/[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 196 by ph10, Mon Jul 30 13:44:50 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. The choice of newline convention does not affect the
244    interpretation of the \en or \er escape sequences.
245  .  .
246  .  .
247  .SH MULTITHREADING  .SH MULTITHREADING
# Line 276  which it was compiled. Details are given Line 265  which it was compiled. Details are given
265  .\" HREF  .\" HREF
266  \fBpcreprecompile\fP  \fBpcreprecompile\fP
267  .\"  .\"
268  documentation.  documentation. However, compiling a regular expression with one version of PCRE
269    for use with a different version is not guaranteed to work and may cause
270    crashes.
271  .  .
272  .  .
273  .SH "CHECKING BUILD-TIME OPTIONS"  .SH "CHECKING BUILD-TIME OPTIONS"
# Line 308  properties is available; otherwise it is Line 299  properties is available; otherwise it is
299    PCRE_CONFIG_NEWLINE    PCRE_CONFIG_NEWLINE
300  .sp  .sp
301  The output is an integer whose value specifies the default character sequence  The output is an integer whose value specifies the default character sequence
302  that is recognized as meaning "newline". The three values that are supported  that is recognized as meaning "newline". The four values that are supported
303  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
304  the standard sequence for your operating system.  default should normally be the standard sequence for your operating system.
305  .sp  .sp
306    PCRE_CONFIG_LINK_SIZE    PCRE_CONFIG_LINK_SIZE
307  .sp  .sp
# Line 387  depend on memory location, the complete Line 378  depend on memory location, the complete
378  fully relocatable, because it may contain a copy of the \fItableptr\fP  fully relocatable, because it may contain a copy of the \fItableptr\fP
379  argument, which is an address (see below).  argument, which is an address (see below).
380  .P  .P
381  The \fIoptions\fP argument contains independent bits that affect the  The \fIoptions\fP argument contains various bit settings that affect the
382  compilation. It should be zero if no options are required. The available  compilation. It should be zero if no options are required. The available
383  options are described below. Some of them, in particular, those that are  options are described below. Some of them, in particular, those that are
384  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 471  If this bit is set, a dot metacharater i
471  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
472  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
473  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
474  negative class such as [^a] always matches newlines, independent of the setting  negative class such as [^a] always matches newline characters, independent of
475  of this option.  the setting of this option.
476  .sp  .sp
477    PCRE_DUPNAMES    PCRE_DUPNAMES
478  .sp  .sp
# Line 544  occurrences of ^ or $ in a pattern, sett Line 535  occurrences of ^ or $ in a pattern, sett
535    PCRE_NEWLINE_CR    PCRE_NEWLINE_CR
536    PCRE_NEWLINE_LF    PCRE_NEWLINE_LF
537    PCRE_NEWLINE_CRLF    PCRE_NEWLINE_CRLF
538      PCRE_NEWLINE_ANYCRLF
539      PCRE_NEWLINE_ANY
540  .sp  .sp
541  These options override the default newline definition that was chosen when PCRE  These options override the default newline definition that was chosen when PCRE
542  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
543  indicated by a single character (CR or LF, respectively). Setting both of them  indicated by a single character (CR or LF, respectively). Setting
544  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
545  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
546  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
547  set, and an unescaped # outside a character class is encountered. This  that any Unicode newline sequence should be recognized. The Unicode newline
548  indicates a comment that lasts until after the next newline.  sequences are the three just mentioned, plus the single characters VT (vertical
549    tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line
550    separator, U+2028), and PS (paragraph separator, U+2029). The last two are
551    recognized only in UTF-8 mode.
552    .P
553    The newline setting in the options word uses three bits that are treated
554    as a number, giving eight possibilities. Currently only six are used (default
555    plus the five values above). This means that if you set more than one newline
556    option, the combination may or may not be sensible. For example,
557    PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but
558    other combinations may yield unused numbers and cause an error.
559    .P
560    The only time that a line break is specially recognized when compiling a
561    pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character
562    class is encountered. This indicates a comment that lasts until after the next
563    line break sequence. In other circumstances, line break sequences are treated
564    as literal data, except that in PCRE_EXTENDED mode, both CR and LF are treated
565    as whitespace characters and are therefore ignored.
566  .P  .P
567  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
568  \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.
569  .sp  .sp
570    PCRE_NO_AUTO_CAPTURE    PCRE_NO_AUTO_CAPTURE
571  .sp  .sp
# Line 606  strings. Line 616  strings.
616  .sp  .sp
617  The following table lists the error codes than may be returned by  The following table lists the error codes than may be returned by
618  \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
619  both compiling functions.  both compiling functions. As PCRE has developed, some error codes have fallen
620    out of use. To avoid confusion, they have not been re-used.
621  .sp  .sp
622     0  no error     0  no error
623     1  \e at end of pattern     1  \e at end of pattern
# Line 618  both compiling functions. Line 629  both compiling functions.
629     7  invalid escape sequence in character class     7  invalid escape sequence in character class
630     8  range out of order in character class     8  range out of order in character class
631     9  nothing to repeat     9  nothing to repeat
632    10  operand of unlimited repeat could match the empty string    10  [this code is not in use]
633    11  internal error: unexpected repeat    11  internal error: unexpected repeat
634    12  unrecognized character after (?    12  unrecognized character after (?
635    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 638  both compiling functions.
638    16  erroffset passed as NULL    16  erroffset passed as NULL
639    17  unknown option bit(s) set    17  unknown option bit(s) set
640    18  missing ) after comment    18  missing ) after comment
641    19  parentheses nested too deeply    19  [this code is not in use]
642    20  regular expression too large    20  regular expression too large
643    21  failed to get memory    21  failed to get memory
644    22  unmatched parentheses    22  unmatched parentheses
# Line 637  both compiling functions. Line 648  both compiling functions.
648    26  malformed number or name after (?(    26  malformed number or name after (?(
649    27  conditional group contains more than two branches    27  conditional group contains more than two branches
650    28  assertion expected after (?(    28  assertion expected after (?(
651    29  (?R or (?digits must be followed by )    29  (?R or (?[+-]digits must be followed by )
652    30  unknown POSIX class name    30  unknown POSIX class name
653    31  POSIX collating elements are not supported    31  POSIX collating elements are not supported
654    32  this version of PCRE is not compiled with PCRE_UTF8 support    32  this version of PCRE is not compiled with PCRE_UTF8 support
655    33  spare error    33  [this code is not in use]
656    34  character value in \ex{...} sequence is too large    34  character value in \ex{...} sequence is too large
657    35  invalid condition (?(0)    35  invalid condition (?(0)
658    36  \eC not allowed in lookbehind assertion    36  \eC not allowed in lookbehind assertion
# Line 650  both compiling functions. Line 661  both compiling functions.
661    39  closing ) for (?C expected    39  closing ) for (?C expected
662    40  recursive call could loop indefinitely    40  recursive call could loop indefinitely
663    41  unrecognized character after (?P    41  unrecognized character after (?P
664    42  syntax error after (?P    42  syntax error in subpattern name (missing terminator)
665    43  two named subpatterns have the same name    43  two named subpatterns have the same name
666    44  invalid UTF-8 string    44  invalid UTF-8 string
667    45  support for \eP, \ep, and \eX has not been compiled    45  support for \eP, \ep, and \eX has not been compiled
# Line 660  both compiling functions. Line 671  both compiling functions.
671    49  too many named subpatterns (maximum 10,000)    49  too many named subpatterns (maximum 10,000)
672    50  repeated subpattern is too long    50  repeated subpattern is too long
673    51  octal value is greater than \e377 (not in UTF-8 mode)    51  octal value is greater than \e377 (not in UTF-8 mode)
674      52  internal error: overran compiling workspace
675      53  internal error: previously-checked referenced subpattern not found
676      54  DEFINE group contains more than one branch
677      55  repeating a DEFINE group is not allowed
678      56  inconsistent NEWLINE options"
679      57  \eg is not followed by a braced name or an optionally braced
680            non-zero number
681      58  (?+ or (?- or (?(+ or (?(- must be followed by a non-zero number
682  .  .
683  .  .
684  .SH "STUDYING A PATTERN"  .SH "STUDYING A PATTERN"
# Line 719  bytes is created. Line 738  bytes is created.
738  .SH "LOCALE SUPPORT"  .SH "LOCALE SUPPORT"
739  .rs  .rs
740  .sp  .sp
741  PCRE handles caseless matching, and determines whether characters are letters  PCRE handles caseless matching, and determines whether characters are letters,
742  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
743  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
744  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
745  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
746  support. The use of locales with Unicode is discouraged.  support. The use of locales with Unicode is discouraged. If you are handling
747  .P  characters with codes greater than 128, you should either use UTF-8 and
748  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.
749  built. This is used when the final argument of \fBpcre_compile()\fP is NULL,  .P
750  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
751  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.
752  default. As more and more applications change to using Unicode, the need for  Normally, the internal tables recognize only ASCII characters. However, when
753  this locale support is expected to die away.  PCRE is built, it is possible to cause the internal tables to be rebuilt in the
754    default "C" locale of the local system, which may cause them to be different.
755    .P
756    The internal tables can always be overridden by tables supplied by the
757    application that calls PCRE. These may be created in a different locale from
758    the default. As more and more applications change to using Unicode, the need
759    for this locale support is expected to die away.
760  .P  .P
761  External tables are built by calling the \fBpcre_maketables()\fP function,  External tables are built by calling the \fBpcre_maketables()\fP function,
762  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 769  the following code could be used:
769    tables = pcre_maketables();    tables = pcre_maketables();
770    re = pcre_compile(..., tables);    re = pcre_compile(..., tables);
771  .sp  .sp
772    The locale name "fr_FR" is used on Linux and other Unix-like systems; if you
773    are using Windows, the name for the French locale is "french".
774    .P
775  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
776  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
777  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 855  variable. (This option used to be called
855  still recognized for backwards compatibility.)  still recognized for backwards compatibility.)
856  .P  .P
857  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
858  (cat|cow|coyote). Otherwise, if either  (cat|cow|coyote), its value is returned. Otherwise, if either
859  .sp  .sp
860  (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
861  starts with "^", or  starts with "^", or
# Line 846  table indicating a fixed set of bytes fo Line 874  table indicating a fixed set of bytes fo
874  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
875  fourth argument should point to an \fBunsigned char *\fP variable.  fourth argument should point to an \fBunsigned char *\fP variable.
876  .sp  .sp
877      PCRE_INFO_JCHANGED
878    .sp
879    Return 1 if the (?J) option setting is used in the pattern, otherwise 0. The
880    fourth argument should point to an \fBint\fP variable. The (?J) internal option
881    setting changes the local PCRE_DUPNAMES option.
882    .sp
883    PCRE_INFO_LASTLITERAL    PCRE_INFO_LASTLITERAL
884  .sp  .sp
885  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 916  their parentheses numbers. For example,
916  PCRE_EXTENDED is set, so white space - including newlines - is ignored):  PCRE_EXTENDED is set, so white space - including newlines - is ignored):
917  .sp  .sp
918  .\" JOIN  .\" JOIN
919    (?P<date> (?P<year>(\ed\ed)?\ed\ed) -    (?<date> (?<year>(\ed\ed)?\ed\ed) -
920    (?P<month>\ed\ed) - (?P<day>\ed\ed) )    (?<month>\ed\ed) - (?<day>\ed\ed) )
921  .sp  .sp
922  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
923  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 932  When writing code to extract data from n
932  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
933  different for each compiled pattern.  different for each compiled pattern.
934  .sp  .sp
935      PCRE_INFO_OKPARTIAL
936    .sp
937    Return 1 if the pattern can be used for partial matching, otherwise 0. The
938    fourth argument should point to an \fBint\fP variable. The
939    .\" HREF
940    \fBpcrepartial\fP
941    .\"
942    documentation lists the restrictions that apply to patterns when partial
943    matching is used.
944    .sp
945    PCRE_INFO_OPTIONS    PCRE_INFO_OPTIONS
946  .sp  .sp
947  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
948  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
949  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
950  top-level option settings within the pattern itself.  top-level option settings at the start of the pattern itself. In other words,
951    they are the options that will be in force when matching starts. For example,
952    if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the
953    result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED.
954  .P  .P
955  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
956  alternatives begin with one of the following:  alternatives begin with one of the following:
# Line 1131  matching time. Line 1178  matching time.
1178    PCRE_NEWLINE_CR    PCRE_NEWLINE_CR
1179    PCRE_NEWLINE_LF    PCRE_NEWLINE_LF
1180    PCRE_NEWLINE_CRLF    PCRE_NEWLINE_CRLF
1181      PCRE_NEWLINE_ANYCRLF
1182      PCRE_NEWLINE_ANY
1183  .sp  .sp
1184  These options override the newline definition that was chosen or defaulted when  These options override the newline definition that was chosen or defaulted when
1185  the pattern was compiled. For details, see the description \fBpcre_compile()\fP  the pattern was compiled. For details, see the description of
1186  above. During matching, the newline choice affects the behaviour of the dot,  \fBpcre_compile()\fP above. During matching, the newline choice affects the
1187  circumflex, and dollar metacharacters.  behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
1188    the way the match position is advanced after a match failure for an unanchored
1189    pattern. When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is
1190    set, and a match attempt fails when the current position is at a CRLF sequence,
1191    the match position is advanced by two characters instead of one, in other
1192    words, to after the CRLF.
1193  .sp  .sp
1194    PCRE_NOTBOL    PCRE_NOTBOL
1195  .sp  .sp
# Line 1336  compiled in an environment of one endian Line 1390  compiled in an environment of one endian
1390  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
1391  not present.  not present.
1392  .sp  .sp
1393    PCRE_ERROR_UNKNOWN_NODE   (-5)    PCRE_ERROR_UNKNOWN_OPCODE (-5)
1394  .sp  .sp
1395  While running the pattern match, an unknown item was encountered in the  While running the pattern match, an unknown item was encountered in the
1396  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 1416  The backtracking limit, as specified by
1416  \fBpcre_extra\fP structure (or defaulted) was reached. See the description  \fBpcre_extra\fP structure (or defaulted) was reached. See the description
1417  above.  above.
1418  .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  
1419    PCRE_ERROR_CALLOUT        (-9)    PCRE_ERROR_CALLOUT        (-9)
1420  .sp  .sp
1421  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 1459  in PCRE or by overwriting of the compile
1459    PCRE_ERROR_BADCOUNT       (-15)    PCRE_ERROR_BADCOUNT       (-15)
1460  .sp  .sp
1461  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.
1462    .sp
1463      PCRE_ERROR_RECURSIONLIMIT (-21)
1464    .sp
1465    The internal recursion limit, as specified by the \fImatch_limit_recursion\fP
1466    field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the
1467    description above.
1468    .sp
1469      PCRE_ERROR_NULLWSLIMIT    (-22)
1470    .sp
1471    When a parenthesized subpattern that can match an empty substring is repeated
1472    with an unbounded upper limit, the subject position at the start of the group
1473    must be remembered, so that a test for an empty string can be made when the end
1474    of the group is reached. The repetition loop is automatically terminated when
1475    an empty string is matched.
1476    .P
1477    Some workspace is required for remembering the starting position. For most
1478    capturing subpatterns, an internal recursive call of the match() function is
1479    used, and in this case, the workspace is taken from the runtime stack. However,
1480    for non-capturing subpatterns, this is not available. Instead, some fixed
1481    workspace (taken from the top-level stack) is used. If it runs out, the
1482    PCRE_ERROR_NULLWSLIMIT error is given. The size of the fixed workspace allows
1483    for up to 1000 repetitions of a non-capturing subpattern that might match an
1484    empty string. If this limit is a problem for you, you can sometimes get round
1485    it by changing a non-capturing subpattern into a capturing one, but that will
1486    increase the amount of runtime stack that is used.
1487    .sp
1488      PCRE_ERROR_BADNEWLINE     (-23)
1489    .sp
1490    An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
1491    .P
1492    Error numbers -16 to -20 are not used by \fBpcre_exec()\fP.
1493  .  .
1494  .  .
1495  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
# Line 1422  This error is given if the value of the Line 1501  This error is given if the value of the
1501  .ti +5n  .ti +5n
1502  .B int \fIbuffersize\fP);  .B int \fIbuffersize\fP);
1503  .PP  .PP
 .br  
1504  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
1505  .ti +5n  .ti +5n
1506  .B int \fIstringcount\fP, int \fIstringnumber\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP,
1507  .ti +5n  .ti +5n
1508  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
1509  .PP  .PP
 .br  
1510  .B int pcre_get_substring_list(const char *\fIsubject\fP,  .B int pcre_get_substring_list(const char *\fIsubject\fP,
1511  .ti +5n  .ti +5n
1512  .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 1545  the string is placed in \fIbuffer\fP, wh
1545  \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
1546  obtained via \fBpcre_malloc\fP, and its address is returned via  obtained via \fBpcre_malloc\fP, and its address is returned via
1547  \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
1548  including the terminating zero, or one of  including the terminating zero, or one of these error codes:
1549  .sp  .sp
1550    PCRE_ERROR_NOMEMORY       (-6)    PCRE_ERROR_NOMEMORY       (-6)
1551  .sp  .sp
# Line 1484  and builds a list of pointers to them. A Line 1561  and builds a list of pointers to them. A
1561  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
1562  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
1563  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
1564  function is zero if all went well, or  function is zero if all went well, or the error code
1565  .sp  .sp
1566    PCRE_ERROR_NOMEMORY       (-6)    PCRE_ERROR_NOMEMORY       (-6)
1567  .sp  .sp
# Line 1515  provided. Line 1592  provided.
1592  .ti +5n  .ti +5n
1593  .B const char *\fIname\fP);  .B const char *\fIname\fP);
1594  .PP  .PP
 .br  
1595  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
1596  .ti +5n  .ti +5n
1597  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1524  provided. Line 1600  provided.
1600  .ti +5n  .ti +5n
1601  .B char *\fIbuffer\fP, int \fIbuffersize\fP);  .B char *\fIbuffer\fP, int \fIbuffersize\fP);
1602  .PP  .PP
 .br  
1603  .B int pcre_get_named_substring(const pcre *\fIcode\fP,  .B int pcre_get_named_substring(const pcre *\fIcode\fP,
1604  .ti +5n  .ti +5n
1605  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1536  provided. Line 1611  provided.
1611  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.
1612  For example, for this pattern  For example, for this pattern
1613  .sp  .sp
1614    (a+)b(?P<xxx>\ed+)...    (a+)b(?<xxx>\ed+)...
1615  .sp  .sp
1616  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
1617  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 1635  pattern. This is needed in order to gain
1635  translation table.  translation table.
1636  .P  .P
1637  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they
1638  then call \fIpcre_copy_substring()\fP or \fIpcre_get_substring()\fP, as  then call \fBpcre_copy_substring()\fP or \fBpcre_get_substring()\fP, as
1639  appropriate.  appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names,
1640    the behaviour may not be what you want (see the next section).
1641  .  .
1642  .  .
1643  .SH "DUPLICATE SUBPATTERN NAMES"  .SH "DUPLICATE SUBPATTERN NAMES"
# Line 1590  argument is the compiled pattern, and th Line 1666  argument is the compiled pattern, and th
1666  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
1667  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
1668  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
1669  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
1670  above in the section entitled \fIInformation about a pattern\fP. Given all the  described above in the section entitled \fIInformation about a pattern\fP.
1671  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
1672  the captured data, if any.  numbers, and hence the captured data, if any.
1673  .  .
1674  .  .
1675  .SH "FINDING ALL POSSIBLE MATCHES"  .SH "FINDING ALL POSSIBLE MATCHES"
# Line 1631  will yield PCRE_ERROR_NOMATCH. Line 1707  will yield PCRE_ERROR_NOMATCH.
1707  .B int *\fIworkspace\fP, int \fIwscount\fP);  .B int *\fIworkspace\fP, int \fIwscount\fP);
1708  .P  .P
1709  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
1710  a compiled pattern, using a "DFA" matching algorithm. This has different  a compiled pattern, using a matching algorithm that scans the subject string
1711  characteristics to the normal algorithm, and is not compatible with Perl. Some  just once, and does not backtrack. This has different characteristics to the
1712  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
1713  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
1714  matching algorithms, see the  matching can be useful. For a discussion of the two matching algorithms, see
1715    the
1716  .\" HREF  .\" HREF
1717  \fBpcrematching\fP  \fBpcrematching\fP
1718  .\"  .\"
# Line 1691  matching string. Line 1768  matching string.
1768    PCRE_DFA_SHORTEST    PCRE_DFA_SHORTEST
1769  .sp  .sp
1770  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
1771  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
1772  this is necessarily the shortest possible match at the first possible matching  works, this is necessarily the shortest possible match at the first possible
1773  point in the subject string.  matching point in the subject string.
1774  .sp  .sp
1775    PCRE_DFA_RESTART    PCRE_DFA_RESTART
1776  .sp  .sp
# Line 1732  the three matched strings are Line 1809  the three matched strings are
1809  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
1810  the number of matched substrings. The substrings themselves are returned in  the number of matched substrings. The substrings themselves are returned in
1811  \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
1812  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
1813  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,
1814  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
1815  data, even though the meaning of the strings is different.)  returns data, even though the meaning of the strings is different.)
1816  .P  .P
1817  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
1818  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 1839  that it does not support, for instance,
1839  .sp  .sp
1840    PCRE_ERROR_DFA_UCOND      (-17)    PCRE_ERROR_DFA_UCOND      (-17)
1841  .sp  .sp
1842  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
1843  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
1844    group. These are not supported.
1845  .sp  .sp
1846    PCRE_ERROR_DFA_UMLIMIT    (-18)    PCRE_ERROR_DFA_UMLIMIT    (-18)
1847  .sp  .sp
# Line 1782  When a recursive subpattern is processed Line 1860  When a recursive subpattern is processed
1860  recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This  recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This
1861  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
1862  extremely rare, as a vector of size 1000 is used.  extremely rare, as a vector of size 1000 is used.
1863  .P  .
1864  .in 0  .
1865  Last updated: 08 June 2006  .SH "SEE ALSO"
1866  .br  .rs
1867  Copyright (c) 1997-2006 University of Cambridge.  .sp
1868    \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
1869    \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
1870    \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
1871    .
1872    .
1873    .SH AUTHOR
1874    .rs
1875    .sp
1876    .nf
1877    Philip Hazel
1878    University Computing Service
1879    Cambridge CB2 3QH, England.
1880    .fi
1881    .
1882    .
1883    .SH REVISION
1884    .rs
1885    .sp
1886    .nf
1887    Last updated: 30 July 2007
1888    Copyright (c) 1997-2007 University of Cambridge.
1889    .fi

Legend:
Removed from v.91  
changed lines
  Added in v.196

  ViewVC Help
Powered by ViewVC 1.1.5