/[pcre]/code/trunk/doc/pcreapi.3
ViewVC logotype

Diff of /code/trunk/doc/pcreapi.3

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

revision 96 by nigel, Fri Mar 2 13:10:43 2007 UTC revision 659 by ph10, Tue Aug 16 09:48:29 2011 UTC
# Line 7  PCRE - Perl-compatible regular expressio Line 7  PCRE - Perl-compatible regular expressio
7  .B #include <pcre.h>  .B #include <pcre.h>
8  .PP  .PP
9  .SM  .SM
 .br  
10  .B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP,  .B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP,
11  .ti +5n  .ti +5n
12  .B const char **\fIerrptr\fP, int *\fIerroffset\fP,  .B const char **\fIerrptr\fP, int *\fIerroffset\fP,
13  .ti +5n  .ti +5n
14  .B const unsigned char *\fItableptr\fP);  .B const unsigned char *\fItableptr\fP);
15  .PP  .PP
 .br  
16  .B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP,  .B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP,
17  .ti +5n  .ti +5n
18  .B int *\fIerrorcodeptr\fP,  .B int *\fIerrorcodeptr\fP,
# Line 23  PCRE - Perl-compatible regular expressio Line 21  PCRE - Perl-compatible regular expressio
21  .ti +5n  .ti +5n
22  .B const unsigned char *\fItableptr\fP);  .B const unsigned char *\fItableptr\fP);
23  .PP  .PP
 .br  
24  .B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP,  .B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP,
25  .ti +5n  .ti +5n
26  .B const char **\fIerrptr\fP);  .B const char **\fIerrptr\fP);
27  .PP  .PP
 .br  
28  .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,"
29  .ti +5n  .ti +5n
30  .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,  .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
31  .ti +5n  .ti +5n
32  .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);  .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);
33  .PP  .PP
 .br  
34  .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,"
35  .ti +5n  .ti +5n
36  .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,  .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
# Line 44  PCRE - Perl-compatible regular expressio Line 39  PCRE - Perl-compatible regular expressio
39  .ti +5n  .ti +5n
40  .B int *\fIworkspace\fP, int \fIwscount\fP);  .B int *\fIworkspace\fP, int \fIwscount\fP);
41  .PP  .PP
 .br  
42  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
43  .ti +5n  .ti +5n
44  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 53  PCRE - Perl-compatible regular expressio Line 47  PCRE - Perl-compatible regular expressio
47  .ti +5n  .ti +5n
48  .B char *\fIbuffer\fP, int \fIbuffersize\fP);  .B char *\fIbuffer\fP, int \fIbuffersize\fP);
49  .PP  .PP
 .br  
50  .B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP,
51  .ti +5n  .ti +5n
52  .B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP,
53  .ti +5n  .ti +5n
54  .B int \fIbuffersize\fP);  .B int \fIbuffersize\fP);
55  .PP  .PP
 .br  
56  .B int pcre_get_named_substring(const pcre *\fIcode\fP,  .B int pcre_get_named_substring(const pcre *\fIcode\fP,
57  .ti +5n  .ti +5n
58  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 69  PCRE - Perl-compatible regular expressio Line 61  PCRE - Perl-compatible regular expressio
61  .ti +5n  .ti +5n
62  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
63  .PP  .PP
 .br  
64  .B int pcre_get_stringnumber(const pcre *\fIcode\fP,  .B int pcre_get_stringnumber(const pcre *\fIcode\fP,
65  .ti +5n  .ti +5n
66  .B const char *\fIname\fP);  .B const char *\fIname\fP);
67  .PP  .PP
 .br  
68  .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,  .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,
69  .ti +5n  .ti +5n
70  .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);  .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);
71  .PP  .PP
 .br  
72  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
73  .ti +5n  .ti +5n
74  .B int \fIstringcount\fP, int \fIstringnumber\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP,
75  .ti +5n  .ti +5n
76  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
77  .PP  .PP
 .br  
78  .B int pcre_get_substring_list(const char *\fIsubject\fP,  .B int pcre_get_substring_list(const char *\fIsubject\fP,
79  .ti +5n  .ti +5n
80  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"
81  .PP  .PP
 .br  
82  .B void pcre_free_substring(const char *\fIstringptr\fP);  .B void pcre_free_substring(const char *\fIstringptr\fP);
83  .PP  .PP
 .br  
84  .B void pcre_free_substring_list(const char **\fIstringptr\fP);  .B void pcre_free_substring_list(const char **\fIstringptr\fP);
85  .PP  .PP
 .br  
86  .B const unsigned char *pcre_maketables(void);  .B const unsigned char *pcre_maketables(void);
87  .PP  .PP
 .br  
88  .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,"
89  .ti +5n  .ti +5n
90  .B int \fIwhat\fP, void *\fIwhere\fP);  .B int \fIwhat\fP, void *\fIwhere\fP);
91  .PP  .PP
 .br  
92  .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int  .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int
93  .B *\fIfirstcharptr\fP);  .B *\fIfirstcharptr\fP);
94  .PP  .PP
 .br  
95  .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);  .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);
96  .PP  .PP
 .br  
97  .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);  .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);
98  .PP  .PP
 .br  
99  .B char *pcre_version(void);  .B char *pcre_version(void);
100  .PP  .PP
 .br  
101  .B void *(*pcre_malloc)(size_t);  .B void *(*pcre_malloc)(size_t);
102  .PP  .PP
 .br  
103  .B void (*pcre_free)(void *);  .B void (*pcre_free)(void *);
104  .PP  .PP
 .br  
105  .B void *(*pcre_stack_malloc)(size_t);  .B void *(*pcre_stack_malloc)(size_t);
106  .PP  .PP
 .br  
107  .B void (*pcre_stack_free)(void *);  .B void (*pcre_stack_free)(void *);
108  .PP  .PP
 .br  
109  .B int (*pcre_callout)(pcre_callout_block *);  .B int (*pcre_callout)(pcre_callout_block *);
110  .  .
111  .  .
# Line 157  an application that uses PCRE. The heade Line 132  an application that uses PCRE. The heade
132  and PCRE_MINOR to contain the major and minor release numbers for the library.  and PCRE_MINOR to contain the major and minor release numbers for the library.
133  Applications can use these to include support for different releases of PCRE.  Applications can use these to include support for different releases of PCRE.
134  .P  .P
135    In a Windows environment, if you want to statically link an application program
136    against a non-dll \fBpcre.a\fP file, you must define PCRE_STATIC before
137    including \fBpcre.h\fP or \fBpcrecpp.h\fP, because otherwise the
138    \fBpcre_malloc()\fP and \fBpcre_free()\fP exported functions will be declared
139    \fB__declspec(dllimport)\fP, with unwanted results.
140    .P
141  The functions \fBpcre_compile()\fP, \fBpcre_compile2()\fP, \fBpcre_study()\fP,  The functions \fBpcre_compile()\fP, \fBpcre_compile2()\fP, \fBpcre_study()\fP,
142  and \fBpcre_exec()\fP are used for compiling and matching regular expressions  and \fBpcre_exec()\fP are used for compiling and matching regular expressions
143  in a Perl-compatible manner. A sample program that demonstrates the simplest  in a Perl-compatible manner. A sample program that demonstrates the simplest
144  way of using them is provided in the file called \fIpcredemo.c\fP in the source  way of using them is provided in the file called \fIpcredemo.c\fP in the PCRE
145  distribution. The  source distribution. A listing of this program is given in the
146    .\" HREF
147    \fBpcredemo\fP
148    .\"
149    documentation, and the
150  .\" HREF  .\" HREF
151  \fBpcresample\fP  \fBpcresample\fP
152  .\"  .\"
153  documentation describes how to run it.  documentation describes how to compile and run it.
154  .P  .P
155  A second matching function, \fBpcre_dfa_exec()\fP, which is not  A second matching function, \fBpcre_dfa_exec()\fP, which is not
156  Perl-compatible, is also provided. This uses a different algorithm for the  Perl-compatible, is also provided. This uses a different algorithm for the
157  matching. The alternative algorithm finds all possible matches (at a given  matching. The alternative algorithm finds all possible matches (at a given
158  point in the subject), and scans the subject just once. However, this algorithm  point in the subject), and scans the subject just once (unless there are
159  does not return captured substrings. A description of the two matching  lookbehind assertions). However, this algorithm does not return captured
160  algorithms and their advantages and disadvantages is given in the  substrings. A description of the two matching algorithms and their advantages
161    and disadvantages is given in the
162  .\" HREF  .\" HREF
163  \fBpcrematching\fP  \fBpcrematching\fP
164  .\"  .\"
# Line 243  points during a matching operation. Deta Line 229  points during a matching operation. Deta
229  documentation.  documentation.
230  .  .
231  .  .
232    .\" HTML <a name="newlines"></a>
233  .SH NEWLINES  .SH NEWLINES
234  .rs  .rs
235  .sp  .sp
236  PCRE supports four different conventions for indicating line breaks in  PCRE supports five different conventions for indicating line breaks in
237  strings: a single CR (carriage return) character, a single LF (linefeed)  strings: a single CR (carriage return) character, a single LF (linefeed)
238  character, the two-character sequence CRLF, or any Unicode newline sequence.  character, the two-character sequence CRLF, any of the three preceding, or any
239  The Unicode newline sequences are the three just mentioned, plus the single  Unicode newline sequence. The Unicode newline sequences are the three just
240  characters VT (vertical tab, U+000B), FF (formfeed, U+000C), NEL (next line,  mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,
241  U+0085), LS (line separator, U+2028), and PS (paragraph separator, U+2029).  U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
242    (paragraph separator, U+2029).
243  .P  .P
244  Each of the first three conventions is used by at least one operating system as  Each of the first three conventions is used by at least one operating system as
245  its standard newline sequence. When PCRE is built, a default can be specified.  its standard newline sequence. When PCRE is built, a default can be specified.
# Line 259  The default default is LF, which is the Line 247  The default default is LF, which is the
247  default can be overridden, either when a pattern is compiled, or when it is  default can be overridden, either when a pattern is compiled, or when it is
248  matched.  matched.
249  .P  .P
250    At compile time, the newline convention can be specified by the \fIoptions\fP
251    argument of \fBpcre_compile()\fP, or it can be specified by special text at the
252    start of the pattern itself; this overrides any other settings. See the
253    .\" HREF
254    \fBpcrepattern\fP
255    .\"
256    page for details of the special character sequences.
257    .P
258  In the PCRE documentation the word "newline" is used to mean "the character or  In the PCRE documentation the word "newline" is used to mean "the character or
259  pair of characters that indicate a line break". The choice of newline  pair of characters that indicate a line break". The choice of newline
260  convention affects the handling of the dot, circumflex, and dollar  convention affects the handling of the dot, circumflex, and dollar
261  metacharacters, the handling of #-comments in /x mode, and, when CRLF is a  metacharacters, the handling of #-comments in /x mode, and, when CRLF is a
262  recognized line ending sequence, the match position advancement for a  recognized line ending sequence, the match position advancement for a
263  non-anchored pattern. The choice of newline convention does not affect the  non-anchored pattern. There is more detail about this in the
264  interpretation of the \en or \er escape sequences.  .\" HTML <a href="#execoptions">
265    .\" </a>
266    section on \fBpcre_exec()\fP options
267    .\"
268    below.
269    .P
270    The choice of newline convention does not affect the interpretation of
271    the \en or \er escape sequences, nor does it affect what \eR matches, which is
272    controlled in a similar way, but by separate options.
273  .  .
274  .  .
275  .SH MULTITHREADING  .SH MULTITHREADING
# Line 289  which it was compiled. Details are given Line 293  which it was compiled. Details are given
293  .\" HREF  .\" HREF
294  \fBpcreprecompile\fP  \fBpcreprecompile\fP
295  .\"  .\"
296  documentation.  documentation. However, compiling a regular expression with one version of PCRE
297    for use with a different version is not guaranteed to work and may cause
298    crashes.
299  .  .
300  .  .
301  .SH "CHECKING BUILD-TIME OPTIONS"  .SH "CHECKING BUILD-TIME OPTIONS"
# Line 322  properties is available; otherwise it is Line 328  properties is available; otherwise it is
328  .sp  .sp
329  The output is an integer whose value specifies the default character sequence  The output is an integer whose value specifies the default character sequence
330  that is recognized as meaning "newline". The four values that are supported  that is recognized as meaning "newline". The four values that are supported
331  are: 10 for LF, 13 for CR, 3338 for CRLF, and -1 for ANY. The default should  are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, and -1 for ANY.
332  normally be the standard sequence for your operating system.  Though they are derived from ASCII, the same values are returned in EBCDIC
333    environments. The default should normally correspond to the standard sequence
334    for your operating system.
335    .sp
336      PCRE_CONFIG_BSR
337    .sp
338    The output is an integer whose value indicates what character sequences the \eR
339    escape sequence matches by default. A value of 0 means that \eR matches any
340    Unicode line ending sequence; a value of 1 means that \eR matches only CR, LF,
341    or CRLF. The default can be overridden when a pattern is compiled or matched.
342  .sp  .sp
343    PCRE_CONFIG_LINK_SIZE    PCRE_CONFIG_LINK_SIZE
344  .sp  .sp
# Line 345  documentation. Line 360  documentation.
360  .sp  .sp
361    PCRE_CONFIG_MATCH_LIMIT    PCRE_CONFIG_MATCH_LIMIT
362  .sp  .sp
363  The output is an 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
364  internal matching function calls in a \fBpcre_exec()\fP execution. Further  internal matching function calls in a \fBpcre_exec()\fP execution. Further
365  details are given with \fBpcre_exec()\fP below.  details are given with \fBpcre_exec()\fP below.
366  .sp  .sp
367    PCRE_CONFIG_MATCH_LIMIT_RECURSION    PCRE_CONFIG_MATCH_LIMIT_RECURSION
368  .sp  .sp
369  The output is an integer that gives the default limit for the depth of  The output is a long integer that gives the default limit for the depth of
370  recursion when calling the internal matching function in a \fBpcre_exec()\fP  recursion when calling the internal matching function in a \fBpcre_exec()\fP
371  execution. Further details are given with \fBpcre_exec()\fP below.  execution. Further details are given with \fBpcre_exec()\fP below.
372  .sp  .sp
# Line 386  avoiding the use of the stack. Line 401  avoiding the use of the stack.
401  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
402  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
403  the two interfaces is that \fBpcre_compile2()\fP has an additional argument,  the two interfaces is that \fBpcre_compile2()\fP has an additional argument,
404  \fIerrorcodeptr\fP, via which a numerical error code can be returned.  \fIerrorcodeptr\fP, via which a numerical error code can be returned. To avoid
405    too much repetition, we refer just to \fBpcre_compile()\fP below, but the
406    information applies equally to \fBpcre_compile2()\fP.
407  .P  .P
408  The pattern is a C string terminated by a binary zero, and is passed in the  The pattern is a C string terminated by a binary zero, and is passed in the
409  \fIpattern\fP argument. A pointer to a single block of memory that is obtained  \fIpattern\fP argument. A pointer to a single block of memory that is obtained
# Line 402  argument, which is an address (see below Line 419  argument, which is an address (see below
419  .P  .P
420  The \fIoptions\fP argument contains various bit settings that affect the  The \fIoptions\fP argument contains various bit settings that affect the
421  compilation. It should be zero if no options are required. The available  compilation. It should be zero if no options are required. The available
422  options are described below. Some of them, in particular, those that are  options are described below. Some of them (in particular, those that are
423  compatible with Perl, can also be set and unset from within the pattern (see  compatible with Perl, but some others as well) can also be set and unset from
424  the detailed description in the  within the pattern (see the detailed description in the
425  .\" HREF  .\" HREF
426  \fBpcrepattern\fP  \fBpcrepattern\fP
427  .\"  .\"
428  documentation). For these options, the contents of the \fIoptions\fP argument  documentation). For those options that can be different in different parts of
429  specifies their initial settings at the start of compilation and execution. The  the pattern, the contents of the \fIoptions\fP argument specifies their
430  PCRE_ANCHORED and PCRE_NEWLINE_\fIxxx\fP options can be set at the time of  settings at the start of compilation and execution. The PCRE_ANCHORED,
431  matching as well as at compile time.  PCRE_BSR_\fIxxx\fP, PCRE_NEWLINE_\fIxxx\fP, PCRE_NO_UTF8_CHECK, and
432    PCRE_NO_START_OPT options can be set at the time of matching as well as at
433    compile time.
434  .P  .P
435  If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.  If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.
436  Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns  Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns
437  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
438  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
439  not try to free it. The offset from the start of the pattern to the character  not try to free it. Normally, the offset from the start of the pattern to the
440  where the error was discovered is placed in the variable pointed to by  byte that was being processed when the error was discovered is placed in the
441  \fIerroffset\fP, which must not be NULL. If it is, an immediate error is given.  variable pointed to by \fIerroffset\fP, which must not be NULL (if it is, an
442    immediate error is given). However, for an invalid UTF-8 string, the offset is
443    that of the first byte of the failing character. Also, some errors are not
444    detected until checks are carried out when the whole pattern has been scanned;
445    in these cases the offset passed back is the length of the pattern.
446    .P
447    Note that the offset is in bytes, not characters, even in UTF-8 mode. It may
448    sometimes point into the middle of a UTF-8 character.
449  .P  .P
450  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
451  \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 466  facility, see the Line 492  facility, see the
492  .\"  .\"
493  documentation.  documentation.
494  .sp  .sp
495      PCRE_BSR_ANYCRLF
496      PCRE_BSR_UNICODE
497    .sp
498    These options (which are mutually exclusive) control what the \eR escape
499    sequence matches. The choice is either to match only CR, LF, or CRLF, or to
500    match any Unicode newline sequence. The default is specified when PCRE is
501    built. It can be overridden from within the pattern, or by setting an option
502    when a compiled pattern is matched.
503    .sp
504    PCRE_CASELESS    PCRE_CASELESS
505  .sp  .sp
506  If this bit is set, letters in the pattern match both upper and lower case  If this bit is set, letters in the pattern match both upper and lower case
# Line 489  pattern. Line 524  pattern.
524  .sp  .sp
525    PCRE_DOTALL    PCRE_DOTALL
526  .sp  .sp
527  If this bit is set, a dot metacharater in the pattern matches all characters,  If this bit is set, a dot metacharacter in the pattern matches a character of
528  including those that indicate newline. Without it, a dot does not match when  any value, including one that indicates a newline. However, it only ever
529  the current position is at a newline. This option is equivalent to Perl's /s  matches one character, even if newlines are coded as CRLF. Without this option,
530  option, and it can be changed within a pattern by a (?s) option setting. A  a dot does not match when the current position is at a newline. This option is
531  negative class such as [^a] always matches newline characters, independent of  equivalent to Perl's /s option, and it can be changed within a pattern by a
532  the setting of this option.  (?s) option setting. A negative class such as [^a] always matches newline
533    characters, independent of the setting of this option.
534  .sp  .sp
535    PCRE_DUPNAMES    PCRE_DUPNAMES
536  .sp  .sp
# Line 516  unescaped # outside a character class an Line 552  unescaped # outside a character class an
552  ignored. This is equivalent to Perl's /x option, and it can be changed within a  ignored. This is equivalent to Perl's /x option, and it can be changed within a
553  pattern by a (?x) option setting.  pattern by a (?x) option setting.
554  .P  .P
555    Which characters are interpreted as newlines is controlled by the options
556    passed to \fBpcre_compile()\fP or by a special sequence at the start of the
557    pattern, as described in the section entitled
558    .\" HTML <a href="pcrepattern.html#newlines">
559    .\" </a>
560    "Newline conventions"
561    .\"
562    in the \fBpcrepattern\fP documentation. Note that the end of this type of
563    comment is a literal newline sequence in the pattern; escape sequences that
564    happen to represent a newline do not count.
565    .P
566  This option makes it possible to include comments inside complicated patterns.  This option makes it possible to include comments inside complicated patterns.
567  Note, however, that this applies only to data characters. Whitespace characters  Note, however, that this applies only to data characters. Whitespace characters
568  may never appear within special character sequences in a pattern, for example  may never appear within special character sequences in a pattern, for example
569  within the sequence (?( which introduces a conditional subpattern.  within the sequence (?( that introduces a conditional subpattern.
570  .sp  .sp
571    PCRE_EXTRA    PCRE_EXTRA
572  .sp  .sp
# Line 529  set, any backslash in a pattern that is Line 576  set, any backslash in a pattern that is
576  special meaning causes an error, thus reserving these combinations for future  special meaning causes an error, thus reserving these combinations for future
577  expansion. By default, as in Perl, a backslash followed by a letter with no  expansion. By default, as in Perl, a backslash followed by a letter with no
578  special meaning is treated as a literal. (Perl can, however, be persuaded to  special meaning is treated as a literal. (Perl can, however, be persuaded to
579  give a warning for this.) There are at present no other features controlled by  give an error for this, by running it with the -w option.) There are at present
580  this option. It can also be set by a (?X) option setting within a pattern.  no other features controlled by this option. It can also be set by a (?X)
581    option setting within a pattern.
582  .sp  .sp
583    PCRE_FIRSTLINE    PCRE_FIRSTLINE
584  .sp  .sp
# Line 538  If this option is set, an unanchored pat Line 586  If this option is set, an unanchored pat
586  the first newline in the subject string, though the matched text may continue  the first newline in the subject string, though the matched text may continue
587  over the newline.  over the newline.
588  .sp  .sp
589      PCRE_JAVASCRIPT_COMPAT
590    .sp
591    If this option is set, PCRE's behaviour is changed in some ways so that it is
592    compatible with JavaScript rather than Perl. The changes are as follows:
593    .P
594    (1) A lone closing square bracket in a pattern causes a compile-time error,
595    because this is illegal in JavaScript (by default it is treated as a data
596    character). Thus, the pattern AB]CD becomes illegal when this option is set.
597    .P
598    (2) At run time, a back reference to an unset subpattern group matches an empty
599    string (by default this causes the current matching alternative to fail). A
600    pattern such as (\e1)(a) succeeds when this option is set (assuming it can find
601    an "a" in the subject), whereas it fails by default, for Perl compatibility.
602    .sp
603    PCRE_MULTILINE    PCRE_MULTILINE
604  .sp  .sp
605  By default, PCRE treats the subject string as consisting of a single line of  By default, PCRE treats the subject string as consisting of a single line of
# Line 557  occurrences of ^ or $ in a pattern, sett Line 619  occurrences of ^ or $ in a pattern, sett
619    PCRE_NEWLINE_CR    PCRE_NEWLINE_CR
620    PCRE_NEWLINE_LF    PCRE_NEWLINE_LF
621    PCRE_NEWLINE_CRLF    PCRE_NEWLINE_CRLF
622      PCRE_NEWLINE_ANYCRLF
623    PCRE_NEWLINE_ANY    PCRE_NEWLINE_ANY
624  .sp  .sp
625  These options override the default newline definition that was chosen when PCRE  These options override the default newline definition that was chosen when PCRE
626  was built. Setting the first or the second specifies that a newline is  was built. Setting the first or the second specifies that a newline is
627  indicated by a single character (CR or LF, respectively). Setting  indicated by a single character (CR or LF, respectively). Setting
628  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
629  CRLF sequence. Setting PCRE_NEWLINE_ANY specifies that any Unicode newline  CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three
630  sequence should be recognized. The Unicode newline sequences are the three just  preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies
631  mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,  that any Unicode newline sequence should be recognized. The Unicode newline
632  U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS  sequences are the three just mentioned, plus the single characters VT (vertical
633  (paragraph separator, U+2029). The last two are recognized only in UTF-8 mode.  tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line
634    separator, U+2028), and PS (paragraph separator, U+2029). The last two are
635    recognized only in UTF-8 mode.
636  .P  .P
637  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
638  as a number, giving eight possibilities. Currently only five are used (default  as a number, giving eight possibilities. Currently only six are used (default
639  plus the four 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
640  option, the combination may or may not be sensible. For example,  option, the combination may or may not be sensible. For example,
641  PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but  PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but
642  other combinations yield unused numbers and cause an error.  other combinations may yield unused numbers and cause an error.
643  .P  .P
644  The only time that a line break is specially recognized when compiling a  The only time that a line break in a pattern is specially recognized when
645  pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character  compiling is when PCRE_EXTENDED is set. CR and LF are whitespace characters,
646  class is encountered. This indicates a comment that lasts until after the next  and so are ignored in this mode. Also, an unescaped # outside a character class
647  line break sequence. In other circumstances, line break sequences are treated  indicates a comment that lasts until after the next line break sequence. In
648  as literal data, except that in PCRE_EXTENDED mode, both CR and LF are treated  other circumstances, line break sequences in patterns are treated as literal
649  as whitespace characters and are therefore ignored.  data.
650  .P  .P
651  The newline option that is set at compile time becomes the default that is used  The newline option that is set at compile time becomes the default that is used
652  for \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, but it can be overridden.  for \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, but it can be overridden.
# Line 594  were followed by ?: but named parenthese Line 659  were followed by ?: but named parenthese
659  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
660  in Perl.  in Perl.
661  .sp  .sp
662      NO_START_OPTIMIZE
663    .sp
664    This is an option that acts at matching time; that is, it is really an option
665    for \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP. If it is set at compile time,
666    it is remembered with the compiled pattern and assumed at matching time. For
667    details see the discussion of PCRE_NO_START_OPTIMIZE
668    .\" HTML <a href="#execoptions">
669    .\" </a>
670    below.
671    .\"
672    .sp
673      PCRE_UCP
674    .sp
675    This option changes the way PCRE processes \eB, \eb, \eD, \ed, \eS, \es, \eW,
676    \ew, and some of the POSIX character classes. By default, only ASCII characters
677    are recognized, but if PCRE_UCP is set, Unicode properties are used instead to
678    classify characters. More details are given in the section on
679    .\" HTML <a href="pcre.html#genericchartypes">
680    .\" </a>
681    generic character types
682    .\"
683    in the
684    .\" HREF
685    \fBpcrepattern\fP
686    .\"
687    page. If you set PCRE_UCP, matching one of the items it affects takes much
688    longer. The option is available only if PCRE has been compiled with Unicode
689    property support.
690    .sp
691    PCRE_UNGREEDY    PCRE_UNGREEDY
692  .sp  .sp
693  This option inverts the "greediness" of the quantifiers so that they are not  This option inverts the "greediness" of the quantifiers so that they are not
# Line 620  page. Line 714  page.
714    PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
715  .sp  .sp
716  When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is  When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is
717  automatically checked. If an invalid UTF-8 sequence of bytes is found,  automatically checked. There is a discussion about the
718  \fBpcre_compile()\fP returns an error. If you already know that your pattern is  .\" HTML <a href="pcre.html#utf8strings">
719  valid, and you want to skip this check for performance reasons, you can set the  .\" </a>
720  PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid  validity of UTF-8 strings
721  UTF-8 string as a pattern is undefined. It may cause your program to crash.  .\"
722  Note that this option can also be passed to \fBpcre_exec()\fP and  in the main
723  \fBpcre_dfa_exec()\fP, to suppress the UTF-8 validity checking of subject  .\" HREF
724  strings.  \fBpcre\fP
725    .\"
726    page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_compile()\fP
727    returns an error. If you already know that your pattern is valid, and you want
728    to skip this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK
729    option. When it is set, the effect of passing an invalid UTF-8 string as a
730    pattern is undefined. It may cause your program to crash. Note that this option
731    can also be passed to \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, to suppress
732    the UTF-8 validity checking of subject strings.
733  .  .
734  .  .
735  .SH "COMPILATION ERROR CODES"  .SH "COMPILATION ERROR CODES"
# Line 650  out of use. To avoid confusion, they hav Line 752  out of use. To avoid confusion, they hav
752     9  nothing to repeat     9  nothing to repeat
753    10  [this code is not in use]    10  [this code is not in use]
754    11  internal error: unexpected repeat    11  internal error: unexpected repeat
755    12  unrecognized character after (?    12  unrecognized character after (? or (?-
756    13  POSIX named classes are supported only within a class    13  POSIX named classes are supported only within a class
757    14  missing )    14  missing )
758    15  reference to non-existent subpattern    15  reference to non-existent subpattern
# Line 658  out of use. To avoid confusion, they hav Line 760  out of use. To avoid confusion, they hav
760    17  unknown option bit(s) set    17  unknown option bit(s) set
761    18  missing ) after comment    18  missing ) after comment
762    19  [this code is not in use]    19  [this code is not in use]
763    20  regular expression too large    20  regular expression is too large
764    21  failed to get memory    21  failed to get memory
765    22  unmatched parentheses    22  unmatched parentheses
766    23  internal error: code overflow    23  internal error: code overflow
# Line 667  out of use. To avoid confusion, they hav Line 769  out of use. To avoid confusion, they hav
769    26  malformed number or name after (?(    26  malformed number or name after (?(
770    27  conditional group contains more than two branches    27  conditional group contains more than two branches
771    28  assertion expected after (?(    28  assertion expected after (?(
772    29  (?R or (?digits must be followed by )    29  (?R or (?[+-]digits must be followed by )
773    30  unknown POSIX class name    30  unknown POSIX class name
774    31  POSIX collating elements are not supported    31  POSIX collating elements are not supported
775    32  this version of PCRE is not compiled with PCRE_UTF8 support    32  this version of PCRE is not compiled with PCRE_UTF8 support
# Line 675  out of use. To avoid confusion, they hav Line 777  out of use. To avoid confusion, they hav
777    34  character value in \ex{...} sequence is too large    34  character value in \ex{...} sequence is too large
778    35  invalid condition (?(0)    35  invalid condition (?(0)
779    36  \eC not allowed in lookbehind assertion    36  \eC not allowed in lookbehind assertion
780    37  PCRE does not support \eL, \el, \eN, \eU, or \eu    37  PCRE does not support \eL, \el, \eN{name}, \eU, or \eu
781    38  number after (?C is > 255    38  number after (?C is > 255
782    39  closing ) for (?C expected    39  closing ) for (?C expected
783    40  recursive call could loop indefinitely    40  recursive call could loop indefinitely
# Line 687  out of use. To avoid confusion, they hav Line 789  out of use. To avoid confusion, they hav
789    46  malformed \eP or \ep sequence    46  malformed \eP or \ep sequence
790    47  unknown property name after \eP or \ep    47  unknown property name after \eP or \ep
791    48  subpattern name is too long (maximum 32 characters)    48  subpattern name is too long (maximum 32 characters)
792    49  too many named subpatterns (maximum 10,000)    49  too many named subpatterns (maximum 10000)
793    50  repeated subpattern is too long    50  [this code is not in use]
794    51  octal value is greater than \e377 (not in UTF-8 mode)    51  octal value is greater than \e377 (not in UTF-8 mode)
795    52  internal error: overran compiling workspace    52  internal error: overran compiling workspace
796    53  internal error: previously-checked referenced subpattern not found    53  internal error: previously-checked referenced subpattern
797            not found
798    54  DEFINE group contains more than one branch    54  DEFINE group contains more than one branch
799    55  repeating a DEFINE group is not allowed    55  repeating a DEFINE group is not allowed
800    56  inconsistent NEWLINE options"    56  inconsistent NEWLINE options
801      57  \eg is not followed by a braced, angle-bracketed, or quoted
802            name/number or by a plain number
803      58  a numbered reference must not be zero
804      59  an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT)
805      60  (*VERB) not recognized
806      61  number is too big
807      62  subpattern name expected
808      63  digit expected after (?+
809      64  ] is an invalid data character in JavaScript compatibility mode
810      65  different names for subpatterns of the same number are
811            not allowed
812      66  (*MARK) must have an argument
813      67  this version of PCRE is not compiled with PCRE_UCP support
814      68  \ec must be followed by an ASCII character
815      69  \ek is not followed by a braced, angle-bracketed, or quoted name
816    .sp
817    The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may
818    be used if the limits were changed when PCRE was built.
819  .  .
820  .  .
821    .\" HTML <a name="studyingapattern"></a>
822  .SH "STUDYING A PATTERN"  .SH "STUDYING A PATTERN"
823  .rs  .rs
824  .sp  .sp
# Line 713  help speed up matching, \fBpcre_study()\ Line 835  help speed up matching, \fBpcre_study()\
835  results of the study.  results of the study.
836  .P  .P
837  The returned value from \fBpcre_study()\fP can be passed directly to  The returned value from \fBpcre_study()\fP can be passed directly to
838  \fBpcre_exec()\fP. However, a \fBpcre_extra\fP block also contains other  \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP. However, a \fBpcre_extra\fP block
839  fields that can be set by the caller before the block is passed; these are  also contains other fields that can be set by the caller before the block is
840  described  passed; these are described
841  .\" HTML <a href="#extradata">  .\" HTML <a href="#extradata">
842  .\" </a>  .\" </a>
843  below  below
844  .\"  .\"
845  in the section on matching a pattern.  in the section on matching a pattern.
846  .P  .P
847  If studying the pattern does not produce any additional information  If studying the pattern does not produce any useful information,
848  \fBpcre_study()\fP returns NULL. In that circumstance, if the calling program  \fBpcre_study()\fP returns NULL. In that circumstance, if the calling program
849  wants to pass any of the other fields to \fBpcre_exec()\fP, it must set up its  wants to pass any of the other fields to \fBpcre_exec()\fP or
850  own \fBpcre_extra\fP block.  \fBpcre_dfa_exec()\fP, it must set up its own \fBpcre_extra\fP block.
851  .P  .P
852  The second argument of \fBpcre_study()\fP contains option bits. At present, no  The second argument of \fBpcre_study()\fP contains option bits. At present, no
853  options are defined, and this argument should always be zero.  options are defined, and this argument should always be zero.
# Line 745  This is a typical call to \fBpcre_study\ Line 867  This is a typical call to \fBpcre_study\
867      0,              /* no options exist */      0,              /* no options exist */
868      &error);        /* set to NULL or points to a message */      &error);        /* set to NULL or points to a message */
869  .sp  .sp
870  At present, studying a pattern is useful only for non-anchored patterns that do  Studying a pattern does two things: first, a lower bound for the length of
871  not have a single fixed starting character. A bitmap of possible starting  subject string that is needed to match the pattern is computed. This does not
872  bytes is created.  mean that there are any strings of that length that match, but it does
873    guarantee that no shorter strings match. The value is used by
874    \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP to avoid wasting time by trying to
875    match strings that are shorter than the lower bound. You can find out the value
876    in a calling program via the \fBpcre_fullinfo()\fP function.
877    .P
878    Studying a pattern is also useful for non-anchored patterns that do not have a
879    single fixed starting character. A bitmap of possible starting bytes is
880    created. This speeds up finding a position in the subject at which to start
881    matching.
882    .P
883    The two optimizations just described can be disabled by setting the
884    PCRE_NO_START_OPTIMIZE option when calling \fBpcre_exec()\fP or
885    \fBpcre_dfa_exec()\fP. You might want to do this if your pattern contains
886    callouts or (*MARK), and you want to make use of these facilities in cases
887    where matching fails. See the discussion of PCRE_NO_START_OPTIMIZE
888    .\" HTML <a href="#execoptions">
889    .\" </a>
890    below.
891    .\"
892  .  .
893  .  .
894  .\" HTML <a name="localesupport"></a>  .\" HTML <a name="localesupport"></a>
895  .SH "LOCALE SUPPORT"  .SH "LOCALE SUPPORT"
896  .rs  .rs
897  .sp  .sp
898  PCRE handles caseless matching, and determines whether characters are letters  PCRE handles caseless matching, and determines whether characters are letters,
899  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
900  value. When running in UTF-8 mode, this applies only to characters with codes  value. When running in UTF-8 mode, this applies only to characters with codes
901  less than 128. Higher-valued codes never match escapes such as \ew or \ed, but  less than 128. By default, higher-valued codes never match escapes such as \ew
902  can be tested with \ep if PCRE is built with Unicode character property  or \ed, but they can be tested with \ep if PCRE is built with Unicode character
903  support. The use of locales with Unicode is discouraged.  property support. Alternatively, the PCRE_UCP option can be set at compile
904  .P  time; this causes \ew and friends to use Unicode property support instead of
905  An internal set of tables is created in the default C locale when PCRE is  built-in tables. The use of locales with Unicode is discouraged. If you are
906  built. This is used when the final argument of \fBpcre_compile()\fP is NULL,  handling characters with codes greater than 128, you should either use UTF-8
907  and is sufficient for many applications. An alternative set of tables can,  and Unicode, or use locales, but not try to mix the two.
908  however, be supplied. These may be created in a different locale from the  .P
909  default. As more and more applications change to using Unicode, the need for  PCRE contains an internal set of tables that are used when the final argument
910  this locale support is expected to die away.  of \fBpcre_compile()\fP is NULL. These are sufficient for many applications.
911    Normally, the internal tables recognize only ASCII characters. However, when
912    PCRE is built, it is possible to cause the internal tables to be rebuilt in the
913    default "C" locale of the local system, which may cause them to be different.
914    .P
915    The internal tables can always be overridden by tables supplied by the
916    application that calls PCRE. These may be created in a different locale from
917    the default. As more and more applications change to using Unicode, the need
918    for this locale support is expected to die away.
919  .P  .P
920  External tables are built by calling the \fBpcre_maketables()\fP function,  External tables are built by calling the \fBpcre_maketables()\fP function,
921  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
# Line 779  the following code could be used: Line 928  the following code could be used:
928    tables = pcre_maketables();    tables = pcre_maketables();
929    re = pcre_compile(..., tables);    re = pcre_compile(..., tables);
930  .sp  .sp
931    The locale name "fr_FR" is used on Linux and other Unix-like systems; if you
932    are using Windows, the name for the French locale is "french".
933    .P
934  When \fBpcre_maketables()\fP runs, the tables are built in memory that is  When \fBpcre_maketables()\fP runs, the tables are built in memory that is
935  obtained via \fBpcre_malloc\fP. It is the caller's responsibility to ensure  obtained via \fBpcre_malloc\fP. It is the caller's responsibility to ensure
936  that the memory containing the tables remains available for as long as it is  that the memory containing the tables remains available for as long as it is
# Line 797  one in which it was compiled. Passing ta Line 949  one in which it was compiled. Passing ta
949  below in the section on matching a pattern.  below in the section on matching a pattern.
950  .  .
951  .  .
952    .\" HTML <a name="infoaboutpattern"></a>
953  .SH "INFORMATION ABOUT A PATTERN"  .SH "INFORMATION ABOUT A PATTERN"
954  .rs  .rs
955  .sp  .sp
# Line 881  table indicating a fixed set of bytes fo Line 1034  table indicating a fixed set of bytes fo
1034  string, a pointer to the table is returned. Otherwise NULL is returned. The  string, a pointer to the table is returned. Otherwise NULL is returned. The
1035  fourth argument should point to an \fBunsigned char *\fP variable.  fourth argument should point to an \fBunsigned char *\fP variable.
1036  .sp  .sp
1037      PCRE_INFO_HASCRORLF
1038    .sp
1039    Return 1 if the pattern contains any explicit matches for CR or LF characters,
1040    otherwise 0. The fourth argument should point to an \fBint\fP variable. An
1041    explicit match is either a literal CR or LF character, or \er or \en.
1042    .sp
1043      PCRE_INFO_JCHANGED
1044    .sp
1045    Return 1 if the (?J) or (?-J) option setting is used in the pattern, otherwise
1046    0. The fourth argument should point to an \fBint\fP variable. (?J) and
1047    (?-J) set and unset the local PCRE_DUPNAMES option, respectively.
1048    .sp
1049    PCRE_INFO_LASTLITERAL    PCRE_INFO_LASTLITERAL
1050  .sp  .sp
1051  Return the value of the rightmost literal byte that must exist in any matched  Return the value of the rightmost literal byte that must exist in any matched
# Line 891  follows something of variable length. Fo Line 1056  follows something of variable length. Fo
1056  /^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
1057  is -1.  is -1.
1058  .sp  .sp
1059      PCRE_INFO_MINLENGTH
1060    .sp
1061    If the pattern was studied and a minimum length for matching subject strings
1062    was computed, its value is returned. Otherwise the returned value is -1. The
1063    value is a number of characters, not bytes (this may be relevant in UTF-8
1064    mode). The fourth argument should point to an \fBint\fP variable. A
1065    non-negative value is a lower bound to the length of any matching string. There
1066    may not be any strings of that length that do actually match, but every string
1067    that does match is at least that long.
1068    .sp
1069    PCRE_INFO_NAMECOUNT    PCRE_INFO_NAMECOUNT
1070    PCRE_INFO_NAMEENTRYSIZE    PCRE_INFO_NAMEENTRYSIZE
1071    PCRE_INFO_NAMETABLE    PCRE_INFO_NAMETABLE
# Line 911  entry; both of these return an \fBint\fP Line 1086  entry; both of these return an \fBint\fP
1086  length of the longest name. PCRE_INFO_NAMETABLE returns a pointer to the first  length of the longest name. PCRE_INFO_NAMETABLE returns a pointer to the first
1087  entry of the table (a pointer to \fBchar\fP). The first two bytes of each entry  entry of the table (a pointer to \fBchar\fP). The first two bytes of each entry
1088  are the number of the capturing parenthesis, most significant byte first. The  are the number of the capturing parenthesis, most significant byte first. The
1089  rest of the entry is the corresponding name, zero terminated. The names are in  rest of the entry is the corresponding name, zero terminated.
1090  alphabetical order. When PCRE_DUPNAMES is set, duplicate names are in order of  .P
1091  their parentheses numbers. For example, consider the following pattern (assume  The names are in alphabetical order. Duplicate names may appear if (?| is used
1092  PCRE_EXTENDED is set, so white space - including newlines - is ignored):  to create multiple groups with the same number, as described in the
1093    .\" HTML <a href="pcrepattern.html#dupsubpatternnumber">
1094    .\" </a>
1095    section on duplicate subpattern numbers
1096    .\"
1097    in the
1098    .\" HREF
1099    \fBpcrepattern\fP
1100    .\"
1101    page. Duplicate names for subpatterns with different numbers are permitted only
1102    if PCRE_DUPNAMES is set. In all cases of duplicate names, they appear in the
1103    table in the order in which they were found in the pattern. In the absence of
1104    (?| this is the order of increasing number; when (?| is used this is not
1105    necessarily the case because later subpatterns may have lower numbers.
1106    .P
1107    As a simple example of the name/number table, consider the following pattern
1108    (assume PCRE_EXTENDED is set, so white space - including newlines - is
1109    ignored):
1110  .sp  .sp
1111  .\" JOIN  .\" JOIN
1112    (?<date> (?<year>(\ed\ed)?\ed\ed) -    (?<date> (?<year>(\ed\ed)?\ed\ed) -
# Line 933  When writing code to extract data from n Line 1125  When writing code to extract data from n
1125  name-to-number map, remember that the length of the entries is likely to be  name-to-number map, remember that the length of the entries is likely to be
1126  different for each compiled pattern.  different for each compiled pattern.
1127  .sp  .sp
1128      PCRE_INFO_OKPARTIAL
1129    .sp
1130    Return 1 if the pattern can be used for partial matching with
1131    \fBpcre_exec()\fP, otherwise 0. The fourth argument should point to an
1132    \fBint\fP variable. From release 8.00, this always returns 1, because the
1133    restrictions that previously applied to partial matching have been lifted. The
1134    .\" HREF
1135    \fBpcrepartial\fP
1136    .\"
1137    documentation gives details of partial matching.
1138    .sp
1139    PCRE_INFO_OPTIONS    PCRE_INFO_OPTIONS
1140  .sp  .sp
1141  Return a copy of the options with which the pattern was compiled. The fourth  Return a copy of the options with which the pattern was compiled. The fourth
1142  argument should point to an \fBunsigned long int\fP variable. These option bits  argument should point to an \fBunsigned long int\fP variable. These option bits
1143  are those specified in the call to \fBpcre_compile()\fP, modified by any  are those specified in the call to \fBpcre_compile()\fP, modified by any
1144  top-level option settings within the pattern itself.  top-level option settings at the start of the pattern itself. In other words,
1145    they are the options that will be in force when matching starts. For example,
1146    if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the
1147    result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED.
1148  .P  .P
1149  A pattern is automatically anchored by PCRE if all of its top-level  A pattern is automatically anchored by PCRE if all of its top-level
1150  alternatives begin with one of the following:  alternatives begin with one of the following:
# Line 962  variable. Line 1168  variable.
1168  .sp  .sp
1169    PCRE_INFO_STUDYSIZE    PCRE_INFO_STUDYSIZE
1170  .sp  .sp
1171  Return the size of the data block pointed to by the \fIstudy_data\fP field in  Return the size of the data block pointed to by the \fIstudy_data\fP field in a
1172  a \fBpcre_extra\fP block. That is, it is the value that was passed to  \fBpcre_extra\fP block. If \fBpcre_extra\fP is NULL, or there is no study data,
1173  \fBpcre_malloc()\fP when PCRE was getting memory into which to place the data  zero is returned. The fourth argument should point to a \fBsize_t\fP variable.
1174  created by \fBpcre_study()\fP. The fourth argument should point to a  The \fIstudy_data\fP field is set by \fBpcre_study()\fP to record information
1175  \fBsize_t\fP variable.  that will speed up matching (see the section entitled
1176    .\" HTML <a href="#studyingapattern">
1177    .\" </a>
1178    "Studying a pattern"
1179    .\"
1180    above). The format of the \fIstudy_data\fP block is private, but its length
1181    is made available via this option so that it can be saved and restored (see the
1182    .\" HREF
1183    \fBpcreprecompile\fP
1184    .\"
1185    documentation for details).
1186  .  .
1187  .  .
1188  .SH "OBSOLETE INFO FUNCTION"  .SH "OBSOLETE INFO FUNCTION"
# Line 1027  is different. (This seems a highly unlik Line 1243  is different. (This seems a highly unlik
1243  .P  .P
1244  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
1245  compiled pattern, which is passed in the \fIcode\fP argument. If the  compiled pattern, which is passed in the \fIcode\fP argument. If the
1246  pattern has been studied, the result of the study should be passed in the  pattern was studied, the result of the study should be passed in the
1247  \fIextra\fP argument. This function is the main matching facility of the  \fIextra\fP argument. This function is the main matching facility of the
1248  library, and it operates in a Perl-like manner. For specialist use there is  library, and it operates in a Perl-like manner. For specialist use there is
1249  also an alternative matching function, which is described  also an alternative matching function, which is described
# Line 1061  Here is an example of a simple call to \ Line 1277  Here is an example of a simple call to \
1277      ovector,        /* vector of integers for substring information */      ovector,        /* vector of integers for substring information */
1278      30);            /* number of elements (NOT size in bytes) */      30);            /* number of elements (NOT size in bytes) */
1279  .  .
1280    .
1281  .\" HTML <a name="extradata"></a>  .\" HTML <a name="extradata"></a>
1282  .SS "Extra data for \fBpcre_exec()\fR"  .SS "Extra data for \fBpcre_exec()\fR"
1283  .rs  .rs
# Line 1077  fields (not necessarily in this order): Line 1294  fields (not necessarily in this order):
1294    unsigned long int \fImatch_limit_recursion\fP;    unsigned long int \fImatch_limit_recursion\fP;
1295    void *\fIcallout_data\fP;    void *\fIcallout_data\fP;
1296    const unsigned char *\fItables\fP;    const unsigned char *\fItables\fP;
1297      unsigned char **\fImark\fP;
1298  .sp  .sp
1299  The \fIflags\fP field is a bitmap that specifies which of the other fields  The \fIflags\fP field is a bitmap that specifies which of the other fields
1300  are set. The flag bits are:  are set. The flag bits are:
# Line 1086  are set. The flag bits are: Line 1304  are set. The flag bits are:
1304    PCRE_EXTRA_MATCH_LIMIT_RECURSION    PCRE_EXTRA_MATCH_LIMIT_RECURSION
1305    PCRE_EXTRA_CALLOUT_DATA    PCRE_EXTRA_CALLOUT_DATA
1306    PCRE_EXTRA_TABLES    PCRE_EXTRA_TABLES
1307      PCRE_EXTRA_MARK
1308  .sp  .sp
1309  Other flag bits should be set to zero. The \fIstudy_data\fP field is set in the  Other flag bits should be set to zero. The \fIstudy_data\fP field is set in the
1310  \fBpcre_extra\fP block that is returned by \fBpcre_study()\fP, together with  \fBpcre_extra\fP block that is returned by \fBpcre_study()\fP, together with
# Line 1095  the block by setting the other fields an Line 1314  the block by setting the other fields an
1314  The \fImatch_limit\fP field provides a means of preventing PCRE from using up a  The \fImatch_limit\fP field provides a means of preventing PCRE from using up a
1315  vast amount of resources when running patterns that are not going to match,  vast amount of resources when running patterns that are not going to match,
1316  but which have a very large number of possibilities in their search trees. The  but which have a very large number of possibilities in their search trees. The
1317  classic example is the use of nested unlimited repeats.  classic example is a pattern that uses nested unlimited repeats.
1318  .P  .P
1319  Internally, PCRE uses a function called \fBmatch()\fP which it calls repeatedly  Internally, PCRE uses a function called \fBmatch()\fP which it calls repeatedly
1320  (sometimes recursively). The limit set by \fImatch_limit\fP is imposed on the  (sometimes recursively). The limit set by \fImatch_limit\fP is imposed on the
# Line 1128  with a \fBpcre_extra\fP block in which \ Line 1347  with a \fBpcre_extra\fP block in which \
1347  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
1348  is exceeded, \fBpcre_exec()\fP returns PCRE_ERROR_RECURSIONLIMIT.  is exceeded, \fBpcre_exec()\fP returns PCRE_ERROR_RECURSIONLIMIT.
1349  .P  .P
1350  The \fIpcre_callout\fP field is used in conjunction with the "callout" feature,  The \fIcallout_data\fP field is used in conjunction with the "callout" feature,
1351  which is described in the  and is described in the
1352  .\" HREF  .\" HREF
1353  \fBpcrecallout\fP  \fBpcrecallout\fP
1354  .\"  .\"
# Line 1148  called. See the Line 1367  called. See the
1367  \fBpcreprecompile\fP  \fBpcreprecompile\fP
1368  .\"  .\"
1369  documentation for a discussion of saving compiled patterns for later use.  documentation for a discussion of saving compiled patterns for later use.
1370    .P
1371    If PCRE_EXTRA_MARK is set in the \fIflags\fP field, the \fImark\fP field must
1372    be set to point to a \fBchar *\fP variable. If the pattern contains any
1373    backtracking control verbs such as (*MARK:NAME), and the execution ends up with
1374    a name to pass back, a pointer to the name string (zero terminated) is placed
1375    in the variable pointed to by the \fImark\fP field. The names are within the
1376    compiled pattern; if you wish to retain such a name you must copy it before
1377    freeing the memory of a compiled pattern. If there is no name to pass back, the
1378    variable pointed to by the \fImark\fP field set to NULL. For details of the
1379    backtracking control verbs, see the section entitled
1380    .\" HTML <a href="pcrepattern#backtrackcontrol">
1381    .\" </a>
1382    "Backtracking control"
1383    .\"
1384    in the
1385    .\" HREF
1386    \fBpcrepattern\fP
1387    .\"
1388    documentation.
1389    .
1390  .  .
1391    .\" HTML <a name="execoptions"></a>
1392  .SS "Option bits for \fBpcre_exec()\fP"  .SS "Option bits for \fBpcre_exec()\fP"
1393  .rs  .rs
1394  .sp  .sp
1395  The unused bits of the \fIoptions\fP argument for \fBpcre_exec()\fP must be  The unused bits of the \fIoptions\fP argument for \fBpcre_exec()\fP must be
1396  zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,  zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,
1397  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK and PCRE_PARTIAL.  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART,
1398    PCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_SOFT, and
1399    PCRE_PARTIAL_HARD.
1400  .sp  .sp
1401    PCRE_ANCHORED    PCRE_ANCHORED
1402  .sp  .sp
# Line 1163  matching position. If a pattern was comp Line 1405  matching position. If a pattern was comp
1405  to be anchored by virtue of its contents, it cannot be made unachored at  to be anchored by virtue of its contents, it cannot be made unachored at
1406  matching time.  matching time.
1407  .sp  .sp
1408      PCRE_BSR_ANYCRLF
1409      PCRE_BSR_UNICODE
1410    .sp
1411    These options (which are mutually exclusive) control what the \eR escape
1412    sequence matches. The choice is either to match only CR, LF, or CRLF, or to
1413    match any Unicode newline sequence. These options override the choice that was
1414    made or defaulted when the pattern was compiled.
1415    .sp
1416    PCRE_NEWLINE_CR    PCRE_NEWLINE_CR
1417    PCRE_NEWLINE_LF    PCRE_NEWLINE_LF
1418    PCRE_NEWLINE_CRLF    PCRE_NEWLINE_CRLF
1419      PCRE_NEWLINE_ANYCRLF
1420    PCRE_NEWLINE_ANY    PCRE_NEWLINE_ANY
1421  .sp  .sp
1422  These options override the newline definition that was chosen or defaulted when  These options override the newline definition that was chosen or defaulted when
# Line 1173  the pattern was compiled. For details, s Line 1424  the pattern was compiled. For details, s
1424  \fBpcre_compile()\fP above. During matching, the newline choice affects the  \fBpcre_compile()\fP above. During matching, the newline choice affects the
1425  behaviour of the dot, circumflex, and dollar metacharacters. It may also alter  behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
1426  the way the match position is advanced after a match failure for an unanchored  the way the match position is advanced after a match failure for an unanchored
1427  pattern. When PCRE_NEWLINE_CRLF or PCRE_NEWLINE_ANY is set, and a match attempt  pattern.
1428  fails when the current position is at a CRLF sequence, the match position is  .P
1429  advanced by two characters instead of one, in other words, to after the CRLF.  When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is set, and a
1430    match attempt for an unanchored pattern fails when the current position is at a
1431    CRLF sequence, and the pattern contains no explicit matches for CR or LF
1432    characters, the match position is advanced by two characters instead of one, in
1433    other words, to after the CRLF.
1434    .P
1435    The above rule is a compromise that makes the most common cases work as
1436    expected. For example, if the pattern is .+A (and the PCRE_DOTALL option is not
1437    set), it does not match the string "\er\enA" because, after failing at the
1438    start, it skips both the CR and the LF before retrying. However, the pattern
1439    [\er\en]A does match that string, because it contains an explicit CR or LF
1440    reference, and so advances only by one character after the first failure.
1441    .P
1442    An explicit match for CR of LF is either a literal appearance of one of those
1443    characters, or one of the \er or \en escape sequences. Implicit matches such as
1444    [^X] do not count, nor does \es (which includes CR and LF in the characters
1445    that it matches).
1446    .P
1447    Notwithstanding the above, anomalous effects may still occur when CRLF is a
1448    valid newline sequence and explicit \er or \en escapes appear in the pattern.
1449  .sp  .sp
1450    PCRE_NOTBOL    PCRE_NOTBOL
1451  .sp  .sp
# Line 1201  match the empty string, the entire match Line 1471  match the empty string, the entire match
1471  .sp  .sp
1472    a?b?    a?b?
1473  .sp  .sp
1474  is applied to a string not beginning with "a" or "b", it matches the empty  is applied to a string not beginning with "a" or "b", it matches an empty
1475  string at the start of the subject. With PCRE_NOTEMPTY set, this match is not  string at the start of the subject. With PCRE_NOTEMPTY set, this match is not
1476  valid, so PCRE searches further into the string for occurrences of "a" or "b".  valid, so PCRE searches further into the string for occurrences of "a" or "b".
1477  .P  .sp
1478  Perl has no direct equivalent of PCRE_NOTEMPTY, but it does make a special case    PCRE_NOTEMPTY_ATSTART
1479  of a pattern match of the empty string within its \fBsplit()\fP function, and  .sp
1480  when using the /g modifier. It is possible to emulate Perl's behaviour after  This is like PCRE_NOTEMPTY, except that an empty string match that is not at
1481  matching a null string by first trying the match again at the same offset with  the start of the subject is permitted. If the pattern is anchored, such a match
1482  PCRE_NOTEMPTY and PCRE_ANCHORED, and then if that fails by advancing the  can occur only if the pattern contains \eK.
1483  starting offset (see below) and trying an ordinary match again. There is some  .P
1484  code that demonstrates how to do this in the \fIpcredemo.c\fP sample program.  Perl has no direct equivalent of PCRE_NOTEMPTY or PCRE_NOTEMPTY_ATSTART, but it
1485    does make a special case of a pattern match of the empty string within its
1486    \fBsplit()\fP function, and when using the /g modifier. It is possible to
1487    emulate Perl's behaviour after matching a null string by first trying the match
1488    again at the same offset with PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED, and then
1489    if that fails, by advancing the starting offset (see below) and trying an
1490    ordinary match again. There is some code that demonstrates how to do this in
1491    the
1492    .\" HREF
1493    \fBpcredemo\fP
1494    .\"
1495    sample program. In the most general case, you have to check to see if the
1496    newline convention recognizes CRLF as a newline, and if so, and the current
1497    character is CR followed by LF, advance the starting offset by two characters
1498    instead of one.
1499    .sp
1500      PCRE_NO_START_OPTIMIZE
1501    .sp
1502    There are a number of optimizations that \fBpcre_exec()\fP uses at the start of
1503    a match, in order to speed up the process. For example, if it is known that an
1504    unanchored match must start with a specific character, it searches the subject
1505    for that character, and fails immediately if it cannot find it, without
1506    actually running the main matching function. This means that a special item
1507    such as (*COMMIT) at the start of a pattern is not considered until after a
1508    suitable starting point for the match has been found. When callouts or (*MARK)
1509    items are in use, these "start-up" optimizations can cause them to be skipped
1510    if the pattern is never actually used. The start-up optimizations are in effect
1511    a pre-scan of the subject that takes place before the pattern is run.
1512    .P
1513    The PCRE_NO_START_OPTIMIZE option disables the start-up optimizations, possibly
1514    causing performance to suffer, but ensuring that in cases where the result is
1515    "no match", the callouts do occur, and that items such as (*COMMIT) and (*MARK)
1516    are considered at every possible starting position in the subject string. If
1517    PCRE_NO_START_OPTIMIZE is set at compile time, it cannot be unset at matching
1518    time.
1519    .P
1520    Setting PCRE_NO_START_OPTIMIZE can change the outcome of a matching operation.
1521    Consider the pattern
1522    .sp
1523      (*COMMIT)ABC
1524    .sp
1525    When this is compiled, PCRE records the fact that a match must start with the
1526    character "A". Suppose the subject string is "DEFABC". The start-up
1527    optimization scans along the subject, finds "A" and runs the first match
1528    attempt from there. The (*COMMIT) item means that the pattern must match the
1529    current starting position, which in this case, it does. However, if the same
1530    match is run with PCRE_NO_START_OPTIMIZE set, the initial scan along the
1531    subject string does not happen. The first match attempt is run starting from
1532    "D" and when this fails, (*COMMIT) prevents any further matches being tried, so
1533    the overall result is "no match". If the pattern is studied, more start-up
1534    optimizations may be used. For example, a minimum length for the subject may be
1535    recorded. Consider the pattern
1536    .sp
1537      (*MARK:A)(X|Y)
1538    .sp
1539    The minimum length for a match is one character. If the subject is "ABC", there
1540    will be attempts to match "ABC", "BC", "C", and then finally an empty string.
1541    If the pattern is studied, the final attempt does not take place, because PCRE
1542    knows that the subject is too short, and so the (*MARK) is never encountered.
1543    In this case, studying the pattern does not affect the overall match result,
1544    which is still "no match", but it does affect the auxiliary information that is
1545    returned.
1546  .sp  .sp
1547    PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
1548  .sp  .sp
1549  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
1550  string is automatically checked when \fBpcre_exec()\fP is subsequently called.  string is automatically checked when \fBpcre_exec()\fP is subsequently called.
1551  The value of \fIstartoffset\fP is also checked to ensure that it points to the  The value of \fIstartoffset\fP is also checked to ensure that it points to the
1552  start of a UTF-8 character. If an invalid UTF-8 sequence of bytes is found,  start of a UTF-8 character. There is a discussion about the validity of UTF-8
1553  \fBpcre_exec()\fP returns the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP  strings in the
1554  contains an invalid value, PCRE_ERROR_BADUTF8_OFFSET is returned.  .\" HTML <a href="pcre.html#utf8strings">
1555    .\" </a>
1556    section on UTF-8 support
1557    .\"
1558    in the main
1559    .\" HREF
1560    \fBpcre\fP
1561    .\"
1562    page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_exec()\fP returns
1563    the error PCRE_ERROR_BADUTF8 or, if PCRE_PARTIAL_HARD is set and the problem is
1564    a truncated UTF-8 character at the end of the subject, PCRE_ERROR_SHORTUTF8. In
1565    both cases, information about the precise nature of the error may also be
1566    returned (see the descriptions of these errors in the section entitled \fIError
1567    return values from\fP \fBpcre_exec()\fP
1568    .\" HTML <a href="#errorlist">
1569    .\" </a>
1570    below).
1571    .\"
1572    If \fIstartoffset\fP contains a value that does not point to the start of a
1573    UTF-8 character (or to the end of the subject), PCRE_ERROR_BADUTF8_OFFSET is
1574    returned.
1575  .P  .P
1576  If you already know that your subject is valid, and you want to skip these  If you already know that your subject is valid, and you want to skip these
1577  checks for performance reasons, you can set the PCRE_NO_UTF8_CHECK option when  checks for performance reasons, you can set the PCRE_NO_UTF8_CHECK option when
1578  calling \fBpcre_exec()\fP. You might want to do this for the second and  calling \fBpcre_exec()\fP. You might want to do this for the second and
1579  subsequent calls to \fBpcre_exec()\fP if you are making repeated calls to find  subsequent calls to \fBpcre_exec()\fP if you are making repeated calls to find
1580  all the matches in a single subject string. However, you should be sure that  all the matches in a single subject string. However, you should be sure that
1581  the value of \fIstartoffset\fP points to the start of a UTF-8 character. When  the value of \fIstartoffset\fP points to the start of a UTF-8 character (or the
1582  PCRE_NO_UTF8_CHECK is set, the effect of passing an invalid UTF-8 string as a  end of the subject). When PCRE_NO_UTF8_CHECK is set, the effect of passing an
1583  subject, or a value of \fIstartoffset\fP that does not point to the start of a  invalid UTF-8 string as a subject or an invalid value of \fIstartoffset\fP is
1584  UTF-8 character, is undefined. Your program may crash.  undefined. Your program may crash.
1585  .sp  .sp
1586    PCRE_PARTIAL    PCRE_PARTIAL_HARD
1587  .sp    PCRE_PARTIAL_SOFT
1588  This option turns on the partial matching feature. If the subject string fails  .sp
1589  to match the pattern, but at some point during the matching process the end of  These options turn on the partial matching feature. For backwards
1590  the subject was reached (that is, the subject partially matches the pattern and  compatibility, PCRE_PARTIAL is a synonym for PCRE_PARTIAL_SOFT. A partial match
1591  the failure to match occurred only because there were not enough subject  occurs if the end of the subject string is reached successfully, but there are
1592  characters), \fBpcre_exec()\fP returns PCRE_ERROR_PARTIAL instead of  not enough subject characters to complete the match. If this happens when
1593  PCRE_ERROR_NOMATCH. When PCRE_PARTIAL is used, there are restrictions on what  PCRE_PARTIAL_SOFT (but not PCRE_PARTIAL_HARD) is set, matching continues by
1594  may appear in the pattern. These are discussed in the  testing any remaining alternatives. Only if no complete match can be found is
1595    PCRE_ERROR_PARTIAL returned instead of PCRE_ERROR_NOMATCH. In other words,
1596    PCRE_PARTIAL_SOFT says that the caller is prepared to handle a partial match,
1597    but only if no complete match can be found.
1598    .P
1599    If PCRE_PARTIAL_HARD is set, it overrides PCRE_PARTIAL_SOFT. In this case, if a
1600    partial match is found, \fBpcre_exec()\fP immediately returns
1601    PCRE_ERROR_PARTIAL, without considering any other alternatives. In other words,
1602    when PCRE_PARTIAL_HARD is set, a partial match is considered to be more
1603    important that an alternative complete match.
1604    .P
1605    In both cases, the portion of the string that was inspected when the partial
1606    match was found is set as the first matching string. There is a more detailed
1607    discussion of partial and multi-segment matching, with examples, in the
1608  .\" HREF  .\" HREF
1609  \fBpcrepartial\fP  \fBpcrepartial\fP
1610  .\"  .\"
1611  documentation.  documentation.
1612  .  .
1613    .
1614  .SS "The string to be matched by \fBpcre_exec()\fP"  .SS "The string to be matched by \fBpcre_exec()\fP"
1615  .rs  .rs
1616  .sp  .sp
1617  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
1618  \fIsubject\fP, a length in \fIlength\fP, and a starting byte offset in  \fIsubject\fP, a length (in bytes) in \fIlength\fP, and a starting byte offset
1619  \fIstartoffset\fP. In UTF-8 mode, the byte offset must point to the start of a  in \fIstartoffset\fP. If this is negative or greater than the length of the
1620  UTF-8 character. Unlike the pattern string, the subject may contain binary zero  subject, \fBpcre_exec()\fP returns PCRE_ERROR_BADOFFSET. When the starting
1621  bytes. When the starting offset is zero, the search for a match starts at the  offset is zero, the search for a match starts at the beginning of the subject,
1622  beginning of the subject, and this is by far the most common case.  and this is by far the most common case. In UTF-8 mode, the byte offset must
1623    point to the start of a UTF-8 character (or the end of the subject). Unlike the
1624    pattern string, the subject may contain binary zero bytes.
1625  .P  .P
1626  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
1627  same subject by calling \fBpcre_exec()\fP again after a previous success.  same subject by calling \fBpcre_exec()\fP again after a previous success.
# Line 1274  start of the subject, which is deemed to Line 1641  start of the subject, which is deemed to
1641  set to 4, it finds the second occurrence of "iss" because it is able to look  set to 4, it finds the second occurrence of "iss" because it is able to look
1642  behind the starting point to discover that it is preceded by a letter.  behind the starting point to discover that it is preceded by a letter.
1643  .P  .P
1644    Finding all the matches in a subject is tricky when the pattern can match an
1645    empty string. It is possible to emulate Perl's /g behaviour by first trying the
1646    match again at the same offset, with the PCRE_NOTEMPTY_ATSTART and
1647    PCRE_ANCHORED options, and then if that fails, advancing the starting offset
1648    and trying an ordinary match again. There is some code that demonstrates how to
1649    do this in the
1650    .\" HREF
1651    \fBpcredemo\fP
1652    .\"
1653    sample program. In the most general case, you have to check to see if the
1654    newline convention recognizes CRLF as a newline, and if so, and the current
1655    character is CR followed by LF, advance the starting offset by two characters
1656    instead of one.
1657    .P
1658  If a non-zero starting offset is passed when the pattern is anchored, one  If a non-zero starting offset is passed when the pattern is anchored, one
1659  attempt to match at the given offset is made. This can only succeed if the  attempt to match at the given offset is made. This can only succeed if the
1660  pattern does not require the match to be at the start of the subject.  pattern does not require the match to be at the start of the subject.
1661  .  .
1662    .
1663  .SS "How \fBpcre_exec()\fP returns captured substrings"  .SS "How \fBpcre_exec()\fP returns captured substrings"
1664  .rs  .rs
1665  .sp  .sp
# Line 1288  pattern. Following the usage in Jeffrey Line 1670  pattern. Following the usage in Jeffrey
1670  a fragment of a pattern that picks out a substring. PCRE supports several other  a fragment of a pattern that picks out a substring. PCRE supports several other
1671  kinds of parenthesized subpattern that do not cause substrings to be captured.  kinds of parenthesized subpattern that do not cause substrings to be captured.
1672  .P  .P
1673  Captured substrings are returned to the caller via a vector of integer offsets  Captured substrings are returned to the caller via a vector of integers whose
1674  whose address is passed in \fIovector\fP. The number of elements in the vector  address is passed in \fIovector\fP. The number of elements in the vector is
1675  is passed in \fIovecsize\fP, which must be a non-negative number. \fBNote\fP:  passed in \fIovecsize\fP, which must be a non-negative number. \fBNote\fP: this
1676  this argument is NOT the size of \fIovector\fP in bytes.  argument is NOT the size of \fIovector\fP in bytes.
1677  .P  .P
1678  The first two-thirds of the vector is used to pass back captured substrings,  The first two-thirds of the vector is used to pass back captured substrings,
1679  each substring using a pair of integers. The remaining third of the vector is  each substring using a pair of integers. The remaining third of the vector is
1680  used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns,  used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns,
1681  and is not available for passing back information. The length passed in  and is not available for passing back information. The number passed in
1682  \fIovecsize\fP should always be a multiple of three. If it is not, it is  \fIovecsize\fP should always be a multiple of three. If it is not, it is
1683  rounded down.  rounded down.
1684  .P  .P
1685  When a match is successful, information about captured substrings is returned  When a match is successful, information about captured substrings is returned
1686  in pairs of integers, starting at the beginning of \fIovector\fP, and  in pairs of integers, starting at the beginning of \fIovector\fP, and
1687  continuing up to two-thirds of its length at the most. The first element of a  continuing up to two-thirds of its length at the most. The first element of
1688  pair is set to the offset of the first character in a substring, and the second  each pair is set to the byte offset of the first character in a substring, and
1689  is set to the offset of the first character after the end of a substring. The  the second is set to the byte offset of the first character after the end of a
1690  first pair, \fIovector[0]\fP and \fIovector[1]\fP, identify the portion of the  substring. \fBNote\fP: these values are always byte offsets, even in UTF-8
1691  subject string matched by the entire pattern. The next pair is used for the  mode. They are not character counts.
1692  first capturing subpattern, and so on. The value returned by \fBpcre_exec()\fP  .P
1693  is one more than the highest numbered pair that has been set. For example, if  The first pair of integers, \fIovector[0]\fP and \fIovector[1]\fP, identify the
1694  two substrings have been captured, the returned value is 3. If there are no  portion of the subject string matched by the entire pattern. The next pair is
1695  capturing subpatterns, the return value from a successful match is 1,  used for the first capturing subpattern, and so on. The value returned by
1696  indicating that just the first pair of offsets has been set.  \fBpcre_exec()\fP is one more than the highest numbered pair that has been set.
1697    For example, if two substrings have been captured, the returned value is 3. If
1698    there are no capturing subpatterns, the return value from a successful match is
1699    1, indicating that just the first pair of offsets has been set.
1700  .P  .P
1701  If a capturing subpattern is matched repeatedly, it is the last portion of the  If a capturing subpattern is matched repeatedly, it is the last portion of the
1702  string that it matched that is returned.  string that it matched that is returned.
1703  .P  .P
1704  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
1705  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
1706  returns a value of zero. In particular, if the substring offsets are not of  returns a value of zero. If the substring offsets are not of interest,
1707  interest, \fBpcre_exec()\fP may be called with \fIovector\fP passed as NULL and  \fBpcre_exec()\fP may be called with \fIovector\fP passed as NULL and
1708  \fIovecsize\fP as zero. However, if the pattern contains back references and  \fIovecsize\fP as zero. However, if the pattern contains back references and
1709  the \fIovector\fP is not big enough to remember the related substrings, PCRE  the \fIovector\fP is not big enough to remember the related substrings, PCRE
1710  has to get additional memory for use during matching. Thus it is usually  has to get additional memory for use during matching. Thus it is usually
1711  advisable to supply an \fIovector\fP.  advisable to supply an \fIovector\fP.
1712  .P  .P
1713  The \fBpcre_info()\fP function can be used to find out how many capturing  The \fBpcre_fullinfo()\fP function can be used to find out how many capturing
1714  subpatterns there are in a compiled pattern. The smallest size for  subpatterns there are in a compiled pattern. The smallest size for
1715  \fIovector\fP that will allow for \fIn\fP captured substrings, in addition to  \fIovector\fP that will allow for \fIn\fP captured substrings, in addition to
1716  the offsets of the substring matched by the whole pattern, is (\fIn\fP+1)*3.  the offsets of the substring matched by the whole pattern, is (\fIn\fP+1)*3.
# Line 1341  Offset values that correspond to unused Line 1726  Offset values that correspond to unused
1726  expression are also set to -1. For example, if the string "abc" is matched  expression are also set to -1. For example, if the string "abc" is matched
1727  against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The  against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The
1728  return from the function is 2, because the highest used capturing subpattern  return from the function is 2, because the highest used capturing subpattern
1729  number is 1. However, you can refer to the offsets for the second and third  number is 1, and the offsets for for the second and third capturing subpatterns
1730  capturing subpatterns if you wish (assuming the vector is large enough, of  (assuming the vector is large enough, of course) are set to -1.
1731  course).  .P
1732    \fBNote\fP: Elements of \fIovector\fP that do not correspond to capturing
1733    parentheses in the pattern are never changed. That is, if a pattern contains
1734    \fIn\fP capturing parentheses, no more than \fIovector[0]\fP to
1735    \fIovector[2n+1]\fP are set by \fBpcre_exec()\fP. The other elements retain
1736    whatever values they previously had.
1737  .P  .P
1738  Some convenience functions are provided for extracting the captured substrings  Some convenience functions are provided for extracting the captured substrings
1739  as separate strings. These are described below.  as separate strings. These are described below.
1740  .  .
1741    .
1742  .\" HTML <a name="errorlist"></a>  .\" HTML <a name="errorlist"></a>
1743  .SS "Error return values from \fBpcre_exec()\fP"  .SS "Error return values from \fBpcre_exec()\fP"
1744  .rs  .rs
# Line 1389  If a pattern contains back references, b Line 1780  If a pattern contains back references, b
1780  gets a block of memory at the start of matching to use for this purpose. If the  gets a block of memory at the start of matching to use for this purpose. If the
1781  call via \fBpcre_malloc()\fP fails, this error is given. The memory is  call via \fBpcre_malloc()\fP fails, this error is given. The memory is
1782  automatically freed at the end of matching.  automatically freed at the end of matching.
1783    .P
1784    This error is also given if \fBpcre_stack_malloc()\fP fails in
1785    \fBpcre_exec()\fP. This can happen only when PCRE has been compiled with
1786    \fB--disable-stack-for-recursion\fP.
1787  .sp  .sp
1788    PCRE_ERROR_NOSUBSTRING    (-7)    PCRE_ERROR_NOSUBSTRING    (-7)
1789  .sp  .sp
# Line 1413  documentation for details. Line 1808  documentation for details.
1808  .sp  .sp
1809    PCRE_ERROR_BADUTF8        (-10)    PCRE_ERROR_BADUTF8        (-10)
1810  .sp  .sp
1811  A string that contains an invalid UTF-8 byte sequence was passed as a subject.  A string that contains an invalid UTF-8 byte sequence was passed as a subject,
1812    and the PCRE_NO_UTF8_CHECK option was not set. If the size of the output vector
1813    (\fIovecsize\fP) is at least 2, the byte offset to the start of the the invalid
1814    UTF-8 character is placed in the first element, and a reason code is placed in
1815    the second element. The reason codes are listed in the
1816    .\" HTML <a href="#badutf8reasons">
1817    .\" </a>
1818    following section.
1819    .\"
1820    For backward compatibility, if PCRE_PARTIAL_HARD is set and the problem is a
1821    truncated UTF-8 character at the end of the subject (reason codes 1 to 5),
1822    PCRE_ERROR_SHORTUTF8 is returned instead of PCRE_ERROR_BADUTF8.
1823  .sp  .sp
1824    PCRE_ERROR_BADUTF8_OFFSET (-11)    PCRE_ERROR_BADUTF8_OFFSET (-11)
1825  .sp  .sp
1826  The UTF-8 byte sequence that was passed as a subject was valid, but the value  The UTF-8 byte sequence that was passed as a subject was checked and found to
1827  of \fIstartoffset\fP did not point to the beginning of a UTF-8 character.  be valid (the PCRE_NO_UTF8_CHECK option was not set), but the value of
1828    \fIstartoffset\fP did not point to the beginning of a UTF-8 character or the
1829    end of the subject.
1830  .sp  .sp
1831    PCRE_ERROR_PARTIAL        (-12)    PCRE_ERROR_PARTIAL        (-12)
1832  .sp  .sp
# Line 1430  documentation for details of partial mat Line 1838  documentation for details of partial mat
1838  .sp  .sp
1839    PCRE_ERROR_BADPARTIAL     (-13)    PCRE_ERROR_BADPARTIAL     (-13)
1840  .sp  .sp
1841  The PCRE_PARTIAL option was used with a compiled pattern containing items that  This code is no longer in use. It was formerly returned when the PCRE_PARTIAL
1842  are not supported for partial matching. See the  option was used with a compiled pattern containing items that were not
1843  .\" HREF  supported for partial matching. From release 8.00 onwards, there are no
1844  \fBpcrepartial\fP  restrictions on partial matching.
 .\"  
 documentation for details of partial matching.  
1845  .sp  .sp
1846    PCRE_ERROR_INTERNAL       (-14)    PCRE_ERROR_INTERNAL       (-14)
1847  .sp  .sp
# Line 1452  The internal recursion limit, as specifi Line 1858  The internal recursion limit, as specifi
1858  field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the  field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the
1859  description above.  description above.
1860  .sp  .sp
   PCRE_ERROR_NULLWSLIMIT    (-22)  
 .sp  
 When a group that can match an empty substring is repeated with an unbounded  
 upper limit, the subject position at the start of the group must be remembered,  
 so that a test for an empty string can be made when the end of the group is  
 reached. Some workspace is required for this; if it runs out, this error is  
 given.  
 .sp  
1861    PCRE_ERROR_BADNEWLINE     (-23)    PCRE_ERROR_BADNEWLINE     (-23)
1862  .sp  .sp
1863  An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.  An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
1864    .sp
1865      PCRE_ERROR_BADOFFSET      (-24)
1866    .sp
1867    The value of \fIstartoffset\fP was negative or greater than the length of the
1868    subject, that is, the value in \fIlength\fP.
1869    .sp
1870      PCRE_ERROR_SHORTUTF8      (-25)
1871    .sp
1872    This error is returned instead of PCRE_ERROR_BADUTF8 when the subject string
1873    ends with a truncated UTF-8 character and the PCRE_PARTIAL_HARD option is set.
1874    Information about the failure is returned as for PCRE_ERROR_BADUTF8. It is in
1875    fact sufficient to detect this case, but this special error code for
1876    PCRE_PARTIAL_HARD precedes the implementation of returned information; it is
1877    retained for backwards compatibility.
1878    .sp
1879      PCRE_ERROR_RECURSELOOP    (-26)
1880    .sp
1881    This error is returned when \fBpcre_exec()\fP detects a recursion loop within
1882    the pattern. Specifically, it means that either the whole pattern or a
1883    subpattern has been called recursively for the second time at the same position
1884    in the subject string. Some simple patterns that might do this are detected and
1885    faulted at compile time, but more complicated cases, in particular mutual
1886    recursions between two different subpatterns, cannot be detected until run
1887    time.
1888  .P  .P
1889  Error numbers -16 to -20 are not used by \fBpcre_exec()\fP.  Error numbers -16 to -20 and -22 are not used by \fBpcre_exec()\fP.
1890    .
1891    .
1892    .\" HTML <a name="badutf8reasons"></a>
1893    .SS "Reason codes for invalid UTF-8 strings"
1894    .rs
1895    .sp
1896    When \fBpcre_exec()\fP returns either PCRE_ERROR_BADUTF8 or
1897    PCRE_ERROR_SHORTUTF8, and the size of the output vector (\fIovecsize\fP) is at
1898    least 2, the offset of the start of the invalid UTF-8 character is placed in
1899    the first output vector element (\fIovector[0]\fP) and a reason code is placed
1900    in the second element (\fIovector[1]\fP). The reason codes are given names in
1901    the \fBpcre.h\fP header file:
1902    .sp
1903      PCRE_UTF8_ERR1
1904      PCRE_UTF8_ERR2
1905      PCRE_UTF8_ERR3
1906      PCRE_UTF8_ERR4
1907      PCRE_UTF8_ERR5
1908    .sp
1909    The string ends with a truncated UTF-8 character; the code specifies how many
1910    bytes are missing (1 to 5). Although RFC 3629 restricts UTF-8 characters to be
1911    no longer than 4 bytes, the encoding scheme (originally defined by RFC 2279)
1912    allows for up to 6 bytes, and this is checked first; hence the possibility of
1913    4 or 5 missing bytes.
1914    .sp
1915      PCRE_UTF8_ERR6
1916      PCRE_UTF8_ERR7
1917      PCRE_UTF8_ERR8
1918      PCRE_UTF8_ERR9
1919      PCRE_UTF8_ERR10
1920    .sp
1921    The two most significant bits of the 2nd, 3rd, 4th, 5th, or 6th byte of the
1922    character do not have the binary value 0b10 (that is, either the most
1923    significant bit is 0, or the next bit is 1).
1924    .sp
1925      PCRE_UTF8_ERR11
1926      PCRE_UTF8_ERR12
1927    .sp
1928    A character that is valid by the RFC 2279 rules is either 5 or 6 bytes long;
1929    these code points are excluded by RFC 3629.
1930    .sp
1931      PCRE_UTF8_ERR13
1932    .sp
1933    A 4-byte character has a value greater than 0x10fff; these code points are
1934    excluded by RFC 3629.
1935    .sp
1936      PCRE_UTF8_ERR14
1937    .sp
1938    A 3-byte character has a value in the range 0xd800 to 0xdfff; this range of
1939    code points are reserved by RFC 3629 for use with UTF-16, and so are excluded
1940    from UTF-8.
1941    .sp
1942      PCRE_UTF8_ERR15
1943      PCRE_UTF8_ERR16
1944      PCRE_UTF8_ERR17
1945      PCRE_UTF8_ERR18
1946      PCRE_UTF8_ERR19
1947    .sp
1948    A 2-, 3-, 4-, 5-, or 6-byte character is "overlong", that is, it codes for a
1949    value that can be represented by fewer bytes, which is invalid. For example,
1950    the two bytes 0xc0, 0xae give the value 0x2e, whose correct coding uses just
1951    one byte.
1952    .sp
1953      PCRE_UTF8_ERR20
1954    .sp
1955    The two most significant bits of the first byte of a character have the binary
1956    value 0b10 (that is, the most significant bit is 1 and the second is 0). Such a
1957    byte can only validly occur as the second or subsequent byte of a multi-byte
1958    character.
1959    .sp
1960      PCRE_UTF8_ERR21
1961    .sp
1962    The first byte of a character has the value 0xfe or 0xff. These values can
1963    never occur in a valid UTF-8 string.
1964  .  .
1965  .  .
1966  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
# Line 1476  Error numbers -16 to -20 are not used by Line 1972  Error numbers -16 to -20 are not used by
1972  .ti +5n  .ti +5n
1973  .B int \fIbuffersize\fP);  .B int \fIbuffersize\fP);
1974  .PP  .PP
 .br  
1975  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
1976  .ti +5n  .ti +5n
1977  .B int \fIstringcount\fP, int \fIstringnumber\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP,
1978  .ti +5n  .ti +5n
1979  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
1980  .PP  .PP
 .br  
1981  .B int pcre_get_substring_list(const char *\fIsubject\fP,  .B int pcre_get_substring_list(const char *\fIsubject\fP,
1982  .ti +5n  .ti +5n
1983  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"
# Line 1569  provided. Line 2063  provided.
2063  .ti +5n  .ti +5n
2064  .B const char *\fIname\fP);  .B const char *\fIname\fP);
2065  .PP  .PP
 .br  
2066  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
2067  .ti +5n  .ti +5n
2068  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1578  provided. Line 2071  provided.
2071  .ti +5n  .ti +5n
2072  .B char *\fIbuffer\fP, int \fIbuffersize\fP);  .B char *\fIbuffer\fP, int \fIbuffersize\fP);
2073  .PP  .PP
 .br  
2074  .B int pcre_get_named_substring(const pcre *\fIcode\fP,  .B int pcre_get_named_substring(const pcre *\fIcode\fP,
2075  .ti +5n  .ti +5n
2076  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1614  pattern. This is needed in order to gain Line 2106  pattern. This is needed in order to gain
2106  translation table.  translation table.
2107  .P  .P
2108  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they
2109  then call \fIpcre_copy_substring()\fP or \fIpcre_get_substring()\fP, as  then call \fBpcre_copy_substring()\fP or \fBpcre_get_substring()\fP, as
2110  appropriate.  appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names,
2111  .  the behaviour may not be what you want (see the next section).
2112    .P
2113    \fBWarning:\fP If the pattern uses the (?| feature to set up multiple
2114    subpatterns with the same number, as described in the
2115    .\" HTML <a href="pcrepattern.html#dupsubpatternnumber">
2116    .\" </a>
2117    section on duplicate subpattern numbers
2118    .\"
2119    in the
2120    .\" HREF
2121    \fBpcrepattern\fP
2122    .\"
2123    page, you cannot use names to distinguish the different subpatterns, because
2124    names are not included in the compiled code. The matching process uses only
2125    numbers. For this reason, the use of different names for subpatterns of the
2126    same number causes an error at compile time.
2127  .  .
2128  .SH "DUPLICATE SUBPATTERN NAMES"  .SH "DUPLICATE SUBPATTERN NAMES"
2129  .rs  .rs
# Line 1626  appropriate. Line 2133  appropriate.
2133  .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);  .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);
2134  .PP  .PP
2135  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
2136  are not required to be unique. Normally, patterns with duplicate names are such  are not required to be unique. (Duplicate names are always allowed for
2137  that in any one match, only one of the named subpatterns participates. An  subpatterns with the same number, created by using the (?| feature. Indeed, if
2138  example is shown in the  such subpatterns are named, they are required to use the same names.)
2139    .P
2140    Normally, patterns with duplicate names are such that in any one match, only
2141    one of the named subpatterns participates. An example is shown in the
2142  .\" HREF  .\" HREF
2143  \fBpcrepattern\fP  \fBpcrepattern\fP
2144  .\"  .\"
2145  documentation. When duplicates are present, \fBpcre_copy_named_substring()\fP  documentation.
2146  and \fBpcre_get_named_substring()\fP return the first substring corresponding  .P
2147  to the given name that is set. If none are set, an empty string is returned.  When duplicates are present, \fBpcre_copy_named_substring()\fP and
2148  The \fBpcre_get_stringnumber()\fP function returns one of the numbers that are  \fBpcre_get_named_substring()\fP return the first substring corresponding to
2149  associated with the name, but it is not defined which it is.  the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING (-7) is
2150  .sp  returned; no data is returned. The \fBpcre_get_stringnumber()\fP function
2151    returns one of the numbers that are associated with the name, but it is not
2152    defined which it is.
2153    .P
2154  If you want to get full details of all captured substrings for a given name,  If you want to get full details of all captured substrings for a given name,
2155  you must use the \fBpcre_get_stringtable_entries()\fP function. The first  you must use the \fBpcre_get_stringtable_entries()\fP function. The first
2156  argument is the compiled pattern, and the second is the name. The third and  argument is the compiled pattern, and the second is the name. The third and
# Line 1645  fourth are pointers to variables which a Line 2158  fourth are pointers to variables which a
2158  has run, they point to the first and last entries in the name-to-number table  has run, they point to the first and last entries in the name-to-number table
2159  for the given name. The function itself returns the length of each entry, or  for the given name. The function itself returns the length of each entry, or
2160  PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is  PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is
2161  described above in the section entitled \fIInformation about a pattern\fP.  described above in the section entitled \fIInformation about a pattern\fP
2162    .\" HTML <a href="#infoaboutpattern">
2163    .\" </a>
2164    above.
2165    .\"
2166  Given all the relevant entries for the name, you can extract each of their  Given all the relevant entries for the name, you can extract each of their
2167  numbers, and hence the captured data, if any.  numbers, and hence the captured data, if any.
2168  .  .
# Line 1689  a compiled pattern, using a matching alg Line 2206  a compiled pattern, using a matching alg
2206  just once, and does not backtrack. This has different characteristics to the  just once, and does not backtrack. This has different characteristics to the
2207  normal algorithm, and is not compatible with Perl. Some of the features of PCRE  normal algorithm, and is not compatible with Perl. Some of the features of PCRE
2208  patterns are not supported. Nevertheless, there are times when this kind of  patterns are not supported. Nevertheless, there are times when this kind of
2209  matching can be useful. For a discussion of the two matching algorithms, see  matching can be useful. For a discussion of the two matching algorithms, and a
2210  the  list of features that \fBpcre_dfa_exec()\fP does not support, see the
2211  .\" HREF  .\" HREF
2212  \fBpcrematching\fP  \fBpcrematching\fP
2213  .\"  .\"
# Line 1729  Here is an example of a simple call to \ Line 2246  Here is an example of a simple call to \
2246  .sp  .sp
2247  The unused bits of the \fIoptions\fP argument for \fBpcre_dfa_exec()\fP must be  The unused bits of the \fIoptions\fP argument for \fBpcre_dfa_exec()\fP must be
2248  zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,  zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,
2249  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL,  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART,
2250  PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last three of these are  PCRE_NO_UTF8_CHECK, PCRE_BSR_ANYCRLF, PCRE_BSR_UNICODE, PCRE_NO_START_OPTIMIZE,
2251  the same as for \fBpcre_exec()\fP, so their description is not repeated here.  PCRE_PARTIAL_HARD, PCRE_PARTIAL_SOFT, PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART.
2252  .sp  All but the last four of these are exactly the same as for \fBpcre_exec()\fP,
2253    PCRE_PARTIAL  so their description is not repeated here.
2254  .sp  .sp
2255  This has the same general effect as it does for \fBpcre_exec()\fP, but the    PCRE_PARTIAL_HARD
2256  details are slightly different. When PCRE_PARTIAL is set for    PCRE_PARTIAL_SOFT
2257  \fBpcre_dfa_exec()\fP, the return code PCRE_ERROR_NOMATCH is converted into  .sp
2258  PCRE_ERROR_PARTIAL if the end of the subject is reached, there have been no  These have the same general effect as they do for \fBpcre_exec()\fP, but the
2259  complete matches, but there is still at least one matching possibility. The  details are slightly different. When PCRE_PARTIAL_HARD is set for
2260  portion of the string that provided the partial match is set as the first  \fBpcre_dfa_exec()\fP, it returns PCRE_ERROR_PARTIAL if the end of the subject
2261  matching string.  is reached and there is still at least one matching possibility that requires
2262    additional characters. This happens even if some complete matches have also
2263    been found. When PCRE_PARTIAL_SOFT is set, the return code PCRE_ERROR_NOMATCH
2264    is converted into PCRE_ERROR_PARTIAL if the end of the subject is reached,
2265    there have been no complete matches, but there is still at least one matching
2266    possibility. The portion of the string that was inspected when the longest
2267    partial match was found is set as the first matching string in both cases.
2268    There is a more detailed discussion of partial and multi-segment matching, with
2269    examples, in the
2270    .\" HREF
2271    \fBpcrepartial\fP
2272    .\"
2273    documentation.
2274  .sp  .sp
2275    PCRE_DFA_SHORTEST    PCRE_DFA_SHORTEST
2276  .sp  .sp
# Line 1752  matching point in the subject string. Line 2281  matching point in the subject string.
2281  .sp  .sp
2282    PCRE_DFA_RESTART    PCRE_DFA_RESTART
2283  .sp  .sp
2284  When \fBpcre_dfa_exec()\fP is called with the PCRE_PARTIAL option, and returns  When \fBpcre_dfa_exec()\fP returns a partial match, it is possible to call it
2285  a partial match, it is possible to call it again, with additional subject  again, with additional subject characters, and have it continue with the same
2286  characters, and have it continue with the same match. The PCRE_DFA_RESTART  match. The PCRE_DFA_RESTART option requests this action; when it is set, the
2287  option requests this action; when it is set, the \fIworkspace\fP and  \fIworkspace\fP and \fIwscount\fP options must reference the same vector as
2288  \fIwscount\fP options must reference the same vector as before because data  before because data about the match so far is left in them after a partial
2289  about the match so far is left in them after a partial match. There is more  match. There is more discussion of this facility in the
 discussion of this facility in the  
2290  .\" HREF  .\" HREF
2291  \fBpcrepartial\fP  \fBpcrepartial\fP
2292  .\"  .\"
2293  documentation.  documentation.
2294  .  .
2295    .
2296  .SS "Successful returns from \fBpcre_dfa_exec()\fP"  .SS "Successful returns from \fBpcre_dfa_exec()\fP"
2297  .rs  .rs
2298  .sp  .sp
# Line 1797  matching string is given first. If there Line 2326  matching string is given first. If there
2326  \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
2327  the longest matches.  the longest matches.
2328  .  .
2329    .
2330  .SS "Error returns from \fBpcre_dfa_exec()\fP"  .SS "Error returns from \fBpcre_dfa_exec()\fP"
2331  .rs  .rs
2332  .sp  .sp
# Line 1846  extremely rare, as a vector of size 1000 Line 2376  extremely rare, as a vector of size 1000
2376  \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),  \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
2377  \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),  \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
2378  \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).  \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
2379  .P  .
2380  .in 0  .
2381  Last updated: 30 November 2006  .SH AUTHOR
2382  .br  .rs
2383  Copyright (c) 1997-2006 University of Cambridge.  .sp
2384    .nf
2385    Philip Hazel
2386    University Computing Service
2387    Cambridge CB2 3QH, England.
2388    .fi
2389    .
2390    .
2391    .SH REVISION
2392    .rs
2393    .sp
2394    .nf
2395    Last updated: 13 August 2011
2396    Copyright (c) 1997-2011 University of Cambridge.
2397    .fi

Legend:
Removed from v.96  
changed lines
  Added in v.659

webmaster@exim.org
ViewVC Help
Powered by ViewVC 1.1.12