/[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 227 by ph10, Tue Aug 21 15:00:15 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. The choice of newline convention does not affect the interpretation of
258    the \en or \er escape sequences.
259  .  .
260  .  .
261  .SH MULTITHREADING  .SH MULTITHREADING
# Line 289  which it was compiled. Details are given Line 279  which it was compiled. Details are given
279  .\" HREF  .\" HREF
280  \fBpcreprecompile\fP  \fBpcreprecompile\fP
281  .\"  .\"
282  documentation.  documentation. However, compiling a regular expression with one version of PCRE
283    for use with a different version is not guaranteed to work and may cause
284    crashes.
285  .  .
286  .  .
287  .SH "CHECKING BUILD-TIME OPTIONS"  .SH "CHECKING BUILD-TIME OPTIONS"
# Line 322  properties is available; otherwise it is Line 314  properties is available; otherwise it is
314  .sp  .sp
315  The output is an integer whose value specifies the default character sequence  The output is an integer whose value specifies the default character sequence
316  that is recognized as meaning "newline". The four values that are supported  that is recognized as meaning "newline". The four values that are supported
317  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
318  normally be the standard sequence for your operating system.  default should normally be the standard sequence for your operating system.
319  .sp  .sp
320    PCRE_CONFIG_LINK_SIZE    PCRE_CONFIG_LINK_SIZE
321  .sp  .sp
# Line 557  occurrences of ^ or $ in a pattern, sett Line 549  occurrences of ^ or $ in a pattern, sett
549    PCRE_NEWLINE_CR    PCRE_NEWLINE_CR
550    PCRE_NEWLINE_LF    PCRE_NEWLINE_LF
551    PCRE_NEWLINE_CRLF    PCRE_NEWLINE_CRLF
552      PCRE_NEWLINE_ANYCRLF
553    PCRE_NEWLINE_ANY    PCRE_NEWLINE_ANY
554  .sp  .sp
555  These options override the default newline definition that was chosen when PCRE  These options override the default newline definition that was chosen when PCRE
556  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
557  indicated by a single character (CR or LF, respectively). Setting  indicated by a single character (CR or LF, respectively). Setting
558  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
559  CRLF sequence. Setting PCRE_NEWLINE_ANY specifies that any Unicode newline  CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three
560  sequence should be recognized. The Unicode newline sequences are the three just  preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies
561  mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,  that any Unicode newline sequence should be recognized. The Unicode newline
562  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
563  (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
564    separator, U+2028), and PS (paragraph separator, U+2029). The last two are
565    recognized only in UTF-8 mode.
566  .P  .P
567  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
568  as a number, giving eight possibilities. Currently only five are used (default  as a number, giving eight possibilities. Currently only six are used (default
569  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
570  option, the combination may or may not be sensible. For example,  option, the combination may or may not be sensible. For example,
571  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
572  other combinations yield unused numbers and cause an error.  other combinations may yield unused numbers and cause an error.
573  .P  .P
574  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
575  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 615  page.
615    PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
616  .sp  .sp
617  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
618  automatically checked. If an invalid UTF-8 sequence of bytes is found,  automatically checked. There is a discussion about the
619  \fBpcre_compile()\fP returns an error. If you already know that your pattern is  .\" HTML <a href="pcre.html#utf8strings">
620  valid, and you want to skip this check for performance reasons, you can set the  .\" </a>
621  PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid  validity of UTF-8 strings
622  UTF-8 string as a pattern is undefined. It may cause your program to crash.  .\"
623  Note that this option can also be passed to \fBpcre_exec()\fP and  in the main
624  \fBpcre_dfa_exec()\fP, to suppress the UTF-8 validity checking of subject  .\" HREF
625  strings.  \fBpcre\fP
626    .\"
627    page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_compile()\fP
628    returns an error. If you already know that your pattern is valid, and you want
629    to skip this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK
630    option. When it is set, the effect of passing an invalid UTF-8 string as a
631    pattern is undefined. It may cause your program to crash. Note that this option
632    can also be passed to \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, to suppress
633    the UTF-8 validity checking of subject strings.
634  .  .
635  .  .
636  .SH "COMPILATION ERROR CODES"  .SH "COMPILATION ERROR CODES"
# Line 667  out of use. To avoid confusion, they hav Line 670  out of use. To avoid confusion, they hav
670    26  malformed number or name after (?(    26  malformed number or name after (?(
671    27  conditional group contains more than two branches    27  conditional group contains more than two branches
672    28  assertion expected after (?(    28  assertion expected after (?(
673    29  (?R or (?digits must be followed by )    29  (?R or (?[+-]digits must be followed by )
674    30  unknown POSIX class name    30  unknown POSIX class name
675    31  POSIX collating elements are not supported    31  POSIX collating elements are not supported
676    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 688  out of use. To avoid confusion, they hav Line 691  out of use. To avoid confusion, they hav
691    47  unknown property name after \eP or \ep    47  unknown property name after \eP or \ep
692    48  subpattern name is too long (maximum 32 characters)    48  subpattern name is too long (maximum 32 characters)
693    49  too many named subpatterns (maximum 10,000)    49  too many named subpatterns (maximum 10,000)
694    50  repeated subpattern is too long    50  [this code is not in use]
695    51  octal value is greater than \e377 (not in UTF-8 mode)    51  octal value is greater than \e377 (not in UTF-8 mode)
696    52  internal error: overran compiling workspace    52  internal error: overran compiling workspace
697    53  internal error: previously-checked referenced subpattern not found    53  internal error: previously-checked referenced subpattern not found
698    54  DEFINE group contains more than one branch    54  DEFINE group contains more than one branch
699    55  repeating a DEFINE group is not allowed    55  repeating a DEFINE group is not allowed
700    56  inconsistent NEWLINE options"    56  inconsistent NEWLINE options"
701      57  \eg is not followed by a braced name or an optionally braced
702            non-zero number
703      58  (?+ or (?- or (?(+ or (?(- must be followed by a non-zero number
704  .  .
705  .  .
706  .SH "STUDYING A PATTERN"  .SH "STUDYING A PATTERN"
# Line 754  bytes is created. Line 760  bytes is created.
760  .SH "LOCALE SUPPORT"  .SH "LOCALE SUPPORT"
761  .rs  .rs
762  .sp  .sp
763  PCRE handles caseless matching, and determines whether characters are letters  PCRE handles caseless matching, and determines whether characters are letters,
764  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
765  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
766  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
767  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
768  support. The use of locales with Unicode is discouraged.  support. The use of locales with Unicode is discouraged. If you are handling
769  .P  characters with codes greater than 128, you should either use UTF-8 and
770  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.
771  built. This is used when the final argument of \fBpcre_compile()\fP is NULL,  .P
772  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
773  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.
774  default. As more and more applications change to using Unicode, the need for  Normally, the internal tables recognize only ASCII characters. However, when
775  this locale support is expected to die away.  PCRE is built, it is possible to cause the internal tables to be rebuilt in the
776    default "C" locale of the local system, which may cause them to be different.
777    .P
778    The internal tables can always be overridden by tables supplied by the
779    application that calls PCRE. These may be created in a different locale from
780    the default. As more and more applications change to using Unicode, the need
781    for this locale support is expected to die away.
782  .P  .P
783  External tables are built by calling the \fBpcre_maketables()\fP function,  External tables are built by calling the \fBpcre_maketables()\fP function,
784  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 791  the following code could be used:
791    tables = pcre_maketables();    tables = pcre_maketables();
792    re = pcre_compile(..., tables);    re = pcre_compile(..., tables);
793  .sp  .sp
794    The locale name "fr_FR" is used on Linux and other Unix-like systems; if you
795    are using Windows, the name for the French locale is "french".
796    .P
797  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
798  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
799  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 896  table indicating a fixed set of bytes fo
896  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
897  fourth argument should point to an \fBunsigned char *\fP variable.  fourth argument should point to an \fBunsigned char *\fP variable.
898  .sp  .sp
899      PCRE_INFO_HASCRORLF
900    .sp
901    Return 1 if the pattern contains any explicit matches for CR or LF characters,
902    otherwise 0. The fourth argument should point to an \fBint\fP variable.
903    .sp
904      PCRE_INFO_JCHANGED
905    .sp
906    Return 1 if the (?J) option setting is used in the pattern, otherwise 0. The
907    fourth argument should point to an \fBint\fP variable. The (?J) internal option
908    setting changes the local PCRE_DUPNAMES option.
909    .sp
910    PCRE_INFO_LASTLITERAL    PCRE_INFO_LASTLITERAL
911  .sp  .sp
912  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 959  When writing code to extract data from n
959  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
960  different for each compiled pattern.  different for each compiled pattern.
961  .sp  .sp
962      PCRE_INFO_OKPARTIAL
963    .sp
964    Return 1 if the pattern can be used for partial matching, otherwise 0. The
965    fourth argument should point to an \fBint\fP variable. The
966    .\" HREF
967    \fBpcrepartial\fP
968    .\"
969    documentation lists the restrictions that apply to patterns when partial
970    matching is used.
971    .sp
972    PCRE_INFO_OPTIONS    PCRE_INFO_OPTIONS
973  .sp  .sp
974  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
975  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
976  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
977  top-level option settings within the pattern itself.  top-level option settings at the start of the pattern itself. In other words,
978    they are the options that will be in force when matching starts. For example,
979    if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the
980    result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED.
981  .P  .P
982  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
983  alternatives begin with one of the following:  alternatives begin with one of the following:
# Line 1149  called. See the Line 1188  called. See the
1188  .\"  .\"
1189  documentation for a discussion of saving compiled patterns for later use.  documentation for a discussion of saving compiled patterns for later use.
1190  .  .
1191    .\" HTML <a name="execoptions"></a>
1192  .SS "Option bits for \fBpcre_exec()\fP"  .SS "Option bits for \fBpcre_exec()\fP"
1193  .rs  .rs
1194  .sp  .sp
# Line 1166  matching time. Line 1206  matching time.
1206    PCRE_NEWLINE_CR    PCRE_NEWLINE_CR
1207    PCRE_NEWLINE_LF    PCRE_NEWLINE_LF
1208    PCRE_NEWLINE_CRLF    PCRE_NEWLINE_CRLF
1209      PCRE_NEWLINE_ANYCRLF
1210    PCRE_NEWLINE_ANY    PCRE_NEWLINE_ANY
1211  .sp  .sp
1212  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 1214  the pattern was compiled. For details, s
1214  \fBpcre_compile()\fP above. During matching, the newline choice affects the  \fBpcre_compile()\fP above. During matching, the newline choice affects the
1215  behaviour of the dot, circumflex, and dollar metacharacters. It may also alter  behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
1216  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
1217  pattern. When PCRE_NEWLINE_CRLF or PCRE_NEWLINE_ANY is set, and a match attempt  pattern.
1218  fails when the current position is at a CRLF sequence, the match position is  .P
1219  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
1220    match attempt for an unanchored pattern fails when the current position is at a
1221    CRLF sequence, and the pattern contains no explicit matches for CR or NL
1222    characters, the match position is advanced by two characters instead of one, in
1223    other words, to after the CRLF.
1224    .P
1225    The above rule is a compromise that makes the most common cases work as
1226    expected. For example, if the pattern is .+A (and the PCRE_DOTALL option is not
1227    set), it does not match the string "\er\enA" because, after failing at the
1228    start, it skips both the CR and the LF before retrying. However, the pattern
1229    [\er\en]A does match that string, because it contains an explicit CR or LF
1230    reference, and so advances only by one character after the first failure.
1231    Note than an explicit CR or LF reference occurs for negated character classes
1232    such as [^X] because they can match CR or LF characters.
1233    .P
1234    Notwithstanding the above, anomalous effects may still occur when CRLF is a
1235    valid newline sequence and explicit \er or \en escapes appear in the pattern.
1236  .sp  .sp
1237    PCRE_NOTBOL    PCRE_NOTBOL
1238  .sp  .sp
# Line 1218  code that demonstrates how to do this in Line 1275  code that demonstrates how to do this in
1275  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
1276  string is automatically checked when \fBpcre_exec()\fP is subsequently called.  string is automatically checked when \fBpcre_exec()\fP is subsequently called.
1277  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
1278  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
1279  \fBpcre_exec()\fP returns the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP  strings in the
1280  contains an invalid value, PCRE_ERROR_BADUTF8_OFFSET is returned.  .\" HTML <a href="pcre.html#utf8strings">
1281    .\" </a>
1282    section on UTF-8 support
1283    .\"
1284    in the main
1285    .\" HREF
1286    \fBpcre\fP
1287    .\"
1288    page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_exec()\fP returns
1289    the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP contains an invalid value,
1290    PCRE_ERROR_BADUTF8_OFFSET is returned.
1291  .P  .P
1292  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
1293  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 1519  The internal recursion limit, as specifi
1519  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
1520  description above.  description above.
1521  .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  
1522    PCRE_ERROR_BADNEWLINE     (-23)    PCRE_ERROR_BADNEWLINE     (-23)
1523  .sp  .sp
1524  An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.  An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
1525  .P  .P
1526  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.
1527  .  .
1528  .  .
1529  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
# Line 1476  Error numbers -16 to -20 are not used by Line 1535  Error numbers -16 to -20 are not used by
1535  .ti +5n  .ti +5n
1536  .B int \fIbuffersize\fP);  .B int \fIbuffersize\fP);
1537  .PP  .PP
 .br  
1538  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
1539  .ti +5n  .ti +5n
1540  .B int \fIstringcount\fP, int \fIstringnumber\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP,
1541  .ti +5n  .ti +5n
1542  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
1543  .PP  .PP
 .br  
1544  .B int pcre_get_substring_list(const char *\fIsubject\fP,  .B int pcre_get_substring_list(const char *\fIsubject\fP,
1545  .ti +5n  .ti +5n
1546  .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 1626  provided.
1626  .ti +5n  .ti +5n
1627  .B const char *\fIname\fP);  .B const char *\fIname\fP);
1628  .PP  .PP
 .br  
1629  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
1630  .ti +5n  .ti +5n
1631  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1578  provided. Line 1634  provided.
1634  .ti +5n  .ti +5n
1635  .B char *\fIbuffer\fP, int \fIbuffersize\fP);  .B char *\fIbuffer\fP, int \fIbuffersize\fP);
1636  .PP  .PP
 .br  
1637  .B int pcre_get_named_substring(const pcre *\fIcode\fP,  .B int pcre_get_named_substring(const pcre *\fIcode\fP,
1638  .ti +5n  .ti +5n
1639  .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 1669  pattern. This is needed in order to gain
1669  translation table.  translation table.
1670  .P  .P
1671  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they
1672  then call \fIpcre_copy_substring()\fP or \fIpcre_get_substring()\fP, as  then call \fBpcre_copy_substring()\fP or \fBpcre_get_substring()\fP, as
1673  appropriate.  appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names,
1674    the behaviour may not be what you want (see the next section).
1675  .  .
1676  .  .
1677  .SH "DUPLICATE SUBPATTERN NAMES"  .SH "DUPLICATE SUBPATTERN NAMES"
# Line 1632  example is shown in the Line 1688  example is shown in the
1688  .\" HREF  .\" HREF
1689  \fBpcrepattern\fP  \fBpcrepattern\fP
1690  .\"  .\"
1691  documentation. When duplicates are present, \fBpcre_copy_named_substring()\fP  documentation.
1692  and \fBpcre_get_named_substring()\fP return the first substring corresponding  .P
1693  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
1694  The \fBpcre_get_stringnumber()\fP function returns one of the numbers that are  \fBpcre_get_named_substring()\fP return the first substring corresponding to
1695  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
1696  .sp  returned; no data is returned. The \fBpcre_get_stringnumber()\fP function
1697    returns one of the numbers that are associated with the name, but it is not
1698    defined which it is.
1699    .P
1700  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,
1701  you must use the \fBpcre_get_stringtable_entries()\fP function. The first  you must use the \fBpcre_get_stringtable_entries()\fP function. The first
1702  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 1905  extremely rare, as a vector of size 1000
1905  \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),  \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
1906  \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),  \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
1907  \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).  \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
1908  .P  .
1909  .in 0  .
1910  Last updated: 30 November 2006  .SH AUTHOR
1911  .br  .rs
1912  Copyright (c) 1997-2006 University of Cambridge.  .sp
1913    .nf
1914    Philip Hazel
1915    University Computing Service
1916    Cambridge CB2 3QH, England.
1917    .fi
1918    .
1919    .
1920    .SH REVISION
1921    .rs
1922    .sp
1923    .nf
1924    Last updated: 21 August 2007
1925    Copyright (c) 1997-2007 University of Cambridge.
1926    .fi

Legend:
Removed from v.96  
changed lines
  Added in v.227

  ViewVC Help
Powered by ViewVC 1.1.5