/[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 96 by nigel, Fri Mar 2 13:10:43 2007 UTC revision 371 by ph10, Mon Aug 25 18:28:05 2008 UTC
# Line 7  PCRE - Perl-compatible regular expressio Line 7  PCRE - Perl-compatible regular expressio
7  .B #include <pcre.h>  .B #include <pcre.h>
8  .PP  .PP
9  .SM  .SM
 .br  
10  .B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP,  .B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP,
11  .ti +5n  .ti +5n
12  .B const char **\fIerrptr\fP, int *\fIerroffset\fP,  .B const char **\fIerrptr\fP, int *\fIerroffset\fP,
13  .ti +5n  .ti +5n
14  .B const unsigned char *\fItableptr\fP);  .B const unsigned char *\fItableptr\fP);
15  .PP  .PP
 .br  
16  .B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP,  .B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP,
17  .ti +5n  .ti +5n
18  .B int *\fIerrorcodeptr\fP,  .B int *\fIerrorcodeptr\fP,
# Line 23  PCRE - Perl-compatible regular expressio Line 21  PCRE - Perl-compatible regular expressio
21  .ti +5n  .ti +5n
22  .B const unsigned char *\fItableptr\fP);  .B const unsigned char *\fItableptr\fP);
23  .PP  .PP
 .br  
24  .B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP,  .B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP,
25  .ti +5n  .ti +5n
26  .B const char **\fIerrptr\fP);  .B const char **\fIerrptr\fP);
27  .PP  .PP
 .br  
28  .B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"  .B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
29  .ti +5n  .ti +5n
30  .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,  .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
31  .ti +5n  .ti +5n
32  .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);  .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);
33  .PP  .PP
 .br  
34  .B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"  .B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
35  .ti +5n  .ti +5n
36  .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,  .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
# Line 44  PCRE - Perl-compatible regular expressio Line 39  PCRE - Perl-compatible regular expressio
39  .ti +5n  .ti +5n
40  .B int *\fIworkspace\fP, int \fIwscount\fP);  .B int *\fIworkspace\fP, int \fIwscount\fP);
41  .PP  .PP
 .br  
42  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
43  .ti +5n  .ti +5n
44  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 53  PCRE - Perl-compatible regular expressio Line 47  PCRE - Perl-compatible regular expressio
47  .ti +5n  .ti +5n
48  .B char *\fIbuffer\fP, int \fIbuffersize\fP);  .B char *\fIbuffer\fP, int \fIbuffersize\fP);
49  .PP  .PP
 .br  
50  .B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP,
51  .ti +5n  .ti +5n
52  .B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP,
53  .ti +5n  .ti +5n
54  .B int \fIbuffersize\fP);  .B int \fIbuffersize\fP);
55  .PP  .PP
 .br  
56  .B int pcre_get_named_substring(const pcre *\fIcode\fP,  .B int pcre_get_named_substring(const pcre *\fIcode\fP,
57  .ti +5n  .ti +5n
58  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 69  PCRE - Perl-compatible regular expressio Line 61  PCRE - Perl-compatible regular expressio
61  .ti +5n  .ti +5n
62  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
63  .PP  .PP
 .br  
64  .B int pcre_get_stringnumber(const pcre *\fIcode\fP,  .B int pcre_get_stringnumber(const pcre *\fIcode\fP,
65  .ti +5n  .ti +5n
66  .B const char *\fIname\fP);  .B const char *\fIname\fP);
67  .PP  .PP
 .br  
68  .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,  .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,
69  .ti +5n  .ti +5n
70  .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);  .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);
71  .PP  .PP
 .br  
72  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
73  .ti +5n  .ti +5n
74  .B int \fIstringcount\fP, int \fIstringnumber\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP,
75  .ti +5n  .ti +5n
76  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
77  .PP  .PP
 .br  
78  .B int pcre_get_substring_list(const char *\fIsubject\fP,  .B int pcre_get_substring_list(const char *\fIsubject\fP,
79  .ti +5n  .ti +5n
80  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"
81  .PP  .PP
 .br  
82  .B void pcre_free_substring(const char *\fIstringptr\fP);  .B void pcre_free_substring(const char *\fIstringptr\fP);
83  .PP  .PP
 .br  
84  .B void pcre_free_substring_list(const char **\fIstringptr\fP);  .B void pcre_free_substring_list(const char **\fIstringptr\fP);
85  .PP  .PP
 .br  
86  .B const unsigned char *pcre_maketables(void);  .B const unsigned char *pcre_maketables(void);
87  .PP  .PP
 .br  
88  .B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"  .B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
89  .ti +5n  .ti +5n
90  .B int \fIwhat\fP, void *\fIwhere\fP);  .B int \fIwhat\fP, void *\fIwhere\fP);
91  .PP  .PP
 .br  
92  .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int  .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int
93  .B *\fIfirstcharptr\fP);  .B *\fIfirstcharptr\fP);
94  .PP  .PP
 .br  
95  .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);  .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);
96  .PP  .PP
 .br  
97  .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);  .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);
98  .PP  .PP
 .br  
99  .B char *pcre_version(void);  .B char *pcre_version(void);
100  .PP  .PP
 .br  
101  .B void *(*pcre_malloc)(size_t);  .B void *(*pcre_malloc)(size_t);
102  .PP  .PP
 .br  
103  .B void (*pcre_free)(void *);  .B void (*pcre_free)(void *);
104  .PP  .PP
 .br  
105  .B void *(*pcre_stack_malloc)(size_t);  .B void *(*pcre_stack_malloc)(size_t);
106  .PP  .PP
 .br  
107  .B void (*pcre_stack_free)(void *);  .B void (*pcre_stack_free)(void *);
108  .PP  .PP
 .br  
109  .B int (*pcre_callout)(pcre_callout_block *);  .B int (*pcre_callout)(pcre_callout_block *);
110  .  .
111  .  .
# Line 165  distribution. The Line 140  distribution. The
140  .\" HREF  .\" HREF
141  \fBpcresample\fP  \fBpcresample\fP
142  .\"  .\"
143  documentation describes how to run it.  documentation describes how to compile and run it.
144  .P  .P
145  A second matching function, \fBpcre_dfa_exec()\fP, which is not  A second matching function, \fBpcre_dfa_exec()\fP, which is not
146  Perl-compatible, is also provided. This uses a different algorithm for the  Perl-compatible, is also provided. This uses a different algorithm for the
# Line 243  points during a matching operation. Deta Line 218  points during a matching operation. Deta
218  documentation.  documentation.
219  .  .
220  .  .
221    .\" HTML <a name="newlines"></a>
222  .SH NEWLINES  .SH NEWLINES
223  .rs  .rs
224  .sp  .sp
225  PCRE supports four different conventions for indicating line breaks in  PCRE supports five different conventions for indicating line breaks in
226  strings: a single CR (carriage return) character, a single LF (linefeed)  strings: a single CR (carriage return) character, a single LF (linefeed)
227  character, the two-character sequence CRLF, or any Unicode newline sequence.  character, the two-character sequence CRLF, any of the three preceding, or any
228  The Unicode newline sequences are the three just mentioned, plus the single  Unicode newline sequence. The Unicode newline sequences are the three just
229  characters VT (vertical tab, U+000B), FF (formfeed, U+000C), NEL (next line,  mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,
230  U+0085), LS (line separator, U+2028), and PS (paragraph separator, U+2029).  U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
231    (paragraph separator, U+2029).
232  .P  .P
233  Each of the first three conventions is used by at least one operating system as  Each of the first three conventions is used by at least one operating system as
234  its standard newline sequence. When PCRE is built, a default can be specified.  its standard newline sequence. When PCRE is built, a default can be specified.
# Line 259  The default default is LF, which is the Line 236  The default default is LF, which is the
236  default can be overridden, either when a pattern is compiled, or when it is  default can be overridden, either when a pattern is compiled, or when it is
237  matched.  matched.
238  .P  .P
239    At compile time, the newline convention can be specified by the \fIoptions\fP
240    argument of \fBpcre_compile()\fP, or it can be specified by special text at the
241    start of the pattern itself; this overrides any other settings. See the
242    .\" HREF
243    \fBpcrepattern\fP
244    .\"
245    page for details of the special character sequences.
246    .P
247  In the PCRE documentation the word "newline" is used to mean "the character or  In the PCRE documentation the word "newline" is used to mean "the character or
248  pair of characters that indicate a line break". The choice of newline  pair of characters that indicate a line break". The choice of newline
249  convention affects the handling of the dot, circumflex, and dollar  convention affects the handling of the dot, circumflex, and dollar
250  metacharacters, the handling of #-comments in /x mode, and, when CRLF is a  metacharacters, the handling of #-comments in /x mode, and, when CRLF is a
251  recognized line ending sequence, the match position advancement for a  recognized line ending sequence, the match position advancement for a
252  non-anchored pattern. The choice of newline convention does not affect the  non-anchored pattern. There is more detail about this in the
253  interpretation of the \en or \er escape sequences.  .\" HTML <a href="#execoptions">
254    .\" </a>
255    section on \fBpcre_exec()\fP options
256    .\"
257    below.
258    .P
259    The choice of newline convention does not affect the interpretation of
260    the \en or \er escape sequences, nor does it affect what \eR matches, which is
261    controlled in a similar way, but by separate options.
262  .  .
263  .  .
264  .SH MULTITHREADING  .SH MULTITHREADING
# Line 289  which it was compiled. Details are given Line 282  which it was compiled. Details are given
282  .\" HREF  .\" HREF
283  \fBpcreprecompile\fP  \fBpcreprecompile\fP
284  .\"  .\"
285  documentation.  documentation. However, compiling a regular expression with one version of PCRE
286    for use with a different version is not guaranteed to work and may cause
287    crashes.
288  .  .
289  .  .
290  .SH "CHECKING BUILD-TIME OPTIONS"  .SH "CHECKING BUILD-TIME OPTIONS"
# Line 322  properties is available; otherwise it is Line 317  properties is available; otherwise it is
317  .sp  .sp
318  The output is an integer whose value specifies the default character sequence  The output is an integer whose value specifies the default character sequence
319  that is recognized as meaning "newline". The four values that are supported  that is recognized as meaning "newline". The four values that are supported
320  are: 10 for LF, 13 for CR, 3338 for CRLF, and -1 for ANY. The default should  are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, and -1 for ANY. The
321  normally be the standard sequence for your operating system.  default should normally be the standard sequence for your operating system.
322    .sp
323      PCRE_CONFIG_BSR
324    .sp
325    The output is an integer whose value indicates what character sequences the \eR
326    escape sequence matches by default. A value of 0 means that \eR matches any
327    Unicode line ending sequence; a value of 1 means that \eR matches only CR, LF,
328    or CRLF. The default can be overridden when a pattern is compiled or matched.
329  .sp  .sp
330    PCRE_CONFIG_LINK_SIZE    PCRE_CONFIG_LINK_SIZE
331  .sp  .sp
# Line 466  facility, see the Line 468  facility, see the
468  .\"  .\"
469  documentation.  documentation.
470  .sp  .sp
471      PCRE_BSR_ANYCRLF
472      PCRE_BSR_UNICODE
473    .sp
474    These options (which are mutually exclusive) control what the \eR escape
475    sequence matches. The choice is either to match only CR, LF, or CRLF, or to
476    match any Unicode newline sequence. The default is specified when PCRE is
477    built. It can be overridden from within the pattern, or by setting an option
478    when a compiled pattern is matched.
479    .sp
480    PCRE_CASELESS    PCRE_CASELESS
481  .sp  .sp
482  If this bit is set, letters in the pattern match both upper and lower case  If this bit is set, letters in the pattern match both upper and lower case
# Line 538  If this option is set, an unanchored pat Line 549  If this option is set, an unanchored pat
549  the first newline in the subject string, though the matched text may continue  the first newline in the subject string, though the matched text may continue
550  over the newline.  over the newline.
551  .sp  .sp
552      PCRE_JAVASCRIPT_COMPAT
553    .sp
554    If this option is set, PCRE's behaviour is changed in some ways so that it is
555    compatible with JavaScript rather than Perl. The changes are as follows:
556    .P
557    (1) A lone closing square bracket in a pattern causes a compile-time error,
558    because this is illegal in JavaScript (by default it is treated as a data
559    character). Thus, the pattern AB]CD becomes illegal when this option is set.
560    .P
561    (2) At run time, a back reference to an unset subpattern group matches an empty
562    string (by default this causes the current matching alternative to fail). A
563    pattern such as (\e1)(a) succeeds when this option is set (assuming it can find
564    an "a" in the subject), whereas it fails by default, for Perl compatibility.
565    .sp
566    PCRE_MULTILINE    PCRE_MULTILINE
567  .sp  .sp
568  By default, PCRE treats the subject string as consisting of a single line of  By default, PCRE treats the subject string as consisting of a single line of
# Line 557  occurrences of ^ or $ in a pattern, sett Line 582  occurrences of ^ or $ in a pattern, sett
582    PCRE_NEWLINE_CR    PCRE_NEWLINE_CR
583    PCRE_NEWLINE_LF    PCRE_NEWLINE_LF
584    PCRE_NEWLINE_CRLF    PCRE_NEWLINE_CRLF
585      PCRE_NEWLINE_ANYCRLF
586    PCRE_NEWLINE_ANY    PCRE_NEWLINE_ANY
587  .sp  .sp
588  These options override the default newline definition that was chosen when PCRE  These options override the default newline definition that was chosen when PCRE
589  was built. Setting the first or the second specifies that a newline is  was built. Setting the first or the second specifies that a newline is
590  indicated by a single character (CR or LF, respectively). Setting  indicated by a single character (CR or LF, respectively). Setting
591  PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character  PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character
592  CRLF sequence. Setting PCRE_NEWLINE_ANY specifies that any Unicode newline  CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three
593  sequence should be recognized. The Unicode newline sequences are the three just  preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies
594  mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,  that any Unicode newline sequence should be recognized. The Unicode newline
595  U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS  sequences are the three just mentioned, plus the single characters VT (vertical
596  (paragraph separator, U+2029). The last two are recognized only in UTF-8 mode.  tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line
597    separator, U+2028), and PS (paragraph separator, U+2029). The last two are
598    recognized only in UTF-8 mode.
599  .P  .P
600  The newline setting in the options word uses three bits that are treated  The newline setting in the options word uses three bits that are treated
601  as a number, giving eight possibilities. Currently only five are used (default  as a number, giving eight possibilities. Currently only six are used (default
602  plus the four values above). This means that if you set more than one newline  plus the five values above). This means that if you set more than one newline
603  option, the combination may or may not be sensible. For example,  option, the combination may or may not be sensible. For example,
604  PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but  PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but
605  other combinations yield unused numbers and cause an error.  other combinations may yield unused numbers and cause an error.
606  .P  .P
607  The only time that a line break is specially recognized when compiling a  The only time that a line break is specially recognized when compiling a
608  pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character  pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character
# Line 620  page. Line 648  page.
648    PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
649  .sp  .sp
650  When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is  When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is
651  automatically checked. If an invalid UTF-8 sequence of bytes is found,  automatically checked. There is a discussion about the
652  \fBpcre_compile()\fP returns an error. If you already know that your pattern is  .\" HTML <a href="pcre.html#utf8strings">
653  valid, and you want to skip this check for performance reasons, you can set the  .\" </a>
654  PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid  validity of UTF-8 strings
655  UTF-8 string as a pattern is undefined. It may cause your program to crash.  .\"
656  Note that this option can also be passed to \fBpcre_exec()\fP and  in the main
657  \fBpcre_dfa_exec()\fP, to suppress the UTF-8 validity checking of subject  .\" HREF
658  strings.  \fBpcre\fP
659    .\"
660    page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_compile()\fP
661    returns an error. If you already know that your pattern is valid, and you want
662    to skip this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK
663    option. When it is set, the effect of passing an invalid UTF-8 string as a
664    pattern is undefined. It may cause your program to crash. Note that this option
665    can also be passed to \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, to suppress
666    the UTF-8 validity checking of subject strings.
667  .  .
668  .  .
669  .SH "COMPILATION ERROR CODES"  .SH "COMPILATION ERROR CODES"
# Line 650  out of use. To avoid confusion, they hav Line 686  out of use. To avoid confusion, they hav
686     9  nothing to repeat     9  nothing to repeat
687    10  [this code is not in use]    10  [this code is not in use]
688    11  internal error: unexpected repeat    11  internal error: unexpected repeat
689    12  unrecognized character after (?    12  unrecognized character after (? or (?-
690    13  POSIX named classes are supported only within a class    13  POSIX named classes are supported only within a class
691    14  missing )    14  missing )
692    15  reference to non-existent subpattern    15  reference to non-existent subpattern
# Line 658  out of use. To avoid confusion, they hav Line 694  out of use. To avoid confusion, they hav
694    17  unknown option bit(s) set    17  unknown option bit(s) set
695    18  missing ) after comment    18  missing ) after comment
696    19  [this code is not in use]    19  [this code is not in use]
697    20  regular expression too large    20  regular expression is too large
698    21  failed to get memory    21  failed to get memory
699    22  unmatched parentheses    22  unmatched parentheses
700    23  internal error: code overflow    23  internal error: code overflow
# Line 667  out of use. To avoid confusion, they hav Line 703  out of use. To avoid confusion, they hav
703    26  malformed number or name after (?(    26  malformed number or name after (?(
704    27  conditional group contains more than two branches    27  conditional group contains more than two branches
705    28  assertion expected after (?(    28  assertion expected after (?(
706    29  (?R or (?digits must be followed by )    29  (?R or (?[+-]digits must be followed by )
707    30  unknown POSIX class name    30  unknown POSIX class name
708    31  POSIX collating elements are not supported    31  POSIX collating elements are not supported
709    32  this version of PCRE is not compiled with PCRE_UTF8 support    32  this version of PCRE is not compiled with PCRE_UTF8 support
# Line 687  out of use. To avoid confusion, they hav Line 723  out of use. To avoid confusion, they hav
723    46  malformed \eP or \ep sequence    46  malformed \eP or \ep sequence
724    47  unknown property name after \eP or \ep    47  unknown property name after \eP or \ep
725    48  subpattern name is too long (maximum 32 characters)    48  subpattern name is too long (maximum 32 characters)
726    49  too many named subpatterns (maximum 10,000)    49  too many named subpatterns (maximum 10000)
727    50  repeated subpattern is too long    50  [this code is not in use]
728    51  octal value is greater than \e377 (not in UTF-8 mode)    51  octal value is greater than \e377 (not in UTF-8 mode)
729    52  internal error: overran compiling workspace    52  internal error: overran compiling workspace
730    53  internal error: previously-checked referenced subpattern not found    53  internal error: previously-checked referenced subpattern not found
731    54  DEFINE group contains more than one branch    54  DEFINE group contains more than one branch
732    55  repeating a DEFINE group is not allowed    55  repeating a DEFINE group is not allowed
733    56  inconsistent NEWLINE options"    56  inconsistent NEWLINE options
734      57  \eg is not followed by a braced, angle-bracketed, or quoted
735            name/number or by a plain number
736      58  a numbered reference must not be zero
737      59  (*VERB) with an argument is not supported
738      60  (*VERB) not recognized
739      61  number is too big
740      62  subpattern name expected
741      63  digit expected after (?+
742      64  ] is an invalid data character in JavaScript compatibility mode
743    .sp
744    The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may
745    be used if the limits were changed when PCRE was built.
746  .  .
747  .  .
748  .SH "STUDYING A PATTERN"  .SH "STUDYING A PATTERN"
# Line 754  bytes is created. Line 802  bytes is created.
802  .SH "LOCALE SUPPORT"  .SH "LOCALE SUPPORT"
803  .rs  .rs
804  .sp  .sp
805  PCRE handles caseless matching, and determines whether characters are letters  PCRE handles caseless matching, and determines whether characters are letters,
806  digits, or whatever, by reference to a set of tables, indexed by character  digits, or whatever, by reference to a set of tables, indexed by character
807  value. When running in UTF-8 mode, this applies only to characters with codes  value. When running in UTF-8 mode, this applies only to characters with codes
808  less than 128. Higher-valued codes never match escapes such as \ew or \ed, but  less than 128. Higher-valued codes never match escapes such as \ew or \ed, but
809  can be tested with \ep if PCRE is built with Unicode character property  can be tested with \ep if PCRE is built with Unicode character property
810  support. The use of locales with Unicode is discouraged.  support. The use of locales with Unicode is discouraged. If you are handling
811  .P  characters with codes greater than 128, you should either use UTF-8 and
812  An internal set of tables is created in the default C locale when PCRE is  Unicode, or use locales, but not try to mix the two.
813  built. This is used when the final argument of \fBpcre_compile()\fP is NULL,  .P
814  and is sufficient for many applications. An alternative set of tables can,  PCRE contains an internal set of tables that are used when the final argument
815  however, be supplied. These may be created in a different locale from the  of \fBpcre_compile()\fP is NULL. These are sufficient for many applications.
816  default. As more and more applications change to using Unicode, the need for  Normally, the internal tables recognize only ASCII characters. However, when
817  this locale support is expected to die away.  PCRE is built, it is possible to cause the internal tables to be rebuilt in the
818    default "C" locale of the local system, which may cause them to be different.
819    .P
820    The internal tables can always be overridden by tables supplied by the
821    application that calls PCRE. These may be created in a different locale from
822    the default. As more and more applications change to using Unicode, the need
823    for this locale support is expected to die away.
824  .P  .P
825  External tables are built by calling the \fBpcre_maketables()\fP function,  External tables are built by calling the \fBpcre_maketables()\fP function,
826  which has no arguments, in the relevant locale. The result can then be passed  which has no arguments, in the relevant locale. The result can then be passed
# Line 779  the following code could be used: Line 833  the following code could be used:
833    tables = pcre_maketables();    tables = pcre_maketables();
834    re = pcre_compile(..., tables);    re = pcre_compile(..., tables);
835  .sp  .sp
836    The locale name "fr_FR" is used on Linux and other Unix-like systems; if you
837    are using Windows, the name for the French locale is "french".
838    .P
839  When \fBpcre_maketables()\fP runs, the tables are built in memory that is  When \fBpcre_maketables()\fP runs, the tables are built in memory that is
840  obtained via \fBpcre_malloc\fP. It is the caller's responsibility to ensure  obtained via \fBpcre_malloc\fP. It is the caller's responsibility to ensure
841  that the memory containing the tables remains available for as long as it is  that the memory containing the tables remains available for as long as it is
# Line 881  table indicating a fixed set of bytes fo Line 938  table indicating a fixed set of bytes fo
938  string, a pointer to the table is returned. Otherwise NULL is returned. The  string, a pointer to the table is returned. Otherwise NULL is returned. The
939  fourth argument should point to an \fBunsigned char *\fP variable.  fourth argument should point to an \fBunsigned char *\fP variable.
940  .sp  .sp
941      PCRE_INFO_HASCRORLF
942    .sp
943    Return 1 if the pattern contains any explicit matches for CR or LF characters,
944    otherwise 0. The fourth argument should point to an \fBint\fP variable. An
945    explicit match is either a literal CR or LF character, or \er or \en.
946    .sp
947      PCRE_INFO_JCHANGED
948    .sp
949    Return 1 if the (?J) or (?-J) option setting is used in the pattern, otherwise
950    0. The fourth argument should point to an \fBint\fP variable. (?J) and
951    (?-J) set and unset the local PCRE_DUPNAMES option, respectively.
952    .sp
953    PCRE_INFO_LASTLITERAL    PCRE_INFO_LASTLITERAL
954  .sp  .sp
955  Return the value of the rightmost literal byte that must exist in any matched  Return the value of the rightmost literal byte that must exist in any matched
# Line 933  When writing code to extract data from n Line 1002  When writing code to extract data from n
1002  name-to-number map, remember that the length of the entries is likely to be  name-to-number map, remember that the length of the entries is likely to be
1003  different for each compiled pattern.  different for each compiled pattern.
1004  .sp  .sp
1005      PCRE_INFO_OKPARTIAL
1006    .sp
1007    Return 1 if the pattern can be used for partial matching, otherwise 0. The
1008    fourth argument should point to an \fBint\fP variable. The
1009    .\" HREF
1010    \fBpcrepartial\fP
1011    .\"
1012    documentation lists the restrictions that apply to patterns when partial
1013    matching is used.
1014    .sp
1015    PCRE_INFO_OPTIONS    PCRE_INFO_OPTIONS
1016  .sp  .sp
1017  Return a copy of the options with which the pattern was compiled. The fourth  Return a copy of the options with which the pattern was compiled. The fourth
1018  argument should point to an \fBunsigned long int\fP variable. These option bits  argument should point to an \fBunsigned long int\fP variable. These option bits
1019  are those specified in the call to \fBpcre_compile()\fP, modified by any  are those specified in the call to \fBpcre_compile()\fP, modified by any
1020  top-level option settings within the pattern itself.  top-level option settings at the start of the pattern itself. In other words,
1021    they are the options that will be in force when matching starts. For example,
1022    if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the
1023    result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED.
1024  .P  .P
1025  A pattern is automatically anchored by PCRE if all of its top-level  A pattern is automatically anchored by PCRE if all of its top-level
1026  alternatives begin with one of the following:  alternatives begin with one of the following:
# Line 1149  called. See the Line 1231  called. See the
1231  .\"  .\"
1232  documentation for a discussion of saving compiled patterns for later use.  documentation for a discussion of saving compiled patterns for later use.
1233  .  .
1234    .\" HTML <a name="execoptions"></a>
1235  .SS "Option bits for \fBpcre_exec()\fP"  .SS "Option bits for \fBpcre_exec()\fP"
1236  .rs  .rs
1237  .sp  .sp
# Line 1163  matching position. If a pattern was comp Line 1246  matching position. If a pattern was comp
1246  to be anchored by virtue of its contents, it cannot be made unachored at  to be anchored by virtue of its contents, it cannot be made unachored at
1247  matching time.  matching time.
1248  .sp  .sp
1249      PCRE_BSR_ANYCRLF
1250      PCRE_BSR_UNICODE
1251    .sp
1252    These options (which are mutually exclusive) control what the \eR escape
1253    sequence matches. The choice is either to match only CR, LF, or CRLF, or to
1254    match any Unicode newline sequence. These options override the choice that was
1255    made or defaulted when the pattern was compiled.
1256    .sp
1257    PCRE_NEWLINE_CR    PCRE_NEWLINE_CR
1258    PCRE_NEWLINE_LF    PCRE_NEWLINE_LF
1259    PCRE_NEWLINE_CRLF    PCRE_NEWLINE_CRLF
1260      PCRE_NEWLINE_ANYCRLF
1261    PCRE_NEWLINE_ANY    PCRE_NEWLINE_ANY
1262  .sp  .sp
1263  These options override the newline definition that was chosen or defaulted when  These options override the newline definition that was chosen or defaulted when
# Line 1173  the pattern was compiled. For details, s Line 1265  the pattern was compiled. For details, s
1265  \fBpcre_compile()\fP above. During matching, the newline choice affects the  \fBpcre_compile()\fP above. During matching, the newline choice affects the
1266  behaviour of the dot, circumflex, and dollar metacharacters. It may also alter  behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
1267  the way the match position is advanced after a match failure for an unanchored  the way the match position is advanced after a match failure for an unanchored
1268  pattern. When PCRE_NEWLINE_CRLF or PCRE_NEWLINE_ANY is set, and a match attempt  pattern.
1269  fails when the current position is at a CRLF sequence, the match position is  .P
1270  advanced by two characters instead of one, in other words, to after the CRLF.  When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is set, and a
1271    match attempt for an unanchored pattern fails when the current position is at a
1272    CRLF sequence, and the pattern contains no explicit matches for CR or LF
1273    characters, the match position is advanced by two characters instead of one, in
1274    other words, to after the CRLF.
1275    .P
1276    The above rule is a compromise that makes the most common cases work as
1277    expected. For example, if the pattern is .+A (and the PCRE_DOTALL option is not
1278    set), it does not match the string "\er\enA" because, after failing at the
1279    start, it skips both the CR and the LF before retrying. However, the pattern
1280    [\er\en]A does match that string, because it contains an explicit CR or LF
1281    reference, and so advances only by one character after the first failure.
1282    .P
1283    An explicit match for CR of LF is either a literal appearance of one of those
1284    characters, or one of the \er or \en escape sequences. Implicit matches such as
1285    [^X] do not count, nor does \es (which includes CR and LF in the characters
1286    that it matches).
1287    .P
1288    Notwithstanding the above, anomalous effects may still occur when CRLF is a
1289    valid newline sequence and explicit \er or \en escapes appear in the pattern.
1290  .sp  .sp
1291    PCRE_NOTBOL    PCRE_NOTBOL
1292  .sp  .sp
# Line 1218  code that demonstrates how to do this in Line 1329  code that demonstrates how to do this in
1329  When PCRE_UTF8 is set at compile time, the validity of the subject as a UTF-8  When PCRE_UTF8 is set at compile time, the validity of the subject as a UTF-8
1330  string is automatically checked when \fBpcre_exec()\fP is subsequently called.  string is automatically checked when \fBpcre_exec()\fP is subsequently called.
1331  The value of \fIstartoffset\fP is also checked to ensure that it points to the  The value of \fIstartoffset\fP is also checked to ensure that it points to the
1332  start of a UTF-8 character. If an invalid UTF-8 sequence of bytes is found,  start of a UTF-8 character. There is a discussion about the validity of UTF-8
1333  \fBpcre_exec()\fP returns the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP  strings in the
1334  contains an invalid value, PCRE_ERROR_BADUTF8_OFFSET is returned.  .\" HTML <a href="pcre.html#utf8strings">
1335    .\" </a>
1336    section on UTF-8 support
1337    .\"
1338    in the main
1339    .\" HREF
1340    \fBpcre\fP
1341    .\"
1342    page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_exec()\fP returns
1343    the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP contains an invalid value,
1344    PCRE_ERROR_BADUTF8_OFFSET is returned.
1345  .P  .P
1346  If you already know that your subject is valid, and you want to skip these  If you already know that your subject is valid, and you want to skip these
1347  checks for performance reasons, you can set the PCRE_NO_UTF8_CHECK option when  checks for performance reasons, you can set the PCRE_NO_UTF8_CHECK option when
# Line 1250  documentation. Line 1371  documentation.
1371  .rs  .rs
1372  .sp  .sp
1373  The subject string is passed to \fBpcre_exec()\fP as a pointer in  The subject string is passed to \fBpcre_exec()\fP as a pointer in
1374  \fIsubject\fP, a length in \fIlength\fP, and a starting byte offset in  \fIsubject\fP, a length (in bytes) in \fIlength\fP, and a starting byte offset
1375  \fIstartoffset\fP. In UTF-8 mode, the byte offset must point to the start of a  in \fIstartoffset\fP. In UTF-8 mode, the byte offset must point to the start of
1376  UTF-8 character. Unlike the pattern string, the subject may contain binary zero  a UTF-8 character. Unlike the pattern string, the subject may contain binary
1377  bytes. When the starting offset is zero, the search for a match starts at the  zero bytes. When the starting offset is zero, the search for a match starts at
1378  beginning of the subject, and this is by far the most common case.  the beginning of the subject, and this is by far the most common case.
1379  .P  .P
1380  A non-zero starting offset is useful when searching for another match in the  A non-zero starting offset is useful when searching for another match in the
1381  same subject by calling \fBpcre_exec()\fP again after a previous success.  same subject by calling \fBpcre_exec()\fP again after a previous success.
# Line 1288  pattern. Following the usage in Jeffrey Line 1409  pattern. Following the usage in Jeffrey
1409  a fragment of a pattern that picks out a substring. PCRE supports several other  a fragment of a pattern that picks out a substring. PCRE supports several other
1410  kinds of parenthesized subpattern that do not cause substrings to be captured.  kinds of parenthesized subpattern that do not cause substrings to be captured.
1411  .P  .P
1412  Captured substrings are returned to the caller via a vector of integer offsets  Captured substrings are returned to the caller via a vector of integers whose
1413  whose address is passed in \fIovector\fP. The number of elements in the vector  address is passed in \fIovector\fP. The number of elements in the vector is
1414  is passed in \fIovecsize\fP, which must be a non-negative number. \fBNote\fP:  passed in \fIovecsize\fP, which must be a non-negative number. \fBNote\fP: this
1415  this argument is NOT the size of \fIovector\fP in bytes.  argument is NOT the size of \fIovector\fP in bytes.
1416  .P  .P
1417  The first two-thirds of the vector is used to pass back captured substrings,  The first two-thirds of the vector is used to pass back captured substrings,
1418  each substring using a pair of integers. The remaining third of the vector is  each substring using a pair of integers. The remaining third of the vector is
1419  used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns,  used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns,
1420  and is not available for passing back information. The length passed in  and is not available for passing back information. The number passed in
1421  \fIovecsize\fP should always be a multiple of three. If it is not, it is  \fIovecsize\fP should always be a multiple of three. If it is not, it is
1422  rounded down.  rounded down.
1423  .P  .P
1424  When a match is successful, information about captured substrings is returned  When a match is successful, information about captured substrings is returned
1425  in pairs of integers, starting at the beginning of \fIovector\fP, and  in pairs of integers, starting at the beginning of \fIovector\fP, and
1426  continuing up to two-thirds of its length at the most. The first element of a  continuing up to two-thirds of its length at the most. The first element of
1427  pair is set to the offset of the first character in a substring, and the second  each pair is set to the byte offset of the first character in a substring, and
1428  is set to the offset of the first character after the end of a substring. The  the second is set to the byte offset of the first character after the end of a
1429  first pair, \fIovector[0]\fP and \fIovector[1]\fP, identify the portion of the  substring. \fBNote\fP: these values are always byte offsets, even in UTF-8
1430  subject string matched by the entire pattern. The next pair is used for the  mode. They are not character counts.
1431  first capturing subpattern, and so on. The value returned by \fBpcre_exec()\fP  .P
1432  is one more than the highest numbered pair that has been set. For example, if  The first pair of integers, \fIovector[0]\fP and \fIovector[1]\fP, identify the
1433  two substrings have been captured, the returned value is 3. If there are no  portion of the subject string matched by the entire pattern. The next pair is
1434  capturing subpatterns, the return value from a successful match is 1,  used for the first capturing subpattern, and so on. The value returned by
1435  indicating that just the first pair of offsets has been set.  \fBpcre_exec()\fP is one more than the highest numbered pair that has been set.
1436    For example, if two substrings have been captured, the returned value is 3. If
1437    there are no capturing subpatterns, the return value from a successful match is
1438    1, indicating that just the first pair of offsets has been set.
1439  .P  .P
1440  If a capturing subpattern is matched repeatedly, it is the last portion of the  If a capturing subpattern is matched repeatedly, it is the last portion of the
1441  string that it matched that is returned.  string that it matched that is returned.
1442  .P  .P
1443  If the vector is too small to hold all the captured substring offsets, it is  If the vector is too small to hold all the captured substring offsets, it is
1444  used as far as possible (up to two-thirds of its length), and the function  used as far as possible (up to two-thirds of its length), and the function
1445  returns a value of zero. In particular, if the substring offsets are not of  returns a value of zero. If the substring offsets are not of interest,
1446  interest, \fBpcre_exec()\fP may be called with \fIovector\fP passed as NULL and  \fBpcre_exec()\fP may be called with \fIovector\fP passed as NULL and
1447  \fIovecsize\fP as zero. However, if the pattern contains back references and  \fIovecsize\fP as zero. However, if the pattern contains back references and
1448  the \fIovector\fP is not big enough to remember the related substrings, PCRE  the \fIovector\fP is not big enough to remember the related substrings, PCRE
1449  has to get additional memory for use during matching. Thus it is usually  has to get additional memory for use during matching. Thus it is usually
# Line 1452  The internal recursion limit, as specifi Line 1576  The internal recursion limit, as specifi
1576  field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the  field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the
1577  description above.  description above.
1578  .sp  .sp
   PCRE_ERROR_NULLWSLIMIT    (-22)  
 .sp  
 When a group that can match an empty substring is repeated with an unbounded  
 upper limit, the subject position at the start of the group must be remembered,  
 so that a test for an empty string can be made when the end of the group is  
 reached. Some workspace is required for this; if it runs out, this error is  
 given.  
 .sp  
1579    PCRE_ERROR_BADNEWLINE     (-23)    PCRE_ERROR_BADNEWLINE     (-23)
1580  .sp  .sp
1581  An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.  An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
1582  .P  .P
1583  Error numbers -16 to -20 are not used by \fBpcre_exec()\fP.  Error numbers -16 to -20 and -22 are not used by \fBpcre_exec()\fP.
1584  .  .
1585  .  .
1586  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
# Line 1476  Error numbers -16 to -20 are not used by Line 1592  Error numbers -16 to -20 are not used by
1592  .ti +5n  .ti +5n
1593  .B int \fIbuffersize\fP);  .B int \fIbuffersize\fP);
1594  .PP  .PP
 .br  
1595  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
1596  .ti +5n  .ti +5n
1597  .B int \fIstringcount\fP, int \fIstringnumber\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP,
1598  .ti +5n  .ti +5n
1599  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
1600  .PP  .PP
 .br  
1601  .B int pcre_get_substring_list(const char *\fIsubject\fP,  .B int pcre_get_substring_list(const char *\fIsubject\fP,
1602  .ti +5n  .ti +5n
1603  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"
# Line 1569  provided. Line 1683  provided.
1683  .ti +5n  .ti +5n
1684  .B const char *\fIname\fP);  .B const char *\fIname\fP);
1685  .PP  .PP
 .br  
1686  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
1687  .ti +5n  .ti +5n
1688  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1578  provided. Line 1691  provided.
1691  .ti +5n  .ti +5n
1692  .B char *\fIbuffer\fP, int \fIbuffersize\fP);  .B char *\fIbuffer\fP, int \fIbuffersize\fP);
1693  .PP  .PP
 .br  
1694  .B int pcre_get_named_substring(const pcre *\fIcode\fP,  .B int pcre_get_named_substring(const pcre *\fIcode\fP,
1695  .ti +5n  .ti +5n
1696  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1614  pattern. This is needed in order to gain Line 1726  pattern. This is needed in order to gain
1726  translation table.  translation table.
1727  .P  .P
1728  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they
1729  then call \fIpcre_copy_substring()\fP or \fIpcre_get_substring()\fP, as  then call \fBpcre_copy_substring()\fP or \fBpcre_get_substring()\fP, as
1730  appropriate.  appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names,
1731    the behaviour may not be what you want (see the next section).
1732  .  .
1733  .  .
1734  .SH "DUPLICATE SUBPATTERN NAMES"  .SH "DUPLICATE SUBPATTERN NAMES"
# Line 1632  example is shown in the Line 1745  example is shown in the
1745  .\" HREF  .\" HREF
1746  \fBpcrepattern\fP  \fBpcrepattern\fP
1747  .\"  .\"
1748  documentation. When duplicates are present, \fBpcre_copy_named_substring()\fP  documentation.
1749  and \fBpcre_get_named_substring()\fP return the first substring corresponding  .P
1750  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
1751  The \fBpcre_get_stringnumber()\fP function returns one of the numbers that are  \fBpcre_get_named_substring()\fP return the first substring corresponding to
1752  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
1753  .sp  returned; no data is returned. The \fBpcre_get_stringnumber()\fP function
1754    returns one of the numbers that are associated with the name, but it is not
1755    defined which it is.
1756    .P
1757  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,
1758  you must use the \fBpcre_get_stringtable_entries()\fP function. The first  you must use the \fBpcre_get_stringtable_entries()\fP function. The first
1759  argument is the compiled pattern, and the second is the name. The third and  argument is the compiled pattern, and the second is the name. The third and
# Line 1846  extremely rare, as a vector of size 1000 Line 1962  extremely rare, as a vector of size 1000
1962  \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),  \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
1963  \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),  \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
1964  \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).  \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
1965  .P  .
1966  .in 0  .
1967  Last updated: 30 November 2006  .SH AUTHOR
1968  .br  .rs
1969  Copyright (c) 1997-2006 University of Cambridge.  .sp
1970    .nf
1971    Philip Hazel
1972    University Computing Service
1973    Cambridge CB2 3QH, England.
1974    .fi
1975    .
1976    .
1977    .SH REVISION
1978    .rs
1979    .sp
1980    .nf
1981    Last updated: 24 August 2008
1982    Copyright (c) 1997-2008 University of Cambridge.
1983    .fi

Legend:
Removed from v.96  
changed lines
  Added in v.371

  ViewVC Help
Powered by ViewVC 1.1.5