Diff for /embedaddon/pcre/doc/html/pcreapi.html between versions 1.1.1.2 and 1.1.1.5

version 1.1.1.2, 2012/02/21 23:50:25 version 1.1.1.5, 2014/06/15 19:46:05
Line 17  man page, in case the conversion went wrong. Line 17  man page, in case the conversion went wrong.
 <li><a name="TOC2" href="#SEC2">PCRE NATIVE API STRING EXTRACTION FUNCTIONS</a>  <li><a name="TOC2" href="#SEC2">PCRE NATIVE API STRING EXTRACTION FUNCTIONS</a>
 <li><a name="TOC3" href="#SEC3">PCRE NATIVE API AUXILIARY FUNCTIONS</a>  <li><a name="TOC3" href="#SEC3">PCRE NATIVE API AUXILIARY FUNCTIONS</a>
 <li><a name="TOC4" href="#SEC4">PCRE NATIVE API INDIRECTED FUNCTIONS</a>  <li><a name="TOC4" href="#SEC4">PCRE NATIVE API INDIRECTED FUNCTIONS</a>
<li><a name="TOC5" href="#SEC5">PCRE 8-BIT AND 16-BIT LIBRARIES</a><li><a name="TOC5" href="#SEC5">PCRE 8-BIT, 16-BIT, AND 32-BIT LIBRARIES</a>
 <li><a name="TOC6" href="#SEC6">PCRE API OVERVIEW</a>  <li><a name="TOC6" href="#SEC6">PCRE API OVERVIEW</a>
 <li><a name="TOC7" href="#SEC7">NEWLINES</a>  <li><a name="TOC7" href="#SEC7">NEWLINES</a>
 <li><a name="TOC8" href="#SEC8">MULTITHREADING</a>  <li><a name="TOC8" href="#SEC8">MULTITHREADING</a>
Line 46  man page, in case the conversion went wrong. Line 46  man page, in case the conversion went wrong.
 <br><a name="SEC1" href="#TOC1">PCRE NATIVE API BASIC FUNCTIONS</a><br>  <br><a name="SEC1" href="#TOC1">PCRE NATIVE API BASIC FUNCTIONS</a><br>
 <P>  <P>
 <b>pcre *pcre_compile(const char *<i>pattern</i>, int <i>options</i>,</b>  <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 char **<i>errptr</i>, int *<i>erroffset</i>,</b>
<b>const unsigned char *<i>tableptr</i>);</b><b>     const unsigned char *<i>tableptr</i>);</b>
</P><br>
<P><br>
 <b>pcre *pcre_compile2(const char *<i>pattern</i>, int <i>options</i>,</b>  <b>pcre *pcre_compile2(const char *<i>pattern</i>, int <i>options</i>,</b>
<b>int *<i>errorcodeptr</i>,</b><b>     int *<i>errorcodeptr</i>,</b>
<b>const char **<i>errptr</i>, int *<i>erroffset</i>,</b><b>     const char **<i>errptr</i>, int *<i>erroffset</i>,</b>
<b>const unsigned char *<i>tableptr</i>);</b><b>     const unsigned char *<i>tableptr</i>);</b>
</P><br>
<P><br>
 <b>pcre_extra *pcre_study(const pcre *<i>code</i>, int <i>options</i>,</b>  <b>pcre_extra *pcre_study(const pcre *<i>code</i>, int <i>options</i>,</b>
<b>const char **<i>errptr</i>);</b><b>     const char **<i>errptr</i>);</b>
</P><br>
<P><br>
 <b>void pcre_free_study(pcre_extra *<i>extra</i>);</b>  <b>void pcre_free_study(pcre_extra *<i>extra</i>);</b>
</P><br>
<P><br>
 <b>int pcre_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b>  <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>     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>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>);</b>
</P><br>
<P><br>
 <b>int pcre_dfa_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b>  <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>     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>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b>
<b>int *<i>workspace</i>, int <i>wscount</i>);</b><b>     int *<i>workspace</i>, int <i>wscount</i>);</b>
 </P>  </P>
 <br><a name="SEC2" href="#TOC1">PCRE NATIVE API STRING EXTRACTION FUNCTIONS</a><br>  <br><a name="SEC2" href="#TOC1">PCRE NATIVE API STRING EXTRACTION FUNCTIONS</a><br>
 <P>  <P>
 <b>int pcre_copy_named_substring(const pcre *<i>code</i>,</b>  <b>int pcre_copy_named_substring(const pcre *<i>code</i>,</b>
<b>const char *<i>subject</i>, int *<i>ovector</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>     int <i>stringcount</i>, const char *<i>stringname</i>,</b>
<b>char *<i>buffer</i>, int <i>buffersize</i>);</b><b>     char *<i>buffer</i>, int <i>buffersize</i>);</b>
</P><br>
<P><br>
 <b>int pcre_copy_substring(const char *<i>subject</i>, int *<i>ovector</i>,</b>  <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>stringcount</i>, int <i>stringnumber</i>, char *<i>buffer</i>,</b>
<b>int <i>buffersize</i>);</b><b>     int <i>buffersize</i>);</b>
</P><br>
<P><br>
 <b>int pcre_get_named_substring(const pcre *<i>code</i>,</b>  <b>int pcre_get_named_substring(const pcre *<i>code</i>,</b>
<b>const char *<i>subject</i>, int *<i>ovector</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>     int <i>stringcount</i>, const char *<i>stringname</i>,</b>
<b>const char **<i>stringptr</i>);</b><b>     const char **<i>stringptr</i>);</b>
</P><br>
<P><br>
 <b>int pcre_get_stringnumber(const pcre *<i>code</i>,</b>  <b>int pcre_get_stringnumber(const pcre *<i>code</i>,</b>
<b>const char *<i>name</i>);</b><b>     const char *<i>name</i>);</b>
</P><br>
<P><br>
 <b>int pcre_get_stringtable_entries(const pcre *<i>code</i>,</b>  <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><br>
<P><br>
 <b>int pcre_get_substring(const char *<i>subject</i>, int *<i>ovector</i>,</b>  <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>     int <i>stringcount</i>, int <i>stringnumber</i>,</b>
<b>const char **<i>stringptr</i>);</b><b>     const char **<i>stringptr</i>);</b>
</P><br>
<P><br>
 <b>int pcre_get_substring_list(const char *<i>subject</i>,</b>  <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><br>
<P><br>
 <b>void pcre_free_substring(const char *<i>stringptr</i>);</b>  <b>void pcre_free_substring(const char *<i>stringptr</i>);</b>
</P><br>
<P><br>
 <b>void pcre_free_substring_list(const char **<i>stringptr</i>);</b>  <b>void pcre_free_substring_list(const char **<i>stringptr</i>);</b>
 </P>  </P>
 <br><a name="SEC3" href="#TOC1">PCRE NATIVE API AUXILIARY FUNCTIONS</a><br>  <br><a name="SEC3" href="#TOC1">PCRE NATIVE API AUXILIARY FUNCTIONS</a><br>
 <P>  <P>
   <b>int pcre_jit_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b>
   <b>     const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b>
   <b>     int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b>
   <b>     pcre_jit_stack *<i>jstack</i>);</b>
   <br>
   <br>
 <b>pcre_jit_stack *pcre_jit_stack_alloc(int <i>startsize</i>, int <i>maxsize</i>);</b>  <b>pcre_jit_stack *pcre_jit_stack_alloc(int <i>startsize</i>, int <i>maxsize</i>);</b>
</P><br>
<P><br>
 <b>void pcre_jit_stack_free(pcre_jit_stack *<i>stack</i>);</b>  <b>void pcre_jit_stack_free(pcre_jit_stack *<i>stack</i>);</b>
</P><br>
<P><br>
 <b>void pcre_assign_jit_stack(pcre_extra *<i>extra</i>,</b>  <b>void pcre_assign_jit_stack(pcre_extra *<i>extra</i>,</b>
<b>pcre_jit_callback <i>callback</i>, void *<i>data</i>);</b><b>     pcre_jit_callback <i>callback</i>, void *<i>data</i>);</b>
</P><br>
<P><br>
 <b>const unsigned char *pcre_maketables(void);</b>  <b>const unsigned char *pcre_maketables(void);</b>
</P><br>
<P><br>
 <b>int pcre_fullinfo(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b>  <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><br>
<P><br>
 <b>int pcre_refcount(pcre *<i>code</i>, int <i>adjust</i>);</b>  <b>int pcre_refcount(pcre *<i>code</i>, int <i>adjust</i>);</b>
</P><br>
<P><br>
 <b>int pcre_config(int <i>what</i>, void *<i>where</i>);</b>  <b>int pcre_config(int <i>what</i>, void *<i>where</i>);</b>
</P><br>
<P><br>
 <b>const char *pcre_version(void);</b>  <b>const char *pcre_version(void);</b>
</P><br>
<P><br>
 <b>int pcre_pattern_to_host_byte_order(pcre *<i>code</i>,</b>  <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>  </P>
 <br><a name="SEC4" href="#TOC1">PCRE NATIVE API INDIRECTED FUNCTIONS</a><br>  <br><a name="SEC4" href="#TOC1">PCRE NATIVE API INDIRECTED FUNCTIONS</a><br>
 <P>  <P>
 <b>void *(*pcre_malloc)(size_t);</b>  <b>void *(*pcre_malloc)(size_t);</b>
</P><br>
<P><br>
 <b>void (*pcre_free)(void *);</b>  <b>void (*pcre_free)(void *);</b>
</P><br>
<P><br>
 <b>void *(*pcre_stack_malloc)(size_t);</b>  <b>void *(*pcre_stack_malloc)(size_t);</b>
</P><br>
<P><br>
 <b>void (*pcre_stack_free)(void *);</b>  <b>void (*pcre_stack_free)(void *);</b>
</P><br>
<P><br>
 <b>int (*pcre_callout)(pcre_callout_block *);</b>  <b>int (*pcre_callout)(pcre_callout_block *);</b>
 </P>  </P>
<br><a name="SEC5" href="#TOC1">PCRE 8-BIT AND 16-BIT LIBRARIES</a><br><br><a name="SEC5" href="#TOC1">PCRE 8-BIT, 16-BIT, AND 32-BIT LIBRARIES</a><br>
 <P>  <P>
From release 8.30, PCRE can be compiled as a library for handling 16-bitAs well as support for 8-bit character strings, PCRE also supports 16-bit
character strings as well as, or instead of, the original library that handlesstrings (from release 8.30) and 32-bit strings (from release 8.32), by means of
8-bit character strings. To avoid too much complication, this documenttwo additional libraries. They can be built as well as, or instead of, the
describes the 8-bit versions of the functions, with only occasional references8-bit library. To avoid too much complication, this document describes the
to the 16-bit library.8-bit versions of the functions, with only occasional references to the 16-bit
 and 32-bit libraries.
 </P>  </P>
 <P>  <P>
The 16-bit functions operate in the same way as their 8-bit counterparts; theyThe 16-bit and 32-bit functions operate in the same way as their 8-bit
just use different data types for their arguments and results, and their namescounterparts; they just use different data types for their arguments and
start with <b>pcre16_</b> instead of <b>pcre_</b>. For every option that has UTF8results, and their names start with <b>pcre16_</b> or <b>pcre32_</b> instead of
in its name (for example, PCRE_UTF8), there is a corresponding 16-bit name with<b>pcre_</b>. For every option that has UTF8 in its name (for example,
UTF8 replaced by UTF16. This facility is in fact just cosmetic; the 16-bitPCRE_UTF8), there are corresponding 16-bit and 32-bit names with UTF8 replaced
option names define the same bit values.by UTF16 or UTF32, respectively. This facility is in fact just cosmetic; the
 16-bit and 32-bit option names define the same bit values.
 </P>  </P>
 <P>  <P>
 References to bytes and UTF-8 in this document should be read as references to  References to bytes and UTF-8 in this document should be read as references to
16-bit data quantities and UTF-16 when using the 16-bit library, unless16-bit data units and UTF-16 when using the 16-bit library, or 32-bit data
specified otherwise. More details of the specific differences for the 16-bitunits and UTF-32 when using the 32-bit library, unless specified otherwise.
library are given in theMore details of the specific differences for the 16-bit and 32-bit libraries
 are given in the
 <a href="pcre16.html"><b>pcre16</b></a>  <a href="pcre16.html"><b>pcre16</b></a>
page.and
 <a href="pcre32.html"><b>pcre32</b></a>
 pages.
 </P>  </P>
 <br><a name="SEC6" href="#TOC1">PCRE API OVERVIEW</a><br>  <br><a name="SEC6" href="#TOC1">PCRE API OVERVIEW</a><br>
 <P>  <P>
Line 233  used if available, by setting an option that is ignore Line 244  used if available, by setting an option that is ignore
 relevant. More complicated programs might need to make use of the functions  relevant. More complicated programs might need to make use of the functions
 <b>pcre_jit_stack_alloc()</b>, <b>pcre_jit_stack_free()</b>, and  <b>pcre_jit_stack_alloc()</b>, <b>pcre_jit_stack_free()</b>, and
 <b>pcre_assign_jit_stack()</b> in order to control the JIT code's memory usage.  <b>pcre_assign_jit_stack()</b> in order to control the JIT code's memory usage.
These functions are discussed in the</P>
 <P>
 From release 8.32 there is also a direct interface for JIT execution, which
 gives improved performance. The JIT-specific functions are discussed in the
 <a href="pcrejit.html"><b>pcrejit</b></a>  <a href="pcrejit.html"><b>pcrejit</b></a>
 documentation.  documentation.
 </P>  </P>
Line 317  PCRE supports five different conventions for indicatin Line 331  PCRE supports five different conventions for indicatin
 strings: a single CR (carriage return) character, a single LF (linefeed)  strings: a single CR (carriage return) character, a single LF (linefeed)
 character, the two-character sequence CRLF, any of the three preceding, or any  character, the two-character sequence CRLF, any of the three preceding, or any
 Unicode newline sequence. The Unicode newline sequences are the three just  Unicode newline sequence. The Unicode newline sequences are the three just
mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,mentioned, plus the single characters VT (vertical tab, U+000B), FF (form feed,
 U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS  U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
 (paragraph separator, U+2029).  (paragraph separator, U+2029).
 </P>  </P>
Line 398  not recognized. The following information is available Line 412  not recognized. The following information is available
   PCRE_CONFIG_UTF8    PCRE_CONFIG_UTF8
 </pre>  </pre>
 The output is an integer that is set to one if UTF-8 support is available;  The output is an integer that is set to one if UTF-8 support is available;
otherwise it is set to zero. If this option is given to the 16-bit version ofotherwise it is set to zero. This value should normally be given to the 8-bit
this function, <b>pcre16_config()</b>, the result is PCRE_ERROR_BADOPTION.version of this function, <b>pcre_config()</b>. If it is given to the 16-bit
 or 32-bit version of this function, the result is PCRE_ERROR_BADOPTION.
 <pre>  <pre>
   PCRE_CONFIG_UTF16    PCRE_CONFIG_UTF16
 </pre>  </pre>
 The output is an integer that is set to one if UTF-16 support is available;  The output is an integer that is set to one if UTF-16 support is available;
 otherwise it is set to zero. This value should normally be given to the 16-bit  otherwise it is set to zero. This value should normally be given to the 16-bit
 version of this function, <b>pcre16_config()</b>. If it is given to the 8-bit  version of this function, <b>pcre16_config()</b>. If it is given to the 8-bit
version of this function, the result is PCRE_ERROR_BADOPTION.or 32-bit version of this function, the result is PCRE_ERROR_BADOPTION.
 <pre>  <pre>
     PCRE_CONFIG_UTF32
   </pre>
   The output is an integer that is set to one if UTF-32 support is available;
   otherwise it is set to zero. This value should normally be given to the 32-bit
   version of this function, <b>pcre32_config()</b>. If it is given to the 8-bit
   or 16-bit version of this function, the result is PCRE_ERROR_BADOPTION.
   <pre>
   PCRE_CONFIG_UNICODE_PROPERTIES    PCRE_CONFIG_UNICODE_PROPERTIES
 </pre>  </pre>
 The output is an integer that is set to one if support for Unicode character  The output is an integer that is set to one if support for Unicode character
Line 428  unaligned)". If JIT support is not available, the resu Line 450  unaligned)". If JIT support is not available, the resu
   PCRE_CONFIG_NEWLINE    PCRE_CONFIG_NEWLINE
 </pre>  </pre>
 The output is an integer whose value specifies the default character sequence  The output is an integer whose value specifies the default character sequence
that is recognized as meaning "newline". The four values that are supportedthat is recognized as meaning "newline". The values that are supported in
are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, and -1 for ANY.ASCII/Unicode environments are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for
Though they are derived from ASCII, the same values are returned in EBCDICANYCRLF, and -1 for ANY. In EBCDIC environments, CR, ANYCRLF, and ANY yield the
environments. The default should normally correspond to the standard sequencesame values. However, the value for LF is normally 21, though some EBCDIC
for your operating system.environments use 37. The corresponding values for CRLF are 3349 and 3365. The
 default should normally correspond to the standard sequence for your operating
 system.
 <pre>  <pre>
   PCRE_CONFIG_BSR    PCRE_CONFIG_BSR
 </pre>  </pre>
Line 446  or CRLF. The default can be overridden when a pattern  Line 470  or CRLF. The default can be overridden when a pattern 
 The output is an integer that contains the number of bytes used for internal  The output is an integer that contains the number of bytes used for internal
 linkage in compiled regular expressions. For the 8-bit library, the value can  linkage in compiled regular expressions. For the 8-bit library, the value can
 be 2, 3, or 4. For the 16-bit library, the value is either 2 or 4 and is still  be 2, 3, or 4. For the 16-bit library, the value is either 2 or 4 and is still
a number of bytes. The default value of 2 is sufficient for all but the mosta number of bytes. For the 32-bit library, the value is either 2 or 4 and is
massive patterns, since it allows the compiled pattern to be up to 64K in size.still a number of bytes. The default value of 2 is sufficient for all but the
Larger values allow larger regular expressions to be compiled, at the expensemost massive patterns, since it allows the compiled pattern to be up to 64K in
of slower matching.size. Larger values allow larger regular expressions to be compiled, at the
 expense of slower matching.
 <pre>  <pre>
   PCRE_CONFIG_POSIX_MALLOC_THRESHOLD    PCRE_CONFIG_POSIX_MALLOC_THRESHOLD
 </pre>  </pre>
Line 459  the Line 484  the
 <a href="pcreposix.html"><b>pcreposix</b></a>  <a href="pcreposix.html"><b>pcreposix</b></a>
 documentation.  documentation.
 <pre>  <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    PCRE_CONFIG_MATCH_LIMIT
 </pre>  </pre>
 The output is a long integer that gives the default limit for the number of  The output is a long integer that gives the default limit for the number of
Line 484  avoiding the use of the stack. Line 516  avoiding the use of the stack.
 <br><a name="SEC11" href="#TOC1">COMPILING A PATTERN</a><br>  <br><a name="SEC11" href="#TOC1">COMPILING A PATTERN</a><br>
 <P>  <P>
 <b>pcre *pcre_compile(const char *<i>pattern</i>, int <i>options</i>,</b>  <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 char **<i>errptr</i>, int *<i>erroffset</i>,</b>
<b>const unsigned char *<i>tableptr</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>pcre *pcre_compile2(const char *<i>pattern</i>, int <i>options</i>,</b>
<b>int *<i>errorcodeptr</i>,</b><b>     int *<i>errorcodeptr</i>,</b>
<b>const char **<i>errptr</i>, int *<i>erroffset</i>,</b><b>     const char **<i>errptr</i>, int *<i>erroffset</i>,</b>
<b>const unsigned char *<i>tableptr</i>);</b><b>     const unsigned char *<i>tableptr</i>);</b>
 </P>  </P>
 <P>  <P>
 Either of the functions <b>pcre_compile()</b> or <b>pcre_compile2()</b> can be  Either of the functions <b>pcre_compile()</b> or <b>pcre_compile2()</b> can be
Line 524  documentation). For those options that can be differen Line 558  documentation). For those options that can be differen
 the pattern, the contents of the <i>options</i> argument specifies their  the pattern, the contents of the <i>options</i> argument specifies their
 settings at the start of compilation and execution. The PCRE_ANCHORED,  settings at the start of compilation and execution. The PCRE_ANCHORED,
 PCRE_BSR_<i>xxx</i>, PCRE_NEWLINE_<i>xxx</i>, PCRE_NO_UTF8_CHECK, and  PCRE_BSR_<i>xxx</i>, PCRE_NEWLINE_<i>xxx</i>, PCRE_NO_UTF8_CHECK, and
PCRE_NO_START_OPT options can be set at the time of matching as well as atPCRE_NO_START_OPTIMIZE options can be set at the time of matching as well as at
 compile time.  compile time.
 </P>  </P>
 <P>  <P>
Line 533  Otherwise, if compilation of a pattern fails, <b>pcre_ Line 567  Otherwise, if compilation of a pattern fails, <b>pcre_
 NULL, and sets the variable pointed to by <i>errptr</i> to point to a textual  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  error message. This is a static string that is part of the library. You must
 not try to free it. Normally, the offset from the start of the pattern to the  not try to free it. Normally, the offset from the start of the pattern to the
byte that was being processed when the error was discovered is placed in thedata unit that was being processed when the error was discovered is placed in
variable pointed to by <i>erroffset</i>, which must not be NULL (if it is, anthe variable pointed to by <i>erroffset</i>, which must not be NULL (if it is,
immediate error is given). However, for an invalid UTF-8 string, the offset isan immediate error is given). However, for an invalid UTF-8 or UTF-16 string,
that of the first byte of the failing character.the offset is that of the first data unit of the failing character.
 </P>  </P>
 <P>  <P>
 Some errors are not detected until the whole pattern has been scanned; in these  Some errors are not detected until the whole pattern has been scanned; in these
 cases, the offset passed back is the length of the pattern. Note that the  cases, the offset passed back is the length of the pattern. Note that the
offset is in bytes, not characters, even in UTF-8 mode. It may sometimes pointoffset is in data units, not characters, even in a UTF mode. It may sometimes
into the middle of a UTF-8 character.point into the middle of a UTF-8 or UTF-16 character.
 </P>  </P>
 <P>  <P>
 If <b>pcre_compile2()</b> is used instead of <b>pcre_compile()</b>, and the  If <b>pcre_compile2()</b> is used instead of <b>pcre_compile()</b>, and the
Line 555  If the final argument, <i>tableptr</i>, is NULL, PCRE  Line 589  If the final argument, <i>tableptr</i>, is NULL, PCRE 
 character tables that are built when PCRE is compiled, using the default C  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  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  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 ispattern, and used again by <b>pcre_exec()</b> and <b>pcre_dfa_exec()</b> when the
passed to it. For more discussion, see the section on locale support below.pattern is matched. For more discussion, see the section on locale support
 below.
 </P>  </P>
 <P>  <P>
 This code fragment shows a typical straightforward call to <b>pcre_compile()</b>:  This code fragment shows a typical straightforward call to <b>pcre_compile()</b>:
Line 641  documentation. Line 676  documentation.
 <pre>  <pre>
   PCRE_EXTENDED    PCRE_EXTENDED
 </pre>  </pre>
If this bit is set, whitespace data characters in the pattern are totallyIf this bit is set, most white space characters in the pattern are totally
ignored except when escaped or inside a character class. Whitespace does notignored except when escaped or inside a character class. However, white space
include the VT character (code 11). In addition, characters between anis not allowed within sequences such as (?&#62; that introduce various
unescaped # outside a character class and the next newline, inclusive, are alsoparenthesized subpatterns, nor within a numerical quantifier such as {1,3}.
ignored. This is equivalent to Perl's /x option, and it can be changed within aHowever, ignorable white space is permitted between an item and a following
pattern by a (?x) option setting.quantifier and between a quantifier and a following + that indicates
 possessiveness.
 </P>  </P>
 <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  Which characters are interpreted as newlines is controlled by the options
 passed to <b>pcre_compile()</b> or by a special sequence at the start of the  passed to <b>pcre_compile()</b> or by a special sequence at the start of the
 pattern, as described in the section entitled  pattern, as described in the section entitled
Line 659  happen to represent a newline do not count. Line 706  happen to represent a newline do not count.
 </P>  </P>
 <P>  <P>
 This option makes it possible to include comments inside complicated patterns.  This option makes it possible to include comments inside complicated patterns.
Note, however, that this applies only to data characters. Whitespace charactersNote, however, that this applies only to data characters. White space characters
 may never appear within special character sequences in a pattern, for example  may never appear within special character sequences in a pattern, for example
 within the sequence (?( that introduces a conditional subpattern.  within the sequence (?( that introduces a conditional subpattern.
 <pre>  <pre>
Line 716  binary zero character followed by z). Line 763  binary zero character followed by z).
 <pre>  <pre>
   PCRE_MULTILINE    PCRE_MULTILINE
 </pre>  </pre>
By default, PCRE treats the subject string as consisting of a single line ofBy default, for the purposes of matching "start of line" and "end of line",
characters (even if it actually contains newlines). The "start of line"PCRE treats the subject string as consisting of a single line of characters,
metacharacter (^) matches only at the start of the string, while the "end ofeven if it actually contains newlines. The "start of line" metacharacter (^)
line" metacharacter ($) matches only at the end of the string, or before amatches only at the start of the string, and the "end of line" metacharacter
terminating newline (unless PCRE_DOLLAR_ENDONLY is set). This is the same as($) matches only at the end of the string, or before a terminating newline
Perl.(except when PCRE_DOLLAR_ENDONLY is set). Note, however, that unless
 PCRE_DOTALL is set, the "any character" metacharacter (.) does not match at a
 newline. This behaviour (for ^, $, and dot) is the same as Perl.
 </P>  </P>
 <P>  <P>
 When PCRE_MULTILINE it is set, the "start of line" and "end of line" constructs  When PCRE_MULTILINE it is set, the "start of line" and "end of line" constructs
Line 731  equivalent to Perl's /m option, and it can be changed  Line 780  equivalent to Perl's /m option, and it can be changed 
 (?m) option setting. If there are no newlines in a subject string, or no  (?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.  occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect.
 <pre>  <pre>
     PCRE_NEVER_UTF
   </pre>
   This option locks out interpretation of the pattern as UTF-8 (or UTF-16 or
   UTF-32 in the 16-bit and 32-bit libraries). In particular, it prevents the
   creator of the pattern from switching to UTF interpretation by starting the
   pattern with (*UTF). This may be useful in applications that process patterns
   from external sources. The combination of PCRE_UTF8 and PCRE_NEVER_UTF also
   causes an error.
   <pre>
   PCRE_NEWLINE_CR    PCRE_NEWLINE_CR
   PCRE_NEWLINE_LF    PCRE_NEWLINE_LF
   PCRE_NEWLINE_CRLF    PCRE_NEWLINE_CRLF
Line 743  indicated by a single character (CR or LF, respectivel Line 801  indicated by a single character (CR or LF, respectivel
 PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character  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  CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three
 preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies  preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies
that any Unicode newline sequence should be recognized. The Unicode newlinethat any Unicode newline sequence should be recognized.
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). For the 8-bit 
library, the last two are recognized only in UTF-8 mode. 
 </P>  </P>
 <P>  <P>
   In an ASCII/Unicode environment, the Unicode newline sequences are the three
   just mentioned, plus the single characters VT (vertical tab, U+000B), FF (form
   feed, U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
   (paragraph separator, U+2029). For the 8-bit library, the last two are
   recognized only in UTF-8 mode.
   </P>
   <P>
   When PCRE is compiled to run in an EBCDIC (mainframe) environment, the code for
   CR is 0x0d, the same as ASCII. However, the character code for LF is normally
   0x15, though in some EBCDIC environments 0x25 is used. Whichever of these is
   not LF is made to correspond to Unicode's NEL character. EBCDIC codes are all
   less than 256. For more details, see the
   <a href="pcrebuild.html"><b>pcrebuild</b></a>
   documentation.
   </P>
   <P>
 The newline setting in the options word uses three bits that are treated  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  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  plus the five values above). This means that if you set more than one newline
Line 759  other combinations may yield unused numbers and cause  Line 829  other combinations may yield unused numbers and cause 
 </P>  </P>
 <P>  <P>
 The only time that a line break in a pattern is specially recognized when  The only time that a line break in a pattern is specially recognized when
compiling is when PCRE_EXTENDED is set. CR and LF are whitespace characters,compiling is when PCRE_EXTENDED is set. CR and LF are white space characters,
 and so are ignored in this mode. Also, an unescaped # outside a character class  and so are ignored in this mode. Also, an unescaped # outside a character class
 indicates a comment that lasts until after the next line break sequence. In  indicates a comment that lasts until after the next line break sequence. In
 other circumstances, line break sequences in patterns are treated as literal  other circumstances, line break sequences in patterns are treated as literal
Line 777  were followed by ?: but named parentheses can still be Line 847  were followed by ?: but named parentheses can still be
 they acquire numbers in the usual way). There is no equivalent of this option  they acquire numbers in the usual way). There is no equivalent of this option
 in Perl.  in Perl.
 <pre>  <pre>
  NO_START_OPTIMIZE  PCRE_NO_AUTO_POSSESS
 </pre>  </pre>
   If this option is set, it disables "auto-possessification". This is an
   optimization that, for example, turns a+b into a++b in order to avoid
   backtracks into a+ that can never be successful. However, if callouts are in
   use, auto-possessification means that some of them are never taken. You can set
   this option if you want the matching functions to do a full unoptimized search
   and run all the callouts, but it is mainly provided for testing purposes.
   <pre>
     PCRE_NO_START_OPTIMIZE
   </pre>
 This is an option that acts at matching time; that is, it is really an option  This is an option that acts at matching time; that is, it is really an option
 for <b>pcre_exec()</b> or <b>pcre_dfa_exec()</b>. If it is set at compile time,  for <b>pcre_exec()</b> or <b>pcre_dfa_exec()</b>. If it is set at compile time,
it is remembered with the compiled pattern and assumed at matching time. Forit is remembered with the compiled pattern and assumed at matching time. This
details see the discussion of PCRE_NO_START_OPTIMIZEis necessary if you want to use JIT execution, because the JIT compiler needs
 to know whether or not this option is set. For details see the discussion of
 PCRE_NO_START_OPTIMIZE
 <a href="#execoptions">below.</a>  <a href="#execoptions">below.</a>
 <pre>  <pre>
   PCRE_UCP    PCRE_UCP
Line 816  page. Line 897  page.
 <pre>  <pre>
   PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
 </pre>  </pre>
When PCRE_UTF8 is set, the validity of the pattern as a UTF-8When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is
string is automatically checked. There is a discussion about theautomatically checked. There is a discussion about the
 <a href="pcreunicode.html#utf8strings">validity of UTF-8 strings</a>  <a href="pcreunicode.html#utf8strings">validity of UTF-8 strings</a>
 in the  in the
 <a href="pcreunicode.html"><b>pcreunicode</b></a>  <a href="pcreunicode.html"><b>pcreunicode</b></a>
Line 825  page. If an invalid UTF-8 sequence is found, <b>pcre_c Line 906  page. If an invalid UTF-8 sequence is found, <b>pcre_c
 error. If you already know that your pattern is valid, and you want to skip  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.  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  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 alsoundefined. It may cause your program to crash or loop. Note that this option
be passed to <b>pcre_exec()</b> and <b>pcre_dfa_exec()</b>, to suppress thecan also be passed to <b>pcre_exec()</b> and <b>pcre_dfa_exec()</b>, to suppress
validity checking of subject strings.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>  </P>
 <br><a name="SEC12" href="#TOC1">COMPILATION ERROR CODES</a><br>  <br><a name="SEC12" href="#TOC1">COMPILATION ERROR CODES</a><br>
 <P>  <P>
 The following table lists the error codes than may be returned by  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  <b>pcre_compile2()</b>, along with the error messages that may be returned by
 both compiling functions. Note that error messages are always 8-bit ASCII  both compiling functions. Note that error messages are always 8-bit ASCII
strings, even in 16-bit mode. As PCRE has developed, some error codes havestrings, even in 16-bit or 32-bit mode. As PCRE has developed, some error codes
fallen out of use. To avoid confusion, they have not been re-used.have fallen out of use. To avoid confusion, they have not been re-used.
 <pre>  <pre>
    0  no error     0  no error
    1  \ at end of pattern     1  \ at end of pattern
Line 871  fallen out of use. To avoid confusion, they have not b Line 954  fallen out of use. To avoid confusion, they have not b
   31  POSIX collating elements are not supported    31  POSIX collating elements are not supported
   32  this version of PCRE is compiled without UTF support    32  this version of PCRE is compiled without UTF support
   33  [this code is not in use]    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)    35  invalid condition (?(0)
   36  \C not allowed in lookbehind assertion    36  \C not allowed in lookbehind assertion
   37  PCRE does not support \L, \l, \N{name}, \U, or \u    37  PCRE does not support \L, \l, \N{name}, \U, or \u
Line 899  fallen out of use. To avoid confusion, they have not b Line 982  fallen out of use. To avoid confusion, they have not b
         name/number or by a plain number          name/number or by a plain number
   58  a numbered reference must not be zero    58  a numbered reference must not be zero
   59  an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT)    59  an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT)
  60  (*VERB) not recognized  60  (*VERB) not recognized or malformed
   61  number is too big    61  number is too big
   62  subpattern name expected    62  subpattern name expected
   63  digit expected after (?+    63  digit expected after (?+
Line 916  fallen out of use. To avoid confusion, they have not b Line 999  fallen out of use. To avoid confusion, they have not b
   72  too many forward references    72  too many forward references
   73  disallowed Unicode code point (&#62;= 0xd800 && &#60;= 0xdfff)    73  disallowed Unicode code point (&#62;= 0xd800 && &#60;= 0xdfff)
   74  invalid UTF-16 string (specifically UTF-16)    74  invalid UTF-16 string (specifically UTF-16)
     75  name is too long in (*MARK), (*PRUNE), (*SKIP), or (*THEN)
     76  character value in \u.... sequence is too large
     77  invalid UTF-32 string (specifically UTF-32)
     78  setting UTF is disabled by the application
     79  non-hex character in \x{} (closing brace missing?)
     80  non-octal character in \o{} (closing brace missing?)
     81  missing opening brace after \o
     82  parentheses are too deeply nested
     83  invalid range in character class
 </pre>  </pre>
 The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may  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.  be used if the limits were changed when PCRE was built.
 <a name="studyingapattern"></a></P>  <a name="studyingapattern"></a></P>
 <br><a name="SEC13" href="#TOC1">STUDYING A PATTERN</a><br>  <br><a name="SEC13" href="#TOC1">STUDYING A PATTERN</a><br>
 <P>  <P>
<b>pcre_extra *pcre_study(const pcre *<i>code</i>, int <i>options</i></b><b>pcre_extra *pcre_study(const pcre *<i>code</i>, int <i>options</i>,</b>
<b>const char **<i>errptr</i>);</b><b>     const char **<i>errptr</i>);</b>
 </P>  </P>
 <P>  <P>
 If a compiled pattern is going to be used several times, it is worth spending  If a compiled pattern is going to be used several times, it is worth spending
Line 944  in the section on matching a pattern. Line 1036  in the section on matching a pattern.
 </P>  </P>
 <P>  <P>
 If studying the pattern does not produce any useful information,  If studying the pattern does not produce any useful information,
<b>pcre_study()</b> returns NULL. In that circumstance, if the calling program<b>pcre_study()</b> returns NULL by default. In that circumstance, if the
wants to pass any of the other fields to <b>pcre_exec()</b> orcalling program wants to pass any of the other fields to <b>pcre_exec()</b> or
<b>pcre_dfa_exec()</b>, it must set up its own <b>pcre_extra</b> block.<b>pcre_dfa_exec()</b>, it must set up its own <b>pcre_extra</b> block. However,
 if <b>pcre_study()</b> is called with the PCRE_STUDY_EXTRA_NEEDED option, it
 returns a <b>pcre_extra</b> block even if studying did not find any additional
 information. It may still return NULL, however, if an error occurs in
 <b>pcre_study()</b>.
 </P>  </P>
 <P>  <P>
The second argument of <b>pcre_study()</b> contains option bits. There is onlyThe second argument of <b>pcre_study()</b> contains option bits. There are three
one option: PCRE_STUDY_JIT_COMPILE. If this is set, and the just-in-timefurther options in addition to PCRE_STUDY_EXTRA_NEEDED:
compiler is available, the pattern is further compiled into machine code that<pre>
executes much faster than the <b>pcre_exec()</b> matching function. If  PCRE_STUDY_JIT_COMPILE
the just-in-time compiler is not available, this option is ignored. All other  PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE
bits in the <i>options</i> argument must be zero.  PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE
 </pre>
 If any of these are set, and the just-in-time compiler is available, the
 pattern is further compiled into machine code that executes much faster than
 the <b>pcre_exec()</b> interpretive matching function. If the just-in-time
 compiler is not available, these options are ignored. All undefined bits in the
 <i>options</i> argument must be zero.
 </P>  </P>
 <P>  <P>
 JIT compilation is a heavyweight optimization. It can take some time for  JIT compilation is a heavyweight optimization. It can take some time for
Line 979  When you are finished with a pattern, you can free the Line 1081  When you are finished with a pattern, you can free the
 study data by calling <b>pcre_free_study()</b>. This function was added to the  study data by calling <b>pcre_free_study()</b>. This function was added to the
 API for release 8.20. For earlier versions, the memory could be freed with  API for release 8.20. For earlier versions, the memory could be freed with
 <b>pcre_free()</b>, just like the pattern itself. This will still work in cases  <b>pcre_free()</b>, just like the pattern itself. This will still work in cases
where PCRE_STUDY_JIT_COMPILE is not used, but it is advisable to change to thewhere JIT optimization is not used, but it is advisable to change to the new
new function when convenient.function when convenient.
 </P>  </P>
 <P>  <P>
 This is a typical way in which <b>pcre_study</b>() is used (except that in a  This is a typical way in which <b>pcre_study</b>() is used (except that in a
Line 1003  real application there should be tests for errors): Line 1105  real application there should be tests for errors):
 Studying a pattern does two things: first, a lower bound for the length of  Studying a pattern does two things: first, a lower bound for the length of
 subject string that is needed to match the pattern is computed. This does not  subject string that is needed to match the pattern is computed. This does not
 mean that there are any strings of that length that match, but it does  mean that there are any strings of that length that match, but it does
guarantee that no shorter strings match. The value is used byguarantee that no shorter strings match. The value is used to avoid wasting
<b>pcre_exec()</b> and <b>pcre_dfa_exec()</b> to avoid wasting time by trying totime by trying to match strings that are shorter than the lower bound. You can
match strings that are shorter than the lower bound. You can find out the valuefind out the value in a calling program via the <b>pcre_fullinfo()</b> function.
in a calling program via the <b>pcre_fullinfo()</b> function. 
 </P>  </P>
 <P>  <P>
 Studying a pattern is also useful for non-anchored patterns that do not have a  Studying a pattern is also useful for non-anchored patterns that do not have a
 single fixed starting character. A bitmap of possible starting bytes is  single fixed starting character. A bitmap of possible starting bytes is
 created. This speeds up finding a position in the subject at which to start  created. This speeds up finding a position in the subject at which to start
matching. (In 16-bit mode, the bitmap is used for 16-bit values less than 256.)matching. (In 16-bit mode, the bitmap is used for 16-bit values less than 256.
 In 32-bit mode, the bitmap is used for 32-bit values less than 256.)
 </P>  </P>
 <P>  <P>
 These two optimizations apply to both <b>pcre_exec()</b> and  These two optimizations apply to both <b>pcre_exec()</b> and
<b>pcre_dfa_exec()</b>. However, they are not used by <b>pcre_exec()</b> if<b>pcre_dfa_exec()</b>, and the information is also used by the JIT compiler.
<b>pcre_study()</b> is called with the PCRE_STUDY_JIT_COMPILE option, andThe optimizations can be disabled by setting the PCRE_NO_START_OPTIMIZE option.
just-in-time compiling is successful. The optimizations can be disabled byYou might want to do this if your pattern contains callouts or (*MARK) and you
setting the PCRE_NO_START_OPTIMIZE option when calling <b>pcre_exec()</b> orwant to make use of these facilities in cases where matching fails.
<b>pcre_dfa_exec()</b>. You might want to do this if your pattern contains</P>
callouts or (*MARK) (which cannot be handled by the JIT compiler), and you want<P>
to make use of these facilities in cases where matching fails. See thePCRE_NO_START_OPTIMIZE can be specified at either compile time or execution
discussion of PCRE_NO_START_OPTIMIZEtime. However, if PCRE_NO_START_OPTIMIZE is passed to <b>pcre_exec()</b>, (that
 is, after any JIT compilation has happened) JIT execution is disabled. For JIT
 execution to work with PCRE_NO_START_OPTIMIZE, the option must be set at
 compile time.
 </P>
 <P>
 There is a longer discussion of PCRE_NO_START_OPTIMIZE
 <a href="#execoptions">below.</a>  <a href="#execoptions">below.</a>
 <a name="localesupport"></a></P>  <a name="localesupport"></a></P>
 <br><a name="SEC14" href="#TOC1">LOCALE SUPPORT</a><br>  <br><a name="SEC14" href="#TOC1">LOCALE SUPPORT</a><br>
 <P>  <P>
 PCRE handles caseless matching, and determines whether characters are letters,  PCRE handles caseless matching, and determines whether characters are letters,
 digits, or whatever, by reference to a set of tables, indexed by character  digits, or whatever, by reference to a set of tables, indexed by character
value. When running in UTF-8 mode, this applies only to characterscode point. When running in UTF-8 mode, or in the 16- or 32-bit libraries, this
with codes less than 128. By default, higher-valued codes never match escapesapplies only to characters with code points less than 256. By default,
such as \w or \d, but they can be tested with \p if PCRE is built withhigher-valued code points never match escapes such as \w or \d. However, if
Unicode character property support. Alternatively, the PCRE_UCP option can bePCRE is built with Unicode property support, all characters can be tested with
set at compile time; this causes \w and friends to use Unicode property\p and \P, or, alternatively, the PCRE_UCP option can be set when a pattern
support instead of built-in tables. The use of locales with Unicode isis compiled; this causes \w and friends to use Unicode property support
discouraged. If you are handling characters with codes greater than 128, youinstead of the built-in tables.
should either use UTF-8 and Unicode, or use locales, but not try to mix the 
two. 
 </P>  </P>
 <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  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.  of <b>pcre_compile()</b> is NULL. These are sufficient for many applications.
 Normally, the internal tables recognize only ASCII characters. However, when  Normally, the internal tables recognize only ASCII characters. However, when
Line 1056  for this locale support is expected to die away. Line 1167  for this locale support is expected to die away.
 <P>  <P>
 External tables are built by calling the <b>pcre_maketables()</b> function,  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  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. Forto <b>pcre_compile()</b> as often as necessary. For example, to build and use
example, to build and use tables that are appropriate for the French localetables that are appropriate for the French locale (where accented characters
(where accented characters with values greater than 128 are treated as letters),with values greater than 128 are treated as letters), the following code could
the following code could be used:be used:
 <pre>  <pre>
   setlocale(LC_CTYPE, "fr_FR");    setlocale(LC_CTYPE, "fr_FR");
   tables = pcre_maketables();    tables = pcre_maketables();
Line 1077  needed. Line 1188  needed.
 <P>  <P>
 The pointer that is passed to <b>pcre_compile()</b> is saved with the compiled  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>  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 singleand 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  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>
 <P>  <P>
 It is possible to pass a table pointer or NULL (indicating the use of the  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,internal tables) to <b>pcre_exec()</b> or <b>pcre_dfa_exec()</b> (see the
this facility could be used to match a pattern in a different locale from thediscussion below in the section on matching a pattern). This facility is
one in which it was compiled. Passing table pointers at run time is discussedprovided for use with pre-compiled patterns that have been saved and reloaded.
below in the section on matching a pattern.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>  <a name="infoaboutpattern"></a></P>
 <br><a name="SEC15" href="#TOC1">INFORMATION ABOUT A PATTERN</a><br>  <br><a name="SEC15" href="#TOC1">INFORMATION ABOUT A PATTERN</a><br>
 <P>  <P>
 <b>int pcre_fullinfo(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b>  <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>
 <P>  <P>
 The <b>pcre_fullinfo()</b> function returns information about a compiled  The <b>pcre_fullinfo()</b> function returns information about a compiled
Line 1112  the following negative numbers: Line 1227  the following negative numbers:
   PCRE_ERROR_BADENDIANNESS  the pattern was compiled with different    PCRE_ERROR_BADENDIANNESS  the pattern was compiled with different
                             endianness                              endianness
   PCRE_ERROR_BADOPTION      the value of <i>what</i> was invalid    PCRE_ERROR_BADOPTION      the value of <i>what</i> was invalid
     PCRE_ERROR_UNSET          the requested field is not set
 </pre>  </pre>
 The "magic number" is placed at the start of each compiled pattern as an simple  The "magic number" is placed at the start of each compiled pattern as an simple
 check against passing an arbitrary memory pointer. The endianness error can  check against passing an arbitrary memory pointer. The endianness error can
Line 1159  variable. Line 1275  variable.
 <P>  <P>
 If there is a fixed first value, for example, the letter "c" from a pattern  If there is a fixed first value, for example, the letter "c" from a pattern
 such as (cat|cow|coyote), its value is returned. In the 8-bit library, the  such as (cat|cow|coyote), its value is returned. In the 8-bit library, the
value is always less than 256; in the 16-bit library the value can be up tovalue is always less than 256. In the 16-bit library the value can be up to
0xffff.0xffff. In the 32-bit library the value can be up to 0x10ffff.
 </P>  </P>
 <P>  <P>
 If there is no fixed first value, and if either  If there is no fixed first value, and if either
Line 1177  starts with "^", or Line 1293  starts with "^", or
 -1 is returned, indicating that the pattern matches only at the start of a  -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  subject string or after any newline within the string. Otherwise -2 is
 returned. For anchored patterns, -2 is returned.  returned. For anchored patterns, -2 is returned.
   </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;
   instead the PCRE_INFO_FIRSTCHARACTERFLAGS and PCRE_INFO_FIRSTCHARACTER values
   should be used.
 <pre>  <pre>
   PCRE_INFO_FIRSTTABLE    PCRE_INFO_FIRSTTABLE
 </pre>  </pre>
Line 1199  Return 1 if the (?J) or (?-J) option setting is used i Line 1321  Return 1 if the (?J) or (?-J) option setting is used i
 <pre>  <pre>
   PCRE_INFO_JIT    PCRE_INFO_JIT
 </pre>  </pre>
Return 1 if the pattern was studied with the PCRE_STUDY_JIT_COMPILE option, andReturn 1 if the pattern was studied with one of the JIT options, and
 just-in-time compiling was successful. The fourth argument should point to an  just-in-time compiling was successful. The fourth argument should point to an
 <b>int</b> variable. A return value of 0 means that JIT support is not available  <b>int</b> variable. A return value of 0 means that JIT support is not available
in this version of PCRE, or that the pattern was not studied with thein this version of PCRE, or that the pattern was not studied with a JIT option,
PCRE_STUDY_JIT_COMPILE option, or that the JIT compiler could not handle thisor that the JIT compiler could not handle this particular pattern. See the
particular pattern. See the 
 <a href="pcrejit.html"><b>pcrejit</b></a>  <a href="pcrejit.html"><b>pcrejit</b></a>
 documentation for details of what can and cannot be handled.  documentation for details of what can and cannot be handled.
 <pre>  <pre>
   PCRE_INFO_JITSIZE    PCRE_INFO_JITSIZE
 </pre>  </pre>
If the pattern was successfully studied with the PCRE_STUDY_JIT_COMPILE option,If the pattern was successfully studied with a JIT option, return the size of
return the size of the JIT compiled code, otherwise return zero. The fourththe JIT compiled code, otherwise return zero. The fourth argument should point
argument should point to a <b>size_t</b> variable.to a <b>size_t</b> variable.
 <pre>  <pre>
   PCRE_INFO_LASTLITERAL    PCRE_INFO_LASTLITERAL
 </pre>  </pre>
Line 1223  value, -1 is returned. For anchored patterns, a last l Line 1344  value, -1 is returned. For anchored patterns, a last l
 only if it follows something of variable length. For example, for the pattern  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  /^a\d+z\d+/ the returned value is "z", but for /^a\dz\d/ the returned value
 is -1.  is -1.
   </P>
   <P>
   Since for the 32-bit library using the non-UTF-32 mode, this function is unable
   to return the full 32-bit range of characters, this value is deprecated;
   instead the PCRE_INFO_REQUIREDCHARFLAGS and PCRE_INFO_REQUIREDCHAR values should
   be used.
 <pre>  <pre>
     PCRE_INFO_MATCH_EMPTY
   </pre>
   Return 1 if the pattern can match an empty string, otherwise 0. The fourth
   argument should point to an <b>int</b> variable.
   <pre>
     PCRE_INFO_MATCHLIMIT
   </pre>
   If the pattern set a match limit by including an item of the form
   (*LIMIT_MATCH=nnnn) at the start, the value is returned. The fourth argument
   should point to an unsigned 32-bit integer. If no such value has been set, the
   call to <b>pcre_fullinfo()</b> returns the error PCRE_ERROR_UNSET.
   <pre>
     PCRE_INFO_MAXLOOKBEHIND
   </pre>
   Return the number of characters (NB not data units) in the longest lookbehind
   assertion in the pattern. This information is useful when doing multi-segment
   matching using the partial matching facilities. Note that the simple assertions
   \b and \B require a one-character lookbehind. \A also registers a
   one-character lookbehind, though it does not actually inspect the previous
   character. This is to ensure that at least one character from the old segment
   is retained when a new segment is processed. Otherwise, if there are no
   lookbehinds in the pattern, \A might match incorrectly at the start of a new
   segment.
   <pre>
   PCRE_INFO_MINLENGTH    PCRE_INFO_MINLENGTH
 </pre>  </pre>
 If the pattern was studied and a minimum length for matching subject strings  If the pattern was studied and a minimum length for matching subject strings
 was computed, its value is returned. Otherwise the returned value is -1. The  was computed, its value is returned. Otherwise the returned value is -1. The
value is a number of characters, which in UTF-8 mode may be different from thevalue is a number of characters, which in UTF mode may be different from the
number of bytes. The fourth argument should point to an <b>int</b> variable. Anumber of data units. The fourth argument should point to an <b>int</b>
non-negative value is a lower bound to the length of any matching string. Therevariable. A non-negative value is a lower bound to the length of any matching
may not be any strings of that length that do actually match, but every stringstring. There may not be any strings of that length that do actually match, but
that does match is at least that long.every string that does match is at least that long.
 <pre>  <pre>
   PCRE_INFO_NAMECOUNT    PCRE_INFO_NAMECOUNT
   PCRE_INFO_NAMEENTRYSIZE    PCRE_INFO_NAMEENTRYSIZE
Line 1256  length of the longest name. PCRE_INFO_NAMETABLE return Line 1407  length of the longest name. PCRE_INFO_NAMETABLE return
 entry of the table. This is a pointer to <b>char</b> in the 8-bit library, where  entry of the table. This is a pointer to <b>char</b> in the 8-bit library, where
 the first two bytes of each entry are the number of the capturing parenthesis,  the first two bytes of each entry are the number of the capturing parenthesis,
 most significant byte first. In the 16-bit library, the pointer points to  most significant byte first. In the 16-bit library, the pointer points to
16-bit data units, the first of which contains the parenthesis number. The rest16-bit data units, the first of which contains the parenthesis number. In the
of the entry is the corresponding name, zero terminated.32-bit library, the pointer points to 32-bit data units, the first of which
 contains the parenthesis number. The rest of the entry is the corresponding
 name, zero terminated.
 </P>  </P>
 <P>  <P>
The names are in alphabetical order. Duplicate names may appear if (?| is usedThe names are in alphabetical order. If (?| is used to create multiple groups
to create multiple groups with the same number, as described in thewith the same number, as described in the
 <a href="pcrepattern.html#dupsubpatternnumber">section on duplicate subpattern numbers</a>  <a href="pcrepattern.html#dupsubpatternnumber">section on duplicate subpattern numbers</a>
 in the  in the
 <a href="pcrepattern.html"><b>pcrepattern</b></a>  <a href="pcrepattern.html"><b>pcrepattern</b></a>
page. Duplicate names for subpatterns with different numbers are permitted onlypage, the groups may be given the same name, but there is only one entry in the
if PCRE_DUPNAMES is set. In all cases of duplicate names, they appear in thetable. Different names for groups of the same number are not permitted.
table in the order in which they were found in the pattern. In the absence ofDuplicate names for subpatterns with different numbers are permitted,
(?| this is the order of increasing number; when (?| is used this is notbut only if PCRE_DUPNAMES is set. They appear in the table in the order in
necessarily the case because later subpatterns may have lower numbers.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>
 <P>  <P>
 As a simple example of the name/number table, consider the following pattern  As a simple example of the name/number table, consider the following pattern
Line 1322  alternatives begin with one of the following: Line 1477  alternatives begin with one of the following:
 For such patterns, the PCRE_ANCHORED bit is set in the options returned by  For such patterns, the PCRE_ANCHORED bit is set in the options returned by
 <b>pcre_fullinfo()</b>.  <b>pcre_fullinfo()</b>.
 <pre>  <pre>
     PCRE_INFO_RECURSIONLIMIT
   </pre>
   If the pattern set a recursion limit by including an item of the form
   (*LIMIT_RECURSION=nnnn) at the start, the value is returned. The fourth
   argument should point to an unsigned 32-bit integer. If no such value has been
   set, the call to <b>pcre_fullinfo()</b> returns the error PCRE_ERROR_UNSET.
   <pre>
   PCRE_INFO_SIZE    PCRE_INFO_SIZE
 </pre>  </pre>
Return the size of the compiled pattern in bytes (for both libraries). TheReturn the size of the compiled pattern in bytes (for all three libraries). The
 fourth argument should point to a <b>size_t</b> variable. This value does not  fourth argument should point to a <b>size_t</b> variable. This value does not
 include the size of the <b>pcre</b> structure that is returned by  include the size of the <b>pcre</b> structure that is returned by
 <b>pcre_compile()</b>. The value that is passed as the argument to  <b>pcre_compile()</b>. The value that is passed as the argument to
Line 1335  does not alter the value returned by this option. Line 1497  does not alter the value returned by this option.
 <pre>  <pre>
   PCRE_INFO_STUDYSIZE    PCRE_INFO_STUDYSIZE
 </pre>  </pre>
Return the size in bytes of the data block pointed to by the <i>study_data</i>Return the size in bytes (for all three libraries) of the data block pointed to
field in a <b>pcre_extra</b> block. If <b>pcre_extra</b> is NULL, or there is noby the <i>study_data</i> field in a <b>pcre_extra</b> block. If <b>pcre_extra</b>
study data, zero is returned. The fourth argument should point to ais NULL, or there is no study data, zero is returned. The fourth argument
<b>size_t</b> variable. The <i>study_data</i> field is set by <b>pcre_study()</b>should point to a <b>size_t</b> variable. The <i>study_data</i> field is set by
to record information that will speed up matching (see the section entitled<b>pcre_study()</b> to record information that will speed up matching (see the
 section entitled
 <a href="#studyingapattern">"Studying a pattern"</a>  <a href="#studyingapattern">"Studying a pattern"</a>
 above). The format of the <i>study_data</i> block is private, but its length  above). The format of the <i>study_data</i> block is private, but its length
 is made available via this option so that it can be saved and restored (see the  is made available via this option so that it can be saved and restored (see the
 <a href="pcreprecompile.html"><b>pcreprecompile</b></a>  <a href="pcreprecompile.html"><b>pcreprecompile</b></a>
 documentation for details).  documentation for details).
   <pre>
     PCRE_INFO_FIRSTCHARACTERFLAGS
   </pre>
   Return information about the first data unit of any matched string, for a
   non-anchored pattern. The fourth argument should point to an <b>int</b>
   variable.
 </P>  </P>
   <P>
   If there is a fixed first value, for example, the letter "c" from a pattern
   such as (cat|cow|coyote), 1 is returned, and the character value can be
   retrieved using PCRE_INFO_FIRSTCHARACTER.
   </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>
   2 is returned, indicating that the pattern matches only at the start of a
   subject string or after any newline within the string. Otherwise 0 is
   returned. For anchored patterns, 0 is returned.
   <pre>
     PCRE_INFO_FIRSTCHARACTER
   </pre>
   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.
   <pre>
     PCRE_INFO_REQUIREDCHARFLAGS
   </pre>
   Returns 1 if there is a rightmost literal data unit that must exist in any
   matched string, other than at its start. The fourth argument should  point to
   an <b>int</b> variable. If there is no such value, 0 is returned. If returning
   1, the character value itself can be retrieved using PCRE_INFO_REQUIREDCHAR.
   </P>
   <P>
   For anchored patterns, a last literal value is recorded only if it follows
   something of variable length. For example, for the pattern /^a\d+z\d+/ the
   returned value 1 (with "z" returned from PCRE_INFO_REQUIREDCHAR), but for
   /^a\dz\d/ the returned value is 0.
   <pre>
     PCRE_INFO_REQUIREDCHAR
   </pre>
   Return the value of the rightmost literal data unit that must exist in any
   matched string, other than at its start, if such a value has been recorded. The
   fourth argument should point to an <b>uint32_t</b> variable. If there is no such
   value, 0 is returned.
   </P>
 <br><a name="SEC16" href="#TOC1">REFERENCE COUNTS</a><br>  <br><a name="SEC16" href="#TOC1">REFERENCE COUNTS</a><br>
 <P>  <P>
 <b>int pcre_refcount(pcre *<i>code</i>, int <i>adjust</i>);</b>  <b>int pcre_refcount(pcre *<i>code</i>, int <i>adjust</i>);</b>
Line 1373  is different. (This seems a highly unlikely scenario.) Line 1594  is different. (This seems a highly unlikely scenario.)
 <br><a name="SEC17" href="#TOC1">MATCHING A PATTERN: THE TRADITIONAL FUNCTION</a><br>  <br><a name="SEC17" href="#TOC1">MATCHING A PATTERN: THE TRADITIONAL FUNCTION</a><br>
 <P>  <P>
 <b>int pcre_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b>  <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>     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>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>);</b>
 </P>  </P>
 <P>  <P>
 The function <b>pcre_exec()</b> is called to match a subject string against a  The function <b>pcre_exec()</b> is called to match a subject string against a
Line 1437  fields (not necessarily in this order): Line 1658  fields (not necessarily in this order):
 </pre>  </pre>
 In the 16-bit version of this structure, the <i>mark</i> field has type  In the 16-bit version of this structure, the <i>mark</i> field has type
 "PCRE_UCHAR16 **".  "PCRE_UCHAR16 **".
   <br>
   <br>
   In the 32-bit version of this structure, the <i>mark</i> field has type
   "PCRE_UCHAR32 **".
 </P>  </P>
 <P>  <P>
The <i>flags</i> field is a bitmap that specifies which of the other fieldsThe <i>flags</i> field is used to specify which of the other fields are set. The
are set. The flag bits are:flag bits are:
 <pre>  <pre>
  PCRE_EXTRA_STUDY_DATA  PCRE_EXTRA_CALLOUT_DATA
   PCRE_EXTRA_EXECUTABLE_JIT    PCRE_EXTRA_EXECUTABLE_JIT
     PCRE_EXTRA_MARK
   PCRE_EXTRA_MATCH_LIMIT    PCRE_EXTRA_MATCH_LIMIT
   PCRE_EXTRA_MATCH_LIMIT_RECURSION    PCRE_EXTRA_MATCH_LIMIT_RECURSION
  PCRE_EXTRA_CALLOUT_DATA  PCRE_EXTRA_STUDY_DATA
   PCRE_EXTRA_TABLES    PCRE_EXTRA_TABLES
   PCRE_EXTRA_MARK  
 </pre>  </pre>
 Other flag bits should be set to zero. The <i>study_data</i> field and sometimes  Other flag bits should be set to zero. The <i>study_data</i> field and sometimes
 the <i>executable_jit</i> field are set in the <b>pcre_extra</b> block that is  the <i>executable_jit</i> field are set in the <b>pcre_extra</b> block that is
 returned by <b>pcre_study()</b>, together with the appropriate flag bits. You  returned by <b>pcre_study()</b>, together with the appropriate flag bits. You
should not set these yourself, but you may add to the block by setting theshould not set these yourself, but you may add to the block by setting other
other fields and their corresponding flag bits.fields and their corresponding flag bits.
 </P>  </P>
 <P>  <P>
 The <i>match_limit</i> field provides a means of preventing PCRE from using up a  The <i>match_limit</i> field provides a means of preventing PCRE from using up a
Line 1472  in the subject string. Line 1697  in the subject string.
 </P>  </P>
 <P>  <P>
 When <b>pcre_exec()</b> is called with a pattern that was successfully studied  When <b>pcre_exec()</b> is called with a pattern that was successfully studied
with the PCRE_STUDY_JIT_COMPILE option, the way that the matching is executedwith a JIT option, the way that the matching is executed is entirely different.
is entirely different. However, there is still the possibility of runawayHowever, there is still the possibility of runaway matching that goes on for a
matching that goes on for a very long time, and so the <i>match_limit</i> valuevery long time, and so the <i>match_limit</i> value is also used in this case
is also used in this case (but in a different way) to limit how long the(but in a different way) to limit how long the matching can continue.
matching can continue. 
 </P>  </P>
 <P>  <P>
 The default value for the limit can be set when PCRE is built; the default  The default value for the limit can be set when PCRE is built; the default
Line 1487  the <i>flags</i> field. If the limit is exceeded, <b>p Line 1711  the <i>flags</i> field. If the limit is exceeded, <b>p
 PCRE_ERROR_MATCHLIMIT.  PCRE_ERROR_MATCHLIMIT.
 </P>  </P>
 <P>  <P>
   A value for the match limit may also be supplied by an item at the start of a
   pattern of the form
   <pre>
     (*LIMIT_MATCH=d)
   </pre>
   where d is a decimal number. However, such a setting is ignored unless d is
   less than the limit set by the caller of <b>pcre_exec()</b> or, if no such limit
   is set, less than the default.
   </P>
   <P>
 The <i>match_limit_recursion</i> field is similar to <i>match_limit</i>, but  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  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  limits the depth of recursion. The recursion depth is a smaller number than the
Line 1497  This limit is of use only if it is set smaller than <i Line 1731  This limit is of use only if it is set smaller than <i
 Limiting the recursion depth limits the amount of machine stack that can be  Limiting the recursion depth limits the amount of machine stack that can be
 used, or, when PCRE has been compiled to use memory on the heap instead of the  used, or, when PCRE has been compiled to use memory on the heap instead of the
 stack, the amount of heap memory that can be used. This limit is not relevant,  stack, the amount of heap memory that can be used. This limit is not relevant,
and is ignored, if the pattern was successfully studied withand is ignored, when matching is done using JIT compiled code.
PCRE_STUDY_JIT_COMPILE. 
 </P>  </P>
 <P>  <P>
 The default value for <i>match_limit_recursion</i> can be set when PCRE is  The default value for <i>match_limit_recursion</i> can be set when PCRE is
Line 1509  PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the <i>flag Line 1742  PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the <i>flag
 is exceeded, <b>pcre_exec()</b> returns PCRE_ERROR_RECURSIONLIMIT.  is exceeded, <b>pcre_exec()</b> returns PCRE_ERROR_RECURSIONLIMIT.
 </P>  </P>
 <P>  <P>
   A value for the recursion limit may also be supplied by an item at the start of
   a pattern of the form
   <pre>
     (*LIMIT_RECURSION=d)
   </pre>
   where d is a decimal number. However, such a setting is ignored unless d is
   less than the limit set by the caller of <b>pcre_exec()</b> or, if no such limit
   is set, less than the default.
   </P>
   <P>
 The <i>callout_data</i> field is used in conjunction with the "callout" feature,  The <i>callout_data</i> field is used in conjunction with the "callout" feature,
 and is described in the  and is described in the
 <a href="pcrecallout.html"><b>pcrecallout</b></a>  <a href="pcrecallout.html"><b>pcrecallout</b></a>
 documentation.  documentation.
 </P>  </P>
 <P>  <P>
The <i>tables</i> field is used to pass a character tables pointer toThe <i>tables</i> field is provided for use with patterns that have been
<b>pcre_exec()</b>; this overrides the value that is stored with the compiledpre-compiled using custom character tables, saved to disc or elsewhere, and
pattern. A non-NULL value is stored with the compiled pattern only if customthen reloaded, because the tables that were used to compile a pattern are not
tables were supplied to <b>pcre_compile()</b> via its <i>tableptr</i> argument.saved with it. See the
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>  <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>
 <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  If PCRE_EXTRA_MARK is set in the <i>flags</i> field, the <i>mark</i> field must
 be set to point to a suitable variable. If the pattern contains any  be set to point to a suitable variable. If the pattern contains any
 backtracking control verbs such as (*MARK:NAME), and the execution ends up with  backtracking control verbs such as (*MARK:NAME), and the execution ends up with
Line 1549  Option bits for <b>pcre_exec()</b> Line 1797  Option bits for <b>pcre_exec()</b>
 The unused bits of the <i>options</i> argument for <b>pcre_exec()</b> must be  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>,  zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_<i>xxx</i>,
 PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART,  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART,
PCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_SOFT, andPCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_HARD, and
PCRE_PARTIAL_HARD.PCRE_PARTIAL_SOFT.
 </P>  </P>
 <P>  <P>
If the pattern was successfully studied with the PCRE_STUDY_JIT_COMPILE option,If the pattern was successfully studied with one of the just-in-time (JIT)
the only supported options for JIT execution are PCRE_NO_UTF8_CHECK,compile options, the only supported options for JIT execution are
PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, and PCRE_NOTEMPTY_ATSTART. Note inPCRE_NO_UTF8_CHECK, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY,
particular that partial matching is not supported. If an unsupported option isPCRE_NOTEMPTY_ATSTART, PCRE_PARTIAL_HARD, and PCRE_PARTIAL_SOFT. If an
used, JIT execution is disabled and the normal interpretive code inunsupported option is used, JIT execution is disabled and the normal
<b>pcre_exec()</b> is run.interpretive code in <b>pcre_exec()</b> is run.
 <pre>  <pre>
   PCRE_ANCHORED    PCRE_ANCHORED
 </pre>  </pre>
Line 1670  unanchored match must start with a specific character, Line 1918  unanchored match must start with a specific character,
 for that character, and fails immediately if it cannot find it, without  for that character, and fails immediately if it cannot find it, without
 actually running the main matching function. This means that a special item  actually running the main matching function. This means that a special item
 such as (*COMMIT) at the start of a pattern is not considered until after a  such as (*COMMIT) at the start of a pattern is not considered until after a
suitable starting point for the match has been found. When callouts or (*MARK)suitable starting point for the match has been found. Also, when callouts or
items are in use, these "start-up" optimizations can cause them to be skipped(*MARK) items are in use, these "start-up" optimizations can cause them to be
if the pattern is never actually used. The start-up optimizations are in effectskipped if the pattern is never actually used. The start-up optimizations are
a pre-scan of the subject that takes place before the pattern is run.in effect a pre-scan of the subject that takes place before the pattern is run.
 </P>  </P>
 <P>  <P>
 The PCRE_NO_START_OPTIMIZE option disables the start-up optimizations, possibly  The PCRE_NO_START_OPTIMIZE option disables the start-up optimizations, possibly
Line 1681  causing performance to suffer, but ensuring that in ca Line 1929  causing performance to suffer, but ensuring that in ca
 "no match", the callouts do occur, and that items such as (*COMMIT) and (*MARK)  "no match", the callouts do occur, and that items such as (*COMMIT) and (*MARK)
 are considered at every possible starting position in the subject string. If  are considered at every possible starting position in the subject string. If
 PCRE_NO_START_OPTIMIZE is set at compile time, it cannot be unset at matching  PCRE_NO_START_OPTIMIZE is set at compile time, it cannot be unset at matching
time.time. The use of PCRE_NO_START_OPTIMIZE at matching time (that is, passing it
 to <b>pcre_exec()</b>) disables JIT execution; in this situation, matching is
 always done using interpretively.
 </P>  </P>
 <P>  <P>
 Setting PCRE_NO_START_OPTIMIZE can change the outcome of a matching operation.  Setting PCRE_NO_START_OPTIMIZE can change the outcome of a matching operation.
Line 1715  returned. Line 1965  returned.
 </pre>  </pre>
 When PCRE_UTF8 is set at compile time, the validity of the subject as a UTF-8  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.  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 theThe entire string is checked before any other processing takes place. The value
start of a UTF-8 character. There is a discussion about the validity of UTF-8of <i>startoffset</i> is also checked to ensure that it points to the start of a
strings in theUTF-8 character. There is a discussion about the
 <a href="pcreunicode.html#utf8strings">validity of UTF-8 strings</a>
 in the
 <a href="pcreunicode.html"><b>pcreunicode</b></a>  <a href="pcreunicode.html"><b>pcreunicode</b></a>
 page. If an invalid sequence of bytes is found, <b>pcre_exec()</b> returns the  page. If an invalid sequence of bytes is found, <b>pcre_exec()</b> returns the
 error PCRE_ERROR_BADUTF8 or, if PCRE_PARTIAL_HARD is set and the problem is a  error PCRE_ERROR_BADUTF8 or, if PCRE_PARTIAL_HARD is set and the problem is a
Line 1739  all the matches in a single subject string. However, y Line 1991  all the matches in a single subject string. However, y
 the value of <i>startoffset</i> points to the start of a character (or the end  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  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  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>  <pre>
   PCRE_PARTIAL_HARD    PCRE_PARTIAL_HARD
   PCRE_PARTIAL_SOFT    PCRE_PARTIAL_SOFT
Line 1773  The string to be matched by <b>pcre_exec()</b> Line 2025  The string to be matched by <b>pcre_exec()</b>
 </b><br>  </b><br>
 <P>  <P>
 The subject string is passed to <b>pcre_exec()</b> as a pointer in  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<i>subject</i>, a length in <i>length</i>, and a starting offset in
in <i>startoffset</i>. If this is negative or greater than the length of the<i>startoffset</i>. The units for <i>length</i> and <i>startoffset</i> are bytes
subject, <b>pcre_exec()</b> returns PCRE_ERROR_BADOFFSET. When the startingfor the 8-bit library, 16-bit data items for the 16-bit library, and 32-bit
offset is zero, the search for a match starts at the beginning of the subject,data items for the 32-bit library.
and this is by far the most common case. In UTF-8 mode, the byte offset must 
point to the start of a UTF-8 character (or the end of the subject). Unlike the 
pattern string, the subject may contain binary zero bytes. 
 </P>  </P>
 <P>  <P>
   If <i>startoffset</i> is negative or greater than the length of the subject,
   <b>pcre_exec()</b> returns PCRE_ERROR_BADOFFSET. When the starting offset is
   zero, the search for a match starts at the beginning of the subject, and this
   is by far the most common case. In UTF-8 or UTF-16 mode, the offset must point
   to the start of a character, or the end of the subject (in UTF-32 mode, one
   data unit equals one character, so all offsets are valid). Unlike the pattern
   string, the subject may contain binary zeroes.
   </P>
   <P>
 A non-zero starting offset is useful when searching for another match in the  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.  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 <i>startoffset</i> differs from just passing over a shortened string and
Line 1847  rounded down. Line 2105  rounded down.
 When a match is successful, information about captured substrings is returned  When a match is successful, information about captured substrings is returned
 in pairs of integers, starting at the beginning of <i>ovector</i>, and  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  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, andeach pair is set to the offset of the first character in a substring, and the
the second is set to the byte offset of the first character after the end of asecond is set to the offset of the first character after the end of a
substring. <b>Note</b>: these values are always byte offsets, even in UTF-8substring. These values are always data unit offsets, even in UTF mode. They
mode. They are not character counts.are byte offsets in the 8-bit library, 16-bit data item offsets in the 16-bit
 library, and 32-bit data item offsets in the 32-bit library. <b>Note</b>: they
 are not character counts.
 </P>  </P>
 <P>  <P>
 The first pair of integers, <i>ovector[0]</i> and <i>ovector[1]</i>, identify the  The first pair of integers, <i>ovector[0]</i> and <i>ovector[1]</i>, identify the
Line 1868  string that it matched that is returned. Line 2128  string that it matched that is returned.
 <P>  <P>
 If the vector is too small to hold all the captured substring offsets, it is  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  used as far as possible (up to two-thirds of its length), and the function
returns a value of zero. If neither the actual string matched not any capturedreturns a value of zero. If neither the actual string matched nor any captured
 substrings are of interest, <b>pcre_exec()</b> may be called with <i>ovector</i>  substrings are of interest, <b>pcre_exec()</b> may be called with <i>ovector</i>
 passed as NULL and <i>ovecsize</i> as zero. However, if the pattern contains  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  back references and the <i>ovector</i> is not big enough to remember the related
Line 2067  time. Line 2327  time.
 <pre>  <pre>
   PCRE_ERROR_JIT_STACKLIMIT (-27)    PCRE_ERROR_JIT_STACKLIMIT (-27)
 </pre>  </pre>
This error is returned when a pattern that was successfully studied using theThis error is returned when a pattern that was successfully studied using a
PCRE_STUDY_JIT_COMPILE option is being matched, but the memory available forJIT compile option is being matched, but the memory available for the
the just-in-time processing stack is not large enough. See thejust-in-time processing stack is not large enough. See the
 <a href="pcrejit.html"><b>pcrejit</b></a>  <a href="pcrejit.html"><b>pcrejit</b></a>
 documentation for more details.  documentation for more details.
 <pre>  <pre>
  PCRE_ERROR_BADMODE (-28)  PCRE_ERROR_BADMODE        (-28)
 </pre>  </pre>
 This error is given if a pattern that was compiled by the 8-bit library is  This error is given if a pattern that was compiled by the 8-bit library is
passed to a 16-bit library function, or vice versa.passed to a 16-bit or 32-bit library function, or vice versa.
 <pre>  <pre>
  PCRE_ERROR_BADENDIANNESS (-29)  PCRE_ERROR_BADENDIANNESS  (-29)
 </pre>  </pre>
 This error is given if a pattern that was compiled and saved is reloaded on a  This error is given if a pattern that was compiled and saved is reloaded on a
 host with different endianness. The utility function  host with different endianness. The utility function
 <b>pcre_pattern_to_host_byte_order()</b> can be used to convert such a pattern  <b>pcre_pattern_to_host_byte_order()</b> can be used to convert such a pattern
 so that it runs on the new host.  so that it runs on the new host.
   <pre>
     PCRE_ERROR_JIT_BADOPTION
   </pre>
   This error is returned when a pattern that was successfully studied using a JIT
   compile option is being matched, but the matching mode (partial or complete
   match) does not correspond to any JIT compilation mode. When the JIT fast path
   function is used, this error may be also given for invalid options. See the
   <a href="pcrejit.html"><b>pcrejit</b></a>
   documentation for more details.
   <pre>
     PCRE_ERROR_BADLENGTH      (-32)
   </pre>
   This error is given if <b>pcre_exec()</b> is called with a negative value for
   the <i>length</i> argument.
 </P>  </P>
 <P>  <P>
Error numbers -16 to -20 and -22 are not used by <b>pcre_exec()</b>.Error numbers -16 to -20, -22, and 30 are not used by <b>pcre_exec()</b>.
 <a name="badutf8reasons"></a></P>  <a name="badutf8reasons"></a></P>
 <br><b>  <br><b>
 Reason codes for invalid UTF-8 strings  Reason codes for invalid UTF-8 strings
 </b><br>  </b><br>
 <P>  <P>
 This section applies only to the 8-bit library. The corresponding information  This section applies only to the 8-bit library. The corresponding information
for the 16-bit library is given in thefor the 16-bit and 32-bit libraries is given in the
 <a href="pcre16.html"><b>pcre16</b></a>  <a href="pcre16.html"><b>pcre16</b></a>
page.and
 <a href="pcre32.html"><b>pcre32</b></a>
 pages.
 </P>  </P>
 <P>  <P>
 When <b>pcre_exec()</b> returns either PCRE_ERROR_BADUTF8 or  When <b>pcre_exec()</b> returns either PCRE_ERROR_BADUTF8 or
Line 2166  character. Line 2442  character.
 </pre>  </pre>
 The first byte of a character has the value 0xfe or 0xff. These values can  The first byte of a character has the value 0xfe or 0xff. These values can
 never occur in a valid UTF-8 string.  never occur in a valid UTF-8 string.
   <pre>
     PCRE_UTF8_ERR22
   </pre>
   This error code was formerly used when the presence of a so-called
   "non-character" caused an error. Unicode corrigendum #9 makes it clear that
   such characters should not cause a string to be rejected, and so this code is
   no longer in use and is never returned.
 </P>  </P>
 <br><a name="SEC18" href="#TOC1">EXTRACTING CAPTURED SUBSTRINGS BY NUMBER</a><br>  <br><a name="SEC18" href="#TOC1">EXTRACTING CAPTURED SUBSTRINGS BY NUMBER</a><br>
 <P>  <P>
 <b>int pcre_copy_substring(const char *<i>subject</i>, int *<i>ovector</i>,</b>  <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>stringcount</i>, int <i>stringnumber</i>, char *<i>buffer</i>,</b>
<b>int <i>buffersize</i>);</b><b>     int <i>buffersize</i>);</b>
</P><br>
<P><br>
 <b>int pcre_get_substring(const char *<i>subject</i>, int *<i>ovector</i>,</b>  <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>     int <i>stringcount</i>, int <i>stringnumber</i>,</b>
<b>const char **<i>stringptr</i>);</b><b>     const char **<i>stringptr</i>);</b>
</P><br>
<P><br>
 <b>int pcre_get_substring_list(const char *<i>subject</i>,</b>  <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>
 <P>  <P>
 Captured substrings can be accessed directly by using the offsets returned by  Captured substrings can be accessed directly by using the offsets returned by
Line 2265  provided. Line 2548  provided.
 <br><a name="SEC19" href="#TOC1">EXTRACTING CAPTURED SUBSTRINGS BY NAME</a><br>  <br><a name="SEC19" href="#TOC1">EXTRACTING CAPTURED SUBSTRINGS BY NAME</a><br>
 <P>  <P>
 <b>int pcre_get_stringnumber(const pcre *<i>code</i>,</b>  <b>int pcre_get_stringnumber(const pcre *<i>code</i>,</b>
<b>const char *<i>name</i>);</b><b>     const char *<i>name</i>);</b>
</P><br>
<P><br>
 <b>int pcre_copy_named_substring(const pcre *<i>code</i>,</b>  <b>int pcre_copy_named_substring(const pcre *<i>code</i>,</b>
<b>const char *<i>subject</i>, int *<i>ovector</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>     int <i>stringcount</i>, const char *<i>stringname</i>,</b>
<b>char *<i>buffer</i>, int <i>buffersize</i>);</b><b>     char *<i>buffer</i>, int <i>buffersize</i>);</b>
</P><br>
<P><br>
 <b>int pcre_get_named_substring(const pcre *<i>code</i>,</b>  <b>int pcre_get_named_substring(const pcre *<i>code</i>,</b>
<b>const char *<i>subject</i>, int *<i>ovector</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>     int <i>stringcount</i>, const char *<i>stringname</i>,</b>
<b>const char **<i>stringptr</i>);</b><b>     const char **<i>stringptr</i>);</b>
 </P>  </P>
 <P>  <P>
 To extract a substring by name, you first have to find associated number.  To extract a substring by name, you first have to find associated number.
Line 2329  same number causes an error at compile time. Line 2612  same number causes an error at compile time.
 <br><a name="SEC20" href="#TOC1">DUPLICATE SUBPATTERN NAMES</a><br>  <br><a name="SEC20" href="#TOC1">DUPLICATE SUBPATTERN NAMES</a><br>
 <P>  <P>
 <b>int pcre_get_stringtable_entries(const pcre *<i>code</i>,</b>  <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>
 <P>  <P>
 When a pattern is compiled with the PCRE_DUPNAMES option, names for subpatterns  When a pattern is compiled with the PCRE_DUPNAMES option, names for subpatterns
Line 2410  the value returned is the size of each block that is o Line 2693  the value returned is the size of each block that is o
 <br><a name="SEC23" href="#TOC1">MATCHING A PATTERN: THE ALTERNATIVE FUNCTION</a><br>  <br><a name="SEC23" href="#TOC1">MATCHING A PATTERN: THE ALTERNATIVE FUNCTION</a><br>
 <P>  <P>
 <b>int pcre_dfa_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b>  <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>     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>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b>
<b>int *<i>workspace</i>, int <i>wscount</i>);</b><b>     int *<i>workspace</i>, int <i>wscount</i>);</b>
 </P>  </P>
 <P>  <P>
 The function <b>pcre_dfa_exec()</b> is called to match a subject string against  The function <b>pcre_dfa_exec()</b> is called to match a subject string against
Line 2541  matching string is given first. If there were too many Line 2824  matching string is given first. If there were too many
 the longest matches. Unlike <b>pcre_exec()</b>, <b>pcre_dfa_exec()</b> can use  the longest matches. Unlike <b>pcre_exec()</b>, <b>pcre_dfa_exec()</b> can use
 the entire <i>ovector</i> for returning matched strings.  the entire <i>ovector</i> for returning matched strings.
 </P>  </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>  <br><b>
 Error returns from <b>pcre_dfa_exec()</b>  Error returns from <b>pcre_dfa_exec()</b>
 </b><br>  </b><br>
Line 2581  When a recursive subpattern is processed, the matching Line 2873  When a recursive subpattern is processed, the matching
 recursively, using private vectors for <i>ovector</i> and <i>workspace</i>. This  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  error is given if the output vector is not large enough. This should be
 extremely rare, as a vector of size 1000 is used.  extremely rare, as a vector of size 1000 is used.
   <pre>
     PCRE_ERROR_DFA_BADRESTART (-30)
   </pre>
   When <b>pcre_dfa_exec()</b> is called with the <b>PCRE_DFA_RESTART</b> option,
   some plausibility checks are made on the contents of the workspace, which
   should contain data about the previous partial match. If any of these checks
   fail, this error is given.
 </P>  </P>
 <br><a name="SEC24" href="#TOC1">SEE ALSO</a><br>  <br><a name="SEC24" href="#TOC1">SEE ALSO</a><br>
 <P>  <P>
<b>pcre16</b>(3), <b>pcrebuild</b>(3), <b>pcrecallout</b>(3), <b>pcrecpp(3)</b>(3),<b>pcre16</b>(3), <b>pcre32</b>(3), <b>pcrebuild</b>(3), <b>pcrecallout</b>(3),
<b>pcrematching</b>(3), <b>pcrepartial</b>(3), <b>pcreposix</b>(3),<b>pcrecpp(3)</b>(3), <b>pcrematching</b>(3), <b>pcrepartial</b>(3),
<b>pcreprecompile</b>(3), <b>pcresample</b>(3), <b>pcrestack</b>(3).<b>pcreposix</b>(3), <b>pcreprecompile</b>(3), <b>pcresample</b>(3),
 <b>pcrestack</b>(3).
 </P>  </P>
 <br><a name="SEC25" href="#TOC1">AUTHOR</a><br>  <br><a name="SEC25" href="#TOC1">AUTHOR</a><br>
 <P>  <P>
Line 2599  Cambridge CB2 3QH, England. Line 2899  Cambridge CB2 3QH, England.
 </P>  </P>
 <br><a name="SEC26" href="#TOC1">REVISION</a><br>  <br><a name="SEC26" href="#TOC1">REVISION</a><br>
 <P>  <P>
Last updated: 21 January 2012Last updated: 12 November 2013
 <br>  <br>
Copyright &copy; 1997-2012 University of Cambridge.Copyright &copy; 1997-2013 University of Cambridge.
 <br>  <br>
 <p>  <p>
 Return to the <a href="index.html">PCRE index page</a>.  Return to the <a href="index.html">PCRE index page</a>.

Removed from v.1.1.1.2  
changed lines
  Added in v.1.1.1.5


FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>