particular, those whose + In a UTF mode, only ASCII numbers and letters have any special meaning + after a backslash. All other characters (in particular, those whose codepoints are greater than 127) are treated as literals. - If a pattern is compiled with the PCRE_EXTENDED option, white space in - the pattern (other than in a character class) and characters between a + If a pattern is compiled with the PCRE_EXTENDED option, white space in + the pattern (other than in a character class) and characters between a # outside a character class and the next newline are ignored. An escap- - ing backslash can be used to include a white space or # character as + ing backslash can be used to include a white space or # character as part of the pattern. - If you want to remove the special meaning from a sequence of charac- - ters, you can do so by putting them between \Q and \E. This is differ- - ent from Perl in that $ and @ are handled as literals in \Q...\E - sequences in PCRE, whereas in Perl, $ and @ cause variable interpola- + If you want to remove the special meaning from a sequence of charac- + ters, you can do so by putting them between \Q and \E. This is differ- + ent from Perl in that $ and @ are handled as literals in \Q...\E + sequences in PCRE, whereas in Perl, $ and @ cause variable interpola- tion. Note the following examples: Pattern PCRE matches Perl matches @@ -4081,20 +4704,20 @@ BACKSLASH \Qabc\$xyz\E abc\$xyz abc\$xyz \Qabc\E\$\Qxyz\E abc$xyz abc$xyz - The \Q...\E sequence is recognized both inside and outside character - classes. An isolated \E that is not preceded by \Q is ignored. If \Q - is not followed by \E later in the pattern, the literal interpretation - continues to the end of the pattern (that is, \E is assumed at the - end). If the isolated \Q is inside a character class, this causes an + The \Q...\E sequence is recognized both inside and outside character + classes. An isolated \E that is not preceded by \Q is ignored. If \Q + is not followed by \E later in the pattern, the literal interpretation + continues to the end of the pattern (that is, \E is assumed at the + end). If the isolated \Q is inside a character class, this causes an error, because the character class is not terminated. Non-printing characters A second use of backslash provides a way of encoding non-printing char- - acters in patterns in a visible manner. There is no restriction on the - appearance of non-printing characters, apart from the binary zero that - terminates a pattern, but when a pattern is being prepared by text - editing, it is often easier to use one of the following escape + acters in patterns in a visible manner. There is no restriction on the + appearance of non-printing characters, apart from the binary zero that + terminates a pattern, but when a pattern is being prepared by text + editing, it is often easier to use one of the following escape sequences than the binary character it represents: \a alarm, that is, the BEL character (hex 07) @@ -4109,14 +4732,23 @@ BACKSLASH \x{hhh..} character with hex code hhh.. (non-JavaScript mode) \uhhhh character with hex code hhhh (JavaScript mode only) - The precise effect of \cx is as follows: if x is a lower case letter, - it is converted to upper case. Then bit 6 of the character (hex 40) is - inverted. Thus \cz becomes hex 1A (z is 7A), but \c{ becomes hex 3B ({ - is 7B), while \c; becomes hex 7B (; is 3B). If the byte following \c + The precise effect of \cx on ASCII characters is as follows: if x is a + lower case letter, it is converted to upper case. Then bit 6 of the + character (hex 40) is inverted. Thus \cA to \cZ become hex 01 to hex 1A + (A is 41, Z is 5A), but \c{ becomes hex 3B ({ is 7B), and \c; becomes + hex 7B (; is 3B). If the data item (byte or 16-bit value) following \c has a value greater than 127, a compile-time error occurs. This locks - out non-ASCII characters in all modes. (When PCRE is compiled in EBCDIC - mode, all byte values are valid. A lower case letter is converted to - upper case, and then the 0xc0 bits are flipped.) + out non-ASCII characters in all modes. + + The \c facility was designed for use with ASCII characters, but with + the extension to Unicode it is even less useful than it once was. It + is, however, recognized when PCRE is compiled in EBCDIC mode, where + data items are always bytes. In this mode, all values are valid after + \c. If the next character is a lower case letter, it is converted to + upper case. Then the 0xc0 bits of the byte are inverted. Thus \cA + becomes hex 01, as in ASCII (A is C1), but because the EBCDIC letters + are disjoint, \cZ becomes hex 29 (Z is E9), and other characters also + generate different values. By default, after \x, from zero to two hexadecimal digits are read (letters can be in upper or lower case). Any number of hexadecimal dig- @@ -4127,9 +4759,11 @@ BACKSLASH 8-bit UTF-8 mode less than 0x10ffff and a valid codepoint 16-bit non-UTF mode less than 0x10000 16-bit UTF-16 mode less than 0x10ffff and a valid codepoint + 32-bit non-UTF mode less than 0x80000000 + 32-bit UTF-32 mode less than 0x10ffff and a valid codepoint Invalid Unicode codepoints are the range 0xd800 to 0xdfff (the so- - called "surrogate" codepoints). + called "surrogate" codepoints), and 0xffef. If characters other than hexadecimal digits appear between \x{ and }, or if there is no terminating }, this form of escape is not recognized. @@ -4172,7 +4806,7 @@ BACKSLASH value of the character is constrained in the same way as characters specified in hexadecimal. For example: - \040 is another way of writing a space + \040 is another way of writing an ASCII space \40 is the same, provided there are fewer than 40 previous capturing subpatterns \7 is always a back reference @@ -4292,7 +4926,7 @@ BACKSLASH codepoints, whether or not PCRE_UCP is set. The horizontal space char- acters are: - U+0009 Horizontal tab + U+0009 Horizontal tab (HT) U+0020 Space U+00A0 Non-break space U+1680 Ogham space mark @@ -4314,11 +4948,11 @@ BACKSLASH The vertical space characters are: - U+000A Linefeed - U+000B Vertical tab - U+000C Form feed - U+000D Carriage return - U+0085 Next line + U+000A Linefeed (LF) + U+000B Vertical tab (VT) + U+000C Form feed (FF) + U+000D Carriage return (CR) + U+0085 Next line (NEL) U+2028 Line separator U+2029 Paragraph separator @@ -4367,10 +5001,10 @@ BACKSLASH (*ANY)(*BSR_ANYCRLF) - They can also be combined with the (*UTF8), (*UTF16), or (*UCP) special - sequences. Inside a character class, \R is treated as an unrecognized - escape sequence, and so matches the letter "R" by default, but causes - an error if PCRE_EXTRA is set. + They can also be combined with the (*UTF8), (*UTF16), (*UTF32) or + (*UCP) special sequences. Inside a character class, \R is treated as an + unrecognized escape sequence, and so matches the letter "R" by default, + but causes an error if PCRE_EXTRA is set. Unicode character properties @@ -4382,7 +5016,7 @@ BACKSLASH \p{xx} a character with the xx property \P{xx} a character without the xx property - \X an extended Unicode sequence + \X a Unicode extended grapheme cluster The property names represented by xx above are limited to the Unicode script names, the general category properties, "Any", which matches any @@ -4485,9 +5119,9 @@ BACKSLASH 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 and - PCRE_NO_UTF16_CHECK in the pcreapi page). Perl does not support the Cs - property. + turned off (see the discussion of PCRE_NO_UTF8_CHECK, + 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 @@ -4500,76 +5134,103 @@ BACKSLASH Specifying caseless matching does not affect these escape sequences. For example, \p{Lu} always matches only upper case letters. - The \X escape matches any number of Unicode characters that form an - extended Unicode sequence. \X is equivalent to + 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 + (*UCP). + + Extended grapheme clusters + + 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- + lier, simpler definition that was equivalent to (?>\PM\pM*) - That is, it matches a character without the "mark" property, followed - by zero or more characters with the "mark" property, and treats the - sequence as an atomic group (see below). Characters with the "mark" - property are typically accents that affect the preceding character. - None of them have codepoints less than 256, so in 8-bit non-UTF-8 mode - \X matches any one character. + 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. - Note that recent versions of Perl have changed \X to match what Unicode - calls an "extended grapheme cluster", which has a more complicated def- - inition. + 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. - Matching characters by Unicode property is not fast, because PCRE has - to search a structure that contains data for over fifteen thousand - characters. That is why the traditional escape sequences such as \d and - \w do not use Unicode properties in PCRE by default, though you can - make them do so by setting the PCRE_UCP option or by starting the pat- - tern with (*UCP). + \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- + 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 + 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 + property. + + 5. Do not end after prepend characters. + + 6. Otherwise, end the cluster. PCRE's additional properties - As well as the standard Unicode properties described in the previous - section, PCRE supports four more that make it possible to convert tra- - ditional escape sequences such as \w and \s and POSIX character classes - to use Unicode properties. PCRE uses these non-standard, non-Perl prop- - erties internally when PCRE_UCP is set. They are: + 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 and POSIX character classes to use Unicode + properties. PCRE uses these non-standard, non-Perl properties inter- + nally when PCRE_UCP is set. They are: Xan Any alphanumeric character Xps Any POSIX space character 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 + 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, except that vertical tab is excluded. Xwd matches the same characters as Xan, plus underscore. 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 + 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. 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 @@ -4580,49 +5241,49 @@ 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. @@ -4630,96 +5291,97 @@ BACKSLASH CIRCUMFLEX AND DOLLAR Outside a character class, in the default matching mode, the circumflex - character is an assertion that is true only if the current matching - point is at the start of the subject string. If the startoffset argu- - ment of pcre_exec() is non-zero, circumflex can never match if the - PCRE_MULTILINE option is unset. Inside a character class, circumflex + 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.) - A dollar character is an assertion that is true only if the current - matching point is at the end of the subject string, or immediately + A dollar character is an assertion that is true only if the current + matching point is at the end of the subject string, or immediately before a newline at the end of the string (by default). Dollar need not - be the last character of the pattern if a number of alternatives are - involved, but it should be the last item in any branch in which it + be the last character of the pattern if a number of alternatives are + involved, but it should be the last item in any branch in which it appears. Dollar has no special meaning in a character class. - The meaning of dollar can be changed so that it matches only at the - very end of the string, by setting the PCRE_DOLLAR_ENDONLY option at + 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. 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 usefully 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 char- - acter. 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 or - PCRE_NO_UTF16_CHECK option is used). + 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 + 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 + 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- @@ -4770,7 +5432,7 @@ SQUARE BRACKETS AND CHARACTER CLASSES 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) mode, characters with values greater than 255 + 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, or by using the \x{ escaping mechanism. @@ -4978,10 +5640,10 @@ INTERNAL OPTION SETTING 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), and (*UCP) - leading sequences that can be used to set UTF and Unicode property - modes; they are equivalent to setting the PCRE_UTF8, PCRE_UTF16, and - the PCRE_UCP options, respectively. + 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. SUBPATTERNS @@ -5196,41 +5858,42 @@ REPETITION In UTF modes, quantifiers apply to characters rather than to individual 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 sequences, each of which - may be several data units long (and they may be of different lengths). + 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 /\*.*\*/ @@ -5239,19 +5902,19 @@ 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 @@ -5259,38 +5922,47 @@ 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 is one situation 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 + fail where a later one succeeds. Consider this pattern: + + (?>.*?a)b + + 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- string that matched the final iteration. For example, after @@ -6160,130 +6832,131 @@ CALLOUTS 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 pcre16_callout (16-bit library). By - default, this variable contains NULL, which disables all calling out. + 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 + 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. - 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. A - complete description of the interface to the callout function is given + 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. A + complete description of the interface to the callout function is given in the pcrecallout documentation. BACKTRACKING CONTROL - Perl 5.10 introduced a number of "Special Backtracking Control Verbs", + Perl 5.10 introduced a number of "Special Backtracking Control Verbs", which are described in the Perl documentation as "experimental and sub- - ject to change or removal in a future version of Perl". It goes on to - say: "Their usage in production code should be noted to avoid problems + ject to change or removal in a future version of Perl". It goes on to + say: "Their usage in production code should be noted to avoid problems during upgrades." The same remarks apply to the PCRE features described in this section. - Since these verbs are specifically related to backtracking, most of - them can be used only when the pattern is to be matched using one of + 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, which use a backtracking algorithm. - With the exception of (*FAIL), which behaves like a failing negative - assertion, they cause an error if encountered by a DFA matching func- + With the exception of (*FAIL), which behaves like a failing negative + assertion, they cause an error if encountered by a DFA matching func- tion. - If any of these verbs are used in an assertion or in a subpattern that + If any of these verbs are used in an assertion or in a subpattern that is called as a subroutine (whether or not recursively), their effect is confined to that subpattern; it does not extend to the surrounding pat- tern, with one exception: the name from a *(MARK), (*PRUNE), or (*THEN) - that is encountered in a successful positive assertion is passed back - when a match succeeds (compare capturing parentheses in assertions). + that is encountered in a successful positive assertion is passed back + when a match succeeds (compare capturing parentheses in assertions). Note that such subpatterns are processed as anchored at the point where - they are tested. Note also that Perl's treatment of subroutines and + they are tested. Note also that Perl's treatment of subroutines and assertions is different in some cases. - 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, with differing be- - haviour, depending on whether or not an argument is present. A name is + (*VERB) or (*VERB:NAME). Some may take either form, with differing be- + haviour, depending on whether or not an argument 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 library. If the name is empty, that is, if the closing parenthe- - sis immediately follows the colon, the effect is as if the colon were - not there. Any number of these verbs may occur in a pattern. + 16-bit and 32-bit library. If the name is empty, that is, if the clos- + ing 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. 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 - character must be present. When one of these optimizations suppresses - the running of a match, any included backtracking verbs will not, of + may know the minimum length of matching subject, or that a particular + character must be present. When one of these optimizations suppresses + the 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 - then continues at the outer level. If (*ACCEPT) is inside capturing + 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) is inside capturing parentheses, the data so far is captured. 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) 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 + When a match succeeds, the name of the last-encountered (*MARK) 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 outputting of (*MARK) data: re> /X(*MARK:A)Y|X(*MARK:B)Z/K @@ -6295,63 +6968,63 @@ 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 (*MARK) is encountered in a positive assertion, its name is recorded and passed back if it is the last-encountered. This does not happen for negative assertions. - After a partial match or a failed match, the name of the last encoun- + After a partial match or a failed match, the name of the last encoun- tered (*MARK) 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 - appears inside an atomic group, its effect is confined to that group, - because once the group has been matched, there is never any backtrack- - ing into it. In this situation, backtracking can "jump back" to the - left of the entire atomic group. (Remember also, as stated above, that + 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, its effect is confined to that group, + because once the group has been matched, there is never any backtrack- + ing into it. In this situation, backtracking can "jump back" to the + left of the entire atomic group. (Remember also, as stated above, that this localization also applies in subroutine calls and assertions.) - These verbs differ in exactly what kind of failure occurs when back- + These verbs differ in exactly what kind of failure occurs when back- tracking reaches them. (*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 the rest of the pattern does not match. Even if the pattern is unanchored, no further attempts to find a match by advancing the starting point take place. Once (*COMMIT) has been passed, - pcre_exec() is committed to finding a match at the current starting + pcre_exec() is committed to finding a match at the current starting point, or not at all. For example: a+(*COMMIT)b - This matches "xxaab" but not "aacaab". It can be thought of as a kind + 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. - 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 pcretest example: re> /(*COMMIT)abc/ @@ -6360,111 +7033,111 @@ BACKTRACKING CONTROL xyzabc\Y No match - PCRE knows that any match must start with "a", so the optimization - skips along the subject to "a" before running the first match attempt, - which succeeds. When the optimization is disabled by the \Y escape in + PCRE knows that any match must start with "a", so the optimization + skips along the subject to "a" before running the first match attempt, + which succeeds. When the optimization is disabled by the \Y escape in the second subject, the match starts at "x" and so the (*COMMIT) causes it 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 - the subject if the rest of the pattern does not match. If the pattern - is unanchored, the normal "bumpalong" advance to the next starting - character then happens. Backtracking can occur as usual to the left of - (*PRUNE), 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 alter- - native to an atomic group or possessive quantifier, but there are some + This verb causes the match to fail at the current starting position in + the subject if the rest of the pattern does not match. If the pattern + is unanchored, the normal "bumpalong" advance to the next starting + character then happens. Backtracking can occur as usual to the left of + (*PRUNE), 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 alter- + native to an atomic group or possessive quantifier, but there are some uses of (*PRUNE) that cannot be expressed in any other way. The behav- - iour of (*PRUNE:NAME) is the same as (*MARK:NAME)(*PRUNE). In an + iour of (*PRUNE:NAME) is the same as (*MARK:NAME)(*PRUNE). In an anchored pattern (*PRUNE) has the same effect as (*COMMIT). (*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. If the + When (*SKIP) has an associated name, its behaviour is modified. If the following pattern fails to match, the previous path through the pattern - is searched for the most recent (*MARK) that has the same name. If one - is found, the "bumpalong" advance is to the subject position that cor- - responds to that (*MARK) instead of to where (*SKIP) was encountered. + is searched for the most recent (*MARK) that has the same name. If one + is found, the "bumpalong" advance is to the subject position that cor- + responds to that (*MARK) instead of to where (*SKIP) was encountered. If no (*MARK) with a matching name is found, the (*SKIP) is ignored. (*THEN) or (*THEN:NAME) - This verb causes a skip to the next innermost alternative if the rest - of the pattern does not match. That is, it cancels pending backtrack- - ing, but only within the current alternative. Its name comes from the + This verb causes a skip to the next innermost alternative if the rest + of the pattern does not match. That is, it cancels pending backtrack- + ing, but only 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. The behaviour of (*THEN:NAME) is exactly the same as - (*MARK:NAME)(*THEN). If (*THEN) is not inside an alternation, it acts + 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. The behaviour of (*THEN:NAME) is exactly the same as + (*MARK:NAME)(*THEN). If (*THEN) is not inside an alternation, it acts like (*PRUNE). - Note that 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 sub- - pattern to the enclosing alternative. Consider this pattern, where A, + Note that 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 sub- + pattern to the enclosing alternative. Consider this pattern, where A, B, etc. are complex pattern fragments that do not contain any | charac- ters 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 also that a conditional subpattern is not considered as having two - alternatives, because only one is ever used. In other words, the | + 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. @@ -6474,16 +7147,16 @@ BACKTRACKING CONTROL (A(*COMMIT)B(*THEN)C|D) - Once A has matched, PCRE is committed to this match, at the current - starting position. If subsequently B matches, but C does not, the nor- + Once A has matched, PCRE is committed to this match, at the current + starting position. If subsequently B matches, but C does not, the nor- mal (*THEN) action of trying the next alternative (that is, D) does not happen because (*COMMIT) overrides. SEE ALSO - pcreapi(3), pcrecallout(3), pcrematching(3), pcresyntax(3), pcre(3), - pcre16(3). + pcreapi(3), pcrecallout(3), pcrematching(3), pcresyntax(3), pcre(3), + pcre16(3), pcre32(3). AUTHOR @@ -6495,11 +7168,11 @@ AUTHOR REVISION - Last updated: 17 June 2012 + Last updated: 10 September 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRESYNTAX(3) PCRESYNTAX(3) @@ -6553,7 +7226,7 @@ CHARACTER TYPES \V a character that is not a vertical white space character \w a "word" character \W a "non-word" character - \X an extended Unicode sequence + \X a Unicode extended grapheme cluster In PCRE, by default, \d, \D, \s, \S, \w, and \W recognize only ASCII characters, even in a UTF mode. However, this can be changed by setting @@ -6747,6 +7420,7 @@ OPTION SETTING (*NO_START_OPT) no start-match optimization (PCRE_NO_START_OPTIMIZE) (*UTF8) set UTF-8 mode: 8-bit library (PCRE_UTF8) (*UTF16) set UTF-16 mode: 16-bit library (PCRE_UTF16) + (*UTF32) set UTF-32 mode: 32-bit library (PCRE_UTF32) (*UCP) set PCRE_UCP (use Unicode properties for \d etc) @@ -6835,7 +7509,7 @@ BACKTRACKING CONTROL NEWLINE CONVENTIONS These are recognized only at the very start of the pattern or after a - (*BSR_...), (*UTF8), (*UTF16) or (*UCP) option. + (*BSR_...), (*UTF8), (*UTF16), (*UTF32) or (*UCP) option. (*CR) carriage return only (*LF) linefeed only @@ -6873,11 +7547,11 @@ AUTHOR REVISION - Last updated: 10 January 2012 + Last updated: 25 August 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCREUNICODE(3) PCREUNICODE(3) @@ -6891,33 +7565,48 @@ UTF-8, UTF-16, AND UNICODE PROPERTY SUPPORT supports UTF-16 by means of a separate 16-bit library. This can be built as well as, or instead of, the 8-bit library. + From Release 8.32, in addition to its previous UTF-8 and UTF-16 sup- + port, PCRE also supports UTF-32 by means of a separate 32-bit library. + This can be built as well as, or instead of, the 8-bit and 16-bit + libraries. + UTF-8 SUPPORT - In order process UTF-8 strings, you must build PCRE's 8-bit library - with UTF support, and, in addition, you must call pcre_compile() with - the PCRE_UTF8 option flag, or the pattern must start with the sequence - (*UTF8). When either of these is the case, both the pattern and any - subject strings that are matched against it are treated as UTF-8 + In order process UTF-8 strings, you must build PCRE's 8-bit library + with UTF support, and, in addition, you must call pcre_compile() with + the PCRE_UTF8 option flag, or the pattern must start with the sequence + (*UTF8). When either of these is the case, both the pattern and any + subject strings that are matched against it are treated as UTF-8 strings instead of strings of 1-byte characters. UTF-16 SUPPORT - In order process UTF-16 strings, you must build PCRE's 16-bit library + In order process UTF-16 strings, you must build PCRE's 16-bit library with UTF support, and, in addition, you must call pcre16_compile() with the PCRE_UTF16 option flag, or the pattern must start with the sequence - (*UTF16). When either of these is the case, both the pattern and any - subject strings that are matched against it are treated as UTF-16 + (*UTF16). When either of these is the case, both the pattern and any + subject strings that are matched against it are treated as UTF-16 strings instead of strings of 16-bit characters. +UTF-32 SUPPORT + + In order process UTF-32 strings, you must build PCRE's 32-bit library + with UTF support, and, in addition, you must call pcre32_compile() with + the PCRE_UTF32 option flag, or the pattern must start with the sequence + (*UTF32). When either of these is the case, both the pattern and any + subject strings that are matched against it are treated as UTF-32 + strings instead of strings of 32-bit characters. + + UTF SUPPORT OVERHEAD If you compile PCRE with UTF support, but do not use it at run time, the library will be a bit bigger, but the additional run time overhead - is limited to testing the PCRE_UTF8/16 flag occasionally, so should not - be very big. + is limited to testing the PCRE_UTF[8|16|32] flag occasionally, so + should not be very big. UNICODE PROPERTY SUPPORT @@ -6944,15 +7633,19 @@ UNICODE PROPERTY SUPPORT fication. Earlier releases of PCRE followed the rules of RFC 2279, which allows the full range of 31-bit values (0 to 0x7FFFFFFF). The current check allows only values in the range U+0 to U+10FFFF, exclud- - ing U+D800 to U+DFFF. + ing the surrogate area, and the non-characters. - The excluded code points are the "Surrogate Area" of Unicode. They are + Excluded code points are the "Surrogate Area" of Unicode. They are reserved for use by UTF-16, where they are used in pairs to encode codepoints with values greater than 0xFFFF. The code points that are encoded by UTF-16 pairs are available independently in the UTF-8 encod- ing. (In other words, the whole surrogate thing is a fudge for UTF-16 which unfortunately messes up UTF-8.) + Also excluded are the "Non-Characters" code points, which are U+FDD0 to + U+FDEF and the last two code points in each plane, U+??FFFE and + U+??FFFF. + If an invalid UTF-8 string is passed to PCRE, an error return is given. At compile time, the only additional information is the offset to the first byte of the failing character. The run-time functions pcre_exec() @@ -6994,6 +7687,10 @@ UNICODE PROPERTY SUPPORT surrogate range U+D800 to U+DFFF are independent code points. Values in the surrogate range must be used in pairs in the correct manner. + Excluded are the "Non-Characters" code points, which are U+FDD0 to + U+FDEF and the last two code points in each plane, U+??FFFE and + U+??FFFF. + If an invalid UTF-16 string is passed to PCRE, an error return is given. At compile time, the only additional information is the offset to the first data unit of the failing character. The run-time functions @@ -7008,30 +7705,66 @@ UNICODE PROPERTY SUPPORT tively) contains only valid UTF-16 sequences. In this case, it does not diagnose an invalid UTF-16 string. + Validity of UTF-32 strings + + When you set the PCRE_UTF32 flag, the strings of 32-bit data units that + are passed as patterns and subjects are (by default) checked for valid- + ity on entry to the relevant functions. This check allows only values + in the range U+0 to U+10FFFF, excluding the surrogate area U+D800 to + U+DFFF, and the "Non-Characters" code points, which are U+FDD0 to + U+FDEF and the last two characters in each plane, U+??FFFE and + U+??FFFF. + + If an invalid UTF-32 string is passed to PCRE, an error return is + given. At compile time, the only additional information is the offset + to the first data unit of the failing character. The run-time functions + pcre32_exec() and pcre32_dfa_exec() also pass back this information, as + well as a more detailed reason code if the caller has provided memory + in which to do this. + + In some situations, you may already know that your strings are valid, + and therefore want to skip these checks in order to improve perfor- + mance. If you set the PCRE_NO_UTF32_CHECK flag at compile time or at + run time, PCRE assumes that the pattern or subject it is given (respec- + tively) contains only valid UTF-32 sequences. In this case, it does not + diagnose an invalid UTF-32 string. + + UTF-32 only uses the lowest 21 bits of the 32 bit characters, and the + application may use the upper bits for internal purposes. To allow you + to pass these strings to PCRE unmodified (thus avoiding the costly + operation of creating a copy of the string with the upper bits masked), + PCRE accepts these 32-bit character strings as-is, but only uses the + lowest 21 bits for matching, if you pass the PCRE_NO_UTF32_CHECK flag + to pcre32_exec() and pcre32_dfa_exec(). However, in this situation, you + will have to apply your own validity check, and avoid the use of JIT + optimization. (The latter restriction may be lifter in a later version + of PCRE.) + General comments about UTF modes - 1. Codepoints less than 256 can be specified by either braced or - unbraced hexadecimal escape sequences (for example, \x{b3} or \xb3). + 1. Codepoints less than 256 can be specified by either braced or + unbraced hexadecimal escape sequences (for example, \x{b3} or \xb3). Larger values have to use braced sequences. - 2. Octal numbers up to \777 are recognized, and in UTF-8 mode, they + 2. Octal numbers up to \777 are recognized, and in UTF-8 mode, they match two-byte characters for values greater than \177. 3. Repeat quantifiers apply to complete UTF characters, not to individ- ual data units, for example: \x{100}{3}. - 4. The dot metacharacter matches one UTF character instead of a single + 4. The dot metacharacter matches one UTF character instead of a single data unit. - 5. The escape sequence \C can be used to match a single byte in UTF-8 - mode, or a single 16-bit data unit in UTF-16 mode, but its use can lead - to some strange effects because it breaks up multi-unit characters (see - the description of \C in the pcrepattern documentation). The use of \C - is not supported in the alternative matching function - pcre[16]_dfa_exec(), nor is it supported in UTF mode by the JIT opti- - mization of pcre[16]_exec(). If JIT optimization is requested for a UTF - pattern that contains \C, it will not succeed, and so the matching will - be carried out by the normal interpretive function. + 5. The escape sequence \C can be used to match a single byte in UTF-8 + mode, or a single 16-bit data unit in UTF-16 mode, or a single 32-bit + data unit in UTF-32 mode, but its use can lead to some strange effects + because it breaks up multi-unit characters (see the description of \C + in the pcrepattern documentation). The use of \C is not supported in + the alternative matching function pcre[16|32]_dfa_exec(), nor is it + supported in UTF mode by the JIT optimization of pcre[16|32]_exec(). If + JIT optimization is requested for a UTF pattern that contains \C, it + will not succeed, and so the matching will be carried out by the normal + interpretive function. 6. The character escapes \b, \B, \d, \D, \s, \S, \w, and \W correctly test characters of any code value, but, by default, the characters that @@ -7056,13 +7789,11 @@ UNICODE PROPERTY SUPPORT 9. Case-insensitive matching applies only to characters whose values are less than 128, unless PCRE is built with Unicode property support. - Even when Unicode property support is available, PCRE still uses its - own character tables when checking the case of low-valued characters, - so as not to degrade performance. The Unicode property information is - used only for characters with higher values. Furthermore, PCRE supports - case-insensitive matching only when there is a one-to-one mapping - between a letter's cases. There are a small number of many-to-one map- - pings in Unicode; these are not supported by PCRE. + A few Unicode characters such as Greek sigma have more than two code- + points that are case-equivalent. Up to and including PCRE release 8.31, + only one-to-one case mappings were supported, but later releases (with + Unicode property support) do treat as case-equivalent all versions of + characters such as Greek sigma. AUTHOR @@ -7074,11 +7805,11 @@ AUTHOR REVISION - Last updated: 14 April 2012 + Last updated: 25 September 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCREJIT(3) PCREJIT(3) @@ -7103,13 +7834,15 @@ PCRE JUST-IN-TIME COMPILER SUPPORT used. The code for this support was written by Zoltan Herczeg. -8-BIT and 16-BIT SUPPORT +8-BIT, 16-BIT AND 32-BIT SUPPORT - JIT support is available for both the 8-bit and 16-bit PCRE libraries. - To keep this documentation simple, only the 8-bit interface is - described in what follows. If you are using the 16-bit library, substi- - tute the 16-bit functions and 16-bit structures (for example, - pcre16_jit_stack instead of pcre_jit_stack). + JIT support is available for all of the 8-bit, 16-bit and 32-bit PCRE + libraries. To keep this documentation simple, only the 8-bit interface + is described in what follows. If you are using the 16-bit library, sub- + stitute the 16-bit functions and 16-bit structures (for example, + pcre16_jit_stack instead of pcre_jit_stack). If you are using the + 32-bit library, substitute the 32-bit functions and 32-bit structures + (for example, pcre32_jit_stack instead of pcre_jit_stack). AVAILABILITY OF JIT SUPPORT @@ -7123,6 +7856,7 @@ AVAILABILITY OF JIT SUPPORT Intel x86 32-bit and 64-bit MIPS 32-bit Power PC 32-bit and 64-bit + SPARC 32-bit (experimental) If --enable-jit is set on an unsupported platform, compilation fails. @@ -7130,8 +7864,10 @@ AVAILABILITY OF JIT SUPPORT port is available by calling pcre_config() with the PCRE_CONFIG_JIT option. The result is 1 when JIT is available, and 0 otherwise. How- ever, a simple program does not need to check this in order to use JIT. - The API is implemented in a way that falls back to the interpretive - code if JIT is not available. + The normal API is implemented in a way that falls back to the interpre- + tive code if JIT is not available. For programs that need the best pos- + sible performance, there is also a "fast path" API that is JIT-spe- + cific. If your program may sometimes be linked with versions of PCRE that are older than 8.20, but you want to use JIT when it is available, you can @@ -7149,17 +7885,18 @@ SIMPLE USE OF JIT pcre_exec(). (2) Use pcre_free_study() to free the pcre_extra block when it is - no longer needed, instead of just freeing it yourself. This - ensures that any JIT data is also freed. + no longer needed, instead of just freeing it yourself. This + ensures that + any JIT data is also freed. - For a program that may be linked with pre-8.20 versions of PCRE, you + For a program that may be linked with pre-8.20 versions of PCRE, you can insert #ifndef PCRE_STUDY_JIT_COMPILE #define PCRE_STUDY_JIT_COMPILE 0 #endif - so that no option is passed to pcre_study(), and then use something + so that no option is passed to pcre_study(), and then use something like this to free the study data: #ifdef PCRE_CONFIG_JIT @@ -7168,50 +7905,50 @@ SIMPLE USE OF JIT pcre_free(study_ptr); #endif - PCRE_STUDY_JIT_COMPILE requests the JIT compiler to generate code for - complete matches. If you want to run partial matches using the - PCRE_PARTIAL_HARD or PCRE_PARTIAL_SOFT options of pcre_exec(), you - should set one or both of the following options in addition to, or + PCRE_STUDY_JIT_COMPILE requests the JIT compiler to generate code for + complete matches. If you want to run partial matches using the + PCRE_PARTIAL_HARD or PCRE_PARTIAL_SOFT options of pcre_exec(), you + should set one or both of the following options in addition to, or instead of, PCRE_STUDY_JIT_COMPILE when you call pcre_study(): PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE - The JIT compiler generates different optimized code for each of the - three modes (normal, soft partial, hard partial). When pcre_exec() is - called, the appropriate code is run if it is available. Otherwise, the + The JIT compiler generates different optimized code for each of the + three modes (normal, soft partial, hard partial). When pcre_exec() is + called, the appropriate code is run if it is available. Otherwise, the pattern is matched using interpretive code. - In some circumstances you may need to call additional functions. These - are described in the section entitled "Controlling the JIT stack" + In some circumstances you may need to call additional functions. These + are described in the section entitled "Controlling the JIT stack" below. - If JIT support is not available, PCRE_STUDY_JIT_COMPILE etc. are + If JIT support is not available, PCRE_STUDY_JIT_COMPILE etc. are ignored, and no JIT data is created. Otherwise, the compiled pattern is - passed to the JIT compiler, which turns it into machine code that exe- - cutes much faster than the normal interpretive code. When pcre_exec() - is passed a pcre_extra block containing a pointer to JIT code of the - appropriate mode (normal or hard/soft partial), it obeys that code - instead of running the interpreter. The result is identical, but the + passed to the JIT compiler, which turns it into machine code that exe- + cutes much faster than the normal interpretive code. When pcre_exec() + is passed a pcre_extra block containing a pointer to JIT code of the + appropriate mode (normal or hard/soft partial), it obeys that code + instead of running the interpreter. The result is identical, but the compiled JIT code runs much faster. - There are some pcre_exec() options that are not supported for JIT exe- - cution. There are also some pattern items that JIT cannot handle. - Details are given below. In both cases, execution automatically falls - back to the interpretive code. If you want to know whether JIT was - actually used for a particular match, you should arrange for a JIT - callback function to be set up as described in the section entitled - "Controlling the JIT stack" below, even if you do not need to supply a - non-default JIT stack. Such a callback function is called whenever JIT - code is about to be obeyed. If the execution options are not right for + There are some pcre_exec() options that are not supported for JIT exe- + cution. There are also some pattern items that JIT cannot handle. + Details are given below. In both cases, execution automatically falls + back to the interpretive code. If you want to know whether JIT was + actually used for a particular match, you should arrange for a JIT + callback function to be set up as described in the section entitled + "Controlling the JIT stack" below, even if you do not need to supply a + non-default JIT stack. Such a callback function is called whenever JIT + code is about to be obeyed. If the execution options are not right for JIT execution, the callback function is not obeyed. - If the JIT compiler finds an unsupported item, no JIT data is gener- - ated. You can find out if JIT execution is available after studying a - pattern by calling pcre_fullinfo() with the PCRE_INFO_JIT option. A - result of 1 means that JIT compilation was successful. A result of 0 + If the JIT compiler finds an unsupported item, no JIT data is gener- + ated. You can find out if JIT execution is available after studying a + pattern by calling pcre_fullinfo() with the PCRE_INFO_JIT option. A + result of 1 means that JIT compilation was successful. A result of 0 means that JIT support is not available, or the pattern was not studied - with PCRE_STUDY_JIT_COMPILE etc., or the JIT compiler was not able to + with PCRE_STUDY_JIT_COMPILE etc., or the JIT compiler was not able to handle the pattern. Once a pattern has been studied, with or without JIT, it can be used as @@ -7220,10 +7957,10 @@ SIMPLE USE OF JIT UNSUPPORTED OPTIONS AND PATTERN ITEMS - The only pcre_exec() options that are supported for JIT execution are - PCRE_NO_UTF8_CHECK, PCRE_NO_UTF16_CHECK, PCRE_NOTBOL, PCRE_NOTEOL, - PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART, PCRE_PARTIAL_HARD, and PCRE_PAR- - TIAL_SOFT. + The only pcre_exec() options that are supported for JIT execution are + PCRE_NO_UTF8_CHECK, PCRE_NO_UTF16_CHECK, PCRE_NO_UTF32_CHECK, PCRE_NOT- + BOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART, PCRE_PAR- + TIAL_HARD, and PCRE_PARTIAL_SOFT. The unsupported pattern items are: @@ -7238,65 +7975,65 @@ UNSUPPORTED OPTIONS AND PATTERN ITEMS RETURN VALUES FROM JIT EXECUTION - When a pattern is matched using JIT execution, the return values are - the same as those given by the interpretive pcre_exec() code, with the - addition of one new error code: PCRE_ERROR_JIT_STACKLIMIT. This means - that the memory used for the JIT stack was insufficient. See "Control- + When a pattern is matched using JIT execution, the return values are + the same as those given by the interpretive pcre_exec() code, with the + addition of one new error code: PCRE_ERROR_JIT_STACKLIMIT. This means + that the memory used for the JIT stack was insufficient. See "Control- ling the JIT stack" below for a discussion of JIT stack usage. For com- - patibility with the interpretive pcre_exec() code, no more than two- - thirds of the ovector argument is used for passing back captured sub- + patibility with the interpretive pcre_exec() code, no more than two- + thirds of the ovector argument is used for passing back captured sub- strings. - The error code PCRE_ERROR_MATCHLIMIT is returned by the JIT code if - searching a very large pattern tree goes on for too long, as it is in - the same circumstance when JIT is not used, but the details of exactly - what is counted are not the same. The PCRE_ERROR_RECURSIONLIMIT error + The error code PCRE_ERROR_MATCHLIMIT is returned by the JIT code if + searching a very large pattern tree goes on for too long, as it is in + the same circumstance when JIT is not used, but the details of exactly + what is counted are not the same. The PCRE_ERROR_RECURSIONLIMIT error code is never returned by JIT execution. SAVING AND RESTORING COMPILED PATTERNS - The code that is generated by the JIT compiler is architecture-spe- - cific, and is also position dependent. For those reasons it cannot be - saved (in a file or database) and restored later like the bytecode and - other data of a compiled pattern. Saving and restoring compiled pat- - terns is not something many people do. More detail about this facility - is given in the pcreprecompile documentation. It should be possible to - run pcre_study() on a saved and restored pattern, and thereby recreate - the JIT data, but because JIT compilation uses significant resources, - it is probably not worth doing this; you might as well recompile the + The code that is generated by the JIT compiler is architecture-spe- + cific, and is also position dependent. For those reasons it cannot be + saved (in a file or database) and restored later like the bytecode and + other data of a compiled pattern. Saving and restoring compiled pat- + terns is not something many people do. More detail about this facility + is given in the pcreprecompile documentation. It should be possible to + run pcre_study() on a saved and restored pattern, and thereby recreate + the JIT data, but because JIT compilation uses significant resources, + it is probably not worth doing this; you might as well recompile the original pattern. CONTROLLING THE JIT STACK When the compiled JIT code runs, it needs a block of memory to use as a - stack. By default, it uses 32K on the machine stack. However, some - large or complicated patterns need more than this. The error - PCRE_ERROR_JIT_STACKLIMIT is given when there is not enough stack. - Three functions are provided for managing blocks of memory for use as - JIT stacks. There is further discussion about the use of JIT stacks in + stack. By default, it uses 32K on the machine stack. However, some + large or complicated patterns need more than this. The error + PCRE_ERROR_JIT_STACKLIMIT is given when there is not enough stack. + Three functions are provided for managing blocks of memory for use as + JIT stacks. There is further discussion about the use of JIT stacks in the section entitled "JIT stack FAQ" below. - The pcre_jit_stack_alloc() function creates a JIT stack. Its arguments - are a starting size and a maximum size, and it returns a pointer to an - opaque structure of type pcre_jit_stack, or NULL if there is an error. - The pcre_jit_stack_free() function can be used to free a stack that is - no longer needed. (For the technically minded: the address space is + The pcre_jit_stack_alloc() function creates a JIT stack. Its arguments + are a starting size and a maximum size, and it returns a pointer to an + opaque structure of type pcre_jit_stack, or NULL if there is an error. + The pcre_jit_stack_free() function can be used to free a stack that is + no longer needed. (For the technically minded: the address space is allocated by mmap or VirtualAlloc.) - JIT uses far less memory for recursion than the interpretive code, and - a maximum stack size of 512K to 1M should be more than enough for any + JIT uses far less memory for recursion than the interpretive code, and + a maximum stack size of 512K to 1M should be more than enough for any pattern. - The pcre_assign_jit_stack() function specifies which stack JIT code + The pcre_assign_jit_stack() function specifies which stack JIT code should use. Its arguments are as follows: pcre_extra *extra pcre_jit_callback callback void *data - The extra argument must be the result of studying a pattern with + The extra argument must be the result of studying a pattern with PCRE_STUDY_JIT_COMPILE etc. There are three cases for the values of the other two options: @@ -7313,29 +8050,29 @@ CONTROLLING THE JIT STACK return value must be a valid JIT stack, the result of calling pcre_jit_stack_alloc(). - A callback function is obeyed whenever JIT code is about to be run; it - is not obeyed when pcre_exec() is called with options that are incom- + A callback function is obeyed whenever JIT code is about to be run; it + is not obeyed when pcre_exec() is called with options that are incom- patible for JIT execution. A callback function can therefore be used to - determine whether a match operation was executed by JIT or by the + determine whether a match operation was executed by JIT or by the interpreter. You may safely use the same JIT stack for more than one pattern (either - by assigning directly or by callback), as long as the patterns are all - matched sequentially in the same thread. In a multithread application, - if you do not specify a JIT stack, or if you assign or pass back NULL - from a callback, that is thread-safe, because each thread has its own - machine stack. However, if you assign or pass back a non-NULL JIT - stack, this must be a different stack for each thread so that the + by assigning directly or by callback), as long as the patterns are all + matched sequentially in the same thread. In a multithread application, + if you do not specify a JIT stack, or if you assign or pass back NULL + from a callback, that is thread-safe, because each thread has its own + machine stack. However, if you assign or pass back a non-NULL JIT + stack, this must be a different stack for each thread so that the application is thread-safe. - Strictly speaking, even more is allowed. You can assign the same non- - NULL stack to any number of patterns as long as they are not used for - matching by multiple threads at the same time. For example, you can - assign the same stack to all compiled patterns, and use a global mutex - in the callback to wait until the stack is available for use. However, + Strictly speaking, even more is allowed. You can assign the same non- + NULL stack to any number of patterns as long as they are not used for + matching by multiple threads at the same time. For example, you can + assign the same stack to all compiled patterns, and use a global mutex + in the callback to wait until the stack is available for use. However, this is an inefficient solution, and not recommended. - This is a suggestion for how a multithreaded program that needs to set + This is a suggestion for how a multithreaded program that needs to set up non-default JIT stacks might operate: During thread initalization @@ -7347,9 +8084,9 @@ CONTROLLING THE JIT STACK Use a one-line callback function return thread_local_var - All the functions described in this section do nothing if JIT is not - available, and pcre_assign_jit_stack() does nothing unless the extra - argument is non-NULL and points to a pcre_extra block that is the + All the functions described in this section do nothing if JIT is not + available, and pcre_assign_jit_stack() does nothing unless the extra + argument is non-NULL and points to a pcre_extra block that is the result of a successful study with PCRE_STUDY_JIT_COMPILE etc. @@ -7357,73 +8094,73 @@ JIT STACK FAQ (1) Why do we need JIT stacks? - PCRE (and JIT) is a recursive, depth-first engine, so it needs a stack - where the local data of the current node is pushed before checking its + PCRE (and JIT) is a recursive, depth-first engine, so it needs a stack + where the local data of the current node is pushed before checking its child nodes. Allocating real machine stack on some platforms is diffi- cult. For example, the stack chain needs to be updated every time if we - extend the stack on PowerPC. Although it is possible, its updating + extend the stack on PowerPC. Although it is possible, its updating time overhead decreases performance. So we do the recursion in memory. (2) Why don't we simply allocate blocks of memory with malloc()? - Modern operating systems have a nice feature: they can reserve an + Modern operating systems have a nice feature: they can reserve an address space instead of allocating memory. We can safely allocate mem- - ory pages inside this address space, so the stack could grow without + ory pages inside this address space, so the stack could grow without moving memory data (this is important because of pointers). Thus we can - allocate 1M address space, and use only a single memory page (usually - 4K) if that is enough. However, we can still grow up to 1M anytime if + allocate 1M address space, and use only a single memory page (usually + 4K) if that is enough. However, we can still grow up to 1M anytime if needed. (3) Who "owns" a JIT stack? The owner of the stack is the user program, not the JIT studied pattern - or anything else. The user program must ensure that if a stack is used - by pcre_exec(), (that is, it is assigned to the pattern currently run- + or anything else. The user program must ensure that if a stack is used + by pcre_exec(), (that is, it is assigned to the pattern currently run- ning), that stack must not be used by any other threads (to avoid over- writing the same memory area). The best practice for multithreaded pro- - grams is to allocate a stack for each thread, and return this stack + grams is to allocate a stack for each thread, and return this stack through the JIT callback function. (4) When should a JIT stack be freed? You can free a JIT stack at any time, as long as it will not be used by - pcre_exec() again. When you assign the stack to a pattern, only a - pointer is set. There is no reference counting or any other magic. You - can free the patterns and stacks in any order, anytime. Just do not - call pcre_exec() with a pattern pointing to an already freed stack, as - that will cause SEGFAULT. (Also, do not free a stack currently used by - pcre_exec() in another thread). You can also replace the stack for a - pattern at any time. You can even free the previous stack before + pcre_exec() again. When you assign the stack to a pattern, only a + pointer is set. There is no reference counting or any other magic. You + can free the patterns and stacks in any order, anytime. Just do not + call pcre_exec() with a pattern pointing to an already freed stack, as + that will cause SEGFAULT. (Also, do not free a stack currently used by + pcre_exec() in another thread). You can also replace the stack for a + pattern at any time. You can even free the previous stack before assigning a replacement. - (5) Should I allocate/free a stack every time before/after calling + (5) Should I allocate/free a stack every time before/after calling pcre_exec()? - No, because this is too costly in terms of resources. However, you - could implement some clever idea which release the stack if it is not - used in let's say two minutes. The JIT callback can help to achive this - without keeping a list of the currently JIT studied patterns. + No, because this is too costly in terms of resources. However, you + could implement some clever idea which release the stack if it is not + used in let's say two minutes. The JIT callback can help to achieve + this without keeping a list of the currently JIT studied patterns. - (6) OK, the stack is for long term memory allocation. But what happens - if a pattern causes stack overflow with a stack of 1M? Is that 1M kept + (6) OK, the stack is for long term memory allocation. But what happens + if a pattern causes stack overflow with a stack of 1M? Is that 1M kept until the stack is freed? - Especially on embedded sytems, it might be a good idea to release mem- - ory sometimes without freeing the stack. There is no API for this at - the moment. Probably a function call which returns with the currently - allocated memory for any stack and another which allows releasing mem- + Especially on embedded sytems, it might be a good idea to release mem- + ory sometimes without freeing the stack. There is no API for this at + the moment. Probably a function call which returns with the currently + allocated memory for any stack and another which allows releasing mem- ory (shrinking the stack) would be a good idea if someone needs this. (7) This is too much of a headache. Isn't there any better solution for JIT stack handling? - No, thanks to Windows. If POSIX threads were used everywhere, we could + No, thanks to Windows. If POSIX threads were used everywhere, we could throw out this complicated API. EXAMPLE CODE - This is a single-threaded example that specifies a JIT stack without + This is a single-threaded example that specifies a JIT stack without using a callback. int rc; @@ -7445,6 +8182,34 @@ EXAMPLE CODE pcre_jit_stack_free(jit_stack); +JIT FAST PATH API + + Because the API described above falls back to interpreted execution + when JIT is not available, it is convenient for programs that are writ- + ten for general use in many environments. However, calling JIT via + pcre_exec() does have a performance impact. Programs that are written + for use where JIT is known to be available, and which need the best + possible performance, can instead use a "fast path" API to call JIT + execution directly instead of calling pcre_exec() (obviously only for + patterns that have been successfully studied by JIT). + + The fast path function is called pcre_jit_exec(), and it takes exactly + the same arguments as pcre_exec(), plus one additional argument that + must point to a JIT stack. The JIT stack arrangements described above + do not apply. The return values are the same as for pcre_exec(). + + When you call pcre_exec(), as well as testing for invalid options, a + number of other sanity checks are performed on the arguments. For exam- + ple, if the subject pointer is NULL, or its length is negative, an + immediate error is given. Also, unless PCRE_NO_UTF[8|16|32] is set, a + UTF subject string is tested for validity. In the interests of speed, + these checks do not happen on the JIT fast path, and if invalid data is + passed, the result is undefined. + + Bypassing the sanity checks and the pcre_exec() wrapping can give + speedups of more than 10%. + + SEE ALSO pcreapi(3) @@ -7459,11 +8224,11 @@ AUTHOR REVISION - Last updated: 04 May 2012 + Last updated: 31 October 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCREPARTIAL(3) PCREPARTIAL(3) @@ -7504,8 +8269,8 @@ PARTIAL MATCHING IN PCRE precedence. If you want to use partial matching with just-in-time optimized code, - you must call pcre_study() or pcre16_study() with one or both of these - options: + you must call pcre_study(), pcre16_study() or pcre32_study() with one + or both of these options: PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE @@ -7524,180 +8289,181 @@ PARTIAL MATCHING IN PCRE abled for partial matching. -PARTIAL MATCHING USING pcre_exec() OR pcre16_exec() +PARTIAL MATCHING USING pcre_exec() OR pcre[16|32]_exec() - A partial match occurs during a call to pcre_exec() or pcre16_exec() - when the end of the subject string is reached successfully, but match- - ing cannot continue because more characters are needed. However, at - least one character in the subject must have been inspected. This char- - acter need not form part of the final matched string; lookbehind asser- - tions and the \K escape sequence provide ways of inspecting characters - before the start of a matched substring. The requirement for inspecting - at least one character exists because an empty string can always be - matched; without such a restriction there would always be a partial - match of an empty string at the end of the subject. + A partial match occurs during a call to pcre_exec() or + pcre[16|32]_exec() when the end of the subject string is reached suc- + cessfully, but matching cannot continue because more characters are + needed. However, at least one character in the subject must have been + inspected. This character need not form part of the final matched + string; lookbehind assertions and the \K escape sequence provide ways + of inspecting characters before the start of a matched substring. The + requirement for inspecting at least one character exists because an + empty string can always be matched; without such a restriction there + would always be a partial match of an empty string at the end of the + subject. - If there are at least two slots in the offsets vector when a partial - match is returned, the first slot is set to the offset of the earliest + If there are at least two slots in the offsets vector when a partial + match is returned, the first slot is set to the offset of the earliest character that was inspected. For convenience, the second offset points to the end of the subject so that a substring can easily be identified. - For the majority of patterns, the first offset identifies the start of - the partially matched string. However, for patterns that contain look- - behind assertions, or \K, or begin with \b or \B, earlier characters + For the majority of patterns, the first offset identifies the start of + the partially matched string. However, for patterns that contain look- + behind assertions, or \K, or begin with \b or \B, earlier characters have been inspected while carrying out the match. For example: /(?<=abc)123/ This pattern matches "123", but only if it is preceded by "abc". If the subject string is "xyzabc12", the offsets after a partial match are for - the substring "abc12", because all these characters are needed if + the substring "abc12", because all these characters are needed if another match is tried with extra characters added to the subject. What happens when a partial match is identified depends on which of the two partial matching options are set. - PCRE_PARTIAL_SOFT WITH pcre_exec() OR pcre16_exec() + PCRE_PARTIAL_SOFT WITH pcre_exec() OR pcre[16|32]_exec() - If PCRE_PARTIAL_SOFT is set when pcre_exec() or pcre16_exec() identi- - fies a partial match, the partial match is remembered, but matching - continues as normal, and other alternatives in the pattern are tried. - If no complete match can be found, PCRE_ERROR_PARTIAL is returned - instead of PCRE_ERROR_NOMATCH. + If PCRE_PARTIAL_SOFT is set when pcre_exec() or pcre[16|32]_exec() + identifies a partial match, the partial match is remembered, but match- + ing continues as normal, and other alternatives in the pattern are + tried. If no complete match can be found, PCRE_ERROR_PARTIAL is + returned instead of PCRE_ERROR_NOMATCH. - This option is "soft" because it prefers a complete match over a par- - tial match. All the various matching items in a pattern behave as if - the subject string is potentially complete. For example, \z, \Z, and $ - match at the end of the subject, as normal, and for \b and \B the end + This option is "soft" because it prefers a complete match over a par- + tial match. All the various matching items in a pattern behave as if + the subject string is potentially complete. For example, \z, \Z, and $ + match at the end of the subject, as normal, and for \b and \B the end of the subject is treated as a non-alphanumeric. - If there is more than one partial match, the first one that was found + If there is more than one partial match, the first one that was found provides the data that is returned. Consider this pattern: /123\w+X|dogY/ - If this is matched against the subject string "abc123dog", both alter- - natives fail to match, but the end of the subject is reached during - matching, so PCRE_ERROR_PARTIAL is returned. The offsets are set to 3 - and 9, identifying "123dog" as the first partial match that was found. - (In this example, there are two partial matches, because "dog" on its + If this is matched against the subject string "abc123dog", both alter- + natives fail to match, but the end of the subject is reached during + matching, so PCRE_ERROR_PARTIAL is returned. The offsets are set to 3 + and 9, identifying "123dog" as the first partial match that was found. + (In this example, there are two partial matches, because "dog" on its own partially matches the second alternative.) - PCRE_PARTIAL_HARD WITH pcre_exec() OR pcre16_exec() + PCRE_PARTIAL_HARD WITH pcre_exec() OR pcre[16|32]_exec() - If PCRE_PARTIAL_HARD is set for pcre_exec() or pcre16_exec(), - PCRE_ERROR_PARTIAL is returned as soon as a partial match is found, + If PCRE_PARTIAL_HARD is set for pcre_exec() or pcre[16|32]_exec(), + PCRE_ERROR_PARTIAL is returned as soon as a partial match is found, without continuing to search for possible complete matches. This option is "hard" because it prefers an earlier partial match over a later com- - plete match. For this reason, the assumption is made that the end of - the supplied subject string may not be the true end of the available + plete match. For this reason, the assumption is made that the end of + the supplied subject string may not be the true end of the available data, and so, if \z, \Z, \b, \B, or $ are encountered at the end of the - subject, the result is PCRE_ERROR_PARTIAL, provided that at least one + subject, the result is PCRE_ERROR_PARTIAL, provided that at least one character in the subject has been inspected. Setting PCRE_PARTIAL_HARD also affects the way UTF-8 and UTF-16 subject - strings are checked for validity. Normally, an invalid sequence causes - the error PCRE_ERROR_BADUTF8 or PCRE_ERROR_BADUTF16. However, in the - special case of a truncated character at the end of the subject, - PCRE_ERROR_SHORTUTF8 or PCRE_ERROR_SHORTUTF16 is returned when + strings are checked for validity. Normally, an invalid sequence causes + the error PCRE_ERROR_BADUTF8 or PCRE_ERROR_BADUTF16. However, in the + special case of a truncated character at the end of the subject, + PCRE_ERROR_SHORTUTF8 or PCRE_ERROR_SHORTUTF16 is returned when PCRE_PARTIAL_HARD is set. Comparing hard and soft partial matching - The difference between the two partial matching options can be illus- + The difference between the two partial matching options can be illus- trated by a pattern such as: /dog(sbody)?/ - This matches either "dog" or "dogsbody", greedily (that is, it prefers - the longer string if possible). If it is matched against the string - "dog" with PCRE_PARTIAL_SOFT, it yields a complete match for "dog". + This matches either "dog" or "dogsbody", greedily (that is, it prefers + the longer string if possible). If it is matched against the string + "dog" with PCRE_PARTIAL_SOFT, it yields a complete match for "dog". However, if PCRE_PARTIAL_HARD is set, the result is PCRE_ERROR_PARTIAL. - On the other hand, if the pattern is made ungreedy the result is dif- + On the other hand, if the pattern is made ungreedy the result is dif- ferent: /dog(sbody)??/ - In this case the result is always a complete match because that is - found first, and matching never continues after finding a complete + In this case the result is always a complete match because that is + found first, and matching never continues after finding a complete match. It might be easier to follow this explanation by thinking of the two patterns like this: /dog(sbody)?/ is the same as /dogsbody|dog/ /dog(sbody)??/ is the same as /dog|dogsbody/ - The second pattern will never match "dogsbody", because it will always + The second pattern will never match "dogsbody", because it will always find the shorter match first. -PARTIAL MATCHING USING pcre_dfa_exec() OR pcre16_dfa_exec() +PARTIAL MATCHING USING pcre_dfa_exec() OR pcre[16|32]_dfa_exec() The DFA functions move along the subject string character by character, - without backtracking, searching for all possible matches simultane- - ously. If the end of the subject is reached before the end of the pat- - tern, there is the possibility of a partial match, again provided that + without backtracking, searching for all possible matches simultane- + ously. If the end of the subject is reached before the end of the pat- + tern, there is the possibility of a partial match, again provided that at least one character has been inspected. - When PCRE_PARTIAL_SOFT is set, PCRE_ERROR_PARTIAL is returned only if - there have been no complete matches. Otherwise, the complete matches - are returned. However, if PCRE_PARTIAL_HARD is set, a partial match - takes precedence over any complete matches. The portion of the string - that was inspected when the longest partial match was found is set as + When PCRE_PARTIAL_SOFT is set, PCRE_ERROR_PARTIAL is returned only if + there have been no complete matches. Otherwise, the complete matches + are returned. However, if PCRE_PARTIAL_HARD is set, a partial match + takes precedence over any complete matches. The portion of the string + that was inspected when the longest partial match was found is set as the first matching string, provided there are at least two slots in the offsets vector. - Because the DFA functions always search for all possible matches, and - there is no difference between greedy and ungreedy repetition, their - behaviour is different from the standard functions when PCRE_PAR- - TIAL_HARD is set. Consider the string "dog" matched against the + Because the DFA functions always search for all possible matches, and + there is no difference between greedy and ungreedy repetition, their + behaviour is different from the standard functions when PCRE_PAR- + TIAL_HARD is set. Consider the string "dog" matched against the ungreedy pattern shown above: /dog(sbody)??/ - Whereas the standard functions stop as soon as they find the complete - match for "dog", the DFA functions also find the partial match for + Whereas the standard functions stop as soon as they find the complete + match for "dog", the DFA functions also find the partial match for "dogsbody", and so return that when PCRE_PARTIAL_HARD is set. PARTIAL MATCHING AND WORD BOUNDARIES - If a pattern ends with one of sequences \b or \B, which test for word - boundaries, partial matching with PCRE_PARTIAL_SOFT can give counter- + If a pattern ends with one of sequences \b or \B, which test for word + boundaries, partial matching with PCRE_PARTIAL_SOFT can give counter- intuitive results. Consider this pattern: /\bcat\b/ This matches "cat", provided there is a word boundary at either end. If the subject string is "the cat", the comparison of the final "t" with a - following character cannot take place, so a partial match is found. - However, normal matching carries on, and \b matches at the end of the - subject when the last character is a letter, so a complete match is - found. The result, therefore, is not PCRE_ERROR_PARTIAL. Using - PCRE_PARTIAL_HARD in this case does yield PCRE_ERROR_PARTIAL, because + following character cannot take place, so a partial match is found. + However, normal matching carries on, and \b matches at the end of the + subject when the last character is a letter, so a complete match is + found. The result, therefore, is not PCRE_ERROR_PARTIAL. Using + PCRE_PARTIAL_HARD in this case does yield PCRE_ERROR_PARTIAL, because then the partial match takes precedence. FORMERLY RESTRICTED PATTERNS For releases of PCRE prior to 8.00, because of the way certain internal - optimizations were implemented in the pcre_exec() function, the - PCRE_PARTIAL option (predecessor of PCRE_PARTIAL_SOFT) could not be - used with all patterns. From release 8.00 onwards, the restrictions no - longer apply, and partial matching with can be requested for any pat- + optimizations were implemented in the pcre_exec() function, the + PCRE_PARTIAL option (predecessor of PCRE_PARTIAL_SOFT) could not be + used with all patterns. From release 8.00 onwards, the restrictions no + longer apply, and partial matching with can be requested for any pat- tern. Items that were formerly restricted were repeated single characters and - repeated metasequences. If PCRE_PARTIAL was set for a pattern that did - not conform to the restrictions, pcre_exec() returned the error code - PCRE_ERROR_BADPARTIAL (-13). This error code is no longer in use. The - PCRE_INFO_OKPARTIAL call to pcre_fullinfo() to find out if a compiled + repeated metasequences. If PCRE_PARTIAL was set for a pattern that did + not conform to the restrictions, pcre_exec() returned the error code + PCRE_ERROR_BADPARTIAL (-13). This error code is no longer in use. The + PCRE_INFO_OKPARTIAL call to pcre_fullinfo() to find out if a compiled pattern can be used for partial matching now always returns 1. EXAMPLE OF PARTIAL MATCHING USING PCRETEST - If the escape sequence \P is present in a pcretest data line, the - PCRE_PARTIAL_SOFT option is used for the match. Here is a run of + If the escape sequence \P is present in a pcretest data line, the + PCRE_PARTIAL_SOFT option is used for the match. Here is a run of pcretest that uses the date example quoted above: re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/ @@ -7713,24 +8479,24 @@ EXAMPLE OF PARTIAL MATCHING USING PCRETEST data> j\P No match - The first data string is matched completely, so pcretest shows the - matched substrings. The remaining four strings do not match the com- + The first data string is matched completely, so pcretest shows the + matched substrings. The remaining four strings do not match the com- plete pattern, but the first two are partial matches. Similar output is obtained if DFA matching is used. - If the escape sequence \P is present more than once in a pcretest data + If the escape sequence \P is present more than once in a pcretest data line, the PCRE_PARTIAL_HARD option is set for the match. -MULTI-SEGMENT MATCHING WITH pcre_dfa_exec() OR pcre16_dfa_exec() +MULTI-SEGMENT MATCHING WITH pcre_dfa_exec() OR pcre[16|32]_dfa_exec() - When a partial match has been found using a DFA matching function, it - is possible to continue the match by providing additional subject data - and calling the function again with the same compiled regular expres- - sion, this time setting the PCRE_DFA_RESTART option. You must pass the + When a partial match has been found using a DFA matching function, it + is possible to continue the match by providing additional subject data + and calling the function again with the same compiled regular expres- + sion, this time setting the PCRE_DFA_RESTART option. You must pass the same working space as before, because this is where details of the pre- - vious partial match are stored. Here is an example using pcretest, - using the \R escape sequence to set the PCRE_DFA_RESTART option (\D + vious partial match are stored. Here is an example using pcretest, + using the \R escape sequence to set the PCRE_DFA_RESTART option (\D specifies the use of the DFA matching function): re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/ @@ -7739,48 +8505,48 @@ MULTI-SEGMENT MATCHING WITH pcre_dfa_exec() OR pcre16_dfa_exec() data> n05\R\D 0: n05 - The first call has "23ja" as the subject, and requests partial match- - ing; the second call has "n05" as the subject for the continued - (restarted) match. Notice that when the match is complete, only the - last part is shown; PCRE does not retain the previously partially- - matched string. It is up to the calling program to do that if it needs + The first call has "23ja" as the subject, and requests partial match- + ing; the second call has "n05" as the subject for the continued + (restarted) match. Notice that when the match is complete, only the + last part is shown; PCRE does not retain the previously partially- + matched string. It is up to the calling program to do that if it needs to. - You can set the PCRE_PARTIAL_SOFT or PCRE_PARTIAL_HARD options with - PCRE_DFA_RESTART to continue partial matching over multiple segments. - This facility can be used to pass very long subject strings to the DFA + You can set the PCRE_PARTIAL_SOFT or PCRE_PARTIAL_HARD options with + PCRE_DFA_RESTART to continue partial matching over multiple segments. + This facility can be used to pass very long subject strings to the DFA matching functions. -MULTI-SEGMENT MATCHING WITH pcre_exec() OR pcre16_exec() +MULTI-SEGMENT MATCHING WITH pcre_exec() OR pcre[16|32]_exec() - From release 8.00, the standard matching functions can also be used to + From release 8.00, the standard matching functions can also be used to do multi-segment matching. Unlike the DFA functions, it is not possible - to restart the previous match with a new segment of data. Instead, new + to restart the previous match with a new segment of data. Instead, new data must be added to the previous subject string, and the entire match - re-run, starting from the point where the partial match occurred. Ear- + re-run, starting from the point where the partial match occurred. Ear- lier data can be discarded. - It is best to use PCRE_PARTIAL_HARD in this situation, because it does - not treat the end of a segment as the end of the subject when matching - \z, \Z, \b, \B, and $. Consider an unanchored pattern that matches + It is best to use PCRE_PARTIAL_HARD in this situation, because it does + not treat the end of a segment as the end of the subject when matching + \z, \Z, \b, \B, and $. Consider an unanchored pattern that matches dates: re> /\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d/ data> The date is 23ja\P\P Partial match: 23ja - At this stage, an application could discard the text preceding "23ja", - add on text from the next segment, and call the matching function - again. Unlike the DFA matching functions, the entire matching string - must always be available, and the complete matching process occurs for + At this stage, an application could discard the text preceding "23ja", + add on text from the next segment, and call the matching function + again. Unlike the DFA matching functions, the entire matching string + must always be available, and the complete matching process occurs for each call, so more memory and more processing time is needed. - Note: If the pattern contains lookbehind assertions, or \K, or starts + Note: If the pattern contains lookbehind assertions, or \K, or starts with \b or \B, the string that is returned for a partial match includes - characters that precede the partially matched string itself, because - these must be retained when adding on more characters for a subsequent - matching attempt. However, in some cases you may need to retain even + characters that precede the partially matched string itself, because + these must be retained when adding on more characters for a subsequent + matching attempt. However, in some cases you may need to retain even earlier characters, as discussed in the next section. @@ -7790,25 +8556,25 @@ ISSUES WITH MULTI-SEGMENT MATCHING whichever matching function is used. 1. If the pattern contains a test for the beginning of a line, you need - to pass the PCRE_NOTBOL option when the subject string for any call - does start at the beginning of a line. There is also a PCRE_NOTEOL + to pass the PCRE_NOTBOL option when the subject string for any call + does start at the beginning of a line. There is also a PCRE_NOTEOL option, but in practice when doing multi-segment matching you should be using PCRE_PARTIAL_HARD, which includes the effect of PCRE_NOTEOL. - 2. Lookbehind assertions that have already been obeyed are catered for + 2. Lookbehind assertions that have already been obeyed are catered for in the offsets that are returned for a partial match. However a lookbe- - hind assertion later in the pattern could require even earlier charac- - ters to be inspected. You can handle this case by using the + hind assertion later in the pattern could require even earlier charac- + ters to be inspected. You can handle this case by using the PCRE_INFO_MAXLOOKBEHIND option of the pcre_fullinfo() or - pcre16_fullinfo() functions to obtain the length of the largest lookbe- - hind in the pattern. This length is given in characters, not bytes. If - you always retain at least that many characters before the partially - matched string, all should be well. (Of course, near the start of the - subject, fewer characters may be present; in that case all characters - should be retained.) - - 3. Because a partial match must always contain at least one character, - what might be considered a partial match of an empty string actually + pcre[16|32]_fullinfo() functions to obtain the length of the largest + lookbehind in the pattern. This length is given in characters, not + bytes. If you always retain at least that many characters before the + partially matched string, all should be well. (Of course, near the + start of the subject, fewer characters may be present; in that case all + characters should be retained.) + + 3. Because a partial match must always contain at least one character, + what might be considered a partial match of an empty string actually gives a "no match" result. For example: re> /c(?<=abc)x/ @@ -7816,19 +8582,19 @@ ISSUES WITH MULTI-SEGMENT MATCHING No match If the next segment begins "cx", a match should be found, but this will - only happen if characters from the previous segment are retained. For - this reason, a "no match" result should be interpreted as "partial + only happen if characters from the previous segment are retained. For + this reason, a "no match" result should be interpreted as "partial match of an empty string" when the pattern contains lookbehinds. - 4. Matching a subject string that is split into multiple segments may - not always produce exactly the same result as matching over one single - long string, especially when PCRE_PARTIAL_SOFT is used. The section - "Partial Matching and Word Boundaries" above describes an issue that - arises if the pattern ends with \b or \B. Another kind of difference - may occur when there are multiple matching possibilities, because (for - PCRE_PARTIAL_SOFT) a partial match result is given only when there are + 4. Matching a subject string that is split into multiple segments may + not always produce exactly the same result as matching over one single + long string, especially when PCRE_PARTIAL_SOFT is used. The section + "Partial Matching and Word Boundaries" above describes an issue that + arises if the pattern ends with \b or \B. Another kind of difference + may occur when there are multiple matching possibilities, because (for + PCRE_PARTIAL_SOFT) a partial match result is given only when there are no completed matches. This means that as soon as the shortest match has - been found, continuation to a new subject segment is no longer possi- + been found, continuation to a new subject segment is no longer possi- ble. Consider again this pcretest example: re> /dog(sbody)?/ @@ -7842,18 +8608,18 @@ ISSUES WITH MULTI-SEGMENT MATCHING 0: dogsbody 1: dog - The first data line passes the string "dogsb" to a standard matching - function, setting the PCRE_PARTIAL_SOFT option. Although the string is - a partial match for "dogsbody", the result is not PCRE_ERROR_PARTIAL, - because the shorter string "dog" is a complete match. Similarly, when - the subject is presented to a DFA matching function in several parts - ("do" and "gsb" being the first two) the match stops when "dog" has - been found, and it is not possible to continue. On the other hand, if - "dogsbody" is presented as a single string, a DFA matching function + The first data line passes the string "dogsb" to a standard matching + function, setting the PCRE_PARTIAL_SOFT option. Although the string is + a partial match for "dogsbody", the result is not PCRE_ERROR_PARTIAL, + because the shorter string "dog" is a complete match. Similarly, when + the subject is presented to a DFA matching function in several parts + ("do" and "gsb" being the first two) the match stops when "dog" has + been found, and it is not possible to continue. On the other hand, if + "dogsbody" is presented as a single string, a DFA matching function finds both matches. - Because of these problems, it is best to use PCRE_PARTIAL_HARD when - matching multi-segment data. The example above then behaves differ- + Because of these problems, it is best to use PCRE_PARTIAL_HARD when + matching multi-segment data. The example above then behaves differ- ently: re> /dog(sbody)?/ @@ -7865,25 +8631,25 @@ ISSUES WITH MULTI-SEGMENT MATCHING Partial match: gsb 5. Patterns that contain alternatives at the top level which do not all - start with the same pattern item may not work as expected when + start with the same pattern item may not work as expected when PCRE_DFA_RESTART is used. For example, consider this pattern: 1234|3789 - If the first part of the subject is "ABC123", a partial match of the - first alternative is found at offset 3. There is no partial match for + If the first part of the subject is "ABC123", a partial match of the + first alternative is found at offset 3. There is no partial match for the second alternative, because such a match does not start at the same - point in the subject string. Attempting to continue with the string - "7890" does not yield a match because only those alternatives that - match at one point in the subject are remembered. The problem arises - because the start of the second alternative matches within the first - alternative. There is no problem with anchored patterns or patterns + point in the subject string. Attempting to continue with the string + "7890" does not yield a match because only those alternatives that + match at one point in the subject are remembered. The problem arises + because the start of the second alternative matches within the first + alternative. There is no problem with anchored patterns or patterns such as: 1234|ABCD - where no string can be a partial match for both alternatives. This is - not a problem if a standard matching function is used, because the + where no string can be a partial match for both alternatives. This is + not a problem if a standard matching function is used, because the entire match has to be rerun each time: re> /1234|3789/ @@ -7893,10 +8659,10 @@ ISSUES WITH MULTI-SEGMENT MATCHING 0: 3789 Of course, instead of using PCRE_DFA_RESTART, the same technique of re- - running the entire match can also be used with the DFA matching func- - tions. Another possibility is to work with two buffers. If a partial - match at offset n in the first buffer is followed by "no match" when - PCRE_DFA_RESTART is used on the second buffer, you can then try a new + running the entire match can also be used with the DFA matching func- + tions. Another possibility is to work with two buffers. If a partial + match at offset n in the first buffer is followed by "no match" when + PCRE_DFA_RESTART is used on the second buffer, you can then try a new match starting at offset n+1 in the first buffer. @@ -7909,11 +8675,11 @@ AUTHOR REVISION - Last updated: 24 February 2012 + Last updated: 24 June 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCREPRECOMPILE(3) PCREPRECOMPILE(3) @@ -7934,10 +8700,10 @@ SAVING AND RE-USING PRECOMPILED PCRE PATTERNS If you save compiled patterns to a file, you can copy them to a differ- ent host and run them there. If the two hosts have different endianness - (byte order), you should run the pcre[16]_pattern_to_host_byte_order() - function on the new host before trying to match the pattern. The match- - ing functions return PCRE_ERROR_BADENDIANNESS if they detect a pattern - with the wrong endianness. + (byte order), you should run the pcre[16|32]_pat- + tern_to_host_byte_order() function on the new host before trying to + match the pattern. The matching functions return PCRE_ERROR_BADENDIAN- + NESS if they detect a pattern with the wrong endianness. Compiling regular expressions with one version of PCRE for use with a different version is not guaranteed to work and may cause crashes, and @@ -7947,13 +8713,13 @@ SAVING AND RE-USING PRECOMPILED PCRE PATTERNS SAVING A COMPILED PATTERN - The value returned by pcre[16]_compile() points to a single block of + The value returned by pcre[16|32]_compile() points to a single block of memory that holds the compiled pattern and associated data. You can - find the length of this block in bytes by calling pcre[16]_fullinfo() - with an argument of PCRE_INFO_SIZE. You can then save the data in any - appropriate manner. Here is sample code for the 8-bit library that com- - piles a pattern and writes it to a file. It assumes that the variable - fd refers to a file that is open for output: + find the length of this block in bytes by calling + pcre[16|32]_fullinfo() with an argument of PCRE_INFO_SIZE. You can then + save the data in any appropriate manner. Here is sample code for the + 8-bit library that compiles a pattern and writes it to a file. It + assumes that the variable fd refers to a file that is open for output: int erroroffset, rc, size; char *error; @@ -7988,30 +8754,30 @@ SAVING A COMPILED PATTERN the PCRE_STUDY_JIT_COMPILE was used, the just-in-time data that is cre- ated cannot be saved because it is too dependent on the current envi- ronment. When studying generates additional information, - pcre[16]_study() returns a pointer to a pcre[16]_extra data block. Its - format is defined in the section on matching a pattern in the pcreapi - documentation. The study_data field points to the binary study data, - and this is what you must save (not the pcre[16]_extra block itself). - The length of the study data can be obtained by calling - pcre[16]_fullinfo() with an argument of PCRE_INFO_STUDYSIZE. Remember - to check that pcre[16]_study() did return a non-NULL value before try- - ing to save the study data. + pcre[16|32]_study() returns a pointer to a pcre[16|32]_extra data + block. Its format is defined in the section on matching a pattern in + the pcreapi documentation. The study_data field points to the binary + study data, and this is what you must save (not the pcre[16|32]_extra + block itself). The length of the study data can be obtained by calling + pcre[16|32]_fullinfo() with an argument of PCRE_INFO_STUDYSIZE. Remem- + ber to check that pcre[16|32]_study() did return a non-NULL value + before trying to save the study data. RE-USING A PRECOMPILED PATTERN Re-using a precompiled pattern is straightforward. Having reloaded it - into main memory, called pcre[16]_pattern_to_host_byte_order() if nec- - essary, you pass its pointer to pcre[16]_exec() or pcre[16]_dfa_exec() - in the usual way. + into main memory, called pcre[16|32]_pattern_to_host_byte_order() if + necessary, you pass its pointer to pcre[16|32]_exec() or + pcre[16|32]_dfa_exec() in the usual way. However, if you passed a pointer to custom character tables when the - pattern was compiled (the tableptr argument of pcre[16]_compile()), you - must now pass a similar pointer to pcre[16]_exec() or - pcre[16]_dfa_exec(), because the value saved with the compiled pattern - will obviously be nonsense. A field in a pcre[16]_extra() block is used - to pass this data, as described in the section on matching a pattern in - the pcreapi documentation. + pattern was compiled (the tableptr argument of pcre[16|32]_compile()), + you must now pass a similar pointer to pcre[16|32]_exec() or + pcre[16|32]_dfa_exec(), because the value saved with the compiled pat- + tern will obviously be nonsense. A field in a pcre[16|32]_extra() block + is used to pass this data, as described in the section on matching a + pattern in the pcreapi documentation. If you did not provide custom character tables when the pattern was compiled, the pointer in the compiled pattern is NULL, which causes the @@ -8019,10 +8785,10 @@ RE-USING A PRECOMPILED PATTERN to take any special action at run time in this case. If you saved study data with the compiled pattern, you need to create - your own pcre[16]_extra data block and set the study_data field to + your own pcre[16|32]_extra data block and set the study_data field to point to the reloaded study data. You must also set the PCRE_EXTRA_STUDY_DATA bit in the flags field to indicate that study - data is present. Then pass the pcre[16]_extra block to the matching + data is present. Then pass the pcre[16|32]_extra block to the matching function in the usual way. If the pattern was studied for just-in-time optimization, that data cannot be saved, and so is lost by a save/restore cycle. @@ -8044,11 +8810,11 @@ AUTHOR REVISION - Last updated: 10 January 2012 + Last updated: 24 June 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCREPERFORM(3) PCREPERFORM(3) @@ -8115,30 +8881,30 @@ COMPILED PATTERN MEMORY USAGE STACK USAGE AT RUN TIME - When pcre_exec() or pcre16_exec() is used for matching, certain kinds - of pattern can cause it to use large amounts of the process stack. In - some environments the default process stack is quite small, and if it - runs out the result is often SIGSEGV. This issue is probably the most - frequently raised problem with PCRE. Rewriting your pattern can often - help. The pcrestack documentation discusses this issue in detail. + When pcre_exec() or pcre[16|32]_exec() is used for matching, certain + kinds of pattern can cause it to use large amounts of the process + stack. In some environments the default process stack is quite small, + and if it runs out the result is often SIGSEGV. This issue is probably + the most frequently raised problem with PCRE. Rewriting your pattern + can often help. The pcrestack documentation discusses this issue in + detail. PROCESSING TIME - Certain items in regular expression patterns are processed more effi- + Certain items in regular expression patterns are processed more effi- ciently than others. It is more efficient to use a character class like - [aeiou] than a set of single-character alternatives such as - (a|e|i|o|u). In general, the simplest construction that provides the + [aeiou] than a set of single-character alternatives such as + (a|e|i|o|u). In general, the simplest construction that provides the required behaviour is usually the most efficient. Jeffrey Friedl's book - contains a lot of useful general discussion about optimizing regular - expressions for efficient performance. This document contains a few + contains a lot of useful general discussion about optimizing regular + expressions for efficient performance. This document contains a few observations about PCRE. - Using Unicode character properties (the \p, \P, and \X escapes) is - slow, because PCRE has to scan a structure that contains data for over - fifteen thousand characters whenever it needs a character's property. - If you can find an alternative pattern that does not use character - properties, it will probably be faster. + Using Unicode character properties (the \p, \P, and \X escapes) is + slow, because PCRE has to use a multi-stage table lookup whenever it + needs a character's property. If you can find an alternative pattern + that does not use character properties, it will probably be faster. By default, the escape sequences \b, \d, \s, and \w, and the POSIX character classes such as [:alpha:] do not use Unicode properties, @@ -8214,11 +8980,11 @@ AUTHOR REVISION - Last updated: 09 January 2012 + Last updated: 25 August 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCREPOSIX(3) PCREPOSIX(3) @@ -8247,49 +9013,50 @@ DESCRIPTION This set of functions provides a POSIX-style API for the PCRE regular expression 8-bit library. See the pcreapi documentation for a descrip- tion of PCRE's native API, which contains much additional functional- - ity. There is no POSIX-style wrapper for PCRE's 16-bit library. + ity. There is no POSIX-style wrapper for PCRE's 16-bit and 32-bit + library. The functions described here are just wrapper functions that ultimately call the PCRE native API. Their prototypes are defined in the - pcreposix.h header file, and on Unix systems the library itself is - called pcreposix.a, so can be accessed by adding -lpcreposix to the - command for linking an application that uses them. Because the POSIX + pcreposix.h header file, and on Unix systems the library itself is + called pcreposix.a, so can be accessed by adding -lpcreposix to the + command for linking an application that uses them. Because the POSIX functions call the native ones, it is also necessary to add -lpcre. - I have implemented only those POSIX option bits that can be reasonably - mapped to PCRE native options. In addition, the option REG_EXTENDED is - defined with the value zero. This has no effect, but since programs - that are written to the POSIX interface often use it, this makes it - easier to slot in PCRE as a replacement library. Other POSIX options + I have implemented only those POSIX option bits that can be reasonably + mapped to PCRE native options. In addition, the option REG_EXTENDED is + defined with the value zero. This has no effect, but since programs + that are written to the POSIX interface often use it, this makes it + easier to slot in PCRE as a replacement library. Other POSIX options are not even defined. - There are also some other options that are not defined by POSIX. These + There are also some other options that are not defined by POSIX. These have been added at the request of users who want to make use of certain PCRE-specific features via the POSIX calling interface. - When PCRE is called via these functions, it is only the API that is - POSIX-like in style. The syntax and semantics of the regular expres- - sions themselves are still those of Perl, subject to the setting of - various PCRE options, as described below. "POSIX-like in style" means - that the API approximates to the POSIX definition; it is not fully - POSIX-compatible, and in multi-byte encoding domains it is probably + When PCRE is called via these functions, it is only the API that is + POSIX-like in style. The syntax and semantics of the regular expres- + sions themselves are still those of Perl, subject to the setting of + various PCRE options, as described below. "POSIX-like in style" means + that the API approximates to the POSIX definition; it is not fully + POSIX-compatible, and in multi-byte encoding domains it is probably even less compatible. - The header for these functions is supplied as pcreposix.h to avoid any - potential clash with other POSIX libraries. It can, of course, be + The header for these functions is supplied as pcreposix.h to avoid any + potential clash with other POSIX libraries. It can, of course, be renamed or aliased as regex.h, which is the "correct" name. It provides - two structure types, regex_t for compiled internal forms, and reg- - match_t for returning captured substrings. It also defines some con- - stants whose names start with "REG_"; these are used for setting + two structure types, regex_t for compiled internal forms, and reg- + match_t for returning captured substrings. It also defines some con- + stants whose names start with "REG_"; these are used for setting options and identifying error codes. COMPILING A PATTERN - The function regcomp() is called to compile a pattern into an internal - form. The pattern is a C string terminated by a binary zero, and is - passed in the argument pattern. The preg argument is a pointer to a - regex_t structure that is used as a base for storing information about + The function regcomp() is called to compile a pattern into an internal + form. The pattern is a C string terminated by a binary zero, and is + passed in the argument pattern. The preg argument is a pointer to a + regex_t structure that is used as a base for storing information about the compiled regular expression. The argument cflags is either zero, or contains one or more of the bits @@ -8303,58 +9070,58 @@ COMPILING A PATTERN REG_ICASE - The PCRE_CASELESS option is set when the regular expression is passed + The PCRE_CASELESS option is set when the regular expression is passed for compilation to the native function. REG_NEWLINE - The PCRE_MULTILINE option is set when the regular expression is passed - for compilation to the native function. Note that this does not mimic - the defined POSIX behaviour for REG_NEWLINE (see the following sec- + The PCRE_MULTILINE option is set when the regular expression is passed + for compilation to the native function. Note that this does not mimic + the defined POSIX behaviour for REG_NEWLINE (see the following sec- tion). REG_NOSUB - The PCRE_NO_AUTO_CAPTURE option is set when the regular expression is + The PCRE_NO_AUTO_CAPTURE option is set when the regular expression is passed for compilation to the native function. In addition, when a pat- - tern that is compiled with this flag is passed to regexec() for match- - ing, the nmatch and pmatch arguments are ignored, and no captured + tern that is compiled with this flag is passed to regexec() for match- + ing, the nmatch and pmatch arguments are ignored, and no captured strings are returned. REG_UCP - The PCRE_UCP option is set when the regular expression is passed for - compilation to the native function. This causes PCRE to use Unicode - properties when matchine \d, \w, etc., instead of just recognizing + The PCRE_UCP option is set when the regular expression is passed for + compilation to the native function. This causes PCRE to use Unicode + properties when matchine \d, \w, etc., instead of just recognizing ASCII values. Note that REG_UTF8 is not part of the POSIX standard. REG_UNGREEDY - The PCRE_UNGREEDY option is set when the regular expression is passed - for compilation to the native function. Note that REG_UNGREEDY is not + The PCRE_UNGREEDY option is set when the regular expression is passed + for compilation to the native function. Note that REG_UNGREEDY is not part of the POSIX standard. REG_UTF8 - The PCRE_UTF8 option is set when the regular expression is passed for - compilation to the native function. This causes the pattern itself and - all data strings used for matching it to be treated as UTF-8 strings. + The PCRE_UTF8 option is set when the regular expression is passed for + compilation to the native function. This causes the pattern itself and + all data strings used for matching it to be treated as UTF-8 strings. Note that REG_UTF8 is not part of the POSIX standard. - In the absence of these flags, no options are passed to the native - function. This means the the regex is compiled with PCRE default - semantics. In particular, the way it handles newline characters in the - subject string is the Perl way, not the POSIX way. Note that setting - PCRE_MULTILINE has only some of the effects specified for REG_NEWLINE. - It does not affect the way newlines are matched by . (they are not) or + In the absence of these flags, no options are passed to the native + function. This means the the regex is compiled with PCRE default + semantics. In particular, the way it handles newline characters in the + subject string is the Perl way, not the POSIX way. Note that setting + PCRE_MULTILINE has only some of the effects specified for REG_NEWLINE. + It does not affect the way newlines are matched by . (they are not) or by a negative class such as [^a] (they are). - The yield of regcomp() is zero on success, and non-zero otherwise. The + The yield of regcomp() is zero on success, and non-zero otherwise. The preg structure is filled in on success, and one member of the structure - is public: re_nsub contains the number of capturing subpatterns in the + is public: re_nsub contains the number of capturing subpatterns in the regular expression. Various error codes are defined in the header file. - NOTE: If the yield of regcomp() is non-zero, you must not attempt to + NOTE: If the yield of regcomp() is non-zero, you must not attempt to use the contents of the preg structure. If, for example, you pass it to regexec(), the result is undefined and your program is likely to crash. @@ -8362,9 +9129,9 @@ COMPILING A PATTERN MATCHING NEWLINE CHARACTERS This area is not simple, because POSIX and Perl take different views of - things. It is not possible to get PCRE to obey POSIX semantics, but - then PCRE was never intended to be a POSIX engine. The following table - lists the different possibilities for matching newline characters in + things. It is not possible to get PCRE to obey POSIX semantics, but + then PCRE was never intended to be a POSIX engine. The following table + lists the different possibilities for matching newline characters in PCRE: Default Change with @@ -8386,19 +9153,19 @@ MATCHING NEWLINE CHARACTERS ^ matches \n in middle no REG_NEWLINE PCRE's behaviour is the same as Perl's, except that there is no equiva- - lent for PCRE_DOLLAR_ENDONLY in Perl. In both PCRE and Perl, there is + lent for PCRE_DOLLAR_ENDONLY in Perl. In both PCRE and Perl, there is no way to stop newline from matching [^a]. - The default POSIX newline handling can be obtained by setting - PCRE_DOTALL and PCRE_DOLLAR_ENDONLY, but there is no way to make PCRE + The default POSIX newline handling can be obtained by setting + PCRE_DOTALL and PCRE_DOLLAR_ENDONLY, but there is no way to make PCRE behave exactly as for the REG_NEWLINE action. MATCHING A PATTERN - The function regexec() is called to match a compiled pattern preg - against a given string, which is by default terminated by a zero byte - (but see REG_STARTEND below), subject to the options in eflags. These + The function regexec() is called to match a compiled pattern preg + against a given string, which is by default terminated by a zero byte + (but see REG_STARTEND below), subject to the options in eflags. These can be: REG_NOTBOL @@ -8420,17 +9187,17 @@ MATCHING A PATTERN REG_STARTEND - The string is considered to start at string + pmatch[0].rm_so and to - have a terminating NUL located at string + pmatch[0].rm_eo (there need - not actually be a NUL at that location), regardless of the value of - nmatch. This is a BSD extension, compatible with but not specified by - IEEE Standard 1003.2 (POSIX.2), and should be used with caution in + The string is considered to start at string + pmatch[0].rm_so and to + have a terminating NUL located at string + pmatch[0].rm_eo (there need + not actually be a NUL at that location), regardless of the value of + nmatch. This is a BSD extension, compatible with but not specified by + IEEE Standard 1003.2 (POSIX.2), and should be used with caution in software intended to be portable to other systems. Note that a non-zero rm_so does not imply REG_NOTBOL; REG_STARTEND affects only the location of the string, not how it is matched. - If the pattern was compiled with the REG_NOSUB flag, no data about any - matched strings is returned. The nmatch and pmatch arguments of + If the pattern was compiled with the REG_NOSUB flag, no data about any + matched strings is returned. The nmatch and pmatch arguments of regexec() are ignored. If the value of nmatch is zero, or if the value pmatch is NULL, no data @@ -8438,34 +9205,34 @@ MATCHING A PATTERN Otherwise,the portion of the string that was matched, and also any cap- tured substrings, are returned via the pmatch argument, which points to - an array of nmatch structures of type regmatch_t, containing the mem- - bers rm_so and rm_eo. These contain the offset to the first character - of each substring and the offset to the first character after the end - of each substring, respectively. The 0th element of the vector relates - to the entire portion of string that was matched; subsequent elements - relate to the capturing subpatterns of the regular expression. Unused + an array of nmatch structures of type regmatch_t, containing the mem- + bers rm_so and rm_eo. These contain the offset to the first character + of each substring and the offset to the first character after the end + of each substring, respectively. The 0th element of the vector relates + to the entire portion of string that was matched; subsequent elements + relate to the capturing subpatterns of the regular expression. Unused entries in the array have both structure members set to -1. - A successful match yields a zero return; various error codes are - defined in the header file, of which REG_NOMATCH is the "expected" + A successful match yields a zero return; various error codes are + defined in the header file, of which REG_NOMATCH is the "expected" failure code. ERROR MESSAGES The regerror() function maps a non-zero errorcode from either regcomp() - or regexec() to a printable message. If preg is not NULL, the error + or regexec() to a printable message. If preg is not NULL, the error should have arisen from the use of that structure. A message terminated - by a binary zero is placed in errbuf. The length of the message, - including the zero, is limited to errbuf_size. The yield of the func- + by a binary zero is placed in errbuf. The length of the message, + including the zero, is limited to errbuf_size. The yield of the func- tion is the size of buffer needed to hold the whole message. MEMORY USAGE - Compiling a regular expression causes memory to be allocated and asso- - ciated with the preg structure. The function regfree() frees all such - memory, after which preg may no longer be used as a compiled expres- + Compiling a regular expression causes memory to be allocated and asso- + ciated with the preg structure. The function regfree() frees all such + memory, after which preg may no longer be used as a compiled expres- sion. @@ -8481,8 +9248,8 @@ REVISION Last updated: 09 January 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRECPP(3) PCRECPP(3) @@ -8501,13 +9268,14 @@ DESCRIPTION functionality was added by Giuseppe Maxia. This brief man page was con- structed from the notes in the pcrecpp.h file, which should be con- sulted for further details. Note that the C++ wrapper supports only the - original 8-bit PCRE library. There is no 16-bit support at present. + original 8-bit PCRE library. There is no 16-bit or 32-bit support at + present. MATCHING INTERFACE - The "FullMatch" operation checks that supplied text matches a supplied - pattern exactly. If pointer arguments are supplied, it copies matched + The "FullMatch" operation checks that supplied text matches a supplied + pattern exactly. If pointer arguments are supplied, it copies matched sub-strings that match sub-patterns into them. Example: successful match @@ -8521,10 +9289,10 @@ MATCHING INTERFACE Example: creating a temporary RE object: pcrecpp::RE("h.*o").FullMatch("hello"); - You can pass in a "const char*" or a "string" for "text". The examples - below tend to use a const char*. You can, as in the different examples - above, store the RE object explicitly in a variable or use a temporary - RE object. The examples below use one mode or the other arbitrarily. + You can pass in a "const char*" or a "string" for "text". The examples + below tend to use a const char*. You can, as in the different examples + above, store the RE object explicitly in a variable or use a temporary + RE object. The examples below use one mode or the other arbitrarily. Either could correctly be used for any of these examples. You must supply extra pointer arguments to extract matched subpieces. @@ -8550,7 +9318,7 @@ MATCHING INTERFACE Example: fails because string cannot be stored in integer !pcrecpp::RE("(.*)").FullMatch("ruby", &i); - The provided pointer arguments can be pointers to any scalar numeric + The provided pointer arguments can be pointers to any scalar numeric type, or one of: string (matched piece is copied to string) @@ -8558,7 +9326,7 @@ MATCHING INTERFACE T (where "bool T::ParseFrom(const char*, int)" exists) NULL (the corresponding matched sub-pattern is not copied) - The function returns true iff all of the following conditions are sat- + The function returns true iff all of the following conditions are sat- isfied: a. "text" matches "pattern" exactly; @@ -8573,41 +9341,41 @@ MATCHING INTERFACE number of sub-patterns, "i"th captured sub-pattern is ignored. - CAVEAT: An optional sub-pattern that does not exist in the matched - string is assigned the empty string. Therefore, the following will + CAVEAT: An optional sub-pattern that does not exist in the matched + string is assigned the empty string. Therefore, the following will return false (because the empty string is not a valid number): int number; pcrecpp::RE::FullMatch("abc", "[a-z]+(\\d+)?", &number); - The matching interface supports at most 16 arguments per call. If you - need more, consider using the more general interface + The matching interface supports at most 16 arguments per call. If you + need more, consider using the more general interface pcrecpp::RE::DoMatch. See pcrecpp.h for the signature for DoMatch. - NOTE: Do not use no_arg, which is used internally to mark the end of a - list of optional arguments, as a placeholder for missing arguments, as + NOTE: Do not use no_arg, which is used internally to mark the end of a + list of optional arguments, as a placeholder for missing arguments, as this can lead to segfaults. QUOTING METACHARACTERS - You can use the "QuoteMeta" operation to insert backslashes before all - potentially meaningful characters in a string. The returned string, + You can use the "QuoteMeta" operation to insert backslashes before all + potentially meaningful characters in a string. The returned string, used as a regular expression, will exactly match the original string. Example: string quoted = RE::QuoteMeta(unquoted); - Note that it's legal to escape a character even if it has no special - meaning in a regular expression -- so this function does that. (This - also makes it identical to the perl function of the same name; see - "perldoc -f quotemeta".) For example, "1.5-2.0?" becomes + Note that it's legal to escape a character even if it has no special + meaning in a regular expression -- so this function does that. (This + also makes it identical to the perl function of the same name; see + "perldoc -f quotemeta".) For example, "1.5-2.0?" becomes "1\.5\-2\.0\?". PARTIAL MATCHES - You can use the "PartialMatch" operation when you want the pattern to + You can use the "PartialMatch" operation when you want the pattern to match any substring of the text. Example: simple search for a string: @@ -8622,13 +9390,13 @@ PARTIAL MATCHES UTF-8 AND THE MATCHING INTERFACE - By default, pattern and text are plain text, one byte per character. - The UTF8 flag, passed to the constructor, causes both pattern and + By default, pattern and text are plain text, one byte per character. + The UTF8 flag, passed to the constructor, causes both pattern and string to be treated as UTF-8 text, still a byte stream but potentially - multiple bytes per character. In practice, the text is likelier to be - UTF-8 than the pattern, but the match returned may depend on the UTF8 - flag, so always use it when matching UTF8 text. For example, "." will - match one byte normally but with UTF8 set may match up to three bytes + multiple bytes per character. In practice, the text is likelier to be + UTF-8 than the pattern, but the match returned may depend on the UTF8 + flag, so always use it when matching UTF8 text. For example, "." will + match one byte normally but with UTF8 set may match up to three bytes of a multi-byte character. Example: @@ -8647,9 +9415,9 @@ UTF-8 AND THE MATCHING INTERFACE PASSING MODIFIERS TO THE REGULAR EXPRESSION ENGINE - PCRE defines some modifiers to change the behavior of the regular - expression engine. The C++ wrapper defines an auxiliary class, - RE_Options, as a vehicle to pass such modifiers to a RE class. Cur- + PCRE defines some modifiers to change the behavior of the regular + expression engine. The C++ wrapper defines an auxiliary class, + RE_Options, as a vehicle to pass such modifiers to a RE class. Cur- rently, the following modifiers are supported: modifier description Perl corresponding @@ -8664,15 +9432,15 @@ PASSING MODIFIERS TO THE REGULAR EXPRESSION ENGINE PCRE_UNGREEDY reverses * and *? N/A PCRE_NO_AUTO_CAPTURE disables capturing parens N/A (*) - (*) Both Perl and PCRE allow non capturing parentheses by means of the - "?:" modifier within the pattern itself. e.g. (?:ab|cd) does not cap- + (*) Both Perl and PCRE allow non capturing parentheses by means of the + "?:" modifier within the pattern itself. e.g. (?:ab|cd) does not cap- ture, while (ab|cd) does. - For a full account on how each modifier works, please check the PCRE + For a full account on how each modifier works, please check the PCRE API reference page. - For each modifier, there are two member functions whose name is made - out of the modifier in lowercase, without the "PCRE_" prefix. For + For each modifier, there are two member functions whose name is made + out of the modifier in lowercase, without the "PCRE_" prefix. For instance, PCRE_CASELESS is handled by bool caseless() @@ -8682,18 +9450,18 @@ PASSING MODIFIERS TO THE REGULAR EXPRESSION ENGINE RE_Options & set_caseless(bool) which sets or unsets the modifier. Moreover, PCRE_EXTRA_MATCH_LIMIT can - be accessed through the set_match_limit() and match_limit() member - functions. Setting match_limit to a non-zero value will limit the exe- - cution of pcre to keep it from doing bad things like blowing the stack - or taking an eternity to return a result. A value of 5000 is good - enough to stop stack blowup in a 2MB thread stack. Setting match_limit - to zero disables match limiting. Alternatively, you can call - match_limit_recursion() which uses PCRE_EXTRA_MATCH_LIMIT_RECURSION to - limit how much PCRE recurses. match_limit() limits the number of + be accessed through the set_match_limit() and match_limit() member + functions. Setting match_limit to a non-zero value will limit the exe- + cution of pcre to keep it from doing bad things like blowing the stack + or taking an eternity to return a result. A value of 5000 is good + enough to stop stack blowup in a 2MB thread stack. Setting match_limit + to zero disables match limiting. Alternatively, you can call + match_limit_recursion() which uses PCRE_EXTRA_MATCH_LIMIT_RECURSION to + limit how much PCRE recurses. match_limit() limits the number of matches PCRE does; match_limit_recursion() limits the depth of internal recursion, and therefore the amount of stack that is used. - Normally, to pass one or more modifiers to a RE class, you declare a + Normally, to pass one or more modifiers to a RE class, you declare a RE_Options object, set the appropriate options, and pass this object to a RE constructor. Example: @@ -8702,8 +9470,8 @@ PASSING MODIFIERS TO THE REGULAR EXPRESSION ENGINE if (RE("HELLO", opt).PartialMatch("hello world")) ... RE_options has two constructors. The default constructor takes no argu- - ments and creates a set of flags that are off by default. The optional - parameter option_flags is to facilitate transfer of legacy code from C + ments and creates a set of flags that are off by default. The optional + parameter option_flags is to facilitate transfer of legacy code from C programs. This lets you do RE(pattern, @@ -8717,15 +9485,15 @@ PASSING MODIFIERS TO THE REGULAR EXPRESSION ENGINE If you are going to pass one of the most used modifiers, there are some convenience functions that return a RE_Options class with the appropri- - ate modifier already set: CASELESS(), UTF8(), MULTILINE(), DOTALL(), + ate modifier already set: CASELESS(), UTF8(), MULTILINE(), DOTALL(), and EXTENDED(). - If you need to set several options at once, and you don't want to go - through the pains of declaring a RE_Options object and setting several - options, there is a parallel method that give you such ability on the - fly. You can concatenate several set_xxxxx() member functions, since - each of them returns a reference to its class object. For example, to - pass PCRE_CASELESS, PCRE_EXTENDED, and PCRE_MULTILINE to a RE with one + If you need to set several options at once, and you don't want to go + through the pains of declaring a RE_Options object and setting several + options, there is a parallel method that give you such ability on the + fly. You can concatenate several set_xxxxx() member functions, since + each of them returns a reference to its class object. For example, to + pass PCRE_CASELESS, PCRE_EXTENDED, and PCRE_MULTILINE to a RE with one statement, you may write: RE(" ^ xyz \\s+ .* blah$", @@ -8737,10 +9505,10 @@ PASSING MODIFIERS TO THE REGULAR EXPRESSION ENGINE SCANNING TEXT INCREMENTALLY - The "Consume" operation may be useful if you want to repeatedly match + The "Consume" operation may be useful if you want to repeatedly match regular expressions at the front of a string and skip over them as they - match. This requires use of the "StringPiece" type, which represents a - sub-range of a real string. Like RE, StringPiece is defined in the + match. This requires use of the "StringPiece" type, which represents a + sub-range of a real string. Like RE, StringPiece is defined in the pcrecpp namespace. Example: read lines of the form "var = value" from a string. @@ -8754,11 +9522,11 @@ SCANNING TEXT INCREMENTALLY ...; } - Each successful call to "Consume" will set "var/value", and also + Each successful call to "Consume" will set "var/value", and also advance "input" so it points past the matched text. - The "FindAndConsume" operation is similar to "Consume" but does not - anchor your match at the beginning of the string. For example, you + The "FindAndConsume" operation is similar to "Consume" but does not + anchor your match at the beginning of the string. For example, you could extract all words from a string by repeatedly calling pcrecpp::RE("(\\w+)").FindAndConsume(&input, &word) @@ -8767,10 +9535,10 @@ SCANNING TEXT INCREMENTALLY PARSING HEX/OCTAL/C-RADIX NUMBERS By default, if you pass a pointer to a numeric value, the corresponding - text is interpreted as a base-10 number. You can instead wrap the + text is interpreted as a base-10 number. You can instead wrap the pointer with a call to one of the operators Hex(), Octal(), or CRadix() - to interpret the text in another base. The CRadix operator interprets - C-style "0" (base-8) and "0x" (base-16) prefixes, but defaults to + to interpret the text in another base. The CRadix operator interprets + C-style "0" (base-8) and "0x" (base-16) prefixes, but defaults to base-10. Example: @@ -8785,30 +9553,30 @@ PARSING HEX/OCTAL/C-RADIX NUMBERS REPLACING PARTS OF STRINGS - You can replace the first match of "pattern" in "str" with "rewrite". - Within "rewrite", backslash-escaped digits (\1 to \9) can be used to - insert text matching corresponding parenthesized group from the pat- + You can replace the first match of "pattern" in "str" with "rewrite". + Within "rewrite", backslash-escaped digits (\1 to \9) can be used to + insert text matching corresponding parenthesized group from the pat- tern. \0 in "rewrite" refers to the entire matching text. For example: string s = "yabba dabba doo"; pcrecpp::RE("b+").Replace("d", &s); - will leave "s" containing "yada dabba doo". The result is true if the + will leave "s" containing "yada dabba doo". The result is true if the pattern matches and a replacement occurs, false otherwise. - GlobalReplace is like Replace except that it replaces all occurrences - of the pattern in the string with the rewrite. Replacements are not + GlobalReplace is like Replace except that it replaces all occurrences + of the pattern in the string with the rewrite. Replacements are not subject to re-matching. For example: string s = "yabba dabba doo"; pcrecpp::RE("b+").GlobalReplace("d", &s); - will leave "s" containing "yada dada doo". It returns the number of + will leave "s" containing "yada dada doo". It returns the number of replacements made. - Extract is like Replace, except that if the pattern matches, "rewrite" - is copied into "out" (an additional argument) with substitutions. The - non-matching portions of "text" are ignored. Returns true iff a match + Extract is like Replace, except that if the pattern matches, "rewrite" + is copied into "out" (an additional argument) with substitutions. The + non-matching portions of "text" are ignored. Returns true iff a match occurred and the extraction happened successfully; if no match occurs, the string is left unaffected. @@ -8823,8 +9591,8 @@ REVISION Last updated: 08 January 2012 ------------------------------------------------------------------------------ - - + + PCRESAMPLE(3) PCRESAMPLE(3) @@ -8924,14 +9692,15 @@ SIZE AND OTHER LIMITATIONS never in practice be relevant. The maximum length of a compiled pattern is approximately 64K data - units (bytes for the 8-bit library, 16-bit units for the 16-bit - library) if PCRE is compiled with the default internal linkage size of - 2 bytes. If you want to process regular expressions that are truly - enormous, you can compile PCRE with an internal linkage size of 3 or 4 - (when building the 16-bit library, 3 is rounded up to 4). See the - README file in the source distribution and the pcrebuild documentation - for details. In these cases the limit is substantially larger. How- - ever, the speed of execution is slower. + units (bytes for the 8-bit library, 32-bit units for the 32-bit + library, and 32-bit units for the 32-bit library) if PCRE is compiled + with the default internal linkage size of 2 bytes. If you want to + process regular expressions that are truly enormous, you can compile + PCRE with an internal linkage size of 3 or 4 (when building the 16-bit + or 32-bit library, 3 is rounded up to 4). See the README file in the + source distribution and the pcrebuild documentation for details. In + these cases the limit is substantially larger. However, the speed of + execution is slower. All values in repeating quantifiers must be less than 65536. @@ -8939,22 +9708,22 @@ SIZE AND OTHER LIMITATIONS can be no more than 65535 capturing subpatterns. There is a limit to the number of forward references to subsequent sub- - patterns of around 200,000. Repeated forward references with fixed - upper limits, for example, (?2){0,100} when subpattern number 2 is to - the right, are included in the count. There is no limit to the number + patterns of around 200,000. Repeated forward references with fixed + upper limits, for example, (?2){0,100} when subpattern number 2 is to + the right, are included in the count. There is no limit to the number of backward references. The maximum length of name for a named subpattern is 32 characters, and the maximum number of named subpatterns is 10000. - The maximum length of a name in a (*MARK), (*PRUNE), (*SKIP), or - (*THEN) verb is 255 for the 8-bit library and 65535 for the 16-bit - library. + The maximum length of a name in a (*MARK), (*PRUNE), (*SKIP), or + (*THEN) verb is 255 for the 8-bit library and 65535 for the 16-bit and + 32-bit library. - The maximum length of a subject string is the largest positive number - that an integer variable can hold. However, when using the traditional + The maximum length of a subject string is the largest positive number + that an integer variable can hold. However, when using the traditional matching function, PCRE uses recursion to handle subpatterns and indef- - inite repetition. This means that the available stack space may limit + inite repetition. This means that the available stack space may limit the size of a subject string that can be processed by certain patterns. For a discussion of stack issues, see the pcrestack documentation. @@ -8971,8 +9740,8 @@ REVISION Last updated: 04 May 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRESTACK(3) PCRESTACK(3) @@ -8982,7 +9751,7 @@ NAME PCRE DISCUSSION OF STACK USAGE - When you call pcre[16]_exec(), it makes use of an internal function + When you call pcre[16|32]_exec(), it makes use of an internal function called match(). This calls itself recursively at branch points in the pattern, in order to remember the state of the match so that it can back up and try a different alternative if the first one fails. As @@ -8998,110 +9767,111 @@ PCRE DISCUSSION OF STACK USAGE result of the current call (a "tail recursion"), the function is just restarted instead. - The above comments apply when pcre[16]_exec() is run in its normal + The above comments apply when pcre[16|32]_exec() is run in its normal interpretive manner. If the pattern was studied with the PCRE_STUDY_JIT_COMPILE option, and just-in-time compiling was success- - ful, and the options passed to pcre[16]_exec() were not incompatible, - the matching process uses the JIT-compiled code instead of the match() - function. In this case, the memory requirements are handled entirely - differently. See the pcrejit documentation for details. - - The pcre[16]_dfa_exec() function operates in an entirely different way, - and uses recursion only when there is a regular expression recursion or - subroutine call in the pattern. This includes the processing of asser- - tion and "once-only" subpatterns, which are handled like subroutine - calls. Normally, these are never very deep, and the limit on the com- - plexity of pcre[16]_dfa_exec() is controlled by the amount of workspace - it is given. However, it is possible to write patterns with runaway - infinite recursions; such patterns will cause pcre[16]_dfa_exec() to - run out of stack. At present, there is no protection against this. - - The comments that follow do NOT apply to pcre[16]_dfa_exec(); they are - relevant only for pcre[16]_exec() without the JIT optimization. - - Reducing pcre[16]_exec()'s stack usage - - Each time that match() is actually called recursively, it uses memory - from the process stack. For certain kinds of pattern and data, very - large amounts of stack may be needed, despite the recognition of "tail - recursion". You can often reduce the amount of recursion, and there- - fore the amount of stack used, by modifying the pattern that is being + ful, and the options passed to pcre[16|32]_exec() were not incompati- + ble, the matching process uses the JIT-compiled code instead of the + match() function. In this case, the memory requirements are handled + entirely differently. See the pcrejit documentation for details. + + The pcre[16|32]_dfa_exec() function operates in an entirely different + way, and uses recursion only when there is a regular expression recur- + sion or subroutine call in the pattern. This includes the processing of + assertion and "once-only" subpatterns, which are handled like subrou- + tine calls. Normally, these are never very deep, and the limit on the + complexity of pcre[16|32]_dfa_exec() is controlled by the amount of + workspace it is given. However, it is possible to write patterns with + runaway infinite recursions; such patterns will cause + pcre[16|32]_dfa_exec() to run out of stack. At present, there is no + protection against this. + + The comments that follow do NOT apply to pcre[16|32]_dfa_exec(); they + are relevant only for pcre[16|32]_exec() without the JIT optimization. + + Reducing pcre[16|32]_exec()'s stack usage + + Each time that match() is actually called recursively, it uses memory + from the process stack. For certain kinds of pattern and data, very + large amounts of stack may be needed, despite the recognition of "tail + recursion". You can often reduce the amount of recursion, and there- + fore the amount of stack used, by modifying the pattern that is being matched. Consider, for example, this pattern: ([^<]|<(?!inet))+ - It matches from wherever it starts until it encounters "<inet" or the - end of the data, and is the kind of pattern that might be used when + It matches from wherever it starts until it encounters "<inet" or the + end of the data, and is the kind of pattern that might be used when processing an XML file. Each iteration of the outer parentheses matches - either one character that is not "<" or a "<" that is not followed by - "inet". However, each time a parenthesis is processed, a recursion + either one character that is not "<" or a "<" that is not followed by + "inet". However, each time a parenthesis is processed, a recursion occurs, so this formulation uses a stack frame for each matched charac- - ter. For a long string, a lot of stack is required. Consider now this + ter. For a long string, a lot of stack is required. Consider now this rewritten pattern, which matches exactly the same strings: ([^<]++|<(?!inet))+ - This uses very much less stack, because runs of characters that do not - contain "<" are "swallowed" in one item inside the parentheses. Recur- - sion happens only when a "<" character that is not followed by "inet" - is encountered (and we assume this is relatively rare). A possessive - quantifier is used to stop any backtracking into the runs of non-"<" + This uses very much less stack, because runs of characters that do not + contain "<" are "swallowed" in one item inside the parentheses. Recur- + sion happens only when a "<" character that is not followed by "inet" + is encountered (and we assume this is relatively rare). A possessive + quantifier is used to stop any backtracking into the runs of non-"<" characters, but that is not related to stack usage. - This example shows that one way of avoiding stack problems when match- + This example shows that one way of avoiding stack problems when match- ing long subject strings is to write repeated parenthesized subpatterns to match more than one character whenever possible. - Compiling PCRE to use heap instead of stack for pcre[16]_exec() - - In environments where stack memory is constrained, you might want to - compile PCRE to use heap memory instead of stack for remembering back- - up points when pcre[16]_exec() is running. This makes it run a lot more - slowly, however. Details of how to do this are given in the pcrebuild - documentation. When built in this way, instead of using the stack, PCRE - obtains and frees memory by calling the functions that are pointed to - by the pcre[16]_stack_malloc and pcre[16]_stack_free variables. By - default, these point to malloc() and free(), but you can replace the - pointers to cause PCRE to use your own functions. Since the block sizes - are always the same, and are always freed in reverse order, it may be - possible to implement customized memory handlers that are more effi- - cient than the standard functions. - - Limiting pcre[16]_exec()'s stack usage - - You can set limits on the number of times that match() is called, both - in total and recursively. If a limit is exceeded, pcre[16]_exec() - returns an error code. Setting suitable limits should prevent it from - running out of stack. The default values of the limits are very large, - and unlikely ever to operate. They can be changed when PCRE is built, - and they can also be set when pcre[16]_exec() is called. For details of - these interfaces, see the pcrebuild documentation and the section on - extra data for pcre[16]_exec() in the pcreapi documentation. + Compiling PCRE to use heap instead of stack for pcre[16|32]_exec() + + In environments where stack memory is constrained, you might want to + compile PCRE to use heap memory instead of stack for remembering back- + up points when pcre[16|32]_exec() is running. This makes it run a lot + more slowly, however. Details of how to do this are given in the pcre- + build documentation. When built in this way, instead of using the + stack, PCRE obtains and frees memory by calling the functions that are + pointed to by the pcre[16|32]_stack_malloc and pcre[16|32]_stack_free + variables. By default, these point to malloc() and free(), but you can + replace the pointers to cause PCRE to use your own functions. Since the + block sizes are always the same, and are always freed in reverse order, + it may be possible to implement customized memory handlers that are + more efficient than the standard functions. + + Limiting pcre[16|32]_exec()'s stack usage + + You can set limits on the number of times that match() is called, both + in total and recursively. If a limit is exceeded, pcre[16|32]_exec() + returns an error code. Setting suitable limits should prevent it from + running out of stack. The default values of the limits are very large, + and unlikely ever to operate. They can be changed when PCRE is built, + and they can also be set when pcre[16|32]_exec() is called. For details + of these interfaces, see the pcrebuild documentation and the section on + extra data for pcre[16|32]_exec() in the pcreapi documentation. As a very rough rule of thumb, you should reckon on about 500 bytes per - recursion. Thus, if you want to limit your stack usage to 8Mb, you - should set the limit at 16000 recursions. A 64Mb stack, on the other + recursion. Thus, if you want to limit your stack usage to 8Mb, you + should set the limit at 16000 recursions. A 64Mb stack, on the other hand, can support around 128000 recursions. In Unix-like environments, the pcretest test program has a command line option (-S) that can be used to increase the size of its stack. As long - as the stack is large enough, another option (-M) can be used to find - the smallest limits that allow a particular pattern to match a given - subject string. This is done by calling pcre[16]_exec() repeatedly with - different limits. + as the stack is large enough, another option (-M) can be used to find + the smallest limits that allow a particular pattern to match a given + subject string. This is done by calling pcre[16|32]_exec() repeatedly + with different limits. Obtaining an estimate of stack usage - The actual amount of stack used per recursion can vary quite a lot, + The actual amount of stack used per recursion can vary quite a lot, depending on the compiler that was used to build PCRE and the optimiza- tion or debugging options that were set for it. The rule of thumb value - of 500 bytes mentioned above may be larger or smaller than what is + of 500 bytes mentioned above may be larger or smaller than what is actually needed. A better approximation can be obtained by running this command: pcretest -m -C - The -C option causes pcretest to output information about the options + The -C option causes pcretest to output information about the options with which PCRE was compiled. When -m is also given (before -C), infor- mation about stack use is given in a line like this: @@ -9110,21 +9880,21 @@ PCRE DISCUSSION OF STACK USAGE The value is approximate because some recursions need a bit more (up to perhaps 16 more bytes). - If the above command is given when PCRE is compiled to use the heap - instead of the stack for recursion, the value that is output is the + If the above command is given when PCRE is compiled to use the heap + instead of the stack for recursion, the value that is output is the size of each block that is obtained from the heap. Changing stack size in Unix-like systems - In Unix-like environments, there is not often a problem with the stack - unless very long strings are involved, though the default limit on - stack size varies from system to system. Values from 8Mb to 64Mb are + In Unix-like environments, there is not often a problem with the stack + unless very long strings are involved, though the default limit on + stack size varies from system to system. Values from 8Mb to 64Mb are common. You can find your default limit by running the command: ulimit -s - Unfortunately, the effect of running out of stack is often SIGSEGV, - though sometimes a more explicit error message is given. You can nor- + Unfortunately, the effect of running out of stack is often SIGSEGV, + though sometimes a more explicit error message is given. You can nor- mally increase the limit on stack size by code such as this: struct rlimit rlim; @@ -9132,15 +9902,15 @@ PCRE DISCUSSION OF STACK USAGE rlim.rlim_cur = 100*1024*1024; setrlimit(RLIMIT_STACK, &rlim); - This reads the current limits (soft and hard) using getrlimit(), then - attempts to increase the soft limit to 100Mb using setrlimit(). You - must do this before calling pcre[16]_exec(). + This reads the current limits (soft and hard) using getrlimit(), then + attempts to increase the soft limit to 100Mb using setrlimit(). You + must do this before calling pcre[16|32]_exec(). Changing stack size in Mac OS X Using setrlimit(), as described above, should also work on Mac OS X. It is also possible to set a stack size when linking a program. There is a - discussion about stack sizes in Mac OS X at this web site: + discussion about stack sizes in Mac OS X at this web site: http://developer.apple.com/qa/qa2005/qa1419.html. @@ -9153,8 +9923,8 @@ AUTHOR REVISION - Last updated: 21 January 2012 + Last updated: 24 June 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + diff --git a/doc/pcre_jit_exec.3 b/doc/pcre_jit_exec.3 new file mode 100644 index 0000000..84c94a5 --- /dev/null +++ b/doc/pcre_jit_exec.3 @@ -0,0 +1,104 @@ +.TH PCRE_EXEC 3 "31 October 2012" "PCRE 8.30" +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include <pcre.h> +.PP +.SM +.B int pcre_jit_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," +.ti +5n +.B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP, +.ti +5n +.B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP, +.ti +5n +.B pcre_jit_stack *\fIjstack\fP); +.PP +.B int pcre16_jit_exec(const pcre16 *\fIcode\fP, "const pcre16_extra *\fIextra\fP," +.ti +5n +.B "PCRE_SPTR16 \fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP, +.ti +5n +.B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP, +.ti +5n +.B pcre_jit_stack *\fIjstack\fP); +.PP +.B int pcre32_jit_exec(const pcre32 *\fIcode\fP, "const pcre32_extra *\fIextra\fP," +.ti +5n +.B "PCRE_SPTR32 \fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP, +.ti +5n +.B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP, +.ti +5n +.B pcre_jit_stack *\fIjstack\fP); +. +.SH DESCRIPTION +.rs +.sp +This function matches a compiled regular expression that has been successfully +studied with one of the JIT options against a given subject string, using a +matching algorithm that is similar to Perl's. It is a "fast path" interface to +JIT, and it bypasses some of the sanity checks that \fBpcre_exec()\fP applies. +It returns offsets to captured substrings. Its arguments are: +.sp + \fIcode\fP Points to the compiled pattern + \fIextra\fP Points to an associated \fBpcre[16|32]_extra\fP structure, + or is NULL + \fIsubject\fP Points to the subject string + \fIlength\fP Length of the subject string, in bytes + \fIstartoffset\fP Offset in bytes in the subject at which to + start matching + \fIoptions\fP Option bits + \fIovector\fP Points to a vector of ints for result offsets + \fIovecsize\fP Number of elements in the vector (a multiple of 3) + \fIjstack\fP Pointer to a JIT stack +.sp +The allowed options are: +.sp + PCRE_NOTBOL Subject string is not the beginning of a line + PCRE_NOTEOL Subject string is not the end of a line + PCRE_NOTEMPTY An empty string is not a valid match + PCRE_NOTEMPTY_ATSTART An empty string at the start of the subject + is not a valid match + PCRE_NO_UTF16_CHECK Do not check the subject for UTF-16 + validity (only relevant if PCRE_UTF16 + was set at compile time) + PCRE_NO_UTF32_CHECK Do not check the subject for UTF-32 + validity (only relevant if PCRE_UTF32 + was set at compile time) + PCRE_NO_UTF8_CHECK Do not check the subject for UTF-8 + validity (only relevant if PCRE_UTF8 + was set at compile time) + PCRE_PARTIAL ) Return PCRE_ERROR_PARTIAL for a partial + PCRE_PARTIAL_SOFT ) match if no full matches are found + PCRE_PARTIAL_HARD Return PCRE_ERROR_PARTIAL for a partial match + if that is found before a full match +.sp +However, the PCRE_NO_UTF[8|16|32]_CHECK options have no effect, as this check +is never applied. For details of partial matching, see the +.\" HREF +\fBpcrepartial\fP +.\" +page. A \fBpcre_extra\fP structure contains the following fields: +.sp + \fIflags\fP Bits indicating which fields are set + \fIstudy_data\fP Opaque data from \fBpcre[16|32]_study()\fP + \fImatch_limit\fP Limit on internal resource use + \fImatch_limit_recursion\fP Limit on internal recursion depth + \fIcallout_data\fP Opaque data passed back to callouts + \fItables\fP Points to character tables or is NULL + \fImark\fP For passing back a *MARK pointer + \fIexecutable_jit\fP Opaque data from JIT compilation +.sp +The flag bits are PCRE_EXTRA_STUDY_DATA, PCRE_EXTRA_MATCH_LIMIT, +PCRE_EXTRA_MATCH_LIMIT_RECURSION, PCRE_EXTRA_CALLOUT_DATA, +PCRE_EXTRA_TABLES, PCRE_EXTRA_MARK and PCRE_EXTRA_EXECUTABLE_JIT. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the JIT API in the +.\" HREF +\fBpcrejit\fP +.\" +page. diff --git a/doc/pcreapi.3 b/doc/pcreapi.3 index 9676a5c..ddeb3da 100644 --- a/doc/pcreapi.3 +++ b/doc/pcreapi.3 @@ -1,4 +1,4 @@ -.TH PCREAPI 3 "29 October 2012" "PCRE 8.32" +.TH PCREAPI 3 "31 October 2012" "PCRE 8.32" .SH NAME PCRE - Perl-compatible regular expressions .sp @@ -95,6 +95,14 @@ PCRE - Perl-compatible regular expressions .SH "PCRE NATIVE API AUXILIARY FUNCTIONS" .rs .sp +.B int pcre_jit_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," +.ti +5n +.B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP, +.ti +5n +.B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP, +.ti +5n +.B pcre_jit_stack *\fIjstack\fP); +.PP .B pcre_jit_stack *pcre_jit_stack_alloc(int \fIstartsize\fP, int \fImaxsize\fP); .PP .B void pcre_jit_stack_free(pcre_jit_stack *\fIstack\fP); @@ -2235,12 +2243,23 @@ host with different endianness. The utility function \fBpcre_pattern_to_host_byte_order()\fP can be used to convert such a pattern so that it runs on the new host. .sp + PCRE_ERROR_JIT_BADOPTION +.sp +This error is returned when a pattern that was successfully studied using a JIT +compile option is being matched, but the matching mode (partial or complete +match) does not correspond to any JIT compilation mode. When the JIT fast path +function is used, this error may be also given for invalid options. See the +.\" HREF +\fBpcrejit\fP +.\" +documentation for more details. +.sp PCRE_ERROR_BADLENGTH (-32) .sp This error is given if \fBpcre_exec()\fP is called with a negative value for the \fIlength\fP argument. .P -Error numbers -16 to -20, -22, 30, and -31 are not used by \fBpcre_exec()\fP. +Error numbers -16 to -20, -22, and 30 are not used by \fBpcre_exec()\fP. . . .\" HTML <a name="badutf8reasons"></a> @@ -2799,6 +2818,6 @@ Cambridge CB2 3QH, England. .rs .sp .nf -Last updated: 29 October 2012 +Last updated: 31 October 2012 Copyright (c) 1997-2012 University of Cambridge. .fi diff --git a/doc/pcregrep.txt b/doc/pcregrep.txt index 395cd65..0d5a12f 100644 --- a/doc/pcregrep.txt +++ b/doc/pcregrep.txt @@ -26,7 +26,7 @@ DESCRIPTION with slashes, as is common in Perl scripts), they are interpreted as part of the pattern. Quotes can of course be used to delimit patterns on the command line because they are interpreted by the shell, and - indeed they are required if a pattern contains white space or shell + indeed quotes are required if a pattern contains white space or shell metacharacters. The first argument that follows any option settings is treated as the @@ -56,25 +56,27 @@ DESCRIPTION times this size is used (to allow for buffering "before" and "after" lines). An error occurs if a line overflows the buffer. - Patterns are limited to 8K or BUFSIZ bytes, whichever is the greater. - BUFSIZ is defined in <stdio.h>. When there is more than one pattern - (specified by the use of -e and/or -f), each pattern is applied to each - line in the order in which they are defined, except that all the -e - patterns are tried before the -f patterns. - - By default, as soon as one pattern matches (or fails to match when -v - is used), no further patterns are considered. However, if --colour (or - --color) is used to colour the matching substrings, or if --only-match- - ing, --file-offsets, or --line-offsets is used to output only the part - of the line that matched (either shown literally, or as an offset), - scanning resumes immediately following the match, so that further - matches on the same line can be found. If there are multiple patterns, - they are all tried on the remainder of the line, but patterns that fol- - low the one that matched are not tried on the earlier part of the line. - - This is the same behaviour as GNU grep, but it does mean that the order - in which multiple patterns are specified can affect the output when one - of the above options is used. + Patterns can be no longer than 8K or BUFSIZ bytes, whichever is the + greater. BUFSIZ is defined in <stdio.h>. When there is more than one + pattern (specified by the use of -e and/or -f), each pattern is applied + to each line in the order in which they are defined, except that all + the -e patterns are tried before the -f patterns. + + By default, as soon as one pattern matches a line, no further patterns + are considered. However, if --colour (or --color) is used to colour the + matching substrings, or if --only-matching, --file-offsets, or --line- + offsets is used to output only the part of the line that matched + (either shown literally, or as an offset), scanning resumes immediately + following the match, so that further matches on the same line can be + found. If there are multiple patterns, they are all tried on the + remainder of the line, but patterns that follow the one that matched + are not tried on the earlier part of the line. + + This behaviour means that the order in which multiple patterns are + specified can affect the output when one of the above options is used. + This is no longer the same behaviour as GNU grep, which now manages to + display earlier matches for later patterns (as long as there is no + overlap). Patterns that can match an empty string are accepted, but empty string matches are never recognized. An example is the pattern @@ -112,8 +114,10 @@ OPTIONS The order in which some of the options appear can affect the output. For example, both the -h and -l options affect the printing of file names. Whichever comes later in the command line will be the one that - takes effect. Numerical values for options may be followed by K or M, - to signify multiplication by 1024 or 1024*1024 respectively. + takes effect. Similarly, except where noted below, if an option is + given twice, the later setting is used. Numerical values for options + may be followed by K or M, to signify multiplication by 1024 or + 1024*1024 respectively. -- This terminates the list of options. It is useful if the next item on the command line starts with a hyphen but is not an @@ -208,12 +212,14 @@ OPTIONS -d action, --directories=action If an input path is a directory, "action" specifies how it is - to be processed. Valid values are "read" (the default), - "recurse" (equivalent to the -r option), or "skip" (silently - skip the path). In the default case, directories are read as - if they were ordinary files. In some operating systems the - effect of reading a directory like this is an immediate end- - of-file. + to be processed. Valid values are "read" (the default in + non-Windows environments, for compatibility with GNU grep), + "recurse" (equivalent to the -r option), or "skip" (silently + skip the path, the default in Windows environments). In the + "read" case, directories are read as if they were ordinary + files. In some operating systems the effect of reading a + directory like this is an immediate end-of-file; in others it + may provoke an error. -e pattern, --regex=pattern, --regexp=pattern Specify a pattern to be matched. This option can be used mul- @@ -221,103 +227,126 @@ OPTIONS be used as a way of specifying a single pattern that starts with a hyphen. When -e is used, no argument pattern is taken from the command line; all arguments are treated as file - names. There is an overall maximum of 100 patterns. They are + names. There is no limit to the number of patterns. They are applied to each line in the order in which they are defined - until one matches (or fails to match if -v is used). If -f is - used with -e, the command line patterns are matched first, - followed by the patterns from the file, independent of the - order in which these options are specified. Note that multi- - ple use of -e is not the same as a single pattern with alter- - natives. For example, X|Y finds the first character in a line - that is X or Y, whereas if the two patterns are given sepa- - rately, pcregrep finds X if it is present, even if it follows - Y in the line. It finds Y only if there is no X in the line. - This really matters only if you are using -o to show the - part(s) of the line that matched. + until one matches. + + If -f is used with -e, the command line patterns are matched + first, followed by the patterns from the file(s), independent + of the order in which these options are specified. Note that + multiple use of -e is not the same as a single pattern with + alternatives. For example, X|Y finds the first character in a + line that is X or Y, whereas if the two patterns are given + separately, with X first, pcregrep finds X if it is present, + even if it follows Y in the line. It finds Y only if there is + no X in the line. This matters only if you are using -o or + --colo(u)r to show the part(s) of the line that matched. --exclude=pattern - When pcregrep is searching the files in a directory as a con- - sequence of the -r (recursive search) option, any regular - files whose names match the pattern are excluded. Subdirecto- - ries are not excluded by this option; they are searched - recursively, subject to the --exclude-dir and --include_dir - options. The pattern is a PCRE regular expression, and is - matched against the final component of the file name (not the - entire path). If a file name matches both --include and - --exclude, it is excluded. There is no short form for this - option. + Files (but not directories) whose names match the pattern are + skipped without being processed. This applies to all files, + whether listed on the command line, obtained from --file- + list, or by scanning a directory. The pattern is a PCRE regu- + lar expression, and is matched against the final component of + the file name, not the entire path. The -F, -w, and -x + options do not apply to this pattern. The option may be given + any number of times in order to specify multiple patterns. If + a file name matches both an --include and an --exclude pat- + tern, it is excluded. There is no short form for this option. + + --exclude-from=filename + Treat each non-empty line of the file as the data for an + --exclude option. What constitutes a newline when reading the + file is the operating system's default. The --newline option + has no effect on this option. This option may be given more + than once in order to specify a number of files to read. --exclude-dir=pattern - When pcregrep is searching the contents of a directory as a - consequence of the -r (recursive search) option, any subdi- - rectories whose names match the pattern are excluded. (Note - that the --exclude option does not affect subdirectories.) - The pattern is a PCRE regular expression, and is matched - against the final component of the name (not the entire - path). If a subdirectory name matches both --include-dir and - --exclude-dir, it is excluded. There is no short form for - this option. + Directories whose names match the pattern are skipped without + being processed, whatever the setting of the --recursive + option. This applies to all directories, whether listed on + the command line, obtained from --file-list, or by scanning a + parent directory. The pattern is a PCRE regular expression, + and is matched against the final component of the directory + name, not the entire path. The -F, -w, and -x options do not + apply to this pattern. The option may be given any number of + times in order to specify more than one pattern. If a direc- + tory matches both --include-dir and --exclude-dir, it is + excluded. There is no short form for this option. -F, --fixed-strings - Interpret each pattern as a list of fixed strings, separated - by newlines, instead of as a regular expression. The -w - (match as a word) and -x (match whole line) options can be - used with -F. They apply to each of the fixed strings. A line - is selected if any of the fixed strings are found in it (sub- - ject to -w or -x, if present). + Interpret each data-matching pattern as a list of fixed + strings, separated by newlines, instead of as a regular + expression. What constitutes a newline for this purpose is + controlled by the --newline option. The -w (match as a word) + and -x (match whole line) options can be used with -F. They + apply to each of the fixed strings. A line is selected if any + of the fixed strings are found in it (subject to -w or -x, if + present). This option applies only to the patterns that are + matched against the contents of files; it does not apply to + patterns specified by any of the --include or --exclude + options. -f filename, --file=filename - Read a number of patterns from the file, one per line, and - match them against each line of input. A data line is output - if any of the patterns match it. The filename can be given as - "-" to refer to the standard input. When -f is used, patterns - specified on the command line using -e may also be present; - they are tested before the file's patterns. However, no other - pattern is taken from the command line; all arguments are - treated as the names of paths to be searched. There is an - overall maximum of 100 patterns. Trailing white space is - removed from each line, and blank lines are ignored. An empty - file contains no patterns and therefore matches nothing. See - also the comments about multiple patterns versus a single - pattern with alternatives in the description of -e above. + Read patterns from the file, one per line, and match them + against each line of input. What constitutes a newline when + reading the file is the operating system's default. The + --newline option has no effect on this option. Trailing white + space is removed from each line, and blank lines are ignored. + An empty file contains no patterns and therefore matches + nothing. See also the comments about multiple patterns versus + a single pattern with alternatives in the description of -e + above. + + If this option is given more than once, all the specified + files are read. A data line is output if any of the patterns + match it. A filename can be given as "-" to refer to the + standard input. When -f is used, patterns specified on the + command line using -e may also be present; they are tested + before the file's patterns. However, no other pattern is + taken from the command line; all arguments are treated as the + names of paths to be searched. --file-list=filename - Read a list of files to be searched from the given file, one - per line. Trailing white space is removed from each line, and - blank lines are ignored. These files are searched before any - others that may be listed on the command line. The filename - can be given as "-" to refer to the standard input. If --file - and --file-list are both specified as "-", patterns are read - first. This is useful only when the standard input is a ter- - minal, from which further lines (the list of files) can be - read after an end-of-file indication. + Read a list of files and/or directories that are to be + scanned from the given file, one per line. Trailing white + space is removed from each line, and blank lines are ignored. + These paths are processed before any that are listed on the + command line. The filename can be given as "-" to refer to + the standard input. If --file and --file-list are both spec- + ified as "-", patterns are read first. This is useful only + when the standard input is a terminal, from which further + lines (the list of files) can be read after an end-of-file + indication. If this option is given more than once, all the + specified files are read. --file-offsets - Instead of showing lines or parts of lines that match, show - each match as an offset from the start of the file and a - length, separated by a comma. In this mode, no context is - shown. That is, the -A, -B, and -C options are ignored. If + Instead of showing lines or parts of lines that match, show + each match as an offset from the start of the file and a + length, separated by a comma. In this mode, no context is + shown. That is, the -A, -B, and -C options are ignored. If there is more than one match in a line, each of them is shown - separately. This option is mutually exclusive with --line- + separately. This option is mutually exclusive with --line- offsets and --only-matching. -H, --with-filename - Force the inclusion of the filename at the start of output - lines when searching a single file. By default, the filename - is not shown in this case. For matching lines, the filename + Force the inclusion of the filename at the start of output + lines when searching a single file. By default, the filename + is not shown in this case. For matching lines, the filename is followed by a colon; for context lines, a hyphen separator - is used. If a line number is also being output, it follows + is used. If a line number is also being output, it follows the file name. -h, --no-filename - Suppress the output filenames when searching multiple files. - By default, filenames are shown when multiple files are - searched. For matching lines, the filename is followed by a - colon; for context lines, a hyphen separator is used. If a + Suppress the output filenames when searching multiple files. + By default, filenames are shown when multiple files are + searched. For matching lines, the filename is followed by a + colon; for context lines, a hyphen separator is used. If a line number is also being output, it follows the file name. - --help Output a help message, giving brief details of the command - options and file type support, and then exit. + --help Output a help message, giving brief details of the command + options and file type support, and then exit. Anything else + on the command line is ignored. -I Treat binary files as never matching. This is equivalent to --binary-files=without-match. @@ -326,41 +355,53 @@ OPTIONS Ignore upper/lower case distinctions during comparisons. --include=pattern - When pcregrep is searching the files in a directory as a con- - sequence of the -r (recursive search) option, only those reg- - ular files whose names match the pattern are included. Subdi- - rectories are always included and searched recursively, sub- - ject to the --include-dir and --exclude-dir options. The pat- - tern is a PCRE regular expression, and is matched against the - final component of the file name (not the entire path). If a - file name matches both --include and --exclude, it is - excluded. There is no short form for this option. + If any --include patterns are specified, the only files that + are processed are those that match one of the patterns (and + do not match an --exclude pattern). This option does not + affect directories, but it applies to all files, whether + listed on the command line, obtained from --file-list, or by + scanning a directory. The pattern is a PCRE regular expres- + sion, and is matched against the final component of the file + name, not the entire path. The -F, -w, and -x options do not + apply to this pattern. The option may be given any number of + times. If a file name matches both an --include and an + --exclude pattern, it is excluded. There is no short form + for this option. + + --include-from=filename + Treat each non-empty line of the file as the data for an + --include option. What constitutes a newline for this purpose + is the operating system's default. The --newline option has + no effect on this option. This option may be given any number + of times; all the files are read. --include-dir=pattern - When pcregrep is searching the contents of a directory as a - consequence of the -r (recursive search) option, only those - subdirectories whose names match the pattern are included. - (Note that the --include option does not affect subdirecto- - ries.) The pattern is a PCRE regular expression, and is - matched against the final component of the name (not the - entire path). If a subdirectory name matches both --include- - dir and --exclude-dir, it is excluded. There is no short form - for this option. + If any --include-dir patterns are specified, the only direc- + tories that are processed are those that match one of the + patterns (and do not match an --exclude-dir pattern). This + applies to all directories, whether listed on the command + line, obtained from --file-list, or by scanning a parent + directory. The pattern is a PCRE regular expression, and is + matched against the final component of the directory name, + not the entire path. The -F, -w, and -x options do not apply + to this pattern. The option may be given any number of times. + If a directory matches both --include-dir and --exclude-dir, + it is excluded. There is no short form for this option. -L, --files-without-match - Instead of outputting lines from the files, just output the - names of the files that do not contain any lines that would - have been output. Each file name is output once, on a sepa- + Instead of outputting lines from the files, just output the + names of the files that do not contain any lines that would + have been output. Each file name is output once, on a sepa- rate line. -l, --files-with-matches - Instead of outputting lines from the files, just output the + Instead of outputting lines from the files, just output the names of the files containing lines that would have been out- - put. Each file name is output once, on a separate line. - Searching normally stops as soon as a matching line is found - in a file. However, if the -c (count) option is also used, - matching continues in order to obtain the correct count, and - those files that have at least one match are listed along + put. Each file name is output once, on a separate line. + Searching normally stops as soon as a matching line is found + in a file. However, if the -c (count) option is also used, + matching continues in order to obtain the correct count, and + those files that have at least one match are listed along with their counts. Using this option with -c is a way of sup- pressing the listing of files with no matches. @@ -370,109 +411,112 @@ OPTIONS input)" is used. There is no short form for this option. --line-buffered - When this option is given, input is read and processed line - by line, and the output is flushed after each write. By - default, input is read in large chunks, unless pcregrep can - determine that it is reading from a terminal (which is cur- - rently possible only in Unix environments). Output to termi- - nal is normally automatically flushed by the operating sys- - tem. This option can be useful when the input or output is - attached to a pipe and you do not want pcregrep to buffer up - large amounts of data. However, its use will affect perfor- + When this option is given, input is read and processed line + by line, and the output is flushed after each write. By + default, input is read in large chunks, unless pcregrep can + determine that it is reading from a terminal (which is cur- + rently possible only in Unix-like environments). Output to + terminal is normally automatically flushed by the operating + system. This option can be useful when the input or output is + attached to a pipe and you do not want pcregrep to buffer up + large amounts of data. However, its use will affect perfor- mance, and the -M (multiline) option ceases to work. --line-offsets - Instead of showing lines or parts of lines that match, show + Instead of showing lines or parts of lines that match, show each match as a line number, the offset from the start of the - line, and a length. The line number is terminated by a colon - (as usual; see the -n option), and the offset and length are - separated by a comma. In this mode, no context is shown. - That is, the -A, -B, and -C options are ignored. If there is - more than one match in a line, each of them is shown sepa- + line, and a length. The line number is terminated by a colon + (as usual; see the -n option), and the offset and length are + separated by a comma. In this mode, no context is shown. + That is, the -A, -B, and -C options are ignored. If there is + more than one match in a line, each of them is shown sepa- rately. This option is mutually exclusive with --file-offsets and --only-matching. --locale=locale-name - This option specifies a locale to be used for pattern match- - ing. It overrides the value in the LC_ALL or LC_CTYPE envi- - ronment variables. If no locale is specified, the PCRE - library's default (usually the "C" locale) is used. There is + This option specifies a locale to be used for pattern match- + ing. It overrides the value in the LC_ALL or LC_CTYPE envi- + ronment variables. If no locale is specified, the PCRE + library's default (usually the "C" locale) is used. There is no short form for this option. --match-limit=number - Processing some regular expression patterns can require a - very large amount of memory, leading in some cases to a pro- - gram crash if not enough is available. Other patterns may - take a very long time to search for all possible matching - strings. The pcre_exec() function that is called by pcregrep - to do the matching has two parameters that can limit the + Processing some regular expression patterns can require a + very large amount of memory, leading in some cases to a pro- + gram crash if not enough is available. Other patterns may + take a very long time to search for all possible matching + strings. The pcre_exec() function that is called by pcregrep + to do the matching has two parameters that can limit the resources that it uses. - The --match-limit option provides a means of limiting + The --match-limit option provides a means of limiting resource usage when processing patterns that are not going to match, but which have a very large number of possibilities in - their search trees. The classic example is a pattern that - uses nested unlimited repeats. Internally, PCRE uses a func- - tion called match() which it calls repeatedly (sometimes - recursively). The limit set by --match-limit is imposed on - the number of times this function is called during a match, - which has the effect of limiting the amount of backtracking + their search trees. The classic example is a pattern that + uses nested unlimited repeats. Internally, PCRE uses a func- + tion called match() which it calls repeatedly (sometimes + recursively). The limit set by --match-limit is imposed on + the number of times this function is called during a match, + which has the effect of limiting the amount of backtracking that can take place. The --recursion-limit option is similar to --match-limit, but instead of limiting the total number of times that match() is called, it limits the depth of recursive calls, which in turn - limits the amount of memory that can be used. The recursion - depth is a smaller number than the total number of calls, + limits the amount of memory that can be used. The recursion + depth is a smaller number than the total number of calls, because not all calls to match() are recursive. This limit is of use only if it is set smaller than --match-limit. - There are no short forms for these options. The default set- - tings are specified when the PCRE library is compiled, with + There are no short forms for these options. The default set- + tings are specified when the PCRE library is compiled, with the default default being 10 million. -M, --multiline - Allow patterns to match more than one line. When this option + Allow patterns to match more than one line. When this option is given, patterns may usefully contain literal newline char- - acters and internal occurrences of ^ and $ characters. The - output for a successful match may consist of more than one - line, the last of which is the one in which the match ended. + acters and internal occurrences of ^ and $ characters. The + output for a successful match may consist of more than one + line, the last of which is the one in which the match ended. If the matched string ends with a newline sequence the output ends at the end of that line. - When this option is set, the PCRE library is called in "mul- - tiline" mode. There is a limit to the number of lines that - can be matched, imposed by the way that pcregrep buffers the - input file as it scans it. However, pcregrep ensures that at + When this option is set, the PCRE library is called in "mul- + tiline" mode. There is a limit to the number of lines that + can be matched, imposed by the way that pcregrep buffers the + input file as it scans it. However, pcregrep ensures that at least 8K characters or the rest of the document (whichever is - the shorter) are available for forward matching, and simi- + the shorter) are available for forward matching, and simi- larly the previous 8K characters (or all the previous charac- - ters, if fewer than 8K) are guaranteed to be available for - lookbehind assertions. This option does not work when input + ters, if fewer than 8K) are guaranteed to be available for + lookbehind assertions. This option does not work when input is read line by line (see --line-buffered.) -N newline-type, --newline=newline-type - The PCRE library supports five different conventions for - indicating the ends of lines. They are the single-character - sequences CR (carriage return) and LF (linefeed), the two- - character sequence CRLF, an "anycrlf" convention, which rec- - ognizes any of the preceding three types, and an "any" con- + The PCRE library supports five different conventions for + indicating the ends of lines. They are the single-character + sequences CR (carriage return) and LF (linefeed), the two- + character sequence CRLF, an "anycrlf" convention, which rec- + ognizes any of the preceding three types, and an "any" con- vention, in which any Unicode line ending sequence is assumed - to end a line. The Unicode sequences are the three just men- - tioned, plus VT (vertical tab, U+000B), FF (form feed, - U+000C), NEL (next line, U+0085), LS (line separator, + to end a line. The Unicode sequences are the three just men- + tioned, plus VT (vertical tab, U+000B), FF (form feed, + U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS (paragraph separator, U+2029). When the PCRE library is built, a default line-ending - sequence is specified. This is normally the standard + sequence is specified. This is normally the standard sequence for the operating system. Unless otherwise specified - by this option, pcregrep uses the library's default. The + by this option, pcregrep uses the library's default. The possible values for this option are CR, LF, CRLF, ANYCRLF, or - ANY. This makes it possible to use pcregrep on files that - have come from other environments without having to modify - their line endings. If the data that is being scanned does - not agree with the convention set by this option, pcregrep - may behave in strange ways. + ANY. This makes it possible to use pcregrep to scan files + that have come from other environments without having to mod- + ify their line endings. If the data that is being scanned + does not agree with the convention set by this option, pcre- + grep may behave in strange ways. Note that this option does + not apply to files specified by the -f, --exclude-from, or + --include-from options, which are expected to use the operat- + ing system's standard newline sequence. -n, --line-number Precede each output line by its line number in the file, fol- @@ -503,44 +547,59 @@ OPTIONS -onumber, --only-matching=number Show only the part of the line that matched the capturing parentheses of the given number. Up to 32 capturing parenthe- - ses are supported. Because these options can be given without - an argument (see above), if an argument is present, it must - be given in the same shell item, for example, -o3 or --only- - matching=2. The comments given for the non-argument case - above also apply to this case. If the specified capturing - parentheses do not exist in the pattern, or were not set in - the match, nothing is output unless the file name or line - number are being printed. + ses are supported, and -o0 is equivalent to -o without a num- + ber. Because these options can be given without an argument + (see above), if an argument is present, it must be given in + the same shell item, for example, -o3 or --only-matching=2. + The comments given for the non-argument case above also apply + to this case. If the specified capturing parentheses do not + exist in the pattern, or were not set in the match, nothing + is output unless the file name or line number are being + printed. + + If this option is given multiple times, multiple substrings + are output, in the order the options are given. For example, + -o3 -o1 -o3 causes the substrings matched by capturing paren- + theses 3 and 1 and then 3 again to be output. By default, + there is no separator (but see the next option). + + --om-separator=text + Specify a separating string for multiple occurrences of -o. + The default is an empty string. Separating strings are never + coloured. -q, --quiet Work quietly, that is, display nothing except error messages. - The exit status indicates whether or not any matches were + The exit status indicates whether or not any matches were found. -r, --recursive - If any given path is a directory, recursively scan the files - it contains, taking note of any --include and --exclude set- - tings. By default, a directory is read as a normal file; in - some operating systems this gives an immediate end-of-file. - This option is a shorthand for setting the -d option to + If any given path is a directory, recursively scan the files + it contains, taking note of any --include and --exclude set- + tings. By default, a directory is read as a normal file; in + some operating systems this gives an immediate end-of-file. + This option is a shorthand for setting the -d option to "recurse". --recursion-limit=number See --match-limit above. -s, --no-messages - Suppress error messages about non-existent or unreadable - files. Such files are quietly skipped. However, the return + Suppress error messages about non-existent or unreadable + files. Such files are quietly skipped. However, the return code is still 2, even if matches were found in other files. -u, --utf-8 - Operate in UTF-8 mode. This option is available only if PCRE - has been compiled with UTF-8 support. Both patterns and sub- - ject lines must be valid strings of UTF-8 characters. + Operate in UTF-8 mode. This option is available only if PCRE + has been compiled with UTF-8 support. All patterns (including + those for any --exclude and --include options) and all sub- + ject lines that are scanned must be valid strings of UTF-8 + characters. -V, --version - Write the version numbers of pcregrep and the PCRE library - that is being used to the standard error stream. + Write the version numbers of pcregrep and the PCRE library to + the standard output and then exit. Anything else on the com- + mand line is ignored. -v, --invert-match Invert the sense of the match, so that lines which do not @@ -548,14 +607,20 @@ OPTIONS -w, --word-regex, --word-regexp Force the patterns to match only whole words. This is equiva- - lent to having \b at the start and end of the pattern. + lent to having \b at the start and end of the pattern. This + option applies only to the patterns that are matched against + the contents of files; it does not apply to patterns speci- + fied by any of the --include or --exclude options. -x, --line-regex, --line-regexp - Force the patterns to be anchored (each must start matching - at the beginning of a line) and in addition, require them to - match entire lines. This is equivalent to having ^ and $ + Force the patterns to be anchored (each must start matching + at the beginning of a line) and in addition, require them to + match entire lines. This is equivalent to having ^ and $ characters at the start and end of each alternative branch in - every pattern. + every pattern. This option applies only to the patterns that + are matched against the contents of files; it does not apply + to patterns specified by any of the --include or --exclude + options. ENVIRONMENT VARIABLES @@ -569,12 +634,16 @@ ENVIRONMENT VARIABLES NEWLINES The -N (--newline) option allows pcregrep to scan files with different - newline conventions from the default. However, the setting of this - option does not affect the way in which pcregrep writes information to - the standard error and output streams. It uses the string "\n" in C - printf() calls to indicate newlines, relying on the C I/O library to - convert this to an appropriate sequence if the output is sent to a - file. + newline conventions from the default. Any parts of the input files that + are written to the standard output are copied identically, with what- + ever newline sequences they have in the input. However, the setting of + this option does not affect the interpretation of files specified by + the -f, --exclude-from, or --include-from options, which are assumed to + use the operating system's standard newline sequence, nor does it + affect the way in which pcregrep writes informational messages to the + standard error and output streams. For these it uses the string "\n" to + indicate newlines, relying on the C I/O library to convert this to an + appropriate sequence. OPTIONS COMPATIBILITY @@ -583,78 +652,79 @@ OPTIONS COMPATIBILITY in the GNU grep program. Any long option of the form --xxx-regexp (GNU terminology) is also available as --xxx-regex (PCRE terminology). How- ever, the --file-list, --file-offsets, --include-dir, --line-offsets, - --locale, --match-limit, -M, --multiline, -N, --newline, --recursion- - limit, -u, and --utf-8 options are specific to pcregrep, as is the use - of the --only-matching option with a capturing parentheses number. - - Although most of the common options work the same way, a few are dif- - ferent in pcregrep. For example, the --include option's argument is a - glob for GNU grep, but a regular expression for pcregrep. If both the - -c and -l options are given, GNU grep lists only file names, without + --locale, --match-limit, -M, --multiline, -N, --newline, --om-separa- + tor, --recursion-limit, -u, and --utf-8 options are specific to pcre- + grep, as is the use of the --only-matching option with a capturing + parentheses number. + + Although most of the common options work the same way, a few are dif- + ferent in pcregrep. For example, the --include option's argument is a + glob for GNU grep, but a regular expression for pcregrep. If both the + -c and -l options are given, GNU grep lists only file names, without counts, but pcregrep gives the counts. OPTIONS WITH DATA There are four different ways in which an option with data can be spec- - ified. If a short form option is used, the data may follow immedi- + ified. If a short form option is used, the data may follow immedi- ately, or (with one exception) in the next command line item. For exam- ple: -f/some/file -f /some/file - The exception is the -o option, which may appear with or without data. - Because of this, if data is present, it must follow immediately in the + The exception is the -o option, which may appear with or without data. + Because of this, if data is present, it must follow immediately in the same item, for example -o3. - If a long form option is used, the data may appear in the same command - line item, separated by an equals character, or (with two exceptions) + If a long form option is used, the data may appear in the same command + line item, separated by an equals character, or (with two exceptions) it may appear in the next command line item. For example: --file=/some/file --file /some/file - Note, however, that if you want to supply a file name beginning with ~ - as data in a shell command, and have the shell expand ~ to a home + Note, however, that if you want to supply a file name beginning with ~ + as data in a shell command, and have the shell expand ~ to a home directory, you must separate the file name from the option, because the shell does not treat ~ specially unless it is at the start of an item. - The exceptions to the above are the --colour (or --color) and --only- - matching options, for which the data is optional. If one of these - options does have data, it must be given in the first form, using an + The exceptions to the above are the --colour (or --color) and --only- + matching options, for which the data is optional. If one of these + options does have data, it must be given in the first form, using an equals character. Otherwise pcregrep will assume that it has no data. MATCHING ERRORS - It is possible to supply a regular expression that takes a very long - time to fail to match certain lines. Such patterns normally involve - nested indefinite repeats, for example: (a+)*\d when matched against a - line of a's with no final digit. The PCRE matching function has a - resource limit that causes it to abort in these circumstances. If this + It is possible to supply a regular expression that takes a very long + time to fail to match certain lines. Such patterns normally involve + nested indefinite repeats, for example: (a+)*\d when matched against a + line of a's with no final digit. The PCRE matching function has a + resource limit that causes it to abort in these circumstances. If this happens, pcregrep outputs an error message and the line that caused the - problem to the standard error stream. If there are more than 20 such + problem to the standard error stream. If there are more than 20 such errors, pcregrep gives up. - The --match-limit option of pcregrep can be used to set the overall - resource limit; there is a second option called --recursion-limit that - sets a limit on the amount of memory (usually stack) that is used (see + The --match-limit option of pcregrep can be used to set the overall + resource limit; there is a second option called --recursion-limit that + sets a limit on the amount of memory (usually stack) that is used (see the discussion of these options above). DIAGNOSTICS Exit status is 0 if any matches were found, 1 if no matches were found, - and 2 for syntax errors, overlong lines, non-existent or inaccessible - files (even if matches were found in other files) or too many matching + and 2 for syntax errors, overlong lines, non-existent or inaccessible + files (even if matches were found in other files) or too many matching errors. Using the -s option to suppress error messages about inaccessi- ble files does not affect the return code. SEE ALSO - pcrepattern(3), pcretest(1). + pcrepattern(3), pcresyntax(3), pcretest(1). AUTHOR @@ -666,5 +736,5 @@ AUTHOR REVISION - Last updated: 04 March 2012 + Last updated: 13 September 2012 Copyright (c) 1997-2012 University of Cambridge. diff --git a/doc/pcrejit.3 b/doc/pcrejit.3 index 7716ed6..a492dcd 100644 --- a/doc/pcrejit.3 +++ b/doc/pcrejit.3 @@ -1,4 +1,4 @@ -.TH PCREJIT 3 "04 May 2012" "PCRE 8.31" +.TH PCREJIT 3 "31 October 2012" "PCRE 8.32" .SH NAME PCRE - Perl-compatible regular expressions .SH "PCRE JUST-IN-TIME COMPILER SUPPORT" @@ -21,13 +21,13 @@ this support was written by Zoltan Herczeg. .SH "8-BIT, 16-BIT AND 32-BIT SUPPORT" .rs .sp -JIT support is available for all of the 8-bit, 16-bit and 32-bit PCRE libraries. -To keep this documentation simple, only the 8-bit interface is described in what -follows. If you are using the 16-bit library, substitute the 16-bit functions -and 16-bit structures (for example, \fIpcre16_jit_stack\fP instead of -\fIpcre_jit_stack\fP). If you are using the 32-bit library, substitute the 32-bit functions -and 32-bit structures (for example, \fIpcre32_jit_stack\fP instead of -\fIpcre_jit_stack\fP). +JIT support is available for all of the 8-bit, 16-bit and 32-bit PCRE +libraries. To keep this documentation simple, only the 8-bit interface is +described in what follows. If you are using the 16-bit library, substitute the +16-bit functions and 16-bit structures (for example, \fIpcre16_jit_stack\fP +instead of \fIpcre_jit_stack\fP). If you are using the 32-bit library, +substitute the 32-bit functions and 32-bit structures (for example, +\fIpcre32_jit_stack\fP instead of \fIpcre_jit_stack\fP). . . .SH "AVAILABILITY OF JIT SUPPORT" @@ -41,14 +41,17 @@ JIT. The support is limited to the following hardware platforms: Intel x86 32-bit and 64-bit MIPS 32-bit Power PC 32-bit and 64-bit + SPARC 32-bit (experimental) .sp If --enable-jit is set on an unsupported platform, compilation fails. .P A program that is linked with PCRE 8.20 or later can tell if JIT support is available by calling \fBpcre_config()\fP with the PCRE_CONFIG_JIT option. The result is 1 when JIT is available, and 0 otherwise. However, a simple program -does not need to check this in order to use JIT. The API is implemented in a -way that falls back to the interpretive code if JIT is not available. +does not need to check this in order to use JIT. The normal API is implemented +in a way that falls back to the interpretive code if JIT is not available. For +programs that need the best possible performance, there is also a "fast path" +API that is JIT-specific. .P If your program may sometimes be linked with versions of PCRE that are older than 8.20, but you want to use JIT when it is available, you can test @@ -66,8 +69,8 @@ You have to do two things to make use of the JIT support in the simplest way: \fBpcre_exec()\fP. .sp (2) Use \fBpcre_free_study()\fP to free the \fBpcre_extra\fP block when it is - no longer needed, instead of just freeing it yourself. This - ensures that any JIT data is also freed. + no longer needed, instead of just freeing it yourself. This ensures that + any JIT data is also freed. .sp For a program that may be linked with pre-8.20 versions of PCRE, you can insert .sp @@ -335,7 +338,7 @@ replacement. .sp No, because this is too costly in terms of resources. However, you could implement some clever idea which release the stack if it is not used in let's -say two minutes. The JIT callback can help to achive this without keeping a +say two minutes. The JIT callback can help to achieve this without keeping a list of the currently JIT studied patterns. .P (6) OK, the stack is for long term memory allocation. But what happens if a @@ -381,6 +384,34 @@ callback. .sp . . +.SH "JIT FAST PATH API" +.rs +.sp +Because the API described above falls back to interpreted execution when JIT is +not available, it is convenient for programs that are written for general use +in many environments. However, calling JIT via \fBpcre_exec()\fP does have a +performance impact. Programs that are written for use where JIT is known to be +available, and which need the best possible performance, can instead use a +"fast path" API to call JIT execution directly instead of calling +\fBpcre_exec()\fP (obviously only for patterns that have been successfully +studied by JIT). +.P +The fast path function is called \fBpcre_jit_exec()\fP, and it takes exactly +the same arguments as \fBpcre_exec()\fP, plus one additional argument that +must point to a JIT stack. The JIT stack arrangements described above do not +apply. The return values are the same as for \fBpcre_exec()\fP. +.P +When you call \fBpcre_exec()\fP, as well as testing for invalid options, a +number of other sanity checks are performed on the arguments. For example, if +the subject pointer is NULL, or its length is negative, an immediate error is +given. Also, unless PCRE_NO_UTF[8|16|32] is set, a UTF subject string is tested +for validity. In the interests of speed, these checks do not happen on the JIT +fast path, and if invalid data is passed, the result is undefined. +.P +Bypassing the sanity checks and the \fBpcre_exec()\fP wrapping can give +speedups of more than 10%. +. +. .SH "SEE ALSO" .rs .sp @@ -401,6 +432,6 @@ Cambridge CB2 3QH, England. .rs .sp .nf -Last updated: 04 May 2012 +Last updated: 31 October 2012 Copyright (c) 1997-2012 University of Cambridge. .fi diff --git a/doc/pcretest.txt b/doc/pcretest.txt index 2d39fb1..fddc888 100644 --- a/doc/pcretest.txt +++ b/doc/pcretest.txt @@ -14,59 +14,86 @@ SYNOPSIS expressions. This document describes the features of the test program; for details of the regular expressions themselves, see the pcrepattern documentation. For details of the PCRE library function calls and their - options, see the pcreapi and pcre16 documentation. The input for - pcretest is a sequence of regular expression patterns and strings to be - matched, as described below. The output shows the result of each match. - Options on the command line and the patterns control PCRE options and - exactly what is output. + options, see the pcreapi , pcre16 and pcre32 documentation. + The input for pcretest is a sequence of regular expression patterns and + strings to be matched, as described below. The output shows the result + of each match. Options on the command line and the patterns control + PCRE options and exactly what is output. -PCRE's 8-BIT and 16-BIT LIBRARIES + As PCRE has evolved, it has acquired many different features, and as a + result, pcretest now has rather a lot of obscure options for testing + every possible feature. Some of these options are specifically designed + for use in conjunction with the test script and data files that are + distributed as part of PCRE, and are unlikely to be of use otherwise. + They are all documented here, but without much justification. + + +PCRE's 8-BIT, 16-BIT AND 32-BIT LIBRARIES From release 8.30, two separate PCRE libraries can be built. The origi- nal one supports 8-bit character strings, whereas the newer 16-bit - library supports character strings encoded in 16-bit units. The - pcretest program can be used to test both libraries. However, it is - itself still an 8-bit program, reading 8-bit input and writing 8-bit - output. When testing the 16-bit library, the patterns and data strings - are converted to 16-bit format before being passed to the PCRE library - functions. Results are converted to 8-bit for output. - - References to functions and structures of the form pcre[16]_xx below + library supports character strings encoded in 16-bit units. From + release 8.32, a third library can be built, supporting character + strings encoded in 32-bit units. The pcretest program can be used to + test all three libraries. However, it is itself still an 8-bit program, + reading 8-bit input and writing 8-bit output. When testing the 16-bit + or 32-bit library, the patterns and data strings are converted to 16- + or 32-bit format before being passed to the PCRE library functions. + Results are converted to 8-bit for output. + + References to functions and structures of the form pcre[16|32]_xx below mean "pcre_xx when using the 8-bit library or pcre16_xx when using the 16-bit library". COMMAND LINE OPTIONS - -16 If both the 8-bit and the 16-bit libraries have been built, - this option causes the 16-bit library to be used. If only the - 16-bit library has been built, this is the default (so has no - effect). If only the 8-bit library has been built, this - option causes an error. + -8 If both the 8-bit library has been built, this option causes + the 8-bit library to be used (which is the default); if the + 8-bit library has not been built, this option causes an + error. + + -16 If both the 8-bit or the 32-bit, and the 16-bit libraries + have been built, this option causes the 16-bit library to be + used. If only the 16-bit library has been built, this is the + default (so has no effect). If only the 8-bit or the 32-bit + library has been built, this option causes an error. - -b Behave as if each pattern has the /B (show byte code) modi- + -32 If both the 8-bit or the 16-bit, and the 32-bit libraries + have been built, this option causes the 32-bit library to be + used. If only the 32-bit library has been built, this is the + default (so has no effect). If only the 8-bit or the 16-bit + library has been built, this option causes an error. + + -b Behave as if each pattern has the /B (show byte code) modi- fier; the internal form is output after compilation. -C Output the version number of the PCRE library, and all avail- - able information about the optional features that are + able information about the optional features that are included, and then exit. All other options are ignored. - -C option Output information about a specific build-time option, then - exit. This functionality is intended for use in scripts such + -C option Output information about a specific build-time option, then + exit. This functionality is intended for use in scripts such as RunTest. The following options output the value indicated: + ebcdic-nl the code for LF (= NL) in an EBCDIC environment: + 0x15 or 0x25 + 0 if used in an ASCII environment linksize the internal link size (2, 3, or 4) newline the default newline setting: CR, LF, CRLF, ANYCRLF, or ANY The following options output 1 for true or zero for false: + ebcdic compiled for an EBCDIC environment jit just-in-time support is available pcre16 the 16-bit library was built + pcre32 the 32-bit library was built pcre8 the 8-bit library was built ucp Unicode property support is available - utf UTF-8 and/or UTF-16 support is available + utf UTF-8 and/or UTF-16 and/or UTF-32 support is + available -d Behave as if each pattern has the /D (debug) modifier; the internal form and information about the compiled pattern is @@ -74,8 +101,8 @@ COMMAND LINE OPTIONS -dfa Behave as if each data line contains the \D escape sequence; this causes the alternative matching function, - pcre[16]_dfa_exec(), to be used instead of the standard - pcre[16]_exec() function (more detail is given below). + pcre[16|32]_dfa_exec(), to be used instead of the standard + pcre[16|32]_exec() function (more detail is given below). -help Output a brief summary these options and then exit. @@ -84,7 +111,7 @@ COMMAND LINE OPTIONS -M Behave as if each data line contains the \M escape sequence; this causes PCRE to discover the minimum MATCH_LIMIT and - MATCH_LIMIT_RECURSION settings by calling pcre[16]_exec() + MATCH_LIMIT_RECURSION settings by calling pcre[16|32]_exec() repeatedly with different limits. -m Output the size of each compiled pattern after it has been @@ -92,12 +119,12 @@ COMMAND LINE OPTIONS expression. The size is given in bytes for both libraries. -o osize Set the number of elements in the output vector that is used - when calling pcre[16]_exec() or pcre[16]_dfa_exec() to be - osize. The default value is 45, which is enough for 14 cap- - turing subexpressions for pcre[16]_exec() or 22 different - matches for pcre[16]_dfa_exec(). The vector size can be - changed for individual matching calls by including \O in the - data line (see below). + when calling pcre[16|32]_exec() or pcre[16|32]_dfa_exec() to + be osize. The default value is 45, which is enough for 14 + capturing subexpressions for pcre[16|32]_exec() or 22 differ- + ent matches for pcre[16|32]_dfa_exec(). The vector size can + be changed for individual matching calls by including \O in + the data line (see below). -p Behave as if each pattern has the /P modifier; the POSIX wrapper API is used to call PCRE. None of the other options @@ -112,12 +139,12 @@ COMMAND LINE OPTIONS -s or -s+ Behave as if each pattern has the /S modifier; in other words, force each pattern to be studied. If -s+ is used, all - the JIT compile options are passed to pcre[16]_study(), caus- - ing just-in-time optimization to be set up if it is avail- - able, for both full and partial matching. Specific JIT com- - pile options can be selected by following -s+ with a digit in - the range 1 to 7, which selects the JIT compile modes as fol- - lows: + the JIT compile options are passed to pcre[16|32]_study(), + causing just-in-time optimization to be set up if it is + available, for both full and partial matching. Specific JIT + compile options can be selected by following -s+ with a digit + in the range 1 to 7, which selects the JIT compile modes as + follows: 1 normal match only 2 soft partial match only @@ -131,29 +158,36 @@ COMMAND LINE OPTIONS after a match or no match when JIT-compiled code was actually used. - If the /I or /D option is present on a pattern (requesting output about - the compiled pattern), information about the result of studying is not - included when studying is caused only by -s and neither -i nor -d is - present on the command line. This behaviour means that the output from - tests that are run with and without -s should be identical, except when - options that output information about the actual running of a match are - set. - - The -M, -t, and -tm options, which give information about resources - used, are likely to produce different output with and without -s. Out- - put may also differ if the /C option is present on an individual pat- - tern. This uses callouts to trace the the matching process, and this - may be different between studied and non-studied patterns. If the pat- - tern contains (*MARK) items there may also be differences, for the same - reason. The -s command line option can be overridden for specific pat- - terns that should never be studied (see the /S pattern modifier below). - - -t Run each compile, study, and match many times with a timer, - and output resulting time per compile or match (in millisec- - onds). Do not set -m with -t, because you will then get the - size output a zillion times, and the timing will be dis- - torted. You can control the number of iterations that are - used for timing by following -t with a number (as a separate + Note that there are pattern options that can override -s, + either specifying no studying at all, or suppressing JIT com- + pilation. + + If the /I or /D option is present on a pattern (requesting + output about the compiled pattern), information about the + result of studying is not included when studying is caused + only by -s and neither -i nor -d is present on the command + line. This behaviour means that the output from tests that + are run with and without -s should be identical, except when + options that output information about the actual running of a + match are set. + + The -M, -t, and -tm options, which give information about + resources used, are likely to produce different output with + and without -s. Output may also differ if the /C option is + present on an individual pattern. This uses callouts to trace + the the matching process, and this may be different between + studied and non-studied patterns. If the pattern contains + (*MARK) items there may also be differences, for the same + reason. The -s command line option can be overridden for spe- + cific patterns that should never be studied (see the /S pat- + tern modifier below). + + -t Run each compile, study, and match many times with a timer, + and output resulting time per compile or match (in millisec- + onds). Do not set -m with -t, because you will then get the + size output a zillion times, and the timing will be dis- + torted. You can control the number of iterations that are + used for timing by following -t with a number (as a separate item on the command line). For example, "-t 1000" would iter- ate 1000 times. The default is to iterate 500000 times. @@ -163,77 +197,128 @@ COMMAND LINE OPTIONS DESCRIPTION - If pcretest is given two filename arguments, it reads from the first + If pcretest is given two filename arguments, it reads from the first and writes to the second. If it is given only one filename argument, it - reads from that file and writes to stdout. Otherwise, it reads from - stdin and writes to stdout, and prompts for each line of input, using + reads from that file and writes to stdout. Otherwise, it reads from + stdin and writes to stdout, and prompts for each line of input, using "re>" to prompt for regular expressions, and "data>" to prompt for data lines. - When pcretest is built, a configuration option can specify that it - should be linked with the libreadline library. When this is done, if + When pcretest is built, a configuration option can specify that it + should be linked with the libreadline library. When this is done, if the input is from a terminal, it is read using the readline() function. - This provides line-editing and history facilities. The output from the + This provides line-editing and history facilities. The output from the -help option states whether or not readline() will be used. The program handles any number of sets of input on a single input file. - Each set starts with a regular expression, and continues with any num- + Each set starts with a regular expression, and continues with any num- ber of data lines to be matched against the pattern. - Each data line is matched separately and independently. If you want to + Each data line is matched separately and independently. If you want to do multi-line matches, you have to use the \n escape sequence (or \r or \r\n, etc., depending on the newline setting) in a single line of input - to encode the newline sequences. There is no limit on the length of - data lines; the input buffer is automatically extended if it is too + to encode the newline sequences. There is no limit on the length of + data lines; the input buffer is automatically extended if it is too small. - An empty line signals the end of the data lines, at which point a new - regular expression is read. The regular expressions are given enclosed + An empty line signals the end of the data lines, at which point a new + regular expression is read. The regular expressions are given enclosed in any non-alphanumeric delimiters other than backslash, for example: /(a|bc)x+yz/ - White space before the initial delimiter is ignored. A regular expres- - sion may be continued over several input lines, in which case the new- - line characters are included within it. It is possible to include the + White space before the initial delimiter is ignored. A regular expres- + sion may be continued over several input lines, in which case the new- + line characters are included within it. It is possible to include the delimiter within the pattern by escaping it, for example /abc\/def/ - If you do so, the escape and the delimiter form part of the pattern, - but since delimiters are always non-alphanumeric, this does not affect - its interpretation. If the terminating delimiter is immediately fol- + If you do so, the escape and the delimiter form part of the pattern, + but since delimiters are always non-alphanumeric, this does not affect + its interpretation. If the terminating delimiter is immediately fol- lowed by a backslash, for example, /abc/\ - then a backslash is added to the end of the pattern. This is done to - provide a way of testing the error condition that arises if a pattern + then a backslash is added to the end of the pattern. This is done to + provide a way of testing the error condition that arises if a pattern finishes with a backslash, because /abc\/ - is interpreted as the first line of a pattern that starts with "abc/", + is interpreted as the first line of a pattern that starts with "abc/", causing pcretest to read the next line as a continuation of the regular expression. PATTERN MODIFIERS - A pattern may be followed by any number of modifiers, which are mostly - single characters. Following Perl usage, these are referred to below - as, for example, "the /i modifier", even though the delimiter of the - pattern need not always be a slash, and no slash is used when writing - modifiers. White space may appear between the final pattern delimiter - and the first modifier, and between the modifiers themselves. + A pattern may be followed by any number of modifiers, which are mostly + single characters, though some of these can be qualified by further + characters. Following Perl usage, these are referred to below as, for + example, "the /i modifier", even though the delimiter of the pattern + need not always be a slash, and no slash is used when writing modi- + fiers. White space may appear between the final pattern delimiter and + the first modifier, and between the modifiers themselves. For refer- + ence, here is a complete list of modifiers. They fall into several + groups that are described in detail in the following sections. + + /8 set UTF mode + /? disable UTF validity check + /+ show remainder of subject after match + /= show all captures (not just those that are set) + + /A set PCRE_ANCHORED + /B show compiled code + /C set PCRE_AUTO_CALLOUT + /D same as /B plus /I + /E set PCRE_DOLLAR_ENDONLY + /F flip byte order in compiled pattern + /f set PCRE_FIRSTLINE + /G find all matches (shorten string) + /g find all matches (use startoffset) + /I show information about pattern + /i set PCRE_CASELESS + /J set PCRE_DUPNAMES + /K show backtracking control names + /L set locale + /M show compiled memory size + /m set PCRE_MULTILINE + /N set PCRE_NO_AUTO_CAPTURE + /P use the POSIX wrapper + /S study the pattern after compilation + /s set PCRE_DOTALL + /T select character tables + /U set PCRE_UNGREEDY + /W set PCRE_UCP + /X set PCRE_EXTRA + /x set PCRE_EXTENDED + /Y set PCRE_NO_START_OPTIMIZE + /Z don't show lengths in /B output + + /<any> set PCRE_NEWLINE_ANY + /<anycrlf> set PCRE_NEWLINE_ANYCRLF + /<cr> set PCRE_NEWLINE_CR + /<crlf> set PCRE_NEWLINE_CRLF + /<lf> set PCRE_NEWLINE_LF + /<bsr_anycrlf> set PCRE_BSR_ANYCRLF + /<bsr_unicode> set PCRE_BSR_UNICODE + /<JS> set PCRE_JAVASCRIPT_COMPAT + + + Perl-compatible modifiers The /i, /m, /s, and /x modifiers set the PCRE_CASELESS, PCRE_MULTILINE, - PCRE_DOTALL, or PCRE_EXTENDED options, respectively, when pcre[16]_com- - pile() is called. These four modifier letters have the same effect as - they do in Perl. For example: + PCRE_DOTALL, or PCRE_EXTENDED options, respectively, when + pcre[16|32]_compile() is called. These four modifier letters have the + same effect as they do in Perl. For example: /caseless/i + + Modifiers for other PCRE options + The following table shows additional modifiers for setting PCRE com- pile-time options that do not correspond to anything in Perl: @@ -243,6 +328,9 @@ PATTERN MODIFIERS /8 PCRE_UTF16 ) when using the 16-bit /? PCRE_NO_UTF16_CHECK ) library + /8 PCRE_UTF32 ) when using the 32-bit + /? PCRE_NO_UTF32_CHECK ) library + /A PCRE_ANCHORED /C PCRE_AUTO_CALLOUT /E PCRE_DOLLAR_ENDONLY @@ -253,14 +341,14 @@ PATTERN MODIFIERS /W PCRE_UCP /X PCRE_EXTRA /Y PCRE_NO_START_OPTIMIZE - /<JS> PCRE_JAVASCRIPT_COMPAT + /<any> PCRE_NEWLINE_ANY + /<anycrlf> PCRE_NEWLINE_ANYCRLF /<cr> PCRE_NEWLINE_CR - /<lf> PCRE_NEWLINE_LF /<crlf> PCRE_NEWLINE_CRLF - /<anycrlf> PCRE_NEWLINE_ANYCRLF - /<any> PCRE_NEWLINE_ANY + /<lf> PCRE_NEWLINE_LF /<bsr_anycrlf> PCRE_BSR_ANYCRLF /<bsr_unicode> PCRE_BSR_UNICODE + /<JS> PCRE_JAVASCRIPT_COMPAT The modifiers that are enclosed in angle brackets are literal strings as shown, including the angle brackets, but the letters within can be @@ -269,10 +357,10 @@ PATTERN MODIFIERS /^abc/m<CRLF> - As well as turning on the PCRE_UTF8/16 option, the /8 modifier causes - all non-printing characters in output strings to be printed using the - \x{hh...} notation. Otherwise, those less than 0x100 are output in hex - without the curly brackets. + As well as turning on the PCRE_UTF8/16/32 option, the /8 modifier + causes all non-printing characters in output strings to be printed + using the \x{hh...} notation. Otherwise, those less than 0x100 are out- + put in hex without the curly brackets. Full details of the PCRE options are given in the pcreapi documenta- tion. @@ -283,14 +371,14 @@ PATTERN MODIFIERS requested by the /g or /G modifier. After finding a match, PCRE is called again to search the remainder of the subject string. The differ- ence between /g and /G is that the former uses the startoffset argument - to pcre[16]_exec() to start searching at a new point within the entire - string (which is in effect what Perl does), whereas the latter passes - over a shortened substring. This makes a difference to the matching - process if the pattern begins with a lookbehind assertion (including \b - or \B). - - If any call to pcre[16]_exec() in a /g or /G sequence matches an empty - string, the next call is done with the PCRE_NOTEMPTY_ATSTART and + to pcre[16|32]_exec() to start searching at a new point within the + entire string (which is in effect what Perl does), whereas the latter + passes over a shortened substring. This makes a difference to the + matching process if the pattern begins with a lookbehind assertion + (including \b or \B). + + If any call to pcre[16|32]_exec() in a /g or /G sequence matches an + empty string, the next call is done with the PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED flags set in order to search for another, non-empty, match at the same point. If this second match fails, the start offset is advanced, and the normal match is retried. This imitates the way @@ -316,10 +404,10 @@ PATTERN MODIFIERS The /= modifier requests that the values of all potential captured parentheses be output after a match. By default, only those up to the highest one actually used in the match are output (corresponding to the - return code from pcre[16]_exec()). Values in the offsets vector corre- - sponding to higher numbers should be set to -1, and these are output as - "<unset>". This modifier gives a way of checking that this is happen- - ing. + return code from pcre[16|32]_exec()). Values in the offsets vector cor- + responding to higher numbers should be set to -1, and these are output + as "<unset>". This modifier gives a way of checking that this is hap- + pening. The /B modifier is a debugging feature. It requests that pcretest out- put a representation of the compiled code after compilation. Normally @@ -341,49 +429,57 @@ PATTERN MODIFIERS The /I modifier requests that pcretest output information about the compiled pattern (whether it is anchored, has a fixed first character, - and so on). It does this by calling pcre[16]_fullinfo() after compiling - a pattern. If the pattern is studied, the results of that are also out- - put. + and so on). It does this by calling pcre[16|32]_fullinfo() after com- + piling a pattern. If the pattern is studied, the results of that are + also output. The /K modifier requests pcretest to show names from backtracking con- - trol verbs that are returned from calls to pcre[16]_exec(). It causes - pcretest to create a pcre[16]_extra block if one has not already been - created by a call to pcre[16]_study(), and to set the PCRE_EXTRA_MARK - flag and the mark field within it, every time that pcre[16]_exec() is - called. If the variable that the mark field points to is non-NULL for a - match, non-match, or partial match, pcretest prints the string to which - it points. For a match, this is shown on a line by itself, tagged with - "MK:". For a non-match it is added to the message. - - The /L modifier must be followed directly by the name of a locale, for + trol verbs that are returned from calls to pcre[16|32]_exec(). It + causes pcretest to create a pcre[16|32]_extra block if one has not + already been created by a call to pcre[16|32]_study(), and to set the + PCRE_EXTRA_MARK flag and the mark field within it, every time that + pcre[16|32]_exec() is called. If the variable that the mark field + points to is non-NULL for a match, non-match, or partial match, + pcretest prints the string to which it points. For a match, this is + shown on a line by itself, tagged with "MK:". For a non-match it is + added to the message. + + The /L modifier must be followed directly by the name of a locale, for example, /pattern/Lfr_FR For this reason, it must be the last modifier. The given locale is set, - pcre[16]_maketables() is called to build a set of character tables for - the locale, and this is then passed to pcre[16]_compile() when compil- - ing the regular expression. Without an /L (or /T) modifier, NULL is - passed as the tables pointer; that is, /L applies only to the expres- - sion on which it appears. - - The /M modifier causes the size in bytes of the memory block used to - hold the compiled pattern to be output. This does not include the size - of the pcre[16] block; it is just the actual compiled data. If the pat- - tern is successfully studied with the PCRE_STUDY_JIT_COMPILE option, + pcre[16|32]_maketables() is called to build a set of character tables + for the locale, and this is then passed to pcre[16|32]_compile() when + compiling the regular expression. Without an /L (or /T) modifier, NULL + is passed as the tables pointer; that is, /L applies only to the + expression on which it appears. + + The /M modifier causes the size in bytes of the memory block used to + hold the compiled pattern to be output. This does not include the size + of the pcre[16|32] block; it is just the actual compiled data. If the + pattern is successfully studied with the PCRE_STUDY_JIT_COMPILE option, the size of the JIT compiled code is also output. - If the /S modifier appears once, it causes pcre[16]_study() to be - called after the expression has been compiled, and the results used - when the expression is matched. If /S appears twice, it suppresses - studying, even if it was requested externally by the -s command line - option. This makes it possible to specify that certain patterns are - always studied, and others are never studied, independently of -s. This - feature is used in the test files in a few cases where the output is - different when the pattern is studied. - - If the /S modifier is immediately followed by a + character, the call - to pcre[16]_study() is made with all the JIT study options, requesting + The /S modifier causes pcre[16|32]_study() to be called after the + expression has been compiled, and the results used when the expression + is matched. There are a number of qualifying characters that may follow + /S. They may appear in any order. + + If S is followed by an exclamation mark, pcre[16|32]_study() is called + with the PCRE_STUDY_EXTRA_NEEDED option, causing it always to return a + pcre_extra block, even when studying discovers no useful information. + + If /S is followed by a second S character, it suppresses studying, even + if it was requested externally by the -s command line option. This + makes it possible to specify that certain patterns are always studied, + and others are never studied, independently of -s. This feature is used + in the test files in a few cases where the output is different when the + pattern is studied. + + If the /S modifier is followed by a + character, the call to + pcre[16|32]_study() is made with all the JIT study options, requesting just-in-time optimization support if it is available, for both normal and partial matching. If you want to restrict the JIT compiling modes, you can follow /S+ with a digit in the range 1 to 7: @@ -403,28 +499,33 @@ PATTERN MODIFIERS given immediately after /S or /S+ because this will be misinterpreted. If JIT studying is successful, the compiled JIT code will automatically - be used when pcre[16]_exec() is run, except when incompatible run-time - options are specified. For more details, see the pcrejit documentation. - See also the \J escape sequence below for a way of setting the size of - the JIT stack. - - The /T modifier must be followed by a single digit. It causes a spe- - cific set of built-in character tables to be passed to pcre[16]_com- - pile(). It is used in the standard PCRE tests to check behaviour with + be used when pcre[16|32]_exec() is run, except when incompatible run- + time options are specified. For more details, see the pcrejit documen- + tation. See also the \J escape sequence below for a way of setting the + size of the JIT stack. + + Finally, if /S is followed by a minus character, JIT compilation is + suppressed, even if it was requested externally by the -s command line + option. This makes it possible to specify that JIT is never to be used + for certain patterns. + + The /T modifier must be followed by a single digit. It causes a spe- + cific set of built-in character tables to be passed to pcre[16|32]_com- + pile(). It is used in the standard PCRE tests to check behaviour with different character tables. The digit specifies the tables as follows: 0 the default ASCII tables, as distributed in pcre_chartables.c.dist 1 a set of tables defining ISO 8859 characters - In table 1, some characters whose codes are greater than 128 are iden- + In table 1, some characters whose codes are greater than 128 are iden- tified as letters, digits, spaces, etc. Using the POSIX wrapper API - The /P modifier causes pcretest to call PCRE via the POSIX wrapper API - rather than its native API. This supports only the 8-bit library. When - /P is set, the following modifiers set options for the regcomp() func- + The /P modifier causes pcretest to call PCRE via the POSIX wrapper API + rather than its native API. This supports only the 8-bit library. When + /P is set, the following modifiers set options for the regcomp() func- tion: /i REG_ICASE @@ -435,17 +536,17 @@ PATTERN MODIFIERS /W REG_UCP ) the POSIX standard /8 REG_UTF8 ) - The /+ modifier works as described above. All other modifiers are + The /+ modifier works as described above. All other modifiers are ignored. DATA LINES - Before each data line is passed to pcre[16]_exec(), leading and trail- - ing white space is removed, and it is then scanned for \ escapes. Some - of these are pretty esoteric features, intended for checking out some - of the more complicated features of PCRE. If you are just testing - "ordinary" regular expressions, you probably don't need any of these. + Before each data line is passed to pcre[16|32]_exec(), leading and + trailing white space is removed, and it is then scanned for \ escapes. + Some of these are pretty esoteric features, intended for checking out + some of the more complicated features of PCRE. If you are just testing + "ordinary" regular expressions, you probably don't need any of these. The following escapes are recognized: \a alarm (BEL, \x07) @@ -459,16 +560,16 @@ DATA LINES \t tab (\x09) \v vertical tab (\x0b) \nnn octal character (up to 3 octal digits); always - a byte unless > 255 in UTF-8 or 16-bit mode + a byte unless > 255 in UTF-8 or 16-bit or 32-bit mode \xhh hexadecimal byte (up to 2 hex digits) \x{hh...} hexadecimal character (any number of hex digits) - \A pass the PCRE_ANCHORED option to pcre[16]_exec() - or pcre[16]_dfa_exec() - \B pass the PCRE_NOTBOL option to pcre[16]_exec() - or pcre[16]_dfa_exec() - \Cdd call pcre[16]_copy_substring() for substring dd + \A pass the PCRE_ANCHORED option to pcre[16|32]_exec() + or pcre[16|32]_dfa_exec() + \B pass the PCRE_NOTBOL option to pcre[16|32]_exec() + or pcre[16|32]_dfa_exec() + \Cdd call pcre[16|32]_copy_substring() for substring dd after a successful match (number less than 32) - \Cname call pcre[16]_copy_named_substring() for substring + \Cname call pcre[16|32]_copy_named_substring() for substring "name" after a successful match (name termin- ated by next non alphanumeric character) \C+ show the current captured substrings at callout @@ -480,88 +581,95 @@ DATA LINES reached for the nth time \C*n pass the number n (may be negative) as callout data; this is used as the callout return value - \D use the pcre[16]_dfa_exec() match function - \F only shortest match for pcre[16]_dfa_exec() - \Gdd call pcre[16]_get_substring() for substring dd + \D use the pcre[16|32]_dfa_exec() match function + \F only shortest match for pcre[16|32]_dfa_exec() + \Gdd call pcre[16|32]_get_substring() for substring dd after a successful match (number less than 32) - \Gname call pcre[16]_get_named_substring() for substring + \Gname call pcre[16|32]_get_named_substring() for substring "name" after a successful match (name termin- ated by next non-alphanumeric character) \Jdd set up a JIT stack of dd kilobytes maximum (any number of digits) - \L call pcre[16]_get_substringlist() after a + \L call pcre[16|32]_get_substringlist() after a successful match \M discover the minimum MATCH_LIMIT and MATCH_LIMIT_RECURSION settings - \N pass the PCRE_NOTEMPTY option to pcre[16]_exec() - or pcre[16]_dfa_exec(); if used twice, pass the + \N pass the PCRE_NOTEMPTY option to pcre[16|32]_exec() + or pcre[16|32]_dfa_exec(); if used twice, pass the PCRE_NOTEMPTY_ATSTART option \Odd set the size of the output vector passed to - pcre[16]_exec() to dd (any number of digits) - \P pass the PCRE_PARTIAL_SOFT option to pcre[16]_exec() - or pcre[16]_dfa_exec(); if used twice, pass the + pcre[16|32]_exec() to dd (any number of digits) + \P pass the PCRE_PARTIAL_SOFT option to pcre[16|32]_exec() + or pcre[16|32]_dfa_exec(); if used twice, pass the PCRE_PARTIAL_HARD option \Qdd set the PCRE_MATCH_LIMIT_RECURSION limit to dd (any number of digits) - \R pass the PCRE_DFA_RESTART option to pcre[16]_dfa_exec() + \R pass the PCRE_DFA_RESTART option to pcre[16|32]_dfa_exec() \S output details of memory get/free calls during matching - \Y pass the PCRE_NO_START_OPTIMIZE option to pcre[16]_exec() - or pcre[16]_dfa_exec() - \Z pass the PCRE_NOTEOL option to pcre[16]_exec() - or pcre[16]_dfa_exec() - \? pass the PCRE_NO_UTF[8|16]_CHECK option to - pcre[16]_exec() or pcre[16]_dfa_exec() + \Y pass the PCRE_NO_START_OPTIMIZE option to + pcre[16|32]_exec() + or pcre[16|32]_dfa_exec() + \Z pass the PCRE_NOTEOL option to pcre[16|32]_exec() + or pcre[16|32]_dfa_exec() + \? pass the PCRE_NO_UTF[8|16|32]_CHECK option to + pcre[16|32]_exec() or pcre[16|32]_dfa_exec() \>dd start the match at offset dd (optional "-"; then any number of digits); this sets the startoffset - argument for pcre[16]_exec() or pcre[16]_dfa_exec() - \<cr> pass the PCRE_NEWLINE_CR option to pcre[16]_exec() - or pcre[16]_dfa_exec() - \<lf> pass the PCRE_NEWLINE_LF option to pcre[16]_exec() - or pcre[16]_dfa_exec() - \<crlf> pass the PCRE_NEWLINE_CRLF option to pcre[16]_exec() - or pcre[16]_dfa_exec() - \<anycrlf> pass the PCRE_NEWLINE_ANYCRLF option to pcre[16]_exec() - or pcre[16]_dfa_exec() - \<any> pass the PCRE_NEWLINE_ANY option to pcre[16]_exec() - or pcre[16]_dfa_exec() - - The use of \x{hh...} is not dependent on the use of the /8 modifier on - the pattern. It is recognized always. There may be any number of hexa- - decimal digits inside the braces; invalid values provoke error mes- + argument for pcre[16|32]_exec() or + pcre[16|32]_dfa_exec() + \<cr> pass the PCRE_NEWLINE_CR option to pcre[16|32]_exec() + or pcre[16|32]_dfa_exec() + \<lf> pass the PCRE_NEWLINE_LF option to pcre[16|32]_exec() + or pcre[16|32]_dfa_exec() + \<crlf> pass the PCRE_NEWLINE_CRLF option to pcre[16|32]_exec() + or pcre[16|32]_dfa_exec() + \<anycrlf> pass the PCRE_NEWLINE_ANYCRLF option to pcre[16|32]_exec() + or pcre[16|32]_dfa_exec() + \<any> pass the PCRE_NEWLINE_ANY option to pcre[16|32]_exec() + or pcre[16|32]_dfa_exec() + + The use of \x{hh...} is not dependent on the use of the /8 modifier on + the pattern. It is recognized always. There may be any number of hexa- + decimal digits inside the braces; invalid values provoke error mes- sages. - Note that \xhh specifies one byte rather than one character in UTF-8 - mode; this makes it possible to construct invalid UTF-8 sequences for - testing purposes. On the other hand, \x{hh} is interpreted as a UTF-8 - character in UTF-8 mode, generating more than one byte if the value is - greater than 127. When testing the 8-bit library not in UTF-8 mode, + Note that \xhh specifies one byte rather than one character in UTF-8 + mode; this makes it possible to construct invalid UTF-8 sequences for + testing purposes. On the other hand, \x{hh} is interpreted as a UTF-8 + character in UTF-8 mode, generating more than one byte if the value is + greater than 127. When testing the 8-bit library not in UTF-8 mode, \x{hh} generates one byte for values less than 256, and causes an error for greater values. In UTF-16 mode, all 4-digit \x{hhhh} values are accepted. This makes it possible to construct invalid UTF-16 sequences for testing purposes. - The escapes that specify line ending sequences are literal strings, + In UTF-32 mode, all 4- to 8-digit \x{...} values are accepted. This + makes it possible to construct invalid UTF-32 sequences for testing + purposes. + + The escapes that specify line ending sequences are literal strings, exactly as shown. No more than one newline setting should be present in any data line. - A backslash followed by anything else just escapes the anything else. - If the very last character is a backslash, it is ignored. This gives a - way of passing an empty line as data, since a real empty line termi- + A backslash followed by anything else just escapes the anything else. + If the very last character is a backslash, it is ignored. This gives a + way of passing an empty line as data, since a real empty line termi- nates the data input. - The \J escape provides a way of setting the maximum stack size that is - used by the just-in-time optimization code. It is ignored if JIT opti- - mization is not being used. Providing a stack that is larger than the + The \J escape provides a way of setting the maximum stack size that is + used by the just-in-time optimization code. It is ignored if JIT opti- + mization is not being used. Providing a stack that is larger than the default 32K is necessary only for very complicated patterns. - If \M is present, pcretest calls pcre[16]_exec() several times, with + If \M is present, pcretest calls pcre[16|32]_exec() several times, with different values in the match_limit and match_limit_recursion fields of - the pcre[16]_extra data structure, until it finds the minimum numbers - for each parameter that allow pcre[16]_exec() to complete without - error. Because this is testing a specific feature of the normal inter- - pretive pcre[16]_exec() execution, the use of any JIT optimization that - might have been set up by the /S+ qualifier of -s+ option is disabled. + the pcre[16|32]_extra data structure, until it finds the minimum num- + bers for each parameter that allow pcre[16|32]_exec() to complete with- + out error. Because this is testing a specific feature of the normal + interpretive pcre[16|32]_exec() execution, the use of any JIT optimiza- + tion that might have been set up by the /S+ qualifier of -s+ option is + disabled. The match_limit number is a measure of the amount of backtracking that takes place, and checking it out can be instructive. For most simple @@ -574,47 +682,48 @@ DATA LINES When \O is used, the value specified may be higher or lower than the size set by the -O command line option (or defaulted to 45); \O applies - only to the call of pcre[16]_exec() for the line in which it appears. + only to the call of pcre[16|32]_exec() for the line in which it + appears. - If the /P modifier was present on the pattern, causing the POSIX wrap- - per API to be used, the only option-setting sequences that have any - effect are \B, \N, and \Z, causing REG_NOTBOL, REG_NOTEMPTY, and + If the /P modifier was present on the pattern, causing the POSIX wrap- + per API to be used, the only option-setting sequences that have any + effect are \B, \N, and \Z, causing REG_NOTBOL, REG_NOTEMPTY, and REG_NOTEOL, respectively, to be passed to regexec(). THE ALTERNATIVE MATCHING FUNCTION - By default, pcretest uses the standard PCRE matching function, - pcre[16]_exec() to match each data line. PCRE also supports an alterna- - tive matching function, pcre[16]_dfa_test(), which operates in a dif- - ferent way, and has some restrictions. The differences between the two - functions are described in the pcrematching documentation. + By default, pcretest uses the standard PCRE matching function, + pcre[16|32]_exec() to match each data line. PCRE also supports an + alternative matching function, pcre[16|32]_dfa_test(), which operates + in a different way, and has some restrictions. The differences between + the two functions are described in the pcrematching documentation. - If a data line contains the \D escape sequence, or if the command line - contains the -dfa option, the alternative matching function is used. + If a data line contains the \D escape sequence, or if the command line + contains the -dfa option, the alternative matching function is used. This function finds all possible matches at a given point. If, however, - the \F escape sequence is present in the data line, it stops after the + the \F escape sequence is present in the data line, it stops after the first match is found. This is always the shortest possible match. DEFAULT OUTPUT FROM PCRETEST - This section describes the output when the normal matching function, - pcre[16]_exec(), is being used. + This section describes the output when the normal matching function, + pcre[16|32]_exec(), is being used. When a match succeeds, pcretest outputs the list of captured substrings - that pcre[16]_exec() returns, starting with number 0 for the string - that matched the whole pattern. Otherwise, it outputs "No match" when - the return is PCRE_ERROR_NOMATCH, and "Partial match:" followed by the - partially matching substring when pcre[16]_exec() returns - PCRE_ERROR_PARTIAL. (Note that this is the entire substring that was - inspected during the partial match; it may include characters before - the actual match start if a lookbehind assertion, \K, \b, or \B was - involved.) For any other return, pcretest outputs the PCRE negative - error number and a short descriptive phrase. If the error is a failed - UTF string check, the offset of the start of the failing character and - the reason code are also output, provided that the size of the output - vector is at least two. Here is an example of an interactive pcretest + that pcre[16|32]_exec() returns, starting with number 0 for the string + that matched the whole pattern. Otherwise, it outputs "No match" when + the return is PCRE_ERROR_NOMATCH, and "Partial match:" followed by the + partially matching substring when pcre[16|32]_exec() returns + PCRE_ERROR_PARTIAL. (Note that this is the entire substring that was + inspected during the partial match; it may include characters before + the actual match start if a lookbehind assertion, \K, \b, or \B was + involved.) For any other return, pcretest outputs the PCRE negative + error number and a short descriptive phrase. If the error is a failed + UTF string check, the offset of the start of the failing character and + the reason code are also output, provided that the size of the output + vector is at least two. Here is an example of an interactive pcretest run. $ pcretest @@ -628,10 +737,10 @@ DEFAULT OUTPUT FROM PCRETEST No match Unset capturing substrings that are not followed by one that is set are - not returned by pcre[16]_exec(), and are not shown by pcretest. In the - following example, there are two capturing substrings, but when the - first data line is matched, the second, unset substring is not shown. - An "internal" unset substring is shown as "<unset>", as for the second + not returned by pcre[16|32]_exec(), and are not shown by pcretest. In + the following example, there are two capturing substrings, but when the + first data line is matched, the second, unset substring is not shown. + An "internal" unset substring is shown as "<unset>", as for the second data line. re> /(a)|(b)/ @@ -643,11 +752,11 @@ DEFAULT OUTPUT FROM PCRETEST 1: <unset> 2: b - If the strings contain any non-printing characters, they are output as - \xhh escapes if the value is less than 256 and UTF mode is not set. + If the strings contain any non-printing characters, they are output as + \xhh escapes if the value is less than 256 and UTF mode is not set. Otherwise they are output as \x{hh...} escapes. See below for the defi- - nition of non-printing characters. If the pattern has the /+ modifier, - the output for substring 0 is followed by the the rest of the subject + nition of non-printing characters. If the pattern has the /+ modifier, + the output for substring 0 is followed by the the rest of the subject string, identified by "0+" like this: re> /cat/+ @@ -655,7 +764,7 @@ DEFAULT OUTPUT FROM PCRETEST 0: cat 0+ aract - If the pattern has the /g or /G modifier, the results of successive + If the pattern has the /g or /G modifier, the results of successive matching attempts are output in sequence, like this: re> /\Bi(\w\w)/g @@ -667,32 +776,32 @@ DEFAULT OUTPUT FROM PCRETEST 0: ipp 1: pp - "No match" is output only if the first match attempt fails. Here is an - example of a failure message (the offset 4 that is specified by \>4 is + "No match" is output only if the first match attempt fails. Here is an + example of a failure message (the offset 4 that is specified by \>4 is past the end of the subject string): re> /xyz/ data> xyz\>4 Error -24 (bad offset value) - If any of the sequences \C, \G, or \L are present in a data line that - is successfully matched, the substrings extracted by the convenience + If any of the sequences \C, \G, or \L are present in a data line that + is successfully matched, the substrings extracted by the convenience functions are output with C, G, or L after the string number instead of a colon. This is in addition to the normal full list. The string length - (that is, the return from the extraction function) is given in paren- + (that is, the return from the extraction function) is given in paren- theses after each string for \C and \G. Note that whereas patterns can be continued over several lines (a plain ">" prompt is used for continuations), data lines may not. However new- - lines can be included in data by means of the \n escape (or \r, \r\n, + lines can be included in data by means of the \n escape (or \r, \r\n, etc., depending on the newline sequence setting). OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION - When the alternative matching function, pcre[16]_dfa_exec(), is used - (by means of the \D escape sequence or the -dfa command line option), - the output consists of a list of all the matches that start at the + When the alternative matching function, pcre[16|32]_dfa_exec(), is used + (by means of the \D escape sequence or the -dfa command line option), + the output consists of a list of all the matches that start at the first point in the subject where there is at least one match. For exam- ple: @@ -702,11 +811,11 @@ OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION 1: tang 2: tan - (Using the normal matching function on this data finds only "tang".) - The longest matching string is always given first (and numbered zero). + (Using the normal matching function on this data finds only "tang".) + The longest matching string is always given first (and numbered zero). After a PCRE_ERROR_PARTIAL return, the output is "Partial match:", fol- - lowed by the partially matching substring. (Note that this is the - entire substring that was inspected during the partial match; it may + lowed by the partially matching substring. (Note that this is the + entire substring that was inspected during the partial match; it may include characters before the actual match start if a lookbehind asser- tion, \K, \b, or \B was involved.) @@ -722,16 +831,16 @@ OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION 1: tan 0: tan - Since the matching function does not support substring capture, the - escape sequences that are concerned with captured substrings are not + Since the matching function does not support substring capture, the + escape sequences that are concerned with captured substrings are not relevant. RESTARTING AFTER A PARTIAL MATCH When the alternative matching function has given the PCRE_ERROR_PARTIAL - return, indicating that the subject partially matched the pattern, you - can restart the match with additional subject data by means of the \R + return, indicating that the subject partially matched the pattern, you + can restart the match with additional subject data by means of the \R escape sequence. For example: re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/ @@ -740,30 +849,30 @@ RESTARTING AFTER A PARTIAL MATCH data> n05\R\D 0: n05 - For further information about partial matching, see the pcrepartial + For further information about partial matching, see the pcrepartial documentation. CALLOUTS - If the pattern contains any callout requests, pcretest's callout func- - tion is called during matching. This works with both matching func- + If the pattern contains any callout requests, pcretest's callout func- + tion is called during matching. This works with both matching func- tions. By default, the called function displays the callout number, the - start and current positions in the text at the callout time, and the + start and current positions in the text at the callout time, and the next pattern item to be tested. For example: --->pqrabcdef 0 ^ ^ \d - This output indicates that callout number 0 occurred for a match - attempt starting at the fourth character of the subject string, when + This output indicates that callout number 0 occurred for a match + attempt starting at the fourth character of the subject string, when the pointer was at the seventh character of the data, and when the next - pattern item was \d. Just one circumflex is output if the start and + pattern item was \d. Just one circumflex is output if the start and current positions are the same. Callouts numbered 255 are assumed to be automatic callouts, inserted as - a result of the /C pattern modifier. In this case, instead of showing - the callout number, the offset in the pattern, preceded by a plus, is + a result of the /C pattern modifier. In this case, instead of showing + the callout number, the offset in the pattern, preceded by a plus, is output. For example: re> /\d?[A-E]\*/C @@ -776,7 +885,7 @@ CALLOUTS 0: E* If a pattern contains (*MARK) items, an additional line is output when- - ever a change of latest mark is passed to the callout function. For + ever a change of latest mark is passed to the callout function. For example: re> /a(*MARK:X)bc/C @@ -790,59 +899,59 @@ CALLOUTS +12 ^ ^ 0: abc - The mark changes between matching "a" and "b", but stays the same for - the rest of the match, so nothing more is output. If, as a result of - backtracking, the mark reverts to being unset, the text "<unset>" is + The mark changes between matching "a" and "b", but stays the same for + the rest of the match, so nothing more is output. If, as a result of + backtracking, the mark reverts to being unset, the text "<unset>" is output. - The callout function in pcretest returns zero (carry on matching) by - default, but you can use a \C item in a data line (as described above) + The callout function in pcretest returns zero (carry on matching) by + default, but you can use a \C item in a data line (as described above) to change this and other parameters of the callout. - Inserting callouts can be helpful when using pcretest to check compli- - cated regular expressions. For further information about callouts, see + Inserting callouts can be helpful when using pcretest to check compli- + cated regular expressions. For further information about callouts, see the pcrecallout documentation. NON-PRINTING CHARACTERS - When pcretest is outputting text in the compiled version of a pattern, - bytes other than 32-126 are always treated as non-printing characters + When pcretest is outputting text in the compiled version of a pattern, + bytes other than 32-126 are always treated as non-printing characters are are therefore shown as hex escapes. - When pcretest is outputting text that is a matched part of a subject - string, it behaves in the same way, unless a different locale has been - set for the pattern (using the /L modifier). In this case, the + When pcretest is outputting text that is a matched part of a subject + string, it behaves in the same way, unless a different locale has been + set for the pattern (using the /L modifier). In this case, the isprint() function to distinguish printing and non-printing characters. SAVING AND RELOADING COMPILED PATTERNS - The facilities described in this section are not available when the - POSIX interface to PCRE is being used, that is, when the /P pattern + The facilities described in this section are not available when the + POSIX interface to PCRE is being used, that is, when the /P pattern modifier is specified. When the POSIX interface is not in use, you can cause pcretest to write - a compiled pattern to a file, by following the modifiers with > and a + a compiled pattern to a file, by following the modifiers with > and a file name. For example: /pattern/im >/some/file - See the pcreprecompile documentation for a discussion about saving and - re-using compiled patterns. Note that if the pattern was successfully + See the pcreprecompile documentation for a discussion about saving and + re-using compiled patterns. Note that if the pattern was successfully studied with JIT optimization, the JIT data cannot be saved. - The data that is written is binary. The first eight bytes are the - length of the compiled pattern data followed by the length of the - optional study data, each written as four bytes in big-endian order - (most significant byte first). If there is no study data (either the + The data that is written is binary. The first eight bytes are the + length of the compiled pattern data followed by the length of the + optional study data, each written as four bytes in big-endian order + (most significant byte first). If there is no study data (either the pattern was not studied, or studying did not return any data), the sec- - ond length is zero. The lengths are followed by an exact copy of the - compiled pattern. If there is additional study data, this (excluding - any JIT data) follows immediately after the compiled pattern. After + ond length is zero. The lengths are followed by an exact copy of the + compiled pattern. If there is additional study data, this (excluding + any JIT data) follows immediately after the compiled pattern. After writing the file, pcretest expects to read a new pattern. - A saved pattern can be reloaded into pcretest by specifying < and a + A saved pattern can be reloaded into pcretest by specifying < and a file name instead of a pattern. The name of the file must not contain a < character, as otherwise pcretest will interpret the line as a pattern delimited by < characters. For example: @@ -851,43 +960,43 @@ SAVING AND RELOADING COMPILED PATTERNS Compiled pattern loaded from /some/file No study data - If the pattern was previously studied with the JIT optimization, the - JIT information cannot be saved and restored, and so is lost. When the - pattern has been loaded, pcretest proceeds to read data lines in the + If the pattern was previously studied with the JIT optimization, the + JIT information cannot be saved and restored, and so is lost. When the + pattern has been loaded, pcretest proceeds to read data lines in the usual way. - You can copy a file written by pcretest to a different host and reload - it there, even if the new host has opposite endianness to the one on - which the pattern was compiled. For example, you can compile on an i86 - machine and run on a SPARC machine. When a pattern is reloaded on a + You can copy a file written by pcretest to a different host and reload + it there, even if the new host has opposite endianness to the one on + which the pattern was compiled. For example, you can compile on an i86 + machine and run on a SPARC machine. When a pattern is reloaded on a host with different endianness, the confirmation message is changed to: Compiled pattern (byte-inverted) loaded from /some/file The test suite contains some saved pre-compiled patterns with different - endianness. These are reloaded using "<!" instead of just "<". This + endianness. These are reloaded using "<!" instead of just "<". This suppresses the "(byte-inverted)" text so that the output is the same on - all hosts. It also forces debugging output once the pattern has been + all hosts. It also forces debugging output once the pattern has been reloaded. - File names for saving and reloading can be absolute or relative, but - note that the shell facility of expanding a file name that starts with + File names for saving and reloading can be absolute or relative, but + note that the shell facility of expanding a file name that starts with a tilde (~) is not available. - The ability to save and reload files in pcretest is intended for test- - ing and experimentation. It is not intended for production use because - only a single pattern can be written to a file. Furthermore, there is - no facility for supplying custom character tables for use with a - reloaded pattern. If the original pattern was compiled with custom - tables, an attempt to match a subject string using a reloaded pattern - is likely to cause pcretest to crash. Finally, if you attempt to load + The ability to save and reload files in pcretest is intended for test- + ing and experimentation. It is not intended for production use because + only a single pattern can be written to a file. Furthermore, there is + no facility for supplying custom character tables for use with a + reloaded pattern. If the original pattern was compiled with custom + tables, an attempt to match a subject string using a reloaded pattern + is likely to cause pcretest to crash. Finally, if you attempt to load a file that is not in the correct format, the result is undefined. SEE ALSO - pcre(3), pcre16(3), pcreapi(3), pcrecallout(3), pcrejit, pcrematch- - ing(3), pcrepartial(d), pcrepattern(3), pcreprecompile(3). + pcre(3), pcre16(3), pcre32(3), pcreapi(3), pcrecallout(3), pcrejit, + pcrematching(3), pcrepartial(d), pcrepattern(3), pcreprecompile(3). AUTHOR @@ -899,5 +1008,5 @@ AUTHOR REVISION - Last updated: 21 February 2012 + Last updated: 10 September 2012 Copyright (c) 1997-2012 University of Cambridge. |