2006 lines
89 KiB
HTML
2006 lines
89 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</a>
|
|
<li><a name="TOC2" href="#SEC2">PCRE API OVERVIEW</a>
|
|
<li><a name="TOC3" href="#SEC3">NEWLINES</a>
|
|
<li><a name="TOC4" href="#SEC4">MULTITHREADING</a>
|
|
<li><a name="TOC5" href="#SEC5">SAVING PRECOMPILED PATTERNS FOR LATER USE</a>
|
|
<li><a name="TOC6" href="#SEC6">CHECKING BUILD-TIME OPTIONS</a>
|
|
<li><a name="TOC7" href="#SEC7">COMPILING A PATTERN</a>
|
|
<li><a name="TOC8" href="#SEC8">COMPILATION ERROR CODES</a>
|
|
<li><a name="TOC9" href="#SEC9">STUDYING A PATTERN</a>
|
|
<li><a name="TOC10" href="#SEC10">LOCALE SUPPORT</a>
|
|
<li><a name="TOC11" href="#SEC11">INFORMATION ABOUT A PATTERN</a>
|
|
<li><a name="TOC12" href="#SEC12">OBSOLETE INFO FUNCTION</a>
|
|
<li><a name="TOC13" href="#SEC13">REFERENCE COUNTS</a>
|
|
<li><a name="TOC14" href="#SEC14">MATCHING A PATTERN: THE TRADITIONAL FUNCTION</a>
|
|
<li><a name="TOC15" href="#SEC15">EXTRACTING CAPTURED SUBSTRINGS BY NUMBER</a>
|
|
<li><a name="TOC16" href="#SEC16">EXTRACTING CAPTURED SUBSTRINGS BY NAME</a>
|
|
<li><a name="TOC17" href="#SEC17">DUPLICATE SUBPATTERN NAMES</a>
|
|
<li><a name="TOC18" href="#SEC18">FINDING ALL POSSIBLE MATCHES</a>
|
|
<li><a name="TOC19" href="#SEC19">MATCHING A PATTERN: THE ALTERNATIVE FUNCTION</a>
|
|
<li><a name="TOC20" href="#SEC20">SEE ALSO</a>
|
|
<li><a name="TOC21" href="#SEC21">AUTHOR</a>
|
|
<li><a name="TOC22" href="#SEC22">REVISION</a>
|
|
</ul>
|
|
<br><a name="SEC1" href="#TOC1">PCRE NATIVE API</a><br>
|
|
<P>
|
|
<b>#include <pcre.h></b>
|
|
</P>
|
|
<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>
|
|
</P>
|
|
<P>
|
|
<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>
|
|
<b>pcre_extra *pcre_study(const pcre *<i>code</i>, int <i>options</i>,</b>
|
|
<b>const char **<i>errptr</i>);</b>
|
|
</P>
|
|
<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>
|
|
<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>
|
|
<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>
|
|
</P>
|
|
<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>
|
|
</P>
|
|
<P>
|
|
<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>
|
|
<b>int pcre_get_stringnumber(const pcre *<i>code</i>,</b>
|
|
<b>const char *<i>name</i>);</b>
|
|
</P>
|
|
<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>
|
|
<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>
|
|
</P>
|
|
<P>
|
|
<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>
|
|
<b>void pcre_free_substring(const char *<i>stringptr</i>);</b>
|
|
</P>
|
|
<P>
|
|
<b>void pcre_free_substring_list(const char **<i>stringptr</i>);</b>
|
|
</P>
|
|
<P>
|
|
<b>const unsigned char *pcre_maketables(void);</b>
|
|
</P>
|
|
<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>
|
|
<b>int pcre_info(const pcre *<i>code</i>, int *<i>optptr</i>, int</b>
|
|
<b>*<i>firstcharptr</i>);</b>
|
|
</P>
|
|
<P>
|
|
<b>int pcre_refcount(pcre *<i>code</i>, int <i>adjust</i>);</b>
|
|
</P>
|
|
<P>
|
|
<b>int pcre_config(int <i>what</i>, void *<i>where</i>);</b>
|
|
</P>
|
|
<P>
|
|
<b>char *pcre_version(void);</b>
|
|
</P>
|
|
<P>
|
|
<b>void *(*pcre_malloc)(size_t);</b>
|
|
</P>
|
|
<P>
|
|
<b>void (*pcre_free)(void *);</b>
|
|
</P>
|
|
<P>
|
|
<b>void *(*pcre_stack_malloc)(size_t);</b>
|
|
</P>
|
|
<P>
|
|
<b>void (*pcre_stack_free)(void *);</b>
|
|
</P>
|
|
<P>
|
|
<b>int (*pcre_callout)(pcre_callout_block *);</b>
|
|
</P>
|
|
<br><a name="SEC2" 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 that correspond to the POSIX regular expression
|
|
API. These 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 is 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 systems the 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>
|
|
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 source
|
|
distribution. The
|
|
<a href="pcresample.html"><b>pcresample</b></a>
|
|
documentation describes how to compile and run it.
|
|
</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. 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; <b>pcre_info()</b> is an obsolete version that returns only
|
|
some of the available information, but is retained for backwards compatibility.
|
|
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 are always called in a stack-like manner (last obtained,
|
|
first freed), and always for memory blocks of the same size. There is a
|
|
discussion about PCRE's stack usage in the
|
|
<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.
|
|
<a name="newlines"></a></P>
|
|
<br><a name="SEC3" 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 (formfeed,
|
|
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="SEC4" 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 function pointed to by <b>pcre_callout</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>
|
|
<br><a name="SEC5" 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. 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="SEC6" 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 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.
|
|
<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_NEWLINE
|
|
</pre>
|
|
The output is an integer whose value specifies the default character sequence
|
|
that is recognized as meaning "newline". The four values that are supported
|
|
are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, and -1 for ANY.
|
|
Though they are derived from ASCII, the same values are returned in EBCDIC
|
|
environments. The default should normally correspond to the standard sequence
|
|
for your operating system.
|
|
<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. The value is 2, 3, or 4. Larger values
|
|
allow larger regular expressions to be compiled, at the expense of slower
|
|
matching. The default value of 2 is sufficient for all but the most massive
|
|
patterns, since it allows the compiled pattern to be up to 64K in size.
|
|
<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_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="SEC7" 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>
|
|
<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.
|
|
</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 also some others) 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 initial
|
|
settings at the start of compilation and execution. The PCRE_ANCHORED and
|
|
PCRE_NEWLINE_<i>xxx</i> 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. The offset from the start of the pattern to the character
|
|
where 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.
|
|
</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>, unless another table pointer is
|
|
passed to it. 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 metacharater in the pattern matches all characters,
|
|
including those that indicate newline. Without it, a dot does not match when
|
|
the current position is at a newline. This option is equivalent to Perl's /s
|
|
option, and it can be changed within a pattern by a (?s) option setting. A
|
|
negative class such as [^a] always matches newline characters, independent of
|
|
the setting of this option.
|
|
<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, whitespace data characters in the pattern are totally
|
|
ignored except when escaped or inside a character class. Whitespace does not
|
|
include the VT character (code 11). In addition, characters between an
|
|
unescaped # outside a character class and the next newline, inclusive, are also
|
|
ignored. This is equivalent to Perl's /x option, and it can be changed within a
|
|
pattern by a (?x) option setting.
|
|
</P>
|
|
<P>
|
|
This option makes it possible to include comments inside complicated patterns.
|
|
Note, however, that this applies only to data characters. Whitespace characters
|
|
may never appear within special character sequences in a pattern, for example
|
|
within the sequence (?( which introduces a conditional subpattern.
|
|
<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 a warning for this.) There are at present no other features controlled by
|
|
this option. It can also be set by a (?X) option setting within a pattern.
|
|
<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.
|
|
<pre>
|
|
PCRE_MULTILINE
|
|
</pre>
|
|
By default, PCRE treats the subject string as consisting of a single line of
|
|
characters (even if it actually contains newlines). The "start of line"
|
|
metacharacter (^) matches only at the start of the string, while the "end of
|
|
line" metacharacter ($) matches only at the end of the string, or before a
|
|
terminating newline (unless PCRE_DOLLAR_ENDONLY is set). This is the same as
|
|
Perl.
|
|
</P>
|
|
<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_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. The Unicode newline
|
|
sequences are the three just mentioned, plus the single characters VT (vertical
|
|
tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line
|
|
separator, U+2028), and PS (paragraph separator, U+2029). The last two are
|
|
recognized only in UTF-8 mode.
|
|
</P>
|
|
<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 is specially recognized when compiling a
|
|
pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character
|
|
class is encountered. This indicates a comment that lasts until after the next
|
|
line break sequence. In other circumstances, line break sequences are treated
|
|
as literal data, except that in PCRE_EXTENDED mode, both CR and LF are treated
|
|
as whitespace characters and are therefore ignored.
|
|
</P>
|
|
<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_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 character strings. However, it is
|
|
available only when PCRE is built to include UTF-8 support. If not, the use
|
|
of this option provokes an error. Details of how this option changes the
|
|
behaviour of PCRE are given in the
|
|
<a href="pcre.html#utf8support">section on UTF-8 support</a>
|
|
in the main
|
|
<a href="pcre.html"><b>pcre</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="pcre.html#utf8strings">validity of UTF-8 strings</a>
|
|
in the main
|
|
<a href="pcre.html"><b>pcre</b></a>
|
|
page. If an invalid UTF-8 sequence of bytes 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. Note that this option
|
|
can also be passed to <b>pcre_exec()</b> and <b>pcre_dfa_exec()</b>, to suppress
|
|
the UTF-8 validity checking of subject strings.
|
|
</P>
|
|
<br><a name="SEC8" 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. 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 not compiled with PCRE_UTF8 support
|
|
33 [this code is not in use]
|
|
34 character value in \x{...} sequence is too large
|
|
35 invalid condition (?(0)
|
|
36 \C not allowed in lookbehind assertion
|
|
37 PCRE does not support \L, \l, \N, \U, or \u
|
|
38 number after (?C is > 255
|
|
39 closing ) for (?C expected
|
|
40 recursive call could loop indefinitely
|
|
41 unrecognized character after (?P
|
|
42 syntax error in subpattern name (missing terminator)
|
|
43 two named subpatterns have the same name
|
|
44 invalid UTF-8 string
|
|
45 support for \P, \p, and \X has not been compiled
|
|
46 malformed \P or \p sequence
|
|
47 unknown property name after \P or \p
|
|
48 subpattern name is too long (maximum 32 characters)
|
|
49 too many named subpatterns (maximum 10000)
|
|
50 [this code is not in use]
|
|
51 octal value is greater than \377 (not in UTF-8 mode)
|
|
52 internal error: overran compiling workspace
|
|
53 internal error: previously-checked referenced subpattern not found
|
|
54 DEFINE group contains more than one branch
|
|
55 repeating a DEFINE group is not allowed
|
|
56 inconsistent NEWLINE options
|
|
57 \g is not followed by a braced, angle-bracketed, or quoted
|
|
name/number or by a plain number
|
|
58 a numbered reference must not be zero
|
|
59 (*VERB) with an argument is not supported
|
|
60 (*VERB) not recognized
|
|
61 number is too big
|
|
62 subpattern name expected
|
|
63 digit expected after (?+
|
|
64 ] is an invalid data character in JavaScript compatibility mode
|
|
</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.
|
|
</P>
|
|
<br><a name="SEC9" 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>. 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 additional information
|
|
<b>pcre_study()</b> returns NULL. In that circumstance, if the calling program
|
|
wants to pass any of the other fields to <b>pcre_exec()</b>, it must set up its
|
|
own <b>pcre_extra</b> block.
|
|
</P>
|
|
<P>
|
|
The second argument of <b>pcre_study()</b> contains option bits. At present, no
|
|
options are defined, and this argument should always be zero.
|
|
</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>
|
|
This is a typical call to <b>pcre_study</b>():
|
|
<pre>
|
|
pcre_extra *pe;
|
|
pe = pcre_study(
|
|
re, /* result of pcre_compile() */
|
|
0, /* no options exist */
|
|
&error); /* set to NULL or points to a message */
|
|
</pre>
|
|
At present, studying a pattern is useful only for non-anchored patterns that do
|
|
not have a single fixed starting character. A bitmap of possible starting
|
|
bytes is created.
|
|
<a name="localesupport"></a></P>
|
|
<br><a name="SEC10" 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
|
|
value. When running in UTF-8 mode, this applies only to characters with codes
|
|
less than 128. Higher-valued codes never match escapes such as \w or \d, but
|
|
can be tested with \p if PCRE is built with Unicode character property
|
|
support. The use of locales with Unicode is discouraged. If you are handling
|
|
characters with codes greater than 128, you should either use UTF-8 and
|
|
Unicode, or use locales, but not try to mix the two.
|
|
</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> or <b>pcre_exec()</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 normally also by <b>pcre_exec()</b>. Thus, by default, for any single
|
|
pattern, compilation, studying and matching all happen in the same locale, but
|
|
different patterns can be compiled in different locales.
|
|
</P>
|
|
<P>
|
|
It is possible to pass a table pointer or NULL (indicating the use of the
|
|
internal tables) to <b>pcre_exec()</b>. Although not intended for this purpose,
|
|
this facility could be used to match a pattern in a different locale from the
|
|
one in which it was compiled. Passing table pointers at run time is discussed
|
|
below in the section on matching a pattern.
|
|
</P>
|
|
<br><a name="SEC11" 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 obsolete <b>pcre_info()</b> function, which is
|
|
nevertheless retained for backwards compability (and is documented below).
|
|
</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_BADOPTION the value of <i>what</i> was invalid
|
|
</pre>
|
|
The "magic number" is placed at the start of each compiled pattern as an simple
|
|
check against passing an arbitrary memory pointer. Here is a typical call of
|
|
<b>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() */
|
|
pe, /* 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
|
|
</pre>
|
|
Return information about the first byte of any matched string, for a
|
|
non-anchored pattern. The fourth argument should point to an <b>int</b>
|
|
variable. (This option used to be called PCRE_INFO_FIRSTCHAR; the old name is
|
|
still recognized for backwards compatibility.)
|
|
</P>
|
|
<P>
|
|
If there is a fixed first byte, for example, from a pattern such as
|
|
(cat|cow|coyote), its value is returned. Otherwise, if either
|
|
<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_FIRSTTABLE
|
|
</pre>
|
|
If the pattern was studied, and this resulted in the construction of a 256-bit
|
|
table indicating a fixed set of bytes for the first byte in any matching
|
|
string, a pointer to the table is returned. Otherwise NULL is returned. The
|
|
fourth argument should point to an <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_LASTLITERAL
|
|
</pre>
|
|
Return the value of the rightmost literal byte that must exist in any matched
|
|
string, other than at its start, if such a byte has been recorded. The fourth
|
|
argument should point to an <b>int</b> variable. If there is no such byte, -1 is
|
|
returned. For anchored patterns, a last literal byte is recorded only if it
|
|
follows something of variable length. For example, for the pattern
|
|
/^a\d+z\d+/ the returned value is "z", but for /^a\dz\d/ the returned value
|
|
is -1.
|
|
<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 (a pointer to <b>char</b>). The first two bytes of each entry
|
|
are the number of the capturing parenthesis, most significant byte first. The
|
|
rest of the entry is the corresponding name, zero terminated. The names are in
|
|
alphabetical order. When PCRE_DUPNAMES is set, duplicate names are in order of
|
|
their parentheses numbers. For example, consider the following pattern (assume
|
|
PCRE_EXTENDED is set, so white space - including newlines - is ignored):
|
|
<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, otherwise 0. The
|
|
fourth argument should point to an <b>int</b> variable. The
|
|
<a href="pcrepartial.html"><b>pcrepartial</b></a>
|
|
documentation lists the restrictions that apply to patterns when partial
|
|
matching is used.
|
|
<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_SIZE
|
|
</pre>
|
|
Return the size of the compiled pattern, that is, the value that was passed as
|
|
the argument to <b>pcre_malloc()</b> when PCRE was getting memory in which to
|
|
place the compiled data. The fourth argument should point to a <b>size_t</b>
|
|
variable.
|
|
<pre>
|
|
PCRE_INFO_STUDYSIZE
|
|
</pre>
|
|
Return the size of the data block pointed to by the <i>study_data</i> field in
|
|
a <b>pcre_extra</b> block. That is, it is the value that was passed to
|
|
<b>pcre_malloc()</b> when PCRE was getting memory into which to place the data
|
|
created by <b>pcre_study()</b>. The fourth argument should point to a
|
|
<b>size_t</b> variable.
|
|
</P>
|
|
<br><a name="SEC12" href="#TOC1">OBSOLETE INFO FUNCTION</a><br>
|
|
<P>
|
|
<b>int pcre_info(const pcre *<i>code</i>, int *<i>optptr</i>, int</b>
|
|
<b>*<i>firstcharptr</i>);</b>
|
|
</P>
|
|
<P>
|
|
The <b>pcre_info()</b> function is now obsolete because its interface is too
|
|
restrictive to return all the available data about a compiled pattern. New
|
|
programs should use <b>pcre_fullinfo()</b> instead. The yield of
|
|
<b>pcre_info()</b> is the number of capturing subpatterns, or one of the
|
|
following negative numbers:
|
|
<pre>
|
|
PCRE_ERROR_NULL the argument <i>code</i> was NULL
|
|
PCRE_ERROR_BADMAGIC the "magic number" was not found
|
|
</pre>
|
|
If the <i>optptr</i> argument is not NULL, a copy of the options with which the
|
|
pattern was compiled is placed in the integer it points to (see
|
|
PCRE_INFO_OPTIONS above).
|
|
</P>
|
|
<P>
|
|
If the pattern is not anchored and the <i>firstcharptr</i> argument is not NULL,
|
|
it is used to pass back information about the first character of any matched
|
|
string (see PCRE_INFO_FIRSTBYTE above).
|
|
</P>
|
|
<br><a name="SEC13" 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="SEC14" 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 has been studied, the result of the study should be passed in the
|
|
<i>extra</i> argument. This function is the main matching facility of the
|
|
library, and it operates in a Perl-like manner. For specialist use there is
|
|
also an alternative matching function, which is described
|
|
<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>;
|
|
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>;
|
|
</pre>
|
|
The <i>flags</i> field is a bitmap that specifies which of the other fields
|
|
are set. The flag bits are:
|
|
<pre>
|
|
PCRE_EXTRA_STUDY_DATA
|
|
PCRE_EXTRA_MATCH_LIMIT
|
|
PCRE_EXTRA_MATCH_LIMIT_RECURSION
|
|
PCRE_EXTRA_CALLOUT_DATA
|
|
PCRE_EXTRA_TABLES
|
|
</pre>
|
|
Other flag bits should be set to zero. The <i>study_data</i> field is set in the
|
|
<b>pcre_extra</b> block that is returned by <b>pcre_study()</b>, together with
|
|
the appropriate flag bit. You should not set this yourself, but you may add to
|
|
the block by setting the other fields and their corresponding flag bits.
|
|
</P>
|
|
<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 the use of nested unlimited repeats.
|
|
</P>
|
|
<P>
|
|
Internally, PCRE 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>
|
|
The default value for the limit can be set when PCRE is built; the default
|
|
default is 10 million, which handles all but the most extreme cases. You can
|
|
override the default by suppling <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>
|
|
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 stack that can be used, or,
|
|
when PCRE has been compiled to use memory on the heap instead of the stack, the
|
|
amount of heap memory that can be used.
|
|
</P>
|
|
<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 suppling <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>
|
|
The <i>pcre_callout</i> field is used in conjunction with the "callout" feature,
|
|
which is described in the
|
|
<a href="pcrecallout.html"><b>pcrecallout</b></a>
|
|
documentation.
|
|
</P>
|
|
<P>
|
|
The <i>tables</i> field is used to pass a character tables pointer to
|
|
<b>pcre_exec()</b>; this overrides the value that is stored with the compiled
|
|
pattern. A non-NULL value is stored with the compiled pattern only if custom
|
|
tables were supplied to <b>pcre_compile()</b> via its <i>tableptr</i> argument.
|
|
If NULL is passed to <b>pcre_exec()</b> using this mechanism, it forces PCRE's
|
|
internal tables to be used. This facility is helpful when re-using patterns
|
|
that have been saved after compiling with an external set of tables, because
|
|
the external tables might be at a different address when <b>pcre_exec()</b> is
|
|
called. See the
|
|
<a href="pcreprecompile.html"><b>pcreprecompile</b></a>
|
|
documentation for a discussion of saving compiled patterns for later use.
|
|
<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_NO_START_OPTIMIZE,
|
|
PCRE_NO_UTF8_CHECK and PCRE_PARTIAL.
|
|
<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 the empty
|
|
string at the start of the subject. With PCRE_NOTEMPTY set, this match is not
|
|
valid, so PCRE searches further into the string for occurrences of "a" or "b".
|
|
</P>
|
|
<P>
|
|
Perl has no direct equivalent of PCRE_NOTEMPTY, but it does make a special case
|
|
of a pattern match of the empty string within its <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 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 <i>pcredemo.c</i> sample program.
|
|
<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 a
|
|
match must start with a specific character, it searches the subject for that
|
|
character, and fails immediately if it cannot find it, without actually running
|
|
the main matching function. When callouts are in use, these optimizations can
|
|
cause them to be skipped. This option disables the "start-up" optimizations,
|
|
causing performance to suffer, but ensuring that the callouts do occur.
|
|
<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 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 validity of UTF-8
|
|
strings in the
|
|
<a href="pcre.html#utf8strings">section on UTF-8 support</a>
|
|
in the main
|
|
<a href="pcre.html"><b>pcre</b></a>
|
|
page. If an invalid UTF-8 sequence of bytes is found, <b>pcre_exec()</b> returns
|
|
the error PCRE_ERROR_BADUTF8. If <i>startoffset</i> contains an invalid value,
|
|
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 UTF-8 character. When
|
|
PCRE_NO_UTF8_CHECK is set, the effect of passing an invalid UTF-8 string as a
|
|
subject, or a value of <i>startoffset</i> that does not point to the start of a
|
|
UTF-8 character, is undefined. Your program may crash.
|
|
<pre>
|
|
PCRE_PARTIAL
|
|
</pre>
|
|
This option turns on the partial matching feature. If the subject string fails
|
|
to match the pattern, but at some point during the matching process the end of
|
|
the subject was reached (that is, the subject partially matches the pattern and
|
|
the failure to match occurred only because there were not enough subject
|
|
characters), <b>pcre_exec()</b> returns PCRE_ERROR_PARTIAL instead of
|
|
PCRE_ERROR_NOMATCH. When PCRE_PARTIAL is used, there are restrictions on what
|
|
may appear in the pattern. These are discussed in the
|
|
<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 bytes) in <i>length</i>, and a starting byte offset
|
|
in <i>startoffset</i>. In UTF-8 mode, the byte offset must point to the start of
|
|
a UTF-8 character. Unlike the pattern string, the subject may contain binary
|
|
zero bytes. When the starting offset is zero, the search for a match starts at
|
|
the beginning of the subject, and this is by far the most common case.
|
|
</P>
|
|
<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 "Mississipi" 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 "issipi", it does not match, because \B is always false at the
|
|
start of the subject, which is deemed to be a word boundary. However, if
|
|
<b>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>
|
|
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 byte offset of the first character in a substring, and
|
|
the second is set to the byte offset of the first character after the end of a
|
|
substring. <b>Note</b>: these values are always byte offsets, even in UTF-8
|
|
mode. 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 the substring offsets are not 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>.
|
|
</P>
|
|
<P>
|
|
The <b>pcre_info()</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. However, you can refer to the offsets for the second and third
|
|
capturing subpatterns if you wish (assuming the vector is large enough, of
|
|
course).
|
|
</P>
|
|
<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.
|
|
<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.
|
|
<pre>
|
|
PCRE_ERROR_BADUTF8_OFFSET (-11)
|
|
</pre>
|
|
The UTF-8 byte sequence that was passed as a subject was valid, but the value
|
|
of <i>startoffset</i> did not point to the beginning of a UTF-8 character.
|
|
<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>
|
|
The PCRE_PARTIAL option was used with a compiled pattern containing items that
|
|
are not supported for partial matching. See the
|
|
<a href="pcrepartial.html"><b>pcrepartial</b></a>
|
|
documentation for details of 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.
|
|
</P>
|
|
<P>
|
|
Error numbers -16 to -20 and -22 are not used by <b>pcre_exec()</b>.
|
|
</P>
|
|
<br><a name="SEC15" 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>
|
|
</P>
|
|
<P>
|
|
<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>
|
|
</P>
|
|
<P>
|
|
<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="SEC16" 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>
|
|
</P>
|
|
<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>
|
|
</P>
|
|
<P>
|
|
<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, you cannot use names to distinguish them,
|
|
because names are not included in the compiled code. The matching process uses
|
|
only numbers.
|
|
</P>
|
|
<br><a name="SEC17" 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. 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>.
|
|
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="SEC18" 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.
|
|
<a name="dfamatch"></a></P>
|
|
<br><a name="SEC19" 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, 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_NO_UTF8_CHECK, PCRE_PARTIAL,
|
|
PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last three of these are
|
|
the same as for <b>pcre_exec()</b>, so their description is not repeated here.
|
|
<pre>
|
|
PCRE_PARTIAL
|
|
</pre>
|
|
This has the same general effect as it does for <b>pcre_exec()</b>, but the
|
|
details are slightly different. When PCRE_PARTIAL is set for
|
|
<b>pcre_dfa_exec()</b>, the return code PCRE_ERROR_NOMATCH is converted into
|
|
PCRE_ERROR_PARTIAL if the end of the subject is reached, there have been no
|
|
complete matches, but there is still at least one matching possibility. The
|
|
portion of the string that provided the partial match is set as the first
|
|
matching string.
|
|
<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> is called with the PCRE_PARTIAL option, and returns
|
|
a partial match, it is possible to call it again, with additional subject
|
|
characters, and have it continue with the same match. The PCRE_DFA_RESTART
|
|
option requests this action; when it is set, the <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.
|
|
</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> field. This is not
|
|
supported (it is meaningless).
|
|
<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.
|
|
</P>
|
|
<br><a name="SEC20" href="#TOC1">SEE ALSO</a><br>
|
|
<P>
|
|
<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="SEC21" href="#TOC1">AUTHOR</a><br>
|
|
<P>
|
|
Philip Hazel
|
|
<br>
|
|
University Computing Service
|
|
<br>
|
|
Cambridge CB2 3QH, England.
|
|
<br>
|
|
</P>
|
|
<br><a name="SEC22" href="#TOC1">REVISION</a><br>
|
|
<P>
|
|
Last updated: 11 April 2009
|
|
<br>
|
|
Copyright © 1997-2009 University of Cambridge.
|
|
<br>
|
|
<p>
|
|
Return to the <a href="index.html">PCRE index page</a>.
|
|
</p>
|