/[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 566 by ph10, Wed Nov 3 18:32:55 2010 UTC revision 1055 by chpe, Tue Oct 16 15:53:30 2012 UTC
# Line 1  Line 1 
1  .TH PCREAPI 3  .TH PCREAPI 3 "07 September 2012" "PCRE 8.32"
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, 16-BIT AND 32-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. From release 8.FIXME, PCRE can also be compiled as a
143    library for handling 32-bit character strings. To avoid too much complication,
144    this document describes the 8-bit versions of the functions, with only
145    occasional references to the 16-bit and 32-bit libraries.
146    .P
147    The 16-bit functions operate in the same way as their 8-bit counterparts; they
148    just use different data types for their arguments and results, and their names
149    start with \fBpcre16_\fP instead of \fBpcre_\fP. For every option that has UTF8
150    in its name (for example, PCRE_UTF8), there is a corresponding 16-bit name with
151    UTF8 replaced by UTF16. This facility is in fact just cosmetic; the 16-bit
152    option names define the same bit values.
153    .P
154    The 32-bit functions operate in the same way as their 8-bit counterparts; they
155    just use different data types for their arguments and results, and their names
156    start with \fBpcre32_\fP instead of \fBpcre_\fP. For every option that has UTF8
157    in its name (for example, PCRE_UTF8), there is a corresponding 32-bit name with
158    UTF8 replaced by UTF32. This facility is in fact just cosmetic; the 32-bit
159    option names define the same bit values.
160    .P
161    References to bytes and UTF-8 in this document should be read as references to
162    16-bit data quantities and UTF-16 when using the 16-bit library, unless
163    specified otherwise. More details of the specific differences for the 16-bit
164    library are given in the
165    .\" HREF
166    \fBpcre16\fP
167    .\"
168    page.
169    .
170    .P
171    References to bytes and UTF-8 in this document should be read as references to
172    32-bit data quantities and UTF-32 when using the 32-bit library, unless
173    specified otherwise. More details of the specific differences for the 32-bit
174    library are given in the
175    .\" HREF
176    \fBpcre32\fP
177    .\"
178    page.
179    .
180    .
181  .SH "PCRE API OVERVIEW"  .SH "PCRE API OVERVIEW"
182  .rs  .rs
183  .sp  .sp
184  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
185  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
186  API. These are described in the  POSIX regular expression API, but they do not give access to all the
187    functionality. They are described in the
188  .\" HREF  .\" HREF
189  \fBpcreposix\fP  \fBpcreposix\fP
190  .\"  .\"
191  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++
192  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
193    documented in the
194  .\" HREF  .\" HREF
195  \fBpcrecpp\fP  \fBpcrecpp\fP
196  .\"  .\"
197  page.  page.
198  .P  .P
199  The native API C function prototypes are defined in the header file  The native API C function prototypes are defined in the header file
200  \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
201  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
202  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
203  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
204  Applications can use these to include support for different releases of PCRE.  for the library. Applications can use these to include support for different
205    releases of PCRE.
206  .P  .P
207  In a Windows environment, if you want to statically link an application program  In a Windows environment, if you want to statically link an application program
208  against a non-dll \fBpcre.a\fP file, you must define PCRE_STATIC before  against a non-dll \fBpcre.a\fP file, you must define PCRE_STATIC before
# Line 152  documentation, and the Line 224  documentation, and the
224  .\"  .\"
225  documentation describes how to compile and run it.  documentation describes how to compile and run it.
226  .P  .P
227    Just-in-time compiler support is an optional feature of PCRE that can be built
228    in appropriate hardware environments. It greatly speeds up the matching
229    performance of many patterns. Simple programs can easily request that it be
230    used if available, by setting an option that is ignored when it is not
231    relevant. More complicated programs might need to make use of the functions
232    \fBpcre_jit_stack_alloc()\fP, \fBpcre_jit_stack_free()\fP, and
233    \fBpcre_assign_jit_stack()\fP in order to control the JIT code's memory usage.
234    These functions are discussed in the
235    .\" HREF
236    \fBpcrejit\fP
237    .\"
238    documentation.
239    .P
240  A second matching function, \fBpcre_dfa_exec()\fP, which is not  A second matching function, \fBpcre_dfa_exec()\fP, which is not
241  Perl-compatible, is also provided. This uses a different algorithm for the  Perl-compatible, is also provided. This uses a different algorithm for the
242  matching. The alternative algorithm finds all possible matches (at a given  matching. The alternative algorithm finds all possible matches (at a given
# Line 186  specialist use. Most commonly, no specia Line 271  specialist use. Most commonly, no specia
271  internal tables that are generated when PCRE is built are used.  internal tables that are generated when PCRE is built are used.
272  .P  .P
273  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
274  compiled pattern; \fBpcre_info()\fP is an obsolete version that returns only  compiled pattern. The function \fBpcre_version()\fP returns a pointer to a
275  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.  
276  .P  .P
277  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
278  containing a compiled pattern. This is provided for the benefit of  containing a compiled pattern. This is provided for the benefit of
# Line 237  PCRE supports five different conventions Line 320  PCRE supports five different conventions
320  strings: a single CR (carriage return) character, a single LF (linefeed)  strings: a single CR (carriage return) character, a single LF (linefeed)
321  character, the two-character sequence CRLF, any of the three preceding, or any  character, the two-character sequence CRLF, any of the three preceding, or any
322  Unicode newline sequence. The Unicode newline sequences are the three just  Unicode newline sequence. The Unicode newline sequences are the three just
323  mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,  mentioned, plus the single characters VT (vertical tab, U+000B), FF (form feed,
324  U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS  U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
325  (paragraph separator, U+2029).  (paragraph separator, U+2029).
326  .P  .P
# Line 282  callout function pointed to by \fBpcre_c Line 365  callout function pointed to by \fBpcre_c
365  .P  .P
366  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
367  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.
368    .P
369    If the just-in-time optimization feature is being used, it needs separate
370    memory stack areas for each thread. See the
371    .\" HREF
372    \fBpcrejit\fP
373    .\"
374    documentation for more details.
375  .  .
376  .  .
377  .SH "SAVING PRECOMPILED PATTERNS FOR LATER USE"  .SH "SAVING PRECOMPILED PATTERNS FOR LATER USE"
# Line 293  which it was compiled. Details are given Line 383  which it was compiled. Details are given
383  .\" HREF  .\" HREF
384  \fBpcreprecompile\fP  \fBpcreprecompile\fP
385  .\"  .\"
386  documentation. However, compiling a regular expression with one version of PCRE  documentation, which includes a description of the
387  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
388  crashes.  expression with one version of PCRE for use with a different version is not
389    guaranteed to work and may cause crashes.
390  .  .
391  .  .
392  .SH "CHECKING BUILD-TIME OPTIONS"  .SH "CHECKING BUILD-TIME OPTIONS"
# Line 312  documentation has more details about the Line 403  documentation has more details about the
403  .P  .P
404  The first argument for \fBpcre_config()\fP is an integer, specifying which  The first argument for \fBpcre_config()\fP is an integer, specifying which
405  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
406  which the information is placed. The following information is available:  which the information is placed. The returned value is zero on success, or the
407    negative error code PCRE_ERROR_BADOPTION if the value in the first argument is
408    not recognized. The following information is available:
409  .sp  .sp
410    PCRE_CONFIG_UTF8    PCRE_CONFIG_UTF8
411  .sp  .sp
412  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;
413  otherwise it is set to zero.  otherwise it is set to zero. This value should normally be given to the 8-bit
414    version of this function, \fBpcre_config()\fP. If it is given to the 16-bit
415    or 32-bit version of this function, the result is PCRE_ERROR_BADOPTION.
416    .sp
417      PCRE_CONFIG_UTF16
418    .sp
419    The output is an integer that is set to one if UTF-16 support is available;
420    otherwise it is set to zero. This value should normally be given to the 16-bit
421    version of this function, \fBpcre16_config()\fP. If it is given to the 8-bit
422    or 32-bit version of this function, the result is PCRE_ERROR_BADOPTION.
423    .sp
424      PCRE_CONFIG_UTF32
425    .sp
426    The output is an integer that is set to one if UTF-32 support is available;
427    otherwise it is set to zero. This value should normally be given to the 32-bit
428    version of this function, \fBpcre32_config()\fP. If it is given to the 8-bit
429    or 16-bit version of this function, the result is PCRE_ERROR_BADOPTION.
430  .sp  .sp
431    PCRE_CONFIG_UNICODE_PROPERTIES    PCRE_CONFIG_UNICODE_PROPERTIES
432  .sp  .sp
433  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
434  properties is available; otherwise it is set to zero.  properties is available; otherwise it is set to zero.
435  .sp  .sp
436      PCRE_CONFIG_JIT
437    .sp
438    The output is an integer that is set to one if support for just-in-time
439    compiling is available; otherwise it is set to zero.
440    .sp
441      PCRE_CONFIG_JITTARGET
442    .sp
443    The output is a pointer to a zero-terminated "const char *" string. If JIT
444    support is available, the string contains the name of the architecture for
445    which the JIT compiler is configured, for example "x86 32bit (little endian +
446    unaligned)". If JIT support is not available, the result is NULL.
447    .sp
448    PCRE_CONFIG_NEWLINE    PCRE_CONFIG_NEWLINE
449  .sp  .sp
450  The output is an integer whose value specifies the default character sequence  The output is an integer whose value specifies the default character sequence
451  that is recognized as meaning "newline". The four values that are supported  that is recognized as meaning "newline". The values that are supported in
452  are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, and -1 for ANY.  ASCII/Unicode environments are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for
453  Though they are derived from ASCII, the same values are returned in EBCDIC  ANYCRLF, and -1 for ANY. In EBCDIC environments, CR, ANYCRLF, and ANY yield the
454  environments. The default should normally correspond to the standard sequence  same values. However, the value for LF is normally 21, though some EBCDIC
455  for your operating system.  environments use 37. The corresponding values for CRLF are 3349 and 3365. The
456    default should normally correspond to the standard sequence for your operating
457    system.
458  .sp  .sp
459    PCRE_CONFIG_BSR    PCRE_CONFIG_BSR
460  .sp  .sp
# Line 343  or CRLF. The default can be overridden w Line 466  or CRLF. The default can be overridden w
466    PCRE_CONFIG_LINK_SIZE    PCRE_CONFIG_LINK_SIZE
467  .sp  .sp
468  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
469  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
470  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
471  matching. The default value of 2 is sufficient for all but the most massive  a number of bytes. For the 32-bit library, the value is either 2 or 4 and is
472  patterns, since it allows the compiled pattern to be up to 64K in size.  still a number of bytes. The default value of 2 is sufficient for all but the
473    most massive patterns, since it allows the compiled pattern to be up to 64K in
474    size. Larger values allow larger regular expressions to be compiled, at the
475    expense of slower matching.
476  .sp  .sp
477    PCRE_CONFIG_POSIX_MALLOC_THRESHOLD    PCRE_CONFIG_POSIX_MALLOC_THRESHOLD
478  .sp  .sp
# Line 428  within the pattern (see the detailed des Line 554  within the pattern (see the detailed des
554  documentation). For those options that can be different in different parts of  documentation). For those options that can be different in different parts of
555  the pattern, the contents of the \fIoptions\fP argument specifies their  the pattern, the contents of the \fIoptions\fP argument specifies their
556  settings at the start of compilation and execution. The PCRE_ANCHORED,  settings at the start of compilation and execution. The PCRE_ANCHORED,
557  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
558  of matching as well as at compile time.  PCRE_NO_START_OPTIMIZE options can be set at the time of matching as well as at
559    compile time.
560  .P  .P
561  If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.  If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.
562  Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns  Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns
563  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
564  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
565  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
566  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
567  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
568  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
569  carried out when the whole pattern has been scanned; in this case the offset is  that of the first byte of the failing character.
570  set to the end of the pattern.  .P
571    Some errors are not detected until the whole pattern has been scanned; in these
572    cases, the offset passed back is the length of the pattern. Note that the
573    offset is in bytes, not characters, even in UTF-8 mode. It may sometimes point
574    into the middle of a UTF-8 character.
575  .P  .P
576  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
577  \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 519  pattern. Line 650  pattern.
650  .sp  .sp
651    PCRE_DOTALL    PCRE_DOTALL
652  .sp  .sp
653  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
654  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
655  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,
656  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
657  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
658  the setting of this option.  (?s) option setting. A negative class such as [^a] always matches newline
659    characters, independent of the setting of this option.
660  .sp  .sp
661    PCRE_DUPNAMES    PCRE_DUPNAMES
662  .sp  .sp
# Line 539  documentation. Line 671  documentation.
671  .sp  .sp
672    PCRE_EXTENDED    PCRE_EXTENDED
673  .sp  .sp
674  If this bit is set, whitespace data characters in the pattern are totally  If this bit is set, white space data characters in the pattern are totally
675  ignored except when escaped or inside a character class. Whitespace does not  ignored except when escaped or inside a character class. White space does not
676  include the VT character (code 11). In addition, characters between an  include the VT character (code 11). In addition, characters between an
677  unescaped # outside a character class and the next newline, inclusive, are also  unescaped # outside a character class and the next newline, inclusive, are also
678  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
679  pattern by a (?x) option setting.  pattern by a (?x) option setting.
680  .P  .P
681    Which characters are interpreted as newlines is controlled by the options
682    passed to \fBpcre_compile()\fP or by a special sequence at the start of the
683    pattern, as described in the section entitled
684    .\" HTML <a href="pcrepattern.html#newlines">
685    .\" </a>
686    "Newline conventions"
687    .\"
688    in the \fBpcrepattern\fP documentation. Note that the end of this type of
689    comment is a literal newline sequence in the pattern; escape sequences that
690    happen to represent a newline do not count.
691    .P
692  This option makes it possible to include comments inside complicated patterns.  This option makes it possible to include comments inside complicated patterns.
693  Note, however, that this applies only to data characters. Whitespace characters  Note, however, that this applies only to data characters. White space characters
694  may never appear within special character sequences in a pattern, for example  may never appear within special character sequences in a pattern, for example
695  within the sequence (?( which introduces a conditional subpattern.  within the sequence (?( that introduces a conditional subpattern.
696  .sp  .sp
697    PCRE_EXTRA    PCRE_EXTRA
698  .sp  .sp
# Line 582  character). Thus, the pattern AB]CD beco Line 725  character). Thus, the pattern AB]CD beco
725  string (by default this causes the current matching alternative to fail). A  string (by default this causes the current matching alternative to fail). A
726  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
727  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.
728    .P
729    (3) \eU matches an upper case "U" character; by default \eU causes a compile
730    time error (Perl uses \eU to upper case subsequent characters).
731    .P
732    (4) \eu matches a lower case "u" character unless it is followed by four
733    hexadecimal digits, in which case the hexadecimal number defines the code point
734    to match. By default, \eu causes a compile time error (Perl uses it to upper
735    case the following character).
736    .P
737    (5) \ex matches a lower case "x" character unless it is followed by two
738    hexadecimal digits, in which case the hexadecimal number defines the code point
739    to match. By default, as in Perl, a hexadecimal number is always expected after
740    \ex, but it may have zero, one, or two digits (so, for example, \exz matches a
741    binary zero character followed by z).
742  .sp  .sp
743    PCRE_MULTILINE    PCRE_MULTILINE
744  .sp  .sp
# Line 611  indicated by a single character (CR or L Line 768  indicated by a single character (CR or L
768  PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character  PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character
769  CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three  CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three
770  preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies  preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies
771  that any Unicode newline sequence should be recognized. The Unicode newline  that any Unicode newline sequence should be recognized.
772  sequences are the three just mentioned, plus the single characters VT (vertical  .P
773  tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line  In an ASCII/Unicode environment, the Unicode newline sequences are the three
774  separator, U+2028), and PS (paragraph separator, U+2029). The last two are  just mentioned, plus the single characters VT (vertical tab, U+000B), FF (form
775    feed, U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
776    (paragraph separator, U+2029). For the 8-bit library, the last two are
777  recognized only in UTF-8 mode.  recognized only in UTF-8 mode.
778  .P  .P
779    When PCRE is compiled to run in an EBCDIC (mainframe) environment, the code for
780    CR is 0x0d, the same as ASCII. However, the character code for LF is normally
781    0x15, though in some EBCDIC environments 0x25 is used. Whichever of these is
782    not LF is made to correspond to Unicode's NEL character. EBCDIC codes are all
783    less than 256. For more details, see the
784    .\" HREF
785    \fBpcrebuild\fP
786    .\"
787    documentation.
788    .P
789  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
790  as a number, giving eight possibilities. Currently only six are used (default  as a number, giving eight possibilities. Currently only six are used (default
791  plus the five values above). This means that if you set more than one newline  plus the five values above). This means that if you set more than one newline
# Line 624  option, the combination may or may not b Line 793  option, the combination may or may not b
793  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
794  other combinations may yield unused numbers and cause an error.  other combinations may yield unused numbers and cause an error.
795  .P  .P
796  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
797  pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character  compiling is when PCRE_EXTENDED is set. CR and LF are white space characters,
798  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
799  line break sequence. In other circumstances, line break sequences are treated  indicates a comment that lasts until after the next line break sequence. In
800  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
801  as whitespace characters and are therefore ignored.  data.
802  .P  .P
803  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
804  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 642  were followed by ?: but named parenthese Line 811  were followed by ?: but named parenthese
811  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
812  in Perl.  in Perl.
813  .sp  .sp
814      NO_START_OPTIMIZE
815    .sp
816    This is an option that acts at matching time; that is, it is really an option
817    for \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP. If it is set at compile time,
818    it is remembered with the compiled pattern and assumed at matching time. For
819    details see the discussion of PCRE_NO_START_OPTIMIZE
820    .\" HTML <a href="#execoptions">
821    .\" </a>
822    below.
823    .\"
824    .sp
825    PCRE_UCP    PCRE_UCP
826  .sp  .sp
827  This option changes the way PCRE processes \eb, \ed, \es, \ew, and some of the  This option changes the way PCRE processes \eB, \eb, \eD, \ed, \eS, \es, \eW,
828  POSIX character classes. By default, only ASCII characters are recognized, but  \ew, and some of the POSIX character classes. By default, only ASCII characters
829  if PCRE_UCP is set, Unicode properties are used instead to classify characters.  are recognized, but if PCRE_UCP is set, Unicode properties are used instead to
830  More details are given in the section on  classify characters. More details are given in the section on
831  .\" HTML <a href="pcre.html#genericchartypes">  .\" HTML <a href="pcre.html#genericchartypes">
832  .\" </a>  .\" </a>
833  generic character types  generic character types
# Line 669  with Perl. It can also be set by a (?U) Line 849  with Perl. It can also be set by a (?U)
849    PCRE_UTF8    PCRE_UTF8
850  .sp  .sp
851  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
852  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
853  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
854  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
855  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  
856  .\" HREF  .\" HREF
857  \fBpcre\fP  \fBpcreunicode\fP
858  .\"  .\"
859  page.  page.
860  .sp  .sp
861    PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
862  .sp  .sp
863  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
864  automatically checked. There is a discussion about the  string is automatically checked. There is a discussion about the
865  .\" HTML <a href="pcre.html#utf8strings">  .\" HTML <a href="pcreunicode.html#utf8strings">
866  .\" </a>  .\" </a>
867  validity of UTF-8 strings  validity of UTF-8 strings
868  .\"  .\"
869  in the main  in the
870  .\" HREF  .\" HREF
871  \fBpcre\fP  \fBpcreunicode\fP
872  .\"  .\"
873  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
874  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
875  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.
876  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
877  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
878  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
879  the UTF-8 validity checking of subject strings.  validity checking of subject strings.
880  .  .
881  .  .
882  .SH "COMPILATION ERROR CODES"  .SH "COMPILATION ERROR CODES"
# Line 709  the UTF-8 validity checking of subject s Line 884  the UTF-8 validity checking of subject s
884  .sp  .sp
885  The following table lists the error codes than may be returned by  The following table lists the error codes than may be returned by
886  \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
887  both compiling functions. As PCRE has developed, some error codes have fallen  both compiling functions. Note that error messages are always 8-bit ASCII
888  out of use. To avoid confusion, they have not been re-used.  strings, even in 16-bit or 32-bit mode. As PCRE has developed, some error codes
889    have fallen out of use. To avoid confusion, they have not been re-used.
890  .sp  .sp
891     0  no error     0  no error
892     1  \e at end of pattern     1  \e at end of pattern
# Line 744  out of use. To avoid confusion, they hav Line 920  out of use. To avoid confusion, they hav
920    29  (?R or (?[+-]digits must be followed by )    29  (?R or (?[+-]digits must be followed by )
921    30  unknown POSIX class name    30  unknown POSIX class name
922    31  POSIX collating elements are not supported    31  POSIX collating elements are not supported
923    32  this version of PCRE is not compiled with PCRE_UTF8 support    32  this version of PCRE is compiled without UTF support
924    33  [this code is not in use]    33  [this code is not in use]
925    34  character value in \ex{...} sequence is too large    34  character value in \ex{...} sequence is too large
926    35  invalid condition (?(0)    35  invalid condition (?(0)
927    36  \eC not allowed in lookbehind assertion    36  \eC not allowed in lookbehind assertion
928    37  PCRE does not support \eL, \el, \eN, \eU, or \eu    37  PCRE does not support \eL, \el, \eN{name}, \eU, or \eu
929    38  number after (?C is > 255    38  number after (?C is > 255
930    39  closing ) for (?C expected    39  closing ) for (?C expected
931    40  recursive call could loop indefinitely    40  recursive call could loop indefinitely
932    41  unrecognized character after (?P    41  unrecognized character after (?P
933    42  syntax error in subpattern name (missing terminator)    42  syntax error in subpattern name (missing terminator)
934    43  two named subpatterns have the same name    43  two named subpatterns have the same name
935    44  invalid UTF-8 string    44  invalid UTF-8 string (specifically UTF-8)
936    45  support for \eP, \ep, and \eX has not been compiled    45  support for \eP, \ep, and \eX has not been compiled
937    46  malformed \eP or \ep sequence    46  malformed \eP or \ep sequence
938    47  unknown property name after \eP or \ep    47  unknown property name after \eP or \ep
939    48  subpattern name is too long (maximum 32 characters)    48  subpattern name is too long (maximum 32 characters)
940    49  too many named subpatterns (maximum 10000)    49  too many named subpatterns (maximum 10000)
941    50  [this code is not in use]    50  [this code is not in use]
942    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
943    52  internal error: overran compiling workspace    52  internal error: overran compiling workspace
944    53  internal error: previously-checked referenced subpattern    53  internal error: previously-checked referenced subpattern
945          not found          not found
# Line 782  out of use. To avoid confusion, they hav Line 958  out of use. To avoid confusion, they hav
958    65  different names for subpatterns of the same number are    65  different names for subpatterns of the same number are
959          not allowed          not allowed
960    66  (*MARK) must have an argument    66  (*MARK) must have an argument
961    67  this version of PCRE is not compiled with PCRE_UCP support    67  this version of PCRE is not compiled with Unicode property
962            support
963      68  \ec must be followed by an ASCII character
964      69  \ek is not followed by a braced, angle-bracketed, or quoted name
965      70  internal error: unknown opcode in find_fixedlength()
966      71  \eN is not supported in a class
967      72  too many forward references
968      73  disallowed Unicode code point (>= 0xd800 && <= 0xdfff)
969      74  invalid UTF-16 string (specifically UTF-16)
970      75  name is too long in (*MARK), (*PRUNE), (*SKIP), or (*THEN)
971      76  character value in \eu.... sequence is too large
972      77  invalid UTF-32 string (specifically UTF-32)
973  .sp  .sp
974  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
975  be used if the limits were changed when PCRE was built.  be used if the limits were changed when PCRE was built.
976  .  .
977  .  .
978    .\" HTML <a name="studyingapattern"></a>
979  .SH "STUDYING A PATTERN"  .SH "STUDYING A PATTERN"
980  .rs  .rs
981  .sp  .sp
# Line 814  below Line 1002  below
1002  in the section on matching a pattern.  in the section on matching a pattern.
1003  .P  .P
1004  If studying the pattern does not produce any useful information,  If studying the pattern does not produce any useful information,
1005  \fBpcre_study()\fP returns NULL. In that circumstance, if the calling program  \fBpcre_study()\fP returns NULL by default. In that circumstance, if the
1006  wants to pass any of the other fields to \fBpcre_exec()\fP or  calling program wants to pass any of the other fields to \fBpcre_exec()\fP or
1007  \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. However,
1008  .P  if \fBpcre_study()\fP is called with the PCRE_STUDY_EXTRA_NEEDED option, it
1009  The second argument of \fBpcre_study()\fP contains option bits. At present, no  returns a \fBpcre_extra\fP block even if studying did not find any additional
1010  options are defined, and this argument should always be zero.  information. It may still return NULL, however, if an error occurs in
1011    \fBpcre_study()\fP.
1012    .P
1013    The second argument of \fBpcre_study()\fP contains option bits. There are three
1014    further options in addition to PCRE_STUDY_EXTRA_NEEDED:
1015    .sp
1016      PCRE_STUDY_JIT_COMPILE
1017      PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE
1018      PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE
1019    .sp
1020    If any of these are set, and the just-in-time compiler is available, the
1021    pattern is further compiled into machine code that executes much faster than
1022    the \fBpcre_exec()\fP interpretive matching function. If the just-in-time
1023    compiler is not available, these options are ignored. All undefined bits in the
1024    \fIoptions\fP argument must be zero.
1025    .P
1026    JIT compilation is a heavyweight optimization. It can take some time for
1027    patterns to be analyzed, and for one-off matches and simple patterns the
1028    benefit of faster execution might be offset by a much slower study time.
1029    Not all patterns can be optimized by the JIT compiler. For those that cannot be
1030    handled, matching automatically falls back to the \fBpcre_exec()\fP
1031    interpreter. For more details, see the
1032    .\" HREF
1033    \fBpcrejit\fP
1034    .\"
1035    documentation.
1036  .P  .P
1037  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
1038  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 828  static string that is part of the librar Line 1041  static string that is part of the librar
1041  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
1042  sure that it has run successfully.  sure that it has run successfully.
1043  .P  .P
1044  This is a typical call to \fBpcre_study\fP():  When you are finished with a pattern, you can free the memory used for the
1045    study data by calling \fBpcre_free_study()\fP. This function was added to the
1046    API for release 8.20. For earlier versions, the memory could be freed with
1047    \fBpcre_free()\fP, just like the pattern itself. This will still work in cases
1048    where JIT optimization is not used, but it is advisable to change to the new
1049    function when convenient.
1050    .P
1051    This is a typical way in which \fBpcre_study\fP() is used (except that in a
1052    real application there should be tests for errors):
1053  .sp  .sp
1054    pcre_extra *pe;    int rc;
1055    pe = pcre_study(    pcre *re;
1056      pcre_extra *sd;
1057      re = pcre_compile("pattern", 0, &error, &erroroffset, NULL);
1058      sd = pcre_study(
1059      re,             /* result of pcre_compile() */      re,             /* result of pcre_compile() */
1060      0,              /* no options exist */      0,              /* no options */
1061      &error);        /* set to NULL or points to a message */      &error);        /* set to NULL or points to a message */
1062      rc = pcre_exec(   /* see below for details of pcre_exec() options */
1063        re, sd, "subject", 7, 0, 0, ovector, 30);
1064      ...
1065      pcre_free_study(sd);
1066      pcre_free(re);
1067  .sp  .sp
1068  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
1069  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
1070  mean that there are any strings of that length that match, but it does  mean that there are any strings of that length that match, but it does
1071  guarantee that no shorter strings match. The value is used by  guarantee that no shorter strings match. The value is used to avoid wasting
1072  \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP to avoid wasting time by trying to  time by trying to match strings that are shorter than the lower bound. You can
1073  match strings that are shorter than the lower bound. You can find out the value  find out the value in a calling program via the \fBpcre_fullinfo()\fP function.
 in a calling program via the \fBpcre_fullinfo()\fP function.  
1074  .P  .P
1075  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
1076  single fixed starting character. A bitmap of possible starting bytes is  single fixed starting character. A bitmap of possible starting bytes is
1077  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
1078  matching.  matching. (In 16-bit mode, the bitmap is used for 16-bit values less than 256.
1079    In 32-bit mode, the bitmap is used for 32-bit values less than 256.)
1080  .P  .P
1081  The two optimizations just described can be disabled by setting the  These two optimizations apply to both \fBpcre_exec()\fP and
1082  PCRE_NO_START_OPTIMIZE option when calling \fBpcre_exec()\fP or  \fBpcre_dfa_exec()\fP, and the information is also used by the JIT compiler.
1083  \fBpcre_dfa_exec()\fP. You might want to do this if your pattern contains  The optimizations can be disabled by setting the PCRE_NO_START_OPTIMIZE option
1084  callouts, or make use of (*MARK), and you make use of these in cases where  when calling \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP, but if this is done,
1085  matching fails. See the discussion of PCRE_NO_START_OPTIMIZE  JIT execution is also disabled. You might want to do this if your pattern
1086    contains callouts or (*MARK) and you want to make use of these facilities in
1087    cases where matching fails. See the discussion of PCRE_NO_START_OPTIMIZE
1088  .\" HTML <a href="#execoptions">  .\" HTML <a href="#execoptions">
1089  .\" </a>  .\" </a>
1090  below.  below.
# Line 866  below. Line 1097  below.
1097  .sp  .sp
1098  PCRE handles caseless matching, and determines whether characters are letters,  PCRE handles caseless matching, and determines whether characters are letters,
1099  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
1100  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
1101  less than 128. By default, higher-valued codes never match escapes such as \ew  with codes less than 128. By default, higher-valued codes never match escapes
1102  or \ed, but they can be tested with \ep if PCRE is built with Unicode character  such as \ew or \ed, but they can be tested with \ep if PCRE is built with
1103  property support. Alternatively, the PCRE_UCP option can be set at compile  Unicode character property support. Alternatively, the PCRE_UCP option can be
1104  time; this causes \ew and friends to use Unicode property support instead of  set at compile time; this causes \ew and friends to use Unicode property
1105  built-in tables. The use of locales with Unicode is discouraged. If you are  support instead of built-in tables. The use of locales with Unicode is
1106  handling characters with codes greater than 128, you should either use UTF-8  discouraged. If you are handling characters with codes greater than 128, you
1107  and Unicode, or use locales, but not try to mix the two.  should either use UTF-8 and Unicode, or use locales, but not try to mix the
1108    two.
1109  .P  .P
1110  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
1111  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 918  one in which it was compiled. Passing ta Line 1150  one in which it was compiled. Passing ta
1150  below in the section on matching a pattern.  below in the section on matching a pattern.
1151  .  .
1152  .  .
1153    .\" HTML <a name="infoaboutpattern"></a>
1154  .SH "INFORMATION ABOUT A PATTERN"  .SH "INFORMATION ABOUT A PATTERN"
1155  .rs  .rs
1156  .sp  .sp
# Line 926  below in the section on matching a patte Line 1159  below in the section on matching a patte
1159  .B int \fIwhat\fP, void *\fIwhere\fP);  .B int \fIwhat\fP, void *\fIwhere\fP);
1160  .PP  .PP
1161  The \fBpcre_fullinfo()\fP function returns information about a compiled  The \fBpcre_fullinfo()\fP function returns information about a compiled
1162  pattern. It replaces the obsolete \fBpcre_info()\fP function, which is  pattern. It replaces the \fBpcre_info()\fP function, which was removed from the
1163  nevertheless retained for backwards compability (and is documented below).  library at version 8.30, after more than 10 years of obsolescence.
1164  .P  .P
1165  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
1166  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 936  information is required, and the fourth Line 1169  information is required, and the fourth
1169  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
1170  the following negative numbers:  the following negative numbers:
1171  .sp  .sp
1172    PCRE_ERROR_NULL       the argument \fIcode\fP was NULL    PCRE_ERROR_NULL           the argument \fIcode\fP was NULL
1173                          the argument \fIwhere\fP was NULL                              the argument \fIwhere\fP was NULL
1174    PCRE_ERROR_BADMAGIC   the "magic number" was not found    PCRE_ERROR_BADMAGIC       the "magic number" was not found
1175    PCRE_ERROR_BADOPTION  the value of \fIwhat\fP was invalid    PCRE_ERROR_BADENDIANNESS  the pattern was compiled with different
1176                                endianness
1177      PCRE_ERROR_BADOPTION      the value of \fIwhat\fP was invalid
1178  .sp  .sp
1179  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
1180  check against passing an arbitrary memory pointer. Here is a typical call of  check against passing an arbitrary memory pointer. The endianness error can
1181  \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
1182    a typical call of \fBpcre_fullinfo()\fP, to obtain the length of the compiled
1183    pattern:
1184  .sp  .sp
1185    int rc;    int rc;
1186    size_t length;    size_t length;
1187    rc = pcre_fullinfo(    rc = pcre_fullinfo(
1188      re,               /* result of pcre_compile() */      re,               /* result of pcre_compile() */
1189      pe,               /* result of pcre_study(), or NULL */      sd,               /* result of pcre_study(), or NULL */
1190      PCRE_INFO_SIZE,   /* what is required */      PCRE_INFO_SIZE,   /* what is required */
1191      &length);         /* where to put the data */      &length);         /* where to put the data */
1192  .sp  .sp
# Line 977  a NULL table pointer. Line 1214  a NULL table pointer.
1214  .sp  .sp
1215    PCRE_INFO_FIRSTBYTE    PCRE_INFO_FIRSTBYTE
1216  .sp  .sp
1217  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
1218  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,
1219  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
1220  still recognized for backwards compatibility.)  variable.
1221  .P  .P
1222  If there is a fixed first byte, for example, from a pattern such as  If there is a fixed first value, for example, the letter "c" from a pattern
1223  (cat|cow|coyote), its value is returned. Otherwise, if either  such as (cat|cow|coyote), its value is returned. In the 8-bit library, the
1224    value is always less than 256. In the 16-bit library the value can be up to
1225    0xffff. In the 32-bit library the value can be up to 0x10ffff.
1226    .P
1227    If there is no fixed first value, and if either
1228  .sp  .sp
1229  (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
1230  starts with "^", or  starts with "^", or
# Line 998  returned. For anchored patterns, -2 is r Line 1239  returned. For anchored patterns, -2 is r
1239    PCRE_INFO_FIRSTTABLE    PCRE_INFO_FIRSTTABLE
1240  .sp  .sp
1241  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
1242  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
1243  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
1244  fourth argument should point to an \fBunsigned char *\fP variable.  fourth argument should point to an \fBunsigned char *\fP variable.
1245  .sp  .sp
# Line 1014  Return 1 if the (?J) or (?-J) option set Line 1255  Return 1 if the (?J) or (?-J) option set
1255  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
1256  (?-J) set and unset the local PCRE_DUPNAMES option, respectively.  (?-J) set and unset the local PCRE_DUPNAMES option, respectively.
1257  .sp  .sp
1258      PCRE_INFO_JIT
1259    .sp
1260    Return 1 if the pattern was studied with one of the JIT options, and
1261    just-in-time compiling was successful. The fourth argument should point to an
1262    \fBint\fP variable. A return value of 0 means that JIT support is not available
1263    in this version of PCRE, or that the pattern was not studied with a JIT option,
1264    or that the JIT compiler could not handle this particular pattern. See the
1265    .\" HREF
1266    \fBpcrejit\fP
1267    .\"
1268    documentation for details of what can and cannot be handled.
1269    .sp
1270      PCRE_INFO_JITSIZE
1271    .sp
1272    If the pattern was successfully studied with a JIT option, return the size of
1273    the JIT compiled code, otherwise return zero. The fourth argument should point
1274    to a \fBsize_t\fP variable.
1275    .sp
1276    PCRE_INFO_LASTLITERAL    PCRE_INFO_LASTLITERAL
1277  .sp  .sp
1278  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
1279  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
1280  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
1281  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
1282  follows something of variable length. For example, for the pattern  only if it follows something of variable length. For example, for the pattern
1283  /^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
1284  is -1.  is -1.
1285  .sp  .sp
1286      PCRE_INFO_MAXLOOKBEHIND
1287    .sp
1288    Return the number of characters (NB not bytes) in the longest lookbehind
1289    assertion in the pattern. Note that the simple assertions \eb and \eB require a
1290    one-character lookbehind. This information is useful when doing multi-segment
1291    matching using the partial matching facilities.
1292    .sp
1293    PCRE_INFO_MINLENGTH    PCRE_INFO_MINLENGTH
1294  .sp  .sp
1295  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
1296  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
1297  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
1298  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
1299  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
1300  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
1301  that does match is at least that long.  that does match is at least that long.
# Line 1052  The map consists of a number of fixed-si Line 1318  The map consists of a number of fixed-si
1318  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
1319  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
1320  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
1321  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
1322  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,
1323  rest of the entry is the corresponding name, zero terminated.  most significant byte first. In the 16-bit library, the pointer points to
1324    16-bit data units, the first of which contains the parenthesis number.
1325    In the 32-bit library, the pointer points to 32-bit data units, the first of
1326    which contains the parenthesis number. The rest
1327    of the entry is the corresponding name, zero terminated.
1328  .P  .P
1329  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
1330  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 1073  table in the order in which they were fo Line 1343  table in the order in which they were fo
1343  necessarily the case because later subpatterns may have lower numbers.  necessarily the case because later subpatterns may have lower numbers.
1344  .P  .P
1345  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
1346  (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
1347  ignored):  space - including newlines - is ignored):
1348  .sp  .sp
1349  .\" JOIN  .\" JOIN
1350    (?<date> (?<year>(\ed\ed)?\ed\ed) -    (?<date> (?<year>(\ed\ed)?\ed\ed) -
# Line 1129  For such patterns, the PCRE_ANCHORED bit Line 1399  For such patterns, the PCRE_ANCHORED bit
1399  .sp  .sp
1400    PCRE_INFO_SIZE    PCRE_INFO_SIZE
1401  .sp  .sp
1402  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
1403  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
1404  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
1405  variable.  \fBpcre_compile()\fP. The value that is passed as the argument to
1406    \fBpcre_malloc()\fP when \fBpcre_compile()\fP is getting memory in which to
1407    place the compiled data is the value returned by this option plus the size of
1408    the \fBpcre\fP structure. Studying a compiled pattern, with or without JIT,
1409    does not alter the value returned by this option.
1410  .sp  .sp
1411    PCRE_INFO_STUDYSIZE    PCRE_INFO_STUDYSIZE
1412  .sp  .sp
1413  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
1414  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  
1415  study data, zero is returned. The fourth argument should point to a  study data, zero is returned. The fourth argument should point to a
1416  \fBsize_t\fP variable.  \fBsize_t\fP variable. The \fIstudy_data\fP field is set by \fBpcre_study()\fP
1417  .  to record information that will speed up matching (see the section entitled
1418  .  .\" HTML <a href="#studyingapattern">
1419  .SH "OBSOLETE INFO FUNCTION"  .\" </a>
1420  .rs  "Studying a pattern"
1421  .sp  .\"
1422  .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
1423  .B *\fIfirstcharptr\fP);  is made available via this option so that it can be saved and restored (see the
1424  .PP  .\" HREF
1425  The \fBpcre_info()\fP function is now obsolete because its interface is too  \fBpcreprecompile\fP
1426  restrictive to return all the available data about a compiled pattern. New  .\"
1427  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).  
1428  .  .
1429  .  .
1430  .SH "REFERENCE COUNTS"  .SH "REFERENCE COUNTS"
# Line 1203  is different. (This seems a highly unlik Line 1462  is different. (This seems a highly unlik
1462  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
1463  compiled pattern, which is passed in the \fIcode\fP argument. If the  compiled pattern, which is passed in the \fIcode\fP argument. If the
1464  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
1465  \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
1466  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
1467  also an alternative matching function, which is described  different subject strings with the same pattern.
1468    .P
1469    This function is the main matching facility of the library, and it operates in
1470    a Perl-like manner. For specialist use there is also an alternative matching
1471    function, which is described
1472  .\" HTML <a href="#dfamatch">  .\" HTML <a href="#dfamatch">
1473  .\" </a>  .\" </a>
1474  below  below
# Line 1236  Here is an example of a simple call to \ Line 1499  Here is an example of a simple call to \
1499      ovector,        /* vector of integers for substring information */      ovector,        /* vector of integers for substring information */
1500      30);            /* number of elements (NOT size in bytes) */      30);            /* number of elements (NOT size in bytes) */
1501  .  .
1502    .
1503  .\" HTML <a name="extradata"></a>  .\" HTML <a name="extradata"></a>
1504  .SS "Extra data for \fBpcre_exec()\fR"  .SS "Extra data for \fBpcre_exec()\fR"
1505  .rs  .rs
# Line 1248  fields (not necessarily in this order): Line 1512  fields (not necessarily in this order):
1512  .sp  .sp
1513    unsigned long int \fIflags\fP;    unsigned long int \fIflags\fP;
1514    void *\fIstudy_data\fP;    void *\fIstudy_data\fP;
1515      void *\fIexecutable_jit\fP;
1516    unsigned long int \fImatch_limit\fP;    unsigned long int \fImatch_limit\fP;
1517    unsigned long int \fImatch_limit_recursion\fP;    unsigned long int \fImatch_limit_recursion\fP;
1518    void *\fIcallout_data\fP;    void *\fIcallout_data\fP;
1519    const unsigned char *\fItables\fP;    const unsigned char *\fItables\fP;
1520    unsigned char **\fImark\fP;    unsigned char **\fImark\fP;
1521  .sp  .sp
1522  The \fIflags\fP field is a bitmap that specifies which of the other fields  In the 16-bit version of this structure, the \fImark\fP field has type
1523  are set. The flag bits are:  "PCRE_UCHAR16 **".
1524  .sp  .sp
1525    PCRE_EXTRA_STUDY_DATA  In the 32-bit version of this structure, the \fImark\fP field has type
1526    "PCRE_UCHAR32 **".
1527    .P
1528    The \fIflags\fP field is used to specify which of the other fields are set. The
1529    flag bits are:
1530    .sp
1531      PCRE_EXTRA_CALLOUT_DATA
1532      PCRE_EXTRA_EXECUTABLE_JIT
1533      PCRE_EXTRA_MARK
1534    PCRE_EXTRA_MATCH_LIMIT    PCRE_EXTRA_MATCH_LIMIT
1535    PCRE_EXTRA_MATCH_LIMIT_RECURSION    PCRE_EXTRA_MATCH_LIMIT_RECURSION
1536    PCRE_EXTRA_CALLOUT_DATA    PCRE_EXTRA_STUDY_DATA
1537    PCRE_EXTRA_TABLES    PCRE_EXTRA_TABLES
   PCRE_EXTRA_MARK  
1538  .sp  .sp
1539  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
1540  \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
1541  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
1542  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 other
1543    fields and their corresponding flag bits.
1544  .P  .P
1545  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
1546  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,
1547  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
1548  classic example is a pattern that uses nested unlimited repeats.  classic example is a pattern that uses nested unlimited repeats.
1549  .P  .P
1550  Internally, PCRE uses a function called \fBmatch()\fP which it calls repeatedly  Internally, \fBpcre_exec()\fP uses a function called \fBmatch()\fP, which it
1551  (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
1552  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
1553  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
1554  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
1555  string.  in the subject string.
1556    .P
1557    When \fBpcre_exec()\fP is called with a pattern that was successfully studied
1558    with a JIT option, the way that the matching is executed is entirely different.
1559    However, there is still the possibility of runaway matching that goes on for a
1560    very long time, and so the \fImatch_limit\fP value is also used in this case
1561    (but in a different way) to limit how long the matching can continue.
1562  .P  .P
1563  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
1564  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 1294  limits the depth of recursion. The recur Line 1573  limits the depth of recursion. The recur
1573  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.
1574  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.
1575  .P  .P
1576  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
1577  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
1578  amount of heap memory that can be used.  stack, the amount of heap memory that can be used. This limit is not relevant,
1579    and is ignored, when matching is done using JIT compiled code.
1580  .P  .P
1581  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
1582  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 1327  called. See the Line 1607  called. See the
1607  documentation for a discussion of saving compiled patterns for later use.  documentation for a discussion of saving compiled patterns for later use.
1608  .P  .P
1609  If PCRE_EXTRA_MARK is set in the \fIflags\fP field, the \fImark\fP field must  If PCRE_EXTRA_MARK is set in the \fIflags\fP field, the \fImark\fP field must
1610  be set to point to a \fBchar *\fP variable. If the pattern contains any  be set to point to a suitable variable. If the pattern contains any
1611  backtracking control verbs such as (*MARK:NAME), and the execution ends up with  backtracking control verbs such as (*MARK:NAME), and the execution ends up with
1612  a name to pass back, a pointer to the name string (zero terminated) is placed  a name to pass back, a pointer to the name string (zero terminated) is placed
1613  in the variable pointed to by the \fImark\fP field. The names are within the  in the variable pointed to by the \fImark\fP field. The names are within the
1614  compiled pattern; if you wish to retain such a name you must copy it before  compiled pattern; if you wish to retain such a name you must copy it before
1615  freeing the memory of a compiled pattern. If there is no name to pass back, the  freeing the memory of a compiled pattern. If there is no name to pass back, the
1616  variable pointed to by the \fImark\fP field set to NULL. For details of the  variable pointed to by the \fImark\fP field is set to NULL. For details of the
1617  backtracking control verbs, see the section entitled  backtracking control verbs, see the section entitled
1618  .\" HTML <a href="pcrepattern#backtrackcontrol">  .\" HTML <a href="pcrepattern#backtrackcontrol">
1619  .\" </a>  .\" </a>
# Line 1353  documentation. Line 1633  documentation.
1633  The unused bits of the \fIoptions\fP argument for \fBpcre_exec()\fP must be  The unused bits of the \fIoptions\fP argument for \fBpcre_exec()\fP must be
1634  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,
1635  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART,  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART,
1636  PCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_SOFT, and  PCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_HARD, and
1637  PCRE_PARTIAL_HARD.  PCRE_PARTIAL_SOFT.
1638    .P
1639    If the pattern was successfully studied with one of the just-in-time (JIT)
1640    compile options, the only supported options for JIT execution are
1641    PCRE_NO_UTF8_CHECK, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY,
1642    PCRE_NOTEMPTY_ATSTART, PCRE_PARTIAL_HARD, and PCRE_PARTIAL_SOFT. If an
1643    unsupported option is used, JIT execution is disabled and the normal
1644    interpretive code in \fBpcre_exec()\fP is run.
1645  .sp  .sp
1646    PCRE_ANCHORED    PCRE_ANCHORED
1647  .sp  .sp
# Line 1450  the Line 1737  the
1737  .\" HREF  .\" HREF
1738  \fBpcredemo\fP  \fBpcredemo\fP
1739  .\"  .\"
1740  sample program. In the most general case, you have to check to see if the  sample program. In the most general case, you have to check to see if the
1741  newline convention recognizes CRLF as a newline, and if so, and the current  newline convention recognizes CRLF as a newline, and if so, and the current
1742  character is CR followed by LF, advance the starting offset by two characters  character is CR followed by LF, advance the starting offset by two characters
1743  instead of one.  instead of one.
1744  .sp  .sp
# Line 1471  a pre-scan of the subject that takes pla Line 1758  a pre-scan of the subject that takes pla
1758  The PCRE_NO_START_OPTIMIZE option disables the start-up optimizations, possibly  The PCRE_NO_START_OPTIMIZE option disables the start-up optimizations, possibly
1759  causing performance to suffer, but ensuring that in cases where the result is  causing performance to suffer, but ensuring that in cases where the result is
1760  "no match", the callouts do occur, and that items such as (*COMMIT) and (*MARK)  "no match", the callouts do occur, and that items such as (*COMMIT) and (*MARK)
1761  are considered at every possible starting position in the subject string.  are considered at every possible starting position in the subject string. If
1762    PCRE_NO_START_OPTIMIZE is set at compile time, it cannot be unset at matching
1763    time. The use of PCRE_NO_START_OPTIMIZE disables JIT execution; when it is set,
1764    matching is always done using interpretively.
1765    .P
1766  Setting PCRE_NO_START_OPTIMIZE can change the outcome of a matching operation.  Setting PCRE_NO_START_OPTIMIZE can change the outcome of a matching operation.
1767  Consider the pattern  Consider the pattern
1768  .sp  .sp
# Line 1503  returned. Line 1794  returned.
1794  .sp  .sp
1795  When PCRE_UTF8 is set at compile time, the validity of the subject as a UTF-8  When PCRE_UTF8 is set at compile time, the validity of the subject as a UTF-8
1796  string is automatically checked when \fBpcre_exec()\fP is subsequently called.  string is automatically checked when \fBpcre_exec()\fP is subsequently called.
1797  The value of \fIstartoffset\fP is also checked to ensure that it points to the  The entire string is checked before any other processing takes place. The value
1798  start of a UTF-8 character. There is a discussion about the validity of UTF-8  of \fIstartoffset\fP is also checked to ensure that it points to the start of a
1799  strings in the  UTF-8 character. There is a discussion about the
1800  .\" HTML <a href="pcre.html#utf8strings">  .\" HTML <a href="pcreunicode.html#utf8strings">
1801  .\" </a>  .\" </a>
1802  section on UTF-8 support  validity of UTF-8 strings
1803  .\"  .\"
1804  in the main  in the
1805  .\" HREF  .\" HREF
1806  \fBpcre\fP  \fBpcreunicode\fP
1807  .\"  .\"
1808  page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_exec()\fP returns  page. If an invalid sequence of bytes is found, \fBpcre_exec()\fP returns the
1809  the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP contains an invalid value,  error PCRE_ERROR_BADUTF8 or, if PCRE_PARTIAL_HARD is set and the problem is a
1810  PCRE_ERROR_BADUTF8_OFFSET is returned.  truncated character at the end of the subject, PCRE_ERROR_SHORTUTF8. In both
1811    cases, information about the precise nature of the error may also be returned
1812    (see the descriptions of these errors in the section entitled \fIError return
1813    values from\fP \fBpcre_exec()\fP
1814    .\" HTML <a href="#errorlist">
1815    .\" </a>
1816    below).
1817    .\"
1818    If \fIstartoffset\fP contains a value that does not point to the start of a
1819    UTF-8 character (or to the end of the subject), PCRE_ERROR_BADUTF8_OFFSET is
1820    returned.
1821  .P  .P
1822  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
1823  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
1824  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
1825  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
1826  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
1827  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
1828  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
1829  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
1830  UTF-8 character, is undefined. Your program may crash.  undefined. Your program may crash.
1831  .sp  .sp
1832    PCRE_PARTIAL_HARD    PCRE_PARTIAL_HARD
1833    PCRE_PARTIAL_SOFT    PCRE_PARTIAL_SOFT
# Line 1544  but only if no complete match can be fou Line 1845  but only if no complete match can be fou
1845  If PCRE_PARTIAL_HARD is set, it overrides PCRE_PARTIAL_SOFT. In this case, if a  If PCRE_PARTIAL_HARD is set, it overrides PCRE_PARTIAL_SOFT. In this case, if a
1846  partial match is found, \fBpcre_exec()\fP immediately returns  partial match is found, \fBpcre_exec()\fP immediately returns
1847  PCRE_ERROR_PARTIAL, without considering any other alternatives. In other words,  PCRE_ERROR_PARTIAL, without considering any other alternatives. In other words,
1848  when PCRE_PARTIAL_HARD is set, a partial match is considered to be more  when PCRE_PARTIAL_HARD is set, a partial match is considered to be more
1849  important that an alternative complete match.  important that an alternative complete match.
1850  .P  .P
1851  In both cases, the portion of the string that was inspected when the partial  In both cases, the portion of the string that was inspected when the partial
# Line 1555  discussion of partial and multi-segment Line 1856  discussion of partial and multi-segment
1856  .\"  .\"
1857  documentation.  documentation.
1858  .  .
1859    .
1860  .SS "The string to be matched by \fBpcre_exec()\fP"  .SS "The string to be matched by \fBpcre_exec()\fP"
1861  .rs  .rs
1862  .sp  .sp
1863  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
1864  \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
1865  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
1866  a UTF-8 character. Unlike the pattern string, the subject may contain binary  subject, \fBpcre_exec()\fP returns PCRE_ERROR_BADOFFSET. When the starting
1867  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,
1868  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
1869    point to the start of a UTF-8 character (or the end of the subject). Unlike the
1870    pattern string, the subject may contain binary zero bytes.
1871  .P  .P
1872  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
1873  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 1583  start of the subject, which is deemed to Line 1887  start of the subject, which is deemed to
1887  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
1888  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.
1889  .P  .P
1890    Finding all the matches in a subject is tricky when the pattern can match an
1891    empty string. It is possible to emulate Perl's /g behaviour by first trying the
1892    match again at the same offset, with the PCRE_NOTEMPTY_ATSTART and
1893    PCRE_ANCHORED options, and then if that fails, advancing the starting offset
1894    and trying an ordinary match again. There is some code that demonstrates how to
1895    do this in the
1896    .\" HREF
1897    \fBpcredemo\fP
1898    .\"
1899    sample program. In the most general case, you have to check to see if the
1900    newline convention recognizes CRLF as a newline, and if so, and the current
1901    character is CR followed by LF, advance the starting offset by two characters
1902    instead of one.
1903    .P
1904  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
1905  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
1906  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.
1907  .  .
1908    .
1909  .SS "How \fBpcre_exec()\fP returns captured substrings"  .SS "How \fBpcre_exec()\fP returns captured substrings"
1910  .rs  .rs
1911  .sp  .sp
# Line 1630  string that it matched that is returned. Line 1949  string that it matched that is returned.
1949  .P  .P
1950  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
1951  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
1952  returns a value of zero. If the substring offsets are not of interest,  returns a value of zero. If neither the actual string matched nor any captured
1953  \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
1954  \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
1955  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
1956  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
1957  advisable to supply an \fIovector\fP.  is usually advisable to supply an \fIovector\fP of reasonable size.
1958    .P
1959    There are some cases where zero is returned (indicating vector overflow) when
1960    in fact the vector is exactly the right size for the final match. For example,
1961    consider the pattern
1962    .sp
1963      (a)(?:(b)c|bd)
1964    .sp
1965    If a vector of 6 elements (allowing for only 1 captured substring) is given
1966    with subject string "abd", \fBpcre_exec()\fP will try to set the second
1967    captured string, thereby recording a vector overflow, before failing to match
1968    "c" and backing up to try the second alternative. The zero return, however,
1969    does correctly indicate that the maximum number of slots (namely 2) have been
1970    filled. In similar cases where there is temporary overflow, but the final
1971    number of used slots is actually less than the maximum, a non-zero value is
1972    returned.
1973  .P  .P
1974  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
1975  subpatterns there are in a compiled pattern. The smallest size for  subpatterns there are in a compiled pattern. The smallest size for
# Line 1653  Offset values that correspond to unused Line 1987  Offset values that correspond to unused
1987  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
1988  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
1989  return from the function is 2, because the highest used capturing subpattern  return from the function is 2, because the highest used capturing subpattern
1990  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
1991  capturing subpatterns if you wish (assuming the vector is large enough, of  (assuming the vector is large enough, of course) are set to -1.
1992  course).  .P
1993    \fBNote\fP: Elements in the first two-thirds of \fIovector\fP that do not
1994    correspond to capturing parentheses in the pattern are never changed. That is,
1995    if a pattern contains \fIn\fP capturing parentheses, no more than
1996    \fIovector[0]\fP to \fIovector[2n+1]\fP are set by \fBpcre_exec()\fP. The other
1997    elements (in the first two-thirds) retain whatever values they previously had.
1998  .P  .P
1999  Some convenience functions are provided for extracting the captured substrings  Some convenience functions are provided for extracting the captured substrings
2000  as separate strings. These are described below.  as separate strings. These are described below.
2001  .  .
2002    .
2003  .\" HTML <a name="errorlist"></a>  .\" HTML <a name="errorlist"></a>
2004  .SS "Error return values from \fBpcre_exec()\fP"  .SS "Error return values from \fBpcre_exec()\fP"
2005  .rs  .rs
# Line 1729  documentation for details. Line 2069  documentation for details.
2069  .sp  .sp
2070    PCRE_ERROR_BADUTF8        (-10)    PCRE_ERROR_BADUTF8        (-10)
2071  .sp  .sp
2072  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,
2073    and the PCRE_NO_UTF8_CHECK option was not set. If the size of the output vector
2074    (\fIovecsize\fP) is at least 2, the byte offset to the start of the the invalid
2075    UTF-8 character is placed in the first element, and a reason code is placed in
2076    the second element. The reason codes are listed in the
2077    .\" HTML <a href="#badutf8reasons">
2078    .\" </a>
2079    following section.
2080    .\"
2081    For backward compatibility, if PCRE_PARTIAL_HARD is set and the problem is a
2082    truncated UTF-8 character at the end of the subject (reason codes 1 to 5),
2083    PCRE_ERROR_SHORTUTF8 is returned instead of PCRE_ERROR_BADUTF8.
2084  .sp  .sp
2085    PCRE_ERROR_BADUTF8_OFFSET (-11)    PCRE_ERROR_BADUTF8_OFFSET (-11)
2086  .sp  .sp
2087  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
2088  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
2089    \fIstartoffset\fP did not point to the beginning of a UTF-8 character or the
2090    end of the subject.
2091  .sp  .sp
2092    PCRE_ERROR_PARTIAL        (-12)    PCRE_ERROR_PARTIAL        (-12)
2093  .sp  .sp
# Line 1769  description above. Line 2122  description above.
2122    PCRE_ERROR_BADNEWLINE     (-23)    PCRE_ERROR_BADNEWLINE     (-23)
2123  .sp  .sp
2124  An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.  An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
2125    .sp
2126      PCRE_ERROR_BADOFFSET      (-24)
2127    .sp
2128    The value of \fIstartoffset\fP was negative or greater than the length of the
2129    subject, that is, the value in \fIlength\fP.
2130    .sp
2131      PCRE_ERROR_SHORTUTF8      (-25)
2132    .sp
2133    This error is returned instead of PCRE_ERROR_BADUTF8 when the subject string
2134    ends with a truncated UTF-8 character and the PCRE_PARTIAL_HARD option is set.
2135    Information about the failure is returned as for PCRE_ERROR_BADUTF8. It is in
2136    fact sufficient to detect this case, but this special error code for
2137    PCRE_PARTIAL_HARD precedes the implementation of returned information; it is
2138    retained for backwards compatibility.
2139    .sp
2140      PCRE_ERROR_RECURSELOOP    (-26)
2141    .sp
2142    This error is returned when \fBpcre_exec()\fP detects a recursion loop within
2143    the pattern. Specifically, it means that either the whole pattern or a
2144    subpattern has been called recursively for the second time at the same position
2145    in the subject string. Some simple patterns that might do this are detected and
2146    faulted at compile time, but more complicated cases, in particular mutual
2147    recursions between two different subpatterns, cannot be detected until run
2148    time.
2149    .sp
2150      PCRE_ERROR_JIT_STACKLIMIT (-27)
2151    .sp
2152    This error is returned when a pattern that was successfully studied using a
2153    JIT compile option is being matched, but the memory available for the
2154    just-in-time processing stack is not large enough. See the
2155    .\" HREF
2156    \fBpcrejit\fP
2157    .\"
2158    documentation for more details.
2159    .sp
2160      PCRE_ERROR_BADMODE        (-28)
2161    .sp
2162    This error is given if a pattern that was compiled by the 8-bit library is
2163    passed to a 16-bit or 32-bit library function, or vice versa.
2164    .sp
2165      PCRE_ERROR_BADENDIANNESS  (-29)
2166    .sp
2167    This error is given if a pattern that was compiled and saved is reloaded on a
2168    host with different endianness. The utility function
2169    \fBpcre_pattern_to_host_byte_order()\fP can be used to convert such a pattern
2170    so that it runs on the new host.
2171    .P
2172    Error numbers -16 to -20, -22, and -30 are not used by \fBpcre_exec()\fP.
2173    .
2174    .
2175    .\" HTML <a name="badutf8reasons"></a>
2176    .SS "Reason codes for invalid UTF-8 strings"
2177    .rs
2178    .sp
2179    This section applies only to the 8-bit library. The corresponding information
2180    for the 16-bit library is given in the
2181    .\" HREF
2182    \fBpcre16\fP
2183    .\"
2184    page. The corresponding information for the 32-bit library is given in the
2185    .\" HREF
2186    \fBpcre32\fP
2187    .\"
2188    page.
2189  .P  .P
2190  Error numbers -16 to -20 and -22 are not used by \fBpcre_exec()\fP.  When \fBpcre_exec()\fP returns either PCRE_ERROR_BADUTF8 or
2191    PCRE_ERROR_SHORTUTF8, and the size of the output vector (\fIovecsize\fP) is at
2192    least 2, the offset of the start of the invalid UTF-8 character is placed in
2193    the first output vector element (\fIovector[0]\fP) and a reason code is placed
2194    in the second element (\fIovector[1]\fP). The reason codes are given names in
2195    the \fBpcre.h\fP header file:
2196    .sp
2197      PCRE_UTF8_ERR1
2198      PCRE_UTF8_ERR2
2199      PCRE_UTF8_ERR3
2200      PCRE_UTF8_ERR4
2201      PCRE_UTF8_ERR5
2202    .sp
2203    The string ends with a truncated UTF-8 character; the code specifies how many
2204    bytes are missing (1 to 5). Although RFC 3629 restricts UTF-8 characters to be
2205    no longer than 4 bytes, the encoding scheme (originally defined by RFC 2279)
2206    allows for up to 6 bytes, and this is checked first; hence the possibility of
2207    4 or 5 missing bytes.
2208    .sp
2209      PCRE_UTF8_ERR6
2210      PCRE_UTF8_ERR7
2211      PCRE_UTF8_ERR8
2212      PCRE_UTF8_ERR9
2213      PCRE_UTF8_ERR10
2214    .sp
2215    The two most significant bits of the 2nd, 3rd, 4th, 5th, or 6th byte of the
2216    character do not have the binary value 0b10 (that is, either the most
2217    significant bit is 0, or the next bit is 1).
2218    .sp
2219      PCRE_UTF8_ERR11
2220      PCRE_UTF8_ERR12
2221    .sp
2222    A character that is valid by the RFC 2279 rules is either 5 or 6 bytes long;
2223    these code points are excluded by RFC 3629.
2224    .sp
2225      PCRE_UTF8_ERR13
2226    .sp
2227    A 4-byte character has a value greater than 0x10fff; these code points are
2228    excluded by RFC 3629.
2229    .sp
2230      PCRE_UTF8_ERR14
2231    .sp
2232    A 3-byte character has a value in the range 0xd800 to 0xdfff; this range of
2233    code points are reserved by RFC 3629 for use with UTF-16, and so are excluded
2234    from UTF-8.
2235    .sp
2236      PCRE_UTF8_ERR15
2237      PCRE_UTF8_ERR16
2238      PCRE_UTF8_ERR17
2239      PCRE_UTF8_ERR18
2240      PCRE_UTF8_ERR19
2241    .sp
2242    A 2-, 3-, 4-, 5-, or 6-byte character is "overlong", that is, it codes for a
2243    value that can be represented by fewer bytes, which is invalid. For example,
2244    the two bytes 0xc0, 0xae give the value 0x2e, whose correct coding uses just
2245    one byte.
2246    .sp
2247      PCRE_UTF8_ERR20
2248    .sp
2249    The two most significant bits of the first byte of a character have the binary
2250    value 0b10 (that is, the most significant bit is 1 and the second is 0). Such a
2251    byte can only validly occur as the second or subsequent byte of a multi-byte
2252    character.
2253    .sp
2254      PCRE_UTF8_ERR21
2255    .sp
2256    The first byte of a character has the value 0xfe or 0xff. These values can
2257    never occur in a valid UTF-8 string.
2258  .  .
2259  .  .
2260  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
# Line 1935  names are not included in the compiled c Line 2419  names are not included in the compiled c
2419  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
2420  same number causes an error at compile time.  same number causes an error at compile time.
2421  .  .
2422    .
2423  .SH "DUPLICATE SUBPATTERN NAMES"  .SH "DUPLICATE SUBPATTERN NAMES"
2424  .rs  .rs
2425  .sp  .sp
# Line 1968  fourth are pointers to variables which a Line 2453  fourth are pointers to variables which a
2453  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
2454  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
2455  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
2456  described above in the section entitled \fIInformation about a pattern\fP.  described above in the section entitled \fIInformation about a pattern\fP
2457    .\" HTML <a href="#infoaboutpattern">
2458    .\" </a>
2459    above.
2460    .\"
2461  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
2462  numbers, and hence the captured data, if any.  numbers, and hence the captured data, if any.
2463  .  .
# Line 1995  other alternatives. Ultimately, when it Line 2484  other alternatives. Ultimately, when it
2484  will yield PCRE_ERROR_NOMATCH.  will yield PCRE_ERROR_NOMATCH.
2485  .  .
2486  .  .
2487    .SH "OBTAINING AN ESTIMATE OF STACK USAGE"
2488    .rs
2489    .sp
2490    Matching certain patterns using \fBpcre_exec()\fP can use a lot of process
2491    stack, which in certain environments can be rather limited in size. Some users
2492    find it helpful to have an estimate of the amount of stack that is used by
2493    \fBpcre_exec()\fP, to help them set recursion limits, as described in the
2494    .\" HREF
2495    \fBpcrestack\fP
2496    .\"
2497    documentation. The estimate that is output by \fBpcretest\fP when called with
2498    the \fB-m\fP and \fB-C\fP options is obtained by calling \fBpcre_exec\fP with
2499    the values NULL, NULL, NULL, -999, and -999 for its first five arguments.
2500    .P
2501    Normally, if its first argument is NULL, \fBpcre_exec()\fP immediately returns
2502    the negative error code PCRE_ERROR_NULL, but with this special combination of
2503    arguments, it returns instead a negative number whose absolute value is the
2504    approximate stack frame size in bytes. (A negative number is used so that it is
2505    clear that no match has happened.) The value is approximate because in some
2506    cases, recursive calls to \fBpcre_exec()\fP occur when there are one or two
2507    additional variables on the stack.
2508    .P
2509    If PCRE has been compiled to use the heap instead of the stack for recursion,
2510    the value returned is the size of each block that is obtained from the heap.
2511    .
2512    .
2513  .\" HTML <a name="dfamatch"></a>  .\" HTML <a name="dfamatch"></a>
2514  .SH "MATCHING A PATTERN: THE ALTERNATIVE FUNCTION"  .SH "MATCHING A PATTERN: THE ALTERNATIVE FUNCTION"
2515  .rs  .rs
# Line 2098  match. There is more discussion of this Line 2613  match. There is more discussion of this
2613  .\"  .\"
2614  documentation.  documentation.
2615  .  .
2616    .
2617  .SS "Successful returns from \fBpcre_dfa_exec()\fP"  .SS "Successful returns from \fBpcre_dfa_exec()\fP"
2618  .rs  .rs
2619  .sp  .sp
# Line 2129  returns data, even though the meaning of Line 2645  returns data, even though the meaning of
2645  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
2646  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
2647  \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
2648  the longest matches.  the longest matches. Unlike \fBpcre_exec()\fP, \fBpcre_dfa_exec()\fP can use
2649    the entire \fIovector\fP for returning matched strings.
2650    .
2651  .  .
2652  .SS "Error returns from \fBpcre_dfa_exec()\fP"  .SS "Error returns from \fBpcre_dfa_exec()\fP"
2653  .rs  .rs
# Line 2158  group. These are not supported. Line 2676  group. These are not supported.
2676    PCRE_ERROR_DFA_UMLIMIT    (-18)    PCRE_ERROR_DFA_UMLIMIT    (-18)
2677  .sp  .sp
2678  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
2679  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
2680  supported (it is meaningless).  \fImatch_limit_recursion\fP fields. This is not supported (these fields are
2681    meaningless for DFA matching).
2682  .sp  .sp
2683    PCRE_ERROR_DFA_WSSIZE     (-19)    PCRE_ERROR_DFA_WSSIZE     (-19)
2684  .sp  .sp
# Line 2172  When a recursive subpattern is processed Line 2691  When a recursive subpattern is processed
2691  recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This  recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This
2692  error is given if the output vector is not large enough. This should be  error is given if the output vector is not large enough. This should be
2693  extremely rare, as a vector of size 1000 is used.  extremely rare, as a vector of size 1000 is used.
2694    .sp
2695      PCRE_ERROR_DFA_BADRESTART (-30)
2696    .sp
2697    When \fBpcre_dfa_exec()\fP is called with the \fBPCRE_DFA_RESTART\fP option,
2698    some plausibility checks are made on the contents of the workspace, which
2699    should contain data about the previous partial match. If any of these checks
2700    fail, this error is given.
2701  .  .
2702  .  .
2703  .SH "SEE ALSO"  .SH "SEE ALSO"
2704  .rs  .rs
2705  .sp  .sp
2706  \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),  \fBpcre16\fP(3), \fBpcre32\fP(3), \fBpcrebuild\fP(3), \fBpcrecallout\fP(3),
2707  \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),  \fBpcrecpp(3)\fP(3), \fBpcrematching\fP(3), \fBpcrepartial\fP(3),
2708  \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).  \fBpcreposix\fP(3), \fBpcreprecompile\fP(3), \fBpcresample\fP(3),
2709    \fBpcrestack\fP(3).
2710  .  .
2711  .  .
2712  .SH AUTHOR  .SH AUTHOR
# Line 2196  Cambridge CB2 3QH, England. Line 2723  Cambridge CB2 3QH, England.
2723  .rs  .rs
2724  .sp  .sp
2725  .nf  .nf
2726  Last updated: 01 November 2010  Last updated: 07 September 2012
2727  Copyright (c) 1997-2010 University of Cambridge.  Copyright (c) 1997-2012 University of Cambridge.
2728  .fi  .fi

Legend:
Removed from v.566  
changed lines
  Added in v.1055

  ViewVC Help
Powered by ViewVC 1.1.5