mirror of
https://github.com/MariaDB/server.git
synced 2025-07-29 05:21:33 +03:00
Upgrading the bundled PCRE to 8.34
This commit is contained in:
Alexander Barkov
@ -46,125 +46,125 @@ man page, in case the conversion went wrong.
|
||||
<br><a name="SEC1" href="#TOC1">PCRE NATIVE API BASIC FUNCTIONS</a><br>
|
||||
<P>
|
||||
<b>pcre *pcre_compile(const char *<i>pattern</i>, int <i>options</i>,</b>
|
||||
<b>const char **<i>errptr</i>, int *<i>erroffset</i>,</b>
|
||||
<b>const unsigned char *<i>tableptr</i>);</b>
|
||||
</P>
|
||||
<P>
|
||||
<b> const char **<i>errptr</i>, int *<i>erroffset</i>,</b>
|
||||
<b> const unsigned char *<i>tableptr</i>);</b>
|
||||
<br>
|
||||
<br>
|
||||
<b>pcre *pcre_compile2(const char *<i>pattern</i>, int <i>options</i>,</b>
|
||||
<b>int *<i>errorcodeptr</i>,</b>
|
||||
<b>const char **<i>errptr</i>, int *<i>erroffset</i>,</b>
|
||||
<b>const unsigned char *<i>tableptr</i>);</b>
|
||||
</P>
|
||||
<P>
|
||||
<b> int *<i>errorcodeptr</i>,</b>
|
||||
<b> const char **<i>errptr</i>, int *<i>erroffset</i>,</b>
|
||||
<b> const unsigned char *<i>tableptr</i>);</b>
|
||||
<br>
|
||||
<br>
|
||||
<b>pcre_extra *pcre_study(const pcre *<i>code</i>, int <i>options</i>,</b>
|
||||
<b>const char **<i>errptr</i>);</b>
|
||||
</P>
|
||||
<P>
|
||||
<b> const char **<i>errptr</i>);</b>
|
||||
<br>
|
||||
<br>
|
||||
<b>void pcre_free_study(pcre_extra *<i>extra</i>);</b>
|
||||
</P>
|
||||
<P>
|
||||
<br>
|
||||
<br>
|
||||
<b>int pcre_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b>
|
||||
<b>const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b>
|
||||
<b>int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>);</b>
|
||||
</P>
|
||||
<P>
|
||||
<b> const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b>
|
||||
<b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>);</b>
|
||||
<br>
|
||||
<br>
|
||||
<b>int pcre_dfa_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b>
|
||||
<b>const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b>
|
||||
<b>int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b>
|
||||
<b>int *<i>workspace</i>, int <i>wscount</i>);</b>
|
||||
<b> const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b>
|
||||
<b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b>
|
||||
<b> int *<i>workspace</i>, int <i>wscount</i>);</b>
|
||||
</P>
|
||||
<br><a name="SEC2" href="#TOC1">PCRE NATIVE API STRING EXTRACTION FUNCTIONS</a><br>
|
||||
<P>
|
||||
<b>int pcre_copy_named_substring(const pcre *<i>code</i>,</b>
|
||||
<b>const char *<i>subject</i>, int *<i>ovector</i>,</b>
|
||||
<b>int <i>stringcount</i>, const char *<i>stringname</i>,</b>
|
||||
<b>char *<i>buffer</i>, int <i>buffersize</i>);</b>
|
||||
</P>
|
||||
<P>
|
||||
<b> const char *<i>subject</i>, int *<i>ovector</i>,</b>
|
||||
<b> int <i>stringcount</i>, const char *<i>stringname</i>,</b>
|
||||
<b> char *<i>buffer</i>, int <i>buffersize</i>);</b>
|
||||
<br>
|
||||
<br>
|
||||
<b>int pcre_copy_substring(const char *<i>subject</i>, int *<i>ovector</i>,</b>
|
||||
<b>int <i>stringcount</i>, int <i>stringnumber</i>, char *<i>buffer</i>,</b>
|
||||
<b>int <i>buffersize</i>);</b>
|
||||
</P>
|
||||
<P>
|
||||
<b> int <i>stringcount</i>, int <i>stringnumber</i>, char *<i>buffer</i>,</b>
|
||||
<b> int <i>buffersize</i>);</b>
|
||||
<br>
|
||||
<br>
|
||||
<b>int pcre_get_named_substring(const pcre *<i>code</i>,</b>
|
||||
<b>const char *<i>subject</i>, int *<i>ovector</i>,</b>
|
||||
<b>int <i>stringcount</i>, const char *<i>stringname</i>,</b>
|
||||
<b>const char **<i>stringptr</i>);</b>
|
||||
</P>
|
||||
<P>
|
||||
<b> const char *<i>subject</i>, int *<i>ovector</i>,</b>
|
||||
<b> int <i>stringcount</i>, const char *<i>stringname</i>,</b>
|
||||
<b> const char **<i>stringptr</i>);</b>
|
||||
<br>
|
||||
<br>
|
||||
<b>int pcre_get_stringnumber(const pcre *<i>code</i>,</b>
|
||||
<b>const char *<i>name</i>);</b>
|
||||
</P>
|
||||
<P>
|
||||
<b> const char *<i>name</i>);</b>
|
||||
<br>
|
||||
<br>
|
||||
<b>int pcre_get_stringtable_entries(const pcre *<i>code</i>,</b>
|
||||
<b>const char *<i>name</i>, char **<i>first</i>, char **<i>last</i>);</b>
|
||||
</P>
|
||||
<P>
|
||||
<b> const char *<i>name</i>, char **<i>first</i>, char **<i>last</i>);</b>
|
||||
<br>
|
||||
<br>
|
||||
<b>int pcre_get_substring(const char *<i>subject</i>, int *<i>ovector</i>,</b>
|
||||
<b>int <i>stringcount</i>, int <i>stringnumber</i>,</b>
|
||||
<b>const char **<i>stringptr</i>);</b>
|
||||
</P>
|
||||
<P>
|
||||
<b> int <i>stringcount</i>, int <i>stringnumber</i>,</b>
|
||||
<b> const char **<i>stringptr</i>);</b>
|
||||
<br>
|
||||
<br>
|
||||
<b>int pcre_get_substring_list(const char *<i>subject</i>,</b>
|
||||
<b>int *<i>ovector</i>, int <i>stringcount</i>, const char ***<i>listptr</i>);</b>
|
||||
</P>
|
||||
<P>
|
||||
<b> int *<i>ovector</i>, int <i>stringcount</i>, const char ***<i>listptr</i>);</b>
|
||||
<br>
|
||||
<br>
|
||||
<b>void pcre_free_substring(const char *<i>stringptr</i>);</b>
|
||||
</P>
|
||||
<P>
|
||||
<br>
|
||||
<br>
|
||||
<b>void pcre_free_substring_list(const char **<i>stringptr</i>);</b>
|
||||
</P>
|
||||
<br><a name="SEC3" href="#TOC1">PCRE NATIVE API AUXILIARY FUNCTIONS</a><br>
|
||||
<P>
|
||||
<b>int pcre_jit_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b>
|
||||
<b>const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b>
|
||||
<b>int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b>
|
||||
<b>pcre_jit_stack *<i>jstack</i>);</b>
|
||||
</P>
|
||||
<P>
|
||||
<b> const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b>
|
||||
<b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b>
|
||||
<b> pcre_jit_stack *<i>jstack</i>);</b>
|
||||
<br>
|
||||
<br>
|
||||
<b>pcre_jit_stack *pcre_jit_stack_alloc(int <i>startsize</i>, int <i>maxsize</i>);</b>
|
||||
</P>
|
||||
<P>
|
||||
<br>
|
||||
<br>
|
||||
<b>void pcre_jit_stack_free(pcre_jit_stack *<i>stack</i>);</b>
|
||||
</P>
|
||||
<P>
|
||||
<br>
|
||||
<br>
|
||||
<b>void pcre_assign_jit_stack(pcre_extra *<i>extra</i>,</b>
|
||||
<b>pcre_jit_callback <i>callback</i>, void *<i>data</i>);</b>
|
||||
</P>
|
||||
<P>
|
||||
<b> pcre_jit_callback <i>callback</i>, void *<i>data</i>);</b>
|
||||
<br>
|
||||
<br>
|
||||
<b>const unsigned char *pcre_maketables(void);</b>
|
||||
</P>
|
||||
<P>
|
||||
<br>
|
||||
<br>
|
||||
<b>int pcre_fullinfo(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b>
|
||||
<b>int <i>what</i>, void *<i>where</i>);</b>
|
||||
</P>
|
||||
<P>
|
||||
<b> int <i>what</i>, void *<i>where</i>);</b>
|
||||
<br>
|
||||
<br>
|
||||
<b>int pcre_refcount(pcre *<i>code</i>, int <i>adjust</i>);</b>
|
||||
</P>
|
||||
<P>
|
||||
<br>
|
||||
<br>
|
||||
<b>int pcre_config(int <i>what</i>, void *<i>where</i>);</b>
|
||||
</P>
|
||||
<P>
|
||||
<br>
|
||||
<br>
|
||||
<b>const char *pcre_version(void);</b>
|
||||
</P>
|
||||
<P>
|
||||
<br>
|
||||
<br>
|
||||
<b>int pcre_pattern_to_host_byte_order(pcre *<i>code</i>,</b>
|
||||
<b>pcre_extra *<i>extra</i>, const unsigned char *<i>tables</i>);</b>
|
||||
<b> pcre_extra *<i>extra</i>, const unsigned char *<i>tables</i>);</b>
|
||||
</P>
|
||||
<br><a name="SEC4" href="#TOC1">PCRE NATIVE API INDIRECTED FUNCTIONS</a><br>
|
||||
<P>
|
||||
<b>void *(*pcre_malloc)(size_t);</b>
|
||||
</P>
|
||||
<P>
|
||||
<br>
|
||||
<br>
|
||||
<b>void (*pcre_free)(void *);</b>
|
||||
</P>
|
||||
<P>
|
||||
<br>
|
||||
<br>
|
||||
<b>void *(*pcre_stack_malloc)(size_t);</b>
|
||||
</P>
|
||||
<P>
|
||||
<br>
|
||||
<br>
|
||||
<b>void (*pcre_stack_free)(void *);</b>
|
||||
</P>
|
||||
<P>
|
||||
<br>
|
||||
<br>
|
||||
<b>int (*pcre_callout)(pcre_callout_block *);</b>
|
||||
</P>
|
||||
<br><a name="SEC5" href="#TOC1">PCRE 8-BIT, 16-BIT, AND 32-BIT LIBRARIES</a><br>
|
||||
@ -483,6 +483,13 @@ interface uses <b>malloc()</b> for output vectors. Further details are given in
|
||||
the
|
||||
<a href="pcreposix.html"><b>pcreposix</b></a>
|
||||
documentation.
|
||||
<pre>
|
||||
PCRE_CONFIG_PARENS_LIMIT
|
||||
</pre>
|
||||
The output is a long integer that gives the maximum depth of nesting of
|
||||
parentheses (of any kind) in a pattern. This limit is imposed to cap the amount
|
||||
of system stack used when a pattern is compiled. It is specified when PCRE is
|
||||
built; the default is 250.
|
||||
<pre>
|
||||
PCRE_CONFIG_MATCH_LIMIT
|
||||
</pre>
|
||||
@ -509,12 +516,14 @@ avoiding the use of the stack.
|
||||
<br><a name="SEC11" href="#TOC1">COMPILING A PATTERN</a><br>
|
||||
<P>
|
||||
<b>pcre *pcre_compile(const char *<i>pattern</i>, int <i>options</i>,</b>
|
||||
<b>const char **<i>errptr</i>, int *<i>erroffset</i>,</b>
|
||||
<b>const unsigned char *<i>tableptr</i>);</b>
|
||||
<b> const char **<i>errptr</i>, int *<i>erroffset</i>,</b>
|
||||
<b> const unsigned char *<i>tableptr</i>);</b>
|
||||
<br>
|
||||
<br>
|
||||
<b>pcre *pcre_compile2(const char *<i>pattern</i>, int <i>options</i>,</b>
|
||||
<b>int *<i>errorcodeptr</i>,</b>
|
||||
<b>const char **<i>errptr</i>, int *<i>erroffset</i>,</b>
|
||||
<b>const unsigned char *<i>tableptr</i>);</b>
|
||||
<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
|
||||
@ -580,8 +589,9 @@ 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.
|
||||
pattern, and used again by <b>pcre_exec()</b> and <b>pcre_dfa_exec()</b> when the
|
||||
pattern is matched. For more discussion, see the section on locale support
|
||||
below.
|
||||
</P>
|
||||
<P>
|
||||
This code fragment shows a typical straightforward call to <b>pcre_compile()</b>:
|
||||
@ -666,12 +676,24 @@ documentation.
|
||||
<pre>
|
||||
PCRE_EXTENDED
|
||||
</pre>
|
||||
If this bit is set, white space data characters in the pattern are totally
|
||||
ignored except when escaped or inside a character class. White space 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.
|
||||
If this bit is set, most white space characters in the pattern are totally
|
||||
ignored except when escaped or inside a character class. However, white space
|
||||
is not allowed within sequences such as (?> that introduce various
|
||||
parenthesized subpatterns, nor within a numerical quantifier such as {1,3}.
|
||||
However, ignorable white space is permitted between an item and a following
|
||||
quantifier and between a quantifier and a following + that indicates
|
||||
possessiveness.
|
||||
</P>
|
||||
<P>
|
||||
White space did not used to include the VT character (code 11), because Perl
|
||||
did not treat this character as white space. However, Perl changed at release
|
||||
5.18, so PCRE followed at release 8.34, and VT is now treated as white space.
|
||||
</P>
|
||||
<P>
|
||||
PCRE_EXTENDED also causes characters between an unescaped # outside a character
|
||||
class and the next newline, inclusive, to be ignored. PCRE_EXTENDED is
|
||||
equivalent to Perl's /x option, and it can be changed within a pattern by a
|
||||
(?x) option setting.
|
||||
</P>
|
||||
<P>
|
||||
Which characters are interpreted as newlines is controlled by the options
|
||||
@ -824,6 +846,15 @@ the pattern. Any opening parenthesis that is not followed by ? behaves as if it
|
||||
were followed by ?: but named parentheses can still be used for capturing (and
|
||||
they acquire numbers in the usual way). There is no equivalent of this option
|
||||
in Perl.
|
||||
<pre>
|
||||
PCRE_NO_AUTO_POSSESS
|
||||
</pre>
|
||||
If this option is set, it disables "auto-possessification". This is an
|
||||
optimization that, for example, turns a+b into a++b in order to avoid
|
||||
backtracks into a+ that can never be successful. However, if callouts are in
|
||||
use, auto-possessification means that some of them are never taken. You can set
|
||||
this option if you want the matching functions to do a full unoptimized search
|
||||
and run all the callouts, but it is mainly provided for testing purposes.
|
||||
<pre>
|
||||
PCRE_NO_START_OPTIMIZE
|
||||
</pre>
|
||||
@ -875,10 +906,10 @@ page. If an invalid UTF-8 sequence is found, <b>pcre_compile()</b> returns an
|
||||
error. If you already know that your pattern is valid, and you want to skip
|
||||
this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK option.
|
||||
When it is set, the effect of passing an invalid UTF-8 string as a pattern is
|
||||
undefined. It may cause your program to crash. Note that this option can also
|
||||
be passed to <b>pcre_exec()</b> and <b>pcre_dfa_exec()</b>, to suppress the
|
||||
validity checking of subject strings only. If the same string is being matched
|
||||
many times, the option can be safely set for the second and subsequent
|
||||
undefined. It may cause your program to crash or loop. Note that this option
|
||||
can also be passed to <b>pcre_exec()</b> and <b>pcre_dfa_exec()</b>, to suppress
|
||||
the validity checking of subject strings only. If the same string is being
|
||||
matched many times, the option can be safely set for the second and subsequent
|
||||
matchings to improve performance.
|
||||
</P>
|
||||
<br><a name="SEC12" href="#TOC1">COMPILATION ERROR CODES</a><br>
|
||||
@ -923,7 +954,7 @@ have fallen out of use. To avoid confusion, they have not been re-used.
|
||||
31 POSIX collating elements are not supported
|
||||
32 this version of PCRE is compiled without UTF support
|
||||
33 [this code is not in use]
|
||||
34 character value in \x{...} sequence is too large
|
||||
34 character value in \x{} or \o{} is too large
|
||||
35 invalid condition (?(0)
|
||||
36 \C not allowed in lookbehind assertion
|
||||
37 PCRE does not support \L, \l, \N{name}, \U, or \u
|
||||
@ -971,14 +1002,20 @@ have fallen out of use. To avoid confusion, they have not been re-used.
|
||||
75 name is too long in (*MARK), (*PRUNE), (*SKIP), or (*THEN)
|
||||
76 character value in \u.... sequence is too large
|
||||
77 invalid UTF-32 string (specifically UTF-32)
|
||||
78 setting UTF is disabled by the application
|
||||
79 non-hex character in \x{} (closing brace missing?)
|
||||
80 non-octal character in \o{} (closing brace missing?)
|
||||
81 missing opening brace after \o
|
||||
82 parentheses are too deeply nested
|
||||
83 invalid range in character class
|
||||
</pre>
|
||||
The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may
|
||||
be used if the limits were changed when PCRE was built.
|
||||
<a name="studyingapattern"></a></P>
|
||||
<br><a name="SEC13" href="#TOC1">STUDYING A PATTERN</a><br>
|
||||
<P>
|
||||
<b>pcre_extra *pcre_study(const pcre *<i>code</i>, int <i>options</i></b>
|
||||
<b>const char **<i>errptr</i>);</b>
|
||||
<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
|
||||
@ -1101,15 +1138,18 @@ There is a longer discussion of PCRE_NO_START_OPTIMIZE
|
||||
<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. By default, higher-valued codes never match escapes
|
||||
such as \w or \d, but they can be tested with \p if PCRE is built with
|
||||
Unicode character property support. Alternatively, the PCRE_UCP option can be
|
||||
set at compile time; this causes \w and friends to use Unicode property
|
||||
support instead of built-in tables. 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.
|
||||
code point. When running in UTF-8 mode, or in the 16- or 32-bit libraries, this
|
||||
applies only to characters with code points less than 256. By default,
|
||||
higher-valued code points never match escapes such as \w or \d. However, if
|
||||
PCRE is built with Unicode property support, all characters can be tested with
|
||||
\p and \P, or, alternatively, the PCRE_UCP option can be set when a pattern
|
||||
is compiled; this causes \w and friends to use Unicode property support
|
||||
instead of the built-in tables.
|
||||
</P>
|
||||
<P>
|
||||
The use of locales with Unicode is discouraged. If you are handling characters
|
||||
with code points greater than 128, you should either use Unicode support, or
|
||||
use locales, but not try to mix the two.
|
||||
</P>
|
||||
<P>
|
||||
PCRE contains an internal set of tables that are used when the final argument
|
||||
@ -1127,10 +1167,10 @@ for this locale support is expected to die away.
|
||||
<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:
|
||||
to <b>pcre_compile()</b> as often as necessary. For example, to build and use
|
||||
tables that are appropriate for the French locale (where accented characters
|
||||
with values greater than 128 are treated as letters), the following code could
|
||||
be used:
|
||||
<pre>
|
||||
setlocale(LC_CTYPE, "fr_FR");
|
||||
tables = pcre_maketables();
|
||||
@ -1148,21 +1188,25 @@ needed.
|
||||
<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
|
||||
and also by <b>pcre_exec()</b> and <b>pcre_dfa_exec()</b>. Thus, for any single
|
||||
pattern, compilation, studying and matching all happen in the same locale, but
|
||||
different patterns can be compiled in different locales.
|
||||
different patterns can be processed in different locales.
|
||||
</P>
|
||||
<P>
|
||||
It is possible to pass a table pointer or NULL (indicating the use of the
|
||||
internal tables) to <b>pcre_exec()</b>. 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.
|
||||
internal tables) to <b>pcre_exec()</b> or <b>pcre_dfa_exec()</b> (see the
|
||||
discussion below in the section on matching a pattern). This facility is
|
||||
provided for use with pre-compiled patterns that have been saved and reloaded.
|
||||
Character tables are not saved with patterns, so if a non-standard table was
|
||||
used at compile time, it must be provided again when the reloaded pattern is
|
||||
matched. Attempting to use this facility to match a pattern in a different
|
||||
locale from the one in which it was compiled is likely to lead to anomalous
|
||||
(usually incorrect) results.
|
||||
<a name="infoaboutpattern"></a></P>
|
||||
<br><a name="SEC15" href="#TOC1">INFORMATION ABOUT A PATTERN</a><br>
|
||||
<P>
|
||||
<b>int pcre_fullinfo(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b>
|
||||
<b>int <i>what</i>, void *<i>where</i>);</b>
|
||||
<b> int <i>what</i>, void *<i>where</i>);</b>
|
||||
</P>
|
||||
<P>
|
||||
The <b>pcre_fullinfo()</b> function returns information about a compiled
|
||||
@ -1303,9 +1347,14 @@ is -1.
|
||||
</P>
|
||||
<P>
|
||||
Since for the 32-bit library using the non-UTF-32 mode, this function is unable
|
||||
to return the full 32-bit range of the character, this value is deprecated;
|
||||
to return the full 32-bit range of characters, this value is deprecated;
|
||||
instead the PCRE_INFO_REQUIREDCHARFLAGS and PCRE_INFO_REQUIREDCHAR values should
|
||||
be used.
|
||||
<pre>
|
||||
PCRE_INFO_MATCH_EMPTY
|
||||
</pre>
|
||||
Return 1 if the pattern can match an empty string, otherwise 0. The fourth
|
||||
argument should point to an <b>int</b> variable.
|
||||
<pre>
|
||||
PCRE_INFO_MATCHLIMIT
|
||||
</pre>
|
||||
@ -1364,16 +1413,18 @@ contains the parenthesis number. The rest of the entry is the corresponding
|
||||
name, zero terminated.
|
||||
</P>
|
||||
<P>
|
||||
The names are in alphabetical order. Duplicate names may appear if (?| is used
|
||||
to create multiple groups with the same number, as described in the
|
||||
The names are in alphabetical order. If (?| is used to create multiple groups
|
||||
with the same number, as described in the
|
||||
<a href="pcrepattern.html#dupsubpatternnumber">section on duplicate subpattern numbers</a>
|
||||
in the
|
||||
<a href="pcrepattern.html"><b>pcrepattern</b></a>
|
||||
page. Duplicate names for subpatterns with different numbers are permitted only
|
||||
if PCRE_DUPNAMES is set. In all cases of duplicate names, they appear in the
|
||||
table in the order in which they were found in the pattern. In the absence of
|
||||
(?| this is the order of increasing number; when (?| is used this is not
|
||||
necessarily the case because later subpatterns may have lower numbers.
|
||||
page, the groups may be given the same name, but there is only one entry in the
|
||||
table. Different names for groups of the same number are not permitted.
|
||||
Duplicate names for subpatterns with different numbers are permitted,
|
||||
but only if PCRE_DUPNAMES is set. They appear in the table in the order in
|
||||
which they were found in the pattern. In the absence of (?| this is the order
|
||||
of increasing number; when (?| is used this is not necessarily the case because
|
||||
later subpatterns may have lower numbers.
|
||||
</P>
|
||||
<P>
|
||||
As a simple example of the name/number table, consider the following pattern
|
||||
@ -1487,30 +1538,14 @@ returned. For anchored patterns, 0 is returned.
|
||||
<pre>
|
||||
PCRE_INFO_FIRSTCHARACTER
|
||||
</pre>
|
||||
Return the fixed first character value, if PCRE_INFO_FIRSTCHARACTERFLAGS
|
||||
returned 1; otherwise returns 0. The fourth argument should point to an
|
||||
<b>uint_t</b> variable.
|
||||
Return the fixed first character value in the situation where
|
||||
PCRE_INFO_FIRSTCHARACTERFLAGS returns 1; otherwise return 0. The fourth
|
||||
argument should point to an <b>uint_t</b> variable.
|
||||
</P>
|
||||
<P>
|
||||
In the 8-bit library, the value is always less than 256. In the 16-bit library
|
||||
the value can be up to 0xffff. In the 32-bit library in UTF-32 mode the value
|
||||
can be up to 0x10ffff, and up to 0xffffffff when not using UTF-32 mode.
|
||||
</P>
|
||||
<P>
|
||||
If there is no fixed first value, and if either
|
||||
<br>
|
||||
<br>
|
||||
(a) the pattern was compiled with the PCRE_MULTILINE option, and every branch
|
||||
starts with "^", or
|
||||
<br>
|
||||
<br>
|
||||
(b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set
|
||||
(if it were set, the pattern would be anchored),
|
||||
<br>
|
||||
<br>
|
||||
-1 is returned, indicating that the pattern matches only at the start of a
|
||||
subject string or after any newline within the string. Otherwise -2 is
|
||||
returned. For anchored patterns, -2 is returned.
|
||||
<pre>
|
||||
PCRE_INFO_REQUIREDCHARFLAGS
|
||||
</pre>
|
||||
@ -1559,8 +1594,8 @@ is different. (This seems a highly unlikely scenario.)
|
||||
<br><a name="SEC17" href="#TOC1">MATCHING A PATTERN: THE TRADITIONAL FUNCTION</a><br>
|
||||
<P>
|
||||
<b>int pcre_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b>
|
||||
<b>const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b>
|
||||
<b>int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>);</b>
|
||||
<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
|
||||
@ -1723,17 +1758,22 @@ and is described in the
|
||||
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
|
||||
The <i>tables</i> field is provided for use with patterns that have been
|
||||
pre-compiled using custom character tables, saved to disc or elsewhere, and
|
||||
then reloaded, because the tables that were used to compile a pattern are not
|
||||
saved with it. See the
|
||||
<a href="pcreprecompile.html"><b>pcreprecompile</b></a>
|
||||
documentation for a discussion of saving compiled patterns for later use.
|
||||
documentation for a discussion of saving compiled patterns for later use. If
|
||||
NULL is passed using this mechanism, it forces PCRE's internal tables to be
|
||||
used.
|
||||
</P>
|
||||
<P>
|
||||
<b>Warning:</b> The tables that <b>pcre_exec()</b> uses must be the same as those
|
||||
that were used when the pattern was compiled. If this is not the case, the
|
||||
behaviour of <b>pcre_exec()</b> is undefined. Therefore, when a pattern is
|
||||
compiled and matched in the same process, this field should never be set. In
|
||||
this (the most common) case, the correct table pointer is automatically passed
|
||||
with the compiled pattern from <b>pcre_compile()</b> to <b>pcre_exec()</b>.
|
||||
</P>
|
||||
<P>
|
||||
If PCRE_EXTRA_MARK is set in the <i>flags</i> field, the <i>mark</i> field must
|
||||
@ -1951,7 +1991,7 @@ all the matches in a single subject string. However, you should be sure that
|
||||
the value of <i>startoffset</i> points to the start of a character (or the end
|
||||
of the subject). When PCRE_NO_UTF8_CHECK is set, the effect of passing an
|
||||
invalid string as a subject or an invalid value of <i>startoffset</i> is
|
||||
undefined. Your program may crash.
|
||||
undefined. Your program may crash or loop.
|
||||
<pre>
|
||||
PCRE_PARTIAL_HARD
|
||||
PCRE_PARTIAL_SOFT
|
||||
@ -2413,17 +2453,17 @@ no longer in use and is never returned.
|
||||
<br><a name="SEC18" href="#TOC1">EXTRACTING CAPTURED SUBSTRINGS BY NUMBER</a><br>
|
||||
<P>
|
||||
<b>int pcre_copy_substring(const char *<i>subject</i>, int *<i>ovector</i>,</b>
|
||||
<b>int <i>stringcount</i>, int <i>stringnumber</i>, char *<i>buffer</i>,</b>
|
||||
<b>int <i>buffersize</i>);</b>
|
||||
</P>
|
||||
<P>
|
||||
<b> int <i>stringcount</i>, int <i>stringnumber</i>, char *<i>buffer</i>,</b>
|
||||
<b> int <i>buffersize</i>);</b>
|
||||
<br>
|
||||
<br>
|
||||
<b>int pcre_get_substring(const char *<i>subject</i>, int *<i>ovector</i>,</b>
|
||||
<b>int <i>stringcount</i>, int <i>stringnumber</i>,</b>
|
||||
<b>const char **<i>stringptr</i>);</b>
|
||||
</P>
|
||||
<P>
|
||||
<b> int <i>stringcount</i>, int <i>stringnumber</i>,</b>
|
||||
<b> const char **<i>stringptr</i>);</b>
|
||||
<br>
|
||||
<br>
|
||||
<b>int pcre_get_substring_list(const char *<i>subject</i>,</b>
|
||||
<b>int *<i>ovector</i>, int <i>stringcount</i>, const char ***<i>listptr</i>);</b>
|
||||
<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
|
||||
@ -2508,19 +2548,19 @@ provided.
|
||||
<br><a name="SEC19" href="#TOC1">EXTRACTING CAPTURED SUBSTRINGS BY NAME</a><br>
|
||||
<P>
|
||||
<b>int pcre_get_stringnumber(const pcre *<i>code</i>,</b>
|
||||
<b>const char *<i>name</i>);</b>
|
||||
</P>
|
||||
<P>
|
||||
<b> const char *<i>name</i>);</b>
|
||||
<br>
|
||||
<br>
|
||||
<b>int pcre_copy_named_substring(const pcre *<i>code</i>,</b>
|
||||
<b>const char *<i>subject</i>, int *<i>ovector</i>,</b>
|
||||
<b>int <i>stringcount</i>, const char *<i>stringname</i>,</b>
|
||||
<b>char *<i>buffer</i>, int <i>buffersize</i>);</b>
|
||||
</P>
|
||||
<P>
|
||||
<b> const char *<i>subject</i>, int *<i>ovector</i>,</b>
|
||||
<b> int <i>stringcount</i>, const char *<i>stringname</i>,</b>
|
||||
<b> char *<i>buffer</i>, int <i>buffersize</i>);</b>
|
||||
<br>
|
||||
<br>
|
||||
<b>int pcre_get_named_substring(const pcre *<i>code</i>,</b>
|
||||
<b>const char *<i>subject</i>, int *<i>ovector</i>,</b>
|
||||
<b>int <i>stringcount</i>, const char *<i>stringname</i>,</b>
|
||||
<b>const char **<i>stringptr</i>);</b>
|
||||
<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.
|
||||
@ -2572,7 +2612,7 @@ same number causes an error at compile time.
|
||||
<br><a name="SEC20" href="#TOC1">DUPLICATE SUBPATTERN NAMES</a><br>
|
||||
<P>
|
||||
<b>int pcre_get_stringtable_entries(const pcre *<i>code</i>,</b>
|
||||
<b>const char *<i>name</i>, char **<i>first</i>, char **<i>last</i>);</b>
|
||||
<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
|
||||
@ -2653,9 +2693,9 @@ the value returned is the size of each block that is obtained from the heap.
|
||||
<br><a name="SEC23" href="#TOC1">MATCHING A PATTERN: THE ALTERNATIVE FUNCTION</a><br>
|
||||
<P>
|
||||
<b>int pcre_dfa_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b>
|
||||
<b>const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b>
|
||||
<b>int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b>
|
||||
<b>int *<i>workspace</i>, int <i>wscount</i>);</b>
|
||||
<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
|
||||
@ -2784,6 +2824,15 @@ matching string is given first. If there were too many matches to fit into
|
||||
the longest matches. Unlike <b>pcre_exec()</b>, <b>pcre_dfa_exec()</b> can use
|
||||
the entire <i>ovector</i> for returning matched strings.
|
||||
</P>
|
||||
<P>
|
||||
NOTE: PCRE's "auto-possessification" optimization usually applies to character
|
||||
repeats at the end of a pattern (as well as internally). For example, the
|
||||
pattern "a\d+" is compiled as if it were "a\d++" because there is no point
|
||||
even considering the possibility of backtracking into the repeated digits. For
|
||||
DFA matching, this means that only one possible match is found. If you really
|
||||
do want multiple matches in such cases, either use an ungreedy repeat
|
||||
("a\d+?") or set the PCRE_NO_AUTO_POSSESS option when compiling.
|
||||
</P>
|
||||
<br><b>
|
||||
Error returns from <b>pcre_dfa_exec()</b>
|
||||
</b><br>
|
||||
@ -2850,7 +2899,7 @@ Cambridge CB2 3QH, England.
|
||||
</P>
|
||||
<br><a name="SEC26" href="#TOC1">REVISION</a><br>
|
||||
<P>
|
||||
Last updated: 12 May 2013
|
||||
Last updated: 12 November 2013
|
||||
<br>
|
||||
Copyright © 1997-2013 University of Cambridge.
|
||||
<br>
|
||||
|
||||
Reference in New Issue
Block a user