/[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 93 by nigel, Sat Feb 24 21:41:42 2007 UTC revision 292 by ph10, Thu Dec 27 09:27:23 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  .  .
# 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 557  occurrences of ^ or $ in a pattern, sett Line 568  occurrences of ^ or $ in a pattern, sett
568    PCRE_NEWLINE_CR    PCRE_NEWLINE_CR
569    PCRE_NEWLINE_LF    PCRE_NEWLINE_LF
570    PCRE_NEWLINE_CRLF    PCRE_NEWLINE_CRLF
571      PCRE_NEWLINE_ANYCRLF
572    PCRE_NEWLINE_ANY    PCRE_NEWLINE_ANY
573  .sp  .sp
574  These options override the default newline definition that was chosen when PCRE  These options override the default newline definition that was chosen when PCRE
575  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
576  indicated by a single character (CR or LF, respectively). Setting  indicated by a single character (CR or LF, respectively). Setting
577  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
578  CRLF sequence. Setting PCRE_NEWLINE_ANY specifies that any Unicode newline  CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three
579  sequence should be recognized. The Unicode newline sequences are the three just  preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies
580  mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,  that any Unicode newline sequence should be recognized. The Unicode newline
581  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
582  (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
583    separator, U+2028), and PS (paragraph separator, U+2029). The last two are
584    recognized only in UTF-8 mode.
585  .P  .P
586  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
587  as a number, giving eight possibilities. Currently only five are used (default  as a number, giving eight possibilities. Currently only six are used (default
588  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
589  option, the combination may or may not be sensible. For example,  option, the combination may or may not be sensible. For example,
590  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
591  other combinations yield unused numbers and cause an error.  other combinations may yield unused numbers and cause an error.
592  .P  .P
593  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
594  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 634  page.
634    PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
635  .sp  .sp
636  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
637  automatically checked. If an invalid UTF-8 sequence of bytes is found,  automatically checked. There is a discussion about the
638  \fBpcre_compile()\fP returns an error. If you already know that your pattern is  .\" HTML <a href="pcre.html#utf8strings">
639  valid, and you want to skip this check for performance reasons, you can set the  .\" </a>
640  PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid  validity of UTF-8 strings
641  UTF-8 string as a pattern is undefined. It may cause your program to crash.  .\"
642  Note that this option can also be passed to \fBpcre_exec()\fP and  in the main
643  \fBpcre_dfa_exec()\fP, to suppress the UTF-8 validity checking of subject  .\" HREF
644  strings.  \fBpcre\fP
645    .\"
646    page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_compile()\fP
647    returns an error. If you already know that your pattern is valid, and you want
648    to skip this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK
649    option. When it is set, the effect of passing an invalid UTF-8 string as a
650    pattern is undefined. It may cause your program to crash. Note that this option
651    can also be passed to \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, to suppress
652    the UTF-8 validity checking of subject strings.
653  .  .
654  .  .
655  .SH "COMPILATION ERROR CODES"  .SH "COMPILATION ERROR CODES"
# Line 650  out of use. To avoid confusion, they hav Line 672  out of use. To avoid confusion, they hav
672     9  nothing to repeat     9  nothing to repeat
673    10  [this code is not in use]    10  [this code is not in use]
674    11  internal error: unexpected repeat    11  internal error: unexpected repeat
675    12  unrecognized character after (?    12  unrecognized character after (? or (?-
676    13  POSIX named classes are supported only within a class    13  POSIX named classes are supported only within a class
677    14  missing )    14  missing )
678    15  reference to non-existent subpattern    15  reference to non-existent subpattern
# Line 658  out of use. To avoid confusion, they hav Line 680  out of use. To avoid confusion, they hav
680    17  unknown option bit(s) set    17  unknown option bit(s) set
681    18  missing ) after comment    18  missing ) after comment
682    19  [this code is not in use]    19  [this code is not in use]
683    20  regular expression too large    20  regular expression is too large
684    21  failed to get memory    21  failed to get memory
685    22  unmatched parentheses    22  unmatched parentheses
686    23  internal error: code overflow    23  internal error: code overflow
# Line 667  out of use. To avoid confusion, they hav Line 689  out of use. To avoid confusion, they hav
689    26  malformed number or name after (?(    26  malformed number or name after (?(
690    27  conditional group contains more than two branches    27  conditional group contains more than two branches
691    28  assertion expected after (?(    28  assertion expected after (?(
692    29  (?R or (?digits must be followed by )    29  (?R or (?[+-]digits must be followed by )
693    30  unknown POSIX class name    30  unknown POSIX class name
694    31  POSIX collating elements are not supported    31  POSIX collating elements are not supported
695    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 709  out of use. To avoid confusion, they hav
709    46  malformed \eP or \ep sequence    46  malformed \eP or \ep sequence
710    47  unknown property name after \eP or \ep    47  unknown property name after \eP or \ep
711    48  subpattern name is too long (maximum 32 characters)    48  subpattern name is too long (maximum 32 characters)
712    49  too many named subpatterns (maximum 10,000)    49  too many named subpatterns (maximum 10000)
713    50  repeated subpattern is too long    50  [this code is not in use]
714    51  octal value is greater than \e377 (not in UTF-8 mode)    51  octal value is greater than \e377 (not in UTF-8 mode)
715    52  internal error: overran compiling workspace    52  internal error: overran compiling workspace
716    53  internal error: previously-checked referenced subpattern not found    53  internal error: previously-checked referenced subpattern not found
717    54  DEFINE group contains more than one branch    54  DEFINE group contains more than one branch
718    55  repeating a DEFINE group is not allowed    55  repeating a DEFINE group is not allowed
719    56  inconsistent NEWLINE options"    56  inconsistent NEWLINE options
720      57  \eg is not followed by a braced name or an optionally braced
721            non-zero number
722      58  (?+ or (?- or (?(+ or (?(- must be followed by a non-zero number
723      59  (*VERB) with an argument is not supported
724      60  (*VERB) not recognized
725      61  number is too big
726      62  subpattern name expected
727      63  digit expected after (?+
728    .sp
729    The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may
730    be used if the limits were changed when PCRE was built.
731  .  .
732  .  .
733  .SH "STUDYING A PATTERN"  .SH "STUDYING A PATTERN"
# Line 754  bytes is created. Line 787  bytes is created.
787  .SH "LOCALE SUPPORT"  .SH "LOCALE SUPPORT"
788  .rs  .rs
789  .sp  .sp
790  PCRE handles caseless matching, and determines whether characters are letters  PCRE handles caseless matching, and determines whether characters are letters,
791  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
792  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
793  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
794  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
795  support. The use of locales with Unicode is discouraged.  support. The use of locales with Unicode is discouraged. If you are handling
796  .P  characters with codes greater than 128, you should either use UTF-8 and
797  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.
798  built. This is used when the final argument of \fBpcre_compile()\fP is NULL,  .P
799  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
800  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.
801  default. As more and more applications change to using Unicode, the need for  Normally, the internal tables recognize only ASCII characters. However, when
802  this locale support is expected to die away.  PCRE is built, it is possible to cause the internal tables to be rebuilt in the
803    default "C" locale of the local system, which may cause them to be different.
804    .P
805    The internal tables can always be overridden by tables supplied by the
806    application that calls PCRE. These may be created in a different locale from
807    the default. As more and more applications change to using Unicode, the need
808    for this locale support is expected to die away.
809  .P  .P
810  External tables are built by calling the \fBpcre_maketables()\fP function,  External tables are built by calling the \fBpcre_maketables()\fP function,
811  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 818  the following code could be used:
818    tables = pcre_maketables();    tables = pcre_maketables();
819    re = pcre_compile(..., tables);    re = pcre_compile(..., tables);
820  .sp  .sp
821    The locale name "fr_FR" is used on Linux and other Unix-like systems; if you
822    are using Windows, the name for the French locale is "french".
823    .P
824  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
825  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
826  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 923  table indicating a fixed set of bytes fo
923  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
924  fourth argument should point to an \fBunsigned char *\fP variable.  fourth argument should point to an \fBunsigned char *\fP variable.
925  .sp  .sp
926      PCRE_INFO_HASCRORLF
927    .sp
928    Return 1 if the pattern contains any explicit matches for CR or LF characters,
929    otherwise 0. The fourth argument should point to an \fBint\fP variable. An
930    explicit match is either a literal CR or LF character, or \er or \en.
931    .sp
932      PCRE_INFO_JCHANGED
933    .sp
934    Return 1 if the (?J) or (?-J) option setting is used in the pattern, otherwise
935    0. The fourth argument should point to an \fBint\fP variable. (?J) and
936    (?-J) set and unset the local PCRE_DUPNAMES option, respectively.
937    .sp
938    PCRE_INFO_LASTLITERAL    PCRE_INFO_LASTLITERAL
939  .sp  .sp
940  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 987  When writing code to extract data from n
987  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
988  different for each compiled pattern.  different for each compiled pattern.
989  .sp  .sp
990      PCRE_INFO_OKPARTIAL
991    .sp
992    Return 1 if the pattern can be used for partial matching, otherwise 0. The
993    fourth argument should point to an \fBint\fP variable. The
994    .\" HREF
995    \fBpcrepartial\fP
996    .\"
997    documentation lists the restrictions that apply to patterns when partial
998    matching is used.
999    .sp
1000    PCRE_INFO_OPTIONS    PCRE_INFO_OPTIONS
1001  .sp  .sp
1002  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
1003  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
1004  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
1005  top-level option settings within the pattern itself.  top-level option settings at the start of the pattern itself. In other words,
1006    they are the options that will be in force when matching starts. For example,
1007    if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the
1008    result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED.
1009  .P  .P
1010  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
1011  alternatives begin with one of the following:  alternatives begin with one of the following:
# Line 1149  called. See the Line 1216  called. See the
1216  .\"  .\"
1217  documentation for a discussion of saving compiled patterns for later use.  documentation for a discussion of saving compiled patterns for later use.
1218  .  .
1219    .\" HTML <a name="execoptions"></a>
1220  .SS "Option bits for \fBpcre_exec()\fP"  .SS "Option bits for \fBpcre_exec()\fP"
1221  .rs  .rs
1222  .sp  .sp
# Line 1163  matching position. If a pattern was comp Line 1231  matching position. If a pattern was comp
1231  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
1232  matching time.  matching time.
1233  .sp  .sp
1234      PCRE_BSR_ANYCRLF
1235      PCRE_BSR_UNICODE
1236    .sp
1237    These options (which are mutually exclusive) control what the \eR escape
1238    sequence matches. The choice is either to match only CR, LF, or CRLF, or to
1239    match any Unicode newline sequence. These options override the choice that was
1240    made or defaulted when the pattern was compiled.
1241    .sp
1242    PCRE_NEWLINE_CR    PCRE_NEWLINE_CR
1243    PCRE_NEWLINE_LF    PCRE_NEWLINE_LF
1244    PCRE_NEWLINE_CRLF    PCRE_NEWLINE_CRLF
1245      PCRE_NEWLINE_ANYCRLF
1246    PCRE_NEWLINE_ANY    PCRE_NEWLINE_ANY
1247  .sp  .sp
1248  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 1250  the pattern was compiled. For details, s
1250  \fBpcre_compile()\fP above. During matching, the newline choice affects the  \fBpcre_compile()\fP above. During matching, the newline choice affects the
1251  behaviour of the dot, circumflex, and dollar metacharacters. It may also alter  behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
1252  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
1253  pattern. When PCRE_NEWLINE_CRLF or PCRE_NEWLINE_ANY is set, and a match attempt  pattern.
1254  fails when the current position is at a CRLF sequence, the match position is  .P
1255  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
1256    match attempt for an unanchored pattern fails when the current position is at a
1257    CRLF sequence, and the pattern contains no explicit matches for CR or LF
1258    characters, the match position is advanced by two characters instead of one, in
1259    other words, to after the CRLF.
1260    .P
1261    The above rule is a compromise that makes the most common cases work as
1262    expected. For example, if the pattern is .+A (and the PCRE_DOTALL option is not
1263    set), it does not match the string "\er\enA" because, after failing at the
1264    start, it skips both the CR and the LF before retrying. However, the pattern
1265    [\er\en]A does match that string, because it contains an explicit CR or LF
1266    reference, and so advances only by one character after the first failure.
1267    .P
1268    An explicit match for CR of LF is either a literal appearance of one of those
1269    characters, or one of the \er or \en escape sequences. Implicit matches such as
1270    [^X] do not count, nor does \es (which includes CR and LF in the characters
1271    that it matches).
1272    .P
1273    Notwithstanding the above, anomalous effects may still occur when CRLF is a
1274    valid newline sequence and explicit \er or \en escapes appear in the pattern.
1275  .sp  .sp
1276    PCRE_NOTBOL    PCRE_NOTBOL
1277  .sp  .sp
# Line 1218  code that demonstrates how to do this in Line 1314  code that demonstrates how to do this in
1314  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
1315  string is automatically checked when \fBpcre_exec()\fP is subsequently called.  string is automatically checked when \fBpcre_exec()\fP is subsequently called.
1316  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
1317  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
1318  \fBpcre_exec()\fP returns the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP  strings in the
1319  contains an invalid value, PCRE_ERROR_BADUTF8_OFFSET is returned.  .\" HTML <a href="pcre.html#utf8strings">
1320    .\" </a>
1321    section on UTF-8 support
1322    .\"
1323    in the main
1324    .\" HREF
1325    \fBpcre\fP
1326    .\"
1327    page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_exec()\fP returns
1328    the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP contains an invalid value,
1329    PCRE_ERROR_BADUTF8_OFFSET is returned.
1330  .P  .P
1331  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
1332  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 1452  The internal recursion limit, as specifi Line 1558  The internal recursion limit, as specifi
1558  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
1559  description above.  description above.
1560  .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  
1561    PCRE_ERROR_BADNEWLINE     (-23)    PCRE_ERROR_BADNEWLINE     (-23)
1562  .sp  .sp
1563  An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.  An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
1564  .P  .P
1565  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.
1566  .  .
1567  .  .
1568  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
# Line 1476  Error numbers -16 to -20 are not used by Line 1574  Error numbers -16 to -20 are not used by
1574  .ti +5n  .ti +5n
1575  .B int \fIbuffersize\fP);  .B int \fIbuffersize\fP);
1576  .PP  .PP
 .br  
1577  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
1578  .ti +5n  .ti +5n
1579  .B int \fIstringcount\fP, int \fIstringnumber\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP,
1580  .ti +5n  .ti +5n
1581  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
1582  .PP  .PP
 .br  
1583  .B int pcre_get_substring_list(const char *\fIsubject\fP,  .B int pcre_get_substring_list(const char *\fIsubject\fP,
1584  .ti +5n  .ti +5n
1585  .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 1665  provided.
1665  .ti +5n  .ti +5n
1666  .B const char *\fIname\fP);  .B const char *\fIname\fP);
1667  .PP  .PP
 .br  
1668  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
1669  .ti +5n  .ti +5n
1670  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1578  provided. Line 1673  provided.
1673  .ti +5n  .ti +5n
1674  .B char *\fIbuffer\fP, int \fIbuffersize\fP);  .B char *\fIbuffer\fP, int \fIbuffersize\fP);
1675  .PP  .PP
 .br  
1676  .B int pcre_get_named_substring(const pcre *\fIcode\fP,  .B int pcre_get_named_substring(const pcre *\fIcode\fP,
1677  .ti +5n  .ti +5n
1678  .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 1708  pattern. This is needed in order to gain
1708  translation table.  translation table.
1709  .P  .P
1710  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they
1711  then call \fIpcre_copy_substring()\fP or \fIpcre_get_substring()\fP, as  then call \fBpcre_copy_substring()\fP or \fBpcre_get_substring()\fP, as
1712  appropriate.  appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names,
1713    the behaviour may not be what you want (see the next section).
1714  .  .
1715  .  .
1716  .SH "DUPLICATE SUBPATTERN NAMES"  .SH "DUPLICATE SUBPATTERN NAMES"
# Line 1632  example is shown in the Line 1727  example is shown in the
1727  .\" HREF  .\" HREF
1728  \fBpcrepattern\fP  \fBpcrepattern\fP
1729  .\"  .\"
1730  documentation. When duplicates are present, \fBpcre_copy_named_substring()\fP  documentation.
1731  and \fBpcre_get_named_substring()\fP return the first substring corresponding  .P
1732  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
1733  The \fBpcre_get_stringnumber()\fP function returns one of the numbers that are  \fBpcre_get_named_substring()\fP return the first substring corresponding to
1734  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
1735  .sp  returned; no data is returned. The \fBpcre_get_stringnumber()\fP function
1736    returns one of the numbers that are associated with the name, but it is not
1737    defined which it is.
1738    .P
1739  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,
1740  you must use the \fBpcre_get_stringtable_entries()\fP function. The first  you must use the \fBpcre_get_stringtable_entries()\fP function. The first
1741  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 1944  extremely rare, as a vector of size 1000
1944  \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),  \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
1945  \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),  \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
1946  \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).  \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
1947  .P  .
1948  .in 0  .
1949  Last updated: 30 November 2006  .SH AUTHOR
1950  .br  .rs
1951  Copyright (c) 1997-2006 University of Cambridge.  .sp
1952    .nf
1953    Philip Hazel
1954    University Computing Service
1955    Cambridge CB2 3QH, England.
1956    .fi
1957    .
1958    .
1959    .SH REVISION
1960    .rs
1961    .sp
1962    .nf
1963    Last updated: 26 December 2007
1964    Copyright (c) 1997-2007 University of Cambridge.
1965    .fi

Legend:
Removed from v.93  
changed lines
  Added in v.292

  ViewVC Help
Powered by ViewVC 1.1.5