383 lines
16 KiB
HTML
383 lines
16 KiB
HTML
<html>
|
|
<head>
|
|
<title>pcre32 specification</title>
|
|
</head>
|
|
<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
|
|
<h1>pcre32 man page</h1>
|
|
<p>
|
|
Return to the <a href="index.html">PCRE index page</a>.
|
|
</p>
|
|
<p>
|
|
This page is part of the PCRE HTML documentation. It was generated automatically
|
|
from the original man page. If there is any nonsense in it, please consult the
|
|
man page, in case the conversion went wrong.
|
|
<br>
|
|
<ul>
|
|
<li><a name="TOC1" href="#SEC1">PCRE 32-BIT API BASIC FUNCTIONS</a>
|
|
<li><a name="TOC2" href="#SEC2">PCRE 32-BIT API STRING EXTRACTION FUNCTIONS</a>
|
|
<li><a name="TOC3" href="#SEC3">PCRE 32-BIT API AUXILIARY FUNCTIONS</a>
|
|
<li><a name="TOC4" href="#SEC4">PCRE 32-BIT API INDIRECTED FUNCTIONS</a>
|
|
<li><a name="TOC5" href="#SEC5">PCRE 32-BIT API 32-BIT-ONLY FUNCTION</a>
|
|
<li><a name="TOC6" href="#SEC6">THE PCRE 32-BIT LIBRARY</a>
|
|
<li><a name="TOC7" href="#SEC7">THE HEADER FILE</a>
|
|
<li><a name="TOC8" href="#SEC8">THE LIBRARY NAME</a>
|
|
<li><a name="TOC9" href="#SEC9">STRING TYPES</a>
|
|
<li><a name="TOC10" href="#SEC10">STRUCTURE TYPES</a>
|
|
<li><a name="TOC11" href="#SEC11">32-BIT FUNCTIONS</a>
|
|
<li><a name="TOC12" href="#SEC12">SUBJECT STRING OFFSETS</a>
|
|
<li><a name="TOC13" href="#SEC13">NAMED SUBPATTERNS</a>
|
|
<li><a name="TOC14" href="#SEC14">OPTION NAMES</a>
|
|
<li><a name="TOC15" href="#SEC15">CHARACTER CODES</a>
|
|
<li><a name="TOC16" href="#SEC16">ERROR NAMES</a>
|
|
<li><a name="TOC17" href="#SEC17">ERROR TEXTS</a>
|
|
<li><a name="TOC18" href="#SEC18">CALLOUTS</a>
|
|
<li><a name="TOC19" href="#SEC19">TESTING</a>
|
|
<li><a name="TOC20" href="#SEC20">NOT SUPPORTED IN 32-BIT MODE</a>
|
|
<li><a name="TOC21" href="#SEC21">AUTHOR</a>
|
|
<li><a name="TOC22" href="#SEC22">REVISION</a>
|
|
</ul>
|
|
<P>
|
|
<b>#include <pcre.h></b>
|
|
</P>
|
|
<br><a name="SEC1" href="#TOC1">PCRE 32-BIT API BASIC FUNCTIONS</a><br>
|
|
<P>
|
|
<b>pcre32 *pcre32_compile(PCRE_SPTR32 <i>pattern</i>, int <i>options</i>,</b>
|
|
<b> const char **<i>errptr</i>, int *<i>erroffset</i>,</b>
|
|
<b> const unsigned char *<i>tableptr</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>pcre32 *pcre32_compile2(PCRE_SPTR32 <i>pattern</i>, int <i>options</i>,</b>
|
|
<b> int *<i>errorcodeptr</i>,</b>
|
|
<b> const unsigned char *<i>tableptr</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>pcre32_extra *pcre32_study(const pcre32 *<i>code</i>, int <i>options</i>,</b>
|
|
<b> const char **<i>errptr</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>void pcre32_free_study(pcre32_extra *<i>extra</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre32_exec(const pcre32 *<i>code</i>, const pcre32_extra *<i>extra</i>,</b>
|
|
<b> PCRE_SPTR32 <i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b>
|
|
<b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre32_dfa_exec(const pcre32 *<i>code</i>, const pcre32_extra *<i>extra</i>,</b>
|
|
<b> PCRE_SPTR32 <i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b>
|
|
<b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b>
|
|
<b> int *<i>workspace</i>, int <i>wscount</i>);</b>
|
|
</P>
|
|
<br><a name="SEC2" href="#TOC1">PCRE 32-BIT API STRING EXTRACTION FUNCTIONS</a><br>
|
|
<P>
|
|
<b>int pcre32_copy_named_substring(const pcre32 *<i>code</i>,</b>
|
|
<b> PCRE_SPTR32 <i>subject</i>, int *<i>ovector</i>,</b>
|
|
<b> int <i>stringcount</i>, PCRE_SPTR32 <i>stringname</i>,</b>
|
|
<b> PCRE_UCHAR32 *<i>buffer</i>, int <i>buffersize</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre32_copy_substring(PCRE_SPTR32 <i>subject</i>, int *<i>ovector</i>,</b>
|
|
<b> int <i>stringcount</i>, int <i>stringnumber</i>, PCRE_UCHAR32 *<i>buffer</i>,</b>
|
|
<b> int <i>buffersize</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre32_get_named_substring(const pcre32 *<i>code</i>,</b>
|
|
<b> PCRE_SPTR32 <i>subject</i>, int *<i>ovector</i>,</b>
|
|
<b> int <i>stringcount</i>, PCRE_SPTR32 <i>stringname</i>,</b>
|
|
<b> PCRE_SPTR32 *<i>stringptr</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre32_get_stringnumber(const pcre32 *<i>code</i>,</b>
|
|
<b> PCRE_SPTR32 <i>name</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre32_get_stringtable_entries(const pcre32 *<i>code</i>,</b>
|
|
<b> PCRE_SPTR32 <i>name</i>, PCRE_UCHAR32 **<i>first</i>, PCRE_UCHAR32 **<i>last</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre32_get_substring(PCRE_SPTR32 <i>subject</i>, int *<i>ovector</i>,</b>
|
|
<b> int <i>stringcount</i>, int <i>stringnumber</i>,</b>
|
|
<b> PCRE_SPTR32 *<i>stringptr</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre32_get_substring_list(PCRE_SPTR32 <i>subject</i>,</b>
|
|
<b> int *<i>ovector</i>, int <i>stringcount</i>, PCRE_SPTR32 **<i>listptr</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>void pcre32_free_substring(PCRE_SPTR32 <i>stringptr</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>void pcre32_free_substring_list(PCRE_SPTR32 *<i>stringptr</i>);</b>
|
|
</P>
|
|
<br><a name="SEC3" href="#TOC1">PCRE 32-BIT API AUXILIARY FUNCTIONS</a><br>
|
|
<P>
|
|
<b>pcre32_jit_stack *pcre32_jit_stack_alloc(int <i>startsize</i>, int <i>maxsize</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>void pcre32_jit_stack_free(pcre32_jit_stack *<i>stack</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>void pcre32_assign_jit_stack(pcre32_extra *<i>extra</i>,</b>
|
|
<b> pcre32_jit_callback <i>callback</i>, void *<i>data</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>const unsigned char *pcre32_maketables(void);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre32_fullinfo(const pcre32 *<i>code</i>, const pcre32_extra *<i>extra</i>,</b>
|
|
<b> int <i>what</i>, void *<i>where</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre32_refcount(pcre32 *<i>code</i>, int <i>adjust</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre32_config(int <i>what</i>, void *<i>where</i>);</b>
|
|
<br>
|
|
<br>
|
|
<b>const char *pcre32_version(void);</b>
|
|
<br>
|
|
<br>
|
|
<b>int pcre32_pattern_to_host_byte_order(pcre32 *<i>code</i>,</b>
|
|
<b> pcre32_extra *<i>extra</i>, const unsigned char *<i>tables</i>);</b>
|
|
</P>
|
|
<br><a name="SEC4" href="#TOC1">PCRE 32-BIT API INDIRECTED FUNCTIONS</a><br>
|
|
<P>
|
|
<b>void *(*pcre32_malloc)(size_t);</b>
|
|
<br>
|
|
<br>
|
|
<b>void (*pcre32_free)(void *);</b>
|
|
<br>
|
|
<br>
|
|
<b>void *(*pcre32_stack_malloc)(size_t);</b>
|
|
<br>
|
|
<br>
|
|
<b>void (*pcre32_stack_free)(void *);</b>
|
|
<br>
|
|
<br>
|
|
<b>int (*pcre32_callout)(pcre32_callout_block *);</b>
|
|
</P>
|
|
<br><a name="SEC5" href="#TOC1">PCRE 32-BIT API 32-BIT-ONLY FUNCTION</a><br>
|
|
<P>
|
|
<b>int pcre32_utf32_to_host_byte_order(PCRE_UCHAR32 *<i>output</i>,</b>
|
|
<b> PCRE_SPTR32 <i>input</i>, int <i>length</i>, int *<i>byte_order</i>,</b>
|
|
<b> int <i>keep_boms</i>);</b>
|
|
</P>
|
|
<br><a name="SEC6" href="#TOC1">THE PCRE 32-BIT LIBRARY</a><br>
|
|
<P>
|
|
Starting with release 8.32, it is possible to compile a PCRE library that
|
|
supports 32-bit character strings, including UTF-32 strings, as well as or
|
|
instead of the original 8-bit library. This work was done by Christian Persch,
|
|
based on the work done by Zoltan Herczeg for the 16-bit library. All three
|
|
libraries contain identical sets of functions, used in exactly the same way.
|
|
Only the names of the functions and the data types of their arguments and
|
|
results are different. To avoid over-complication and reduce the documentation
|
|
maintenance load, most of the PCRE documentation describes the 8-bit library,
|
|
with only occasional references to the 16-bit and 32-bit libraries. This page
|
|
describes what is different when you use the 32-bit library.
|
|
</P>
|
|
<P>
|
|
WARNING: A single application can be linked with all or any of the three
|
|
libraries, but you must take care when processing any particular pattern
|
|
to use functions from just one library. For example, if you want to study
|
|
a pattern that was compiled with <b>pcre32_compile()</b>, you must do so
|
|
with <b>pcre32_study()</b>, not <b>pcre_study()</b>, and you must free the
|
|
study data with <b>pcre32_free_study()</b>.
|
|
</P>
|
|
<br><a name="SEC7" href="#TOC1">THE HEADER FILE</a><br>
|
|
<P>
|
|
There is only one header file, <b>pcre.h</b>. It contains prototypes for all the
|
|
functions in all libraries, as well as definitions of flags, structures, error
|
|
codes, etc.
|
|
</P>
|
|
<br><a name="SEC8" href="#TOC1">THE LIBRARY NAME</a><br>
|
|
<P>
|
|
In Unix-like systems, the 32-bit library is called <b>libpcre32</b>, and can
|
|
normally be accesss by adding <b>-lpcre32</b> to the command for linking an
|
|
application that uses PCRE.
|
|
</P>
|
|
<br><a name="SEC9" href="#TOC1">STRING TYPES</a><br>
|
|
<P>
|
|
In the 8-bit library, strings are passed to PCRE library functions as vectors
|
|
of bytes with the C type "char *". In the 32-bit library, strings are passed as
|
|
vectors of unsigned 32-bit quantities. The macro PCRE_UCHAR32 specifies an
|
|
appropriate data type, and PCRE_SPTR32 is defined as "const PCRE_UCHAR32 *". In
|
|
very many environments, "unsigned int" is a 32-bit data type. When PCRE is
|
|
built, it defines PCRE_UCHAR32 as "unsigned int", but checks that it really is
|
|
a 32-bit data type. If it is not, the build fails with an error message telling
|
|
the maintainer to modify the definition appropriately.
|
|
</P>
|
|
<br><a name="SEC10" href="#TOC1">STRUCTURE TYPES</a><br>
|
|
<P>
|
|
The types of the opaque structures that are used for compiled 32-bit patterns
|
|
and JIT stacks are <b>pcre32</b> and <b>pcre32_jit_stack</b> respectively. The
|
|
type of the user-accessible structure that is returned by <b>pcre32_study()</b>
|
|
is <b>pcre32_extra</b>, and the type of the structure that is used for passing
|
|
data to a callout function is <b>pcre32_callout_block</b>. These structures
|
|
contain the same fields, with the same names, as their 8-bit counterparts. The
|
|
only difference is that pointers to character strings are 32-bit instead of
|
|
8-bit types.
|
|
</P>
|
|
<br><a name="SEC11" href="#TOC1">32-BIT FUNCTIONS</a><br>
|
|
<P>
|
|
For every function in the 8-bit library there is a corresponding function in
|
|
the 32-bit library with a name that starts with <b>pcre32_</b> instead of
|
|
<b>pcre_</b>. The prototypes are listed above. In addition, there is one extra
|
|
function, <b>pcre32_utf32_to_host_byte_order()</b>. This is a utility function
|
|
that converts a UTF-32 character string to host byte order if necessary. The
|
|
other 32-bit functions expect the strings they are passed to be in host byte
|
|
order.
|
|
</P>
|
|
<P>
|
|
The <i>input</i> and <i>output</i> arguments of
|
|
<b>pcre32_utf32_to_host_byte_order()</b> may point to the same address, that is,
|
|
conversion in place is supported. The output buffer must be at least as long as
|
|
the input.
|
|
</P>
|
|
<P>
|
|
The <i>length</i> argument specifies the number of 32-bit data units in the
|
|
input string; a negative value specifies a zero-terminated string.
|
|
</P>
|
|
<P>
|
|
If <i>byte_order</i> is NULL, it is assumed that the string starts off in host
|
|
byte order. This may be changed by byte-order marks (BOMs) anywhere in the
|
|
string (commonly as the first character).
|
|
</P>
|
|
<P>
|
|
If <i>byte_order</i> is not NULL, a non-zero value of the integer to which it
|
|
points means that the input starts off in host byte order, otherwise the
|
|
opposite order is assumed. Again, BOMs in the string can change this. The final
|
|
byte order is passed back at the end of processing.
|
|
</P>
|
|
<P>
|
|
If <i>keep_boms</i> is not zero, byte-order mark characters (0xfeff) are copied
|
|
into the output string. Otherwise they are discarded.
|
|
</P>
|
|
<P>
|
|
The result of the function is the number of 32-bit units placed into the output
|
|
buffer, including the zero terminator if the string was zero-terminated.
|
|
</P>
|
|
<br><a name="SEC12" href="#TOC1">SUBJECT STRING OFFSETS</a><br>
|
|
<P>
|
|
The lengths and starting offsets of subject strings must be specified in 32-bit
|
|
data units, and the offsets within subject strings that are returned by the
|
|
matching functions are in also 32-bit units rather than bytes.
|
|
</P>
|
|
<br><a name="SEC13" href="#TOC1">NAMED SUBPATTERNS</a><br>
|
|
<P>
|
|
The name-to-number translation table that is maintained for named subpatterns
|
|
uses 32-bit characters. The <b>pcre32_get_stringtable_entries()</b> function
|
|
returns the length of each entry in the table as the number of 32-bit data
|
|
units.
|
|
</P>
|
|
<br><a name="SEC14" href="#TOC1">OPTION NAMES</a><br>
|
|
<P>
|
|
There are two new general option names, PCRE_UTF32 and PCRE_NO_UTF32_CHECK,
|
|
which correspond to PCRE_UTF8 and PCRE_NO_UTF8_CHECK in the 8-bit library. In
|
|
fact, these new options define the same bits in the options word. There is a
|
|
discussion about the
|
|
<a href="pcreunicode.html#utf32strings">validity of UTF-32 strings</a>
|
|
in the
|
|
<a href="pcreunicode.html"><b>pcreunicode</b></a>
|
|
page.
|
|
</P>
|
|
<P>
|
|
For the <b>pcre32_config()</b> function there is an option PCRE_CONFIG_UTF32
|
|
that returns 1 if UTF-32 support is configured, otherwise 0. If this option is
|
|
given to <b>pcre_config()</b> or <b>pcre16_config()</b>, or if the
|
|
PCRE_CONFIG_UTF8 or PCRE_CONFIG_UTF16 option is given to <b>pcre32_config()</b>,
|
|
the result is the PCRE_ERROR_BADOPTION error.
|
|
</P>
|
|
<br><a name="SEC15" href="#TOC1">CHARACTER CODES</a><br>
|
|
<P>
|
|
In 32-bit mode, when PCRE_UTF32 is not set, character values are treated in the
|
|
same way as in 8-bit, non UTF-8 mode, except, of course, that they can range
|
|
from 0 to 0x7fffffff instead of 0 to 0xff. Character types for characters less
|
|
than 0xff can therefore be influenced by the locale in the same way as before.
|
|
Characters greater than 0xff have only one case, and no "type" (such as letter
|
|
or digit).
|
|
</P>
|
|
<P>
|
|
In UTF-32 mode, the character code is Unicode, in the range 0 to 0x10ffff, with
|
|
the exception of values in the range 0xd800 to 0xdfff because those are
|
|
"surrogate" values that are ill-formed in UTF-32.
|
|
</P>
|
|
<P>
|
|
A UTF-32 string can indicate its endianness by special code knows as a
|
|
byte-order mark (BOM). The PCRE functions do not handle this, expecting strings
|
|
to be in host byte order. A utility function called
|
|
<b>pcre32_utf32_to_host_byte_order()</b> is provided to help with this (see
|
|
above).
|
|
</P>
|
|
<br><a name="SEC16" href="#TOC1">ERROR NAMES</a><br>
|
|
<P>
|
|
The error PCRE_ERROR_BADUTF32 corresponds to its 8-bit counterpart.
|
|
The error PCRE_ERROR_BADMODE is given when a compiled
|
|
pattern is passed to a function that processes patterns in the other
|
|
mode, for example, if a pattern compiled with <b>pcre_compile()</b> is passed to
|
|
<b>pcre32_exec()</b>.
|
|
</P>
|
|
<P>
|
|
There are new error codes whose names begin with PCRE_UTF32_ERR for invalid
|
|
UTF-32 strings, corresponding to the PCRE_UTF8_ERR codes for UTF-8 strings that
|
|
are described in the section entitled
|
|
<a href="pcreapi.html#badutf8reasons">"Reason codes for invalid UTF-8 strings"</a>
|
|
in the main
|
|
<a href="pcreapi.html"><b>pcreapi</b></a>
|
|
page. The UTF-32 errors are:
|
|
<pre>
|
|
PCRE_UTF32_ERR1 Surrogate character (range from 0xd800 to 0xdfff)
|
|
PCRE_UTF32_ERR2 Non-character
|
|
PCRE_UTF32_ERR3 Character > 0x10ffff
|
|
</PRE>
|
|
</P>
|
|
<br><a name="SEC17" href="#TOC1">ERROR TEXTS</a><br>
|
|
<P>
|
|
If there is an error while compiling a pattern, the error text that is passed
|
|
back by <b>pcre32_compile()</b> or <b>pcre32_compile2()</b> is still an 8-bit
|
|
character string, zero-terminated.
|
|
</P>
|
|
<br><a name="SEC18" href="#TOC1">CALLOUTS</a><br>
|
|
<P>
|
|
The <i>subject</i> and <i>mark</i> fields in the callout block that is passed to
|
|
a callout function point to 32-bit vectors.
|
|
</P>
|
|
<br><a name="SEC19" href="#TOC1">TESTING</a><br>
|
|
<P>
|
|
The <b>pcretest</b> program continues to operate with 8-bit input and output
|
|
files, but it can be used for testing the 32-bit library. If it is run with the
|
|
command line option <b>-32</b>, patterns and subject strings are converted from
|
|
8-bit to 32-bit before being passed to PCRE, and the 32-bit library functions
|
|
are used instead of the 8-bit ones. Returned 32-bit strings are converted to
|
|
8-bit for output. If both the 8-bit and the 16-bit libraries were not compiled,
|
|
<b>pcretest</b> defaults to 32-bit and the <b>-32</b> option is ignored.
|
|
</P>
|
|
<P>
|
|
When PCRE is being built, the <b>RunTest</b> script that is called by "make
|
|
check" uses the <b>pcretest</b> <b>-C</b> option to discover which of the 8-bit,
|
|
16-bit and 32-bit libraries has been built, and runs the tests appropriately.
|
|
</P>
|
|
<br><a name="SEC20" href="#TOC1">NOT SUPPORTED IN 32-BIT MODE</a><br>
|
|
<P>
|
|
Not all the features of the 8-bit library are available with the 32-bit
|
|
library. The C++ and POSIX wrapper functions support only the 8-bit library,
|
|
and the <b>pcregrep</b> program is at present 8-bit only.
|
|
</P>
|
|
<br><a name="SEC21" href="#TOC1">AUTHOR</a><br>
|
|
<P>
|
|
Philip Hazel
|
|
<br>
|
|
University Computing Service
|
|
<br>
|
|
Cambridge CB2 3QH, England.
|
|
<br>
|
|
</P>
|
|
<br><a name="SEC22" href="#TOC1">REVISION</a><br>
|
|
<P>
|
|
Last updated: 12 May 2013
|
|
<br>
|
|
Copyright © 1997-2013 University of Cambridge.
|
|
<br>
|
|
<p>
|
|
Return to the <a href="index.html">PCRE index page</a>.
|
|
</p>
|