/[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 226 by ph10, Tue Aug 21 11:46:08 2007 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 170  documentation describes how to run it. Line 145  documentation describes how to run it.
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 244  documentation. Line 219  documentation.
219  .  .
220  .  .
221  .SH NEWLINES  .SH NEWLINES
222  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.  
223  .sp  .sp
224    PCRE supports five different conventions for indicating line breaks in
225    strings: a single CR (carriage return) character, a single LF (linefeed)
226    character, the two-character sequence CRLF, any of the three preceding, or any
227    Unicode newline sequence. The Unicode newline sequences are the three just
228    mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,
229    U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
230    (paragraph separator, U+2029).
231    .P
232    Each of the first three conventions is used by at least one operating system as
233    its standard newline sequence. When PCRE is built, a default can be specified.
234    The default default is LF, which is the Unix standard. When PCRE is run, the
235    default can be overridden, either when a pattern is compiled, or when it is
236    matched.
237    .P
238  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
239  pair of characters that indicate a line break".  pair of characters that indicate a line break". The choice of newline
240    convention affects the handling of the dot, circumflex, and dollar
241    metacharacters, the handling of #-comments in /x mode, and, when CRLF is a
242    recognized line ending sequence, the match position advancement for a
243    non-anchored pattern. There is more detail about this in the
244    .\" HTML <a href="#execoptions">
245    .\" </a>
246    section on \fBpcre_exec()\fP options
247    .\"
248    below. The choice of newline convention does not affect the interpretation of
249    the \en or \er escape sequences.
250  .  .
251  .  .
252  .SH MULTITHREADING  .SH MULTITHREADING
# Line 276  which it was compiled. Details are given Line 270  which it was compiled. Details are given
270  .\" HREF  .\" HREF
271  \fBpcreprecompile\fP  \fBpcreprecompile\fP
272  .\"  .\"
273  documentation.  documentation. However, compiling a regular expression with one version of PCRE
274    for use with a different version is not guaranteed to work and may cause
275    crashes.
276  .  .
277  .  .
278  .SH "CHECKING BUILD-TIME OPTIONS"  .SH "CHECKING BUILD-TIME OPTIONS"
# Line 308  properties is available; otherwise it is Line 304  properties is available; otherwise it is
304    PCRE_CONFIG_NEWLINE    PCRE_CONFIG_NEWLINE
305  .sp  .sp
306  The output is an integer whose value specifies the default character sequence  The output is an integer whose value specifies the default character sequence
307  that is recognized as meaning "newline". The three values that are supported  that is recognized as meaning "newline". The four values that are supported
308  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
309  the standard sequence for your operating system.  default should normally be the standard sequence for your operating system.
310  .sp  .sp
311    PCRE_CONFIG_LINK_SIZE    PCRE_CONFIG_LINK_SIZE
312  .sp  .sp
# Line 387  depend on memory location, the complete Line 383  depend on memory location, the complete
383  fully relocatable, because it may contain a copy of the \fItableptr\fP  fully relocatable, because it may contain a copy of the \fItableptr\fP
384  argument, which is an address (see below).  argument, which is an address (see below).
385  .P  .P
386  The \fIoptions\fP argument contains independent bits that affect the  The \fIoptions\fP argument contains various bit settings that affect the
387  compilation. It should be zero if no options are required. The available  compilation. It should be zero if no options are required. The available
388  options are described below. Some of them, in particular, those that are  options are described below. Some of them, in particular, those that are
389  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 480  If this bit is set, a dot metacharater i Line 476  If this bit is set, a dot metacharater i
476  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
477  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
478  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
479  negative class such as [^a] always matches newlines, independent of the setting  negative class such as [^a] always matches newline characters, independent of
480  of this option.  the setting of this option.
481  .sp  .sp
482    PCRE_DUPNAMES    PCRE_DUPNAMES
483  .sp  .sp
# Line 544  occurrences of ^ or $ in a pattern, sett Line 540  occurrences of ^ or $ in a pattern, sett
540    PCRE_NEWLINE_CR    PCRE_NEWLINE_CR
541    PCRE_NEWLINE_LF    PCRE_NEWLINE_LF
542    PCRE_NEWLINE_CRLF    PCRE_NEWLINE_CRLF
543      PCRE_NEWLINE_ANYCRLF
544      PCRE_NEWLINE_ANY
545  .sp  .sp
546  These options override the default newline definition that was chosen when PCRE  These options override the default newline definition that was chosen when PCRE
547  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
548  indicated by a single character (CR or LF, respectively). Setting both of them  indicated by a single character (CR or LF, respectively). Setting
549  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
550  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
551  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
552  set, and an unescaped # outside a character class is encountered. This  that any Unicode newline sequence should be recognized. The Unicode newline
553  indicates a comment that lasts until after the next newline.  sequences are the three just mentioned, plus the single characters VT (vertical
554    tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line
555    separator, U+2028), and PS (paragraph separator, U+2029). The last two are
556    recognized only in UTF-8 mode.
557    .P
558    The newline setting in the options word uses three bits that are treated
559    as a number, giving eight possibilities. Currently only six are used (default
560    plus the five values above). This means that if you set more than one newline
561    option, the combination may or may not be sensible. For example,
562    PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but
563    other combinations may yield unused numbers and cause an error.
564    .P
565    The only time that a line break is specially recognized when compiling a
566    pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character
567    class is encountered. This indicates a comment that lasts until after the next
568    line break sequence. In other circumstances, line break sequences are treated
569    as literal data, except that in PCRE_EXTENDED mode, both CR and LF are treated
570    as whitespace characters and are therefore ignored.
571  .P  .P
572  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
573  \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.
574  .sp  .sp
575    PCRE_NO_AUTO_CAPTURE    PCRE_NO_AUTO_CAPTURE
576  .sp  .sp
# Line 591  page. Line 606  page.
606    PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
607  .sp  .sp
608  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
609  automatically checked. If an invalid UTF-8 sequence of bytes is found,  automatically checked. There is a discussion about the
610  \fBpcre_compile()\fP returns an error. If you already know that your pattern is  .\" HTML <a href="pcre.html#utf8strings">
611  valid, and you want to skip this check for performance reasons, you can set the  .\" </a>
612  PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid  validity of UTF-8 strings
613  UTF-8 string as a pattern is undefined. It may cause your program to crash.  .\"
614  Note that this option can also be passed to \fBpcre_exec()\fP and  in the main
615  \fBpcre_dfa_exec()\fP, to suppress the UTF-8 validity checking of subject  .\" HREF
616  strings.  \fBpcre\fP
617    .\"
618    page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_compile()\fP
619    returns an error. If you already know that your pattern is valid, and you want
620    to skip this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK
621    option. When it is set, the effect of passing an invalid UTF-8 string as a
622    pattern is undefined. It may cause your program to crash. Note that this option
623    can also be passed to \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, to suppress
624    the UTF-8 validity checking of subject strings.
625  .  .
626  .  .
627  .SH "COMPILATION ERROR CODES"  .SH "COMPILATION ERROR CODES"
# Line 606  strings. Line 629  strings.
629  .sp  .sp
630  The following table lists the error codes than may be returned by  The following table lists the error codes than may be returned by
631  \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
632  both compiling functions.  both compiling functions. As PCRE has developed, some error codes have fallen
633    out of use. To avoid confusion, they have not been re-used.
634  .sp  .sp
635     0  no error     0  no error
636     1  \e at end of pattern     1  \e at end of pattern
# Line 618  both compiling functions. Line 642  both compiling functions.
642     7  invalid escape sequence in character class     7  invalid escape sequence in character class
643     8  range out of order in character class     8  range out of order in character class
644     9  nothing to repeat     9  nothing to repeat
645    10  operand of unlimited repeat could match the empty string    10  [this code is not in use]
646    11  internal error: unexpected repeat    11  internal error: unexpected repeat
647    12  unrecognized character after (?    12  unrecognized character after (?
648    13  POSIX named classes are supported only within a class    13  POSIX named classes are supported only within a class
# Line 627  both compiling functions. Line 651  both compiling functions.
651    16  erroffset passed as NULL    16  erroffset passed as NULL
652    17  unknown option bit(s) set    17  unknown option bit(s) set
653    18  missing ) after comment    18  missing ) after comment
654    19  parentheses nested too deeply    19  [this code is not in use]
655    20  regular expression too large    20  regular expression too large
656    21  failed to get memory    21  failed to get memory
657    22  unmatched parentheses    22  unmatched parentheses
# Line 637  both compiling functions. Line 661  both compiling functions.
661    26  malformed number or name after (?(    26  malformed number or name after (?(
662    27  conditional group contains more than two branches    27  conditional group contains more than two branches
663    28  assertion expected after (?(    28  assertion expected after (?(
664    29  (?R or (?digits must be followed by )    29  (?R or (?[+-]digits must be followed by )
665    30  unknown POSIX class name    30  unknown POSIX class name
666    31  POSIX collating elements are not supported    31  POSIX collating elements are not supported
667    32  this version of PCRE is not compiled with PCRE_UTF8 support    32  this version of PCRE is not compiled with PCRE_UTF8 support
668    33  spare error    33  [this code is not in use]
669    34  character value in \ex{...} sequence is too large    34  character value in \ex{...} sequence is too large
670    35  invalid condition (?(0)    35  invalid condition (?(0)
671    36  \eC not allowed in lookbehind assertion    36  \eC not allowed in lookbehind assertion
# Line 650  both compiling functions. Line 674  both compiling functions.
674    39  closing ) for (?C expected    39  closing ) for (?C expected
675    40  recursive call could loop indefinitely    40  recursive call could loop indefinitely
676    41  unrecognized character after (?P    41  unrecognized character after (?P
677    42  syntax error after (?P    42  syntax error in subpattern name (missing terminator)
678    43  two named subpatterns have the same name    43  two named subpatterns have the same name
679    44  invalid UTF-8 string    44  invalid UTF-8 string
680    45  support for \eP, \ep, and \eX has not been compiled    45  support for \eP, \ep, and \eX has not been compiled
# Line 658  both compiling functions. Line 682  both compiling functions.
682    47  unknown property name after \eP or \ep    47  unknown property name after \eP or \ep
683    48  subpattern name is too long (maximum 32 characters)    48  subpattern name is too long (maximum 32 characters)
684    49  too many named subpatterns (maximum 10,000)    49  too many named subpatterns (maximum 10,000)
685    50  repeated subpattern is too long    50  [this code is not in use]
686    51  octal value is greater than \e377 (not in UTF-8 mode)    51  octal value is greater than \e377 (not in UTF-8 mode)
687      52  internal error: overran compiling workspace
688      53  internal error: previously-checked referenced subpattern not found
689      54  DEFINE group contains more than one branch
690      55  repeating a DEFINE group is not allowed
691      56  inconsistent NEWLINE options"
692      57  \eg is not followed by a braced name or an optionally braced
693            non-zero number
694      58  (?+ or (?- or (?(+ or (?(- must be followed by a non-zero number
695  .  .
696  .  .
697  .SH "STUDYING A PATTERN"  .SH "STUDYING A PATTERN"
# Line 719  bytes is created. Line 751  bytes is created.
751  .SH "LOCALE SUPPORT"  .SH "LOCALE SUPPORT"
752  .rs  .rs
753  .sp  .sp
754  PCRE handles caseless matching, and determines whether characters are letters  PCRE handles caseless matching, and determines whether characters are letters,
755  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
756  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
757  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
758  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
759  support. The use of locales with Unicode is discouraged.  support. The use of locales with Unicode is discouraged. If you are handling
760  .P  characters with codes greater than 128, you should either use UTF-8 and
761  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.
762  built. This is used when the final argument of \fBpcre_compile()\fP is NULL,  .P
763  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
764  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.
765  default. As more and more applications change to using Unicode, the need for  Normally, the internal tables recognize only ASCII characters. However, when
766  this locale support is expected to die away.  PCRE is built, it is possible to cause the internal tables to be rebuilt in the
767    default "C" locale of the local system, which may cause them to be different.
768    .P
769    The internal tables can always be overridden by tables supplied by the
770    application that calls PCRE. These may be created in a different locale from
771    the default. As more and more applications change to using Unicode, the need
772    for this locale support is expected to die away.
773  .P  .P
774  External tables are built by calling the \fBpcre_maketables()\fP function,  External tables are built by calling the \fBpcre_maketables()\fP function,
775  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 782  the following code could be used:
782    tables = pcre_maketables();    tables = pcre_maketables();
783    re = pcre_compile(..., tables);    re = pcre_compile(..., tables);
784  .sp  .sp
785    The locale name "fr_FR" is used on Linux and other Unix-like systems; if you
786    are using Windows, the name for the French locale is "french".
787    .P
788  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
789  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
790  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 868  variable. (This option used to be called
868  still recognized for backwards compatibility.)  still recognized for backwards compatibility.)
869  .P  .P
870  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
871  (cat|cow|coyote). Otherwise, if either  (cat|cow|coyote), its value is returned. Otherwise, if either
872  .sp  .sp
873  (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
874  starts with "^", or  starts with "^", or
# Line 846  table indicating a fixed set of bytes fo Line 887  table indicating a fixed set of bytes fo
887  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
888  fourth argument should point to an \fBunsigned char *\fP variable.  fourth argument should point to an \fBunsigned char *\fP variable.
889  .sp  .sp
890      PCRE_INFO_HASCRORLF
891    .sp
892    Return 1 if the pattern contains any explicit matches for CR or LF characters,
893    otherwise 0. The fourth argument should point to an \fBint\fP variable.
894    .sp
895      PCRE_INFO_JCHANGED
896    .sp
897    Return 1 if the (?J) option setting is used in the pattern, otherwise 0. The
898    fourth argument should point to an \fBint\fP variable. The (?J) internal option
899    setting changes the local PCRE_DUPNAMES option.
900    .sp
901    PCRE_INFO_LASTLITERAL    PCRE_INFO_LASTLITERAL
902  .sp  .sp
903  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 934  their parentheses numbers. For example,
934  PCRE_EXTENDED is set, so white space - including newlines - is ignored):  PCRE_EXTENDED is set, so white space - including newlines - is ignored):
935  .sp  .sp
936  .\" JOIN  .\" JOIN
937    (?P<date> (?P<year>(\ed\ed)?\ed\ed) -    (?<date> (?<year>(\ed\ed)?\ed\ed) -
938    (?P<month>\ed\ed) - (?P<day>\ed\ed) )    (?<month>\ed\ed) - (?<day>\ed\ed) )
939  .sp  .sp
940  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
941  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 950  When writing code to extract data from n
950  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
951  different for each compiled pattern.  different for each compiled pattern.
952  .sp  .sp
953      PCRE_INFO_OKPARTIAL
954    .sp
955    Return 1 if the pattern can be used for partial matching, otherwise 0. The
956    fourth argument should point to an \fBint\fP variable. The
957    .\" HREF
958    \fBpcrepartial\fP
959    .\"
960    documentation lists the restrictions that apply to patterns when partial
961    matching is used.
962    .sp
963    PCRE_INFO_OPTIONS    PCRE_INFO_OPTIONS
964  .sp  .sp
965  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
966  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
967  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
968  top-level option settings within the pattern itself.  top-level option settings at the start of the pattern itself. In other words,
969    they are the options that will be in force when matching starts. For example,
970    if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the
971    result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED.
972  .P  .P
973  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
974  alternatives begin with one of the following:  alternatives begin with one of the following:
# Line 1114  called. See the Line 1179  called. See the
1179  .\"  .\"
1180  documentation for a discussion of saving compiled patterns for later use.  documentation for a discussion of saving compiled patterns for later use.
1181  .  .
1182    .\" HTML <a name="execoptions"></a>
1183  .SS "Option bits for \fBpcre_exec()\fP"  .SS "Option bits for \fBpcre_exec()\fP"
1184  .rs  .rs
1185  .sp  .sp
# Line 1131  matching time. Line 1197  matching time.
1197    PCRE_NEWLINE_CR    PCRE_NEWLINE_CR
1198    PCRE_NEWLINE_LF    PCRE_NEWLINE_LF
1199    PCRE_NEWLINE_CRLF    PCRE_NEWLINE_CRLF
1200      PCRE_NEWLINE_ANYCRLF
1201      PCRE_NEWLINE_ANY
1202  .sp  .sp
1203  These options override the newline definition that was chosen or defaulted when  These options override the newline definition that was chosen or defaulted when
1204  the pattern was compiled. For details, see the description \fBpcre_compile()\fP  the pattern was compiled. For details, see the description of
1205  above. During matching, the newline choice affects the behaviour of the dot,  \fBpcre_compile()\fP above. During matching, the newline choice affects the
1206  circumflex, and dollar metacharacters.  behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
1207    the way the match position is advanced after a match failure for an unanchored
1208    pattern.
1209    .P
1210    When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is set, and a
1211    match attempt for an unanchored pattern fails when the current position is at a
1212    CRLF sequence, and the pattern contains no explicit matches for CR or NL
1213    characters, the match position is advanced by two characters instead of one, in
1214    other words, to after the CRLF.
1215    .P
1216    The above rule is a compromise that makes the most common cases work as
1217    expected. For example, if the pattern is .+A (and the PCRE_DOTALL option is not
1218    set), it does not match the string "\er\enA" because, after failing at the
1219    start, it skips both the CR and the LF before retrying. However, the pattern
1220    [\er\en]A does match that string, because it contains an explicit CR or LF
1221    reference, and so advances only by one character after the first failure.
1222    Note than an explicit CR or LF reference occurs for negated character classes
1223    such as [^X] because they can match CR or LF characters.
1224    .P
1225    Notwithstanding the above, anomalous effects may still occur when CRLF is a
1226    valid newline sequence and explicit \er or \en escapes appear in the pattern.
1227  .sp  .sp
1228    PCRE_NOTBOL    PCRE_NOTBOL
1229  .sp  .sp
# Line 1178  code that demonstrates how to do this in Line 1266  code that demonstrates how to do this in
1266  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
1267  string is automatically checked when \fBpcre_exec()\fP is subsequently called.  string is automatically checked when \fBpcre_exec()\fP is subsequently called.
1268  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
1269  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
1270  \fBpcre_exec()\fP returns the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP  strings in the
1271  contains an invalid value, PCRE_ERROR_BADUTF8_OFFSET is returned.  .\" HTML <a href="pcre.html#utf8strings">
1272    .\" </a>
1273    section on UTF-8 support
1274    .\"
1275    in the main
1276    .\" HREF
1277    \fBpcre\fP
1278    .\"
1279    page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_exec()\fP returns
1280    the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP contains an invalid value,
1281    PCRE_ERROR_BADUTF8_OFFSET is returned.
1282  .P  .P
1283  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
1284  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 1434  compiled in an environment of one endian
1434  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
1435  not present.  not present.
1436  .sp  .sp
1437    PCRE_ERROR_UNKNOWN_NODE   (-5)    PCRE_ERROR_UNKNOWN_OPCODE (-5)
1438  .sp  .sp
1439  While running the pattern match, an unknown item was encountered in the  While running the pattern match, an unknown item was encountered in the
1440  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 1460  The backtracking limit, as specified by
1460  \fBpcre_extra\fP structure (or defaulted) was reached. See the description  \fBpcre_extra\fP structure (or defaulted) was reached. See the description
1461  above.  above.
1462  .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  
1463    PCRE_ERROR_CALLOUT        (-9)    PCRE_ERROR_CALLOUT        (-9)
1464  .sp  .sp
1465  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 1503  in PCRE or by overwriting of the compile
1503    PCRE_ERROR_BADCOUNT       (-15)    PCRE_ERROR_BADCOUNT       (-15)
1504  .sp  .sp
1505  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.
1506    .sp
1507      PCRE_ERROR_RECURSIONLIMIT (-21)
1508    .sp
1509    The internal recursion limit, as specified by the \fImatch_limit_recursion\fP
1510    field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the
1511    description above.
1512    .sp
1513      PCRE_ERROR_BADNEWLINE     (-23)
1514    .sp
1515    An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
1516    .P
1517    Error numbers -16 to -20 and -22 are not used by \fBpcre_exec()\fP.
1518  .  .
1519  .  .
1520  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
# Line 1422  This error is given if the value of the Line 1526  This error is given if the value of the
1526  .ti +5n  .ti +5n
1527  .B int \fIbuffersize\fP);  .B int \fIbuffersize\fP);
1528  .PP  .PP
 .br  
1529  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
1530  .ti +5n  .ti +5n
1531  .B int \fIstringcount\fP, int \fIstringnumber\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP,
1532  .ti +5n  .ti +5n
1533  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
1534  .PP  .PP
 .br  
1535  .B int pcre_get_substring_list(const char *\fIsubject\fP,  .B int pcre_get_substring_list(const char *\fIsubject\fP,
1536  .ti +5n  .ti +5n
1537  .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 1570  the string is placed in \fIbuffer\fP, wh
1570  \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
1571  obtained via \fBpcre_malloc\fP, and its address is returned via  obtained via \fBpcre_malloc\fP, and its address is returned via
1572  \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
1573  including the terminating zero, or one of  including the terminating zero, or one of these error codes:
1574  .sp  .sp
1575    PCRE_ERROR_NOMEMORY       (-6)    PCRE_ERROR_NOMEMORY       (-6)
1576  .sp  .sp
# Line 1484  and builds a list of pointers to them. A Line 1586  and builds a list of pointers to them. A
1586  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
1587  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
1588  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
1589  function is zero if all went well, or  function is zero if all went well, or the error code
1590  .sp  .sp
1591    PCRE_ERROR_NOMEMORY       (-6)    PCRE_ERROR_NOMEMORY       (-6)
1592  .sp  .sp
# Line 1515  provided. Line 1617  provided.
1617  .ti +5n  .ti +5n
1618  .B const char *\fIname\fP);  .B const char *\fIname\fP);
1619  .PP  .PP
 .br  
1620  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
1621  .ti +5n  .ti +5n
1622  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1524  provided. Line 1625  provided.
1625  .ti +5n  .ti +5n
1626  .B char *\fIbuffer\fP, int \fIbuffersize\fP);  .B char *\fIbuffer\fP, int \fIbuffersize\fP);
1627  .PP  .PP
 .br  
1628  .B int pcre_get_named_substring(const pcre *\fIcode\fP,  .B int pcre_get_named_substring(const pcre *\fIcode\fP,
1629  .ti +5n  .ti +5n
1630  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1536  provided. Line 1636  provided.
1636  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.
1637  For example, for this pattern  For example, for this pattern
1638  .sp  .sp
1639    (a+)b(?P<xxx>\ed+)...    (a+)b(?<xxx>\ed+)...
1640  .sp  .sp
1641  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
1642  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 1660  pattern. This is needed in order to gain
1660  translation table.  translation table.
1661  .P  .P
1662  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they
1663  then call \fIpcre_copy_substring()\fP or \fIpcre_get_substring()\fP, as  then call \fBpcre_copy_substring()\fP or \fBpcre_get_substring()\fP, as
1664  appropriate.  appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names,
1665    the behaviour may not be what you want (see the next section).
1666  .  .
1667  .  .
1668  .SH "DUPLICATE SUBPATTERN NAMES"  .SH "DUPLICATE SUBPATTERN NAMES"
# Line 1578  example is shown in the Line 1679  example is shown in the
1679  .\" HREF  .\" HREF
1680  \fBpcrepattern\fP  \fBpcrepattern\fP
1681  .\"  .\"
1682  documentation. When duplicates are present, \fBpcre_copy_named_substring()\fP  documentation.
1683  and \fBpcre_get_named_substring()\fP return the first substring corresponding  .P
1684  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
1685  The \fBpcre_get_stringnumber()\fP function returns one of the numbers that are  \fBpcre_get_named_substring()\fP return the first substring corresponding to
1686  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
1687  .sp  returned; no data is returned. The \fBpcre_get_stringnumber()\fP function
1688    returns one of the numbers that are associated with the name, but it is not
1689    defined which it is.
1690    .P
1691  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,
1692  you must use the \fBpcre_get_stringtable_entries()\fP function. The first  you must use the \fBpcre_get_stringtable_entries()\fP function. The first
1693  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
1694  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
1695  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
1696  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
1697  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
1698  above in the section entitled \fIInformation about a pattern\fP. Given all the  described above in the section entitled \fIInformation about a pattern\fP.
1699  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
1700  the captured data, if any.  numbers, and hence the captured data, if any.
1701  .  .
1702  .  .
1703  .SH "FINDING ALL POSSIBLE MATCHES"  .SH "FINDING ALL POSSIBLE MATCHES"
# Line 1631  will yield PCRE_ERROR_NOMATCH. Line 1735  will yield PCRE_ERROR_NOMATCH.
1735  .B int *\fIworkspace\fP, int \fIwscount\fP);  .B int *\fIworkspace\fP, int \fIwscount\fP);
1736  .P  .P
1737  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
1738  a compiled pattern, using a "DFA" matching algorithm. This has different  a compiled pattern, using a matching algorithm that scans the subject string
1739  characteristics to the normal algorithm, and is not compatible with Perl. Some  just once, and does not backtrack. This has different characteristics to the
1740  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
1741  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
1742  matching algorithms, see the  matching can be useful. For a discussion of the two matching algorithms, see
1743    the
1744  .\" HREF  .\" HREF
1745  \fBpcrematching\fP  \fBpcrematching\fP
1746  .\"  .\"
# Line 1691  matching string. Line 1796  matching string.
1796    PCRE_DFA_SHORTEST    PCRE_DFA_SHORTEST
1797  .sp  .sp
1798  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
1799  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
1800  this is necessarily the shortest possible match at the first possible matching  works, this is necessarily the shortest possible match at the first possible
1801  point in the subject string.  matching point in the subject string.
1802  .sp  .sp
1803    PCRE_DFA_RESTART    PCRE_DFA_RESTART
1804  .sp  .sp
# Line 1732  the three matched strings are Line 1837  the three matched strings are
1837  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
1838  the number of matched substrings. The substrings themselves are returned in  the number of matched substrings. The substrings themselves are returned in
1839  \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
1840  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
1841  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,
1842  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
1843  data, even though the meaning of the strings is different.)  returns data, even though the meaning of the strings is different.)
1844  .P  .P
1845  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
1846  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 1867  that it does not support, for instance,
1867  .sp  .sp
1868    PCRE_ERROR_DFA_UCOND      (-17)    PCRE_ERROR_DFA_UCOND      (-17)
1869  .sp  .sp
1870  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
1871  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
1872    group. These are not supported.
1873  .sp  .sp
1874    PCRE_ERROR_DFA_UMLIMIT    (-18)    PCRE_ERROR_DFA_UMLIMIT    (-18)
1875  .sp  .sp
# Line 1782  When a recursive subpattern is processed Line 1888  When a recursive subpattern is processed
1888  recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This  recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This
1889  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
1890  extremely rare, as a vector of size 1000 is used.  extremely rare, as a vector of size 1000 is used.
1891  .P  .
1892  .in 0  .
1893  Last updated: 08 June 2006  .SH "SEE ALSO"
1894  .br  .rs
1895  Copyright (c) 1997-2006 University of Cambridge.  .sp
1896    \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
1897    \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
1898    \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
1899    .
1900    .
1901    .SH AUTHOR
1902    .rs
1903    .sp
1904    .nf
1905    Philip Hazel
1906    University Computing Service
1907    Cambridge CB2 3QH, England.
1908    .fi
1909    .
1910    .
1911    .SH REVISION
1912    .rs
1913    .sp
1914    .nf
1915    Last updated: 21 August 2007
1916    Copyright (c) 1997-2007 University of Cambridge.
1917    .fi

Legend:
Removed from v.91  
changed lines
  Added in v.226

  ViewVC Help
Powered by ViewVC 1.1.5