/[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 91 by nigel, Sat Feb 24 21:41:34 2007 UTC revision 336 by ph10, Sat Apr 12 15:59:03 2008 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  .  .
112  .SH "PCRE API OVERVIEW"  .SH "PCRE API OVERVIEW"
113  .rs  .rs
114  .sp  .sp
115  PCRE has its own native API, which is described in this document. There is  PCRE has its own native API, which is described in this document. There are
116  also a set of wrapper functions that correspond to the POSIX regular expression  also some wrapper functions that correspond to the POSIX regular expression
117  API. These are described in the  API. These are described in the
118  .\" HREF  .\" HREF
119  \fBpcreposix\fP  \fBpcreposix\fP
# 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
147  matching. The alternative algorithm finds all possible matches (at a given  matching. The alternative algorithm finds all possible matches (at a given
148  point in the subject). However, this algorithm does not return captured  point in the subject), and scans the subject just once. However, this algorithm
149  substrings. A description of the two matching algorithms and their advantages  does not return captured substrings. A description of the two matching
150  and disadvantages is given in the  algorithms and their advantages and disadvantages is given in the
151  .\" HREF  .\" HREF
152  \fBpcrematching\fP  \fBpcrematching\fP
153  .\"  .\"
# 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  PCRE supports three different conventions for indicating line breaks in  .rs
 strings: a single CR character, a single LF character, or the two-character  
 sequence CRLF. All three are used as "standard" by different operating systems.  
 When PCRE is built, a default can be specified. The default default is LF,  
 which is the Unix standard. When PCRE is run, the default can be overridden,  
 either when a pattern is compiled, or when it is matched.  
224  .sp  .sp
225    PCRE supports five different conventions for indicating line breaks in
226    strings: a single CR (carriage return) character, a single LF (linefeed)
227    character, the two-character sequence CRLF, any of the three preceding, or any
228    Unicode newline sequence. The Unicode newline sequences are the three just
229    mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,
230    U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
231    (paragraph separator, U+2029).
232    .P
233    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.
235    The default default is LF, which is the Unix standard. When PCRE is run, the
236    default can be overridden, either when a pattern is compiled, or when it is
237    matched.
238    .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".  pair of characters that indicate a line break". The choice of newline
249    convention affects the handling of the dot, circumflex, and dollar
250    metacharacters, the handling of #-comments in /x mode, and, when CRLF is a
251    recognized line ending sequence, the match position advancement for a
252    non-anchored pattern. There is more detail about this in the
253    .\" 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 276  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 308  properties is available; otherwise it is Line 316  properties is available; otherwise it is
316    PCRE_CONFIG_NEWLINE    PCRE_CONFIG_NEWLINE
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 three values that are supported  that is recognized as meaning "newline". The four values that are supported
320  are: 10 for LF, 13 for CR, and 3338 for CRLF. The default should normally be  are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, and -1 for ANY. The
321  the standard sequence for your operating system.  default should normally be the standard sequence for your operating system.
322    .sp
323      PCRE_CONFIG_BSR
324    .sp
325    The output is an integer whose value indicates what character sequences the \eR
326    escape sequence matches by default. A value of 0 means that \eR matches any
327    Unicode line ending sequence; a value of 1 means that \eR matches only CR, LF,
328    or CRLF. The default can be overridden when a pattern is compiled or matched.
329  .sp  .sp
330    PCRE_CONFIG_LINK_SIZE    PCRE_CONFIG_LINK_SIZE
331  .sp  .sp
# Line 387  depend on memory location, the complete Line 402  depend on memory location, the complete
402  fully relocatable, because it may contain a copy of the \fItableptr\fP  fully relocatable, because it may contain a copy of the \fItableptr\fP
403  argument, which is an address (see below).  argument, which is an address (see below).
404  .P  .P
405  The \fIoptions\fP argument contains independent bits that affect the  The \fIoptions\fP argument contains various bit settings that affect the
406  compilation. It should be zero if no options are required. The available  compilation. It should be zero if no options are required. The available
407  options are described below. Some of them, in particular, those that are  options are described below. Some of them, in particular, those that are
408  compatible with Perl, can also be set and unset from within the pattern (see  compatible with Perl, can also be set and unset from within the pattern (see
# Line 453  facility, see the Line 468  facility, see the
468  .\"  .\"
469  documentation.  documentation.
470  .sp  .sp
471      PCRE_BSR_ANYCRLF
472      PCRE_BSR_UNICODE
473    .sp
474    These options (which are mutually exclusive) control what the \eR escape
475    sequence matches. The choice is either to match only CR, LF, or CRLF, or to
476    match any Unicode newline sequence. The default is specified when PCRE is
477    built. It can be overridden from within the pattern, or by setting an option
478    when a compiled pattern is matched.
479    .sp
480    PCRE_CASELESS    PCRE_CASELESS
481  .sp  .sp
482  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 480  If this bit is set, a dot metacharater i Line 504  If this bit is set, a dot metacharater i
504  including those that indicate newline. Without it, a dot does not match when  including those that indicate newline. Without it, a dot does not match when
505  the current position is at a newline. This option is equivalent to Perl's /s  the current position is at a newline. This option is equivalent to Perl's /s
506  option, and it can be changed within a pattern by a (?s) option setting. A  option, and it can be changed within a pattern by a (?s) option setting. A
507  negative class such as [^a] always matches newlines, independent of the setting  negative class such as [^a] always matches newline characters, independent of
508  of this option.  the setting of this option.
509  .sp  .sp
510    PCRE_DUPNAMES    PCRE_DUPNAMES
511  .sp  .sp
# Line 525  If this option is set, an unanchored pat Line 549  If this option is set, an unanchored pat
549  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
550  over the newline.  over the newline.
551  .sp  .sp
552      PCRE_JAVASCRIPT_COMPAT
553    .sp
554    If this option is set, PCRE's behaviour is changed in some ways so that it is
555    compatible with JavaScript rather than Perl. The changes are as follows:
556    .P
557    (1) A lone closing square bracket in a pattern causes a compile-time error,
558    because this is illegal in JavaScript (by default it is treated as a data
559    character). Thus, the pattern AB]CD becomes illegal when this option is set.
560    .P
561    (2) At run time, a back reference to an unset subpattern group matches an empty
562    string (by default this causes the current matching path to fail). A pattern
563    such as (\1)(a) succeeds when this option is set (assuming it can find an "a"
564    in the subject), whereas it fails by default, for Perl compatibility.
565    .sp
566    PCRE_MULTILINE    PCRE_MULTILINE
567  .sp  .sp
568  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 544  occurrences of ^ or $ in a pattern, sett Line 582  occurrences of ^ or $ in a pattern, sett
582    PCRE_NEWLINE_CR    PCRE_NEWLINE_CR
583    PCRE_NEWLINE_LF    PCRE_NEWLINE_LF
584    PCRE_NEWLINE_CRLF    PCRE_NEWLINE_CRLF
585      PCRE_NEWLINE_ANYCRLF
586      PCRE_NEWLINE_ANY
587  .sp  .sp
588  These options override the default newline definition that was chosen when PCRE  These options override the default newline definition that was chosen when PCRE
589  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
590  indicated by a single character (CR or LF, respectively). Setting both of them  indicated by a single character (CR or LF, respectively). Setting
591  specifies that a newline is indicated by the two-character CRLF sequence. For  PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character
592  convenience, PCRE_NEWLINE_CRLF is defined to contain both bits. The only time  CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three
593  that a line break is relevant when compiling a pattern is if PCRE_EXTENDED is  preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies
594  set, and an unescaped # outside a character class is encountered. This  that any Unicode newline sequence should be recognized. The Unicode newline
595  indicates a comment that lasts until after the next newline.  sequences are the three just mentioned, plus the single characters VT (vertical
596    tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line
597    separator, U+2028), and PS (paragraph separator, U+2029). The last two are
598    recognized only in UTF-8 mode.
599    .P
600    The newline setting in the options word uses three bits that are treated
601    as a number, giving eight possibilities. Currently only six are used (default
602    plus the five values above). This means that if you set more than one newline
603    option, the combination may or may not be sensible. For example,
604    PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but
605    other combinations may yield unused numbers and cause an error.
606    .P
607    The only time that a line break is specially recognized when compiling a
608    pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character
609    class is encountered. This indicates a comment that lasts until after the next
610    line break sequence. In other circumstances, line break sequences are treated
611    as literal data, except that in PCRE_EXTENDED mode, both CR and LF are treated
612    as whitespace characters and are therefore ignored.
613  .P  .P
614  The newline option set at compile time becomes the default that is used for  The newline option that is set at compile time becomes the default that is used
615  \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.
616  .sp  .sp
617    PCRE_NO_AUTO_CAPTURE    PCRE_NO_AUTO_CAPTURE
618  .sp  .sp
# Line 591  page. Line 648  page.
648    PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
649  .sp  .sp
650  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
651  automatically checked. If an invalid UTF-8 sequence of bytes is found,  automatically checked. There is a discussion about the
652  \fBpcre_compile()\fP returns an error. If you already know that your pattern is  .\" HTML <a href="pcre.html#utf8strings">
653  valid, and you want to skip this check for performance reasons, you can set the  .\" </a>
654  PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid  validity of UTF-8 strings
655  UTF-8 string as a pattern is undefined. It may cause your program to crash.  .\"
656  Note that this option can also be passed to \fBpcre_exec()\fP and  in the main
657  \fBpcre_dfa_exec()\fP, to suppress the UTF-8 validity checking of subject  .\" HREF
658  strings.  \fBpcre\fP
659    .\"
660    page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_compile()\fP
661    returns an error. If you already know that your pattern is valid, and you want
662    to skip this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK
663    option. When it is set, the effect of passing an invalid UTF-8 string as a
664    pattern is undefined. It may cause your program to crash. Note that this option
665    can also be passed to \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, to suppress
666    the UTF-8 validity checking of subject strings.
667  .  .
668  .  .
669  .SH "COMPILATION ERROR CODES"  .SH "COMPILATION ERROR CODES"
# Line 606  strings. Line 671  strings.
671  .sp  .sp
672  The following table lists the error codes than may be returned by  The following table lists the error codes than may be returned by
673  \fBpcre_compile2()\fP, along with the error messages that may be returned by  \fBpcre_compile2()\fP, along with the error messages that may be returned by
674  both compiling functions.  both compiling functions. As PCRE has developed, some error codes have fallen
675    out of use. To avoid confusion, they have not been re-used.
676  .sp  .sp
677     0  no error     0  no error
678     1  \e at end of pattern     1  \e at end of pattern
# Line 618  both compiling functions. Line 684  both compiling functions.
684     7  invalid escape sequence in character class     7  invalid escape sequence in character class
685     8  range out of order in character class     8  range out of order in character class
686     9  nothing to repeat     9  nothing to repeat
687    10  operand of unlimited repeat could match the empty string    10  [this code is not in use]
688    11  internal error: unexpected repeat    11  internal error: unexpected repeat
689    12  unrecognized character after (?    12  unrecognized character after (? or (?-
690    13  POSIX named classes are supported only within a class    13  POSIX named classes are supported only within a class
691    14  missing )    14  missing )
692    15  reference to non-existent subpattern    15  reference to non-existent subpattern
693    16  erroffset passed as NULL    16  erroffset passed as NULL
694    17  unknown option bit(s) set    17  unknown option bit(s) set
695    18  missing ) after comment    18  missing ) after comment
696    19  parentheses nested too deeply    19  [this code is not in use]
697    20  regular expression too large    20  regular expression is too large
698    21  failed to get memory    21  failed to get memory
699    22  unmatched parentheses    22  unmatched parentheses
700    23  internal error: code overflow    23  internal error: code overflow
# Line 637  both compiling functions. Line 703  both compiling functions.
703    26  malformed number or name after (?(    26  malformed number or name after (?(
704    27  conditional group contains more than two branches    27  conditional group contains more than two branches
705    28  assertion expected after (?(    28  assertion expected after (?(
706    29  (?R or (?digits must be followed by )    29  (?R or (?[+-]digits must be followed by )
707    30  unknown POSIX class name    30  unknown POSIX class name
708    31  POSIX collating elements are not supported    31  POSIX collating elements are not supported
709    32  this version of PCRE is not compiled with PCRE_UTF8 support    32  this version of PCRE is not compiled with PCRE_UTF8 support
710    33  spare error    33  [this code is not in use]
711    34  character value in \ex{...} sequence is too large    34  character value in \ex{...} sequence is too large
712    35  invalid condition (?(0)    35  invalid condition (?(0)
713    36  \eC not allowed in lookbehind assertion    36  \eC not allowed in lookbehind assertion
# Line 650  both compiling functions. Line 716  both compiling functions.
716    39  closing ) for (?C expected    39  closing ) for (?C expected
717    40  recursive call could loop indefinitely    40  recursive call could loop indefinitely
718    41  unrecognized character after (?P    41  unrecognized character after (?P
719    42  syntax error after (?P    42  syntax error in subpattern name (missing terminator)
720    43  two named subpatterns have the same name    43  two named subpatterns have the same name
721    44  invalid UTF-8 string    44  invalid UTF-8 string
722    45  support for \eP, \ep, and \eX has not been compiled    45  support for \eP, \ep, and \eX has not been compiled
723    46  malformed \eP or \ep sequence    46  malformed \eP or \ep sequence
724    47  unknown property name after \eP or \ep    47  unknown property name after \eP or \ep
725    48  subpattern name is too long (maximum 32 characters)    48  subpattern name is too long (maximum 32 characters)
726    49  too many named subpatterns (maximum 10,000)    49  too many named subpatterns (maximum 10000)
727    50  repeated subpattern is too long    50  [this code is not in use]
728    51  octal value is greater than \e377 (not in UTF-8 mode)    51  octal value is greater than \e377 (not in UTF-8 mode)
729      52  internal error: overran compiling workspace
730      53  internal error: previously-checked referenced subpattern not found
731      54  DEFINE group contains more than one branch
732      55  repeating a DEFINE group is not allowed
733      56  inconsistent NEWLINE options
734      57  \eg is not followed by a braced, angle-bracketed, or quoted
735            name/number or by a plain number
736      58  a numbered reference must not be zero
737      59  (*VERB) with an argument is not supported
738      60  (*VERB) not recognized
739      61  number is too big
740      62  subpattern name expected
741      63  digit expected after (?+
742      64  ] is an invalid data character in JavaScript compatibility mode
743    .sp
744    The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may
745    be used if the limits were changed when PCRE was built.
746  .  .
747  .  .
748  .SH "STUDYING A PATTERN"  .SH "STUDYING A PATTERN"
# Line 719  bytes is created. Line 802  bytes is created.
802  .SH "LOCALE SUPPORT"  .SH "LOCALE SUPPORT"
803  .rs  .rs
804  .sp  .sp
805  PCRE handles caseless matching, and determines whether characters are letters  PCRE handles caseless matching, and determines whether characters are letters,
806  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
807  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
808  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
809  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
810  support. The use of locales with Unicode is discouraged.  support. The use of locales with Unicode is discouraged. If you are handling
811  .P  characters with codes greater than 128, you should either use UTF-8 and
812  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.
813  built. This is used when the final argument of \fBpcre_compile()\fP is NULL,  .P
814  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
815  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.
816  default. As more and more applications change to using Unicode, the need for  Normally, the internal tables recognize only ASCII characters. However, when
817  this locale support is expected to die away.  PCRE is built, it is possible to cause the internal tables to be rebuilt in the
818    default "C" locale of the local system, which may cause them to be different.
819    .P
820    The internal tables can always be overridden by tables supplied by the
821    application that calls PCRE. These may be created in a different locale from
822    the default. As more and more applications change to using Unicode, the need
823    for this locale support is expected to die away.
824  .P  .P
825  External tables are built by calling the \fBpcre_maketables()\fP function,  External tables are built by calling the \fBpcre_maketables()\fP function,
826  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 744  the following code could be used: Line 833  the following code could be used:
833    tables = pcre_maketables();    tables = pcre_maketables();
834    re = pcre_compile(..., tables);    re = pcre_compile(..., tables);
835  .sp  .sp
836    The locale name "fr_FR" is used on Linux and other Unix-like systems; if you
837    are using Windows, the name for the French locale is "french".
838    .P
839  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
840  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
841  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 827  variable. (This option used to be called Line 919  variable. (This option used to be called
919  still recognized for backwards compatibility.)  still recognized for backwards compatibility.)
920  .P  .P
921  If there is a fixed first byte, for example, from a pattern such as  If there is a fixed first byte, for example, from a pattern such as
922  (cat|cow|coyote). Otherwise, if either  (cat|cow|coyote), its value is returned. Otherwise, if either
923  .sp  .sp
924  (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch  (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch
925  starts with "^", or  starts with "^", or
# Line 846  table indicating a fixed set of bytes fo Line 938  table indicating a fixed set of bytes fo
938  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
939  fourth argument should point to an \fBunsigned char *\fP variable.  fourth argument should point to an \fBunsigned char *\fP variable.
940  .sp  .sp
941      PCRE_INFO_HASCRORLF
942    .sp
943    Return 1 if the pattern contains any explicit matches for CR or LF characters,
944    otherwise 0. The fourth argument should point to an \fBint\fP variable. An
945    explicit match is either a literal CR or LF character, or \er or \en.
946    .sp
947      PCRE_INFO_JCHANGED
948    .sp
949    Return 1 if the (?J) or (?-J) option setting is used in the pattern, otherwise
950    0. The fourth argument should point to an \fBint\fP variable. (?J) and
951    (?-J) set and unset the local PCRE_DUPNAMES option, respectively.
952    .sp
953    PCRE_INFO_LASTLITERAL    PCRE_INFO_LASTLITERAL
954  .sp  .sp
955  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 882  their parentheses numbers. For example, Line 986  their parentheses numbers. For example,
986  PCRE_EXTENDED is set, so white space - including newlines - is ignored):  PCRE_EXTENDED is set, so white space - including newlines - is ignored):
987  .sp  .sp
988  .\" JOIN  .\" JOIN
989    (?P<date> (?P<year>(\ed\ed)?\ed\ed) -    (?<date> (?<year>(\ed\ed)?\ed\ed) -
990    (?P<month>\ed\ed) - (?P<day>\ed\ed) )    (?<month>\ed\ed) - (?<day>\ed\ed) )
991  .sp  .sp
992  There are four named subpatterns, so the table has four entries, and each entry  There are four named subpatterns, so the table has four entries, and each entry
993  in the table is eight bytes long. The table is as follows, with non-printing  in the table is eight bytes long. The table is as follows, with non-printing
# Line 898  When writing code to extract data from n Line 1002  When writing code to extract data from n
1002  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
1003  different for each compiled pattern.  different for each compiled pattern.
1004  .sp  .sp
1005      PCRE_INFO_OKPARTIAL
1006    .sp
1007    Return 1 if the pattern can be used for partial matching, otherwise 0. The
1008    fourth argument should point to an \fBint\fP variable. The
1009    .\" HREF
1010    \fBpcrepartial\fP
1011    .\"
1012    documentation lists the restrictions that apply to patterns when partial
1013    matching is used.
1014    .sp
1015    PCRE_INFO_OPTIONS    PCRE_INFO_OPTIONS
1016  .sp  .sp
1017  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
1018  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
1019  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
1020  top-level option settings within the pattern itself.  top-level option settings at the start of the pattern itself. In other words,
1021    they are the options that will be in force when matching starts. For example,
1022    if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the
1023    result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED.
1024  .P  .P
1025  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
1026  alternatives begin with one of the following:  alternatives begin with one of the following:
# Line 1114  called. See the Line 1231  called. See the
1231  .\"  .\"
1232  documentation for a discussion of saving compiled patterns for later use.  documentation for a discussion of saving compiled patterns for later use.
1233  .  .
1234    .\" HTML <a name="execoptions"></a>
1235  .SS "Option bits for \fBpcre_exec()\fP"  .SS "Option bits for \fBpcre_exec()\fP"
1236  .rs  .rs
1237  .sp  .sp
# Line 1128  matching position. If a pattern was comp Line 1246  matching position. If a pattern was comp
1246  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
1247  matching time.  matching time.
1248  .sp  .sp
1249      PCRE_BSR_ANYCRLF
1250      PCRE_BSR_UNICODE
1251    .sp
1252    These options (which are mutually exclusive) control what the \eR escape
1253    sequence matches. The choice is either to match only CR, LF, or CRLF, or to
1254    match any Unicode newline sequence. These options override the choice that was
1255    made or defaulted when the pattern was compiled.
1256    .sp
1257    PCRE_NEWLINE_CR    PCRE_NEWLINE_CR
1258    PCRE_NEWLINE_LF    PCRE_NEWLINE_LF
1259    PCRE_NEWLINE_CRLF    PCRE_NEWLINE_CRLF
1260      PCRE_NEWLINE_ANYCRLF
1261      PCRE_NEWLINE_ANY
1262  .sp  .sp
1263  These options override the newline definition that was chosen or defaulted when  These options override the newline definition that was chosen or defaulted when
1264  the pattern was compiled. For details, see the description \fBpcre_compile()\fP  the pattern was compiled. For details, see the description of
1265  above. During matching, the newline choice affects the behaviour of the dot,  \fBpcre_compile()\fP above. During matching, the newline choice affects the
1266  circumflex, and dollar metacharacters.  behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
1267    the way the match position is advanced after a match failure for an unanchored
1268    pattern.
1269    .P
1270    When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is set, and a
1271    match attempt for an unanchored pattern fails when the current position is at a
1272    CRLF sequence, and the pattern contains no explicit matches for CR or LF
1273    characters, the match position is advanced by two characters instead of one, in
1274    other words, to after the CRLF.
1275    .P
1276    The above rule is a compromise that makes the most common cases work as
1277    expected. For example, if the pattern is .+A (and the PCRE_DOTALL option is not
1278    set), it does not match the string "\er\enA" because, after failing at the
1279    start, it skips both the CR and the LF before retrying. However, the pattern
1280    [\er\en]A does match that string, because it contains an explicit CR or LF
1281    reference, and so advances only by one character after the first failure.
1282    .P
1283    An explicit match for CR of LF is either a literal appearance of one of those
1284    characters, or one of the \er or \en escape sequences. Implicit matches such as
1285    [^X] do not count, nor does \es (which includes CR and LF in the characters
1286    that it matches).
1287    .P
1288    Notwithstanding the above, anomalous effects may still occur when CRLF is a
1289    valid newline sequence and explicit \er or \en escapes appear in the pattern.
1290  .sp  .sp
1291    PCRE_NOTBOL    PCRE_NOTBOL
1292  .sp  .sp
# Line 1178  code that demonstrates how to do this in Line 1329  code that demonstrates how to do this in
1329  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
1330  string is automatically checked when \fBpcre_exec()\fP is subsequently called.  string is automatically checked when \fBpcre_exec()\fP is subsequently called.
1331  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
1332  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
1333  \fBpcre_exec()\fP returns the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP  strings in the
1334  contains an invalid value, PCRE_ERROR_BADUTF8_OFFSET is returned.  .\" HTML <a href="pcre.html#utf8strings">
1335    .\" </a>
1336    section on UTF-8 support
1337    .\"
1338    in the main
1339    .\" HREF
1340    \fBpcre\fP
1341    .\"
1342    page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_exec()\fP returns
1343    the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP contains an invalid value,
1344    PCRE_ERROR_BADUTF8_OFFSET is returned.
1345  .P  .P
1346  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
1347  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 1336  compiled in an environment of one endian Line 1497  compiled in an environment of one endian
1497  other endianness. This is the error that PCRE gives when the magic number is  other endianness. This is the error that PCRE gives when the magic number is
1498  not present.  not present.
1499  .sp  .sp
1500    PCRE_ERROR_UNKNOWN_NODE   (-5)    PCRE_ERROR_UNKNOWN_OPCODE (-5)
1501  .sp  .sp
1502  While running the pattern match, an unknown item was encountered in the  While running the pattern match, an unknown item was encountered in the
1503  compiled pattern. This error could be caused by a bug in PCRE or by overwriting  compiled pattern. This error could be caused by a bug in PCRE or by overwriting
# Line 1362  The backtracking limit, as specified by Line 1523  The backtracking limit, as specified by
1523  \fBpcre_extra\fP structure (or defaulted) was reached. See the description  \fBpcre_extra\fP structure (or defaulted) was reached. See the description
1524  above.  above.
1525  .sp  .sp
   PCRE_ERROR_RECURSIONLIMIT (-21)  
 .sp  
 The internal recursion limit, as specified by the \fImatch_limit_recursion\fP  
 field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the  
 description above.  
 .sp  
1526    PCRE_ERROR_CALLOUT        (-9)    PCRE_ERROR_CALLOUT        (-9)
1527  .sp  .sp
1528  This error is never generated by \fBpcre_exec()\fP itself. It is provided for  This error is never generated by \fBpcre_exec()\fP itself. It is provided for
# Line 1411  in PCRE or by overwriting of the compile Line 1566  in PCRE or by overwriting of the compile
1566    PCRE_ERROR_BADCOUNT       (-15)    PCRE_ERROR_BADCOUNT       (-15)
1567  .sp  .sp
1568  This error is given if the value of the \fIovecsize\fP argument is negative.  This error is given if the value of the \fIovecsize\fP argument is negative.
1569    .sp
1570      PCRE_ERROR_RECURSIONLIMIT (-21)
1571    .sp
1572    The internal recursion limit, as specified by the \fImatch_limit_recursion\fP
1573    field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the
1574    description above.
1575    .sp
1576      PCRE_ERROR_BADNEWLINE     (-23)
1577    .sp
1578    An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
1579    .P
1580    Error numbers -16 to -20 and -22 are not used by \fBpcre_exec()\fP.
1581  .  .
1582  .  .
1583  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
# Line 1422  This error is given if the value of the Line 1589  This error is given if the value of the
1589  .ti +5n  .ti +5n
1590  .B int \fIbuffersize\fP);  .B int \fIbuffersize\fP);
1591  .PP  .PP
 .br  
1592  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
1593  .ti +5n  .ti +5n
1594  .B int \fIstringcount\fP, int \fIstringnumber\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP,
1595  .ti +5n  .ti +5n
1596  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
1597  .PP  .PP
 .br  
1598  .B int pcre_get_substring_list(const char *\fIsubject\fP,  .B int pcre_get_substring_list(const char *\fIsubject\fP,
1599  .ti +5n  .ti +5n
1600  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"
# Line 1468  the string is placed in \fIbuffer\fP, wh Line 1633  the string is placed in \fIbuffer\fP, wh
1633  \fIbuffersize\fP, while for \fBpcre_get_substring()\fP a new block of memory is  \fIbuffersize\fP, while for \fBpcre_get_substring()\fP a new block of memory is
1634  obtained via \fBpcre_malloc\fP, and its address is returned via  obtained via \fBpcre_malloc\fP, and its address is returned via
1635  \fIstringptr\fP. The yield of the function is the length of the string, not  \fIstringptr\fP. The yield of the function is the length of the string, not
1636  including the terminating zero, or one of  including the terminating zero, or one of these error codes:
1637  .sp  .sp
1638    PCRE_ERROR_NOMEMORY       (-6)    PCRE_ERROR_NOMEMORY       (-6)
1639  .sp  .sp
# Line 1484  and builds a list of pointers to them. A Line 1649  and builds a list of pointers to them. A
1649  memory that is obtained via \fBpcre_malloc\fP. The address of the memory block  memory that is obtained via \fBpcre_malloc\fP. The address of the memory block
1650  is returned via \fIlistptr\fP, which is also the start of the list of string  is returned via \fIlistptr\fP, which is also the start of the list of string
1651  pointers. The end of the list is marked by a NULL pointer. The yield of the  pointers. The end of the list is marked by a NULL pointer. The yield of the
1652  function is zero if all went well, or  function is zero if all went well, or the error code
1653  .sp  .sp
1654    PCRE_ERROR_NOMEMORY       (-6)    PCRE_ERROR_NOMEMORY       (-6)
1655  .sp  .sp
# Line 1515  provided. Line 1680  provided.
1680  .ti +5n  .ti +5n
1681  .B const char *\fIname\fP);  .B const char *\fIname\fP);
1682  .PP  .PP
 .br  
1683  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
1684  .ti +5n  .ti +5n
1685  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1524  provided. Line 1688  provided.
1688  .ti +5n  .ti +5n
1689  .B char *\fIbuffer\fP, int \fIbuffersize\fP);  .B char *\fIbuffer\fP, int \fIbuffersize\fP);
1690  .PP  .PP
 .br  
1691  .B int pcre_get_named_substring(const pcre *\fIcode\fP,  .B int pcre_get_named_substring(const pcre *\fIcode\fP,
1692  .ti +5n  .ti +5n
1693  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1536  provided. Line 1699  provided.
1699  To extract a substring by name, you first have to find associated number.  To extract a substring by name, you first have to find associated number.
1700  For example, for this pattern  For example, for this pattern
1701  .sp  .sp
1702    (a+)b(?P<xxx>\ed+)...    (a+)b(?<xxx>\ed+)...
1703  .sp  .sp
1704  the number of the subpattern called "xxx" is 2. If the name is known to be  the number of the subpattern called "xxx" is 2. If the name is known to be
1705  unique (PCRE_DUPNAMES was not set), you can find the number from the name by  unique (PCRE_DUPNAMES was not set), you can find the number from the name by
# Line 1560  pattern. This is needed in order to gain Line 1723  pattern. This is needed in order to gain
1723  translation table.  translation table.
1724  .P  .P
1725  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they
1726  then call \fIpcre_copy_substring()\fP or \fIpcre_get_substring()\fP, as  then call \fBpcre_copy_substring()\fP or \fBpcre_get_substring()\fP, as
1727  appropriate.  appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names,
1728    the behaviour may not be what you want (see the next section).
1729  .  .
1730  .  .
1731  .SH "DUPLICATE SUBPATTERN NAMES"  .SH "DUPLICATE SUBPATTERN NAMES"
# Line 1578  example is shown in the Line 1742  example is shown in the
1742  .\" HREF  .\" HREF
1743  \fBpcrepattern\fP  \fBpcrepattern\fP
1744  .\"  .\"
1745  documentation. When duplicates are present, \fBpcre_copy_named_substring()\fP  documentation.
1746  and \fBpcre_get_named_substring()\fP return the first substring corresponding  .P
1747  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
1748  The \fBpcre_get_stringnumber()\fP function returns one of the numbers that are  \fBpcre_get_named_substring()\fP return the first substring corresponding to
1749  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
1750  .sp  returned; no data is returned. The \fBpcre_get_stringnumber()\fP function
1751    returns one of the numbers that are associated with the name, but it is not
1752    defined which it is.
1753    .P
1754  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,
1755  you must use the \fBpcre_get_stringtable_entries()\fP function. The first  you must use the \fBpcre_get_stringtable_entries()\fP function. The first
1756  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
1757  fourth are pointers to variables which are updated by the function. After it  fourth are pointers to variables which are updated by the function. After it
1758  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
1759  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
1760  PCRE_ERROR_NOSUBSTRING if there are none. The format of the table is described  PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is
1761  above in the section entitled \fIInformation about a pattern\fP. Given all the  described above in the section entitled \fIInformation about a pattern\fP.
1762  relevant entries for the name, you can extract each of their numbers, and hence  Given all the relevant entries for the name, you can extract each of their
1763  the captured data, if any.  numbers, and hence the captured data, if any.
1764  .  .
1765  .  .
1766  .SH "FINDING ALL POSSIBLE MATCHES"  .SH "FINDING ALL POSSIBLE MATCHES"
# Line 1631  will yield PCRE_ERROR_NOMATCH. Line 1798  will yield PCRE_ERROR_NOMATCH.
1798  .B int *\fIworkspace\fP, int \fIwscount\fP);  .B int *\fIworkspace\fP, int \fIwscount\fP);
1799  .P  .P
1800  The function \fBpcre_dfa_exec()\fP is called to match a subject string against  The function \fBpcre_dfa_exec()\fP is called to match a subject string against
1801  a compiled pattern, using a "DFA" matching algorithm. This has different  a compiled pattern, using a matching algorithm that scans the subject string
1802  characteristics to the normal algorithm, and is not compatible with Perl. Some  just once, and does not backtrack. This has different characteristics to the
1803  of the features of PCRE patterns are not supported. Nevertheless, there are  normal algorithm, and is not compatible with Perl. Some of the features of PCRE
1804  times when this kind of matching can be useful. For a discussion of the two  patterns are not supported. Nevertheless, there are times when this kind of
1805  matching algorithms, see the  matching can be useful. For a discussion of the two matching algorithms, see
1806    the
1807  .\" HREF  .\" HREF
1808  \fBpcrematching\fP  \fBpcrematching\fP
1809  .\"  .\"
# Line 1691  matching string. Line 1859  matching string.
1859    PCRE_DFA_SHORTEST    PCRE_DFA_SHORTEST
1860  .sp  .sp
1861  Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to stop as  Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to stop as
1862  soon as it has found one match. Because of the way the DFA algorithm works,  soon as it has found one match. Because of the way the alternative algorithm
1863  this is necessarily the shortest possible match at the first possible matching  works, this is necessarily the shortest possible match at the first possible
1864  point in the subject string.  matching point in the subject string.
1865  .sp  .sp
1866    PCRE_DFA_RESTART    PCRE_DFA_RESTART
1867  .sp  .sp
# Line 1732  the three matched strings are Line 1900  the three matched strings are
1900  On success, the yield of the function is a number greater than zero, which is  On success, the yield of the function is a number greater than zero, which is
1901  the number of matched substrings. The substrings themselves are returned in  the number of matched substrings. The substrings themselves are returned in
1902  \fIovector\fP. Each string uses two elements; the first is the offset to the  \fIovector\fP. Each string uses two elements; the first is the offset to the
1903  start, and the second is the offset to the end. All the strings have the same  start, and the second is the offset to the end. In fact, all the strings have
1904  start offset. (Space could have been saved by giving this only once, but it was  the same start offset. (Space could have been saved by giving this only once,
1905  decided to retain some compatibility with the way \fBpcre_exec()\fP returns  but it was decided to retain some compatibility with the way \fBpcre_exec()\fP
1906  data, even though the meaning of the strings is different.)  returns data, even though the meaning of the strings is different.)
1907  .P  .P
1908  The strings are returned in reverse order of length; that is, the longest  The strings are returned in reverse order of length; that is, the longest
1909  matching string is given first. If there were too many matches to fit into  matching string is given first. If there were too many matches to fit into
# Line 1762  that it does not support, for instance, Line 1930  that it does not support, for instance,
1930  .sp  .sp
1931    PCRE_ERROR_DFA_UCOND      (-17)    PCRE_ERROR_DFA_UCOND      (-17)
1932  .sp  .sp
1933  This return is given if \fBpcre_dfa_exec()\fP encounters a condition item in a  This return is given if \fBpcre_dfa_exec()\fP encounters a condition item that
1934  pattern that uses a back reference for the condition. This is not supported.  uses a back reference for the condition, or a test for recursion in a specific
1935    group. These are not supported.
1936  .sp  .sp
1937    PCRE_ERROR_DFA_UMLIMIT    (-18)    PCRE_ERROR_DFA_UMLIMIT    (-18)
1938  .sp  .sp
# Line 1782  When a recursive subpattern is processed Line 1951  When a recursive subpattern is processed
1951  recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This  recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This
1952  error is given if the output vector is not large enough. This should be  error is given if the output vector is not large enough. This should be
1953  extremely rare, as a vector of size 1000 is used.  extremely rare, as a vector of size 1000 is used.
1954  .P  .
1955  .in 0  .
1956  Last updated: 08 June 2006  .SH "SEE ALSO"
1957  .br  .rs
1958  Copyright (c) 1997-2006 University of Cambridge.  .sp
1959    \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
1960    \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
1961    \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
1962    .
1963    .
1964    .SH AUTHOR
1965    .rs
1966    .sp
1967    .nf
1968    Philip Hazel
1969    University Computing Service
1970    Cambridge CB2 3QH, England.
1971    .fi
1972    .
1973    .
1974    .SH REVISION
1975    .rs
1976    .sp
1977    .nf
1978    Last updated: 12 April 2008
1979    Copyright (c) 1997-2008 University of Cambridge.
1980    .fi

Legend:
Removed from v.91  
changed lines
  Added in v.336

  ViewVC Help
Powered by ViewVC 1.1.5