/[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 461 by ph10, Mon Oct 5 10:59:35 2009 UTC revision 859 by ph10, Mon Jan 9 17:43:54 2012 UTC
# Line 1  Line 1 
1  .TH PCREAPI 3  .TH PCREAPI 3
2  .SH NAME  .SH NAME
3  PCRE - Perl-compatible regular expressions  PCRE - Perl-compatible regular expressions
 .SH "PCRE NATIVE API"  
 .rs  
4  .sp  .sp
5  .B #include <pcre.h>  .B #include <pcre.h>
6  .PP  .
7    .
8    .SH "PCRE NATIVE API BASIC FUNCTIONS"
9    .rs
10    .sp
11  .SM  .SM
12  .B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP,  .B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP,
13  .ti +5n  .ti +5n
# Line 25  PCRE - Perl-compatible regular expressio Line 27  PCRE - Perl-compatible regular expressio
27  .ti +5n  .ti +5n
28  .B const char **\fIerrptr\fP);  .B const char **\fIerrptr\fP);
29  .PP  .PP
30    .B void pcre_free_study(pcre_extra *\fIextra\fP);
31    .PP
32  .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,"
33  .ti +5n  .ti +5n
34  .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,  .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
# Line 38  PCRE - Perl-compatible regular expressio Line 42  PCRE - Perl-compatible regular expressio
42  .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP,  .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP,
43  .ti +5n  .ti +5n
44  .B int *\fIworkspace\fP, int \fIwscount\fP);  .B int *\fIworkspace\fP, int \fIwscount\fP);
45  .PP  .
46    .
47    .SH "PCRE NATIVE API STRING EXTRACTION FUNCTIONS"
48    .rs
49    .sp
50  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
51  .ti +5n  .ti +5n
52  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 82  PCRE - Perl-compatible regular expressio Line 90  PCRE - Perl-compatible regular expressio
90  .B void pcre_free_substring(const char *\fIstringptr\fP);  .B void pcre_free_substring(const char *\fIstringptr\fP);
91  .PP  .PP
92  .B void pcre_free_substring_list(const char **\fIstringptr\fP);  .B void pcre_free_substring_list(const char **\fIstringptr\fP);
93    .
94    .
95    .SH "PCRE NATIVE API AUXILIARY FUNCTIONS"
96    .rs
97    .sp
98    .B pcre_jit_stack *pcre_jit_stack_alloc(int \fIstartsize\fP, int \fImaxsize\fP);
99    .PP
100    .B void pcre_jit_stack_free(pcre_jit_stack *\fIstack\fP);
101    .PP
102    .B void pcre_assign_jit_stack(pcre_extra *\fIextra\fP,
103    .ti +5n
104    .B pcre_jit_callback \fIcallback\fP, void *\fIdata\fP);
105  .PP  .PP
106  .B const unsigned char *pcre_maketables(void);  .B const unsigned char *pcre_maketables(void);
107  .PP  .PP
# Line 89  PCRE - Perl-compatible regular expressio Line 109  PCRE - Perl-compatible regular expressio
109  .ti +5n  .ti +5n
110  .B int \fIwhat\fP, void *\fIwhere\fP);  .B int \fIwhat\fP, void *\fIwhere\fP);
111  .PP  .PP
 .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int  
 .B *\fIfirstcharptr\fP);  
 .PP  
112  .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);  .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);
113  .PP  .PP
114  .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);  .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);
115  .PP  .PP
116  .B char *pcre_version(void);  .B const char *pcre_version(void);
117  .PP  .PP
118    .B int pcre_pattern_to_host_byte_order(pcre *\fIcode\fP,
119    .ti +5n
120    .B pcre_extra *\fIextra\fP, const unsigned char *\fItables\fP);
121    .
122    .
123    .SH "PCRE NATIVE API INDIRECTED FUNCTIONS"
124    .rs
125    .sp
126  .B void *(*pcre_malloc)(size_t);  .B void *(*pcre_malloc)(size_t);
127  .PP  .PP
128  .B void (*pcre_free)(void *);  .B void (*pcre_free)(void *);
# Line 109  PCRE - Perl-compatible regular expressio Line 134  PCRE - Perl-compatible regular expressio
134  .B int (*pcre_callout)(pcre_callout_block *);  .B int (*pcre_callout)(pcre_callout_block *);
135  .  .
136  .  .
137    .SH "PCRE 8-BIT AND 16-BIT LIBRARIES"
138    .rs
139    .sp
140    From release 8.30, PCRE can be compiled as a library for handling 16-bit
141    character strings as well as, or instead of, the original library that handles
142    8-bit character strings. To avoid too much complication, this document
143    describes the 8-bit versions of the functions, with only occasional references
144    to the 16-bit library.
145    .P
146    The 16-bit functions operate in the same way as their 8-bit counterparts; they
147    just use different data types for their arguments and results, and their names
148    start with \fBpcre16_\fP instead of \fBpcre_\fP. For every option that has UTF8
149    in its name (for example, PCRE_UTF8), there is a corresponding 16-bit name with
150    UTF8 replaced by UTF16. This facility is in fact just cosmetic; the 16-bit
151    option names define the same bit values.
152    .P
153    References to bytes and UTF-8 in this document should be read as references to
154    16-bit data quantities and UTF-16 when using the 16-bit library, unless
155    specified otherwise. More details of the specific differences for the 16-bit
156    library are given in the
157    .\" HREF
158    \fBpcre16\fP
159    .\"
160    page.
161    .
162    .
163  .SH "PCRE API OVERVIEW"  .SH "PCRE API OVERVIEW"
164  .rs  .rs
165  .sp  .sp
166  PCRE has its own native API, which is described in this document. There are  PCRE has its own native API, which is described in this document. There are
167  also some wrapper functions that correspond to the POSIX regular expression  also some wrapper functions (for the 8-bit library only) that correspond to the
168  API. These are described in the  POSIX regular expression API, but they do not give access to all the
169    functionality. They are described in the
170  .\" HREF  .\" HREF
171  \fBpcreposix\fP  \fBpcreposix\fP
172  .\"  .\"
173  documentation. Both of these APIs define a set of C function calls. A C++  documentation. Both of these APIs define a set of C function calls. A C++
174  wrapper is distributed with PCRE. It is documented in the  wrapper (again for the 8-bit library only) is also distributed with PCRE. It is
175    documented in the
176  .\" HREF  .\" HREF
177  \fBpcrecpp\fP  \fBpcrecpp\fP
178  .\"  .\"
179  page.  page.
180  .P  .P
181  The native API C function prototypes are defined in the header file  The native API C function prototypes are defined in the header file
182  \fBpcre.h\fP, and on Unix systems the library itself is called \fBlibpcre\fP.  \fBpcre.h\fP, and on Unix-like systems the (8-bit) library itself is called
183  It can normally be accessed by adding \fB-lpcre\fP to the command for linking  \fBlibpcre\fP. It can normally be accessed by adding \fB-lpcre\fP to the
184  an application that uses PCRE. The header file defines the macros PCRE_MAJOR  command for linking an application that uses PCRE. The header file defines the
185  and PCRE_MINOR to contain the major and minor release numbers for the library.  macros PCRE_MAJOR and PCRE_MINOR to contain the major and minor release numbers
186  Applications can use these to include support for different releases of PCRE.  for the library. Applications can use these to include support for different
187    releases of PCRE.
188    .P
189    In a Windows environment, if you want to statically link an application program
190    against a non-dll \fBpcre.a\fP file, you must define PCRE_STATIC before
191    including \fBpcre.h\fP or \fBpcrecpp.h\fP, because otherwise the
192    \fBpcre_malloc()\fP and \fBpcre_free()\fP exported functions will be declared
193    \fB__declspec(dllimport)\fP, with unwanted results.
194  .P  .P
195  The functions \fBpcre_compile()\fP, \fBpcre_compile2()\fP, \fBpcre_study()\fP,  The functions \fBpcre_compile()\fP, \fBpcre_compile2()\fP, \fBpcre_study()\fP,
196  and \fBpcre_exec()\fP are used for compiling and matching regular expressions  and \fBpcre_exec()\fP are used for compiling and matching regular expressions
# Line 146  documentation, and the Line 206  documentation, and the
206  .\"  .\"
207  documentation describes how to compile and run it.  documentation describes how to compile and run it.
208  .P  .P
209    Just-in-time compiler support is an optional feature of PCRE that can be built
210    in appropriate hardware environments. It greatly speeds up the matching
211    performance of many patterns. Simple programs can easily request that it be
212    used if available, by setting an option that is ignored when it is not
213    relevant. More complicated programs might need to make use of the functions
214    \fBpcre_jit_stack_alloc()\fP, \fBpcre_jit_stack_free()\fP, and
215    \fBpcre_assign_jit_stack()\fP in order to control the JIT code's memory usage.
216    These functions are discussed in the
217    .\" HREF
218    \fBpcrejit\fP
219    .\"
220    documentation.
221    .P
222  A second matching function, \fBpcre_dfa_exec()\fP, which is not  A second matching function, \fBpcre_dfa_exec()\fP, which is not
223  Perl-compatible, is also provided. This uses a different algorithm for the  Perl-compatible, is also provided. This uses a different algorithm for the
224  matching. The alternative algorithm finds all possible matches (at a given  matching. The alternative algorithm finds all possible matches (at a given
# Line 180  specialist use. Most commonly, no specia Line 253  specialist use. Most commonly, no specia
253  internal tables that are generated when PCRE is built are used.  internal tables that are generated when PCRE is built are used.
254  .P  .P
255  The function \fBpcre_fullinfo()\fP is used to find out information about a  The function \fBpcre_fullinfo()\fP is used to find out information about a
256  compiled pattern; \fBpcre_info()\fP is an obsolete version that returns only  compiled pattern. The function \fBpcre_version()\fP returns a pointer to a
257  some of the available information, but is retained for backwards compatibility.  string containing the version of PCRE and its date of release.
 The function \fBpcre_version()\fP returns a pointer to a string containing the  
 version of PCRE and its date of release.  
258  .P  .P
259  The function \fBpcre_refcount()\fP maintains a reference count in a data block  The function \fBpcre_refcount()\fP maintains a reference count in a data block
260  containing a compiled pattern. This is provided for the benefit of  containing a compiled pattern. This is provided for the benefit of
# Line 276  callout function pointed to by \fBpcre_c Line 347  callout function pointed to by \fBpcre_c
347  .P  .P
348  The compiled form of a regular expression is not altered during matching, so  The compiled form of a regular expression is not altered during matching, so
349  the same compiled pattern can safely be used by several threads at once.  the same compiled pattern can safely be used by several threads at once.
350    .P
351    If the just-in-time optimization feature is being used, it needs separate
352    memory stack areas for each thread. See the
353    .\" HREF
354    \fBpcrejit\fP
355    .\"
356    documentation for more details.
357  .  .
358  .  .
359  .SH "SAVING PRECOMPILED PATTERNS FOR LATER USE"  .SH "SAVING PRECOMPILED PATTERNS FOR LATER USE"
# Line 287  which it was compiled. Details are given Line 365  which it was compiled. Details are given
365  .\" HREF  .\" HREF
366  \fBpcreprecompile\fP  \fBpcreprecompile\fP
367  .\"  .\"
368  documentation. However, compiling a regular expression with one version of PCRE  documentation, which includes a description of the
369  for use with a different version is not guaranteed to work and may cause  \fBpcre_pattern_to_host_byte_order()\fP function. However, compiling a regular
370  crashes.  expression with one version of PCRE for use with a different version is not
371    guaranteed to work and may cause crashes.
372  .  .
373  .  .
374  .SH "CHECKING BUILD-TIME OPTIONS"  .SH "CHECKING BUILD-TIME OPTIONS"
# Line 306  documentation has more details about the Line 385  documentation has more details about the
385  .P  .P
386  The first argument for \fBpcre_config()\fP is an integer, specifying which  The first argument for \fBpcre_config()\fP is an integer, specifying which
387  information is required; the second argument is a pointer to a variable into  information is required; the second argument is a pointer to a variable into
388  which the information is placed. The following information is available:  which the information is placed. The returned value is zero on success, or the
389    negative error code PCRE_ERROR_BADOPTION if the value in the first argument is
390    not recognized. The following information is available:
391  .sp  .sp
392    PCRE_CONFIG_UTF8    PCRE_CONFIG_UTF8
393  .sp  .sp
394  The output is an integer that is set to one if UTF-8 support is available;  The output is an integer that is set to one if UTF-8 support is available;
395  otherwise it is set to zero.  otherwise it is set to zero. If this option is given to the 16-bit version of
396    this function, \fBpcre16_config()\fP, the result is PCRE_ERROR_BADOPTION.
397    .sp
398      PCRE_CONFIG_UTF16
399    .sp
400    The output is an integer that is set to one if UTF-16 support is available;
401    otherwise it is set to zero. This value should normally be given to the 16-bit
402    version of this function, \fBpcre16_config()\fP. If it is given to the 8-bit
403    version of this function, the result is PCRE_ERROR_BADOPTION.
404  .sp  .sp
405    PCRE_CONFIG_UNICODE_PROPERTIES    PCRE_CONFIG_UNICODE_PROPERTIES
406  .sp  .sp
407  The output is an integer that is set to one if support for Unicode character  The output is an integer that is set to one if support for Unicode character
408  properties is available; otherwise it is set to zero.  properties is available; otherwise it is set to zero.
409  .sp  .sp
410      PCRE_CONFIG_JIT
411    .sp
412    The output is an integer that is set to one if support for just-in-time
413    compiling is available; otherwise it is set to zero.
414    .sp
415    PCRE_CONFIG_NEWLINE    PCRE_CONFIG_NEWLINE
416  .sp  .sp
417  The output is an integer whose value specifies the default character sequence  The output is an integer whose value specifies the default character sequence
# Line 337  or CRLF. The default can be overridden w Line 431  or CRLF. The default can be overridden w
431    PCRE_CONFIG_LINK_SIZE    PCRE_CONFIG_LINK_SIZE
432  .sp  .sp
433  The output is an integer that contains the number of bytes used for internal  The output is an integer that contains the number of bytes used for internal
434  linkage in compiled regular expressions. The value is 2, 3, or 4. Larger values  linkage in compiled regular expressions. For the 8-bit library, the value can
435  allow larger regular expressions to be compiled, at the expense of slower  be 2, 3, or 4. For the 16-bit library, the value is either 2 or 4 and is still
436  matching. The default value of 2 is sufficient for all but the most massive  a number of bytes. The default value of 2 is sufficient for all but the most
437  patterns, since it allows the compiled pattern to be up to 64K in size.  massive patterns, since it allows the compiled pattern to be up to 64K in size.
438    Larger values allow larger regular expressions to be compiled, at the expense
439    of slower matching.
440  .sp  .sp
441    PCRE_CONFIG_POSIX_MALLOC_THRESHOLD    PCRE_CONFIG_POSIX_MALLOC_THRESHOLD
442  .sp  .sp
# Line 422  within the pattern (see the detailed des Line 518  within the pattern (see the detailed des
518  documentation). For those options that can be different in different parts of  documentation). For those options that can be different in different parts of
519  the pattern, the contents of the \fIoptions\fP argument specifies their  the pattern, the contents of the \fIoptions\fP argument specifies their
520  settings at the start of compilation and execution. The PCRE_ANCHORED,  settings at the start of compilation and execution. The PCRE_ANCHORED,
521  PCRE_BSR_\fIxxx\fP, and PCRE_NEWLINE_\fIxxx\fP options can be set at the time  PCRE_BSR_\fIxxx\fP, PCRE_NEWLINE_\fIxxx\fP, PCRE_NO_UTF8_CHECK, and
522  of matching as well as at compile time.  PCRE_NO_START_OPT options can be set at the time of matching as well as at
523    compile time.
524  .P  .P
525  If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.  If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.
526  Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns  Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns
527  NULL, and sets the variable pointed to by \fIerrptr\fP to point to a textual  NULL, and sets the variable pointed to by \fIerrptr\fP to point to a textual
528  error message. This is a static string that is part of the library. You must  error message. This is a static string that is part of the library. You must
529  not try to free it. The byte offset from the start of the pattern to the  not try to free it. Normally, the offset from the start of the pattern to the
530  character that was being processed when the error was discovered is placed in  byte that was being processed when the error was discovered is placed in the
531  the variable pointed to by \fIerroffset\fP, which must not be NULL. If it is,  variable pointed to by \fIerroffset\fP, which must not be NULL (if it is, an
532  an immediate error is given. Some errors are not detected until checks are  immediate error is given). However, for an invalid UTF-8 string, the offset is
533  carried out when the whole pattern has been scanned; in this case the offset is  that of the first byte of the failing character.
534  set to the end of the pattern.  .P
535    Some errors are not detected until the whole pattern has been scanned; in these
536    cases, the offset passed back is the length of the pattern. Note that the
537    offset is in bytes, not characters, even in UTF-8 mode. It may sometimes point
538    into the middle of a UTF-8 character.
539  .P  .P
540  If \fBpcre_compile2()\fP is used instead of \fBpcre_compile()\fP, and the  If \fBpcre_compile2()\fP is used instead of \fBpcre_compile()\fP, and the
541  \fIerrorcodeptr\fP argument is not NULL, a non-zero error code number is  \fIerrorcodeptr\fP argument is not NULL, a non-zero error code number is
# Line 513  pattern. Line 614  pattern.
614  .sp  .sp
615    PCRE_DOTALL    PCRE_DOTALL
616  .sp  .sp
617  If this bit is set, a dot metacharater in the pattern matches all characters,  If this bit is set, a dot metacharacter in the pattern matches a character of
618  including those that indicate newline. Without it, a dot does not match when  any value, including one that indicates a newline. However, it only ever
619  the current position is at a newline. This option is equivalent to Perl's /s  matches one character, even if newlines are coded as CRLF. Without this option,
620  option, and it can be changed within a pattern by a (?s) option setting. A  a dot does not match when the current position is at a newline. This option is
621  negative class such as [^a] always matches newline characters, independent of  equivalent to Perl's /s option, and it can be changed within a pattern by a
622  the setting of this option.  (?s) option setting. A negative class such as [^a] always matches newline
623    characters, independent of the setting of this option.
624  .sp  .sp
625    PCRE_DUPNAMES    PCRE_DUPNAMES
626  .sp  .sp
# Line 540  unescaped # outside a character class an Line 642  unescaped # outside a character class an
642  ignored. This is equivalent to Perl's /x option, and it can be changed within a  ignored. This is equivalent to Perl's /x option, and it can be changed within a
643  pattern by a (?x) option setting.  pattern by a (?x) option setting.
644  .P  .P
645    Which characters are interpreted as newlines is controlled by the options
646    passed to \fBpcre_compile()\fP or by a special sequence at the start of the
647    pattern, as described in the section entitled
648    .\" HTML <a href="pcrepattern.html#newlines">
649    .\" </a>
650    "Newline conventions"
651    .\"
652    in the \fBpcrepattern\fP documentation. Note that the end of this type of
653    comment is a literal newline sequence in the pattern; escape sequences that
654    happen to represent a newline do not count.
655    .P
656  This option makes it possible to include comments inside complicated patterns.  This option makes it possible to include comments inside complicated patterns.
657  Note, however, that this applies only to data characters. Whitespace characters  Note, however, that this applies only to data characters. Whitespace characters
658  may never appear within special character sequences in a pattern, for example  may never appear within special character sequences in a pattern, for example
659  within the sequence (?( which introduces a conditional subpattern.  within the sequence (?( that introduces a conditional subpattern.
660  .sp  .sp
661    PCRE_EXTRA    PCRE_EXTRA
662  .sp  .sp
# Line 553  set, any backslash in a pattern that is Line 666  set, any backslash in a pattern that is
666  special meaning causes an error, thus reserving these combinations for future  special meaning causes an error, thus reserving these combinations for future
667  expansion. By default, as in Perl, a backslash followed by a letter with no  expansion. By default, as in Perl, a backslash followed by a letter with no
668  special meaning is treated as a literal. (Perl can, however, be persuaded to  special meaning is treated as a literal. (Perl can, however, be persuaded to
669  give a warning for this.) There are at present no other features controlled by  give an error for this, by running it with the -w option.) There are at present
670  this option. It can also be set by a (?X) option setting within a pattern.  no other features controlled by this option. It can also be set by a (?X)
671    option setting within a pattern.
672  .sp  .sp
673    PCRE_FIRSTLINE    PCRE_FIRSTLINE
674  .sp  .sp
# Line 575  character). Thus, the pattern AB]CD beco Line 689  character). Thus, the pattern AB]CD beco
689  string (by default this causes the current matching alternative to fail). A  string (by default this causes the current matching alternative to fail). A
690  pattern such as (\e1)(a) succeeds when this option is set (assuming it can find  pattern such as (\e1)(a) succeeds when this option is set (assuming it can find
691  an "a" in the subject), whereas it fails by default, for Perl compatibility.  an "a" in the subject), whereas it fails by default, for Perl compatibility.
692    .P
693    (3) \eU matches an upper case "U" character; by default \eU causes a compile
694    time error (Perl uses \eU to upper case subsequent characters).
695    .P
696    (4) \eu matches a lower case "u" character unless it is followed by four
697    hexadecimal digits, in which case the hexadecimal number defines the code point
698    to match. By default, \eu causes a compile time error (Perl uses it to upper
699    case the following character).
700    .P
701    (5) \ex matches a lower case "x" character unless it is followed by two
702    hexadecimal digits, in which case the hexadecimal number defines the code point
703    to match. By default, as in Perl, a hexadecimal number is always expected after
704    \ex, but it may have zero, one, or two digits (so, for example, \exz matches a
705    binary zero character followed by z).
706  .sp  .sp
707    PCRE_MULTILINE    PCRE_MULTILINE
708  .sp  .sp
# Line 607  preceding sequences should be recognized Line 735  preceding sequences should be recognized
735  that any Unicode newline sequence should be recognized. The Unicode newline  that any Unicode newline sequence should be recognized. The Unicode newline
736  sequences are the three just mentioned, plus the single characters VT (vertical  sequences are the three just mentioned, plus the single characters VT (vertical
737  tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line  tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line
738  separator, U+2028), and PS (paragraph separator, U+2029). The last two are  separator, U+2028), and PS (paragraph separator, U+2029). For the 8-bit
739  recognized only in UTF-8 mode.  library, the last two are recognized only in UTF-8 mode.
740  .P  .P
741  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
742  as a number, giving eight possibilities. Currently only six are used (default  as a number, giving eight possibilities. Currently only six are used (default
# Line 617  option, the combination may or may not b Line 745  option, the combination may or may not b
745  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
746  other combinations may yield unused numbers and cause an error.  other combinations may yield unused numbers and cause an error.
747  .P  .P
748  The only time that a line break is specially recognized when compiling a  The only time that a line break in a pattern is specially recognized when
749  pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character  compiling is when PCRE_EXTENDED is set. CR and LF are whitespace characters,
750  class is encountered. This indicates a comment that lasts until after the next  and so are ignored in this mode. Also, an unescaped # outside a character class
751  line break sequence. In other circumstances, line break sequences are treated  indicates a comment that lasts until after the next line break sequence. In
752  as literal data, except that in PCRE_EXTENDED mode, both CR and LF are treated  other circumstances, line break sequences in patterns are treated as literal
753  as whitespace characters and are therefore ignored.  data.
754  .P  .P
755  The newline option that is set at compile time becomes the default that is used  The newline option that is set at compile time becomes the default that is used
756  for \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, but it can be overridden.  for \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, but it can be overridden.
# Line 635  were followed by ?: but named parenthese Line 763  were followed by ?: but named parenthese
763  they acquire numbers in the usual way). There is no equivalent of this option  they acquire numbers in the usual way). There is no equivalent of this option
764  in Perl.  in Perl.
765  .sp  .sp
766      NO_START_OPTIMIZE
767    .sp
768    This is an option that acts at matching time; that is, it is really an option
769    for \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP. If it is set at compile time,
770    it is remembered with the compiled pattern and assumed at matching time. For
771    details see the discussion of PCRE_NO_START_OPTIMIZE
772    .\" HTML <a href="#execoptions">
773    .\" </a>
774    below.
775    .\"
776    .sp
777      PCRE_UCP
778    .sp
779    This option changes the way PCRE processes \eB, \eb, \eD, \ed, \eS, \es, \eW,
780    \ew, and some of the POSIX character classes. By default, only ASCII characters
781    are recognized, but if PCRE_UCP is set, Unicode properties are used instead to
782    classify characters. More details are given in the section on
783    .\" HTML <a href="pcre.html#genericchartypes">
784    .\" </a>
785    generic character types
786    .\"
787    in the
788    .\" HREF
789    \fBpcrepattern\fP
790    .\"
791    page. If you set PCRE_UCP, matching one of the items it affects takes much
792    longer. The option is available only if PCRE has been compiled with Unicode
793    property support.
794    .sp
795    PCRE_UNGREEDY    PCRE_UNGREEDY
796  .sp  .sp
797  This option inverts the "greediness" of the quantifiers so that they are not  This option inverts the "greediness" of the quantifiers so that they are not
# Line 644  with Perl. It can also be set by a (?U) Line 801  with Perl. It can also be set by a (?U)
801    PCRE_UTF8    PCRE_UTF8
802  .sp  .sp
803  This option causes PCRE to regard both the pattern and the subject as strings  This option causes PCRE to regard both the pattern and the subject as strings
804  of UTF-8 characters instead of single-byte character strings. However, it is  of UTF-8 characters instead of single-byte strings. However, it is available
805  available only when PCRE is built to include UTF-8 support. If not, the use  only when PCRE is built to include UTF support. If not, the use of this option
806  of this option provokes an error. Details of how this option changes the  provokes an error. Details of how this option changes the behaviour of PCRE are
807  behaviour of PCRE are given in the  given in the
 .\" HTML <a href="pcre.html#utf8support">  
 .\" </a>  
 section on UTF-8 support  
 .\"  
 in the main  
808  .\" HREF  .\" HREF
809  \fBpcre\fP  \fBpcreunicode\fP
810  .\"  .\"
811  page.  page.
812  .sp  .sp
813    PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
814  .sp  .sp
815  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
816  automatically checked. There is a discussion about the  string is automatically checked. There is a discussion about the
817  .\" HTML <a href="pcre.html#utf8strings">  .\" HTML <a href="pcreunicode.html#utf8strings">
818  .\" </a>  .\" </a>
819  validity of UTF-8 strings  validity of UTF-8 strings
820  .\"  .\"
821  in the main  in the
822  .\" HREF  .\" HREF
823  \fBpcre\fP  \fBpcreunicode\fP
824  .\"  .\"
825  page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_compile()\fP  page. If an invalid UTF-8 sequence is found, \fBpcre_compile()\fP returns an
826  returns an error. If you already know that your pattern is valid, and you want  error. If you already know that your pattern is valid, and you want to skip
827  to skip this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK  this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK option.
828  option. When it is set, the effect of passing an invalid UTF-8 string as a  When it is set, the effect of passing an invalid UTF-8 string as a pattern is
829  pattern is undefined. It may cause your program to crash. Note that this option  undefined. It may cause your program to crash. Note that this option can also
830  can also be passed to \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, to suppress  be passed to \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, to suppress the
831  the UTF-8 validity checking of subject strings.  validity checking of subject strings.
832  .  .
833  .  .
834  .SH "COMPILATION ERROR CODES"  .SH "COMPILATION ERROR CODES"
# Line 684  the UTF-8 validity checking of subject s Line 836  the UTF-8 validity checking of subject s
836  .sp  .sp
837  The following table lists the error codes than may be returned by  The following table lists the error codes than may be returned by
838  \fBpcre_compile2()\fP, along with the error messages that may be returned by  \fBpcre_compile2()\fP, along with the error messages that may be returned by
839  both compiling functions. As PCRE has developed, some error codes have fallen  both compiling functions. Note that error messages are always 8-bit ASCII
840  out of use. To avoid confusion, they have not been re-used.  strings, even in 16-bit mode. As PCRE has developed, some error codes have
841    fallen out of use. To avoid confusion, they have not been re-used.
842  .sp  .sp
843     0  no error     0  no error
844     1  \e at end of pattern     1  \e at end of pattern
# Line 719  out of use. To avoid confusion, they hav Line 872  out of use. To avoid confusion, they hav
872    29  (?R or (?[+-]digits must be followed by )    29  (?R or (?[+-]digits must be followed by )
873    30  unknown POSIX class name    30  unknown POSIX class name
874    31  POSIX collating elements are not supported    31  POSIX collating elements are not supported
875    32  this version of PCRE is not compiled with PCRE_UTF8 support    32  this version of PCRE is compiled without UTF support
876    33  [this code is not in use]    33  [this code is not in use]
877    34  character value in \ex{...} sequence is too large    34  character value in \ex{...} sequence is too large
878    35  invalid condition (?(0)    35  invalid condition (?(0)
879    36  \eC not allowed in lookbehind assertion    36  \eC not allowed in lookbehind assertion
880    37  PCRE does not support \eL, \el, \eN, \eU, or \eu    37  PCRE does not support \eL, \el, \eN{name}, \eU, or \eu
881    38  number after (?C is > 255    38  number after (?C is > 255
882    39  closing ) for (?C expected    39  closing ) for (?C expected
883    40  recursive call could loop indefinitely    40  recursive call could loop indefinitely
884    41  unrecognized character after (?P    41  unrecognized character after (?P
885    42  syntax error in subpattern name (missing terminator)    42  syntax error in subpattern name (missing terminator)
886    43  two named subpatterns have the same name    43  two named subpatterns have the same name
887    44  invalid UTF-8 string    44  invalid UTF-8 string (specifically UTF-8)
888    45  support for \eP, \ep, and \eX has not been compiled    45  support for \eP, \ep, and \eX has not been compiled
889    46  malformed \eP or \ep sequence    46  malformed \eP or \ep sequence
890    47  unknown property name after \eP or \ep    47  unknown property name after \eP or \ep
891    48  subpattern name is too long (maximum 32 characters)    48  subpattern name is too long (maximum 32 characters)
892    49  too many named subpatterns (maximum 10000)    49  too many named subpatterns (maximum 10000)
893    50  [this code is not in use]    50  [this code is not in use]
894    51  octal value is greater than \e377 (not in UTF-8 mode)    51  octal value is greater than \e377 in 8-bit non-UTF-8 mode
895    52  internal error: overran compiling workspace    52  internal error: overran compiling workspace
896    53  internal error: previously-checked referenced subpattern not found    53  internal error: previously-checked referenced subpattern
897            not found
898    54  DEFINE group contains more than one branch    54  DEFINE group contains more than one branch
899    55  repeating a DEFINE group is not allowed    55  repeating a DEFINE group is not allowed
900    56  inconsistent NEWLINE options    56  inconsistent NEWLINE options
901    57  \eg is not followed by a braced, angle-bracketed, or quoted    57  \eg is not followed by a braced, angle-bracketed, or quoted
902          name/number or by a plain number          name/number or by a plain number
903    58  a numbered reference must not be zero    58  a numbered reference must not be zero
904    59  (*VERB) with an argument is not supported    59  an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT)
905    60  (*VERB) not recognized    60  (*VERB) not recognized
906    61  number is too big    61  number is too big
907    62  subpattern name expected    62  subpattern name expected
908    63  digit expected after (?+    63  digit expected after (?+
909    64  ] is an invalid data character in JavaScript compatibility mode    64  ] is an invalid data character in JavaScript compatibility mode
910      65  different names for subpatterns of the same number are
911            not allowed
912      66  (*MARK) must have an argument
913      67  this version of PCRE is not compiled with Unicode property
914            support
915      68  \ec must be followed by an ASCII character
916      69  \ek is not followed by a braced, angle-bracketed, or quoted name
917      70  internal error: unknown opcode in find_fixedlength()
918      71  \eN is not supported in a class
919      72  too many forward references
920      73  disallowed Unicode code point (>= 0xd800 && <= 0xdfff)
921      74  invalid UTF-16 string (specifically UTF-16)
922  .sp  .sp
923  The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may  The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may
924  be used if the limits were changed when PCRE was built.  be used if the limits were changed when PCRE was built.
925  .  .
926  .  .
927    .\" HTML <a name="studyingapattern"></a>
928  .SH "STUDYING A PATTERN"  .SH "STUDYING A PATTERN"
929  .rs  .rs
930  .sp  .sp
# Line 788  If studying the pattern does not produce Line 955  If studying the pattern does not produce
955  wants to pass any of the other fields to \fBpcre_exec()\fP or  wants to pass any of the other fields to \fBpcre_exec()\fP or
956  \fBpcre_dfa_exec()\fP, it must set up its own \fBpcre_extra\fP block.  \fBpcre_dfa_exec()\fP, it must set up its own \fBpcre_extra\fP block.
957  .P  .P
958  The second argument of \fBpcre_study()\fP contains option bits. At present, no  The second argument of \fBpcre_study()\fP contains option bits. There is only
959  options are defined, and this argument should always be zero.  one option: PCRE_STUDY_JIT_COMPILE. If this is set, and the just-in-time
960    compiler is available, the pattern is further compiled into machine code that
961    executes much faster than the \fBpcre_exec()\fP matching function. If
962    the just-in-time compiler is not available, this option is ignored. All other
963    bits in the \fIoptions\fP argument must be zero.
964    .P
965    JIT compilation is a heavyweight optimization. It can take some time for
966    patterns to be analyzed, and for one-off matches and simple patterns the
967    benefit of faster execution might be offset by a much slower study time.
968    Not all patterns can be optimized by the JIT compiler. For those that cannot be
969    handled, matching automatically falls back to the \fBpcre_exec()\fP
970    interpreter. For more details, see the
971    .\" HREF
972    \fBpcrejit\fP
973    .\"
974    documentation.
975  .P  .P
976  The third argument for \fBpcre_study()\fP is a pointer for an error message. If  The third argument for \fBpcre_study()\fP is a pointer for an error message. If
977  studying succeeds (even if no data is returned), the variable it points to is  studying succeeds (even if no data is returned), the variable it points to is
# Line 798  static string that is part of the librar Line 980  static string that is part of the librar
980  should test the error pointer for NULL after calling \fBpcre_study()\fP, to be  should test the error pointer for NULL after calling \fBpcre_study()\fP, to be
981  sure that it has run successfully.  sure that it has run successfully.
982  .P  .P
983  This is a typical call to \fBpcre_study\fP():  When you are finished with a pattern, you can free the memory used for the
984    study data by calling \fBpcre_free_study()\fP. This function was added to the
985    API for release 8.20. For earlier versions, the memory could be freed with
986    \fBpcre_free()\fP, just like the pattern itself. This will still work in cases
987    where PCRE_STUDY_JIT_COMPILE is not used, but it is advisable to change to the
988    new function when convenient.
989    .P
990    This is a typical way in which \fBpcre_study\fP() is used (except that in a
991    real application there should be tests for errors):
992  .sp  .sp
993    pcre_extra *pe;    int rc;
994    pe = pcre_study(    pcre *re;
995      pcre_extra *sd;
996      re = pcre_compile("pattern", 0, &error, &erroroffset, NULL);
997      sd = pcre_study(
998      re,             /* result of pcre_compile() */      re,             /* result of pcre_compile() */
999      0,              /* no options exist */      0,              /* no options */
1000      &error);        /* set to NULL or points to a message */      &error);        /* set to NULL or points to a message */
1001      rc = pcre_exec(   /* see below for details of pcre_exec() options */
1002        re, sd, "subject", 7, 0, 0, ovector, 30);
1003      ...
1004      pcre_free_study(sd);
1005      pcre_free(re);
1006  .sp  .sp
1007  Studying a pattern does two things: first, a lower bound for the length of  Studying a pattern does two things: first, a lower bound for the length of
1008  subject string that is needed to match the pattern is computed. This does not  subject string that is needed to match the pattern is computed. This does not
# Line 817  in a calling program via the \fBpcre_ful Line 1015  in a calling program via the \fBpcre_ful
1015  Studying a pattern is also useful for non-anchored patterns that do not have a  Studying a pattern is also useful for non-anchored patterns that do not have a
1016  single fixed starting character. A bitmap of possible starting bytes is  single fixed starting character. A bitmap of possible starting bytes is
1017  created. This speeds up finding a position in the subject at which to start  created. This speeds up finding a position in the subject at which to start
1018  matching.  matching. (In 16-bit mode, the bitmap is used for 16-bit values less than 256.)
1019    .P
1020    These two optimizations apply to both \fBpcre_exec()\fP and
1021    \fBpcre_dfa_exec()\fP. However, they are not used by \fBpcre_exec()\fP if
1022    \fBpcre_study()\fP is called with the PCRE_STUDY_JIT_COMPILE option, and
1023    just-in-time compiling is successful. The optimizations can be disabled by
1024    setting the PCRE_NO_START_OPTIMIZE option when calling \fBpcre_exec()\fP or
1025    \fBpcre_dfa_exec()\fP. You might want to do this if your pattern contains
1026    callouts or (*MARK) (which cannot be handled by the JIT compiler), and you want
1027    to make use of these facilities in cases where matching fails. See the
1028    discussion of PCRE_NO_START_OPTIMIZE
1029    .\" HTML <a href="#execoptions">
1030    .\" </a>
1031    below.
1032    .\"
1033  .  .
1034  .  .
1035  .\" HTML <a name="localesupport"></a>  .\" HTML <a name="localesupport"></a>
# Line 826  matching. Line 1038  matching.
1038  .sp  .sp
1039  PCRE handles caseless matching, and determines whether characters are letters,  PCRE handles caseless matching, and determines whether characters are letters,
1040  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
1041  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
1042  less than 128. Higher-valued codes never match escapes such as \ew or \ed, but  with codes less than 128. By default, higher-valued codes never match escapes
1043  can be tested with \ep if PCRE is built with Unicode character property  such as \ew or \ed, but they can be tested with \ep if PCRE is built with
1044  support. The use of locales with Unicode is discouraged. If you are handling  Unicode character property support. Alternatively, the PCRE_UCP option can be
1045  characters with codes greater than 128, you should either use UTF-8 and  set at compile time; this causes \ew and friends to use Unicode property
1046  Unicode, or use locales, but not try to mix the two.  support instead of built-in tables. The use of locales with Unicode is
1047    discouraged. If you are handling characters with codes greater than 128, you
1048    should either use UTF-8 and Unicode, or use locales, but not try to mix the
1049    two.
1050  .P  .P
1051  PCRE contains an internal set of tables that are used when the final argument  PCRE contains an internal set of tables that are used when the final argument
1052  of \fBpcre_compile()\fP is NULL. These are sufficient for many applications.  of \fBpcre_compile()\fP is NULL. These are sufficient for many applications.
# Line 876  one in which it was compiled. Passing ta Line 1091  one in which it was compiled. Passing ta
1091  below in the section on matching a pattern.  below in the section on matching a pattern.
1092  .  .
1093  .  .
1094    .\" HTML <a name="infoaboutpattern"></a>
1095  .SH "INFORMATION ABOUT A PATTERN"  .SH "INFORMATION ABOUT A PATTERN"
1096  .rs  .rs
1097  .sp  .sp
# Line 884  below in the section on matching a patte Line 1100  below in the section on matching a patte
1100  .B int \fIwhat\fP, void *\fIwhere\fP);  .B int \fIwhat\fP, void *\fIwhere\fP);
1101  .PP  .PP
1102  The \fBpcre_fullinfo()\fP function returns information about a compiled  The \fBpcre_fullinfo()\fP function returns information about a compiled
1103  pattern. It replaces the obsolete \fBpcre_info()\fP function, which is  pattern. It replaces the \fBpcre_info()\fP function, which was removed from the
1104  nevertheless retained for backwards compability (and is documented below).  library at version 8.30, after more than 10 years of obsolescence.
1105  .P  .P
1106  The first argument for \fBpcre_fullinfo()\fP is a pointer to the compiled  The first argument for \fBpcre_fullinfo()\fP is a pointer to the compiled
1107  pattern. The second argument is the result of \fBpcre_study()\fP, or NULL if  pattern. The second argument is the result of \fBpcre_study()\fP, or NULL if
# Line 894  information is required, and the fourth Line 1110  information is required, and the fourth
1110  to receive the data. The yield of the function is zero for success, or one of  to receive the data. The yield of the function is zero for success, or one of
1111  the following negative numbers:  the following negative numbers:
1112  .sp  .sp
1113    PCRE_ERROR_NULL       the argument \fIcode\fP was NULL    PCRE_ERROR_NULL           the argument \fIcode\fP was NULL
1114                          the argument \fIwhere\fP was NULL                              the argument \fIwhere\fP was NULL
1115    PCRE_ERROR_BADMAGIC   the "magic number" was not found    PCRE_ERROR_BADMAGIC       the "magic number" was not found
1116    PCRE_ERROR_BADOPTION  the value of \fIwhat\fP was invalid    PCRE_ERROR_BADENDIANNESS  the pattern was compiled with different
1117                                endianness
1118      PCRE_ERROR_BADOPTION      the value of \fIwhat\fP was invalid
1119  .sp  .sp
1120  The "magic number" is placed at the start of each compiled pattern as an simple  The "magic number" is placed at the start of each compiled pattern as an simple
1121  check against passing an arbitrary memory pointer. Here is a typical call of  check against passing an arbitrary memory pointer. The endianness error can
1122  \fBpcre_fullinfo()\fP, to obtain the length of the compiled pattern:  occur if a compiled pattern is saved and reloaded on a different host. Here is
1123    a typical call of \fBpcre_fullinfo()\fP, to obtain the length of the compiled
1124    pattern:
1125  .sp  .sp
1126    int rc;    int rc;
1127    size_t length;    size_t length;
1128    rc = pcre_fullinfo(    rc = pcre_fullinfo(
1129      re,               /* result of pcre_compile() */      re,               /* result of pcre_compile() */
1130      pe,               /* result of pcre_study(), or NULL */      sd,               /* result of pcre_study(), or NULL */
1131      PCRE_INFO_SIZE,   /* what is required */      PCRE_INFO_SIZE,   /* what is required */
1132      &length);         /* where to put the data */      &length);         /* where to put the data */
1133  .sp  .sp
# Line 935  a NULL table pointer. Line 1155  a NULL table pointer.
1155  .sp  .sp
1156    PCRE_INFO_FIRSTBYTE    PCRE_INFO_FIRSTBYTE
1157  .sp  .sp
1158  Return information about the first byte of any matched string, for a  Return information about the first data unit of any matched string, for a
1159  non-anchored pattern. The fourth argument should point to an \fBint\fP  non-anchored pattern. (The name of this option refers to the 8-bit library,
1160  variable. (This option used to be called PCRE_INFO_FIRSTCHAR; the old name is  where data units are bytes.) The fourth argument should point to an \fBint\fP
1161  still recognized for backwards compatibility.)  variable.
1162    .P
1163    If there is a fixed first value, for example, the letter "c" from a pattern
1164    such as (cat|cow|coyote), its value is returned. In the 8-bit library, the
1165    value is always less than 256; in the 16-bit library the value can be up to
1166    0xffff.
1167  .P  .P
1168  If there is a fixed first byte, for example, from a pattern such as  If there is no fixed first value, and if either
 (cat|cow|coyote), its value is returned. Otherwise, if either  
1169  .sp  .sp
1170  (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch  (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch
1171  starts with "^", or  starts with "^", or
# Line 956  returned. For anchored patterns, -2 is r Line 1180  returned. For anchored patterns, -2 is r
1180    PCRE_INFO_FIRSTTABLE    PCRE_INFO_FIRSTTABLE
1181  .sp  .sp
1182  If the pattern was studied, and this resulted in the construction of a 256-bit  If the pattern was studied, and this resulted in the construction of a 256-bit
1183  table indicating a fixed set of bytes for the first byte in any matching  table indicating a fixed set of values for the first data unit in any matching
1184  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
1185  fourth argument should point to an \fBunsigned char *\fP variable.  fourth argument should point to an \fBunsigned char *\fP variable.
1186  .sp  .sp
# Line 972  Return 1 if the (?J) or (?-J) option set Line 1196  Return 1 if the (?J) or (?-J) option set
1196  0. The fourth argument should point to an \fBint\fP variable. (?J) and  0. The fourth argument should point to an \fBint\fP variable. (?J) and
1197  (?-J) set and unset the local PCRE_DUPNAMES option, respectively.  (?-J) set and unset the local PCRE_DUPNAMES option, respectively.
1198  .sp  .sp
1199      PCRE_INFO_JIT
1200    .sp
1201    Return 1 if the pattern was studied with the PCRE_STUDY_JIT_COMPILE option, and
1202    just-in-time compiling was successful. The fourth argument should point to an
1203    \fBint\fP variable. A return value of 0 means that JIT support is not available
1204    in this version of PCRE, or that the pattern was not studied with the
1205    PCRE_STUDY_JIT_COMPILE option, or that the JIT compiler could not handle this
1206    particular pattern. See the
1207    .\" HREF
1208    \fBpcrejit\fP
1209    .\"
1210    documentation for details of what can and cannot be handled.
1211    .sp
1212      PCRE_INFO_JITSIZE
1213    .sp
1214    If the pattern was successfully studied with the PCRE_STUDY_JIT_COMPILE option,
1215    return the size of the JIT compiled code, otherwise return zero. The fourth
1216    argument should point to a \fBsize_t\fP variable.
1217    .sp
1218    PCRE_INFO_LASTLITERAL    PCRE_INFO_LASTLITERAL
1219  .sp  .sp
1220  Return the value of the rightmost literal byte that must exist in any matched  Return the value of the rightmost literal data unit that must exist in any
1221  string, other than at its start, if such a byte has been recorded. The fourth  matched string, other than at its start, if such a value has been recorded. The
1222  argument should point to an \fBint\fP variable. If there is no such byte, -1 is  fourth argument should point to an \fBint\fP variable. If there is no such
1223  returned. For anchored patterns, a last literal byte is recorded only if it  value, -1 is returned. For anchored patterns, a last literal value is recorded
1224  follows something of variable length. For example, for the pattern  only if it follows something of variable length. For example, for the pattern
1225  /^a\ed+z\ed+/ the returned value is "z", but for /^a\edz\ed/ the returned value  /^a\ed+z\ed+/ the returned value is "z", but for /^a\edz\ed/ the returned value
1226  is -1.  is -1.
1227  .sp  .sp
# Line 986  is -1. Line 1229  is -1.
1229  .sp  .sp
1230  If the pattern was studied and a minimum length for matching subject strings  If the pattern was studied and a minimum length for matching subject strings
1231  was computed, its value is returned. Otherwise the returned value is -1. The  was computed, its value is returned. Otherwise the returned value is -1. The
1232  value is a number of characters, not bytes (this may be relevant in UTF-8  value is a number of characters, which in UTF-8 mode may be different from the
1233  mode). The fourth argument should point to an \fBint\fP variable. A  number of bytes. The fourth argument should point to an \fBint\fP variable. A
1234  non-negative value is a lower bound to the length of any matching string. There  non-negative value is a lower bound to the length of any matching string. There
1235  may not be any strings of that length that do actually match, but every string  may not be any strings of that length that do actually match, but every string
1236  that does match is at least that long.  that does match is at least that long.
# Line 1010  The map consists of a number of fixed-si Line 1253  The map consists of a number of fixed-si
1253  the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size of each  the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size of each
1254  entry; both of these return an \fBint\fP value. The entry size depends on the  entry; both of these return an \fBint\fP value. The entry size depends on the
1255  length of the longest name. PCRE_INFO_NAMETABLE returns a pointer to the first  length of the longest name. PCRE_INFO_NAMETABLE returns a pointer to the first
1256  entry of the table (a pointer to \fBchar\fP). The first two bytes of each entry  entry of the table. This is a pointer to \fBchar\fP in the 8-bit library, where
1257  are the number of the capturing parenthesis, most significant byte first. The  the first two bytes of each entry are the number of the capturing parenthesis,
1258  rest of the entry is the corresponding name, zero terminated.  most significant byte first. In the 16-bit library, the pointer points to
1259    16-bit data units, the first of which contains the parenthesis number. The rest
1260    of the entry is the corresponding name, zero terminated.
1261  .P  .P
1262  The names are in alphabetical order. Duplicate names may appear if (?| is used  The names are in alphabetical order. Duplicate names may appear if (?| is used
1263  to create multiple groups with the same number, as described in the  to create multiple groups with the same number, as described in the
# Line 1031  table in the order in which they were fo Line 1276  table in the order in which they were fo
1276  necessarily the case because later subpatterns may have lower numbers.  necessarily the case because later subpatterns may have lower numbers.
1277  .P  .P
1278  As a simple example of the name/number table, consider the following pattern  As a simple example of the name/number table, consider the following pattern
1279  (assume PCRE_EXTENDED is set, so white space - including newlines - is  after compilation by the 8-bit library (assume PCRE_EXTENDED is set, so white
1280  ignored):  space - including newlines - is ignored):
1281  .sp  .sp
1282  .\" JOIN  .\" JOIN
1283    (?<date> (?<year>(\ed\ed)?\ed\ed) -    (?<date> (?<year>(\ed\ed)?\ed\ed) -
# Line 1087  For such patterns, the PCRE_ANCHORED bit Line 1332  For such patterns, the PCRE_ANCHORED bit
1332  .sp  .sp
1333    PCRE_INFO_SIZE    PCRE_INFO_SIZE
1334  .sp  .sp
1335  Return the size of the compiled pattern, that is, the value that was passed as  Return the size of the compiled pattern in bytes (for both libraries). The
1336  the argument to \fBpcre_malloc()\fP when PCRE was getting memory in which to  fourth argument should point to a \fBsize_t\fP variable. This value does not
1337  place the compiled data. The fourth argument should point to a \fBsize_t\fP  include the size of the \fBpcre\fP structure that is returned by
1338  variable.  \fBpcre_compile()\fP. The value that is passed as the argument to
1339    \fBpcre_malloc()\fP when \fBpcre_compile()\fP is getting memory in which to
1340    place the compiled data is the value returned by this option plus the size of
1341    the \fBpcre\fP structure. Studying a compiled pattern, with or without JIT,
1342    does not alter the value returned by this option.
1343  .sp  .sp
1344    PCRE_INFO_STUDYSIZE    PCRE_INFO_STUDYSIZE
1345  .sp  .sp
1346  Return the size of the data block pointed to by the \fIstudy_data\fP field in  Return the size in bytes of the data block pointed to by the \fIstudy_data\fP
1347  a \fBpcre_extra\fP block. That is, it is the value that was passed to  field in a \fBpcre_extra\fP block. If \fBpcre_extra\fP is NULL, or there is no
 \fBpcre_malloc()\fP when PCRE was getting memory into which to place the data  
 created by \fBpcre_study()\fP. If \fBpcre_extra\fP is NULL, or there is no  
1348  study data, zero is returned. The fourth argument should point to a  study data, zero is returned. The fourth argument should point to a
1349  \fBsize_t\fP variable.  \fBsize_t\fP variable. The \fIstudy_data\fP field is set by \fBpcre_study()\fP
1350  .  to record information that will speed up matching (see the section entitled
1351  .  .\" HTML <a href="#studyingapattern">
1352  .SH "OBSOLETE INFO FUNCTION"  .\" </a>
1353  .rs  "Studying a pattern"
1354  .sp  .\"
1355  .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int  above). The format of the \fIstudy_data\fP block is private, but its length
1356  .B *\fIfirstcharptr\fP);  is made available via this option so that it can be saved and restored (see the
1357  .PP  .\" HREF
1358  The \fBpcre_info()\fP function is now obsolete because its interface is too  \fBpcreprecompile\fP
1359  restrictive to return all the available data about a compiled pattern. New  .\"
1360  programs should use \fBpcre_fullinfo()\fP instead. The yield of  documentation for details).
 \fBpcre_info()\fP is the number of capturing subpatterns, or one of the  
 following negative numbers:  
 .sp  
   PCRE_ERROR_NULL       the argument \fIcode\fP was NULL  
   PCRE_ERROR_BADMAGIC   the "magic number" was not found  
 .sp  
 If the \fIoptptr\fP argument is not NULL, a copy of the options with which the  
 pattern was compiled is placed in the integer it points to (see  
 PCRE_INFO_OPTIONS above).  
 .P  
 If the pattern is not anchored and the \fIfirstcharptr\fP argument is not NULL,  
 it is used to pass back information about the first character of any matched  
 string (see PCRE_INFO_FIRSTBYTE above).  
1361  .  .
1362  .  .
1363  .SH "REFERENCE COUNTS"  .SH "REFERENCE COUNTS"
# Line 1161  is different. (This seems a highly unlik Line 1395  is different. (This seems a highly unlik
1395  The function \fBpcre_exec()\fP is called to match a subject string against a  The function \fBpcre_exec()\fP is called to match a subject string against a
1396  compiled pattern, which is passed in the \fIcode\fP argument. If the  compiled pattern, which is passed in the \fIcode\fP argument. If the
1397  pattern was studied, the result of the study should be passed in the  pattern was studied, the result of the study should be passed in the
1398  \fIextra\fP argument. This function is the main matching facility of the  \fIextra\fP argument. You can call \fBpcre_exec()\fP with the same \fIcode\fP
1399  library, and it operates in a Perl-like manner. For specialist use there is  and \fIextra\fP arguments as many times as you like, in order to match
1400  also an alternative matching function, which is described  different subject strings with the same pattern.
1401    .P
1402    This function is the main matching facility of the library, and it operates in
1403    a Perl-like manner. For specialist use there is also an alternative matching
1404    function, which is described
1405  .\" HTML <a href="#dfamatch">  .\" HTML <a href="#dfamatch">
1406  .\" </a>  .\" </a>
1407  below  below
# Line 1194  Here is an example of a simple call to \ Line 1432  Here is an example of a simple call to \
1432      ovector,        /* vector of integers for substring information */      ovector,        /* vector of integers for substring information */
1433      30);            /* number of elements (NOT size in bytes) */      30);            /* number of elements (NOT size in bytes) */
1434  .  .
1435    .
1436  .\" HTML <a name="extradata"></a>  .\" HTML <a name="extradata"></a>
1437  .SS "Extra data for \fBpcre_exec()\fR"  .SS "Extra data for \fBpcre_exec()\fR"
1438  .rs  .rs
# Line 1206  fields (not necessarily in this order): Line 1445  fields (not necessarily in this order):
1445  .sp  .sp
1446    unsigned long int \fIflags\fP;    unsigned long int \fIflags\fP;
1447    void *\fIstudy_data\fP;    void *\fIstudy_data\fP;
1448      void *\fIexecutable_jit\fP;
1449    unsigned long int \fImatch_limit\fP;    unsigned long int \fImatch_limit\fP;
1450    unsigned long int \fImatch_limit_recursion\fP;    unsigned long int \fImatch_limit_recursion\fP;
1451    void *\fIcallout_data\fP;    void *\fIcallout_data\fP;
1452    const unsigned char *\fItables\fP;    const unsigned char *\fItables\fP;
1453      unsigned char **\fImark\fP;
1454  .sp  .sp
1455    In the 16-bit version of this structure, the \fImark\fP field has type
1456    "PCRE_UCHAR16 **".
1457    .P
1458  The \fIflags\fP field is a bitmap that specifies which of the other fields  The \fIflags\fP field is a bitmap that specifies which of the other fields
1459  are set. The flag bits are:  are set. The flag bits are:
1460  .sp  .sp
1461    PCRE_EXTRA_STUDY_DATA    PCRE_EXTRA_STUDY_DATA
1462      PCRE_EXTRA_EXECUTABLE_JIT
1463    PCRE_EXTRA_MATCH_LIMIT    PCRE_EXTRA_MATCH_LIMIT
1464    PCRE_EXTRA_MATCH_LIMIT_RECURSION    PCRE_EXTRA_MATCH_LIMIT_RECURSION
1465    PCRE_EXTRA_CALLOUT_DATA    PCRE_EXTRA_CALLOUT_DATA
1466    PCRE_EXTRA_TABLES    PCRE_EXTRA_TABLES
1467      PCRE_EXTRA_MARK
1468  .sp  .sp
1469  Other flag bits should be set to zero. The \fIstudy_data\fP field is set in the  Other flag bits should be set to zero. The \fIstudy_data\fP field and sometimes
1470  \fBpcre_extra\fP block that is returned by \fBpcre_study()\fP, together with  the \fIexecutable_jit\fP field are set in the \fBpcre_extra\fP block that is
1471  the appropriate flag bit. You should not set this yourself, but you may add to  returned by \fBpcre_study()\fP, together with the appropriate flag bits. You
1472  the block by setting the other fields and their corresponding flag bits.  should not set these yourself, but you may add to the block by setting the
1473    other fields and their corresponding flag bits.
1474  .P  .P
1475  The \fImatch_limit\fP field provides a means of preventing PCRE from using up a  The \fImatch_limit\fP field provides a means of preventing PCRE from using up a
1476  vast amount of resources when running patterns that are not going to match,  vast amount of resources when running patterns that are not going to match,
1477  but which have a very large number of possibilities in their search trees. The  but which have a very large number of possibilities in their search trees. The
1478  classic example is a pattern that uses nested unlimited repeats.  classic example is a pattern that uses nested unlimited repeats.
1479  .P  .P
1480  Internally, PCRE uses a function called \fBmatch()\fP which it calls repeatedly  Internally, \fBpcre_exec()\fP uses a function called \fBmatch()\fP, which it
1481  (sometimes recursively). The limit set by \fImatch_limit\fP is imposed on the  calls repeatedly (sometimes recursively). The limit set by \fImatch_limit\fP is
1482  number of times this function is called during a match, which has the effect of  imposed on the number of times this function is called during a match, which
1483  limiting the amount of backtracking that can take place. For patterns that are  has the effect of limiting the amount of backtracking that can take place. For
1484  not anchored, the count restarts from zero for each position in the subject  patterns that are not anchored, the count restarts from zero for each position
1485  string.  in the subject string.
1486    .P
1487    When \fBpcre_exec()\fP is called with a pattern that was successfully studied
1488    with the PCRE_STUDY_JIT_COMPILE option, the way that the matching is executed
1489    is entirely different. However, there is still the possibility of runaway
1490    matching that goes on for a very long time, and so the \fImatch_limit\fP value
1491    is also used in this case (but in a different way) to limit how long the
1492    matching can continue.
1493  .P  .P
1494  The default value for the limit can be set when PCRE is built; the default  The default value for the limit can be set when PCRE is built; the default
1495  default is 10 million, which handles all but the most extreme cases. You can  default is 10 million, which handles all but the most extreme cases. You can
# Line 1250  limits the depth of recursion. The recur Line 1504  limits the depth of recursion. The recur
1504  total number of calls, because not all calls to \fBmatch()\fP are recursive.  total number of calls, because not all calls to \fBmatch()\fP are recursive.
1505  This limit is of use only if it is set smaller than \fImatch_limit\fP.  This limit is of use only if it is set smaller than \fImatch_limit\fP.
1506  .P  .P
1507  Limiting the recursion depth limits the amount of stack that can be used, or,  Limiting the recursion depth limits the amount of machine stack that can be
1508  when PCRE has been compiled to use memory on the heap instead of the stack, the  used, or, when PCRE has been compiled to use memory on the heap instead of the
1509  amount of heap memory that can be used.  stack, the amount of heap memory that can be used. This limit is not relevant,
1510    and is ignored, if the pattern was successfully studied with
1511    PCRE_STUDY_JIT_COMPILE.
1512  .P  .P
1513  The default value for \fImatch_limit_recursion\fP can be set when PCRE is  The default value for \fImatch_limit_recursion\fP can be set when PCRE is
1514  built; the default default is the same value as the default for  built; the default default is the same value as the default for
# Line 1281  called. See the Line 1537  called. See the
1537  \fBpcreprecompile\fP  \fBpcreprecompile\fP
1538  .\"  .\"
1539  documentation for a discussion of saving compiled patterns for later use.  documentation for a discussion of saving compiled patterns for later use.
1540    .P
1541    If PCRE_EXTRA_MARK is set in the \fIflags\fP field, the \fImark\fP field must
1542    be set to point to a suitable variable. If the pattern contains any
1543    backtracking control verbs such as (*MARK:NAME), and the execution ends up with
1544    a name to pass back, a pointer to the name string (zero terminated) is placed
1545    in the variable pointed to by the \fImark\fP field. The names are within the
1546    compiled pattern; if you wish to retain such a name you must copy it before
1547    freeing the memory of a compiled pattern. If there is no name to pass back, the
1548    variable pointed to by the \fImark\fP field is set to NULL. For details of the
1549    backtracking control verbs, see the section entitled
1550    .\" HTML <a href="pcrepattern#backtrackcontrol">
1551    .\" </a>
1552    "Backtracking control"
1553    .\"
1554    in the
1555    .\" HREF
1556    \fBpcrepattern\fP
1557    .\"
1558    documentation.
1559    .
1560  .  .
1561  .\" HTML <a name="execoptions"></a>  .\" HTML <a name="execoptions"></a>
1562  .SS "Option bits for \fBpcre_exec()\fP"  .SS "Option bits for \fBpcre_exec()\fP"
# Line 1291  zero. The only bits that may be set are Line 1567  zero. The only bits that may be set are
1567  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART,  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART,
1568  PCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_SOFT, and  PCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_SOFT, and
1569  PCRE_PARTIAL_HARD.  PCRE_PARTIAL_HARD.
1570    .P
1571    If the pattern was successfully studied with the PCRE_STUDY_JIT_COMPILE option,
1572    the only supported options for JIT execution are PCRE_NO_UTF8_CHECK,
1573    PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, and PCRE_NOTEMPTY_ATSTART. Note in
1574    particular that partial matching is not supported. If an unsupported option is
1575    used, JIT execution is disabled and the normal interpretive code in
1576    \fBpcre_exec()\fP is run.
1577  .sp  .sp
1578    PCRE_ANCHORED    PCRE_ANCHORED
1579  .sp  .sp
# Line 1386  the Line 1669  the
1669  .\" HREF  .\" HREF
1670  \fBpcredemo\fP  \fBpcredemo\fP
1671  .\"  .\"
1672  sample program.  sample program. In the most general case, you have to check to see if the
1673    newline convention recognizes CRLF as a newline, and if so, and the current
1674    character is CR followed by LF, advance the starting offset by two characters
1675    instead of one.
1676  .sp  .sp
1677    PCRE_NO_START_OPTIMIZE    PCRE_NO_START_OPTIMIZE
1678  .sp  .sp
1679  There are a number of optimizations that \fBpcre_exec()\fP uses at the start of  There are a number of optimizations that \fBpcre_exec()\fP uses at the start of
1680  a match, in order to speed up the process. For example, if it is known that a  a match, in order to speed up the process. For example, if it is known that an
1681  match must start with a specific character, it searches the subject for that  unanchored match must start with a specific character, it searches the subject
1682  character, and fails immediately if it cannot find it, without actually running  for that character, and fails immediately if it cannot find it, without
1683  the main matching function. When callouts are in use, these optimizations can  actually running the main matching function. This means that a special item
1684  cause them to be skipped. This option disables the "start-up" optimizations,  such as (*COMMIT) at the start of a pattern is not considered until after a
1685  causing performance to suffer, but ensuring that the callouts do occur.  suitable starting point for the match has been found. When callouts or (*MARK)
1686    items are in use, these "start-up" optimizations can cause them to be skipped
1687    if the pattern is never actually used. The start-up optimizations are in effect
1688    a pre-scan of the subject that takes place before the pattern is run.
1689    .P
1690    The PCRE_NO_START_OPTIMIZE option disables the start-up optimizations, possibly
1691    causing performance to suffer, but ensuring that in cases where the result is
1692    "no match", the callouts do occur, and that items such as (*COMMIT) and (*MARK)
1693    are considered at every possible starting position in the subject string. If
1694    PCRE_NO_START_OPTIMIZE is set at compile time, it cannot be unset at matching
1695    time.
1696    .P
1697    Setting PCRE_NO_START_OPTIMIZE can change the outcome of a matching operation.
1698    Consider the pattern
1699    .sp
1700      (*COMMIT)ABC
1701    .sp
1702    When this is compiled, PCRE records the fact that a match must start with the
1703    character "A". Suppose the subject string is "DEFABC". The start-up
1704    optimization scans along the subject, finds "A" and runs the first match
1705    attempt from there. The (*COMMIT) item means that the pattern must match the
1706    current starting position, which in this case, it does. However, if the same
1707    match is run with PCRE_NO_START_OPTIMIZE set, the initial scan along the
1708    subject string does not happen. The first match attempt is run starting from
1709    "D" and when this fails, (*COMMIT) prevents any further matches being tried, so
1710    the overall result is "no match". If the pattern is studied, more start-up
1711    optimizations may be used. For example, a minimum length for the subject may be
1712    recorded. Consider the pattern
1713    .sp
1714      (*MARK:A)(X|Y)
1715    .sp
1716    The minimum length for a match is one character. If the subject is "ABC", there
1717    will be attempts to match "ABC", "BC", "C", and then finally an empty string.
1718    If the pattern is studied, the final attempt does not take place, because PCRE
1719    knows that the subject is too short, and so the (*MARK) is never encountered.
1720    In this case, studying the pattern does not affect the overall match result,
1721    which is still "no match", but it does affect the auxiliary information that is
1722    returned.
1723  .sp  .sp
1724    PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
1725  .sp  .sp
# Line 1405  string is automatically checked when \fB Line 1728  string is automatically checked when \fB
1728  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
1729  start of a UTF-8 character. There is a discussion about the validity of UTF-8  start of a UTF-8 character. There is a discussion about the validity of UTF-8
1730  strings in the  strings in the
 .\" HTML <a href="pcre.html#utf8strings">  
 .\" </a>  
 section on UTF-8 support  
 .\"  
 in the main  
1731  .\" HREF  .\" HREF
1732  \fBpcre\fP  \fBpcreunicode\fP
1733    .\"
1734    page. If an invalid sequence of bytes is found, \fBpcre_exec()\fP returns the
1735    error PCRE_ERROR_BADUTF8 or, if PCRE_PARTIAL_HARD is set and the problem is a
1736    truncated character at the end of the subject, PCRE_ERROR_SHORTUTF8. In both
1737    cases, information about the precise nature of the error may also be returned
1738    (see the descriptions of these errors in the section entitled \fIError return
1739    values from\fP \fBpcre_exec()\fP
1740    .\" HTML <a href="#errorlist">
1741    .\" </a>
1742    below).
1743  .\"  .\"
1744  page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_exec()\fP returns  If \fIstartoffset\fP contains a value that does not point to the start of a
1745  the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP contains an invalid value,  UTF-8 character (or to the end of the subject), PCRE_ERROR_BADUTF8_OFFSET is
1746  PCRE_ERROR_BADUTF8_OFFSET is returned.  returned.
1747  .P  .P
1748  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
1749  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
1750  calling \fBpcre_exec()\fP. You might want to do this for the second and  calling \fBpcre_exec()\fP. You might want to do this for the second and
1751  subsequent calls to \fBpcre_exec()\fP if you are making repeated calls to find  subsequent calls to \fBpcre_exec()\fP if you are making repeated calls to find
1752  all the matches in a single subject string. However, you should be sure that  all the matches in a single subject string. However, you should be sure that
1753  the value of \fIstartoffset\fP points to the start of a UTF-8 character. When  the value of \fIstartoffset\fP points to the start of a character (or the end
1754  PCRE_NO_UTF8_CHECK is set, the effect of passing an invalid UTF-8 string as a  of the subject). When PCRE_NO_UTF8_CHECK is set, the effect of passing an
1755  subject, or a value of \fIstartoffset\fP that does not point to the start of a  invalid string as a subject or an invalid value of \fIstartoffset\fP is
1756  UTF-8 character, is undefined. Your program may crash.  undefined. Your program may crash.
1757  .sp  .sp
1758    PCRE_PARTIAL_HARD    PCRE_PARTIAL_HARD
1759    PCRE_PARTIAL_SOFT    PCRE_PARTIAL_SOFT
# Line 1434  These options turn on the partial matchi Line 1762  These options turn on the partial matchi
1762  compatibility, PCRE_PARTIAL is a synonym for PCRE_PARTIAL_SOFT. A partial match  compatibility, PCRE_PARTIAL is a synonym for PCRE_PARTIAL_SOFT. A partial match
1763  occurs if the end of the subject string is reached successfully, but there are  occurs if the end of the subject string is reached successfully, but there are
1764  not enough subject characters to complete the match. If this happens when  not enough subject characters to complete the match. If this happens when
1765  PCRE_PARTIAL_HARD is set, \fBpcre_exec()\fP immediately returns  PCRE_PARTIAL_SOFT (but not PCRE_PARTIAL_HARD) is set, matching continues by
1766  PCRE_ERROR_PARTIAL. Otherwise, if PCRE_PARTIAL_SOFT is set, matching continues  testing any remaining alternatives. Only if no complete match can be found is
1767  by testing any other alternatives. Only if they all fail is PCRE_ERROR_PARTIAL  PCRE_ERROR_PARTIAL returned instead of PCRE_ERROR_NOMATCH. In other words,
1768  returned (instead of PCRE_ERROR_NOMATCH). The portion of the string that  PCRE_PARTIAL_SOFT says that the caller is prepared to handle a partial match,
1769  was inspected when the partial match was found is set as the first matching  but only if no complete match can be found.
1770  string. There is a more detailed discussion in the  .P
1771    If PCRE_PARTIAL_HARD is set, it overrides PCRE_PARTIAL_SOFT. In this case, if a
1772    partial match is found, \fBpcre_exec()\fP immediately returns
1773    PCRE_ERROR_PARTIAL, without considering any other alternatives. In other words,
1774    when PCRE_PARTIAL_HARD is set, a partial match is considered to be more
1775    important that an alternative complete match.
1776    .P
1777    In both cases, the portion of the string that was inspected when the partial
1778    match was found is set as the first matching string. There is a more detailed
1779    discussion of partial and multi-segment matching, with examples, in the
1780  .\" HREF  .\" HREF
1781  \fBpcrepartial\fP  \fBpcrepartial\fP
1782  .\"  .\"
1783  documentation.  documentation.
1784  .  .
1785    .
1786  .SS "The string to be matched by \fBpcre_exec()\fP"  .SS "The string to be matched by \fBpcre_exec()\fP"
1787  .rs  .rs
1788  .sp  .sp
1789  The subject string is passed to \fBpcre_exec()\fP as a pointer in  The subject string is passed to \fBpcre_exec()\fP as a pointer in
1790  \fIsubject\fP, a length (in bytes) in \fIlength\fP, and a starting byte offset  \fIsubject\fP, a length in bytes in \fIlength\fP, and a starting byte offset
1791  in \fIstartoffset\fP. In UTF-8 mode, the byte offset must point to the start of  in \fIstartoffset\fP. If this is negative or greater than the length of the
1792  a UTF-8 character. Unlike the pattern string, the subject may contain binary  subject, \fBpcre_exec()\fP returns PCRE_ERROR_BADOFFSET. When the starting
1793  zero bytes. When the starting offset is zero, the search for a match starts at  offset is zero, the search for a match starts at the beginning of the subject,
1794  the beginning of the subject, and this is by far the most common case.  and this is by far the most common case. In UTF-8 mode, the byte offset must
1795    point to the start of a UTF-8 character (or the end of the subject). Unlike the
1796    pattern string, the subject may contain binary zero bytes.
1797  .P  .P
1798  A non-zero starting offset is useful when searching for another match in the  A non-zero starting offset is useful when searching for another match in the
1799  same subject by calling \fBpcre_exec()\fP again after a previous success.  same subject by calling \fBpcre_exec()\fP again after a previous success.
# Line 1473  start of the subject, which is deemed to Line 1813  start of the subject, which is deemed to
1813  set to 4, it finds the second occurrence of "iss" because it is able to look  set to 4, it finds the second occurrence of "iss" because it is able to look
1814  behind the starting point to discover that it is preceded by a letter.  behind the starting point to discover that it is preceded by a letter.
1815  .P  .P
1816    Finding all the matches in a subject is tricky when the pattern can match an
1817    empty string. It is possible to emulate Perl's /g behaviour by first trying the
1818    match again at the same offset, with the PCRE_NOTEMPTY_ATSTART and
1819    PCRE_ANCHORED options, and then if that fails, advancing the starting offset
1820    and trying an ordinary match again. There is some code that demonstrates how to
1821    do this in the
1822    .\" HREF
1823    \fBpcredemo\fP
1824    .\"
1825    sample program. In the most general case, you have to check to see if the
1826    newline convention recognizes CRLF as a newline, and if so, and the current
1827    character is CR followed by LF, advance the starting offset by two characters
1828    instead of one.
1829    .P
1830  If a non-zero starting offset is passed when the pattern is anchored, one  If a non-zero starting offset is passed when the pattern is anchored, one
1831  attempt to match at the given offset is made. This can only succeed if the  attempt to match at the given offset is made. This can only succeed if the
1832  pattern does not require the match to be at the start of the subject.  pattern does not require the match to be at the start of the subject.
1833  .  .
1834    .
1835  .SS "How \fBpcre_exec()\fP returns captured substrings"  .SS "How \fBpcre_exec()\fP returns captured substrings"
1836  .rs  .rs
1837  .sp  .sp
# Line 1520  string that it matched that is returned. Line 1875  string that it matched that is returned.
1875  .P  .P
1876  If the vector is too small to hold all the captured substring offsets, it is  If the vector is too small to hold all the captured substring offsets, it is
1877  used as far as possible (up to two-thirds of its length), and the function  used as far as possible (up to two-thirds of its length), and the function
1878  returns a value of zero. If the substring offsets are not of interest,  returns a value of zero. If neither the actual string matched not any captured
1879  \fBpcre_exec()\fP may be called with \fIovector\fP passed as NULL and  substrings are of interest, \fBpcre_exec()\fP may be called with \fIovector\fP
1880  \fIovecsize\fP as zero. However, if the pattern contains back references and  passed as NULL and \fIovecsize\fP as zero. However, if the pattern contains
1881  the \fIovector\fP is not big enough to remember the related substrings, PCRE  back references and the \fIovector\fP is not big enough to remember the related
1882  has to get additional memory for use during matching. Thus it is usually  substrings, PCRE has to get additional memory for use during matching. Thus it
1883  advisable to supply an \fIovector\fP.  is usually advisable to supply an \fIovector\fP of reasonable size.
1884    .P
1885    There are some cases where zero is returned (indicating vector overflow) when
1886    in fact the vector is exactly the right size for the final match. For example,
1887    consider the pattern
1888    .sp
1889      (a)(?:(b)c|bd)
1890    .sp
1891    If a vector of 6 elements (allowing for only 1 captured substring) is given
1892    with subject string "abd", \fBpcre_exec()\fP will try to set the second
1893    captured string, thereby recording a vector overflow, before failing to match
1894    "c" and backing up to try the second alternative. The zero return, however,
1895    does correctly indicate that the maximum number of slots (namely 2) have been
1896    filled. In similar cases where there is temporary overflow, but the final
1897    number of used slots is actually less than the maximum, a non-zero value is
1898    returned.
1899  .P  .P
1900  The \fBpcre_fullinfo()\fP function can be used to find out how many capturing  The \fBpcre_fullinfo()\fP function can be used to find out how many capturing
1901  subpatterns there are in a compiled pattern. The smallest size for  subpatterns there are in a compiled pattern. The smallest size for
# Line 1543  Offset values that correspond to unused Line 1913  Offset values that correspond to unused
1913  expression are also set to -1. For example, if the string "abc" is matched  expression are also set to -1. For example, if the string "abc" is matched
1914  against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The  against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The
1915  return from the function is 2, because the highest used capturing subpattern  return from the function is 2, because the highest used capturing subpattern
1916  number is 1. However, you can refer to the offsets for the second and third  number is 1, and the offsets for for the second and third capturing subpatterns
1917  capturing subpatterns if you wish (assuming the vector is large enough, of  (assuming the vector is large enough, of course) are set to -1.
1918  course).  .P
1919    \fBNote\fP: Elements in the first two-thirds of \fIovector\fP that do not
1920    correspond to capturing parentheses in the pattern are never changed. That is,
1921    if a pattern contains \fIn\fP capturing parentheses, no more than
1922    \fIovector[0]\fP to \fIovector[2n+1]\fP are set by \fBpcre_exec()\fP. The other
1923    elements (in the first two-thirds) retain whatever values they previously had.
1924  .P  .P
1925  Some convenience functions are provided for extracting the captured substrings  Some convenience functions are provided for extracting the captured substrings
1926  as separate strings. These are described below.  as separate strings. These are described below.
1927  .  .
1928    .
1929  .\" HTML <a name="errorlist"></a>  .\" HTML <a name="errorlist"></a>
1930  .SS "Error return values from \fBpcre_exec()\fP"  .SS "Error return values from \fBpcre_exec()\fP"
1931  .rs  .rs
# Line 1591  If a pattern contains back references, b Line 1967  If a pattern contains back references, b
1967  gets a block of memory at the start of matching to use for this purpose. If the  gets a block of memory at the start of matching to use for this purpose. If the
1968  call via \fBpcre_malloc()\fP fails, this error is given. The memory is  call via \fBpcre_malloc()\fP fails, this error is given. The memory is
1969  automatically freed at the end of matching.  automatically freed at the end of matching.
1970    .P
1971    This error is also given if \fBpcre_stack_malloc()\fP fails in
1972    \fBpcre_exec()\fP. This can happen only when PCRE has been compiled with
1973    \fB--disable-stack-for-recursion\fP.
1974  .sp  .sp
1975    PCRE_ERROR_NOSUBSTRING    (-7)    PCRE_ERROR_NOSUBSTRING    (-7)
1976  .sp  .sp
# Line 1615  documentation for details. Line 1995  documentation for details.
1995  .sp  .sp
1996    PCRE_ERROR_BADUTF8        (-10)    PCRE_ERROR_BADUTF8        (-10)
1997  .sp  .sp
1998  A string that contains an invalid UTF-8 byte sequence was passed as a subject.  A string that contains an invalid UTF-8 byte sequence was passed as a subject,
1999    and the PCRE_NO_UTF8_CHECK option was not set. If the size of the output vector
2000    (\fIovecsize\fP) is at least 2, the byte offset to the start of the the invalid
2001    UTF-8 character is placed in the first element, and a reason code is placed in
2002    the second element. The reason codes are listed in the
2003    .\" HTML <a href="#badutf8reasons">
2004    .\" </a>
2005    following section.
2006    .\"
2007    For backward compatibility, if PCRE_PARTIAL_HARD is set and the problem is a
2008    truncated UTF-8 character at the end of the subject (reason codes 1 to 5),
2009    PCRE_ERROR_SHORTUTF8 is returned instead of PCRE_ERROR_BADUTF8.
2010  .sp  .sp
2011    PCRE_ERROR_BADUTF8_OFFSET (-11)    PCRE_ERROR_BADUTF8_OFFSET (-11)
2012  .sp  .sp
2013  The UTF-8 byte sequence that was passed as a subject was valid, but the value  The UTF-8 byte sequence that was passed as a subject was checked and found to
2014  of \fIstartoffset\fP did not point to the beginning of a UTF-8 character.  be valid (the PCRE_NO_UTF8_CHECK option was not set), but the value of
2015    \fIstartoffset\fP did not point to the beginning of a UTF-8 character or the
2016    end of the subject.
2017  .sp  .sp
2018    PCRE_ERROR_PARTIAL        (-12)    PCRE_ERROR_PARTIAL        (-12)
2019  .sp  .sp
# Line 1655  description above. Line 2048  description above.
2048    PCRE_ERROR_BADNEWLINE     (-23)    PCRE_ERROR_BADNEWLINE     (-23)
2049  .sp  .sp
2050  An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.  An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
2051    .sp
2052      PCRE_ERROR_BADOFFSET      (-24)
2053    .sp
2054    The value of \fIstartoffset\fP was negative or greater than the length of the
2055    subject, that is, the value in \fIlength\fP.
2056    .sp
2057      PCRE_ERROR_SHORTUTF8      (-25)
2058    .sp
2059    This error is returned instead of PCRE_ERROR_BADUTF8 when the subject string
2060    ends with a truncated UTF-8 character and the PCRE_PARTIAL_HARD option is set.
2061    Information about the failure is returned as for PCRE_ERROR_BADUTF8. It is in
2062    fact sufficient to detect this case, but this special error code for
2063    PCRE_PARTIAL_HARD precedes the implementation of returned information; it is
2064    retained for backwards compatibility.
2065    .sp
2066      PCRE_ERROR_RECURSELOOP    (-26)
2067    .sp
2068    This error is returned when \fBpcre_exec()\fP detects a recursion loop within
2069    the pattern. Specifically, it means that either the whole pattern or a
2070    subpattern has been called recursively for the second time at the same position
2071    in the subject string. Some simple patterns that might do this are detected and
2072    faulted at compile time, but more complicated cases, in particular mutual
2073    recursions between two different subpatterns, cannot be detected until run
2074    time.
2075    .sp
2076      PCRE_ERROR_JIT_STACKLIMIT (-27)
2077    .sp
2078    This error is returned when a pattern that was successfully studied using the
2079    PCRE_STUDY_JIT_COMPILE option is being matched, but the memory available for
2080    the just-in-time processing stack is not large enough. See the
2081    .\" HREF
2082    \fBpcrejit\fP
2083    .\"
2084    documentation for more details.
2085    .sp
2086      PCRE_ERROR_BADMODE (-28)
2087    .sp
2088    This error is given if a pattern that was compiled by the 8-bit library is
2089    passed to a 16-bit library function, or vice versa.
2090    .sp
2091      PCRE_ERROR_BADENDIANNESS (-29)
2092    .sp
2093    This error is given if a pattern that was compiled and saved is reloaded on a
2094    host with different endianness. The utility function
2095    \fBpcre_pattern_to_host_byte_order()\fP can be used to convert such a pattern
2096    so that it runs on the new host.
2097  .P  .P
2098  Error numbers -16 to -20 and -22 are not used by \fBpcre_exec()\fP.  Error numbers -16 to -20 and -22 are not used by \fBpcre_exec()\fP.
2099  .  .
2100  .  .
2101    .\" HTML <a name="badutf8reasons"></a>
2102    .SS "Reason codes for invalid UTF-8 strings"
2103    .rs
2104    .sp
2105    This section applies only to the 8-bit library. The corresponding information
2106    for the 16-bit library is given in the
2107    .\" HREF
2108    \fBpcre16\fP
2109    .\"
2110    page.
2111    .P
2112    When \fBpcre_exec()\fP returns either PCRE_ERROR_BADUTF8 or
2113    PCRE_ERROR_SHORTUTF8, and the size of the output vector (\fIovecsize\fP) is at
2114    least 2, the offset of the start of the invalid UTF-8 character is placed in
2115    the first output vector element (\fIovector[0]\fP) and a reason code is placed
2116    in the second element (\fIovector[1]\fP). The reason codes are given names in
2117    the \fBpcre.h\fP header file:
2118    .sp
2119      PCRE_UTF8_ERR1
2120      PCRE_UTF8_ERR2
2121      PCRE_UTF8_ERR3
2122      PCRE_UTF8_ERR4
2123      PCRE_UTF8_ERR5
2124    .sp
2125    The string ends with a truncated UTF-8 character; the code specifies how many
2126    bytes are missing (1 to 5). Although RFC 3629 restricts UTF-8 characters to be
2127    no longer than 4 bytes, the encoding scheme (originally defined by RFC 2279)
2128    allows for up to 6 bytes, and this is checked first; hence the possibility of
2129    4 or 5 missing bytes.
2130    .sp
2131      PCRE_UTF8_ERR6
2132      PCRE_UTF8_ERR7
2133      PCRE_UTF8_ERR8
2134      PCRE_UTF8_ERR9
2135      PCRE_UTF8_ERR10
2136    .sp
2137    The two most significant bits of the 2nd, 3rd, 4th, 5th, or 6th byte of the
2138    character do not have the binary value 0b10 (that is, either the most
2139    significant bit is 0, or the next bit is 1).
2140    .sp
2141      PCRE_UTF8_ERR11
2142      PCRE_UTF8_ERR12
2143    .sp
2144    A character that is valid by the RFC 2279 rules is either 5 or 6 bytes long;
2145    these code points are excluded by RFC 3629.
2146    .sp
2147      PCRE_UTF8_ERR13
2148    .sp
2149    A 4-byte character has a value greater than 0x10fff; these code points are
2150    excluded by RFC 3629.
2151    .sp
2152      PCRE_UTF8_ERR14
2153    .sp
2154    A 3-byte character has a value in the range 0xd800 to 0xdfff; this range of
2155    code points are reserved by RFC 3629 for use with UTF-16, and so are excluded
2156    from UTF-8.
2157    .sp
2158      PCRE_UTF8_ERR15
2159      PCRE_UTF8_ERR16
2160      PCRE_UTF8_ERR17
2161      PCRE_UTF8_ERR18
2162      PCRE_UTF8_ERR19
2163    .sp
2164    A 2-, 3-, 4-, 5-, or 6-byte character is "overlong", that is, it codes for a
2165    value that can be represented by fewer bytes, which is invalid. For example,
2166    the two bytes 0xc0, 0xae give the value 0x2e, whose correct coding uses just
2167    one byte.
2168    .sp
2169      PCRE_UTF8_ERR20
2170    .sp
2171    The two most significant bits of the first byte of a character have the binary
2172    value 0b10 (that is, the most significant bit is 1 and the second is 0). Such a
2173    byte can only validly occur as the second or subsequent byte of a multi-byte
2174    character.
2175    .sp
2176      PCRE_UTF8_ERR21
2177    .sp
2178    The first byte of a character has the value 0xfe or 0xff. These values can
2179    never occur in a valid UTF-8 string.
2180    .
2181    .
2182  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
2183  .rs  .rs
2184  .sp  .sp
# Line 1821  names are not included in the compiled c Line 2341  names are not included in the compiled c
2341  numbers. For this reason, the use of different names for subpatterns of the  numbers. For this reason, the use of different names for subpatterns of the
2342  same number causes an error at compile time.  same number causes an error at compile time.
2343  .  .
2344    .
2345  .SH "DUPLICATE SUBPATTERN NAMES"  .SH "DUPLICATE SUBPATTERN NAMES"
2346  .rs  .rs
2347  .sp  .sp
# Line 1854  fourth are pointers to variables which a Line 2375  fourth are pointers to variables which a
2375  has run, they point to the first and last entries in the name-to-number table  has run, they point to the first and last entries in the name-to-number table
2376  for the given name. The function itself returns the length of each entry, or  for the given name. The function itself returns the length of each entry, or
2377  PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is  PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is
2378  described above in the section entitled \fIInformation about a pattern\fP.  described above in the section entitled \fIInformation about a pattern\fP
2379    .\" HTML <a href="#infoaboutpattern">
2380    .\" </a>
2381    above.
2382    .\"
2383  Given all the relevant entries for the name, you can extract each of their  Given all the relevant entries for the name, you can extract each of their
2384  numbers, and hence the captured data, if any.  numbers, and hence the captured data, if any.
2385  .  .
# Line 1939  Here is an example of a simple call to \ Line 2464  Here is an example of a simple call to \
2464  The unused bits of the \fIoptions\fP argument for \fBpcre_dfa_exec()\fP must be  The unused bits of the \fIoptions\fP argument for \fBpcre_dfa_exec()\fP must be
2465  zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,  zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,
2466  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART,  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART,
2467  PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_HARD, PCRE_PARTIAL_SOFT, PCRE_DFA_SHORTEST,  PCRE_NO_UTF8_CHECK, PCRE_BSR_ANYCRLF, PCRE_BSR_UNICODE, PCRE_NO_START_OPTIMIZE,
2468  and PCRE_DFA_RESTART. All but the last four of these are exactly the same as  PCRE_PARTIAL_HARD, PCRE_PARTIAL_SOFT, PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART.
2469  for \fBpcre_exec()\fP, so their description is not repeated here.  All but the last four of these are exactly the same as for \fBpcre_exec()\fP,
2470    so their description is not repeated here.
2471  .sp  .sp
2472    PCRE_PARTIAL_HARD    PCRE_PARTIAL_HARD
2473    PCRE_PARTIAL_SOFT    PCRE_PARTIAL_SOFT
# Line 1956  is converted into PCRE_ERROR_PARTIAL if Line 2482  is converted into PCRE_ERROR_PARTIAL if
2482  there have been no complete matches, but there is still at least one matching  there have been no complete matches, but there is still at least one matching
2483  possibility. The portion of the string that was inspected when the longest  possibility. The portion of the string that was inspected when the longest
2484  partial match was found is set as the first matching string in both cases.  partial match was found is set as the first matching string in both cases.
2485    There is a more detailed discussion of partial and multi-segment matching, with
2486    examples, in the
2487    .\" HREF
2488    \fBpcrepartial\fP
2489    .\"
2490    documentation.
2491  .sp  .sp
2492    PCRE_DFA_SHORTEST    PCRE_DFA_SHORTEST
2493  .sp  .sp
# Line 1977  match. There is more discussion of this Line 2509  match. There is more discussion of this
2509  .\"  .\"
2510  documentation.  documentation.
2511  .  .
2512    .
2513  .SS "Successful returns from \fBpcre_dfa_exec()\fP"  .SS "Successful returns from \fBpcre_dfa_exec()\fP"
2514  .rs  .rs
2515  .sp  .sp
# Line 2008  returns data, even though the meaning of Line 2541  returns data, even though the meaning of
2541  The strings are returned in reverse order of length; that is, the longest  The strings are returned in reverse order of length; that is, the longest
2542  matching string is given first. If there were too many matches to fit into  matching string is given first. If there were too many matches to fit into
2543  \fIovector\fP, the yield of the function is zero, and the vector is filled with  \fIovector\fP, the yield of the function is zero, and the vector is filled with
2544  the longest matches.  the longest matches. Unlike \fBpcre_exec()\fP, \fBpcre_dfa_exec()\fP can use
2545    the entire \fIovector\fP for returning matched strings.
2546    .
2547  .  .
2548  .SS "Error returns from \fBpcre_dfa_exec()\fP"  .SS "Error returns from \fBpcre_dfa_exec()\fP"
2549  .rs  .rs
# Line 2037  group. These are not supported. Line 2572  group. These are not supported.
2572    PCRE_ERROR_DFA_UMLIMIT    (-18)    PCRE_ERROR_DFA_UMLIMIT    (-18)
2573  .sp  .sp
2574  This return is given if \fBpcre_dfa_exec()\fP is called with an \fIextra\fP  This return is given if \fBpcre_dfa_exec()\fP is called with an \fIextra\fP
2575  block that contains a setting of the \fImatch_limit\fP field. This is not  block that contains a setting of the \fImatch_limit\fP or
2576  supported (it is meaningless).  \fImatch_limit_recursion\fP fields. This is not supported (these fields are
2577    meaningless for DFA matching).
2578  .sp  .sp
2579    PCRE_ERROR_DFA_WSSIZE     (-19)    PCRE_ERROR_DFA_WSSIZE     (-19)
2580  .sp  .sp
# Line 2056  extremely rare, as a vector of size 1000 Line 2592  extremely rare, as a vector of size 1000
2592  .SH "SEE ALSO"  .SH "SEE ALSO"
2593  .rs  .rs
2594  .sp  .sp
2595  \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),  \fBpcre16\fP(3), \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
2596  \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),  \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
2597  \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).  \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
2598  .  .
# Line 2075  Cambridge CB2 3QH, England. Line 2611  Cambridge CB2 3QH, England.
2611  .rs  .rs
2612  .sp  .sp
2613  .nf  .nf
2614  Last updated: 03 October 2009  Last updated: 07 January 2012
2615  Copyright (c) 1997-2009 University of Cambridge.  Copyright (c) 1997-2012 University of Cambridge.
2616  .fi  .fi

Legend:
Removed from v.461  
changed lines
  Added in v.859

  ViewVC Help
Powered by ViewVC 1.1.5