/[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 686 by ph10, Tue Sep 6 16:06:36 2011 UTC revision 959 by ph10, Sat Apr 14 16:16:58 2012 UTC
# Line 1  Line 1 
1  .TH PCREAPI 3  .TH PCREAPI 3 "14 April 2012" "PCRE 8.31"
2  .SH NAME  .SH NAME
3  PCRE - Perl-compatible regular expressions  PCRE - Perl-compatible regular expressions
4    .sp
5    .B #include <pcre.h>
6    .
7    .
8  .SH "PCRE NATIVE API BASIC FUNCTIONS"  .SH "PCRE NATIVE API BASIC FUNCTIONS"
9  .rs  .rs
10  .sp  .sp
 .B #include <pcre.h>  
 .PP  
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 32  PCRE - Perl-compatible regular expressio Line 34  PCRE - Perl-compatible regular expressio
34  .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,  .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
35  .ti +5n  .ti +5n
36  .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);  .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);
 .  
 .  
 .SH "PCRE NATIVE API AUXILIARY FUNCTIONS"  
 .rs  
 .sp  
 .B pcre_jit_stack *pcre_jit_stack_alloc(int \fIstartsize\fP, int \fImaxsize\fP);  
 .PP  
 .B void pcre_jit_stack_free(pcre_jit_stack *\fIstack\fP);  
 .PP  
 .B void pcre_assign_jit_stack(pcre_extra *\fIextra\fP,  
 .ti +5n  
 .B pcre_jit_callback \fIcallback\fP, void *\fIdata\fP);  
37  .PP  .PP
38  .B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"  .B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
39  .ti +5n  .ti +5n
# Line 52  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 96  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 103  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
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"  .SH "PCRE NATIVE API INDIRECTED FUNCTIONS"
# Line 127  PCRE - Perl-compatible regular expressio Line 134  PCRE - Perl-compatible regular expressio
134  .B int (*pcre_callout)(pcre_callout_block *);  .B int (*pcre_callout)(pcre_callout_block *);
135  .  .
136  .  .
137    .SH "PCRE 8-BIT AND 16-BIT LIBRARIES"
138    .rs
139    .sp
140    From release 8.30, PCRE can be compiled as a library for handling 16-bit
141    character strings as well as, or instead of, the original library that handles
142    8-bit character strings. To avoid too much complication, this document
143    describes the 8-bit versions of the functions, with only occasional references
144    to the 16-bit library.
145    .P
146    The 16-bit functions operate in the same way as their 8-bit counterparts; they
147    just use different data types for their arguments and results, and their names
148    start with \fBpcre16_\fP instead of \fBpcre_\fP. For every option that has UTF8
149    in its name (for example, PCRE_UTF8), there is a corresponding 16-bit name with
150    UTF8 replaced by UTF16. This facility is in fact just cosmetic; the 16-bit
151    option names define the same bit values.
152    .P
153    References to bytes and UTF-8 in this document should be read as references to
154    16-bit data quantities and UTF-16 when using the 16-bit library, unless
155    specified otherwise. More details of the specific differences for the 16-bit
156    library are given in the
157    .\" HREF
158    \fBpcre16\fP
159    .\"
160    page.
161    .
162    .
163  .SH "PCRE API OVERVIEW"  .SH "PCRE API OVERVIEW"
164  .rs  .rs
165  .sp  .sp
166  PCRE has its own native API, which is described in this document. There are  PCRE has its own native API, which is described in this document. There are
167  also some wrapper functions that correspond to the POSIX regular expression  also some wrapper functions (for the 8-bit library only) that correspond to the
168  API, but they do not give access to all the functionality. They are described  POSIX regular expression API, but they do not give access to all the
169  in the  functionality. They are described in the
170  .\" HREF  .\" HREF
171  \fBpcreposix\fP  \fBpcreposix\fP
172  .\"  .\"
173  documentation. Both of these APIs define a set of C function calls. A C++  documentation. Both of these APIs define a set of C function calls. A C++
174  wrapper is also distributed with PCRE. It is documented in the  wrapper (again for the 8-bit library only) is also distributed with PCRE. It is
175    documented in the
176  .\" HREF  .\" HREF
177  \fBpcrecpp\fP  \fBpcrecpp\fP
178  .\"  .\"
179  page.  page.
180  .P  .P
181  The native API C function prototypes are defined in the header file  The native API C function prototypes are defined in the header file
182  \fBpcre.h\fP, and on Unix systems the library itself is called \fBlibpcre\fP.  \fBpcre.h\fP, and on Unix-like systems the (8-bit) library itself is called
183  It can normally be accessed by adding \fB-lpcre\fP to the command for linking  \fBlibpcre\fP. It can normally be accessed by adding \fB-lpcre\fP to the
184  an application that uses PCRE. The header file defines the macros PCRE_MAJOR  command for linking an application that uses PCRE. The header file defines the
185  and PCRE_MINOR to contain the major and minor release numbers for the library.  macros PCRE_MAJOR and PCRE_MINOR to contain the major and minor release numbers
186  Applications can use these to include support for different releases of PCRE.  for the library. Applications can use these to include support for different
187    releases of PCRE.
188  .P  .P
189  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
190  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 218  specialist use. Most commonly, no specia Line 253  specialist use. Most commonly, no specia
253  internal tables that are generated when PCRE is built are used.  internal tables that are generated when PCRE is built are used.
254  .P  .P
255  The function \fBpcre_fullinfo()\fP is used to find out information about a  The function \fBpcre_fullinfo()\fP is used to find out information about a
256  compiled pattern; \fBpcre_info()\fP is an obsolete version that returns only  compiled pattern. The function \fBpcre_version()\fP returns a pointer to a
257  some of the available information, but is retained for backwards compatibility.  string containing the version of PCRE and its date of release.
 The function \fBpcre_version()\fP returns a pointer to a string containing the  
 version of PCRE and its date of release.  
258  .P  .P
259  The function \fBpcre_refcount()\fP maintains a reference count in a data block  The function \fBpcre_refcount()\fP maintains a reference count in a data block
260  containing a compiled pattern. This is provided for the benefit of  containing a compiled pattern. This is provided for the benefit of
# Line 315  callout function pointed to by \fBpcre_c Line 348  callout function pointed to by \fBpcre_c
348  The compiled form of a regular expression is not altered during matching, so  The compiled form of a regular expression is not altered during matching, so
349  the same compiled pattern can safely be used by several threads at once.  the same compiled pattern can safely be used by several threads at once.
350  .P  .P
351  If the just-in-time optimization feature is being used, it needs separate  If the just-in-time optimization feature is being used, it needs separate
352  memory stack areas for each thread. See the  memory stack areas for each thread. See the
353  .\" HREF  .\" HREF
354  \fBpcrejit\fP  \fBpcrejit\fP
# Line 332  which it was compiled. Details are given Line 365  which it was compiled. Details are given
365  .\" HREF  .\" HREF
366  \fBpcreprecompile\fP  \fBpcreprecompile\fP
367  .\"  .\"
368  documentation. However, compiling a regular expression with one version of PCRE  documentation, which includes a description of the
369  for use with a different version is not guaranteed to work and may cause  \fBpcre_pattern_to_host_byte_order()\fP function. However, compiling a regular
370  crashes.  expression with one version of PCRE for use with a different version is not
371    guaranteed to work and may cause crashes.
372  .  .
373  .  .
374  .SH "CHECKING BUILD-TIME OPTIONS"  .SH "CHECKING BUILD-TIME OPTIONS"
# Line 351  documentation has more details about the Line 385  documentation has more details about the
385  .P  .P
386  The first argument for \fBpcre_config()\fP is an integer, specifying which  The first argument for \fBpcre_config()\fP is an integer, specifying which
387  information is required; the second argument is a pointer to a variable into  information is required; the second argument is a pointer to a variable into
388  which the information is placed. The following information is available:  which the information is placed. The returned value is zero on success, or the
389    negative error code PCRE_ERROR_BADOPTION if the value in the first argument is
390    not recognized. The following information is available:
391  .sp  .sp
392    PCRE_CONFIG_UTF8    PCRE_CONFIG_UTF8
393  .sp  .sp
394  The output is an integer that is set to one if UTF-8 support is available;  The output is an integer that is set to one if UTF-8 support is available;
395  otherwise it is set to zero.  otherwise it is set to zero. If this option is given to the 16-bit version of
396    this function, \fBpcre16_config()\fP, the result is PCRE_ERROR_BADOPTION.
397    .sp
398      PCRE_CONFIG_UTF16
399    .sp
400    The output is an integer that is set to one if UTF-16 support is available;
401    otherwise it is set to zero. This value should normally be given to the 16-bit
402    version of this function, \fBpcre16_config()\fP. If it is given to the 8-bit
403    version of this function, the result is PCRE_ERROR_BADOPTION.
404  .sp  .sp
405    PCRE_CONFIG_UNICODE_PROPERTIES    PCRE_CONFIG_UNICODE_PROPERTIES
406  .sp  .sp
# Line 365  properties is available; otherwise it is Line 409  properties is available; otherwise it is
409  .sp  .sp
410    PCRE_CONFIG_JIT    PCRE_CONFIG_JIT
411  .sp  .sp
412  The output is an integer that is set to one if support for just-in-time  The output is an integer that is set to one if support for just-in-time
413  compiling is available; otherwise it is set to zero.  compiling is available; otherwise it is set to zero.
414    .sp
415      PCRE_CONFIG_JITTARGET
416    .sp
417    The output is a pointer to a zero-terminated "const char *" string. If JIT
418    support is available, the string contains the name of the architecture for
419    which the JIT compiler is configured, for example "x86 32bit (little endian +
420    unaligned)". If JIT support is not available, the result is NULL.
421  .sp  .sp
422    PCRE_CONFIG_NEWLINE    PCRE_CONFIG_NEWLINE
423  .sp  .sp
# Line 387  or CRLF. The default can be overridden w Line 438  or CRLF. The default can be overridden w
438    PCRE_CONFIG_LINK_SIZE    PCRE_CONFIG_LINK_SIZE
439  .sp  .sp
440  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
441  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
442  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
443  matching. The default value of 2 is sufficient for all but the most massive  a number of bytes. The default value of 2 is sufficient for all but the most
444  patterns, since it allows the compiled pattern to be up to 64K in size.  massive patterns, since it allows the compiled pattern to be up to 64K in size.
445    Larger values allow larger regular expressions to be compiled, at the expense
446    of slower matching.
447  .sp  .sp
448    PCRE_CONFIG_POSIX_MALLOC_THRESHOLD    PCRE_CONFIG_POSIX_MALLOC_THRESHOLD
449  .sp  .sp
# Line 473  documentation). For those options that c Line 526  documentation). For those options that c
526  the pattern, the contents of the \fIoptions\fP argument specifies their  the pattern, the contents of the \fIoptions\fP argument specifies their
527  settings at the start of compilation and execution. The PCRE_ANCHORED,  settings at the start of compilation and execution. The PCRE_ANCHORED,
528  PCRE_BSR_\fIxxx\fP, PCRE_NEWLINE_\fIxxx\fP, PCRE_NO_UTF8_CHECK, and  PCRE_BSR_\fIxxx\fP, PCRE_NEWLINE_\fIxxx\fP, PCRE_NO_UTF8_CHECK, and
529  PCRE_NO_START_OPT options can be set at the time of matching as well as at  PCRE_NO_START_OPTIMIZE options can be set at the time of matching as well as at
530  compile time.  compile time.
531  .P  .P
532  If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.  If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.
# Line 484  not try to free it. Normally, the offset Line 537  not try to free it. Normally, the offset
537  byte that was being processed when the error was discovered is placed in the  byte that was being processed when the error was discovered is placed in the
538  variable pointed to by \fIerroffset\fP, which must not be NULL (if it is, an  variable pointed to by \fIerroffset\fP, which must not be NULL (if it is, an
539  immediate error is given). However, for an invalid UTF-8 string, the offset is  immediate error is given). However, for an invalid UTF-8 string, the offset is
540  that of the first byte of the failing character. Also, some errors are not  that of the first byte of the failing character.
 detected until checks are carried out when the whole pattern has been scanned;  
 in these cases the offset passed back is the length of the pattern.  
541  .P  .P
542  Note that the offset is in bytes, not characters, even in UTF-8 mode. It may  Some errors are not detected until the whole pattern has been scanned; in these
543  sometimes point into the middle of a UTF-8 character.  cases, the offset passed back is the length of the pattern. Note that the
544    offset is in bytes, not characters, even in UTF-8 mode. It may sometimes point
545    into the middle of a UTF-8 character.
546  .P  .P
547  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
548  \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 643  character). Thus, the pattern AB]CD beco Line 696  character). Thus, the pattern AB]CD beco
696  string (by default this causes the current matching alternative to fail). A  string (by default this causes the current matching alternative to fail). A
697  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
698  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.
699    .P
700    (3) \eU matches an upper case "U" character; by default \eU causes a compile
701    time error (Perl uses \eU to upper case subsequent characters).
702    .P
703    (4) \eu matches a lower case "u" character unless it is followed by four
704    hexadecimal digits, in which case the hexadecimal number defines the code point
705    to match. By default, \eu causes a compile time error (Perl uses it to upper
706    case the following character).
707    .P
708    (5) \ex matches a lower case "x" character unless it is followed by two
709    hexadecimal digits, in which case the hexadecimal number defines the code point
710    to match. By default, as in Perl, a hexadecimal number is always expected after
711    \ex, but it may have zero, one, or two digits (so, for example, \exz matches a
712    binary zero character followed by z).
713  .sp  .sp
714    PCRE_MULTILINE    PCRE_MULTILINE
715  .sp  .sp
# Line 675  preceding sequences should be recognized Line 742  preceding sequences should be recognized
742  that any Unicode newline sequence should be recognized. The Unicode newline  that any Unicode newline sequence should be recognized. The Unicode newline
743  sequences are the three just mentioned, plus the single characters VT (vertical  sequences are the three just mentioned, plus the single characters VT (vertical
744  tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line  tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line
745  separator, U+2028), and PS (paragraph separator, U+2029). The last two are  separator, U+2028), and PS (paragraph separator, U+2029). For the 8-bit
746  recognized only in UTF-8 mode.  library, the last two are recognized only in UTF-8 mode.
747  .P  .P
748  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
749  as a number, giving eight possibilities. Currently only six are used (default  as a number, giving eight possibilities. Currently only six are used (default
# Line 741  with Perl. It can also be set by a (?U) Line 808  with Perl. It can also be set by a (?U)
808    PCRE_UTF8    PCRE_UTF8
809  .sp  .sp
810  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
811  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
812  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
813  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
814  behaviour of PCRE are given in the  given in the
815  .\" HREF  .\" HREF
816  \fBpcreunicode\fP  \fBpcreunicode\fP
817  .\"  .\"
# Line 752  page. Line 819  page.
819  .sp  .sp
820    PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
821  .sp  .sp
822  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
823  automatically checked. There is a discussion about the  string is automatically checked. There is a discussion about the
824  .\" HTML <a href="pcre.html#utf8strings">  .\" HTML <a href="pcreunicode.html#utf8strings">
825  .\" </a>  .\" </a>
826  validity of UTF-8 strings  validity of UTF-8 strings
827  .\"  .\"
828  in the main  in the
829  .\" HREF  .\" HREF
830  \fBpcre\fP  \fBpcreunicode\fP
831  .\"  .\"
832  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
833  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
834  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.
835  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
836  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
837  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
838  the UTF-8 validity checking of subject strings.  validity checking of subject strings.
839  .  .
840  .  .
841  .SH "COMPILATION ERROR CODES"  .SH "COMPILATION ERROR CODES"
# Line 776  the UTF-8 validity checking of subject s Line 843  the UTF-8 validity checking of subject s
843  .sp  .sp
844  The following table lists the error codes than may be returned by  The following table lists the error codes than may be returned by
845  \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
846  both compiling functions. As PCRE has developed, some error codes have fallen  both compiling functions. Note that error messages are always 8-bit ASCII
847  out of use. To avoid confusion, they have not been re-used.  strings, even in 16-bit mode. As PCRE has developed, some error codes have
848    fallen out of use. To avoid confusion, they have not been re-used.
849  .sp  .sp
850     0  no error     0  no error
851     1  \e at end of pattern     1  \e at end of pattern
# Line 811  out of use. To avoid confusion, they hav Line 879  out of use. To avoid confusion, they hav
879    29  (?R or (?[+-]digits must be followed by )    29  (?R or (?[+-]digits must be followed by )
880    30  unknown POSIX class name    30  unknown POSIX class name
881    31  POSIX collating elements are not supported    31  POSIX collating elements are not supported
882    32  this version of PCRE is not compiled with PCRE_UTF8 support    32  this version of PCRE is compiled without UTF support
883    33  [this code is not in use]    33  [this code is not in use]
884    34  character value in \ex{...} sequence is too large    34  character value in \ex{...} sequence is too large
885    35  invalid condition (?(0)    35  invalid condition (?(0)
# Line 823  out of use. To avoid confusion, they hav Line 891  out of use. To avoid confusion, they hav
891    41  unrecognized character after (?P    41  unrecognized character after (?P
892    42  syntax error in subpattern name (missing terminator)    42  syntax error in subpattern name (missing terminator)
893    43  two named subpatterns have the same name    43  two named subpatterns have the same name
894    44  invalid UTF-8 string    44  invalid UTF-8 string (specifically UTF-8)
895    45  support for \eP, \ep, and \eX has not been compiled    45  support for \eP, \ep, and \eX has not been compiled
896    46  malformed \eP or \ep sequence    46  malformed \eP or \ep sequence
897    47  unknown property name after \eP or \ep    47  unknown property name after \eP or \ep
898    48  subpattern name is too long (maximum 32 characters)    48  subpattern name is too long (maximum 32 characters)
899    49  too many named subpatterns (maximum 10000)    49  too many named subpatterns (maximum 10000)
900    50  [this code is not in use]    50  [this code is not in use]
901    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
902    52  internal error: overran compiling workspace    52  internal error: overran compiling workspace
903    53  internal error: previously-checked referenced subpattern    53  internal error: previously-checked referenced subpattern
904          not found          not found
# Line 849  out of use. To avoid confusion, they hav Line 917  out of use. To avoid confusion, they hav
917    65  different names for subpatterns of the same number are    65  different names for subpatterns of the same number are
918          not allowed          not allowed
919    66  (*MARK) must have an argument    66  (*MARK) must have an argument
920    67  this version of PCRE is not compiled with PCRE_UCP support    67  this version of PCRE is not compiled with Unicode property
921            support
922    68  \ec must be followed by an ASCII character    68  \ec must be followed by an ASCII character
923    69  \ek is not followed by a braced, angle-bracketed, or quoted name    69  \ek is not followed by a braced, angle-bracketed, or quoted name
924      70  internal error: unknown opcode in find_fixedlength()
925      71  \eN is not supported in a class
926      72  too many forward references
927      73  disallowed Unicode code point (>= 0xd800 && <= 0xdfff)
928      74  invalid UTF-16 string (specifically UTF-16)
929  .sp  .sp
930  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
931  be used if the limits were changed when PCRE was built.  be used if the limits were changed when PCRE was built.
# Line 888  If studying the pattern does not produce Line 962  If studying the pattern does not produce
962  wants to pass any of the other fields to \fBpcre_exec()\fP or  wants to pass any of the other fields to \fBpcre_exec()\fP or
963  \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.
964  .P  .P
965  The second argument of \fBpcre_study()\fP contains option bits. There is only  The second argument of \fBpcre_study()\fP contains option bits. There are three
966  one option: PCRE_STUDY_JIT_COMPILE. If this is set, and the just-in-time  options:
967  compiler is available, the pattern is further compiled into machine code that  .sp
968  executes much faster than the \fBpcre_exec()\fP matching function. If    PCRE_STUDY_JIT_COMPILE
969  the just-in-time compiler is not available, this option is ignored. All other    PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE
970  bits in the \fIoptions\fP argument must be zero.    PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE
971    .sp
972    If any of these are set, and the just-in-time compiler is available, the
973    pattern is further compiled into machine code that executes much faster than
974    the \fBpcre_exec()\fP interpretive matching function. If the just-in-time
975    compiler is not available, these options are ignored. All other bits in the
976    \fIoptions\fP argument must be zero.
977  .P  .P
978  JIT compilation is a heavyweight optimization. It can take some time for  JIT compilation is a heavyweight optimization. It can take some time for
979  patterns to be analyzed, and for one-off matches and simple patterns the  patterns to be analyzed, and for one-off matches and simple patterns the
980  benefit of faster execution might be offset by a much slower study time.  benefit of faster execution might be offset by a much slower study time.
981  Not all patterns can be optimized by the JIT compiler. For those that cannot be  Not all patterns can be optimized by the JIT compiler. For those that cannot be
982  handled, matching automatically falls back to the \fBpcre_exec()\fP  handled, matching automatically falls back to the \fBpcre_exec()\fP
983  interpreter. For more details, see the  interpreter. For more details, see the
984  .\" HREF  .\" HREF
# Line 917  When you are finished with a pattern, yo Line 997  When you are finished with a pattern, yo
997  study data by calling \fBpcre_free_study()\fP. This function was added to the  study data by calling \fBpcre_free_study()\fP. This function was added to the
998  API for release 8.20. For earlier versions, the memory could be freed with  API for release 8.20. For earlier versions, the memory could be freed with
999  \fBpcre_free()\fP, just like the pattern itself. This will still work in cases  \fBpcre_free()\fP, just like the pattern itself. This will still work in cases
1000  where PCRE_STUDY_JIT_COMPILE is not used, but it is advisable to change to the  where JIT optimization is not used, but it is advisable to change to the new
1001  new function when convenient.  function when convenient.
1002  .P  .P
1003  This is a typical way in which \fBpcre_study\fP() is used (except that in a  This is a typical way in which \fBpcre_study\fP() is used (except that in a
1004  real application there should be tests for errors):  real application there should be tests for errors):
1005  .sp  .sp
1006    int rc;    int rc;
# Line 932  real application there should be tests f Line 1012  real application there should be tests f
1012      0,              /* no options */      0,              /* no options */
1013      &error);        /* set to NULL or points to a message */      &error);        /* set to NULL or points to a message */
1014    rc = pcre_exec(   /* see below for details of pcre_exec() options */    rc = pcre_exec(   /* see below for details of pcre_exec() options */
1015      re, sd, "subject", 7, 0, 0, ovector, 30);      re, sd, "subject", 7, 0, 0, ovector, 30);
1016    ...    ...
1017    pcre_free_study(sd);    pcre_free_study(sd);
1018    pcre_free(re);    pcre_free(re);
1019  .sp  .sp
1020  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
1021  subject string that is needed to match the pattern is computed. This does not  subject string that is needed to match the pattern is computed. This does not
# Line 948  in a calling program via the \fBpcre_ful Line 1028  in a calling program via the \fBpcre_ful
1028  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
1029  single fixed starting character. A bitmap of possible starting bytes is  single fixed starting character. A bitmap of possible starting bytes is
1030  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
1031  matching.  matching. (In 16-bit mode, the bitmap is used for 16-bit values less than 256.)
1032  .P  .P
1033  These two optimizations apply to both \fBpcre_exec()\fP and  These two optimizations apply to both \fBpcre_exec()\fP and
1034  \fBpcre_dfa_exec()\fP. However, they are not used by \fBpcre_exec()\fP if  \fBpcre_dfa_exec()\fP, and the information is also used by the JIT compiler.
1035  \fBpcre_study()\fP is called with the PCRE_STUDY_JIT_COMPILE option, and  The optimizations can be disabled by setting the PCRE_NO_START_OPTIMIZE option
1036  just-in-time compiling is successful. The optimizations can be disabled by  when calling \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP, but if this is done,
1037  setting the PCRE_NO_START_OPTIMIZE option when calling \fBpcre_exec()\fP or  JIT execution is also disabled. You might want to do this if your pattern
1038  \fBpcre_dfa_exec()\fP. You might want to do this if your pattern contains  contains callouts or (*MARK) and you want to make use of these facilities in
1039  callouts or (*MARK) (which cannot be handled by the JIT compiler), and you want  cases where matching fails. See the discussion of PCRE_NO_START_OPTIMIZE
 to make use of these facilities in cases where matching fails. See the  
 discussion of PCRE_NO_START_OPTIMIZE  
1040  .\" HTML <a href="#execoptions">  .\" HTML <a href="#execoptions">
1041  .\" </a>  .\" </a>
1042  below.  below.
# Line 971  below. Line 1049  below.
1049  .sp  .sp
1050  PCRE handles caseless matching, and determines whether characters are letters,  PCRE handles caseless matching, and determines whether characters are letters,
1051  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
1052  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
1053  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
1054  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
1055  property support. Alternatively, the PCRE_UCP option can be set at compile  Unicode character property support. Alternatively, the PCRE_UCP option can be
1056  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
1057  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
1058  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
1059  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
1060    two.
1061  .P  .P
1062  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
1063  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 1032  below in the section on matching a patte Line 1111  below in the section on matching a patte
1111  .B int \fIwhat\fP, void *\fIwhere\fP);  .B int \fIwhat\fP, void *\fIwhere\fP);
1112  .PP  .PP
1113  The \fBpcre_fullinfo()\fP function returns information about a compiled  The \fBpcre_fullinfo()\fP function returns information about a compiled
1114  pattern. It replaces the obsolete \fBpcre_info()\fP function, which is  pattern. It replaces the \fBpcre_info()\fP function, which was removed from the
1115  nevertheless retained for backwards compability (and is documented below).  library at version 8.30, after more than 10 years of obsolescence.
1116  .P  .P
1117  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
1118  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 1042  information is required, and the fourth Line 1121  information is required, and the fourth
1121  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
1122  the following negative numbers:  the following negative numbers:
1123  .sp  .sp
1124    PCRE_ERROR_NULL       the argument \fIcode\fP was NULL    PCRE_ERROR_NULL           the argument \fIcode\fP was NULL
1125                          the argument \fIwhere\fP was NULL                              the argument \fIwhere\fP was NULL
1126    PCRE_ERROR_BADMAGIC   the "magic number" was not found    PCRE_ERROR_BADMAGIC       the "magic number" was not found
1127    PCRE_ERROR_BADOPTION  the value of \fIwhat\fP was invalid    PCRE_ERROR_BADENDIANNESS  the pattern was compiled with different
1128                                endianness
1129      PCRE_ERROR_BADOPTION      the value of \fIwhat\fP was invalid
1130  .sp  .sp
1131  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
1132  check against passing an arbitrary memory pointer. Here is a typical call of  check against passing an arbitrary memory pointer. The endianness error can
1133  \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
1134    a typical call of \fBpcre_fullinfo()\fP, to obtain the length of the compiled
1135    pattern:
1136  .sp  .sp
1137    int rc;    int rc;
1138    size_t length;    size_t length;
# Line 1083  a NULL table pointer. Line 1166  a NULL table pointer.
1166  .sp  .sp
1167    PCRE_INFO_FIRSTBYTE    PCRE_INFO_FIRSTBYTE
1168  .sp  .sp
1169  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
1170  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,
1171  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
1172  still recognized for backwards compatibility.)  variable.
1173  .P  .P
1174  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
1175  (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
1176    value is always less than 256; in the 16-bit library the value can be up to
1177    0xffff.
1178    .P
1179    If there is no fixed first value, and if either
1180  .sp  .sp
1181  (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
1182  starts with "^", or  starts with "^", or
# Line 1104  returned. For anchored patterns, -2 is r Line 1191  returned. For anchored patterns, -2 is r
1191    PCRE_INFO_FIRSTTABLE    PCRE_INFO_FIRSTTABLE
1192  .sp  .sp
1193  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
1194  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
1195  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
1196  fourth argument should point to an \fBunsigned char *\fP variable.  fourth argument should point to an \fBunsigned char *\fP variable.
1197  .sp  .sp
# Line 1122  Return 1 if the (?J) or (?-J) option set Line 1209  Return 1 if the (?J) or (?-J) option set
1209  .sp  .sp
1210    PCRE_INFO_JIT    PCRE_INFO_JIT
1211  .sp  .sp
1212  Return 1 if the pattern was studied with the PCRE_STUDY_JIT_COMPILE option, and  Return 1 if the pattern was studied with one of the JIT options, and
1213  just-in-time compiling was successful. The fourth argument should point to an  just-in-time compiling was successful. The fourth argument should point to an
1214  \fBint\fP variable. A return value of 0 means that JIT support is not available  \fBint\fP variable. A return value of 0 means that JIT support is not available
1215  in this version of PCRE, or that the pattern was not studied with the  in this version of PCRE, or that the pattern was not studied with a JIT option,
1216  PCRE_STUDY_JIT_COMPILE option, or that the JIT compiler could not handle this  or that the JIT compiler could not handle this particular pattern. See the
 particular pattern. See the  
1217  .\" HREF  .\" HREF
1218  \fBpcrejit\fP  \fBpcrejit\fP
1219  .\"  .\"
1220  documentation for details of what can and cannot be handled.  documentation for details of what can and cannot be handled.
1221  .sp  .sp
1222      PCRE_INFO_JITSIZE
1223    .sp
1224    If the pattern was successfully studied with a JIT option, return the size of
1225    the JIT compiled code, otherwise return zero. The fourth argument should point
1226    to a \fBsize_t\fP variable.
1227    .sp
1228    PCRE_INFO_LASTLITERAL    PCRE_INFO_LASTLITERAL
1229  .sp  .sp
1230  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
1231  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
1232  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
1233  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
1234  follows something of variable length. For example, for the pattern  only if it follows something of variable length. For example, for the pattern
1235  /^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
1236  is -1.  is -1.
1237  .sp  .sp
1238      PCRE_INFO_MAXLOOKBEHIND
1239    .sp
1240    Return the number of characters (NB not bytes) in the longest lookbehind
1241    assertion in the pattern. Note that the simple assertions \eb and \eB require a
1242    one-character lookbehind. This information is useful when doing multi-segment
1243    matching using the partial matching facilities.
1244    .sp
1245    PCRE_INFO_MINLENGTH    PCRE_INFO_MINLENGTH
1246  .sp  .sp
1247  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
1248  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
1249  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
1250  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
1251  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
1252  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
1253  that does match is at least that long.  that does match is at least that long.
# Line 1171  The map consists of a number of fixed-si Line 1270  The map consists of a number of fixed-si
1270  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
1271  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
1272  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
1273  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
1274  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,
1275  rest of the entry is the corresponding name, zero terminated.  most significant byte first. In the 16-bit library, the pointer points to
1276    16-bit data units, the first of which contains the parenthesis number. The rest
1277    of the entry is the corresponding name, zero terminated.
1278  .P  .P
1279  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
1280  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 1192  table in the order in which they were fo Line 1293  table in the order in which they were fo
1293  necessarily the case because later subpatterns may have lower numbers.  necessarily the case because later subpatterns may have lower numbers.
1294  .P  .P
1295  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
1296  (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
1297  ignored):  space - including newlines - is ignored):
1298  .sp  .sp
1299  .\" JOIN  .\" JOIN
1300    (?<date> (?<year>(\ed\ed)?\ed\ed) -    (?<date> (?<year>(\ed\ed)?\ed\ed) -
# Line 1248  For such patterns, the PCRE_ANCHORED bit Line 1349  For such patterns, the PCRE_ANCHORED bit
1349  .sp  .sp
1350    PCRE_INFO_SIZE    PCRE_INFO_SIZE
1351  .sp  .sp
1352  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
1353  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
1354  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
1355  variable.  \fBpcre_compile()\fP. The value that is passed as the argument to
1356    \fBpcre_malloc()\fP when \fBpcre_compile()\fP is getting memory in which to
1357    place the compiled data is the value returned by this option plus the size of
1358    the \fBpcre\fP structure. Studying a compiled pattern, with or without JIT,
1359    does not alter the value returned by this option.
1360  .sp  .sp
1361    PCRE_INFO_STUDYSIZE    PCRE_INFO_STUDYSIZE
1362  .sp  .sp
1363  Return the size of the data block pointed to by the \fIstudy_data\fP field in a  Return the size in bytes of the data block pointed to by the \fIstudy_data\fP
1364  \fBpcre_extra\fP block. If \fBpcre_extra\fP is NULL, or there is no study data,  field in a \fBpcre_extra\fP block. If \fBpcre_extra\fP is NULL, or there is no
1365  zero is returned. The fourth argument should point to a \fBsize_t\fP variable.  study data, zero is returned. The fourth argument should point to a
1366  The \fIstudy_data\fP field is set by \fBpcre_study()\fP to record information  \fBsize_t\fP variable. The \fIstudy_data\fP field is set by \fBpcre_study()\fP
1367  that will speed up matching (see the section entitled  to record information that will speed up matching (see the section entitled
1368  .\" HTML <a href="#studyingapattern">  .\" HTML <a href="#studyingapattern">
1369  .\" </a>  .\" </a>
1370  "Studying a pattern"  "Studying a pattern"
# Line 1272  is made available via this option so tha Line 1377  is made available via this option so tha
1377  documentation for details).  documentation for details).
1378  .  .
1379  .  .
 .SH "OBSOLETE INFO FUNCTION"  
 .rs  
 .sp  
 .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int  
 .B *\fIfirstcharptr\fP);  
 .PP  
 The \fBpcre_info()\fP function is now obsolete because its interface is too  
 restrictive to return all the available data about a compiled pattern. New  
 programs should use \fBpcre_fullinfo()\fP instead. The yield of  
 \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).  
 .  
 .  
1380  .SH "REFERENCE COUNTS"  .SH "REFERENCE COUNTS"
1381  .rs  .rs
1382  .sp  .sp
# Line 1331  is different. (This seems a highly unlik Line 1412  is different. (This seems a highly unlik
1412  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
1413  compiled pattern, which is passed in the \fIcode\fP argument. If the  compiled pattern, which is passed in the \fIcode\fP argument. If the
1414  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
1415  \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
1416  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
1417  also an alternative matching function, which is described  different subject strings with the same pattern.
1418    .P
1419    This function is the main matching facility of the library, and it operates in
1420    a Perl-like manner. For specialist use there is also an alternative matching
1421    function, which is described
1422  .\" HTML <a href="#dfamatch">  .\" HTML <a href="#dfamatch">
1423  .\" </a>  .\" </a>
1424  below  below
# Line 1377  fields (not necessarily in this order): Line 1462  fields (not necessarily in this order):
1462  .sp  .sp
1463    unsigned long int \fIflags\fP;    unsigned long int \fIflags\fP;
1464    void *\fIstudy_data\fP;    void *\fIstudy_data\fP;
1465    void *\fIexecutable_jit\fP;    void *\fIexecutable_jit\fP;
1466    unsigned long int \fImatch_limit\fP;    unsigned long int \fImatch_limit\fP;
1467    unsigned long int \fImatch_limit_recursion\fP;    unsigned long int \fImatch_limit_recursion\fP;
1468    void *\fIcallout_data\fP;    void *\fIcallout_data\fP;
1469    const unsigned char *\fItables\fP;    const unsigned char *\fItables\fP;
1470    unsigned char **\fImark\fP;    unsigned char **\fImark\fP;
1471  .sp  .sp
1472  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
1473  are set. The flag bits are:  "PCRE_UCHAR16 **".
1474    .P
1475    The \fIflags\fP field is used to specify which of the other fields are set. The
1476    flag bits are:
1477  .sp  .sp
1478    PCRE_EXTRA_STUDY_DATA    PCRE_EXTRA_CALLOUT_DATA
1479    PCRE_EXTRA_EXECUTABLE_JIT    PCRE_EXTRA_EXECUTABLE_JIT
1480      PCRE_EXTRA_MARK
1481    PCRE_EXTRA_MATCH_LIMIT    PCRE_EXTRA_MATCH_LIMIT
1482    PCRE_EXTRA_MATCH_LIMIT_RECURSION    PCRE_EXTRA_MATCH_LIMIT_RECURSION
1483    PCRE_EXTRA_CALLOUT_DATA    PCRE_EXTRA_STUDY_DATA
1484    PCRE_EXTRA_TABLES    PCRE_EXTRA_TABLES
   PCRE_EXTRA_MARK  
1485  .sp  .sp
1486  Other flag bits should be set to zero. The \fIstudy_data\fP field and sometimes  Other flag bits should be set to zero. The \fIstudy_data\fP field and sometimes
1487  the \fIexecutable_jit\fP field are set in the \fBpcre_extra\fP block that is  the \fIexecutable_jit\fP field are set in the \fBpcre_extra\fP block that is
1488  returned by \fBpcre_study()\fP, together with the appropriate flag bits. You  returned by \fBpcre_study()\fP, together with the appropriate flag bits. You
1489  should not set these yourself, but you may add to the block by setting the  should not set these yourself, but you may add to the block by setting other
1490  other fields and their corresponding flag bits.  fields and their corresponding flag bits.
1491  .P  .P
1492  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
1493  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,
# Line 1411  calls repeatedly (sometimes recursively) Line 1499  calls repeatedly (sometimes recursively)
1499  imposed on the number of times this function is called during a match, which  imposed on the number of times this function is called during a match, which
1500  has the effect of limiting the amount of backtracking that can take place. For  has the effect of limiting the amount of backtracking that can take place. For
1501  patterns that are not anchored, the count restarts from zero for each position  patterns that are not anchored, the count restarts from zero for each position
1502  in the subject string.  in the subject string.
1503  .P  .P
1504  When \fBpcre_exec()\fP is called with a pattern that was successfully studied  When \fBpcre_exec()\fP is called with a pattern that was successfully studied
1505  with the PCRE_STUDY_JIT_COMPILE option, the way that the matching is executed  with a JIT option, the way that the matching is executed is entirely different.
1506  is entirely different. However, there is still the possibility of runaway  However, there is still the possibility of runaway matching that goes on for a
1507  matching that goes on for a very long time, and so the \fImatch_limit\fP value  very long time, and so the \fImatch_limit\fP value is also used in this case
1508  is also used in this case (but in a different way) to limit how long the  (but in a different way) to limit how long the matching can continue.
 matching can continue.  
1509  .P  .P
1510  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
1511  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 1431  The \fImatch_limit_recursion\fP field is Line 1518  The \fImatch_limit_recursion\fP field is
1518  instead of limiting the total number of times that \fBmatch()\fP is called, it  instead of limiting the total number of times that \fBmatch()\fP is called, it
1519  limits the depth of recursion. The recursion depth is a smaller number than the  limits the depth of recursion. The recursion depth is a smaller number than the
1520  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.
1521  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.
1522  .P  .P
1523  Limiting the recursion depth limits the amount of machine stack that can be  Limiting the recursion depth limits the amount of machine stack that can be
1524  used, or, when PCRE has been compiled to use memory on the heap instead of the  used, or, when PCRE has been compiled to use memory on the heap instead of the
1525  stack, the amount of heap memory that can be used. This limit is not relevant,  stack, the amount of heap memory that can be used. This limit is not relevant,
1526  and is ignored, if the pattern was successfully studied with  and is ignored, when matching is done using JIT compiled code.
 PCRE_STUDY_JIT_COMPILE.  
1527  .P  .P
1528  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
1529  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 1468  called. See the Line 1554  called. See the
1554  documentation for a discussion of saving compiled patterns for later use.  documentation for a discussion of saving compiled patterns for later use.
1555  .P  .P
1556  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
1557  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
1558  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
1559  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
1560  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
1561  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
1562  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
1563  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
1564  backtracking control verbs, see the section entitled  backtracking control verbs, see the section entitled
1565  .\" HTML <a href="pcrepattern#backtrackcontrol">  .\" HTML <a href="pcrepattern#backtrackcontrol">
1566  .\" </a>  .\" </a>
# Line 1494  documentation. Line 1580  documentation.
1580  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
1581  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,
1582  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART,  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART,
1583  PCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_SOFT, and  PCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_HARD, and
1584  PCRE_PARTIAL_HARD.  PCRE_PARTIAL_SOFT.
1585  .P  .P
1586  If the pattern was successfully studied with the PCRE_STUDY_JIT_COMPILE option,  If the pattern was successfully studied with one of the just-in-time (JIT)
1587  the only supported options for JIT execution are PCRE_NO_UTF8_CHECK,  compile options, the only supported options for JIT execution are
1588  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, and PCRE_NOTEMPTY_ATSTART. Note in  PCRE_NO_UTF8_CHECK, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY,
1589  particular that partial matching is not supported. If an unsupported option is  PCRE_NOTEMPTY_ATSTART, PCRE_PARTIAL_HARD, and PCRE_PARTIAL_SOFT. If an
1590  used, JIT execution is disabled and the normal interpretive code in  unsupported option is used, JIT execution is disabled and the normal
1591  \fBpcre_exec()\fP is run.  interpretive code in \fBpcre_exec()\fP is run.
1592  .sp  .sp
1593    PCRE_ANCHORED    PCRE_ANCHORED
1594  .sp  .sp
# Line 1621  causing performance to suffer, but ensur Line 1707  causing performance to suffer, but ensur
1707  "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)
1708  are considered at every possible starting position in the subject string. If  are considered at every possible starting position in the subject string. If
1709  PCRE_NO_START_OPTIMIZE is set at compile time, it cannot be unset at matching  PCRE_NO_START_OPTIMIZE is set at compile time, it cannot be unset at matching
1710  time.  time. The use of PCRE_NO_START_OPTIMIZE disables JIT execution; when it is set,
1711    matching is always done using interpretively.
1712  .P  .P
1713  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.
1714  Consider the pattern  Consider the pattern
# Line 1654  returned. Line 1741  returned.
1741  .sp  .sp
1742  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
1743  string is automatically checked when \fBpcre_exec()\fP is subsequently called.  string is automatically checked when \fBpcre_exec()\fP is subsequently called.
1744  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
1745  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
1746  strings in the  UTF-8 character. There is a discussion about the
1747  .\" HTML <a href="pcre.html#utf8strings">  .\" HTML <a href="pcreunicode.html#utf8strings">
1748  .\" </a>  .\" </a>
1749  section on UTF-8 support  validity of UTF-8 strings
1750  .\"  .\"
1751  in the main  in the
1752  .\" HREF  .\" HREF
1753  \fBpcre\fP  \fBpcreunicode\fP
1754  .\"  .\"
1755  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
1756  the error PCRE_ERROR_BADUTF8 or, if PCRE_PARTIAL_HARD is set and the problem is  error PCRE_ERROR_BADUTF8 or, if PCRE_PARTIAL_HARD is set and the problem is a
1757  a truncated UTF-8 character at the end of the subject, PCRE_ERROR_SHORTUTF8. In  truncated character at the end of the subject, PCRE_ERROR_SHORTUTF8. In both
1758  both cases, information about the precise nature of the error may also be  cases, information about the precise nature of the error may also be returned
1759  returned (see the descriptions of these errors in the section entitled \fIError  (see the descriptions of these errors in the section entitled \fIError return
1760  return values from\fP \fBpcre_exec()\fP  values from\fP \fBpcre_exec()\fP
1761  .\" HTML <a href="#errorlist">  .\" HTML <a href="#errorlist">
1762  .\" </a>  .\" </a>
1763  below).  below).
# Line 1684  checks for performance reasons, you can Line 1771  checks for performance reasons, you can
1771  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
1772  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
1773  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
1774  the value of \fIstartoffset\fP points to the start of a UTF-8 character (or the  the value of \fIstartoffset\fP points to the start of a character (or the end
1775  end of the subject). When PCRE_NO_UTF8_CHECK is set, the effect of passing an  of the subject). When PCRE_NO_UTF8_CHECK is set, the effect of passing an
1776  invalid UTF-8 string as a subject or an invalid value of \fIstartoffset\fP is  invalid string as a subject or an invalid value of \fIstartoffset\fP is
1777  undefined. Your program may crash.  undefined. Your program may crash.
1778  .sp  .sp
1779    PCRE_PARTIAL_HARD    PCRE_PARTIAL_HARD
# Line 1721  documentation. Line 1808  documentation.
1808  .rs  .rs
1809  .sp  .sp
1810  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
1811  \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
1812  in \fIstartoffset\fP. If this is negative or greater than the length of the  in \fIstartoffset\fP. If this is negative or greater than the length of the
1813  subject, \fBpcre_exec()\fP returns PCRE_ERROR_BADOFFSET. When the starting  subject, \fBpcre_exec()\fP returns PCRE_ERROR_BADOFFSET. When the starting
1814  offset is zero, the search for a match starts at the beginning of the subject,  offset is zero, the search for a match starts at the beginning of the subject,
# Line 1809  string that it matched that is returned. Line 1896  string that it matched that is returned.
1896  .P  .P
1897  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
1898  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
1899  returns a value of zero. If neither the actual string matched not any captured  returns a value of zero. If neither the actual string matched nor any captured
1900  substrings are of interest, \fBpcre_exec()\fP may be called with \fIovector\fP  substrings are of interest, \fBpcre_exec()\fP may be called with \fIovector\fP
1901  passed as NULL and \fIovecsize\fP as zero. However, if the pattern contains  passed as NULL and \fIovecsize\fP as zero. However, if the pattern contains
1902  back references and the \fIovector\fP is not big enough to remember the related  back references and the \fIovector\fP is not big enough to remember the related
# Line 1825  consider the pattern Line 1912  consider the pattern
1912  If a vector of 6 elements (allowing for only 1 captured substring) is given  If a vector of 6 elements (allowing for only 1 captured substring) is given
1913  with subject string "abd", \fBpcre_exec()\fP will try to set the second  with subject string "abd", \fBpcre_exec()\fP will try to set the second
1914  captured string, thereby recording a vector overflow, before failing to match  captured string, thereby recording a vector overflow, before failing to match
1915  "c" and backing up to try the second alternative. The zero return, however,  "c" and backing up to try the second alternative. The zero return, however,
1916  does correctly indicate that the maximum number of slots (namely 2) have been  does correctly indicate that the maximum number of slots (namely 2) have been
1917  filled. In similar cases where there is temporary overflow, but the final  filled. In similar cases where there is temporary overflow, but the final
1918  number of used slots is actually less than the maximum, a non-zero value is  number of used slots is actually less than the maximum, a non-zero value is
# Line 2009  time. Line 2096  time.
2096  .sp  .sp
2097    PCRE_ERROR_JIT_STACKLIMIT (-27)    PCRE_ERROR_JIT_STACKLIMIT (-27)
2098  .sp  .sp
2099  This error is returned when a pattern that was successfully studied using the  This error is returned when a pattern that was successfully studied using a
2100  PCRE_STUDY_JIT_COMPILE option is being matched, but the memory available for  JIT compile option is being matched, but the memory available for the
2101  the just-in-time processing stack is not large enough. See the  just-in-time processing stack is not large enough. See the
2102  .\" HREF  .\" HREF
2103  \fBpcrejit\fP  \fBpcrejit\fP
2104  .\"  .\"
2105  documentation for more details.  documentation for more details.
2106    .sp
2107      PCRE_ERROR_BADMODE (-28)
2108    .sp
2109    This error is given if a pattern that was compiled by the 8-bit library is
2110    passed to a 16-bit library function, or vice versa.
2111    .sp
2112      PCRE_ERROR_BADENDIANNESS (-29)
2113    .sp
2114    This error is given if a pattern that was compiled and saved is reloaded on a
2115    host with different endianness. The utility function
2116    \fBpcre_pattern_to_host_byte_order()\fP can be used to convert such a pattern
2117    so that it runs on the new host.
2118  .P  .P
2119  Error numbers -16 to -20 and -22 are not used by \fBpcre_exec()\fP.  Error numbers -16 to -20 and -22 are not used by \fBpcre_exec()\fP.
2120  .  .
# Line 2024  Error numbers -16 to -20 and -22 are not Line 2123  Error numbers -16 to -20 and -22 are not
2123  .SS "Reason codes for invalid UTF-8 strings"  .SS "Reason codes for invalid UTF-8 strings"
2124  .rs  .rs
2125  .sp  .sp
2126    This section applies only to the 8-bit library. The corresponding information
2127    for the 16-bit library is given in the
2128    .\" HREF
2129    \fBpcre16\fP
2130    .\"
2131    page.
2132    .P
2133  When \fBpcre_exec()\fP returns either PCRE_ERROR_BADUTF8 or  When \fBpcre_exec()\fP returns either PCRE_ERROR_BADUTF8 or
2134  PCRE_ERROR_SHORTUTF8, and the size of the output vector (\fIovecsize\fP) is at  PCRE_ERROR_SHORTUTF8, and the size of the output vector (\fIovecsize\fP) is at
2135  least 2, the offset of the start of the invalid UTF-8 character is placed in  least 2, the offset of the start of the invalid UTF-8 character is placed in
# Line 2321  other alternatives. Ultimately, when it Line 2427  other alternatives. Ultimately, when it
2427  will yield PCRE_ERROR_NOMATCH.  will yield PCRE_ERROR_NOMATCH.
2428  .  .
2429  .  .
2430    .SH "OBTAINING AN ESTIMATE OF STACK USAGE"
2431    .rs
2432    .sp
2433    Matching certain patterns using \fBpcre_exec()\fP can use a lot of process
2434    stack, which in certain environments can be rather limited in size. Some users
2435    find it helpful to have an estimate of the amount of stack that is used by
2436    \fBpcre_exec()\fP, to help them set recursion limits, as described in the
2437    .\" HREF
2438    \fBpcrestack\fP
2439    .\"
2440    documentation. The estimate that is output by \fBpcretest\fP when called with
2441    the \fB-m\fP and \fB-C\fP options is obtained by calling \fBpcre_exec\fP with
2442    the values NULL, NULL, NULL, -999, and -999 for its first five arguments.
2443    .P
2444    Normally, if its first argument is NULL, \fBpcre_exec()\fP immediately returns
2445    the negative error code PCRE_ERROR_NULL, but with this special combination of
2446    arguments, it returns instead a negative number whose absolute value is the
2447    approximate stack frame size in bytes. (A negative number is used so that it is
2448    clear that no match has happened.) The value is approximate because in some
2449    cases, recursive calls to \fBpcre_exec()\fP occur when there are one or two
2450    additional variables on the stack.
2451    .P
2452    If PCRE has been compiled to use the heap instead of the stack for recursion,
2453    the value returned is the size of each block that is obtained from the heap.
2454    .
2455    .
2456  .\" HTML <a name="dfamatch"></a>  .\" HTML <a name="dfamatch"></a>
2457  .SH "MATCHING A PATTERN: THE ALTERNATIVE FUNCTION"  .SH "MATCHING A PATTERN: THE ALTERNATIVE FUNCTION"
2458  .rs  .rs
# Line 2456  returns data, even though the meaning of Line 2588  returns data, even though the meaning of
2588  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
2589  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
2590  \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
2591  the longest matches. Unlike \fBpcre_exec()\fP, \fBpcre_dfa_exec()\fP can use  the longest matches. Unlike \fBpcre_exec()\fP, \fBpcre_dfa_exec()\fP can use
2592  the entire \fIovector\fP for returning matched strings.  the entire \fIovector\fP for returning matched strings.
2593  .  .
2594  .  .
# Line 2507  extremely rare, as a vector of size 1000 Line 2639  extremely rare, as a vector of size 1000
2639  .SH "SEE ALSO"  .SH "SEE ALSO"
2640  .rs  .rs
2641  .sp  .sp
2642  \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),  \fBpcre16\fP(3), \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
2643  \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),  \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
2644  \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).  \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
2645  .  .
# Line 2526  Cambridge CB2 3QH, England. Line 2658  Cambridge CB2 3QH, England.
2658  .rs  .rs
2659  .sp  .sp
2660  .nf  .nf
2661  Last updated: 06 September 2011  Last updated: 14 April 2012
2662  Copyright (c) 1997-2011 University of Cambridge.  Copyright (c) 1997-2012 University of Cambridge.
2663  .fi  .fi

Legend:
Removed from v.686  
changed lines
  Added in v.959

  ViewVC Help
Powered by ViewVC 1.1.5