embedaddon/pcre/doc/pcreapi.3 - diff

Return to pcreapi.3 CVS log

Up to [ELWIX - Embedded LightWeight unIX -] / embedaddon / pcre / doc

Diff for /embedaddon/pcre/doc/pcreapi.3 between versions 1.1.1.3 and 1.1.1.5

version 1.1.1.3, 2012/10/09 09:19:17	version 1.1.1.5, 2014/06/15 19:46:05
Line 1	Line 1
.TH PCREAPI 3 "04 May 2012" "PCRE 8.31"	.TH PCREAPI 3 "12 November 2013" "PCRE 8.34"
.SH NAME	.SH NAME
PCRE - Perl-compatible regular expressions	PCRE - Perl-compatible regular expressions
.sp	.sp
Line 8 PCRE - Perl-compatible regular expressions	Line 8 PCRE - Perl-compatible regular expressions
.SH "PCRE NATIVE API BASIC FUNCTIONS"	.SH "PCRE NATIVE API BASIC FUNCTIONS"
.rs	.rs
.sp	.sp
.SM	.nf
.B pcre pcre_compile(const char \fIpattern\fP, int \fIoptions\fP,	.B pcre pcre_compile(const char \fIpattern\fP, int \fIoptions\fP,
.ti +5n	.B " const char *\fIerrptr\fP, int \fIerroffset\fP,"
.B const char *\fIerrptr\fP, int \fIerroffset\fP,	.B " const unsigned char *\fItableptr\fP);"
.ti +5n	.sp
.B const unsigned char *\fItableptr\fP);
.PP
.B pcre pcre_compile2(const char \fIpattern\fP, int \fIoptions\fP,	.B pcre pcre_compile2(const char \fIpattern\fP, int \fIoptions\fP,
.ti +5n	.B " int *\fIerrorcodeptr\fP,"
.B int *\fIerrorcodeptr\fP,	.B " const char *\fIerrptr\fP, int \fIerroffset\fP,"
.ti +5n	.B " const unsigned char *\fItableptr\fP);"
.B const char *\fIerrptr\fP, int \fIerroffset\fP,	.sp
.ti +5n
.B const unsigned char *\fItableptr\fP);
.PP
.B pcre_extra pcre_study(const pcre \fIcode\fP, int \fIoptions\fP,	.B pcre_extra pcre_study(const pcre \fIcode\fP, int \fIoptions\fP,
.ti +5n	.B " const char **\fIerrptr\fP);"
.B const char **\fIerrptr\fP);	.B void pcre_free_study(pcre_extra *\fIextra\fP);
.PP
.B void pcre_free_study(pcre_extra *\fIextra\fP);	.B void pcre_free_study(pcre_extra *\fIextra\fP);
.PP	.sp
.B int pcre_exec(const pcre \fIcode\fP, "const pcre_extra \fIextra\fP,"	.B int pcre_exec(const pcre \fIcode\fP, "const pcre_extra \fIextra\fP,"
.ti +5n	.B " const char *\fIsubject\fP, int \fIlength\fP, int \fIstartoffset\fP,"
.B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,	.B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);"
.ti +5n	.sp
.B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);
.PP
.B int pcre_dfa_exec(const pcre \fIcode\fP, "const pcre_extra \fIextra\fP,"	.B int pcre_dfa_exec(const pcre \fIcode\fP, "const pcre_extra \fIextra\fP,"
.ti +5n	.B " const char *\fIsubject\fP, int \fIlength\fP, int \fIstartoffset\fP,"
.B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,	.B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP,"
.ti +5n	.B " int *\fIworkspace\fP, int \fIwscount\fP);"
.B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP,	.fi
.ti +5n
.B int *\fIworkspace\fP, int \fIwscount\fP);
.	.
.	.
.SH "PCRE NATIVE API STRING EXTRACTION FUNCTIONS"	.SH "PCRE NATIVE API STRING EXTRACTION FUNCTIONS"
.rs	.rs
.sp	.sp
	.nf
.B int pcre_copy_named_substring(const pcre *\fIcode\fP,	.B int pcre_copy_named_substring(const pcre *\fIcode\fP,
.ti +5n	.B " const char \fIsubject\fP, int \fIovector\fP,"
.B const char \fIsubject\fP, int \fIovector\fP,	.B " int \fIstringcount\fP, const char *\fIstringname\fP,"
.ti +5n	.B " char *\fIbuffer\fP, int \fIbuffersize\fP);"
.B int \fIstringcount\fP, const char *\fIstringname\fP,	.sp
.ti +5n
.B char *\fIbuffer\fP, int \fIbuffersize\fP);
.PP
.B int pcre_copy_substring(const char \fIsubject\fP, int \fIovector\fP,	.B int pcre_copy_substring(const char \fIsubject\fP, int \fIovector\fP,
.ti +5n	.B " int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP,"
.B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP,	.B " int \fIbuffersize\fP);"
.ti +5n	.sp
.B int \fIbuffersize\fP);
.PP
.B int pcre_get_named_substring(const pcre *\fIcode\fP,	.B int pcre_get_named_substring(const pcre *\fIcode\fP,
.ti +5n	.B " const char \fIsubject\fP, int \fIovector\fP,"
.B const char \fIsubject\fP, int \fIovector\fP,	.B " int \fIstringcount\fP, const char *\fIstringname\fP,"
.ti +5n	.B " const char **\fIstringptr\fP);"
.B int \fIstringcount\fP, const char *\fIstringname\fP,	.sp
.ti +5n
.B const char **\fIstringptr\fP);
.PP
.B int pcre_get_stringnumber(const pcre *\fIcode\fP,	.B int pcre_get_stringnumber(const pcre *\fIcode\fP,
.ti +5n	.B " const char *\fIname\fP);"
.B const char *\fIname\fP);	.B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,
.PP
.B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,	.B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,
.ti +5n	.B " const char \fIname\fP, char \fIfirst\fP, char *\fIlast\fP);"
.B const char \fIname\fP, char \fIfirst\fP, char *\fIlast\fP);	.B int pcre_get_substring(const char \fIsubject\fP, int \fIovector\fP,
.PP
.B int pcre_get_substring(const char \fIsubject\fP, int \fIovector\fP,	.B int pcre_get_substring(const char \fIsubject\fP, int \fIovector\fP,
.ti +5n	.B " int \fIstringcount\fP, int \fIstringnumber\fP,"
.B int \fIstringcount\fP, int \fIstringnumber\fP,	.B " const char **\fIstringptr\fP);"
.ti +5n	.sp
.B const char **\fIstringptr\fP);
.PP
.B int pcre_get_substring_list(const char *\fIsubject\fP,	.B int pcre_get_substring_list(const char *\fIsubject\fP,
.ti +5n	.B " int \fIovector\fP, int \fIstringcount\fP, const char **\fIlistptr\fP);"
.B int \fIovector\fP, int \fIstringcount\fP, "const char **\fIlistptr\fP);"	.B void pcre_free_substring(const char *\fIstringptr\fP);
.PP
.B void pcre_free_substring(const char *\fIstringptr\fP);	.B void pcre_free_substring(const char *\fIstringptr\fP);
.PP	.sp
.B void pcre_free_substring_list(const char **\fIstringptr\fP);	.B void pcre_free_substring_list(const char **\fIstringptr\fP);
	.fi
.	.
.	.
.SH "PCRE NATIVE API AUXILIARY FUNCTIONS"	.SH "PCRE NATIVE API AUXILIARY FUNCTIONS"
.rs	.rs
.sp	.sp
	.nf
	.B int pcre_jit_exec(const pcre \fIcode\fP, "const pcre_extra \fIextra\fP,"
	.B " const char *\fIsubject\fP, int \fIlength\fP, int \fIstartoffset\fP,"
	.B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP,"
	.B " pcre_jit_stack *\fIjstack\fP);"
	.sp
.B pcre_jit_stack *pcre_jit_stack_alloc(int \fIstartsize\fP, int \fImaxsize\fP);	.B pcre_jit_stack *pcre_jit_stack_alloc(int \fIstartsize\fP, int \fImaxsize\fP);
.PP	.sp
.B void pcre_jit_stack_free(pcre_jit_stack *\fIstack\fP);	.B void pcre_jit_stack_free(pcre_jit_stack *\fIstack\fP);
.PP	.sp
.B void pcre_assign_jit_stack(pcre_extra *\fIextra\fP,	.B void pcre_assign_jit_stack(pcre_extra *\fIextra\fP,
.ti +5n	.B " pcre_jit_callback \fIcallback\fP, void *\fIdata\fP);"
.B pcre_jit_callback \fIcallback\fP, void *\fIdata\fP);	.B const unsigned char *pcre_maketables(void);
.PP
.B const unsigned char *pcre_maketables(void);	.B const unsigned char *pcre_maketables(void);
.PP	.sp
.B int pcre_fullinfo(const pcre \fIcode\fP, "const pcre_extra \fIextra\fP,"	.B int pcre_fullinfo(const pcre \fIcode\fP, "const pcre_extra \fIextra\fP,"
.ti +5n	.B " int \fIwhat\fP, void *\fIwhere\fP);"
.B int \fIwhat\fP, void *\fIwhere\fP);	.B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);
.PP
.B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);	.B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);
.PP	.sp
.B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);	.B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);
.PP	.sp
.B const char *pcre_version(void);	.B const char *pcre_version(void);
.PP	.sp
.B int pcre_pattern_to_host_byte_order(pcre *\fIcode\fP,	.B int pcre_pattern_to_host_byte_order(pcre *\fIcode\fP,
.ti +5n	.B " pcre_extra \fIextra\fP, const unsigned char \fItables\fP);"
.B pcre_extra \fIextra\fP, const unsigned char \fItables\fP);	.
.	.
.	.
.SH "PCRE NATIVE API INDIRECTED FUNCTIONS"	.SH "PCRE NATIVE API INDIRECTED FUNCTIONS"
.rs	.rs
.sp	.sp
	.nf
.B void (pcre_malloc)(size_t);	.B void (pcre_malloc)(size_t);
.PP	.sp
.B void (pcre_free)(void );	.B void (pcre_free)(void );
.PP	.sp
.B void (pcre_stack_malloc)(size_t);	.B void (pcre_stack_malloc)(size_t);
.PP	.sp
.B void (pcre_stack_free)(void );	.B void (pcre_stack_free)(void );
.PP	.sp
.B int (pcre_callout)(pcre_callout_block );	.B int (pcre_callout)(pcre_callout_block );
	.fi
.	.
.	.
.SH "PCRE 8-BIT AND 16-BIT LIBRARIES"	.SH "PCRE 8-BIT, 16-BIT, AND 32-BIT LIBRARIES"
.rs	.rs
.sp	.sp
From release 8.30, PCRE can be compiled as a library for handling 16-bit	As 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 handles	strings (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 document	two additional libraries. They can be built as well as, or instead of, the
describes the 8-bit versions of the functions, with only occasional references	8-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
The 16-bit functions operate in the same way as their 8-bit counterparts; they	The 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 names	counterparts; they just use different data types for their arguments and
start with \fBpcre16_\fP instead of \fBpcre_\fP. For every option that has UTF8	results, and their names start with \fBpcre16_\fP or \fBpcre32_\fP instead of
in its name (for example, PCRE_UTF8), there is a corresponding 16-bit name with	\fBpcre_\fP. For every option that has UTF8 in its name (for example,
UTF8 replaced by UTF16. This facility is in fact just cosmetic; the 16-bit	PCRE_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
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, unless	16-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-bit	units and UTF-32 when using the 32-bit library, unless specified otherwise.
library are given in the	More details of the specific differences for the 16-bit and 32-bit libraries
	are given in the
.\" HREF	.\" HREF
\fBpcre16\fP	\fBpcre16\fP
.\"	.\"
page.	and
	.\" HREF
	\fBpcre32\fP
	.\"
	pages.
.	.
.	.
.SH "PCRE API OVERVIEW"	.SH "PCRE API OVERVIEW"
Line 213 used if available, by setting an option that is ignore	Line 205 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
\fBpcre_jit_stack_alloc()\fP, \fBpcre_jit_stack_free()\fP, and	\fBpcre_jit_stack_alloc()\fP, \fBpcre_jit_stack_free()\fP, and
\fBpcre_assign_jit_stack()\fP in order to control the JIT code's memory usage.	\fBpcre_assign_jit_stack()\fP in order to control the JIT code's memory usage.
These functions are discussed in the	.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
.\" HREF	.\" HREF
\fBpcrejit\fP	\fBpcrejit\fP
.\"	.\"
Line 392 not recognized. The following information is available	Line 386 not recognized. The following information is available
PCRE_CONFIG_UTF8	PCRE_CONFIG_UTF8
.sp	.sp
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 of	otherwise it is set to zero. This value should normally be given to the 8-bit
this function, \fBpcre16_config()\fP, the result is PCRE_ERROR_BADOPTION.	version of this function, \fBpcre_config()\fP. If it is given to the 16-bit
	or 32-bit version of this function, the result is PCRE_ERROR_BADOPTION.
.sp	.sp
PCRE_CONFIG_UTF16	PCRE_CONFIG_UTF16
.sp	.sp
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, \fBpcre16_config()\fP. If it is given to the 8-bit	version of this function, \fBpcre16_config()\fP. 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.
.sp	.sp
	PCRE_CONFIG_UTF32
	.sp
	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, \fBpcre32_config()\fP. If it is given to the 8-bit
	or 16-bit version of this function, the result is PCRE_ERROR_BADOPTION.
	.sp
PCRE_CONFIG_UNICODE_PROPERTIES	PCRE_CONFIG_UNICODE_PROPERTIES
.sp	.sp
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 422 unaligned)". If JIT support is not available, the resu	Line 424 unaligned)". If JIT support is not available, the resu
PCRE_CONFIG_NEWLINE	PCRE_CONFIG_NEWLINE
.sp	.sp
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 supported	that 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 EBCDIC	ANYCRLF, and -1 for ANY. In EBCDIC environments, CR, ANYCRLF, and ANY yield the
environments. The default should normally correspond to the standard sequence	same 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.
.sp	.sp
PCRE_CONFIG_BSR	PCRE_CONFIG_BSR
.sp	.sp
Line 440 or CRLF. The default can be overridden when a pattern	Line 444 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 most	a 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 expense	most 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.
.sp	.sp
PCRE_CONFIG_POSIX_MALLOC_THRESHOLD	PCRE_CONFIG_POSIX_MALLOC_THRESHOLD
.sp	.sp
Line 455 the	Line 460 the
.\"	.\"
documentation.	documentation.
.sp	.sp
	PCRE_CONFIG_PARENS_LIMIT
	.sp
	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.
	.sp
PCRE_CONFIG_MATCH_LIMIT	PCRE_CONFIG_MATCH_LIMIT
.sp	.sp
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 481 avoiding the use of the stack.	Line 493 avoiding the use of the stack.
.SH "COMPILING A PATTERN"	.SH "COMPILING A PATTERN"
.rs	.rs
.sp	.sp
	.nf
.B pcre pcre_compile(const char \fIpattern\fP, int \fIoptions\fP,	.B pcre pcre_compile(const char \fIpattern\fP, int \fIoptions\fP,
.ti +5n	.B " const char *\fIerrptr\fP, int \fIerroffset\fP,"
.B const char *\fIerrptr\fP, int \fIerroffset\fP,	.B " const unsigned char *\fItableptr\fP);"
.ti +5n
.B const unsigned char *\fItableptr\fP);
.sp	.sp
.B pcre pcre_compile2(const char \fIpattern\fP, int \fIoptions\fP,	.B pcre pcre_compile2(const char \fIpattern\fP, int \fIoptions\fP,
.ti +5n	.B " int *\fIerrorcodeptr\fP,"
.B int *\fIerrorcodeptr\fP,	.B " const char *\fIerrptr\fP, int \fIerroffset\fP,"
.ti +5n	.B " const unsigned char *\fItableptr\fP);"
.B const char *\fIerrptr\fP, int \fIerroffset\fP,	.fi
.ti +5n
.B const unsigned char *\fItableptr\fP);
.P	.P
Either of the functions \fBpcre_compile()\fP or \fBpcre_compile2()\fP can be	Either of the functions \fBpcre_compile()\fP or \fBpcre_compile2()\fP can be
called to compile a pattern into an internal form. The only difference between	called to compile a pattern into an internal form. The only difference between
Line 534 Otherwise, if compilation of a pattern fails, \fBpcre_	Line 543 Otherwise, if compilation of a pattern fails, \fBpcre_
NULL, and sets the variable pointed to by \fIerrptr\fP to point to a textual	NULL, and sets the variable pointed to by \fIerrptr\fP 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 the	data unit that was being processed when the error was discovered is placed in
variable pointed to by \fIerroffset\fP, which must not be NULL (if it is, an	the variable pointed to by \fIerroffset\fP, which must not be NULL (if it is,
immediate error is given). However, for an invalid UTF-8 string, the offset is	an 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
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 point	offset 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
If \fBpcre_compile2()\fP is used instead of \fBpcre_compile()\fP, and the	If \fBpcre_compile2()\fP is used instead of \fBpcre_compile()\fP, and the
\fIerrorcodeptr\fP argument is not NULL, a non-zero error code number is	\fIerrorcodeptr\fP argument is not NULL, a non-zero error code number is
Line 553 If the final argument, \fItableptr\fP, is NULL, PCRE u	Line 562 If the final argument, \fItableptr\fP, is NULL, PCRE u
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, \fItableptr\fP must be an address that is the result of a	locale. Otherwise, \fItableptr\fP must be an address that is the result of a
call to \fBpcre_maketables()\fP. This value is stored with the compiled	call to \fBpcre_maketables()\fP. This value is stored with the compiled
pattern, and used again by \fBpcre_exec()\fP, unless another table pointer is	pattern, and used again by \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP 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
This code fragment shows a typical straightforward call to \fBpcre_compile()\fP:	This code fragment shows a typical straightforward call to \fBpcre_compile()\fP:
.sp	.sp
Line 642 documentation.	Line 652 documentation.
.sp	.sp
PCRE_EXTENDED	PCRE_EXTENDED
.sp	.sp
If this bit is set, white space data characters in the pattern are totally	If this bit is set, most white space characters in the pattern are totally
ignored except when escaped or inside a character class. White space does not	ignored except when escaped or inside a character class. However, white space
include the VT character (code 11). In addition, characters between an	is not allowed within sequences such as (?> that introduce various
unescaped # outside a character class and the next newline, inclusive, are also	parenthesized 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 a	However, 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
	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
	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
Which characters are interpreted as newlines is controlled by the options	Which characters are interpreted as newlines is controlled by the options
passed to \fBpcre_compile()\fP or by a special sequence at the start of the	passed to \fBpcre_compile()\fP 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 713 binary zero character followed by z).	Line 733 binary zero character followed by z).
.sp	.sp
PCRE_MULTILINE	PCRE_MULTILINE
.sp	.sp
By default, PCRE treats the subject string as consisting of a single line of	By 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 of	even if it actually contains newlines. The "start of line" metacharacter (^)
line" metacharacter ($) matches only at the end of the string, or before a	matches only at the start of the string, and the "end of line" metacharacter
terminating newline (unless PCRE_DOLLAR_ENDONLY is set). This is the same as	($) 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
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
match immediately following or immediately before internal newlines in the	match immediately following or immediately before internal newlines in the
Line 727 equivalent to Perl's /m option, and it can be changed	Line 749 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.
.sp	.sp
	PCRE_NEVER_UTF
	.sp
	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.
	.sp
PCRE_NEWLINE_CR	PCRE_NEWLINE_CR
PCRE_NEWLINE_LF	PCRE_NEWLINE_LF
PCRE_NEWLINE_CRLF	PCRE_NEWLINE_CRLF
Line 739 indicated by a single character (CR or LF, respectivel	Line 770 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 newline	that any Unicode newline sequence should be recognized.
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
	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
	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
	.\" HREF
	\fBpcrebuild\fP
	.\"
	documentation.
	.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 770 were followed by ?: but named parentheses can still be	Line 813 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.
.sp	.sp
NO_START_OPTIMIZE	PCRE_NO_AUTO_POSSESS
.sp	.sp
	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.
	.sp
	PCRE_NO_START_OPTIMIZE
	.sp
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 \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP. If it is set at compile time,	for \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP. If it is set at compile time,
it is remembered with the compiled pattern and assumed at matching time. For	it is remembered with the compiled pattern and assumed at matching time. This
details see the discussion of PCRE_NO_START_OPTIMIZE	is necessary if you want to use JIT execution, because the JIT compiler needs
	to know whether or not this option is set. For details see the discussion of
	PCRE_NO_START_OPTIMIZE
.\" HTML <a href="#execoptions">	.\" HTML <a href="#execoptions">
.\" </a>	.\" </a>
below.	below.
Line 819 page.	Line 873 page.
.sp	.sp
PCRE_NO_UTF8_CHECK	PCRE_NO_UTF8_CHECK
.sp	.sp
When PCRE_UTF8 is set, the validity of the pattern as a UTF-8	When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is
string is automatically checked. There is a discussion about the	automatically checked. There is a discussion about the
.\" HTML <a href="pcreunicode.html#utf8strings">	.\" HTML <a href="pcreunicode.html#utf8strings">
.\" </a>	.\" </a>
validity of UTF-8 strings	validity of UTF-8 strings
Line 833 page. If an invalid UTF-8 sequence is found, \fBpcre_c	Line 887 page. If an invalid UTF-8 sequence is found, \fBpcre_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 also	undefined. It may cause your program to crash or loop. Note that this option
be passed to \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, to suppress the	can also be passed to \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, 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.
.	.
.	.
.SH "COMPILATION ERROR CODES"	.SH "COMPILATION ERROR CODES"
Line 844 validity checking of subject strings.	Line 900 validity checking of subject strings.
The following table lists the error codes than may be returned by	The following table lists the error codes than may be returned by
\fBpcre_compile2()\fP, along with the error messages that may be returned by	\fBpcre_compile2()\fP, 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 have	strings, 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.
.sp	.sp
0 no error	0 no error
1 \e at end of pattern	1 \e at end of pattern
Line 881 fallen out of use. To avoid confusion, they have not b	Line 937 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 \ex{...} sequence is too large	34 character value in \ex{} or \eo{} is too large
35 invalid condition (?(0)	35 invalid condition (?(0)
36 \eC not allowed in lookbehind assertion	36 \eC not allowed in lookbehind assertion
37 PCRE does not support \eL, \el, \eN{name}, \eU, or \eu	37 PCRE does not support \eL, \el, \eN{name}, \eU, or \eu
Line 909 fallen out of use. To avoid confusion, they have not b	Line 965 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 928 fallen out of use. To avoid confusion, they have not b	Line 984 fallen out of use. To avoid confusion, they have not b
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)	75 name is too long in (MARK), (PRUNE), (SKIP), or (THEN)
76 character value in \eu.... sequence is too large	76 character value in \eu.... 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 \ex{} (closing brace missing?)
	80 non-octal character in \eo{} (closing brace missing?)
	81 missing opening brace after \eo
	82 parentheses are too deeply nested
	83 invalid range in character class
.sp	.sp
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.
Line 937 be used if the limits were changed when PCRE was built	Line 1000 be used if the limits were changed when PCRE was built
.SH "STUDYING A PATTERN"	.SH "STUDYING A PATTERN"
.rs	.rs
.sp	.sp
.B pcre_extra pcre_study(const pcre \fIcode\fP, int \fIoptions\fP	.nf
.ti +5n	.B pcre_extra pcre_study(const pcre \fIcode\fP, int \fIoptions\fP,
.B const char **\fIerrptr\fP);	.B " const char **\fIerrptr\fP);"
	.fi
.PP	.PP
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
more time analyzing it in order to speed up the time taken for matching. The	more time analyzing it in order to speed up the time taken for matching. The
Line 960 below	Line 1024 below
in the section on matching a pattern.	in the section on matching a pattern.
.P	.P
If studying the pattern does not produce any useful information,	If studying the pattern does not produce any useful information,
\fBpcre_study()\fP returns NULL. In that circumstance, if the calling program	\fBpcre_study()\fP returns NULL by default. In that circumstance, if the
wants to pass any of the other fields to \fBpcre_exec()\fP or	calling program wants to pass any of the other fields to \fBpcre_exec()\fP or
\fBpcre_dfa_exec()\fP, it must set up its own \fBpcre_extra\fP block.	\fBpcre_dfa_exec()\fP, it must set up its own \fBpcre_extra\fP block. However,
	if \fBpcre_study()\fP is called with the PCRE_STUDY_EXTRA_NEEDED option, it
	returns a \fBpcre_extra\fP block even if studying did not find any additional
	information. It may still return NULL, however, if an error occurs in
	\fBpcre_study()\fP.
.P	.P
The second argument of \fBpcre_study()\fP contains option bits. There are three	The second argument of \fBpcre_study()\fP contains option bits. There are three
options:	further options in addition to PCRE_STUDY_EXTRA_NEEDED:
.sp	.sp
PCRE_STUDY_JIT_COMPILE	PCRE_STUDY_JIT_COMPILE
PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE	PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE
Line 974 options:	Line 1042 options:
If any of these are set, and the just-in-time compiler is available, the	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	pattern is further compiled into machine code that executes much faster than
the \fBpcre_exec()\fP interpretive matching function. If the just-in-time	the \fBpcre_exec()\fP interpretive matching function. If the just-in-time
compiler is not available, these options are ignored. All other bits in the	compiler is not available, these options are ignored. All undefined bits in the
\fIoptions\fP argument must be zero.	\fIoptions\fP argument must be zero.
.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 1022 real application there should be tests for errors):	Line 1090 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 by	guarantee that no shorter strings match. The value is used to avoid wasting
\fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP to avoid wasting time by trying to	time 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 value	find out the value in a calling program via the \fBpcre_fullinfo()\fP function.
in a calling program via the \fBpcre_fullinfo()\fP function.
.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
These two optimizations apply to both \fBpcre_exec()\fP and	These two optimizations apply to both \fBpcre_exec()\fP and
\fBpcre_dfa_exec()\fP, and the information is also used by the JIT compiler.	\fBpcre_dfa_exec()\fP, and the information is also used by the JIT compiler.
The optimizations can be disabled by setting the PCRE_NO_START_OPTIMIZE option	The optimizations can be disabled by setting the PCRE_NO_START_OPTIMIZE option.
when calling \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP, but if this is done,	You might want to do this if your pattern contains callouts or (*MARK) and you
JIT execution is also disabled. You might want to do this if your pattern	want to make use of these facilities in cases where matching fails.
contains callouts or (*MARK) and you want to make use of these facilities in	.P
cases where matching fails. See the discussion of PCRE_NO_START_OPTIMIZE	PCRE_NO_START_OPTIMIZE can be specified at either compile time or execution
	time. However, if PCRE_NO_START_OPTIMIZE is passed to \fBpcre_exec()\fP, (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
	There is a longer discussion of PCRE_NO_START_OPTIMIZE
.\" HTML <a href="#execoptions">	.\" HTML <a href="#execoptions">
.\" </a>	.\" </a>
below.	below.
Line 1051 below.	Line 1125 below.
.sp	.sp
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 characters	code 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 escapes	applies only to characters with code points less than 256. By default,
such as \ew or \ed, but they can be tested with \ep if PCRE is built with	higher-valued code points never match escapes such as \ew or \ed. However, if
Unicode character property support. Alternatively, the PCRE_UCP option can be	PCRE is built with Unicode property support, all characters can be tested with
set at compile time; this causes \ew and friends to use Unicode property	\ep and \eP, or, alternatively, the PCRE_UCP option can be set when a pattern
support instead of built-in tables. The use of locales with Unicode is	is compiled; this causes \ew and friends to use Unicode property support
discouraged. If you are handling characters with codes greater than 128, you	instead of the built-in tables.
should either use UTF-8 and Unicode, or use locales, but not try to mix the
two.
.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
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 \fBpcre_compile()\fP is NULL. These are sufficient for many applications.	of \fBpcre_compile()\fP 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 1074 for this locale support is expected to die away.	Line 1150 for this locale support is expected to die away.
.P	.P
External tables are built by calling the \fBpcre_maketables()\fP function,	External tables are built by calling the \fBpcre_maketables()\fP 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 \fBpcre_compile()\fP or \fBpcre_exec()\fP as often as necessary. For	to \fBpcre_compile()\fP as often as necessary. For example, to build and use
example, to build and use tables that are appropriate for the French locale	tables 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:
.sp	.sp
setlocale(LC_CTYPE, "fr_FR");	setlocale(LC_CTYPE, "fr_FR");
tables = pcre_maketables();	tables = pcre_maketables();
Line 1093 needed.	Line 1169 needed.
.P	.P
The pointer that is passed to \fBpcre_compile()\fP is saved with the compiled	The pointer that is passed to \fBpcre_compile()\fP is saved with the compiled
pattern, and the same tables are used via this pointer by \fBpcre_study()\fP	pattern, and the same tables are used via this pointer by \fBpcre_study()\fP
and normally also by \fBpcre_exec()\fP. Thus, by default, for any single	and also by \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP. 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
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 \fBpcre_exec()\fP. Although not intended for this purpose,	internal tables) to \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP (see the
this facility could be used to match a pattern in a different locale from the	discussion below in the section on matching a pattern). This facility is
one in which it was compiled. Passing table pointers at run time is discussed	provided 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.
.	.
.	.
.\" HTML <a name="infoaboutpattern"></a>	.\" HTML <a name="infoaboutpattern"></a>
.SH "INFORMATION ABOUT A PATTERN"	.SH "INFORMATION ABOUT A PATTERN"
.rs	.rs
.sp	.sp
	.nf
.B int pcre_fullinfo(const pcre \fIcode\fP, "const pcre_extra \fIextra\fP,"	.B int pcre_fullinfo(const pcre \fIcode\fP, "const pcre_extra \fIextra\fP,"
.ti +5n	.B " int \fIwhat\fP, void *\fIwhere\fP);"
.B int \fIwhat\fP, void *\fIwhere\fP);	.PP
.PP	.PP
The \fBpcre_fullinfo()\fP function returns information about a compiled	The \fBpcre_fullinfo()\fP function returns information about a compiled
pattern. It replaces the \fBpcre_info()\fP function, which was removed from the	pattern. It replaces the \fBpcre_info()\fP function, which was removed from the
Line 1129 the following negative numbers:	Line 1210 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 \fIwhat\fP was invalid	PCRE_ERROR_BADOPTION the value of \fIwhat\fP was invalid
	PCRE_ERROR_UNSET the requested field is not set
.sp	.sp
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 1175 variable.	Line 1257 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 to	value 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
If there is no fixed first value, and if either	If there is no fixed first value, and if either
.sp	.sp
Line 1189 starts with "^", or	Line 1271 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
	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.
.sp	.sp
PCRE_INFO_FIRSTTABLE	PCRE_INFO_FIRSTTABLE
.sp	.sp
Line 1236 value, -1 is returned. For anchored patterns, a last l	Line 1323 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\ed+z\ed+/ the returned value is "z", but for /^a\edz\ed/ the returned value	/^a\ed+z\ed+/ the returned value is "z", but for /^a\edz\ed/ the returned value
is -1.	is -1.
	.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.
.sp	.sp
	PCRE_INFO_MATCH_EMPTY
	.sp
	Return 1 if the pattern can match an empty string, otherwise 0. The fourth
	argument should point to an \fBint\fP variable.
	.sp
	PCRE_INFO_MATCHLIMIT
	.sp
	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 \fBpcre_fullinfo()\fP returns the error PCRE_ERROR_UNSET.
	.sp
PCRE_INFO_MAXLOOKBEHIND	PCRE_INFO_MAXLOOKBEHIND
.sp	.sp
Return the number of characters (NB not bytes) in the longest lookbehind	Return the number of characters (NB not data units) in the longest lookbehind
assertion in the pattern. Note that the simple assertions \eb and \eB require a	assertion in the pattern. This information is useful when doing multi-segment
one-character lookbehind. This information is useful when doing multi-segment	matching using the partial matching facilities. Note that the simple assertions
matching using the partial matching facilities.	\eb and \eB require a one-character lookbehind. \eA 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, \eA might match incorrectly at the start of a new
	segment.
.sp	.sp
PCRE_INFO_MINLENGTH	PCRE_INFO_MINLENGTH
.sp	.sp
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 the	value is a number of characters, which in UTF mode may be different from the
number of bytes. The fourth argument should point to an \fBint\fP variable. A	number of data units. The fourth argument should point to an \fBint\fP
non-negative value is a lower bound to the length of any matching string. There	variable. 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 string	string. 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.
.sp	.sp
PCRE_INFO_NAMECOUNT	PCRE_INFO_NAMECOUNT
PCRE_INFO_NAMEENTRYSIZE	PCRE_INFO_NAMEENTRYSIZE
Line 1275 length of the longest name. PCRE_INFO_NAMETABLE return	Line 1384 length of the longest name. PCRE_INFO_NAMETABLE return
entry of the table. This is a pointer to \fBchar\fP in the 8-bit library, where	entry of the table. This is a pointer to \fBchar\fP 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 rest	16-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
The names are in alphabetical order. Duplicate names may appear if (?\| is used	The names are in alphabetical order. If (?\| is used to create multiple groups
to create multiple groups with the same number, as described in the	with the same number, as described in the
.\" HTML <a href="pcrepattern.html#dupsubpatternnumber">	.\" HTML <a href="pcrepattern.html#dupsubpatternnumber">
.\" </a>	.\" </a>
section on duplicate subpattern numbers	section on duplicate subpattern numbers
Line 1288 in the	Line 1399 in the
.\" HREF	.\" HREF
\fBpcrepattern\fP	\fBpcrepattern\fP
.\"	.\"
page. Duplicate names for subpatterns with different numbers are permitted only	page, 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 the	table. 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 of	Duplicate names for subpatterns with different numbers are permitted,
(?\| this is the order of increasing number; when (?\| is used this is not	but 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
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
after compilation by the 8-bit library (assume PCRE_EXTENDED is set, so white	after compilation by the 8-bit library (assume PCRE_EXTENDED is set, so white
Line 1349 alternatives begin with one of the following:	Line 1462 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
\fBpcre_fullinfo()\fP.	\fBpcre_fullinfo()\fP.
.sp	.sp
	PCRE_INFO_RECURSIONLIMIT
	.sp
	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 \fBpcre_fullinfo()\fP returns the error PCRE_ERROR_UNSET.
	.sp
PCRE_INFO_SIZE	PCRE_INFO_SIZE
.sp	.sp
Return the size of the compiled pattern in bytes (for both libraries). The	Return the size of the compiled pattern in bytes (for all three libraries). The
fourth argument should point to a \fBsize_t\fP variable. This value does not	fourth argument should point to a \fBsize_t\fP variable. This value does not
include the size of the \fBpcre\fP structure that is returned by	include the size of the \fBpcre\fP structure that is returned by
\fBpcre_compile()\fP. The value that is passed as the argument to	\fBpcre_compile()\fP. The value that is passed as the argument to
Line 1362 does not alter the value returned by this option.	Line 1482 does not alter the value returned by this option.
.sp	.sp
PCRE_INFO_STUDYSIZE	PCRE_INFO_STUDYSIZE
.sp	.sp
Return the size in bytes of the data block pointed to by the \fIstudy_data\fP	Return the size in bytes (for all three libraries) of the data block pointed to
field in a \fBpcre_extra\fP block. If \fBpcre_extra\fP is NULL, or there is no	by the \fIstudy_data\fP field in a \fBpcre_extra\fP block. If \fBpcre_extra\fP
study data, zero is returned. The fourth argument should point to a	is NULL, or there is no study data, zero is returned. The fourth argument
\fBsize_t\fP variable. The \fIstudy_data\fP field is set by \fBpcre_study()\fP	should point to a \fBsize_t\fP variable. The \fIstudy_data\fP field is set by
to record information that will speed up matching (see the section entitled	\fBpcre_study()\fP to record information that will speed up matching (see the
	section entitled
.\" HTML <a href="#studyingapattern">	.\" HTML <a href="#studyingapattern">
.\" </a>	.\" </a>
"Studying a pattern"	"Studying a pattern"
Line 1377 is made available via this option so that it can be sa	Line 1498 is made available via this option so that it can be sa
\fBpcreprecompile\fP	\fBpcreprecompile\fP
.\"	.\"
documentation for details).	documentation for details).
	.sp
	PCRE_INFO_FIRSTCHARACTERFLAGS
	.sp
	Return information about the first data unit of any matched string, for a
	non-anchored pattern. The fourth argument should point to an \fBint\fP
	variable.
	.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
	If there is no fixed first value, and if either
	.sp
	(a) the pattern was compiled with the PCRE_MULTILINE option, and every branch
	starts with "^", or
	.sp
	(b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set
	(if it were set, the pattern would be anchored),
	.sp
	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.
	.sp
	PCRE_INFO_FIRSTCHARACTER
	.sp
	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 \fBuint_t\fP variable.
	.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.
	.sp
	PCRE_INFO_REQUIREDCHARFLAGS
	.sp
	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 \fBint\fP 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
	For anchored patterns, a last literal value is recorded only if it follows
	something of variable length. For example, for the pattern /^a\ed+z\ed+/ the
	returned value 1 (with "z" returned from PCRE_INFO_REQUIREDCHAR), but for
	/^a\edz\ed/ the returned value is 0.
	.sp
	PCRE_INFO_REQUIREDCHAR
	.sp
	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 \fBuint32_t\fP variable. If there is no such
	value, 0 is returned.
.	.
.	.
.SH "REFERENCE COUNTS"	.SH "REFERENCE COUNTS"
Line 1405 is different. (This seems a highly unlikely scenario.)	Line 1577 is different. (This seems a highly unlikely scenario.)
.SH "MATCHING A PATTERN: THE TRADITIONAL FUNCTION"	.SH "MATCHING A PATTERN: THE TRADITIONAL FUNCTION"
.rs	.rs
.sp	.sp
	.nf
.B int pcre_exec(const pcre \fIcode\fP, "const pcre_extra \fIextra\fP,"	.B int pcre_exec(const pcre \fIcode\fP, "const pcre_extra \fIextra\fP,"
.ti +5n	.B " const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
.B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,	.B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);"
.ti +5n	.fi
.B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);
.P	.P
The function \fBpcre_exec()\fP is called to match a subject string against a	The function \fBpcre_exec()\fP is called to match a subject string against a
compiled pattern, which is passed in the \fIcode\fP argument. If the	compiled pattern, which is passed in the \fIcode\fP argument. If the
Line 1473 fields (not necessarily in this order):	Line 1645 fields (not necessarily in this order):
.sp	.sp
In the 16-bit version of this structure, the \fImark\fP field has type	In the 16-bit version of this structure, the \fImark\fP field has type
"PCRE_UCHAR16 **".	"PCRE_UCHAR16 **".
	.sp
	In the 32-bit version of this structure, the \fImark\fP field has type
	"PCRE_UCHAR32 **".
.P	.P
The \fIflags\fP field is used to specify which of the other fields are set. The	The \fIflags\fP field is used to specify which of the other fields are set. The
flag bits are:	flag bits are:
Line 1516 block in which \fImatch_limit\fP is set, and PCRE_EXTR	Line 1691 block in which \fImatch_limit\fP is set, and PCRE_EXTR
the \fIflags\fP field. If the limit is exceeded, \fBpcre_exec()\fP returns	the \fIflags\fP field. If the limit is exceeded, \fBpcre_exec()\fP returns
PCRE_ERROR_MATCHLIMIT.	PCRE_ERROR_MATCHLIMIT.
.P	.P
	A value for the match limit may also be supplied by an item at the start of a
	pattern of the form
	.sp
	(*LIMIT_MATCH=d)
	.sp
	where d is a decimal number. However, such a setting is ignored unless d is
	less than the limit set by the caller of \fBpcre_exec()\fP or, if no such limit
	is set, less than the default.
	.P
The \fImatch_limit_recursion\fP field is similar to \fImatch_limit\fP, but	The \fImatch_limit_recursion\fP field is similar to \fImatch_limit\fP, but
instead of limiting the total number of times that \fBmatch()\fP is called, it	instead of limiting the total number of times that \fBmatch()\fP 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 1534 with a \fBpcre_extra\fP block in which \fImatch_limit_	Line 1718 with a \fBpcre_extra\fP block in which \fImatch_limit_
PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the \fIflags\fP field. If the limit	PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the \fIflags\fP field. If the limit
is exceeded, \fBpcre_exec()\fP returns PCRE_ERROR_RECURSIONLIMIT.	is exceeded, \fBpcre_exec()\fP returns PCRE_ERROR_RECURSIONLIMIT.
.P	.P
	A value for the recursion limit may also be supplied by an item at the start of
	a pattern of the form
	.sp
	(*LIMIT_RECURSION=d)
	.sp
	where d is a decimal number. However, such a setting is ignored unless d is
	less than the limit set by the caller of \fBpcre_exec()\fP or, if no such limit
	is set, less than the default.
	.P
The \fIcallout_data\fP field is used in conjunction with the "callout" feature,	The \fIcallout_data\fP field is used in conjunction with the "callout" feature,
and is described in the	and is described in the
.\" HREF	.\" HREF
Line 1541 and is described in the	Line 1734 and is described in the
.\"	.\"
documentation.	documentation.
.P	.P
The \fItables\fP field is used to pass a character tables pointer to	The \fItables\fP field is provided for use with patterns that have been
\fBpcre_exec()\fP; this overrides the value that is stored with the compiled	pre-compiled using custom character tables, saved to disc or elsewhere, and
pattern. A non-NULL value is stored with the compiled pattern only if custom	then reloaded, because the tables that were used to compile a pattern are not
tables were supplied to \fBpcre_compile()\fP via its \fItableptr\fP argument.	saved with it. See the
If NULL is passed to \fBpcre_exec()\fP 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 \fBpcre_exec()\fP is
called. See the
.\" HREF	.\" HREF
\fBpcreprecompile\fP	\fBpcreprecompile\fP
.\"	.\"
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
	\fBWarning:\fP The tables that \fBpcre_exec()\fP uses must be the same as those
	that were used when the pattern was compiled. If this is not the case, the
	behaviour of \fBpcre_exec()\fP 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 \fBpcre_compile()\fP to \fBpcre_exec()\fP.
	.P
If PCRE_EXTRA_MARK is set in the \fIflags\fP field, the \fImark\fP field must	If PCRE_EXTRA_MARK is set in the \fIflags\fP field, the \fImark\fP 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 1699 unanchored match must start with a specific character,	Line 1896 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 effect	skipped 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
The PCRE_NO_START_OPTIMIZE option disables the start-up optimizations, possibly	The PCRE_NO_START_OPTIMIZE option disables the start-up optimizations, possibly
causing performance to suffer, but ensuring that in cases where the result is	causing performance to suffer, but ensuring that in cases where the result is
"no match", the callouts do occur, and that items such as (COMMIT) and (MARK)	"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. The use of PCRE_NO_START_OPTIMIZE disables JIT execution; when it is set,	time. The use of PCRE_NO_START_OPTIMIZE at matching time (that is, passing it
matching is always done using interpretively.	to \fBpcre_exec()\fP) disables JIT execution; in this situation, matching is
	always done using interpretively.
.P	.P
Setting PCRE_NO_START_OPTIMIZE can change the outcome of a matching operation.	Setting PCRE_NO_START_OPTIMIZE can change the outcome of a matching operation.
Consider the pattern	Consider the pattern
Line 1776 all the matches in a single subject string. However, y	Line 1974 all the matches in a single subject string. However, y
the value of \fIstartoffset\fP points to the start of a character (or the end	the value of \fIstartoffset\fP 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 \fIstartoffset\fP is	invalid string as a subject or an invalid value of \fIstartoffset\fP is
undefined. Your program may crash.	undefined. Your program may crash or loop.
.sp	.sp
PCRE_PARTIAL_HARD	PCRE_PARTIAL_HARD
PCRE_PARTIAL_SOFT	PCRE_PARTIAL_SOFT
Line 1810 documentation.	Line 2008 documentation.
.rs	.rs
.sp	.sp
The subject string is passed to \fBpcre_exec()\fP as a pointer in	The subject string is passed to \fBpcre_exec()\fP as a pointer in
\fIsubject\fP, a length in bytes in \fIlength\fP, and a starting byte offset	\fIsubject\fP, a length in \fIlength\fP, and a starting offset in
in \fIstartoffset\fP. If this is negative or greater than the length of the	\fIstartoffset\fP. The units for \fIlength\fP and \fIstartoffset\fP are bytes
subject, \fBpcre_exec()\fP returns PCRE_ERROR_BADOFFSET. When the starting	for 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
	If \fIstartoffset\fP is negative or greater than the length of the subject,
	\fBpcre_exec()\fP 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
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 \fBpcre_exec()\fP again after a previous success.	same subject by calling \fBpcre_exec()\fP again after a previous success.
Setting \fIstartoffset\fP differs from just passing over a shortened string and	Setting \fIstartoffset\fP differs from just passing over a shortened string and
Line 1880 rounded down.	Line 2083 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 \fIovector\fP, and	in pairs of integers, starting at the beginning of \fIovector\fP, 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, and	each 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 a	second is set to the offset of the first character after the end of a
substring. \fBNote\fP: these values are always byte offsets, even in UTF-8	substring. 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. \fBNote\fP: they
	are not character counts.
.P	.P
The first pair of integers, \fIovector[0]\fP and \fIovector[1]\fP, identify the	The first pair of integers, \fIovector[0]\fP and \fIovector[1]\fP, identify the
portion of the subject string matched by the entire pattern. The next pair is	portion of the subject string matched by the entire pattern. The next pair is
Line 2109 documentation for more details.	Line 2314 documentation for more details.
PCRE_ERROR_BADMODE (-28)	PCRE_ERROR_BADMODE (-28)
.sp	.sp
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.
.sp	.sp
PCRE_ERROR_BADENDIANNESS (-29)	PCRE_ERROR_BADENDIANNESS (-29)
.sp	.sp
Line 2117 This error is given if a pattern that was compiled and	Line 2322 This error is given if a pattern that was compiled and
host with different endianness. The utility function	host with different endianness. The utility function
\fBpcre_pattern_to_host_byte_order()\fP can be used to convert such a pattern	\fBpcre_pattern_to_host_byte_order()\fP can be used to convert such a pattern
so that it runs on the new host.	so that it runs on the new host.
	.sp
	PCRE_ERROR_JIT_BADOPTION
	.sp
	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
	.\" HREF
	\fBpcrejit\fP
	.\"
	documentation for more details.
	.sp
	PCRE_ERROR_BADLENGTH (-32)
	.sp
	This error is given if \fBpcre_exec()\fP is called with a negative value for
	the \fIlength\fP argument.
.P	.P
Error numbers -16 to -20, -22, and -30 are not used by \fBpcre_exec()\fP.	Error numbers -16 to -20, -22, and 30 are not used by \fBpcre_exec()\fP.
.	.
.	.
.\" HTML <a name="badutf8reasons"></a>	.\" HTML <a name="badutf8reasons"></a>
Line 2126 Error numbers -16 to -20, -22, and -30 are not used by	Line 2347 Error numbers -16 to -20, -22, and -30 are not used by
.rs	.rs
.sp	.sp
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 the	for the 16-bit and 32-bit libraries is given in the
.\" HREF	.\" HREF
\fBpcre16\fP	\fBpcre16\fP
.\"	.\"
page.	and
	.\" HREF
	\fBpcre32\fP
	.\"
	pages.
.P	.P
When \fBpcre_exec()\fP returns either PCRE_ERROR_BADUTF8 or	When \fBpcre_exec()\fP returns either PCRE_ERROR_BADUTF8 or
PCRE_ERROR_SHORTUTF8, and the size of the output vector (\fIovecsize\fP) is at	PCRE_ERROR_SHORTUTF8, and the size of the output vector (\fIovecsize\fP) is at
Line 2200 character.	Line 2425 character.
.sp	.sp
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.
	.sp
	PCRE_UTF8_ERR22
	.sp
	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.
.	.
.	.
.SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"	.SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
.rs	.rs
.sp	.sp
	.nf
.B int pcre_copy_substring(const char \fIsubject\fP, int \fIovector\fP,	.B int pcre_copy_substring(const char \fIsubject\fP, int \fIovector\fP,
.ti +5n	.B " int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP,"
.B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP,	.B " int \fIbuffersize\fP);"
.ti +5n	.sp
.B int \fIbuffersize\fP);
.PP
.B int pcre_get_substring(const char \fIsubject\fP, int \fIovector\fP,	.B int pcre_get_substring(const char \fIsubject\fP, int \fIovector\fP,
.ti +5n	.B " int \fIstringcount\fP, int \fIstringnumber\fP,"
.B int \fIstringcount\fP, int \fIstringnumber\fP,	.B " const char **\fIstringptr\fP);"
.ti +5n	.sp
.B const char **\fIstringptr\fP);
.PP
.B int pcre_get_substring_list(const char *\fIsubject\fP,	.B int pcre_get_substring_list(const char *\fIsubject\fP,
.ti +5n	.B " int \fIovector\fP, int \fIstringcount\fP, const char **\fIlistptr\fP);"
.B int \fIovector\fP, int \fIstringcount\fP, "const char **\fIlistptr\fP);"	.PP
.PP	.PP
Captured substrings can be accessed directly by using the offsets returned by	Captured substrings can be accessed directly by using the offsets returned by
\fBpcre_exec()\fP in \fIovector\fP. For convenience, the functions	\fBpcre_exec()\fP in \fIovector\fP. For convenience, the functions
Line 2298 provided.	Line 2527 provided.
.SH "EXTRACTING CAPTURED SUBSTRINGS BY NAME"	.SH "EXTRACTING CAPTURED SUBSTRINGS BY NAME"
.rs	.rs
.sp	.sp
	.nf
.B int pcre_get_stringnumber(const pcre *\fIcode\fP,	.B int pcre_get_stringnumber(const pcre *\fIcode\fP,
.ti +5n	.B " const char *\fIname\fP);"
.B const char *\fIname\fP);	.B int pcre_copy_named_substring(const pcre *\fIcode\fP,
.PP
.B int pcre_copy_named_substring(const pcre *\fIcode\fP,	.B int pcre_copy_named_substring(const pcre *\fIcode\fP,
.ti +5n	.B " const char \fIsubject\fP, int \fIovector\fP,"
.B const char \fIsubject\fP, int \fIovector\fP,	.B " int \fIstringcount\fP, const char *\fIstringname\fP,"
.ti +5n	.B " char *\fIbuffer\fP, int \fIbuffersize\fP);"
.B int \fIstringcount\fP, const char *\fIstringname\fP,	.sp
.ti +5n
.B char *\fIbuffer\fP, int \fIbuffersize\fP);
.PP
.B int pcre_get_named_substring(const pcre *\fIcode\fP,	.B int pcre_get_named_substring(const pcre *\fIcode\fP,
.ti +5n	.B " const char \fIsubject\fP, int \fIovector\fP,"
.B const char \fIsubject\fP, int \fIovector\fP,	.B " int \fIstringcount\fP, const char *\fIstringname\fP,"
.ti +5n	.B " const char **\fIstringptr\fP);"
.B int \fIstringcount\fP, const char *\fIstringname\fP,	.fi
.ti +5n
.B const char **\fIstringptr\fP);
.PP	.PP
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.
For example, for this pattern	For example, for this pattern
Line 2368 same number causes an error at compile time.	Line 2592 same number causes an error at compile time.
.SH "DUPLICATE SUBPATTERN NAMES"	.SH "DUPLICATE SUBPATTERN NAMES"
.rs	.rs
.sp	.sp
	.nf
.B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,	.B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,
.ti +5n	.B " const char \fIname\fP, char \fIfirst\fP, char *\fIlast\fP);"
.B const char \fIname\fP, char \fIfirst\fP, char *\fIlast\fP);	.PP
.PP	.PP
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
are not required to be unique. (Duplicate names are always allowed for	are not required to be unique. (Duplicate names are always allowed for
Line 2459 the value returned is the size of each block that is o	Line 2684 the value returned is the size of each block that is o
.SH "MATCHING A PATTERN: THE ALTERNATIVE FUNCTION"	.SH "MATCHING A PATTERN: THE ALTERNATIVE FUNCTION"
.rs	.rs
.sp	.sp
	.nf
.B int pcre_dfa_exec(const pcre \fIcode\fP, "const pcre_extra \fIextra\fP,"	.B int pcre_dfa_exec(const pcre \fIcode\fP, "const pcre_extra \fIextra\fP,"
.ti +5n	.B " const char *\fIsubject\fP, int \fIlength\fP, int \fIstartoffset\fP,"
.B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,	.B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP,"
.ti +5n	.B " int *\fIworkspace\fP, int \fIwscount\fP);"
.B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP,	.fi
.ti +5n
.B int *\fIworkspace\fP, int \fIwscount\fP);
.P	.P
The function \fBpcre_dfa_exec()\fP is called to match a subject string against	The function \fBpcre_dfa_exec()\fP is called to match a subject string against
a compiled pattern, using a matching algorithm that scans the subject string	a compiled pattern, using a matching algorithm that scans the subject string
Line 2592 matching string is given first. If there were too many	Line 2816 matching string is given first. If there were too many
\fIovector\fP, the yield of the function is zero, and the vector is filled with	\fIovector\fP, the yield of the function is zero, and the vector is filled with
the longest matches. Unlike \fBpcre_exec()\fP, \fBpcre_dfa_exec()\fP can use	the longest matches. Unlike \fBpcre_exec()\fP, \fBpcre_dfa_exec()\fP can use
the entire \fIovector\fP for returning matched strings.	the entire \fIovector\fP for returning matched strings.
	.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\ed+" is compiled as if it were "a\ed++" 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\ed+?") or set the PCRE_NO_AUTO_POSSESS option when compiling.
.	.
.	.
.SS "Error returns from \fBpcre_dfa_exec()\fP"	.SS "Error returns from \fBpcre_dfa_exec()\fP"
Line 2648 fail, this error is given.	Line 2880 fail, this error is given.
.SH "SEE ALSO"	.SH "SEE ALSO"
.rs	.rs
.sp	.sp
\fBpcre16\fP(3), \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),	\fBpcre16\fP(3), \fBpcre32\fP(3), \fBpcrebuild\fP(3), \fBpcrecallout\fP(3),
\fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),	\fBpcrecpp(3)\fP(3), \fBpcrematching\fP(3), \fBpcrepartial\fP(3),
\fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).	\fBpcreposix\fP(3), \fBpcreprecompile\fP(3), \fBpcresample\fP(3),
	\fBpcrestack\fP(3).
.	.
.	.
.SH AUTHOR	.SH AUTHOR
Line 2667 Cambridge CB2 3QH, England.	Line 2900 Cambridge CB2 3QH, England.
.rs	.rs
.sp	.sp
.nf	.nf
Last updated: 17 June 2012	Last updated: 12 November 2013
Copyright (c) 1997-2012 University of Cambridge.	Copyright (c) 1997-2013 University of Cambridge.
.fi	.fi

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

Removed from v.1.1.1.3
changed lines
	Added in v.1.1.1.5