/[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 150 by ph10, Tue Apr 17 08:22:40 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 308  properties is available; otherwise it is Line 297  properties is available; otherwise it is
297    PCRE_CONFIG_NEWLINE    PCRE_CONFIG_NEWLINE
298  .sp  .sp
299  The output is an integer whose value specifies the default character sequence  The output is an integer whose value specifies the default character sequence
300  that is recognized as meaning "newline". The three values that are supported  that is recognized as meaning "newline". The four values that are supported
301  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
302  the standard sequence for your operating system.  default should normally be the standard sequence for your operating system.
303  .sp  .sp
304    PCRE_CONFIG_LINK_SIZE    PCRE_CONFIG_LINK_SIZE
305  .sp  .sp
# Line 387  depend on memory location, the complete Line 376  depend on memory location, the complete
376  fully relocatable, because it may contain a copy of the \fItableptr\fP  fully relocatable, because it may contain a copy of the \fItableptr\fP
377  argument, which is an address (see below).  argument, which is an address (see below).
378  .P  .P
379  The \fIoptions\fP argument contains independent bits that affect the  The \fIoptions\fP argument contains various bit settings that affect the
380  compilation. It should be zero if no options are required. The available  compilation. It should be zero if no options are required. The available
381  options are described below. Some of them, in particular, those that are  options are described below. Some of them, in particular, those that are
382  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 469  If this bit is set, a dot metacharater i
469  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
470  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
471  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
472  negative class such as [^a] always matches newlines, independent of the setting  negative class such as [^a] always matches newline characters, independent of
473  of this option.  the setting of this option.
474  .sp  .sp
475    PCRE_DUPNAMES    PCRE_DUPNAMES
476  .sp  .sp
# Line 544  occurrences of ^ or $ in a pattern, sett Line 533  occurrences of ^ or $ in a pattern, sett
533    PCRE_NEWLINE_CR    PCRE_NEWLINE_CR
534    PCRE_NEWLINE_LF    PCRE_NEWLINE_LF
535    PCRE_NEWLINE_CRLF    PCRE_NEWLINE_CRLF
536      PCRE_NEWLINE_ANYCRLF
537      PCRE_NEWLINE_ANY
538  .sp  .sp
539  These options override the default newline definition that was chosen when PCRE  These options override the default newline definition that was chosen when PCRE
540  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
541  indicated by a single character (CR or LF, respectively). Setting both of them  indicated by a single character (CR or LF, respectively). Setting
542  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
543  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
544  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
545  set, and an unescaped # outside a character class is encountered. This  that any Unicode newline sequence should be recognized. The Unicode newline
546  indicates a comment that lasts until after the next newline.  sequences are the three just mentioned, plus the single characters VT (vertical
547    tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line
548    separator, U+2028), and PS (paragraph separator, U+2029). The last two are
549    recognized only in UTF-8 mode.
550    .P
551    The newline setting in the options word uses three bits that are treated
552    as a number, giving eight possibilities. Currently only six are used (default
553    plus the five values above). This means that if you set more than one newline
554    option, the combination may or may not be sensible. For example,
555    PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but
556    other combinations may yield unused numbers and cause an error.
557    .P
558    The only time that a line break is specially recognized when compiling a
559    pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character
560    class is encountered. This indicates a comment that lasts until after the next
561    line break sequence. In other circumstances, line break sequences are treated
562    as literal data, except that in PCRE_EXTENDED mode, both CR and LF are treated
563    as whitespace characters and are therefore ignored.
564  .P  .P
565  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
566  \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.
567  .sp  .sp
568    PCRE_NO_AUTO_CAPTURE    PCRE_NO_AUTO_CAPTURE
569  .sp  .sp
# Line 606  strings. Line 614  strings.
614  .sp  .sp
615  The following table lists the error codes than may be returned by  The following table lists the error codes than may be returned by
616  \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
617  both compiling functions.  both compiling functions. As PCRE has developed, some error codes have fallen
618    out of use. To avoid confusion, they have not been re-used.
619  .sp  .sp
620     0  no error     0  no error
621     1  \e at end of pattern     1  \e at end of pattern
# Line 618  both compiling functions. Line 627  both compiling functions.
627     7  invalid escape sequence in character class     7  invalid escape sequence in character class
628     8  range out of order in character class     8  range out of order in character class
629     9  nothing to repeat     9  nothing to repeat
630    10  operand of unlimited repeat could match the empty string    10  [this code is not in use]
631    11  internal error: unexpected repeat    11  internal error: unexpected repeat
632    12  unrecognized character after (?    12  unrecognized character after (?
633    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 636  both compiling functions.
636    16  erroffset passed as NULL    16  erroffset passed as NULL
637    17  unknown option bit(s) set    17  unknown option bit(s) set
638    18  missing ) after comment    18  missing ) after comment
639    19  parentheses nested too deeply    19  [this code is not in use]
640    20  regular expression too large    20  regular expression too large
641    21  failed to get memory    21  failed to get memory
642    22  unmatched parentheses    22  unmatched parentheses
# Line 641  both compiling functions. Line 650  both compiling functions.
650    30  unknown POSIX class name    30  unknown POSIX class name
651    31  POSIX collating elements are not supported    31  POSIX collating elements are not supported
652    32  this version of PCRE is not compiled with PCRE_UTF8 support    32  this version of PCRE is not compiled with PCRE_UTF8 support
653    33  spare error    33  [this code is not in use]
654    34  character value in \ex{...} sequence is too large    34  character value in \ex{...} sequence is too large
655    35  invalid condition (?(0)    35  invalid condition (?(0)
656    36  \eC not allowed in lookbehind assertion    36  \eC not allowed in lookbehind assertion
# Line 650  both compiling functions. Line 659  both compiling functions.
659    39  closing ) for (?C expected    39  closing ) for (?C expected
660    40  recursive call could loop indefinitely    40  recursive call could loop indefinitely
661    41  unrecognized character after (?P    41  unrecognized character after (?P
662    42  syntax error after (?P    42  syntax error in subpattern name (missing terminator)
663    43  two named subpatterns have the same name    43  two named subpatterns have the same name
664    44  invalid UTF-8 string    44  invalid UTF-8 string
665    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 669  both compiling functions.
669    49  too many named subpatterns (maximum 10,000)    49  too many named subpatterns (maximum 10,000)
670    50  repeated subpattern is too long    50  repeated subpattern is too long
671    51  octal value is greater than \e377 (not in UTF-8 mode)    51  octal value is greater than \e377 (not in UTF-8 mode)
672      52  internal error: overran compiling workspace
673      53  internal error: previously-checked referenced subpattern not found
674      54  DEFINE group contains more than one branch
675      55  repeating a DEFINE group is not allowed
676      56  inconsistent NEWLINE options"
677  .  .
678  .  .
679  .SH "STUDYING A PATTERN"  .SH "STUDYING A PATTERN"
# Line 719  bytes is created. Line 733  bytes is created.
733  .SH "LOCALE SUPPORT"  .SH "LOCALE SUPPORT"
734  .rs  .rs
735  .sp  .sp
736  PCRE handles caseless matching, and determines whether characters are letters  PCRE handles caseless matching, and determines whether characters are letters,
737  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
738  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
739  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
740  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
741  support. The use of locales with Unicode is discouraged.  support. The use of locales with Unicode is discouraged. If you are handling
742  .P  characters with codes greater than 128, you should either use UTF-8 and
743  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.
744  built. This is used when the final argument of \fBpcre_compile()\fP is NULL,  .P
745  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
746  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.
747  default. As more and more applications change to using Unicode, the need for  Normally, the internal tables recognize only ASCII characters. However, when
748  this locale support is expected to die away.  PCRE is built, it is possible to cause the internal tables to be rebuilt in the
749    default "C" locale of the local system, which may cause them to be different.
750    .P
751    The internal tables can always be overridden by tables supplied by the
752    application that calls PCRE. These may be created in a different locale from
753    the default. As more and more applications change to using Unicode, the need
754    for this locale support is expected to die away.
755  .P  .P
756  External tables are built by calling the \fBpcre_maketables()\fP function,  External tables are built by calling the \fBpcre_maketables()\fP function,
757  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 764  the following code could be used:
764    tables = pcre_maketables();    tables = pcre_maketables();
765    re = pcre_compile(..., tables);    re = pcre_compile(..., tables);
766  .sp  .sp
767    The locale name "fr_FR" is used on Linux and other Unix-like systems; if you
768    are using Windows, the name for the French locale is "french".
769    .P
770  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
771  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
772  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 850  variable. (This option used to be called
850  still recognized for backwards compatibility.)  still recognized for backwards compatibility.)
851  .P  .P
852  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
853  (cat|cow|coyote). Otherwise, if either  (cat|cow|coyote), its value is returned. Otherwise, if either
854  .sp  .sp
855  (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
856  starts with "^", or  starts with "^", or
# Line 882  their parentheses numbers. For example, Line 905  their parentheses numbers. For example,
905  PCRE_EXTENDED is set, so white space - including newlines - is ignored):  PCRE_EXTENDED is set, so white space - including newlines - is ignored):
906  .sp  .sp
907  .\" JOIN  .\" JOIN
908    (?P<date> (?P<year>(\ed\ed)?\ed\ed) -    (?<date> (?<year>(\ed\ed)?\ed\ed) -
909    (?P<month>\ed\ed) - (?P<day>\ed\ed) )    (?<month>\ed\ed) - (?<day>\ed\ed) )
910  .sp  .sp
911  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
912  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 1131  matching time. Line 1154  matching time.
1154    PCRE_NEWLINE_CR    PCRE_NEWLINE_CR
1155    PCRE_NEWLINE_LF    PCRE_NEWLINE_LF
1156    PCRE_NEWLINE_CRLF    PCRE_NEWLINE_CRLF
1157      PCRE_NEWLINE_ANYCRLF
1158      PCRE_NEWLINE_ANY
1159  .sp  .sp
1160  These options override the newline definition that was chosen or defaulted when  These options override the newline definition that was chosen or defaulted when
1161  the pattern was compiled. For details, see the description \fBpcre_compile()\fP  the pattern was compiled. For details, see the description of
1162  above. During matching, the newline choice affects the behaviour of the dot,  \fBpcre_compile()\fP above. During matching, the newline choice affects the
1163  circumflex, and dollar metacharacters.  behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
1164    the way the match position is advanced after a match failure for an unanchored
1165    pattern. When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is
1166    set, and a match attempt fails when the current position is at a CRLF sequence,
1167    the match position is advanced by two characters instead of one, in other
1168    words, to after the CRLF.
1169  .sp  .sp
1170    PCRE_NOTBOL    PCRE_NOTBOL
1171  .sp  .sp
# Line 1336  compiled in an environment of one endian Line 1366  compiled in an environment of one endian
1366  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
1367  not present.  not present.
1368  .sp  .sp
1369    PCRE_ERROR_UNKNOWN_NODE   (-5)    PCRE_ERROR_UNKNOWN_OPCODE (-5)
1370  .sp  .sp
1371  While running the pattern match, an unknown item was encountered in the  While running the pattern match, an unknown item was encountered in the
1372  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 1392  The backtracking limit, as specified by
1392  \fBpcre_extra\fP structure (or defaulted) was reached. See the description  \fBpcre_extra\fP structure (or defaulted) was reached. See the description
1393  above.  above.
1394  .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  
1395    PCRE_ERROR_CALLOUT        (-9)    PCRE_ERROR_CALLOUT        (-9)
1396  .sp  .sp
1397  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 1435  in PCRE or by overwriting of the compile
1435    PCRE_ERROR_BADCOUNT       (-15)    PCRE_ERROR_BADCOUNT       (-15)
1436  .sp  .sp
1437  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.
1438    .sp
1439      PCRE_ERROR_RECURSIONLIMIT (-21)
1440    .sp
1441    The internal recursion limit, as specified by the \fImatch_limit_recursion\fP
1442    field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the
1443    description above.
1444    .sp
1445      PCRE_ERROR_NULLWSLIMIT    (-22)
1446    .sp
1447    When a group that can match an empty substring is repeated with an unbounded
1448    upper limit, the subject position at the start of the group must be remembered,
1449    so that a test for an empty string can be made when the end of the group is
1450    reached. Some workspace is required for this; if it runs out, this error is
1451    given.
1452    .sp
1453      PCRE_ERROR_BADNEWLINE     (-23)
1454    .sp
1455    An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
1456    .P
1457    Error numbers -16 to -20 are not used by \fBpcre_exec()\fP.
1458  .  .
1459  .  .
1460  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
# Line 1422  This error is given if the value of the Line 1466  This error is given if the value of the
1466  .ti +5n  .ti +5n
1467  .B int \fIbuffersize\fP);  .B int \fIbuffersize\fP);
1468  .PP  .PP
 .br  
1469  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
1470  .ti +5n  .ti +5n
1471  .B int \fIstringcount\fP, int \fIstringnumber\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP,
1472  .ti +5n  .ti +5n
1473  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
1474  .PP  .PP
 .br  
1475  .B int pcre_get_substring_list(const char *\fIsubject\fP,  .B int pcre_get_substring_list(const char *\fIsubject\fP,
1476  .ti +5n  .ti +5n
1477  .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 1510  the string is placed in \fIbuffer\fP, wh
1510  \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
1511  obtained via \fBpcre_malloc\fP, and its address is returned via  obtained via \fBpcre_malloc\fP, and its address is returned via
1512  \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
1513  including the terminating zero, or one of  including the terminating zero, or one of these error codes:
1514  .sp  .sp
1515    PCRE_ERROR_NOMEMORY       (-6)    PCRE_ERROR_NOMEMORY       (-6)
1516  .sp  .sp
# Line 1484  and builds a list of pointers to them. A Line 1526  and builds a list of pointers to them. A
1526  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
1527  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
1528  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
1529  function is zero if all went well, or  function is zero if all went well, or the error code
1530  .sp  .sp
1531    PCRE_ERROR_NOMEMORY       (-6)    PCRE_ERROR_NOMEMORY       (-6)
1532  .sp  .sp
# Line 1515  provided. Line 1557  provided.
1557  .ti +5n  .ti +5n
1558  .B const char *\fIname\fP);  .B const char *\fIname\fP);
1559  .PP  .PP
 .br  
1560  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
1561  .ti +5n  .ti +5n
1562  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1524  provided. Line 1565  provided.
1565  .ti +5n  .ti +5n
1566  .B char *\fIbuffer\fP, int \fIbuffersize\fP);  .B char *\fIbuffer\fP, int \fIbuffersize\fP);
1567  .PP  .PP
 .br  
1568  .B int pcre_get_named_substring(const pcre *\fIcode\fP,  .B int pcre_get_named_substring(const pcre *\fIcode\fP,
1569  .ti +5n  .ti +5n
1570  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1536  provided. Line 1576  provided.
1576  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.
1577  For example, for this pattern  For example, for this pattern
1578  .sp  .sp
1579    (a+)b(?P<xxx>\ed+)...    (a+)b(?<xxx>\ed+)...
1580  .sp  .sp
1581  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
1582  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 1600  pattern. This is needed in order to gain
1600  translation table.  translation table.
1601  .P  .P
1602  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they
1603  then call \fIpcre_copy_substring()\fP or \fIpcre_get_substring()\fP, as  then call \fBpcre_copy_substring()\fP or \fBpcre_get_substring()\fP, as
1604  appropriate.  appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names,
1605    the behaviour may not be what you want (see the next section).
1606  .  .
1607  .  .
1608  .SH "DUPLICATE SUBPATTERN NAMES"  .SH "DUPLICATE SUBPATTERN NAMES"
# Line 1590  argument is the compiled pattern, and th Line 1631  argument is the compiled pattern, and th
1631  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
1632  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
1633  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
1634  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
1635  above in the section entitled \fIInformation about a pattern\fP. Given all the  described above in the section entitled \fIInformation about a pattern\fP.
1636  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
1637  the captured data, if any.  numbers, and hence the captured data, if any.
1638  .  .
1639  .  .
1640  .SH "FINDING ALL POSSIBLE MATCHES"  .SH "FINDING ALL POSSIBLE MATCHES"
# Line 1631  will yield PCRE_ERROR_NOMATCH. Line 1672  will yield PCRE_ERROR_NOMATCH.
1672  .B int *\fIworkspace\fP, int \fIwscount\fP);  .B int *\fIworkspace\fP, int \fIwscount\fP);
1673  .P  .P
1674  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
1675  a compiled pattern, using a "DFA" matching algorithm. This has different  a compiled pattern, using a matching algorithm that scans the subject string
1676  characteristics to the normal algorithm, and is not compatible with Perl. Some  just once, and does not backtrack. This has different characteristics to the
1677  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
1678  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
1679  matching algorithms, see the  matching can be useful. For a discussion of the two matching algorithms, see
1680    the
1681  .\" HREF  .\" HREF
1682  \fBpcrematching\fP  \fBpcrematching\fP
1683  .\"  .\"
# Line 1691  matching string. Line 1733  matching string.
1733    PCRE_DFA_SHORTEST    PCRE_DFA_SHORTEST
1734  .sp  .sp
1735  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
1736  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
1737  this is necessarily the shortest possible match at the first possible matching  works, this is necessarily the shortest possible match at the first possible
1738  point in the subject string.  matching point in the subject string.
1739  .sp  .sp
1740    PCRE_DFA_RESTART    PCRE_DFA_RESTART
1741  .sp  .sp
# Line 1732  the three matched strings are Line 1774  the three matched strings are
1774  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
1775  the number of matched substrings. The substrings themselves are returned in  the number of matched substrings. The substrings themselves are returned in
1776  \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
1777  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
1778  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,
1779  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
1780  data, even though the meaning of the strings is different.)  returns data, even though the meaning of the strings is different.)
1781  .P  .P
1782  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
1783  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 1804  that it does not support, for instance,
1804  .sp  .sp
1805    PCRE_ERROR_DFA_UCOND      (-17)    PCRE_ERROR_DFA_UCOND      (-17)
1806  .sp  .sp
1807  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
1808  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
1809    group. These are not supported.
1810  .sp  .sp
1811    PCRE_ERROR_DFA_UMLIMIT    (-18)    PCRE_ERROR_DFA_UMLIMIT    (-18)
1812  .sp  .sp
# Line 1782  When a recursive subpattern is processed Line 1825  When a recursive subpattern is processed
1825  recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This  recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This
1826  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
1827  extremely rare, as a vector of size 1000 is used.  extremely rare, as a vector of size 1000 is used.
1828  .P  .
1829  .in 0  .
1830  Last updated: 08 June 2006  .SH "SEE ALSO"
1831  .br  .rs
1832  Copyright (c) 1997-2006 University of Cambridge.  .sp
1833    \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
1834    \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
1835    \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
1836    .
1837    .
1838    .SH AUTHOR
1839    .rs
1840    .sp
1841    .nf
1842    Philip Hazel
1843    University Computing Service
1844    Cambridge CB2 3QH, England.
1845    .fi
1846    .
1847    .
1848    .SH REVISION
1849    .rs
1850    .sp
1851    .nf
1852    Last updated: 16 April 2007
1853    Copyright (c) 1997-2007 University of Cambridge.
1854    .fi

Legend:
Removed from v.91  
changed lines
  Added in v.150

  ViewVC Help
Powered by ViewVC 1.1.5