/[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 836 by ph10, Wed Dec 28 17:16:11 2011 UTC revision 887 by ph10, Tue Jan 17 14:32:32 2012 UTC
# Line 1  Line 1 
1  .TH PCREAPI 3  .TH PCREAPI 3
2  .SH NAME  .SH NAME
3  PCRE - Perl-compatible regular expressions  PCRE - Perl-compatible regular expressions
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 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 368  properties is available; otherwise it is Line 412  properties is available; otherwise it is
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  .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
422    PCRE_CONFIG_NEWLINE    PCRE_CONFIG_NEWLINE
423  .sp  .sp
424  The output is an integer whose value specifies the default character sequence  The output is an integer whose value specifies the default character sequence
# Line 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 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 689  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 755  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 766  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 790  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 825  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 837  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 863  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 962  in a calling program via the \fBpcre_ful Line 1022  in a calling program via the \fBpcre_ful
1022  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
1023  single fixed starting character. A bitmap of possible starting bytes is  single fixed starting character. A bitmap of possible starting bytes is
1024  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
1025  matching.  matching. (In 16-bit mode, the bitmap is used for 16-bit values less than 256.)
1026  .P  .P
1027  These two optimizations apply to both \fBpcre_exec()\fP and  These two optimizations apply to both \fBpcre_exec()\fP and
1028  \fBpcre_dfa_exec()\fP. However, they are not used by \fBpcre_exec()\fP if  \fBpcre_dfa_exec()\fP. However, they are not used by \fBpcre_exec()\fP if
# Line 985  below. Line 1045  below.
1045  .sp  .sp
1046  PCRE handles caseless matching, and determines whether characters are letters,  PCRE handles caseless matching, and determines whether characters are letters,
1047  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
1048  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
1049  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
1050  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
1051  property support. Alternatively, the PCRE_UCP option can be set at compile  Unicode character property support. Alternatively, the PCRE_UCP option can be
1052  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
1053  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
1054  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
1055  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
1056    two.
1057  .P  .P
1058  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
1059  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 1046  below in the section on matching a patte Line 1107  below in the section on matching a patte
1107  .B int \fIwhat\fP, void *\fIwhere\fP);  .B int \fIwhat\fP, void *\fIwhere\fP);
1108  .PP  .PP
1109  The \fBpcre_fullinfo()\fP function returns information about a compiled  The \fBpcre_fullinfo()\fP function returns information about a compiled
1110  pattern. It replaces the obsolete \fBpcre_info()\fP function, which is  pattern. It replaces the \fBpcre_info()\fP function, which was removed from the
1111  nevertheless retained for backwards compability (and is documented below).  library at version 8.30, after more than 10 years of obsolescence.
1112  .P  .P
1113  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
1114  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 1056  information is required, and the fourth Line 1117  information is required, and the fourth
1117  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
1118  the following negative numbers:  the following negative numbers:
1119  .sp  .sp
1120    PCRE_ERROR_NULL       the argument \fIcode\fP was NULL    PCRE_ERROR_NULL           the argument \fIcode\fP was NULL
1121                          the argument \fIwhere\fP was NULL                              the argument \fIwhere\fP was NULL
1122    PCRE_ERROR_BADMAGIC   the "magic number" was not found    PCRE_ERROR_BADMAGIC       the "magic number" was not found
1123    PCRE_ERROR_BADOPTION  the value of \fIwhat\fP was invalid    PCRE_ERROR_BADENDIANNESS  the pattern was compiled with different
1124                                endianness
1125      PCRE_ERROR_BADOPTION      the value of \fIwhat\fP was invalid
1126  .sp  .sp
1127  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
1128  check against passing an arbitrary memory pointer. Here is a typical call of  check against passing an arbitrary memory pointer. The endianness error can
1129  \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
1130    a typical call of \fBpcre_fullinfo()\fP, to obtain the length of the compiled
1131    pattern:
1132  .sp  .sp
1133    int rc;    int rc;
1134    size_t length;    size_t length;
# Line 1097  a NULL table pointer. Line 1162  a NULL table pointer.
1162  .sp  .sp
1163    PCRE_INFO_FIRSTBYTE    PCRE_INFO_FIRSTBYTE
1164  .sp  .sp
1165  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
1166  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,
1167  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
1168  still recognized for backwards compatibility.)  variable.
1169    .P
1170    If there is a fixed first value, for example, the letter "c" from a pattern
1171    such as (cat|cow|coyote), its value is returned. In the 8-bit library, the
1172    value is always less than 256; in the 16-bit library the value can be up to
1173    0xffff.
1174  .P  .P
1175  If there is a fixed first byte, for example, from a pattern such as  If there is no fixed first value, and if either
 (cat|cow|coyote), its value is returned. Otherwise, if either  
1176  .sp  .sp
1177  (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
1178  starts with "^", or  starts with "^", or
# Line 1118  returned. For anchored patterns, -2 is r Line 1187  returned. For anchored patterns, -2 is r
1187    PCRE_INFO_FIRSTTABLE    PCRE_INFO_FIRSTTABLE
1188  .sp  .sp
1189  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
1190  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
1191  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
1192  fourth argument should point to an \fBunsigned char *\fP variable.  fourth argument should point to an \fBunsigned char *\fP variable.
1193  .sp  .sp
# Line 1155  argument should point to a \fBsize_t\fP Line 1224  argument should point to a \fBsize_t\fP
1224  .sp  .sp
1225    PCRE_INFO_LASTLITERAL    PCRE_INFO_LASTLITERAL
1226  .sp  .sp
1227  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
1228  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
1229  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
1230  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
1231  follows something of variable length. For example, for the pattern  only if it follows something of variable length. For example, for the pattern
1232  /^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
1233  is -1.  is -1.
1234  .sp  .sp
# Line 1167  is -1. Line 1236  is -1.
1236  .sp  .sp
1237  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
1238  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
1239  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
1240  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
1241  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
1242  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
1243  that does match is at least that long.  that does match is at least that long.
# Line 1191  The map consists of a number of fixed-si Line 1260  The map consists of a number of fixed-si
1260  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
1261  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
1262  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
1263  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
1264  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,
1265  rest of the entry is the corresponding name, zero terminated.  most significant byte first. In the 16-bit library, the pointer points to
1266    16-bit data units, the first of which contains the parenthesis number. The rest
1267    of the entry is the corresponding name, zero terminated.
1268  .P  .P
1269  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
1270  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 1212  table in the order in which they were fo Line 1283  table in the order in which they were fo
1283  necessarily the case because later subpatterns may have lower numbers.  necessarily the case because later subpatterns may have lower numbers.
1284  .P  .P
1285  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
1286  (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
1287  ignored):  space - including newlines - is ignored):
1288  .sp  .sp
1289  .\" JOIN  .\" JOIN
1290    (?<date> (?<year>(\ed\ed)?\ed\ed) -    (?<date> (?<year>(\ed\ed)?\ed\ed) -
# Line 1268  For such patterns, the PCRE_ANCHORED bit Line 1339  For such patterns, the PCRE_ANCHORED bit
1339  .sp  .sp
1340    PCRE_INFO_SIZE    PCRE_INFO_SIZE
1341  .sp  .sp
1342  Return the size of the compiled pattern. The fourth argument should point to a  Return the size of the compiled pattern in bytes (for both libraries). The
1343  \fBsize_t\fP variable. This value does not include the size of the \fBpcre\fP  fourth argument should point to a \fBsize_t\fP variable. This value does not
1344  structure that is returned by \fBpcre_compile()\fP. The value that is passed as  include the size of the \fBpcre\fP structure that is returned by
1345  the argument to \fBpcre_malloc()\fP when \fBpcre_compile()\fP is getting memory  \fBpcre_compile()\fP. The value that is passed as the argument to
1346  in which to place the compiled data is the value returned by this option plus  \fBpcre_malloc()\fP when \fBpcre_compile()\fP is getting memory in which to
1347  the size of the \fBpcre\fP structure. Studying a compiled pattern, with or  place the compiled data is the value returned by this option plus the size of
1348  without JIT, does not alter the value returned by this option.  the \fBpcre\fP structure. Studying a compiled pattern, with or without JIT,
1349    does not alter the value returned by this option.
1350  .sp  .sp
1351    PCRE_INFO_STUDYSIZE    PCRE_INFO_STUDYSIZE
1352  .sp  .sp
1353  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
1354  \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
1355  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
1356  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
1357  that will speed up matching (see the section entitled  to record information that will speed up matching (see the section entitled
1358  .\" HTML <a href="#studyingapattern">  .\" HTML <a href="#studyingapattern">
1359  .\" </a>  .\" </a>
1360  "Studying a pattern"  "Studying a pattern"
# Line 1295  is made available via this option so tha Line 1367  is made available via this option so tha
1367  documentation for details).  documentation for details).
1368  .  .
1369  .  .
 .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).  
 .  
 .  
1370  .SH "REFERENCE COUNTS"  .SH "REFERENCE COUNTS"
1371  .rs  .rs
1372  .sp  .sp
# Line 1411  fields (not necessarily in this order): Line 1459  fields (not necessarily in this order):
1459    const unsigned char *\fItables\fP;    const unsigned char *\fItables\fP;
1460    unsigned char **\fImark\fP;    unsigned char **\fImark\fP;
1461  .sp  .sp
1462    In the 16-bit version of this structure, the \fImark\fP field has type
1463    "PCRE_UCHAR16 **".
1464    .P
1465  The \fIflags\fP field is a bitmap that specifies which of the other fields  The \fIflags\fP field is a bitmap that specifies which of the other fields
1466  are set. The flag bits are:  are set. The flag bits are:
1467  .sp  .sp
# Line 1495  called. See the Line 1546  called. See the
1546  documentation for a discussion of saving compiled patterns for later use.  documentation for a discussion of saving compiled patterns for later use.
1547  .P  .P
1548  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
1549  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
1550  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
1551  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
1552  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
1553  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
1554  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
1555  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
1556  backtracking control verbs, see the section entitled  backtracking control verbs, see the section entitled
1557  .\" HTML <a href="pcrepattern#backtrackcontrol">  .\" HTML <a href="pcrepattern#backtrackcontrol">
1558  .\" </a>  .\" </a>
# Line 1684  string is automatically checked when \fB Line 1735  string is automatically checked when \fB
1735  The value of \fIstartoffset\fP is also checked to ensure that it points to the  The value of \fIstartoffset\fP is also checked to ensure that it points to the
1736  start of a UTF-8 character. There is a discussion about the validity of UTF-8  start of a UTF-8 character. There is a discussion about the validity of UTF-8
1737  strings in the  strings in the
 .\" HTML <a href="pcre.html#utf8strings">  
 .\" </a>  
 section on UTF-8 support  
 .\"  
 in the main  
1738  .\" HREF  .\" HREF
1739  \fBpcre\fP  \fBpcreunicode\fP
1740  .\"  .\"
1741  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
1742  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
1743  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
1744  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
1745  returned (see the descriptions of these errors in the section entitled \fIError  (see the descriptions of these errors in the section entitled \fIError return
1746  return values from\fP \fBpcre_exec()\fP  values from\fP \fBpcre_exec()\fP
1747  .\" HTML <a href="#errorlist">  .\" HTML <a href="#errorlist">
1748  .\" </a>  .\" </a>
1749  below).  below).
# Line 1711  checks for performance reasons, you can Line 1757  checks for performance reasons, you can
1757  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
1758  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
1759  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
1760  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
1761  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
1762  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
1763  undefined. Your program may crash.  undefined. Your program may crash.
1764  .sp  .sp
1765    PCRE_PARTIAL_HARD    PCRE_PARTIAL_HARD
# Line 1748  documentation. Line 1794  documentation.
1794  .rs  .rs
1795  .sp  .sp
1796  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
1797  \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
1798  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
1799  subject, \fBpcre_exec()\fP returns PCRE_ERROR_BADOFFSET. When the starting  subject, \fBpcre_exec()\fP returns PCRE_ERROR_BADOFFSET. When the starting
1800  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 2043  the just-in-time processing stack is not Line 2089  the just-in-time processing stack is not
2089  \fBpcrejit\fP  \fBpcrejit\fP
2090  .\"  .\"
2091  documentation for more details.  documentation for more details.
2092    .sp
2093      PCRE_ERROR_BADMODE (-28)
2094    .sp
2095    This error is given if a pattern that was compiled by the 8-bit library is
2096    passed to a 16-bit library function, or vice versa.
2097    .sp
2098      PCRE_ERROR_BADENDIANNESS (-29)
2099    .sp
2100    This error is given if a pattern that was compiled and saved is reloaded on a
2101    host with different endianness. The utility function
2102    \fBpcre_pattern_to_host_byte_order()\fP can be used to convert such a pattern
2103    so that it runs on the new host.
2104  .P  .P
2105  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.
2106  .  .
# Line 2051  Error numbers -16 to -20 and -22 are not Line 2109  Error numbers -16 to -20 and -22 are not
2109  .SS "Reason codes for invalid UTF-8 strings"  .SS "Reason codes for invalid UTF-8 strings"
2110  .rs  .rs
2111  .sp  .sp
2112    This section applies only to the 8-bit library. The corresponding information
2113    for the 16-bit library is given in the
2114    .\" HREF
2115    \fBpcre16\fP
2116    .\"
2117    page.
2118    .P
2119  When \fBpcre_exec()\fP returns either PCRE_ERROR_BADUTF8 or  When \fBpcre_exec()\fP returns either PCRE_ERROR_BADUTF8 or
2120  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
2121  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 2534  extremely rare, as a vector of size 1000 Line 2599  extremely rare, as a vector of size 1000
2599  .SH "SEE ALSO"  .SH "SEE ALSO"
2600  .rs  .rs
2601  .sp  .sp
2602  \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),  \fBpcre16\fP(3), \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
2603  \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),  \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
2604  \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).  \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
2605  .  .
# Line 2553  Cambridge CB2 3QH, England. Line 2618  Cambridge CB2 3QH, England.
2618  .rs  .rs
2619  .sp  .sp
2620  .nf  .nf
2621  Last updated: 02 December 2011  Last updated: 17 January 2012
2622  Copyright (c) 1997-2011 University of Cambridge.  Copyright (c) 1997-2012 University of Cambridge.
2623  .fi  .fi

Legend:
Removed from v.836  
changed lines
  Added in v.887

  ViewVC Help
Powered by ViewVC 1.1.5