/[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 209 by ph10, Tue Aug 7 09:22:06 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 246  documentation. Line 221  documentation.
221  .SH NEWLINES  .SH NEWLINES
222  .rs  .rs
223  .sp  .sp
224  PCRE supports four different conventions for indicating line breaks in  PCRE supports five different conventions for indicating line breaks in
225  strings: a single CR (carriage return) character, a single LF (linefeed)  strings: a single CR (carriage return) character, a single LF (linefeed)
226  character, the two-character sequence CRLF, or any Unicode newline sequence.  character, the two-character sequence CRLF, any of the three preceding, or any
227  The Unicode newline sequences are the three just mentioned, plus the single  Unicode newline sequence. The Unicode newline sequences are the three just
228  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,
229  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
230    (paragraph separator, U+2029).
231  .P  .P
232  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
233  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 289  which it was compiled. Details are given Line 265  which it was compiled. Details are given
265  .\" HREF  .\" HREF
266  \fBpcreprecompile\fP  \fBpcreprecompile\fP
267  .\"  .\"
268  documentation.  documentation. However, compiling a regular expression with one version of PCRE
269    for use with a different version is not guaranteed to work and may cause
270    crashes.
271  .  .
272  .  .
273  .SH "CHECKING BUILD-TIME OPTIONS"  .SH "CHECKING BUILD-TIME OPTIONS"
# Line 322  properties is available; otherwise it is Line 300  properties is available; otherwise it is
300  .sp  .sp
301  The output is an integer whose value specifies the default character sequence  The output is an integer whose value specifies the default character sequence
302  that is recognized as meaning "newline". The four values that are supported  that is recognized as meaning "newline". The four values that are supported
303  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
304  normally be the standard sequence for your operating system.  default should normally be the standard sequence for your operating system.
305  .sp  .sp
306    PCRE_CONFIG_LINK_SIZE    PCRE_CONFIG_LINK_SIZE
307  .sp  .sp
# Line 557  occurrences of ^ or $ in a pattern, sett Line 535  occurrences of ^ or $ in a pattern, sett
535    PCRE_NEWLINE_CR    PCRE_NEWLINE_CR
536    PCRE_NEWLINE_LF    PCRE_NEWLINE_LF
537    PCRE_NEWLINE_CRLF    PCRE_NEWLINE_CRLF
538      PCRE_NEWLINE_ANYCRLF
539    PCRE_NEWLINE_ANY    PCRE_NEWLINE_ANY
540  .sp  .sp
541  These options override the default newline definition that was chosen when PCRE  These options override the default newline definition that was chosen when PCRE
542  was built. Setting the first or the second specifies that a newline is  was built. Setting the first or the second specifies that a newline is
543  indicated by a single character (CR or LF, respectively). Setting  indicated by a single character (CR or LF, respectively). Setting
544  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
545  CRLF sequence. Setting PCRE_NEWLINE_ANY specifies that any Unicode newline  CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three
546  sequence should be recognized. The Unicode newline sequences are the three just  preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies
547  mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,  that any Unicode newline sequence should be recognized. The Unicode newline
548  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
549  (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
550    separator, U+2028), and PS (paragraph separator, U+2029). The last two are
551    recognized only in UTF-8 mode.
552  .P  .P
553  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
554  as a number, giving eight possibilities. Currently only five are used (default  as a number, giving eight possibilities. Currently only six are used (default
555  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
556  option, the combination may or may not be sensible. For example,  option, the combination may or may not be sensible. For example,
557  PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but  PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but
558  other combinations yield unused numbers and cause an error.  other combinations may yield unused numbers and cause an error.
559  .P  .P
560  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
561  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 601  page.
601    PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
602  .sp  .sp
603  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
604  automatically checked. If an invalid UTF-8 sequence of bytes is found,  automatically checked. Note that the check is for a syntactically valid UTF-8
605  \fBpcre_compile()\fP returns an error. If you already know that your pattern is  byte string, as defined by RFC 2279. It is \fInot\fP a check for a UTF-8 string
606  valid, and you want to skip this check for performance reasons, you can set the  of assigned or allowable Unicode code points.
607  PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid  .P
608  UTF-8 string as a pattern is undefined. It may cause your program to crash.  If an invalid UTF-8 sequence of bytes is found, \fBpcre_compile()\fP returns an
609  Note that this option can also be passed to \fBpcre_exec()\fP and  error. If you already know that your pattern is valid, and you want to skip
610  \fBpcre_dfa_exec()\fP, to suppress the UTF-8 validity checking of subject  this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK option.
611  strings.  When it is set, the effect of passing an invalid UTF-8 string as a pattern is
612    undefined. It may cause your program to crash. Note that this option can also
613    be passed to \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, to suppress the UTF-8
614    validity checking of subject strings.
615  .  .
616  .  .
617  .SH "COMPILATION ERROR CODES"  .SH "COMPILATION ERROR CODES"
# Line 667  out of use. To avoid confusion, they hav Line 651  out of use. To avoid confusion, they hav
651    26  malformed number or name after (?(    26  malformed number or name after (?(
652    27  conditional group contains more than two branches    27  conditional group contains more than two branches
653    28  assertion expected after (?(    28  assertion expected after (?(
654    29  (?R or (?digits must be followed by )    29  (?R or (?[+-]digits must be followed by )
655    30  unknown POSIX class name    30  unknown POSIX class name
656    31  POSIX collating elements are not supported    31  POSIX collating elements are not supported
657    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 672  out of use. To avoid confusion, they hav
672    47  unknown property name after \eP or \ep    47  unknown property name after \eP or \ep
673    48  subpattern name is too long (maximum 32 characters)    48  subpattern name is too long (maximum 32 characters)
674    49  too many named subpatterns (maximum 10,000)    49  too many named subpatterns (maximum 10,000)
675    50  repeated subpattern is too long    50  [this code is not in use]
676    51  octal value is greater than \e377 (not in UTF-8 mode)    51  octal value is greater than \e377 (not in UTF-8 mode)
677    52  internal error: overran compiling workspace    52  internal error: overran compiling workspace
678    53  internal error: previously-checked referenced subpattern not found    53  internal error: previously-checked referenced subpattern not found
679    54  DEFINE group contains more than one branch    54  DEFINE group contains more than one branch
680    55  repeating a DEFINE group is not allowed    55  repeating a DEFINE group is not allowed
681    56  inconsistent NEWLINE options"    56  inconsistent NEWLINE options"
682      57  \eg is not followed by a braced name or an optionally braced
683            non-zero number
684      58  (?+ or (?- or (?(+ or (?(- must be followed by a non-zero number
685  .  .
686  .  .
687  .SH "STUDYING A PATTERN"  .SH "STUDYING A PATTERN"
# Line 754  bytes is created. Line 741  bytes is created.
741  .SH "LOCALE SUPPORT"  .SH "LOCALE SUPPORT"
742  .rs  .rs
743  .sp  .sp
744  PCRE handles caseless matching, and determines whether characters are letters  PCRE handles caseless matching, and determines whether characters are letters,
745  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
746  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
747  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
748  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
749  support. The use of locales with Unicode is discouraged.  support. The use of locales with Unicode is discouraged. If you are handling
750  .P  characters with codes greater than 128, you should either use UTF-8 and
751  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.
752  built. This is used when the final argument of \fBpcre_compile()\fP is NULL,  .P
753  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
754  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.
755  default. As more and more applications change to using Unicode, the need for  Normally, the internal tables recognize only ASCII characters. However, when
756  this locale support is expected to die away.  PCRE is built, it is possible to cause the internal tables to be rebuilt in the
757    default "C" locale of the local system, which may cause them to be different.
758    .P
759    The internal tables can always be overridden by tables supplied by the
760    application that calls PCRE. These may be created in a different locale from
761    the default. As more and more applications change to using Unicode, the need
762    for this locale support is expected to die away.
763  .P  .P
764  External tables are built by calling the \fBpcre_maketables()\fP function,  External tables are built by calling the \fBpcre_maketables()\fP function,
765  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 772  the following code could be used:
772    tables = pcre_maketables();    tables = pcre_maketables();
773    re = pcre_compile(..., tables);    re = pcre_compile(..., tables);
774  .sp  .sp
775    The locale name "fr_FR" is used on Linux and other Unix-like systems; if you
776    are using Windows, the name for the French locale is "french".
777    .P
778  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
779  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
780  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 877  table indicating a fixed set of bytes fo
877  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
878  fourth argument should point to an \fBunsigned char *\fP variable.  fourth argument should point to an \fBunsigned char *\fP variable.
879  .sp  .sp
880      PCRE_INFO_JCHANGED
881    .sp
882    Return 1 if the (?J) option setting is used in the pattern, otherwise 0. The
883    fourth argument should point to an \fBint\fP variable. The (?J) internal option
884    setting changes the local PCRE_DUPNAMES option.
885    .sp
886    PCRE_INFO_LASTLITERAL    PCRE_INFO_LASTLITERAL
887  .sp  .sp
888  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 935  When writing code to extract data from n
935  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
936  different for each compiled pattern.  different for each compiled pattern.
937  .sp  .sp
938      PCRE_INFO_OKPARTIAL
939    .sp
940    Return 1 if the pattern can be used for partial matching, otherwise 0. The
941    fourth argument should point to an \fBint\fP variable. The
942    .\" HREF
943    \fBpcrepartial\fP
944    .\"
945    documentation lists the restrictions that apply to patterns when partial
946    matching is used.
947    .sp
948    PCRE_INFO_OPTIONS    PCRE_INFO_OPTIONS
949  .sp  .sp
950  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
951  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
952  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
953  top-level option settings within the pattern itself.  top-level option settings at the start of the pattern itself. In other words,
954    they are the options that will be in force when matching starts. For example,
955    if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the
956    result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED.
957  .P  .P
958  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
959  alternatives begin with one of the following:  alternatives begin with one of the following:
# Line 1166  matching time. Line 1181  matching time.
1181    PCRE_NEWLINE_CR    PCRE_NEWLINE_CR
1182    PCRE_NEWLINE_LF    PCRE_NEWLINE_LF
1183    PCRE_NEWLINE_CRLF    PCRE_NEWLINE_CRLF
1184      PCRE_NEWLINE_ANYCRLF
1185    PCRE_NEWLINE_ANY    PCRE_NEWLINE_ANY
1186  .sp  .sp
1187  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 1189  the pattern was compiled. For details, s
1189  \fBpcre_compile()\fP above. During matching, the newline choice affects the  \fBpcre_compile()\fP above. During matching, the newline choice affects the
1190  behaviour of the dot, circumflex, and dollar metacharacters. It may also alter  behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
1191  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
1192  pattern. When PCRE_NEWLINE_CRLF or PCRE_NEWLINE_ANY is set, and a match attempt  pattern. When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is
1193  fails when the current position is at a CRLF sequence, the match position is  set, and a match attempt fails when the current position is at a CRLF sequence,
1194  advanced by two characters instead of one, in other words, to after the CRLF.  the match position is advanced by two characters instead of one, in other
1195    words, to after the CRLF.
1196  .sp  .sp
1197    PCRE_NOTBOL    PCRE_NOTBOL
1198  .sp  .sp
# Line 1217  code that demonstrates how to do this in Line 1234  code that demonstrates how to do this in
1234  .sp  .sp
1235  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
1236  string is automatically checked when \fBpcre_exec()\fP is subsequently called.  string is automatically checked when \fBpcre_exec()\fP is subsequently called.
1237  The value of \fIstartoffset\fP is also checked to ensure that it points to the  Note that the check is for a syntactically valid UTF-8 byte string, as defined
1238  start of a UTF-8 character. If an invalid UTF-8 sequence of bytes is found,  by RFC 2279. It is \fInot\fP a check for a UTF-8 string of assigned or
1239  \fBpcre_exec()\fP returns the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP  allowable Unicode code points. The value of \fIstartoffset\fP is also checked
1240  contains an invalid value, PCRE_ERROR_BADUTF8_OFFSET is returned.  to ensure that it points to the start of a UTF-8 character. If an invalid UTF-8
1241    sequence of bytes is found, \fBpcre_exec()\fP returns the error
1242    PCRE_ERROR_BADUTF8. If \fIstartoffset\fP contains an invalid value,
1243    PCRE_ERROR_BADUTF8_OFFSET is returned.
1244  .P  .P
1245  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
1246  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 1472  The internal recursion limit, as specifi
1472  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
1473  description above.  description above.
1474  .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  
1475    PCRE_ERROR_BADNEWLINE     (-23)    PCRE_ERROR_BADNEWLINE     (-23)
1476  .sp  .sp
1477  An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.  An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
1478  .P  .P
1479  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.
1480  .  .
1481  .  .
1482  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
# Line 1476  Error numbers -16 to -20 are not used by Line 1488  Error numbers -16 to -20 are not used by
1488  .ti +5n  .ti +5n
1489  .B int \fIbuffersize\fP);  .B int \fIbuffersize\fP);
1490  .PP  .PP
 .br  
1491  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
1492  .ti +5n  .ti +5n
1493  .B int \fIstringcount\fP, int \fIstringnumber\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP,
1494  .ti +5n  .ti +5n
1495  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
1496  .PP  .PP
 .br  
1497  .B int pcre_get_substring_list(const char *\fIsubject\fP,  .B int pcre_get_substring_list(const char *\fIsubject\fP,
1498  .ti +5n  .ti +5n
1499  .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 1579  provided.
1579  .ti +5n  .ti +5n
1580  .B const char *\fIname\fP);  .B const char *\fIname\fP);
1581  .PP  .PP
 .br  
1582  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
1583  .ti +5n  .ti +5n
1584  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1578  provided. Line 1587  provided.
1587  .ti +5n  .ti +5n
1588  .B char *\fIbuffer\fP, int \fIbuffersize\fP);  .B char *\fIbuffer\fP, int \fIbuffersize\fP);
1589  .PP  .PP
 .br  
1590  .B int pcre_get_named_substring(const pcre *\fIcode\fP,  .B int pcre_get_named_substring(const pcre *\fIcode\fP,
1591  .ti +5n  .ti +5n
1592  .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 1622  pattern. This is needed in order to gain
1622  translation table.  translation table.
1623  .P  .P
1624  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they
1625  then call \fIpcre_copy_substring()\fP or \fIpcre_get_substring()\fP, as  then call \fBpcre_copy_substring()\fP or \fBpcre_get_substring()\fP, as
1626  appropriate.  appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names,
1627    the behaviour may not be what you want (see the next section).
1628  .  .
1629  .  .
1630  .SH "DUPLICATE SUBPATTERN NAMES"  .SH "DUPLICATE SUBPATTERN NAMES"
# Line 1632  example is shown in the Line 1641  example is shown in the
1641  .\" HREF  .\" HREF
1642  \fBpcrepattern\fP  \fBpcrepattern\fP
1643  .\"  .\"
1644  documentation. When duplicates are present, \fBpcre_copy_named_substring()\fP  documentation.
1645  and \fBpcre_get_named_substring()\fP return the first substring corresponding  .P
1646  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
1647  The \fBpcre_get_stringnumber()\fP function returns one of the numbers that are  \fBpcre_get_named_substring()\fP return the first substring corresponding to
1648  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
1649  .sp  returned; no data is returned. The \fBpcre_get_stringnumber()\fP function
1650    returns one of the numbers that are associated with the name, but it is not
1651    defined which it is.
1652    .P
1653  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,
1654  you must use the \fBpcre_get_stringtable_entries()\fP function. The first  you must use the \fBpcre_get_stringtable_entries()\fP function. The first
1655  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 1858  extremely rare, as a vector of size 1000
1858  \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),  \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
1859  \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),  \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
1860  \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).  \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
1861  .P  .
1862  .in 0  .
1863  Last updated: 30 November 2006  .SH AUTHOR
1864  .br  .rs
1865  Copyright (c) 1997-2006 University of Cambridge.  .sp
1866    .nf
1867    Philip Hazel
1868    University Computing Service
1869    Cambridge CB2 3QH, England.
1870    .fi
1871    .
1872    .
1873    .SH REVISION
1874    .rs
1875    .sp
1876    .nf
1877    Last updated: 07 August 2007
1878    Copyright (c) 1997-2007 University of Cambridge.
1879    .fi

Legend:
Removed from v.96  
changed lines
  Added in v.209

  ViewVC Help
Powered by ViewVC 1.1.5