2922 lines
132 KiB
HTML
2922 lines
132 KiB
HTML
<html>
|
|
<head>
|
|
<title>pcreapi specification</title>
|
|
</head>
|
|
<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
|
|
<h1>pcreapi man page</h1>
|
|
<p>
|
|
Return to the <a href="index.html">PCRE index page</a>.
|
|
</p>
|
|
<p>
|
|
This page is part of the PCRE HTML documentation. It was generated automatically
|
|
from the original man page. If there is any nonsense in it, please consult the
|
|
man page, in case the conversion went wrong.
|
|
<br>
|
|
<ul>
|
|
<li><a name="TOC1" href="#SEC1">PCRE NATIVE API BASIC FUNCTIONS</a>
|
|
<li><a name="TOC2" href="#SEC2">PCRE NATIVE API STRING EXTRACTION FUNCTIONS</a>
|
|
<li><a name="TOC3" href="#SEC3">PCRE NATIVE API AUXILIARY FUNCTIONS</a>
|
|
<li><a name="TOC4" href="#SEC4">PCRE NATIVE API INDIRECTED FUNCTIONS</a>
|
|
<li><a name="TOC5" href="#SEC5">PCRE 8-BIT, 16-BIT, AND 32-BIT LIBRARIES</a>
|
|
<li><a name="TOC6" href="#SEC6">PCRE API OVERVIEW</a>
|
|
<li><a name="TOC7" href="#SEC7">NEWLINES</a>
|
|
<li><a name="TOC8" href="#SEC8">MULTITHREADING</a>
|
|
<li><a name="TOC9" href="#SEC9">SAVING PRECOMPILED PATTERNS FOR LATER USE</a>
|
|
<li><a name="TOC10" href="#SEC10">CHECKING BUILD-TIME OPTIONS</a>
|
|
<li><a name="TOC11" href="#SEC11">COMPILING A PATTERN</a>
|
|
<li><a name="TOC12" href="#SEC12">COMPILATION ERROR CODES</a>
|
|
<li><a name="TOC13" href="#SEC13">STUDYING A PATTERN</a>
|
|
<li><a name="TOC14" href="#SEC14">LOCALE SUPPORT</a>
|
|
<li><a name="TOC15" href="#SEC15">INFORMATION ABOUT A PATTERN</a>
|
|
<li><a name="TOC16" href="#SEC16">REFERENCE COUNTS</a>
|
|
<li><a name="TOC17" href="#SEC17">MATCHING A PATTERN: THE TRADITIONAL FUNCTION</a>
|
|
<li><a name="TOC18" href="#SEC18">EXTRACTING CAPTURED SUBSTRINGS BY NUMBER</a>
|
|
<li><a name="TOC19" href="#SEC19">EXTRACTING CAPTURED SUBSTRINGS BY NAME</a>
|
|
<li><a name="TOC20" href="#SEC20">DUPLICATE SUBPATTERN NAMES</a>
|
|
<li><a name="TOC21" href="#SEC21">FINDING ALL POSSIBLE MATCHES</a>
|
|
<li><a name="TOC22" href="#SEC22">OBTAINING AN ESTIMATE OF STACK USAGE</a>
|
|
<li><a name="TOC23" href="#SEC23">MATCHING A PATTERN: THE ALTERNATIVE FUNCTION</a>
|
|
<li><a name="TOC24" href="#SEC24">SEE ALSO</a>
|
|
<li><a name="TOC25" href="#SEC25">AUTHOR</a>
|
|
<li><a name="TOC26" href="#SEC26">REVISION</a>
|
|
</ul>
|
|
<P>
|
|
<b>#include <pcre.h></b>
|
|
</P>
|
|
<br><a name="SEC1" href="#TOC1">PCRE NATIVE API BASIC FUNCTIONS</a><br>
|
|
<P>
|
|
<b>pcre *pcre_compile(const char *<i>pattern</i>, int <i>options</i>,</b>
|
|
<b> const char **<i>errptr</i>, int *<i>erroffset</i>,</b>
|
|
<b> const unsigned char *<i>tableptr</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>pcre *pcre_compile2(const char *<i>pattern</i>, int <i>options</i>,</b>
|
|
<b> int *<i>errorcodeptr</i>,</b>
|
|
<b> const char **<i>errptr</i>, int *<i>erroffset</i>,</b>
|
|
<b> const unsigned char *<i>tableptr</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>pcre_extra *pcre_study(const pcre *<i>code</i>, int <i>options</i>,</b>
|
|
<b> const char **<i>errptr</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>void pcre_free_study(pcre_extra *<i>extra</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b>
|
|
<b> const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b>
|
|
<b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre_dfa_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b>
|
|
<b> const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b>
|
|
<b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b>
|
|
<b> int *<i>workspace</i>, int <i>wscount</i>);</b>
|
|
</P>
|
|
<br><a name="SEC2" href="#TOC1">PCRE NATIVE API STRING EXTRACTION FUNCTIONS</a><br>
|
|
<P>
|
|
<b>int pcre_copy_named_substring(const pcre *<i>code</i>,</b>
|
|
<b> const char *<i>subject</i>, int *<i>ovector</i>,</b>
|
|
<b> int <i>stringcount</i>, const char *<i>stringname</i>,</b>
|
|
<b> char *<i>buffer</i>, int <i>buffersize</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre_copy_substring(const char *<i>subject</i>, int *<i>ovector</i>,</b>
|
|
<b> int <i>stringcount</i>, int <i>stringnumber</i>, char *<i>buffer</i>,</b>
|
|
<b> int <i>buffersize</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre_get_named_substring(const pcre *<i>code</i>,</b>
|
|
<b> const char *<i>subject</i>, int *<i>ovector</i>,</b>
|
|
<b> int <i>stringcount</i>, const char *<i>stringname</i>,</b>
|
|
<b> const char **<i>stringptr</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre_get_stringnumber(const pcre *<i>code</i>,</b>
|
|
<b> const char *<i>name</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre_get_stringtable_entries(const pcre *<i>code</i>,</b>
|
|
<b> const char *<i>name</i>, char **<i>first</i>, char **<i>last</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre_get_substring(const char *<i>subject</i>, int *<i>ovector</i>,</b>
|
|
<b> int <i>stringcount</i>, int <i>stringnumber</i>,</b>
|
|
<b> const char **<i>stringptr</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre_get_substring_list(const char *<i>subject</i>,</b>
|
|
<b> int *<i>ovector</i>, int <i>stringcount</i>, const char ***<i>listptr</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>void pcre_free_substring(const char *<i>stringptr</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>void pcre_free_substring_list(const char **<i>stringptr</i>);</b>
|
|
</P>
|
|
<br><a name="SEC3" href="#TOC1">PCRE NATIVE API AUXILIARY FUNCTIONS</a><br>
|
|
<P>
|
|
<b>int pcre_jit_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b>
|
|
<b> const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b>
|
|
<b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b>
|
|
<b> pcre_jit_stack *<i>jstack</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>pcre_jit_stack *pcre_jit_stack_alloc(int <i>startsize</i>, int <i>maxsize</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>void pcre_jit_stack_free(pcre_jit_stack *<i>stack</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>void pcre_assign_jit_stack(pcre_extra *<i>extra</i>,</b>
|
|
<b> pcre_jit_callback <i>callback</i>, void *<i>data</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>const unsigned char *pcre_maketables(void);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre_fullinfo(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b>
|
|
<b> int <i>what</i>, void *<i>where</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre_refcount(pcre *<i>code</i>, int <i>adjust</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre_config(int <i>what</i>, void *<i>where</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>const char *pcre_version(void);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre_pattern_to_host_byte_order(pcre *<i>code</i>,</b>
|
|
<b> pcre_extra *<i>extra</i>, const unsigned char *<i>tables</i>);</b>
|
|
</P>
|
|
<br><a name="SEC4" href="#TOC1">PCRE NATIVE API INDIRECTED FUNCTIONS</a><br>
|
|
<P>
|
|
<b>void *(*pcre_malloc)(size_t);</b>
|
|
<br>
|
|
<br>
|
|
<b>void (*pcre_free)(void *);</b>
|
|
<br>
|
|
<br>
|
|
<b>void *(*pcre_stack_malloc)(size_t);</b>
|
|
<br>
|
|
<br>
|
|
<b>void (*pcre_stack_free)(void *);</b>
|
|
<br>
|
|
<br>
|
|
<b>int (*pcre_callout)(pcre_callout_block *);</b>
|
|
<br>
|
|
<br>
|
|
<b>int (*pcre_stack_guard)(void);</b>
|
|
</P>
|
|
<br><a name="SEC5" href="#TOC1">PCRE 8-BIT, 16-BIT, AND 32-BIT LIBRARIES</a><br>
|
|
<P>
|
|
As well as support for 8-bit character strings, PCRE also supports 16-bit
|
|
strings (from release 8.30) and 32-bit strings (from release 8.32), by means of
|
|
two additional libraries. They can be built as well as, or instead of, the
|
|
8-bit library. To avoid too much complication, this document describes the
|
|
8-bit versions of the functions, with only occasional references to the 16-bit
|
|
and 32-bit libraries.
|
|
</P>
|
|
<P>
|
|
The 16-bit and 32-bit functions operate in the same way as their 8-bit
|
|
counterparts; they just use different data types for their arguments and
|
|
results, and their names start with <b>pcre16_</b> or <b>pcre32_</b> instead of
|
|
<b>pcre_</b>. For every option that has UTF8 in its name (for example,
|
|
PCRE_UTF8), there are corresponding 16-bit and 32-bit names with UTF8 replaced
|
|
by UTF16 or UTF32, respectively. This facility is in fact just cosmetic; the
|
|
16-bit and 32-bit option names define the same bit values.
|
|
</P>
|
|
<P>
|
|
References to bytes and UTF-8 in this document should be read as references to
|
|
16-bit data units and UTF-16 when using the 16-bit library, or 32-bit data
|
|
units and UTF-32 when using the 32-bit library, unless specified otherwise.
|
|
More details of the specific differences for the 16-bit and 32-bit libraries
|
|
are given in the
|
|
<a href="pcre16.html"><b>pcre16</b></a>
|
|
and
|
|
<a href="pcre32.html"><b>pcre32</b></a>
|
|
pages.
|
|
</P>
|
|
<br><a name="SEC6" href="#TOC1">PCRE API OVERVIEW</a><br>
|
|
<P>
|
|
PCRE has its own native API, which is described in this document. There are
|
|
also some wrapper functions (for the 8-bit library only) that correspond to the
|
|
POSIX regular expression API, but they do not give access to all the
|
|
functionality. They are described in the
|
|
<a href="pcreposix.html"><b>pcreposix</b></a>
|
|
documentation. Both of these APIs define a set of C function calls. A C++
|
|
wrapper (again for the 8-bit library only) is also distributed with PCRE. It is
|
|
documented in the
|
|
<a href="pcrecpp.html"><b>pcrecpp</b></a>
|
|
page.
|
|
</P>
|
|
<P>
|
|
The native API C function prototypes are defined in the header file
|
|
<b>pcre.h</b>, and on Unix-like systems the (8-bit) library itself is called
|
|
<b>libpcre</b>. It can normally be accessed by adding <b>-lpcre</b> to the
|
|
command for linking an application that uses PCRE. The header file defines the
|
|
macros PCRE_MAJOR and PCRE_MINOR to contain the major and minor release numbers
|
|
for the library. Applications can use these to include support for different
|
|
releases of PCRE.
|
|
</P>
|
|
<P>
|
|
In a Windows environment, if you want to statically link an application program
|
|
against a non-dll <b>pcre.a</b> file, you must define PCRE_STATIC before
|
|
including <b>pcre.h</b> or <b>pcrecpp.h</b>, because otherwise the
|
|
<b>pcre_malloc()</b> and <b>pcre_free()</b> exported functions will be declared
|
|
<b>__declspec(dllimport)</b>, with unwanted results.
|
|
</P>
|
|
<P>
|
|
The functions <b>pcre_compile()</b>, <b>pcre_compile2()</b>, <b>pcre_study()</b>,
|
|
and <b>pcre_exec()</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>pcredemo.c</i> in the PCRE
|
|
source distribution. A listing of this program is given in the
|
|
<a href="pcredemo.html"><b>pcredemo</b></a>
|
|
documentation, and the
|
|
<a href="pcresample.html"><b>pcresample</b></a>
|
|
documentation describes how to compile and run it.
|
|
</P>
|
|
<P>
|
|
Just-in-time compiler support is an optional feature of PCRE that can be built
|
|
in appropriate hardware environments. It greatly speeds up the matching
|
|
performance of many patterns. Simple programs can easily request that it be
|
|
used if available, by setting an option that is ignored when it is not
|
|
relevant. More complicated programs might need to make use of the functions
|
|
<b>pcre_jit_stack_alloc()</b>, <b>pcre_jit_stack_free()</b>, and
|
|
<b>pcre_assign_jit_stack()</b> in order to control the JIT code's memory usage.
|
|
</P>
|
|
<P>
|
|
From release 8.32 there is also a direct interface for JIT execution, which
|
|
gives improved performance. The JIT-specific functions are discussed in the
|
|
<a href="pcrejit.html"><b>pcrejit</b></a>
|
|
documentation.
|
|
</P>
|
|
<P>
|
|
A second matching function, <b>pcre_dfa_exec()</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="pcrematching.html"><b>pcrematching</b></a>
|
|
documentation.
|
|
</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>pcre_exec()</b>. They are:
|
|
<pre>
|
|
<b>pcre_copy_substring()</b>
|
|
<b>pcre_copy_named_substring()</b>
|
|
<b>pcre_get_substring()</b>
|
|
<b>pcre_get_named_substring()</b>
|
|
<b>pcre_get_substring_list()</b>
|
|
<b>pcre_get_stringnumber()</b>
|
|
<b>pcre_get_stringtable_entries()</b>
|
|
</pre>
|
|
<b>pcre_free_substring()</b> and <b>pcre_free_substring_list()</b> are also
|
|
provided, to free the memory used for extracted strings.
|
|
</P>
|
|
<P>
|
|
The function <b>pcre_maketables()</b> is used to build a set of character tables
|
|
in the current locale for passing to <b>pcre_compile()</b>, <b>pcre_exec()</b>,
|
|
or <b>pcre_dfa_exec()</b>. This is an optional facility that is provided for
|
|
specialist use. Most commonly, no special tables are passed, in which case
|
|
internal tables that are generated when PCRE is built are used.
|
|
</P>
|
|
<P>
|
|
The function <b>pcre_fullinfo()</b> is used to find out information about a
|
|
compiled pattern. The function <b>pcre_version()</b> returns a pointer to a
|
|
string containing the version of PCRE and its date of release.
|
|
</P>
|
|
<P>
|
|
The function <b>pcre_refcount()</b> maintains a reference count in a data block
|
|
containing a compiled pattern. This is provided for the benefit of
|
|
object-oriented applications.
|
|
</P>
|
|
<P>
|
|
The global variables <b>pcre_malloc</b> and <b>pcre_free</b> initially contain
|
|
the entry points of the standard <b>malloc()</b> and <b>free()</b> functions,
|
|
respectively. PCRE calls the memory management functions via these variables,
|
|
so a calling program can replace them if it wishes to intercept the calls. This
|
|
should be done before calling any PCRE functions.
|
|
</P>
|
|
<P>
|
|
The global variables <b>pcre_stack_malloc</b> and <b>pcre_stack_free</b> are also
|
|
indirections to memory management functions. These special functions are used
|
|
only when PCRE is compiled to use the heap for remembering data, instead of
|
|
recursive function calls, when running the <b>pcre_exec()</b> function. See the
|
|
<a href="pcrebuild.html"><b>pcrebuild</b></a>
|
|
documentation for details of how to do this. It is a non-standard way of
|
|
building PCRE, for use in environments that have limited stacks. Because of the
|
|
greater use of memory management, it runs more slowly. Separate functions are
|
|
provided so that special-purpose external code can be used for this case. When
|
|
used, these functions always allocate memory blocks of the same size. There is
|
|
a discussion about PCRE's stack usage in the
|
|
<a href="pcrestack.html"><b>pcrestack</b></a>
|
|
documentation.
|
|
</P>
|
|
<P>
|
|
The global variable <b>pcre_callout</b> initially contains NULL. It can be set
|
|
by the caller to a "callout" function, which PCRE will then call at specified
|
|
points during a matching operation. Details are given in the
|
|
<a href="pcrecallout.html"><b>pcrecallout</b></a>
|
|
documentation.
|
|
</P>
|
|
<P>
|
|
The global variable <b>pcre_stack_guard</b> initially contains NULL. It can be
|
|
set by the caller to a function that is called by PCRE whenever it starts
|
|
to compile a parenthesized part of a pattern. When parentheses are nested, PCRE
|
|
uses recursive function calls, which use up the system stack. This function is
|
|
provided so that applications with restricted stacks can force a compilation
|
|
error if the stack runs out. The function should return zero if all is well, or
|
|
non-zero to force an error.
|
|
<a name="newlines"></a></P>
|
|
<br><a name="SEC7" href="#TOC1">NEWLINES</a><br>
|
|
<P>
|
|
PCRE supports five different conventions for indicating line breaks in
|
|
strings: a single CR (carriage return) character, a single LF (linefeed)
|
|
character, the two-character sequence CRLF, any of the three preceding, or any
|
|
Unicode newline sequence. The Unicode newline sequences are the three just
|
|
mentioned, plus the single characters VT (vertical tab, U+000B), FF (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 PCRE is built, a default can be specified.
|
|
The default default is LF, which is the Unix standard. When PCRE is run, the
|
|
default can be overridden, either when a pattern is compiled, or when it is
|
|
matched.
|
|
</P>
|
|
<P>
|
|
At compile time, the newline convention can be specified by the <i>options</i>
|
|
argument of <b>pcre_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="pcrepattern.html"><b>pcrepattern</b></a>
|
|
page for details of the special character sequences.
|
|
</P>
|
|
<P>
|
|
In the PCRE documentation the word "newline" is used to mean "the character or
|
|
pair of characters that indicate a line break". The choice of newline
|
|
convention affects the handling of the dot, circumflex, and dollar
|
|
metacharacters, the handling of #-comments in /x mode, and, when CRLF is a
|
|
recognized line ending sequence, the match position advancement for a
|
|
non-anchored pattern. There is more detail about this in the
|
|
<a href="#execoptions">section on <b>pcre_exec()</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 is
|
|
controlled in a similar way, but by separate options.
|
|
</P>
|
|
<br><a name="SEC8" href="#TOC1">MULTITHREADING</a><br>
|
|
<P>
|
|
The PCRE functions can be used in multi-threading applications, with the
|
|
proviso that the memory management functions pointed to by <b>pcre_malloc</b>,
|
|
<b>pcre_free</b>, <b>pcre_stack_malloc</b>, and <b>pcre_stack_free</b>, and the
|
|
callout and stack-checking functions pointed to by <b>pcre_callout</b> and
|
|
<b>pcre_stack_guard</b>, are shared by all threads.
|
|
</P>
|
|
<P>
|
|
The compiled form of a regular expression is not altered during matching, so
|
|
the same compiled pattern can safely be used by several threads at once.
|
|
</P>
|
|
<P>
|
|
If the just-in-time optimization feature is being used, it needs separate
|
|
memory stack areas for each thread. See the
|
|
<a href="pcrejit.html"><b>pcrejit</b></a>
|
|
documentation for more details.
|
|
</P>
|
|
<br><a name="SEC9" href="#TOC1">SAVING PRECOMPILED PATTERNS FOR LATER USE</a><br>
|
|
<P>
|
|
The compiled form of a regular expression can be saved and re-used at a later
|
|
time, possibly by a different program, and even on a host other than the one on
|
|
which it was compiled. Details are given in the
|
|
<a href="pcreprecompile.html"><b>pcreprecompile</b></a>
|
|
documentation, which includes a description of the
|
|
<b>pcre_pattern_to_host_byte_order()</b> function. However, compiling a regular
|
|
expression with one version of PCRE for use with a different version is not
|
|
guaranteed to work and may cause crashes.
|
|
</P>
|
|
<br><a name="SEC10" href="#TOC1">CHECKING BUILD-TIME OPTIONS</a><br>
|
|
<P>
|
|
<b>int pcre_config(int <i>what</i>, void *<i>where</i>);</b>
|
|
</P>
|
|
<P>
|
|
The function <b>pcre_config()</b> makes it possible for a PCRE client to
|
|
discover which optional features have been compiled into the PCRE library. The
|
|
<a href="pcrebuild.html"><b>pcrebuild</b></a>
|
|
documentation has more details about these optional features.
|
|
</P>
|
|
<P>
|
|
The first argument for <b>pcre_config()</b> is an integer, specifying which
|
|
information is required; the second argument is a pointer to a variable into
|
|
which the information is placed. The returned value is zero on success, or the
|
|
negative error code PCRE_ERROR_BADOPTION if the value in the first argument is
|
|
not recognized. The following information is available:
|
|
<pre>
|
|
PCRE_CONFIG_UTF8
|
|
</pre>
|
|
The output is an integer that is set to one if UTF-8 support is available;
|
|
otherwise it is set to zero. This value should normally be given to the 8-bit
|
|
version of this function, <b>pcre_config()</b>. If it is given to the 16-bit
|
|
or 32-bit version of this function, the result is PCRE_ERROR_BADOPTION.
|
|
<pre>
|
|
PCRE_CONFIG_UTF16
|
|
</pre>
|
|
The output is an integer that is set to one if UTF-16 support is available;
|
|
otherwise it is set to zero. This value should normally be given to the 16-bit
|
|
version of this function, <b>pcre16_config()</b>. If it is given to the 8-bit
|
|
or 32-bit version of this function, the result is PCRE_ERROR_BADOPTION.
|
|
<pre>
|
|
PCRE_CONFIG_UTF32
|
|
</pre>
|
|
The output is an integer that is set to one if UTF-32 support is available;
|
|
otherwise it is set to zero. This value should normally be given to the 32-bit
|
|
version of this function, <b>pcre32_config()</b>. If it is given to the 8-bit
|
|
or 16-bit version of this function, the result is PCRE_ERROR_BADOPTION.
|
|
<pre>
|
|
PCRE_CONFIG_UNICODE_PROPERTIES
|
|
</pre>
|
|
The output is an integer that is set to one if support for Unicode character
|
|
properties is available; otherwise it is set to zero.
|
|
<pre>
|
|
PCRE_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>
|
|
PCRE_CONFIG_JITTARGET
|
|
</pre>
|
|
The output is a pointer to a zero-terminated "const char *" string. If JIT
|
|
support is available, the string 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, the result is NULL.
|
|
<pre>
|
|
PCRE_CONFIG_NEWLINE
|
|
</pre>
|
|
The output is an integer whose value specifies the default character sequence
|
|
that is recognized as meaning "newline". The values that are supported in
|
|
ASCII/Unicode environments are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for
|
|
ANYCRLF, and -1 for ANY. In EBCDIC environments, CR, ANYCRLF, and ANY yield the
|
|
same values. However, the value for LF is normally 21, though some EBCDIC
|
|
environments use 37. The corresponding values for CRLF are 3349 and 3365. The
|
|
default should normally correspond to the standard sequence for your operating
|
|
system.
|
|
<pre>
|
|
PCRE_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>
|
|
PCRE_CONFIG_LINK_SIZE
|
|
</pre>
|
|
The output is an integer that contains the number of bytes used for internal
|
|
linkage in compiled regular expressions. For the 8-bit library, the value can
|
|
be 2, 3, or 4. For the 16-bit library, the value is either 2 or 4 and is still
|
|
a number of bytes. For the 32-bit library, the value is either 2 or 4 and is
|
|
still a number of bytes. The default value of 2 is sufficient for all but the
|
|
most massive patterns, since it allows the compiled pattern to be up to 64K in
|
|
size. Larger values allow larger regular expressions to be compiled, at the
|
|
expense of slower matching.
|
|
<pre>
|
|
PCRE_CONFIG_POSIX_MALLOC_THRESHOLD
|
|
</pre>
|
|
The output is an integer that contains the threshold above which the POSIX
|
|
interface uses <b>malloc()</b> for output vectors. Further details are given in
|
|
the
|
|
<a href="pcreposix.html"><b>pcreposix</b></a>
|
|
documentation.
|
|
<pre>
|
|
PCRE_CONFIG_PARENS_LIMIT
|
|
</pre>
|
|
The output is a 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 PCRE 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, you can set a pointer to an external checking function
|
|
in <b>pcre_stack_guard</b>.
|
|
<pre>
|
|
PCRE_CONFIG_MATCH_LIMIT
|
|
</pre>
|
|
The output is a long integer that gives the default limit for the number of
|
|
internal matching function calls in a <b>pcre_exec()</b> execution. Further
|
|
details are given with <b>pcre_exec()</b> below.
|
|
<pre>
|
|
PCRE_CONFIG_MATCH_LIMIT_RECURSION
|
|
</pre>
|
|
The output is a long integer that gives the default limit for the depth of
|
|
recursion when calling the internal matching function in a <b>pcre_exec()</b>
|
|
execution. Further details are given with <b>pcre_exec()</b> below.
|
|
<pre>
|
|
PCRE_CONFIG_STACKRECURSE
|
|
</pre>
|
|
The output is an integer that is set to one if internal recursion when running
|
|
<b>pcre_exec()</b> is implemented by recursive function calls that use the stack
|
|
to remember their state. This is the usual way that PCRE is compiled. The
|
|
output is zero if PCRE was compiled to use blocks of data on the heap instead
|
|
of recursive function calls. In this case, <b>pcre_stack_malloc</b> and
|
|
<b>pcre_stack_free</b> are called to manage memory blocks on the heap, thus
|
|
avoiding the use of the stack.
|
|
</P>
|
|
<br><a name="SEC11" href="#TOC1">COMPILING A PATTERN</a><br>
|
|
<P>
|
|
<b>pcre *pcre_compile(const char *<i>pattern</i>, int <i>options</i>,</b>
|
|
<b> const char **<i>errptr</i>, int *<i>erroffset</i>,</b>
|
|
<b> const unsigned char *<i>tableptr</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>pcre *pcre_compile2(const char *<i>pattern</i>, int <i>options</i>,</b>
|
|
<b> int *<i>errorcodeptr</i>,</b>
|
|
<b> const char **<i>errptr</i>, int *<i>erroffset</i>,</b>
|
|
<b> const unsigned char *<i>tableptr</i>);</b>
|
|
</P>
|
|
<P>
|
|
Either of the functions <b>pcre_compile()</b> or <b>pcre_compile2()</b> can be
|
|
called to compile a pattern into an internal form. The only difference between
|
|
the two interfaces is that <b>pcre_compile2()</b> has an additional argument,
|
|
<i>errorcodeptr</i>, via which a numerical error code can be returned. To avoid
|
|
too much repetition, we refer just to <b>pcre_compile()</b> below, but the
|
|
information applies equally to <b>pcre_compile2()</b>.
|
|
</P>
|
|
<P>
|
|
The pattern is a C string terminated by a binary zero, and is passed in the
|
|
<i>pattern</i> argument. A pointer to a single block of memory that is obtained
|
|
via <b>pcre_malloc</b> is returned. This contains the compiled code and related
|
|
data. The <b>pcre</b> type is defined for the returned block; this is a typedef
|
|
for a structure whose contents are not externally defined. It is up to the
|
|
caller to free the memory (via <b>pcre_free</b>) when it is no longer required.
|
|
</P>
|
|
<P>
|
|
Although the compiled code of a PCRE regex is relocatable, that is, it does not
|
|
depend on memory location, the complete <b>pcre</b> data block is not
|
|
fully relocatable, because it may contain a copy of the <i>tableptr</i>
|
|
argument, which is an address (see below).
|
|
</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="pcrepattern.html"><b>pcrepattern</b></a>
|
|
documentation). 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 and execution. The PCRE_ANCHORED,
|
|
PCRE_BSR_<i>xxx</i>, PCRE_NEWLINE_<i>xxx</i>, PCRE_NO_UTF8_CHECK, and
|
|
PCRE_NO_START_OPTIMIZE options can be set at the time of matching as well as at
|
|
compile time.
|
|
</P>
|
|
<P>
|
|
If <i>errptr</i> is NULL, <b>pcre_compile()</b> returns NULL immediately.
|
|
Otherwise, if compilation of a pattern fails, <b>pcre_compile()</b> returns
|
|
NULL, and sets the variable pointed to by <i>errptr</i> to point to a textual
|
|
error message. This is a static string that is part of the library. You must
|
|
not try to free it. Normally, the offset from the start of the pattern to the
|
|
data unit that was being processed when the error was discovered is placed in
|
|
the variable pointed to by <i>erroffset</i>, which must not be NULL (if it is,
|
|
an immediate error is given). However, for an invalid UTF-8 or UTF-16 string,
|
|
the offset is that of the first data 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 data 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>
|
|
If <b>pcre_compile2()</b> is used instead of <b>pcre_compile()</b>, and the
|
|
<i>errorcodeptr</i> argument is not NULL, a non-zero error code number is
|
|
returned via this argument in the event of an error. This is in addition to the
|
|
textual error message. Error codes and messages are listed below.
|
|
</P>
|
|
<P>
|
|
If the final argument, <i>tableptr</i>, is NULL, PCRE uses a default set of
|
|
character tables that are built when PCRE is compiled, using the default C
|
|
locale. Otherwise, <i>tableptr</i> must be an address that is the result of a
|
|
call to <b>pcre_maketables()</b>. This value is stored with the compiled
|
|
pattern, and used again by <b>pcre_exec()</b> and <b>pcre_dfa_exec()</b> when the
|
|
pattern is matched. For more discussion, see the section on locale support
|
|
below.
|
|
</P>
|
|
<P>
|
|
This code fragment shows a typical straightforward call to <b>pcre_compile()</b>:
|
|
<pre>
|
|
pcre *re;
|
|
const char *error;
|
|
int erroffset;
|
|
re = pcre_compile(
|
|
"^A.*Z", /* the pattern */
|
|
0, /* default options */
|
|
&error, /* for error message */
|
|
&erroffset, /* for error offset */
|
|
NULL); /* use default character tables */
|
|
</pre>
|
|
The following names for option bits are defined in the <b>pcre.h</b> header
|
|
file:
|
|
<pre>
|
|
PCRE_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>
|
|
PCRE_AUTO_CALLOUT
|
|
</pre>
|
|
If this bit is set, <b>pcre_compile()</b> automatically inserts callout items,
|
|
all with number 255, before each pattern item. For discussion of the callout
|
|
facility, see the
|
|
<a href="pcrecallout.html"><b>pcrecallout</b></a>
|
|
documentation.
|
|
<pre>
|
|
PCRE_BSR_ANYCRLF
|
|
PCRE_BSR_UNICODE
|
|
</pre>
|
|
These options (which are mutually exclusive) control what the \R escape
|
|
sequence matches. The choice is either to match only CR, LF, or CRLF, or to
|
|
match any Unicode newline sequence. The default is specified when PCRE is
|
|
built. It can be overridden from within the pattern, or by setting an option
|
|
when a compiled pattern is matched.
|
|
<pre>
|
|
PCRE_CASELESS
|
|
</pre>
|
|
If this bit is set, letters in the pattern match both upper and lower case
|
|
letters. It is equivalent to Perl's /i option, and it can be changed within a
|
|
pattern by a (?i) option setting. In UTF-8 mode, PCRE always understands the
|
|
concept of case for characters whose values are less than 128, so caseless
|
|
matching is always possible. For characters with higher values, the concept of
|
|
case is supported if PCRE is compiled with Unicode property support, but not
|
|
otherwise. If you want to use caseless matching for characters 128 and above,
|
|
you must ensure that PCRE is compiled with Unicode property support as well as
|
|
with UTF-8 support.
|
|
<pre>
|
|
PCRE_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 PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is set.
|
|
There is no equivalent to this option in Perl, and no way to set it within a
|
|
pattern.
|
|
<pre>
|
|
PCRE_DOTALL
|
|
</pre>
|
|
If this bit is set, a dot metacharacter in the pattern matches a character of
|
|
any value, 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 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>
|
|
PCRE_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="pcrepattern.html"><b>pcrepattern</b></a>
|
|
documentation.
|
|
<pre>
|
|
PCRE_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 a numerical quantifier such as {1,3}.
|
|
However, ignorable white space is permitted between an item and a following
|
|
quantifier and between a quantifier and a following + that indicates
|
|
possessiveness.
|
|
</P>
|
|
<P>
|
|
White space did not used to include the VT character (code 11), because Perl
|
|
did not treat this character as white space. However, Perl changed at release
|
|
5.18, so PCRE followed at release 8.34, and VT is now treated as white space.
|
|
</P>
|
|
<P>
|
|
PCRE_EXTENDED also causes characters between an unescaped # outside a character
|
|
class and the next newline, inclusive, to be ignored. PCRE_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 is controlled by the options
|
|
passed to <b>pcre_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>pcrepattern</b> documentation. 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.
|
|
</P>
|
|
<P>
|
|
This option makes it possible to include comments inside complicated patterns.
|
|
Note, however, that this applies only to data characters. White space characters
|
|
may never appear within special character sequences in a pattern, for example
|
|
within the sequence (?( that introduces a conditional subpattern.
|
|
<pre>
|
|
PCRE_EXTRA
|
|
</pre>
|
|
This option was invented in order to turn on additional functionality of PCRE
|
|
that is incompatible with Perl, but it is currently of very little use. When
|
|
set, any backslash in a pattern that is followed by a letter that has no
|
|
special meaning causes an error, thus reserving these combinations for future
|
|
expansion. By default, as in Perl, a backslash followed by a letter with no
|
|
special meaning is treated as a literal. (Perl can, however, be persuaded to
|
|
give an error for this, by running it with the -w option.) There are at present
|
|
no other features controlled by this option. It can also be set by a (?X)
|
|
option setting within a pattern.
|
|
<pre>
|
|
PCRE_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>
|
|
PCRE_JAVASCRIPT_COMPAT
|
|
</pre>
|
|
If this option is set, PCRE's behaviour is changed in some ways so that it is
|
|
compatible with JavaScript rather than Perl. The changes are as follows:
|
|
</P>
|
|
<P>
|
|
(1) A lone closing square bracket in a pattern causes a compile-time error,
|
|
because this is illegal in JavaScript (by default it is treated as a data
|
|
character). Thus, the pattern AB]CD becomes illegal when this option is set.
|
|
</P>
|
|
<P>
|
|
(2) At run time, a back reference to an unset subpattern group matches an empty
|
|
string (by default this causes the current matching alternative to fail). A
|
|
pattern such as (\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.
|
|
</P>
|
|
<P>
|
|
(3) \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>
|
|
(4) \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>
|
|
(5) \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>
|
|
PCRE_MULTILINE
|
|
</pre>
|
|
By default, for the purposes of matching "start of line" and "end of line",
|
|
PCRE treats the subject string as consisting of a single line of characters,
|
|
even if it actually contains newlines. The "start of line" metacharacter (^)
|
|
matches only at the start of the string, and the "end of line" metacharacter
|
|
($) matches only at the end of the string, or before a terminating newline
|
|
(except when PCRE_DOLLAR_ENDONLY is set). Note, however, that unless
|
|
PCRE_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 PCRE_MULTILINE it is set, the "start of line" and "end of line" constructs
|
|
match immediately following or immediately before internal newlines in the
|
|
subject string, respectively, as well as at the very start and end. This is
|
|
equivalent to Perl's /m option, and it can be changed within a pattern by a
|
|
(?m) option setting. If there are no newlines in a subject string, or no
|
|
occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect.
|
|
<pre>
|
|
PCRE_NEVER_UTF
|
|
</pre>
|
|
This option locks out interpretation of the pattern as UTF-8 (or UTF-16 or
|
|
UTF-32 in the 16-bit and 32-bit libraries). 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 PCRE_UTF8 and PCRE_NEVER_UTF also
|
|
causes an error.
|
|
<pre>
|
|
PCRE_NEWLINE_CR
|
|
PCRE_NEWLINE_LF
|
|
PCRE_NEWLINE_CRLF
|
|
PCRE_NEWLINE_ANYCRLF
|
|
PCRE_NEWLINE_ANY
|
|
</pre>
|
|
These options override the default newline definition that was chosen when PCRE
|
|
was built. Setting the first or the second specifies that a newline is
|
|
indicated by a single character (CR or LF, respectively). Setting
|
|
PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character
|
|
CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three
|
|
preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies
|
|
that any Unicode newline sequence should be recognized.
|
|
</P>
|
|
<P>
|
|
In an ASCII/Unicode environment, the Unicode newline sequences are the three
|
|
just mentioned, plus the single characters VT (vertical tab, U+000B), FF (form
|
|
feed, U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
|
|
(paragraph separator, U+2029). For the 8-bit library, the last two are
|
|
recognized only in UTF-8 mode.
|
|
</P>
|
|
<P>
|
|
When PCRE is compiled to run in an EBCDIC (mainframe) environment, the code for
|
|
CR is 0x0d, the same as ASCII. However, the character code for LF is normally
|
|
0x15, though in some EBCDIC environments 0x25 is used. Whichever of these is
|
|
not LF is made to correspond to Unicode's NEL character. EBCDIC codes are all
|
|
less than 256. For more details, see the
|
|
<a href="pcrebuild.html"><b>pcrebuild</b></a>
|
|
documentation.
|
|
</P>
|
|
<P>
|
|
The newline setting in the options word uses three bits that are treated
|
|
as a number, giving eight possibilities. Currently only six are used (default
|
|
plus the five values above). This means that if you set more than one newline
|
|
option, the combination may or may not be sensible. For example,
|
|
PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but
|
|
other combinations may yield unused numbers and cause an error.
|
|
</P>
|
|
<P>
|
|
The only time that a line break in a pattern is specially recognized when
|
|
compiling is when PCRE_EXTENDED is set. CR and LF are white space characters,
|
|
and so are ignored in this mode. Also, an unescaped # outside a character class
|
|
indicates a comment that lasts until after the next line break sequence. In
|
|
other circumstances, line break sequences in patterns are treated as literal
|
|
data.
|
|
</P>
|
|
<P>
|
|
The newline option that is set at compile time becomes the default that is used
|
|
for <b>pcre_exec()</b> and <b>pcre_dfa_exec()</b>, but it can be overridden.
|
|
<pre>
|
|
PCRE_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>
|
|
PCRE_NO_AUTO_POSSESS
|
|
</pre>
|
|
If this option is set, it disables "auto-possessification". This 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 of them 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>
|
|
PCRE_NO_START_OPTIMIZE
|
|
</pre>
|
|
This is an option that acts at matching time; that is, it is really an option
|
|
for <b>pcre_exec()</b> or <b>pcre_dfa_exec()</b>. If it is set at compile time,
|
|
it is remembered with the compiled pattern and assumed at matching time. This
|
|
is necessary if you want to use JIT execution, because the JIT compiler needs
|
|
to know whether or not this option is set. For details see the discussion of
|
|
PCRE_NO_START_OPTIMIZE
|
|
<a href="#execoptions">below.</a>
|
|
<pre>
|
|
PCRE_UCP
|
|
</pre>
|
|
This option changes the way PCRE processes \B, \b, \D, \d, \S, \s, \W,
|
|
\w, and some of the POSIX character classes. By default, only ASCII characters
|
|
are recognized, but if PCRE_UCP is set, Unicode properties are used instead to
|
|
classify characters. More details are given in the section on
|
|
<a href="pcre.html#genericchartypes">generic character types</a>
|
|
in the
|
|
<a href="pcrepattern.html"><b>pcrepattern</b></a>
|
|
page. If you set PCRE_UCP, matching one of the items it affects takes much
|
|
longer. The option is available only if PCRE has been compiled with Unicode
|
|
property support.
|
|
<pre>
|
|
PCRE_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>
|
|
PCRE_UTF8
|
|
</pre>
|
|
This option causes PCRE to regard both the pattern and the subject as strings
|
|
of UTF-8 characters instead of single-byte strings. However, it is available
|
|
only when PCRE is built to include UTF support. If not, the use of this option
|
|
provokes an error. Details of how this option changes the behaviour of PCRE are
|
|
given in the
|
|
<a href="pcreunicode.html"><b>pcreunicode</b></a>
|
|
page.
|
|
<pre>
|
|
PCRE_NO_UTF8_CHECK
|
|
</pre>
|
|
When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is
|
|
automatically checked. There is a discussion about the
|
|
<a href="pcreunicode.html#utf8strings">validity of UTF-8 strings</a>
|
|
in the
|
|
<a href="pcreunicode.html"><b>pcreunicode</b></a>
|
|
page. If an invalid UTF-8 sequence is found, <b>pcre_compile()</b> returns an
|
|
error. If you already know that your pattern is valid, and you want to skip
|
|
this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK option.
|
|
When it is set, the effect of passing an invalid UTF-8 string as a pattern is
|
|
undefined. It may cause your program to crash or loop. Note that this option
|
|
can also be passed to <b>pcre_exec()</b> and <b>pcre_dfa_exec()</b>, to suppress
|
|
the validity checking of subject strings only. If the same string is being
|
|
matched many times, the option can be safely set for the second and subsequent
|
|
matchings to improve performance.
|
|
</P>
|
|
<br><a name="SEC12" href="#TOC1">COMPILATION ERROR CODES</a><br>
|
|
<P>
|
|
The following table lists the error codes than may be returned by
|
|
<b>pcre_compile2()</b>, along with the error messages that may be returned by
|
|
both compiling functions. Note that error messages are always 8-bit ASCII
|
|
strings, even in 16-bit or 32-bit mode. As PCRE has developed, some error codes
|
|
have fallen out of use. To avoid confusion, they have not been re-used.
|
|
<pre>
|
|
0 no error
|
|
1 \ at end of pattern
|
|
2 \c at end of pattern
|
|
3 unrecognized character follows \
|
|
4 numbers out of order in {} quantifier
|
|
5 number too big in {} quantifier
|
|
6 missing terminating ] for character class
|
|
7 invalid escape sequence in character class
|
|
8 range out of order in character class
|
|
9 nothing to repeat
|
|
10 [this code is not in use]
|
|
11 internal error: unexpected repeat
|
|
12 unrecognized character after (? or (?-
|
|
13 POSIX named classes are supported only within a class
|
|
14 missing )
|
|
15 reference to non-existent subpattern
|
|
16 erroffset passed as NULL
|
|
17 unknown option bit(s) set
|
|
18 missing ) after comment
|
|
19 [this code is not in use]
|
|
20 regular expression is too large
|
|
21 failed to get memory
|
|
22 unmatched parentheses
|
|
23 internal error: code overflow
|
|
24 unrecognized character after (?<
|
|
25 lookbehind assertion is not fixed length
|
|
26 malformed number or name after (?(
|
|
27 conditional group contains more than two branches
|
|
28 assertion expected after (?(
|
|
29 (?R or (?[+-]digits must be followed by )
|
|
30 unknown POSIX class name
|
|
31 POSIX collating elements are not supported
|
|
32 this version of PCRE is compiled without UTF support
|
|
33 [this code is not in use]
|
|
34 character value in \x{} or \o{} is too large
|
|
35 invalid condition (?(0)
|
|
36 \C not allowed in lookbehind assertion
|
|
37 PCRE does not support \L, \l, \N{name}, \U, or \u
|
|
38 number after (?C is > 255
|
|
39 closing ) for (?C expected
|
|
40 recursive call could loop indefinitely
|
|
41 unrecognized character after (?P
|
|
42 syntax error in subpattern name (missing terminator)
|
|
43 two named subpatterns have the same name
|
|
44 invalid UTF-8 string (specifically UTF-8)
|
|
45 support for \P, \p, and \X has not been compiled
|
|
46 malformed \P or \p sequence
|
|
47 unknown property name after \P or \p
|
|
48 subpattern name is too long (maximum 32 characters)
|
|
49 too many named subpatterns (maximum 10000)
|
|
50 [this code is not in use]
|
|
51 octal value is greater than \377 in 8-bit non-UTF-8 mode
|
|
52 internal error: overran compiling workspace
|
|
53 internal error: previously-checked referenced subpattern
|
|
not found
|
|
54 DEFINE group contains more than one branch
|
|
55 repeating a DEFINE group is not allowed
|
|
56 inconsistent NEWLINE options
|
|
57 \g is not followed by a braced, angle-bracketed, or quoted
|
|
name/number or by a plain number
|
|
58 a numbered reference must not be zero
|
|
59 an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT)
|
|
60 (*VERB) not recognized or malformed
|
|
61 number is too big
|
|
62 subpattern name expected
|
|
63 digit expected after (?+
|
|
64 ] is an invalid data character in JavaScript compatibility mode
|
|
65 different names for subpatterns of the same number are
|
|
not allowed
|
|
66 (*MARK) must have an argument
|
|
67 this version of PCRE is not compiled with Unicode property
|
|
support
|
|
68 \c must be followed by an ASCII character
|
|
69 \k is not followed by a braced, angle-bracketed, or quoted name
|
|
70 internal error: unknown opcode in find_fixedlength()
|
|
71 \N is not supported in a class
|
|
72 too many forward references
|
|
73 disallowed Unicode code point (>= 0xd800 && <= 0xdfff)
|
|
74 invalid UTF-16 string (specifically UTF-16)
|
|
75 name is too long in (*MARK), (*PRUNE), (*SKIP), or (*THEN)
|
|
76 character value in \u.... sequence is too large
|
|
77 invalid UTF-32 string (specifically UTF-32)
|
|
78 setting UTF is disabled by the application
|
|
79 non-hex character in \x{} (closing brace missing?)
|
|
80 non-octal character in \o{} (closing brace missing?)
|
|
81 missing opening brace after \o
|
|
82 parentheses are too deeply nested
|
|
83 invalid range in character class
|
|
84 group name must start with a non-digit
|
|
85 parentheses are too deeply nested (stack check)
|
|
</pre>
|
|
The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may
|
|
be used if the limits were changed when PCRE was built.
|
|
<a name="studyingapattern"></a></P>
|
|
<br><a name="SEC13" href="#TOC1">STUDYING A PATTERN</a><br>
|
|
<P>
|
|
<b>pcre_extra *pcre_study(const pcre *<i>code</i>, int <i>options</i>,</b>
|
|
<b> const char **<i>errptr</i>);</b>
|
|
</P>
|
|
<P>
|
|
If a compiled pattern is going to be used several times, it is worth spending
|
|
more time analyzing it in order to speed up the time taken for matching. The
|
|
function <b>pcre_study()</b> takes a pointer to a compiled pattern as its first
|
|
argument. If studying the pattern produces additional information that will
|
|
help speed up matching, <b>pcre_study()</b> returns a pointer to a
|
|
<b>pcre_extra</b> block, in which the <i>study_data</i> field points to the
|
|
results of the study.
|
|
</P>
|
|
<P>
|
|
The returned value from <b>pcre_study()</b> can be passed directly to
|
|
<b>pcre_exec()</b> or <b>pcre_dfa_exec()</b>. However, a <b>pcre_extra</b> block
|
|
also contains other fields that can be set by the caller before the block is
|
|
passed; these are described
|
|
<a href="#extradata">below</a>
|
|
in the section on matching a pattern.
|
|
</P>
|
|
<P>
|
|
If studying the pattern does not produce any useful information,
|
|
<b>pcre_study()</b> returns NULL by default. In that circumstance, if the
|
|
calling program wants to pass any of the other fields to <b>pcre_exec()</b> or
|
|
<b>pcre_dfa_exec()</b>, it must set up its own <b>pcre_extra</b> block. However,
|
|
if <b>pcre_study()</b> is called with the PCRE_STUDY_EXTRA_NEEDED option, it
|
|
returns a <b>pcre_extra</b> block even if studying did not find any additional
|
|
information. It may still return NULL, however, if an error occurs in
|
|
<b>pcre_study()</b>.
|
|
</P>
|
|
<P>
|
|
The second argument of <b>pcre_study()</b> contains option bits. There are three
|
|
further options in addition to PCRE_STUDY_EXTRA_NEEDED:
|
|
<pre>
|
|
PCRE_STUDY_JIT_COMPILE
|
|
PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE
|
|
PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE
|
|
</pre>
|
|
If any of these are set, and the just-in-time compiler is available, the
|
|
pattern is further compiled into machine code that executes much faster than
|
|
the <b>pcre_exec()</b> interpretive matching function. If the just-in-time
|
|
compiler is not available, these options are ignored. All undefined bits in the
|
|
<i>options</i> argument must be zero.
|
|
</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 study time.
|
|
Not all patterns can be optimized by the JIT compiler. For those that cannot be
|
|
handled, matching automatically falls back to the <b>pcre_exec()</b>
|
|
interpreter. For more details, see the
|
|
<a href="pcrejit.html"><b>pcrejit</b></a>
|
|
documentation.
|
|
</P>
|
|
<P>
|
|
The third argument for <b>pcre_study()</b> is a pointer for an error message. If
|
|
studying succeeds (even if no data is returned), the variable it points to is
|
|
set to NULL. Otherwise it is set to point to a textual error message. This is a
|
|
static string that is part of the library. You must not try to free it. You
|
|
should test the error pointer for NULL after calling <b>pcre_study()</b>, to be
|
|
sure that it has run successfully.
|
|
</P>
|
|
<P>
|
|
When you are finished with a pattern, you can free the memory used for the
|
|
study data by calling <b>pcre_free_study()</b>. This function was added to the
|
|
API for release 8.20. For earlier versions, the memory could be freed with
|
|
<b>pcre_free()</b>, just like the pattern itself. This will still work in cases
|
|
where JIT optimization is not used, but it is advisable to change to the new
|
|
function when convenient.
|
|
</P>
|
|
<P>
|
|
This is a typical way in which <b>pcre_study</b>() is used (except that in a
|
|
real application there should be tests for errors):
|
|
<pre>
|
|
int rc;
|
|
pcre *re;
|
|
pcre_extra *sd;
|
|
re = pcre_compile("pattern", 0, &error, &erroroffset, NULL);
|
|
sd = pcre_study(
|
|
re, /* result of pcre_compile() */
|
|
0, /* no options */
|
|
&error); /* set to NULL or points to a message */
|
|
rc = pcre_exec( /* see below for details of pcre_exec() options */
|
|
re, sd, "subject", 7, 0, 0, ovector, 30);
|
|
...
|
|
pcre_free_study(sd);
|
|
pcre_free(re);
|
|
</pre>
|
|
Studying a pattern does two things: first, a lower bound for the length of
|
|
subject string that is needed to match the pattern is computed. This does not
|
|
mean that there are any strings of that length that match, but it does
|
|
guarantee that no shorter strings match. The value is used to avoid wasting
|
|
time by trying to match strings that are shorter than the lower bound. You can
|
|
find out the value in a calling program via the <b>pcre_fullinfo()</b> function.
|
|
</P>
|
|
<P>
|
|
Studying a pattern is also useful for non-anchored patterns that do not have a
|
|
single fixed starting character. A bitmap of possible starting bytes is
|
|
created. This speeds up finding a position in the subject at which to start
|
|
matching. (In 16-bit mode, the bitmap is used for 16-bit values less than 256.
|
|
In 32-bit mode, the bitmap is used for 32-bit values less than 256.)
|
|
</P>
|
|
<P>
|
|
These two optimizations apply to both <b>pcre_exec()</b> and
|
|
<b>pcre_dfa_exec()</b>, and the information is also used by the JIT compiler.
|
|
The optimizations can be disabled by setting the PCRE_NO_START_OPTIMIZE option.
|
|
You might want to do this if your pattern contains callouts or (*MARK) and you
|
|
want to make use of these facilities in cases where matching fails.
|
|
</P>
|
|
<P>
|
|
PCRE_NO_START_OPTIMIZE can be specified at either compile time or execution
|
|
time. However, if PCRE_NO_START_OPTIMIZE is passed to <b>pcre_exec()</b>, (that
|
|
is, after any JIT compilation has happened) JIT execution is disabled. For JIT
|
|
execution to work with PCRE_NO_START_OPTIMIZE, the option must be set at
|
|
compile time.
|
|
</P>
|
|
<P>
|
|
There is a longer discussion of PCRE_NO_START_OPTIMIZE
|
|
<a href="#execoptions">below.</a>
|
|
<a name="localesupport"></a></P>
|
|
<br><a name="SEC14" href="#TOC1">LOCALE SUPPORT</a><br>
|
|
<P>
|
|
PCRE 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 in the 16- 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
|
|
PCRE is built with Unicode property support, all characters can be tested with
|
|
\p and \P, or, alternatively, the PCRE_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>
|
|
PCRE contains an internal set of tables that are used when the final argument
|
|
of <b>pcre_compile()</b> is NULL. These are sufficient for many applications.
|
|
Normally, the internal tables recognize only ASCII characters. However, when
|
|
PCRE is built, it is possible to cause the internal tables to be rebuilt in the
|
|
default "C" locale of the local system, which may cause them to be different.
|
|
</P>
|
|
<P>
|
|
The internal tables can always be overridden by tables supplied by the
|
|
application that calls PCRE. These may be created in a different locale from
|
|
the default. As more and more applications change to using Unicode, the need
|
|
for this locale support is expected to die away.
|
|
</P>
|
|
<P>
|
|
External tables are built by calling the <b>pcre_maketables()</b> function,
|
|
which has no arguments, in the relevant locale. The result can then be passed
|
|
to <b>pcre_compile()</b> as often as necessary. For example, to build and use
|
|
tables that are appropriate for the French locale (where accented characters
|
|
with values greater than 128 are treated as letters), the following code could
|
|
be used:
|
|
<pre>
|
|
setlocale(LC_CTYPE, "fr_FR");
|
|
tables = pcre_maketables();
|
|
re = pcre_compile(..., tables);
|
|
</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".
|
|
</P>
|
|
<P>
|
|
When <b>pcre_maketables()</b> runs, the tables are built in memory that is
|
|
obtained via <b>pcre_malloc</b>. 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 to <b>pcre_compile()</b> is saved with the compiled
|
|
pattern, and the same tables are used via this pointer by <b>pcre_study()</b>
|
|
and also by <b>pcre_exec()</b> and <b>pcre_dfa_exec()</b>. Thus, for any single
|
|
pattern, compilation, studying and matching all happen in the same locale, but
|
|
different patterns can be processed in different locales.
|
|
</P>
|
|
<P>
|
|
It is possible to pass a table pointer or NULL (indicating the use of the
|
|
internal tables) to <b>pcre_exec()</b> or <b>pcre_dfa_exec()</b> (see the
|
|
discussion below in the section on matching a pattern). This facility is
|
|
provided for use with pre-compiled patterns that have been saved and reloaded.
|
|
Character tables are not saved with patterns, so if a non-standard table was
|
|
used at compile time, it must be provided again when the reloaded pattern is
|
|
matched. Attempting to use this facility to match a pattern in a different
|
|
locale from the one in which it was compiled is likely to lead to anomalous
|
|
(usually incorrect) results.
|
|
<a name="infoaboutpattern"></a></P>
|
|
<br><a name="SEC15" href="#TOC1">INFORMATION ABOUT A PATTERN</a><br>
|
|
<P>
|
|
<b>int pcre_fullinfo(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b>
|
|
<b> int <i>what</i>, void *<i>where</i>);</b>
|
|
</P>
|
|
<P>
|
|
The <b>pcre_fullinfo()</b> function returns information about a compiled
|
|
pattern. It replaces the <b>pcre_info()</b> function, which was removed from the
|
|
library at version 8.30, after more than 10 years of obsolescence.
|
|
</P>
|
|
<P>
|
|
The first argument for <b>pcre_fullinfo()</b> is a pointer to the compiled
|
|
pattern. The second argument is the result of <b>pcre_study()</b>, or NULL if
|
|
the pattern was not studied. The third argument specifies which piece of
|
|
information is required, and the fourth argument is a pointer to a variable
|
|
to receive the data. The yield of the function is zero for success, or one of
|
|
the following negative numbers:
|
|
<pre>
|
|
PCRE_ERROR_NULL the argument <i>code</i> was NULL
|
|
the argument <i>where</i> was NULL
|
|
PCRE_ERROR_BADMAGIC the "magic number" was not found
|
|
PCRE_ERROR_BADENDIANNESS the pattern was compiled with different
|
|
endianness
|
|
PCRE_ERROR_BADOPTION the value of <i>what</i> was invalid
|
|
PCRE_ERROR_UNSET the requested field is not set
|
|
</pre>
|
|
The "magic number" is placed at the start of each compiled pattern as a simple
|
|
check against passing an arbitrary memory pointer. The endianness error can
|
|
occur if a compiled pattern is saved and reloaded on a different host. Here is
|
|
a typical call of <b>pcre_fullinfo()</b>, to obtain the length of the compiled
|
|
pattern:
|
|
<pre>
|
|
int rc;
|
|
size_t length;
|
|
rc = pcre_fullinfo(
|
|
re, /* result of pcre_compile() */
|
|
sd, /* result of pcre_study(), or NULL */
|
|
PCRE_INFO_SIZE, /* what is required */
|
|
&length); /* where to put the data */
|
|
</pre>
|
|
The possible values for the third argument are defined in <b>pcre.h</b>, and are
|
|
as follows:
|
|
<pre>
|
|
PCRE_INFO_BACKREFMAX
|
|
</pre>
|
|
Return the number of the highest back reference in the pattern. The fourth
|
|
argument should point to an <b>int</b> variable. Zero is returned if there are
|
|
no back references.
|
|
<pre>
|
|
PCRE_INFO_CAPTURECOUNT
|
|
</pre>
|
|
Return the number of capturing subpatterns in the pattern. The fourth argument
|
|
should point to an <b>int</b> variable.
|
|
<pre>
|
|
PCRE_INFO_DEFAULT_TABLES
|
|
</pre>
|
|
Return a pointer to the internal default character tables within PCRE. The
|
|
fourth argument should point to an <b>unsigned char *</b> variable. This
|
|
information call is provided for internal use by the <b>pcre_study()</b>
|
|
function. External callers can cause PCRE to use its internal tables by passing
|
|
a NULL table pointer.
|
|
<pre>
|
|
PCRE_INFO_FIRSTBYTE (deprecated)
|
|
</pre>
|
|
Return information about the first data unit of any matched string, for a
|
|
non-anchored pattern. The name of this option refers to the 8-bit library,
|
|
where data units are bytes. The fourth argument should point to an <b>int</b>
|
|
variable. Negative values are used for special cases. However, this means that
|
|
when the 32-bit library is in non-UTF-32 mode, the full 32-bit range of
|
|
characters cannot be returned. For this reason, this value is deprecated; use
|
|
PCRE_INFO_FIRSTCHARACTERFLAGS and PCRE_INFO_FIRSTCHARACTER instead.
|
|
</P>
|
|
<P>
|
|
If there is a fixed first value, for example, the letter "c" from a pattern
|
|
such as (cat|cow|coyote), its value is returned. In the 8-bit library, the
|
|
value is always less than 256. In the 16-bit library the value can be up to
|
|
0xffff. In the 32-bit library the value can be up to 0x10ffff.
|
|
</P>
|
|
<P>
|
|
If there is no fixed first value, and if either
|
|
<br>
|
|
<br>
|
|
(a) the pattern was compiled with the PCRE_MULTILINE option, and every branch
|
|
starts with "^", or
|
|
<br>
|
|
<br>
|
|
(b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set
|
|
(if it were set, the pattern would be anchored),
|
|
<br>
|
|
<br>
|
|
-1 is returned, indicating that the pattern matches only at the start of a
|
|
subject string or after any newline within the string. Otherwise -2 is
|
|
returned. For anchored patterns, -2 is returned.
|
|
<pre>
|
|
PCRE_INFO_FIRSTCHARACTER
|
|
</pre>
|
|
Return the value of the first data unit (non-UTF character) of any matched
|
|
string in the situation where PCRE_INFO_FIRSTCHARACTERFLAGS returns 1;
|
|
otherwise return 0. The fourth argument should point to a <b>uint_t</b>
|
|
variable.
|
|
</P>
|
|
<P>
|
|
In the 8-bit library, the value is always less than 256. In the 16-bit library
|
|
the value can be up to 0xffff. In the 32-bit library in UTF-32 mode the value
|
|
can be up to 0x10ffff, and up to 0xffffffff when not using UTF-32 mode.
|
|
<pre>
|
|
PCRE_INFO_FIRSTCHARACTERFLAGS
|
|
</pre>
|
|
Return information about the first data unit of any matched string, for a
|
|
non-anchored pattern. The fourth argument should point to an <b>int</b>
|
|
variable.
|
|
</P>
|
|
<P>
|
|
If there is a fixed first value, for example, the letter "c" from a pattern
|
|
such as (cat|cow|coyote), 1 is returned, and the character value can be
|
|
retrieved using PCRE_INFO_FIRSTCHARACTER. If there is no fixed first value, and
|
|
if either
|
|
<br>
|
|
<br>
|
|
(a) the pattern was compiled with the PCRE_MULTILINE option, and every branch
|
|
starts with "^", or
|
|
<br>
|
|
<br>
|
|
(b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set
|
|
(if it were set, the pattern would be anchored),
|
|
<br>
|
|
<br>
|
|
2 is returned, indicating that the pattern matches only at the start of a
|
|
subject string or after any newline within the string. Otherwise 0 is
|
|
returned. For anchored patterns, 0 is returned.
|
|
<pre>
|
|
PCRE_INFO_FIRSTTABLE
|
|
</pre>
|
|
If the pattern was studied, and this resulted in the construction of a 256-bit
|
|
table indicating a fixed set of values for the first data unit in any matching
|
|
string, a pointer to the table is returned. Otherwise NULL is returned. The
|
|
fourth argument should point to an <b>unsigned char *</b> variable.
|
|
<pre>
|
|
PCRE_INFO_HASCRORLF
|
|
</pre>
|
|
Return 1 if the pattern contains any explicit matches for CR or LF characters,
|
|
otherwise 0. The fourth argument should point to an <b>int</b> variable. An
|
|
explicit match is either a literal CR or LF character, or \r or \n.
|
|
<pre>
|
|
PCRE_INFO_JCHANGED
|
|
</pre>
|
|
Return 1 if the (?J) or (?-J) option setting is used in the pattern, otherwise
|
|
0. The fourth argument should point to an <b>int</b> variable. (?J) and
|
|
(?-J) set and unset the local PCRE_DUPNAMES option, respectively.
|
|
<pre>
|
|
PCRE_INFO_JIT
|
|
</pre>
|
|
Return 1 if the pattern was studied with one of the JIT options, and
|
|
just-in-time compiling was successful. The fourth argument should point to an
|
|
<b>int</b> variable. A return value of 0 means that JIT support is not available
|
|
in this version of PCRE, or that the pattern was not studied with a JIT option,
|
|
or that the JIT compiler could not handle this particular pattern. See the
|
|
<a href="pcrejit.html"><b>pcrejit</b></a>
|
|
documentation for details of what can and cannot be handled.
|
|
<pre>
|
|
PCRE_INFO_JITSIZE
|
|
</pre>
|
|
If the pattern was successfully studied with a JIT option, return the size of
|
|
the JIT compiled code, otherwise return zero. The fourth argument should point
|
|
to a <b>size_t</b> variable.
|
|
<pre>
|
|
PCRE_INFO_LASTLITERAL
|
|
</pre>
|
|
Return the value of the rightmost literal data unit that must exist in any
|
|
matched string, other than at its start, if such a value has been recorded. The
|
|
fourth argument should point to an <b>int</b> variable. If there is no such
|
|
value, -1 is returned. For anchored patterns, a last literal value is recorded
|
|
only if it follows something of variable length. For example, for the pattern
|
|
/^a\d+z\d+/ the returned value is "z", but for /^a\dz\d/ the returned value
|
|
is -1.
|
|
</P>
|
|
<P>
|
|
Since for the 32-bit library using the non-UTF-32 mode, this function is unable
|
|
to return the full 32-bit range of characters, this value is deprecated;
|
|
instead the PCRE_INFO_REQUIREDCHARFLAGS and PCRE_INFO_REQUIREDCHAR values should
|
|
be used.
|
|
<pre>
|
|
PCRE_INFO_MATCH_EMPTY
|
|
</pre>
|
|
Return 1 if the pattern can match an empty string, otherwise 0. The fourth
|
|
argument should point to an <b>int</b> variable.
|
|
<pre>
|
|
PCRE_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 fourth argument
|
|
should point to an unsigned 32-bit integer. If no such value has been set, the
|
|
call to <b>pcre_fullinfo()</b> returns the error PCRE_ERROR_UNSET.
|
|
<pre>
|
|
PCRE_INFO_MAXLOOKBEHIND
|
|
</pre>
|
|
Return the number of characters (NB not data units) in the longest lookbehind
|
|
assertion in the pattern. 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>
|
|
PCRE_INFO_MINLENGTH
|
|
</pre>
|
|
If the pattern was studied and a minimum length for matching subject strings
|
|
was computed, its value is returned. Otherwise the returned value is -1. The
|
|
value is a number of characters, which in UTF mode may be different from the
|
|
number of data units. The fourth argument should point to an <b>int</b>
|
|
variable. A non-negative value is a lower bound to the length of any matching
|
|
string. There may not be any strings of that length that do actually match, but
|
|
every string that does match is at least that long.
|
|
<pre>
|
|
PCRE_INFO_NAMECOUNT
|
|
PCRE_INFO_NAMEENTRYSIZE
|
|
PCRE_INFO_NAMETABLE
|
|
</pre>
|
|
PCRE supports the use of named as well as numbered capturing parentheses. The
|
|
names are just an additional way of identifying the parentheses, which still
|
|
acquire numbers. Several convenience functions such as
|
|
<b>pcre_get_named_substring()</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>pcre_exec()</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. PCRE_INFO_NAMECOUNT gives
|
|
the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size of each
|
|
entry; both of these return an <b>int</b> value. The entry size depends on the
|
|
length of the longest name. PCRE_INFO_NAMETABLE returns a pointer to the first
|
|
entry of the table. This is a pointer to <b>char</b> in the 8-bit library, where
|
|
the first two bytes of each entry are the number of the capturing parenthesis,
|
|
most significant byte first. In the 16-bit library, the pointer points to
|
|
16-bit data units, the first of which contains the parenthesis number. 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="pcrepattern.html#dupsubpatternnumber">section on duplicate subpattern numbers</a>
|
|
in the
|
|
<a href="pcrepattern.html"><b>pcrepattern</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.
|
|
Duplicate names for subpatterns with different numbers are permitted,
|
|
but only if PCRE_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 PCRE_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>
|
|
PCRE_INFO_OKPARTIAL
|
|
</pre>
|
|
Return 1 if the pattern can be used for partial matching with
|
|
<b>pcre_exec()</b>, otherwise 0. The fourth argument should point to an
|
|
<b>int</b> variable. From release 8.00, this always returns 1, because the
|
|
restrictions that previously applied to partial matching have been lifted. The
|
|
<a href="pcrepartial.html"><b>pcrepartial</b></a>
|
|
documentation gives details of partial matching.
|
|
<pre>
|
|
PCRE_INFO_OPTIONS
|
|
</pre>
|
|
Return a copy of the options with which the pattern was compiled. The fourth
|
|
argument should point to an <b>unsigned long int</b> variable. These option bits
|
|
are those specified in the call to <b>pcre_compile()</b>, modified by any
|
|
top-level option settings at the start of the pattern itself. In other words,
|
|
they are the options that will be in force when matching starts. For example,
|
|
if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the
|
|
result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED.
|
|
</P>
|
|
<P>
|
|
A pattern is automatically anchored by PCRE if all of its top-level
|
|
alternatives begin with one of the following:
|
|
<pre>
|
|
^ unless PCRE_MULTILINE is set
|
|
\A always
|
|
\G always
|
|
.* if PCRE_DOTALL is set and there are no back references to the subpattern in which .* appears
|
|
</pre>
|
|
For such patterns, the PCRE_ANCHORED bit is set in the options returned by
|
|
<b>pcre_fullinfo()</b>.
|
|
<pre>
|
|
PCRE_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 fourth
|
|
argument should point to an unsigned 32-bit integer. If no such value has been
|
|
set, the call to <b>pcre_fullinfo()</b> returns the error PCRE_ERROR_UNSET.
|
|
<pre>
|
|
PCRE_INFO_SIZE
|
|
</pre>
|
|
Return the size of the compiled pattern in bytes (for all three libraries). The
|
|
fourth argument should point to a <b>size_t</b> variable. This value does not
|
|
include the size of the <b>pcre</b> structure that is returned by
|
|
<b>pcre_compile()</b>. The value that is passed as the argument to
|
|
<b>pcre_malloc()</b> when <b>pcre_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>pcre</b> structure. Studying a compiled pattern, with or without JIT,
|
|
does not alter the value returned by this option.
|
|
<pre>
|
|
PCRE_INFO_STUDYSIZE
|
|
</pre>
|
|
Return the size in bytes (for all three libraries) of the data block pointed to
|
|
by the <i>study_data</i> field in a <b>pcre_extra</b> block. If <b>pcre_extra</b>
|
|
is NULL, or there is no study data, zero is returned. The fourth argument
|
|
should point to a <b>size_t</b> variable. The <i>study_data</i> field is set by
|
|
<b>pcre_study()</b> to record information that will speed up matching (see the
|
|
section entitled
|
|
<a href="#studyingapattern">"Studying a pattern"</a>
|
|
above). The format of the <i>study_data</i> block is private, but its length
|
|
is made available via this option so that it can be saved and restored (see the
|
|
<a href="pcreprecompile.html"><b>pcreprecompile</b></a>
|
|
documentation for details).
|
|
<pre>
|
|
PCRE_INFO_REQUIREDCHARFLAGS
|
|
</pre>
|
|
Returns 1 if there is a rightmost literal data unit that must exist in any
|
|
matched string, other than at its start. The fourth argument should point to
|
|
an <b>int</b> variable. If there is no such value, 0 is returned. If returning
|
|
1, the character value itself can be retrieved using PCRE_INFO_REQUIREDCHAR.
|
|
</P>
|
|
<P>
|
|
For anchored patterns, a last literal value is recorded only if it follows
|
|
something of variable length. For example, for the pattern /^a\d+z\d+/ the
|
|
returned value 1 (with "z" returned from PCRE_INFO_REQUIREDCHAR), but for
|
|
/^a\dz\d/ the returned value is 0.
|
|
<pre>
|
|
PCRE_INFO_REQUIREDCHAR
|
|
</pre>
|
|
Return the value of the rightmost literal data unit that must exist in any
|
|
matched string, other than at its start, if such a value has been recorded. The
|
|
fourth argument should point to a <b>uint32_t</b> variable. If there is no such
|
|
value, 0 is returned.
|
|
</P>
|
|
<br><a name="SEC16" href="#TOC1">REFERENCE COUNTS</a><br>
|
|
<P>
|
|
<b>int pcre_refcount(pcre *<i>code</i>, int <i>adjust</i>);</b>
|
|
</P>
|
|
<P>
|
|
The <b>pcre_refcount()</b> function is used to maintain a reference count in the
|
|
data block that contains a compiled pattern. It is provided for the benefit of
|
|
applications that operate in an object-oriented manner, where different parts
|
|
of the application may be using the same compiled pattern, but you want to free
|
|
the block when they are all done.
|
|
</P>
|
|
<P>
|
|
When a pattern is compiled, the reference count field is initialized to zero.
|
|
It is changed only by calling this function, whose action is to add the
|
|
<i>adjust</i> value (which may be positive or negative) to it. The yield of the
|
|
function is the new value. However, the value of the count is constrained to
|
|
lie between 0 and 65535, inclusive. If the new value is outside these limits,
|
|
it is forced to the appropriate limit value.
|
|
</P>
|
|
<P>
|
|
Except when it is zero, the reference count is not correctly preserved if a
|
|
pattern is compiled on one host and then transferred to a host whose byte-order
|
|
is different. (This seems a highly unlikely scenario.)
|
|
</P>
|
|
<br><a name="SEC17" href="#TOC1">MATCHING A PATTERN: THE TRADITIONAL FUNCTION</a><br>
|
|
<P>
|
|
<b>int pcre_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b>
|
|
<b> const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b>
|
|
<b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>);</b>
|
|
</P>
|
|
<P>
|
|
The function <b>pcre_exec()</b> is called to match a subject string against a
|
|
compiled pattern, which is passed in the <i>code</i> argument. If the
|
|
pattern was studied, the result of the study should be passed in the
|
|
<i>extra</i> argument. You can call <b>pcre_exec()</b> with the same <i>code</i>
|
|
and <i>extra</i> arguments as many times as you like, in order 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>pcre_dfa_exec()</b> function.
|
|
</P>
|
|
<P>
|
|
In most applications, the pattern will have been compiled (and optionally
|
|
studied) in the same process that calls <b>pcre_exec()</b>. However, it is
|
|
possible to save compiled patterns and study data, and then use them later
|
|
in different processes, possibly even on different hosts. For a discussion
|
|
about this, see the
|
|
<a href="pcreprecompile.html"><b>pcreprecompile</b></a>
|
|
documentation.
|
|
</P>
|
|
<P>
|
|
Here is an example of a simple call to <b>pcre_exec()</b>:
|
|
<pre>
|
|
int rc;
|
|
int ovector[30];
|
|
rc = pcre_exec(
|
|
re, /* result of pcre_compile() */
|
|
NULL, /* we didn't study the pattern */
|
|
"some string", /* the subject string */
|
|
11, /* the length of the subject string */
|
|
0, /* start at offset 0 in the subject */
|
|
0, /* default options */
|
|
ovector, /* vector of integers for substring information */
|
|
30); /* number of elements (NOT size in bytes) */
|
|
<a name="extradata"></a></PRE>
|
|
</P>
|
|
<br><b>
|
|
Extra data for <b>pcre_exec()</b>
|
|
</b><br>
|
|
<P>
|
|
If the <i>extra</i> argument is not NULL, it must point to a <b>pcre_extra</b>
|
|
data block. The <b>pcre_study()</b> function returns such a block (when it
|
|
doesn't return NULL), but you can also create one for yourself, and pass
|
|
additional information in it. The <b>pcre_extra</b> block contains the following
|
|
fields (not necessarily in this order):
|
|
<pre>
|
|
unsigned long int <i>flags</i>;
|
|
void *<i>study_data</i>;
|
|
void *<i>executable_jit</i>;
|
|
unsigned long int <i>match_limit</i>;
|
|
unsigned long int <i>match_limit_recursion</i>;
|
|
void *<i>callout_data</i>;
|
|
const unsigned char *<i>tables</i>;
|
|
unsigned char **<i>mark</i>;
|
|
</pre>
|
|
In the 16-bit version of this structure, the <i>mark</i> field has type
|
|
"PCRE_UCHAR16 **".
|
|
<br>
|
|
<br>
|
|
In the 32-bit version of this structure, the <i>mark</i> field has type
|
|
"PCRE_UCHAR32 **".
|
|
</P>
|
|
<P>
|
|
The <i>flags</i> field is used to specify which of the other fields are set. The
|
|
flag bits are:
|
|
<pre>
|
|
PCRE_EXTRA_CALLOUT_DATA
|
|
PCRE_EXTRA_EXECUTABLE_JIT
|
|
PCRE_EXTRA_MARK
|
|
PCRE_EXTRA_MATCH_LIMIT
|
|
PCRE_EXTRA_MATCH_LIMIT_RECURSION
|
|
PCRE_EXTRA_STUDY_DATA
|
|
PCRE_EXTRA_TABLES
|
|
</pre>
|
|
Other flag bits should be set to zero. The <i>study_data</i> field and sometimes
|
|
the <i>executable_jit</i> field are set in the <b>pcre_extra</b> block that is
|
|
returned by <b>pcre_study()</b>, together with the appropriate flag bits. You
|
|
should not set these yourself, but you may add to the block by setting other
|
|
fields and their corresponding flag bits.
|
|
</P>
|
|
<P>
|
|
The <i>match_limit</i> field provides a means of preventing PCRE from using up a
|
|
vast amount of resources when running patterns that are not going to match,
|
|
but which have a very large number of possibilities in their search trees. The
|
|
classic example is a pattern that uses nested unlimited repeats.
|
|
</P>
|
|
<P>
|
|
Internally, <b>pcre_exec()</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.
|
|
</P>
|
|
<P>
|
|
When <b>pcre_exec()</b> is called with a pattern that was successfully studied
|
|
with a JIT option, the way that the matching is executed is entirely different.
|
|
However, there is still the possibility of runaway matching that goes on for a
|
|
very long time, and so the <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 PCRE is built; the default
|
|
default is 10 million, which handles all but the most extreme cases. You can
|
|
override the default by supplying <b>pcre_exec()</b> with a <b>pcre_extra</b>
|
|
block in which <i>match_limit</i> is set, and PCRE_EXTRA_MATCH_LIMIT is set in
|
|
the <i>flags</i> field. If the limit is exceeded, <b>pcre_exec()</b> returns
|
|
PCRE_ERROR_MATCHLIMIT.
|
|
</P>
|
|
<P>
|
|
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=d)
|
|
</pre>
|
|
where d is a decimal number. However, such a setting is ignored unless d is
|
|
less than the limit set by the caller of <b>pcre_exec()</b> or, if no such limit
|
|
is set, less than the default.
|
|
</P>
|
|
<P>
|
|
The <i>match_limit_recursion</i> field 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 machine stack that can be
|
|
used, or, when PCRE has been compiled to use memory on the heap instead of the
|
|
stack, the amount of heap memory that can be used. This limit is not relevant,
|
|
and is ignored, when matching is done using JIT compiled code.
|
|
</P>
|
|
<P>
|
|
The default value for <i>match_limit_recursion</i> can be set when PCRE is
|
|
built; the default default is the same value as the default for
|
|
<i>match_limit</i>. You can override the default by supplying <b>pcre_exec()</b>
|
|
with a <b>pcre_extra</b> block in which <i>match_limit_recursion</i> is set, and
|
|
PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the <i>flags</i> field. If the limit
|
|
is exceeded, <b>pcre_exec()</b> returns PCRE_ERROR_RECURSIONLIMIT.
|
|
</P>
|
|
<P>
|
|
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=d)
|
|
</pre>
|
|
where d is a decimal number. However, such a setting is ignored unless d is
|
|
less than the limit set by the caller of <b>pcre_exec()</b> or, if no such limit
|
|
is set, less than the default.
|
|
</P>
|
|
<P>
|
|
The <i>callout_data</i> field is used in conjunction with the "callout" feature,
|
|
and is described in the
|
|
<a href="pcrecallout.html"><b>pcrecallout</b></a>
|
|
documentation.
|
|
</P>
|
|
<P>
|
|
The <i>tables</i> field is provided for use with patterns that have been
|
|
pre-compiled using custom character tables, saved to disc or elsewhere, and
|
|
then reloaded, because the tables that were used to compile a pattern are not
|
|
saved with it. See the
|
|
<a href="pcreprecompile.html"><b>pcreprecompile</b></a>
|
|
documentation for a discussion of saving compiled patterns for later use. If
|
|
NULL is passed using this mechanism, it forces PCRE's internal tables to be
|
|
used.
|
|
</P>
|
|
<P>
|
|
<b>Warning:</b> The tables that <b>pcre_exec()</b> uses must be the same as those
|
|
that were used when the pattern was compiled. If this is not the case, the
|
|
behaviour of <b>pcre_exec()</b> is undefined. Therefore, when a pattern is
|
|
compiled and matched in the same process, this field should never be set. In
|
|
this (the most common) case, the correct table pointer is automatically passed
|
|
with the compiled pattern from <b>pcre_compile()</b> to <b>pcre_exec()</b>.
|
|
</P>
|
|
<P>
|
|
If PCRE_EXTRA_MARK is set in the <i>flags</i> field, the <i>mark</i> field must
|
|
be set to point to a suitable variable. If the pattern contains any
|
|
backtracking control verbs such as (*MARK:NAME), and the execution ends up with
|
|
a name to pass back, a pointer to the name string (zero terminated) is placed
|
|
in the variable pointed to by the <i>mark</i> field. The names are within the
|
|
compiled pattern; if you wish to retain such a name you must copy it before
|
|
freeing the memory of a compiled pattern. If there is no name to pass back, the
|
|
variable pointed to by the <i>mark</i> field is set to NULL. For details of the
|
|
backtracking control verbs, see the section entitled
|
|
<a href="pcrepattern#backtrackcontrol">"Backtracking control"</a>
|
|
in the
|
|
<a href="pcrepattern.html"><b>pcrepattern</b></a>
|
|
documentation.
|
|
<a name="execoptions"></a></P>
|
|
<br><b>
|
|
Option bits for <b>pcre_exec()</b>
|
|
</b><br>
|
|
<P>
|
|
The unused bits of the <i>options</i> argument for <b>pcre_exec()</b> must be
|
|
zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_<i>xxx</i>,
|
|
PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART,
|
|
PCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_HARD, and
|
|
PCRE_PARTIAL_SOFT.
|
|
</P>
|
|
<P>
|
|
If the pattern was successfully studied with one of the just-in-time (JIT)
|
|
compile options, the only supported options for JIT execution are
|
|
PCRE_NO_UTF8_CHECK, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY,
|
|
PCRE_NOTEMPTY_ATSTART, PCRE_PARTIAL_HARD, and PCRE_PARTIAL_SOFT. If an
|
|
unsupported option is used, JIT execution is disabled and the normal
|
|
interpretive code in <b>pcre_exec()</b> is run.
|
|
<pre>
|
|
PCRE_ANCHORED
|
|
</pre>
|
|
The PCRE_ANCHORED option limits <b>pcre_exec()</b> to matching at the first
|
|
matching position. If a pattern was compiled with PCRE_ANCHORED, or turned out
|
|
to be anchored by virtue of its contents, it cannot be made unachored at
|
|
matching time.
|
|
<pre>
|
|
PCRE_BSR_ANYCRLF
|
|
PCRE_BSR_UNICODE
|
|
</pre>
|
|
These options (which are mutually exclusive) control what the \R escape
|
|
sequence matches. The choice is either to match only CR, LF, or CRLF, or to
|
|
match any Unicode newline sequence. These options override the choice that was
|
|
made or defaulted when the pattern was compiled.
|
|
<pre>
|
|
PCRE_NEWLINE_CR
|
|
PCRE_NEWLINE_LF
|
|
PCRE_NEWLINE_CRLF
|
|
PCRE_NEWLINE_ANYCRLF
|
|
PCRE_NEWLINE_ANY
|
|
</pre>
|
|
These options override the newline definition that was chosen or defaulted when
|
|
the pattern was compiled. For details, see the description of
|
|
<b>pcre_compile()</b> above. During matching, the newline choice affects the
|
|
behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
|
|
the way the match position is advanced after a match failure for an unanchored
|
|
pattern.
|
|
</P>
|
|
<P>
|
|
When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is set, and a
|
|
match attempt for an unanchored pattern fails when the current position is at a
|
|
CRLF sequence, and the pattern contains no explicit matches for CR or LF
|
|
characters, the match position is advanced by two characters instead of one, in
|
|
other words, to after the CRLF.
|
|
</P>
|
|
<P>
|
|
The above rule is a compromise that makes the most common cases work as
|
|
expected. For example, if the pattern is .+A (and the PCRE_DOTALL option is not
|
|
set), it does not match the string "\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, 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.
|
|
<pre>
|
|
PCRE_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 PCRE_MULTILINE (at compile time) causes circumflex
|
|
never to match. This option affects only the behaviour of the circumflex
|
|
metacharacter. It does not affect \A.
|
|
<pre>
|
|
PCRE_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 PCRE_MULTILINE (at
|
|
compile time) causes dollar never to match. This option affects only the
|
|
behaviour of the dollar metacharacter. It does not affect \Z or \z.
|
|
<pre>
|
|
PCRE_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 PCRE_NOTEMPTY set, this match is not
|
|
valid, so PCRE searches further into the string for occurrences of "a" or "b".
|
|
<pre>
|
|
PCRE_NOTEMPTY_ATSTART
|
|
</pre>
|
|
This is like PCRE_NOTEMPTY, except that an empty string match that is not at
|
|
the start of the subject is permitted. If the pattern is anchored, such a match
|
|
can occur only if the pattern contains \K.
|
|
</P>
|
|
<P>
|
|
Perl has no direct equivalent of PCRE_NOTEMPTY or PCRE_NOTEMPTY_ATSTART, but it
|
|
does make a special case of a pattern match of the empty string within its
|
|
<b>split()</b> function, and when using the /g modifier. It is possible to
|
|
emulate Perl's behaviour after matching a null string by first trying the match
|
|
again at the same offset with PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED, and then
|
|
if that fails, by advancing the starting offset (see below) and trying an
|
|
ordinary match again. There is some code that demonstrates how to do this in
|
|
the
|
|
<a href="pcredemo.html"><b>pcredemo</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.
|
|
<pre>
|
|
PCRE_NO_START_OPTIMIZE
|
|
</pre>
|
|
There are a number of optimizations that <b>pcre_exec()</b> uses at the start of
|
|
a match, in order to speed up the process. For example, if it is known that an
|
|
unanchored match must start with a specific character, it searches the subject
|
|
for that character, and fails immediately if it cannot find it, without
|
|
actually running the main matching function. 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 PCRE_NO_START_OPTIMIZE option disables the start-up optimizations, possibly
|
|
causing performance to suffer, but ensuring that in cases where the result is
|
|
"no match", the callouts do occur, and that items such as (*COMMIT) and (*MARK)
|
|
are considered at every possible starting position in the subject string. If
|
|
PCRE_NO_START_OPTIMIZE is set at compile time, it cannot be unset at matching
|
|
time. The use of PCRE_NO_START_OPTIMIZE at matching time (that is, passing it
|
|
to <b>pcre_exec()</b>) disables JIT execution; in this situation, matching is
|
|
always done using interpretively.
|
|
</P>
|
|
<P>
|
|
Setting PCRE_NO_START_OPTIMIZE can change the outcome of a matching operation.
|
|
Consider the pattern
|
|
<pre>
|
|
(*COMMIT)ABC
|
|
</pre>
|
|
When this is compiled, PCRE records the fact that a match must start with the
|
|
character "A". Suppose the subject string is "DEFABC". The start-up
|
|
optimization scans along the subject, finds "A" and runs the first match
|
|
attempt from there. The (*COMMIT) item means that the pattern must match the
|
|
current starting position, which in this case, it does. However, if the same
|
|
match is run with PCRE_NO_START_OPTIMIZE set, the initial scan along the
|
|
subject string does not happen. The first match attempt is run starting from
|
|
"D" and when this fails, (*COMMIT) prevents any further matches being tried, so
|
|
the overall result is "no match". If the pattern is studied, more start-up
|
|
optimizations may be used. 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", "C", and then finally an empty string.
|
|
If the pattern is studied, the final attempt does not take place, because PCRE
|
|
knows that the subject is too short, and so the (*MARK) is never encountered.
|
|
In this case, studying the pattern does not affect the overall match result,
|
|
which is still "no match", but it does affect the auxiliary information that is
|
|
returned.
|
|
<pre>
|
|
PCRE_NO_UTF8_CHECK
|
|
</pre>
|
|
When PCRE_UTF8 is set at compile time, the validity of the subject as a UTF-8
|
|
string is automatically checked when <b>pcre_exec()</b> is subsequently called.
|
|
The entire string is checked before any other processing takes place. The value
|
|
of <i>startoffset</i> is also checked to ensure that it points to the start of a
|
|
UTF-8 character. There is a discussion about the
|
|
<a href="pcreunicode.html#utf8strings">validity of UTF-8 strings</a>
|
|
in the
|
|
<a href="pcreunicode.html"><b>pcreunicode</b></a>
|
|
page. If an invalid sequence of bytes is found, <b>pcre_exec()</b> returns the
|
|
error PCRE_ERROR_BADUTF8 or, if PCRE_PARTIAL_HARD is set and the problem is a
|
|
truncated character at the end of the subject, PCRE_ERROR_SHORTUTF8. In both
|
|
cases, information about the precise nature of the error may also be returned
|
|
(see the descriptions of these errors in the section entitled \fIError return
|
|
values from\fP <b>pcre_exec()</b>
|
|
<a href="#errorlist">below).</a>
|
|
If <i>startoffset</i> contains a value that does not point to the start of a
|
|
UTF-8 character (or to the end of the subject), PCRE_ERROR_BADUTF8_OFFSET is
|
|
returned.
|
|
</P>
|
|
<P>
|
|
If you already know that your subject is valid, and you want to skip these
|
|
checks for performance reasons, you can set the PCRE_NO_UTF8_CHECK option when
|
|
calling <b>pcre_exec()</b>. You might want to do this for the second and
|
|
subsequent calls to <b>pcre_exec()</b> if you are making repeated calls to find
|
|
all the matches in a single subject string. However, you should be sure that
|
|
the value of <i>startoffset</i> points to the start of a character (or the end
|
|
of the subject). When PCRE_NO_UTF8_CHECK is set, the effect of passing an
|
|
invalid string as a subject or an invalid value of <i>startoffset</i> is
|
|
undefined. Your program may crash or loop.
|
|
<pre>
|
|
PCRE_PARTIAL_HARD
|
|
PCRE_PARTIAL_SOFT
|
|
</pre>
|
|
These options turn on the partial matching feature. For backwards
|
|
compatibility, PCRE_PARTIAL is a synonym for PCRE_PARTIAL_SOFT. A partial match
|
|
occurs if the end of the subject string is reached successfully, but there are
|
|
not enough subject characters to complete the match. If this happens when
|
|
PCRE_PARTIAL_SOFT (but not PCRE_PARTIAL_HARD) is set, matching continues by
|
|
testing any remaining alternatives. Only if no complete match can be found is
|
|
PCRE_ERROR_PARTIAL returned instead of PCRE_ERROR_NOMATCH. In other words,
|
|
PCRE_PARTIAL_SOFT says that the caller is prepared to handle a partial match,
|
|
but only if no complete match can be found.
|
|
</P>
|
|
<P>
|
|
If PCRE_PARTIAL_HARD is set, it overrides PCRE_PARTIAL_SOFT. In this case, if a
|
|
partial match is found, <b>pcre_exec()</b> immediately returns
|
|
PCRE_ERROR_PARTIAL, without considering any other alternatives. In other words,
|
|
when PCRE_PARTIAL_HARD is set, a partial match is considered to be more
|
|
important that an alternative complete match.
|
|
</P>
|
|
<P>
|
|
In both cases, the portion of the string that was inspected when the partial
|
|
match was found is set as the first matching string. There is a more detailed
|
|
discussion of partial and multi-segment matching, with examples, in the
|
|
<a href="pcrepartial.html"><b>pcrepartial</b></a>
|
|
documentation.
|
|
</P>
|
|
<br><b>
|
|
The string to be matched by <b>pcre_exec()</b>
|
|
</b><br>
|
|
<P>
|
|
The subject string is passed to <b>pcre_exec()</b> as a pointer in
|
|
<i>subject</i>, a length in <i>length</i>, and a starting offset in
|
|
<i>startoffset</i>. The units for <i>length</i> and <i>startoffset</i> are bytes
|
|
for the 8-bit library, 16-bit data items for the 16-bit library, and 32-bit
|
|
data items for the 32-bit library.
|
|
</P>
|
|
<P>
|
|
If <i>startoffset</i> is negative or greater than the length of the subject,
|
|
<b>pcre_exec()</b> returns PCRE_ERROR_BADOFFSET. When the starting offset is
|
|
zero, the search for a match starts at the beginning of the subject, and this
|
|
is by far the most common case. In UTF-8 or UTF-16 mode, the offset must point
|
|
to the start of a character, or the end of the subject (in UTF-32 mode, one
|
|
data unit equals one character, so all offsets are valid). Unlike 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>pcre_exec()</b> again after a previous success.
|
|
Setting <i>startoffset</i> differs from just passing over a shortened string and
|
|
setting PCRE_NOTBOL in the case of a pattern that begins with any kind of
|
|
lookbehind. For example, consider the pattern
|
|
<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 "Mississippi" the first call to <b>pcre_exec()</b> finds the first
|
|
occurrence. If <b>pcre_exec()</b> is called again with just the remainder of the
|
|
subject, namely "issippi", 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>pcre_exec()</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 PCRE_NOTEMPTY_ATSTART and
|
|
PCRE_ANCHORED options, and then if that fails, advancing the starting offset
|
|
and trying an ordinary match again. There is some code that demonstrates how to
|
|
do this in the
|
|
<a href="pcredemo.html"><b>pcredemo</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.
|
|
</P>
|
|
<br><b>
|
|
How <b>pcre_exec()</b> returns captured substrings
|
|
</b><br>
|
|
<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 parts of the
|
|
pattern. Following the usage in Jeffrey Friedl's book, this is called
|
|
"capturing" in what follows, and the phrase "capturing subpattern" is used for
|
|
a fragment of a pattern that picks out a substring. PCRE supports several other
|
|
kinds of parenthesized subpattern that do not cause substrings to be captured.
|
|
</P>
|
|
<P>
|
|
Captured substrings are returned to the caller via a vector of integers whose
|
|
address is passed in <i>ovector</i>. The number of elements in the vector is
|
|
passed in <i>ovecsize</i>, which must be a non-negative number. <b>Note</b>: this
|
|
argument is NOT the size of <i>ovector</i> in bytes.
|
|
</P>
|
|
<P>
|
|
The first two-thirds of the vector is used to pass back captured substrings,
|
|
each substring using a pair of integers. The remaining third of the vector is
|
|
used as workspace by <b>pcre_exec()</b> while matching capturing subpatterns,
|
|
and is not available for passing back information. The number passed in
|
|
<i>ovecsize</i> should always be a multiple of three. If it is not, it is
|
|
rounded down.
|
|
</P>
|
|
<P>
|
|
When a match is successful, information about captured substrings is returned
|
|
in pairs of integers, starting at the beginning of <i>ovector</i>, and
|
|
continuing up to two-thirds of its length at the most. The first element of
|
|
each pair is set to the offset of the first character in a substring, and the
|
|
second is set to the offset of the first character after the end of a
|
|
substring. These values are always data unit offsets, even in UTF mode. They
|
|
are byte offsets in the 8-bit library, 16-bit data item offsets in the 16-bit
|
|
library, and 32-bit data item offsets in the 32-bit library. <b>Note</b>: they
|
|
are not character counts.
|
|
</P>
|
|
<P>
|
|
The first pair of integers, <i>ovector[0]</i> and <i>ovector[1]</i>, identify the
|
|
portion of the subject string matched by the entire pattern. The next pair is
|
|
used for the first capturing subpattern, and so on. The value returned by
|
|
<b>pcre_exec()</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, it is the last portion of the
|
|
string that it matched that is returned.
|
|
</P>
|
|
<P>
|
|
If the vector is too small to hold all the captured substring offsets, it is
|
|
used as far as possible (up to two-thirds of its length), and the function
|
|
returns a value of zero. If neither the actual string matched nor any captured
|
|
substrings are of interest, <b>pcre_exec()</b> may be called with <i>ovector</i>
|
|
passed as NULL and <i>ovecsize</i> as zero. However, if the pattern contains
|
|
back references and the <i>ovector</i> is not big enough to remember the related
|
|
substrings, PCRE has to get additional memory for use during matching. Thus it
|
|
is usually advisable to supply an <i>ovector</i> of reasonable size.
|
|
</P>
|
|
<P>
|
|
There are some cases where zero is returned (indicating vector overflow) when
|
|
in fact the vector is exactly the right size for the final match. For example,
|
|
consider the pattern
|
|
<pre>
|
|
(a)(?:(b)c|bd)
|
|
</pre>
|
|
If a vector of 6 elements (allowing for only 1 captured substring) is given
|
|
with subject string "abd", <b>pcre_exec()</b> will try to set the second
|
|
captured string, thereby recording a vector overflow, before failing to match
|
|
"c" and backing up to try the second alternative. The zero return, however,
|
|
does correctly indicate that the maximum number of slots (namely 2) have been
|
|
filled. In similar cases where there is temporary overflow, but the final
|
|
number of used slots is actually less than the maximum, a non-zero value is
|
|
returned.
|
|
</P>
|
|
<P>
|
|
The <b>pcre_fullinfo()</b> function can be used to find out how many capturing
|
|
subpatterns there are in a compiled pattern. The smallest size for
|
|
<i>ovector</i> that will allow for <i>n</i> captured substrings, in addition to
|
|
the offsets of the substring matched by the whole pattern, is (<i>n</i>+1)*3.
|
|
</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 -1.
|
|
</P>
|
|
<P>
|
|
Offset values that correspond to unused subpatterns at the end of the
|
|
expression are also set to -1. For example, if the string "abc" is matched
|
|
against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The
|
|
return from the function is 2, because the highest used capturing subpattern
|
|
number is 1, and the offsets for for the second and third capturing subpatterns
|
|
(assuming the vector is large enough, of course) are set to -1.
|
|
</P>
|
|
<P>
|
|
<b>Note</b>: Elements in the first two-thirds of <i>ovector</i> 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>pcre_exec()</b>. The other
|
|
elements (in the first two-thirds) retain whatever values they previously had.
|
|
</P>
|
|
<P>
|
|
Some convenience functions are provided for extracting the captured substrings
|
|
as separate strings. These are described below.
|
|
<a name="errorlist"></a></P>
|
|
<br><b>
|
|
Error return values from <b>pcre_exec()</b>
|
|
</b><br>
|
|
<P>
|
|
If <b>pcre_exec()</b> fails, it returns a negative number. The following are
|
|
defined in the header file:
|
|
<pre>
|
|
PCRE_ERROR_NOMATCH (-1)
|
|
</pre>
|
|
The subject string did not match the pattern.
|
|
<pre>
|
|
PCRE_ERROR_NULL (-2)
|
|
</pre>
|
|
Either <i>code</i> or <i>subject</i> was passed as NULL, or <i>ovector</i> was
|
|
NULL and <i>ovecsize</i> was not zero.
|
|
<pre>
|
|
PCRE_ERROR_BADOPTION (-3)
|
|
</pre>
|
|
An unrecognized bit was set in the <i>options</i> argument.
|
|
<pre>
|
|
PCRE_ERROR_BADMAGIC (-4)
|
|
</pre>
|
|
PCRE stores a 4-byte "magic number" at the start of the compiled code, to catch
|
|
the case when it is passed a junk pointer and to detect when a pattern that was
|
|
compiled in an environment of one endianness is run in an environment with the
|
|
other endianness. This is the error that PCRE gives when the magic number is
|
|
not present.
|
|
<pre>
|
|
PCRE_ERROR_UNKNOWN_OPCODE (-5)
|
|
</pre>
|
|
While running the pattern match, an unknown item was encountered in the
|
|
compiled pattern. This error could be caused by a bug in PCRE or by overwriting
|
|
of the compiled pattern.
|
|
<pre>
|
|
PCRE_ERROR_NOMEMORY (-6)
|
|
</pre>
|
|
If a pattern contains back references, but the <i>ovector</i> that is passed to
|
|
<b>pcre_exec()</b> is not big enough to remember the referenced substrings, PCRE
|
|
gets a block of memory at the start of matching to use for this purpose. If the
|
|
call via <b>pcre_malloc()</b> fails, this error is given. The memory is
|
|
automatically freed at the end of matching.
|
|
</P>
|
|
<P>
|
|
This error is also given if <b>pcre_stack_malloc()</b> fails in
|
|
<b>pcre_exec()</b>. This can happen only when PCRE has been compiled with
|
|
<b>--disable-stack-for-recursion</b>.
|
|
<pre>
|
|
PCRE_ERROR_NOSUBSTRING (-7)
|
|
</pre>
|
|
This error is used by the <b>pcre_copy_substring()</b>,
|
|
<b>pcre_get_substring()</b>, and <b>pcre_get_substring_list()</b> functions (see
|
|
below). It is never returned by <b>pcre_exec()</b>.
|
|
<pre>
|
|
PCRE_ERROR_MATCHLIMIT (-8)
|
|
</pre>
|
|
The backtracking limit, as specified by the <i>match_limit</i> field in a
|
|
<b>pcre_extra</b> structure (or defaulted) was reached. See the description
|
|
above.
|
|
<pre>
|
|
PCRE_ERROR_CALLOUT (-9)
|
|
</pre>
|
|
This error is never generated by <b>pcre_exec()</b> itself. It is provided for
|
|
use by callout functions that want to yield a distinctive error code. See the
|
|
<a href="pcrecallout.html"><b>pcrecallout</b></a>
|
|
documentation for details.
|
|
<pre>
|
|
PCRE_ERROR_BADUTF8 (-10)
|
|
</pre>
|
|
A string that contains an invalid UTF-8 byte sequence was passed as a subject,
|
|
and the PCRE_NO_UTF8_CHECK option was not set. If the size of the output vector
|
|
(<i>ovecsize</i>) is at least 2, the byte offset to the start of the the invalid
|
|
UTF-8 character is placed in the first element, and a reason code is placed in
|
|
the second element. The reason codes are listed in the
|
|
<a href="#badutf8reasons">following section.</a>
|
|
For backward compatibility, if PCRE_PARTIAL_HARD is set and the problem is a
|
|
truncated UTF-8 character at the end of the subject (reason codes 1 to 5),
|
|
PCRE_ERROR_SHORTUTF8 is returned instead of PCRE_ERROR_BADUTF8.
|
|
<pre>
|
|
PCRE_ERROR_BADUTF8_OFFSET (-11)
|
|
</pre>
|
|
The UTF-8 byte sequence that was passed as a subject was checked and found to
|
|
be valid (the PCRE_NO_UTF8_CHECK option was not set), but the value of
|
|
<i>startoffset</i> did not point to the beginning of a UTF-8 character or the
|
|
end of the subject.
|
|
<pre>
|
|
PCRE_ERROR_PARTIAL (-12)
|
|
</pre>
|
|
The subject string did not match, but it did match partially. See the
|
|
<a href="pcrepartial.html"><b>pcrepartial</b></a>
|
|
documentation for details of partial matching.
|
|
<pre>
|
|
PCRE_ERROR_BADPARTIAL (-13)
|
|
</pre>
|
|
This code is no longer in use. It was formerly returned when the PCRE_PARTIAL
|
|
option was used with a compiled pattern containing items that were not
|
|
supported for partial matching. From release 8.00 onwards, there are no
|
|
restrictions on partial matching.
|
|
<pre>
|
|
PCRE_ERROR_INTERNAL (-14)
|
|
</pre>
|
|
An unexpected internal error has occurred. This error could be caused by a bug
|
|
in PCRE or by overwriting of the compiled pattern.
|
|
<pre>
|
|
PCRE_ERROR_BADCOUNT (-15)
|
|
</pre>
|
|
This error is given if the value of the <i>ovecsize</i> argument is negative.
|
|
<pre>
|
|
PCRE_ERROR_RECURSIONLIMIT (-21)
|
|
</pre>
|
|
The internal recursion limit, as specified by the <i>match_limit_recursion</i>
|
|
field in a <b>pcre_extra</b> structure (or defaulted) was reached. See the
|
|
description above.
|
|
<pre>
|
|
PCRE_ERROR_BADNEWLINE (-23)
|
|
</pre>
|
|
An invalid combination of PCRE_NEWLINE_<i>xxx</i> options was given.
|
|
<pre>
|
|
PCRE_ERROR_BADOFFSET (-24)
|
|
</pre>
|
|
The value of <i>startoffset</i> was negative or greater than the length of the
|
|
subject, that is, the value in <i>length</i>.
|
|
<pre>
|
|
PCRE_ERROR_SHORTUTF8 (-25)
|
|
</pre>
|
|
This error is returned instead of PCRE_ERROR_BADUTF8 when the subject string
|
|
ends with a truncated UTF-8 character and the PCRE_PARTIAL_HARD option is set.
|
|
Information about the failure is returned as for PCRE_ERROR_BADUTF8. It is in
|
|
fact sufficient to detect this case, but this special error code for
|
|
PCRE_PARTIAL_HARD precedes the implementation of returned information; it is
|
|
retained for backwards compatibility.
|
|
<pre>
|
|
PCRE_ERROR_RECURSELOOP (-26)
|
|
</pre>
|
|
This error is returned when <b>pcre_exec()</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>
|
|
PCRE_ERROR_JIT_STACKLIMIT (-27)
|
|
</pre>
|
|
This error is returned when a pattern that was successfully studied using a
|
|
JIT compile option is being matched, but the memory available for the
|
|
just-in-time processing stack is not large enough. See the
|
|
<a href="pcrejit.html"><b>pcrejit</b></a>
|
|
documentation for more details.
|
|
<pre>
|
|
PCRE_ERROR_BADMODE (-28)
|
|
</pre>
|
|
This error is given if a pattern that was compiled by the 8-bit library is
|
|
passed to a 16-bit or 32-bit library function, or vice versa.
|
|
<pre>
|
|
PCRE_ERROR_BADENDIANNESS (-29)
|
|
</pre>
|
|
This error is given if a pattern that was compiled and saved is reloaded on a
|
|
host with different endianness. The utility function
|
|
<b>pcre_pattern_to_host_byte_order()</b> can be used to convert such a pattern
|
|
so that it runs on the new host.
|
|
<pre>
|
|
PCRE_ERROR_JIT_BADOPTION
|
|
</pre>
|
|
This error is returned when a pattern that was successfully studied using a JIT
|
|
compile option is being matched, but the matching mode (partial or complete
|
|
match) does not correspond to any JIT compilation mode. When the JIT fast path
|
|
function is used, this error may be also given for invalid options. See the
|
|
<a href="pcrejit.html"><b>pcrejit</b></a>
|
|
documentation for more details.
|
|
<pre>
|
|
PCRE_ERROR_BADLENGTH (-32)
|
|
</pre>
|
|
This error is given if <b>pcre_exec()</b> is called with a negative value for
|
|
the <i>length</i> argument.
|
|
</P>
|
|
<P>
|
|
Error numbers -16 to -20, -22, and 30 are not used by <b>pcre_exec()</b>.
|
|
<a name="badutf8reasons"></a></P>
|
|
<br><b>
|
|
Reason codes for invalid UTF-8 strings
|
|
</b><br>
|
|
<P>
|
|
This section applies only to the 8-bit library. The corresponding information
|
|
for the 16-bit and 32-bit libraries is given in the
|
|
<a href="pcre16.html"><b>pcre16</b></a>
|
|
and
|
|
<a href="pcre32.html"><b>pcre32</b></a>
|
|
pages.
|
|
</P>
|
|
<P>
|
|
When <b>pcre_exec()</b> returns either PCRE_ERROR_BADUTF8 or
|
|
PCRE_ERROR_SHORTUTF8, and the size of the output vector (<i>ovecsize</i>) is at
|
|
least 2, the offset of the start of the invalid UTF-8 character is placed in
|
|
the first output vector element (<i>ovector[0]</i>) and a reason code is placed
|
|
in the second element (<i>ovector[1]</i>). The reason codes are given names in
|
|
the <b>pcre.h</b> header file:
|
|
<pre>
|
|
PCRE_UTF8_ERR1
|
|
PCRE_UTF8_ERR2
|
|
PCRE_UTF8_ERR3
|
|
PCRE_UTF8_ERR4
|
|
PCRE_UTF8_ERR5
|
|
</pre>
|
|
The string ends with a truncated UTF-8 character; the code specifies how many
|
|
bytes are missing (1 to 5). Although RFC 3629 restricts UTF-8 characters to be
|
|
no longer than 4 bytes, the encoding scheme (originally defined by RFC 2279)
|
|
allows for up to 6 bytes, and this is checked first; hence the possibility of
|
|
4 or 5 missing bytes.
|
|
<pre>
|
|
PCRE_UTF8_ERR6
|
|
PCRE_UTF8_ERR7
|
|
PCRE_UTF8_ERR8
|
|
PCRE_UTF8_ERR9
|
|
PCRE_UTF8_ERR10
|
|
</pre>
|
|
The two most significant bits of the 2nd, 3rd, 4th, 5th, or 6th byte of the
|
|
character do not have the binary value 0b10 (that is, either the most
|
|
significant bit is 0, or the next bit is 1).
|
|
<pre>
|
|
PCRE_UTF8_ERR11
|
|
PCRE_UTF8_ERR12
|
|
</pre>
|
|
A character that is valid by the RFC 2279 rules is either 5 or 6 bytes long;
|
|
these code points are excluded by RFC 3629.
|
|
<pre>
|
|
PCRE_UTF8_ERR13
|
|
</pre>
|
|
A 4-byte character has a value greater than 0x10fff; these code points are
|
|
excluded by RFC 3629.
|
|
<pre>
|
|
PCRE_UTF8_ERR14
|
|
</pre>
|
|
A 3-byte character has a value in the range 0xd800 to 0xdfff; this range of
|
|
code points are reserved by RFC 3629 for use with UTF-16, and so are excluded
|
|
from UTF-8.
|
|
<pre>
|
|
PCRE_UTF8_ERR15
|
|
PCRE_UTF8_ERR16
|
|
PCRE_UTF8_ERR17
|
|
PCRE_UTF8_ERR18
|
|
PCRE_UTF8_ERR19
|
|
</pre>
|
|
A 2-, 3-, 4-, 5-, or 6-byte character is "overlong", that is, it codes for a
|
|
value that can be represented by fewer bytes, which is invalid. For example,
|
|
the two bytes 0xc0, 0xae give the value 0x2e, whose correct coding uses just
|
|
one byte.
|
|
<pre>
|
|
PCRE_UTF8_ERR20
|
|
</pre>
|
|
The two most significant bits of the first byte of a character have the binary
|
|
value 0b10 (that is, the most significant bit is 1 and the second is 0). Such a
|
|
byte can only validly occur as the second or subsequent byte of a multi-byte
|
|
character.
|
|
<pre>
|
|
PCRE_UTF8_ERR21
|
|
</pre>
|
|
The first byte of a character has the value 0xfe or 0xff. These values can
|
|
never occur in a valid UTF-8 string.
|
|
<pre>
|
|
PCRE_UTF8_ERR22
|
|
</pre>
|
|
This error code was formerly used when the presence of a so-called
|
|
"non-character" caused an error. Unicode corrigendum #9 makes it clear that
|
|
such characters should not cause a string to be rejected, and so this code is
|
|
no longer in use and is never returned.
|
|
</P>
|
|
<br><a name="SEC18" href="#TOC1">EXTRACTING CAPTURED SUBSTRINGS BY NUMBER</a><br>
|
|
<P>
|
|
<b>int pcre_copy_substring(const char *<i>subject</i>, int *<i>ovector</i>,</b>
|
|
<b> int <i>stringcount</i>, int <i>stringnumber</i>, char *<i>buffer</i>,</b>
|
|
<b> int <i>buffersize</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre_get_substring(const char *<i>subject</i>, int *<i>ovector</i>,</b>
|
|
<b> int <i>stringcount</i>, int <i>stringnumber</i>,</b>
|
|
<b> const char **<i>stringptr</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre_get_substring_list(const char *<i>subject</i>,</b>
|
|
<b> int *<i>ovector</i>, int <i>stringcount</i>, const char ***<i>listptr</i>);</b>
|
|
</P>
|
|
<P>
|
|
Captured substrings can be accessed directly by using the offsets returned by
|
|
<b>pcre_exec()</b> in <i>ovector</i>. For convenience, the functions
|
|
<b>pcre_copy_substring()</b>, <b>pcre_get_substring()</b>, and
|
|
<b>pcre_get_substring_list()</b> are provided for extracting captured substrings
|
|
as new, separate, zero-terminated strings. These functions identify substrings
|
|
by number. The next section describes functions for extracting named
|
|
substrings.
|
|
</P>
|
|
<P>
|
|
A substring that contains a binary zero is correctly extracted and has a
|
|
further zero added on the end, but the result is not, of course, a C string.
|
|
However, you can process such a string by referring to the length that is
|
|
returned by <b>pcre_copy_substring()</b> and <b>pcre_get_substring()</b>.
|
|
Unfortunately, the interface to <b>pcre_get_substring_list()</b> is not adequate
|
|
for handling strings containing binary zeros, because the end of the final
|
|
string is not independently indicated.
|
|
</P>
|
|
<P>
|
|
The first three arguments are the same for all three of these functions:
|
|
<i>subject</i> is the subject string that has just been successfully matched,
|
|
<i>ovector</i> is a pointer to the vector of integer offsets that was passed to
|
|
<b>pcre_exec()</b>, and <i>stringcount</i> is the number of substrings that were
|
|
captured by the match, including the substring that matched the entire regular
|
|
expression. This is the value returned by <b>pcre_exec()</b> if it is greater
|
|
than zero. If <b>pcre_exec()</b> returned zero, indicating that it ran out of
|
|
space in <i>ovector</i>, the value passed as <i>stringcount</i> should be the
|
|
number of elements in the vector divided by three.
|
|
</P>
|
|
<P>
|
|
The functions <b>pcre_copy_substring()</b> and <b>pcre_get_substring()</b>
|
|
extract a single substring, whose number is given as <i>stringnumber</i>. A
|
|
value of zero extracts the substring that matched the entire pattern, whereas
|
|
higher values extract the captured substrings. For <b>pcre_copy_substring()</b>,
|
|
the string is placed in <i>buffer</i>, whose length is given by
|
|
<i>buffersize</i>, while for <b>pcre_get_substring()</b> a new block of memory is
|
|
obtained via <b>pcre_malloc</b>, and its address is returned via
|
|
<i>stringptr</i>. The yield of the function is the length of the string, not
|
|
including the terminating zero, or one of these error codes:
|
|
<pre>
|
|
PCRE_ERROR_NOMEMORY (-6)
|
|
</pre>
|
|
The buffer was too small for <b>pcre_copy_substring()</b>, or the attempt to get
|
|
memory failed for <b>pcre_get_substring()</b>.
|
|
<pre>
|
|
PCRE_ERROR_NOSUBSTRING (-7)
|
|
</pre>
|
|
There is no substring whose number is <i>stringnumber</i>.
|
|
</P>
|
|
<P>
|
|
The <b>pcre_get_substring_list()</b> function extracts all available substrings
|
|
and builds a list of pointers to them. All this is done in a single block of
|
|
memory that is obtained via <b>pcre_malloc</b>. 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 yield of the
|
|
function is zero if all went well, or the error code
|
|
<pre>
|
|
PCRE_ERROR_NOMEMORY (-6)
|
|
</pre>
|
|
if the attempt to get the memory block failed.
|
|
</P>
|
|
<P>
|
|
When any of these functions encounter 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, they return an empty
|
|
string. This can be distinguished from a genuine zero-length substring by
|
|
inspecting the appropriate offset in <i>ovector</i>, which is negative for unset
|
|
substrings.
|
|
</P>
|
|
<P>
|
|
The two convenience functions <b>pcre_free_substring()</b> and
|
|
<b>pcre_free_substring_list()</b> can be used to free the memory returned by
|
|
a previous call of <b>pcre_get_substring()</b> or
|
|
<b>pcre_get_substring_list()</b>, respectively. They do nothing more than call
|
|
the function pointed to by <b>pcre_free</b>, which of course could be called
|
|
directly from a C program. However, PCRE is used in some situations where it is
|
|
linked via a special interface to another programming language that cannot use
|
|
<b>pcre_free</b> directly; it is for these cases that the functions are
|
|
provided.
|
|
</P>
|
|
<br><a name="SEC19" href="#TOC1">EXTRACTING CAPTURED SUBSTRINGS BY NAME</a><br>
|
|
<P>
|
|
<b>int pcre_get_stringnumber(const pcre *<i>code</i>,</b>
|
|
<b> const char *<i>name</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre_copy_named_substring(const pcre *<i>code</i>,</b>
|
|
<b> const char *<i>subject</i>, int *<i>ovector</i>,</b>
|
|
<b> int <i>stringcount</i>, const char *<i>stringname</i>,</b>
|
|
<b> char *<i>buffer</i>, int <i>buffersize</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre_get_named_substring(const pcre *<i>code</i>,</b>
|
|
<b> const char *<i>subject</i>, int *<i>ovector</i>,</b>
|
|
<b> int <i>stringcount</i>, const char *<i>stringname</i>,</b>
|
|
<b> const char **<i>stringptr</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 (PCRE_DUPNAMES was not set), you can find the number from the name by
|
|
calling <b>pcre_get_stringnumber()</b>. The first argument is the compiled
|
|
pattern, and the second is the name. The yield of the function is the
|
|
subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no subpattern of
|
|
that name.
|
|
</P>
|
|
<P>
|
|
Given the number, you can extract the substring directly, or use one of the
|
|
functions described in the previous section. For convenience, there are also
|
|
two functions that do the whole job.
|
|
</P>
|
|
<P>
|
|
Most of the arguments of <b>pcre_copy_named_substring()</b> and
|
|
<b>pcre_get_named_substring()</b> are the same as those for the similarly named
|
|
functions that extract by number. As these are described in the previous
|
|
section, they are not re-described here. There are just two differences:
|
|
</P>
|
|
<P>
|
|
First, instead of a substring number, a substring name is given. Second, there
|
|
is an extra argument, given at the start, which is a pointer to the compiled
|
|
pattern. This is needed in order to gain access to the name-to-number
|
|
translation table.
|
|
</P>
|
|
<P>
|
|
These functions call <b>pcre_get_stringnumber()</b>, and if it succeeds, they
|
|
then call <b>pcre_copy_substring()</b> or <b>pcre_get_substring()</b>, as
|
|
appropriate. <b>NOTE:</b> If PCRE_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="pcrepattern.html#dupsubpatternnumber">section on duplicate subpattern numbers</a>
|
|
in the
|
|
<a href="pcrepattern.html"><b>pcrepattern</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="SEC20" href="#TOC1">DUPLICATE SUBPATTERN NAMES</a><br>
|
|
<P>
|
|
<b>int pcre_get_stringtable_entries(const pcre *<i>code</i>,</b>
|
|
<b> const char *<i>name</i>, char **<i>first</i>, char **<i>last</i>);</b>
|
|
</P>
|
|
<P>
|
|
When a pattern is compiled with the PCRE_DUPNAMES option, names for subpatterns
|
|
are not required to be unique. (Duplicate names are always allowed for
|
|
subpatterns with the same number, created by using the (?| feature. Indeed, if
|
|
such subpatterns are named, they are required to use the same names.)
|
|
</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="pcrepattern.html"><b>pcrepattern</b></a>
|
|
documentation.
|
|
</P>
|
|
<P>
|
|
When duplicates are present, <b>pcre_copy_named_substring()</b> and
|
|
<b>pcre_get_named_substring()</b> return the first substring corresponding to
|
|
the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING (-7) is
|
|
returned; no data is returned. The <b>pcre_get_stringnumber()</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>pcre_get_stringtable_entries()</b> function. The first
|
|
argument is the compiled pattern, and the second is the name. The third and
|
|
fourth are pointers to variables which are updated by the function. After it
|
|
has run, they point to the first and last entries in the name-to-number table
|
|
for the given name. The function itself returns the length of each entry, or
|
|
PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is
|
|
described above in the section entitled <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, if any.
|
|
</P>
|
|
<br><a name="SEC21" 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, consider
|
|
using the alternative matching function (see below) instead. If you cannot use
|
|
the alternative function, but still need to find all possible matches, you
|
|
can kludge it up by making use of the callout facility, which is described in
|
|
the
|
|
<a href="pcrecallout.html"><b>pcrecallout</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>pcre_exec()</b> to backtrack and try
|
|
other alternatives. Ultimately, when it runs out of matches, <b>pcre_exec()</b>
|
|
will yield PCRE_ERROR_NOMATCH.
|
|
</P>
|
|
<br><a name="SEC22" href="#TOC1">OBTAINING AN ESTIMATE OF STACK USAGE</a><br>
|
|
<P>
|
|
Matching certain patterns using <b>pcre_exec()</b> can use a lot of process
|
|
stack, which in certain environments can be rather limited in size. Some users
|
|
find it helpful to have an estimate of the amount of stack that is used by
|
|
<b>pcre_exec()</b>, to help them set recursion limits, as described in the
|
|
<a href="pcrestack.html"><b>pcrestack</b></a>
|
|
documentation. The estimate that is output by <b>pcretest</b> when called with
|
|
the <b>-m</b> and <b>-C</b> options is obtained by calling <b>pcre_exec</b> with
|
|
the values NULL, NULL, NULL, -999, and -999 for its first five arguments.
|
|
</P>
|
|
<P>
|
|
Normally, if its first argument is NULL, <b>pcre_exec()</b> immediately returns
|
|
the negative error code PCRE_ERROR_NULL, but with this special combination of
|
|
arguments, it returns instead a negative number whose absolute value is the
|
|
approximate stack frame size in bytes. (A negative number is used so that it is
|
|
clear that no match has happened.) The value is approximate because in some
|
|
cases, recursive calls to <b>pcre_exec()</b> occur when there are one or two
|
|
additional variables on the stack.
|
|
</P>
|
|
<P>
|
|
If PCRE has been compiled to use the heap instead of the stack for recursion,
|
|
the value returned is the size of each block that is obtained from the heap.
|
|
<a name="dfamatch"></a></P>
|
|
<br><a name="SEC23" href="#TOC1">MATCHING A PATTERN: THE ALTERNATIVE FUNCTION</a><br>
|
|
<P>
|
|
<b>int pcre_dfa_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b>
|
|
<b> const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b>
|
|
<b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b>
|
|
<b> int *<i>workspace</i>, int <i>wscount</i>);</b>
|
|
</P>
|
|
<P>
|
|
The function <b>pcre_dfa_exec()</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 PCRE
|
|
patterns are not supported. Nevertheless, there are times when this kind of
|
|
matching can be useful. For a discussion of the two matching algorithms, and a
|
|
list of features that <b>pcre_dfa_exec()</b> does not support, see the
|
|
<a href="pcrematching.html"><b>pcrematching</b></a>
|
|
documentation.
|
|
</P>
|
|
<P>
|
|
The arguments for the <b>pcre_dfa_exec()</b> function are the same as for
|
|
<b>pcre_exec()</b>, plus two extras. The <i>ovector</i> argument is used in a
|
|
different way, and this is described below. The other common arguments are used
|
|
in the same way as for <b>pcre_exec()</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 will be 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>pcre_dfa_exec()</b>:
|
|
<pre>
|
|
int rc;
|
|
int ovector[10];
|
|
int wspace[20];
|
|
rc = pcre_dfa_exec(
|
|
re, /* result of pcre_compile() */
|
|
NULL, /* we didn't study the pattern */
|
|
"some string", /* the subject string */
|
|
11, /* the length of the subject string */
|
|
0, /* start at offset 0 in the subject */
|
|
0, /* default options */
|
|
ovector, /* vector of integers for substring information */
|
|
10, /* number of elements (NOT size in bytes) */
|
|
wspace, /* working space vector */
|
|
20); /* number of elements (NOT size in bytes) */
|
|
</PRE>
|
|
</P>
|
|
<br><b>
|
|
Option bits for <b>pcre_dfa_exec()</b>
|
|
</b><br>
|
|
<P>
|
|
The unused bits of the <i>options</i> argument for <b>pcre_dfa_exec()</b> must be
|
|
zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_<i>xxx</i>,
|
|
PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART,
|
|
PCRE_NO_UTF8_CHECK, PCRE_BSR_ANYCRLF, PCRE_BSR_UNICODE, PCRE_NO_START_OPTIMIZE,
|
|
PCRE_PARTIAL_HARD, PCRE_PARTIAL_SOFT, PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART.
|
|
All but the last four of these are exactly the same as for <b>pcre_exec()</b>,
|
|
so their description is not repeated here.
|
|
<pre>
|
|
PCRE_PARTIAL_HARD
|
|
PCRE_PARTIAL_SOFT
|
|
</pre>
|
|
These have the same general effect as they do for <b>pcre_exec()</b>, but the
|
|
details are slightly different. When PCRE_PARTIAL_HARD is set for
|
|
<b>pcre_dfa_exec()</b>, it returns PCRE_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 also
|
|
been found. When PCRE_PARTIAL_SOFT is set, the return code PCRE_ERROR_NOMATCH
|
|
is converted into PCRE_ERROR_PARTIAL if the end of the subject is reached,
|
|
there have been no complete matches, but there is still at least one matching
|
|
possibility. The portion of the string that was inspected when the longest
|
|
partial match was found is set as the first matching string in both cases.
|
|
There is a more detailed discussion of partial and multi-segment matching, with
|
|
examples, in the
|
|
<a href="pcrepartial.html"><b>pcrepartial</b></a>
|
|
documentation.
|
|
<pre>
|
|
PCRE_DFA_SHORTEST
|
|
</pre>
|
|
Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to stop as
|
|
soon as it has found one match. Because of the way the alternative algorithm
|
|
works, this is necessarily the shortest possible match at the first possible
|
|
matching point in the subject string.
|
|
<pre>
|
|
PCRE_DFA_RESTART
|
|
</pre>
|
|
When <b>pcre_dfa_exec()</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 PCRE_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="pcrepartial.html"><b>pcrepartial</b></a>
|
|
documentation.
|
|
</P>
|
|
<br><b>
|
|
Successful returns from <b>pcre_dfa_exec()</b>
|
|
</b><br>
|
|
<P>
|
|
When <b>pcre_dfa_exec()</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 substrings themselves are returned in
|
|
<i>ovector</i>. Each string uses two elements; the first is the offset to the
|
|
start, and the second is the offset to the end. In fact, all the strings have
|
|
the same start offset. (Space could have been saved by giving this only once,
|
|
but it was decided to retain some compatibility with the way <b>pcre_exec()</b>
|
|
returns data, even though the meaning of the strings is different.)
|
|
</P>
|
|
<P>
|
|
The strings are returned in reverse order of length; that is, the longest
|
|
matching string is given first. If there were too many matches to fit into
|
|
<i>ovector</i>, the yield of the function is zero, and the vector is filled with
|
|
the longest matches. Unlike <b>pcre_exec()</b>, <b>pcre_dfa_exec()</b> can use
|
|
the entire <i>ovector</i> for returning matched strings.
|
|
</P>
|
|
<P>
|
|
NOTE: PCRE'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
|
|
even considering the possibility of 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 PCRE_NO_AUTO_POSSESS option when compiling.
|
|
</P>
|
|
<br><b>
|
|
Error returns from <b>pcre_dfa_exec()</b>
|
|
</b><br>
|
|
<P>
|
|
The <b>pcre_dfa_exec()</b> function returns a negative number when it fails.
|
|
Many of the errors are the same as for <b>pcre_exec()</b>, and these are
|
|
described
|
|
<a href="#errorlist">above.</a>
|
|
There are in addition the following errors that are specific to
|
|
<b>pcre_dfa_exec()</b>:
|
|
<pre>
|
|
PCRE_ERROR_DFA_UITEM (-16)
|
|
</pre>
|
|
This return is given if <b>pcre_dfa_exec()</b> encounters an item in the pattern
|
|
that it does not support, for instance, the use of \C or a back reference.
|
|
<pre>
|
|
PCRE_ERROR_DFA_UCOND (-17)
|
|
</pre>
|
|
This return is given if <b>pcre_dfa_exec()</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>
|
|
PCRE_ERROR_DFA_UMLIMIT (-18)
|
|
</pre>
|
|
This return is given if <b>pcre_dfa_exec()</b> is called with an <i>extra</i>
|
|
block that contains a setting of the <i>match_limit</i> or
|
|
<i>match_limit_recursion</i> fields. This is not supported (these fields are
|
|
meaningless for DFA matching).
|
|
<pre>
|
|
PCRE_ERROR_DFA_WSSIZE (-19)
|
|
</pre>
|
|
This return is given if <b>pcre_dfa_exec()</b> runs out of space in the
|
|
<i>workspace</i> vector.
|
|
<pre>
|
|
PCRE_ERROR_DFA_RECURSE (-20)
|
|
</pre>
|
|
When a recursive subpattern is processed, the matching function calls itself
|
|
recursively, using private vectors for <i>ovector</i> and <i>workspace</i>. This
|
|
error is given if the output vector is not large enough. This should be
|
|
extremely rare, as a vector of size 1000 is used.
|
|
<pre>
|
|
PCRE_ERROR_DFA_BADRESTART (-30)
|
|
</pre>
|
|
When <b>pcre_dfa_exec()</b> is called with the <b>PCRE_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="SEC24" href="#TOC1">SEE ALSO</a><br>
|
|
<P>
|
|
<b>pcre16</b>(3), <b>pcre32</b>(3), <b>pcrebuild</b>(3), <b>pcrecallout</b>(3),
|
|
<b>pcrecpp(3)</b>(3), <b>pcrematching</b>(3), <b>pcrepartial</b>(3),
|
|
<b>pcreposix</b>(3), <b>pcreprecompile</b>(3), <b>pcresample</b>(3),
|
|
<b>pcrestack</b>(3).
|
|
</P>
|
|
<br><a name="SEC25" href="#TOC1">AUTHOR</a><br>
|
|
<P>
|
|
Philip Hazel
|
|
<br>
|
|
University Computing Service
|
|
<br>
|
|
Cambridge CB2 3QH, England.
|
|
<br>
|
|
</P>
|
|
<br><a name="SEC26" href="#TOC1">REVISION</a><br>
|
|
<P>
|
|
Last updated: 18 December 2015
|
|
<br>
|
|
Copyright © 1997-2015 University of Cambridge.
|
|
<br>
|
|
<p>
|
|
Return to the <a href="index.html">PCRE index page</a>.
|
|
</p>
|