2589 lines
116 KiB
HTML
2589 lines
116 KiB
HTML
<html>
|
|
<head>
|
|
<title>pcre2api specification</title>
|
|
</head>
|
|
<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
|
|
<h1>pcre2api man page</h1>
|
|
<p>
|
|
Return to the <a href="index.html">PCRE2 index page</a>.
|
|
</p>
|
|
<p>
|
|
This page is part of the PCRE2 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">PCRE2 NATIVE API BASIC FUNCTIONS</a>
|
|
<li><a name="TOC2" href="#SEC2">PCRE2 NATIVE API AUXILIARY MATCH FUNCTIONS</a>
|
|
<li><a name="TOC3" href="#SEC3">PCRE2 NATIVE API GENERAL CONTEXT FUNCTIONS</a>
|
|
<li><a name="TOC4" href="#SEC4">PCRE2 NATIVE API COMPILE CONTEXT FUNCTIONS</a>
|
|
<li><a name="TOC5" href="#SEC5">PCRE2 NATIVE API MATCH CONTEXT FUNCTIONS</a>
|
|
<li><a name="TOC6" href="#SEC6">PCRE2 NATIVE API STRING EXTRACTION FUNCTIONS</a>
|
|
<li><a name="TOC7" href="#SEC7">PCRE2 NATIVE API JIT FUNCTIONS</a>
|
|
<li><a name="TOC8" href="#SEC8">PCRE2 NATIVE API AUXILIARY FUNCTIONS</a>
|
|
<li><a name="TOC9" href="#SEC9">PCRE2 8-BIT, 16-BIT, AND 32-BIT LIBRARIES</a>
|
|
<li><a name="TOC10" href="#SEC10">PCRE2 API OVERVIEW</a>
|
|
<li><a name="TOC11" href="#SEC11">NEWLINES</a>
|
|
<li><a name="TOC12" href="#SEC12">MULTITHREADING</a>
|
|
<li><a name="TOC13" href="#SEC13">PCRE2 CONTEXTS</a>
|
|
<li><a name="TOC14" href="#SEC14">CHECKING BUILD-TIME OPTIONS</a>
|
|
<li><a name="TOC15" href="#SEC15">COMPILING A PATTERN</a>
|
|
<li><a name="TOC16" href="#SEC16">COMPILATION ERROR CODES</a>
|
|
<li><a name="TOC17" href="#SEC17">JUST-IN-TIME (JIT) COMPILATION</a>
|
|
<li><a name="TOC18" href="#SEC18">LOCALE SUPPORT</a>
|
|
<li><a name="TOC19" href="#SEC19">INFORMATION ABOUT A COMPILED PATTERN</a>
|
|
<li><a name="TOC20" href="#SEC20">THE MATCH DATA BLOCK</a>
|
|
<li><a name="TOC21" href="#SEC21">MATCHING A PATTERN: THE TRADITIONAL FUNCTION</a>
|
|
<li><a name="TOC22" href="#SEC22">NEWLINE HANDLING WHEN MATCHING</a>
|
|
<li><a name="TOC23" href="#SEC23">HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS</a>
|
|
<li><a name="TOC24" href="#SEC24">EXTRACTING CAPTURED SUBSTRINGS BY NUMBER</a>
|
|
<li><a name="TOC25" href="#SEC25">EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS</a>
|
|
<li><a name="TOC26" href="#SEC26">EXTRACTING CAPTURED SUBSTRINGS BY NAME</a>
|
|
<li><a name="TOC27" href="#SEC27">DUPLICATE SUBPATTERN NAMES</a>
|
|
<li><a name="TOC28" href="#SEC28">FINDING ALL POSSIBLE MATCHES</a>
|
|
<li><a name="TOC29" href="#SEC29">MATCHING A PATTERN: THE ALTERNATIVE FUNCTION</a>
|
|
<li><a name="TOC30" href="#SEC30">SEE ALSO</a>
|
|
<li><a name="TOC31" href="#SEC31">AUTHOR</a>
|
|
<li><a name="TOC32" href="#SEC32">REVISION</a>
|
|
</ul>
|
|
<P>
|
|
<b>#include <pcre2.h></b>
|
|
<br>
|
|
<br>
|
|
PCRE2 is a new API for PCRE. This document contains a description of all its
|
|
functions. See the
|
|
<a href="pcre2.html"><b>pcre2</b></a>
|
|
document for an overview of all the PCRE2 documentation.
|
|
</P>
|
|
<br><a name="SEC1" href="#TOC1">PCRE2 NATIVE API BASIC FUNCTIONS</a><br>
|
|
<P>
|
|
<b>pcre2_code *pcre2_compile(PCRE2_SPTR <i>pattern</i>, PCRE2_SIZE <i>length</i>,</b>
|
|
<b> uint32_t <i>options</i>, int *<i>errorcode</i>, PCRE2_SIZE *<i>erroroffset,</i></b>
|
|
<b> pcre2_compile_context *<i>ccontext</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>pcre2_code_free(pcre2_code *<i>code</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>pcre2_match_data_create(uint32_t <i>ovecsize</i>,</b>
|
|
<b> pcre2_general_context *<i>gcontext</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>pcre2_match_data_create_from_pattern(pcre2_code *<i>code</i>,</b>
|
|
<b> pcre2_general_context *<i>gcontext</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre2_match(const pcre2_code *<i>code</i>, PCRE2_SPTR <i>subject</i>,</b>
|
|
<b> PCRE2_SIZE <i>length</i>, PCRE2_SIZE <i>startoffset</i>,</b>
|
|
<b> uint32_t <i>options</i>, pcre2_match_data *<i>match_data</i>,</b>
|
|
<b> pcre2_match_context *<i>mcontext</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre2_dfa_match(const pcre2_code *<i>code</i>, PCRE2_SPTR <i>subject</i>,</b>
|
|
<b> PCRE2_SIZE <i>length</i>, PCRE2_SIZE <i>startoffset</i>,</b>
|
|
<b> uint32_t <i>options</i>, pcre2_match_data *<i>match_data</i>,</b>
|
|
<b> pcre2_match_context *<i>mcontext</i>,</b>
|
|
<b> int *<i>workspace</i>, PCRE2_SIZE <i>wscount</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>void pcre2_match_data_free(pcre2_match_data *<i>match_data</i>);</b>
|
|
</P>
|
|
<br><a name="SEC2" href="#TOC1">PCRE2 NATIVE API AUXILIARY MATCH FUNCTIONS</a><br>
|
|
<P>
|
|
<b>PCRE2_SPTR pcre2_get_mark(pcre2_match_data *<i>match_data</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>uint32_t pcre2_get_ovector_count(pcre2_match_data *<i>match_data</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>PCRE2_SIZE *pcre2_get_ovector_pointer(pcre2_match_data *<i>match_data</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>PCRE2_SIZE pcre2_get_startchar(pcre2_match_data *<i>match_data</i>);</b>
|
|
</P>
|
|
<br><a name="SEC3" href="#TOC1">PCRE2 NATIVE API GENERAL CONTEXT FUNCTIONS</a><br>
|
|
<P>
|
|
<b>pcre2_general_context *pcre2_general_context_create(</b>
|
|
<b> void *(*<i>private_malloc</i>)(PCRE2_SIZE, void *),</b>
|
|
<b> void (*<i>private_free</i>)(void *, void *), void *<i>memory_data</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>pcre2_general_context *pcre2_general_context_copy(</b>
|
|
<b> pcre2_general_context *<i>gcontext</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>void pcre2_general_context_free(pcre2_general_context *<i>gcontext</i>);</b>
|
|
</P>
|
|
<br><a name="SEC4" href="#TOC1">PCRE2 NATIVE API COMPILE CONTEXT FUNCTIONS</a><br>
|
|
<P>
|
|
<b>pcre2_compile_context *pcre2_compile_context_create(</b>
|
|
<b> pcre2_general_context *<i>gcontext</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>pcre2_compile_context *pcre2_compile_context_copy(</b>
|
|
<b> pcre2_compile_context *<i>ccontext</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>void pcre2_compile_context_free(pcre2_compile_context *<i>ccontext</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre2_set_bsr(pcre2_compile_context *<i>ccontext</i>,</b>
|
|
<b> uint32_t <i>value</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre2_set_character_tables(pcre2_compile_context *<i>ccontext</i>,</b>
|
|
<b> const unsigned char *<i>tables</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre2_set_newline(pcre2_compile_context *<i>ccontext</i>,</b>
|
|
<b> uint32_t <i>value</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre2_set_parens_nest_limit(pcre2_compile_context *<i>ccontext</i>,</b>
|
|
<b> uint32_t <i>value</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre2_set_compile_recursion_guard(pcre2_compile_context *<i>ccontext</i>,</b>
|
|
<b> int (*<i>guard_function</i>)(uint32_t));</b>
|
|
</P>
|
|
<br><a name="SEC5" href="#TOC1">PCRE2 NATIVE API MATCH CONTEXT FUNCTIONS</a><br>
|
|
<P>
|
|
<b>pcre2_match_context *pcre2_match_context_create(</b>
|
|
<b> pcre2_general_context *<i>gcontext</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>pcre2_match_context *pcre2_match_context_copy(</b>
|
|
<b> pcre2_match_context *<i>mcontext</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>void pcre2_match_context_free(pcre2_match_context *<i>mcontext</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre2_set_callout(pcre2_match_context *<i>mcontext</i>,</b>
|
|
<b> int (*<i>callout_function</i>)(pcre2_callout_block *),</b>
|
|
<b> void *<i>callout_data</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre2_set_match_limit(pcre2_match_context *<i>mcontext</i>,</b>
|
|
<b> uint32_t <i>value</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre2_set_recursion_limit(pcre2_match_context *<i>mcontext</i>,</b>
|
|
<b> uint32_t <i>value</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre2_set_recursion_memory_management(</b>
|
|
<b> pcre2_match_context *<i>mcontext</i>,</b>
|
|
<b> void *(*<i>private_malloc</i>)(PCRE2_SIZE, void *),</b>
|
|
<b> void (*<i>private_free</i>)(void *, void *), void *<i>memory_data</i>);</b>
|
|
</P>
|
|
<br><a name="SEC6" href="#TOC1">PCRE2 NATIVE API STRING EXTRACTION FUNCTIONS</a><br>
|
|
<P>
|
|
<b>int pcre2_substring_copy_byname(pcre2_match_data *<i>match_data</i>,</b>
|
|
<b> PCRE2_SPTR <i>name</i>, PCRE2_UCHAR *<i>buffer</i>, PCRE2_SIZE *<i>bufflen</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre2_substring_copy_bynumber(pcre2_match_data *<i>match_data</i>,</b>
|
|
<b> unsigned int <i>number</i>, PCRE2_UCHAR *<i>buffer</i>,</b>
|
|
<b> PCRE2_SIZE *<i>bufflen</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>void pcre2_substring_free(PCRE2_UCHAR *<i>buffer</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre2_substring_get_byname(pcre2_match_data *<i>match_data</i>,</b>
|
|
<b> PCRE2_SPTR <i>name</i>, PCRE2_UCHAR **<i>bufferptr</i>, PCRE2_SIZE *<i>bufflen</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre2_substring_get_bynumber(pcre2_match_data *<i>match_data</i>,</b>
|
|
<b> unsigned int <i>number</i>, PCRE2_UCHAR **<i>bufferptr</i>,</b>
|
|
<b> PCRE2_SIZE *<i>bufflen</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre2_substring_length_byname(pcre2_match_data *<i>match_data</i>,</b>
|
|
<b> PCRE2_SPTR <i>name</i>, PCRE2_SIZE *<i>length</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre2_substring_length_bynumber(pcre2_match_data *<i>match_data</i>,</b>
|
|
<b> unsigned int <i>number</i>, PCRE2_SIZE *<i>length</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre2_substring_nametable_scan(const pcre2_code *<i>code</i>,</b>
|
|
<b> PCRE2_SPTR <i>name</i>, PCRE2_SPTR *<i>first</i>, PCRE2_SPTR *<i>last</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre2_substring_number_from_name(const pcre2_code *<i>code</i>,</b>
|
|
<b> PCRE2_SPTR <i>name</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>void pcre2_substring_list_free(PCRE2_SPTR *<i>list</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre2_substring_list_get(pcre2_match_data *<i>match_data</i>,</b>
|
|
<b>" PCRE2_UCHAR ***<i>listptr</i>, PCRE2_SIZE **<i>lengthsptr</i>);</b>
|
|
</P>
|
|
<br><a name="SEC7" href="#TOC1">PCRE2 NATIVE API JIT FUNCTIONS</a><br>
|
|
<P>
|
|
<b>int pcre2_jit_compile(pcre2_code *<i>code</i>, uint32_t <i>options</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre2_jit_match(const pcre2_code *<i>code</i>, PCRE2_SPTR <i>subject</i>,</b>
|
|
<b> PCRE2_SIZE <i>length</i>, PCRE2_SIZE <i>startoffset</i>,</b>
|
|
<b> uint32_t <i>options</i>, pcre2_match_data *<i>match_data</i>,</b>
|
|
<b> pcre2_match_context *<i>mcontext</i>, pcre2_jit_stack *<i>jit_stack</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>void pcre2_jit_free_unused_memory(pcre2_general_context *<i>gcontext</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>pcre2_jit_stack *pcre2_jit_stack_create(pcre2_general_context *<i>gcontext</i>,</b>
|
|
<b> PCRE2_SIZE <i>startsize</i>, PCRE2_SIZE <i>maxsize</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>void pcre2_jit_stack_assign(const pcre2_code *<i>code</i>,</b>
|
|
<b> pcre2_jit_callback <i>callback_function</i>, void *<i>callback_data</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>void pcre2_jit_stack_free(pcre2_jit_stack *<i>jit_stack</i>);</b>
|
|
</P>
|
|
<br><a name="SEC8" href="#TOC1">PCRE2 NATIVE API AUXILIARY FUNCTIONS</a><br>
|
|
<P>
|
|
<b>int pcre2_get_error_message(int <i>errorcode</i>, PCRE2_UCHAR *<i>buffer</i>,</b>
|
|
<b> PCRE2_SIZE <i>bufflen</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>const unsigned char *pcre2_maketables(pcre2_general_context *<i>gcontext</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre2_pattern_info(const pcre2 *<i>code</i>, uint32_t <i>what</i>, void *<i>where</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre2_config(uint32_t <i>what</i>, void *<i>where</i>);</b>
|
|
</P>
|
|
<br><a name="SEC9" href="#TOC1">PCRE2 8-BIT, 16-BIT, AND 32-BIT LIBRARIES</a><br>
|
|
<P>
|
|
There are three PCRE2 libraries, supporting 8-bit, 16-bit, and 32-bit code
|
|
units, respectively. However, there is just one header file, <b>pcre2.h</b>.
|
|
This contains the function prototypes and other definitions for all three
|
|
libraries. One, two, or all three can be installed simultaneously. On Unix-like
|
|
systems the libraries are called <b>libpcre2-8</b>, <b>libpcre2-16</b>, and
|
|
<b>libpcre2-32</b>, and they can also co-exist with the original PCRE libraries.
|
|
</P>
|
|
<P>
|
|
Character strings are passed to and from a PCRE2 library as a sequence of
|
|
unsigned integers in code units of the appropriate width. Every PCRE2 function
|
|
comes in three different forms, one for each library, for example:
|
|
<pre>
|
|
<b>pcre2_compile_8()</b>
|
|
<b>pcre2_compile_16()</b>
|
|
<b>pcre2_compile_32()</b>
|
|
</pre>
|
|
There are also three different sets of data types:
|
|
<pre>
|
|
<b>PCRE2_UCHAR8, PCRE2_UCHAR16, PCRE2_UCHAR32</b>
|
|
<b>PCRE2_SPTR8, PCRE2_SPTR16, PCRE2_SPTR32</b>
|
|
</pre>
|
|
The UCHAR types define unsigned code units of the appropriate widths. For
|
|
example, PCRE2_UCHAR16 is usually defined as `uint16_t'. The SPTR types are
|
|
constant pointers to the equivalent UCHAR types, that is, they are pointers to
|
|
vectors of unsigned code units.
|
|
</P>
|
|
<P>
|
|
Many applications use only one code unit width. For their convenience, macros
|
|
are defined whose names are the generic forms such as <b>pcre2_compile()</b> and
|
|
PCRE2_SPTR. These macros use the value of the macro PCRE2_CODE_UNIT_WIDTH to
|
|
generate the appropriate width-specific function and macro names.
|
|
PCRE2_CODE_UNIT_WIDTH is not defined by default. An application must define it
|
|
to be 8, 16, or 32 before including <b>pcre2.h</b> in order to make use of the
|
|
generic names.
|
|
</P>
|
|
<P>
|
|
Applications that use more than one code unit width can be linked with more
|
|
than one PCRE2 library, but must define PCRE2_CODE_UNIT_WIDTH to be 0 before
|
|
including <b>pcre2.h</b>, and then use the real function names. Any code that is
|
|
to be included in an environment where the value of PCRE2_CODE_UNIT_WIDTH is
|
|
unknown should also use the real function names. (Unfortunately, it is not
|
|
possible in C code to save and restore the value of a macro.)
|
|
</P>
|
|
<P>
|
|
If PCRE2_CODE_UNIT_WIDTH is not defined before including <b>pcre2.h</b>, a
|
|
compiler error occurs.
|
|
</P>
|
|
<P>
|
|
When using multiple libraries in an application, you must take care when
|
|
processing any particular pattern to use only functions from a single library.
|
|
For example, if you want to run a match using a pattern that was compiled with
|
|
<b>pcre2_compile_16()</b>, you must do so with <b>pcre2_match_16()</b>, not
|
|
<b>pcre2_match_8()</b>.
|
|
</P>
|
|
<P>
|
|
In the function summaries above, and in the rest of this document and other
|
|
PCRE2 documents, functions and data types are described using their generic
|
|
names, without the 8, 16, or 32 suffix.
|
|
</P>
|
|
<br><a name="SEC10" href="#TOC1">PCRE2 API OVERVIEW</a><br>
|
|
<P>
|
|
PCRE2 has its own native API, which is described in this document. There are
|
|
also some wrapper functions for the 8-bit library that correspond to the
|
|
POSIX regular expression API, but they do not give access to all the
|
|
functionality. They are described in the
|
|
<a href="pcre2posix.html"><b>pcre2posix</b></a>
|
|
documentation. Both these APIs define a set of C function calls.
|
|
</P>
|
|
<P>
|
|
The native API C data types, function prototypes, option values, and error
|
|
codes are defined in the header file <b>pcre2.h</b>, which contains definitions
|
|
of PCRE2_MAJOR and PCRE2_MINOR, the major and minor release numbers for the
|
|
library. Applications can use these to include support for different releases
|
|
of PCRE2.
|
|
</P>
|
|
<P>
|
|
In a Windows environment, if you want to statically link an application program
|
|
against a non-dll PCRE2 library, you must define PCRE2_STATIC before including
|
|
<b>pcre2.h</b>.
|
|
</P>
|
|
<P>
|
|
The functions <b>pcre2_compile()</b>, and <b>pcre2_match()</b> are used for
|
|
compiling and matching regular expressions in a Perl-compatible manner. A
|
|
sample program that demonstrates the simplest way of using them is provided in
|
|
the file called <i>pcre2demo.c</i> in the PCRE2 source distribution. A listing
|
|
of this program is given in the
|
|
<a href="pcre2demo.html"><b>pcre2demo</b></a>
|
|
documentation, and the
|
|
<a href="pcre2sample.html"><b>pcre2sample</b></a>
|
|
documentation describes how to compile and run it.
|
|
</P>
|
|
<P>
|
|
Just-in-time compiler support is an optional feature of PCRE2 that can be built
|
|
in appropriate hardware environments. It greatly speeds up the matching
|
|
performance of many patterns. Programs can request that it be used if
|
|
available, by calling <b>pcre2_jit_compile()</b> after a pattern has been
|
|
successfully compiled by <b>pcre2_compile()</b>. This does nothing if JIT
|
|
support is not available.
|
|
</P>
|
|
<P>
|
|
More complicated programs might need to make use of the specialist functions
|
|
<b>pcre2_jit_stack_create()</b>, <b>pcre2_jit_stack_free()</b>, and
|
|
<b>pcre2_jit_stack_assign()</b> in order to control the JIT code's memory usage.
|
|
</P>
|
|
<P>
|
|
JIT matching is automatically used by <b>pcre2_match()</b> if it is available.
|
|
There is also a direct interface for JIT matching, which gives improved
|
|
performance. The JIT-specific functions are discussed in the
|
|
<a href="pcre2jit.html"><b>pcre2jit</b></a>
|
|
documentation.
|
|
</P>
|
|
<P>
|
|
A second matching function, <b>pcre2_dfa_match()</b>, which is not
|
|
Perl-compatible, is also provided. This uses a different algorithm for the
|
|
matching. The alternative algorithm finds all possible matches (at a given
|
|
point in the subject), and scans the subject just once (unless there are
|
|
lookbehind assertions). However, this algorithm does not return captured
|
|
substrings. A description of the two matching algorithms and their advantages
|
|
and disadvantages is given in the
|
|
<a href="pcre2matching.html"><b>pcre2matching</b></a>
|
|
documentation. There is no JIT support for <b>pcre2_dfa_match()</b>.
|
|
</P>
|
|
<P>
|
|
In addition to the main compiling and matching functions, there are convenience
|
|
functions for extracting captured substrings from a subject string that is
|
|
matched by <b>pcre2_match()</b>. They are:
|
|
<pre>
|
|
<b>pcre2_substring_copy_byname()</b>
|
|
<b>pcre2_substring_copy_bynumber()</b>
|
|
<b>pcre2_substring_get_byname()</b>
|
|
<b>pcre2_substring_get_bynumber()</b>
|
|
<b>pcre2_substring_list_get()</b>
|
|
<b>pcre2_substring_length_byname()</b>
|
|
<b>pcre2_substring_length_bynumber()</b>
|
|
<b>pcre2_substring_nametable_scan()</b>
|
|
<b>pcre2_substring_number_from_name()</b>
|
|
</pre>
|
|
<b>pcre2_substring_free()</b> and <b>pcre2_substring_list_free()</b> are also
|
|
provided, to free the memory used for extracted strings.
|
|
</P>
|
|
<P>
|
|
There are functions for finding out information about a compiled pattern
|
|
(<b>pcre2_pattern_info()</b>) and about the configuration with which PCRE2 was
|
|
built (<b>pcre2_config()</b>).
|
|
<a name="newlines"></a></P>
|
|
<br><a name="SEC11" href="#TOC1">NEWLINES</a><br>
|
|
<P>
|
|
PCRE2 supports five different conventions for indicating line breaks in
|
|
strings: a single CR (carriage return) character, a single LF (linefeed)
|
|
character, the two-character sequence CRLF, any of the three preceding, or any
|
|
Unicode newline sequence. The Unicode newline sequences are the three just
|
|
mentioned, plus the single characters VT (vertical tab, U+000B), FF (form feed,
|
|
U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
|
|
(paragraph separator, U+2029).
|
|
</P>
|
|
<P>
|
|
Each of the first three conventions is used by at least one operating system as
|
|
its standard newline sequence. When PCRE2 is built, a default can be specified.
|
|
The default default is LF, which is the Unix standard. When PCRE2 is run, the
|
|
default can be overridden, either when a pattern is compiled, or when it is
|
|
matched.
|
|
</P>
|
|
<P>
|
|
The newline convention can be changed when calling <b>pcre2_compile()</b>, or it
|
|
can be specified by special text at the start of the pattern itself; this
|
|
overrides any other settings. See the
|
|
<a href="pcre2pattern.html"><b>pcre2pattern</b></a>
|
|
page for details of the special character sequences.
|
|
</P>
|
|
<P>
|
|
In the PCRE2 documentation the word "newline" is used to mean "the character or
|
|
pair of characters that indicate a line break". The choice of newline
|
|
convention affects the handling of the dot, circumflex, and dollar
|
|
metacharacters, the handling of #-comments in /x mode, and, when CRLF is a
|
|
recognized line ending sequence, the match position advancement for a
|
|
non-anchored pattern. There is more detail about this in the
|
|
<a href="#matchoptions">section on <b>pcre2_match()</b> options</a>
|
|
below.
|
|
</P>
|
|
<P>
|
|
The choice of newline convention does not affect the interpretation of
|
|
the \n or \r escape sequences, nor does it affect what \R matches, which has
|
|
its own separate control.
|
|
</P>
|
|
<br><a name="SEC12" href="#TOC1">MULTITHREADING</a><br>
|
|
<P>
|
|
In a multithreaded application it is important to keep thread-specific data
|
|
separate from data that can be shared between threads. The PCRE2 library code
|
|
itself is thread-safe: it contains no static or global variables. The API is
|
|
designed to be fairly simple for non-threaded applications while at the same
|
|
time ensuring that multithreaded applications can use it.
|
|
</P>
|
|
<P>
|
|
There are several different blocks of data that are used to pass information
|
|
between the application and the PCRE libraries.
|
|
</P>
|
|
<P>
|
|
(1) A pointer to the compiled form of a pattern is returned to the user when
|
|
<b>pcre2_compile()</b> is successful. The data in the compiled pattern is fixed,
|
|
and does not change when the pattern is matched. Therefore, it is thread-safe,
|
|
that is, the same compiled pattern can be used by more than one thread
|
|
simultaneously. An application can compile all its patterns at the start,
|
|
before forking off multiple threads that use them. However, if the just-in-time
|
|
optimization feature is being used, it needs separate memory stack areas for
|
|
each thread. See the
|
|
<a href="pcre2jit.html"><b>pcre2jit</b></a>
|
|
documentation for more details.
|
|
</P>
|
|
<P>
|
|
(2) The next section below introduces the idea of "contexts" in which PCRE2
|
|
functions are called. A context is nothing more than a collection of parameters
|
|
that control the way PCRE2 operates. Grouping a number of parameters together
|
|
in a context is a convenient way of passing them to a PCRE2 function without
|
|
using lots of arguments. The parameters that are stored in contexts are in some
|
|
sense "advanced features" of the API. Many straightforward applications will
|
|
not need to use contexts.
|
|
</P>
|
|
<P>
|
|
In a multithreaded application, if the parameters in a context are values that
|
|
are never changed, the same context can be used by all the threads. However, if
|
|
any thread needs to change any value in a context, it must make its own
|
|
thread-specific copy.
|
|
</P>
|
|
<P>
|
|
(3) The matching functions need a block of memory for working space and for
|
|
storing the results of a match. This includes details of what was matched, as
|
|
well as additional information such as the name of a (*MARK) setting. Each
|
|
thread must provide its own version of this memory.
|
|
</P>
|
|
<br><a name="SEC13" href="#TOC1">PCRE2 CONTEXTS</a><br>
|
|
<P>
|
|
Some PCRE2 functions have a lot of parameters, many of which are used only by
|
|
specialist applications, for example, those that use custom memory management
|
|
or non-standard character tables. To keep function argument lists at a
|
|
reasonable size, and at the same time to keep the API extensible, "uncommon"
|
|
parameters are passed to certain functions in a <b>context</b> instead of
|
|
directly. A context is just a block of memory that holds the parameter values.
|
|
Applications that do not need to adjust any of the context parameters can pass
|
|
NULL when a context pointer is required.
|
|
</P>
|
|
<P>
|
|
There are three different types of context: a general context that is relevant
|
|
for several PCRE2 operations, a compile-time context, and a match-time context.
|
|
</P>
|
|
<br><b>
|
|
The general context
|
|
</b><br>
|
|
<P>
|
|
At present, this context just contains pointers to (and data for) external
|
|
memory management functions that are called from several places in the PCRE2
|
|
library. The context is named `general' rather than specifically `memory'
|
|
because in future other fields may be added. If you do not want to supply your
|
|
own custom memory management functions, you do not need to bother with a
|
|
general context. A general context is created by:
|
|
<b>pcre2_general_context *pcre2_general_context_create(</b>
|
|
<b> void *(*<i>private_malloc</i>)(PCRE2_SIZE, void *),</b>
|
|
<b> void (*<i>private_free</i>)(void *, void *), void *<i>memory_data</i>);</b>
|
|
<br>
|
|
<br>
|
|
The two function pointers specify custom memory management functions, whose
|
|
prototypes are:
|
|
<pre>
|
|
<b>void *private_malloc(PCRE2_SIZE, void *);</b>
|
|
<b>void private_free(void *, void *);</b>
|
|
</pre>
|
|
Whenever code in PCRE2 calls these functions, the final argument is the value
|
|
of <i>memory_data</i>. Either of the first two arguments of the creation
|
|
function may be NULL, in which case the system memory management functions
|
|
<i>malloc()</i> and <i>free()</i> are used. (This is not currently useful, as
|
|
there are no other fields in a general context, but in future there might be.)
|
|
The <i>private_malloc()</i> function is used (if supplied) to obtain memory for
|
|
storing the context, and all three values are saved as part of the context.
|
|
</P>
|
|
<P>
|
|
Whenever PCRE2 creates a data block of any kind, the block contains a pointer
|
|
to the <i>free()</i> function that matches the <i>malloc()</i> function that was
|
|
used. When the time comes to free the block, this function is called.
|
|
</P>
|
|
<P>
|
|
A general context can be copied by calling:
|
|
<b>pcre2_general_context *pcre2_general_context_copy(</b>
|
|
<b> pcre2_general_context *<i>gcontext</i>);</b>
|
|
<br>
|
|
<br>
|
|
The memory used for a general context should be freed by calling:
|
|
<b>void pcre2_general_context_free(pcre2_general_context *<i>gcontext</i>);</b>
|
|
<a name="compilecontext"></a></P>
|
|
<br><b>
|
|
The compile context
|
|
</b><br>
|
|
<P>
|
|
A compile context is required if you want to change the default values of any
|
|
of the following compile-time parameters:
|
|
<pre>
|
|
What \R matches (Unicode newlines or CR, LF, CRLF only);
|
|
PCRE2's character tables;
|
|
The newline character sequence;
|
|
The compile time nested parentheses limit;
|
|
An external function for stack checking.
|
|
</pre>
|
|
A compile context is also required if you are using custom memory management.
|
|
If none of these apply, just pass NULL as the context argument of
|
|
<i>pcre2_compile()</i>.
|
|
</P>
|
|
<P>
|
|
A compile context is created, copied, and freed by the following functions:
|
|
<b>pcre2_compile_context *pcre2_compile_context_create(</b>
|
|
<b> pcre2_general_context *<i>gcontext</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>pcre2_compile_context *pcre2_compile_context_copy(</b>
|
|
<b> pcre2_compile_context *<i>ccontext</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>void pcre2_compile_context_free(pcre2_compile_context *<i>ccontext</i>);</b>
|
|
<br>
|
|
<br>
|
|
A compile context is created with default values for its parameters. These can
|
|
be changed by calling the following functions, which return 0 on success, or
|
|
PCRE2_ERROR_BADDATA if invalid data is detected.
|
|
<b>int pcre2_set_bsr(pcre2_compile_context *<i>ccontext</i>,</b>
|
|
<b> uint32_t <i>value</i>);</b>
|
|
<br>
|
|
<br>
|
|
The value must be PCRE2_BSR_ANYCRLF, to specify that \R matches only CR, LF,
|
|
or CRLF, or PCRE2_BSR_UNICODE, to specify that \R matches any Unicode line
|
|
ending sequence. The value of this parameter does not affect what is compiled;
|
|
it is just saved with the compiled pattern. The value is used by the JIT
|
|
compiler and by the two interpreted matching functions, <i>pcre2_match()</i> and
|
|
<i>pcre2_dfa_match()</i>.
|
|
<b>int pcre2_set_character_tables(pcre2_compile_context *<i>ccontext</i>,</b>
|
|
<b> const unsigned char *<i>tables</i>);</b>
|
|
<br>
|
|
<br>
|
|
The value must be the result of a call to <i>pcre2_maketables()</i>, whose only
|
|
argument is a general context. This function builds a set of character tables
|
|
in the current locale.
|
|
<b>int pcre2_set_newline(pcre2_compile_context *<i>ccontext</i>,</b>
|
|
<b> uint32_t <i>value</i>);</b>
|
|
<br>
|
|
<br>
|
|
This specifies which characters or character sequences are to be recognized as
|
|
newlines. The value must be one of PCRE2_NEWLINE_CR (carriage return only),
|
|
PCRE2_NEWLINE_LF (linefeed only), PCRE2_NEWLINE_CRLF (the two-character
|
|
sequence CR followed by LF), PCRE2_NEWLINE_ANYCRLF (any of the above), or
|
|
PCRE2_NEWLINE_ANY (any Unicode newline sequence).
|
|
</P>
|
|
<P>
|
|
When a pattern is compiled with the PCRE2_EXTENDED option, the value of this
|
|
parameter affects the recognition of white space and the end of internal
|
|
comments starting with #. The value is saved with the compiled pattern for
|
|
subsequent use by the JIT compiler and by the two interpreted matching
|
|
functions, <i>pcre2_match()</i> and <i>pcre2_dfa_match()</i>.
|
|
<b>int pcre2_set_parens_nest_limit(pcre2_compile_context *<i>ccontext</i>,</b>
|
|
<b> uint32_t <i>value</i>);</b>
|
|
<br>
|
|
<br>
|
|
This parameter ajusts the limit, set when PCRE2 is built (default 250), on the
|
|
depth of parenthesis nesting in a pattern. This limit stops rogue patterns
|
|
using up too much system stack when being compiled.
|
|
<b>int pcre2_set_compile_recursion_guard(pcre2_compile_context *<i>ccontext</i>,</b>
|
|
<b> int (*<i>guard_function</i>)(uint32_t));</b>
|
|
<br>
|
|
<br>
|
|
There is at least one application that runs PCRE2 in threads with very limited
|
|
system stack, where running out of stack is to be avoided at all costs. The
|
|
parenthesis limit above cannot take account of how much stack is actually
|
|
available. For a finer control, you can supply a function that is called
|
|
whenever <b>pcre2_compile()</b> starts to compile a parenthesized part of a
|
|
pattern. The argument to the function gives the current depth of nesting. The
|
|
function should return zero if all is well, or non-zero to force an error.
|
|
<a name="matchcontext"></a></P>
|
|
<br><b>
|
|
The match context
|
|
</b><br>
|
|
<P>
|
|
A match context is required if you want to change the default values of any
|
|
of the following match-time parameters:
|
|
<pre>
|
|
A callout function
|
|
The limit for calling <i>match()</i>
|
|
The limit for calling <i>match()</i> recursively
|
|
</pre>
|
|
A match context is also required if you are using custom memory management.
|
|
If none of these apply, just pass NULL as the context argument of
|
|
<b>pcre2_match()</b>, <b>pcre2_dfa_match()</b>, or <b>pcre2_jit_match()</b>.
|
|
</P>
|
|
<P>
|
|
A match context is created, copied, and freed by the following functions:
|
|
<b>pcre2_match_context *pcre2_match_context_create(</b>
|
|
<b> pcre2_general_context *<i>gcontext</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>pcre2_match_context *pcre2_match_context_copy(</b>
|
|
<b> pcre2_match_context *<i>mcontext</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>void pcre2_match_context_free(pcre2_match_context *<i>mcontext</i>);</b>
|
|
<br>
|
|
<br>
|
|
A match context is created with default values for its parameters. These can
|
|
be changed by calling the following functions, which return 0 on success, or
|
|
PCRE2_ERROR_BADDATA if invalid data is detected.
|
|
<b>int pcre2_set_callout(pcre2_match_context *<i>mcontext</i>,</b>
|
|
<b> int (*<i>callout_function</i>)(pcre2_callout_block *),</b>
|
|
<b> void *<i>callout_data</i>);</b>
|
|
<br>
|
|
<br>
|
|
This sets up a "callout" function, which PCRE2 will call at specified points
|
|
during a matching operation. Details are given in the
|
|
<a href="pcre2callout.html"><b>pcre2callout</b></a>
|
|
documentation.
|
|
<b>int pcre2_set_match_limit(pcre2_match_context *<i>mcontext</i>,</b>
|
|
<b> uint32_t <i>value</i>);</b>
|
|
<br>
|
|
<br>
|
|
The <i>match_limit</i> parameter provides a means of preventing PCRE2 from using
|
|
up too many resources 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.
|
|
</P>
|
|
<P>
|
|
Internally, <b>pcre2_match()</b> uses a function called <b>match()</b>, which it
|
|
calls repeatedly (sometimes recursively). The limit set by <i>match_limit</i> 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. This limit is not relevant to <b>pcre2_dfa_match()</b>,
|
|
which ignores it.
|
|
</P>
|
|
<P>
|
|
When <b>pcre2_match()</b> is called with a pattern that was successfully studied
|
|
with <b>pcre2_jit_compile()</b>, 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 <i>match_limit</i> value is also
|
|
used in this case (but in a different way) to limit how long the matching can
|
|
continue.
|
|
</P>
|
|
<P>
|
|
The default value for the limit can be set when PCRE2 is built; the default
|
|
default is 10 million, which handles all but the most extreme cases. If the
|
|
limit is exceeded, <b>pcre2_match()</b> returns PCRE2_ERROR_MATCHLIMIT. A value
|
|
for the match limit may also be supplied by an item at the start of a pattern
|
|
of the form
|
|
<pre>
|
|
(*LIMIT_MATCH=ddd)
|
|
</pre>
|
|
where ddd is a decimal number. However, such a setting is ignored unless ddd is
|
|
less than the limit set by the caller of <b>pcre2_match()</b> or, if no such
|
|
limit is set, less than the default.
|
|
<b>int pcre2_set_recursion_limit(pcre2_match_context *<i>mcontext</i>,</b>
|
|
<b> uint32_t <i>value</i>);</b>
|
|
<br>
|
|
<br>
|
|
The <i>recursion_limit</i> parameter is similar to <i>match_limit</i>, but
|
|
instead of limiting the total number of times that <b>match()</b> 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 <b>match()</b> are recursive.
|
|
This limit is of use only if it is set smaller than <i>match_limit</i>.
|
|
</P>
|
|
<P>
|
|
Limiting the recursion depth limits the amount of system stack that can be
|
|
used, or, when PCRE2 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 or by the
|
|
<b>pcre2_dfa_match()</b> function.
|
|
</P>
|
|
<P>
|
|
The default value for <i>recursion_limit</i> can be set when PCRE2 is built; the
|
|
default default is the same value as the default for <i>match_limit</i>. If the
|
|
limit is exceeded, <b>pcre2_match()</b> returns PCRE2_ERROR_RECURSIONLIMIT. A
|
|
value for the recursion limit may also be supplied by an item at the start of a
|
|
pattern of the form
|
|
<pre>
|
|
(*LIMIT_RECURSION=ddd)
|
|
</pre>
|
|
where ddd is a decimal number. However, such a setting is ignored unless ddd is
|
|
less than the limit set by the caller of <b>pcre2_match()</b> or, if no such
|
|
limit is set, less than the default.
|
|
<b>int pcre2_set_recursion_memory_management(</b>
|
|
<b> pcre2_match_context *<i>mcontext</i>,</b>
|
|
<b> void *(*<i>private_malloc</i>)(PCRE2_SIZE, void *),</b>
|
|
<b> void (*<i>private_free</i>)(void *, void *), void *<i>memory_data</i>);</b>
|
|
<br>
|
|
<br>
|
|
This function sets up two additional custom memory management functions for use
|
|
by <b>pcre2_match()</b> when PCRE2 is compiled to use the heap for remembering
|
|
backtracking data, instead of recursive function calls that use the system
|
|
stack. There is a discussion about PCRE2's stack usage in the
|
|
<a href="pcre2stack.html"><b>pcre2stack</b></a>
|
|
documentation. See the
|
|
<a href="pcre2build.html"><b>pcre2build</b></a>
|
|
documentation for details of how to build PCRE2. Using the heap for recursion
|
|
is a non-standard way of building PCRE2, for use in environments that have
|
|
limited stacks. Because of the greater use of memory management,
|
|
<b>pcre2_match()</b> runs more slowly. Functions that are different to the
|
|
general custom memory functions are provided so that special-purpose external
|
|
code can be used for this case, because the memory blocks are all the same
|
|
size. The blocks are retained by <b>pcre2_match()</b> until it is about to exit
|
|
so that they can be re-used when possible during the match. In the absence of
|
|
these functions, the normal custom memory management functions are used, if
|
|
supplied, otherwise the system functions.
|
|
</P>
|
|
<br><a name="SEC14" href="#TOC1">CHECKING BUILD-TIME OPTIONS</a><br>
|
|
<P>
|
|
<b>int pcre2_config(uint32_t <i>what</i>, void *<i>where</i>);</b>
|
|
</P>
|
|
<P>
|
|
The function <b>pcre2_config()</b> makes it possible for a PCRE2 client to
|
|
discover which optional features have been compiled into the PCRE2 library. The
|
|
<a href="pcre2build.html"><b>pcre2build</b></a>
|
|
documentation has more details about these optional features.
|
|
</P>
|
|
<P>
|
|
The first argument for <b>pcre2_config()</b> specifies which information is
|
|
required. The second argument is a pointer to memory into which the information
|
|
is placed. If NULL is passed, the function returns the amount of memory that is
|
|
needed for the requested information. For calls that return numerical values,
|
|
the value is in bytes; when requesting these values, <i>where</i> should point
|
|
to appropriately aligned memory. For calls that return strings, the required
|
|
length is given in code units, not counting the terminating zero.
|
|
</P>
|
|
<P>
|
|
When requesting information, the returned value from <b>pcre2_config()</b> is
|
|
non-negative on success, or the negative error code PCRE2_ERROR_BADOPTION if
|
|
the value in the first argument is not recognized. The following information is
|
|
available:
|
|
<pre>
|
|
PCRE2_CONFIG_BSR
|
|
</pre>
|
|
The output is an integer whose value indicates what character sequences the \R
|
|
escape sequence matches by default. A value of 0 means that \R matches any
|
|
Unicode line ending sequence; a value of 1 means that \R matches only CR, LF,
|
|
or CRLF. The default can be overridden when a pattern is compiled or matched.
|
|
<pre>
|
|
PCRE2_CONFIG_JIT
|
|
</pre>
|
|
The output is an integer that is set to one if support for just-in-time
|
|
compiling is available; otherwise it is set to zero.
|
|
<pre>
|
|
PCRE2_CONFIG_JITTARGET
|
|
</pre>
|
|
The <i>where</i> argument should point to a buffer that is at least 48 code
|
|
units long. (The exact length needed can be found by calling
|
|
<b>pcre2_config()</b> with <b>where</b> set to NULL.) The buffer is filled with a
|
|
string that contains the name of the architecture for which the JIT compiler is
|
|
configured, for example "x86 32bit (little endian + unaligned)". If JIT support
|
|
is not available, PCRE2_ERROR_BADOPTION is returned, otherwise the length of
|
|
the string, in code units, is returned.
|
|
<pre>
|
|
PCRE2_CONFIG_LINKSIZE
|
|
</pre>
|
|
The output is an integer that contains the number of bytes used for internal
|
|
linkage in compiled regular expressions. When PCRE2 is configured, the value
|
|
can be set to 2, 3, or 4, with the default being 2. This is the value that is
|
|
returned by <b>pcre2_config()</b>. However, when the 16-bit library is compiled,
|
|
a value of 3 is rounded up to 4, and when the 32-bit library is compiled,
|
|
internal linkages always use 4 bytes, so the configured value is not relevant.
|
|
</P>
|
|
<P>
|
|
The default value of 2 for the 8-bit and 16-bit libraries is sufficient for all
|
|
but the most massive patterns, since it allows the size of the compiled pattern
|
|
to be up to 64K code units. Larger values allow larger regular expressions to
|
|
be compiled by those two libraries, but at the expense of slower matching.
|
|
<pre>
|
|
PCRE2_CONFIG_MATCHLIMIT
|
|
</pre>
|
|
The output is an unsigned long integer that gives the default limit for the
|
|
number of internal matching function calls in a <b>pcre2_match()</b> execution.
|
|
Further details are given with <b>pcre2_match()</b> below.
|
|
<pre>
|
|
PCRE2_CONFIG_NEWLINE
|
|
</pre>
|
|
The output is an integer whose value specifies the default character sequence
|
|
that is recognized as meaning "newline". The values are:
|
|
<pre>
|
|
1 Carriage return (CR)
|
|
2 Linefeed (LF)
|
|
3 Carriage return, linefeed (CRLF)
|
|
4 Any Unicode line ending
|
|
5 Any of CR, LF, or CRLF
|
|
</pre>
|
|
The default should normally correspond to the standard sequence for your
|
|
operating system.
|
|
<pre>
|
|
PCRE2_CONFIG_PARENSLIMIT
|
|
</pre>
|
|
The output is an unsigned long integer that gives the maximum depth of nesting
|
|
of parentheses (of any kind) in a pattern. This limit is imposed to cap the
|
|
amount of system stack used when a pattern is compiled. It is specified when
|
|
PCRE2 is built; the default is 250. This limit does not take into account the
|
|
stack that may already be used by the calling application. For finer control
|
|
over compilation stack usage, see <b>pcre2_set_compile_recursion_guard()</b>.
|
|
<pre>
|
|
PCRE2_CONFIG_RECURSIONLIMIT
|
|
</pre>
|
|
The output is an unsigned long integer that gives the default limit for the
|
|
depth of recursion when calling the internal matching function in a
|
|
<b>pcre2_match()</b> execution. Further details are given with
|
|
<b>pcre2_match()</b> below.
|
|
<pre>
|
|
PCRE2_CONFIG_STACKRECURSE
|
|
</pre>
|
|
The output is an integer that is set to one if internal recursion when running
|
|
<b>pcre2_match()</b> is implemented by recursive function calls that use the
|
|
system stack to remember their state. This is the usual way that PCRE2 is
|
|
compiled. The output is zero if PCRE2 was compiled to use blocks of data on the
|
|
heap instead of recursive function calls.
|
|
<pre>
|
|
PCRE2_CONFIG_UNICODE_VERSION
|
|
</pre>
|
|
The <i>where</i> argument should point to a buffer that is at least 24 code
|
|
units long. (The exact length needed can be found by calling
|
|
<b>pcre2_config()</b> with <b>where</b> set to NULL.) If PCRE2 has been compiled
|
|
without Unicode support, the buffer is filled with the text "Unicode not
|
|
supported". Otherwise, the Unicode version string (for example, "7.0.0") is
|
|
inserted. The string is zero-terminated. The function returns the length of the
|
|
string in code units.
|
|
<pre>
|
|
PCRE2_CONFIG_UNICODE
|
|
</pre>
|
|
The output is an integer that is set to one if Unicode support is available;
|
|
otherwise it is set to zero. Unicode support implies UTF support.
|
|
<pre>
|
|
PCRE2_CONFIG_VERSION
|
|
</pre>
|
|
The <i>where</i> argument should point to a buffer that is at least 12 code
|
|
units long. (The exact length needed can be found by calling
|
|
<b>pcre2_config()</b> with <b>where</b> set to NULL.) The buffer is filled with
|
|
the PCRE2 version string, zero-terminated. The length of the string (in code
|
|
units) is returned.
|
|
<a name="compiling"></a></P>
|
|
<br><a name="SEC15" href="#TOC1">COMPILING A PATTERN</a><br>
|
|
<P>
|
|
<b>pcre2_code *pcre2_compile(PCRE2_SPTR <i>pattern</i>, PCRE2_SIZE <i>length</i>,</b>
|
|
<b> uint32_t <i>options</i>, int *<i>errorcode</i>, PCRE2_SIZE *<i>erroroffset,</i></b>
|
|
<b> pcre2_compile_context *<i>ccontext</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>pcre2_code_free(pcre2_code *<i>code</i>);</b>
|
|
</P>
|
|
<P>
|
|
This function compiles a pattern, defined by a pointer to a string of code
|
|
units and a length, into an internal form. If the pattern is zero-terminated,
|
|
the length should be specified as PCRE2_ZERO_TERMINATED. The function returns a
|
|
pointer to a block of memory that contains the compiled pattern and related
|
|
data. The caller must free the memory by calling <b>pcre2_code_free()</b> when
|
|
it is no longer needed.
|
|
</P>
|
|
<P>
|
|
If the compile context argument <i>ccontext</i> is NULL, the memory is obtained
|
|
by calling <b>malloc()</b>. Otherwise, it is obtained from the same memory
|
|
function that was used for the compile context.
|
|
</P>
|
|
<P>
|
|
The <i>options</i> argument contains various bit settings that affect the
|
|
compilation. It should be zero if no options are required. The available
|
|
options are described below. Some of them (in particular, those that are
|
|
compatible with Perl, but some others as well) can also be set and unset from
|
|
within the pattern (see the detailed description in the
|
|
<a href="pcre2pattern.html"><b>pcre2pattern</b></a>
|
|
documentation).
|
|
</P>
|
|
<P>
|
|
For those options that can be different in different parts of the pattern, the
|
|
contents of the <i>options</i> argument specifies their settings at the start of
|
|
compilation. The PCRE2_ANCHORED and PCRE2_NO_UTF_CHECK options can be set at
|
|
the time of matching as well as at compile time.
|
|
</P>
|
|
<P>
|
|
Other, less frequently required compile-time parameters (for example, the
|
|
newline setting) can be provided in a compile context (as described
|
|
<a href="#compilecontext">above).</a>
|
|
</P>
|
|
<P>
|
|
If <i>errorcode</i> or <i>erroroffset</i> is NULL, <b>pcre2_compile()</b> returns
|
|
NULL immediately. Otherwise, if compilation of a pattern fails,
|
|
<b>pcre2_compile()</b> returns NULL, having set these variables to an error code
|
|
and an offset (number of code units) within the pattern, respectively. The
|
|
<b>pcre2_get_error_message()</b> function provides a textual message for each
|
|
error code. Compilation errors are positive numbers, but UTF formatting errors
|
|
are negative numbers. For an invalid UTF-8 or UTF-16 string, the offset is that
|
|
of the first code unit of the failing character.
|
|
</P>
|
|
<P>
|
|
Some errors are not detected until the whole pattern has been scanned; in these
|
|
cases, the offset passed back is the length of the pattern. Note that the
|
|
offset is in code units, not characters, even in a UTF mode. It may sometimes
|
|
point into the middle of a UTF-8 or UTF-16 character.
|
|
</P>
|
|
<P>
|
|
This code fragment shows a typical straightforward call to
|
|
<b>pcre2_compile()</b>:
|
|
<pre>
|
|
pcre2_code *re;
|
|
PCRE2_SIZE erroffset;
|
|
int errorcode;
|
|
re = pcre2_compile(
|
|
"^A.*Z", /* the pattern */
|
|
PCRE2_ZERO_TERMINATED, /* the pattern is zero-terminated */
|
|
0, /* default options */
|
|
&errorcode, /* for error code */
|
|
&erroffset, /* for error offset */
|
|
NULL); /* no compile context */
|
|
</pre>
|
|
The following names for option bits are defined in the <b>pcre2.h</b> header
|
|
file:
|
|
<pre>
|
|
PCRE2_ANCHORED
|
|
</pre>
|
|
If this bit is set, the pattern is forced to be "anchored", that is, it is
|
|
constrained to match only at the first matching point in the string that is
|
|
being searched (the "subject string"). This effect can also be achieved by
|
|
appropriate constructs in the pattern itself, which is the only way to do it in
|
|
Perl.
|
|
<pre>
|
|
PCRE2_ALLOW_EMPTY_CLASS
|
|
</pre>
|
|
By default, for compatibility with Perl, a closing square bracket that
|
|
immediately follows an opening one is treated as a data character for the
|
|
class. When PCRE2_ALLOW_EMPTY_CLASS is set, it terminates the class, which
|
|
therefore contains no characters and so can never match.
|
|
<pre>
|
|
PCRE2_ALT_BSUX
|
|
</pre>
|
|
This option request alternative handling of three escape sequences, which
|
|
makes PCRE2's behaviour more like ECMAscript (aka JavaScript). When it is set:
|
|
</P>
|
|
<P>
|
|
(1) \U matches an upper case "U" character; by default \U causes a compile
|
|
time error (Perl uses \U to upper case subsequent characters).
|
|
</P>
|
|
<P>
|
|
(2) \u matches a lower case "u" character unless it is followed by four
|
|
hexadecimal digits, in which case the hexadecimal number defines the code point
|
|
to match. By default, \u causes a compile time error (Perl uses it to upper
|
|
case the following character).
|
|
</P>
|
|
<P>
|
|
(3) \x matches a lower case "x" character unless it is followed by two
|
|
hexadecimal digits, in which case the hexadecimal number defines the code point
|
|
to match. By default, as in Perl, a hexadecimal number is always expected after
|
|
\x, but it may have zero, one, or two digits (so, for example, \xz matches a
|
|
binary zero character followed by z).
|
|
<pre>
|
|
PCRE2_AUTO_CALLOUT
|
|
</pre>
|
|
If this bit is set, <b>pcre2_compile()</b> automatically inserts callout items,
|
|
all with number 255, before each pattern item. For discussion of the callout
|
|
facility, see the
|
|
<a href="pcre2callout.html"><b>pcre2callout</b></a>
|
|
documentation.
|
|
<pre>
|
|
PCRE2_CASELESS
|
|
</pre>
|
|
If this bit is set, letters in the pattern match both upper and lower case
|
|
letters in the subject. It is equivalent to Perl's /i option, and it can be
|
|
changed within a pattern by a (?i) option setting.
|
|
<pre>
|
|
PCRE2_DOLLAR_ENDONLY
|
|
</pre>
|
|
If this bit is set, a dollar metacharacter in the pattern matches only at the
|
|
end of the subject string. Without this option, a dollar also matches
|
|
immediately before a newline at the end of the string (but not before any other
|
|
newlines). The PCRE2_DOLLAR_ENDONLY option is ignored if PCRE2_MULTILINE is
|
|
set. There is no equivalent to this option in Perl, and no way to set it within
|
|
a pattern.
|
|
<pre>
|
|
PCRE2_DOTALL
|
|
</pre>
|
|
If this bit is set, a dot metacharacter in the pattern matches any character,
|
|
including one that indicates a newline. However, it only ever matches one
|
|
character, even if newlines are coded as CRLF. Without this option, a dot does
|
|
not match when the current position in the subject is at a newline. This option
|
|
is equivalent to Perl's /s option, and it can be changed within a pattern by a
|
|
(?s) option setting. A negative class such as [^a] always matches newline
|
|
characters, independent of the setting of this option.
|
|
<pre>
|
|
PCRE2_DUPNAMES
|
|
</pre>
|
|
If this bit is set, names used to identify capturing subpatterns need not be
|
|
unique. This can be helpful for certain types of pattern when it is known that
|
|
only one instance of the named subpattern can ever be matched. There are more
|
|
details of named subpatterns below; see also the
|
|
<a href="pcre2pattern.html"><b>pcre2pattern</b></a>
|
|
documentation.
|
|
<pre>
|
|
PCRE2_EXTENDED
|
|
</pre>
|
|
If this bit is set, most white space characters in the pattern are totally
|
|
ignored except when escaped or inside a character class. However, white space
|
|
is not allowed within sequences such as (?> that introduce various
|
|
parenthesized subpatterns, nor within numerical quantifiers such as {1,3}.
|
|
Ignorable white space is permitted between an item and a following quantifier
|
|
and between a quantifier and a following + that indicates possessiveness.
|
|
</P>
|
|
<P>
|
|
PCRE2_EXTENDED also causes characters between an unescaped # outside a
|
|
character class and the next newline, inclusive, to be ignored, which makes it
|
|
possible to include comments inside complicated patterns. Note that the end of
|
|
this type of comment is a literal newline sequence in the pattern; escape
|
|
sequences that happen to represent a newline do not count. PCRE2_EXTENDED is
|
|
equivalent to Perl's /x option, and it can be changed within a pattern by a
|
|
(?x) option setting.
|
|
</P>
|
|
<P>
|
|
Which characters are interpreted as newlines can be specified by a setting in
|
|
the compile context that is passed to <b>pcre2_compile()</b> or by a special
|
|
sequence at the start of the pattern, as described in the section entitled
|
|
<a href="pcrepattern.html#newlines">"Newline conventions"</a>
|
|
in the <b>pcre2pattern</b> documentation. A default is defined when PCRE2 is
|
|
built.
|
|
<pre>
|
|
PCRE2_FIRSTLINE
|
|
</pre>
|
|
If this option is set, an unanchored pattern is required to match before or at
|
|
the first newline in the subject string, though the matched text may continue
|
|
over the newline.
|
|
<pre>
|
|
PCRE2_MATCH_UNSET_BACKREF
|
|
</pre>
|
|
If this option is set, a back reference to an unset subpattern group matches an
|
|
empty string (by default this causes the current matching alternative to fail).
|
|
A pattern such as (\1)(a) succeeds when this option is set (assuming it can
|
|
find an "a" in the subject), whereas it fails by default, for Perl
|
|
compatibility. Setting this option makes PCRE2 behave more like ECMAscript (aka
|
|
JavaScript).
|
|
<pre>
|
|
PCRE2_MULTILINE
|
|
</pre>
|
|
By default, for the purposes of matching "start of line" and "end of line",
|
|
PCRE2 treats the subject string as consisting of a single line of characters,
|
|
even if it actually contains newlines. The "start of line" metacharacter (^)
|
|
matches only at the start of the string, and the "end of line" metacharacter
|
|
($) matches only at the end of the string, or before a terminating newline
|
|
(except when PCRE2_DOLLAR_ENDONLY is set). Note, however, that unless
|
|
PCRE2_DOTALL is set, the "any character" metacharacter (.) does not match at a
|
|
newline. This behaviour (for ^, $, and dot) is the same as Perl.
|
|
</P>
|
|
<P>
|
|
When PCRE2_MULTILINE it is set, the "start of line" and "end of line"
|
|
constructs match immediately following or immediately before internal newlines
|
|
in the subject string, respectively, as well as at the very start and end. This
|
|
is equivalent to Perl's /m option, and it can be changed within a pattern by a
|
|
(?m) option setting. If there are no newlines in a subject string, or no
|
|
occurrences of ^ or $ in a pattern, setting PCRE2_MULTILINE has no effect.
|
|
<pre>
|
|
PCRE2_NEVER_UCP
|
|
</pre>
|
|
This option locks out the use of Unicode properties for handling \B, \b, \D,
|
|
\d, \S, \s, \W, \w, and some of the POSIX character classes, as described
|
|
for the PCRE2_UCP option below. In particular, it prevents the creator of the
|
|
pattern from enabling this facility by starting the pattern with (*UCP). This
|
|
may be useful in applications that process patterns from external sources. The
|
|
option combination PCRE_UCP and PCRE_NEVER_UCP causes an error.
|
|
<pre>
|
|
PCRE2_NEVER_UTF
|
|
</pre>
|
|
This option locks out interpretation of the pattern as UTF-8, UTF-16, or
|
|
UTF-32, depending on which library is in use. In particular, it prevents the
|
|
creator of the pattern from switching to UTF interpretation by starting the
|
|
pattern with (*UTF). This may be useful in applications that process patterns
|
|
from external sources. The combination of PCRE2_UTF and PCRE2_NEVER_UTF causes
|
|
an error.
|
|
<pre>
|
|
PCRE2_NO_AUTO_CAPTURE
|
|
</pre>
|
|
If this option is set, it disables the use of numbered capturing parentheses in
|
|
the pattern. Any opening parenthesis that is not followed by ? behaves as if it
|
|
were followed by ?: but named parentheses can still be used for capturing (and
|
|
they acquire numbers in the usual way). There is no equivalent of this option
|
|
in Perl.
|
|
<pre>
|
|
PCRE2_NO_AUTO_POSSESS
|
|
</pre>
|
|
If this option is set, it disables "auto-possessification", which is an
|
|
optimization that, for example, turns a+b into a++b in order to avoid
|
|
backtracks into a+ that can never be successful. However, if callouts are in
|
|
use, auto-possessification means that some callouts are never taken. You can
|
|
set this option if you want the matching functions to do a full unoptimized
|
|
search and run all the callouts, but it is mainly provided for testing
|
|
purposes.
|
|
<pre>
|
|
PCRE2_NO_START_OPTIMIZE
|
|
</pre>
|
|
This is an option whose main effect is at matching time. It does not change
|
|
what <b>pcre2_compile()</b> generates, but it does affect the output of the JIT
|
|
compiler.
|
|
</P>
|
|
<P>
|
|
There are a number of optimizations that may occur 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, the matching code 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 pattern is not considered until after a
|
|
suitable starting point for the match has been found. Also, 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-scan of the subject that takes place before the pattern is run.
|
|
</P>
|
|
<P>
|
|
The PCRE2_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.
|
|
</P>
|
|
<P>
|
|
Setting PCRE2_NO_START_OPTIMIZE may change the outcome of a matching operation.
|
|
Consider the pattern
|
|
<pre>
|
|
(*COMMIT)ABC
|
|
</pre>
|
|
When this is compiled, PCRE2 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 pattern must match the
|
|
current starting position, which in this case, it does. However, if the same
|
|
match is run with PCRE2_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". There are also other start-up optimizations.
|
|
For example, a minimum length for the subject may be recorded. Consider the
|
|
pattern
|
|
<pre>
|
|
(*MARK:A)(X|Y)
|
|
</pre>
|
|
The minimum length for a match is one character. If the subject is "ABC", there
|
|
will be attempts to match "ABC", "BC", and "C". An attempt to match an empty
|
|
string at the end of the subject does not take place, because PCRE2 knows that
|
|
the subject is now too short, and so the (*MARK) is never encountered. In this
|
|
case, the optimization does not affect the overall match result, which is still
|
|
"no match", but it does affect the auxiliary information that is returned.
|
|
<pre>
|
|
PCRE2_NO_UTF_CHECK
|
|
</pre>
|
|
When PCRE2_UTF is set, the validity of the pattern as a UTF string is
|
|
automatically checked. There are discussions about the validity of
|
|
<a href="pcre2unicode.html#utf8strings">UTF-8 strings,</a>
|
|
<a href="pcre2unicode.html#utf16strings">UTF-16 strings,</a>
|
|
and
|
|
<a href="pcre2unicode.html#utf32strings">UTF-32 strings</a>
|
|
in the
|
|
<a href="pcre2unicode.html"><b>pcre2unicode</b></a>
|
|
document.
|
|
If an invalid UTF sequence is found, <b>pcre2_compile()</b> returns a negative
|
|
error code.
|
|
</P>
|
|
<P>
|
|
If you know that your pattern is valid, and you want to skip this check for
|
|
performance reasons, you can set the PCRE2_NO_UTF_CHECK option. When it is set,
|
|
the effect of passing an invalid UTF string as a pattern is undefined. It may
|
|
cause your program to crash or loop. Note that this option can also be passed
|
|
to <b>pcre2_match()</b> and <b>pcre_dfa_match()</b>, to suppress validity
|
|
checking of the subject string.
|
|
<pre>
|
|
PCRE2_UCP
|
|
</pre>
|
|
This option changes the way PCRE2 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 PCRE2_UCP is set, Unicode properties are used instead to
|
|
classify characters. More details are given in the section on
|
|
<a href="pcre2.html#genericchartypes">generic character types</a>
|
|
in the
|
|
<a href="pcre2pattern.html"><b>pcre2pattern</b></a>
|
|
page. If you set PCRE2_UCP, matching one of the items it affects takes much
|
|
longer. The option is available only if PCRE2 has been compiled with UTF
|
|
support.
|
|
<pre>
|
|
PCRE2_UNGREEDY
|
|
</pre>
|
|
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.
|
|
<pre>
|
|
PCRE2_UTF
|
|
</pre>
|
|
This option causes PCRE2 to regard both the pattern and the subject strings
|
|
that are subsequently processed as strings of UTF characters instead of
|
|
single-code-unit strings. However, it is available only when PCRE2 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 PCRE2 are given in the
|
|
<a href="pcre2unicode.html"><b>pcre2unicode</b></a>
|
|
page.
|
|
</P>
|
|
<br><a name="SEC16" href="#TOC1">COMPILATION ERROR CODES</a><br>
|
|
<P>
|
|
There are over 80 positive error codes that <b>pcre2_compile()</b> may return if
|
|
it finds an error in the pattern. There are also some negative error codes that
|
|
are used for invalid UTF strings. These are the same as given by
|
|
<b>pcre2_match()</b> and <b>pcre2_dfa_match()</b>, and are described in the
|
|
<a href="pcre2unicode.html"><b>pcre2unicode</b></a>
|
|
page. The <b>pcre2_get_error_message()</b> function can be called to obtain a
|
|
textual error message from any error code.
|
|
</P>
|
|
<br><a name="SEC17" href="#TOC1">JUST-IN-TIME (JIT) COMPILATION</a><br>
|
|
<P>
|
|
<b>int pcre2_jit_compile(pcre2_code *<i>code</i>, uint32_t <i>options</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre2_jit_match(const pcre2_code *<i>code</i>, PCRE2_SPTR <i>subject</i>,</b>
|
|
<b> PCRE2_SIZE <i>length</i>, PCRE2_SIZE <i>startoffset</i>,</b>
|
|
<b> uint32_t <i>options</i>, pcre2_match_data *<i>match_data</i>,</b>
|
|
<b> pcre2_match_context *<i>mcontext</i>, pcre2_jit_stack *<i>jit_stack</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>void pcre2_jit_free_unused_memory(pcre2_general_context *<i>gcontext</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>pcre2_jit_stack *pcre2_jit_stack_create(pcre2_general_context *<i>gcontext</i>,</b>
|
|
<b> PCRE2_SIZE <i>startsize</i>, PCRE2_SIZE <i>maxsize</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>void pcre2_jit_stack_assign(const pcre2_code *<i>code</i>,</b>
|
|
<b> pcre2_jit_callback <i>callback_function</i>, void *<i>callback_data</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>void pcre2_jit_stack_free(pcre2_jit_stack *<i>jit_stack</i>);</b>
|
|
</P>
|
|
<P>
|
|
These functions provide support for JIT compilation, which, if the just-in-time
|
|
compiler is available, further processes a compiled pattern into machine code
|
|
that executes much faster than the <b>pcre2_match()</b> interpretive matching
|
|
function. Full details are given in the
|
|
<a href="pcre2jit.html"><b>pcre2jit</b></a>
|
|
documentation.
|
|
</P>
|
|
<P>
|
|
JIT compilation is a heavyweight optimization. It can take some time for
|
|
patterns to be analyzed, and for one-off matches and simple patterns the
|
|
benefit of faster execution might be offset by a much slower compilation time.
|
|
Most, but not all patterns can be optimized by the JIT compiler.
|
|
<a name="localesupport"></a></P>
|
|
<br><a name="SEC18" href="#TOC1">LOCALE SUPPORT</a><br>
|
|
<P>
|
|
PCRE2 handles caseless matching, and determines whether characters are letters,
|
|
digits, or whatever, by reference to a set of tables, indexed by character code
|
|
point. When running in UTF-8 mode, or using the 16-bit or 32-bit libraries,
|
|
this applies only to characters with code points less than 256. By default,
|
|
higher-valued code points never match escapes such as \w or \d. However, if
|
|
PCRE2 is built with UTF support, all characters can be tested with \p and \P,
|
|
or, alternatively, the PCRE2_UCP option can be set when a pattern is compiled;
|
|
this causes \w and friends to use Unicode property support instead of the
|
|
built-in tables.
|
|
</P>
|
|
<P>
|
|
The use of locales with Unicode is discouraged. If you are handling characters
|
|
with code points greater than 128, you should either use Unicode support, or
|
|
use locales, but not try to mix the two.
|
|
</P>
|
|
<P>
|
|
PCRE2 contains an internal set of character tables that are used by default.
|
|
These are sufficient for many applications. Normally, the internal tables
|
|
recognize only ASCII characters. However, when PCRE2 is built, it is possible
|
|
to cause the internal tables to be rebuilt in the default "C" locale of the
|
|
local system, which may cause them to be different.
|
|
</P>
|
|
<P>
|
|
The internal tables can be overridden by tables supplied by the application
|
|
that calls PCRE2. These may be created in a different locale from the default.
|
|
As more and more applications change to using Unicode, the need for this locale
|
|
support is expected to die away.
|
|
</P>
|
|
<P>
|
|
External tables are built by calling the <b>pcre2_maketables()</b> function, in
|
|
the relevant locale. The result can be passed to <b>pcre2_compile()</b> as often
|
|
as necessary, by creating a compile context and calling
|
|
<b>pcre2_set_character_tables()</b> to set the tables pointer therein. For
|
|
example, to build and use tables that are appropriate for the French locale
|
|
(where accented characters with values greater than 128 are treated as
|
|
letters), the following code could be used:
|
|
<pre>
|
|
setlocale(LC_CTYPE, "fr_FR");
|
|
tables = pcre2_maketables(NULL);
|
|
ccontext = pcre2_compile_context_create(NULL);
|
|
pcre2_set_character_tables(ccontext, tables);
|
|
re = pcre2_compile(..., ccontext);
|
|
</pre>
|
|
The locale name "fr_FR" is used on Linux and other Unix-like systems; if you
|
|
are using Windows, the name for the French locale is "french". It is the
|
|
caller's responsibility to ensure that the memory containing the tables remains
|
|
available for as long as it is needed.
|
|
</P>
|
|
<P>
|
|
The pointer that is passed (via the compile context) to <b>pcre2_compile()</b>
|
|
is saved with the compiled pattern, and the same tables are used by
|
|
<b>pcre2_match()</b> and <b>pcre_dfa_match()</b>. Thus, for any single pattern,
|
|
compilation, and matching all happen in the same locale, but different patterns
|
|
can be processed in different locales.
|
|
<a name="infoaboutpattern"></a></P>
|
|
<br><a name="SEC19" href="#TOC1">INFORMATION ABOUT A COMPILED PATTERN</a><br>
|
|
<P>
|
|
<b>int pcre2_pattern_info(const pcre2 *<i>code</i>, uint32_t <i>what</i>, void *<i>where</i>);</b>
|
|
</P>
|
|
<P>
|
|
The <b>pcre2_pattern_info()</b> function returns information about a compiled
|
|
pattern. The first argument is a pointer to the compiled pattern. The second
|
|
argument specifies which piece of information is required, and the third
|
|
argument is a pointer to a variable to receive the data. If the third argument
|
|
is NULL, the first argument is ignored, and the function returns the size in
|
|
bytes of the variable that is required for the information requested.
|
|
Otherwise, The yield of the function is zero for success, or one of the
|
|
following negative numbers:
|
|
<pre>
|
|
PCRE2_ERROR_NULL the argument <i>code</i> was NULL
|
|
PCRE2_ERROR_BADMAGIC the "magic number" was not found
|
|
PCRE2_ERROR_BADOPTION the value of <i>what</i> was invalid
|
|
PCRE2_ERROR_UNSET the requested field is not set
|
|
</pre>
|
|
The "magic number" is placed at the start of each compiled pattern as an simple
|
|
check against passing an arbitrary memory pointer. Here is a typical call of
|
|
<b>pcre2_pattern_info()</b>, to obtain the length of the compiled pattern:
|
|
<pre>
|
|
int rc;
|
|
size_t length;
|
|
rc = pcre2_pattern_info(
|
|
re, /* result of pcre2_compile() */
|
|
PCRE2_INFO_SIZE, /* what is required */
|
|
&length); /* where to put the data */
|
|
</pre>
|
|
The possible values for the second argument are defined in <b>pcre2.h</b>, and
|
|
are as follows:
|
|
<pre>
|
|
PCRE2_INFO_ALLOPTIONS
|
|
PCRE2_INFO_ARGOPTIONS
|
|
</pre>
|
|
Return a copy of the pattern's options. The third argument should point to a
|
|
<b>uint32_t</b> variable. PCRE2_INFO_ARGOPTIONS returns exactly the options that
|
|
were passed to <b>pcre2_compile()</b>, whereas PCRE2_INFO_ALLOPTIONS returns
|
|
the compile options as 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 PCRE2_EXTENDED option, the result is PCRE2_CASELESS,
|
|
PCRE2_MULTILINE, and PCRE2_EXTENDED.
|
|
</P>
|
|
<P>
|
|
A pattern is automatically anchored by PCRE2 if all of its top-level
|
|
alternatives begin with one of the following:
|
|
<pre>
|
|
^ unless PCRE2_MULTILINE is set
|
|
\A always
|
|
\G always
|
|
.* if PCRE2_DOTALL is set and there are no back references to the subpattern in which .* appears
|
|
</pre>
|
|
For such patterns, the PCRE2_ANCHORED bit is set in the options returned for
|
|
PCRE2_INFO_ALLOPTIONS.
|
|
<pre>
|
|
PCRE2_INFO_BACKREFMAX
|
|
</pre>
|
|
Return the number of the highest back reference in the pattern. The third
|
|
argument should point to an <b>uint32_t</b> variable. Zero is returned if there
|
|
are no back references.
|
|
<pre>
|
|
PCRE2_INFO_BSR
|
|
</pre>
|
|
The output is a uint32_t whose value indicates what character sequences the \R
|
|
escape sequence matches by default. A value of 0 means that \R matches any
|
|
Unicode line ending sequence; a value of 1 means that \R matches only CR, LF,
|
|
or CRLF. The default can be overridden when a pattern is matched.
|
|
<pre>
|
|
PCRE2_INFO_CAPTURECOUNT
|
|
</pre>
|
|
Return the number of capturing subpatterns in the pattern. The third argument
|
|
should point to an <b>uint32_t</b> variable.
|
|
<pre>
|
|
PCRE2_INFO_FIRSTCODETYPE
|
|
</pre>
|
|
Return information about the first code unit of any matched string, for a
|
|
non-anchored pattern. The third argument should point to an <b>uint32_t</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 PCRE2_INFO_FIRSTCODEUNIT. If there is no fixed first value, and
|
|
if either
|
|
<br>
|
|
<br>
|
|
(a) the pattern was compiled with the PCRE2_MULTILINE option, and every branch
|
|
starts with "^", or
|
|
<br>
|
|
<br>
|
|
(b) every branch of the pattern starts with ".*" and PCRE2_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>
|
|
PCRE2_INFO_FIRSTCODEUNIT
|
|
</pre>
|
|
Return the value of the first code unit of any matched string in the situation
|
|
where PCRE2_INFO_FIRSTCODETYPE returns 1; otherwise return 0. The third
|
|
argument should point to an <b>uint32_t</b> 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.
|
|
<pre>
|
|
PCRE2_INFO_FIRSTBITMAP
|
|
</pre>
|
|
In the absence of a single first code unit for a non-anchored pattern,
|
|
<b>pcre2_compile()</b> may construct a 256-bit table that defines a fixed set of
|
|
values for the first code unit in any match. For example, a pattern that starts
|
|
with [abc] results in a table with three bits set. When code unit values
|
|
greater than 255 are supported, the flag bit for 255 means "any code unit of
|
|
value 255 or above". If such a table was constructed, a pointer to it is
|
|
returned. Otherwise NULL is returned. The third argument should point to an
|
|
<b>const uint8_t *</b> variable.
|
|
<pre>
|
|
PCRE2_INFO_HASCRORLF
|
|
</pre>
|
|
Return 1 if the pattern contains any explicit matches for CR or LF characters,
|
|
otherwise 0. The third argument should point to an <b>uint32_t</b> variable. An
|
|
explicit match is either a literal CR or LF character, or \r or \n.
|
|
<pre>
|
|
PCRE2_INFO_JCHANGED
|
|
</pre>
|
|
Return 1 if the (?J) or (?-J) option setting is used in the pattern, otherwise
|
|
0. The third argument should point to an <b>uint32_t</b> variable. (?J) and
|
|
(?-J) set and unset the local PCRE2_DUPNAMES option, respectively.
|
|
<pre>
|
|
PCRE2_INFO_JITSIZE
|
|
</pre>
|
|
If the compiled pattern was successfully processed by
|
|
<b>pcre2_jit_compile()</b>, return the size of the JIT compiled code, otherwise
|
|
return zero. The third argument should point to a <b>size_t</b> variable.
|
|
<pre>
|
|
PCRE2_INFO_LASTCODETYPE
|
|
</pre>
|
|
Returns 1 if there is a rightmost literal code unit that must exist in any
|
|
matched string, other than at its start. The third argument should point to an
|
|
<b>uint32_t</b> variable. If there is no such value, 0 is returned. When 1 is
|
|
returned, the code unit value itself can be retrieved using
|
|
PCRE2_INFO_LASTCODEUNIT.
|
|
</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 is 1 (with "z" returned from PCRE2_INFO_LASTCODEUNIT), but for
|
|
/^a\dz\d/ the returned value is 0.
|
|
<pre>
|
|
PCRE2_INFO_LASTCODEUNIT
|
|
</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
|
|
third argument should point to an <b>uint32_t</b> variable. If there is no such
|
|
value, 0 is returned.
|
|
<pre>
|
|
PCRE2_INFO_MATCHEMPTY
|
|
</pre>
|
|
Return 1 if the pattern can match an empty string, otherwise 0. The third
|
|
argument should point to an <b>uint32_t</b> variable.
|
|
<pre>
|
|
PCRE2_INFO_MATCHLIMIT
|
|
</pre>
|
|
If the pattern set a match limit by including an item of the form
|
|
(*LIMIT_MATCH=nnnn) at the start, the value is returned. The third argument
|
|
should point to an unsigned 32-bit integer. If no such value has been set, the
|
|
call to <b>pcre2_pattern_info()</b> returns the error PCRE2_ERROR_UNSET.
|
|
<pre>
|
|
PCRE2_INFO_MAXLOOKBEHIND
|
|
</pre>
|
|
Return the number of characters (not code units) in the longest lookbehind
|
|
assertion in the pattern. The third argument should point to an unsigned 32-bit
|
|
integer. This information is useful when doing multi-segment matching using the
|
|
partial matching facilities. Note that the simple assertions \b and \B
|
|
require a one-character lookbehind. \A also registers a one-character
|
|
lookbehind, though it does not actually inspect the previous character. This is
|
|
to ensure that at least one character from the old segment is retained when a
|
|
new segment is processed. Otherwise, if there are no lookbehinds in the
|
|
pattern, \A might match incorrectly at the start of a new segment.
|
|
<pre>
|
|
PCRE2_INFO_MINLENGTH
|
|
</pre>
|
|
If a minimum length for matching subject strings was computed, its value is
|
|
returned. Otherwise the returned value is 0. The value is a number of
|
|
characters, which in UTF mode may be different from the number of code units.
|
|
The third argument should point to an <b>uint32_t</b> variable. The 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.
|
|
<pre>
|
|
PCRE2_INFO_NAMECOUNT
|
|
PCRE2_INFO_NAMEENTRYSIZE
|
|
PCRE2_INFO_NAMETABLE
|
|
</pre>
|
|
PCRE2 supports the use of named as well as numbered capturing parentheses. The
|
|
names are just an additional way of identifying the parentheses, which still
|
|
acquire numbers. Several convenience functions such as
|
|
<b>pcre2_substring_get_byname()</b> are provided for extracting captured
|
|
substrings by name. It is also possible to extract the data directly, by first
|
|
converting the name to a number in order to access the correct pointers in the
|
|
output vector (described with <b>pcre2_match()</b> below). To do the conversion,
|
|
you need to use the name-to-number map, which is described by these three
|
|
values.
|
|
</P>
|
|
<P>
|
|
The map consists of a number of fixed-size entries. PCRE2_INFO_NAMECOUNT gives
|
|
the number of entries, and PCRE2_INFO_NAMEENTRYSIZE gives the size of each
|
|
entry; both of these return a <b>uint32_t</b> value. The entry size depends on
|
|
the length of the longest name. PCRE2_INFO_NAMETABLE returns a pointer to the
|
|
first entry of the table. This is a PCRE2_SPTR pointer to a block of code
|
|
units. In the 8-bit library, 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. 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>
|
|
The names are in alphabetical order. If (?| is used to create multiple groups
|
|
with the same number, as described in the
|
|
<a href="pcre2pattern.html#dupsubpatternnumber">section on duplicate subpattern numbers</a>
|
|
in the
|
|
<a href="pcre2pattern.html"><b>pcre2pattern</b></a>
|
|
page, the groups may be given the same name, but there is only one entry in the
|
|
table. Different names for groups of the same number are not permitted.
|
|
</P>
|
|
<P>
|
|
Duplicate names for subpatterns with different numbers are permitted, but only
|
|
if PCRE2_DUPNAMES is set. They appear in the table in the order in which they
|
|
were found in the pattern. In the absence of (?| this is the order of
|
|
increasing number; when (?| is used this is not necessarily the case because
|
|
later subpatterns may have lower numbers.
|
|
</P>
|
|
<P>
|
|
As a simple example of the name/number table, consider the following pattern
|
|
after compilation by the 8-bit library (assume PCRE2_EXTENDED is set, so white
|
|
space - including newlines - is ignored):
|
|
<pre>
|
|
(?<date> (?<year>(\d\d)?\d\d) - (?<month>\d\d) - (?<day>\d\d) )
|
|
</pre>
|
|
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 ??:
|
|
<pre>
|
|
00 01 d a t e 00 ??
|
|
00 05 d a y 00 ?? ??
|
|
00 04 m o n t h 00
|
|
00 02 y e a r 00 ??
|
|
</pre>
|
|
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.
|
|
<pre>
|
|
PCRE2_INFO_NEWLINE
|
|
</pre>
|
|
The output is a <b>uint32_t</b> whose value specifies the default character
|
|
sequence that will be recognized as meaning "newline" while matching. The
|
|
values are:
|
|
<pre>
|
|
1 Carriage return (CR)
|
|
2 Linefeed (LF)
|
|
3 Carriage return, linefeed (CRLF)
|
|
4 Any Unicode line ending
|
|
5 Any of CR, LF, or CRLF
|
|
</pre>
|
|
The default can be overridden when a pattern is matched.
|
|
<pre>
|
|
PCRE2_INFO_RECURSIONLIMIT
|
|
</pre>
|
|
If the pattern set a recursion limit by including an item of the form
|
|
(*LIMIT_RECURSION=nnnn) at the start, the value is returned. The third
|
|
argument should point to an unsigned 32-bit integer. If no such value has been
|
|
set, the call to <b>pcre2_pattern_info()</b> returns the error PCRE2_ERROR_UNSET.
|
|
<pre>
|
|
PCRE2_INFO_SIZE
|
|
</pre>
|
|
Return the size of the compiled pattern in bytes (for all three libraries). The
|
|
third argument should point to a <b>size_t</b> variable. This value does not
|
|
include the size of the <b>pcre2_code</b> structure that is returned by
|
|
<b>pcre_compile()</b>. The value that is used when <b>pcre2_compile()</b> is
|
|
getting memory in which to place the compiled data is the value returned by
|
|
this option plus the size of the <b>pcre2_code</b> structure. Processing a
|
|
pattern with the JIT compiler does not alter the value returned by this option.
|
|
<a name="matchdatablock"></a></P>
|
|
<br><a name="SEC20" href="#TOC1">THE MATCH DATA BLOCK</a><br>
|
|
<P>
|
|
<b>pcre2_match_data_create(uint32_t <i>ovecsize</i>,</b>
|
|
<b> pcre2_general_context *<i>gcontext</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>pcre2_match_data_create_from_pattern(pcre2_code *<i>code</i>,</b>
|
|
<b> pcre2_general_context *<i>gcontext</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>void pcre2_match_data_free(pcre2_match_data *<i>match_data</i>);</b>
|
|
</P>
|
|
<P>
|
|
Information about successful and unsuccessful matches is placed in a match
|
|
data block, which is an opaque structure that is accessed by function calls. In
|
|
particular, the match data block contains a vector of offsets into the subject
|
|
string that define the matched part of the subject and any substrings that were
|
|
capured. This is know as the <i>ovector</i>.
|
|
</P>
|
|
<P>
|
|
Before calling <b>pcre2_match()</b> or <b>pcre2_dfa_match()</b> you must create a
|
|
match data block by calling one of the creation functions above. For
|
|
<b>pcre2_match_data_create()</b>, the first argument is the number of pairs of
|
|
offsets in the <i>ovector</i>. One pair of offsets is required to identify the
|
|
string that matched the whole pattern, with another pair for each captured
|
|
substring. For example, a value of 4 creates enough space to record the matched
|
|
portion of the subject plus three captured substrings. A minimum of at least 1
|
|
pair is imposed by <b>pcre2_match_data_create()</b>, so it is always possible to
|
|
return the overall matched string.
|
|
</P>
|
|
<P>
|
|
For <b>pcre2_match_data_create_from_pattern()</b>, the first argument is a
|
|
pointer to a compiled pattern. In this case the ovector is created to be
|
|
exactly the right size to hold all the substrings a pattern might capture.
|
|
</P>
|
|
<P>
|
|
The second argument of both these functions ia a pointer to a general context,
|
|
which can specify custom memory management for obtaining the memory for the
|
|
match data block. If you are not using custom memory management, pass NULL.
|
|
</P>
|
|
<P>
|
|
A match data block can be used many times, with the same or different compiled
|
|
patterns. When it is no longer needed, it should be freed by calling
|
|
<b>pcre2_match_data_free()</b>. How to extract information from a match data
|
|
block after a match operation is described in the sections on
|
|
<a href="#matchedstrings">matched strings</a>
|
|
and
|
|
<a href="#matchotherdata">other match data</a>
|
|
below.
|
|
</P>
|
|
<br><a name="SEC21" href="#TOC1">MATCHING A PATTERN: THE TRADITIONAL FUNCTION</a><br>
|
|
<P>
|
|
<b>int pcre2_match(const pcre2_code *<i>code</i>, PCRE2_SPTR <i>subject</i>,</b>
|
|
<b> PCRE2_SIZE <i>length</i>, PCRE2_SIZE <i>startoffset</i>,</b>
|
|
<b> uint32_t <i>options</i>, pcre2_match_data *<i>match_data</i>,</b>
|
|
<b> pcre2_match_context *<i>mcontext</i>);</b>
|
|
</P>
|
|
<P>
|
|
The function <b>pcre2_match()</b> is called to match a subject string against a
|
|
compiled pattern, which is passed in the <i>code</i> argument. You can call
|
|
<b>pcre2_match()</b> with the same <i>code</i> argument as many times as you
|
|
like, in order to find multiple matches in the subject string or to match
|
|
different subject strings with the same pattern.
|
|
</P>
|
|
<P>
|
|
This function is the main matching facility of the library, and it operates in
|
|
a Perl-like manner. For specialist use there is also an alternative matching
|
|
function, which is described
|
|
<a href="#dfamatch">below</a>
|
|
in the section about the <b>pcre2_dfa_match()</b> function.
|
|
</P>
|
|
<P>
|
|
Here is an example of a simple call to <b>pcre2_match()</b>:
|
|
<pre>
|
|
pcre2_match_data *md = pcre2_match_data_create(4, NULL);
|
|
int rc = pcre2_match(
|
|
re, /* result of pcre2_compile() */
|
|
"some string", /* the subject string */
|
|
11, /* the length of the subject string */
|
|
0, /* start at offset 0 in the subject */
|
|
0, /* default options */
|
|
match_data, /* the match data block */
|
|
NULL); /* a match context; NULL means use defaults */
|
|
</pre>
|
|
If the subject string is zero-terminated, the length can be given as
|
|
PCRE2_ZERO_TERMINATED. A match context must be provided if certain less common
|
|
matching parameters are to be changed. For details, see the section on
|
|
<a href="#matchcontext">the match context</a>
|
|
above.
|
|
</P>
|
|
<br><b>
|
|
The string to be matched by <b>pcre2_match()</b>
|
|
</b><br>
|
|
<P>
|
|
The subject string is passed to <b>pcre2_match()</b> as a pointer in
|
|
<i>subject</i>, a length in <i>length</i>, and a starting offset in
|
|
<i>startoffset</i>. The length and offset are in code units, not characters.
|
|
That is, they are in bytes for the 8-bit library, 16-bit code units for the
|
|
16-bit library, and 32-bit code units for the 32-bit library, whether or not
|
|
UTF processing is enabled.
|
|
</P>
|
|
<P>
|
|
If <i>startoffset</i> is greater than the length of the subject,
|
|
<b>pcre2_match()</b> returns PCRE2_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 or UTF-16 mode, the starting offset
|
|
must point to the start of a character, or to the end of the subject (in UTF-32
|
|
mode, one code unit equals one character, so all offsets are valid). Like the
|
|
pattern string, the subject may contain binary zeroes.
|
|
</P>
|
|
<P>
|
|
A non-zero starting offset is useful when searching for another match in the
|
|
same subject by calling <b>pcre2_match()</b> again after a previous success.
|
|
Setting <i>startoffset</i> differs from passing over a shortened string and
|
|
setting PCRE2_NOTBOL in the case of a pattern that begins with any kind of
|
|
lookbehind. For example, consider the pattern
|
|
<pre>
|
|
\Biss\B
|
|
</pre>
|
|
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 <b>pcre2_match()</b> finds the first
|
|
occurrence. If <b>pcre2_match()</b> 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
|
|
<b>pcre2_match()</b> is passed the entire string again, but with
|
|
<i>startoffset</i> set to 4, it finds the second occurrence of "iss" because it
|
|
is able to look behind the starting point to discover that it is preceded by a
|
|
letter.
|
|
</P>
|
|
<P>
|
|
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 PCRE2_NOTEMPTY_ATSTART and
|
|
PCRE2_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
|
|
<a href="pcre2demo.html"><b>pcre2demo</b></a>
|
|
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.
|
|
</P>
|
|
<P>
|
|
If a non-zero starting offset is passed when the pattern is anchored, one
|
|
attempt to match at the given offset is made. This can only succeed if the
|
|
pattern does not require the match to be at the start of the subject.
|
|
<a name="matchoptions"></a></P>
|
|
<br><b>
|
|
Option bits for <b>pcre2_match()</b>
|
|
</b><br>
|
|
<P>
|
|
The unused bits of the <i>options</i> argument for <b>pcre2_match()</b> must be
|
|
zero. The only bits that may be set are PCRE2_ANCHORED, PCRE2_NOTBOL,
|
|
PCRE2_NOTEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART, PCRE2_NO_UTF_CHECK,
|
|
PCRE2_PARTIAL_HARD, and PCRE2_PARTIAL_SOFT. Their action is described below.
|
|
</P>
|
|
<P>
|
|
If the pattern was successfully processed by the just-in-time (JIT) compiler,
|
|
the only supported options for matching using the JIT code are PCRE2_NOTBOL,
|
|
PCRE2_NOTEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART, PCRE2_NO_UTF_CHECK,
|
|
PCRE2_PARTIAL_HARD, and PCRE2_PARTIAL_SOFT. If an unsupported option is used,
|
|
JIT matching is disabled and the normal interpretive code in
|
|
<b>pcre2_match()</b> is run.
|
|
<pre>
|
|
PCRE2_ANCHORED
|
|
</pre>
|
|
The PCRE2_ANCHORED option limits <b>pcre2_match()</b> to matching at the first
|
|
matching position. If a pattern was compiled with PCRE2_ANCHORED, or turned out
|
|
to be anchored by virtue of its contents, it cannot be made unachored at
|
|
matching time. Note that setting the option at match time disables JIT
|
|
matching.
|
|
<pre>
|
|
PCRE2_NOTBOL
|
|
</pre>
|
|
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 PCRE2_MULTILINE (at compile time) causes circumflex
|
|
never to match. This option affects only the behaviour of the circumflex
|
|
metacharacter. It does not affect \A.
|
|
<pre>
|
|
PCRE2_NOTEOL
|
|
</pre>
|
|
This option specifies that the end of the subject string is not the end of a
|
|
line, so the dollar metacharacter should not match it nor (except in multiline
|
|
mode) a newline immediately before it. Setting this without PCRE2_MULTILINE (at
|
|
compile time) causes dollar never to match. This option affects only the
|
|
behaviour of the dollar metacharacter. It does not affect \Z or \z.
|
|
<pre>
|
|
PCRE2_NOTEMPTY
|
|
</pre>
|
|
An empty string is not considered to be a valid match if this option is set. If
|
|
there are alternatives in the pattern, they are tried. If all the alternatives
|
|
match the empty string, the entire match fails. For example, if the pattern
|
|
<pre>
|
|
a?b?
|
|
</pre>
|
|
is applied to a string not beginning with "a" or "b", it matches an empty
|
|
string at the start of the subject. With PCRE2_NOTEMPTY set, this match is not
|
|
valid, so PCRE2 searches further into the string for occurrences of "a" or "b".
|
|
<pre>
|
|
PCRE2_NOTEMPTY_ATSTART
|
|
</pre>
|
|
This is like PCRE2_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.
|
|
<pre>
|
|
PCRE2_NO_UTF_CHECK
|
|
</pre>
|
|
When PCRE2_UTF is set at compile time, the validity of the subject as a UTF
|
|
string is checked by default when <b>pcre2_match()</b> is subsequently called.
|
|
The entire string is checked before any other processing takes place, and a
|
|
negative error code is returned if the check fails. There are several UTF error
|
|
codes for each code unit width, corresponding to different problems with the
|
|
code unit sequence. The value of <i>startoffset</i> is also checked, to ensure
|
|
that it points to the start of a character or to the end of the subject. There
|
|
are discussions about the validity of
|
|
<a href="pcre2unicode.html#utf8strings">UTF-8 strings,</a>
|
|
<a href="pcre2unicode.html#utf16strings">UTF-16 strings,</a>
|
|
and
|
|
<a href="pcre2unicode.html#utf32strings">UTF-32 strings</a>
|
|
in the
|
|
<a href="pcre2unicode.html"><b>pcre2unicode</b></a>
|
|
page.
|
|
</P>
|
|
<P>
|
|
If you know that your subject is valid, and you want to skip these checks for
|
|
performance reasons, you can set the PCRE2_NO_UTF_CHECK option when calling
|
|
<b>pcre2_match()</b>. You might want to do this for the second and subsequent
|
|
calls to <b>pcre2_match()</b> if you are making repeated calls to find all the
|
|
matches in a single subject string.
|
|
</P>
|
|
<P>
|
|
NOTE: When PCRE2_NO_UTF_CHECK is set, the effect of passing an invalid string
|
|
as a subject, or an invalid value of <i>startoffset</i>, is undefined. Your
|
|
program may crash or loop indefinitely.
|
|
<pre>
|
|
PCRE2_PARTIAL_HARD
|
|
PCRE2_PARTIAL_SOFT
|
|
</pre>
|
|
These options turn on the partial matching feature. 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
|
|
PCRE2_PARTIAL_SOFT (but not PCRE2_PARTIAL_HARD) is set, matching continues by
|
|
testing any remaining alternatives. Only if no complete match can be found is
|
|
PCRE2_ERROR_PARTIAL returned instead of PCRE2_ERROR_NOMATCH. In other words,
|
|
PCRE2_PARTIAL_SOFT says that the caller is prepared to handle a partial match,
|
|
but only if no complete match can be found.
|
|
</P>
|
|
<P>
|
|
If PCRE2_PARTIAL_HARD is set, it overrides PCRE2_PARTIAL_SOFT. In this case, if
|
|
a partial match is found, <b>pcre2_match()</b> immediately returns
|
|
PCRE2_ERROR_PARTIAL, without considering any other alternatives. In other
|
|
words, when PCRE2_PARTIAL_HARD is set, a partial match is considered to be more
|
|
important that an alternative complete match.
|
|
</P>
|
|
<P>
|
|
There is a more detailed discussion of partial and multi-segment matching, with
|
|
examples, in the
|
|
<a href="pcre2partial.html"><b>pcre2partial</b></a>
|
|
documentation.
|
|
</P>
|
|
<br><a name="SEC22" href="#TOC1">NEWLINE HANDLING WHEN MATCHING</a><br>
|
|
<P>
|
|
When PCRE2 is built, a default newline convention is set; this is usually the
|
|
standard convention for the operating system. The default can be overridden in
|
|
either a
|
|
<a href="#compilecontext">compile context</a>
|
|
or a
|
|
<a href="#matchcontext">match context.</a>
|
|
However, changing the newline convention at match time disables JIT matching.
|
|
During matching, the newline choice affects the behaviour of the dot,
|
|
circumflex, and dollar metacharacters. It may also alter the way the match
|
|
position is advanced after a match failure for an unanchored pattern.
|
|
</P>
|
|
<P>
|
|
When PCRE2_NEWLINE_CRLF, PCRE2_NEWLINE_ANYCRLF, or PCRE2_NEWLINE_ANY is set,
|
|
and a match attempt for an unanchored pattern fails when the current position
|
|
is at a CRLF sequence, and the pattern contains no explicit matches for CR or
|
|
LF characters, the match position is advanced by two characters instead of one,
|
|
in other words, to after the CRLF.
|
|
</P>
|
|
<P>
|
|
The above rule is a compromise that makes the most common cases work as
|
|
expected. For example, if the pattern is .+A (and the PCRE2_DOTALL option is
|
|
not set), it does not match the string "\r\nA" because, after failing at the
|
|
start, it skips both the CR and the LF before retrying. However, the pattern
|
|
[\r\n]A does match that string, because it contains an explicit CR or LF
|
|
reference, and so advances only by one character after the first failure.
|
|
</P>
|
|
<P>
|
|
An explicit match for CR of LF is either a literal appearance of one of those
|
|
characters in the pattern, 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).
|
|
</P>
|
|
<P>
|
|
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.
|
|
<a name="matchedstrings"></a></P>
|
|
<br><a name="SEC23" href="#TOC1">HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS</a><br>
|
|
<P>
|
|
<b>uint32_t pcre2_get_ovector_count(pcre2_match_data *<i>match_data</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>PCRE2_SIZE *pcre2_get_ovector_pointer(pcre2_match_data *<i>match_data</i>);</b>
|
|
</P>
|
|
<P>
|
|
In general, a pattern matches a certain portion of the subject, and in
|
|
addition, further substrings from the subject may be picked out by
|
|
parenthesized parts of the pattern. Following the usage in Jeffrey Friedl's
|
|
book, this is called "capturing" in what follows, and the phrase "capturing
|
|
subpattern" is used for a fragment of a pattern that picks out a substring.
|
|
PCRE2 supports several other kinds of parenthesized subpattern that do not
|
|
cause substrings to be captured. The <b>pcre2_pattern_info()</b> function can be
|
|
used to find out how many capturing subpatterns there are in a compiled
|
|
pattern.
|
|
</P>
|
|
<P>
|
|
The overall matched string and any captured substrings are returned to the
|
|
caller via a vector of PCRE2_SIZE values, called the <b>ovector</b>. This is
|
|
contained within the
|
|
<a href="#matchdatablock">match data block.</a>
|
|
You can obtain direct access to the ovector by calling
|
|
<b>pcre2_get_ovector_pointer()</b> to find its address, and
|
|
<b>pcre2_get_ovector_count()</b> to find the number of pairs of values it
|
|
contains. Alternatively, you can use the auxiliary functions for accessing
|
|
captured substrings
|
|
<a href="#extractbynumber">by number</a>
|
|
or
|
|
<a href="#extractbyname">by name</a>
|
|
(see below).
|
|
</P>
|
|
<P>
|
|
Within the ovector, the first in each pair of values is set to the offset of
|
|
the first code unit of a substring, and the second is set to the offset of the
|
|
first code unit after the end of a substring. These values are always code unit
|
|
offsets, not character offsets. That is, they are byte offsets in the 8-bit
|
|
library, 16-bit offsets in the 16-bit library, and 32-bit offsets in the 32-bit
|
|
library.
|
|
</P>
|
|
<P>
|
|
The first pair of offsets (that is, <i>ovector[0]</i> and <i>ovector[1]</i>)
|
|
identifies the portion of the subject string that was matched by the entire
|
|
pattern. The next pair is used for the first capturing subpattern, and so on.
|
|
The value returned by <b>pcre2_match()</b> is one more than the highest numbered
|
|
pair that has been set. For example, if two substrings have been captured, the
|
|
returned value is 3. If there are no capturing subpatterns, the return value
|
|
from a successful match is 1, indicating that just the first pair of offsets
|
|
has been set.
|
|
</P>
|
|
<P>
|
|
If a capturing subpattern is matched repeatedly within a single match
|
|
operation, it is the last portion of the string that it matched that is
|
|
returned.
|
|
</P>
|
|
<P>
|
|
If the ovector is too small to hold all the captured substring offsets, as much
|
|
as possible is filled in, and the function returns a value of zero. If captured
|
|
substrings are not of interest, <b>pcre2_match()</b> may be called with a match
|
|
data block whose ovector is of minimum length (that is, one pair). However, if
|
|
the pattern contains back references and the <i>ovector</i> is not big enough to
|
|
remember the related substrings, PCRE2 has to get additional memory for use
|
|
during matching. Thus it is usually advisable to set up a match data block
|
|
containing an ovector of reasonable size.
|
|
</P>
|
|
<P>
|
|
It is possible for capturing subpattern number <i>n+1</i> to match some part of
|
|
the subject when subpattern <i>n</i> has not been used at all. For example, if
|
|
the string "abc" is matched against the pattern (a|(z))(bc) the return from the
|
|
function is 4, and subpatterns 1 and 3 are matched, but 2 is not. When this
|
|
happens, both values in the offset pairs corresponding to unused subpatterns
|
|
are set to PCRE2_UNSET.
|
|
</P>
|
|
<P>
|
|
Offset values that correspond to unused subpatterns at the end of the
|
|
expression are also set to PCRE2_UNSET. 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. The offsets for for the second and third capturing
|
|
subpatterns (assuming the vector is large enough, of course) are set to
|
|
PCRE2_UNSET.
|
|
</P>
|
|
<P>
|
|
Elements in the ovector that do not correspond to capturing parentheses in the
|
|
pattern are never changed. That is, if a pattern contains <i>n</i> capturing
|
|
parentheses, no more than <i>ovector[0]</i> to <i>ovector[2n+1]</i> are set by
|
|
<b>pcre2_match()</b>. The other elements retain whatever values they previously
|
|
had.
|
|
<a name="matchotherdata"></a></P>
|
|
<br><b>
|
|
Other information about the match
|
|
</b><br>
|
|
<P>
|
|
<b>PCRE2_SPTR pcre2_get_mark(pcre2_match_data *<i>match_data</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>PCRE2_SIZE pcre2_get_startchar(pcre2_match_data *<i>match_data</i>);</b>
|
|
</P>
|
|
<P>
|
|
In addition to the offsets in the ovector, other information about a match is
|
|
retained in the match data block and can be retrieved by the above functions.
|
|
</P>
|
|
<P>
|
|
When a (*MARK) name is to be passed back, <b>pcre2_get_mark()</b> returns a
|
|
pointer to the zero-terminated name, which is within the compiled pattern.
|
|
Otherwise NULL is returned. A (*MARK) name may be available after a failed
|
|
match or a partial match, as well as after a successful one.
|
|
</P>
|
|
<P>
|
|
The code unit offset of the character at which a successful match started is
|
|
returned by <b>pcre2_get_startchar()</b>. For a non-partial match, this can be
|
|
different to the value of <i>ovector[0]</i> if the pattern contains the \K
|
|
escape sequence. After a partial match, however, this value is always the same
|
|
as <i>ovector[0]</i> because \K does not affect the result of a partial match.
|
|
<a name="errorlist"></a></P>
|
|
<br><b>
|
|
Error return values from <b>pcre2_match()</b>
|
|
</b><br>
|
|
<P>
|
|
If <b>pcre2_match()</b> fails, it returns a negative number. This can be
|
|
converted to a text string by calling <b>pcre2_get_error_message()</b>. Negative
|
|
error codes are also returned by other functions, and are documented with them.
|
|
The codes are given names in the header file. If UTF checking is in force and
|
|
an invalid UTF subject string is detected, one of a number of UTF-specific
|
|
negative error codes is returned. Details are given in the
|
|
<a href="pcre2unicode.html"><b>pcre2unicode</b></a>
|
|
page. The following are the other errors that may be returned by
|
|
<b>pcre2_match()</b>:
|
|
<pre>
|
|
PCRE2_ERROR_NOMATCH
|
|
</pre>
|
|
The subject string did not match the pattern.
|
|
<pre>
|
|
PCRE2_ERROR_PARTIAL
|
|
</pre>
|
|
The subject string did not match, but it did match partially. See the
|
|
<a href="pcre2partial.html"><b>pcre2partial</b></a>
|
|
documentation for details of partial matching.
|
|
<pre>
|
|
PCRE2_ERROR_BADMAGIC
|
|
</pre>
|
|
PCRE2 stores a 4-byte "magic number" at the start of the compiled code, to
|
|
catch the case when it is passed a junk pointer. This is the error that is
|
|
returned when the magic number is not present.
|
|
<pre>
|
|
PCRE2_ERROR_BADMODE
|
|
</pre>
|
|
This error is given when a pattern that was compiled by the 8-bit library is
|
|
passed to a 16-bit or 32-bit library function, or vice versa.
|
|
<pre>
|
|
PCRE2_ERROR_BADOFFSET
|
|
</pre>
|
|
The value of <i>startoffset</i> greater than the length of the subject.
|
|
<pre>
|
|
PCRE2_ERROR_BADOPTION
|
|
</pre>
|
|
An unrecognized bit was set in the <i>options</i> argument.
|
|
<pre>
|
|
PCRE2_ERROR_BADUTFOFFSET
|
|
</pre>
|
|
The UTF code unit sequence that was passed as a subject was checked and found
|
|
to be valid (the PCRE2_NO_UTF_CHECK option was not set), but the value of
|
|
<i>startoffset</i> did not point to the beginning of a UTF character or the end
|
|
of the subject.
|
|
<pre>
|
|
PCRE2_ERROR_CALLOUT
|
|
</pre>
|
|
This error is never generated by <b>pcre2_match()</b> itself. It is provided for
|
|
use by callout functions that want to cause <b>pcre2_match()</b> to return a
|
|
distinctive error code. See the
|
|
<a href="pcre2callout.html"><b>pcre2callout</b></a>
|
|
documentation for details.
|
|
<pre>
|
|
PCRE2_ERROR_INTERNAL
|
|
</pre>
|
|
An unexpected internal error has occurred. This error could be caused by a bug
|
|
in PCRE2 or by overwriting of the compiled pattern.
|
|
<pre>
|
|
PCRE2_ERROR_JIT_BADOPTION
|
|
</pre>
|
|
This error is returned when a pattern that was successfully studied using JIT
|
|
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="pcre2jit.html"><b>pcre2jit</b></a>
|
|
documentation for more details.
|
|
<pre>
|
|
PCRE2_ERROR_JIT_STACKLIMIT
|
|
</pre>
|
|
This error is returned when a pattern that was successfully studied using JIT
|
|
is being matched, but the memory available for the just-in-time processing
|
|
stack is not large enough. See the
|
|
<a href="pcre2jit.html"><b>pcre2jit</b></a>
|
|
documentation for more details.
|
|
<pre>
|
|
PCRE2_ERROR_MATCHLIMIT
|
|
</pre>
|
|
The backtracking limit was reached.
|
|
<pre>
|
|
PCRE2_ERROR_NOMEMORY
|
|
</pre>
|
|
If a pattern contains back references, but the ovector is not big enough to
|
|
remember the referenced substrings, PCRE2 gets a block of memory at the start
|
|
of matching to use for this purpose. There are some other special cases where
|
|
extra memory is needed during matching. This error is given when memory cannot
|
|
be obtained.
|
|
<pre>
|
|
PCRE2_ERROR_NULL
|
|
</pre>
|
|
Either the <i>code</i>, <i>subject</i>, or <i>match_data</i> argument was passed
|
|
as NULL.
|
|
<pre>
|
|
PCRE2_ERROR_RECURSELOOP
|
|
</pre>
|
|
This error is returned when <b>pcre2_match()</b> 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 position
|
|
in the subject string. Some simple patterns that might do this are detected and
|
|
faulted at compile time, but more complicated cases, in particular mutual
|
|
recursions between two different subpatterns, cannot be detected until run
|
|
time.
|
|
<pre>
|
|
PCRE2_ERROR_RECURSIONLIMIT
|
|
</pre>
|
|
The internal recursion limit was reached.
|
|
<a name="extractbynumber"></a></P>
|
|
<br><a name="SEC24" href="#TOC1">EXTRACTING CAPTURED SUBSTRINGS BY NUMBER</a><br>
|
|
<P>
|
|
<b>int pcre2_substring_length_bynumber(pcre2_match_data *<i>match_data</i>,</b>
|
|
<b> unsigned int <i>number</i>, PCRE2_SIZE *<i>length</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre2_substring_copy_bynumber(pcre2_match_data *<i>match_data</i>,</b>
|
|
<b> unsigned int <i>number</i>, PCRE2_UCHAR *<i>buffer</i>,</b>
|
|
<b> PCRE2_SIZE *<i>bufflen</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre2_substring_get_bynumber(pcre2_match_data *<i>match_data</i>,</b>
|
|
<b> unsigned int <i>number</i>, PCRE2_UCHAR **<i>bufferptr</i>,</b>
|
|
<b> PCRE2_SIZE *<i>bufflen</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>void pcre2_substring_free(PCRE2_UCHAR *<i>buffer</i>);</b>
|
|
</P>
|
|
<P>
|
|
Captured substrings can be accessed directly by using the ovector as described
|
|
<a href="#matchedstrings">above.</a>
|
|
For convenience, auxiliary functions are provided for extracting captured
|
|
substrings as new, separate, zero-terminated strings. The functions in this
|
|
section identify substrings by number. The next section describes similar
|
|
functions for extracting substrings by name. 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.
|
|
</P>
|
|
<P>
|
|
You can find the length in code units of a captured substring without
|
|
extracting it by calling <b>pcre2_substring_length_bynumber()</b>. The first
|
|
argument is a pointer to the match data block, the second is the group number,
|
|
and the third is a pointer to a variable into which the length is placed.
|
|
</P>
|
|
<P>
|
|
The <b>pcre2_substring_copy_bynumber()</b> function copies one string into a
|
|
supplied buffer, whereas <b>pcre2_substring_get_bynumber()</b> copies it into
|
|
new memory, obtained using the same memory allocation function that was used
|
|
for the match data block. The first two arguments of these functions are a
|
|
pointer to the match data block and a capturing group number. A group number of
|
|
zero extracts the substring that matched the entire pattern, and higher values
|
|
extract the captured substrings.
|
|
</P>
|
|
<P>
|
|
The final arguments of <b>pcre2_substring_copy_bynumber()</b> are a pointer to
|
|
the buffer and a pointer to a variable that contains its length in code units.
|
|
This is updated to contain the actual number of code units used, excluding the
|
|
terminating zero.
|
|
</P>
|
|
<P>
|
|
For <b>pcre2_substring_get_bynumber()</b> the third and fourth arguments point
|
|
to variables that are updated with a pointer to the new memory and the number
|
|
of code units that comprise the substring, again excluding the terminating
|
|
zero. When the substring is no longer needed, the memory should be freed by
|
|
calling <b>pcre2_substring_free()</b>.
|
|
</P>
|
|
<P>
|
|
The return value from these functions is zero for success, or one of these
|
|
error codes:
|
|
<pre>
|
|
PCRE2_ERROR_NOMEMORY
|
|
</pre>
|
|
The buffer was too small for <b>pcre2_substring_copy_bynumber()</b>, or the
|
|
attempt to get memory failed for <b>pcre2_substring_get_bynumber()</b>.
|
|
<pre>
|
|
PCRE2_ERROR_NOSUBSTRING
|
|
</pre>
|
|
No substring with the given number was captured. This could be because there is
|
|
no capturing group of that number in the pattern, or because the group with
|
|
that number did not participate in the match, or because the ovector was too
|
|
small to capture that group.
|
|
</P>
|
|
<br><a name="SEC25" href="#TOC1">EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS</a><br>
|
|
<P>
|
|
<b>int pcre2_substring_list_get(pcre2_match_data *<i>match_data</i>,</b>
|
|
<b>" PCRE2_UCHAR ***<i>listptr</i>, PCRE2_SIZE **<i>lengthsptr</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>void pcre2_substring_list_free(PCRE2_SPTR *<i>list</i>);</b>
|
|
</P>
|
|
<P>
|
|
The <b>pcre2_substring_list_get()</b> function extracts all available substrings
|
|
and builds a list of pointers to them, and a second list that contains their
|
|
lengths (in code units), excluding a terminating zero that is added to each of
|
|
them. All this is done in a single block of memory that is obtained using the
|
|
same memory allocation function that was used to get the match data block.
|
|
</P>
|
|
<P>
|
|
The address of the memory block is returned via <i>listptr</i>, which is also
|
|
the start of the list of string pointers. The end of the list is marked by a
|
|
NULL pointer. The address of the list of lengths is returned via
|
|
<i>lengthsptr</i>. If your strings do not contain binary zeros and you do not
|
|
therefore need the lengths, you may supply NULL as the <b>lengthsptr</b>
|
|
argument to disable the creation of a list of lengths. The yield of the
|
|
function is zero if all went well, or PCRE2_ERROR_NOMEMORY if the memory block
|
|
could not be obtained. When the list is no longer needed, it should be freed by
|
|
calling <b>pcre2_substring_list_free()</b>.
|
|
</P>
|
|
<P>
|
|
If this function encounters a substring that is unset, which can happen when
|
|
capturing subpattern number <i>n+1</i> matches some part of the subject, but
|
|
subpattern <i>n</i> has not been used at all, it returns an empty string. This
|
|
can be distinguished from a genuine zero-length substring by inspecting the
|
|
appropriate offset in the ovector, which contains PCRE2_UNSET for unset
|
|
substrings.
|
|
<a name="extractbynname"></a></P>
|
|
<br><a name="SEC26" href="#TOC1">EXTRACTING CAPTURED SUBSTRINGS BY NAME</a><br>
|
|
<P>
|
|
<b>int pcre2_substring_number_from_name(const pcre2_code *<i>code</i>,</b>
|
|
<b> PCRE2_SPTR <i>name</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre2_substring_length_byname(pcre2_match_data *<i>match_data</i>,</b>
|
|
<b> PCRE2_SPTR <i>name</i>, PCRE2_SIZE *<i>length</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre2_substring_copy_byname(pcre2_match_data *<i>match_data</i>,</b>
|
|
<b> PCRE2_SPTR <i>name</i>, PCRE2_UCHAR *<i>buffer</i>, PCRE2_SIZE *<i>bufflen</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre2_substring_get_byname(pcre2_match_data *<i>match_data</i>,</b>
|
|
<b> PCRE2_SPTR <i>name</i>, PCRE2_UCHAR **<i>bufferptr</i>, PCRE2_SIZE *<i>bufflen</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>void pcre2_substring_free(PCRE2_UCHAR *<i>buffer</i>);</b>
|
|
</P>
|
|
<P>
|
|
To extract a substring by name, you first have to find associated number.
|
|
For example, for this pattern:
|
|
<pre>
|
|
(a+)b(?<xxx>\d+)...
|
|
</pre>
|
|
the number of the subpattern called "xxx" is 2. If the name is known to be
|
|
unique (PCRE2_DUPNAMES was not set), you can find the number from the name by
|
|
calling <b>pcre2_substring_number_from_name()</b>. The first argument is the
|
|
compiled pattern, and the second is the name. The yield of the function is the
|
|
subpattern number, PCRE2_ERROR_NOSUBSTRING if there is no subpattern of that
|
|
name, or PCRE2_ERROR_NOUNIQUESUBSTRING if there is more than one subpattern of
|
|
that name.
|
|
</P>
|
|
<P>
|
|
Given the number, you can extract the substring directly, or use one of the
|
|
functions described in the previous section. For convenience, there are also
|
|
"byname" functions that correspond to the "bynumber" functions, the only
|
|
difference being that the second argument is a name instead of a number.
|
|
However, if PCRE2_DUPNAMES is set and there are duplicate names,
|
|
the behaviour may not be what you want (see the next section).
|
|
</P>
|
|
<P>
|
|
<b>Warning:</b> If the pattern uses the (?| feature to set up multiple
|
|
subpatterns with the same number, as described in the
|
|
<a href="pcre2pattern.html#dupsubpatternnumber">section on duplicate subpattern numbers</a>
|
|
in the
|
|
<a href="pcre2pattern.html"><b>pcre2pattern</b></a>
|
|
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.
|
|
</P>
|
|
<br><a name="SEC27" href="#TOC1">DUPLICATE SUBPATTERN NAMES</a><br>
|
|
<P>
|
|
<b>int pcre2_substring_nametable_scan(const pcre2_code *<i>code</i>,</b>
|
|
<b> PCRE2_SPTR <i>name</i>, PCRE2_SPTR *<i>first</i>, PCRE2_SPTR *<i>last</i>);</b>
|
|
</P>
|
|
<P>
|
|
When a pattern is compiled with the PCRE2_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.
|
|
</P>
|
|
<P>
|
|
Normally, patterns with duplicate names are such that in any one match, only
|
|
one of the named subpatterns participates. An example is shown in the
|
|
<a href="pcre2pattern.html"><b>pcre2pattern</b></a>
|
|
documentation.
|
|
</P>
|
|
<P>
|
|
When duplicates are present, <b>pcre2_substring_copy_byname()</b> and
|
|
<b>pcre2_substring_get_byname()</b> return the first substring corresponding to
|
|
the given name that is set. If none are set, PCRE2_ERROR_NOSUBSTRING is
|
|
returned. The <b>pcre2_substring_number_from_name()</b> function returns one of
|
|
the numbers that are associated with the name, but it is not defined which it
|
|
is.
|
|
</P>
|
|
<P>
|
|
If you want to get full details of all captured substrings for a given name,
|
|
you must use the <b>pcre2_substring_nametable_scan()</b> function. The first
|
|
argument is the compiled pattern, and the second is the name. If the third and
|
|
fourth arguments are NULL, the function returns a group number (it is not
|
|
defined which). Otherwise, the third and fourth arguments must be pointers to
|
|
variables that 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, and the
|
|
function returns the length of each entry. In both cases,
|
|
PCRE2_ERROR_NOSUBSTRING is returned if there are no entries for the given name.
|
|
</P>
|
|
<P>
|
|
The format of the name table is described above in the section entitled
|
|
<i>Information about a pattern</i>
|
|
<a href="#infoaboutpattern">above.</a>
|
|
Given all the relevant entries for the name, you can extract each of their
|
|
numbers, and hence the captured data.
|
|
</P>
|
|
<br><a name="SEC28" href="#TOC1">FINDING ALL POSSIBLE MATCHES</a><br>
|
|
<P>
|
|
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 at a given
|
|
position, consider using the alternative matching function (see below) instead.
|
|
If you cannot use the alternative function, you can kludge it up by making use
|
|
of the callout facility, which is described in the
|
|
<a href="pcre2callout.html"><b>pcre2callout</b></a>
|
|
documentation.
|
|
</P>
|
|
<P>
|
|
What you have to do is to insert a callout right at the end of the pattern.
|
|
When your callout function is called, extract and save the current matched
|
|
substring. Then return 1, which forces <b>pcre2_match()</b> to backtrack and try
|
|
other alternatives. Ultimately, when it runs out of matches,
|
|
<b>pcre2_match()</b> will yield PCRE2_ERROR_NOMATCH.
|
|
<a name="dfamatch"></a></P>
|
|
<br><a name="SEC29" href="#TOC1">MATCHING A PATTERN: THE ALTERNATIVE FUNCTION</a><br>
|
|
<P>
|
|
<b>int pcre2_dfa_match(const pcre2_code *<i>code</i>, PCRE2_SPTR <i>subject</i>,</b>
|
|
<b> PCRE2_SIZE <i>length</i>, PCRE2_SIZE <i>startoffset</i>,</b>
|
|
<b> uint32_t <i>options</i>, pcre2_match_data *<i>match_data</i>,</b>
|
|
<b> pcre2_match_context *<i>mcontext</i>,</b>
|
|
<b> int *<i>workspace</i>, PCRE2_SIZE <i>wscount</i>);</b>
|
|
</P>
|
|
<P>
|
|
The function <b>pcre2_dfa_match()</b> 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
|
|
PCRE2 patterns are not supported. Nevertheless, 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 <b>pcre2_dfa_match()</b> does not support, see the
|
|
<a href="pcre2matching.html"><b>pcre2matching</b></a>
|
|
documentation.
|
|
</P>
|
|
<P>
|
|
The arguments for the <b>pcre2_dfa_match()</b> function are the same as for
|
|
<b>pcre2_match()</b>, plus two extras. The ovector within the match data block
|
|
is used in a different way, and this is described below. The other common
|
|
arguments are used in the same way as for <b>pcre2_match()</b>, so their
|
|
description is not repeated here.
|
|
</P>
|
|
<P>
|
|
The two additional arguments provide workspace for the function. The workspace
|
|
vector should contain at least 20 elements. It is used for keeping track of
|
|
multiple paths through the pattern tree. More workspace is needed for patterns
|
|
and subjects where there are a lot of potential matches.
|
|
</P>
|
|
<P>
|
|
Here is an example of a simple call to <b>pcre2_dfa_match()</b>:
|
|
<pre>
|
|
int wspace[20];
|
|
pcre2_match_data *md = pcre2_match_data_create(4, NULL);
|
|
int rc = pcre2_dfa_match(
|
|
re, /* result of pcre2_compile() */
|
|
"some string", /* the subject string */
|
|
11, /* the length of the subject string */
|
|
0, /* start at offset 0 in the subject */
|
|
0, /* default options */
|
|
match_data, /* the match data block */
|
|
NULL, /* a match context; NULL means use defaults */
|
|
wspace, /* working space vector */
|
|
20); /* number of elements (NOT size in bytes) */
|
|
</PRE>
|
|
</P>
|
|
<br><b>
|
|
Option bits for <b>pcre_dfa_match()</b>
|
|
</b><br>
|
|
<P>
|
|
The unused bits of the <i>options</i> argument for <b>pcre2_dfa_match()</b> must
|
|
be zero. The only bits that may be set are PCRE2_ANCHORED, PCRE2_NOTBOL,
|
|
PCRE2_NOTEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART, PCRE2_NO_UTF_CHECK,
|
|
PCRE2_PARTIAL_HARD, PCRE2_PARTIAL_SOFT, PCRE2_DFA_SHORTEST, and
|
|
PCRE2_DFA_RESTART. All but the last four of these are exactly the same as for
|
|
<b>pcre2_match()</b>, so their description is not repeated here.
|
|
<pre>
|
|
PCRE2_PARTIAL_HARD
|
|
PCRE2_PARTIAL_SOFT
|
|
</pre>
|
|
These have the same general effect as they do for <b>pcre2_match()</b>, but the
|
|
details are slightly different. When PCRE2_PARTIAL_HARD is set for
|
|
<b>pcre2_dfa_match()</b>, it returns PCRE2_ERROR_PARTIAL if the end of the
|
|
subject is reached and there is still at least one matching possibility that
|
|
requires additional characters. This happens even if some complete matches have
|
|
already been found. When PCRE2_PARTIAL_SOFT is set, the return code
|
|
PCRE2_ERROR_NOMATCH is converted into PCRE2_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 examples, in the
|
|
<a href="pcre2partial.html"><b>pcre2partial</b></a>
|
|
documentation.
|
|
<pre>
|
|
PCRE2_DFA_SHORTEST
|
|
</pre>
|
|
Setting the PCRE2_DFA_SHORTEST option causes the matching algorithm to stop as
|
|
soon as it has found one match. Because of the way the alternative algorithm
|
|
works, this is necessarily the shortest possible match at the first possible
|
|
matching point in the subject string.
|
|
<pre>
|
|
PCRE2_DFA_RESTART
|
|
</pre>
|
|
When <b>pcre2_dfa_match()</b> returns a partial match, it is possible to call it
|
|
again, with additional subject characters, and have it continue with the same
|
|
match. The PCRE2_DFA_RESTART option requests this action; when it is set, the
|
|
<i>workspace</i> and <i>wscount</i> 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
|
|
<a href="pcre2partial.html"><b>pcre2partial</b></a>
|
|
documentation.
|
|
</P>
|
|
<br><b>
|
|
Successful returns from <b>pcre2_dfa_match()</b>
|
|
</b><br>
|
|
<P>
|
|
When <b>pcre2_dfa_match()</b> succeeds, it may have matched more than one
|
|
substring in the subject. Note, however, that all the matches from one run of
|
|
the function start at the same point in the subject. The shorter matches are
|
|
all initial substrings of the longer matches. For example, if the pattern
|
|
<pre>
|
|
<.*>
|
|
</pre>
|
|
is matched against the string
|
|
<pre>
|
|
This is <something> <something else> <something further> no more
|
|
</pre>
|
|
the three matched strings are
|
|
<pre>
|
|
<something>
|
|
<something> <something else>
|
|
<something> <something else> <something further>
|
|
</pre>
|
|
On success, the yield of the function is a number greater than zero, which is
|
|
the number of matched substrings. The offsets of the substrings are returned in
|
|
the ovector, and can be extracted in the same way as for <b>pcre2_match()</b>.
|
|
They are returned in reverse order of length; that is, the longest
|
|
matching string is given first. If there were too many matches to fit into
|
|
the ovector, the yield of the function is zero, and the vector is filled with
|
|
the longest matches.
|
|
</P>
|
|
<P>
|
|
NOTE: PCRE2's "auto-possessification" optimization usually applies to character
|
|
repeats at the end of a pattern (as well as internally). For example, the
|
|
pattern "a\d+" is compiled as if it were "a\d++" because there is no point in
|
|
backtracking into the repeated digits. For DFA matching, this means that only
|
|
one possible match is found. If you really do want multiple matches in such
|
|
cases, either use an ungreedy repeat ("a\d+?") or set the
|
|
PCRE2_NO_AUTO_POSSESS option when compiling.
|
|
</P>
|
|
<br><b>
|
|
Error returns from <b>pcre2_dfa_match()</b>
|
|
</b><br>
|
|
<P>
|
|
The <b>pcre2_dfa_match()</b> function returns a negative number when it fails.
|
|
Many of the errors are the same as for <b>pcre2_match()</b>, as described
|
|
<a href="#errorlist">above.</a>
|
|
There are in addition the following errors that are specific to
|
|
<b>pcre2_dfa_match()</b>:
|
|
<pre>
|
|
PCRE2_ERROR_DFA_UITEM
|
|
</pre>
|
|
This return is given if <b>pcre2_dfa_match()</b> encounters an item in the
|
|
pattern that it does not support, for instance, the use of \C or a back
|
|
reference.
|
|
<pre>
|
|
PCRE2_ERROR_DFA_UCOND
|
|
</pre>
|
|
This return is given if <b>pcre2_dfa_match()</b> 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.
|
|
<pre>
|
|
PCRE2_ERROR_DFA_WSSIZE
|
|
</pre>
|
|
This return is given if <b>pcre2_dfa_match()</b> runs out of space in the
|
|
<i>workspace</i> vector.
|
|
<pre>
|
|
PCRE2_ERROR_DFA_RECURSE
|
|
</pre>
|
|
When a recursive subpattern is processed, the matching function calls itself
|
|
recursively, using private memory for the ovector and <i>workspace</i>. This
|
|
error is given if the internal ovector is not large enough. This should be
|
|
extremely rare, as a vector of size 1000 is used.
|
|
<pre>
|
|
PCRE2_ERROR_DFA_BADRESTART
|
|
</pre>
|
|
When <b>pcre2_dfa_match()</b> is called with the <b>pcre2_dfa_RESTART</b> 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.
|
|
</P>
|
|
<br><a name="SEC30" href="#TOC1">SEE ALSO</a><br>
|
|
<P>
|
|
<b>pcre2build</b>(3), <b>pcre2libs</b>(3), <b>pcre2callout</b>(3),
|
|
<b>pcre2matching</b>(3), <b>pcre2partial</b>(3), <b>pcre2posix</b>(3),
|
|
<b>pcre2demo(3)</b>, <b>pcre2sample</b>(3), <b>pcre2stack</b>(3).
|
|
</P>
|
|
<br><a name="SEC31" href="#TOC1">AUTHOR</a><br>
|
|
<P>
|
|
Philip Hazel
|
|
<br>
|
|
University Computing Service
|
|
<br>
|
|
Cambridge CB2 3QH, England.
|
|
<br>
|
|
</P>
|
|
<br><a name="SEC32" href="#TOC1">REVISION</a><br>
|
|
<P>
|
|
Last updated: 03 November 2014
|
|
<br>
|
|
Copyright © 1997-2014 University of Cambridge.
|
|
<br>
|
|
<p>
|
|
Return to the <a href="index.html">PCRE2 index page</a>.
|
|
</p>
|