/[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 745 by ph10, Mon Nov 14 11:41:03 2011 UTC revision 1194 by ph10, Wed Oct 31 17:42:29 2012 UTC
# Line 1  Line 1 
1  .TH PCREAPI 3  .TH PCREAPI 3 "31 October 2012" "PCRE 8.32"
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 int pcre_jit_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
99    .ti +5n
100    .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
101    .ti +5n
102    .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP,
103    .ti +5n
104    .B pcre_jit_stack *\fIjstack\fP);
105    .PP
106    .B pcre_jit_stack *pcre_jit_stack_alloc(int \fIstartsize\fP, int \fImaxsize\fP);
107    .PP
108    .B void pcre_jit_stack_free(pcre_jit_stack *\fIstack\fP);
109    .PP
110    .B void pcre_assign_jit_stack(pcre_extra *\fIextra\fP,
111    .ti +5n
112    .B pcre_jit_callback \fIcallback\fP, void *\fIdata\fP);
113  .PP  .PP
114  .B const unsigned char *pcre_maketables(void);  .B const unsigned char *pcre_maketables(void);
115  .PP  .PP
# Line 103  PCRE - Perl-compatible regular expressio Line 117  PCRE - Perl-compatible regular expressio
117  .ti +5n  .ti +5n
118  .B int \fIwhat\fP, void *\fIwhere\fP);  .B int \fIwhat\fP, void *\fIwhere\fP);
119  .PP  .PP
 .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int  
 .B *\fIfirstcharptr\fP);  
 .PP  
120  .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);  .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);
121  .PP  .PP
122  .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);  .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);
123  .PP  .PP
124  .B char *pcre_version(void);  .B const char *pcre_version(void);
125    .PP
126    .B int pcre_pattern_to_host_byte_order(pcre *\fIcode\fP,
127    .ti +5n
128    .B pcre_extra *\fIextra\fP, const unsigned char *\fItables\fP);
129  .  .
130  .  .
131  .SH "PCRE NATIVE API INDIRECTED FUNCTIONS"  .SH "PCRE NATIVE API INDIRECTED FUNCTIONS"
# Line 127  PCRE - Perl-compatible regular expressio Line 142  PCRE - Perl-compatible regular expressio
142  .B int (*pcre_callout)(pcre_callout_block *);  .B int (*pcre_callout)(pcre_callout_block *);
143  .  .
144  .  .
145    .SH "PCRE 8-BIT, 16-BIT AND 32-BIT LIBRARIES"
146    .rs
147    .sp
148    From release 8.30, PCRE can be compiled as a library for handling 16-bit
149    character strings as well as, or instead of, the original library that handles
150    8-bit character strings. From release 8.32, PCRE can also be compiled as a
151    library for handling 32-bit character strings. To avoid too much complication,
152    this document describes the 8-bit versions of the functions, with only
153    occasional references to the 16-bit and 32-bit libraries.
154    .P
155    The 16-bit and 32-bit functions operate in the same way as their 8-bit
156    counterparts; they just use different data types for their arguments and
157    results, and their names start with \fBpcre16_\fP or \fBpcre32_\fP instead of
158    \fBpcre_\fP. For every option that has UTF8 in its name (for example,
159    PCRE_UTF8), there are corresponding 16-bit and 32-bit names with UTF8 replaced
160    by UTF16 or UTF32, respectively. This facility is in fact just cosmetic; the
161    16-bit and 32-bit option names define the same bit values.
162    .P
163    References to bytes and UTF-8 in this document should be read as references to
164    16-bit data quantities and UTF-16 when using the 16-bit library, or 32-bit data
165    quantities and UTF-32 when using the 32-bit library, unless specified
166    otherwise. More details of the specific differences for the 16-bit and 32-bit
167    libraries are given in the
168    .\" HREF
169    \fBpcre16\fP
170    .\"
171    and
172    .\" HREF
173    \fBpcre32\fP
174    .\"
175    pages.
176    .
177    .
178  .SH "PCRE API OVERVIEW"  .SH "PCRE API OVERVIEW"
179  .rs  .rs
180  .sp  .sp
181  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
182  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
183  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
184  in the  functionality. They are described in the
185  .\" HREF  .\" HREF
186  \fBpcreposix\fP  \fBpcreposix\fP
187  .\"  .\"
188  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++
189  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
190    documented in the
191  .\" HREF  .\" HREF
192  \fBpcrecpp\fP  \fBpcrecpp\fP
193  .\"  .\"
194  page.  page.
195  .P  .P
196  The native API C function prototypes are defined in the header file  The native API C function prototypes are defined in the header file
197  \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
198  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
199  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
200  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
201  Applications can use these to include support for different releases of PCRE.  for the library. Applications can use these to include support for different
202    releases of PCRE.
203  .P  .P
204  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
205  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 178  used if available, by setting an option Line 228  used if available, by setting an option
228  relevant. More complicated programs might need to make use of the functions  relevant. More complicated programs might need to make use of the functions
229  \fBpcre_jit_stack_alloc()\fP, \fBpcre_jit_stack_free()\fP, and  \fBpcre_jit_stack_alloc()\fP, \fBpcre_jit_stack_free()\fP, and
230  \fBpcre_assign_jit_stack()\fP in order to control the JIT code's memory usage.  \fBpcre_assign_jit_stack()\fP in order to control the JIT code's memory usage.
231  These functions are discussed in the  .P
232    From release 8.32 there is also a direct interface for JIT execution, which
233    gives improved performance. The JIT-specific functions are discussed in the
234  .\" HREF  .\" HREF
235  \fBpcrejit\fP  \fBpcrejit\fP
236  .\"  .\"
# Line 218  specialist use. Most commonly, no specia Line 270  specialist use. Most commonly, no specia
270  internal tables that are generated when PCRE is built are used.  internal tables that are generated when PCRE is built are used.
271  .P  .P
272  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
273  compiled pattern; \fBpcre_info()\fP is an obsolete version that returns only  compiled pattern. The function \fBpcre_version()\fP returns a pointer to a
274  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.  
275  .P  .P
276  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
277  containing a compiled pattern. This is provided for the benefit of  containing a compiled pattern. This is provided for the benefit of
# Line 269  PCRE supports five different conventions Line 319  PCRE supports five different conventions
319  strings: a single CR (carriage return) character, a single LF (linefeed)  strings: a single CR (carriage return) character, a single LF (linefeed)
320  character, the two-character sequence CRLF, any of the three preceding, or any  character, the two-character sequence CRLF, any of the three preceding, or any
321  Unicode newline sequence. The Unicode newline sequences are the three just  Unicode newline sequence. The Unicode newline sequences are the three just
322  mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,  mentioned, plus the single characters VT (vertical tab, U+000B), FF (form feed,
323  U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS  U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
324  (paragraph separator, U+2029).  (paragraph separator, U+2029).
325  .P  .P
# Line 332  which it was compiled. Details are given Line 382  which it was compiled. Details are given
382  .\" HREF  .\" HREF
383  \fBpcreprecompile\fP  \fBpcreprecompile\fP
384  .\"  .\"
385  documentation. However, compiling a regular expression with one version of PCRE  documentation, which includes a description of the
386  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
387  crashes.  expression with one version of PCRE for use with a different version is not
388    guaranteed to work and may cause crashes.
389  .  .
390  .  .
391  .SH "CHECKING BUILD-TIME OPTIONS"  .SH "CHECKING BUILD-TIME OPTIONS"
# Line 351  documentation has more details about the Line 402  documentation has more details about the
402  .P  .P
403  The first argument for \fBpcre_config()\fP is an integer, specifying which  The first argument for \fBpcre_config()\fP is an integer, specifying which
404  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
405  which the information is placed. The following information is available:  which the information is placed. The returned value is zero on success, or the
406    negative error code PCRE_ERROR_BADOPTION if the value in the first argument is
407    not recognized. The following information is available:
408  .sp  .sp
409    PCRE_CONFIG_UTF8    PCRE_CONFIG_UTF8
410  .sp  .sp
411  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;
412  otherwise it is set to zero.  otherwise it is set to zero. This value should normally be given to the 8-bit
413    version of this function, \fBpcre_config()\fP. If it is given to the 16-bit
414    or 32-bit version of this function, the result is PCRE_ERROR_BADOPTION.
415    .sp
416      PCRE_CONFIG_UTF16
417    .sp
418    The output is an integer that is set to one if UTF-16 support is available;
419    otherwise it is set to zero. This value should normally be given to the 16-bit
420    version of this function, \fBpcre16_config()\fP. If it is given to the 8-bit
421    or 32-bit version of this function, the result is PCRE_ERROR_BADOPTION.
422    .sp
423      PCRE_CONFIG_UTF32
424    .sp
425    The output is an integer that is set to one if UTF-32 support is available;
426    otherwise it is set to zero. This value should normally be given to the 32-bit
427    version of this function, \fBpcre32_config()\fP. If it is given to the 8-bit
428    or 16-bit version of this function, the result is PCRE_ERROR_BADOPTION.
429  .sp  .sp
430    PCRE_CONFIG_UNICODE_PROPERTIES    PCRE_CONFIG_UNICODE_PROPERTIES
431  .sp  .sp
# Line 368  properties is available; otherwise it is Line 437  properties is available; otherwise it is
437  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
438  compiling is available; otherwise it is set to zero.  compiling is available; otherwise it is set to zero.
439  .sp  .sp
440      PCRE_CONFIG_JITTARGET
441    .sp
442    The output is a pointer to a zero-terminated "const char *" string. If JIT
443    support is available, the string contains the name of the architecture for
444    which the JIT compiler is configured, for example "x86 32bit (little endian +
445    unaligned)". If JIT support is not available, the result is NULL.
446    .sp
447    PCRE_CONFIG_NEWLINE    PCRE_CONFIG_NEWLINE
448  .sp  .sp
449  The output is an integer whose value specifies the default character sequence  The output is an integer whose value specifies the default character sequence
450  that is recognized as meaning "newline". The four values that are supported  that is recognized as meaning "newline". The values that are supported in
451  are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, and -1 for ANY.  ASCII/Unicode environments are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for
452  Though they are derived from ASCII, the same values are returned in EBCDIC  ANYCRLF, and -1 for ANY. In EBCDIC environments, CR, ANYCRLF, and ANY yield the
453  environments. The default should normally correspond to the standard sequence  same values. However, the value for LF is normally 21, though some EBCDIC
454  for your operating system.  environments use 37. The corresponding values for CRLF are 3349 and 3365. The
455    default should normally correspond to the standard sequence for your operating
456    system.
457  .sp  .sp
458    PCRE_CONFIG_BSR    PCRE_CONFIG_BSR
459  .sp  .sp
# Line 387  or CRLF. The default can be overridden w Line 465  or CRLF. The default can be overridden w
465    PCRE_CONFIG_LINK_SIZE    PCRE_CONFIG_LINK_SIZE
466  .sp  .sp
467  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
468  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
469  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
470  matching. The default value of 2 is sufficient for all but the most massive  a number of bytes. For the 32-bit library, the value is either 2 or 4 and is
471  patterns, since it allows the compiled pattern to be up to 64K in size.  still a number of bytes. The default value of 2 is sufficient for all but the
472    most massive patterns, since it allows the compiled pattern to be up to 64K in
473    size. Larger values allow larger regular expressions to be compiled, at the
474    expense of slower matching.
475  .sp  .sp
476    PCRE_CONFIG_POSIX_MALLOC_THRESHOLD    PCRE_CONFIG_POSIX_MALLOC_THRESHOLD
477  .sp  .sp
# Line 473  documentation). For those options that c Line 554  documentation). For those options that c
554  the pattern, the contents of the \fIoptions\fP argument specifies their  the pattern, the contents of the \fIoptions\fP argument specifies their
555  settings at the start of compilation and execution. The PCRE_ANCHORED,  settings at the start of compilation and execution. The PCRE_ANCHORED,
556  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
557  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
558  compile time.  compile time.
559  .P  .P
560  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 565  not try to free it. Normally, the offset
565  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
566  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
567  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
568  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.  
569  .P  .P
570  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
571  sometimes point into the middle of a UTF-8 character.  cases, the offset passed back is the length of the pattern. Note that the
572    offset is in bytes, not characters, even in UTF-8 mode. It may sometimes point
573    into the middle of a UTF-8 character.
574  .P  .P
575  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
576  \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 589  documentation. Line 670  documentation.
670  .sp  .sp
671    PCRE_EXTENDED    PCRE_EXTENDED
672  .sp  .sp
673  If this bit is set, whitespace data characters in the pattern are totally  If this bit is set, white space data characters in the pattern are totally
674  ignored except when escaped or inside a character class. Whitespace does not  ignored except when escaped or inside a character class. White space does not
675  include the VT character (code 11). In addition, characters between an  include the VT character (code 11). In addition, characters between an
676  unescaped # outside a character class and the next newline, inclusive, are also  unescaped # outside a character class and the next newline, inclusive, are also
677  ignored. This is equivalent to Perl's /x option, and it can be changed within a  ignored. This is equivalent to Perl's /x option, and it can be changed within a
# Line 608  comment is a literal newline sequence in Line 689  comment is a literal newline sequence in
689  happen to represent a newline do not count.  happen to represent a newline do not count.
690  .P  .P
691  This option makes it possible to include comments inside complicated patterns.  This option makes it possible to include comments inside complicated patterns.
692  Note, however, that this applies only to data characters. Whitespace characters  Note, however, that this applies only to data characters. White space characters
693  may never appear within special character sequences in a pattern, for example  may never appear within special character sequences in a pattern, for example
694  within the sequence (?( that introduces a conditional subpattern.  within the sequence (?( that introduces a conditional subpattern.
695  .sp  .sp
# Line 644  string (by default this causes the curre Line 725  string (by default this causes the curre
725  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
726  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.
727  .P  .P
728  (3) \eU matches an upper case "U" character; by default \eU causes a compile  (3) \eU matches an upper case "U" character; by default \eU causes a compile
729  time error (Perl uses \eU to upper case subsequent characters).  time error (Perl uses \eU to upper case subsequent characters).
730  .P  .P
731  (4) \eu matches a lower case "u" character unless it is followed by four  (4) \eu matches a lower case "u" character unless it is followed by four
732  hexadecimal digits, in which case the hexadecimal number defines the code point  hexadecimal digits, in which case the hexadecimal number defines the code point
733  to match. By default, \eu causes a compile time error (Perl uses it to upper  to match. By default, \eu causes a compile time error (Perl uses it to upper
734  case the following character).  case the following character).
735  .P  .P
736  (5) \ex matches a lower case "x" character unless it is followed by two  (5) \ex matches a lower case "x" character unless it is followed by two
737  hexadecimal digits, in which case the hexadecimal number defines the code point  hexadecimal digits, in which case the hexadecimal number defines the code point
738  to match. By default, as in Perl, a hexadecimal number is always expected after  to match. By default, as in Perl, a hexadecimal number is always expected after
739  \ex, but it may have zero, one, or two digits (so, for example, \exz matches a  \ex, but it may have zero, one, or two digits (so, for example, \exz matches a
740  binary zero character followed by z).  binary zero character followed by z).
741  .sp  .sp
742    PCRE_MULTILINE    PCRE_MULTILINE
# Line 686  indicated by a single character (CR or L Line 767  indicated by a single character (CR or L
767  PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character  PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character
768  CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three  CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three
769  preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies  preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies
770  that any Unicode newline sequence should be recognized. The Unicode newline  that any Unicode newline sequence should be recognized.
771  sequences are the three just mentioned, plus the single characters VT (vertical  .P
772  tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line  In an ASCII/Unicode environment, the Unicode newline sequences are the three
773  separator, U+2028), and PS (paragraph separator, U+2029). The last two are  just mentioned, plus the single characters VT (vertical tab, U+000B), FF (form
774    feed, U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
775    (paragraph separator, U+2029). For the 8-bit library, the last two are
776  recognized only in UTF-8 mode.  recognized only in UTF-8 mode.
777  .P  .P
778    When PCRE is compiled to run in an EBCDIC (mainframe) environment, the code for
779    CR is 0x0d, the same as ASCII. However, the character code for LF is normally
780    0x15, though in some EBCDIC environments 0x25 is used. Whichever of these is
781    not LF is made to correspond to Unicode's NEL character. EBCDIC codes are all
782    less than 256. For more details, see the
783    .\" HREF
784    \fBpcrebuild\fP
785    .\"
786    documentation.
787    .P
788  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
789  as a number, giving eight possibilities. Currently only six are used (default  as a number, giving eight possibilities. Currently only six are used (default
790  plus the five values above). This means that if you set more than one newline  plus the five values above). This means that if you set more than one newline
# Line 700  PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is Line 793  PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is
793  other combinations may yield unused numbers and cause an error.  other combinations may yield unused numbers and cause an error.
794  .P  .P
795  The only time that a line break in a pattern is specially recognized when  The only time that a line break in a pattern is specially recognized when
796  compiling is when PCRE_EXTENDED is set. CR and LF are whitespace characters,  compiling is when PCRE_EXTENDED is set. CR and LF are white space characters,
797  and so are ignored in this mode. Also, an unescaped # outside a character class  and so are ignored in this mode. Also, an unescaped # outside a character class
798  indicates a comment that lasts until after the next line break sequence. In  indicates a comment that lasts until after the next line break sequence. In
799  other circumstances, line break sequences in patterns are treated as literal  other circumstances, line break sequences in patterns are treated as literal
# Line 755  with Perl. It can also be set by a (?U) Line 848  with Perl. It can also be set by a (?U)
848    PCRE_UTF8    PCRE_UTF8
849  .sp  .sp
850  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
851  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
852  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
853  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
854  behaviour of PCRE are given in the  given in the
855  .\" HREF  .\" HREF
856  \fBpcreunicode\fP  \fBpcreunicode\fP
857  .\"  .\"
# Line 768  page. Line 861  page.
861  .sp  .sp
862  When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is  When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is
863  automatically checked. There is a discussion about the  automatically checked. There is a discussion about the
864  .\" HTML <a href="pcre.html#utf8strings">  .\" HTML <a href="pcreunicode.html#utf8strings">
865  .\" </a>  .\" </a>
866  validity of UTF-8 strings  validity of UTF-8 strings
867  .\"  .\"
868  in the main  in the
869  .\" HREF  .\" HREF
870  \fBpcre\fP  \fBpcreunicode\fP
871  .\"  .\"
872  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
873  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
874  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.
875  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
876  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
877  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
878  the UTF-8 validity checking of subject strings.  validity checking of subject strings only. If the same string is being matched
879    many times, the option can be safely set for the second and subsequent
880    matchings to improve performance.
881  .  .
882  .  .
883  .SH "COMPILATION ERROR CODES"  .SH "COMPILATION ERROR CODES"
# Line 790  the UTF-8 validity checking of subject s Line 885  the UTF-8 validity checking of subject s
885  .sp  .sp
886  The following table lists the error codes than may be returned by  The following table lists the error codes than may be returned by
887  \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
888  both compiling functions. As PCRE has developed, some error codes have fallen  both compiling functions. Note that error messages are always 8-bit ASCII
889  out of use. To avoid confusion, they have not been re-used.  strings, even in 16-bit or 32-bit mode. As PCRE has developed, some error codes
890    have fallen out of use. To avoid confusion, they have not been re-used.
891  .sp  .sp
892     0  no error     0  no error
893     1  \e at end of pattern     1  \e at end of pattern
# Line 825  out of use. To avoid confusion, they hav Line 921  out of use. To avoid confusion, they hav
921    29  (?R or (?[+-]digits must be followed by )    29  (?R or (?[+-]digits must be followed by )
922    30  unknown POSIX class name    30  unknown POSIX class name
923    31  POSIX collating elements are not supported    31  POSIX collating elements are not supported
924    32  this version of PCRE is not compiled with PCRE_UTF8 support    32  this version of PCRE is compiled without UTF support
925    33  [this code is not in use]    33  [this code is not in use]
926    34  character value in \ex{...} sequence is too large    34  character value in \ex{...} sequence is too large
927    35  invalid condition (?(0)    35  invalid condition (?(0)
# Line 837  out of use. To avoid confusion, they hav Line 933  out of use. To avoid confusion, they hav
933    41  unrecognized character after (?P    41  unrecognized character after (?P
934    42  syntax error in subpattern name (missing terminator)    42  syntax error in subpattern name (missing terminator)
935    43  two named subpatterns have the same name    43  two named subpatterns have the same name
936    44  invalid UTF-8 string    44  invalid UTF-8 string (specifically UTF-8)
937    45  support for \eP, \ep, and \eX has not been compiled    45  support for \eP, \ep, and \eX has not been compiled
938    46  malformed \eP or \ep sequence    46  malformed \eP or \ep sequence
939    47  unknown property name after \eP or \ep    47  unknown property name after \eP or \ep
940    48  subpattern name is too long (maximum 32 characters)    48  subpattern name is too long (maximum 32 characters)
941    49  too many named subpatterns (maximum 10000)    49  too many named subpatterns (maximum 10000)
942    50  [this code is not in use]    50  [this code is not in use]
943    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
944    52  internal error: overran compiling workspace    52  internal error: overran compiling workspace
945    53  internal error: previously-checked referenced subpattern    53  internal error: previously-checked referenced subpattern
946          not found          not found
# Line 863  out of use. To avoid confusion, they hav Line 959  out of use. To avoid confusion, they hav
959    65  different names for subpatterns of the same number are    65  different names for subpatterns of the same number are
960          not allowed          not allowed
961    66  (*MARK) must have an argument    66  (*MARK) must have an argument
962    67  this version of PCRE is not compiled with PCRE_UCP support    67  this version of PCRE is not compiled with Unicode property
963            support
964    68  \ec must be followed by an ASCII character    68  \ec must be followed by an ASCII character
965    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
966      70  internal error: unknown opcode in find_fixedlength()
967      71  \eN is not supported in a class
968      72  too many forward references
969      73  disallowed Unicode code point (>= 0xd800 && <= 0xdfff)
970      74  invalid UTF-16 string (specifically UTF-16)
971      75  name is too long in (*MARK), (*PRUNE), (*SKIP), or (*THEN)
972      76  character value in \eu.... sequence is too large
973      77  invalid UTF-32 string (specifically UTF-32)
974  .sp  .sp
975  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
976  be used if the limits were changed when PCRE was built.  be used if the limits were changed when PCRE was built.
# Line 898  below Line 1003  below
1003  in the section on matching a pattern.  in the section on matching a pattern.
1004  .P  .P
1005  If studying the pattern does not produce any useful information,  If studying the pattern does not produce any useful information,
1006  \fBpcre_study()\fP returns NULL. In that circumstance, if the calling program  \fBpcre_study()\fP returns NULL by default. In that circumstance, if the
1007  wants to pass any of the other fields to \fBpcre_exec()\fP or  calling program wants to pass any of the other fields to \fBpcre_exec()\fP or
1008  \fBpcre_dfa_exec()\fP, it must set up its own \fBpcre_extra\fP block.  \fBpcre_dfa_exec()\fP, it must set up its own \fBpcre_extra\fP block. However,
1009  .P  if \fBpcre_study()\fP is called with the PCRE_STUDY_EXTRA_NEEDED option, it
1010  The second argument of \fBpcre_study()\fP contains option bits. There is only  returns a \fBpcre_extra\fP block even if studying did not find any additional
1011  one option: PCRE_STUDY_JIT_COMPILE. If this is set, and the just-in-time  information. It may still return NULL, however, if an error occurs in
1012  compiler is available, the pattern is further compiled into machine code that  \fBpcre_study()\fP.
1013  executes much faster than the \fBpcre_exec()\fP matching function. If  .P
1014  the just-in-time compiler is not available, this option is ignored. All other  The second argument of \fBpcre_study()\fP contains option bits. There are three
1015  bits in the \fIoptions\fP argument must be zero.  further options in addition to PCRE_STUDY_EXTRA_NEEDED:
1016    .sp
1017      PCRE_STUDY_JIT_COMPILE
1018      PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE
1019      PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE
1020    .sp
1021    If any of these are set, and the just-in-time compiler is available, the
1022    pattern is further compiled into machine code that executes much faster than
1023    the \fBpcre_exec()\fP interpretive matching function. If the just-in-time
1024    compiler is not available, these options are ignored. All undefined bits in the
1025    \fIoptions\fP argument must be zero.
1026  .P  .P
1027  JIT compilation is a heavyweight optimization. It can take some time for  JIT compilation is a heavyweight optimization. It can take some time for
1028  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
# Line 931  When you are finished with a pattern, yo Line 1046  When you are finished with a pattern, yo
1046  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
1047  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
1048  \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
1049  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
1050  new function when convenient.  function when convenient.
1051  .P  .P
1052  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
1053  real application there should be tests for errors):  real application there should be tests for errors):
# Line 954  real application there should be tests f Line 1069  real application there should be tests f
1069  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
1070  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
1071  mean that there are any strings of that length that match, but it does  mean that there are any strings of that length that match, but it does
1072  guarantee that no shorter strings match. The value is used by  guarantee that no shorter strings match. The value is used to avoid wasting
1073  \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP to avoid wasting time by trying to  time by trying to match strings that are shorter than the lower bound. You can
1074  match strings that are shorter than the lower bound. You can find out the value  find out the value in a calling program via the \fBpcre_fullinfo()\fP function.
 in a calling program via the \fBpcre_fullinfo()\fP function.  
1075  .P  .P
1076  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
1077  single fixed starting character. A bitmap of possible starting bytes is  single fixed starting character. A bitmap of possible starting bytes is
1078  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
1079  matching.  matching. (In 16-bit mode, the bitmap is used for 16-bit values less than 256.
1080    In 32-bit mode, the bitmap is used for 32-bit values less than 256.)
1081  .P  .P
1082  These two optimizations apply to both \fBpcre_exec()\fP and  These two optimizations apply to both \fBpcre_exec()\fP and
1083  \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.
1084  \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
1085  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,
1086  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
1087  \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
1088  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  
1089  .\" HTML <a href="#execoptions">  .\" HTML <a href="#execoptions">
1090  .\" </a>  .\" </a>
1091  below.  below.
# Line 985  below. Line 1098  below.
1098  .sp  .sp
1099  PCRE handles caseless matching, and determines whether characters are letters,  PCRE handles caseless matching, and determines whether characters are letters,
1100  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
1101  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
1102  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
1103  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
1104  property support. Alternatively, the PCRE_UCP option can be set at compile  Unicode character property support. Alternatively, the PCRE_UCP option can be
1105  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
1106  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
1107  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
1108  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
1109    two.
1110  .P  .P
1111  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
1112  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 1160  below in the section on matching a patte
1160  .B int \fIwhat\fP, void *\fIwhere\fP);  .B int \fIwhat\fP, void *\fIwhere\fP);
1161  .PP  .PP
1162  The \fBpcre_fullinfo()\fP function returns information about a compiled  The \fBpcre_fullinfo()\fP function returns information about a compiled
1163  pattern. It replaces the obsolete \fBpcre_info()\fP function, which is  pattern. It replaces the \fBpcre_info()\fP function, which was removed from the
1164  nevertheless retained for backwards compability (and is documented below).  library at version 8.30, after more than 10 years of obsolescence.
1165  .P  .P
1166  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
1167  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 1170  information is required, and the fourth
1170  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
1171  the following negative numbers:  the following negative numbers:
1172  .sp  .sp
1173    PCRE_ERROR_NULL       the argument \fIcode\fP was NULL    PCRE_ERROR_NULL           the argument \fIcode\fP was NULL
1174                          the argument \fIwhere\fP was NULL                              the argument \fIwhere\fP was NULL
1175    PCRE_ERROR_BADMAGIC   the "magic number" was not found    PCRE_ERROR_BADMAGIC       the "magic number" was not found
1176    PCRE_ERROR_BADOPTION  the value of \fIwhat\fP was invalid    PCRE_ERROR_BADENDIANNESS  the pattern was compiled with different
1177                                endianness
1178      PCRE_ERROR_BADOPTION      the value of \fIwhat\fP was invalid
1179  .sp  .sp
1180  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
1181  check against passing an arbitrary memory pointer. Here is a typical call of  check against passing an arbitrary memory pointer. The endianness error can
1182  \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
1183    a typical call of \fBpcre_fullinfo()\fP, to obtain the length of the compiled
1184    pattern:
1185  .sp  .sp
1186    int rc;    int rc;
1187    size_t length;    size_t length;
# Line 1097  a NULL table pointer. Line 1215  a NULL table pointer.
1215  .sp  .sp
1216    PCRE_INFO_FIRSTBYTE    PCRE_INFO_FIRSTBYTE
1217  .sp  .sp
1218  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
1219  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,
1220  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
1221  still recognized for backwards compatibility.)  variable.
1222    .P
1223    If there is a fixed first value, for example, the letter "c" from a pattern
1224    such as (cat|cow|coyote), its value is returned. In the 8-bit library, the
1225    value is always less than 256. In the 16-bit library the value can be up to
1226    0xffff. In the 32-bit library the value can be up to 0x10ffff.
1227  .P  .P
1228  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  
1229  .sp  .sp
1230  (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
1231  starts with "^", or  starts with "^", or
# Line 1114  starts with "^", or Line 1236  starts with "^", or
1236  -1 is returned, indicating that the pattern matches only at the start of a  -1 is returned, indicating that the pattern matches only at the start of a
1237  subject string or after any newline within the string. Otherwise -2 is  subject string or after any newline within the string. Otherwise -2 is
1238  returned. For anchored patterns, -2 is returned.  returned. For anchored patterns, -2 is returned.
1239    .P
1240    Since for the 32-bit library using the non-UTF-32 mode, this function is unable
1241    to return the full 32-bit range of the character, this value is deprecated;
1242    instead the PCRE_INFO_FIRSTCHARACTERFLAGS and PCRE_INFO_FIRSTCHARACTER values
1243    should be used.
1244  .sp  .sp
1245    PCRE_INFO_FIRSTTABLE    PCRE_INFO_FIRSTTABLE
1246  .sp  .sp
1247  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
1248  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
1249  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
1250  fourth argument should point to an \fBunsigned char *\fP variable.  fourth argument should point to an \fBunsigned char *\fP variable.
1251  .sp  .sp
# Line 1136  Return 1 if the (?J) or (?-J) option set Line 1263  Return 1 if the (?J) or (?-J) option set
1263  .sp  .sp
1264    PCRE_INFO_JIT    PCRE_INFO_JIT
1265  .sp  .sp
1266  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
1267  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
1268  \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
1269  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,
1270  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  
1271  .\" HREF  .\" HREF
1272  \fBpcrejit\fP  \fBpcrejit\fP
1273  .\"  .\"
1274  documentation for details of what can and cannot be handled.  documentation for details of what can and cannot be handled.
1275  .sp  .sp
1276      PCRE_INFO_JITSIZE
1277    .sp
1278    If the pattern was successfully studied with a JIT option, return the size of
1279    the JIT compiled code, otherwise return zero. The fourth argument should point
1280    to a \fBsize_t\fP variable.
1281    .sp
1282    PCRE_INFO_LASTLITERAL    PCRE_INFO_LASTLITERAL
1283  .sp  .sp
1284  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
1285  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
1286  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
1287  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
1288  follows something of variable length. For example, for the pattern  only if it follows something of variable length. For example, for the pattern
1289  /^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
1290  is -1.  is -1.
1291    .P
1292    Since for the 32-bit library using the non-UTF-32 mode, this function is unable
1293    to return the full 32-bit range of the character, this value is deprecated;
1294    instead the PCRE_INFO_REQUIREDCHARFLAGS and PCRE_INFO_REQUIREDCHAR values should
1295    be used.
1296    .sp
1297      PCRE_INFO_MAXLOOKBEHIND
1298    .sp
1299    Return the number of characters (NB not bytes) in the longest lookbehind
1300    assertion in the pattern. Note that the simple assertions \eb and \eB require a
1301    one-character lookbehind. This information is useful when doing multi-segment
1302    matching using the partial matching facilities.
1303  .sp  .sp
1304    PCRE_INFO_MINLENGTH    PCRE_INFO_MINLENGTH
1305  .sp  .sp
1306  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
1307  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
1308  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
1309  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
1310  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
1311  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
1312  that does match is at least that long.  that does match is at least that long.
# Line 1185  The map consists of a number of fixed-si Line 1329  The map consists of a number of fixed-si
1329  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
1330  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
1331  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
1332  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
1333  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,
1334  rest of the entry is the corresponding name, zero terminated.  most significant byte first. In the 16-bit library, the pointer points to
1335    16-bit data units, the first of which contains the parenthesis number.
1336    In the 32-bit library, the pointer points to 32-bit data units, the first of
1337    which contains the parenthesis number. The rest
1338    of the entry is the corresponding name, zero terminated.
1339  .P  .P
1340  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
1341  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 1206  table in the order in which they were fo Line 1354  table in the order in which they were fo
1354  necessarily the case because later subpatterns may have lower numbers.  necessarily the case because later subpatterns may have lower numbers.
1355  .P  .P
1356  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
1357  (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
1358  ignored):  space - including newlines - is ignored):
1359  .sp  .sp
1360  .\" JOIN  .\" JOIN
1361    (?<date> (?<year>(\ed\ed)?\ed\ed) -    (?<date> (?<year>(\ed\ed)?\ed\ed) -
# Line 1262  For such patterns, the PCRE_ANCHORED bit Line 1410  For such patterns, the PCRE_ANCHORED bit
1410  .sp  .sp
1411    PCRE_INFO_SIZE    PCRE_INFO_SIZE
1412  .sp  .sp
1413  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
1414  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
1415  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
1416  variable.  \fBpcre_compile()\fP. The value that is passed as the argument to
1417    \fBpcre_malloc()\fP when \fBpcre_compile()\fP is getting memory in which to
1418    place the compiled data is the value returned by this option plus the size of
1419    the \fBpcre\fP structure. Studying a compiled pattern, with or without JIT,
1420    does not alter the value returned by this option.
1421  .sp  .sp
1422    PCRE_INFO_STUDYSIZE    PCRE_INFO_STUDYSIZE
1423  .sp  .sp
1424  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
1425  \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
1426  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
1427  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
1428  that will speed up matching (see the section entitled  to record information that will speed up matching (see the section entitled
1429  .\" HTML <a href="#studyingapattern">  .\" HTML <a href="#studyingapattern">
1430  .\" </a>  .\" </a>
1431  "Studying a pattern"  "Studying a pattern"
# Line 1284  is made available via this option so tha Line 1436  is made available via this option so tha
1436  \fBpcreprecompile\fP  \fBpcreprecompile\fP
1437  .\"  .\"
1438  documentation for details).  documentation for details).
 .  
 .  
 .SH "OBSOLETE INFO FUNCTION"  
 .rs  
1439  .sp  .sp
1440  .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int    PCRE_INFO_FIRSTCHARACTERFLAGS
 .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:  
1441  .sp  .sp
1442    PCRE_ERROR_NULL       the argument \fIcode\fP was NULL  Return information about the first data unit of any matched string, for a
1443    PCRE_ERROR_BADMAGIC   the "magic number" was not found  non-anchored pattern. The fourth argument should point to an \fBint\fP
1444    variable.
1445    .P
1446    If there is a fixed first value, for example, the letter "c" from a pattern
1447    such as (cat|cow|coyote), 1 is returned, and the character value can be
1448    retrieved using PCRE_INFO_FIRSTCHARACTER.
1449    .P
1450    If there is no fixed first value, and if either
1451  .sp  .sp
1452  If the \fIoptptr\fP argument is not NULL, a copy of the options with which the  (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch
1453  pattern was compiled is placed in the integer it points to (see  starts with "^", or
1454  PCRE_INFO_OPTIONS above).  .sp
1455    (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set
1456    (if it were set, the pattern would be anchored),
1457    .sp
1458    2 is returned, indicating that the pattern matches only at the start of a
1459    subject string or after any newline within the string. Otherwise 0 is
1460    returned. For anchored patterns, 0 is returned.
1461    .sp
1462      PCRE_INFO_FIRSTCHARACTER
1463    .sp
1464    Return the fixed first character value, if PCRE_INFO_FIRSTCHARACTERFLAGS
1465    returned 1; otherwise returns 0. The fourth argument should point to an
1466    \fBuint_t\fP variable.
1467  .P  .P
1468  If the pattern is not anchored and the \fIfirstcharptr\fP argument is not NULL,  In the 8-bit library, the value is always less than 256. In the 16-bit library
1469  it is used to pass back information about the first character of any matched  the value can be up to 0xffff. In the 32-bit library in UTF-32 mode the value
1470  string (see PCRE_INFO_FIRSTBYTE above).  can be up to 0x10ffff, and up to 0xffffffff when not using UTF-32 mode.
1471    .P
1472    If there is no fixed first value, and if either
1473    .sp
1474    (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch
1475    starts with "^", or
1476    .sp
1477    (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set
1478    (if it were set, the pattern would be anchored),
1479    .sp
1480    -1 is returned, indicating that the pattern matches only at the start of a
1481    subject string or after any newline within the string. Otherwise -2 is
1482    returned. For anchored patterns, -2 is returned.
1483    .sp
1484      PCRE_INFO_REQUIREDCHARFLAGS
1485    .sp
1486    Returns 1 if there is a rightmost literal data unit that must exist in any
1487    matched string, other than at its start. The fourth argument should  point to
1488    an \fBint\fP variable. If there is no such value, 0 is returned. If returning
1489    1, the character value itself can be retrieved using PCRE_INFO_REQUIREDCHAR.
1490    .P
1491    For anchored patterns, a last literal value is recorded only if it follows
1492    something of variable length. For example, for the pattern /^a\ed+z\ed+/ the
1493    returned value 1 (with "z" returned from PCRE_INFO_REQUIREDCHAR), but for
1494    /^a\edz\ed/ the returned value is 0.
1495    .sp
1496      PCRE_INFO_REQUIREDCHAR
1497    .sp
1498    Return the value of the rightmost literal data unit that must exist in any
1499    matched string, other than at its start, if such a value has been recorded. The
1500    fourth argument should point to an \fBuint32_t\fP variable. If there is no such
1501    value, 0 is returned.
1502  .  .
1503  .  .
1504  .SH "REFERENCE COUNTS"  .SH "REFERENCE COUNTS"
# Line 1402  fields (not necessarily in this order): Line 1593  fields (not necessarily in this order):
1593    const unsigned char *\fItables\fP;    const unsigned char *\fItables\fP;
1594    unsigned char **\fImark\fP;    unsigned char **\fImark\fP;
1595  .sp  .sp
1596  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
1597  are set. The flag bits are:  "PCRE_UCHAR16 **".
1598  .sp  .sp
1599    PCRE_EXTRA_STUDY_DATA  In the 32-bit version of this structure, the \fImark\fP field has type
1600    "PCRE_UCHAR32 **".
1601    .P
1602    The \fIflags\fP field is used to specify which of the other fields are set. The
1603    flag bits are:
1604    .sp
1605      PCRE_EXTRA_CALLOUT_DATA
1606    PCRE_EXTRA_EXECUTABLE_JIT    PCRE_EXTRA_EXECUTABLE_JIT
1607      PCRE_EXTRA_MARK
1608    PCRE_EXTRA_MATCH_LIMIT    PCRE_EXTRA_MATCH_LIMIT
1609    PCRE_EXTRA_MATCH_LIMIT_RECURSION    PCRE_EXTRA_MATCH_LIMIT_RECURSION
1610    PCRE_EXTRA_CALLOUT_DATA    PCRE_EXTRA_STUDY_DATA
1611    PCRE_EXTRA_TABLES    PCRE_EXTRA_TABLES
   PCRE_EXTRA_MARK  
1612  .sp  .sp
1613  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
1614  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
1615  returned by \fBpcre_study()\fP, together with the appropriate flag bits. You  returned by \fBpcre_study()\fP, together with the appropriate flag bits. You
1616  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
1617  other fields and their corresponding flag bits.  fields and their corresponding flag bits.
1618  .P  .P
1619  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
1620  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 1432  patterns that are not anchored, the coun Line 1629  patterns that are not anchored, the coun
1629  in the subject string.  in the subject string.
1630  .P  .P
1631  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
1632  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.
1633  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
1634  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
1635  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.  
1636  .P  .P
1637  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
1638  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 1454  This limit is of use only if it is set s Line 1650  This limit is of use only if it is set s
1650  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
1651  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
1652  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,
1653  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.  
1654  .P  .P
1655  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
1656  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 1486  called. See the Line 1681  called. See the
1681  documentation for a discussion of saving compiled patterns for later use.  documentation for a discussion of saving compiled patterns for later use.
1682  .P  .P
1683  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
1684  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
1685  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
1686  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
1687  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
1688  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
1689  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
1690  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
1691  backtracking control verbs, see the section entitled  backtracking control verbs, see the section entitled
1692  .\" HTML <a href="pcrepattern#backtrackcontrol">  .\" HTML <a href="pcrepattern#backtrackcontrol">
1693  .\" </a>  .\" </a>
# Line 1512  documentation. Line 1707  documentation.
1707  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
1708  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,
1709  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART,  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART,
1710  PCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_SOFT, and  PCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_HARD, and
1711  PCRE_PARTIAL_HARD.  PCRE_PARTIAL_SOFT.
1712  .P  .P
1713  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)
1714  the only supported options for JIT execution are PCRE_NO_UTF8_CHECK,  compile options, the only supported options for JIT execution are
1715  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, and PCRE_NOTEMPTY_ATSTART. Note in  PCRE_NO_UTF8_CHECK, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY,
1716  particular that partial matching is not supported. If an unsupported option is  PCRE_NOTEMPTY_ATSTART, PCRE_PARTIAL_HARD, and PCRE_PARTIAL_SOFT. If an
1717  used, JIT execution is disabled and the normal interpretive code in  unsupported option is used, JIT execution is disabled and the normal
1718  \fBpcre_exec()\fP is run.  interpretive code in \fBpcre_exec()\fP is run.
1719  .sp  .sp
1720    PCRE_ANCHORED    PCRE_ANCHORED
1721  .sp  .sp
# Line 1639  causing performance to suffer, but ensur Line 1834  causing performance to suffer, but ensur
1834  "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)
1835  are considered at every possible starting position in the subject string. If  are considered at every possible starting position in the subject string. If
1836  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
1837  time.  time. The use of PCRE_NO_START_OPTIMIZE disables JIT execution; when it is set,
1838    matching is always done using interpretively.
1839  .P  .P
1840  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.
1841  Consider the pattern  Consider the pattern
# Line 1672  returned. Line 1868  returned.
1868  .sp  .sp
1869  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
1870  string is automatically checked when \fBpcre_exec()\fP is subsequently called.  string is automatically checked when \fBpcre_exec()\fP is subsequently called.
1871  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
1872  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
1873  strings in the  UTF-8 character. There is a discussion about the
1874  .\" HTML <a href="pcre.html#utf8strings">  .\" HTML <a href="pcreunicode.html#utf8strings">
1875  .\" </a>  .\" </a>
1876  section on UTF-8 support  validity of UTF-8 strings
1877  .\"  .\"
1878  in the main  in the
1879  .\" HREF  .\" HREF
1880  \fBpcre\fP  \fBpcreunicode\fP
1881  .\"  .\"
1882  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
1883  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
1884  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
1885  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
1886  returned (see the descriptions of these errors in the section entitled \fIError  (see the descriptions of these errors in the section entitled \fIError return
1887  return values from\fP \fBpcre_exec()\fP  values from\fP \fBpcre_exec()\fP
1888  .\" HTML <a href="#errorlist">  .\" HTML <a href="#errorlist">
1889  .\" </a>  .\" </a>
1890  below).  below).
# Line 1702  checks for performance reasons, you can Line 1898  checks for performance reasons, you can
1898  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
1899  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
1900  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
1901  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
1902  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
1903  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
1904  undefined. Your program may crash.  undefined. Your program may crash.
1905  .sp  .sp
1906    PCRE_PARTIAL_HARD    PCRE_PARTIAL_HARD
# Line 1739  documentation. Line 1935  documentation.
1935  .rs  .rs
1936  .sp  .sp
1937  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
1938  \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
1939  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
1940  subject, \fBpcre_exec()\fP returns PCRE_ERROR_BADOFFSET. When the starting  subject, \fBpcre_exec()\fP returns PCRE_ERROR_BADOFFSET. When the starting
1941  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 1827  string that it matched that is returned. Line 2023  string that it matched that is returned.
2023  .P  .P
2024  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
2025  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
2026  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
2027  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
2028  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
2029  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 2027  time. Line 2223  time.
2223  .sp  .sp
2224    PCRE_ERROR_JIT_STACKLIMIT (-27)    PCRE_ERROR_JIT_STACKLIMIT (-27)
2225  .sp  .sp
2226  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
2227  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
2228  the just-in-time processing stack is not large enough. See the  just-in-time processing stack is not large enough. See the
2229    .\" HREF
2230    \fBpcrejit\fP
2231    .\"
2232    documentation for more details.
2233    .sp
2234      PCRE_ERROR_BADMODE        (-28)
2235    .sp
2236    This error is given if a pattern that was compiled by the 8-bit library is
2237    passed to a 16-bit or 32-bit library function, or vice versa.
2238    .sp
2239      PCRE_ERROR_BADENDIANNESS  (-29)
2240    .sp
2241    This error is given if a pattern that was compiled and saved is reloaded on a
2242    host with different endianness. The utility function
2243    \fBpcre_pattern_to_host_byte_order()\fP can be used to convert such a pattern
2244    so that it runs on the new host.
2245    .sp
2246      PCRE_ERROR_JIT_BADOPTION
2247    .sp
2248    This error is returned when a pattern that was successfully studied using a JIT
2249    compile option is being matched, but the matching mode (partial or complete
2250    match) does not correspond to any JIT compilation mode. When the JIT fast path
2251    function is used, this error may be also given for invalid options. See the
2252  .\" HREF  .\" HREF
2253  \fBpcrejit\fP  \fBpcrejit\fP
2254  .\"  .\"
2255  documentation for more details.  documentation for more details.
2256    .sp
2257      PCRE_ERROR_BADLENGTH      (-32)
2258    .sp
2259    This error is given if \fBpcre_exec()\fP is called with a negative value for
2260    the \fIlength\fP argument.
2261  .P  .P
2262  Error numbers -16 to -20 and -22 are not used by \fBpcre_exec()\fP.  Error numbers -16 to -20, -22, and 30 are not used by \fBpcre_exec()\fP.
2263  .  .
2264  .  .
2265  .\" HTML <a name="badutf8reasons"></a>  .\" HTML <a name="badutf8reasons"></a>
2266  .SS "Reason codes for invalid UTF-8 strings"  .SS "Reason codes for invalid UTF-8 strings"
2267  .rs  .rs
2268  .sp  .sp
2269    This section applies only to the 8-bit library. The corresponding information
2270    for the 16-bit library is given in the
2271    .\" HREF
2272    \fBpcre16\fP
2273    .\"
2274    page. The corresponding information for the 32-bit library is given in the
2275    .\" HREF
2276    \fBpcre32\fP
2277    .\"
2278    page.
2279    .P
2280  When \fBpcre_exec()\fP returns either PCRE_ERROR_BADUTF8 or  When \fBpcre_exec()\fP returns either PCRE_ERROR_BADUTF8 or
2281  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
2282  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 2110  character. Line 2345  character.
2345  .sp  .sp
2346  The first byte of a character has the value 0xfe or 0xff. These values can  The first byte of a character has the value 0xfe or 0xff. These values can
2347  never occur in a valid UTF-8 string.  never occur in a valid UTF-8 string.
2348    .sp
2349      PCRE_UTF8_ERR2
2350    .sp
2351    Non-character. These are the last two characters in each plane (0xfffe, 0xffff,
2352    0x1fffe, 0x1ffff .. 0x10fffe, 0x10ffff), and the characters 0xfdd0..0xfdef.
2353  .  .
2354  .  .
2355  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
# Line 2339  other alternatives. Ultimately, when it Line 2579  other alternatives. Ultimately, when it
2579  will yield PCRE_ERROR_NOMATCH.  will yield PCRE_ERROR_NOMATCH.
2580  .  .
2581  .  .
2582    .SH "OBTAINING AN ESTIMATE OF STACK USAGE"
2583    .rs
2584    .sp
2585    Matching certain patterns using \fBpcre_exec()\fP can use a lot of process
2586    stack, which in certain environments can be rather limited in size. Some users
2587    find it helpful to have an estimate of the amount of stack that is used by
2588    \fBpcre_exec()\fP, to help them set recursion limits, as described in the
2589    .\" HREF
2590    \fBpcrestack\fP
2591    .\"
2592    documentation. The estimate that is output by \fBpcretest\fP when called with
2593    the \fB-m\fP and \fB-C\fP options is obtained by calling \fBpcre_exec\fP with
2594    the values NULL, NULL, NULL, -999, and -999 for its first five arguments.
2595    .P
2596    Normally, if its first argument is NULL, \fBpcre_exec()\fP immediately returns
2597    the negative error code PCRE_ERROR_NULL, but with this special combination of
2598    arguments, it returns instead a negative number whose absolute value is the
2599    approximate stack frame size in bytes. (A negative number is used so that it is
2600    clear that no match has happened.) The value is approximate because in some
2601    cases, recursive calls to \fBpcre_exec()\fP occur when there are one or two
2602    additional variables on the stack.
2603    .P
2604    If PCRE has been compiled to use the heap instead of the stack for recursion,
2605    the value returned is the size of each block that is obtained from the heap.
2606    .
2607    .
2608  .\" HTML <a name="dfamatch"></a>  .\" HTML <a name="dfamatch"></a>
2609  .SH "MATCHING A PATTERN: THE ALTERNATIVE FUNCTION"  .SH "MATCHING A PATTERN: THE ALTERNATIVE FUNCTION"
2610  .rs  .rs
# Line 2520  When a recursive subpattern is processed Line 2786  When a recursive subpattern is processed
2786  recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This  recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This
2787  error is given if the output vector is not large enough. This should be  error is given if the output vector is not large enough. This should be
2788  extremely rare, as a vector of size 1000 is used.  extremely rare, as a vector of size 1000 is used.
2789    .sp
2790      PCRE_ERROR_DFA_BADRESTART (-30)
2791    .sp
2792    When \fBpcre_dfa_exec()\fP is called with the \fBPCRE_DFA_RESTART\fP option,
2793    some plausibility checks are made on the contents of the workspace, which
2794    should contain data about the previous partial match. If any of these checks
2795    fail, this error is given.
2796  .  .
2797  .  .
2798  .SH "SEE ALSO"  .SH "SEE ALSO"
2799  .rs  .rs
2800  .sp  .sp
2801  \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),  \fBpcre16\fP(3), \fBpcre32\fP(3), \fBpcrebuild\fP(3), \fBpcrecallout\fP(3),
2802  \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),  \fBpcrecpp(3)\fP(3), \fBpcrematching\fP(3), \fBpcrepartial\fP(3),
2803  \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).  \fBpcreposix\fP(3), \fBpcreprecompile\fP(3), \fBpcresample\fP(3),
2804    \fBpcrestack\fP(3).
2805  .  .
2806  .  .
2807  .SH AUTHOR  .SH AUTHOR
# Line 2544  Cambridge CB2 3QH, England. Line 2818  Cambridge CB2 3QH, England.
2818  .rs  .rs
2819  .sp  .sp
2820  .nf  .nf
2821  Last updated: 14 November 2011  Last updated: 31 October 2012
2822  Copyright (c) 1997-2011 University of Cambridge.  Copyright (c) 1997-2012 University of Cambridge.
2823  .fi  .fi

Legend:
Removed from v.745  
changed lines
  Added in v.1194

  ViewVC Help
Powered by ViewVC 1.1.5