/[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 93 by nigel, Sat Feb 24 21:41:42 2007 UTC revision 391 by ph10, Tue Mar 17 21:16:01 2009 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 165  distribution. The Line 140  distribution. The
140  .\" HREF  .\" HREF
141  \fBpcresample\fP  \fBpcresample\fP
142  .\"  .\"
143  documentation describes how to run it.  documentation describes how to compile and run it.
144  .P  .P
145  A second matching function, \fBpcre_dfa_exec()\fP, which is not  A second matching function, \fBpcre_dfa_exec()\fP, which is not
146  Perl-compatible, is also provided. This uses a different algorithm for the  Perl-compatible, is also provided. This uses a different algorithm for the
# Line 243  points during a matching operation. Deta Line 218  points during a matching operation. Deta
218  documentation.  documentation.
219  .  .
220  .  .
221    .\" HTML <a name="newlines"></a>
222  .SH NEWLINES  .SH NEWLINES
223  .rs  .rs
224  .sp  .sp
225  PCRE supports four different conventions for indicating line breaks in  PCRE supports five different conventions for indicating line breaks in
226  strings: a single CR (carriage return) character, a single LF (linefeed)  strings: a single CR (carriage return) character, a single LF (linefeed)
227  character, the two-character sequence CRLF, or any Unicode newline sequence.  character, the two-character sequence CRLF, any of the three preceding, or any
228  The Unicode newline sequences are the three just mentioned, plus the single  Unicode newline sequence. The Unicode newline sequences are the three just
229  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,
230  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
231    (paragraph separator, U+2029).
232  .P  .P
233  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
234  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 236  The default default is LF, which is the
236  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
237  matched.  matched.
238  .P  .P
239    At compile time, the newline convention can be specified by the \fIoptions\fP
240    argument of \fBpcre_compile()\fP, or it can be specified by special text at the
241    start of the pattern itself; this overrides any other settings. See the
242    .\" HREF
243    \fBpcrepattern\fP
244    .\"
245    page for details of the special character sequences.
246    .P
247  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
248  pair of characters that indicate a line break". The choice of newline  pair of characters that indicate a line break". The choice of newline
249  convention affects the handling of the dot, circumflex, and dollar  convention affects the handling of the dot, circumflex, and dollar
250  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
251  recognized line ending sequence, the match position advancement for a  recognized line ending sequence, the match position advancement for a
252  non-anchored pattern. The choice of newline convention does not affect the  non-anchored pattern. There is more detail about this in the
253  interpretation of the \en or \er escape sequences.  .\" HTML <a href="#execoptions">
254    .\" </a>
255    section on \fBpcre_exec()\fP options
256    .\"
257    below.
258    .P
259    The choice of newline convention does not affect the interpretation of
260    the \en or \er escape sequences, nor does it affect what \eR matches, which is
261    controlled in a similar way, but by separate options.
262  .  .
263  .  .
264  .SH MULTITHREADING  .SH MULTITHREADING
# Line 289  which it was compiled. Details are given Line 282  which it was compiled. Details are given
282  .\" HREF  .\" HREF
283  \fBpcreprecompile\fP  \fBpcreprecompile\fP
284  .\"  .\"
285  documentation.  documentation. However, compiling a regular expression with one version of PCRE
286    for use with a different version is not guaranteed to work and may cause
287    crashes.
288  .  .
289  .  .
290  .SH "CHECKING BUILD-TIME OPTIONS"  .SH "CHECKING BUILD-TIME OPTIONS"
# Line 322  properties is available; otherwise it is Line 317  properties is available; otherwise it is
317  .sp  .sp
318  The output is an integer whose value specifies the default character sequence  The output is an integer whose value specifies the default character sequence
319  that is recognized as meaning "newline". The four values that are supported  that is recognized as meaning "newline". The four values that are supported
320  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.
321  normally be the standard sequence for your operating system.  Though they are derived from ASCII, the same values are returned in EBCDIC
322    environments. The default should normally correspond to the standard sequence
323    for your operating system.
324    .sp
325      PCRE_CONFIG_BSR
326    .sp
327    The output is an integer whose value indicates what character sequences the \eR
328    escape sequence matches by default. A value of 0 means that \eR matches any
329    Unicode line ending sequence; a value of 1 means that \eR matches only CR, LF,
330    or CRLF. The default can be overridden when a pattern is compiled or matched.
331  .sp  .sp
332    PCRE_CONFIG_LINK_SIZE    PCRE_CONFIG_LINK_SIZE
333  .sp  .sp
# Line 345  documentation. Line 349  documentation.
349  .sp  .sp
350    PCRE_CONFIG_MATCH_LIMIT    PCRE_CONFIG_MATCH_LIMIT
351  .sp  .sp
352  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
353  internal matching function calls in a \fBpcre_exec()\fP execution. Further  internal matching function calls in a \fBpcre_exec()\fP execution. Further
354  details are given with \fBpcre_exec()\fP below.  details are given with \fBpcre_exec()\fP below.
355  .sp  .sp
356    PCRE_CONFIG_MATCH_LIMIT_RECURSION    PCRE_CONFIG_MATCH_LIMIT_RECURSION
357  .sp  .sp
358  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
359  recursion when calling the internal matching function in a \fBpcre_exec()\fP  recursion when calling the internal matching function in a \fBpcre_exec()\fP
360  execution. Further details are given with \fBpcre_exec()\fP below.  execution. Further details are given with \fBpcre_exec()\fP below.
361  .sp  .sp
# Line 466  facility, see the Line 470  facility, see the
470  .\"  .\"
471  documentation.  documentation.
472  .sp  .sp
473      PCRE_BSR_ANYCRLF
474      PCRE_BSR_UNICODE
475    .sp
476    These options (which are mutually exclusive) control what the \eR escape
477    sequence matches. The choice is either to match only CR, LF, or CRLF, or to
478    match any Unicode newline sequence. The default is specified when PCRE is
479    built. It can be overridden from within the pattern, or by setting an option
480    when a compiled pattern is matched.
481    .sp
482    PCRE_CASELESS    PCRE_CASELESS
483  .sp  .sp
484  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 538  If this option is set, an unanchored pat Line 551  If this option is set, an unanchored pat
551  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
552  over the newline.  over the newline.
553  .sp  .sp
554      PCRE_JAVASCRIPT_COMPAT
555    .sp
556    If this option is set, PCRE's behaviour is changed in some ways so that it is
557    compatible with JavaScript rather than Perl. The changes are as follows:
558    .P
559    (1) A lone closing square bracket in a pattern causes a compile-time error,
560    because this is illegal in JavaScript (by default it is treated as a data
561    character). Thus, the pattern AB]CD becomes illegal when this option is set.
562    .P
563    (2) At run time, a back reference to an unset subpattern group matches an empty
564    string (by default this causes the current matching alternative to fail). A
565    pattern such as (\e1)(a) succeeds when this option is set (assuming it can find
566    an "a" in the subject), whereas it fails by default, for Perl compatibility.
567    .sp
568    PCRE_MULTILINE    PCRE_MULTILINE
569  .sp  .sp
570  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 584  occurrences of ^ or $ in a pattern, sett
584    PCRE_NEWLINE_CR    PCRE_NEWLINE_CR
585    PCRE_NEWLINE_LF    PCRE_NEWLINE_LF
586    PCRE_NEWLINE_CRLF    PCRE_NEWLINE_CRLF
587      PCRE_NEWLINE_ANYCRLF
588    PCRE_NEWLINE_ANY    PCRE_NEWLINE_ANY
589  .sp  .sp
590  These options override the default newline definition that was chosen when PCRE  These options override the default newline definition that was chosen when PCRE
591  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
592  indicated by a single character (CR or LF, respectively). Setting  indicated by a single character (CR or LF, respectively). Setting
593  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
594  CRLF sequence. Setting PCRE_NEWLINE_ANY specifies that any Unicode newline  CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three
595  sequence should be recognized. The Unicode newline sequences are the three just  preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies
596  mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,  that any Unicode newline sequence should be recognized. The Unicode newline
597  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
598  (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
599    separator, U+2028), and PS (paragraph separator, U+2029). The last two are
600    recognized only in UTF-8 mode.
601  .P  .P
602  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
603  as a number, giving eight possibilities. Currently only five are used (default  as a number, giving eight possibilities. Currently only six are used (default
604  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
605  option, the combination may or may not be sensible. For example,  option, the combination may or may not be sensible. For example,
606  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
607  other combinations yield unused numbers and cause an error.  other combinations may yield unused numbers and cause an error.
608  .P  .P
609  The only time that a line break is specially recognized when compiling a  The only time that a line break is specially recognized when compiling a
610  pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character  pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character
# Line 620  page. Line 650  page.
650    PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
651  .sp  .sp
652  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
653  automatically checked. If an invalid UTF-8 sequence of bytes is found,  automatically checked. There is a discussion about the
654  \fBpcre_compile()\fP returns an error. If you already know that your pattern is  .\" HTML <a href="pcre.html#utf8strings">
655  valid, and you want to skip this check for performance reasons, you can set the  .\" </a>
656  PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid  validity of UTF-8 strings
657  UTF-8 string as a pattern is undefined. It may cause your program to crash.  .\"
658  Note that this option can also be passed to \fBpcre_exec()\fP and  in the main
659  \fBpcre_dfa_exec()\fP, to suppress the UTF-8 validity checking of subject  .\" HREF
660  strings.  \fBpcre\fP
661    .\"
662    page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_compile()\fP
663    returns an error. If you already know that your pattern is valid, and you want
664    to skip this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK
665    option. When it is set, the effect of passing an invalid UTF-8 string as a
666    pattern is undefined. It may cause your program to crash. Note that this option
667    can also be passed to \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, to suppress
668    the UTF-8 validity checking of subject strings.
669  .  .
670  .  .
671  .SH "COMPILATION ERROR CODES"  .SH "COMPILATION ERROR CODES"
# Line 650  out of use. To avoid confusion, they hav Line 688  out of use. To avoid confusion, they hav
688     9  nothing to repeat     9  nothing to repeat
689    10  [this code is not in use]    10  [this code is not in use]
690    11  internal error: unexpected repeat    11  internal error: unexpected repeat
691    12  unrecognized character after (?    12  unrecognized character after (? or (?-
692    13  POSIX named classes are supported only within a class    13  POSIX named classes are supported only within a class
693    14  missing )    14  missing )
694    15  reference to non-existent subpattern    15  reference to non-existent subpattern
# Line 658  out of use. To avoid confusion, they hav Line 696  out of use. To avoid confusion, they hav
696    17  unknown option bit(s) set    17  unknown option bit(s) set
697    18  missing ) after comment    18  missing ) after comment
698    19  [this code is not in use]    19  [this code is not in use]
699    20  regular expression too large    20  regular expression is too large
700    21  failed to get memory    21  failed to get memory
701    22  unmatched parentheses    22  unmatched parentheses
702    23  internal error: code overflow    23  internal error: code overflow
# Line 667  out of use. To avoid confusion, they hav Line 705  out of use. To avoid confusion, they hav
705    26  malformed number or name after (?(    26  malformed number or name after (?(
706    27  conditional group contains more than two branches    27  conditional group contains more than two branches
707    28  assertion expected after (?(    28  assertion expected after (?(
708    29  (?R or (?digits must be followed by )    29  (?R or (?[+-]digits must be followed by )
709    30  unknown POSIX class name    30  unknown POSIX class name
710    31  POSIX collating elements are not supported    31  POSIX collating elements are not supported
711    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 687  out of use. To avoid confusion, they hav Line 725  out of use. To avoid confusion, they hav
725    46  malformed \eP or \ep sequence    46  malformed \eP or \ep sequence
726    47  unknown property name after \eP or \ep    47  unknown property name after \eP or \ep
727    48  subpattern name is too long (maximum 32 characters)    48  subpattern name is too long (maximum 32 characters)
728    49  too many named subpatterns (maximum 10,000)    49  too many named subpatterns (maximum 10000)
729    50  repeated subpattern is too long    50  [this code is not in use]
730    51  octal value is greater than \e377 (not in UTF-8 mode)    51  octal value is greater than \e377 (not in UTF-8 mode)
731    52  internal error: overran compiling workspace    52  internal error: overran compiling workspace
732    53  internal error: previously-checked referenced subpattern not found    53  internal error: previously-checked referenced subpattern not found
733    54  DEFINE group contains more than one branch    54  DEFINE group contains more than one branch
734    55  repeating a DEFINE group is not allowed    55  repeating a DEFINE group is not allowed
735    56  inconsistent NEWLINE options"    56  inconsistent NEWLINE options
736      57  \eg is not followed by a braced, angle-bracketed, or quoted
737            name/number or by a plain number
738      58  a numbered reference must not be zero
739      59  (*VERB) with an argument is not supported
740      60  (*VERB) not recognized
741      61  number is too big
742      62  subpattern name expected
743      63  digit expected after (?+
744      64  ] is an invalid data character in JavaScript compatibility mode
745    .sp
746    The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may
747    be used if the limits were changed when PCRE was built.
748  .  .
749  .  .
750  .SH "STUDYING A PATTERN"  .SH "STUDYING A PATTERN"
# Line 754  bytes is created. Line 804  bytes is created.
804  .SH "LOCALE SUPPORT"  .SH "LOCALE SUPPORT"
805  .rs  .rs
806  .sp  .sp
807  PCRE handles caseless matching, and determines whether characters are letters  PCRE handles caseless matching, and determines whether characters are letters,
808  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
809  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
810  less than 128. Higher-valued codes never match escapes such as \ew or \ed, but  less than 128. Higher-valued codes never match escapes such as \ew or \ed, but
811  can be tested with \ep if PCRE is built with Unicode character property  can be tested with \ep if PCRE is built with Unicode character property
812  support. The use of locales with Unicode is discouraged.  support. The use of locales with Unicode is discouraged. If you are handling
813  .P  characters with codes greater than 128, you should either use UTF-8 and
814  An internal set of tables is created in the default C locale when PCRE is  Unicode, or use locales, but not try to mix the two.
815  built. This is used when the final argument of \fBpcre_compile()\fP is NULL,  .P
816  and is sufficient for many applications. An alternative set of tables can,  PCRE contains an internal set of tables that are used when the final argument
817  however, be supplied. These may be created in a different locale from the  of \fBpcre_compile()\fP is NULL. These are sufficient for many applications.
818  default. As more and more applications change to using Unicode, the need for  Normally, the internal tables recognize only ASCII characters. However, when
819  this locale support is expected to die away.  PCRE is built, it is possible to cause the internal tables to be rebuilt in the
820    default "C" locale of the local system, which may cause them to be different.
821    .P
822    The internal tables can always be overridden by tables supplied by the
823    application that calls PCRE. These may be created in a different locale from
824    the default. As more and more applications change to using Unicode, the need
825    for this locale support is expected to die away.
826  .P  .P
827  External tables are built by calling the \fBpcre_maketables()\fP function,  External tables are built by calling the \fBpcre_maketables()\fP function,
828  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 835  the following code could be used:
835    tables = pcre_maketables();    tables = pcre_maketables();
836    re = pcre_compile(..., tables);    re = pcre_compile(..., tables);
837  .sp  .sp
838    The locale name "fr_FR" is used on Linux and other Unix-like systems; if you
839    are using Windows, the name for the French locale is "french".
840    .P
841  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
842  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
843  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 881  table indicating a fixed set of bytes fo Line 940  table indicating a fixed set of bytes fo
940  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
941  fourth argument should point to an \fBunsigned char *\fP variable.  fourth argument should point to an \fBunsigned char *\fP variable.
942  .sp  .sp
943      PCRE_INFO_HASCRORLF
944    .sp
945    Return 1 if the pattern contains any explicit matches for CR or LF characters,
946    otherwise 0. The fourth argument should point to an \fBint\fP variable. An
947    explicit match is either a literal CR or LF character, or \er or \en.
948    .sp
949      PCRE_INFO_JCHANGED
950    .sp
951    Return 1 if the (?J) or (?-J) option setting is used in the pattern, otherwise
952    0. The fourth argument should point to an \fBint\fP variable. (?J) and
953    (?-J) set and unset the local PCRE_DUPNAMES option, respectively.
954    .sp
955    PCRE_INFO_LASTLITERAL    PCRE_INFO_LASTLITERAL
956  .sp  .sp
957  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 933  When writing code to extract data from n Line 1004  When writing code to extract data from n
1004  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
1005  different for each compiled pattern.  different for each compiled pattern.
1006  .sp  .sp
1007      PCRE_INFO_OKPARTIAL
1008    .sp
1009    Return 1 if the pattern can be used for partial matching, otherwise 0. The
1010    fourth argument should point to an \fBint\fP variable. The
1011    .\" HREF
1012    \fBpcrepartial\fP
1013    .\"
1014    documentation lists the restrictions that apply to patterns when partial
1015    matching is used.
1016    .sp
1017    PCRE_INFO_OPTIONS    PCRE_INFO_OPTIONS
1018  .sp  .sp
1019  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
1020  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
1021  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
1022  top-level option settings within the pattern itself.  top-level option settings at the start of the pattern itself. In other words,
1023    they are the options that will be in force when matching starts. For example,
1024    if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the
1025    result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED.
1026  .P  .P
1027  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
1028  alternatives begin with one of the following:  alternatives begin with one of the following:
# Line 1149  called. See the Line 1233  called. See the
1233  .\"  .\"
1234  documentation for a discussion of saving compiled patterns for later use.  documentation for a discussion of saving compiled patterns for later use.
1235  .  .
1236    .\" HTML <a name="execoptions"></a>
1237  .SS "Option bits for \fBpcre_exec()\fP"  .SS "Option bits for \fBpcre_exec()\fP"
1238  .rs  .rs
1239  .sp  .sp
1240  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
1241  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,
1242  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK and PCRE_PARTIAL.  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_START_OPTIMIZE,
1243    PCRE_NO_UTF8_CHECK and PCRE_PARTIAL.
1244  .sp  .sp
1245    PCRE_ANCHORED    PCRE_ANCHORED
1246  .sp  .sp
# Line 1163  matching position. If a pattern was comp Line 1249  matching position. If a pattern was comp
1249  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
1250  matching time.  matching time.
1251  .sp  .sp
1252      PCRE_BSR_ANYCRLF
1253      PCRE_BSR_UNICODE
1254    .sp
1255    These options (which are mutually exclusive) control what the \eR escape
1256    sequence matches. The choice is either to match only CR, LF, or CRLF, or to
1257    match any Unicode newline sequence. These options override the choice that was
1258    made or defaulted when the pattern was compiled.
1259    .sp
1260    PCRE_NEWLINE_CR    PCRE_NEWLINE_CR
1261    PCRE_NEWLINE_LF    PCRE_NEWLINE_LF
1262    PCRE_NEWLINE_CRLF    PCRE_NEWLINE_CRLF
1263      PCRE_NEWLINE_ANYCRLF
1264    PCRE_NEWLINE_ANY    PCRE_NEWLINE_ANY
1265  .sp  .sp
1266  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 1268  the pattern was compiled. For details, s
1268  \fBpcre_compile()\fP above. During matching, the newline choice affects the  \fBpcre_compile()\fP above. During matching, the newline choice affects the
1269  behaviour of the dot, circumflex, and dollar metacharacters. It may also alter  behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
1270  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
1271  pattern. When PCRE_NEWLINE_CRLF or PCRE_NEWLINE_ANY is set, and a match attempt  pattern.
1272  fails when the current position is at a CRLF sequence, the match position is  .P
1273  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
1274    match attempt for an unanchored pattern fails when the current position is at a
1275    CRLF sequence, and the pattern contains no explicit matches for CR or LF
1276    characters, the match position is advanced by two characters instead of one, in
1277    other words, to after the CRLF.
1278    .P
1279    The above rule is a compromise that makes the most common cases work as
1280    expected. For example, if the pattern is .+A (and the PCRE_DOTALL option is not
1281    set), it does not match the string "\er\enA" because, after failing at the
1282    start, it skips both the CR and the LF before retrying. However, the pattern
1283    [\er\en]A does match that string, because it contains an explicit CR or LF
1284    reference, and so advances only by one character after the first failure.
1285    .P
1286    An explicit match for CR of LF is either a literal appearance of one of those
1287    characters, or one of the \er or \en escape sequences. Implicit matches such as
1288    [^X] do not count, nor does \es (which includes CR and LF in the characters
1289    that it matches).
1290    .P
1291    Notwithstanding the above, anomalous effects may still occur when CRLF is a
1292    valid newline sequence and explicit \er or \en escapes appear in the pattern.
1293  .sp  .sp
1294    PCRE_NOTBOL    PCRE_NOTBOL
1295  .sp  .sp
# Line 1213  PCRE_NOTEMPTY and PCRE_ANCHORED, and the Line 1327  PCRE_NOTEMPTY and PCRE_ANCHORED, and the
1327  starting offset (see below) and trying an ordinary match again. There is some  starting offset (see below) and trying an ordinary match again. There is some
1328  code that demonstrates how to do this in the \fIpcredemo.c\fP sample program.  code that demonstrates how to do this in the \fIpcredemo.c\fP sample program.
1329  .sp  .sp
1330      PCRE_NO_START_OPTIMIZE
1331    .sp
1332    There are a number of optimizations that \fBpcre_exec()\fP uses at the start of
1333    a match, in order to speed up the process. For example, if it is known that a
1334    match must start with a specific character, it searches the subject for that
1335    character, and fails immediately if it cannot find it, without actually running
1336    the main matching function. When callouts are in use, these optimizations can
1337    cause them to be skipped. This option disables the "start-up" optimizations,
1338    causing performance to suffer, but ensuring that the callouts do occur.
1339    .sp
1340    PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
1341  .sp  .sp
1342  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
1343  string is automatically checked when \fBpcre_exec()\fP is subsequently called.  string is automatically checked when \fBpcre_exec()\fP is subsequently called.
1344  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
1345  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
1346  \fBpcre_exec()\fP returns the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP  strings in the
1347  contains an invalid value, PCRE_ERROR_BADUTF8_OFFSET is returned.  .\" HTML <a href="pcre.html#utf8strings">
1348    .\" </a>
1349    section on UTF-8 support
1350    .\"
1351    in the main
1352    .\" HREF
1353    \fBpcre\fP
1354    .\"
1355    page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_exec()\fP returns
1356    the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP contains an invalid value,
1357    PCRE_ERROR_BADUTF8_OFFSET is returned.
1358  .P  .P
1359  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
1360  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
# Line 1250  documentation. Line 1384  documentation.
1384  .rs  .rs
1385  .sp  .sp
1386  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
1387  \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
1388  \fIstartoffset\fP. In UTF-8 mode, the byte offset must point to the start of a  in \fIstartoffset\fP. In UTF-8 mode, the byte offset must point to the start of
1389  UTF-8 character. Unlike the pattern string, the subject may contain binary zero  a UTF-8 character. Unlike the pattern string, the subject may contain binary
1390  bytes. When the starting offset is zero, the search for a match starts at the  zero bytes. When the starting offset is zero, the search for a match starts at
1391  beginning of the subject, and this is by far the most common case.  the beginning of the subject, and this is by far the most common case.
1392  .P  .P
1393  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
1394  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 1288  pattern. Following the usage in Jeffrey Line 1422  pattern. Following the usage in Jeffrey
1422  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
1423  kinds of parenthesized subpattern that do not cause substrings to be captured.  kinds of parenthesized subpattern that do not cause substrings to be captured.
1424  .P  .P
1425  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
1426  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
1427  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
1428  this argument is NOT the size of \fIovector\fP in bytes.  argument is NOT the size of \fIovector\fP in bytes.
1429  .P  .P
1430  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,
1431  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
1432  used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns,  used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns,
1433  and is not available for passing back information. The length passed in  and is not available for passing back information. The number passed in
1434  \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
1435  rounded down.  rounded down.
1436  .P  .P
1437  When a match is successful, information about captured substrings is returned  When a match is successful, information about captured substrings is returned
1438  in pairs of integers, starting at the beginning of \fIovector\fP, and  in pairs of integers, starting at the beginning of \fIovector\fP, and
1439  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
1440  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
1441  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
1442  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
1443  subject string matched by the entire pattern. The next pair is used for the  mode. They are not character counts.
1444  first capturing subpattern, and so on. The value returned by \fBpcre_exec()\fP  .P
1445  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
1446  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
1447  capturing subpatterns, the return value from a successful match is 1,  used for the first capturing subpattern, and so on. The value returned by
1448  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.
1449    For example, if two substrings have been captured, the returned value is 3. If
1450    there are no capturing subpatterns, the return value from a successful match is
1451    1, indicating that just the first pair of offsets has been set.
1452  .P  .P
1453  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
1454  string that it matched that is returned.  string that it matched that is returned.
1455  .P  .P
1456  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
1457  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
1458  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,
1459  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
1460  \fIovecsize\fP as zero. However, if the pattern contains back references and  \fIovecsize\fP as zero. However, if the pattern contains back references and
1461  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
1462  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
# Line 1452  The internal recursion limit, as specifi Line 1589  The internal recursion limit, as specifi
1589  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
1590  description above.  description above.
1591  .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  
1592    PCRE_ERROR_BADNEWLINE     (-23)    PCRE_ERROR_BADNEWLINE     (-23)
1593  .sp  .sp
1594  An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.  An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
1595  .P  .P
1596  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.
1597  .  .
1598  .  .
1599  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
# Line 1476  Error numbers -16 to -20 are not used by Line 1605  Error numbers -16 to -20 are not used by
1605  .ti +5n  .ti +5n
1606  .B int \fIbuffersize\fP);  .B int \fIbuffersize\fP);
1607  .PP  .PP
 .br  
1608  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
1609  .ti +5n  .ti +5n
1610  .B int \fIstringcount\fP, int \fIstringnumber\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP,
1611  .ti +5n  .ti +5n
1612  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
1613  .PP  .PP
 .br  
1614  .B int pcre_get_substring_list(const char *\fIsubject\fP,  .B int pcre_get_substring_list(const char *\fIsubject\fP,
1615  .ti +5n  .ti +5n
1616  .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 1696  provided.
1696  .ti +5n  .ti +5n
1697  .B const char *\fIname\fP);  .B const char *\fIname\fP);
1698  .PP  .PP
 .br  
1699  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
1700  .ti +5n  .ti +5n
1701  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1578  provided. Line 1704  provided.
1704  .ti +5n  .ti +5n
1705  .B char *\fIbuffer\fP, int \fIbuffersize\fP);  .B char *\fIbuffer\fP, int \fIbuffersize\fP);
1706  .PP  .PP
 .br  
1707  .B int pcre_get_named_substring(const pcre *\fIcode\fP,  .B int pcre_get_named_substring(const pcre *\fIcode\fP,
1708  .ti +5n  .ti +5n
1709  .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 1739  pattern. This is needed in order to gain
1739  translation table.  translation table.
1740  .P  .P
1741  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they
1742  then call \fIpcre_copy_substring()\fP or \fIpcre_get_substring()\fP, as  then call \fBpcre_copy_substring()\fP or \fBpcre_get_substring()\fP, as
1743  appropriate.  appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names,
1744  .  the behaviour may not be what you want (see the next section).
1745    .P
1746    \fBWarning:\fP If the pattern uses the "(?|" feature to set up multiple
1747    subpatterns with the same number, you cannot use names to distinguish them,
1748    because names are not included in the compiled code. The matching process uses
1749    only numbers.
1750  .  .
1751  .SH "DUPLICATE SUBPATTERN NAMES"  .SH "DUPLICATE SUBPATTERN NAMES"
1752  .rs  .rs
# Line 1632  example is shown in the Line 1762  example is shown in the
1762  .\" HREF  .\" HREF
1763  \fBpcrepattern\fP  \fBpcrepattern\fP
1764  .\"  .\"
1765  documentation. When duplicates are present, \fBpcre_copy_named_substring()\fP  documentation.
1766  and \fBpcre_get_named_substring()\fP return the first substring corresponding  .P
1767  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
1768  The \fBpcre_get_stringnumber()\fP function returns one of the numbers that are  \fBpcre_get_named_substring()\fP return the first substring corresponding to
1769  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
1770  .sp  returned; no data is returned. The \fBpcre_get_stringnumber()\fP function
1771    returns one of the numbers that are associated with the name, but it is not
1772    defined which it is.
1773    .P
1774  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,
1775  you must use the \fBpcre_get_stringtable_entries()\fP function. The first  you must use the \fBpcre_get_stringtable_entries()\fP function. The first
1776  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 1846  extremely rare, as a vector of size 1000 Line 1979  extremely rare, as a vector of size 1000
1979  \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),  \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
1980  \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),  \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
1981  \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).  \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
1982  .P  .
1983  .in 0  .
1984  Last updated: 30 November 2006  .SH AUTHOR
1985  .br  .rs
1986  Copyright (c) 1997-2006 University of Cambridge.  .sp
1987    .nf
1988    Philip Hazel
1989    University Computing Service
1990    Cambridge CB2 3QH, England.
1991    .fi
1992    .
1993    .
1994    .SH REVISION
1995    .rs
1996    .sp
1997    .nf
1998    Last updated: 17 March 2009
1999    Copyright (c) 1997-2009 University of Cambridge.
2000    .fi

Legend:
Removed from v.93  
changed lines
  Added in v.391

  ViewVC Help
Powered by ViewVC 1.1.5