\n";
+$inpara = 1;
+}
+
+
+# Main program
+
+$innf = 0;
+$inpara = 0;
+$inpre = 0;
+$wrotetext = 0;
+$toc = 0;
+$ref = 1;
+
+while ($#ARGV >= 0 && $ARGV[0] =~ /^-/)
+ {
+ $toc = 1 if $ARGV[0] eq "-toc";
+ shift;
+ }
+
+# Initial output to STDOUT
+
+print <
+Return to the PCRE index page.
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+$ARGV[0] man page
+
+End
+
+print "\n" if ($toc);
+
+open(TEMP, ">/tmp/$$") || die "Can't open /tmp/$$ for output\n";
+
+while (
\n" if ($toc);
+
+# Copy the remainder to the standard output
+
+close(TEMP);
+open(TEMP, "/tmp/$$") || die "Can't open /tmp/$$ for input\n";
+
+print while ( and
that delimit literal sections will do the spacing.
+ # Always skip if no previous output.
+
+ elsif (/^\.sp/)
+ {
+ if ($wrotetext)
+ {
+ $_ =
\n
\n" if (!/^[\s.]/);
+ }
+ redo; # Now process the lookahead line we just read
+ }
+ }
+ elsif (/^\.TP/ || /^\.PP/ || /^\.P/)
+ {
+ &new_para();
+ }
+ elsif (/^\.SH\s*("?)(.*)\1/)
+ {
+ # Ignore the NAME section
+ if ($2 =~ /^NAME\b/)
+ {
+
$title
\n",
+ $ref, $ref);
+ $ref++;
+ }
+ else
+ {
+ print TEMP "
\n$title\n
\n";
+ }
+ }
+ elsif (/^\.SS\s*("?)(.*)\1/)
+ {
+ &end_para();
+ my($title) = &do_line($2);
+ print TEMP "
\n$title\n
\n";
+ }
+ elsif (/^\.B\s*(.*)/)
+ {
+ &new_para() if (!$inpara);
+ $_ = &do_line($1);
+ s/"(.*?)"/$1/g;
+ print TEMP "$_\n";
+ $wrotetext = 1;
+ }
+ elsif (/^\.I\s*(.*)/)
+ {
+ &new_para() if (!$inpara);
+ $_ = &do_line($1);
+ s/"(.*?)"/$1/g;
+ print TEMP "$_\n";
+ $wrotetext = 1;
+ }
+
+ # A comment that starts "HREF" takes the next line as a name that
+ # is turned into a hyperlink, using the text given, which might be
+ # in a special font. If it ends in () or (digits) or punctuation, they
+ # aren't part of the link.
+
+ elsif (/^\.\\"\s*HREF/)
+ {
+ $_=\n";
+ while (
\n";
+ $inpre = 1;
+ }
+ }
+ elsif ($inpre)
+ {
+ print TEMP "\n";
+ $inpre = 0;
+ }
+
+ # Add
to the end of a non-literal line if we are within .nf/.fi
+
+ $_ .= "
\n" if (!$inpre && $innf);
+
+ print TEMP;
+ $wrotetext = 1;
+ }
+
+# The TOC, if present, will have been written - terminate it
+
+print "
+The HTML documentation for PCRE comprises the following pages: +
+ +| pcre | +Introductory page |
| pcre16 | +Discussion of the 16-bit PCRE library |
| pcre32 | +Discussion of the 32-bit PCRE library |
| pcre-config | +Information about the installation configuration |
| pcreapi | +PCRE's native API |
| pcrebuild | +Options for building PCRE |
| pcrecallout | +The callout facility |
| pcrecompat | +Compability with Perl |
| pcrecpp | +The C++ wrapper for the PCRE library |
| pcredemo | +A demonstration C program that uses the PCRE library |
| pcregrep | +The pcregrep command |
| pcrejit | +Discussion of the just-in-time optimization support |
| pcrelimits | +Details of size and other limits |
| pcrematching | +Discussion of the two matching algorithms |
| pcrepartial | +Using PCRE for partial matching |
| pcrepattern | +Specification of the regular expressions supported by PCRE |
| pcreperform | +Some comments on performance |
| pcreposix | +The POSIX API to the PCRE library |
| pcreprecompile | +How to save and re-use compiled patterns |
| pcresample | +Discussion of the pcredemo program |
| pcrestack | +Discussion of PCRE's stack usage |
| pcresyntax | +Syntax quick-reference summary |
| pcretest | +The pcretest command for testing PCRE |
| pcreunicode | +Discussion of Unicode and UTF-8/UTF-16/UTF-32 support |
+There are also individual pages that summarize the interface for each function +in the library. There is a single page for each triple of 8-bit/16-bit/32-bit +functions. +
+ +| pcre_assign_jit_stack | +Assign stack for JIT matching |
| pcre_compile | +Compile a regular expression |
| pcre_compile2 | +Compile a regular expression (alternate interface) |
| pcre_config | +Show build-time configuration options |
| pcre_copy_named_substring | +Extract named substring into given buffer |
| pcre_copy_substring | +Extract numbered substring into given buffer |
| pcre_dfa_exec | +Match a compiled pattern to a subject string + (DFA algorithm; not Perl compatible) |
| pcre_free_study | +Free study data |
| pcre_exec | +Match a compiled pattern to a subject string + (Perl compatible) |
| pcre_free_substring | +Free extracted substring |
| pcre_free_substring_list | +Free list of extracted substrings |
| pcre_fullinfo | +Extract information about a pattern |
| pcre_get_named_substring | +Extract named substring into new memory |
| pcre_get_stringnumber | +Convert captured string name to number |
| pcre_get_substring | +Extract numbered substring into new memory |
| pcre_get_substring_list | +Extract all substrings into new memory |
| pcre_info | +Obsolete information extraction function |
| pcre_jit_stack_alloc | +Create a stack for JIT matching |
| pcre_jit_stack_free | +Free a JIT matching stack |
| pcre_maketables | +Build character tables in current locale |
| pcre_pattern_to_host_byte_order | +Convert compiled pattern to host byte order if necessary |
| pcre_refcount | +Maintain reference count in compiled pattern |
| pcre_study | +Study a compiled pattern |
| pcre_utf16_to_host_byte_order | +Convert UTF-16 string to host byte order if necessary |
| pcre_utf32_to_host_byte_order | +Convert UTF-32 string to host byte order if necessary |
| pcre_version | +Return PCRE version and release date |
+Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+pcre-config [--prefix] [--exec-prefix] [--version] [--libs] +[--libs16] [--libs32] [--libs-cpp] [--libs-posix] +[--cflags] [--cflags-posix] +
++pcre-config returns the configuration of the installed PCRE +libraries and the options required to compile a program to use them. Some of +the options apply only to the 8-bit, or 16-bit, or 32-bit libraries, +respectively, and are +not available if only one of those libraries has been built. If an unavailable +option is encountered, the "usage" information is output. +
++--prefix +Writes the directory prefix used in the PCRE installation for architecture +independent files (/usr on many systems, /usr/local on some +systems) to the standard output. +
++--exec-prefix +Writes the directory prefix used in the PCRE installation for architecture +dependent files (normally the same as --prefix) to the standard output. +
++--version +Writes the version number of the installed PCRE libraries to the standard +output. +
++--libs +Writes to the standard output the command line options required to link +with the 8-bit PCRE library (-lpcre on many systems). +
++--libs16 +Writes to the standard output the command line options required to link +with the 16-bit PCRE library (-lpcre16 on many systems). +
++--libs32 +Writes to the standard output the command line options required to link +with the 32-bit PCRE library (-lpcre32 on many systems). +
++--libs-cpp +Writes to the standard output the command line options required to link with +PCRE's C++ wrapper library (-lpcrecpp -lpcre on many +systems). +
++--libs-posix +Writes to the standard output the command line options required to link with +PCRE's POSIX API wrapper library (-lpcreposix -lpcre on many +systems). +
++--cflags +Writes to the standard output the command line options required to compile +files that use PCRE (this may include some -I options, but is blank on +many systems). +
++--cflags-posix +Writes to the standard output the command line options required to compile +files that use PCRE's POSIX API wrapper library (this may include some -I +options, but is blank on many systems). +
++pcre(3) +
++This manual page was originally written by Mark Baker for the Debian GNU/Linux +system. It has been subsequently revised as a generic PCRE man page. +
+
+Last updated: 24 June 2012
+
+
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcre.html b/tools/pcre/doc/html/pcre.html new file mode 100644 index 00000000..edb7479a --- /dev/null +++ b/tools/pcre/doc/html/pcre.html @@ -0,0 +1,204 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+The PCRE library is a set of functions that implement regular expression +pattern matching using the same syntax and semantics as Perl, with just a few +differences. Some features that appeared in Python and PCRE before they +appeared in Perl are also available using the Python syntax, there is some +support for one or two .NET and Oniguruma syntax items, and there is an option +for requesting some minor changes that give better JavaScript compatibility. +
++Starting with release 8.30, it is possible to compile two separate PCRE +libraries: the original, which supports 8-bit character strings (including +UTF-8 strings), and a second library that supports 16-bit character strings +(including UTF-16 strings). The build process allows either one or both to be +built. The majority of the work to make this possible was done by Zoltan +Herczeg. +
++Starting with release 8.32 it is possible to compile a third separate PCRE +library, which supports 32-bit character strings (including +UTF-32 strings). The build process allows any set of the 8-, 16- and 32-bit +libraries. The work to make this possible was done by Christian Persch. +
++The three libraries contain identical sets of functions, except that the names +in the 16-bit library start with pcre16_ instead of pcre_, and the +names in the 32-bit library start with pcre32_ instead of pcre_. To +avoid over-complication and reduce the documentation maintenance load, most of +the documentation describes the 8-bit library, with the differences for the +16-bit and 32-bit libraries described separately in the +pcre16 +and +pcre32 +pages. References to functions or structures of the form pcre[16|32]_xxx +should be read as meaning "pcre_xxx when using the 8-bit library, +pcre16_xxx when using the 16-bit library, or pcre32_xxx when using +the 32-bit library". +
++The current implementation of PCRE corresponds approximately with Perl 5.12, +including support for UTF-8/16/32 encoded strings and Unicode general category +properties. However, UTF-8/16/32 and Unicode support has to be explicitly +enabled; it is not the default. The Unicode tables correspond to Unicode +release 6.2.0. +
++In addition to the Perl-compatible matching function, PCRE contains an +alternative function that matches the same compiled patterns in a different +way. In certain circumstances, the alternative function has some advantages. +For a discussion of the two matching algorithms, see the +pcrematching +page. +
++PCRE is written in C and released as a C library. A number of people have +written wrappers and interfaces of various kinds. In particular, Google Inc. +have provided a comprehensive C++ wrapper for the 8-bit library. This is now +included as part of the PCRE distribution. The +pcrecpp +page has details of this interface. Other people's contributions can be found +in the Contrib directory at the primary FTP site, which is: +ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre +
++Details of exactly which Perl regular expression features are and are not +supported by PCRE are given in separate documents. See the +pcrepattern +and +pcrecompat +pages. There is a syntax summary in the +pcresyntax +page. +
++Some features of PCRE can be included, excluded, or changed when the library is +built. The +pcre_config() +function makes it possible for a client to discover which features are +available. The features themselves are described in the +pcrebuild +page. Documentation about building PCRE for various operating systems can be +found in the README and NON-AUTOTOOLS_BUILD files in the source +distribution. +
++The libraries contains a number of undocumented internal functions and data +tables that are used by more than one of the exported external functions, but +which are not intended for use by external callers. Their names all begin with +"_pcre_" or "_pcre16_" or "_pcre32_", which hopefully will not provoke any name +clashes. In some environments, it is possible to control which external symbols +are exported when a shared library is built, and in these cases the +undocumented symbols are not exported. +
++If you are using PCRE in a non-UTF application that permits users to supply +arbitrary patterns for compilation, you should be aware of a feature that +allows users to turn on UTF support from within a pattern, provided that PCRE +was built with UTF support. For example, an 8-bit pattern that begins with +"(*UTF8)" or "(*UTF)" turns on UTF-8 mode, which interprets patterns and +subjects as strings of UTF-8 characters instead of individual 8-bit characters. +This causes both the pattern and any data against which it is matched to be +checked for UTF-8 validity. If the data string is very long, such a check might +use sufficiently many resources as to cause your application to lose +performance. +
++The best way of guarding against this possibility is to use the +pcre_fullinfo() function to check the compiled pattern's options for UTF. +
++If your application is one that supports UTF, be aware that validity checking +can take time. If the same data string is to be matched many times, you can use +the PCRE_NO_UTF[8|16|32]_CHECK option for the second and subsequent matches to +save redundant checks. +
++Another way that performance can be hit is by running a pattern that has a very +large search tree against a string that will never match. Nested unlimited +repeats in a pattern are a common example. PCRE provides some protection +against this: see the PCRE_EXTRA_MATCH_LIMIT feature in the +pcreapi +page. +
++The user documentation for PCRE comprises a number of different sections. In +the "man" format, each of these is a separate "man page". In the HTML format, +each is a separate page, linked from the index page. In the plain text format, +all the sections, except the pcredemo section, are concatenated, for ease +of searching. The sections are as follows: +
+ pcre this document + pcre16 details of the 16-bit library + pcre32 details of the 32-bit library + pcre-config show PCRE installation configuration information + pcreapi details of PCRE's native C API + pcrebuild options for building PCRE + pcrecallout details of the callout feature + pcrecompat discussion of Perl compatibility + pcrecpp details of the C++ wrapper for the 8-bit library + pcredemo a demonstration C program that uses PCRE + pcregrep description of the pcregrep command (8-bit only) + pcrejit discussion of the just-in-time optimization support + pcrelimits details of size and other limits + pcrematching discussion of the two matching algorithms + pcrepartial details of the partial matching facility + pcrepattern syntax and semantics of supported regular expressions + pcreperform discussion of performance issues + pcreposix the POSIX-compatible C API for the 8-bit library + pcreprecompile details of saving and re-using precompiled patterns + pcresample discussion of the pcredemo program + pcrestack discussion of stack usage + pcresyntax quick syntax reference + pcretest description of the pcretest testing command + pcreunicode discussion of Unicode and UTF-8/16/32 support ++In addition, in the "man" and HTML formats, there is a short page for each +C library function, listing its arguments and results. + +
+Philip Hazel
+
+University Computing Service
+
+Cambridge CB2 3QH, England.
+
+
+Putting an actual email address here seems to have been a spam magnet, so I've +taken it away. If you want to email me, use my two initials, followed by the +two digits 10, at the domain cam.ac.uk. +
+
+Last updated: 11 November 2012
+
+Copyright © 1997-2012 University of Cambridge.
+
+
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcre16.html b/tools/pcre/doc/html/pcre16.html new file mode 100644 index 00000000..179b2ada --- /dev/null +++ b/tools/pcre/doc/html/pcre16.html @@ -0,0 +1,383 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+#include <pcre.h> +
++pcre16 *pcre16_compile(PCRE_SPTR16 pattern, int options, +const char **errptr, int *erroffset, +const unsigned char *tableptr); +
++pcre16 *pcre16_compile2(PCRE_SPTR16 pattern, int options, +int *errorcodeptr, +const char **errptr, int *erroffset, +const unsigned char *tableptr); +
++pcre16_extra *pcre16_study(const pcre16 *code, int options, +const char **errptr); +
++void pcre16_free_study(pcre16_extra *extra); +
++int pcre16_exec(const pcre16 *code, const pcre16_extra *extra, +PCRE_SPTR16 subject, int length, int startoffset, +int options, int *ovector, int ovecsize); +
++int pcre16_dfa_exec(const pcre16 *code, const pcre16_extra *extra, +PCRE_SPTR16 subject, int length, int startoffset, +int options, int *ovector, int ovecsize, +int *workspace, int wscount); +
++int pcre16_copy_named_substring(const pcre16 *code, +PCRE_SPTR16 subject, int *ovector, +int stringcount, PCRE_SPTR16 stringname, +PCRE_UCHAR16 *buffer, int buffersize); +
++int pcre16_copy_substring(PCRE_SPTR16 subject, int *ovector, +int stringcount, int stringnumber, PCRE_UCHAR16 *buffer, +int buffersize); +
++int pcre16_get_named_substring(const pcre16 *code, +PCRE_SPTR16 subject, int *ovector, +int stringcount, PCRE_SPTR16 stringname, +PCRE_SPTR16 *stringptr); +
++int pcre16_get_stringnumber(const pcre16 *code, +PCRE_SPTR16 name); +
++int pcre16_get_stringtable_entries(const pcre16 *code, +PCRE_SPTR16 name, PCRE_UCHAR16 **first, PCRE_UCHAR16 **last); +
++int pcre16_get_substring(PCRE_SPTR16 subject, int *ovector, +int stringcount, int stringnumber, +PCRE_SPTR16 *stringptr); +
++int pcre16_get_substring_list(PCRE_SPTR16 subject, +int *ovector, int stringcount, PCRE_SPTR16 **listptr); +
++void pcre16_free_substring(PCRE_SPTR16 stringptr); +
++void pcre16_free_substring_list(PCRE_SPTR16 *stringptr); +
++pcre16_jit_stack *pcre16_jit_stack_alloc(int startsize, int maxsize); +
++void pcre16_jit_stack_free(pcre16_jit_stack *stack); +
++void pcre16_assign_jit_stack(pcre16_extra *extra, +pcre16_jit_callback callback, void *data); +
++const unsigned char *pcre16_maketables(void); +
++int pcre16_fullinfo(const pcre16 *code, const pcre16_extra *extra, +int what, void *where); +
++int pcre16_refcount(pcre16 *code, int adjust); +
++int pcre16_config(int what, void *where); +
++const char *pcre16_version(void); +
++int pcre16_pattern_to_host_byte_order(pcre16 *code, +pcre16_extra *extra, const unsigned char *tables); +
++void *(*pcre16_malloc)(size_t); +
++void (*pcre16_free)(void *); +
++void *(*pcre16_stack_malloc)(size_t); +
++void (*pcre16_stack_free)(void *); +
++int (*pcre16_callout)(pcre16_callout_block *); +
++int pcre16_utf16_to_host_byte_order(PCRE_UCHAR16 *output, +PCRE_SPTR16 input, int length, int *byte_order, +int keep_boms); +
++Starting with release 8.30, it is possible to compile a PCRE library that +supports 16-bit character strings, including UTF-16 strings, as well as or +instead of the original 8-bit library. The majority of the work to make this +possible was done by Zoltan Herczeg. The two libraries contain identical sets +of functions, used in exactly the same way. Only the names of the functions and +the data types of their arguments and results are different. To avoid +over-complication and reduce the documentation maintenance load, most of the +PCRE documentation describes the 8-bit library, with only occasional references +to the 16-bit library. This page describes what is different when you use the +16-bit library. +
++WARNING: A single application can be linked with both libraries, but you must +take care when processing any particular pattern to use functions from just one +library. For example, if you want to study a pattern that was compiled with +pcre16_compile(), you must do so with pcre16_study(), not +pcre_study(), and you must free the study data with +pcre16_free_study(). +
++There is only one header file, pcre.h. It contains prototypes for all the +functions in all libraries, as well as definitions of flags, structures, error +codes, etc. +
++In Unix-like systems, the 16-bit library is called libpcre16, and can +normally be accesss by adding -lpcre16 to the command for linking an +application that uses PCRE. +
++In the 8-bit library, strings are passed to PCRE library functions as vectors +of bytes with the C type "char *". In the 16-bit library, strings are passed as +vectors of unsigned 16-bit quantities. The macro PCRE_UCHAR16 specifies an +appropriate data type, and PCRE_SPTR16 is defined as "const PCRE_UCHAR16 *". In +very many environments, "short int" is a 16-bit data type. When PCRE is built, +it defines PCRE_UCHAR16 as "unsigned short int", but checks that it really is a +16-bit data type. If it is not, the build fails with an error message telling +the maintainer to modify the definition appropriately. +
++The types of the opaque structures that are used for compiled 16-bit patterns +and JIT stacks are pcre16 and pcre16_jit_stack respectively. The +type of the user-accessible structure that is returned by pcre16_study() +is pcre16_extra, and the type of the structure that is used for passing +data to a callout function is pcre16_callout_block. These structures +contain the same fields, with the same names, as their 8-bit counterparts. The +only difference is that pointers to character strings are 16-bit instead of +8-bit types. +
++For every function in the 8-bit library there is a corresponding function in +the 16-bit library with a name that starts with pcre16_ instead of +pcre_. The prototypes are listed above. In addition, there is one extra +function, pcre16_utf16_to_host_byte_order(). This is a utility function +that converts a UTF-16 character string to host byte order if necessary. The +other 16-bit functions expect the strings they are passed to be in host byte +order. +
++The input and output arguments of +pcre16_utf16_to_host_byte_order() may point to the same address, that is, +conversion in place is supported. The output buffer must be at least as long as +the input. +
++The length argument specifies the number of 16-bit data units in the +input string; a negative value specifies a zero-terminated string. +
++If byte_order is NULL, it is assumed that the string starts off in host +byte order. This may be changed by byte-order marks (BOMs) anywhere in the +string (commonly as the first character). +
++If byte_order is not NULL, a non-zero value of the integer to which it +points means that the input starts off in host byte order, otherwise the +opposite order is assumed. Again, BOMs in the string can change this. The final +byte order is passed back at the end of processing. +
++If keep_boms is not zero, byte-order mark characters (0xfeff) are copied +into the output string. Otherwise they are discarded. +
++The result of the function is the number of 16-bit units placed into the output +buffer, including the zero terminator if the string was zero-terminated. +
++The offsets within subject strings that are returned by the matching functions +are in 16-bit units rather than bytes. +
++The name-to-number translation table that is maintained for named subpatterns +uses 16-bit characters. The pcre16_get_stringtable_entries() function +returns the length of each entry in the table as the number of 16-bit data +units. +
++There are two new general option names, PCRE_UTF16 and PCRE_NO_UTF16_CHECK, +which correspond to PCRE_UTF8 and PCRE_NO_UTF8_CHECK in the 8-bit library. In +fact, these new options define the same bits in the options word. There is a +discussion about the +validity of UTF-16 strings +in the +pcreunicode +page. +
++For the pcre16_config() function there is an option PCRE_CONFIG_UTF16 +that returns 1 if UTF-16 support is configured, otherwise 0. If this option is +given to pcre_config() or pcre32_config(), or if the +PCRE_CONFIG_UTF8 or PCRE_CONFIG_UTF32 option is given to pcre16_config(), +the result is the PCRE_ERROR_BADOPTION error. +
++In 16-bit mode, when PCRE_UTF16 is not set, character values are treated in the +same way as in 8-bit, non UTF-8 mode, except, of course, that they can range +from 0 to 0xffff instead of 0 to 0xff. Character types for characters less than +0xff can therefore be influenced by the locale in the same way as before. +Characters greater than 0xff have only one case, and no "type" (such as letter +or digit). +
++In UTF-16 mode, the character code is Unicode, in the range 0 to 0x10ffff, with +the exception of values in the range 0xd800 to 0xdfff because those are +"surrogate" values that are used in pairs to encode values greater than 0xffff. +
++A UTF-16 string can indicate its endianness by special code knows as a +byte-order mark (BOM). The PCRE functions do not handle this, expecting strings +to be in host byte order. A utility function called +pcre16_utf16_to_host_byte_order() is provided to help with this (see +above). +
++The errors PCRE_ERROR_BADUTF16_OFFSET and PCRE_ERROR_SHORTUTF16 correspond to +their 8-bit counterparts. The error PCRE_ERROR_BADMODE is given when a compiled +pattern is passed to a function that processes patterns in the other +mode, for example, if a pattern compiled with pcre_compile() is passed to +pcre16_exec(). +
++There are new error codes whose names begin with PCRE_UTF16_ERR for invalid +UTF-16 strings, corresponding to the PCRE_UTF8_ERR codes for UTF-8 strings that +are described in the section entitled +"Reason codes for invalid UTF-8 strings" +in the main +pcreapi +page. The UTF-16 errors are: +
+ PCRE_UTF16_ERR1 Missing low surrogate at end of string + PCRE_UTF16_ERR2 Invalid low surrogate follows high surrogate + PCRE_UTF16_ERR3 Isolated low surrogate + PCRE_UTF16_ERR4 Non-character ++ +
+If there is an error while compiling a pattern, the error text that is passed +back by pcre16_compile() or pcre16_compile2() is still an 8-bit +character string, zero-terminated. +
++The subject and mark fields in the callout block that is passed to +a callout function point to 16-bit vectors. +
++The pcretest program continues to operate with 8-bit input and output +files, but it can be used for testing the 16-bit library. If it is run with the +command line option -16, patterns and subject strings are converted from +8-bit to 16-bit before being passed to PCRE, and the 16-bit library functions +are used instead of the 8-bit ones. Returned 16-bit strings are converted to +8-bit for output. If both the 8-bit and the 32-bit libraries were not compiled, +pcretest defaults to 16-bit and the -16 option is ignored. +
++When PCRE is being built, the RunTest script that is called by "make +check" uses the pcretest -C option to discover which of the 8-bit, +16-bit and 32-bit libraries has been built, and runs the tests appropriately. +
++Not all the features of the 8-bit library are available with the 16-bit +library. The C++ and POSIX wrapper functions support only the 8-bit library, +and the pcregrep program is at present 8-bit only. +
+
+Philip Hazel
+
+University Computing Service
+
+Cambridge CB2 3QH, England.
+
+
+Last updated: 08 November 2012
+
+Copyright © 1997-2012 University of Cambridge.
+
+
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcre_assign_jit_stack.html b/tools/pcre/doc/html/pcre_assign_jit_stack.html new file mode 100644 index 00000000..d77d4e1c --- /dev/null +++ b/tools/pcre/doc/html/pcre_assign_jit_stack.html @@ -0,0 +1,76 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+SYNOPSIS
+
+
+#include <pcre.h> +
++void pcre_assign_jit_stack(pcre_extra *extra, +pcre_jit_callback callback, void *data); +
++void pcre16_assign_jit_stack(pcre16_extra *extra, +pcre16_jit_callback callback, void *data); +
++void pcre32_assign_jit_stack(pcre32_extra *extra, +pcre32_jit_callback callback, void *data); +
++This function provides control over the memory used as a stack at run-time by a +call to pcre[16|32]_exec() with a pattern that has been successfully +compiled with JIT optimization. The arguments are: +
+ extra the data pointer returned by pcre[16|32]_study() + callback a callback function + data a JIT stack or a value to be passed to the callback + function ++ +
+If callback is NULL and data is NULL, an internal 32K block on +the machine stack is used. +
++If callback is NULL and data is not NULL, data must +be a valid JIT stack, the result of calling pcre[16|32]_jit_stack_alloc(). +
++If callback not NULL, it is called with data as an argument at +the start of matching, in order to set up a JIT stack. If the result is NULL, +the internal 32K stack is used; otherwise the return value must be a valid JIT +stack, the result of calling pcre[16|32]_jit_stack_alloc(). +
++You may safely assign the same JIT stack to multiple patterns, as long as they +are all matched in the same thread. In a multithread application, each thread +must use its own JIT stack. For more details, see the +pcrejit +page. +
++There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcre_compile.html b/tools/pcre/doc/html/pcre_compile.html new file mode 100644 index 00000000..01214751 --- /dev/null +++ b/tools/pcre/doc/html/pcre_compile.html @@ -0,0 +1,108 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+SYNOPSIS
+
+
+#include <pcre.h> +
++pcre *pcre_compile(const char *pattern, int options, +const char **errptr, int *erroffset, +const unsigned char *tableptr); +
++pcre16 *pcre16_compile(PCRE_SPTR16 pattern, int options, +const char **errptr, int *erroffset, +const unsigned char *tableptr); +
++pcre32 *pcre32_compile(PCRE_SPTR32 pattern, int options, +const char **errptr, int *erroffset, +const unsigned char *tableptr); +
++This function compiles a regular expression into an internal form. It is the +same as pcre[16|32]_compile2(), except for the absence of the +errorcodeptr argument. Its arguments are: +
+ pattern A zero-terminated string containing the + regular expression to be compiled + options Zero or more option bits + errptr Where to put an error message + erroffset Offset in pattern where error was found + tableptr Pointer to character tables, or NULL to + use the built-in default ++The option bits are: +
+ PCRE_ANCHORED Force pattern anchoring + PCRE_AUTO_CALLOUT Compile automatic callouts + PCRE_BSR_ANYCRLF \R matches only CR, LF, or CRLF + PCRE_BSR_UNICODE \R matches all Unicode line endings + PCRE_CASELESS Do caseless matching + PCRE_DOLLAR_ENDONLY $ not to match newline at end + PCRE_DOTALL . matches anything including NL + PCRE_DUPNAMES Allow duplicate names for subpatterns + PCRE_EXTENDED Ignore white space and # comments + PCRE_EXTRA PCRE extra features + (not much use currently) + PCRE_FIRSTLINE Force matching to be before newline + PCRE_JAVASCRIPT_COMPAT JavaScript compatibility + PCRE_MULTILINE ^ and $ match newlines within data + PCRE_NEWLINE_ANY Recognize any Unicode newline sequence + PCRE_NEWLINE_ANYCRLF Recognize CR, LF, and CRLF as newline + sequences + PCRE_NEWLINE_CR Set CR as the newline sequence + PCRE_NEWLINE_CRLF Set CRLF as the newline sequence + PCRE_NEWLINE_LF Set LF as the newline sequence + PCRE_NO_AUTO_CAPTURE Disable numbered capturing paren- + theses (named ones available) + PCRE_NO_UTF16_CHECK Do not check the pattern for UTF-16 + validity (only relevant if + PCRE_UTF16 is set) + PCRE_NO_UTF32_CHECK Do not check the pattern for UTF-32 + validity (only relevant if + PCRE_UTF32 is set) + PCRE_NO_UTF8_CHECK Do not check the pattern for UTF-8 + validity (only relevant if + PCRE_UTF8 is set) + PCRE_UCP Use Unicode properties for \d, \w, etc. + PCRE_UNGREEDY Invert greediness of quantifiers + PCRE_UTF16 Run in pcre16_compile() UTF-16 mode + PCRE_UTF32 Run in pcre32_compile() UTF-32 mode + PCRE_UTF8 Run in pcre_compile() UTF-8 mode ++PCRE must be built with UTF support in order to use PCRE_UTF8/16/32 and +PCRE_NO_UTF8/16/32_CHECK, and with UCP support if PCRE_UCP is used. + +
+The yield of the function is a pointer to a private data structure that +contains the compiled pattern, or NULL if an error was detected. Note that +compiling regular expressions with one version of PCRE for use with a different +version is not guaranteed to work and may cause crashes. +
++There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcre_compile2.html b/tools/pcre/doc/html/pcre_compile2.html new file mode 100644 index 00000000..7d76bd9c --- /dev/null +++ b/tools/pcre/doc/html/pcre_compile2.html @@ -0,0 +1,112 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+SYNOPSIS
+
+
+#include <pcre.h> +
++pcre *pcre_compile2(const char *pattern, int options, +int *errorcodeptr, +const char **errptr, int *erroffset, +const unsigned char *tableptr); +
++pcre16 *pcre16_compile2(PCRE_SPTR16 pattern, int options, +int *errorcodeptr, +const char **errptr, int *erroffset, +const unsigned char *tableptr); +
++pcre32 *pcre32_compile2(PCRE_SPTR32 pattern, int options, +int *errorcodeptr, +const char **errptr, int *erroffset, +const unsigned char *tableptr); +
++This function compiles a regular expression into an internal form. It is the +same as pcre[16|32]_compile(), except for the addition of the +errorcodeptr argument. The arguments are: +
+ pattern A zero-terminated string containing the + regular expression to be compiled + options Zero or more option bits + errorcodeptr Where to put an error code + errptr Where to put an error message + erroffset Offset in pattern where error was found + tableptr Pointer to character tables, or NULL to + use the built-in default ++The option bits are: +
+ PCRE_ANCHORED Force pattern anchoring + PCRE_AUTO_CALLOUT Compile automatic callouts + PCRE_BSR_ANYCRLF \R matches only CR, LF, or CRLF + PCRE_BSR_UNICODE \R matches all Unicode line endings + PCRE_CASELESS Do caseless matching + PCRE_DOLLAR_ENDONLY $ not to match newline at end + PCRE_DOTALL . matches anything including NL + PCRE_DUPNAMES Allow duplicate names for subpatterns + PCRE_EXTENDED Ignore white space and # comments + PCRE_EXTRA PCRE extra features + (not much use currently) + PCRE_FIRSTLINE Force matching to be before newline + PCRE_JAVASCRIPT_COMPAT JavaScript compatibility + PCRE_MULTILINE ^ and $ match newlines within data + PCRE_NEWLINE_ANY Recognize any Unicode newline sequence + PCRE_NEWLINE_ANYCRLF Recognize CR, LF, and CRLF as newline + sequences + PCRE_NEWLINE_CR Set CR as the newline sequence + PCRE_NEWLINE_CRLF Set CRLF as the newline sequence + PCRE_NEWLINE_LF Set LF as the newline sequence + PCRE_NO_AUTO_CAPTURE Disable numbered capturing paren- + theses (named ones available) + PCRE_NO_UTF16_CHECK Do not check the pattern for UTF-16 + validity (only relevant if + PCRE_UTF16 is set) + PCRE_NO_UTF32_CHECK Do not check the pattern for UTF-32 + validity (only relevant if + PCRE_UTF32 is set) + PCRE_NO_UTF8_CHECK Do not check the pattern for UTF-8 + validity (only relevant if + PCRE_UTF8 is set) + PCRE_UCP Use Unicode properties for \d, \w, etc. + PCRE_UNGREEDY Invert greediness of quantifiers + PCRE_UTF16 Run pcre16_compile() in UTF-16 mode + PCRE_UTF32 Run pcre32_compile() in UTF-32 mode + PCRE_UTF8 Run pcre_compile() in UTF-8 mode ++PCRE must be built with UTF support in order to use PCRE_UTF8/16/32 and +PCRE_NO_UTF8/16/32_CHECK, and with UCP support if PCRE_UCP is used. + +
+The yield of the function is a pointer to a private data structure that +contains the compiled pattern, or NULL if an error was detected. Note that +compiling regular expressions with one version of PCRE for use with a different +version is not guaranteed to work and may cause crashes. +
++There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcre_config.html b/tools/pcre/doc/html/pcre_config.html new file mode 100644 index 00000000..fc10d183 --- /dev/null +++ b/tools/pcre/doc/html/pcre_config.html @@ -0,0 +1,91 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+SYNOPSIS
+
+
+#include <pcre.h> +
++int pcre_config(int what, void *where); +
++int pcre16_config(int what, void *where); +
++int pcre32_config(int what, void *where); +
++This function makes it possible for a client program to find out which optional +features are available in the version of the PCRE library it is using. The +arguments are as follows: +
+ what A code specifying what information is required + where Points to where to put the data ++The where argument must point to an integer variable, except for +PCRE_CONFIG_MATCH_LIMIT and PCRE_CONFIG_MATCH_LIMIT_RECURSION, when it must +point to an unsigned long integer. The available codes are: +
+ PCRE_CONFIG_JIT Availability of just-in-time compiler + support (1=yes 0=no) + PCRE_CONFIG_JITTARGET String containing information about the + target architecture for the JIT compiler, + or NULL if there is no JIT support + PCRE_CONFIG_LINK_SIZE Internal link size: 2, 3, or 4 + PCRE_CONFIG_MATCH_LIMIT Internal resource limit + PCRE_CONFIG_MATCH_LIMIT_RECURSION + Internal recursion depth limit + PCRE_CONFIG_NEWLINE Value of the default newline sequence: + 13 (0x000d) for CR + 10 (0x000a) for LF + 3338 (0x0d0a) for CRLF + -2 for ANYCRLF + -1 for ANY + PCRE_CONFIG_BSR Indicates what \R matches by default: + 0 all Unicode line endings + 1 CR, LF, or CRLF only + PCRE_CONFIG_POSIX_MALLOC_THRESHOLD + Threshold of return slots, above which + malloc() is used by the POSIX API + PCRE_CONFIG_STACKRECURSE Recursion implementation (1=stack 0=heap) + PCRE_CONFIG_UTF16 Availability of UTF-16 support (1=yes + 0=no); option for pcre16_config() + PCRE_CONFIG_UTF32 Availability of UTF-32 support (1=yes + 0=no); option for pcre32_config() + PCRE_CONFIG_UTF8 Availability of UTF-8 support (1=yes 0=no); + option for pcre_config() + PCRE_CONFIG_UNICODE_PROPERTIES + Availability of Unicode property support + (1=yes 0=no) ++The function yields 0 on success or PCRE_ERROR_BADOPTION otherwise. That error +is also given if PCRE_CONFIG_UTF16 or PCRE_CONFIG_UTF32 is passed to +pcre_config(), if PCRE_CONFIG_UTF8 or PCRE_CONFIG_UTF32 is passed to +pcre16_config(), or if PCRE_CONFIG_UTF8 or PCRE_CONFIG_UTF16 is passed to +pcre32_config(). + +
+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcre_copy_named_substring.html b/tools/pcre/doc/html/pcre_copy_named_substring.html new file mode 100644 index 00000000..ae4f6905 --- /dev/null +++ b/tools/pcre/doc/html/pcre_copy_named_substring.html @@ -0,0 +1,65 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+SYNOPSIS
+
+
+#include <pcre.h> +
++int pcre_copy_named_substring(const pcre *code, +const char *subject, int *ovector, +int stringcount, const char *stringname, +char *buffer, int buffersize); +
++int pcre16_copy_named_substring(const pcre16 *code, +PCRE_SPTR16 subject, int *ovector, +int stringcount, PCRE_SPTR16 stringname, +PCRE_UCHAR16 *buffer, int buffersize); +
++int pcre32_copy_named_substring(const pcre32 *code, +PCRE_SPTR32 subject, int *ovector, +int stringcount, PCRE_SPTR32 stringname, +PCRE_UCHAR32 *buffer, int buffersize); +
++This is a convenience function for extracting a captured substring, identified +by name, into a given buffer. The arguments are: +
+ code Pattern that was successfully matched + subject Subject that has been successfully matched + ovector Offset vector that pcre[16|32]_exec() used + stringcount Value returned by pcre[16|32]_exec() + stringname Name of the required substring + buffer Buffer to receive the string + buffersize Size of buffer ++The yield is the length of the substring, PCRE_ERROR_NOMEMORY if the buffer was +too small, or PCRE_ERROR_NOSUBSTRING if the string name is invalid. + +
+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcre_copy_substring.html b/tools/pcre/doc/html/pcre_copy_substring.html new file mode 100644 index 00000000..12bfb636 --- /dev/null +++ b/tools/pcre/doc/html/pcre_copy_substring.html @@ -0,0 +1,61 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+SYNOPSIS
+
+
+#include <pcre.h> +
++int pcre_copy_substring(const char *subject, int *ovector, +int stringcount, int stringnumber, char *buffer, +int buffersize); +
++int pcre16_copy_substring(PCRE_SPTR16 subject, int *ovector, +int stringcount, int stringnumber, PCRE_UCHAR16 *buffer, +int buffersize); +
++int pcre32_copy_substring(PCRE_SPTR32 subject, int *ovector, +int stringcount, int stringnumber, PCRE_UCHAR32 *buffer, +int buffersize); +
++This is a convenience function for extracting a captured substring into a given +buffer. The arguments are: +
+ subject Subject that has been successfully matched + ovector Offset vector that pcre[16|32]_exec() used + stringcount Value returned by pcre[16|32]_exec() + stringnumber Number of the required substring + buffer Buffer to receive the string + buffersize Size of buffer ++The yield is the length of the string, PCRE_ERROR_NOMEMORY if the buffer was +too small, or PCRE_ERROR_NOSUBSTRING if the string number is invalid. + +
+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcre_dfa_exec.html b/tools/pcre/doc/html/pcre_dfa_exec.html new file mode 100644 index 00000000..663e1d0f --- /dev/null +++ b/tools/pcre/doc/html/pcre_dfa_exec.html @@ -0,0 +1,128 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+SYNOPSIS
+
+
+#include <pcre.h> +
++int pcre_dfa_exec(const pcre *code, const pcre_extra *extra, +const char *subject, int length, int startoffset, +int options, int *ovector, int ovecsize, +int *workspace, int wscount); +
++int pcre16_dfa_exec(const pcre16 *code, const pcre16_extra *extra, +PCRE_SPTR16 subject, int length, int startoffset, +int options, int *ovector, int ovecsize, +int *workspace, int wscount); +
++int pcre32_dfa_exec(const pcre32 *code, const pcre32_extra *extra, +PCRE_SPTR32 subject, int length, int startoffset, +int options, int *ovector, int ovecsize, +int *workspace, int wscount); +
++This function matches a compiled regular expression against a given subject +string, using an alternative matching algorithm that scans the subject string +just once (not Perl-compatible). Note that the main, Perl-compatible, +matching function is pcre[16|32]_exec(). The arguments for this function +are: +
+ code Points to the compiled pattern + extra Points to an associated pcre[16|32]_extra structure, + or is NULL + subject Points to the subject string + length Length of the subject string, in bytes + startoffset Offset in bytes in the subject at which to + start matching + options Option bits + ovector Points to a vector of ints for result offsets + ovecsize Number of elements in the vector + workspace Points to a vector of ints used as working space + wscount Number of elements in the vector ++The options are: +
+ PCRE_ANCHORED Match only at the first position + PCRE_BSR_ANYCRLF \R matches only CR, LF, or CRLF + PCRE_BSR_UNICODE \R matches all Unicode line endings + PCRE_NEWLINE_ANY Recognize any Unicode newline sequence + PCRE_NEWLINE_ANYCRLF Recognize CR, LF, & CRLF as newline sequences + PCRE_NEWLINE_CR Recognize CR as the only newline sequence + PCRE_NEWLINE_CRLF Recognize CRLF as the only newline sequence + PCRE_NEWLINE_LF Recognize LF as the only newline sequence + PCRE_NOTBOL Subject is not the beginning of a line + PCRE_NOTEOL Subject is not the end of a line + PCRE_NOTEMPTY An empty string is not a valid match + PCRE_NOTEMPTY_ATSTART An empty string at the start of the subject + is not a valid match + PCRE_NO_START_OPTIMIZE Do not do "start-match" optimizations + PCRE_NO_UTF16_CHECK Do not check the subject for UTF-16 + validity (only relevant if PCRE_UTF16 + was set at compile time) + PCRE_NO_UTF32_CHECK Do not check the subject for UTF-32 + validity (only relevant if PCRE_UTF32 + was set at compile time) + PCRE_NO_UTF8_CHECK Do not check the subject for UTF-8 + validity (only relevant if PCRE_UTF8 + was set at compile time) + PCRE_PARTIAL ) Return PCRE_ERROR_PARTIAL for a partial + PCRE_PARTIAL_SOFT ) match if no full matches are found + PCRE_PARTIAL_HARD Return PCRE_ERROR_PARTIAL for a partial match + even if there is a full match as well + PCRE_DFA_SHORTEST Return only the shortest match + PCRE_DFA_RESTART Restart after a partial match ++There are restrictions on what may appear in a pattern when using this matching +function. Details are given in the +pcrematching +documentation. For details of partial matching, see the +pcrepartial +page. + +
+A pcre[16|32]_extra structure contains the following fields: +
+ flags Bits indicating which fields are set + study_data Opaque data from pcre[16|32]_study() + match_limit Limit on internal resource use + match_limit_recursion Limit on internal recursion depth + callout_data Opaque data passed back to callouts + tables Points to character tables or is NULL + mark For passing back a *MARK pointer + executable_jit Opaque data from JIT compilation ++The flag bits are PCRE_EXTRA_STUDY_DATA, PCRE_EXTRA_MATCH_LIMIT, +PCRE_EXTRA_MATCH_LIMIT_RECURSION, PCRE_EXTRA_CALLOUT_DATA, +PCRE_EXTRA_TABLES, PCRE_EXTRA_MARK and PCRE_EXTRA_EXECUTABLE_JIT. For this +matching function, the match_limit and match_limit_recursion fields +are not used, and must not be set. The PCRE_EXTRA_EXECUTABLE_JIT flag and +the corresponding variable are ignored. + +
+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcre_exec.html b/tools/pcre/doc/html/pcre_exec.html new file mode 100644 index 00000000..e4ddf9a8 --- /dev/null +++ b/tools/pcre/doc/html/pcre_exec.html @@ -0,0 +1,110 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+SYNOPSIS
+
+
+#include <pcre.h> +
++int pcre_exec(const pcre *code, const pcre_extra *extra, +const char *subject, int length, int startoffset, +int options, int *ovector, int ovecsize); +
++int pcre16_exec(const pcre16 *code, const pcre16_extra *extra, +PCRE_SPTR16 subject, int length, int startoffset, +int options, int *ovector, int ovecsize); +
++int pcre32_exec(const pcre32 *code, const pcre32_extra *extra, +PCRE_SPTR32 subject, int length, int startoffset, +int options, int *ovector, int ovecsize); +
++This function matches a compiled regular expression against a given subject +string, using a matching algorithm that is similar to Perl's. It returns +offsets to captured substrings. Its arguments are: +
+ code Points to the compiled pattern + extra Points to an associated pcre[16|32]_extra structure, + or is NULL + subject Points to the subject string + length Length of the subject string, in bytes + startoffset Offset in bytes in the subject at which to + start matching + options Option bits + ovector Points to a vector of ints for result offsets + ovecsize Number of elements in the vector (a multiple of 3) ++The options are: +
+ PCRE_ANCHORED Match only at the first position + PCRE_BSR_ANYCRLF \R matches only CR, LF, or CRLF + PCRE_BSR_UNICODE \R matches all Unicode line endings + PCRE_NEWLINE_ANY Recognize any Unicode newline sequence + PCRE_NEWLINE_ANYCRLF Recognize CR, LF, & CRLF as newline sequences + PCRE_NEWLINE_CR Recognize CR as the only newline sequence + PCRE_NEWLINE_CRLF Recognize CRLF as the only newline sequence + PCRE_NEWLINE_LF Recognize LF as the only newline sequence + PCRE_NOTBOL Subject string is not the beginning of a line + PCRE_NOTEOL Subject string is not the end of a line + PCRE_NOTEMPTY An empty string is not a valid match + PCRE_NOTEMPTY_ATSTART An empty string at the start of the subject + is not a valid match + PCRE_NO_START_OPTIMIZE Do not do "start-match" optimizations + PCRE_NO_UTF16_CHECK Do not check the subject for UTF-16 + validity (only relevant if PCRE_UTF16 + was set at compile time) + PCRE_NO_UTF32_CHECK Do not check the subject for UTF-32 + validity (only relevant if PCRE_UTF32 + was set at compile time) + PCRE_NO_UTF8_CHECK Do not check the subject for UTF-8 + validity (only relevant if PCRE_UTF8 + was set at compile time) + PCRE_PARTIAL ) Return PCRE_ERROR_PARTIAL for a partial + PCRE_PARTIAL_SOFT ) match if no full matches are found + PCRE_PARTIAL_HARD Return PCRE_ERROR_PARTIAL for a partial match + if that is found before a full match ++For details of partial matching, see the +pcrepartial +page. A pcre_extra structure contains the following fields: +
+ flags Bits indicating which fields are set + study_data Opaque data from pcre[16|32]_study() + match_limit Limit on internal resource use + match_limit_recursion Limit on internal recursion depth + callout_data Opaque data passed back to callouts + tables Points to character tables or is NULL + mark For passing back a *MARK pointer + executable_jit Opaque data from JIT compilation ++The flag bits are PCRE_EXTRA_STUDY_DATA, PCRE_EXTRA_MATCH_LIMIT, +PCRE_EXTRA_MATCH_LIMIT_RECURSION, PCRE_EXTRA_CALLOUT_DATA, +PCRE_EXTRA_TABLES, PCRE_EXTRA_MARK and PCRE_EXTRA_EXECUTABLE_JIT. + +
+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcre_free_study.html b/tools/pcre/doc/html/pcre_free_study.html new file mode 100644 index 00000000..7f9e10e8 --- /dev/null +++ b/tools/pcre/doc/html/pcre_free_study.html @@ -0,0 +1,46 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+SYNOPSIS
+
+
+#include <pcre.h> +
++void pcre_free_study(pcre_extra *extra); +
++void pcre16_free_study(pcre16_extra *extra); +
++void pcre32_free_study(pcre32_extra *extra); +
++This function is used to free the memory used for the data generated by a call +to pcre[16|32]_study() when it is no longer needed. The argument must be the +result of such a call. +
++There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcre_free_substring.html b/tools/pcre/doc/html/pcre_free_substring.html new file mode 100644 index 00000000..1fe66107 --- /dev/null +++ b/tools/pcre/doc/html/pcre_free_substring.html @@ -0,0 +1,46 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+SYNOPSIS
+
+
+#include <pcre.h> +
++void pcre_free_substring(const char *stringptr); +
++void pcre16_free_substring(PCRE_SPTR16 stringptr); +
++void pcre32_free_substring(PCRE_SPTR32 stringptr); +
++This is a convenience function for freeing the store obtained by a previous +call to pcre[16|32]_get_substring() or pcre[16|32]_get_named_substring(). +Its only argument is a pointer to the string. +
++There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcre_free_substring_list.html b/tools/pcre/doc/html/pcre_free_substring_list.html new file mode 100644 index 00000000..c0861780 --- /dev/null +++ b/tools/pcre/doc/html/pcre_free_substring_list.html @@ -0,0 +1,46 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+SYNOPSIS
+
+
+#include <pcre.h> +
++void pcre_free_substring_list(const char **stringptr); +
++void pcre16_free_substring_list(PCRE_SPTR16 *stringptr); +
++void pcre32_free_substring_list(PCRE_SPTR32 *stringptr); +
++This is a convenience function for freeing the store obtained by a previous +call to pcre[16|32]_get_substring_list(). Its only argument is a pointer to +the list of string pointers. +
++There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcre_fullinfo.html b/tools/pcre/doc/html/pcre_fullinfo.html new file mode 100644 index 00000000..d353432b --- /dev/null +++ b/tools/pcre/doc/html/pcre_fullinfo.html @@ -0,0 +1,108 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+SYNOPSIS
+
+
+#include <pcre.h> +
++int pcre_fullinfo(const pcre *code, const pcre_extra *extra, +int what, void *where); +
++int pcre16_fullinfo(const pcre16 *code, const pcre16_extra *extra, +int what, void *where); +
++int pcre32_fullinfo(const pcre32 *code, const pcre32_extra *extra, +int what, void *where); +
++This function returns information about a compiled pattern. Its arguments are: +
+ code Compiled regular expression + extra Result of pcre[16|32]_study() or NULL + what What information is required + where Where to put the information ++The following information is available: +
+ PCRE_INFO_BACKREFMAX Number of highest back reference + PCRE_INFO_CAPTURECOUNT Number of capturing subpatterns + PCRE_INFO_DEFAULT_TABLES Pointer to default tables + PCRE_INFO_FIRSTBYTE Fixed first data unit for a match, or + -1 for start of string + or after newline, or + -2 otherwise + PCRE_INFO_FIRSTTABLE Table of first data units (after studying) + PCRE_INFO_HASCRORLF Return 1 if explicit CR or LF matches exist + PCRE_INFO_JCHANGED Return 1 if (?J) or (?-J) was used + PCRE_INFO_JIT Return 1 after successful JIT compilation + PCRE_INFO_JITSIZE Size of JIT compiled code + PCRE_INFO_LASTLITERAL Literal last data unit required + PCRE_INFO_MINLENGTH Lower bound length of matching strings + PCRE_INFO_NAMECOUNT Number of named subpatterns + PCRE_INFO_NAMEENTRYSIZE Size of name table entry + PCRE_INFO_NAMETABLE Pointer to name table + PCRE_INFO_OKPARTIAL Return 1 if partial matching can be tried + (always returns 1 after release 8.00) + PCRE_INFO_OPTIONS Option bits used for compilation + PCRE_INFO_SIZE Size of compiled pattern + PCRE_INFO_STUDYSIZE Size of study data + PCRE_INFO_FIRSTCHARACTER Fixed first data unit for a match + PCRE_INFO_FIRSTCHARACTERFLAGS Returns + 1 if there is a first data character set, which can + then be retrieved using PCRE_INFO_FIRSTCHARACTER, + 2 if the first character is at the start of the data + string or after a newline, and + 0 otherwise + PCRE_INFO_REQUIREDCHAR Literal last data unit required + PCRE_INFO_REQUIREDCHARFLAGS Returns 1 if the last data character is set (which can then + be retrieved using PCRE_INFO_REQUIREDCHAR); 0 otherwise ++The where argument must point to an integer variable, except for the +following what values: +
+ PCRE_INFO_DEFAULT_TABLES const unsigned char * + PCRE_INFO_FIRSTTABLE const unsigned char * + PCRE_INFO_NAMETABLE PCRE_SPTR16 (16-bit library) + PCRE_INFO_NAMETABLE PCRE_SPTR32 (32-bit library) + PCRE_INFO_NAMETABLE const unsigned char * (8-bit library) + PCRE_INFO_OPTIONS unsigned long int + PCRE_INFO_SIZE size_t + PCRE_INFO_FIRSTCHARACTER uint32_t + PCRE_INFO_REQUIREDCHAR uint32_t ++The yield of the function is zero on success or: +
+ PCRE_ERROR_NULL the argument code was NULL + the argument where was NULL + PCRE_ERROR_BADMAGIC the "magic number" was not found + PCRE_ERROR_BADOPTION the value of what was invalid ++ +
+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcre_get_named_substring.html b/tools/pcre/doc/html/pcre_get_named_substring.html new file mode 100644 index 00000000..6150ad71 --- /dev/null +++ b/tools/pcre/doc/html/pcre_get_named_substring.html @@ -0,0 +1,68 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+SYNOPSIS
+
+
+#include <pcre.h> +
++int pcre_get_named_substring(const pcre *code, +const char *subject, int *ovector, +int stringcount, const char *stringname, +const char **stringptr); +
++int pcre16_get_named_substring(const pcre16 *code, +PCRE_SPTR16 subject, int *ovector, +int stringcount, PCRE_SPTR16 stringname, +PCRE_SPTR16 *stringptr); +
++int pcre32_get_named_substring(const pcre32 *code, +PCRE_SPTR32 subject, int *ovector, +int stringcount, PCRE_SPTR32 stringname, +PCRE_SPTR32 *stringptr); +
++This is a convenience function for extracting a captured substring by name. The +arguments are: +
+ code Compiled pattern + subject Subject that has been successfully matched + ovector Offset vector that pcre[16|32]_exec() used + stringcount Value returned by pcre[16|32]_exec() + stringname Name of the required substring + stringptr Where to put the string pointer ++The memory in which the substring is placed is obtained by calling +pcre[16|32]_malloc(). The convenience function +pcre[16|32]_free_substring() can be used to free it when it is no longer +needed. The yield of the function is the length of the extracted substring, +PCRE_ERROR_NOMEMORY if sufficient memory could not be obtained, or +PCRE_ERROR_NOSUBSTRING if the string name is invalid. + +
+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcre_get_stringnumber.html b/tools/pcre/doc/html/pcre_get_stringnumber.html new file mode 100644 index 00000000..08967de3 --- /dev/null +++ b/tools/pcre/doc/html/pcre_get_stringnumber.html @@ -0,0 +1,57 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+SYNOPSIS
+
+
+#include <pcre.h> +
++int pcre_get_stringnumber(const pcre *code, +const char *name); +
++int pcre16_get_stringnumber(const pcre16 *code, +PCRE_SPTR16 name); +
++int pcre32_get_stringnumber(const pcre32 *code, +PCRE_SPTR32 name); +
++This convenience function finds the number of a named substring capturing +parenthesis in a compiled pattern. Its arguments are: +
+ code Compiled regular expression + name Name whose number is required ++The yield of the function is the number of the parenthesis if the name is +found, or PCRE_ERROR_NOSUBSTRING otherwise. When duplicate names are allowed +(PCRE_DUPNAMES is set), it is not defined which of the numbers is returned by +pcre[16|32]_get_stringnumber(). You can obtain the complete list by calling +pcre[16|32]_get_stringtable_entries(). + +
+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcre_get_stringtable_entries.html b/tools/pcre/doc/html/pcre_get_stringtable_entries.html new file mode 100644 index 00000000..38f9c0c9 --- /dev/null +++ b/tools/pcre/doc/html/pcre_get_stringtable_entries.html @@ -0,0 +1,60 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+SYNOPSIS
+
+
+#include <pcre.h> +
++int pcre_get_stringtable_entries(const pcre *code, +const char *name, char **first, char **last); +
++int pcre16_get_stringtable_entries(const pcre16 *code, +PCRE_SPTR16 name, PCRE_UCHAR16 **first, PCRE_UCHAR16 **last); +
++int pcre32_get_stringtable_entries(const pcre32 *code, +PCRE_SPTR32 name, PCRE_UCHAR32 **first, PCRE_UCHAR32 **last); +
++This convenience function finds, for a compiled pattern, the first and last +entries for a given name in the table that translates capturing parenthesis +names into numbers. When names are required to be unique (PCRE_DUPNAMES is +not set), it is usually easier to use pcre[16|32]_get_stringnumber() +instead. +
+ code Compiled regular expression + name Name whose entries required + first Where to return a pointer to the first entry + last Where to return a pointer to the last entry ++The yield of the function is the length of each entry, or +PCRE_ERROR_NOSUBSTRING if none are found. + +
+There is a complete description of the PCRE native API, including the format of +the table entries, in the +pcreapi +page, and a description of the POSIX API in the +pcreposix +page. +
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcre_get_substring.html b/tools/pcre/doc/html/pcre_get_substring.html new file mode 100644 index 00000000..2a5a610f --- /dev/null +++ b/tools/pcre/doc/html/pcre_get_substring.html @@ -0,0 +1,64 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+SYNOPSIS
+
+
+#include <pcre.h> +
++int pcre_get_substring(const char *subject, int *ovector, +int stringcount, int stringnumber, +const char **stringptr); +
++int pcre16_get_substring(PCRE_SPTR16 subject, int *ovector, +int stringcount, int stringnumber, +PCRE_SPTR16 *stringptr); +
++int pcre32_get_substring(PCRE_SPTR32 subject, int *ovector, +int stringcount, int stringnumber, +PCRE_SPTR32 *stringptr); +
++This is a convenience function for extracting a captured substring. The +arguments are: +
+ subject Subject that has been successfully matched + ovector Offset vector that pcre[16|32]_exec() used + stringcount Value returned by pcre[16|32]_exec() + stringnumber Number of the required substring + stringptr Where to put the string pointer ++The memory in which the substring is placed is obtained by calling +pcre[16|32]_malloc(). The convenience function +pcre[16|32]_free_substring() can be used to free it when it is no longer +needed. The yield of the function is the length of the substring, +PCRE_ERROR_NOMEMORY if sufficient memory could not be obtained, or +PCRE_ERROR_NOSUBSTRING if the string number is invalid. + +
+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcre_get_substring_list.html b/tools/pcre/doc/html/pcre_get_substring_list.html new file mode 100644 index 00000000..85edef4b --- /dev/null +++ b/tools/pcre/doc/html/pcre_get_substring_list.html @@ -0,0 +1,61 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+SYNOPSIS
+
+
+#include <pcre.h> +
++int pcre_get_substring_list(const char *subject, +int *ovector, int stringcount, const char ***listptr); +
++int pcre16_get_substring_list(PCRE_SPTR16 subject, +int *ovector, int stringcount, PCRE_SPTR16 **listptr); +
++int pcre32_get_substring_list(PCRE_SPTR32 subject, +int *ovector, int stringcount, PCRE_SPTR32 **listptr); +
++This is a convenience function for extracting a list of all the captured +substrings. The arguments are: +
+ subject Subject that has been successfully matched + ovector Offset vector that pcre[16|32]_exec used + stringcount Value returned by pcre[16|32]_exec + listptr Where to put a pointer to the list ++The memory in which the substrings and the list are placed is obtained by +calling pcre[16|32]_malloc(). The convenience function +pcre[16|32]_free_substring_list() can be used to free it when it is no +longer needed. A pointer to a list of pointers is put in the variable whose +address is in listptr. The list is terminated by a NULL pointer. The +yield of the function is zero on success or PCRE_ERROR_NOMEMORY if sufficient +memory could not be obtained. + +
+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcre_jit_exec.html b/tools/pcre/doc/html/pcre_jit_exec.html new file mode 100644 index 00000000..0c63503a --- /dev/null +++ b/tools/pcre/doc/html/pcre_jit_exec.html @@ -0,0 +1,108 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+SYNOPSIS
+
+
+#include <pcre.h> +
++int pcre_jit_exec(const pcre *code, const pcre_extra *extra, +const char *subject, int length, int startoffset, +int options, int *ovector, int ovecsize, +pcre_jit_stack *jstack); +
++int pcre16_jit_exec(const pcre16 *code, const pcre16_extra *extra, +PCRE_SPTR16 subject, int length, int startoffset, +int options, int *ovector, int ovecsize, +pcre_jit_stack *jstack); +
++int pcre32_jit_exec(const pcre32 *code, const pcre32_extra *extra, +PCRE_SPTR32 subject, int length, int startoffset, +int options, int *ovector, int ovecsize, +pcre_jit_stack *jstack); +
++This function matches a compiled regular expression that has been successfully +studied with one of the JIT options against a given subject string, using a +matching algorithm that is similar to Perl's. It is a "fast path" interface to +JIT, and it bypasses some of the sanity checks that pcre_exec() applies. +It returns offsets to captured substrings. Its arguments are: +
+ code Points to the compiled pattern + extra Points to an associated pcre[16|32]_extra structure, + or is NULL + subject Points to the subject string + length Length of the subject string, in bytes + startoffset Offset in bytes in the subject at which to + start matching + options Option bits + ovector Points to a vector of ints for result offsets + ovecsize Number of elements in the vector (a multiple of 3) + jstack Pointer to a JIT stack ++The allowed options are: +
+ PCRE_NOTBOL Subject string is not the beginning of a line + PCRE_NOTEOL Subject string is not the end of a line + PCRE_NOTEMPTY An empty string is not a valid match + PCRE_NOTEMPTY_ATSTART An empty string at the start of the subject + is not a valid match + PCRE_NO_UTF16_CHECK Do not check the subject for UTF-16 + validity (only relevant if PCRE_UTF16 + was set at compile time) + PCRE_NO_UTF32_CHECK Do not check the subject for UTF-32 + validity (only relevant if PCRE_UTF32 + was set at compile time) + PCRE_NO_UTF8_CHECK Do not check the subject for UTF-8 + validity (only relevant if PCRE_UTF8 + was set at compile time) + PCRE_PARTIAL ) Return PCRE_ERROR_PARTIAL for a partial + PCRE_PARTIAL_SOFT ) match if no full matches are found + PCRE_PARTIAL_HARD Return PCRE_ERROR_PARTIAL for a partial match + if that is found before a full match ++However, the PCRE_NO_UTF[8|16|32]_CHECK options have no effect, as this check +is never applied. For details of partial matching, see the +pcrepartial +page. A pcre_extra structure contains the following fields: +
+ flags Bits indicating which fields are set + study_data Opaque data from pcre[16|32]_study() + match_limit Limit on internal resource use + match_limit_recursion Limit on internal recursion depth + callout_data Opaque data passed back to callouts + tables Points to character tables or is NULL + mark For passing back a *MARK pointer + executable_jit Opaque data from JIT compilation ++The flag bits are PCRE_EXTRA_STUDY_DATA, PCRE_EXTRA_MATCH_LIMIT, +PCRE_EXTRA_MATCH_LIMIT_RECURSION, PCRE_EXTRA_CALLOUT_DATA, +PCRE_EXTRA_TABLES, PCRE_EXTRA_MARK and PCRE_EXTRA_EXECUTABLE_JIT. + +
+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the JIT API in the +pcrejit +page. +
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcre_jit_stack_alloc.html b/tools/pcre/doc/html/pcre_jit_stack_alloc.html new file mode 100644 index 00000000..4153ee59 --- /dev/null +++ b/tools/pcre/doc/html/pcre_jit_stack_alloc.html @@ -0,0 +1,55 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+SYNOPSIS
+
+
+#include <pcre.h> +
++pcre_jit_stack *pcre_jit_stack_alloc(int startsize, +int maxsize); +
++pcre16_jit_stack *pcre16_jit_stack_alloc(int startsize, +int maxsize); +
++pcre32_jit_stack *pcre32_jit_stack_alloc(int startsize, +int maxsize); +
++This function is used to create a stack for use by the code compiled by the JIT +optimization of pcre[16|32]_study(). The arguments are a starting size for +the stack, and a maximum size to which it is allowed to grow. The result can be +passed to the JIT run-time code by pcre[16|32]_assign_jit_stack(), or that +function can set up a callback for obtaining a stack. A maximum stack size of +512K to 1M should be more than enough for any pattern. For more details, see +the +pcrejit +page. +
++There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcre_jit_stack_free.html b/tools/pcre/doc/html/pcre_jit_stack_free.html new file mode 100644 index 00000000..8bd06e46 --- /dev/null +++ b/tools/pcre/doc/html/pcre_jit_stack_free.html @@ -0,0 +1,48 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+SYNOPSIS
+
+
+#include <pcre.h> +
++void pcre_jit_stack_free(pcre_jit_stack *stack); +
++void pcre16_jit_stack_free(pcre16_jit_stack *stack); +
++void pcre32_jit_stack_free(pcre32_jit_stack *stack); +
++This function is used to free a JIT stack that was created by +pcre[16|32]_jit_stack_alloc() when it is no longer needed. For more details, +see the +pcrejit +page. +
++There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcre_maketables.html b/tools/pcre/doc/html/pcre_maketables.html new file mode 100644 index 00000000..3a7b5ebc --- /dev/null +++ b/tools/pcre/doc/html/pcre_maketables.html @@ -0,0 +1,48 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+SYNOPSIS
+
+
+#include <pcre.h> +
++const unsigned char *pcre_maketables(void); +
++const unsigned char *pcre16_maketables(void); +
++const unsigned char *pcre32_maketables(void); +
++This function builds a set of character tables for character values less than +256. These can be passed to pcre[16|32]_compile() to override PCRE's +internal, built-in tables (which were made by pcre[16|32]_maketables() when +PCRE was compiled). You might want to do this if you are using a non-standard +locale. The function yields a pointer to the tables. +
++There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcre_pattern_to_host_byte_order.html b/tools/pcre/doc/html/pcre_pattern_to_host_byte_order.html new file mode 100644 index 00000000..68d6f5a1 --- /dev/null +++ b/tools/pcre/doc/html/pcre_pattern_to_host_byte_order.html @@ -0,0 +1,58 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+SYNOPSIS
+
+
+#include <pcre.h> +
++int pcre_pattern_to_host_byte_order(pcre *code, +pcre_extra *extra, const unsigned char *tables); +
++int pcre16_pattern_to_host_byte_order(pcre16 *code, +pcre16_extra *extra, const unsigned char *tables); +
++int pcre32_pattern_to_host_byte_order(pcre32 *code, +pcre32_extra *extra, const unsigned char *tables); +
++This function ensures that the bytes in 2-byte and 4-byte values in a compiled +pattern are in the correct order for the current host. It is useful when a +pattern that has been compiled on one host is transferred to another that might +have different endianness. The arguments are: +
+ code A compiled regular expression + extra Points to an associated pcre[16|32]_extra structure, + or is NULL + tables Pointer to character tables, or NULL to + set the built-in default ++The result is 0 for success, a negative PCRE_ERROR_xxx value otherwise. + +
+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcre_refcount.html b/tools/pcre/doc/html/pcre_refcount.html new file mode 100644 index 00000000..bfb92e6d --- /dev/null +++ b/tools/pcre/doc/html/pcre_refcount.html @@ -0,0 +1,51 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+SYNOPSIS
+
+
+#include <pcre.h> +
++int pcre_refcount(pcre *code, int adjust); +
++int pcre16_refcount(pcre16 *code, int adjust); +
++int pcre32_refcount(pcre32 *code, int adjust); +
++This function is used to maintain a reference count inside a data block that +contains a compiled pattern. Its arguments are: +
+ code Compiled regular expression + adjust Adjustment to reference value ++The yield of the function is the adjusted reference value, which is constrained +to lie between 0 and 65535. + +
+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcre_study.html b/tools/pcre/doc/html/pcre_study.html new file mode 100644 index 00000000..2baf54c4 --- /dev/null +++ b/tools/pcre/doc/html/pcre_study.html @@ -0,0 +1,68 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+SYNOPSIS
+
+
+#include <pcre.h> +
++pcre_extra *pcre_study(const pcre *code, int options, +const char **errptr); +
++pcre16_extra *pcre16_study(const pcre16 *code, int options, +const char **errptr); +
++pcre32_extra *pcre32_study(const pcre32 *code, int options, +const char **errptr); +
++This function studies a compiled pattern, to see if additional information can +be extracted that might speed up matching. Its arguments are: +
+ code A compiled regular expression + options Options for pcre[16|32]_study() + errptr Where to put an error message ++If the function succeeds, it returns a value that can be passed to +pcre[16|32]_exec() or pcre[16|32]_dfa_exec() via their extra +arguments. + +
+If the function returns NULL, either it could not find any additional +information, or there was an error. You can tell the difference by looking at +the error value. It is NULL in first case. +
++The only option is PCRE_STUDY_JIT_COMPILE. It requests just-in-time compilation +if possible. If PCRE has been compiled without JIT support, this option is +ignored. See the +pcrejit +page for further details. +
++There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcre_utf16_to_host_byte_order.html b/tools/pcre/doc/html/pcre_utf16_to_host_byte_order.html new file mode 100644 index 00000000..164e2365 --- /dev/null +++ b/tools/pcre/doc/html/pcre_utf16_to_host_byte_order.html @@ -0,0 +1,57 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+SYNOPSIS
+
+
+#include <pcre.h> +
++int pcre16_utf16_to_host_byte_order(PCRE_UCHAR16 *output, +PCRE_SPTR16 input, int length, int *host_byte_order, +int keep_boms); +
++This function, which exists only in the 16-bit library, converts a UTF-16 +string to the correct order for the current host, taking account of any byte +order marks (BOMs) within the string. Its arguments are: +
+ output pointer to output buffer, may be the same as input + input pointer to input buffer + length number of 16-bit units in the input, or negative for + a zero-terminated string + host_byte_order a NULL value or a non-zero value pointed to means + start in host byte order + keep_boms if non-zero, BOMs are copied to the output string ++The result of the function is the number of 16-bit units placed into the output +buffer, including the zero terminator if the string was zero-terminated. + +
+If host_byte_order is not NULL, it is set to indicate the byte order that +is current at the end of the string. +
++There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcre_version.html b/tools/pcre/doc/html/pcre_version.html new file mode 100644 index 00000000..d33e7189 --- /dev/null +++ b/tools/pcre/doc/html/pcre_version.html @@ -0,0 +1,46 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+SYNOPSIS
+
+
+#include <pcre.h> +
++const char *pcre_version(void); +
++const char *pcre16_version(void); +
++const char *pcre32_version(void); +
++This function (even in the 16-bit and 32-bit libraries) returns a +zero-terminated, 8-bit character string that gives the version number of the +PCRE library and the date of its release. +
++There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcreapi.html b/tools/pcre/doc/html/pcreapi.html new file mode 100644 index 00000000..59398df3 --- /dev/null +++ b/tools/pcre/doc/html/pcreapi.html @@ -0,0 +1,2786 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+#include <pcre.h> +
++pcre *pcre_compile(const char *pattern, int options, +const char **errptr, int *erroffset, +const unsigned char *tableptr); +
++pcre *pcre_compile2(const char *pattern, int options, +int *errorcodeptr, +const char **errptr, int *erroffset, +const unsigned char *tableptr); +
++pcre_extra *pcre_study(const pcre *code, int options, +const char **errptr); +
++void pcre_free_study(pcre_extra *extra); +
++int pcre_exec(const pcre *code, const pcre_extra *extra, +const char *subject, int length, int startoffset, +int options, int *ovector, int ovecsize); +
++int pcre_dfa_exec(const pcre *code, const pcre_extra *extra, +const char *subject, int length, int startoffset, +int options, int *ovector, int ovecsize, +int *workspace, int wscount); +
++int pcre_copy_named_substring(const pcre *code, +const char *subject, int *ovector, +int stringcount, const char *stringname, +char *buffer, int buffersize); +
++int pcre_copy_substring(const char *subject, int *ovector, +int stringcount, int stringnumber, char *buffer, +int buffersize); +
++int pcre_get_named_substring(const pcre *code, +const char *subject, int *ovector, +int stringcount, const char *stringname, +const char **stringptr); +
++int pcre_get_stringnumber(const pcre *code, +const char *name); +
++int pcre_get_stringtable_entries(const pcre *code, +const char *name, char **first, char **last); +
++int pcre_get_substring(const char *subject, int *ovector, +int stringcount, int stringnumber, +const char **stringptr); +
++int pcre_get_substring_list(const char *subject, +int *ovector, int stringcount, const char ***listptr); +
++void pcre_free_substring(const char *stringptr); +
++void pcre_free_substring_list(const char **stringptr); +
++int pcre_jit_exec(const pcre *code, const pcre_extra *extra, +const char *subject, int length, int startoffset, +int options, int *ovector, int ovecsize, +pcre_jit_stack *jstack); +
++pcre_jit_stack *pcre_jit_stack_alloc(int startsize, int maxsize); +
++void pcre_jit_stack_free(pcre_jit_stack *stack); +
++void pcre_assign_jit_stack(pcre_extra *extra, +pcre_jit_callback callback, void *data); +
++const unsigned char *pcre_maketables(void); +
++int pcre_fullinfo(const pcre *code, const pcre_extra *extra, +int what, void *where); +
++int pcre_refcount(pcre *code, int adjust); +
++int pcre_config(int what, void *where); +
++const char *pcre_version(void); +
++int pcre_pattern_to_host_byte_order(pcre *code, +pcre_extra *extra, const unsigned char *tables); +
++void *(*pcre_malloc)(size_t); +
++void (*pcre_free)(void *); +
++void *(*pcre_stack_malloc)(size_t); +
++void (*pcre_stack_free)(void *); +
++int (*pcre_callout)(pcre_callout_block *); +
++As well as support for 8-bit character strings, PCRE also supports 16-bit +strings (from release 8.30) and 32-bit strings (from release 8.32), by means of +two additional libraries. They can be built as well as, or instead of, the +8-bit library. To avoid too much complication, this document describes the +8-bit versions of the functions, with only occasional references to the 16-bit +and 32-bit libraries. +
++The 16-bit and 32-bit functions operate in the same way as their 8-bit +counterparts; they just use different data types for their arguments and +results, and their names start with pcre16_ or pcre32_ instead of +pcre_. For every option that has UTF8 in its name (for example, +PCRE_UTF8), there are corresponding 16-bit and 32-bit names with UTF8 replaced +by UTF16 or UTF32, respectively. This facility is in fact just cosmetic; the +16-bit and 32-bit option names define the same bit values. +
++References to bytes and UTF-8 in this document should be read as references to +16-bit data quantities and UTF-16 when using the 16-bit library, or 32-bit data +quantities and UTF-32 when using the 32-bit library, unless specified +otherwise. More details of the specific differences for the 16-bit and 32-bit +libraries are given in the +pcre16 +and +pcre32 +pages. +
++PCRE has its own native API, which is described in this document. There are +also some wrapper functions (for the 8-bit library only) that correspond to the +POSIX regular expression API, but they do not give access to all the +functionality. They are described in the +pcreposix +documentation. Both of these APIs define a set of C function calls. A C++ +wrapper (again for the 8-bit library only) is also distributed with PCRE. It is +documented in the +pcrecpp +page. +
++The native API C function prototypes are defined in the header file +pcre.h, and on Unix-like systems the (8-bit) library itself is called +libpcre. It can normally be accessed by adding -lpcre to the +command for linking an application that uses PCRE. The header file defines the +macros PCRE_MAJOR and PCRE_MINOR to contain the major and minor release numbers +for the library. Applications can use these to include support for different +releases of PCRE. +
++In a Windows environment, if you want to statically link an application program +against a non-dll pcre.a file, you must define PCRE_STATIC before +including pcre.h or pcrecpp.h, because otherwise the +pcre_malloc() and pcre_free() exported functions will be declared +__declspec(dllimport), with unwanted results. +
++The functions pcre_compile(), pcre_compile2(), pcre_study(), +and pcre_exec() are used for compiling and matching regular expressions +in a Perl-compatible manner. A sample program that demonstrates the simplest +way of using them is provided in the file called pcredemo.c in the PCRE +source distribution. A listing of this program is given in the +pcredemo +documentation, and the +pcresample +documentation describes how to compile and run it. +
++Just-in-time compiler support is an optional feature of PCRE that can be built +in appropriate hardware environments. It greatly speeds up the matching +performance of many patterns. Simple programs can easily request that it be +used if available, by setting an option that is ignored when it is not +relevant. More complicated programs might need to make use of the functions +pcre_jit_stack_alloc(), pcre_jit_stack_free(), and +pcre_assign_jit_stack() in order to control the JIT code's memory usage. +
++From release 8.32 there is also a direct interface for JIT execution, which +gives improved performance. The JIT-specific functions are discussed in the +pcrejit +documentation. +
++A second matching function, pcre_dfa_exec(), which is not +Perl-compatible, is also provided. This uses a different algorithm for the +matching. The alternative algorithm finds all possible matches (at a given +point in the subject), and scans the subject just once (unless there are +lookbehind assertions). However, this algorithm does not return captured +substrings. A description of the two matching algorithms and their advantages +and disadvantages is given in the +pcrematching +documentation. +
++In addition to the main compiling and matching functions, there are convenience +functions for extracting captured substrings from a subject string that is +matched by pcre_exec(). They are: +
+ pcre_copy_substring() + pcre_copy_named_substring() + pcre_get_substring() + pcre_get_named_substring() + pcre_get_substring_list() + pcre_get_stringnumber() + pcre_get_stringtable_entries() ++pcre_free_substring() and pcre_free_substring_list() are also +provided, to free the memory used for extracted strings. + +
+The function pcre_maketables() is used to build a set of character tables +in the current locale for passing to pcre_compile(), pcre_exec(), +or pcre_dfa_exec(). This is an optional facility that is provided for +specialist use. Most commonly, no special tables are passed, in which case +internal tables that are generated when PCRE is built are used. +
++The function pcre_fullinfo() is used to find out information about a +compiled pattern. The function pcre_version() returns a pointer to a +string containing the version of PCRE and its date of release. +
++The function pcre_refcount() maintains a reference count in a data block +containing a compiled pattern. This is provided for the benefit of +object-oriented applications. +
++The global variables pcre_malloc and pcre_free initially contain +the entry points of the standard malloc() and free() functions, +respectively. PCRE calls the memory management functions via these variables, +so a calling program can replace them if it wishes to intercept the calls. This +should be done before calling any PCRE functions. +
++The global variables pcre_stack_malloc and pcre_stack_free are also +indirections to memory management functions. These special functions are used +only when PCRE is compiled to use the heap for remembering data, instead of +recursive function calls, when running the pcre_exec() function. See the +pcrebuild +documentation for details of how to do this. It is a non-standard way of +building PCRE, for use in environments that have limited stacks. Because of the +greater use of memory management, it runs more slowly. Separate functions are +provided so that special-purpose external code can be used for this case. When +used, these functions are always called in a stack-like manner (last obtained, +first freed), and always for memory blocks of the same size. There is a +discussion about PCRE's stack usage in the +pcrestack +documentation. +
++The global variable pcre_callout initially contains NULL. It can be set +by the caller to a "callout" function, which PCRE will then call at specified +points during a matching operation. Details are given in the +pcrecallout +documentation. +
++PCRE supports five different conventions for indicating line breaks in +strings: a single CR (carriage return) character, a single LF (linefeed) +character, the two-character sequence CRLF, any of the three preceding, or any +Unicode newline sequence. The Unicode newline sequences are the three just +mentioned, plus the single characters VT (vertical tab, U+000B), FF (form feed, +U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS +(paragraph separator, U+2029). +
++Each of the first three conventions is used by at least one operating system as +its standard newline sequence. When PCRE is built, a default can be specified. +The default default is LF, which is the Unix standard. When PCRE is run, the +default can be overridden, either when a pattern is compiled, or when it is +matched. +
++At compile time, the newline convention can be specified by the options +argument of pcre_compile(), or it can be specified by special text at the +start of the pattern itself; this overrides any other settings. See the +pcrepattern +page for details of the special character sequences. +
++In the PCRE documentation the word "newline" is used to mean "the character or +pair of characters that indicate a line break". The choice of newline +convention affects the handling of the dot, circumflex, and dollar +metacharacters, the handling of #-comments in /x mode, and, when CRLF is a +recognized line ending sequence, the match position advancement for a +non-anchored pattern. There is more detail about this in the +section on pcre_exec() options +below. +
++The choice of newline convention does not affect the interpretation of +the \n or \r escape sequences, nor does it affect what \R matches, which is +controlled in a similar way, but by separate options. +
++The PCRE functions can be used in multi-threading applications, with the +proviso that the memory management functions pointed to by pcre_malloc, +pcre_free, pcre_stack_malloc, and pcre_stack_free, and the +callout function pointed to by pcre_callout, are shared by all threads. +
++The compiled form of a regular expression is not altered during matching, so +the same compiled pattern can safely be used by several threads at once. +
++If the just-in-time optimization feature is being used, it needs separate +memory stack areas for each thread. See the +pcrejit +documentation for more details. +
++The compiled form of a regular expression can be saved and re-used at a later +time, possibly by a different program, and even on a host other than the one on +which it was compiled. Details are given in the +pcreprecompile +documentation, which includes a description of the +pcre_pattern_to_host_byte_order() function. However, compiling a regular +expression with one version of PCRE for use with a different version is not +guaranteed to work and may cause crashes. +
++int pcre_config(int what, void *where); +
++The function pcre_config() makes it possible for a PCRE client to +discover which optional features have been compiled into the PCRE library. The +pcrebuild +documentation has more details about these optional features. +
++The first argument for pcre_config() is an integer, specifying which +information is required; the second argument is a pointer to a variable into +which the information is placed. The returned value is zero on success, or the +negative error code PCRE_ERROR_BADOPTION if the value in the first argument is +not recognized. The following information is available: +
+ PCRE_CONFIG_UTF8 ++The output is an integer that is set to one if UTF-8 support is available; +otherwise it is set to zero. This value should normally be given to the 8-bit +version of this function, pcre_config(). If it is given to the 16-bit +or 32-bit version of this function, the result is PCRE_ERROR_BADOPTION. +
+ PCRE_CONFIG_UTF16 ++The output is an integer that is set to one if UTF-16 support is available; +otherwise it is set to zero. This value should normally be given to the 16-bit +version of this function, pcre16_config(). If it is given to the 8-bit +or 32-bit version of this function, the result is PCRE_ERROR_BADOPTION. +
+ PCRE_CONFIG_UTF32 ++The output is an integer that is set to one if UTF-32 support is available; +otherwise it is set to zero. This value should normally be given to the 32-bit +version of this function, pcre32_config(). If it is given to the 8-bit +or 16-bit version of this function, the result is PCRE_ERROR_BADOPTION. +
+ PCRE_CONFIG_UNICODE_PROPERTIES ++The output is an integer that is set to one if support for Unicode character +properties is available; otherwise it is set to zero. +
+ PCRE_CONFIG_JIT ++The output is an integer that is set to one if support for just-in-time +compiling is available; otherwise it is set to zero. +
+ PCRE_CONFIG_JITTARGET ++The output is a pointer to a zero-terminated "const char *" string. If JIT +support is available, the string contains the name of the architecture for +which the JIT compiler is configured, for example "x86 32bit (little endian + +unaligned)". If JIT support is not available, the result is NULL. +
+ PCRE_CONFIG_NEWLINE ++The output is an integer whose value specifies the default character sequence +that is recognized as meaning "newline". The values that are supported in +ASCII/Unicode environments are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for +ANYCRLF, and -1 for ANY. In EBCDIC environments, CR, ANYCRLF, and ANY yield the +same values. However, the value for LF is normally 21, though some EBCDIC +environments use 37. The corresponding values for CRLF are 3349 and 3365. The +default should normally correspond to the standard sequence for your operating +system. +
+ PCRE_CONFIG_BSR ++The output is an integer whose value indicates what character sequences the \R +escape sequence matches by default. A value of 0 means that \R matches any +Unicode line ending sequence; a value of 1 means that \R matches only CR, LF, +or CRLF. The default can be overridden when a pattern is compiled or matched. +
+ PCRE_CONFIG_LINK_SIZE ++The output is an integer that contains the number of bytes used for internal +linkage in compiled regular expressions. For the 8-bit library, the value can +be 2, 3, or 4. For the 16-bit library, the value is either 2 or 4 and is still +a number of bytes. For the 32-bit library, the value is either 2 or 4 and is +still a number of bytes. The default value of 2 is sufficient for all but the +most massive patterns, since it allows the compiled pattern to be up to 64K in +size. Larger values allow larger regular expressions to be compiled, at the +expense of slower matching. +
+ PCRE_CONFIG_POSIX_MALLOC_THRESHOLD ++The output is an integer that contains the threshold above which the POSIX +interface uses malloc() for output vectors. Further details are given in +the +pcreposix +documentation. +
+ PCRE_CONFIG_MATCH_LIMIT ++The output is a long integer that gives the default limit for the number of +internal matching function calls in a pcre_exec() execution. Further +details are given with pcre_exec() below. +
+ PCRE_CONFIG_MATCH_LIMIT_RECURSION ++The output is a long integer that gives the default limit for the depth of +recursion when calling the internal matching function in a pcre_exec() +execution. Further details are given with pcre_exec() below. +
+ PCRE_CONFIG_STACKRECURSE ++The output is an integer that is set to one if internal recursion when running +pcre_exec() is implemented by recursive function calls that use the stack +to remember their state. This is the usual way that PCRE is compiled. The +output is zero if PCRE was compiled to use blocks of data on the heap instead +of recursive function calls. In this case, pcre_stack_malloc and +pcre_stack_free are called to manage memory blocks on the heap, thus +avoiding the use of the stack. + +
+pcre *pcre_compile(const char *pattern, int options, +const char **errptr, int *erroffset, +const unsigned char *tableptr); +pcre *pcre_compile2(const char *pattern, int options, +int *errorcodeptr, +const char **errptr, int *erroffset, +const unsigned char *tableptr); +
++Either of the functions pcre_compile() or pcre_compile2() can be +called to compile a pattern into an internal form. The only difference between +the two interfaces is that pcre_compile2() has an additional argument, +errorcodeptr, via which a numerical error code can be returned. To avoid +too much repetition, we refer just to pcre_compile() below, but the +information applies equally to pcre_compile2(). +
++The pattern is a C string terminated by a binary zero, and is passed in the +pattern argument. A pointer to a single block of memory that is obtained +via pcre_malloc is returned. This contains the compiled code and related +data. The pcre type is defined for the returned block; this is a typedef +for a structure whose contents are not externally defined. It is up to the +caller to free the memory (via pcre_free) when it is no longer required. +
++Although the compiled code of a PCRE regex is relocatable, that is, it does not +depend on memory location, the complete pcre data block is not +fully relocatable, because it may contain a copy of the tableptr +argument, which is an address (see below). +
++The options argument contains various bit settings that affect the +compilation. It should be zero if no options are required. The available +options are described below. Some of them (in particular, those that are +compatible with Perl, but some others as well) can also be set and unset from +within the pattern (see the detailed description in the +pcrepattern +documentation). For those options that can be different in different parts of +the pattern, the contents of the options argument specifies their +settings at the start of compilation and execution. The PCRE_ANCHORED, +PCRE_BSR_xxx, PCRE_NEWLINE_xxx, PCRE_NO_UTF8_CHECK, and +PCRE_NO_START_OPTIMIZE options can be set at the time of matching as well as at +compile time. +
++If errptr is NULL, pcre_compile() returns NULL immediately. +Otherwise, if compilation of a pattern fails, pcre_compile() returns +NULL, and sets the variable pointed to by errptr to point to a textual +error message. This is a static string that is part of the library. You must +not try to free it. Normally, the offset from the start of the pattern to the +byte that was being processed when the error was discovered is placed in the +variable pointed to by erroffset, which must not be NULL (if it is, an +immediate error is given). However, for an invalid UTF-8 string, the offset is +that of the first byte of the failing character. +
++Some errors are not detected until the whole pattern has been scanned; in these +cases, the offset passed back is the length of the pattern. Note that the +offset is in bytes, not characters, even in UTF-8 mode. It may sometimes point +into the middle of a UTF-8 character. +
++If pcre_compile2() is used instead of pcre_compile(), and the +errorcodeptr argument is not NULL, a non-zero error code number is +returned via this argument in the event of an error. This is in addition to the +textual error message. Error codes and messages are listed below. +
++If the final argument, tableptr, is NULL, PCRE uses a default set of +character tables that are built when PCRE is compiled, using the default C +locale. Otherwise, tableptr must be an address that is the result of a +call to pcre_maketables(). This value is stored with the compiled +pattern, and used again by pcre_exec(), unless another table pointer is +passed to it. For more discussion, see the section on locale support below. +
++This code fragment shows a typical straightforward call to pcre_compile(): +
+ pcre *re; + const char *error; + int erroffset; + re = pcre_compile( + "^A.*Z", /* the pattern */ + 0, /* default options */ + &error, /* for error message */ + &erroffset, /* for error offset */ + NULL); /* use default character tables */ ++The following names for option bits are defined in the pcre.h header +file: +
+ PCRE_ANCHORED ++If this bit is set, the pattern is forced to be "anchored", that is, it is +constrained to match only at the first matching point in the string that is +being searched (the "subject string"). This effect can also be achieved by +appropriate constructs in the pattern itself, which is the only way to do it in +Perl. +
+ PCRE_AUTO_CALLOUT ++If this bit is set, pcre_compile() automatically inserts callout items, +all with number 255, before each pattern item. For discussion of the callout +facility, see the +pcrecallout +documentation. +
+ PCRE_BSR_ANYCRLF + PCRE_BSR_UNICODE ++These options (which are mutually exclusive) control what the \R escape +sequence matches. The choice is either to match only CR, LF, or CRLF, or to +match any Unicode newline sequence. The default is specified when PCRE is +built. It can be overridden from within the pattern, or by setting an option +when a compiled pattern is matched. +
+ PCRE_CASELESS ++If this bit is set, letters in the pattern match both upper and lower case +letters. It is equivalent to Perl's /i option, and it can be changed within a +pattern by a (?i) option setting. In UTF-8 mode, PCRE always understands the +concept of case for characters whose values are less than 128, so caseless +matching is always possible. For characters with higher values, the concept of +case is supported if PCRE is compiled with Unicode property support, but not +otherwise. If you want to use caseless matching for characters 128 and above, +you must ensure that PCRE is compiled with Unicode property support as well as +with UTF-8 support. +
+ PCRE_DOLLAR_ENDONLY ++If this bit is set, a dollar metacharacter in the pattern matches only at the +end of the subject string. Without this option, a dollar also matches +immediately before a newline at the end of the string (but not before any other +newlines). The PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is set. +There is no equivalent to this option in Perl, and no way to set it within a +pattern. +
+ PCRE_DOTALL ++If this bit is set, a dot metacharacter in the pattern matches a character of +any value, including one that indicates a newline. However, it only ever +matches one character, even if newlines are coded as CRLF. Without this option, +a dot does not match when the current position is at a newline. This option is +equivalent to Perl's /s option, and it can be changed within a pattern by a +(?s) option setting. A negative class such as [^a] always matches newline +characters, independent of the setting of this option. +
+ PCRE_DUPNAMES ++If this bit is set, names used to identify capturing subpatterns need not be +unique. This can be helpful for certain types of pattern when it is known that +only one instance of the named subpattern can ever be matched. There are more +details of named subpatterns below; see also the +pcrepattern +documentation. +
+ PCRE_EXTENDED ++If this bit is set, white space data characters in the pattern are totally +ignored except when escaped or inside a character class. White space does not +include the VT character (code 11). In addition, characters between an +unescaped # outside a character class and the next newline, inclusive, are also +ignored. This is equivalent to Perl's /x option, and it can be changed within a +pattern by a (?x) option setting. + +
+Which characters are interpreted as newlines is controlled by the options +passed to pcre_compile() or by a special sequence at the start of the +pattern, as described in the section entitled +"Newline conventions" +in the pcrepattern documentation. Note that the end of this type of +comment is a literal newline sequence in the pattern; escape sequences that +happen to represent a newline do not count. +
++This option makes it possible to include comments inside complicated patterns. +Note, however, that this applies only to data characters. White space characters +may never appear within special character sequences in a pattern, for example +within the sequence (?( that introduces a conditional subpattern. +
+ PCRE_EXTRA ++This option was invented in order to turn on additional functionality of PCRE +that is incompatible with Perl, but it is currently of very little use. When +set, any backslash in a pattern that is followed by a letter that has no +special meaning causes an error, thus reserving these combinations for future +expansion. By default, as in Perl, a backslash followed by a letter with no +special meaning is treated as a literal. (Perl can, however, be persuaded to +give an error for this, by running it with the -w option.) There are at present +no other features controlled by this option. It can also be set by a (?X) +option setting within a pattern. +
+ PCRE_FIRSTLINE ++If this option is set, an unanchored pattern is required to match before or at +the first newline in the subject string, though the matched text may continue +over the newline. +
+ PCRE_JAVASCRIPT_COMPAT ++If this option is set, PCRE's behaviour is changed in some ways so that it is +compatible with JavaScript rather than Perl. The changes are as follows: + +
+(1) A lone closing square bracket in a pattern causes a compile-time error, +because this is illegal in JavaScript (by default it is treated as a data +character). Thus, the pattern AB]CD becomes illegal when this option is set. +
++(2) At run time, a back reference to an unset subpattern group matches an empty +string (by default this causes the current matching alternative to fail). A +pattern such as (\1)(a) succeeds when this option is set (assuming it can find +an "a" in the subject), whereas it fails by default, for Perl compatibility. +
++(3) \U matches an upper case "U" character; by default \U causes a compile +time error (Perl uses \U to upper case subsequent characters). +
++(4) \u matches a lower case "u" character unless it is followed by four +hexadecimal digits, in which case the hexadecimal number defines the code point +to match. By default, \u causes a compile time error (Perl uses it to upper +case the following character). +
++(5) \x matches a lower case "x" character unless it is followed by two +hexadecimal digits, in which case the hexadecimal number defines the code point +to match. By default, as in Perl, a hexadecimal number is always expected after +\x, but it may have zero, one, or two digits (so, for example, \xz matches a +binary zero character followed by z). +
+ PCRE_MULTILINE ++By default, PCRE treats the subject string as consisting of a single line of +characters (even if it actually contains newlines). The "start of line" +metacharacter (^) matches only at the start of the string, while the "end of +line" metacharacter ($) matches only at the end of the string, or before a +terminating newline (unless PCRE_DOLLAR_ENDONLY is set). This is the same as +Perl. + +
+When PCRE_MULTILINE it is set, the "start of line" and "end of line" constructs +match immediately following or immediately before internal newlines in the +subject string, respectively, as well as at the very start and end. This is +equivalent to Perl's /m option, and it can be changed within a pattern by a +(?m) option setting. If there are no newlines in a subject string, or no +occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect. +
+ PCRE_NEWLINE_CR + PCRE_NEWLINE_LF + PCRE_NEWLINE_CRLF + PCRE_NEWLINE_ANYCRLF + PCRE_NEWLINE_ANY ++These options override the default newline definition that was chosen when PCRE +was built. Setting the first or the second specifies that a newline is +indicated by a single character (CR or LF, respectively). Setting +PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character +CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three +preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies +that any Unicode newline sequence should be recognized. + +
+In an ASCII/Unicode environment, the Unicode newline sequences are the three +just mentioned, plus the single characters VT (vertical tab, U+000B), FF (form +feed, U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS +(paragraph separator, U+2029). For the 8-bit library, the last two are +recognized only in UTF-8 mode. +
++When PCRE is compiled to run in an EBCDIC (mainframe) environment, the code for +CR is 0x0d, the same as ASCII. However, the character code for LF is normally +0x15, though in some EBCDIC environments 0x25 is used. Whichever of these is +not LF is made to correspond to Unicode's NEL character. EBCDIC codes are all +less than 256. For more details, see the +pcrebuild +documentation. +
++The newline setting in the options word uses three bits that are treated +as a number, giving eight possibilities. Currently only six are used (default +plus the five values above). This means that if you set more than one newline +option, the combination may or may not be sensible. For example, +PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but +other combinations may yield unused numbers and cause an error. +
++The only time that a line break in a pattern is specially recognized when +compiling is when PCRE_EXTENDED is set. CR and LF are white space characters, +and so are ignored in this mode. Also, an unescaped # outside a character class +indicates a comment that lasts until after the next line break sequence. In +other circumstances, line break sequences in patterns are treated as literal +data. +
++The newline option that is set at compile time becomes the default that is used +for pcre_exec() and pcre_dfa_exec(), but it can be overridden. +
+ PCRE_NO_AUTO_CAPTURE ++If this option is set, it disables the use of numbered capturing parentheses in +the pattern. Any opening parenthesis that is not followed by ? behaves as if it +were followed by ?: but named parentheses can still be used for capturing (and +they acquire numbers in the usual way). There is no equivalent of this option +in Perl. +
+ NO_START_OPTIMIZE ++This is an option that acts at matching time; that is, it is really an option +for pcre_exec() or pcre_dfa_exec(). If it is set at compile time, +it is remembered with the compiled pattern and assumed at matching time. For +details see the discussion of PCRE_NO_START_OPTIMIZE +below. +
+ PCRE_UCP ++This option changes the way PCRE processes \B, \b, \D, \d, \S, \s, \W, +\w, and some of the POSIX character classes. By default, only ASCII characters +are recognized, but if PCRE_UCP is set, Unicode properties are used instead to +classify characters. More details are given in the section on +generic character types +in the +pcrepattern +page. If you set PCRE_UCP, matching one of the items it affects takes much +longer. The option is available only if PCRE has been compiled with Unicode +property support. +
+ PCRE_UNGREEDY ++This option inverts the "greediness" of the quantifiers so that they are not +greedy by default, but become greedy if followed by "?". It is not compatible +with Perl. It can also be set by a (?U) option setting within the pattern. +
+ PCRE_UTF8 ++This option causes PCRE to regard both the pattern and the subject as strings +of UTF-8 characters instead of single-byte strings. However, it is available +only when PCRE is built to include UTF support. If not, the use of this option +provokes an error. Details of how this option changes the behaviour of PCRE are +given in the +pcreunicode +page. +
+ PCRE_NO_UTF8_CHECK ++When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is +automatically checked. There is a discussion about the +validity of UTF-8 strings +in the +pcreunicode +page. If an invalid UTF-8 sequence is found, pcre_compile() returns an +error. If you already know that your pattern is valid, and you want to skip +this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK option. +When it is set, the effect of passing an invalid UTF-8 string as a pattern is +undefined. It may cause your program to crash. Note that this option can also +be passed to pcre_exec() and pcre_dfa_exec(), to suppress the +validity checking of subject strings only. If the same string is being matched +many times, the option can be safely set for the second and subsequent +matchings to improve performance. + +
+The following table lists the error codes than may be returned by +pcre_compile2(), along with the error messages that may be returned by +both compiling functions. Note that error messages are always 8-bit ASCII +strings, even in 16-bit or 32-bit mode. As PCRE has developed, some error codes +have fallen out of use. To avoid confusion, they have not been re-used. +
+ 0 no error
+ 1 \ at end of pattern
+ 2 \c at end of pattern
+ 3 unrecognized character follows \
+ 4 numbers out of order in {} quantifier
+ 5 number too big in {} quantifier
+ 6 missing terminating ] for character class
+ 7 invalid escape sequence in character class
+ 8 range out of order in character class
+ 9 nothing to repeat
+ 10 [this code is not in use]
+ 11 internal error: unexpected repeat
+ 12 unrecognized character after (? or (?-
+ 13 POSIX named classes are supported only within a class
+ 14 missing )
+ 15 reference to non-existent subpattern
+ 16 erroffset passed as NULL
+ 17 unknown option bit(s) set
+ 18 missing ) after comment
+ 19 [this code is not in use]
+ 20 regular expression is too large
+ 21 failed to get memory
+ 22 unmatched parentheses
+ 23 internal error: code overflow
+ 24 unrecognized character after (?<
+ 25 lookbehind assertion is not fixed length
+ 26 malformed number or name after (?(
+ 27 conditional group contains more than two branches
+ 28 assertion expected after (?(
+ 29 (?R or (?[+-]digits must be followed by )
+ 30 unknown POSIX class name
+ 31 POSIX collating elements are not supported
+ 32 this version of PCRE is compiled without UTF support
+ 33 [this code is not in use]
+ 34 character value in \x{...} sequence is too large
+ 35 invalid condition (?(0)
+ 36 \C not allowed in lookbehind assertion
+ 37 PCRE does not support \L, \l, \N{name}, \U, or \u
+ 38 number after (?C is > 255
+ 39 closing ) for (?C expected
+ 40 recursive call could loop indefinitely
+ 41 unrecognized character after (?P
+ 42 syntax error in subpattern name (missing terminator)
+ 43 two named subpatterns have the same name
+ 44 invalid UTF-8 string (specifically UTF-8)
+ 45 support for \P, \p, and \X has not been compiled
+ 46 malformed \P or \p sequence
+ 47 unknown property name after \P or \p
+ 48 subpattern name is too long (maximum 32 characters)
+ 49 too many named subpatterns (maximum 10000)
+ 50 [this code is not in use]
+ 51 octal value is greater than \377 in 8-bit non-UTF-8 mode
+ 52 internal error: overran compiling workspace
+ 53 internal error: previously-checked referenced subpattern
+ not found
+ 54 DEFINE group contains more than one branch
+ 55 repeating a DEFINE group is not allowed
+ 56 inconsistent NEWLINE options
+ 57 \g is not followed by a braced, angle-bracketed, or quoted
+ name/number or by a plain number
+ 58 a numbered reference must not be zero
+ 59 an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT)
+ 60 (*VERB) not recognized
+ 61 number is too big
+ 62 subpattern name expected
+ 63 digit expected after (?+
+ 64 ] is an invalid data character in JavaScript compatibility mode
+ 65 different names for subpatterns of the same number are
+ not allowed
+ 66 (*MARK) must have an argument
+ 67 this version of PCRE is not compiled with Unicode property
+ support
+ 68 \c must be followed by an ASCII character
+ 69 \k is not followed by a braced, angle-bracketed, or quoted name
+ 70 internal error: unknown opcode in find_fixedlength()
+ 71 \N is not supported in a class
+ 72 too many forward references
+ 73 disallowed Unicode code point (>= 0xd800 && <= 0xdfff)
+ 74 invalid UTF-16 string (specifically UTF-16)
+ 75 name is too long in (*MARK), (*PRUNE), (*SKIP), or (*THEN)
+ 76 character value in \u.... sequence is too large
+ 77 invalid UTF-32 string (specifically UTF-32)
+
+The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may
+be used if the limits were changed when PCRE was built.
+
++pcre_extra *pcre_study(const pcre *code, int options +const char **errptr); +
++If a compiled pattern is going to be used several times, it is worth spending +more time analyzing it in order to speed up the time taken for matching. The +function pcre_study() takes a pointer to a compiled pattern as its first +argument. If studying the pattern produces additional information that will +help speed up matching, pcre_study() returns a pointer to a +pcre_extra block, in which the study_data field points to the +results of the study. +
++The returned value from pcre_study() can be passed directly to +pcre_exec() or pcre_dfa_exec(). However, a pcre_extra block +also contains other fields that can be set by the caller before the block is +passed; these are described +below +in the section on matching a pattern. +
++If studying the pattern does not produce any useful information, +pcre_study() returns NULL by default. In that circumstance, if the +calling program wants to pass any of the other fields to pcre_exec() or +pcre_dfa_exec(), it must set up its own pcre_extra block. However, +if pcre_study() is called with the PCRE_STUDY_EXTRA_NEEDED option, it +returns a pcre_extra block even if studying did not find any additional +information. It may still return NULL, however, if an error occurs in +pcre_study(). +
++The second argument of pcre_study() contains option bits. There are three +further options in addition to PCRE_STUDY_EXTRA_NEEDED: +
+ PCRE_STUDY_JIT_COMPILE + PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE + PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE ++If any of these are set, and the just-in-time compiler is available, the +pattern is further compiled into machine code that executes much faster than +the pcre_exec() interpretive matching function. If the just-in-time +compiler is not available, these options are ignored. All undefined bits in the +options argument must be zero. + +
+JIT compilation is a heavyweight optimization. It can take some time for +patterns to be analyzed, and for one-off matches and simple patterns the +benefit of faster execution might be offset by a much slower study time. +Not all patterns can be optimized by the JIT compiler. For those that cannot be +handled, matching automatically falls back to the pcre_exec() +interpreter. For more details, see the +pcrejit +documentation. +
++The third argument for pcre_study() is a pointer for an error message. If +studying succeeds (even if no data is returned), the variable it points to is +set to NULL. Otherwise it is set to point to a textual error message. This is a +static string that is part of the library. You must not try to free it. You +should test the error pointer for NULL after calling pcre_study(), to be +sure that it has run successfully. +
++When you are finished with a pattern, you can free the memory used for the +study data by calling pcre_free_study(). This function was added to the +API for release 8.20. For earlier versions, the memory could be freed with +pcre_free(), just like the pattern itself. This will still work in cases +where JIT optimization is not used, but it is advisable to change to the new +function when convenient. +
++This is a typical way in which pcre_study() is used (except that in a +real application there should be tests for errors): +
+ int rc;
+ pcre *re;
+ pcre_extra *sd;
+ re = pcre_compile("pattern", 0, &error, &erroroffset, NULL);
+ sd = pcre_study(
+ re, /* result of pcre_compile() */
+ 0, /* no options */
+ &error); /* set to NULL or points to a message */
+ rc = pcre_exec( /* see below for details of pcre_exec() options */
+ re, sd, "subject", 7, 0, 0, ovector, 30);
+ ...
+ pcre_free_study(sd);
+ pcre_free(re);
+
+Studying a pattern does two things: first, a lower bound for the length of
+subject string that is needed to match the pattern is computed. This does not
+mean that there are any strings of that length that match, but it does
+guarantee that no shorter strings match. The value is used to avoid wasting
+time by trying to match strings that are shorter than the lower bound. You can
+find out the value in a calling program via the pcre_fullinfo() function.
+
++Studying a pattern is also useful for non-anchored patterns that do not have a +single fixed starting character. A bitmap of possible starting bytes is +created. This speeds up finding a position in the subject at which to start +matching. (In 16-bit mode, the bitmap is used for 16-bit values less than 256. +In 32-bit mode, the bitmap is used for 32-bit values less than 256.) +
++These two optimizations apply to both pcre_exec() and +pcre_dfa_exec(), and the information is also used by the JIT compiler. +The optimizations can be disabled by setting the PCRE_NO_START_OPTIMIZE option +when calling pcre_exec() or pcre_dfa_exec(), but if this is done, +JIT execution is also disabled. You might want to do this if your pattern +contains callouts or (*MARK) and you want to make use of these facilities in +cases where matching fails. See the discussion of PCRE_NO_START_OPTIMIZE +below. +
++PCRE handles caseless matching, and determines whether characters are letters, +digits, or whatever, by reference to a set of tables, indexed by character +value. When running in UTF-8 mode, this applies only to characters +with codes less than 128. By default, higher-valued codes never match escapes +such as \w or \d, but they can be tested with \p if PCRE is built with +Unicode character property support. Alternatively, the PCRE_UCP option can be +set at compile time; this causes \w and friends to use Unicode property +support instead of built-in tables. The use of locales with Unicode is +discouraged. If you are handling characters with codes greater than 128, you +should either use UTF-8 and Unicode, or use locales, but not try to mix the +two. +
++PCRE contains an internal set of tables that are used when the final argument +of pcre_compile() is NULL. These are sufficient for many applications. +Normally, the internal tables recognize only ASCII characters. However, when +PCRE is built, it is possible to cause the internal tables to be rebuilt in the +default "C" locale of the local system, which may cause them to be different. +
++The internal tables can always be overridden by tables supplied by the +application that calls PCRE. These may be created in a different locale from +the default. As more and more applications change to using Unicode, the need +for this locale support is expected to die away. +
++External tables are built by calling the pcre_maketables() function, +which has no arguments, in the relevant locale. The result can then be passed +to pcre_compile() or pcre_exec() as often as necessary. For +example, to build and use tables that are appropriate for the French locale +(where accented characters with values greater than 128 are treated as letters), +the following code could be used: +
+ setlocale(LC_CTYPE, "fr_FR"); + tables = pcre_maketables(); + re = pcre_compile(..., tables); ++The locale name "fr_FR" is used on Linux and other Unix-like systems; if you +are using Windows, the name for the French locale is "french". + +
+When pcre_maketables() runs, the tables are built in memory that is +obtained via pcre_malloc. It is the caller's responsibility to ensure +that the memory containing the tables remains available for as long as it is +needed. +
++The pointer that is passed to pcre_compile() is saved with the compiled +pattern, and the same tables are used via this pointer by pcre_study() +and normally also by pcre_exec(). Thus, by default, for any single +pattern, compilation, studying and matching all happen in the same locale, but +different patterns can be compiled in different locales. +
++It is possible to pass a table pointer or NULL (indicating the use of the +internal tables) to pcre_exec(). Although not intended for this purpose, +this facility could be used to match a pattern in a different locale from the +one in which it was compiled. Passing table pointers at run time is discussed +below in the section on matching a pattern. +
++int pcre_fullinfo(const pcre *code, const pcre_extra *extra, +int what, void *where); +
++The pcre_fullinfo() function returns information about a compiled +pattern. It replaces the pcre_info() function, which was removed from the +library at version 8.30, after more than 10 years of obsolescence. +
++The first argument for pcre_fullinfo() is a pointer to the compiled +pattern. The second argument is the result of pcre_study(), or NULL if +the pattern was not studied. The third argument specifies which piece of +information is required, and the fourth argument is a pointer to a variable +to receive the data. The yield of the function is zero for success, or one of +the following negative numbers: +
+ PCRE_ERROR_NULL the argument code was NULL + the argument where was NULL + PCRE_ERROR_BADMAGIC the "magic number" was not found + PCRE_ERROR_BADENDIANNESS the pattern was compiled with different + endianness + PCRE_ERROR_BADOPTION the value of what was invalid ++The "magic number" is placed at the start of each compiled pattern as an simple +check against passing an arbitrary memory pointer. The endianness error can +occur if a compiled pattern is saved and reloaded on a different host. Here is +a typical call of pcre_fullinfo(), to obtain the length of the compiled +pattern: +
+ int rc; + size_t length; + rc = pcre_fullinfo( + re, /* result of pcre_compile() */ + sd, /* result of pcre_study(), or NULL */ + PCRE_INFO_SIZE, /* what is required */ + &length); /* where to put the data */ ++The possible values for the third argument are defined in pcre.h, and are +as follows: +
+ PCRE_INFO_BACKREFMAX ++Return the number of the highest back reference in the pattern. The fourth +argument should point to an int variable. Zero is returned if there are +no back references. +
+ PCRE_INFO_CAPTURECOUNT ++Return the number of capturing subpatterns in the pattern. The fourth argument +should point to an int variable. +
+ PCRE_INFO_DEFAULT_TABLES ++Return a pointer to the internal default character tables within PCRE. The +fourth argument should point to an unsigned char * variable. This +information call is provided for internal use by the pcre_study() +function. External callers can cause PCRE to use its internal tables by passing +a NULL table pointer. +
+ PCRE_INFO_FIRSTBYTE ++Return information about the first data unit of any matched string, for a +non-anchored pattern. (The name of this option refers to the 8-bit library, +where data units are bytes.) The fourth argument should point to an int +variable. + +
+If there is a fixed first value, for example, the letter "c" from a pattern +such as (cat|cow|coyote), its value is returned. In the 8-bit library, the +value is always less than 256. In the 16-bit library the value can be up to +0xffff. In the 32-bit library the value can be up to 0x10ffff. +
+
+If there is no fixed first value, and if either
+
+
+(a) the pattern was compiled with the PCRE_MULTILINE option, and every branch
+starts with "^", or
+
+
+(b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set
+(if it were set, the pattern would be anchored),
+
+
+-1 is returned, indicating that the pattern matches only at the start of a
+subject string or after any newline within the string. Otherwise -2 is
+returned. For anchored patterns, -2 is returned.
+
+Since for the 32-bit library using the non-UTF-32 mode, this function is unable +to return the full 32-bit range of the character, this value is deprecated; +instead the PCRE_INFO_FIRSTCHARACTERFLAGS and PCRE_INFO_FIRSTCHARACTER values +should be used. +
+ PCRE_INFO_FIRSTTABLE ++If the pattern was studied, and this resulted in the construction of a 256-bit +table indicating a fixed set of values for the first data unit in any matching +string, a pointer to the table is returned. Otherwise NULL is returned. The +fourth argument should point to an unsigned char * variable. +
+ PCRE_INFO_HASCRORLF ++Return 1 if the pattern contains any explicit matches for CR or LF characters, +otherwise 0. The fourth argument should point to an int variable. An +explicit match is either a literal CR or LF character, or \r or \n. +
+ PCRE_INFO_JCHANGED ++Return 1 if the (?J) or (?-J) option setting is used in the pattern, otherwise +0. The fourth argument should point to an int variable. (?J) and +(?-J) set and unset the local PCRE_DUPNAMES option, respectively. +
+ PCRE_INFO_JIT ++Return 1 if the pattern was studied with one of the JIT options, and +just-in-time compiling was successful. The fourth argument should point to an +int variable. A return value of 0 means that JIT support is not available +in this version of PCRE, or that the pattern was not studied with a JIT option, +or that the JIT compiler could not handle this particular pattern. See the +pcrejit +documentation for details of what can and cannot be handled. +
+ PCRE_INFO_JITSIZE ++If the pattern was successfully studied with a JIT option, return the size of +the JIT compiled code, otherwise return zero. The fourth argument should point +to a size_t variable. +
+ PCRE_INFO_LASTLITERAL ++Return the value of the rightmost literal data unit that must exist in any +matched string, other than at its start, if such a value has been recorded. The +fourth argument should point to an int variable. If there is no such +value, -1 is returned. For anchored patterns, a last literal value is recorded +only if it follows something of variable length. For example, for the pattern +/^a\d+z\d+/ the returned value is "z", but for /^a\dz\d/ the returned value +is -1. + +
+Since for the 32-bit library using the non-UTF-32 mode, this function is unable +to return the full 32-bit range of the character, this value is deprecated; +instead the PCRE_INFO_REQUIREDCHARFLAGS and PCRE_INFO_REQUIREDCHAR values should +be used. +
+ PCRE_INFO_MAXLOOKBEHIND ++Return the number of characters (NB not bytes) in the longest lookbehind +assertion in the pattern. Note that the simple assertions \b and \B require a +one-character lookbehind. This information is useful when doing multi-segment +matching using the partial matching facilities. +
+ PCRE_INFO_MINLENGTH ++If the pattern was studied and a minimum length for matching subject strings +was computed, its value is returned. Otherwise the returned value is -1. The +value is a number of characters, which in UTF-8 mode may be different from the +number of bytes. The fourth argument should point to an int variable. A +non-negative value is a lower bound to the length of any matching string. There +may not be any strings of that length that do actually match, but every string +that does match is at least that long. +
+ PCRE_INFO_NAMECOUNT + PCRE_INFO_NAMEENTRYSIZE + PCRE_INFO_NAMETABLE ++PCRE supports the use of named as well as numbered capturing parentheses. The +names are just an additional way of identifying the parentheses, which still +acquire numbers. Several convenience functions such as +pcre_get_named_substring() are provided for extracting captured +substrings by name. It is also possible to extract the data directly, by first +converting the name to a number in order to access the correct pointers in the +output vector (described with pcre_exec() below). To do the conversion, +you need to use the name-to-number map, which is described by these three +values. + +
+The map consists of a number of fixed-size entries. PCRE_INFO_NAMECOUNT gives +the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size of each +entry; both of these return an int value. The entry size depends on the +length of the longest name. PCRE_INFO_NAMETABLE returns a pointer to the first +entry of the table. This is a pointer to char in the 8-bit library, where +the first two bytes of each entry are the number of the capturing parenthesis, +most significant byte first. In the 16-bit library, the pointer points to +16-bit data units, the first of which contains the parenthesis number. +In the 32-bit library, the pointer points to 32-bit data units, the first of +which contains the parenthesis number. The rest +of the entry is the corresponding name, zero terminated. +
++The names are in alphabetical order. Duplicate names may appear if (?| is used +to create multiple groups with the same number, as described in the +section on duplicate subpattern numbers +in the +pcrepattern +page. Duplicate names for subpatterns with different numbers are permitted only +if PCRE_DUPNAMES is set. In all cases of duplicate names, they appear in the +table in the order in which they were found in the pattern. In the absence of +(?| this is the order of increasing number; when (?| is used this is not +necessarily the case because later subpatterns may have lower numbers. +
++As a simple example of the name/number table, consider the following pattern +after compilation by the 8-bit library (assume PCRE_EXTENDED is set, so white +space - including newlines - is ignored): +
+ (?<date> (?<year>(\d\d)?\d\d) - (?<month>\d\d) - (?<day>\d\d) ) ++There are four named subpatterns, so the table has four entries, and each entry +in the table is eight bytes long. The table is as follows, with non-printing +bytes shows in hexadecimal, and undefined bytes shown as ??: +
+ 00 01 d a t e 00 ?? + 00 05 d a y 00 ?? ?? + 00 04 m o n t h 00 + 00 02 y e a r 00 ?? ++When writing code to extract data from named subpatterns using the +name-to-number map, remember that the length of the entries is likely to be +different for each compiled pattern. +
+ PCRE_INFO_OKPARTIAL ++Return 1 if the pattern can be used for partial matching with +pcre_exec(), otherwise 0. The fourth argument should point to an +int variable. From release 8.00, this always returns 1, because the +restrictions that previously applied to partial matching have been lifted. The +pcrepartial +documentation gives details of partial matching. +
+ PCRE_INFO_OPTIONS ++Return a copy of the options with which the pattern was compiled. The fourth +argument should point to an unsigned long int variable. These option bits +are those specified in the call to pcre_compile(), modified by any +top-level option settings at the start of the pattern itself. In other words, +they are the options that will be in force when matching starts. For example, +if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the +result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED. + +
+A pattern is automatically anchored by PCRE if all of its top-level +alternatives begin with one of the following: +
+ ^ unless PCRE_MULTILINE is set + \A always + \G always + .* if PCRE_DOTALL is set and there are no back references to the subpattern in which .* appears ++For such patterns, the PCRE_ANCHORED bit is set in the options returned by +pcre_fullinfo(). +
+ PCRE_INFO_SIZE ++Return the size of the compiled pattern in bytes (for both libraries). The +fourth argument should point to a size_t variable. This value does not +include the size of the pcre structure that is returned by +pcre_compile(). The value that is passed as the argument to +pcre_malloc() when pcre_compile() is getting memory in which to +place the compiled data is the value returned by this option plus the size of +the pcre structure. Studying a compiled pattern, with or without JIT, +does not alter the value returned by this option. +
+ PCRE_INFO_STUDYSIZE ++Return the size in bytes of the data block pointed to by the study_data +field in a pcre_extra block. If pcre_extra is NULL, or there is no +study data, zero is returned. The fourth argument should point to a +size_t variable. The study_data field is set by pcre_study() +to record information that will speed up matching (see the section entitled +"Studying a pattern" +above). The format of the study_data block is private, but its length +is made available via this option so that it can be saved and restored (see the +pcreprecompile +documentation for details). +
+ PCRE_INFO_FIRSTCHARACTERFLAGS ++Return information about the first data unit of any matched string, for a +non-anchored pattern. The fourth argument should point to an int +variable. + +
+If there is a fixed first value, for example, the letter "c" from a pattern +such as (cat|cow|coyote), 1 is returned, and the character value can be +retrieved using PCRE_INFO_FIRSTCHARACTER. +
+
+If there is no fixed first value, and if either
+
+
+(a) the pattern was compiled with the PCRE_MULTILINE option, and every branch
+starts with "^", or
+
+
+(b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set
+(if it were set, the pattern would be anchored),
+
+
+2 is returned, indicating that the pattern matches only at the start of a
+subject string or after any newline within the string. Otherwise 0 is
+returned. For anchored patterns, 0 is returned.
+
+ PCRE_INFO_FIRSTCHARACTER ++Return the fixed first character value, if PCRE_INFO_FIRSTCHARACTERFLAGS +returned 1; otherwise returns 0. The fourth argument should point to an +uint_t variable. + +
+In the 8-bit library, the value is always less than 256. In the 16-bit library +the value can be up to 0xffff. In the 32-bit library in UTF-32 mode the value +can be up to 0x10ffff, and up to 0xffffffff when not using UTF-32 mode. +
+
+If there is no fixed first value, and if either
+
+
+(a) the pattern was compiled with the PCRE_MULTILINE option, and every branch
+starts with "^", or
+
+
+(b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set
+(if it were set, the pattern would be anchored),
+
+
+-1 is returned, indicating that the pattern matches only at the start of a
+subject string or after any newline within the string. Otherwise -2 is
+returned. For anchored patterns, -2 is returned.
+
+ PCRE_INFO_REQUIREDCHARFLAGS ++Returns 1 if there is a rightmost literal data unit that must exist in any +matched string, other than at its start. The fourth argument should point to +an int variable. If there is no such value, 0 is returned. If returning +1, the character value itself can be retrieved using PCRE_INFO_REQUIREDCHAR. + +
+For anchored patterns, a last literal value is recorded only if it follows +something of variable length. For example, for the pattern /^a\d+z\d+/ the +returned value 1 (with "z" returned from PCRE_INFO_REQUIREDCHAR), but for +/^a\dz\d/ the returned value is 0. +
+ PCRE_INFO_REQUIREDCHAR ++Return the value of the rightmost literal data unit that must exist in any +matched string, other than at its start, if such a value has been recorded. The +fourth argument should point to an uint32_t variable. If there is no such +value, 0 is returned. + +
+int pcre_refcount(pcre *code, int adjust); +
++The pcre_refcount() function is used to maintain a reference count in the +data block that contains a compiled pattern. It is provided for the benefit of +applications that operate in an object-oriented manner, where different parts +of the application may be using the same compiled pattern, but you want to free +the block when they are all done. +
++When a pattern is compiled, the reference count field is initialized to zero. +It is changed only by calling this function, whose action is to add the +adjust value (which may be positive or negative) to it. The yield of the +function is the new value. However, the value of the count is constrained to +lie between 0 and 65535, inclusive. If the new value is outside these limits, +it is forced to the appropriate limit value. +
++Except when it is zero, the reference count is not correctly preserved if a +pattern is compiled on one host and then transferred to a host whose byte-order +is different. (This seems a highly unlikely scenario.) +
++int pcre_exec(const pcre *code, const pcre_extra *extra, +const char *subject, int length, int startoffset, +int options, int *ovector, int ovecsize); +
++The function pcre_exec() is called to match a subject string against a +compiled pattern, which is passed in the code argument. If the +pattern was studied, the result of the study should be passed in the +extra argument. You can call pcre_exec() with the same code +and extra arguments as many times as you like, in order to match +different subject strings with the same pattern. +
++This function is the main matching facility of the library, and it operates in +a Perl-like manner. For specialist use there is also an alternative matching +function, which is described +below +in the section about the pcre_dfa_exec() function. +
++In most applications, the pattern will have been compiled (and optionally +studied) in the same process that calls pcre_exec(). However, it is +possible to save compiled patterns and study data, and then use them later +in different processes, possibly even on different hosts. For a discussion +about this, see the +pcreprecompile +documentation. +
++Here is an example of a simple call to pcre_exec(): +
+ int rc; + int ovector[30]; + rc = pcre_exec( + re, /* result of pcre_compile() */ + NULL, /* we didn't study the pattern */ + "some string", /* the subject string */ + 11, /* the length of the subject string */ + 0, /* start at offset 0 in the subject */ + 0, /* default options */ + ovector, /* vector of integers for substring information */ + 30); /* number of elements (NOT size in bytes) */ ++ +
+If the extra argument is not NULL, it must point to a pcre_extra +data block. The pcre_study() function returns such a block (when it +doesn't return NULL), but you can also create one for yourself, and pass +additional information in it. The pcre_extra block contains the following +fields (not necessarily in this order): +
+ unsigned long int flags; + void *study_data; + void *executable_jit; + unsigned long int match_limit; + unsigned long int match_limit_recursion; + void *callout_data; + const unsigned char *tables; + unsigned char **mark; ++In the 16-bit version of this structure, the mark field has type +"PCRE_UCHAR16 **". +
+The flags field is used to specify which of the other fields are set. The +flag bits are: +
+ PCRE_EXTRA_CALLOUT_DATA + PCRE_EXTRA_EXECUTABLE_JIT + PCRE_EXTRA_MARK + PCRE_EXTRA_MATCH_LIMIT + PCRE_EXTRA_MATCH_LIMIT_RECURSION + PCRE_EXTRA_STUDY_DATA + PCRE_EXTRA_TABLES ++Other flag bits should be set to zero. The study_data field and sometimes +the executable_jit field are set in the pcre_extra block that is +returned by pcre_study(), together with the appropriate flag bits. You +should not set these yourself, but you may add to the block by setting other +fields and their corresponding flag bits. + +
+The match_limit field provides a means of preventing PCRE from using up a +vast amount of resources when running patterns that are not going to match, +but which have a very large number of possibilities in their search trees. The +classic example is a pattern that uses nested unlimited repeats. +
++Internally, pcre_exec() uses a function called match(), which it +calls repeatedly (sometimes recursively). The limit set by match_limit is +imposed on the number of times this function is called during a match, which +has the effect of limiting the amount of backtracking that can take place. For +patterns that are not anchored, the count restarts from zero for each position +in the subject string. +
++When pcre_exec() is called with a pattern that was successfully studied +with a JIT option, the way that the matching is executed is entirely different. +However, there is still the possibility of runaway matching that goes on for a +very long time, and so the match_limit value is also used in this case +(but in a different way) to limit how long the matching can continue. +
++The default value for the limit can be set when PCRE is built; the default +default is 10 million, which handles all but the most extreme cases. You can +override the default by suppling pcre_exec() with a pcre_extra +block in which match_limit is set, and PCRE_EXTRA_MATCH_LIMIT is set in +the flags field. If the limit is exceeded, pcre_exec() returns +PCRE_ERROR_MATCHLIMIT. +
++The match_limit_recursion field is similar to match_limit, but +instead of limiting the total number of times that match() is called, it +limits the depth of recursion. The recursion depth is a smaller number than the +total number of calls, because not all calls to match() are recursive. +This limit is of use only if it is set smaller than match_limit. +
++Limiting the recursion depth limits the amount of machine stack that can be +used, or, when PCRE has been compiled to use memory on the heap instead of the +stack, the amount of heap memory that can be used. This limit is not relevant, +and is ignored, when matching is done using JIT compiled code. +
++The default value for match_limit_recursion can be set when PCRE is +built; the default default is the same value as the default for +match_limit. You can override the default by suppling pcre_exec() +with a pcre_extra block in which match_limit_recursion is set, and +PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the flags field. If the limit +is exceeded, pcre_exec() returns PCRE_ERROR_RECURSIONLIMIT. +
++The callout_data field is used in conjunction with the "callout" feature, +and is described in the +pcrecallout +documentation. +
++The tables field is used to pass a character tables pointer to +pcre_exec(); this overrides the value that is stored with the compiled +pattern. A non-NULL value is stored with the compiled pattern only if custom +tables were supplied to pcre_compile() via its tableptr argument. +If NULL is passed to pcre_exec() using this mechanism, it forces PCRE's +internal tables to be used. This facility is helpful when re-using patterns +that have been saved after compiling with an external set of tables, because +the external tables might be at a different address when pcre_exec() is +called. See the +pcreprecompile +documentation for a discussion of saving compiled patterns for later use. +
++If PCRE_EXTRA_MARK is set in the flags field, the mark field must +be set to point to a suitable variable. If the pattern contains any +backtracking control verbs such as (*MARK:NAME), and the execution ends up with +a name to pass back, a pointer to the name string (zero terminated) is placed +in the variable pointed to by the mark field. The names are within the +compiled pattern; if you wish to retain such a name you must copy it before +freeing the memory of a compiled pattern. If there is no name to pass back, the +variable pointed to by the mark field is set to NULL. For details of the +backtracking control verbs, see the section entitled +"Backtracking control" +in the +pcrepattern +documentation. +
++The unused bits of the options argument for pcre_exec() must be +zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_xxx, +PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART, +PCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_HARD, and +PCRE_PARTIAL_SOFT. +
++If the pattern was successfully studied with one of the just-in-time (JIT) +compile options, the only supported options for JIT execution are +PCRE_NO_UTF8_CHECK, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, +PCRE_NOTEMPTY_ATSTART, PCRE_PARTIAL_HARD, and PCRE_PARTIAL_SOFT. If an +unsupported option is used, JIT execution is disabled and the normal +interpretive code in pcre_exec() is run. +
+ PCRE_ANCHORED ++The PCRE_ANCHORED option limits pcre_exec() to matching at the first +matching position. If a pattern was compiled with PCRE_ANCHORED, or turned out +to be anchored by virtue of its contents, it cannot be made unachored at +matching time. +
+ PCRE_BSR_ANYCRLF + PCRE_BSR_UNICODE ++These options (which are mutually exclusive) control what the \R escape +sequence matches. The choice is either to match only CR, LF, or CRLF, or to +match any Unicode newline sequence. These options override the choice that was +made or defaulted when the pattern was compiled. +
+ PCRE_NEWLINE_CR + PCRE_NEWLINE_LF + PCRE_NEWLINE_CRLF + PCRE_NEWLINE_ANYCRLF + PCRE_NEWLINE_ANY ++These options override the newline definition that was chosen or defaulted when +the pattern was compiled. For details, see the description of +pcre_compile() above. During matching, the newline choice affects the +behaviour of the dot, circumflex, and dollar metacharacters. It may also alter +the way the match position is advanced after a match failure for an unanchored +pattern. + +
+When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is set, and a +match attempt for an unanchored pattern fails when the current position is at a +CRLF sequence, and the pattern contains no explicit matches for CR or LF +characters, the match position is advanced by two characters instead of one, in +other words, to after the CRLF. +
++The above rule is a compromise that makes the most common cases work as +expected. For example, if the pattern is .+A (and the PCRE_DOTALL option is not +set), it does not match the string "\r\nA" because, after failing at the +start, it skips both the CR and the LF before retrying. However, the pattern +[\r\n]A does match that string, because it contains an explicit CR or LF +reference, and so advances only by one character after the first failure. +
++An explicit match for CR of LF is either a literal appearance of one of those +characters, or one of the \r or \n escape sequences. Implicit matches such as +[^X] do not count, nor does \s (which includes CR and LF in the characters +that it matches). +
++Notwithstanding the above, anomalous effects may still occur when CRLF is a +valid newline sequence and explicit \r or \n escapes appear in the pattern. +
+ PCRE_NOTBOL ++This option specifies that first character of the subject string is not the +beginning of a line, so the circumflex metacharacter should not match before +it. Setting this without PCRE_MULTILINE (at compile time) causes circumflex +never to match. This option affects only the behaviour of the circumflex +metacharacter. It does not affect \A. +
+ PCRE_NOTEOL ++This option specifies that the end of the subject string is not the end of a +line, so the dollar metacharacter should not match it nor (except in multiline +mode) a newline immediately before it. Setting this without PCRE_MULTILINE (at +compile time) causes dollar never to match. This option affects only the +behaviour of the dollar metacharacter. It does not affect \Z or \z. +
+ PCRE_NOTEMPTY ++An empty string is not considered to be a valid match if this option is set. If +there are alternatives in the pattern, they are tried. If all the alternatives +match the empty string, the entire match fails. For example, if the pattern +
+ a?b? ++is applied to a string not beginning with "a" or "b", it matches an empty +string at the start of the subject. With PCRE_NOTEMPTY set, this match is not +valid, so PCRE searches further into the string for occurrences of "a" or "b". +
+ PCRE_NOTEMPTY_ATSTART ++This is like PCRE_NOTEMPTY, except that an empty string match that is not at +the start of the subject is permitted. If the pattern is anchored, such a match +can occur only if the pattern contains \K. + +
+Perl has no direct equivalent of PCRE_NOTEMPTY or PCRE_NOTEMPTY_ATSTART, but it +does make a special case of a pattern match of the empty string within its +split() function, and when using the /g modifier. It is possible to +emulate Perl's behaviour after matching a null string by first trying the match +again at the same offset with PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED, and then +if that fails, by advancing the starting offset (see below) and trying an +ordinary match again. There is some code that demonstrates how to do this in +the +pcredemo +sample program. In the most general case, you have to check to see if the +newline convention recognizes CRLF as a newline, and if so, and the current +character is CR followed by LF, advance the starting offset by two characters +instead of one. +
+ PCRE_NO_START_OPTIMIZE ++There are a number of optimizations that pcre_exec() uses at the start of +a match, in order to speed up the process. For example, if it is known that an +unanchored match must start with a specific character, it searches the subject +for that character, and fails immediately if it cannot find it, without +actually running the main matching function. This means that a special item +such as (*COMMIT) at the start of a pattern is not considered until after a +suitable starting point for the match has been found. When callouts or (*MARK) +items are in use, these "start-up" optimizations can cause them to be skipped +if the pattern is never actually used. The start-up optimizations are in effect +a pre-scan of the subject that takes place before the pattern is run. + +
+The PCRE_NO_START_OPTIMIZE option disables the start-up optimizations, possibly +causing performance to suffer, but ensuring that in cases where the result is +"no match", the callouts do occur, and that items such as (*COMMIT) and (*MARK) +are considered at every possible starting position in the subject string. If +PCRE_NO_START_OPTIMIZE is set at compile time, it cannot be unset at matching +time. The use of PCRE_NO_START_OPTIMIZE disables JIT execution; when it is set, +matching is always done using interpretively. +
++Setting PCRE_NO_START_OPTIMIZE can change the outcome of a matching operation. +Consider the pattern +
+ (*COMMIT)ABC ++When this is compiled, PCRE records the fact that a match must start with the +character "A". Suppose the subject string is "DEFABC". The start-up +optimization scans along the subject, finds "A" and runs the first match +attempt from there. The (*COMMIT) item means that the pattern must match the +current starting position, which in this case, it does. However, if the same +match is run with PCRE_NO_START_OPTIMIZE set, the initial scan along the +subject string does not happen. The first match attempt is run starting from +"D" and when this fails, (*COMMIT) prevents any further matches being tried, so +the overall result is "no match". If the pattern is studied, more start-up +optimizations may be used. For example, a minimum length for the subject may be +recorded. Consider the pattern +
+ (*MARK:A)(X|Y) ++The minimum length for a match is one character. If the subject is "ABC", there +will be attempts to match "ABC", "BC", "C", and then finally an empty string. +If the pattern is studied, the final attempt does not take place, because PCRE +knows that the subject is too short, and so the (*MARK) is never encountered. +In this case, studying the pattern does not affect the overall match result, +which is still "no match", but it does affect the auxiliary information that is +returned. +
+ PCRE_NO_UTF8_CHECK ++When PCRE_UTF8 is set at compile time, the validity of the subject as a UTF-8 +string is automatically checked when pcre_exec() is subsequently called. +The entire string is checked before any other processing takes place. The value +of startoffset is also checked to ensure that it points to the start of a +UTF-8 character. There is a discussion about the +validity of UTF-8 strings +in the +pcreunicode +page. If an invalid sequence of bytes is found, pcre_exec() returns the +error PCRE_ERROR_BADUTF8 or, if PCRE_PARTIAL_HARD is set and the problem is a +truncated character at the end of the subject, PCRE_ERROR_SHORTUTF8. In both +cases, information about the precise nature of the error may also be returned +(see the descriptions of these errors in the section entitled \fIError return +values from\fP pcre_exec() +below). +If startoffset contains a value that does not point to the start of a +UTF-8 character (or to the end of the subject), PCRE_ERROR_BADUTF8_OFFSET is +returned. + +
+If you already know that your subject is valid, and you want to skip these +checks for performance reasons, you can set the PCRE_NO_UTF8_CHECK option when +calling pcre_exec(). You might want to do this for the second and +subsequent calls to pcre_exec() if you are making repeated calls to find +all the matches in a single subject string. However, you should be sure that +the value of startoffset points to the start of a character (or the end +of the subject). When PCRE_NO_UTF8_CHECK is set, the effect of passing an +invalid string as a subject or an invalid value of startoffset is +undefined. Your program may crash. +
+ PCRE_PARTIAL_HARD + PCRE_PARTIAL_SOFT ++These options turn on the partial matching feature. For backwards +compatibility, PCRE_PARTIAL is a synonym for PCRE_PARTIAL_SOFT. A partial match +occurs if the end of the subject string is reached successfully, but there are +not enough subject characters to complete the match. If this happens when +PCRE_PARTIAL_SOFT (but not PCRE_PARTIAL_HARD) is set, matching continues by +testing any remaining alternatives. Only if no complete match can be found is +PCRE_ERROR_PARTIAL returned instead of PCRE_ERROR_NOMATCH. In other words, +PCRE_PARTIAL_SOFT says that the caller is prepared to handle a partial match, +but only if no complete match can be found. + +
+If PCRE_PARTIAL_HARD is set, it overrides PCRE_PARTIAL_SOFT. In this case, if a +partial match is found, pcre_exec() immediately returns +PCRE_ERROR_PARTIAL, without considering any other alternatives. In other words, +when PCRE_PARTIAL_HARD is set, a partial match is considered to be more +important that an alternative complete match. +
++In both cases, the portion of the string that was inspected when the partial +match was found is set as the first matching string. There is a more detailed +discussion of partial and multi-segment matching, with examples, in the +pcrepartial +documentation. +
++The subject string is passed to pcre_exec() as a pointer in +subject, a length in bytes in length, and a starting byte offset +in startoffset. If this is negative or greater than the length of the +subject, pcre_exec() returns PCRE_ERROR_BADOFFSET. When the starting +offset is zero, the search for a match starts at the beginning of the subject, +and this is by far the most common case. In UTF-8 mode, the byte offset must +point to the start of a UTF-8 character (or the end of the subject). Unlike the +pattern string, the subject may contain binary zero bytes. +
++A non-zero starting offset is useful when searching for another match in the +same subject by calling pcre_exec() again after a previous success. +Setting startoffset differs from just passing over a shortened string and +setting PCRE_NOTBOL in the case of a pattern that begins with any kind of +lookbehind. For example, consider the pattern +
+ \Biss\B ++which finds occurrences of "iss" in the middle of words. (\B matches only if +the current position in the subject is not a word boundary.) When applied to +the string "Mississipi" the first call to pcre_exec() finds the first +occurrence. If pcre_exec() is called again with just the remainder of the +subject, namely "issipi", it does not match, because \B is always false at the +start of the subject, which is deemed to be a word boundary. However, if +pcre_exec() is passed the entire string again, but with startoffset +set to 4, it finds the second occurrence of "iss" because it is able to look +behind the starting point to discover that it is preceded by a letter. + +
+Finding all the matches in a subject is tricky when the pattern can match an +empty string. It is possible to emulate Perl's /g behaviour by first trying the +match again at the same offset, with the PCRE_NOTEMPTY_ATSTART and +PCRE_ANCHORED options, and then if that fails, advancing the starting offset +and trying an ordinary match again. There is some code that demonstrates how to +do this in the +pcredemo +sample program. In the most general case, you have to check to see if the +newline convention recognizes CRLF as a newline, and if so, and the current +character is CR followed by LF, advance the starting offset by two characters +instead of one. +
++If a non-zero starting offset is passed when the pattern is anchored, one +attempt to match at the given offset is made. This can only succeed if the +pattern does not require the match to be at the start of the subject. +
++In general, a pattern matches a certain portion of the subject, and in +addition, further substrings from the subject may be picked out by parts of the +pattern. Following the usage in Jeffrey Friedl's book, this is called +"capturing" in what follows, and the phrase "capturing subpattern" is used for +a fragment of a pattern that picks out a substring. PCRE supports several other +kinds of parenthesized subpattern that do not cause substrings to be captured. +
++Captured substrings are returned to the caller via a vector of integers whose +address is passed in ovector. The number of elements in the vector is +passed in ovecsize, which must be a non-negative number. Note: this +argument is NOT the size of ovector in bytes. +
++The first two-thirds of the vector is used to pass back captured substrings, +each substring using a pair of integers. The remaining third of the vector is +used as workspace by pcre_exec() while matching capturing subpatterns, +and is not available for passing back information. The number passed in +ovecsize should always be a multiple of three. If it is not, it is +rounded down. +
++When a match is successful, information about captured substrings is returned +in pairs of integers, starting at the beginning of ovector, and +continuing up to two-thirds of its length at the most. The first element of +each pair is set to the byte offset of the first character in a substring, and +the second is set to the byte offset of the first character after the end of a +substring. Note: these values are always byte offsets, even in UTF-8 +mode. They are not character counts. +
++The first pair of integers, ovector[0] and ovector[1], identify the +portion of the subject string matched by the entire pattern. The next pair is +used for the first capturing subpattern, and so on. The value returned by +pcre_exec() is one more than the highest numbered pair that has been set. +For example, if two substrings have been captured, the returned value is 3. If +there are no capturing subpatterns, the return value from a successful match is +1, indicating that just the first pair of offsets has been set. +
++If a capturing subpattern is matched repeatedly, it is the last portion of the +string that it matched that is returned. +
++If the vector is too small to hold all the captured substring offsets, it is +used as far as possible (up to two-thirds of its length), and the function +returns a value of zero. If neither the actual string matched nor any captured +substrings are of interest, pcre_exec() may be called with ovector +passed as NULL and ovecsize as zero. However, if the pattern contains +back references and the ovector is not big enough to remember the related +substrings, PCRE has to get additional memory for use during matching. Thus it +is usually advisable to supply an ovector of reasonable size. +
++There are some cases where zero is returned (indicating vector overflow) when +in fact the vector is exactly the right size for the final match. For example, +consider the pattern +
+ (a)(?:(b)c|bd) ++If a vector of 6 elements (allowing for only 1 captured substring) is given +with subject string "abd", pcre_exec() will try to set the second +captured string, thereby recording a vector overflow, before failing to match +"c" and backing up to try the second alternative. The zero return, however, +does correctly indicate that the maximum number of slots (namely 2) have been +filled. In similar cases where there is temporary overflow, but the final +number of used slots is actually less than the maximum, a non-zero value is +returned. + +
+The pcre_fullinfo() function can be used to find out how many capturing +subpatterns there are in a compiled pattern. The smallest size for +ovector that will allow for n captured substrings, in addition to +the offsets of the substring matched by the whole pattern, is (n+1)*3. +
++It is possible for capturing subpattern number n+1 to match some part of +the subject when subpattern n has not been used at all. For example, if +the string "abc" is matched against the pattern (a|(z))(bc) the return from the +function is 4, and subpatterns 1 and 3 are matched, but 2 is not. When this +happens, both values in the offset pairs corresponding to unused subpatterns +are set to -1. +
++Offset values that correspond to unused subpatterns at the end of the +expression are also set to -1. For example, if the string "abc" is matched +against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The +return from the function is 2, because the highest used capturing subpattern +number is 1, and the offsets for for the second and third capturing subpatterns +(assuming the vector is large enough, of course) are set to -1. +
++Note: Elements in the first two-thirds of ovector that do not +correspond to capturing parentheses in the pattern are never changed. That is, +if a pattern contains n capturing parentheses, no more than +ovector[0] to ovector[2n+1] are set by pcre_exec(). The other +elements (in the first two-thirds) retain whatever values they previously had. +
++Some convenience functions are provided for extracting the captured substrings +as separate strings. These are described below. +
++If pcre_exec() fails, it returns a negative number. The following are +defined in the header file: +
+ PCRE_ERROR_NOMATCH (-1) ++The subject string did not match the pattern. +
+ PCRE_ERROR_NULL (-2) ++Either code or subject was passed as NULL, or ovector was +NULL and ovecsize was not zero. +
+ PCRE_ERROR_BADOPTION (-3) ++An unrecognized bit was set in the options argument. +
+ PCRE_ERROR_BADMAGIC (-4) ++PCRE stores a 4-byte "magic number" at the start of the compiled code, to catch +the case when it is passed a junk pointer and to detect when a pattern that was +compiled in an environment of one endianness is run in an environment with the +other endianness. This is the error that PCRE gives when the magic number is +not present. +
+ PCRE_ERROR_UNKNOWN_OPCODE (-5) ++While running the pattern match, an unknown item was encountered in the +compiled pattern. This error could be caused by a bug in PCRE or by overwriting +of the compiled pattern. +
+ PCRE_ERROR_NOMEMORY (-6) ++If a pattern contains back references, but the ovector that is passed to +pcre_exec() is not big enough to remember the referenced substrings, PCRE +gets a block of memory at the start of matching to use for this purpose. If the +call via pcre_malloc() fails, this error is given. The memory is +automatically freed at the end of matching. + +
+This error is also given if pcre_stack_malloc() fails in +pcre_exec(). This can happen only when PCRE has been compiled with +--disable-stack-for-recursion. +
+ PCRE_ERROR_NOSUBSTRING (-7) ++This error is used by the pcre_copy_substring(), +pcre_get_substring(), and pcre_get_substring_list() functions (see +below). It is never returned by pcre_exec(). +
+ PCRE_ERROR_MATCHLIMIT (-8) ++The backtracking limit, as specified by the match_limit field in a +pcre_extra structure (or defaulted) was reached. See the description +above. +
+ PCRE_ERROR_CALLOUT (-9) ++This error is never generated by pcre_exec() itself. It is provided for +use by callout functions that want to yield a distinctive error code. See the +pcrecallout +documentation for details. +
+ PCRE_ERROR_BADUTF8 (-10) ++A string that contains an invalid UTF-8 byte sequence was passed as a subject, +and the PCRE_NO_UTF8_CHECK option was not set. If the size of the output vector +(ovecsize) is at least 2, the byte offset to the start of the the invalid +UTF-8 character is placed in the first element, and a reason code is placed in +the second element. The reason codes are listed in the +following section. +For backward compatibility, if PCRE_PARTIAL_HARD is set and the problem is a +truncated UTF-8 character at the end of the subject (reason codes 1 to 5), +PCRE_ERROR_SHORTUTF8 is returned instead of PCRE_ERROR_BADUTF8. +
+ PCRE_ERROR_BADUTF8_OFFSET (-11) ++The UTF-8 byte sequence that was passed as a subject was checked and found to +be valid (the PCRE_NO_UTF8_CHECK option was not set), but the value of +startoffset did not point to the beginning of a UTF-8 character or the +end of the subject. +
+ PCRE_ERROR_PARTIAL (-12) ++The subject string did not match, but it did match partially. See the +pcrepartial +documentation for details of partial matching. +
+ PCRE_ERROR_BADPARTIAL (-13) ++This code is no longer in use. It was formerly returned when the PCRE_PARTIAL +option was used with a compiled pattern containing items that were not +supported for partial matching. From release 8.00 onwards, there are no +restrictions on partial matching. +
+ PCRE_ERROR_INTERNAL (-14) ++An unexpected internal error has occurred. This error could be caused by a bug +in PCRE or by overwriting of the compiled pattern. +
+ PCRE_ERROR_BADCOUNT (-15) ++This error is given if the value of the ovecsize argument is negative. +
+ PCRE_ERROR_RECURSIONLIMIT (-21) ++The internal recursion limit, as specified by the match_limit_recursion +field in a pcre_extra structure (or defaulted) was reached. See the +description above. +
+ PCRE_ERROR_BADNEWLINE (-23) ++An invalid combination of PCRE_NEWLINE_xxx options was given. +
+ PCRE_ERROR_BADOFFSET (-24) ++The value of startoffset was negative or greater than the length of the +subject, that is, the value in length. +
+ PCRE_ERROR_SHORTUTF8 (-25) ++This error is returned instead of PCRE_ERROR_BADUTF8 when the subject string +ends with a truncated UTF-8 character and the PCRE_PARTIAL_HARD option is set. +Information about the failure is returned as for PCRE_ERROR_BADUTF8. It is in +fact sufficient to detect this case, but this special error code for +PCRE_PARTIAL_HARD precedes the implementation of returned information; it is +retained for backwards compatibility. +
+ PCRE_ERROR_RECURSELOOP (-26) ++This error is returned when pcre_exec() detects a recursion loop within +the pattern. Specifically, it means that either the whole pattern or a +subpattern has been called recursively for the second time at the same position +in the subject string. Some simple patterns that might do this are detected and +faulted at compile time, but more complicated cases, in particular mutual +recursions between two different subpatterns, cannot be detected until run +time. +
+ PCRE_ERROR_JIT_STACKLIMIT (-27) ++This error is returned when a pattern that was successfully studied using a +JIT compile option is being matched, but the memory available for the +just-in-time processing stack is not large enough. See the +pcrejit +documentation for more details. +
+ PCRE_ERROR_BADMODE (-28) ++This error is given if a pattern that was compiled by the 8-bit library is +passed to a 16-bit or 32-bit library function, or vice versa. +
+ PCRE_ERROR_BADENDIANNESS (-29) ++This error is given if a pattern that was compiled and saved is reloaded on a +host with different endianness. The utility function +pcre_pattern_to_host_byte_order() can be used to convert such a pattern +so that it runs on the new host. +
+ PCRE_ERROR_JIT_BADOPTION ++This error is returned when a pattern that was successfully studied using a JIT +compile option is being matched, but the matching mode (partial or complete +match) does not correspond to any JIT compilation mode. When the JIT fast path +function is used, this error may be also given for invalid options. See the +pcrejit +documentation for more details. +
+ PCRE_ERROR_BADLENGTH (-32) ++This error is given if pcre_exec() is called with a negative value for +the length argument. + +
+Error numbers -16 to -20, -22, and 30 are not used by pcre_exec(). +
++This section applies only to the 8-bit library. The corresponding information +for the 16-bit and 32-bit libraries is given in the +pcre16 +and +pcre32 +pages. +
++When pcre_exec() returns either PCRE_ERROR_BADUTF8 or +PCRE_ERROR_SHORTUTF8, and the size of the output vector (ovecsize) is at +least 2, the offset of the start of the invalid UTF-8 character is placed in +the first output vector element (ovector[0]) and a reason code is placed +in the second element (ovector[1]). The reason codes are given names in +the pcre.h header file: +
+ PCRE_UTF8_ERR1 + PCRE_UTF8_ERR2 + PCRE_UTF8_ERR3 + PCRE_UTF8_ERR4 + PCRE_UTF8_ERR5 ++The string ends with a truncated UTF-8 character; the code specifies how many +bytes are missing (1 to 5). Although RFC 3629 restricts UTF-8 characters to be +no longer than 4 bytes, the encoding scheme (originally defined by RFC 2279) +allows for up to 6 bytes, and this is checked first; hence the possibility of +4 or 5 missing bytes. +
+ PCRE_UTF8_ERR6 + PCRE_UTF8_ERR7 + PCRE_UTF8_ERR8 + PCRE_UTF8_ERR9 + PCRE_UTF8_ERR10 ++The two most significant bits of the 2nd, 3rd, 4th, 5th, or 6th byte of the +character do not have the binary value 0b10 (that is, either the most +significant bit is 0, or the next bit is 1). +
+ PCRE_UTF8_ERR11 + PCRE_UTF8_ERR12 ++A character that is valid by the RFC 2279 rules is either 5 or 6 bytes long; +these code points are excluded by RFC 3629. +
+ PCRE_UTF8_ERR13 ++A 4-byte character has a value greater than 0x10fff; these code points are +excluded by RFC 3629. +
+ PCRE_UTF8_ERR14 ++A 3-byte character has a value in the range 0xd800 to 0xdfff; this range of +code points are reserved by RFC 3629 for use with UTF-16, and so are excluded +from UTF-8. +
+ PCRE_UTF8_ERR15 + PCRE_UTF8_ERR16 + PCRE_UTF8_ERR17 + PCRE_UTF8_ERR18 + PCRE_UTF8_ERR19 ++A 2-, 3-, 4-, 5-, or 6-byte character is "overlong", that is, it codes for a +value that can be represented by fewer bytes, which is invalid. For example, +the two bytes 0xc0, 0xae give the value 0x2e, whose correct coding uses just +one byte. +
+ PCRE_UTF8_ERR20 ++The two most significant bits of the first byte of a character have the binary +value 0b10 (that is, the most significant bit is 1 and the second is 0). Such a +byte can only validly occur as the second or subsequent byte of a multi-byte +character. +
+ PCRE_UTF8_ERR21 ++The first byte of a character has the value 0xfe or 0xff. These values can +never occur in a valid UTF-8 string. +
+ PCRE_UTF8_ERR2 ++Non-character. These are the last two characters in each plane (0xfffe, 0xffff, +0x1fffe, 0x1ffff .. 0x10fffe, 0x10ffff), and the characters 0xfdd0..0xfdef. + +
+int pcre_copy_substring(const char *subject, int *ovector, +int stringcount, int stringnumber, char *buffer, +int buffersize); +
++int pcre_get_substring(const char *subject, int *ovector, +int stringcount, int stringnumber, +const char **stringptr); +
++int pcre_get_substring_list(const char *subject, +int *ovector, int stringcount, const char ***listptr); +
++Captured substrings can be accessed directly by using the offsets returned by +pcre_exec() in ovector. For convenience, the functions +pcre_copy_substring(), pcre_get_substring(), and +pcre_get_substring_list() are provided for extracting captured substrings +as new, separate, zero-terminated strings. These functions identify substrings +by number. The next section describes functions for extracting named +substrings. +
++A substring that contains a binary zero is correctly extracted and has a +further zero added on the end, but the result is not, of course, a C string. +However, you can process such a string by referring to the length that is +returned by pcre_copy_substring() and pcre_get_substring(). +Unfortunately, the interface to pcre_get_substring_list() is not adequate +for handling strings containing binary zeros, because the end of the final +string is not independently indicated. +
++The first three arguments are the same for all three of these functions: +subject is the subject string that has just been successfully matched, +ovector is a pointer to the vector of integer offsets that was passed to +pcre_exec(), and stringcount is the number of substrings that were +captured by the match, including the substring that matched the entire regular +expression. This is the value returned by pcre_exec() if it is greater +than zero. If pcre_exec() returned zero, indicating that it ran out of +space in ovector, the value passed as stringcount should be the +number of elements in the vector divided by three. +
++The functions pcre_copy_substring() and pcre_get_substring() +extract a single substring, whose number is given as stringnumber. A +value of zero extracts the substring that matched the entire pattern, whereas +higher values extract the captured substrings. For pcre_copy_substring(), +the string is placed in buffer, whose length is given by +buffersize, while for pcre_get_substring() a new block of memory is +obtained via pcre_malloc, and its address is returned via +stringptr. The yield of the function is the length of the string, not +including the terminating zero, or one of these error codes: +
+ PCRE_ERROR_NOMEMORY (-6) ++The buffer was too small for pcre_copy_substring(), or the attempt to get +memory failed for pcre_get_substring(). +
+ PCRE_ERROR_NOSUBSTRING (-7) ++There is no substring whose number is stringnumber. + +
+The pcre_get_substring_list() function extracts all available substrings +and builds a list of pointers to them. All this is done in a single block of +memory that is obtained via pcre_malloc. The address of the memory block +is returned via listptr, which is also the start of the list of string +pointers. The end of the list is marked by a NULL pointer. The yield of the +function is zero if all went well, or the error code +
+ PCRE_ERROR_NOMEMORY (-6) ++if the attempt to get the memory block failed. + +
+When any of these functions encounter a substring that is unset, which can +happen when capturing subpattern number n+1 matches some part of the +subject, but subpattern n has not been used at all, they return an empty +string. This can be distinguished from a genuine zero-length substring by +inspecting the appropriate offset in ovector, which is negative for unset +substrings. +
++The two convenience functions pcre_free_substring() and +pcre_free_substring_list() can be used to free the memory returned by +a previous call of pcre_get_substring() or +pcre_get_substring_list(), respectively. They do nothing more than call +the function pointed to by pcre_free, which of course could be called +directly from a C program. However, PCRE is used in some situations where it is +linked via a special interface to another programming language that cannot use +pcre_free directly; it is for these cases that the functions are +provided. +
++int pcre_get_stringnumber(const pcre *code, +const char *name); +
++int pcre_copy_named_substring(const pcre *code, +const char *subject, int *ovector, +int stringcount, const char *stringname, +char *buffer, int buffersize); +
++int pcre_get_named_substring(const pcre *code, +const char *subject, int *ovector, +int stringcount, const char *stringname, +const char **stringptr); +
++To extract a substring by name, you first have to find associated number. +For example, for this pattern +
+ (a+)b(?<xxx>\d+)... ++the number of the subpattern called "xxx" is 2. If the name is known to be +unique (PCRE_DUPNAMES was not set), you can find the number from the name by +calling pcre_get_stringnumber(). The first argument is the compiled +pattern, and the second is the name. The yield of the function is the +subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no subpattern of +that name. + +
+Given the number, you can extract the substring directly, or use one of the +functions described in the previous section. For convenience, there are also +two functions that do the whole job. +
++Most of the arguments of pcre_copy_named_substring() and +pcre_get_named_substring() are the same as those for the similarly named +functions that extract by number. As these are described in the previous +section, they are not re-described here. There are just two differences: +
++First, instead of a substring number, a substring name is given. Second, there +is an extra argument, given at the start, which is a pointer to the compiled +pattern. This is needed in order to gain access to the name-to-number +translation table. +
++These functions call pcre_get_stringnumber(), and if it succeeds, they +then call pcre_copy_substring() or pcre_get_substring(), as +appropriate. NOTE: If PCRE_DUPNAMES is set and there are duplicate names, +the behaviour may not be what you want (see the next section). +
++Warning: If the pattern uses the (?| feature to set up multiple +subpatterns with the same number, as described in the +section on duplicate subpattern numbers +in the +pcrepattern +page, you cannot use names to distinguish the different subpatterns, because +names are not included in the compiled code. The matching process uses only +numbers. For this reason, the use of different names for subpatterns of the +same number causes an error at compile time. +
++int pcre_get_stringtable_entries(const pcre *code, +const char *name, char **first, char **last); +
++When a pattern is compiled with the PCRE_DUPNAMES option, names for subpatterns +are not required to be unique. (Duplicate names are always allowed for +subpatterns with the same number, created by using the (?| feature. Indeed, if +such subpatterns are named, they are required to use the same names.) +
++Normally, patterns with duplicate names are such that in any one match, only +one of the named subpatterns participates. An example is shown in the +pcrepattern +documentation. +
++When duplicates are present, pcre_copy_named_substring() and +pcre_get_named_substring() return the first substring corresponding to +the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING (-7) is +returned; no data is returned. The pcre_get_stringnumber() function +returns one of the numbers that are associated with the name, but it is not +defined which it is. +
++If you want to get full details of all captured substrings for a given name, +you must use the pcre_get_stringtable_entries() function. The first +argument is the compiled pattern, and the second is the name. The third and +fourth are pointers to variables which are updated by the function. After it +has run, they point to the first and last entries in the name-to-number table +for the given name. The function itself returns the length of each entry, or +PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is +described above in the section entitled Information about a pattern +above. +Given all the relevant entries for the name, you can extract each of their +numbers, and hence the captured data, if any. +
++The traditional matching function uses a similar algorithm to Perl, which stops +when it finds the first match, starting at a given point in the subject. If you +want to find all possible matches, or the longest possible match, consider +using the alternative matching function (see below) instead. If you cannot use +the alternative function, but still need to find all possible matches, you +can kludge it up by making use of the callout facility, which is described in +the +pcrecallout +documentation. +
++What you have to do is to insert a callout right at the end of the pattern. +When your callout function is called, extract and save the current matched +substring. Then return 1, which forces pcre_exec() to backtrack and try +other alternatives. Ultimately, when it runs out of matches, pcre_exec() +will yield PCRE_ERROR_NOMATCH. +
++Matching certain patterns using pcre_exec() can use a lot of process +stack, which in certain environments can be rather limited in size. Some users +find it helpful to have an estimate of the amount of stack that is used by +pcre_exec(), to help them set recursion limits, as described in the +pcrestack +documentation. The estimate that is output by pcretest when called with +the -m and -C options is obtained by calling pcre_exec with +the values NULL, NULL, NULL, -999, and -999 for its first five arguments. +
++Normally, if its first argument is NULL, pcre_exec() immediately returns +the negative error code PCRE_ERROR_NULL, but with this special combination of +arguments, it returns instead a negative number whose absolute value is the +approximate stack frame size in bytes. (A negative number is used so that it is +clear that no match has happened.) The value is approximate because in some +cases, recursive calls to pcre_exec() occur when there are one or two +additional variables on the stack. +
++If PCRE has been compiled to use the heap instead of the stack for recursion, +the value returned is the size of each block that is obtained from the heap. +
++int pcre_dfa_exec(const pcre *code, const pcre_extra *extra, +const char *subject, int length, int startoffset, +int options, int *ovector, int ovecsize, +int *workspace, int wscount); +
++The function pcre_dfa_exec() is called to match a subject string against +a compiled pattern, using a matching algorithm that scans the subject string +just once, and does not backtrack. This has different characteristics to the +normal algorithm, and is not compatible with Perl. Some of the features of PCRE +patterns are not supported. Nevertheless, there are times when this kind of +matching can be useful. For a discussion of the two matching algorithms, and a +list of features that pcre_dfa_exec() does not support, see the +pcrematching +documentation. +
++The arguments for the pcre_dfa_exec() function are the same as for +pcre_exec(), plus two extras. The ovector argument is used in a +different way, and this is described below. The other common arguments are used +in the same way as for pcre_exec(), so their description is not repeated +here. +
++The two additional arguments provide workspace for the function. The workspace +vector should contain at least 20 elements. It is used for keeping track of +multiple paths through the pattern tree. More workspace will be needed for +patterns and subjects where there are a lot of potential matches. +
++Here is an example of a simple call to pcre_dfa_exec(): +
+ int rc; + int ovector[10]; + int wspace[20]; + rc = pcre_dfa_exec( + re, /* result of pcre_compile() */ + NULL, /* we didn't study the pattern */ + "some string", /* the subject string */ + 11, /* the length of the subject string */ + 0, /* start at offset 0 in the subject */ + 0, /* default options */ + ovector, /* vector of integers for substring information */ + 10, /* number of elements (NOT size in bytes) */ + wspace, /* working space vector */ + 20); /* number of elements (NOT size in bytes) */ ++ +
+The unused bits of the options argument for pcre_dfa_exec() must be +zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_xxx, +PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART, +PCRE_NO_UTF8_CHECK, PCRE_BSR_ANYCRLF, PCRE_BSR_UNICODE, PCRE_NO_START_OPTIMIZE, +PCRE_PARTIAL_HARD, PCRE_PARTIAL_SOFT, PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. +All but the last four of these are exactly the same as for pcre_exec(), +so their description is not repeated here. +
+ PCRE_PARTIAL_HARD + PCRE_PARTIAL_SOFT ++These have the same general effect as they do for pcre_exec(), but the +details are slightly different. When PCRE_PARTIAL_HARD is set for +pcre_dfa_exec(), it returns PCRE_ERROR_PARTIAL if the end of the subject +is reached and there is still at least one matching possibility that requires +additional characters. This happens even if some complete matches have also +been found. When PCRE_PARTIAL_SOFT is set, the return code PCRE_ERROR_NOMATCH +is converted into PCRE_ERROR_PARTIAL if the end of the subject is reached, +there have been no complete matches, but there is still at least one matching +possibility. The portion of the string that was inspected when the longest +partial match was found is set as the first matching string in both cases. +There is a more detailed discussion of partial and multi-segment matching, with +examples, in the +pcrepartial +documentation. +
+ PCRE_DFA_SHORTEST ++Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to stop as +soon as it has found one match. Because of the way the alternative algorithm +works, this is necessarily the shortest possible match at the first possible +matching point in the subject string. +
+ PCRE_DFA_RESTART ++When pcre_dfa_exec() returns a partial match, it is possible to call it +again, with additional subject characters, and have it continue with the same +match. The PCRE_DFA_RESTART option requests this action; when it is set, the +workspace and wscount options must reference the same vector as +before because data about the match so far is left in them after a partial +match. There is more discussion of this facility in the +pcrepartial +documentation. + +
+When pcre_dfa_exec() succeeds, it may have matched more than one +substring in the subject. Note, however, that all the matches from one run of +the function start at the same point in the subject. The shorter matches are +all initial substrings of the longer matches. For example, if the pattern +
+ <.*> ++is matched against the string +
+ This is <something> <something else> <something further> no more ++the three matched strings are +
+ <something> + <something> <something else> + <something> <something else> <something further> ++On success, the yield of the function is a number greater than zero, which is +the number of matched substrings. The substrings themselves are returned in +ovector. Each string uses two elements; the first is the offset to the +start, and the second is the offset to the end. In fact, all the strings have +the same start offset. (Space could have been saved by giving this only once, +but it was decided to retain some compatibility with the way pcre_exec() +returns data, even though the meaning of the strings is different.) + +
+The strings are returned in reverse order of length; that is, the longest +matching string is given first. If there were too many matches to fit into +ovector, the yield of the function is zero, and the vector is filled with +the longest matches. Unlike pcre_exec(), pcre_dfa_exec() can use +the entire ovector for returning matched strings. +
++The pcre_dfa_exec() function returns a negative number when it fails. +Many of the errors are the same as for pcre_exec(), and these are +described +above. +There are in addition the following errors that are specific to +pcre_dfa_exec(): +
+ PCRE_ERROR_DFA_UITEM (-16) ++This return is given if pcre_dfa_exec() encounters an item in the pattern +that it does not support, for instance, the use of \C or a back reference. +
+ PCRE_ERROR_DFA_UCOND (-17) ++This return is given if pcre_dfa_exec() encounters a condition item that +uses a back reference for the condition, or a test for recursion in a specific +group. These are not supported. +
+ PCRE_ERROR_DFA_UMLIMIT (-18) ++This return is given if pcre_dfa_exec() is called with an extra +block that contains a setting of the match_limit or +match_limit_recursion fields. This is not supported (these fields are +meaningless for DFA matching). +
+ PCRE_ERROR_DFA_WSSIZE (-19) ++This return is given if pcre_dfa_exec() runs out of space in the +workspace vector. +
+ PCRE_ERROR_DFA_RECURSE (-20) ++When a recursive subpattern is processed, the matching function calls itself +recursively, using private vectors for ovector and workspace. This +error is given if the output vector is not large enough. This should be +extremely rare, as a vector of size 1000 is used. +
+ PCRE_ERROR_DFA_BADRESTART (-30) ++When pcre_dfa_exec() is called with the PCRE_DFA_RESTART option, +some plausibility checks are made on the contents of the workspace, which +should contain data about the previous partial match. If any of these checks +fail, this error is given. + +
+pcre16(3), pcre32(3), pcrebuild(3), pcrecallout(3), +pcrecpp(3)(3), pcrematching(3), pcrepartial(3), +pcreposix(3), pcreprecompile(3), pcresample(3), +pcrestack(3). +
+
+Philip Hazel
+
+University Computing Service
+
+Cambridge CB2 3QH, England.
+
+
+Last updated: 08 November 2012
+
+Copyright © 1997-2012 University of Cambridge.
+
+
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcrebuild.html b/tools/pcre/doc/html/pcrebuild.html new file mode 100644 index 00000000..6eb169b3 --- /dev/null +++ b/tools/pcre/doc/html/pcrebuild.html @@ -0,0 +1,517 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+This document describes the optional features of PCRE that can be selected when +the library is compiled. It assumes use of the configure script, where +the optional features are selected or deselected by providing options to +configure before running the make command. However, the same +options can be selected in both Unix-like and non-Unix-like environments using +the GUI facility of cmake-gui if you are using CMake instead of +configure to build PCRE. +
++There is a lot more information about building PCRE without using +configure (including information about using CMake or building "by +hand") in the file called NON-AUTOTOOLS-BUILD, which is part of the PCRE +distribution. You should consult this file as well as the README file if +you are building in a non-Unix-like environment. +
++The complete list of options for configure (which includes the standard +ones such as the selection of the installation directory) can be obtained by +running +
+ ./configure --help ++The following sections include descriptions of options whose names begin with +--enable or --disable. These settings specify changes to the defaults for the +configure command. Because of the way that configure works, +--enable and --disable always come in pairs, so the complementary option always +exists as well, but as it specifies the default, it is not described. + +
+By default, a library called libpcre is built, containing functions that +take string arguments contained in vectors of bytes, either as single-byte +characters, or interpreted as UTF-8 strings. You can also build a separate +library, called libpcre16, in which strings are contained in vectors of +16-bit data units and interpreted either as single-unit characters or UTF-16 +strings, by adding +
+ --enable-pcre16 ++to the configure command. You can also build a separate +library, called libpcre32, in which strings are contained in vectors of +32-bit data units and interpreted either as single-unit characters or UTF-32 +strings, by adding +
+ --enable-pcre32 ++to the configure command. If you do not want the 8-bit library, add +
+ --disable-pcre8 ++as well. At least one of the three libraries must be built. Note that the C++ +and POSIX wrappers are for the 8-bit library only, and that pcregrep is +an 8-bit program. None of these are built if you select only the 16-bit or +32-bit libraries. + +
+The PCRE building process uses libtool to build both shared and static +Unix libraries by default. You can suppress one of these by adding one of +
+ --disable-shared + --disable-static ++to the configure command, as required. + +
+By default, if the 8-bit library is being built, the configure script +will search for a C++ compiler and C++ header files. If it finds them, it +automatically builds the C++ wrapper library (which supports only 8-bit +strings). You can disable this by adding +
+ --disable-cpp ++to the configure command. + +
+To build PCRE with support for UTF Unicode character strings, add +
+ --enable-utf ++to the configure command. This setting applies to all three libraries, +adding support for UTF-8 to the 8-bit library, support for UTF-16 to the 16-bit +library, and support for UTF-32 to the to the 32-bit library. There are no +separate options for enabling UTF-8, UTF-16 and UTF-32 independently because +that would allow ridiculous settings such as requesting UTF-16 support while +building only the 8-bit library. It is not possible to build one library with +UTF support and another without in the same configuration. (For backwards +compatibility, --enable-utf8 is a synonym of --enable-utf.) + +
+Of itself, this setting does not make PCRE treat strings as UTF-8, UTF-16 or +UTF-32. As well as compiling PCRE with this option, you also have have to set +the PCRE_UTF8, PCRE_UTF16 or PCRE_UTF32 option (as appropriate) when you call +one of the pattern compiling functions. +
++If you set --enable-utf when compiling in an EBCDIC environment, PCRE expects +its input to be either ASCII or UTF-8 (depending on the run-time option). It is +not possible to support both EBCDIC and UTF-8 codes in the same version of the +library. Consequently, --enable-utf and --enable-ebcdic are mutually +exclusive. +
++UTF support allows the libraries to process character codepoints up to 0x10ffff +in the strings that they handle. On its own, however, it does not provide any +facilities for accessing the properties of such characters. If you want to be +able to use the pattern escapes \P, \p, and \X, which refer to Unicode +character properties, you must add +
+ --enable-unicode-properties ++to the configure command. This implies UTF support, even if you have +not explicitly requested it. + +
+Including Unicode property support adds around 30K of tables to the PCRE +library. Only the general category properties such as Lu and Nd are +supported. Details are given in the +pcrepattern +documentation. +
++Just-in-time compiler support is included in the build by specifying +
+ --enable-jit ++This support is available only for certain hardware architectures. If this +option is set for an unsupported architecture, a compile time error occurs. +See the +pcrejit +documentation for a discussion of JIT usage. When JIT support is enabled, +pcregrep automatically makes use of it, unless you add +
+ --disable-pcregrep-jit ++to the "configure" command. + +
+By default, PCRE interprets the linefeed (LF) character as indicating the end +of a line. This is the normal newline character on Unix-like systems. You can +compile PCRE to use carriage return (CR) instead, by adding +
+ --enable-newline-is-cr ++to the configure command. There is also a --enable-newline-is-lf option, +which explicitly specifies linefeed as the newline character. +
+ --enable-newline-is-crlf ++to the configure command. There is a fourth option, specified by +
+ --enable-newline-is-anycrlf ++which causes PCRE to recognize any of the three sequences CR, LF, or CRLF as +indicating a line ending. Finally, a fifth option, specified by +
+ --enable-newline-is-any ++causes PCRE to recognize any Unicode newline sequence. + +
+Whatever line ending convention is selected when PCRE is built can be +overridden when the library functions are called. At build time it is +conventional to use the standard for your operating system. +
++By default, the sequence \R in a pattern matches any Unicode newline sequence, +whatever has been selected as the line ending sequence. If you specify +
+ --enable-bsr-anycrlf ++the default is changed so that \R matches only CR, LF, or CRLF. Whatever is +selected when PCRE is built can be overridden when the library functions are +called. + +
+When the 8-bit library is called through the POSIX interface (see the +pcreposix +documentation), additional working storage is required for holding the pointers +to capturing substrings, because PCRE requires three integers per substring, +whereas the POSIX interface provides only two. If the number of expected +substrings is small, the wrapper function uses space on the stack, because this +is faster than using malloc() for each call. The default threshold above +which the stack is no longer used is 10; it can be changed by adding a setting +such as +
+ --with-posix-malloc-threshold=20 ++to the configure command. + +
+Within a compiled pattern, offset values are used to point from one part to +another (for example, from an opening parenthesis to an alternation +metacharacter). By default, in the 8-bit and 16-bit libraries, two-byte values +are used for these offsets, leading to a maximum size for a compiled pattern of +around 64K. This is sufficient to handle all but the most gigantic patterns. +Nevertheless, some people do want to process truly enormous patterns, so it is +possible to compile PCRE to use three-byte or four-byte offsets by adding a +setting such as +
+ --with-link-size=3 ++to the configure command. The value given must be 2, 3, or 4. For the +16-bit library, a value of 3 is rounded up to 4. In these libraries, using +longer offsets slows down the operation of PCRE because it has to load +additional data when handling them. For the 32-bit library the value is always +4 and cannot be overridden; the value of --with-link-size is ignored. + +
+When matching with the pcre_exec() function, PCRE implements backtracking +by making recursive calls to an internal function called match(). In +environments where the size of the stack is limited, this can severely limit +PCRE's operation. (The Unix environment does not usually suffer from this +problem, but it may sometimes be necessary to increase the maximum stack size. +There is a discussion in the +pcrestack +documentation.) An alternative approach to recursion that uses memory from the +heap to remember data, instead of using recursive function calls, has been +implemented to work round the problem of limited stack size. If you want to +build a version of PCRE that works this way, add +
+ --disable-stack-for-recursion ++to the configure command. With this configuration, PCRE will use the +pcre_stack_malloc and pcre_stack_free variables to call memory +management functions. By default these point to malloc() and +free(), but you can replace the pointers so that your own functions are +used instead. + +
+Separate functions are provided rather than using pcre_malloc and +pcre_free because the usage is very predictable: the block sizes +requested are always the same, and the blocks are always freed in reverse +order. A calling program might be able to implement optimized functions that +perform better than malloc() and free(). PCRE runs noticeably more +slowly when built in this way. This option affects only the pcre_exec() +function; it is not relevant for pcre_dfa_exec(). +
++Internally, PCRE has a function called match(), which it calls repeatedly +(sometimes recursively) when matching a pattern with the pcre_exec() +function. By controlling the maximum number of times this function may be +called during a single matching operation, a limit can be placed on the +resources used by a single call to pcre_exec(). The limit can be changed +at run time, as described in the +pcreapi +documentation. The default is 10 million, but this can be changed by adding a +setting such as +
+ --with-match-limit=500000 ++to the configure command. This setting has no effect on the +pcre_dfa_exec() matching function. + +
+In some environments it is desirable to limit the depth of recursive calls of +match() more strictly than the total number of calls, in order to +restrict the maximum amount of stack (or heap, if --disable-stack-for-recursion +is specified) that is used. A second limit controls this; it defaults to the +value that is set for --with-match-limit, which imposes no additional +constraints. However, you can set a lower limit by adding, for example, +
+ --with-match-limit-recursion=10000 ++to the configure command. This value can also be overridden at run time. + +
+PCRE uses fixed tables for processing characters whose code values are less +than 256. By default, PCRE is built with a set of tables that are distributed +in the file pcre_chartables.c.dist. These tables are for ASCII codes +only. If you add +
+ --enable-rebuild-chartables ++to the configure command, the distributed tables are no longer used. +Instead, a program called dftables is compiled and run. This outputs the +source for new set of tables, created in the default locale of your C run-time +system. (This method of replacing the tables does not work if you are cross +compiling, because dftables is run on the local host. If you need to +create alternative tables when cross compiling, you will have to do so "by +hand".) + +
+PCRE assumes by default that it will run in an environment where the character +code is ASCII (or Unicode, which is a superset of ASCII). This is the case for +most computer operating systems. PCRE can, however, be compiled to run in an +EBCDIC environment by adding +
+ --enable-ebcdic ++to the configure command. This setting implies +--enable-rebuild-chartables. You should only use it if you know that you are in +an EBCDIC environment (for example, an IBM mainframe operating system). The +--enable-ebcdic option is incompatible with --enable-utf. + +
+The EBCDIC character that corresponds to an ASCII LF is assumed to have the +value 0x15 by default. However, in some EBCDIC environments, 0x25 is used. In +such an environment you should use +
+ --enable-ebcdic-nl25 ++as well as, or instead of, --enable-ebcdic. The EBCDIC character for CR has the +same value as in ASCII, namely, 0x0d. Whichever of 0x15 and 0x25 is not +chosen as LF is made to correspond to the Unicode NEL character (which, in +Unicode, is 0x85). + +
+The options that select newline behaviour, such as --enable-newline-is-cr, +and equivalent run-time options, refer to these character values in an EBCDIC +environment. +
++By default, pcregrep reads all files as plain text. You can build it so +that it recognizes files whose names end in .gz or .bz2, and reads +them with libz or libbz2, respectively, by adding one or both of +
+ --enable-pcregrep-libz + --enable-pcregrep-libbz2 ++to the configure command. These options naturally require that the +relevant libraries are installed on your system. Configuration will fail if +they are not. + +
+pcregrep uses an internal buffer to hold a "window" on the file it is +scanning, in order to be able to output "before" and "after" lines when it +finds a match. The size of the buffer is controlled by a parameter whose +default value is 20K. The buffer itself is three times this size, but because +of the way it is used for holding "before" lines, the longest line that is +guaranteed to be processable is the parameter size. You can change the default +parameter value by adding, for example, +
+ --with-pcregrep-bufsize=50K ++to the configure command. The caller of \fPpcregrep\fP can, however, +override this value by specifying a run-time option. + +
+If you add +
+ --enable-pcretest-libreadline ++to the configure command, pcretest is linked with the +libreadline library, and when its input is from a terminal, it reads it +using the readline() function. This provides line-editing and history +facilities. Note that libreadline is GPL-licensed, so if you distribute a +binary of pcretest linked in this way, there may be licensing issues. + +
+Setting this option causes the -lreadline option to be added to the +pcretest build. In many operating environments with a sytem-installed +libreadline this is sufficient. However, in some environments (e.g. +if an unmodified distribution version of readline is in use), some extra +configuration may be necessary. The INSTALL file for libreadline says +this: +
+ "Readline uses the termcap functions, but does not link with the + termcap or curses library itself, allowing applications which link + with readline the to choose an appropriate library." ++If your environment has not been set up so that an appropriate library is +automatically included, you may need to add something like +
+ LIBS="-ncurses" ++immediately before the configure command. + +
+By adding the +
+ --enable-valgrind ++option to to the configure command, PCRE will use valgrind annotations +to mark certain memory regions as unaddressable. This allows it to detect +invalid memory accesses, and is mostly useful for debugging PCRE itself. + +
+If your C compiler is gcc, you can build a version of PCRE that can generate a +code coverage report for its test suite. To enable this, you must install +lcov version 1.6 or above. Then specify +
+ --enable-coverage ++to the configure command and build PCRE in the usual way. + +
+Note that using ccache (a caching C compiler) is incompatible with code +coverage reporting. If you have configured ccache to run automatically +on your system, you must set the environment variable +
+ CCACHE_DISABLE=1 ++before running make to build PCRE, so that ccache is not used. + +
+When --enable-coverage is used, the following addition targets are added to the +Makefile: +
+ make coverage ++This creates a fresh coverage report for the PCRE test suite. It is equivalent +to running "make coverage-reset", "make coverage-baseline", "make check", and +then "make coverage-report". +
+ make coverage-reset ++This zeroes the coverage counters, but does nothing else. +
+ make coverage-baseline ++This captures baseline coverage information. +
+ make coverage-report ++This creates the coverage report. +
+ make coverage-clean-report ++This removes the generated coverage report without cleaning the coverage data +itself. +
+ make coverage-clean-data ++This removes the captured coverage data without removing the coverage files +created at compile time (*.gcno). +
+ make coverage-clean ++This cleans all coverage data including the generated coverage report. For more +information about code coverage, see the gcov and lcov +documentation. + +
+pcreapi(3), pcre16, pcre32, pcre_config(3). +
+
+Philip Hazel
+
+University Computing Service
+
+Cambridge CB2 3QH, England.
+
+
+Last updated: 30 October 2012
+
+Copyright © 1997-2012 University of Cambridge.
+
+
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcrecallout.html b/tools/pcre/doc/html/pcrecallout.html new file mode 100644 index 00000000..b28e347f --- /dev/null +++ b/tools/pcre/doc/html/pcrecallout.html @@ -0,0 +1,243 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+#include <pcre.h> +
++int (*pcre_callout)(pcre_callout_block *); +
++int (*pcre16_callout)(pcre16_callout_block *); +
++int (*pcre32_callout)(pcre32_callout_block *); +
++PCRE provides a feature called "callout", which is a means of temporarily +passing control to the caller of PCRE in the middle of pattern matching. The +caller of PCRE provides an external function by putting its entry point in the +global variable pcre_callout (pcre16_callout for the 16-bit +library, pcre32_callout for the 32-bit library). By default, this +variable contains NULL, which disables all calling out. +
++Within a regular expression, (?C) indicates the points at which the external +function is to be called. Different callout points can be identified by putting +a number less than 256 after the letter C. The default value is zero. +For example, this pattern has two callout points: +
+ (?C1)abc(?C2)def ++If the PCRE_AUTO_CALLOUT option bit is set when a pattern is compiled, PCRE +automatically inserts callouts, all with number 255, before each item in the +pattern. For example, if PCRE_AUTO_CALLOUT is used with the pattern +
+ A(\d{2}|--)
+
+it is processed as if it were
++The use of callouts in a pattern makes it ineligible for optimization by the +just-in-time compiler. Studying such a pattern with the PCRE_STUDY_JIT_COMPILE +option always fails. +
++You should be aware that, because of optimizations in the way PCRE matches +patterns by default, callouts sometimes do not happen. For example, if the +pattern is +
+ ab(?C4)cd ++PCRE knows that any matching string must contain the letter "d". If the subject +string is "abyz", the lack of "d" means that matching doesn't ever start, and +the callout is never reached. However, with "abyd", though the result is still +no match, the callout is obeyed. + +
+If the pattern is studied, PCRE knows the minimum length of a matching string, +and will immediately give a "no match" return without actually running a match +if the subject is not long enough, or, for unanchored patterns, if it has +been scanned far enough. +
++You can disable these optimizations by passing the PCRE_NO_START_OPTIMIZE +option to the matching function, or by starting the pattern with +(*NO_START_OPT). This slows down the matching process, but does ensure that +callouts such as the example above are obeyed. +
++During matching, when PCRE reaches a callout point, the external function +defined by pcre_callout or pcre[16|32]_callout is called +(if it is set). This applies to both normal and DFA matching. The only +argument to the callout function is a pointer to a pcre_callout +or pcre[16|32]_callout block. +These structures contains the following fields: +
+ int version; + int callout_number; + int *offset_vector; + const char *subject; (8-bit version) + PCRE_SPTR16 subject; (16-bit version) + PCRE_SPTR32 subject; (32-bit version) + int subject_length; + int start_match; + int current_position; + int capture_top; + int capture_last; + void *callout_data; + int pattern_position; + int next_item_length; + const unsigned char *mark; (8-bit version) + const PCRE_UCHAR16 *mark; (16-bit version) + const PCRE_UCHAR32 *mark; (32-bit version) ++The version field is an integer containing the version number of the +block format. The initial version was 0; the current version is 2. The version +number will change again in future if additional fields are added, but the +intention is never to remove any of the existing fields. + +
+The callout_number field contains the number of the callout, as compiled +into the pattern (that is, the number after ?C for manual callouts, and 255 for +automatically generated callouts). +
++The offset_vector field is a pointer to the vector of offsets that was +passed by the caller to the matching function. When pcre_exec() or +pcre[16|32]_exec() is used, the contents can be inspected, in order to extract +substrings that have been matched so far, in the same way as for extracting +substrings after a match has completed. For the DFA matching functions, this +field is not useful. +
++The subject and subject_length fields contain copies of the values +that were passed to the matching function. +
++The start_match field normally contains the offset within the subject at +which the current match attempt started. However, if the escape sequence \K +has been encountered, this value is changed to reflect the modified starting +point. If the pattern is not anchored, the callout function may be called +several times from the same point in the pattern for different starting points +in the subject. +
++The current_position field contains the offset within the subject of the +current match pointer. +
++When the pcre_exec() or pcre[16|32]_exec() is used, the +capture_top field contains one more than the number of the highest +numbered captured substring so far. If no substrings have been captured, the +value of capture_top is one. This is always the case when the DFA +functions are used, because they do not support captured substrings. +
++The capture_last field contains the number of the most recently captured +substring. If no substrings have been captured, its value is -1. This is always +the case for the DFA matching functions. +
++The callout_data field contains a value that is passed to a matching +function specifically so that it can be passed back in callouts. It is passed +in the callout_data field of a pcre_extra or pcre[16|32]_extra +data structure. If no such data was passed, the value of callout_data in +a callout block is NULL. There is a description of the pcre_extra +structure in the +pcreapi +documentation. +
++The pattern_position field is present from version 1 of the callout +structure. It contains the offset to the next item to be matched in the pattern +string. +
++The next_item_length field is present from version 1 of the callout +structure. It contains the length of the next item to be matched in the pattern +string. When the callout immediately precedes an alternation bar, a closing +parenthesis, or the end of the pattern, the length is zero. When the callout +precedes an opening parenthesis, the length is that of the entire subpattern. +
++The pattern_position and next_item_length fields are intended to +help in distinguishing between different automatic callouts, which all have the +same callout number. However, they are set for all callouts. +
++The mark field is present from version 2 of the callout structure. In +callouts from pcre_exec() or pcre[16|32]_exec() it contains a pointer to +the zero-terminated name of the most recently passed (*MARK), (*PRUNE), or +(*THEN) item in the match, or NULL if no such items have been passed. Instances +of (*PRUNE) or (*THEN) without a name do not obliterate a previous (*MARK). In +callouts from the DFA matching functions this field always contains NULL. +
++The external callout function returns an integer to PCRE. If the value is zero, +matching proceeds as normal. If the value is greater than zero, matching fails +at the current point, but the testing of other matching possibilities goes +ahead, just as if a lookahead assertion had failed. If the value is less than +zero, the match is abandoned, the matching function returns the negative value. +
++Negative values should normally be chosen from the set of PCRE_ERROR_xxx +values. In particular, PCRE_ERROR_NOMATCH forces a standard "no match" failure. +The error number PCRE_ERROR_CALLOUT is reserved for use by callout functions; +it will never be used by PCRE itself. +
+
+Philip Hazel
+
+University Computing Service
+
+Cambridge CB2 3QH, England.
+
+
+Last updated: 24 June 2012
+
+Copyright © 1997-2012 University of Cambridge.
+
+
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcrecompat.html b/tools/pcre/doc/html/pcrecompat.html new file mode 100644 index 00000000..0637781b --- /dev/null +++ b/tools/pcre/doc/html/pcrecompat.html @@ -0,0 +1,216 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+DIFFERENCES BETWEEN PCRE AND PERL
+
+
+This document describes the differences in the ways that PCRE and Perl handle +regular expressions. The differences described here are with respect to Perl +versions 5.10 and above. +
++1. PCRE has only a subset of Perl's Unicode support. Details of what it does +have are given in the +pcreunicode +page. +
++2. PCRE allows repeat quantifiers only on parenthesized assertions, but they do +not mean what you might think. For example, (?!a){3} does not assert that the +next three characters are not "a". It just asserts that the next character is +not "a" three times (in principle: PCRE optimizes this to run the assertion +just once). Perl allows repeat quantifiers on other assertions such as \b, but +these do not seem to have any use. +
++3. Capturing subpatterns that occur inside negative lookahead assertions are +counted, but their entries in the offsets vector are never set. Perl sets its +numerical variables from any such patterns that are matched before the +assertion fails to match something (thereby succeeding), but only if the +negative lookahead assertion contains just one branch. +
++4. Though binary zero characters are supported in the subject string, they are +not allowed in a pattern string because it is passed as a normal C string, +terminated by zero. The escape sequence \0 can be used in the pattern to +represent a binary zero. +
++5. The following Perl escape sequences are not supported: \l, \u, \L, +\U, and \N when followed by a character name or Unicode value. (\N on its +own, matching a non-newline character, is supported.) In fact these are +implemented by Perl's general string-handling and are not part of its pattern +matching engine. If any of these are encountered by PCRE, an error is +generated by default. However, if the PCRE_JAVASCRIPT_COMPAT option is set, +\U and \u are interpreted as JavaScript interprets them. +
++6. The Perl escape sequences \p, \P, and \X are supported only if PCRE is +built with Unicode character property support. The properties that can be +tested with \p and \P are limited to the general category properties such as +Lu and Nd, script names such as Greek or Han, and the derived properties Any +and L&. PCRE does support the Cs (surrogate) property, which Perl does not; the +Perl documentation says "Because Perl hides the need for the user to understand +the internal representation of Unicode characters, there is no need to +implement the somewhat messy concept of surrogates." +
++7. PCRE does support the \Q...\E escape for quoting substrings. Characters in +between are treated as literals. This is slightly different from Perl in that $ +and @ are also handled as literals inside the quotes. In Perl, they cause +variable interpolation (but of course PCRE does not have variables). Note the +following examples: +
+ Pattern PCRE matches Perl matches + + \Qabc$xyz\E abc$xyz abc followed by the contents of $xyz + \Qabc\$xyz\E abc\$xyz abc\$xyz + \Qabc\E\$\Qxyz\E abc$xyz abc$xyz ++The \Q...\E sequence is recognized both inside and outside character classes. + +
+8. Fairly obviously, PCRE does not support the (?{code}) and (??{code}) +constructions. However, there is support for recursive patterns. This is not +available in Perl 5.8, but it is in Perl 5.10. Also, the PCRE "callout" +feature allows an external function to be called during pattern matching. See +the +pcrecallout +documentation for details. +
++9. Subpatterns that are called as subroutines (whether or not recursively) are +always treated as atomic groups in PCRE. This is like Python, but unlike Perl. +Captured values that are set outside a subroutine call can be reference from +inside in PCRE, but not in Perl. There is a discussion that explains these +differences in more detail in the +section on recursion differences from Perl +in the +pcrepattern +page. +
++10. If any of the backtracking control verbs are used in an assertion or in a +subpattern that is called as a subroutine (whether or not recursively), their +effect is confined to that subpattern; it does not extend to the surrounding +pattern. This is not always the case in Perl. In particular, if (*THEN) is +present in a group that is called as a subroutine, its action is limited to +that group, even if the group does not contain any | characters. There is one +exception to this: the name from a *(MARK), (*PRUNE), or (*THEN) that is +encountered in a successful positive assertion is passed back when a +match succeeds (compare capturing parentheses in assertions). Note that such +subpatterns are processed as anchored at the point where they are tested. +
++11. There are some differences that are concerned with the settings of captured +strings when part of a pattern is repeated. For example, matching "aba" against +the pattern /^(a(b)?)+$/ in Perl leaves $2 unset, but in PCRE it is set to "b". +
++12. PCRE's handling of duplicate subpattern numbers and duplicate subpattern +names is not as general as Perl's. This is a consequence of the fact the PCRE +works internally just with numbers, using an external table to translate +between numbers and names. In particular, a pattern such as (?|(?<a>A)|(?<b)B), +where the two capturing parentheses have the same number but different names, +is not supported, and causes an error at compile time. If it were allowed, it +would not be possible to distinguish which parentheses matched, because both +names map to capturing subpattern number 1. To avoid this confusing situation, +an error is given at compile time. +
++13. Perl recognizes comments in some places that PCRE does not, for example, +between the ( and ? at the start of a subpattern. If the /x modifier is set, +Perl allows white space between ( and ? but PCRE never does, even if the +PCRE_EXTENDED option is set. +
+
+14. PCRE provides some extensions to the Perl regular expression facilities.
+Perl 5.10 includes new features that are not in earlier versions of Perl, some
+of which (such as named parentheses) have been in PCRE for some time. This list
+is with respect to Perl 5.10:
+
+
+(a) Although lookbehind assertions in PCRE must match fixed length strings,
+each alternative branch of a lookbehind assertion can match a different length
+of string. Perl requires them all to have the same length.
+
+
+(b) If PCRE_DOLLAR_ENDONLY is set and PCRE_MULTILINE is not set, the $
+meta-character matches only at the very end of the string.
+
+
+(c) If PCRE_EXTRA is set, a backslash followed by a letter with no special
+meaning is faulted. Otherwise, like Perl, the backslash is quietly ignored.
+(Perl can be made to issue a warning.)
+
+
+(d) If PCRE_UNGREEDY is set, the greediness of the repetition quantifiers is
+inverted, that is, by default they are not greedy, but if followed by a
+question mark they are.
+
+
+(e) PCRE_ANCHORED can be used at matching time to force a pattern to be tried
+only at the first matching position in the subject string.
+
+
+(f) The PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART, and
+PCRE_NO_AUTO_CAPTURE options for pcre_exec() have no Perl equivalents.
+
+
+(g) The \R escape sequence can be restricted to match only CR, LF, or CRLF
+by the PCRE_BSR_ANYCRLF option.
+
+
+(h) The callout facility is PCRE-specific.
+
+
+(i) The partial matching facility is PCRE-specific.
+
+
+(j) Patterns compiled by PCRE can be saved and re-used at a later time, even on
+different hosts that have the other endianness. However, this does not apply to
+optimized data created by the just-in-time compiler.
+
+
+(k) The alternative matching functions (pcre_dfa_exec(),
+pcre16_dfa_exec() and pcre32_dfa_exec(),) match in a different way
+and are not Perl-compatible.
+
+
+(l) PCRE recognizes some special sequences such as (*CR) at the start of
+a pattern that set overall options that cannot be changed within the pattern.
+
+Philip Hazel
+
+University Computing Service
+
+Cambridge CB2 3QH, England.
+
+
+Last updated: 25 August 2012
+
+Copyright © 1997-2012 University of Cambridge.
+
+
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcrecpp.html b/tools/pcre/doc/html/pcrecpp.html new file mode 100644 index 00000000..b7eac3a3 --- /dev/null +++ b/tools/pcre/doc/html/pcrecpp.html @@ -0,0 +1,368 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+#include <pcrecpp.h> +
++The C++ wrapper for PCRE was provided by Google Inc. Some additional +functionality was added by Giuseppe Maxia. This brief man page was constructed +from the notes in the pcrecpp.h file, which should be consulted for +further details. Note that the C++ wrapper supports only the original 8-bit +PCRE library. There is no 16-bit or 32-bit support at present. +
++The "FullMatch" operation checks that supplied text matches a supplied pattern +exactly. If pointer arguments are supplied, it copies matched sub-strings that +match sub-patterns into them. +
+ Example: successful match
+ pcrecpp::RE re("h.*o");
+ re.FullMatch("hello");
+
+ Example: unsuccessful match (requires full match):
+ pcrecpp::RE re("e");
+ !re.FullMatch("hello");
+
+ Example: creating a temporary RE object:
+ pcrecpp::RE("h.*o").FullMatch("hello");
+
+You can pass in a "const char*" or a "string" for "text". The examples below
+tend to use a const char*. You can, as in the different examples above, store
+the RE object explicitly in a variable or use a temporary RE object. The
+examples below use one mode or the other arbitrarily. Either could correctly be
+used for any of these examples.
+
++You must supply extra pointer arguments to extract matched subpieces. +
+ Example: extracts "ruby" into "s" and 1234 into "i"
+ int i;
+ string s;
+ pcrecpp::RE re("(\\w+):(\\d+)");
+ re.FullMatch("ruby:1234", &s, &i);
+
+ Example: does not try to extract any extra sub-patterns
+ re.FullMatch("ruby:1234", &s);
+
+ Example: does not try to extract into NULL
+ re.FullMatch("ruby:1234", NULL, &i);
+
+ Example: integer overflow causes failure
+ !re.FullMatch("ruby:1234567891234", NULL, &i);
+
+ Example: fails because there aren't enough sub-patterns:
+ !pcrecpp::RE("\\w+:\\d+").FullMatch("ruby:1234", &s);
+
+ Example: fails because string cannot be stored in integer
+ !pcrecpp::RE("(.*)").FullMatch("ruby", &i);
+
+The provided pointer arguments can be pointers to any scalar numeric
+type, or one of:
++ string (matched piece is copied to string) + StringPiece (StringPiece is mutated to point to matched piece) + T (where "bool T::ParseFrom(const char*, int)" exists) + NULL (the corresponding matched sub-pattern is not copied) ++The function returns true iff all of the following conditions are satisfied: +
+ a. "text" matches "pattern" exactly; + + b. The number of matched sub-patterns is >= number of supplied + pointers; + + c. The "i"th argument has a suitable type for holding the + string captured as the "i"th sub-pattern. If you pass in + void * NULL for the "i"th argument, or a non-void * NULL + of the correct type, or pass fewer arguments than the + number of sub-patterns, "i"th captured sub-pattern is + ignored. ++CAVEAT: An optional sub-pattern that does not exist in the matched +string is assigned the empty string. Therefore, the following will +return false (because the empty string is not a valid number): +
+ int number;
+ pcrecpp::RE::FullMatch("abc", "[a-z]+(\\d+)?", &number);
+
+The matching interface supports at most 16 arguments per call.
+If you need more, consider using the more general interface
+pcrecpp::RE::DoMatch. See pcrecpp.h for the signature for
+DoMatch.
+
++NOTE: Do not use no_arg, which is used internally to mark the end of a +list of optional arguments, as a placeholder for missing arguments, as this can +lead to segfaults. +
++You can use the "QuoteMeta" operation to insert backslashes before all +potentially meaningful characters in a string. The returned string, used as a +regular expression, will exactly match the original string. +
+ Example: + string quoted = RE::QuoteMeta(unquoted); ++Note that it's legal to escape a character even if it has no special meaning in +a regular expression -- so this function does that. (This also makes it +identical to the perl function of the same name; see "perldoc -f quotemeta".) +For example, "1.5-2.0?" becomes "1\.5\-2\.0\?". + +
+You can use the "PartialMatch" operation when you want the pattern +to match any substring of the text. +
+ Example: simple search for a string:
+ pcrecpp::RE("ell").PartialMatch("hello");
+
+ Example: find first number in a string:
+ int number;
+ pcrecpp::RE re("(\\d+)");
+ re.PartialMatch("x*100 + 20", &number);
+ assert(number == 100);
+
+
++By default, pattern and text are plain text, one byte per character. The UTF8 +flag, passed to the constructor, causes both pattern and string to be treated +as UTF-8 text, still a byte stream but potentially multiple bytes per +character. In practice, the text is likelier to be UTF-8 than the pattern, but +the match returned may depend on the UTF8 flag, so always use it when matching +UTF8 text. For example, "." will match one byte normally but with UTF8 set may +match up to three bytes of a multi-byte character. +
+ Example: + pcrecpp::RE_Options options; + options.set_utf8(); + pcrecpp::RE re(utf8_pattern, options); + re.FullMatch(utf8_string); + + Example: using the convenience function UTF8(): + pcrecpp::RE re(utf8_pattern, pcrecpp::UTF8()); + re.FullMatch(utf8_string); ++NOTE: The UTF8 flag is ignored if pcre was not configured with the +
+ --enable-utf8 flag. ++ +
+PCRE defines some modifiers to change the behavior of the regular expression +engine. The C++ wrapper defines an auxiliary class, RE_Options, as a vehicle to +pass such modifiers to a RE class. Currently, the following modifiers are +supported: +
+ modifier description Perl corresponding + + PCRE_CASELESS case insensitive match /i + PCRE_MULTILINE multiple lines match /m + PCRE_DOTALL dot matches newlines /s + PCRE_DOLLAR_ENDONLY $ matches only at end N/A + PCRE_EXTRA strict escape parsing N/A + PCRE_EXTENDED ignore white spaces /x + PCRE_UTF8 handles UTF8 chars built-in + PCRE_UNGREEDY reverses * and *? N/A + PCRE_NO_AUTO_CAPTURE disables capturing parens N/A (*) ++(*) Both Perl and PCRE allow non capturing parentheses by means of the +"?:" modifier within the pattern itself. e.g. (?:ab|cd) does not +capture, while (ab|cd) does. + +
+For a full account on how each modifier works, please check the +PCRE API reference page. +
++For each modifier, there are two member functions whose name is made +out of the modifier in lowercase, without the "PCRE_" prefix. For +instance, PCRE_CASELESS is handled by +
+ bool caseless() ++which returns true if the modifier is set, and +
+ RE_Options & set_caseless(bool) ++which sets or unsets the modifier. Moreover, PCRE_EXTRA_MATCH_LIMIT can be +accessed through the set_match_limit() and match_limit() member +functions. Setting match_limit to a non-zero value will limit the +execution of pcre to keep it from doing bad things like blowing the stack or +taking an eternity to return a result. A value of 5000 is good enough to stop +stack blowup in a 2MB thread stack. Setting match_limit to zero disables +match limiting. Alternatively, you can call match_limit_recursion() +which uses PCRE_EXTRA_MATCH_LIMIT_RECURSION to limit how much PCRE +recurses. match_limit() limits the number of matches PCRE does; +match_limit_recursion() limits the depth of internal recursion, and +therefore the amount of stack that is used. + +
+Normally, to pass one or more modifiers to a RE class, you declare +a RE_Options object, set the appropriate options, and pass this +object to a RE constructor. Example: +
+ RE_Options opt;
+ opt.set_caseless(true);
+ if (RE("HELLO", opt).PartialMatch("hello world")) ...
+
+RE_options has two constructors. The default constructor takes no arguments and
+creates a set of flags that are off by default. The optional parameter
+option_flags is to facilitate transfer of legacy code from C programs.
+This lets you do
++ RE(pattern, + RE_Options(PCRE_CASELESS|PCRE_MULTILINE)).PartialMatch(str); ++However, new code is better off doing +
+ RE(pattern, + RE_Options().set_caseless(true).set_multiline(true)) + .PartialMatch(str); ++If you are going to pass one of the most used modifiers, there are some +convenience functions that return a RE_Options class with the +appropriate modifier already set: CASELESS(), UTF8(), +MULTILINE(), DOTALL(), and EXTENDED(). + +
+If you need to set several options at once, and you don't want to go through +the pains of declaring a RE_Options object and setting several options, there +is a parallel method that give you such ability on the fly. You can concatenate +several set_xxxxx() member functions, since each of them returns a +reference to its class object. For example, to pass PCRE_CASELESS, +PCRE_EXTENDED, and PCRE_MULTILINE to a RE with one statement, you may write: +
+ RE(" ^ xyz \\s+ .* blah$",
+ RE_Options()
+ .set_caseless(true)
+ .set_extended(true)
+ .set_multiline(true)).PartialMatch(sometext);
+
+
+
++The "Consume" operation may be useful if you want to repeatedly +match regular expressions at the front of a string and skip over +them as they match. This requires use of the "StringPiece" type, +which represents a sub-range of a real string. Like RE, StringPiece +is defined in the pcrecpp namespace. +
+ Example: read lines of the form "var = value" from a string.
+ string contents = ...; // Fill string somehow
+ pcrecpp::StringPiece input(contents); // Wrap in a StringPiece
+
+ string var;
+ int value;
+ pcrecpp::RE re("(\\w+) = (\\d+)\n");
+ while (re.Consume(&input, &var, &value)) {
+ ...;
+ }
+
+Each successful call to "Consume" will set "var/value", and also
+advance "input" so it points past the matched text.
+
++The "FindAndConsume" operation is similar to "Consume" but does not +anchor your match at the beginning of the string. For example, you +could extract all words from a string by repeatedly calling +
+ pcrecpp::RE("(\\w+)").FindAndConsume(&input, &word)
+
+
++By default, if you pass a pointer to a numeric value, the +corresponding text is interpreted as a base-10 number. You can +instead wrap the pointer with a call to one of the operators Hex(), +Octal(), or CRadix() to interpret the text in another base. The +CRadix operator interprets C-style "0" (base-8) and "0x" (base-16) +prefixes, but defaults to base-10. +
+ Example:
+ int a, b, c, d;
+ pcrecpp::RE re("(.*) (.*) (.*) (.*)");
+ re.FullMatch("100 40 0100 0x40",
+ pcrecpp::Octal(&a), pcrecpp::Hex(&b),
+ pcrecpp::CRadix(&c), pcrecpp::CRadix(&d));
+
+will leave 64 in a, b, c, and d.
+
++You can replace the first match of "pattern" in "str" with "rewrite". +Within "rewrite", backslash-escaped digits (\1 to \9) can be +used to insert text matching corresponding parenthesized group +from the pattern. \0 in "rewrite" refers to the entire matching +text. For example: +
+ string s = "yabba dabba doo";
+ pcrecpp::RE("b+").Replace("d", &s);
+
+will leave "s" containing "yada dabba doo". The result is true if the pattern
+matches and a replacement occurs, false otherwise.
+
++GlobalReplace is like Replace except that it replaces all +occurrences of the pattern in the string with the rewrite. Replacements are +not subject to re-matching. For example: +
+ string s = "yabba dabba doo";
+ pcrecpp::RE("b+").GlobalReplace("d", &s);
+
+will leave "s" containing "yada dada doo". It returns the number of
+replacements made.
+
++Extract is like Replace, except that if the pattern matches, +"rewrite" is copied into "out" (an additional argument) with substitutions. +The non-matching portions of "text" are ignored. Returns true iff a match +occurred and the extraction happened successfully; if no match occurs, the +string is left unaffected. +
+
+The C++ wrapper was contributed by Google Inc.
+
+Copyright © 2007 Google Inc.
+
+
+Last updated: 08 January 2012
+
+
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcredemo.html b/tools/pcre/doc/html/pcredemo.html new file mode 100644 index 00000000..894a9308 --- /dev/null +++ b/tools/pcre/doc/html/pcredemo.html @@ -0,0 +1,426 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+/*************************************************
+* PCRE DEMONSTRATION PROGRAM *
+*************************************************/
+
+/* This is a demonstration program to illustrate the most straightforward ways
+of calling the PCRE regular expression library from a C program. See the
+pcresample documentation for a short discussion ("man pcresample" if you have
+the PCRE man pages installed).
+
+In Unix-like environments, if PCRE is installed in your standard system
+libraries, you should be able to compile this program using this command:
+
+gcc -Wall pcredemo.c -lpcre -o pcredemo
+
+If PCRE is not installed in a standard place, it is likely to be installed with
+support for the pkg-config mechanism. If you have pkg-config, you can compile
+this program using this command:
+
+gcc -Wall pcredemo.c `pkg-config --cflags --libs libpcre` -o pcredemo
+
+If you do not have pkg-config, you may have to use this:
+
+gcc -Wall pcredemo.c -I/usr/local/include -L/usr/local/lib \
+ -R/usr/local/lib -lpcre -o pcredemo
+
+Replace "/usr/local/include" and "/usr/local/lib" with wherever the include and
+library files for PCRE are installed on your system. Only some operating
+systems (e.g. Solaris) use the -R option.
+
+Building under Windows:
+
+If you want to statically link this program against a non-dll .a file, you must
+define PCRE_STATIC before including pcre.h, otherwise the pcre_malloc() and
+pcre_free() exported functions will be declared __declspec(dllimport), with
+unwanted results. So in this environment, uncomment the following line. */
+
+/* #define PCRE_STATIC */
+
+#include <stdio.h>
+#include <string.h>
+#include <pcre.h>
+
+#define OVECCOUNT 30 /* should be a multiple of 3 */
+
+
+int main(int argc, char **argv)
+{
+pcre *re;
+const char *error;
+char *pattern;
+char *subject;
+unsigned char *name_table;
+unsigned int option_bits;
+int erroffset;
+int find_all;
+int crlf_is_newline;
+int namecount;
+int name_entry_size;
+int ovector[OVECCOUNT];
+int subject_length;
+int rc, i;
+int utf8;
+
+
+/**************************************************************************
+* First, sort out the command line. There is only one possible option at *
+* the moment, "-g" to request repeated matching to find all occurrences, *
+* like Perl's /g option. We set the variable find_all to a non-zero value *
+* if the -g option is present. Apart from that, there must be exactly two *
+* arguments. *
+**************************************************************************/
+
+find_all = 0;
+for (i = 1; i < argc; i++)
+ {
+ if (strcmp(argv[i], "-g") == 0) find_all = 1;
+ else break;
+ }
+
+/* After the options, we require exactly two arguments, which are the pattern,
+and the subject string. */
+
+if (argc - i != 2)
+ {
+ printf("Two arguments required: a regex and a subject string\n");
+ return 1;
+ }
+
+pattern = argv[i];
+subject = argv[i+1];
+subject_length = (int)strlen(subject);
+
+
+/*************************************************************************
+* Now we are going to compile the regular expression pattern, and handle *
+* and errors that are detected. *
+*************************************************************************/
+
+re = pcre_compile(
+ pattern, /* the pattern */
+ 0, /* default options */
+ &error, /* for error message */
+ &erroffset, /* for error offset */
+ NULL); /* use default character tables */
+
+/* Compilation failed: print the error message and exit */
+
+if (re == NULL)
+ {
+ printf("PCRE compilation failed at offset %d: %s\n", erroffset, error);
+ return 1;
+ }
+
+
+/*************************************************************************
+* If the compilation succeeded, we call PCRE again, in order to do a *
+* pattern match against the subject string. This does just ONE match. If *
+* further matching is needed, it will be done below. *
+*************************************************************************/
+
+rc = pcre_exec(
+ re, /* the compiled pattern */
+ NULL, /* no extra data - we didn't study the pattern */
+ subject, /* the subject string */
+ subject_length, /* the length of the subject */
+ 0, /* start at offset 0 in the subject */
+ 0, /* default options */
+ ovector, /* output vector for substring information */
+ OVECCOUNT); /* number of elements in the output vector */
+
+/* Matching failed: handle error cases */
+
+if (rc < 0)
+ {
+ switch(rc)
+ {
+ case PCRE_ERROR_NOMATCH: printf("No match\n"); break;
+ /*
+ Handle other special cases if you like
+ */
+ default: printf("Matching error %d\n", rc); break;
+ }
+ pcre_free(re); /* Release memory used for the compiled pattern */
+ return 1;
+ }
+
+/* Match succeded */
+
+printf("\nMatch succeeded at offset %d\n", ovector[0]);
+
+
+/*************************************************************************
+* We have found the first match within the subject string. If the output *
+* vector wasn't big enough, say so. Then output any substrings that were *
+* captured. *
+*************************************************************************/
+
+/* The output vector wasn't big enough */
+
+if (rc == 0)
+ {
+ rc = OVECCOUNT/3;
+ printf("ovector only has room for %d captured substrings\n", rc - 1);
+ }
+
+/* Show substrings stored in the output vector by number. Obviously, in a real
+application you might want to do things other than print them. */
+
+for (i = 0; i < rc; i++)
+ {
+ char *substring_start = subject + ovector[2*i];
+ int substring_length = ovector[2*i+1] - ovector[2*i];
+ printf("%2d: %.*s\n", i, substring_length, substring_start);
+ }
+
+
+/**************************************************************************
+* That concludes the basic part of this demonstration program. We have *
+* compiled a pattern, and performed a single match. The code that follows *
+* shows first how to access named substrings, and then how to code for *
+* repeated matches on the same subject. *
+**************************************************************************/
+
+/* See if there are any named substrings, and if so, show them by name. First
+we have to extract the count of named parentheses from the pattern. */
+
+(void)pcre_fullinfo(
+ re, /* the compiled pattern */
+ NULL, /* no extra data - we didn't study the pattern */
+ PCRE_INFO_NAMECOUNT, /* number of named substrings */
+ &namecount); /* where to put the answer */
+
+if (namecount <= 0) printf("No named substrings\n"); else
+ {
+ unsigned char *tabptr;
+ printf("Named substrings\n");
+
+ /* Before we can access the substrings, we must extract the table for
+ translating names to numbers, and the size of each entry in the table. */
+
+ (void)pcre_fullinfo(
+ re, /* the compiled pattern */
+ NULL, /* no extra data - we didn't study the pattern */
+ PCRE_INFO_NAMETABLE, /* address of the table */
+ &name_table); /* where to put the answer */
+
+ (void)pcre_fullinfo(
+ re, /* the compiled pattern */
+ NULL, /* no extra data - we didn't study the pattern */
+ PCRE_INFO_NAMEENTRYSIZE, /* size of each entry in the table */
+ &name_entry_size); /* where to put the answer */
+
+ /* Now we can scan the table and, for each entry, print the number, the name,
+ and the substring itself. */
+
+ tabptr = name_table;
+ for (i = 0; i < namecount; i++)
+ {
+ int n = (tabptr[0] << 8) | tabptr[1];
+ printf("(%d) %*s: %.*s\n", n, name_entry_size - 3, tabptr + 2,
+ ovector[2*n+1] - ovector[2*n], subject + ovector[2*n]);
+ tabptr += name_entry_size;
+ }
+ }
+
+
+/*************************************************************************
+* If the "-g" option was given on the command line, we want to continue *
+* to search for additional matches in the subject string, in a similar *
+* way to the /g option in Perl. This turns out to be trickier than you *
+* might think because of the possibility of matching an empty string. *
+* What happens is as follows: *
+* *
+* If the previous match was NOT for an empty string, we can just start *
+* the next match at the end of the previous one. *
+* *
+* If the previous match WAS for an empty string, we can't do that, as it *
+* would lead to an infinite loop. Instead, a special call of pcre_exec() *
+* is made with the PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED flags set. *
+* The first of these tells PCRE that an empty string at the start of the *
+* subject is not a valid match; other possibilities must be tried. The *
+* second flag restricts PCRE to one match attempt at the initial string *
+* position. If this match succeeds, an alternative to the empty string *
+* match has been found, and we can print it and proceed round the loop, *
+* advancing by the length of whatever was found. If this match does not *
+* succeed, we still stay in the loop, advancing by just one character. *
+* In UTF-8 mode, which can be set by (*UTF8) in the pattern, this may be *
+* more than one byte. *
+* *
+* However, there is a complication concerned with newlines. When the *
+* newline convention is such that CRLF is a valid newline, we must *
+* advance by two characters rather than one. The newline convention can *
+* be set in the regex by (*CR), etc.; if not, we must find the default. *
+*************************************************************************/
+
+if (!find_all) /* Check for -g */
+ {
+ pcre_free(re); /* Release the memory used for the compiled pattern */
+ return 0; /* Finish unless -g was given */
+ }
+
+/* Before running the loop, check for UTF-8 and whether CRLF is a valid newline
+sequence. First, find the options with which the regex was compiled; extract
+the UTF-8 state, and mask off all but the newline options. */
+
+(void)pcre_fullinfo(re, NULL, PCRE_INFO_OPTIONS, &option_bits);
+utf8 = option_bits & PCRE_UTF8;
+option_bits &= PCRE_NEWLINE_CR|PCRE_NEWLINE_LF|PCRE_NEWLINE_CRLF|
+ PCRE_NEWLINE_ANY|PCRE_NEWLINE_ANYCRLF;
+
+/* If no newline options were set, find the default newline convention from the
+build configuration. */
+
+if (option_bits == 0)
+ {
+ int d;
+ (void)pcre_config(PCRE_CONFIG_NEWLINE, &d);
+ /* Note that these values are always the ASCII ones, even in
+ EBCDIC environments. CR = 13, NL = 10. */
+ option_bits = (d == 13)? PCRE_NEWLINE_CR :
+ (d == 10)? PCRE_NEWLINE_LF :
+ (d == (13<<8 | 10))? PCRE_NEWLINE_CRLF :
+ (d == -2)? PCRE_NEWLINE_ANYCRLF :
+ (d == -1)? PCRE_NEWLINE_ANY : 0;
+ }
+
+/* See if CRLF is a valid newline sequence. */
+
+crlf_is_newline =
+ option_bits == PCRE_NEWLINE_ANY ||
+ option_bits == PCRE_NEWLINE_CRLF ||
+ option_bits == PCRE_NEWLINE_ANYCRLF;
+
+/* Loop for second and subsequent matches */
+
+for (;;)
+ {
+ int options = 0; /* Normally no options */
+ int start_offset = ovector[1]; /* Start at end of previous match */
+
+ /* If the previous match was for an empty string, we are finished if we are
+ at the end of the subject. Otherwise, arrange to run another match at the
+ same point to see if a non-empty match can be found. */
+
+ if (ovector[0] == ovector[1])
+ {
+ if (ovector[0] == subject_length) break;
+ options = PCRE_NOTEMPTY_ATSTART | PCRE_ANCHORED;
+ }
+
+ /* Run the next matching operation */
+
+ rc = pcre_exec(
+ re, /* the compiled pattern */
+ NULL, /* no extra data - we didn't study the pattern */
+ subject, /* the subject string */
+ subject_length, /* the length of the subject */
+ start_offset, /* starting offset in the subject */
+ options, /* options */
+ ovector, /* output vector for substring information */
+ OVECCOUNT); /* number of elements in the output vector */
+
+ /* This time, a result of NOMATCH isn't an error. If the value in "options"
+ is zero, it just means we have found all possible matches, so the loop ends.
+ Otherwise, it means we have failed to find a non-empty-string match at a
+ point where there was a previous empty-string match. In this case, we do what
+ Perl does: advance the matching position by one character, and continue. We
+ do this by setting the "end of previous match" offset, because that is picked
+ up at the top of the loop as the point at which to start again.
+
+ There are two complications: (a) When CRLF is a valid newline sequence, and
+ the current position is just before it, advance by an extra byte. (b)
+ Otherwise we must ensure that we skip an entire UTF-8 character if we are in
+ UTF-8 mode. */
+
+ if (rc == PCRE_ERROR_NOMATCH)
+ {
+ if (options == 0) break; /* All matches found */
+ ovector[1] = start_offset + 1; /* Advance one byte */
+ if (crlf_is_newline && /* If CRLF is newline & */
+ start_offset < subject_length - 1 && /* we are at CRLF, */
+ subject[start_offset] == '\r' &&
+ subject[start_offset + 1] == '\n')
+ ovector[1] += 1; /* Advance by one more. */
+ else if (utf8) /* Otherwise, ensure we */
+ { /* advance a whole UTF-8 */
+ while (ovector[1] < subject_length) /* character. */
+ {
+ if ((subject[ovector[1]] & 0xc0) != 0x80) break;
+ ovector[1] += 1;
+ }
+ }
+ continue; /* Go round the loop again */
+ }
+
+ /* Other matching errors are not recoverable. */
+
+ if (rc < 0)
+ {
+ printf("Matching error %d\n", rc);
+ pcre_free(re); /* Release memory used for the compiled pattern */
+ return 1;
+ }
+
+ /* Match succeded */
+
+ printf("\nMatch succeeded again at offset %d\n", ovector[0]);
+
+ /* The match succeeded, but the output vector wasn't big enough. */
+
+ if (rc == 0)
+ {
+ rc = OVECCOUNT/3;
+ printf("ovector only has room for %d captured substrings\n", rc - 1);
+ }
+
+ /* As before, show substrings stored in the output vector by number, and then
+ also any named substrings. */
+
+ for (i = 0; i < rc; i++)
+ {
+ char *substring_start = subject + ovector[2*i];
+ int substring_length = ovector[2*i+1] - ovector[2*i];
+ printf("%2d: %.*s\n", i, substring_length, substring_start);
+ }
+
+ if (namecount <= 0) printf("No named substrings\n"); else
+ {
+ unsigned char *tabptr = name_table;
+ printf("Named substrings\n");
+ for (i = 0; i < namecount; i++)
+ {
+ int n = (tabptr[0] << 8) | tabptr[1];
+ printf("(%d) %*s: %.*s\n", n, name_entry_size - 3, tabptr + 2,
+ ovector[2*n+1] - ovector[2*n], subject + ovector[2*n]);
+ tabptr += name_entry_size;
+ }
+ }
+ } /* End of loop to find second and subsequent matches */
+
+printf("\n");
+pcre_free(re); /* Release memory used for the compiled pattern */
+return 0;
+}
+
+/* End of pcredemo.c */
+
+Return to the PCRE index page.
+
diff --git a/tools/pcre/doc/html/pcregrep.html b/tools/pcre/doc/html/pcregrep.html
new file mode 100644
index 00000000..bac8f9a4
--- /dev/null
+++ b/tools/pcre/doc/html/pcregrep.html
@@ -0,0 +1,757 @@
+
+
+pcregrep specification
+
+
+pcregrep man page
+
+Return to the PCRE index page.
+
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+pcregrep [options] [long options] [pattern] [path1 path2 ...] +
++pcregrep searches files for character patterns, in the same way as other +grep commands do, but it uses the PCRE regular expression library to support +patterns that are compatible with the regular expressions of Perl 5. See +pcrepattern(3) +for a full description of syntax and semantics of the regular expressions +that PCRE supports. +
++Patterns, whether supplied on the command line or in a separate file, are given +without delimiters. For example: +
+ pcregrep Thursday /etc/motd ++If you attempt to use delimiters (for example, by surrounding a pattern with +slashes, as is common in Perl scripts), they are interpreted as part of the +pattern. Quotes can of course be used to delimit patterns on the command line +because they are interpreted by the shell, and indeed quotes are required if a +pattern contains white space or shell metacharacters. + +
+The first argument that follows any option settings is treated as the single +pattern to be matched when neither -e nor -f is present. +Conversely, when one or both of these options are used to specify patterns, all +arguments are treated as path names. At least one of -e, -f, or an +argument pattern must be provided. +
++If no files are specified, pcregrep reads the standard input. The +standard input can also be referenced by a name consisting of a single hyphen. +For example: +
+ pcregrep some-pattern /file1 - /file3 ++By default, each line that matches a pattern is copied to the standard +output, and if there is more than one file, the file name is output at the +start of each line, followed by a colon. However, there are options that can +change how pcregrep behaves. In particular, the -M option makes it +possible to search for patterns that span line boundaries. What defines a line +boundary is controlled by the -N (--newline) option. + +
+The amount of memory used for buffering files that are being scanned is +controlled by a parameter that can be set by the --buffer-size option. +The default value for this parameter is specified when pcregrep is built, +with the default default being 20K. A block of memory three times this size is +used (to allow for buffering "before" and "after" lines). An error occurs if a +line overflows the buffer. +
++Patterns can be no longer than 8K or BUFSIZ bytes, whichever is the greater. +BUFSIZ is defined in <stdio.h>. When there is more than one pattern +(specified by the use of -e and/or -f), each pattern is applied to +each line in the order in which they are defined, except that all the -e +patterns are tried before the -f patterns. +
++By default, as soon as one pattern matches a line, no further patterns are +considered. However, if --colour (or --color) is used to colour the +matching substrings, or if --only-matching, --file-offsets, or +--line-offsets is used to output only the part of the line that matched +(either shown literally, or as an offset), scanning resumes immediately +following the match, so that further matches on the same line can be found. If +there are multiple patterns, they are all tried on the remainder of the line, +but patterns that follow the one that matched are not tried on the earlier part +of the line. +
++This behaviour means that the order in which multiple patterns are specified +can affect the output when one of the above options is used. This is no longer +the same behaviour as GNU grep, which now manages to display earlier matches +for later patterns (as long as there is no overlap). +
++Patterns that can match an empty string are accepted, but empty string +matches are never recognized. An example is the pattern "(super)?(man)?", in +which all components are optional. This pattern finds all occurrences of both +"super" and "man"; the output differs from matching with "super|man" when only +the matching substrings are being shown. +
++If the LC_ALL or LC_CTYPE environment variable is set, +pcregrep uses the value to set a locale when calling the PCRE library. +The --locale option can be used to override this. +
++It is possible to compile pcregrep so that it uses libz or +libbz2 to read files whose names end in .gz or .bz2, +respectively. You can find out whether your binary has support for one or both +of these file types by running it with the --help option. If the +appropriate support is not present, files are treated as plain text. The +standard input is always so treated. +
++By default, a file that contains a binary zero byte within the first 1024 bytes +is identified as a binary file, and is processed specially. (GNU grep also +identifies binary files in this manner.) See the --binary-files option +for a means of changing the way binary files are handled. +
++The order in which some of the options appear can affect the output. For +example, both the -h and -l options affect the printing of file +names. Whichever comes later in the command line will be the one that takes +effect. Similarly, except where noted below, if an option is given twice, the +later setting is used. Numerical values for options may be followed by K or M, +to signify multiplication by 1024 or 1024*1024 respectively. +
++-- +This terminates the list of options. It is useful if the next item on the +command line starts with a hyphen but is not an option. This allows for the +processing of patterns and filenames that start with hyphens. +
++-A number, --after-context=number +Output number lines of context after each matching line. If filenames +and/or line numbers are being output, a hyphen separator is used instead of a +colon for the context lines. A line containing "--" is output between each +group of lines, unless they are in fact contiguous in the input file. The value +of number is expected to be relatively small. However, pcregrep +guarantees to have up to 8K of following text available for context output. +
++-a, --text +Treat binary files as text. This is equivalent to +--binary-files=text. +
++-B number, --before-context=number +Output number lines of context before each matching line. If filenames +and/or line numbers are being output, a hyphen separator is used instead of a +colon for the context lines. A line containing "--" is output between each +group of lines, unless they are in fact contiguous in the input file. The value +of number is expected to be relatively small. However, pcregrep +guarantees to have up to 8K of preceding text available for context output. +
++--binary-files=word +Specify how binary files are to be processed. If the word is "binary" (the +default), pattern matching is performed on binary files, but the only output is +"Binary file <name> matches" when a match succeeds. If the word is "text", +which is equivalent to the -a or --text option, binary files are +processed in the same way as any other file. In this case, when a match +succeeds, the output may be binary garbage, which can have nasty effects if +sent to a terminal. If the word is "without-match", which is equivalent to the +-I option, binary files are not processed at all; they are assumed not to +be of interest. +
++--buffer-size=number +Set the parameter that controls how much memory is used for buffering files +that are being scanned. +
++-C number, --context=number +Output number lines of context both before and after each matching line. +This is equivalent to setting both -A and -B to the same value. +
++-c, --count +Do not output individual lines from the files that are being scanned; instead +output the number of lines that would otherwise have been shown. If no lines +are selected, the number zero is output. If several files are are being +scanned, a count is output for each of them. However, if the +--files-with-matches option is also used, only those files whose counts +are greater than zero are listed. When -c is used, the -A, +-B, and -C options are ignored. +
++--colour, --color +If this option is given without any data, it is equivalent to "--colour=auto". +If data is required, it must be given in the same shell item, separated by an +equals sign. +
+
+--colour=value, --color=value
+This option specifies under what circumstances the parts of a line that matched
+a pattern should be coloured in the output. By default, the output is not
+coloured. The value (which is optional, see above) may be "never", "always", or
+"auto". In the latter case, colouring happens only if the standard output is
+connected to a terminal. More resources are used when colouring is enabled,
+because pcregrep has to search for all possible matches in a line, not
+just one, in order to colour them all.
+
+
+The colour that is used can be specified by setting the environment variable
+PCREGREP_COLOUR or PCREGREP_COLOR. The value of this variable should be a
+string of two numbers, separated by a semicolon. They are copied directly into
+the control string for setting colour on a terminal, so it is your
+responsibility to ensure that they make sense. If neither of the environment
+variables is set, the default is "1;31", which gives red.
+
+-D action, --devices=action +If an input path is not a regular file or a directory, "action" specifies how +it is to be processed. Valid values are "read" (the default) or "skip" +(silently skip the path). +
++-d action, --directories=action +If an input path is a directory, "action" specifies how it is to be processed. +Valid values are "read" (the default in non-Windows environments, for +compatibility with GNU grep), "recurse" (equivalent to the -r option), or +"skip" (silently skip the path, the default in Windows environments). In the +"read" case, directories are read as if they were ordinary files. In some +operating systems the effect of reading a directory like this is an immediate +end-of-file; in others it may provoke an error. +
+
+-e pattern, --regex=pattern, --regexp=pattern
+Specify a pattern to be matched. This option can be used multiple times in
+order to specify several patterns. It can also be used as a way of specifying a
+single pattern that starts with a hyphen. When -e is used, no argument
+pattern is taken from the command line; all arguments are treated as file
+names. There is no limit to the number of patterns. They are applied to each
+line in the order in which they are defined until one matches.
+
+
+If -f is used with -e, the command line patterns are matched first,
+followed by the patterns from the file(s), independent of the order in which
+these options are specified. Note that multiple use of -e is not the same
+as a single pattern with alternatives. For example, X|Y finds the first
+character in a line that is X or Y, whereas if the two patterns are given
+separately, with X first, pcregrep finds X if it is present, even if it
+follows Y in the line. It finds Y only if there is no X in the line. This
+matters only if you are using -o or --colo(u)r to show the part(s)
+of the line that matched.
+
+--exclude=pattern +Files (but not directories) whose names match the pattern are skipped without +being processed. This applies to all files, whether listed on the command line, +obtained from --file-list, or by scanning a directory. The pattern is a +PCRE regular expression, and is matched against the final component of the file +name, not the entire path. The -F, -w, and -x options do not +apply to this pattern. The option may be given any number of times in order to +specify multiple patterns. If a file name matches both an --include +and an --exclude pattern, it is excluded. There is no short form for this +option. +
++--exclude-from=filename +Treat each non-empty line of the file as the data for an --exclude +option. What constitutes a newline when reading the file is the operating +system's default. The --newline option has no effect on this option. This +option may be given more than once in order to specify a number of files to +read. +
++--exclude-dir=pattern +Directories whose names match the pattern are skipped without being processed, +whatever the setting of the --recursive option. This applies to all +directories, whether listed on the command line, obtained from +--file-list, or by scanning a parent directory. The pattern is a PCRE +regular expression, and is matched against the final component of the directory +name, not the entire path. The -F, -w, and -x options do not +apply to this pattern. The option may be given any number of times in order to +specify more than one pattern. If a directory matches both --include-dir +and --exclude-dir, it is excluded. There is no short form for this +option. +
++-F, --fixed-strings +Interpret each data-matching pattern as a list of fixed strings, separated by +newlines, instead of as a regular expression. What constitutes a newline for +this purpose is controlled by the --newline option. The -w (match +as a word) and -x (match whole line) options can be used with -F. +They apply to each of the fixed strings. A line is selected if any of the fixed +strings are found in it (subject to -w or -x, if present). This +option applies only to the patterns that are matched against the contents of +files; it does not apply to patterns specified by any of the --include or +--exclude options. +
+
+-f filename, --file=filename
+Read patterns from the file, one per line, and match them against
+each line of input. What constitutes a newline when reading the file is the
+operating system's default. The --newline option has no effect on this
+option. Trailing white space is removed from each line, and blank lines are
+ignored. An empty file contains no patterns and therefore matches nothing. See
+also the comments about multiple patterns versus a single pattern with
+alternatives in the description of -e above.
+
+
+If this option is given more than once, all the specified files are
+read. A data line is output if any of the patterns match it. A filename can
+be given as "-" to refer to the standard input. When -f is used, patterns
+specified on the command line using -e may also be present; they are
+tested before the file's patterns. However, no other pattern is taken from the
+command line; all arguments are treated as the names of paths to be searched.
+
+--file-list=filename +Read a list of files and/or directories that are to be scanned from the given +file, one per line. Trailing white space is removed from each line, and blank +lines are ignored. These paths are processed before any that are listed on the +command line. The filename can be given as "-" to refer to the standard input. +If --file and --file-list are both specified as "-", patterns are +read first. This is useful only when the standard input is a terminal, from +which further lines (the list of files) can be read after an end-of-file +indication. If this option is given more than once, all the specified files are +read. +
++--file-offsets +Instead of showing lines or parts of lines that match, show each match as an +offset from the start of the file and a length, separated by a comma. In this +mode, no context is shown. That is, the -A, -B, and -C +options are ignored. If there is more than one match in a line, each of them is +shown separately. This option is mutually exclusive with --line-offsets +and --only-matching. +
++-H, --with-filename +Force the inclusion of the filename at the start of output lines when searching +a single file. By default, the filename is not shown in this case. For matching +lines, the filename is followed by a colon; for context lines, a hyphen +separator is used. If a line number is also being output, it follows the file +name. +
++-h, --no-filename +Suppress the output filenames when searching multiple files. By default, +filenames are shown when multiple files are searched. For matching lines, the +filename is followed by a colon; for context lines, a hyphen separator is used. +If a line number is also being output, it follows the file name. +
++--help +Output a help message, giving brief details of the command options and file +type support, and then exit. Anything else on the command line is +ignored. +
++-I +Treat binary files as never matching. This is equivalent to +--binary-files=without-match. +
++-i, --ignore-case +Ignore upper/lower case distinctions during comparisons. +
++--include=pattern +If any --include patterns are specified, the only files that are +processed are those that match one of the patterns (and do not match an +--exclude pattern). This option does not affect directories, but it +applies to all files, whether listed on the command line, obtained from +--file-list, or by scanning a directory. The pattern is a PCRE regular +expression, and is matched against the final component of the file name, not +the entire path. The -F, -w, and -x options do not apply to +this pattern. The option may be given any number of times. If a file name +matches both an --include and an --exclude pattern, it is excluded. +There is no short form for this option. +
++--include-from=filename +Treat each non-empty line of the file as the data for an --include +option. What constitutes a newline for this purpose is the operating system's +default. The --newline option has no effect on this option. This option +may be given any number of times; all the files are read. +
++--include-dir=pattern +If any --include-dir patterns are specified, the only directories that +are processed are those that match one of the patterns (and do not match an +--exclude-dir pattern). This applies to all directories, whether listed +on the command line, obtained from --file-list, or by scanning a parent +directory. The pattern is a PCRE regular expression, and is matched against the +final component of the directory name, not the entire path. The -F, +-w, and -x options do not apply to this pattern. The option may be +given any number of times. If a directory matches both --include-dir and +--exclude-dir, it is excluded. There is no short form for this option. +
++-L, --files-without-match +Instead of outputting lines from the files, just output the names of the files +that do not contain any lines that would have been output. Each file name is +output once, on a separate line. +
++-l, --files-with-matches +Instead of outputting lines from the files, just output the names of the files +containing lines that would have been output. Each file name is output +once, on a separate line. Searching normally stops as soon as a matching line +is found in a file. However, if the -c (count) option is also used, +matching continues in order to obtain the correct count, and those files that +have at least one match are listed along with their counts. Using this option +with -c is a way of suppressing the listing of files with no matches. +
++--label=name +This option supplies a name to be used for the standard input when file names +are being output. If not supplied, "(standard input)" is used. There is no +short form for this option. +
++--line-buffered +When this option is given, input is read and processed line by line, and the +output is flushed after each write. By default, input is read in large chunks, +unless pcregrep can determine that it is reading from a terminal (which +is currently possible only in Unix-like environments). Output to terminal is +normally automatically flushed by the operating system. This option can be +useful when the input or output is attached to a pipe and you do not want +pcregrep to buffer up large amounts of data. However, its use will affect +performance, and the -M (multiline) option ceases to work. +
++--line-offsets +Instead of showing lines or parts of lines that match, show each match as a +line number, the offset from the start of the line, and a length. The line +number is terminated by a colon (as usual; see the -n option), and the +offset and length are separated by a comma. In this mode, no context is shown. +That is, the -A, -B, and -C options are ignored. If there is +more than one match in a line, each of them is shown separately. This option is +mutually exclusive with --file-offsets and --only-matching. +
++--locale=locale-name +This option specifies a locale to be used for pattern matching. It overrides +the value in the LC_ALL or LC_CTYPE environment variables. If no +locale is specified, the PCRE library's default (usually the "C" locale) is +used. There is no short form for this option. +
+
+--match-limit=number
+Processing some regular expression patterns can require a very large amount of
+memory, leading in some cases to a program crash if not enough is available.
+Other patterns may take a very long time to search for all possible matching
+strings. The pcre_exec() function that is called by pcregrep to do
+the matching has two parameters that can limit the resources that it uses.
+
+
+The --match-limit option provides a means of limiting resource usage
+when processing patterns that are not going to match, but which have a very
+large number of possibilities in their search trees. The classic example is a
+pattern that uses nested unlimited repeats. Internally, PCRE uses a function
+called match() which it calls repeatedly (sometimes recursively). The
+limit set by --match-limit is imposed on the number of times this
+function is called during a match, which has the effect of limiting the amount
+of backtracking that can take place.
+
+
+The --recursion-limit option is similar to --match-limit, but
+instead of limiting the total number of times that match() is called, it
+limits the depth of recursive calls, which in turn limits the amount of memory
+that can be used. The recursion depth is a smaller number than the total number
+of calls, because not all calls to match() are recursive. This limit is
+of use only if it is set smaller than --match-limit.
+
+
+There are no short forms for these options. The default settings are specified
+when the PCRE library is compiled, with the default default being 10 million.
+
+-M, --multiline
+Allow patterns to match more than one line. When this option is given, patterns
+may usefully contain literal newline characters and internal occurrences of ^
+and $ characters. The output for a successful match may consist of more than
+one line, the last of which is the one in which the match ended. If the matched
+string ends with a newline sequence the output ends at the end of that line.
+
+
+When this option is set, the PCRE library is called in "multiline" mode.
+There is a limit to the number of lines that can be matched, imposed by the way
+that pcregrep buffers the input file as it scans it. However,
+pcregrep ensures that at least 8K characters or the rest of the document
+(whichever is the shorter) are available for forward matching, and similarly
+the previous 8K characters (or all the previous characters, if fewer than 8K)
+are guaranteed to be available for lookbehind assertions. This option does not
+work when input is read line by line (see \fP--line-buffered\fP.)
+
+-N newline-type, --newline=newline-type
+The PCRE library supports five different conventions for indicating
+the ends of lines. They are the single-character sequences CR (carriage return)
+and LF (linefeed), the two-character sequence CRLF, an "anycrlf" convention,
+which recognizes any of the preceding three types, and an "any" convention, in
+which any Unicode line ending sequence is assumed to end a line. The Unicode
+sequences are the three just mentioned, plus VT (vertical tab, U+000B), FF
+(form feed, U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and
+PS (paragraph separator, U+2029).
+
+
+When the PCRE library is built, a default line-ending sequence is specified.
+This is normally the standard sequence for the operating system. Unless
+otherwise specified by this option, pcregrep uses the library's default.
+The possible values for this option are CR, LF, CRLF, ANYCRLF, or ANY. This
+makes it possible to use pcregrep to scan files that have come from other
+environments without having to modify their line endings. If the data that is
+being scanned does not agree with the convention set by this option,
+pcregrep may behave in strange ways. Note that this option does not
+apply to files specified by the -f, --exclude-from, or
+--include-from options, which are expected to use the operating system's
+standard newline sequence.
+
+-n, --line-number +Precede each output line by its line number in the file, followed by a colon +for matching lines or a hyphen for context lines. If the filename is also being +output, it precedes the line number. This option is forced if +--line-offsets is used. +
++--no-jit +If the PCRE library is built with support for just-in-time compiling (which +speeds up matching), pcregrep automatically makes use of this, unless it +was explicitly disabled at build time. This option can be used to disable the +use of JIT at run time. It is provided for testing and working round problems. +It should never be needed in normal use. +
++-o, --only-matching +Show only the part of the line that matched a pattern instead of the whole +line. In this mode, no context is shown. That is, the -A, -B, and +-C options are ignored. If there is more than one match in a line, each +of them is shown separately. If -o is combined with -v (invert the +sense of the match to find non-matching lines), no output is generated, but the +return code is set appropriately. If the matched portion of the line is empty, +nothing is output unless the file name or line number are being printed, in +which case they are shown on an otherwise empty line. This option is mutually +exclusive with --file-offsets and --line-offsets. +
+
+-onumber, --only-matching=number
+Show only the part of the line that matched the capturing parentheses of the
+given number. Up to 32 capturing parentheses are supported, and -o0 is
+equivalent to -o without a number. Because these options can be given
+without an argument (see above), if an argument is present, it must be given in
+the same shell item, for example, -o3 or --only-matching=2. The comments given
+for the non-argument case above also apply to this case. If the specified
+capturing parentheses do not exist in the pattern, or were not set in the
+match, nothing is output unless the file name or line number are being printed.
+
+
+If this option is given multiple times, multiple substrings are output, in the
+order the options are given. For example, -o3 -o1 -o3 causes the substrings
+matched by capturing parentheses 3 and 1 and then 3 again to be output. By
+default, there is no separator (but see the next option).
+
+--om-separator=text +Specify a separating string for multiple occurrences of -o. The default +is an empty string. Separating strings are never coloured. +
++-q, --quiet +Work quietly, that is, display nothing except error messages. The exit +status indicates whether or not any matches were found. +
++-r, --recursive +If any given path is a directory, recursively scan the files it contains, +taking note of any --include and --exclude settings. By default, a +directory is read as a normal file; in some operating systems this gives an +immediate end-of-file. This option is a shorthand for setting the -d +option to "recurse". +
++--recursion-limit=number +See --match-limit above. +
++-s, --no-messages +Suppress error messages about non-existent or unreadable files. Such files are +quietly skipped. However, the return code is still 2, even if matches were +found in other files. +
++-u, --utf-8 +Operate in UTF-8 mode. This option is available only if PCRE has been compiled +with UTF-8 support. All patterns (including those for any --exclude and +--include options) and all subject lines that are scanned must be valid +strings of UTF-8 characters. +
++-V, --version +Write the version numbers of pcregrep and the PCRE library to the +standard output and then exit. Anything else on the command line is +ignored. +
++-v, --invert-match +Invert the sense of the match, so that lines which do not match any of +the patterns are the ones that are found. +
++-w, --word-regex, --word-regexp +Force the patterns to match only whole words. This is equivalent to having \b +at the start and end of the pattern. This option applies only to the patterns +that are matched against the contents of files; it does not apply to patterns +specified by any of the --include or --exclude options. +
++-x, --line-regex, --line-regexp +Force the patterns to be anchored (each must start matching at the beginning of +a line) and in addition, require them to match entire lines. This is equivalent +to having ^ and $ characters at the start and end of each alternative branch in +every pattern. This option applies only to the patterns that are matched +against the contents of files; it does not apply to patterns specified by any +of the --include or --exclude options. +
++The environment variables LC_ALL and LC_CTYPE are examined, in that +order, for a locale. The first one that is set is used. This can be overridden +by the --locale option. If no locale is set, the PCRE library's default +(usually the "C" locale) is used. +
++The -N (--newline) option allows pcregrep to scan files with +different newline conventions from the default. Any parts of the input files +that are written to the standard output are copied identically, with whatever +newline sequences they have in the input. However, the setting of this option +does not affect the interpretation of files specified by the -f, +--exclude-from, or --include-from options, which are assumed to use +the operating system's standard newline sequence, nor does it affect the way in +which pcregrep writes informational messages to the standard error and +output streams. For these it uses the string "\n" to indicate newlines, +relying on the C I/O library to convert this to an appropriate sequence. +
++Many of the short and long forms of pcregrep's options are the same +as in the GNU grep program. Any long option of the form +--xxx-regexp (GNU terminology) is also available as --xxx-regex +(PCRE terminology). However, the --file-list, --file-offsets, +--include-dir, --line-offsets, --locale, --match-limit, +-M, --multiline, -N, --newline, --om-separator, +--recursion-limit, -u, and --utf-8 options are specific to +pcregrep, as is the use of the --only-matching option with a +capturing parentheses number. +
++Although most of the common options work the same way, a few are different in +pcregrep. For example, the --include option's argument is a glob +for GNU grep, but a regular expression for pcregrep. If both the +-c and -l options are given, GNU grep lists only file names, +without counts, but pcregrep gives the counts. +
++There are four different ways in which an option with data can be specified. +If a short form option is used, the data may follow immediately, or (with one +exception) in the next command line item. For example: +
+ -f/some/file + -f /some/file ++The exception is the -o option, which may appear with or without data. +Because of this, if data is present, it must follow immediately in the same +item, for example -o3. + +
+If a long form option is used, the data may appear in the same command line +item, separated by an equals character, or (with two exceptions) it may appear +in the next command line item. For example: +
+ --file=/some/file + --file /some/file ++Note, however, that if you want to supply a file name beginning with ~ as data +in a shell command, and have the shell expand ~ to a home directory, you must +separate the file name from the option, because the shell does not treat ~ +specially unless it is at the start of an item. + +
+The exceptions to the above are the --colour (or --color) and +--only-matching options, for which the data is optional. If one of these +options does have data, it must be given in the first form, using an equals +character. Otherwise pcregrep will assume that it has no data. +
++It is possible to supply a regular expression that takes a very long time to +fail to match certain lines. Such patterns normally involve nested indefinite +repeats, for example: (a+)*\d when matched against a line of a's with no final +digit. The PCRE matching function has a resource limit that causes it to abort +in these circumstances. If this happens, pcregrep outputs an error +message and the line that caused the problem to the standard error stream. If +there are more than 20 such errors, pcregrep gives up. +
++The --match-limit option of pcregrep can be used to set the overall +resource limit; there is a second option called --recursion-limit that +sets a limit on the amount of memory (usually stack) that is used (see the +discussion of these options above). +
++Exit status is 0 if any matches were found, 1 if no matches were found, and 2 +for syntax errors, overlong lines, non-existent or inaccessible files (even if +matches were found in other files) or too many matching errors. Using the +-s option to suppress error messages about inaccessible files does not +affect the return code. +
++pcrepattern(3), pcresyntax(3), pcretest(1). +
+
+Philip Hazel
+
+University Computing Service
+
+Cambridge CB2 3QH, England.
+
+
+Last updated: 13 September 2012
+
+Copyright © 1997-2012 University of Cambridge.
+
+
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcrejit.html b/tools/pcre/doc/html/pcrejit.html new file mode 100644 index 00000000..6286fccb --- /dev/null +++ b/tools/pcre/doc/html/pcrejit.html @@ -0,0 +1,458 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+Just-in-time compiling is a heavyweight optimization that can greatly speed up +pattern matching. However, it comes at the cost of extra processing before the +match is performed. Therefore, it is of most benefit when the same pattern is +going to be matched many times. This does not necessarily mean many calls of a +matching function; if the pattern is not anchored, matching attempts may take +place many times at various positions in the subject, even for a single call. +Therefore, if the subject string is very long, it may still pay to use JIT for +one-off matches. +
++JIT support applies only to the traditional Perl-compatible matching function. +It does not apply when the DFA matching function is being used. The code for +this support was written by Zoltan Herczeg. +
++JIT support is available for all of the 8-bit, 16-bit and 32-bit PCRE +libraries. To keep this documentation simple, only the 8-bit interface is +described in what follows. If you are using the 16-bit library, substitute the +16-bit functions and 16-bit structures (for example, pcre16_jit_stack +instead of pcre_jit_stack). If you are using the 32-bit library, +substitute the 32-bit functions and 32-bit structures (for example, +pcre32_jit_stack instead of pcre_jit_stack). +
++JIT support is an optional feature of PCRE. The "configure" option --enable-jit +(or equivalent CMake option) must be set when PCRE is built if you want to use +JIT. The support is limited to the following hardware platforms: +
+ ARM v5, v7, and Thumb2 + Intel x86 32-bit and 64-bit + MIPS 32-bit + Power PC 32-bit and 64-bit + SPARC 32-bit (experimental) ++If --enable-jit is set on an unsupported platform, compilation fails. + +
+A program that is linked with PCRE 8.20 or later can tell if JIT support is +available by calling pcre_config() with the PCRE_CONFIG_JIT option. The +result is 1 when JIT is available, and 0 otherwise. However, a simple program +does not need to check this in order to use JIT. The normal API is implemented +in a way that falls back to the interpretive code if JIT is not available. For +programs that need the best possible performance, there is also a "fast path" +API that is JIT-specific. +
++If your program may sometimes be linked with versions of PCRE that are older +than 8.20, but you want to use JIT when it is available, you can test +the values of PCRE_MAJOR and PCRE_MINOR, or the existence of a JIT macro such +as PCRE_CONFIG_JIT, for compile-time control of your code. +
++You have to do two things to make use of the JIT support in the simplest way: +
+ (1) Call pcre_study() with the PCRE_STUDY_JIT_COMPILE option for + each compiled pattern, and pass the resulting pcre_extra block to + pcre_exec(). + + (2) Use pcre_free_study() to free the pcre_extra block when it is + no longer needed, instead of just freeing it yourself. This ensures that + any JIT data is also freed. ++For a program that may be linked with pre-8.20 versions of PCRE, you can insert +
+ #ifndef PCRE_STUDY_JIT_COMPILE + #define PCRE_STUDY_JIT_COMPILE 0 + #endif ++so that no option is passed to pcre_study(), and then use something like +this to free the study data: +
+ #ifdef PCRE_CONFIG_JIT + pcre_free_study(study_ptr); + #else + pcre_free(study_ptr); + #endif ++PCRE_STUDY_JIT_COMPILE requests the JIT compiler to generate code for complete +matches. If you want to run partial matches using the PCRE_PARTIAL_HARD or +PCRE_PARTIAL_SOFT options of pcre_exec(), you should set one or both of +the following options in addition to, or instead of, PCRE_STUDY_JIT_COMPILE +when you call pcre_study(): +
+ PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE + PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE ++The JIT compiler generates different optimized code for each of the three +modes (normal, soft partial, hard partial). When pcre_exec() is called, +the appropriate code is run if it is available. Otherwise, the pattern is +matched using interpretive code. + +
+In some circumstances you may need to call additional functions. These are +described in the section entitled +"Controlling the JIT stack" +below. +
++If JIT support is not available, PCRE_STUDY_JIT_COMPILE etc. are ignored, and +no JIT data is created. Otherwise, the compiled pattern is passed to the JIT +compiler, which turns it into machine code that executes much faster than the +normal interpretive code. When pcre_exec() is passed a pcre_extra +block containing a pointer to JIT code of the appropriate mode (normal or +hard/soft partial), it obeys that code instead of running the interpreter. The +result is identical, but the compiled JIT code runs much faster. +
++There are some pcre_exec() options that are not supported for JIT +execution. There are also some pattern items that JIT cannot handle. Details +are given below. In both cases, execution automatically falls back to the +interpretive code. If you want to know whether JIT was actually used for a +particular match, you should arrange for a JIT callback function to be set up +as described in the section entitled +"Controlling the JIT stack" +below, even if you do not need to supply a non-default JIT stack. Such a +callback function is called whenever JIT code is about to be obeyed. If the +execution options are not right for JIT execution, the callback function is not +obeyed. +
++If the JIT compiler finds an unsupported item, no JIT data is generated. You +can find out if JIT execution is available after studying a pattern by calling +pcre_fullinfo() with the PCRE_INFO_JIT option. A result of 1 means that +JIT compilation was successful. A result of 0 means that JIT support is not +available, or the pattern was not studied with PCRE_STUDY_JIT_COMPILE etc., or +the JIT compiler was not able to handle the pattern. +
++Once a pattern has been studied, with or without JIT, it can be used as many +times as you like for matching different subject strings. +
++The only pcre_exec() options that are supported for JIT execution are +PCRE_NO_UTF8_CHECK, PCRE_NO_UTF16_CHECK, PCRE_NO_UTF32_CHECK, PCRE_NOTBOL, +PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART, PCRE_PARTIAL_HARD, and +PCRE_PARTIAL_SOFT. +
++The unsupported pattern items are: +
+ \C match a single byte; not supported in UTF-8 mode + (?Cn) callouts + (*PRUNE) ) + (*SKIP) ) backtracking control verbs + (*THEN) ) ++Support for some of these may be added in future. + +
+When a pattern is matched using JIT execution, the return values are the same +as those given by the interpretive pcre_exec() code, with the addition of +one new error code: PCRE_ERROR_JIT_STACKLIMIT. This means that the memory used +for the JIT stack was insufficient. See +"Controlling the JIT stack" +below for a discussion of JIT stack usage. For compatibility with the +interpretive pcre_exec() code, no more than two-thirds of the +ovector argument is used for passing back captured substrings. +
++The error code PCRE_ERROR_MATCHLIMIT is returned by the JIT code if searching a +very large pattern tree goes on for too long, as it is in the same circumstance +when JIT is not used, but the details of exactly what is counted are not the +same. The PCRE_ERROR_RECURSIONLIMIT error code is never returned by JIT +execution. +
++The code that is generated by the JIT compiler is architecture-specific, and is +also position dependent. For those reasons it cannot be saved (in a file or +database) and restored later like the bytecode and other data of a compiled +pattern. Saving and restoring compiled patterns is not something many people +do. More detail about this facility is given in the +pcreprecompile +documentation. It should be possible to run pcre_study() on a saved and +restored pattern, and thereby recreate the JIT data, but because JIT +compilation uses significant resources, it is probably not worth doing this; +you might as well recompile the original pattern. +
++When the compiled JIT code runs, it needs a block of memory to use as a stack. +By default, it uses 32K on the machine stack. However, some large or +complicated patterns need more than this. The error PCRE_ERROR_JIT_STACKLIMIT +is given when there is not enough stack. Three functions are provided for +managing blocks of memory for use as JIT stacks. There is further discussion +about the use of JIT stacks in the section entitled +"JIT stack FAQ" +below. +
++The pcre_jit_stack_alloc() function creates a JIT stack. Its arguments +are a starting size and a maximum size, and it returns a pointer to an opaque +structure of type pcre_jit_stack, or NULL if there is an error. The +pcre_jit_stack_free() function can be used to free a stack that is no +longer needed. (For the technically minded: the address space is allocated by +mmap or VirtualAlloc.) +
++JIT uses far less memory for recursion than the interpretive code, +and a maximum stack size of 512K to 1M should be more than enough for any +pattern. +
++The pcre_assign_jit_stack() function specifies which stack JIT code +should use. Its arguments are as follows: +
+ pcre_extra *extra + pcre_jit_callback callback + void *data ++The extra argument must be the result of studying a pattern with +PCRE_STUDY_JIT_COMPILE etc. There are three cases for the values of the other +two options: +
+ (1) If callback is NULL and data is NULL, an internal 32K block + on the machine stack is used. + + (2) If callback is NULL and data is not NULL, data must be + a valid JIT stack, the result of calling pcre_jit_stack_alloc(). + + (3) If callback is not NULL, it must point to a function that is + called with data as an argument at the start of matching, in + order to set up a JIT stack. If the return from the callback + function is NULL, the internal 32K stack is used; otherwise the + return value must be a valid JIT stack, the result of calling + pcre_jit_stack_alloc(). ++A callback function is obeyed whenever JIT code is about to be run; it is not +obeyed when pcre_exec() is called with options that are incompatible for +JIT execution. A callback function can therefore be used to determine whether a +match operation was executed by JIT or by the interpreter. + +
+You may safely use the same JIT stack for more than one pattern (either by +assigning directly or by callback), as long as the patterns are all matched +sequentially in the same thread. In a multithread application, if you do not +specify a JIT stack, or if you assign or pass back NULL from a callback, that +is thread-safe, because each thread has its own machine stack. However, if you +assign or pass back a non-NULL JIT stack, this must be a different stack for +each thread so that the application is thread-safe. +
++Strictly speaking, even more is allowed. You can assign the same non-NULL stack +to any number of patterns as long as they are not used for matching by multiple +threads at the same time. For example, you can assign the same stack to all +compiled patterns, and use a global mutex in the callback to wait until the +stack is available for use. However, this is an inefficient solution, and not +recommended. +
++This is a suggestion for how a multithreaded program that needs to set up +non-default JIT stacks might operate: +
+ During thread initalization + thread_local_var = pcre_jit_stack_alloc(...) + + During thread exit + pcre_jit_stack_free(thread_local_var) + + Use a one-line callback function + return thread_local_var ++All the functions described in this section do nothing if JIT is not available, +and pcre_assign_jit_stack() does nothing unless the extra argument +is non-NULL and points to a pcre_extra block that is the result of a +successful study with PCRE_STUDY_JIT_COMPILE etc. + +
+(1) Why do we need JIT stacks?
+
+
+PCRE (and JIT) is a recursive, depth-first engine, so it needs a stack where
+the local data of the current node is pushed before checking its child nodes.
+Allocating real machine stack on some platforms is difficult. For example, the
+stack chain needs to be updated every time if we extend the stack on PowerPC.
+Although it is possible, its updating time overhead decreases performance. So
+we do the recursion in memory.
+
+(2) Why don't we simply allocate blocks of memory with malloc()?
+
+
+Modern operating systems have a nice feature: they can reserve an address space
+instead of allocating memory. We can safely allocate memory pages inside this
+address space, so the stack could grow without moving memory data (this is
+important because of pointers). Thus we can allocate 1M address space, and use
+only a single memory page (usually 4K) if that is enough. However, we can still
+grow up to 1M anytime if needed.
+
+(3) Who "owns" a JIT stack?
+
+
+The owner of the stack is the user program, not the JIT studied pattern or
+anything else. The user program must ensure that if a stack is used by
+pcre_exec(), (that is, it is assigned to the pattern currently running),
+that stack must not be used by any other threads (to avoid overwriting the same
+memory area). The best practice for multithreaded programs is to allocate a
+stack for each thread, and return this stack through the JIT callback function.
+
+(4) When should a JIT stack be freed?
+
+
+You can free a JIT stack at any time, as long as it will not be used by
+pcre_exec() again. When you assign the stack to a pattern, only a pointer
+is set. There is no reference counting or any other magic. You can free the
+patterns and stacks in any order, anytime. Just do not call
+pcre_exec() with a pattern pointing to an already freed stack, as that
+will cause SEGFAULT. (Also, do not free a stack currently used by
+pcre_exec() in another thread). You can also replace the stack for a
+pattern at any time. You can even free the previous stack before assigning a
+replacement.
+
+(5) Should I allocate/free a stack every time before/after calling
+pcre_exec()?
+
+
+No, because this is too costly in terms of resources. However, you could
+implement some clever idea which release the stack if it is not used in let's
+say two minutes. The JIT callback can help to achieve this without keeping a
+list of the currently JIT studied patterns.
+
+(6) OK, the stack is for long term memory allocation. But what happens if a
+pattern causes stack overflow with a stack of 1M? Is that 1M kept until the
+stack is freed?
+
+
+Especially on embedded sytems, it might be a good idea to release memory
+sometimes without freeing the stack. There is no API for this at the moment.
+Probably a function call which returns with the currently allocated memory for
+any stack and another which allows releasing memory (shrinking the stack) would
+be a good idea if someone needs this.
+
+(7) This is too much of a headache. Isn't there any better solution for JIT
+stack handling?
+
+
+No, thanks to Windows. If POSIX threads were used everywhere, we could throw
+out this complicated API.
+
+This is a single-threaded example that specifies a JIT stack without using a +callback. +
+ int rc; + int ovector[30]; + pcre *re; + pcre_extra *extra; + pcre_jit_stack *jit_stack; + + re = pcre_compile(pattern, 0, &error, &erroffset, NULL); + /* Check for errors */ + extra = pcre_study(re, PCRE_STUDY_JIT_COMPILE, &error); + jit_stack = pcre_jit_stack_alloc(32*1024, 512*1024); + /* Check for error (NULL) */ + pcre_assign_jit_stack(extra, NULL, jit_stack); + rc = pcre_exec(re, extra, subject, length, 0, 0, ovector, 30); + /* Check results */ + pcre_free(re); + pcre_free_study(extra); + pcre_jit_stack_free(jit_stack); + ++ +
+Because the API described above falls back to interpreted execution when JIT is +not available, it is convenient for programs that are written for general use +in many environments. However, calling JIT via pcre_exec() does have a +performance impact. Programs that are written for use where JIT is known to be +available, and which need the best possible performance, can instead use a +"fast path" API to call JIT execution directly instead of calling +pcre_exec() (obviously only for patterns that have been successfully +studied by JIT). +
++The fast path function is called pcre_jit_exec(), and it takes exactly +the same arguments as pcre_exec(), plus one additional argument that +must point to a JIT stack. The JIT stack arrangements described above do not +apply. The return values are the same as for pcre_exec(). +
++When you call pcre_exec(), as well as testing for invalid options, a +number of other sanity checks are performed on the arguments. For example, if +the subject pointer is NULL, or its length is negative, an immediate error is +given. Also, unless PCRE_NO_UTF[8|16|32] is set, a UTF subject string is tested +for validity. In the interests of speed, these checks do not happen on the JIT +fast path, and if invalid data is passed, the result is undefined. +
++Bypassing the sanity checks and the pcre_exec() wrapping can give +speedups of more than 10%. +
++pcreapi(3) +
+
+Philip Hazel (FAQ by Zoltan Herczeg)
+
+University Computing Service
+
+Cambridge CB2 3QH, England.
+
+
+Last updated: 31 October 2012
+
+Copyright © 1997-2012 University of Cambridge.
+
+
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcrelimits.html b/tools/pcre/doc/html/pcrelimits.html new file mode 100644 index 00000000..b83a8010 --- /dev/null +++ b/tools/pcre/doc/html/pcrelimits.html @@ -0,0 +1,86 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+SIZE AND OTHER LIMITATIONS
+
+
+There are some size limitations in PCRE but it is hoped that they will never in +practice be relevant. +
++The maximum length of a compiled pattern is approximately 64K data units (bytes +for the 8-bit library, 32-bit units for the 32-bit library, and 32-bit units for +the 32-bit library) if PCRE is compiled with the default internal linkage size +of 2 bytes. If you want to process regular expressions that are truly enormous, +you can compile PCRE with an internal linkage size of 3 or 4 (when building the +16-bit or 32-bit library, 3 is rounded up to 4). See the README file in +the source distribution and the +pcrebuild +documentation for details. In these cases the limit is substantially larger. +However, the speed of execution is slower. +
++All values in repeating quantifiers must be less than 65536. +
++There is no limit to the number of parenthesized subpatterns, but there can be +no more than 65535 capturing subpatterns. +
++There is a limit to the number of forward references to subsequent subpatterns +of around 200,000. Repeated forward references with fixed upper limits, for +example, (?2){0,100} when subpattern number 2 is to the right, are included in +the count. There is no limit to the number of backward references. +
++The maximum length of name for a named subpattern is 32 characters, and the +maximum number of named subpatterns is 10000. +
++The maximum length of a name in a (*MARK), (*PRUNE), (*SKIP), or (*THEN) verb +is 255 for the 8-bit library and 65535 for the 16-bit and 32-bit library. +
++The maximum length of a subject string is the largest positive number that an +integer variable can hold. However, when using the traditional matching +function, PCRE uses recursion to handle subpatterns and indefinite repetition. +This means that the available stack space may limit the size of a subject +string that can be processed by certain patterns. For a discussion of stack +issues, see the +pcrestack +documentation. +
+
+Philip Hazel
+
+University Computing Service
+
+Cambridge CB2 3QH, England.
+
+
+Last updated: 04 May 2012
+
+Copyright © 1997-2012 University of Cambridge.
+
+
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcrematching.html b/tools/pcre/doc/html/pcrematching.html new file mode 100644 index 00000000..f1854314 --- /dev/null +++ b/tools/pcre/doc/html/pcrematching.html @@ -0,0 +1,233 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+This document describes the two different algorithms that are available in PCRE +for matching a compiled regular expression against a given subject string. The +"standard" algorithm is the one provided by the pcre_exec(), +pcre16_exec() and pcre32_exec() functions. These work in the same +as as Perl's matching function, and provide a Perl-compatible matching operation. +The just-in-time (JIT) optimization that is described in the +pcrejit +documentation is compatible with these functions. +
++An alternative algorithm is provided by the pcre_dfa_exec(), +pcre16_dfa_exec() and pcre32_dfa_exec() functions; they operate in +a different way, and are not Perl-compatible. This alternative has advantages +and disadvantages compared with the standard algorithm, and these are described +below. +
++When there is only one possible way in which a given subject string can match a +pattern, the two algorithms give the same answer. A difference arises, however, +when there are multiple possibilities. For example, if the pattern +
+ ^<.*> ++is matched against the string +
+ <something> <something else> <something further> ++there are three possible answers. The standard algorithm finds only one of +them, whereas the alternative algorithm finds all three. + +
+The set of strings that are matched by a regular expression can be represented +as a tree structure. An unlimited repetition in the pattern makes the tree of +infinite size, but it is still a tree. Matching the pattern to a given subject +string (from a given starting point) can be thought of as a search of the tree. +There are two ways to search a tree: depth-first and breadth-first, and these +correspond to the two matching algorithms provided by PCRE. +
++In the terminology of Jeffrey Friedl's book "Mastering Regular +Expressions", the standard algorithm is an "NFA algorithm". It conducts a +depth-first search of the pattern tree. That is, it proceeds along a single +path through the tree, checking that the subject matches what is required. When +there is a mismatch, the algorithm tries any alternatives at the current point, +and if they all fail, it backs up to the previous branch point in the tree, and +tries the next alternative branch at that level. This often involves backing up +(moving to the left) in the subject string as well. The order in which +repetition branches are tried is controlled by the greedy or ungreedy nature of +the quantifier. +
++If a leaf node is reached, a matching string has been found, and at that point +the algorithm stops. Thus, if there is more than one possible match, this +algorithm returns the first one that it finds. Whether this is the shortest, +the longest, or some intermediate length depends on the way the greedy and +ungreedy repetition quantifiers are specified in the pattern. +
++Because it ends up with a single path through the tree, it is relatively +straightforward for this algorithm to keep track of the substrings that are +matched by portions of the pattern in parentheses. This provides support for +capturing parentheses and back references. +
++This algorithm conducts a breadth-first search of the tree. Starting from the +first matching point in the subject, it scans the subject string from left to +right, once, character by character, and as it does this, it remembers all the +paths through the tree that represent valid matches. In Friedl's terminology, +this is a kind of "DFA algorithm", though it is not implemented as a +traditional finite state machine (it keeps multiple states active +simultaneously). +
++Although the general principle of this matching algorithm is that it scans the +subject string only once, without backtracking, there is one exception: when a +lookaround assertion is encountered, the characters following or preceding the +current point have to be independently inspected. +
++The scan continues until either the end of the subject is reached, or there are +no more unterminated paths. At this point, terminated paths represent the +different matching possibilities (if there are none, the match has failed). +Thus, if there is more than one possible match, this algorithm finds all of +them, and in particular, it finds the longest. The matches are returned in +decreasing order of length. There is an option to stop the algorithm after the +first match (which is necessarily the shortest) is found. +
++Note that all the matches that are found start at the same point in the +subject. If the pattern +
+ cat(er(pillar)?)? ++is matched against the string "the caterpillar catchment", the result will be +the three strings "caterpillar", "cater", and "cat" that start at the fifth +character of the subject. The algorithm does not automatically move on to find +matches that start at later positions. + +
+There are a number of features of PCRE regular expressions that are not +supported by the alternative matching algorithm. They are as follows: +
++1. Because the algorithm finds all possible matches, the greedy or ungreedy +nature of repetition quantifiers is not relevant. Greedy and ungreedy +quantifiers are treated in exactly the same way. However, possessive +quantifiers can make a difference when what follows could also match what is +quantified, for example in a pattern like this: +
+ ^a++\w! ++This pattern matches "aaab!" but not "aaa!", which would be matched by a +non-possessive quantifier. Similarly, if an atomic group is present, it is +matched as if it were a standalone pattern at the current point, and the +longest match is then "locked in" for the rest of the overall pattern. + +
+2. When dealing with multiple paths through the tree simultaneously, it is not +straightforward to keep track of captured substrings for the different matching +possibilities, and PCRE's implementation of this algorithm does not attempt to +do this. This means that no captured substrings are available. +
++3. Because no substrings are captured, back references within the pattern are +not supported, and cause errors if encountered. +
++4. For the same reason, conditional expressions that use a backreference as the +condition or test for a specific group recursion are not supported. +
++5. Because many paths through the tree may be active, the \K escape sequence, +which resets the start of the match when encountered (but may be on some paths +and not on others), is not supported. It causes an error if encountered. +
++6. Callouts are supported, but the value of the capture_top field is +always 1, and the value of the capture_last field is always -1. +
++7. The \C escape sequence, which (in the standard algorithm) always matches a +single data unit, even in UTF-8, UTF-16 or UTF-32 modes, is not supported in +these modes, because the alternative algorithm moves through the subject string +one character (not data unit) at a time, for all active paths through the tree. +
++8. Except for (*FAIL), the backtracking control verbs such as (*PRUNE) are not +supported. (*FAIL) is supported, and behaves like a failing negative assertion. +
++Using the alternative matching algorithm provides the following advantages: +
++1. All possible matches (at a single point in the subject) are automatically +found, and in particular, the longest match is found. To find more than one +match using the standard algorithm, you have to do kludgy things with +callouts. +
++2. Because the alternative algorithm scans the subject string just once, and +never needs to backtrack (except for lookbehinds), it is possible to pass very +long subject strings to the matching function in several pieces, checking for +partial matching each time. Although it is possible to do multi-segment +matching using the standard algorithm by retaining partially matched +substrings, it is more complicated. The +pcrepartial +documentation gives details of partial matching and discusses multi-segment +matching. +
++The alternative algorithm suffers from a number of disadvantages: +
++1. It is substantially slower than the standard algorithm. This is partly +because it has to search for all possible matches, but is also because it is +less susceptible to optimization. +
++2. Capturing parentheses and back references are not supported. +
++3. Although atomic groups are supported, their use does not provide the +performance advantage that it does for the standard algorithm. +
+
+Philip Hazel
+
+University Computing Service
+
+Cambridge CB2 3QH, England.
+
+
+Last updated: 08 January 2012
+
+Copyright © 1997-2012 University of Cambridge.
+
+
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcrepartial.html b/tools/pcre/doc/html/pcrepartial.html new file mode 100644 index 00000000..298f92e0 --- /dev/null +++ b/tools/pcre/doc/html/pcrepartial.html @@ -0,0 +1,474 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+In normal use of PCRE, if the subject string that is passed to a matching +function matches as far as it goes, but is too short to match the entire +pattern, PCRE_ERROR_NOMATCH is returned. There are circumstances where it might +be helpful to distinguish this case from other cases in which there is no +match. +
++Consider, for example, an application where a human is required to type in data +for a field with specific formatting requirements. An example might be a date +in the form ddmmmyy, defined by this pattern: +
+ ^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$ ++If the application sees the user's keystrokes one by one, and can check that +what has been typed so far is potentially valid, it is able to raise an error +as soon as a mistake is made, by beeping and not reflecting the character that +has been typed, for example. This immediate feedback is likely to be a better +user interface than a check that is delayed until the entire string has been +entered. Partial matching can also be useful when the subject string is very +long and is not all available at once. + +
+PCRE supports partial matching by means of the PCRE_PARTIAL_SOFT and +PCRE_PARTIAL_HARD options, which can be set when calling any of the matching +functions. For backwards compatibility, PCRE_PARTIAL is a synonym for +PCRE_PARTIAL_SOFT. The essential difference between the two options is whether +or not a partial match is preferred to an alternative complete match, though +the details differ between the two types of matching function. If both options +are set, PCRE_PARTIAL_HARD takes precedence. +
++If you want to use partial matching with just-in-time optimized code, you must +call pcre_study(), pcre16_study() or pcre32_study() with one +or both of these options: +
+ PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE + PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE ++PCRE_STUDY_JIT_COMPILE should also be set if you are going to run non-partial +matches on the same pattern. If the appropriate JIT study mode has not been set +for a match, the interpretive matching code is used. + +
+Setting a partial matching option disables two of PCRE's standard +optimizations. PCRE remembers the last literal data unit in a pattern, and +abandons matching immediately if it is not present in the subject string. This +optimization cannot be used for a subject string that might match only +partially. If the pattern was studied, PCRE knows the minimum length of a +matching string, and does not bother to run the matching function on shorter +strings. This optimization is also disabled for partial matching. +
++A partial match occurs during a call to pcre_exec() or +pcre[16|32]_exec() when the end of the subject string is reached successfully, +but matching cannot continue because more characters are needed. However, at +least one character in the subject must have been inspected. This character +need not form part of the final matched string; lookbehind assertions and the +\K escape sequence provide ways of inspecting characters before the start of a +matched substring. The requirement for inspecting at least one character exists +because an empty string can always be matched; without such a restriction there +would always be a partial match of an empty string at the end of the subject. +
++If there are at least two slots in the offsets vector when a partial match is +returned, the first slot is set to the offset of the earliest character that +was inspected. For convenience, the second offset points to the end of the +subject so that a substring can easily be identified. +
++For the majority of patterns, the first offset identifies the start of the +partially matched string. However, for patterns that contain lookbehind +assertions, or \K, or begin with \b or \B, earlier characters have been +inspected while carrying out the match. For example: +
+ /(?<=abc)123/ ++This pattern matches "123", but only if it is preceded by "abc". If the subject +string is "xyzabc12", the offsets after a partial match are for the substring +"abc12", because all these characters are needed if another match is tried +with extra characters added to the subject. + +
+What happens when a partial match is identified depends on which of the two +partial matching options are set. +
++If PCRE_PARTIAL_SOFT is set when pcre_exec() or pcre[16|32]_exec() +identifies a partial match, the partial match is remembered, but matching +continues as normal, and other alternatives in the pattern are tried. If no +complete match can be found, PCRE_ERROR_PARTIAL is returned instead of +PCRE_ERROR_NOMATCH. +
++This option is "soft" because it prefers a complete match over a partial match. +All the various matching items in a pattern behave as if the subject string is +potentially complete. For example, \z, \Z, and $ match at the end of the +subject, as normal, and for \b and \B the end of the subject is treated as a +non-alphanumeric. +
++If there is more than one partial match, the first one that was found provides +the data that is returned. Consider this pattern: +
+ /123\w+X|dogY/ ++If this is matched against the subject string "abc123dog", both +alternatives fail to match, but the end of the subject is reached during +matching, so PCRE_ERROR_PARTIAL is returned. The offsets are set to 3 and 9, +identifying "123dog" as the first partial match that was found. (In this +example, there are two partial matches, because "dog" on its own partially +matches the second alternative.) + +
+If PCRE_PARTIAL_HARD is set for pcre_exec() or pcre[16|32]_exec(), +PCRE_ERROR_PARTIAL is returned as soon as a partial match is found, without +continuing to search for possible complete matches. This option is "hard" +because it prefers an earlier partial match over a later complete match. For +this reason, the assumption is made that the end of the supplied subject string +may not be the true end of the available data, and so, if \z, \Z, \b, \B, +or $ are encountered at the end of the subject, the result is +PCRE_ERROR_PARTIAL, provided that at least one character in the subject has +been inspected. +
++Setting PCRE_PARTIAL_HARD also affects the way UTF-8 and UTF-16 +subject strings are checked for validity. Normally, an invalid sequence +causes the error PCRE_ERROR_BADUTF8 or PCRE_ERROR_BADUTF16. However, in the +special case of a truncated character at the end of the subject, +PCRE_ERROR_SHORTUTF8 or PCRE_ERROR_SHORTUTF16 is returned when +PCRE_PARTIAL_HARD is set. +
++The difference between the two partial matching options can be illustrated by a +pattern such as: +
+ /dog(sbody)?/ ++This matches either "dog" or "dogsbody", greedily (that is, it prefers the +longer string if possible). If it is matched against the string "dog" with +PCRE_PARTIAL_SOFT, it yields a complete match for "dog". However, if +PCRE_PARTIAL_HARD is set, the result is PCRE_ERROR_PARTIAL. On the other hand, +if the pattern is made ungreedy the result is different: +
+ /dog(sbody)??/ ++In this case the result is always a complete match because that is found first, +and matching never continues after finding a complete match. It might be easier +to follow this explanation by thinking of the two patterns like this: +
+ /dog(sbody)?/ is the same as /dogsbody|dog/ + /dog(sbody)??/ is the same as /dog|dogsbody/ ++The second pattern will never match "dogsbody", because it will always find the +shorter match first. + +
+The DFA functions move along the subject string character by character, without +backtracking, searching for all possible matches simultaneously. If the end of +the subject is reached before the end of the pattern, there is the possibility +of a partial match, again provided that at least one character has been +inspected. +
++When PCRE_PARTIAL_SOFT is set, PCRE_ERROR_PARTIAL is returned only if there +have been no complete matches. Otherwise, the complete matches are returned. +However, if PCRE_PARTIAL_HARD is set, a partial match takes precedence over any +complete matches. The portion of the string that was inspected when the longest +partial match was found is set as the first matching string, provided there are +at least two slots in the offsets vector. +
++Because the DFA functions always search for all possible matches, and there is +no difference between greedy and ungreedy repetition, their behaviour is +different from the standard functions when PCRE_PARTIAL_HARD is set. Consider +the string "dog" matched against the ungreedy pattern shown above: +
+ /dog(sbody)??/ ++Whereas the standard functions stop as soon as they find the complete match for +"dog", the DFA functions also find the partial match for "dogsbody", and so +return that when PCRE_PARTIAL_HARD is set. + +
+If a pattern ends with one of sequences \b or \B, which test for word +boundaries, partial matching with PCRE_PARTIAL_SOFT can give counter-intuitive +results. Consider this pattern: +
+ /\bcat\b/ ++This matches "cat", provided there is a word boundary at either end. If the +subject string is "the cat", the comparison of the final "t" with a following +character cannot take place, so a partial match is found. However, normal +matching carries on, and \b matches at the end of the subject when the last +character is a letter, so a complete match is found. The result, therefore, is +not PCRE_ERROR_PARTIAL. Using PCRE_PARTIAL_HARD in this case does yield +PCRE_ERROR_PARTIAL, because then the partial match takes precedence. + +
+For releases of PCRE prior to 8.00, because of the way certain internal +optimizations were implemented in the pcre_exec() function, the +PCRE_PARTIAL option (predecessor of PCRE_PARTIAL_SOFT) could not be used with +all patterns. From release 8.00 onwards, the restrictions no longer apply, and +partial matching with can be requested for any pattern. +
++Items that were formerly restricted were repeated single characters and +repeated metasequences. If PCRE_PARTIAL was set for a pattern that did not +conform to the restrictions, pcre_exec() returned the error code +PCRE_ERROR_BADPARTIAL (-13). This error code is no longer in use. The +PCRE_INFO_OKPARTIAL call to pcre_fullinfo() to find out if a compiled +pattern can be used for partial matching now always returns 1. +
++If the escape sequence \P is present in a pcretest data line, the +PCRE_PARTIAL_SOFT option is used for the match. Here is a run of pcretest +that uses the date example quoted above: +
+ re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/ + data> 25jun04\P + 0: 25jun04 + 1: jun + data> 25dec3\P + Partial match: 23dec3 + data> 3ju\P + Partial match: 3ju + data> 3juj\P + No match + data> j\P + No match ++The first data string is matched completely, so pcretest shows the +matched substrings. The remaining four strings do not match the complete +pattern, but the first two are partial matches. Similar output is obtained +if DFA matching is used. + +
+If the escape sequence \P is present more than once in a pcretest data +line, the PCRE_PARTIAL_HARD option is set for the match. +
++When a partial match has been found using a DFA matching function, it is +possible to continue the match by providing additional subject data and calling +the function again with the same compiled regular expression, this time setting +the PCRE_DFA_RESTART option. You must pass the same working space as before, +because this is where details of the previous partial match are stored. Here is +an example using pcretest, using the \R escape sequence to set the +PCRE_DFA_RESTART option (\D specifies the use of the DFA matching function): +
+ re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/ + data> 23ja\P\D + Partial match: 23ja + data> n05\R\D + 0: n05 ++The first call has "23ja" as the subject, and requests partial matching; the +second call has "n05" as the subject for the continued (restarted) match. +Notice that when the match is complete, only the last part is shown; PCRE does +not retain the previously partially-matched string. It is up to the calling +program to do that if it needs to. + +
+You can set the PCRE_PARTIAL_SOFT or PCRE_PARTIAL_HARD options with +PCRE_DFA_RESTART to continue partial matching over multiple segments. This +facility can be used to pass very long subject strings to the DFA matching +functions. +
++From release 8.00, the standard matching functions can also be used to do +multi-segment matching. Unlike the DFA functions, it is not possible to +restart the previous match with a new segment of data. Instead, new data must +be added to the previous subject string, and the entire match re-run, starting +from the point where the partial match occurred. Earlier data can be discarded. +
++It is best to use PCRE_PARTIAL_HARD in this situation, because it does not +treat the end of a segment as the end of the subject when matching \z, \Z, +\b, \B, and $. Consider an unanchored pattern that matches dates: +
+ re> /\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d/ + data> The date is 23ja\P\P + Partial match: 23ja ++At this stage, an application could discard the text preceding "23ja", add on +text from the next segment, and call the matching function again. Unlike the +DFA matching functions, the entire matching string must always be available, +and the complete matching process occurs for each call, so more memory and more +processing time is needed. + +
+Note: If the pattern contains lookbehind assertions, or \K, or starts +with \b or \B, the string that is returned for a partial match includes +characters that precede the partially matched string itself, because these must +be retained when adding on more characters for a subsequent matching attempt. +However, in some cases you may need to retain even earlier characters, as +discussed in the next section. +
++Certain types of pattern may give problems with multi-segment matching, +whichever matching function is used. +
++1. If the pattern contains a test for the beginning of a line, you need to pass +the PCRE_NOTBOL option when the subject string for any call does start at the +beginning of a line. There is also a PCRE_NOTEOL option, but in practice when +doing multi-segment matching you should be using PCRE_PARTIAL_HARD, which +includes the effect of PCRE_NOTEOL. +
++2. Lookbehind assertions that have already been obeyed are catered for in the +offsets that are returned for a partial match. However a lookbehind assertion +later in the pattern could require even earlier characters to be inspected. You +can handle this case by using the PCRE_INFO_MAXLOOKBEHIND option of the +pcre_fullinfo() or pcre[16|32]_fullinfo() functions to obtain the length +of the largest lookbehind in the pattern. This length is given in characters, +not bytes. If you always retain at least that many characters before the +partially matched string, all should be well. (Of course, near the start of the +subject, fewer characters may be present; in that case all characters should be +retained.) +
++3. Because a partial match must always contain at least one character, what +might be considered a partial match of an empty string actually gives a "no +match" result. For example: +
+ re> /c(?<=abc)x/ + data> ab\P + No match ++If the next segment begins "cx", a match should be found, but this will only +happen if characters from the previous segment are retained. For this reason, a +"no match" result should be interpreted as "partial match of an empty string" +when the pattern contains lookbehinds. + +
+4. Matching a subject string that is split into multiple segments may not +always produce exactly the same result as matching over one single long string, +especially when PCRE_PARTIAL_SOFT is used. The section "Partial Matching and +Word Boundaries" above describes an issue that arises if the pattern ends with +\b or \B. Another kind of difference may occur when there are multiple +matching possibilities, because (for PCRE_PARTIAL_SOFT) a partial match result +is given only when there are no completed matches. This means that as soon as +the shortest match has been found, continuation to a new subject segment is no +longer possible. Consider again this pcretest example: +
+ re> /dog(sbody)?/ + data> dogsb\P + 0: dog + data> do\P\D + Partial match: do + data> gsb\R\P\D + 0: g + data> dogsbody\D + 0: dogsbody + 1: dog ++The first data line passes the string "dogsb" to a standard matching function, +setting the PCRE_PARTIAL_SOFT option. Although the string is a partial match +for "dogsbody", the result is not PCRE_ERROR_PARTIAL, because the shorter +string "dog" is a complete match. Similarly, when the subject is presented to +a DFA matching function in several parts ("do" and "gsb" being the first two) +the match stops when "dog" has been found, and it is not possible to continue. +On the other hand, if "dogsbody" is presented as a single string, a DFA +matching function finds both matches. + +
+Because of these problems, it is best to use PCRE_PARTIAL_HARD when matching +multi-segment data. The example above then behaves differently: +
+ re> /dog(sbody)?/ + data> dogsb\P\P + Partial match: dogsb + data> do\P\D + Partial match: do + data> gsb\R\P\P\D + Partial match: gsb ++5. Patterns that contain alternatives at the top level which do not all start +with the same pattern item may not work as expected when PCRE_DFA_RESTART is +used. For example, consider this pattern: +
+ 1234|3789 ++If the first part of the subject is "ABC123", a partial match of the first +alternative is found at offset 3. There is no partial match for the second +alternative, because such a match does not start at the same point in the +subject string. Attempting to continue with the string "7890" does not yield a +match because only those alternatives that match at one point in the subject +are remembered. The problem arises because the start of the second alternative +matches within the first alternative. There is no problem with anchored +patterns or patterns such as: +
+ 1234|ABCD ++where no string can be a partial match for both alternatives. This is not a +problem if a standard matching function is used, because the entire match has +to be rerun each time: +
+ re> /1234|3789/ + data> ABC123\P\P + Partial match: 123 + data> 1237890 + 0: 3789 ++Of course, instead of using PCRE_DFA_RESTART, the same technique of re-running +the entire match can also be used with the DFA matching functions. Another +possibility is to work with two buffers. If a partial match at offset n +in the first buffer is followed by "no match" when PCRE_DFA_RESTART is used on +the second buffer, you can then try a new match starting at offset n+1 in +the first buffer. + +
+Philip Hazel
+
+University Computing Service
+
+Cambridge CB2 3QH, England.
+
+
+Last updated: 24 June 2012
+
+Copyright © 1997-2012 University of Cambridge.
+
+
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcrepattern.html b/tools/pcre/doc/html/pcrepattern.html new file mode 100644 index 00000000..ee55d06e --- /dev/null +++ b/tools/pcre/doc/html/pcrepattern.html @@ -0,0 +1,2953 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+The syntax and semantics of the regular expressions that are supported by PCRE +are described in detail below. There is a quick-reference syntax summary in the +pcresyntax +page. PCRE tries to match Perl syntax and semantics as closely as it can. PCRE +also supports some alternative regular expression syntax (which does not +conflict with the Perl syntax) in order to provide some compatibility with +regular expressions in Python, .NET, and Oniguruma. +
++Perl's regular expressions are described in its own documentation, and +regular expressions in general are covered in a number of books, some of which +have copious examples. Jeffrey Friedl's "Mastering Regular Expressions", +published by O'Reilly, covers regular expressions in great detail. This +description of PCRE's regular expressions is intended as reference material. +
++The original operation of PCRE was on strings of one-byte characters. However, +there is now also support for UTF-8 strings in the original library, an +extra library that supports 16-bit and UTF-16 character strings, and a +third library that supports 32-bit and UTF-32 character strings. To use these +features, PCRE must be built to include appropriate support. When using UTF +strings you must either call the compiling function with the PCRE_UTF8, +PCRE_UTF16, or PCRE_UTF32 option, or the pattern must start with one of +these special sequences: +
+ (*UTF8) + (*UTF16) + (*UTF32) + (*UTF) ++(*UTF) is a generic sequence that can be used with any of the libraries. +Starting a pattern with such a sequence is equivalent to setting the relevant +option. This feature is not Perl-compatible. How setting a UTF mode affects +pattern matching is mentioned in several places below. There is also a summary +of features in the +pcreunicode +page. + +
+Another special sequence that may appear at the start of a pattern or in +combination with (*UTF8), (*UTF16), (*UTF32) or (*UTF) is: +
+ (*UCP) ++This has the same effect as setting the PCRE_UCP option: it causes sequences +such as \d and \w to use Unicode properties to determine character types, +instead of recognizing only characters with codes less than 128 via a lookup +table. + +
+If a pattern starts with (*NO_START_OPT), it has the same effect as setting the +PCRE_NO_START_OPTIMIZE option either at compile or matching time. There are +also some more of these special sequences that are concerned with the handling +of newlines; they are described below. +
++The remainder of this document discusses the patterns that are supported by +PCRE when one its main matching functions, pcre_exec() (8-bit) or +pcre[16|32]_exec() (16- or 32-bit), is used. PCRE also has alternative +matching functions, pcre_dfa_exec() and pcre[16|32_dfa_exec(), +which match using a different algorithm that is not Perl-compatible. Some of +the features discussed below are not available when DFA matching is used. The +advantages and disadvantages of the alternative functions, and how they differ +from the normal functions, are discussed in the +pcrematching +page. +
++PCRE can be compiled to run in an environment that uses EBCDIC as its character +code rather than ASCII or Unicode (typically a mainframe system). In the +sections below, character code values are ASCII or Unicode; in an EBCDIC +environment these characters may have different code values, and there are no +code points greater than 255. +
++PCRE supports five different conventions for indicating line breaks in +strings: a single CR (carriage return) character, a single LF (linefeed) +character, the two-character sequence CRLF, any of the three preceding, or any +Unicode newline sequence. The +pcreapi +page has +further discussion +about newlines, and shows how to set the newline convention in the +options arguments for the compiling and matching functions. +
++It is also possible to specify a newline convention by starting a pattern +string with one of the following five sequences: +
+ (*CR) carriage return + (*LF) linefeed + (*CRLF) carriage return, followed by linefeed + (*ANYCRLF) any of the three above + (*ANY) all Unicode newline sequences ++These override the default and the options given to the compiling function. For +example, on a Unix system where LF is the default newline sequence, the pattern +
+ (*CR)a.b ++changes the convention to CR. That pattern matches "a\nb" because LF is no +longer a newline. Note that these special settings, which are not +Perl-compatible, are recognized only at the very start of a pattern, and that +they must be in upper case. If more than one of them is present, the last one +is used. + +
+The newline convention affects where the circumflex and dollar assertions are +true. It also affects the interpretation of the dot metacharacter when +PCRE_DOTALL is not set, and the behaviour of \N. However, it does not affect +what the \R escape sequence matches. By default, this is any Unicode newline +sequence, for Perl compatibility. However, this can be changed; see the +description of \R in the section entitled +"Newline sequences" +below. A change of \R setting can be combined with a change of newline +convention. +
++A regular expression is a pattern that is matched against a subject string from +left to right. Most characters stand for themselves in a pattern, and match the +corresponding characters in the subject. As a trivial example, the pattern +
+ The quick brown fox ++matches a portion of a subject string that is identical to itself. When +caseless matching is specified (the PCRE_CASELESS option), letters are matched +independently of case. In a UTF mode, PCRE always understands the concept of +case for characters whose values are less than 128, so caseless matching is +always possible. For characters with higher values, the concept of case is +supported if PCRE is compiled with Unicode property support, but not otherwise. +If you want to use caseless matching for characters 128 and above, you must +ensure that PCRE is compiled with Unicode property support as well as with +UTF support. + +
+The power of regular expressions comes from the ability to include alternatives +and repetitions in the pattern. These are encoded in the pattern by the use of +metacharacters, which do not stand for themselves but instead are +interpreted in some special way. +
++There are two different sets of metacharacters: those that are recognized +anywhere in the pattern except within square brackets, and those that are +recognized within square brackets. Outside square brackets, the metacharacters +are as follows: +
+ \ general escape character with several uses
+ ^ assert start of string (or line, in multiline mode)
+ $ assert end of string (or line, in multiline mode)
+ . match any character except newline (by default)
+ [ start character class definition
+ | start of alternative branch
+ ( start subpattern
+ ) end subpattern
+ ? extends the meaning of (
+ also 0 or 1 quantifier
+ also quantifier minimizer
+ * 0 or more quantifier
+ + 1 or more quantifier
+ also "possessive quantifier"
+ { start min/max quantifier
+
+Part of a pattern that is in square brackets is called a "character class". In
+a character class the only metacharacters are:
++ \ general escape character + ^ negate the class, but only if the first character + - indicates character range + [ POSIX character class (only if followed by POSIX syntax) + ] terminates the character class ++The following sections describe the use of each of the metacharacters. + +
+The backslash character has several uses. Firstly, if it is followed by a +character that is not a number or a letter, it takes away any special meaning +that character may have. This use of backslash as an escape character applies +both inside and outside character classes. +
++For example, if you want to match a * character, you write \* in the pattern. +This escaping action applies whether or not the following character would +otherwise be interpreted as a metacharacter, so it is always safe to precede a +non-alphanumeric with backslash to specify that it stands for itself. In +particular, if you want to match a backslash, you write \\. +
++In a UTF mode, only ASCII numbers and letters have any special meaning after a +backslash. All other characters (in particular, those whose codepoints are +greater than 127) are treated as literals. +
++If a pattern is compiled with the PCRE_EXTENDED option, white space in the +pattern (other than in a character class) and characters between a # outside +a character class and the next newline are ignored. An escaping backslash can +be used to include a white space or # character as part of the pattern. +
++If you want to remove the special meaning from a sequence of characters, you +can do so by putting them between \Q and \E. This is different from Perl in +that $ and @ are handled as literals in \Q...\E sequences in PCRE, whereas in +Perl, $ and @ cause variable interpolation. Note the following examples: +
+ Pattern PCRE matches Perl matches + + \Qabc$xyz\E abc$xyz abc followed by the contents of $xyz + \Qabc\$xyz\E abc\$xyz abc\$xyz + \Qabc\E\$\Qxyz\E abc$xyz abc$xyz ++The \Q...\E sequence is recognized both inside and outside character classes. +An isolated \E that is not preceded by \Q is ignored. If \Q is not followed +by \E later in the pattern, the literal interpretation continues to the end of +the pattern (that is, \E is assumed at the end). If the isolated \Q is inside +a character class, this causes an error, because the character class is not +terminated. + +
+A second use of backslash provides a way of encoding non-printing characters +in patterns in a visible manner. There is no restriction on the appearance of +non-printing characters, apart from the binary zero that terminates a pattern, +but when a pattern is being prepared by text editing, it is often easier to use +one of the following escape sequences than the binary character it represents: +
+ \a alarm, that is, the BEL character (hex 07)
+ \cx "control-x", where x is any ASCII character
+ \e escape (hex 1B)
+ \f form feed (hex 0C)
+ \n linefeed (hex 0A)
+ \r carriage return (hex 0D)
+ \t tab (hex 09)
+ \ddd character with octal code ddd, or back reference
+ \xhh character with hex code hh
+ \x{hhh..} character with hex code hhh.. (non-JavaScript mode)
+ \uhhhh character with hex code hhhh (JavaScript mode only)
+
+The precise effect of \cx on ASCII characters is as follows: if x is a lower
+case letter, it is converted to upper case. Then bit 6 of the character (hex
+40) is inverted. Thus \cA to \cZ become hex 01 to hex 1A (A is 41, Z is 5A),
+but \c{ becomes hex 3B ({ is 7B), and \c; becomes hex 7B (; is 3B). If the
+data item (byte or 16-bit value) following \c has a value greater than 127, a
+compile-time error occurs. This locks out non-ASCII characters in all modes.
+
++The \c facility was designed for use with ASCII characters, but with the +extension to Unicode it is even less useful than it once was. It is, however, +recognized when PCRE is compiled in EBCDIC mode, where data items are always +bytes. In this mode, all values are valid after \c. If the next character is a +lower case letter, it is converted to upper case. Then the 0xc0 bits of the +byte are inverted. Thus \cA becomes hex 01, as in ASCII (A is C1), but because +the EBCDIC letters are disjoint, \cZ becomes hex 29 (Z is E9), and other +characters also generate different values. +
++By default, after \x, from zero to two hexadecimal digits are read (letters +can be in upper or lower case). Any number of hexadecimal digits may appear +between \x{ and }, but the character code is constrained as follows: +
+ 8-bit non-UTF mode less than 0x100 + 8-bit UTF-8 mode less than 0x10ffff and a valid codepoint + 16-bit non-UTF mode less than 0x10000 + 16-bit UTF-16 mode less than 0x10ffff and a valid codepoint + 32-bit non-UTF mode less than 0x80000000 + 32-bit UTF-32 mode less than 0x10ffff and a valid codepoint ++Invalid Unicode codepoints are the range 0xd800 to 0xdfff (the so-called +"surrogate" codepoints), and 0xffef. + +
+If characters other than hexadecimal digits appear between \x{ and }, or if +there is no terminating }, this form of escape is not recognized. Instead, the +initial \x will be interpreted as a basic hexadecimal escape, with no +following digits, giving a character whose value is zero. +
++If the PCRE_JAVASCRIPT_COMPAT option is set, the interpretation of \x is +as just described only when it is followed by two hexadecimal digits. +Otherwise, it matches a literal "x" character. In JavaScript mode, support for +code points greater than 256 is provided by \u, which must be followed by +four hexadecimal digits; otherwise it matches a literal "u" character. +Character codes specified by \u in JavaScript mode are constrained in the same +was as those specified by \x in non-JavaScript mode. +
++Characters whose value is less than 256 can be defined by either of the two +syntaxes for \x (or by \u in JavaScript mode). There is no difference in the +way they are handled. For example, \xdc is exactly the same as \x{dc} (or +\u00dc in JavaScript mode). +
++After \0 up to two further octal digits are read. If there are fewer than two +digits, just those that are present are used. Thus the sequence \0\x\07 +specifies two binary zeros followed by a BEL character (code value 7). Make +sure you supply two digits after the initial zero if the pattern character that +follows is itself an octal digit. +
++The handling of a backslash followed by a digit other than 0 is complicated. +Outside a character class, PCRE reads it and any following digits as a decimal +number. If the number is less than 10, or if there have been at least that many +previous capturing left parentheses in the expression, the entire sequence is +taken as a back reference. A description of how this works is given +later, +following the discussion of +parenthesized subpatterns. +
++Inside a character class, or if the decimal number is greater than 9 and there +have not been that many capturing subpatterns, PCRE re-reads up to three octal +digits following the backslash, and uses them to generate a data character. Any +subsequent digits stand for themselves. The value of the character is +constrained in the same way as characters specified in hexadecimal. +For example: +
+ \040 is another way of writing an ASCII space + \40 is the same, provided there are fewer than 40 previous capturing subpatterns + \7 is always a back reference + \11 might be a back reference, or another way of writing a tab + \011 is always a tab + \0113 is a tab followed by the character "3" + \113 might be a back reference, otherwise the character with octal code 113 + \377 might be a back reference, otherwise the value 255 (decimal) + \81 is either a back reference, or a binary zero followed by the two characters "8" and "1" ++Note that octal values of 100 or greater must not be introduced by a leading +zero, because no more than three octal digits are ever read. + +
+All the sequences that define a single character value can be used both inside +and outside character classes. In addition, inside a character class, \b is +interpreted as the backspace character (hex 08). +
++\N is not allowed in a character class. \B, \R, and \X are not special +inside a character class. Like other unrecognized escape sequences, they are +treated as the literal characters "B", "R", and "X" by default, but cause an +error if the PCRE_EXTRA option is set. Outside a character class, these +sequences have different meanings. +
++In Perl, the sequences \l, \L, \u, and \U are recognized by its string +handler and used to modify the case of following characters. By default, PCRE +does not support these escape sequences. However, if the PCRE_JAVASCRIPT_COMPAT +option is set, \U matches a "U" character, and \u can be used to define a +character by code point, as described in the previous section. +
++The sequence \g followed by an unsigned or a negative number, optionally +enclosed in braces, is an absolute or relative back reference. A named back +reference can be coded as \g{name}. Back references are discussed +later, +following the discussion of +parenthesized subpatterns. +
++For compatibility with Oniguruma, the non-Perl syntax \g followed by a name or +a number enclosed either in angle brackets or single quotes, is an alternative +syntax for referencing a subpattern as a "subroutine". Details are discussed +later. +Note that \g{...} (Perl syntax) and \g<...> (Oniguruma syntax) are not +synonymous. The former is a back reference; the latter is a +subroutine +call. +
++Another use of backslash is for specifying generic character types: +
+ \d any decimal digit + \D any character that is not a decimal digit + \h any horizontal white space character + \H any character that is not a horizontal white space character + \s any white space character + \S any character that is not a white space character + \v any vertical white space character + \V any character that is not a vertical white space character + \w any "word" character + \W any "non-word" character ++There is also the single sequence \N, which matches a non-newline character. +This is the same as +the "." metacharacter +when PCRE_DOTALL is not set. Perl also uses \N to match characters by name; +PCRE does not support this. + +
+Each pair of lower and upper case escape sequences partitions the complete set +of characters into two disjoint sets. Any given character matches one, and only +one, of each pair. The sequences can appear both inside and outside character +classes. They each match one character of the appropriate type. If the current +matching point is at the end of the subject string, all of them fail, because +there is no character to match. +
++For compatibility with Perl, \s does not match the VT character (code 11). +This makes it different from the the POSIX "space" class. The \s characters +are HT (9), LF (10), FF (12), CR (13), and space (32). If "use locale;" is +included in a Perl script, \s may match the VT character. In PCRE, it never +does. +
++A "word" character is an underscore or any character that is a letter or digit. +By default, the definition of letters and digits is controlled by PCRE's +low-valued character tables, and may vary if locale-specific matching is taking +place (see +"Locale support" +in the +pcreapi +page). For example, in a French locale such as "fr_FR" in Unix-like systems, +or "french" in Windows, some character codes greater than 128 are used for +accented letters, and these are then matched by \w. The use of locales with +Unicode is discouraged. +
++By default, in a UTF mode, characters with values greater than 128 never match +\d, \s, or \w, and always match \D, \S, and \W. These sequences retain +their original meanings from before UTF support was available, mainly for +efficiency reasons. However, if PCRE is compiled with Unicode property support, +and the PCRE_UCP option is set, the behaviour is changed so that Unicode +properties are used to determine character types, as follows: +
+ \d any character that \p{Nd} matches (decimal digit)
+ \s any character that \p{Z} matches, plus HT, LF, FF, CR
+ \w any character that \p{L} or \p{N} matches, plus underscore
+
+The upper case escapes match the inverse sets of characters. Note that \d
+matches only decimal digits, whereas \w matches any Unicode digit, as well as
+any Unicode letter, and underscore. Note also that PCRE_UCP affects \b, and
+\B because they are defined in terms of \w and \W. Matching these sequences
+is noticeably slower when PCRE_UCP is set.
+
++The sequences \h, \H, \v, and \V are features that were added to Perl at +release 5.10. In contrast to the other sequences, which match only ASCII +characters by default, these always match certain high-valued codepoints, +whether or not PCRE_UCP is set. The horizontal space characters are: +
+ U+0009 Horizontal tab (HT) + U+0020 Space + U+00A0 Non-break space + U+1680 Ogham space mark + U+180E Mongolian vowel separator + U+2000 En quad + U+2001 Em quad + U+2002 En space + U+2003 Em space + U+2004 Three-per-em space + U+2005 Four-per-em space + U+2006 Six-per-em space + U+2007 Figure space + U+2008 Punctuation space + U+2009 Thin space + U+200A Hair space + U+202F Narrow no-break space + U+205F Medium mathematical space + U+3000 Ideographic space ++The vertical space characters are: +
+ U+000A Linefeed (LF) + U+000B Vertical tab (VT) + U+000C Form feed (FF) + U+000D Carriage return (CR) + U+0085 Next line (NEL) + U+2028 Line separator + U+2029 Paragraph separator ++In 8-bit, non-UTF-8 mode, only the characters with codepoints less than 256 are +relevant. + +
+Outside a character class, by default, the escape sequence \R matches any +Unicode newline sequence. In 8-bit non-UTF-8 mode \R is equivalent to the +following: +
+ (?>\r\n|\n|\x0b|\f|\r|\x85) ++This is an example of an "atomic group", details of which are given +below. +This particular group matches either the two-character sequence CR followed by +LF, or one of the single characters LF (linefeed, U+000A), VT (vertical tab, +U+000B), FF (form feed, U+000C), CR (carriage return, U+000D), or NEL (next +line, U+0085). The two-character sequence is treated as a single unit that +cannot be split. + +
+In other modes, two additional characters whose codepoints are greater than 255 +are added: LS (line separator, U+2028) and PS (paragraph separator, U+2029). +Unicode character property support is not needed for these characters to be +recognized. +
++It is possible to restrict \R to match only CR, LF, or CRLF (instead of the +complete set of Unicode line endings) by setting the option PCRE_BSR_ANYCRLF +either at compile time or when the pattern is matched. (BSR is an abbrevation +for "backslash R".) This can be made the default when PCRE is built; if this is +the case, the other behaviour can be requested via the PCRE_BSR_UNICODE option. +It is also possible to specify these settings by starting a pattern string with +one of the following sequences: +
+ (*BSR_ANYCRLF) CR, LF, or CRLF only + (*BSR_UNICODE) any Unicode newline sequence ++These override the default and the options given to the compiling function, but +they can themselves be overridden by options given to a matching function. Note +that these special settings, which are not Perl-compatible, are recognized only +at the very start of a pattern, and that they must be in upper case. If more +than one of them is present, the last one is used. They can be combined with a +change of newline convention; for example, a pattern can start with: +
+ (*ANY)(*BSR_ANYCRLF) ++They can also be combined with the (*UTF8), (*UTF16), (*UTF32), (*UTF) or +(*UCP) special sequences. Inside a character class, \R is treated as an +unrecognized escape sequence, and so matches the letter "R" by default, but +causes an error if PCRE_EXTRA is set. + +
+When PCRE is built with Unicode character property support, three additional +escape sequences that match characters with specific properties are available. +When in 8-bit non-UTF-8 mode, these sequences are of course limited to testing +characters whose codepoints are less than 256, but they do work in this mode. +The extra escape sequences are: +
+ \p{xx} a character with the xx property
+ \P{xx} a character without the xx property
+ \X a Unicode extended grapheme cluster
+
+The property names represented by xx above are limited to the Unicode
+script names, the general category properties, "Any", which matches any
+character (including newline), and some special PCRE properties (described
+in the
+next section).
+Other Perl properties such as "InMusicalSymbols" are not currently supported by
+PCRE. Note that \P{Any} does not match any characters, so always causes a
+match failure.
+
++Sets of Unicode characters are defined as belonging to certain scripts. A +character from one of these sets can be matched using a script name. For +example: +
+ \p{Greek}
+ \P{Han}
+
+Those that are not part of an identified script are lumped together as
+"Common". The current list of scripts is:
+
++Arabic, +Armenian, +Avestan, +Balinese, +Bamum, +Batak, +Bengali, +Bopomofo, +Brahmi, +Braille, +Buginese, +Buhid, +Canadian_Aboriginal, +Carian, +Chakma, +Cham, +Cherokee, +Common, +Coptic, +Cuneiform, +Cypriot, +Cyrillic, +Deseret, +Devanagari, +Egyptian_Hieroglyphs, +Ethiopic, +Georgian, +Glagolitic, +Gothic, +Greek, +Gujarati, +Gurmukhi, +Han, +Hangul, +Hanunoo, +Hebrew, +Hiragana, +Imperial_Aramaic, +Inherited, +Inscriptional_Pahlavi, +Inscriptional_Parthian, +Javanese, +Kaithi, +Kannada, +Katakana, +Kayah_Li, +Kharoshthi, +Khmer, +Lao, +Latin, +Lepcha, +Limbu, +Linear_B, +Lisu, +Lycian, +Lydian, +Malayalam, +Mandaic, +Meetei_Mayek, +Meroitic_Cursive, +Meroitic_Hieroglyphs, +Miao, +Mongolian, +Myanmar, +New_Tai_Lue, +Nko, +Ogham, +Old_Italic, +Old_Persian, +Old_South_Arabian, +Old_Turkic, +Ol_Chiki, +Oriya, +Osmanya, +Phags_Pa, +Phoenician, +Rejang, +Runic, +Samaritan, +Saurashtra, +Sharada, +Shavian, +Sinhala, +Sora_Sompeng, +Sundanese, +Syloti_Nagri, +Syriac, +Tagalog, +Tagbanwa, +Tai_Le, +Tai_Tham, +Tai_Viet, +Takri, +Tamil, +Telugu, +Thaana, +Thai, +Tibetan, +Tifinagh, +Ugaritic, +Vai, +Yi. +
++Each character has exactly one Unicode general category property, specified by +a two-letter abbreviation. For compatibility with Perl, negation can be +specified by including a circumflex between the opening brace and the property +name. For example, \p{^Lu} is the same as \P{Lu}. +
++If only one letter is specified with \p or \P, it includes all the general +category properties that start with that letter. In this case, in the absence +of negation, the curly brackets in the escape sequence are optional; these two +examples have the same effect: +
+ \p{L}
+ \pL
+
+The following general category property codes are supported:
++ C Other + Cc Control + Cf Format + Cn Unassigned + Co Private use + Cs Surrogate + + L Letter + Ll Lower case letter + Lm Modifier letter + Lo Other letter + Lt Title case letter + Lu Upper case letter + + M Mark + Mc Spacing mark + Me Enclosing mark + Mn Non-spacing mark + + N Number + Nd Decimal number + Nl Letter number + No Other number + + P Punctuation + Pc Connector punctuation + Pd Dash punctuation + Pe Close punctuation + Pf Final punctuation + Pi Initial punctuation + Po Other punctuation + Ps Open punctuation + + S Symbol + Sc Currency symbol + Sk Modifier symbol + Sm Mathematical symbol + So Other symbol + + Z Separator + Zl Line separator + Zp Paragraph separator + Zs Space separator ++The special property L& is also supported: it matches a character that has +the Lu, Ll, or Lt property, in other words, a letter that is not classified as +a modifier or "other". + +
+The Cs (Surrogate) property applies only to characters in the range U+D800 to +U+DFFF. Such characters are not valid in Unicode strings and so +cannot be tested by PCRE, unless UTF validity checking has been turned off +(see the discussion of PCRE_NO_UTF8_CHECK, PCRE_NO_UTF16_CHECK and +PCRE_NO_UTF32_CHECK in the +pcreapi +page). Perl does not support the Cs property. +
++The long synonyms for property names that Perl supports (such as \p{Letter}) +are not supported by PCRE, nor is it permitted to prefix any of these +properties with "Is". +
++No character that is in the Unicode table has the Cn (unassigned) property. +Instead, this property is assumed for any code point that is not in the +Unicode table. +
++Specifying caseless matching does not affect these escape sequences. For +example, \p{Lu} always matches only upper case letters. +
++Matching characters by Unicode property is not fast, because PCRE has to do a +multistage table lookup in order to find a character's property. That is why +the traditional escape sequences such as \d and \w do not use Unicode +properties in PCRE by default, though you can make them do so by setting the +PCRE_UCP option or by starting the pattern with (*UCP). +
++The \X escape matches any number of Unicode characters that form an "extended +grapheme cluster", and treats the sequence as an atomic group +(see below). +Up to and including release 8.31, PCRE matched an earlier, simpler definition +that was equivalent to +
+ (?>\PM\pM*) ++That is, it matched a character without the "mark" property, followed by zero +or more characters with the "mark" property. Characters with the "mark" +property are typically non-spacing accents that affect the preceding character. + +
+This simple definition was extended in Unicode to include more complicated +kinds of composite character by giving each character a grapheme breaking +property, and creating rules that use these properties to define the boundaries +of extended grapheme clusters. In releases of PCRE later than 8.31, \X matches +one of these clusters. +
++\X always matches at least one character. Then it decides whether to add +additional characters according to the following rules for ending a cluster: +
++1. End at the end of the subject string. +
++2. Do not end between CR and LF; otherwise end after any control character. +
++3. Do not break Hangul (a Korean script) syllable sequences. Hangul characters +are of five types: L, V, T, LV, and LVT. An L character may be followed by an +L, V, LV, or LVT character; an LV or V character may be followed by a V or T +character; an LVT or T character may be follwed only by a T character. +
++4. Do not end before extending characters or spacing marks. Characters with +the "mark" property always have the "extend" grapheme breaking property. +
++5. Do not end after prepend characters. +
++6. Otherwise, end the cluster. +
++As well as the standard Unicode properties described above, PCRE supports four +more that make it possible to convert traditional escape sequences such as \w +and \s and POSIX character classes to use Unicode properties. PCRE uses these +non-standard, non-Perl properties internally when PCRE_UCP is set. They are: +
+ Xan Any alphanumeric character + Xps Any POSIX space character + Xsp Any Perl space character + Xwd Any Perl "word" character ++Xan matches characters that have either the L (letter) or the N (number) +property. Xps matches the characters tab, linefeed, vertical tab, form feed, or +carriage return, and any other character that has the Z (separator) property. +Xsp is the same as Xps, except that vertical tab is excluded. Xwd matches the +same characters as Xan, plus underscore. + +
+The escape sequence \K causes any previously matched characters not to be +included in the final matched sequence. For example, the pattern: +
+ foo\Kbar ++matches "foobar", but reports that it has matched "bar". This feature is +similar to a lookbehind assertion +(described below). +However, in this case, the part of the subject before the real match does not +have to be of fixed length, as lookbehind assertions do. The use of \K does +not interfere with the setting of +captured substrings. +For example, when the pattern +
+ (foo)\Kbar ++matches "foobar", the first substring is still set to "foo". + +
+Perl documents that the use of \K within assertions is "not well defined". In +PCRE, \K is acted upon when it occurs inside positive assertions, but is +ignored in negative assertions. +
++The final use of backslash is for certain simple assertions. An assertion +specifies a condition that has to be met at a particular point in a match, +without consuming any characters from the subject string. The use of +subpatterns for more complicated assertions is described +below. +The backslashed assertions are: +
+ \b matches at a word boundary + \B matches when not at a word boundary + \A matches at the start of the subject + \Z matches at the end of the subject + also matches before a newline at the end of the subject + \z matches only at the end of the subject + \G matches at the first matching position in the subject ++Inside a character class, \b has a different meaning; it matches the backspace +character. If any other of these assertions appears in a character class, by +default it matches the corresponding literal character (for example, \B +matches the letter B). However, if the PCRE_EXTRA option is set, an "invalid +escape sequence" error is generated instead. + +
+A word boundary is a position in the subject string where the current character +and the previous character do not both match \w or \W (i.e. one matches +\w and the other matches \W), or the start or end of the string if the +first or last character matches \w, respectively. In a UTF mode, the meanings +of \w and \W can be changed by setting the PCRE_UCP option. When this is +done, it also affects \b and \B. Neither PCRE nor Perl has a separate "start +of word" or "end of word" metasequence. However, whatever follows \b normally +determines which it is. For example, the fragment \ba matches "a" at the start +of a word. +
++The \A, \Z, and \z assertions differ from the traditional circumflex and +dollar (described in the next section) in that they only ever match at the very +start and end of the subject string, whatever options are set. Thus, they are +independent of multiline mode. These three assertions are not affected by the +PCRE_NOTBOL or PCRE_NOTEOL options, which affect only the behaviour of the +circumflex and dollar metacharacters. However, if the startoffset +argument of pcre_exec() is non-zero, indicating that matching is to start +at a point other than the beginning of the subject, \A can never match. The +difference between \Z and \z is that \Z matches before a newline at the end +of the string as well as at the very end, whereas \z matches only at the end. +
++The \G assertion is true only when the current matching position is at the +start point of the match, as specified by the startoffset argument of +pcre_exec(). It differs from \A when the value of startoffset is +non-zero. By calling pcre_exec() multiple times with appropriate +arguments, you can mimic Perl's /g option, and it is in this kind of +implementation where \G can be useful. +
++Note, however, that PCRE's interpretation of \G, as the start of the current +match, is subtly different from Perl's, which defines it as the end of the +previous match. In Perl, these can be different when the previously matched +string was empty. Because PCRE does just one match at a time, it cannot +reproduce this behaviour. +
++If all the alternatives of a pattern begin with \G, the expression is anchored +to the starting match position, and the "anchored" flag is set in the compiled +regular expression. +
++The circumflex and dollar metacharacters are zero-width assertions. That is, +they test for a particular condition being true without consuming any +characters from the subject string. +
++Outside a character class, in the default matching mode, the circumflex +character is an assertion that is true only if the current matching point is at +the start of the subject string. If the startoffset argument of +pcre_exec() is non-zero, circumflex can never match if the PCRE_MULTILINE +option is unset. Inside a character class, circumflex has an entirely different +meaning +(see below). +
++Circumflex need not be the first character of the pattern if a number of +alternatives are involved, but it should be the first thing in each alternative +in which it appears if the pattern is ever to match that branch. If all +possible alternatives start with a circumflex, that is, if the pattern is +constrained to match only at the start of the subject, it is said to be an +"anchored" pattern. (There are also other constructs that can cause a pattern +to be anchored.) +
++The dollar character is an assertion that is true only if the current matching +point is at the end of the subject string, or immediately before a newline at +the end of the string (by default). Note, however, that it does not actually +match the newline. Dollar need not be the last character of the pattern if a +number of alternatives are involved, but it should be the last item in any +branch in which it appears. Dollar has no special meaning in a character class. +
++The meaning of dollar can be changed so that it matches only at the very end of +the string, by setting the PCRE_DOLLAR_ENDONLY option at compile time. This +does not affect the \Z assertion. +
++The meanings of the circumflex and dollar characters are changed if the +PCRE_MULTILINE option is set. When this is the case, a circumflex matches +immediately after internal newlines as well as at the start of the subject +string. It does not match after a newline that ends the string. A dollar +matches before any newlines in the string, as well as at the very end, when +PCRE_MULTILINE is set. When newline is specified as the two-character +sequence CRLF, isolated CR and LF characters do not indicate newlines. +
++For example, the pattern /^abc$/ matches the subject string "def\nabc" (where +\n represents a newline) in multiline mode, but not otherwise. Consequently, +patterns that are anchored in single line mode because all branches start with +^ are not anchored in multiline mode, and a match for circumflex is possible +when the startoffset argument of pcre_exec() is non-zero. The +PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is set. +
++Note that the sequences \A, \Z, and \z can be used to match the start and +end of the subject in both modes, and if all branches of a pattern start with +\A it is always anchored, whether or not PCRE_MULTILINE is set. +
++Outside a character class, a dot in the pattern matches any one character in +the subject string except (by default) a character that signifies the end of a +line. +
++When a line ending is defined as a single character, dot never matches that +character; when the two-character sequence CRLF is used, dot does not match CR +if it is immediately followed by LF, but otherwise it matches all characters +(including isolated CRs and LFs). When any Unicode line endings are being +recognized, dot does not match CR or LF or any of the other line ending +characters. +
++The behaviour of dot with regard to newlines can be changed. If the PCRE_DOTALL +option is set, a dot matches any one character, without exception. If the +two-character sequence CRLF is present in the subject string, it takes two dots +to match it. +
++The handling of dot is entirely independent of the handling of circumflex and +dollar, the only relationship being that they both involve newlines. Dot has no +special meaning in a character class. +
++The escape sequence \N behaves like a dot, except that it is not affected by +the PCRE_DOTALL option. In other words, it matches any character except one +that signifies the end of a line. Perl also uses \N to match characters by +name; PCRE does not support this. +
++Outside a character class, the escape sequence \C matches any one data unit, +whether or not a UTF mode is set. In the 8-bit library, one data unit is one +byte; in the 16-bit library it is a 16-bit unit; in the 32-bit library it is +a 32-bit unit. Unlike a dot, \C always +matches line-ending characters. The feature is provided in Perl in order to +match individual bytes in UTF-8 mode, but it is unclear how it can usefully be +used. Because \C breaks up characters into individual data units, matching one +unit with \C in a UTF mode means that the rest of the string may start with a +malformed UTF character. This has undefined results, because PCRE assumes that +it is dealing with valid UTF strings (and by default it checks this at the +start of processing unless the PCRE_NO_UTF8_CHECK, PCRE_NO_UTF16_CHECK or +PCRE_NO_UTF32_CHECK option is used). +
++PCRE does not allow \C to appear in lookbehind assertions +(described below) +in a UTF mode, because this would make it impossible to calculate the length of +the lookbehind. +
++In general, the \C escape sequence is best avoided. However, one +way of using it that avoids the problem of malformed UTF characters is to use a +lookahead to check the length of the next character, as in this pattern, which +could be used with a UTF-8 string (ignore white space and line breaks): +
+ (?| (?=[\x00-\x7f])(\C) |
+ (?=[\x80-\x{7ff}])(\C)(\C) |
+ (?=[\x{800}-\x{ffff}])(\C)(\C)(\C) |
+ (?=[\x{10000}-\x{1fffff}])(\C)(\C)(\C)(\C))
+
+A group that starts with (?| resets the capturing parentheses numbers in each
+alternative (see
+"Duplicate Subpattern Numbers"
+below). The assertions at the start of each branch check the next UTF-8
+character for values whose encoding uses 1, 2, 3, or 4 bytes, respectively. The
+character's individual bytes are then captured by the appropriate number of
+groups.
+
++An opening square bracket introduces a character class, terminated by a closing +square bracket. A closing square bracket on its own is not special by default. +However, if the PCRE_JAVASCRIPT_COMPAT option is set, a lone closing square +bracket causes a compile-time error. If a closing square bracket is required as +a member of the class, it should be the first data character in the class +(after an initial circumflex, if present) or escaped with a backslash. +
++A character class matches a single character in the subject. In a UTF mode, the +character may be more than one data unit long. A matched character must be in +the set of characters defined by the class, unless the first character in the +class definition is a circumflex, in which case the subject character must not +be in the set defined by the class. If a circumflex is actually required as a +member of the class, ensure it is not the first character, or escape it with a +backslash. +
++For example, the character class [aeiou] matches any lower case vowel, while +[^aeiou] matches any character that is not a lower case vowel. Note that a +circumflex is just a convenient notation for specifying the characters that +are in the class by enumerating those that are not. A class that starts with a +circumflex is not an assertion; it still consumes a character from the subject +string, and therefore it fails if the current pointer is at the end of the +string. +
++In UTF-8 (UTF-16, UTF-32) mode, characters with values greater than 255 (0xffff) +can be included in a class as a literal string of data units, or by using the +\x{ escaping mechanism. +
++When caseless matching is set, any letters in a class represent both their +upper case and lower case versions, so for example, a caseless [aeiou] matches +"A" as well as "a", and a caseless [^aeiou] does not match "A", whereas a +caseful version would. In a UTF mode, PCRE always understands the concept of +case for characters whose values are less than 128, so caseless matching is +always possible. For characters with higher values, the concept of case is +supported if PCRE is compiled with Unicode property support, but not otherwise. +If you want to use caseless matching in a UTF mode for characters 128 and +above, you must ensure that PCRE is compiled with Unicode property support as +well as with UTF support. +
++Characters that might indicate line breaks are never treated in any special way +when matching character classes, whatever line-ending sequence is in use, and +whatever setting of the PCRE_DOTALL and PCRE_MULTILINE options is used. A class +such as [^a] always matches one of these characters. +
++The minus (hyphen) character can be used to specify a range of characters in a +character class. For example, [d-m] matches any letter between d and m, +inclusive. If a minus character is required in a class, it must be escaped with +a backslash or appear in a position where it cannot be interpreted as +indicating a range, typically as the first or last character in the class. +
++It is not possible to have the literal character "]" as the end character of a +range. A pattern such as [W-]46] is interpreted as a class of two characters +("W" and "-") followed by a literal string "46]", so it would match "W46]" or +"-46]". However, if the "]" is escaped with a backslash it is interpreted as +the end of range, so [W-\]46] is interpreted as a class containing a range +followed by two other characters. The octal or hexadecimal representation of +"]" can also be used to end a range. +
++Ranges operate in the collating sequence of character values. They can also be +used for characters specified numerically, for example [\000-\037]. Ranges +can include any characters that are valid for the current mode. +
++If a range that includes letters is used when caseless matching is set, it +matches the letters in either case. For example, [W-c] is equivalent to +[][\\^_`wxyzabc], matched caselessly, and in a non-UTF mode, if character +tables for a French locale are in use, [\xc8-\xcb] matches accented E +characters in both cases. In UTF modes, PCRE supports the concept of case for +characters with values greater than 128 only when it is compiled with Unicode +property support. +
++The character escape sequences \d, \D, \h, \H, \p, \P, \s, \S, \v, +\V, \w, and \W may appear in a character class, and add the characters that +they match to the class. For example, [\dABCDEF] matches any hexadecimal +digit. In UTF modes, the PCRE_UCP option affects the meanings of \d, \s, \w +and their upper case partners, just as it does when they appear outside a +character class, as described in the section entitled +"Generic character types" +above. The escape sequence \b has a different meaning inside a character +class; it matches the backspace character. The sequences \B, \N, \R, and \X +are not special inside a character class. Like any other unrecognized escape +sequences, they are treated as the literal characters "B", "N", "R", and "X" by +default, but cause an error if the PCRE_EXTRA option is set. +
++A circumflex can conveniently be used with the upper case character types to +specify a more restricted set of characters than the matching lower case type. +For example, the class [^\W_] matches any letter or digit, but not underscore, +whereas [\w] includes underscore. A positive character class should be read as +"something OR something OR ..." and a negative class as "NOT something AND NOT +something AND NOT ...". +
++The only metacharacters that are recognized in character classes are backslash, +hyphen (only where it can be interpreted as specifying a range), circumflex +(only at the start), opening square bracket (only when it can be interpreted as +introducing a POSIX class name - see the next section), and the terminating +closing square bracket. However, escaping other non-alphanumeric characters +does no harm. +
++Perl supports the POSIX notation for character classes. This uses names +enclosed by [: and :] within the enclosing square brackets. PCRE also supports +this notation. For example, +
+ [01[:alpha:]%] ++matches "0", "1", any alphabetic character, or "%". The supported class names +are: +
+ alnum letters and digits + alpha letters + ascii character codes 0 - 127 + blank space or tab only + cntrl control characters + digit decimal digits (same as \d) + graph printing characters, excluding space + lower lower case letters + print printing characters, including space + punct printing characters, excluding letters and digits and space + space white space (not quite the same as \s) + upper upper case letters + word "word" characters (same as \w) + xdigit hexadecimal digits ++The "space" characters are HT (9), LF (10), VT (11), FF (12), CR (13), and +space (32). Notice that this list includes the VT character (code 11). This +makes "space" different to \s, which does not include VT (for Perl +compatibility). + +
+The name "word" is a Perl extension, and "blank" is a GNU extension from Perl +5.8. Another Perl extension is negation, which is indicated by a ^ character +after the colon. For example, +
+ [12[:^digit:]] ++matches "1", "2", or any non-digit. PCRE (and Perl) also recognize the POSIX +syntax [.ch.] and [=ch=] where "ch" is a "collating element", but these are not +supported, and an error is given if they are encountered. + +
+By default, in UTF modes, characters with values greater than 128 do not match +any of the POSIX character classes. However, if the PCRE_UCP option is passed +to pcre_compile(), some of the classes are changed so that Unicode +character properties are used. This is achieved by replacing the POSIX classes +by other sequences, as follows: +
+ [:alnum:] becomes \p{Xan}
+ [:alpha:] becomes \p{L}
+ [:blank:] becomes \h
+ [:digit:] becomes \p{Nd}
+ [:lower:] becomes \p{Ll}
+ [:space:] becomes \p{Xps}
+ [:upper:] becomes \p{Lu}
+ [:word:] becomes \p{Xwd}
+
+Negated versions, such as [:^alpha:] use \P instead of \p. The other POSIX
+classes are unchanged, and match only characters with code points less than
+128.
+
++Vertical bar characters are used to separate alternative patterns. For example, +the pattern +
+ gilbert|sullivan ++matches either "gilbert" or "sullivan". Any number of alternatives may appear, +and an empty alternative is permitted (matching the empty string). The matching +process tries each alternative in turn, from left to right, and the first one +that succeeds is used. If the alternatives are within a subpattern +(defined below), +"succeeds" means matching the rest of the main pattern as well as the +alternative in the subpattern. + +
+The settings of the PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, and +PCRE_EXTENDED options (which are Perl-compatible) can be changed from within +the pattern by a sequence of Perl option letters enclosed between "(?" and ")". +The option letters are +
+ i for PCRE_CASELESS + m for PCRE_MULTILINE + s for PCRE_DOTALL + x for PCRE_EXTENDED ++For example, (?im) sets caseless, multiline matching. It is also possible to +unset these options by preceding the letter with a hyphen, and a combined +setting and unsetting such as (?im-sx), which sets PCRE_CASELESS and +PCRE_MULTILINE while unsetting PCRE_DOTALL and PCRE_EXTENDED, is also +permitted. If a letter appears both before and after the hyphen, the option is +unset. + +
+The PCRE-specific options PCRE_DUPNAMES, PCRE_UNGREEDY, and PCRE_EXTRA can be +changed in the same way as the Perl-compatible options by using the characters +J, U and X respectively. +
++When one of these option changes occurs at top level (that is, not inside +subpattern parentheses), the change applies to the remainder of the pattern +that follows. If the change is placed right at the start of a pattern, PCRE +extracts it into the global options (and it will therefore show up in data +extracted by the pcre_fullinfo() function). +
++An option change within a subpattern (see below for a description of +subpatterns) affects only that part of the subpattern that follows it, so +
+ (a(?i)b)c ++matches abc and aBc and no other strings (assuming PCRE_CASELESS is not used). +By this means, options can be made to have different settings in different +parts of the pattern. Any changes made in one alternative do carry on +into subsequent branches within the same subpattern. For example, +
+ (a(?i)b|c) ++matches "ab", "aB", "c", and "C", even though when matching "C" the first +branch is abandoned before the option setting. This is because the effects of +option settings happen at compile time. There would be some very weird +behaviour otherwise. + +
+Note: There are other PCRE-specific options that can be set by the +application when the compiling or matching functions are called. In some cases +the pattern can contain special leading sequences such as (*CRLF) to override +what the application has set or what has been defaulted. Details are given in +the section entitled +"Newline sequences" +above. There are also the (*UTF8), (*UTF16),(*UTF32), and (*UCP) leading +sequences that can be used to set UTF and Unicode property modes; they are +equivalent to setting the PCRE_UTF8, PCRE_UTF16, PCRE_UTF32 and the PCRE_UCP +options, respectively. The (*UTF) sequence is a generic version that can be +used with any of the libraries. +
+
+Subpatterns are delimited by parentheses (round brackets), which can be nested.
+Turning part of a pattern into a subpattern does two things:
+
+
+1. It localizes a set of alternatives. For example, the pattern
+
+ cat(aract|erpillar|) ++matches "cataract", "caterpillar", or "cat". Without the parentheses, it would +match "cataract", "erpillar" or an empty string. +
+Opening parentheses are counted from left to right (starting from 1) to obtain +numbers for the capturing subpatterns. For example, if the string "the red +king" is matched against the pattern +
+ the ((red|white) (king|queen)) ++the captured substrings are "red king", "red", and "king", and are numbered 1, +2, and 3, respectively. + +
+The fact that plain parentheses fulfil two functions is not always helpful. +There are often times when a grouping subpattern is required without a +capturing requirement. If an opening parenthesis is followed by a question mark +and a colon, the subpattern does not do any capturing, and is not counted when +computing the number of any subsequent capturing subpatterns. For example, if +the string "the white queen" is matched against the pattern +
+ the ((?:red|white) (king|queen)) ++the captured substrings are "white queen" and "queen", and are numbered 1 and +2. The maximum number of capturing subpatterns is 65535. + +
+As a convenient shorthand, if any option settings are required at the start of +a non-capturing subpattern, the option letters may appear between the "?" and +the ":". Thus the two patterns +
+ (?i:saturday|sunday) + (?:(?i)saturday|sunday) ++match exactly the same set of strings. Because alternative branches are tried +from left to right, and options are not reset until the end of the subpattern +is reached, an option setting in one branch does affect subsequent branches, so +the above patterns match "SUNDAY" as well as "Saturday". + +
+Perl 5.10 introduced a feature whereby each alternative in a subpattern uses +the same numbers for its capturing parentheses. Such a subpattern starts with +(?| and is itself a non-capturing subpattern. For example, consider this +pattern: +
+ (?|(Sat)ur|(Sun))day ++Because the two alternatives are inside a (?| group, both sets of capturing +parentheses are numbered one. Thus, when the pattern matches, you can look +at captured substring number one, whichever alternative matched. This construct +is useful when you want to capture part, but not all, of one of a number of +alternatives. Inside a (?| group, parentheses are numbered as usual, but the +number is reset at the start of each branch. The numbers of any capturing +parentheses that follow the subpattern start after the highest number used in +any branch. The following example is taken from the Perl documentation. The +numbers underneath show in which buffer the captured content will be stored. +
+ # before ---------------branch-reset----------- after + / ( a ) (?| x ( y ) z | (p (q) r) | (t) u (v) ) ( z ) /x + # 1 2 2 3 2 3 4 ++A back reference to a numbered subpattern uses the most recent value that is +set for that number by any subpattern. The following pattern matches "abcabc" +or "defdef": +
+ /(?|(abc)|(def))\1/ ++In contrast, a subroutine call to a numbered subpattern always refers to the +first one in the pattern with the given number. The following pattern matches +"abcabc" or "defabc": +
+ /(?|(abc)|(def))(?1)/ ++If a +condition test +for a subpattern's having matched refers to a non-unique number, the test is +true if any of the subpatterns of that number have matched. + +
+An alternative approach to using this "branch reset" feature is to use +duplicate named subpatterns, as described in the next section. +
++Identifying capturing parentheses by number is simple, but it can be very hard +to keep track of the numbers in complicated regular expressions. Furthermore, +if an expression is modified, the numbers may change. To help with this +difficulty, PCRE supports the naming of subpatterns. This feature was not +added to Perl until release 5.10. Python had the feature earlier, and PCRE +introduced it at release 4.0, using the Python syntax. PCRE now supports both +the Perl and the Python syntax. Perl allows identically numbered subpatterns to +have different names, but PCRE does not. +
++In PCRE, a subpattern can be named in one of three ways: (?<name>...) or +(?'name'...) as in Perl, or (?P<name>...) as in Python. References to capturing +parentheses from other parts of the pattern, such as +back references, +recursion, +and +conditions, +can be made by name as well as by number. +
++Names consist of up to 32 alphanumeric characters and underscores. Named +capturing parentheses are still allocated numbers as well as names, exactly as +if the names were not present. The PCRE API provides function calls for +extracting the name-to-number translation table from a compiled pattern. There +is also a convenience function for extracting a captured substring by name. +
++By default, a name must be unique within a pattern, but it is possible to relax +this constraint by setting the PCRE_DUPNAMES option at compile time. (Duplicate +names are also always permitted for subpatterns with the same number, set up as +described in the previous section.) Duplicate names can be useful for patterns +where only one instance of the named parentheses can match. Suppose you want to +match the name of a weekday, either as a 3-letter abbreviation or as the full +name, and in both cases you want to extract the abbreviation. This pattern +(ignoring the line breaks) does the job: +
+ (?<DN>Mon|Fri|Sun)(?:day)?| + (?<DN>Tue)(?:sday)?| + (?<DN>Wed)(?:nesday)?| + (?<DN>Thu)(?:rsday)?| + (?<DN>Sat)(?:urday)? ++There are five capturing substrings, but only one is ever set after a match. +(An alternative way of solving this problem is to use a "branch reset" +subpattern, as described in the previous section.) + +
+The convenience function for extracting the data by name returns the substring +for the first (and in this example, the only) subpattern of that name that +matched. This saves searching to find which numbered subpattern it was. +
++If you make a back reference to a non-unique named subpattern from elsewhere in +the pattern, the one that corresponds to the first occurrence of the name is +used. In the absence of duplicate numbers (see the previous section) this is +the one with the lowest number. If you use a named reference in a condition +test (see the +section about conditions +below), either to check whether a subpattern has matched, or to check for +recursion, all subpatterns with the same name are tested. If the condition is +true for any one of them, the overall condition is true. This is the same +behaviour as testing by number. For further details of the interfaces for +handling named subpatterns, see the +pcreapi +documentation. +
++Warning: You cannot use different names to distinguish between two +subpatterns with the same number because PCRE uses only the numbers when +matching. For this reason, an error is given at compile time if different names +are given to subpatterns with the same number. However, you can give the same +name to subpatterns with the same number, even when PCRE_DUPNAMES is not set. +
++Repetition is specified by quantifiers, which can follow any of the following +items: +
+ a literal data character + the dot metacharacter + the \C escape sequence + the \X escape sequence + the \R escape sequence + an escape such as \d or \pL that matches a single character + a character class + a back reference (see next section) + a parenthesized subpattern (including assertions) + a subroutine call to a subpattern (recursive or otherwise) ++The general repetition quantifier specifies a minimum and maximum number of +permitted matches, by giving the two numbers in curly brackets (braces), +separated by a comma. The numbers must be less than 65536, and the first must +be less than or equal to the second. For example: +
+ z{2,4}
+
+matches "zz", "zzz", or "zzzz". A closing brace on its own is not a special
+character. If the second number is omitted, but the comma is present, there is
+no upper limit; if the second number and the comma are both omitted, the
+quantifier specifies an exact number of required matches. Thus
+
+ [aeiou]{3,}
+
+matches at least 3 successive vowels, but may match many more, while
+
+ \d{8}
+
+matches exactly 8 digits. An opening curly bracket that appears in a position
+where a quantifier is not allowed, or one that does not match the syntax of a
+quantifier, is taken as a literal character. For example, {,6} is not a
+quantifier, but a literal string of four characters.
+
++In UTF modes, quantifiers apply to characters rather than to individual data +units. Thus, for example, \x{100}{2} matches two characters, each of +which is represented by a two-byte sequence in a UTF-8 string. Similarly, +\X{3} matches three Unicode extended grapheme clusters, each of which may be +several data units long (and they may be of different lengths). +
++The quantifier {0} is permitted, causing the expression to behave as if the +previous item and the quantifier were not present. This may be useful for +subpatterns that are referenced as +subroutines +from elsewhere in the pattern (but see also the section entitled +"Defining subpatterns for use by reference only" +below). Items other than subpatterns that have a {0} quantifier are omitted +from the compiled pattern. +
++For convenience, the three most common quantifiers have single-character +abbreviations: +
+ * is equivalent to {0,}
+ + is equivalent to {1,}
+ ? is equivalent to {0,1}
+
+It is possible to construct infinite loops by following a subpattern that can
+match no characters with a quantifier that has no upper limit, for example:
++ (a?)* ++Earlier versions of Perl and PCRE used to give an error at compile time for +such patterns. However, because there are cases where this can be useful, such +patterns are now accepted, but if any repetition of the subpattern does in fact +match no characters, the loop is forcibly broken. + +
+By default, the quantifiers are "greedy", that is, they match as much as +possible (up to the maximum number of permitted times), without causing the +rest of the pattern to fail. The classic example of where this gives problems +is in trying to match comments in C programs. These appear between /* and */ +and within the comment, individual * and / characters may appear. An attempt to +match C comments by applying the pattern +
+ /\*.*\*/ ++to the string +
+ /* first comment */ not comment /* second comment */ ++fails, because it matches the entire string owing to the greediness of the .* +item. + +
+However, if a quantifier is followed by a question mark, it ceases to be +greedy, and instead matches the minimum number of times possible, so the +pattern +
+ /\*.*?\*/ ++does the right thing with the C comments. The meaning of the various +quantifiers is not otherwise changed, just the preferred number of matches. +Do not confuse this use of question mark with its use as a quantifier in its +own right. Because it has two uses, it can sometimes appear doubled, as in +
+ \d??\d ++which matches one digit by preference, but can match two if that is the only +way the rest of the pattern matches. + +
+If the PCRE_UNGREEDY option is set (an option that is not available in Perl), +the quantifiers are not greedy by default, but individual ones can be made +greedy by following them with a question mark. In other words, it inverts the +default behaviour. +
++When a parenthesized subpattern is quantified with a minimum repeat count that +is greater than 1 or with a limited maximum, more memory is required for the +compiled pattern, in proportion to the size of the minimum or maximum. +
++If a pattern starts with .* or .{0,} and the PCRE_DOTALL option (equivalent +to Perl's /s) is set, thus allowing the dot to match newlines, the pattern is +implicitly anchored, because whatever follows will be tried against every +character position in the subject string, so there is no point in retrying the +overall match at any position after the first. PCRE normally treats such a +pattern as though it were preceded by \A. +
++In cases where it is known that the subject string contains no newlines, it is +worth setting PCRE_DOTALL in order to obtain this optimization, or +alternatively using ^ to indicate anchoring explicitly. +
++However, there are some cases where the optimization cannot be used. When .* +is inside capturing parentheses that are the subject of a back reference +elsewhere in the pattern, a match at the start may fail where a later one +succeeds. Consider, for example: +
+ (.*)abc\1 ++If the subject is "xyz123abc123" the match point is the fourth character. For +this reason, such a pattern is not implicitly anchored. + +
+Another case where implicit anchoring is not applied is when the leading .* is +inside an atomic group. Once again, a match at the start may fail where a later +one succeeds. Consider this pattern: +
+ (?>.*?a)b ++It matches "ab" in the subject "aab". The use of the backtracking control verbs +(*PRUNE) and (*SKIP) also disable this optimization. + +
+When a capturing subpattern is repeated, the value captured is the substring +that matched the final iteration. For example, after +
+ (tweedle[dume]{3}\s*)+
+
+has matched "tweedledum tweedledee" the value of the captured substring is
+"tweedledee". However, if there are nested capturing subpatterns, the
+corresponding captured values may have been set in previous iterations. For
+example, after
++ /(a|(b))+/ ++matches "aba" the value of the second captured substring is "b". + +
+With both maximizing ("greedy") and minimizing ("ungreedy" or "lazy") +repetition, failure of what follows normally causes the repeated item to be +re-evaluated to see if a different number of repeats allows the rest of the +pattern to match. Sometimes it is useful to prevent this, either to change the +nature of the match, or to cause it fail earlier than it otherwise might, when +the author of the pattern knows there is no point in carrying on. +
++Consider, for example, the pattern \d+foo when applied to the subject line +
+ 123456bar ++After matching all 6 digits and then failing to match "foo", the normal +action of the matcher is to try again with only 5 digits matching the \d+ +item, and then with 4, and so on, before ultimately failing. "Atomic grouping" +(a term taken from Jeffrey Friedl's book) provides the means for specifying +that once a subpattern has matched, it is not to be re-evaluated in this way. + +
+If we use atomic grouping for the previous example, the matcher gives up +immediately on failing to match "foo" the first time. The notation is a kind of +special parenthesis, starting with (?> as in this example: +
+ (?>\d+)foo ++This kind of parenthesis "locks up" the part of the pattern it contains once +it has matched, and a failure further into the pattern is prevented from +backtracking into it. Backtracking past it to previous items, however, works as +normal. + +
+An alternative description is that a subpattern of this type matches the string +of characters that an identical standalone pattern would match, if anchored at +the current point in the subject string. +
++Atomic grouping subpatterns are not capturing subpatterns. Simple cases such as +the above example can be thought of as a maximizing repeat that must swallow +everything it can. So, while both \d+ and \d+? are prepared to adjust the +number of digits they match in order to make the rest of the pattern match, +(?>\d+) can only match an entire sequence of digits. +
++Atomic groups in general can of course contain arbitrarily complicated +subpatterns, and can be nested. However, when the subpattern for an atomic +group is just a single repeated item, as in the example above, a simpler +notation, called a "possessive quantifier" can be used. This consists of an +additional + character following a quantifier. Using this notation, the +previous example can be rewritten as +
+ \d++foo ++Note that a possessive quantifier can be used with an entire group, for +example: +
+ (abc|xyz){2,3}+
+
+Possessive quantifiers are always greedy; the setting of the PCRE_UNGREEDY
+option is ignored. They are a convenient notation for the simpler forms of
+atomic group. However, there is no difference in the meaning of a possessive
+quantifier and the equivalent atomic group, though there may be a performance
+difference; possessive quantifiers should be slightly faster.
+
++The possessive quantifier syntax is an extension to the Perl 5.8 syntax. +Jeffrey Friedl originated the idea (and the name) in the first edition of his +book. Mike McCloskey liked it, so implemented it when he built Sun's Java +package, and PCRE copied it from there. It ultimately found its way into Perl +at release 5.10. +
++PCRE has an optimization that automatically "possessifies" certain simple +pattern constructs. For example, the sequence A+B is treated as A++B because +there is no point in backtracking into a sequence of A's when B must follow. +
++When a pattern contains an unlimited repeat inside a subpattern that can itself +be repeated an unlimited number of times, the use of an atomic group is the +only way to avoid some failing matches taking a very long time indeed. The +pattern +
+ (\D+|<\d+>)*[!?] ++matches an unlimited number of substrings that either consist of non-digits, or +digits enclosed in <>, followed by either ! or ?. When it matches, it runs +quickly. However, if it is applied to +
+ aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa ++it takes a long time before reporting failure. This is because the string can +be divided between the internal \D+ repeat and the external * repeat in a +large number of ways, and all have to be tried. (The example uses [!?] rather +than a single character at the end, because both PCRE and Perl have an +optimization that allows for fast failure when a single character is used. They +remember the last single character that is required for a match, and fail early +if it is not present in the string.) If the pattern is changed so that it uses +an atomic group, like this: +
+ ((?>\D+)|<\d+>)*[!?] ++sequences of non-digits cannot be broken, and failure happens quickly. + +
+Outside a character class, a backslash followed by a digit greater than 0 (and +possibly further digits) is a back reference to a capturing subpattern earlier +(that is, to its left) in the pattern, provided there have been that many +previous capturing left parentheses. +
++However, if the decimal number following the backslash is less than 10, it is +always taken as a back reference, and causes an error only if there are not +that many capturing left parentheses in the entire pattern. In other words, the +parentheses that are referenced need not be to the left of the reference for +numbers less than 10. A "forward back reference" of this type can make sense +when a repetition is involved and the subpattern to the right has participated +in an earlier iteration. +
++It is not possible to have a numerical "forward back reference" to a subpattern +whose number is 10 or more using this syntax because a sequence such as \50 is +interpreted as a character defined in octal. See the subsection entitled +"Non-printing characters" +above +for further details of the handling of digits following a backslash. There is +no such problem when named parentheses are used. A back reference to any +subpattern is possible using named parentheses (see below). +
++Another way of avoiding the ambiguity inherent in the use of digits following a +backslash is to use the \g escape sequence. This escape must be followed by an +unsigned number or a negative number, optionally enclosed in braces. These +examples are all identical: +
+ (ring), \1
+ (ring), \g1
+ (ring), \g{1}
+
+An unsigned number specifies an absolute reference without the ambiguity that
+is present in the older syntax. It is also useful when literal digits follow
+the reference. A negative number is a relative reference. Consider this
+example:
+
+ (abc(def)ghi)\g{-1}
+
+The sequence \g{-1} is a reference to the most recently started capturing
+subpattern before \g, that is, is it equivalent to \2 in this example.
+Similarly, \g{-2} would be equivalent to \1. The use of relative references
+can be helpful in long patterns, and also in patterns that are created by
+joining together fragments that contain references within themselves.
+
++A back reference matches whatever actually matched the capturing subpattern in +the current subject string, rather than anything matching the subpattern +itself (see +"Subpatterns as subroutines" +below for a way of doing that). So the pattern +
+ (sens|respons)e and \1ibility ++matches "sense and sensibility" and "response and responsibility", but not +"sense and responsibility". If caseful matching is in force at the time of the +back reference, the case of letters is relevant. For example, +
+ ((?i)rah)\s+\1 ++matches "rah rah" and "RAH RAH", but not "RAH rah", even though the original +capturing subpattern is matched caselessly. + +
+There are several different ways of writing back references to named +subpatterns. The .NET syntax \k{name} and the Perl syntax \k<name> or +\k'name' are supported, as is the Python syntax (?P=name). Perl 5.10's unified +back reference syntax, in which \g can be used for both numeric and named +references, is also supported. We could rewrite the above example in any of +the following ways: +
+ (?<p1>(?i)rah)\s+\k<p1>
+ (?'p1'(?i)rah)\s+\k{p1}
+ (?P<p1>(?i)rah)\s+(?P=p1)
+ (?<p1>(?i)rah)\s+\g{p1}
+
+A subpattern that is referenced by name may appear in the pattern before or
+after the reference.
+
++There may be more than one back reference to the same subpattern. If a +subpattern has not actually been used in a particular match, any back +references to it always fail by default. For example, the pattern +
+ (a|(bc))\2 ++always fails if it starts to match "a" rather than "bc". However, if the +PCRE_JAVASCRIPT_COMPAT option is set at compile time, a back reference to an +unset value matches an empty string. + +
+Because there may be many capturing parentheses in a pattern, all digits +following a backslash are taken as part of a potential back reference number. +If the pattern continues with a digit character, some delimiter must be used to +terminate the back reference. If the PCRE_EXTENDED option is set, this can be +white space. Otherwise, the \g{ syntax or an empty comment (see +"Comments" +below) can be used. +
++A back reference that occurs inside the parentheses to which it refers fails +when the subpattern is first used, so, for example, (a\1) never matches. +However, such references can be useful inside repeated subpatterns. For +example, the pattern +
+ (a|b\1)+ ++matches any number of "a"s and also "aba", "ababbaa" etc. At each iteration of +the subpattern, the back reference matches the character string corresponding +to the previous iteration. In order for this to work, the pattern must be such +that the first iteration does not need to match the back reference. This can be +done using alternation, as in the example above, or by a quantifier with a +minimum of zero. + +
+Back references of this type cause the group that they reference to be treated +as an +atomic group. +Once the whole group has been matched, a subsequent matching failure cannot +cause backtracking into the middle of the group. +
++An assertion is a test on the characters following or preceding the current +matching point that does not actually consume any characters. The simple +assertions coded as \b, \B, \A, \G, \Z, \z, ^ and $ are described +above. +
++More complicated assertions are coded as subpatterns. There are two kinds: +those that look ahead of the current position in the subject string, and those +that look behind it. An assertion subpattern is matched in the normal way, +except that it does not cause the current matching position to be changed. +
++Assertion subpatterns are not capturing subpatterns. If such an assertion +contains capturing subpatterns within it, these are counted for the purposes of +numbering the capturing subpatterns in the whole pattern. However, substring +capturing is carried out only for positive assertions, because it does not make +sense for negative assertions. +
+
+For compatibility with Perl, assertion subpatterns may be repeated; though
+it makes no sense to assert the same thing several times, the side effect of
+capturing parentheses may occasionally be useful. In practice, there only three
+cases:
+
+
+(1) If the quantifier is {0}, the assertion is never obeyed during matching.
+However, it may contain internal capturing parenthesized groups that are called
+from elsewhere via the
+subroutine mechanism.
+
+
+(2) If quantifier is {0,n} where n is greater than zero, it is treated as if it
+were {0,1}. At run time, the rest of the pattern match is tried with and
+without the assertion, the order depending on the greediness of the quantifier.
+
+
+(3) If the minimum repetition is greater than zero, the quantifier is ignored.
+The assertion is obeyed just once when encountered during matching.
+
+Lookahead assertions start with (?= for positive assertions and (?! for +negative assertions. For example, +
+ \w+(?=;) ++matches a word followed by a semicolon, but does not include the semicolon in +the match, and +
+ foo(?!bar) ++matches any occurrence of "foo" that is not followed by "bar". Note that the +apparently similar pattern +
+ (?!foo)bar ++does not find an occurrence of "bar" that is preceded by something other than +"foo"; it finds any occurrence of "bar" whatsoever, because the assertion +(?!foo) is always true when the next three characters are "bar". A +lookbehind assertion is needed to achieve the other effect. + +
+If you want to force a matching failure at some point in a pattern, the most +convenient way to do it is with (?!) because an empty string always matches, so +an assertion that requires there not to be an empty string must always fail. +The backtracking control verb (*FAIL) or (*F) is a synonym for (?!). +
++Lookbehind assertions start with (?<= for positive assertions and (?<! for +negative assertions. For example, +
+ (?<!foo)bar ++does find an occurrence of "bar" that is not preceded by "foo". The contents of +a lookbehind assertion are restricted such that all the strings it matches must +have a fixed length. However, if there are several top-level alternatives, they +do not all have to have the same fixed length. Thus +
+ (?<=bullock|donkey) ++is permitted, but +
+ (?<!dogs?|cats?) ++causes an error at compile time. Branches that match different length strings +are permitted only at the top level of a lookbehind assertion. This is an +extension compared with Perl, which requires all branches to match the same +length of string. An assertion such as +
+ (?<=ab(c|de)) ++is not permitted, because its single top-level branch can match two different +lengths, but it is acceptable to PCRE if rewritten to use two top-level +branches: +
+ (?<=abc|abde) ++In some cases, the escape sequence \K +(see above) +can be used instead of a lookbehind assertion to get round the fixed-length +restriction. + +
+The implementation of lookbehind assertions is, for each alternative, to +temporarily move the current position back by the fixed length and then try to +match. If there are insufficient characters before the current position, the +assertion fails. +
++In a UTF mode, PCRE does not allow the \C escape (which matches a single data +unit even in a UTF mode) to appear in lookbehind assertions, because it makes +it impossible to calculate the length of the lookbehind. The \X and \R +escapes, which can match different numbers of data units, are also not +permitted. +
++"Subroutine" +calls (see below) such as (?2) or (?&X) are permitted in lookbehinds, as long +as the subpattern matches a fixed-length string. +Recursion, +however, is not supported. +
++Possessive quantifiers can be used in conjunction with lookbehind assertions to +specify efficient matching of fixed-length strings at the end of subject +strings. Consider a simple pattern such as +
+ abcd$ ++when applied to a long string that does not match. Because matching proceeds +from left to right, PCRE will look for each "a" in the subject and then see if +what follows matches the rest of the pattern. If the pattern is specified as +
+ ^.*abcd$ ++the initial .* matches the entire string at first, but when this fails (because +there is no following "a"), it backtracks to match all but the last character, +then all but the last two characters, and so on. Once again the search for "a" +covers the entire string, from right to left, so we are no better off. However, +if the pattern is written as +
+ ^.*+(?<=abcd) ++there can be no backtracking for the .*+ item; it can match only the entire +string. The subsequent lookbehind assertion does a single test on the last four +characters. If it fails, the match fails immediately. For long strings, this +approach makes a significant difference to the processing time. + +
+Several assertions (of any sort) may occur in succession. For example, +
+ (?<=\d{3})(?<!999)foo
+
+matches "foo" preceded by three digits that are not "999". Notice that each of
+the assertions is applied independently at the same point in the subject
+string. First there is a check that the previous three characters are all
+digits, and then there is a check that the same three characters are not "999".
+This pattern does not match "foo" preceded by six characters, the first
+of which are digits and the last three of which are not "999". For example, it
+doesn't match "123abcfoo". A pattern to do that is
+
+ (?<=\d{3}...)(?<!999)foo
+
+This time the first assertion looks at the preceding six characters, checking
+that the first three are digits, and then the second assertion checks that the
+preceding three characters are not "999".
+
++Assertions can be nested in any combination. For example, +
+ (?<=(?<!foo)bar)baz ++matches an occurrence of "baz" that is preceded by "bar" which in turn is not +preceded by "foo", while +
+ (?<=\d{3}(?!999)...)foo
+
+is another pattern that matches "foo" preceded by three digits and any three
+characters that are not "999".
+
++It is possible to cause the matching process to obey a subpattern +conditionally or to choose between two alternative subpatterns, depending on +the result of an assertion, or whether a specific capturing subpattern has +already been matched. The two possible forms of conditional subpattern are: +
+ (?(condition)yes-pattern) + (?(condition)yes-pattern|no-pattern) ++If the condition is satisfied, the yes-pattern is used; otherwise the +no-pattern (if present) is used. If there are more than two alternatives in the +subpattern, a compile-time error occurs. Each of the two alternatives may +itself contain nested subpatterns of any form, including conditional +subpatterns; the restriction to two alternatives applies only at the level of +the condition. This pattern fragment is an example where the alternatives are +complex: +
+ (?(1) (A|B|C) | (D | (?(2)E|F) | E) ) + ++ +
+There are four kinds of condition: references to subpatterns, references to +recursion, a pseudo-condition called DEFINE, and assertions. +
++If the text between the parentheses consists of a sequence of digits, the +condition is true if a capturing subpattern of that number has previously +matched. If there is more than one capturing subpattern with the same number +(see the earlier +section about duplicate subpattern numbers), +the condition is true if any of them have matched. An alternative notation is +to precede the digits with a plus or minus sign. In this case, the subpattern +number is relative rather than absolute. The most recently opened parentheses +can be referenced by (?(-1), the next most recent by (?(-2), and so on. Inside +loops it can also make sense to refer to subsequent groups. The next +parentheses to be opened can be referenced as (?(+1), and so on. (The value +zero in any of these forms is not used; it provokes a compile-time error.) +
++Consider the following pattern, which contains non-significant white space to +make it more readable (assume the PCRE_EXTENDED option) and to divide it into +three parts for ease of discussion: +
+ ( \( )? [^()]+ (?(1) \) ) ++The first part matches an optional opening parenthesis, and if that +character is present, sets it as the first captured substring. The second part +matches one or more characters that are not parentheses. The third part is a +conditional subpattern that tests whether or not the first set of parentheses +matched. If they did, that is, if subject started with an opening parenthesis, +the condition is true, and so the yes-pattern is executed and a closing +parenthesis is required. Otherwise, since no-pattern is not present, the +subpattern matches nothing. In other words, this pattern matches a sequence of +non-parentheses, optionally enclosed in parentheses. + +
+If you were embedding this pattern in a larger one, you could use a relative +reference: +
+ ...other stuff... ( \( )? [^()]+ (?(-1) \) ) ... ++This makes the fragment independent of the parentheses in the larger pattern. + +
+Perl uses the syntax (?(<name>)...) or (?('name')...) to test for a used +subpattern by name. For compatibility with earlier versions of PCRE, which had +this facility before Perl, the syntax (?(name)...) is also recognized. However, +there is a possible ambiguity with this syntax, because subpattern names may +consist entirely of digits. PCRE looks first for a named subpattern; if it +cannot find one and the name consists entirely of digits, PCRE looks for a +subpattern of that number, which must be greater than zero. Using subpattern +names that consist entirely of digits is not recommended. +
++Rewriting the above example to use a named subpattern gives this: +
+ (?<OPEN> \( )? [^()]+ (?(<OPEN>) \) ) ++If the name used in a condition of this kind is a duplicate, the test is +applied to all subpatterns of the same name, and is true if any one of them has +matched. + +
+If the condition is the string (R), and there is no subpattern with the name R, +the condition is true if a recursive call to the whole pattern or any +subpattern has been made. If digits or a name preceded by ampersand follow the +letter R, for example: +
+ (?(R3)...) or (?(R&name)...) ++the condition is true if the most recent recursion is into a subpattern whose +number or name is given. This condition does not check the entire recursion +stack. If the name used in a condition of this kind is a duplicate, the test is +applied to all subpatterns of the same name, and is true if any one of them is +the most recent recursion. + +
+At "top level", all these recursion test conditions are false. +The syntax for recursive patterns +is described below. +
++If the condition is the string (DEFINE), and there is no subpattern with the +name DEFINE, the condition is always false. In this case, there may be only one +alternative in the subpattern. It is always skipped if control reaches this +point in the pattern; the idea of DEFINE is that it can be used to define +subroutines that can be referenced from elsewhere. (The use of +subroutines +is described below.) For example, a pattern to match an IPv4 address such as +"192.168.23.245" could be written like this (ignore white space and line +breaks): +
+ (?(DEFINE) (?<byte> 2[0-4]\d | 25[0-5] | 1\d\d | [1-9]?\d) )
+ \b (?&byte) (\.(?&byte)){3} \b
+
+The first part of the pattern is a DEFINE group inside which a another group
+named "byte" is defined. This matches an individual component of an IPv4
+address (a number less than 256). When matching takes place, this part of the
+pattern is skipped because DEFINE acts like a false condition. The rest of the
+pattern uses references to the named group to match the four dot-separated
+components of an IPv4 address, insisting on a word boundary at each end.
+
++If the condition is not in any of the above formats, it must be an assertion. +This may be a positive or negative lookahead or lookbehind assertion. Consider +this pattern, again containing non-significant white space, and with the two +alternatives on the second line: +
+ (?(?=[^a-z]*[a-z])
+ \d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} )
+
+The condition is a positive lookahead assertion that matches an optional
+sequence of non-letters followed by a letter. In other words, it tests for the
+presence of at least one letter in the subject. If a letter is found, the
+subject is matched against the first alternative; otherwise it is matched
+against the second. This pattern matches strings in one of the two forms
+dd-aaa-dd or dd-dd-dd, where aaa are letters and dd are digits.
+
++There are two ways of including comments in patterns that are processed by +PCRE. In both cases, the start of the comment must not be in a character class, +nor in the middle of any other sequence of related characters such as (?: or a +subpattern name or number. The characters that make up a comment play no part +in the pattern matching. +
++The sequence (?# marks the start of a comment that continues up to the next +closing parenthesis. Nested parentheses are not permitted. If the PCRE_EXTENDED +option is set, an unescaped # character also introduces a comment, which in +this case continues to immediately after the next newline character or +character sequence in the pattern. Which characters are interpreted as newlines +is controlled by the options passed to a compiling function or by a special +sequence at the start of the pattern, as described in the section entitled +"Newline conventions" +above. Note that the end of this type of comment is a literal newline sequence +in the pattern; escape sequences that happen to represent a newline do not +count. For example, consider this pattern when PCRE_EXTENDED is set, and the +default newline convention is in force: +
+ abc #comment \n still comment ++On encountering the # character, pcre_compile() skips along, looking for +a newline in the pattern. The sequence \n is still literal at this stage, so +it does not terminate the comment. Only an actual character with the code value +0x0a (the default newline) does so. + +
+Consider the problem of matching a string in parentheses, allowing for +unlimited nested parentheses. Without the use of recursion, the best that can +be done is to use a pattern that matches up to some fixed depth of nesting. It +is not possible to handle an arbitrary nesting depth. +
++For some time, Perl has provided a facility that allows regular expressions to +recurse (amongst other things). It does this by interpolating Perl code in the +expression at run time, and the code can refer to the expression itself. A Perl +pattern using code interpolation to solve the parentheses problem can be +created like this: +
+ $re = qr{\( (?: (?>[^()]+) | (?p{$re}) )* \)}x;
+
+The (?p{...}) item interpolates Perl code at run time, and in this case refers
+recursively to the pattern in which it appears.
+
++Obviously, PCRE cannot support the interpolation of Perl code. Instead, it +supports special syntax for recursion of the entire pattern, and also for +individual subpattern recursion. After its introduction in PCRE and Python, +this kind of recursion was subsequently introduced into Perl at release 5.10. +
++A special item that consists of (? followed by a number greater than zero and a +closing parenthesis is a recursive subroutine call of the subpattern of the +given number, provided that it occurs inside that subpattern. (If not, it is a +non-recursive subroutine +call, which is described in the next section.) The special item (?R) or (?0) is +a recursive call of the entire regular expression. +
++This PCRE pattern solves the nested parentheses problem (assume the +PCRE_EXTENDED option is set so that white space is ignored): +
+ \( ( [^()]++ | (?R) )* \) ++First it matches an opening parenthesis. Then it matches any number of +substrings which can either be a sequence of non-parentheses, or a recursive +match of the pattern itself (that is, a correctly parenthesized substring). +Finally there is a closing parenthesis. Note the use of a possessive quantifier +to avoid backtracking into sequences of non-parentheses. + +
+If this were part of a larger pattern, you would not want to recurse the entire +pattern, so instead you could use this: +
+ ( \( ( [^()]++ | (?1) )* \) ) ++We have put the pattern into parentheses, and caused the recursion to refer to +them instead of the whole pattern. + +
+In a larger pattern, keeping track of parenthesis numbers can be tricky. This +is made easier by the use of relative references. Instead of (?1) in the +pattern above you can write (?-2) to refer to the second most recently opened +parentheses preceding the recursion. In other words, a negative number counts +capturing parentheses leftwards from the point at which it is encountered. +
++It is also possible to refer to subsequently opened parentheses, by writing +references such as (?+2). However, these cannot be recursive because the +reference is not inside the parentheses that are referenced. They are always +non-recursive subroutine +calls, as described in the next section. +
++An alternative approach is to use named parentheses instead. The Perl syntax +for this is (?&name); PCRE's earlier syntax (?P>name) is also supported. We +could rewrite the above example as follows: +
+ (?<pn> \( ( [^()]++ | (?&pn) )* \) ) ++If there is more than one subpattern with the same name, the earliest one is +used. + +
+This particular example pattern that we have been looking at contains nested +unlimited repeats, and so the use of a possessive quantifier for matching +strings of non-parentheses is important when applying the pattern to strings +that do not match. For example, when this pattern is applied to +
+ (aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa() ++it yields "no match" quickly. However, if a possessive quantifier is not used, +the match runs for a very long time indeed because there are so many different +ways the + and * repeats can carve up the subject, and all have to be tested +before failure can be reported. + +
+At the end of a match, the values of capturing parentheses are those from +the outermost level. If you want to obtain intermediate values, a callout +function can be used (see below and the +pcrecallout +documentation). If the pattern above is matched against +
+ (ab(cd)ef) ++the value for the inner capturing parentheses (numbered 2) is "ef", which is +the last value taken on at the top level. If a capturing subpattern is not +matched at the top level, its final captured value is unset, even if it was +(temporarily) set at a deeper level during the matching process. + +
+If there are more than 15 capturing parentheses in a pattern, PCRE has to +obtain extra memory to store data during a recursion, which it does by using +pcre_malloc, freeing it via pcre_free afterwards. If no memory can +be obtained, the match fails with the PCRE_ERROR_NOMEMORY error. +
++Do not confuse the (?R) item with the condition (R), which tests for recursion. +Consider this pattern, which matches text in angle brackets, allowing for +arbitrary nesting. Only digits are allowed in nested brackets (that is, when +recursing), whereas any characters are permitted at the outer level. +
+ < (?: (?(R) \d++ | [^<>]*+) | (?R)) * > ++In this pattern, (?(R) is the start of a conditional subpattern, with two +different alternatives for the recursive and non-recursive cases. The (?R) item +is the actual recursive call. + +
+Recursion processing in PCRE differs from Perl in two important ways. In PCRE +(like Python, but unlike Perl), a recursive subpattern call is always treated +as an atomic group. That is, once it has matched some of the subject string, it +is never re-entered, even if it contains untried alternatives and there is a +subsequent matching failure. This can be illustrated by the following pattern, +which purports to match a palindromic string that contains an odd number of +characters (for example, "a", "aba", "abcba", "abcdcba"): +
+ ^(.|(.)(?1)\2)$ ++The idea is that it either matches a single character, or two identical +characters surrounding a sub-palindrome. In Perl, this pattern works; in PCRE +it does not if the pattern is longer than three characters. Consider the +subject string "abcba": + +
+At the top level, the first character is matched, but as it is not at the end +of the string, the first alternative fails; the second alternative is taken +and the recursion kicks in. The recursive call to subpattern 1 successfully +matches the next character ("b"). (Note that the beginning and end of line +tests are not part of the recursion). +
++Back at the top level, the next character ("c") is compared with what +subpattern 2 matched, which was "a". This fails. Because the recursion is +treated as an atomic group, there are now no backtracking points, and so the +entire match fails. (Perl is able, at this point, to re-enter the recursion and +try the second alternative.) However, if the pattern is written with the +alternatives in the other order, things are different: +
+ ^((.)(?1)\2|.)$ ++This time, the recursing alternative is tried first, and continues to recurse +until it runs out of characters, at which point the recursion fails. But this +time we do have another alternative to try at the higher level. That is the big +difference: in the previous case the remaining alternative is at a deeper +recursion level, which PCRE cannot use. + +
+To change the pattern so that it matches all palindromic strings, not just +those with an odd number of characters, it is tempting to change the pattern to +this: +
+ ^((.)(?1)\2|.?)$ ++Again, this works in Perl, but not in PCRE, and for the same reason. When a +deeper recursion has matched a single character, it cannot be entered again in +order to match an empty string. The solution is to separate the two cases, and +write out the odd and even cases as alternatives at the higher level: +
+ ^(?:((.)(?1)\2|)|((.)(?3)\4|.)) ++If you want to match typical palindromic phrases, the pattern has to ignore all +non-word characters, which can be done like this: +
+ ^\W*+(?:((.)\W*+(?1)\W*+\2|)|((.)\W*+(?3)\W*+\4|\W*+.\W*+))\W*+$ ++If run with the PCRE_CASELESS option, this pattern matches phrases such as "A +man, a plan, a canal: Panama!" and it works well in both PCRE and Perl. Note +the use of the possessive quantifier *+ to avoid backtracking into sequences of +non-word characters. Without this, PCRE takes a great deal longer (ten times or +more) to match typical phrases, and Perl takes so long that you think it has +gone into a loop. + +
+WARNING: The palindrome-matching patterns above work only if the subject +string does not start with a palindrome that is shorter than the entire string. +For example, although "abcba" is correctly matched, if the subject is "ababa", +PCRE finds the palindrome "aba" at the start, then fails at top level because +the end of the string does not follow. Once again, it cannot jump back into the +recursion to try other alternatives, so the entire match fails. +
++The second way in which PCRE and Perl differ in their recursion processing is +in the handling of captured values. In Perl, when a subpattern is called +recursively or as a subpattern (see the next section), it has no access to any +values that were captured outside the recursion, whereas in PCRE these values +can be referenced. Consider this pattern: +
+ ^(.)(\1|a(?2)) ++In PCRE, this pattern matches "bab". The first capturing parentheses match "b", +then in the second group, when the back reference \1 fails to match "b", the +second alternative matches "a" and then recurses. In the recursion, \1 does +now match "b" and so the whole match succeeds. In Perl, the pattern fails to +match because inside the recursive call \1 cannot access the externally set +value. + +
+If the syntax for a recursive subpattern call (either by number or by +name) is used outside the parentheses to which it refers, it operates like a +subroutine in a programming language. The called subpattern may be defined +before or after the reference. A numbered reference can be absolute or +relative, as in these examples: +
+ (...(absolute)...)...(?2)... + (...(relative)...)...(?-1)... + (...(?+1)...(relative)... ++An earlier example pointed out that the pattern +
+ (sens|respons)e and \1ibility ++matches "sense and sensibility" and "response and responsibility", but not +"sense and responsibility". If instead the pattern +
+ (sens|respons)e and (?1)ibility ++is used, it does match "sense and responsibility" as well as the other two +strings. Another example is given in the discussion of DEFINE above. + +
+All subroutine calls, whether recursive or not, are always treated as atomic +groups. That is, once a subroutine has matched some of the subject string, it +is never re-entered, even if it contains untried alternatives and there is a +subsequent matching failure. Any capturing parentheses that are set during the +subroutine call revert to their previous values afterwards. +
++Processing options such as case-independence are fixed when a subpattern is +defined, so if it is used as a subroutine, such options cannot be changed for +different calls. For example, consider this pattern: +
+ (abc)(?i:(?-1)) ++It matches "abcabc". It does not match "abcABC" because the change of +processing option does not affect the called subpattern. + +
+For compatibility with Oniguruma, the non-Perl syntax \g followed by a name or +a number enclosed either in angle brackets or single quotes, is an alternative +syntax for referencing a subpattern as a subroutine, possibly recursively. Here +are two of the examples used above, rewritten using this syntax: +
+ (?<pn> \( ( (?>[^()]+) | \g<pn> )* \) ) + (sens|respons)e and \g'1'ibility ++PCRE supports an extension to Oniguruma: if a number is preceded by a +plus or a minus sign it is taken as a relative reference. For example: +
+ (abc)(?i:\g<-1>) ++Note that \g{...} (Perl syntax) and \g<...> (Oniguruma syntax) are not +synonymous. The former is a back reference; the latter is a subroutine call. + +
+Perl has a feature whereby using the sequence (?{...}) causes arbitrary Perl +code to be obeyed in the middle of matching a regular expression. This makes it +possible, amongst other things, to extract different substrings that match the +same pair of parentheses when there is a repetition. +
++PCRE provides a similar feature, but of course it cannot obey arbitrary Perl +code. The feature is called "callout". The caller of PCRE provides an external +function by putting its entry point in the global variable pcre_callout +(8-bit library) or pcre[16|32]_callout (16-bit or 32-bit library). +By default, this variable contains NULL, which disables all calling out. +
++Within a regular expression, (?C) indicates the points at which the external +function is to be called. If you want to identify different callout points, you +can put a number less than 256 after the letter C. The default value is zero. +For example, this pattern has two callout points: +
+ (?C1)abc(?C2)def ++If the PCRE_AUTO_CALLOUT flag is passed to a compiling function, callouts are +automatically installed before each item in the pattern. They are all numbered +255. + +
+During matching, when PCRE reaches a callout point, the external function is +called. It is provided with the number of the callout, the position in the +pattern, and, optionally, one item of data originally supplied by the caller of +the matching function. The callout function may cause matching to proceed, to +backtrack, or to fail altogether. A complete description of the interface to +the callout function is given in the +pcrecallout +documentation. +
++Perl 5.10 introduced a number of "Special Backtracking Control Verbs", which +are described in the Perl documentation as "experimental and subject to change +or removal in a future version of Perl". It goes on to say: "Their usage in +production code should be noted to avoid problems during upgrades." The same +remarks apply to the PCRE features described in this section. +
++Since these verbs are specifically related to backtracking, most of them can be +used only when the pattern is to be matched using one of the traditional +matching functions, which use a backtracking algorithm. With the exception of +(*FAIL), which behaves like a failing negative assertion, they cause an error +if encountered by a DFA matching function. +
++If any of these verbs are used in an assertion or in a subpattern that is +called as a subroutine (whether or not recursively), their effect is confined +to that subpattern; it does not extend to the surrounding pattern, with one +exception: the name from a *(MARK), (*PRUNE), or (*THEN) that is encountered in +a successful positive assertion is passed back when a match succeeds +(compare capturing parentheses in assertions). Note that such subpatterns are +processed as anchored at the point where they are tested. Note also that Perl's +treatment of subroutines and assertions is different in some cases. +
++The new verbs make use of what was previously invalid syntax: an opening +parenthesis followed by an asterisk. They are generally of the form +(*VERB) or (*VERB:NAME). Some may take either form, with differing behaviour, +depending on whether or not an argument is present. A name is any sequence of +characters that does not include a closing parenthesis. The maximum length of +name is 255 in the 8-bit library and 65535 in the 16-bit and 32-bit library. +If the name is empty, that is, if the closing parenthesis immediately follows +the colon, the effect is as if the colon were not there. Any number of these +verbs may occur in a pattern. +
++PCRE contains some optimizations that are used to speed up matching by running +some checks at the start of each match attempt. For example, it may know the +minimum length of matching subject, or that a particular character must be +present. When one of these optimizations suppresses the running of a match, any +included backtracking verbs will not, of course, be processed. You can suppress +the start-of-match optimizations by setting the PCRE_NO_START_OPTIMIZE option +when calling pcre_compile() or pcre_exec(), or by starting the +pattern with (*NO_START_OPT). There is more discussion of this option in the +section entitled +"Option bits for pcre_exec()" +in the +pcreapi +documentation. +
++Experiments with Perl suggest that it too has similar optimizations, sometimes +leading to anomalous results. +
++The following verbs act as soon as they are encountered. They may not be +followed by a name. +
+ (*ACCEPT) ++This verb causes the match to end successfully, skipping the remainder of the +pattern. However, when it is inside a subpattern that is called as a +subroutine, only that subpattern is ended successfully. Matching then continues +at the outer level. If (*ACCEPT) is inside capturing parentheses, the data so +far is captured. For example: +
+ A((?:A|B(*ACCEPT)|C)D) ++This matches "AB", "AAD", or "ACD"; when it matches "AB", "B" is captured by +the outer parentheses. +
+ (*FAIL) or (*F) ++This verb causes a matching failure, forcing backtracking to occur. It is +equivalent to (?!) but easier to read. The Perl documentation notes that it is +probably useful only when combined with (?{}) or (??{}). Those are, of course, +Perl features that are not present in PCRE. The nearest equivalent is the +callout feature, as for example in this pattern: +
+ a+(?C)(*FAIL) ++A match with the string "aaaa" always fails, but the callout is taken before +each backtrack happens (in this example, 10 times). + +
+There is one verb whose main purpose is to track how a match was arrived at, +though it also has a secondary use in conjunction with advancing the match +starting point (see (*SKIP) below). +
+ (*MARK:NAME) or (*:NAME) ++A name is always required with this verb. There may be as many instances of +(*MARK) as you like in a pattern, and their names do not have to be unique. + +
+When a match succeeds, the name of the last-encountered (*MARK) on the matching +path is passed back to the caller as described in the section entitled +"Extra data for pcre_exec()" +in the +pcreapi +documentation. Here is an example of pcretest output, where the /K +modifier requests the retrieval and outputting of (*MARK) data: +
+ re> /X(*MARK:A)Y|X(*MARK:B)Z/K + data> XY + 0: XY + MK: A + XZ + 0: XZ + MK: B ++The (*MARK) name is tagged with "MK:" in this output, and in this example it +indicates which of the two alternatives matched. This is a more efficient way +of obtaining this information than putting each alternative in its own +capturing parentheses. + +
+If (*MARK) is encountered in a positive assertion, its name is recorded and +passed back if it is the last-encountered. This does not happen for negative +assertions. +
++After a partial match or a failed match, the name of the last encountered +(*MARK) in the entire match process is returned. For example: +
+ re> /X(*MARK:A)Y|X(*MARK:B)Z/K + data> XP + No match, mark = B ++Note that in this unanchored example the mark is retained from the match +attempt that started at the letter "X" in the subject. Subsequent match +attempts starting at "P" and then with an empty string do not get as far as the +(*MARK) item, but nevertheless do not reset it. + +
+If you are interested in (*MARK) values after failed matches, you should +probably set the PCRE_NO_START_OPTIMIZE option +(see above) +to ensure that the match is always attempted. +
++The following verbs do nothing when they are encountered. Matching continues +with what follows, but if there is no subsequent match, causing a backtrack to +the verb, a failure is forced. That is, backtracking cannot pass to the left of +the verb. However, when one of these verbs appears inside an atomic group, its +effect is confined to that group, because once the group has been matched, +there is never any backtracking into it. In this situation, backtracking can +"jump back" to the left of the entire atomic group. (Remember also, as stated +above, that this localization also applies in subroutine calls and assertions.) +
++These verbs differ in exactly what kind of failure occurs when backtracking +reaches them. +
+ (*COMMIT) ++This verb, which may not be followed by a name, causes the whole match to fail +outright if the rest of the pattern does not match. Even if the pattern is +unanchored, no further attempts to find a match by advancing the starting point +take place. Once (*COMMIT) has been passed, pcre_exec() is committed to +finding a match at the current starting point, or not at all. For example: +
+ a+(*COMMIT)b ++This matches "xxaab" but not "aacaab". It can be thought of as a kind of +dynamic anchor, or "I've started, so I must finish." The name of the most +recently passed (*MARK) in the path is passed back when (*COMMIT) forces a +match failure. + +
+Note that (*COMMIT) at the start of a pattern is not the same as an anchor, +unless PCRE's start-of-match optimizations are turned off, as shown in this +pcretest example: +
+ re> /(*COMMIT)abc/ + data> xyzabc + 0: abc + xyzabc\Y + No match ++PCRE knows that any match must start with "a", so the optimization skips along +the subject to "a" before running the first match attempt, which succeeds. When +the optimization is disabled by the \Y escape in the second subject, the match +starts at "x" and so the (*COMMIT) causes it to fail without trying any other +starting points. +
+ (*PRUNE) or (*PRUNE:NAME) ++This verb causes the match to fail at the current starting position in the +subject if the rest of the pattern does not match. If the pattern is +unanchored, the normal "bumpalong" advance to the next starting character then +happens. Backtracking can occur as usual to the left of (*PRUNE), before it is +reached, or when matching to the right of (*PRUNE), but if there is no match to +the right, backtracking cannot cross (*PRUNE). In simple cases, the use of +(*PRUNE) is just an alternative to an atomic group or possessive quantifier, +but there are some uses of (*PRUNE) that cannot be expressed in any other way. +The behaviour of (*PRUNE:NAME) is the same as (*MARK:NAME)(*PRUNE). In an +anchored pattern (*PRUNE) has the same effect as (*COMMIT). +
+ (*SKIP) ++This verb, when given without a name, is like (*PRUNE), except that if the +pattern is unanchored, the "bumpalong" advance is not to the next character, +but to the position in the subject where (*SKIP) was encountered. (*SKIP) +signifies that whatever text was matched leading up to it cannot be part of a +successful match. Consider: +
+ a+(*SKIP)b ++If the subject is "aaaac...", after the first match attempt fails (starting at +the first character in the string), the starting point skips on to start the +next attempt at "c". Note that a possessive quantifer does not have the same +effect as this example; although it would suppress backtracking during the +first match attempt, the second attempt would start at the second character +instead of skipping on to "c". +
+ (*SKIP:NAME) ++When (*SKIP) has an associated name, its behaviour is modified. If the +following pattern fails to match, the previous path through the pattern is +searched for the most recent (*MARK) that has the same name. If one is found, +the "bumpalong" advance is to the subject position that corresponds to that +(*MARK) instead of to where (*SKIP) was encountered. If no (*MARK) with a +matching name is found, the (*SKIP) is ignored. +
+ (*THEN) or (*THEN:NAME) ++This verb causes a skip to the next innermost alternative if the rest of the +pattern does not match. That is, it cancels pending backtracking, but only +within the current alternative. Its name comes from the observation that it can +be used for a pattern-based if-then-else block: +
+ ( COND1 (*THEN) FOO | COND2 (*THEN) BAR | COND3 (*THEN) BAZ ) ... ++If the COND1 pattern matches, FOO is tried (and possibly further items after +the end of the group if FOO succeeds); on failure, the matcher skips to the +second alternative and tries COND2, without backtracking into COND1. The +behaviour of (*THEN:NAME) is exactly the same as (*MARK:NAME)(*THEN). +If (*THEN) is not inside an alternation, it acts like (*PRUNE). + +
+Note that a subpattern that does not contain a | character is just a part of +the enclosing alternative; it is not a nested alternation with only one +alternative. The effect of (*THEN) extends beyond such a subpattern to the +enclosing alternative. Consider this pattern, where A, B, etc. are complex +pattern fragments that do not contain any | characters at this level: +
+ A (B(*THEN)C) | D ++If A and B are matched, but there is a failure in C, matching does not +backtrack into A; instead it moves to the next alternative, that is, D. +However, if the subpattern containing (*THEN) is given an alternative, it +behaves differently: +
+ A (B(*THEN)C | (*FAIL)) | D ++The effect of (*THEN) is now confined to the inner subpattern. After a failure +in C, matching moves to (*FAIL), which causes the whole subpattern to fail +because there are no more alternatives to try. In this case, matching does now +backtrack into A. + +
+Note also that a conditional subpattern is not considered as having two +alternatives, because only one is ever used. In other words, the | character in +a conditional subpattern has a different meaning. Ignoring white space, +consider: +
+ ^.*? (?(?=a) a | b(*THEN)c ) ++If the subject is "ba", this pattern does not match. Because .*? is ungreedy, +it initially matches zero characters. The condition (?=a) then fails, the +character "b" is matched, but "c" is not. At this point, matching does not +backtrack to .*? as might perhaps be expected from the presence of the | +character. The conditional subpattern is part of the single alternative that +comprises the whole pattern, and so the match fails. (If there was a backtrack +into .*?, allowing it to match "b", the match would succeed.) + +
+The verbs just described provide four different "strengths" of control when +subsequent matching fails. (*THEN) is the weakest, carrying on the match at the +next alternative. (*PRUNE) comes next, failing the match at the current +starting position, but allowing an advance to the next character (for an +unanchored pattern). (*SKIP) is similar, except that the advance may be more +than one character. (*COMMIT) is the strongest, causing the entire match to +fail. +
++If more than one such verb is present in a pattern, the "strongest" one wins. +For example, consider this pattern, where A, B, etc. are complex pattern +fragments: +
+ (A(*COMMIT)B(*THEN)C|D) ++Once A has matched, PCRE is committed to this match, at the current starting +position. If subsequently B matches, but C does not, the normal (*THEN) action +of trying the next alternative (that is, D) does not happen because (*COMMIT) +overrides. + +
+pcreapi(3), pcrecallout(3), pcrematching(3), +pcresyntax(3), pcre(3), pcre16(3), pcre32(3). +
+
+Philip Hazel
+
+University Computing Service
+
+Cambridge CB2 3QH, England.
+
+
+Last updated: 11 November 2012
+
+Copyright © 1997-2012 University of Cambridge.
+
+
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcreperform.html b/tools/pcre/doc/html/pcreperform.html new file mode 100644 index 00000000..dda207f9 --- /dev/null +++ b/tools/pcre/doc/html/pcreperform.html @@ -0,0 +1,195 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+PCRE PERFORMANCE
+
+
+Two aspects of performance are discussed below: memory usage and processing +time. The way you express your pattern as a regular expression can affect both +of them. +
++Patterns are compiled by PCRE into a reasonably efficient interpretive code, so +that most simple patterns do not use much memory. However, there is one case +where the memory usage of a compiled pattern can be unexpectedly large. If a +parenthesized subpattern has a quantifier with a minimum greater than 1 and/or +a limited maximum, the whole subpattern is repeated in the compiled code. For +example, the pattern +
+ (abc|def){2,4}
+
+is compiled as if it were
++ (abc|def)(abc|def)((abc|def)(abc|def)?)? ++(Technical aside: It is done this way so that backtrack points within each of +the repetitions can be independently maintained.) + +
+For regular expressions whose quantifiers use only small numbers, this is not +usually a problem. However, if the numbers are large, and particularly if such +repetitions are nested, the memory usage can become an embarrassment. For +example, the very simple pattern +
+ ((ab){1,1000}c){1,3}
+
+uses 51K bytes when compiled using the 8-bit library. When PCRE is compiled
+with its default internal pointer size of two bytes, the size limit on a
+compiled pattern is 64K data units, and this is reached with the above pattern
+if the outer repetition is increased from 3 to 4. PCRE can be compiled to use
+larger internal pointers and thus handle larger compiled patterns, but it is
+better to try to rewrite your pattern to use less memory if you can.
+
++One way of reducing the memory usage for such patterns is to make use of PCRE's +"subroutine" +facility. Re-writing the above pattern as +
+ ((ab)(?2){0,999}c)(?1){0,2}
+
+reduces the memory requirements to 18K, and indeed it remains under 20K even
+with the outer repetition increased to 100. However, this pattern is not
+exactly equivalent, because the "subroutine" calls are treated as
+atomic groups
+into which there can be no backtracking if there is a subsequent matching
+failure. Therefore, PCRE cannot do this kind of rewriting automatically.
+Furthermore, there is a noticeable loss of speed when executing the modified
+pattern. Nevertheless, if the atomic grouping is not a problem and the loss of
+speed is acceptable, this kind of rewriting will allow you to process patterns
+that PCRE cannot otherwise handle.
+
++When pcre_exec() or pcre[16|32]_exec() is used for matching, certain +kinds of pattern can cause it to use large amounts of the process stack. In +some environments the default process stack is quite small, and if it runs out +the result is often SIGSEGV. This issue is probably the most frequently raised +problem with PCRE. Rewriting your pattern can often help. The +pcrestack +documentation discusses this issue in detail. +
++Certain items in regular expression patterns are processed more efficiently +than others. It is more efficient to use a character class like [aeiou] than a +set of single-character alternatives such as (a|e|i|o|u). In general, the +simplest construction that provides the required behaviour is usually the most +efficient. Jeffrey Friedl's book contains a lot of useful general discussion +about optimizing regular expressions for efficient performance. This document +contains a few observations about PCRE. +
++Using Unicode character properties (the \p, \P, and \X escapes) is slow, +because PCRE has to use a multi-stage table lookup whenever it needs a +character's property. If you can find an alternative pattern that does not use +character properties, it will probably be faster. +
++By default, the escape sequences \b, \d, \s, and \w, and the POSIX +character classes such as [:alpha:] do not use Unicode properties, partly for +backwards compatibility, and partly for performance reasons. However, you can +set PCRE_UCP if you want Unicode character properties to be used. This can +double the matching time for items such as \d, when matched with +a traditional matching function; the performance loss is less with +a DFA matching function, and in both cases there is not much difference for +\b. +
++When a pattern begins with .* not in parentheses, or in parentheses that are +not the subject of a backreference, and the PCRE_DOTALL option is set, the +pattern is implicitly anchored by PCRE, since it can match only at the start of +a subject string. However, if PCRE_DOTALL is not set, PCRE cannot make this +optimization, because the . metacharacter does not then match a newline, and if +the subject string contains newlines, the pattern may match from the character +immediately following one of them instead of from the very start. For example, +the pattern +
+ .*second ++matches the subject "first\nand second" (where \n stands for a newline +character), with the match starting at the seventh character. In order to do +this, PCRE has to retry the match starting after every newline in the subject. + +
+If you are using such a pattern with subject strings that do not contain +newlines, the best performance is obtained by setting PCRE_DOTALL, or starting +the pattern with ^.* or ^.*? to indicate explicit anchoring. That saves PCRE +from having to scan along the subject looking for a newline to restart at. +
++Beware of patterns that contain nested indefinite repeats. These can take a +long time to run when applied to a string that does not match. Consider the +pattern fragment +
+ ^(a+)* ++This can match "aaaa" in 16 different ways, and this number increases very +rapidly as the string gets longer. (The * repeat can match 0, 1, 2, 3, or 4 +times, and for each of those cases other than 0 or 4, the + repeats can match +different numbers of times.) When the remainder of the pattern is such that the +entire match is going to fail, PCRE has in principle to try every possible +variation, and this can take an extremely long time, even for relatively short +strings. + +
+An optimization catches some of the more simple cases such as +
+ (a+)*b ++where a literal character follows. Before embarking on the standard matching +procedure, PCRE checks that there is a "b" later in the subject string, and if +there is not, it fails the match immediately. However, when there is no +following literal this optimization cannot be used. You can see the difference +by comparing the behaviour of +
+ (a+)*\d ++with the pattern above. The former gives a failure almost instantly when +applied to a whole line of "a" characters, whereas the latter takes an +appreciable time with strings longer than about 20 characters. + +
+In many cases, the solution to this kind of performance issue is to use an +atomic group or a possessive quantifier. +
+
+Philip Hazel
+
+University Computing Service
+
+Cambridge CB2 3QH, England.
+
+
+Last updated: 25 August 2012
+
+Copyright © 1997-2012 University of Cambridge.
+
+
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcreposix.html b/tools/pcre/doc/html/pcreposix.html new file mode 100644 index 00000000..0e5b296a --- /dev/null +++ b/tools/pcre/doc/html/pcreposix.html @@ -0,0 +1,292 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+#include <pcreposix.h> +
++int regcomp(regex_t *preg, const char *pattern, +int cflags); +
++int regexec(regex_t *preg, const char *string, +size_t nmatch, regmatch_t pmatch[], int eflags); +
++size_t regerror(int errcode, const regex_t *preg, +char *errbuf, size_t errbuf_size); +
++void regfree(regex_t *preg); +
++This set of functions provides a POSIX-style API for the PCRE regular +expression 8-bit library. See the +pcreapi +documentation for a description of PCRE's native API, which contains much +additional functionality. There is no POSIX-style wrapper for PCRE's 16-bit +and 32-bit library. +
++The functions described here are just wrapper functions that ultimately call +the PCRE native API. Their prototypes are defined in the pcreposix.h +header file, and on Unix systems the library itself is called +pcreposix.a, so can be accessed by adding -lpcreposix to the +command for linking an application that uses them. Because the POSIX functions +call the native ones, it is also necessary to add -lpcre. +
++I have implemented only those POSIX option bits that can be reasonably mapped +to PCRE native options. In addition, the option REG_EXTENDED is defined with +the value zero. This has no effect, but since programs that are written to the +POSIX interface often use it, this makes it easier to slot in PCRE as a +replacement library. Other POSIX options are not even defined. +
++There are also some other options that are not defined by POSIX. These have +been added at the request of users who want to make use of certain +PCRE-specific features via the POSIX calling interface. +
++When PCRE is called via these functions, it is only the API that is POSIX-like +in style. The syntax and semantics of the regular expressions themselves are +still those of Perl, subject to the setting of various PCRE options, as +described below. "POSIX-like in style" means that the API approximates to the +POSIX definition; it is not fully POSIX-compatible, and in multi-byte encoding +domains it is probably even less compatible. +
++The header for these functions is supplied as pcreposix.h to avoid any +potential clash with other POSIX libraries. It can, of course, be renamed or +aliased as regex.h, which is the "correct" name. It provides two +structure types, regex_t for compiled internal forms, and +regmatch_t for returning captured substrings. It also defines some +constants whose names start with "REG_"; these are used for setting options and +identifying error codes. +
++The function regcomp() is called to compile a pattern into an +internal form. The pattern is a C string terminated by a binary zero, and +is passed in the argument pattern. The preg argument is a pointer +to a regex_t structure that is used as a base for storing information +about the compiled regular expression. +
++The argument cflags is either zero, or contains one or more of the bits +defined by the following macros: +
+ REG_DOTALL ++The PCRE_DOTALL option is set when the regular expression is passed for +compilation to the native function. Note that REG_DOTALL is not part of the +POSIX standard. +
+ REG_ICASE ++The PCRE_CASELESS option is set when the regular expression is passed for +compilation to the native function. +
+ REG_NEWLINE ++The PCRE_MULTILINE option is set when the regular expression is passed for +compilation to the native function. Note that this does not mimic the +defined POSIX behaviour for REG_NEWLINE (see the following section). +
+ REG_NOSUB ++The PCRE_NO_AUTO_CAPTURE option is set when the regular expression is passed +for compilation to the native function. In addition, when a pattern that is +compiled with this flag is passed to regexec() for matching, the +nmatch and pmatch arguments are ignored, and no captured strings +are returned. +
+ REG_UCP ++The PCRE_UCP option is set when the regular expression is passed for +compilation to the native function. This causes PCRE to use Unicode properties +when matchine \d, \w, etc., instead of just recognizing ASCII values. Note +that REG_UTF8 is not part of the POSIX standard. +
+ REG_UNGREEDY ++The PCRE_UNGREEDY option is set when the regular expression is passed for +compilation to the native function. Note that REG_UNGREEDY is not part of the +POSIX standard. +
+ REG_UTF8 ++The PCRE_UTF8 option is set when the regular expression is passed for +compilation to the native function. This causes the pattern itself and all data +strings used for matching it to be treated as UTF-8 strings. Note that REG_UTF8 +is not part of the POSIX standard. + +
+In the absence of these flags, no options are passed to the native function. +This means the the regex is compiled with PCRE default semantics. In +particular, the way it handles newline characters in the subject string is the +Perl way, not the POSIX way. Note that setting PCRE_MULTILINE has only +some of the effects specified for REG_NEWLINE. It does not affect the way +newlines are matched by . (they are not) or by a negative class such as [^a] +(they are). +
++The yield of regcomp() is zero on success, and non-zero otherwise. The +preg structure is filled in on success, and one member of the structure +is public: re_nsub contains the number of capturing subpatterns in +the regular expression. Various error codes are defined in the header file. +
++NOTE: If the yield of regcomp() is non-zero, you must not attempt to +use the contents of the preg structure. If, for example, you pass it to +regexec(), the result is undefined and your program is likely to crash. +
++This area is not simple, because POSIX and Perl take different views of things. +It is not possible to get PCRE to obey POSIX semantics, but then PCRE was never +intended to be a POSIX engine. The following table lists the different +possibilities for matching newline characters in PCRE: +
+ Default Change with + + . matches newline no PCRE_DOTALL + newline matches [^a] yes not changeable + $ matches \n at end yes PCRE_DOLLARENDONLY + $ matches \n in middle no PCRE_MULTILINE + ^ matches \n in middle no PCRE_MULTILINE ++This is the equivalent table for POSIX: +
+ Default Change with + + . matches newline yes REG_NEWLINE + newline matches [^a] yes REG_NEWLINE + $ matches \n at end no REG_NEWLINE + $ matches \n in middle no REG_NEWLINE + ^ matches \n in middle no REG_NEWLINE ++PCRE's behaviour is the same as Perl's, except that there is no equivalent for +PCRE_DOLLAR_ENDONLY in Perl. In both PCRE and Perl, there is no way to stop +newline from matching [^a]. + +
+The default POSIX newline handling can be obtained by setting PCRE_DOTALL and +PCRE_DOLLAR_ENDONLY, but there is no way to make PCRE behave exactly as for the +REG_NEWLINE action. +
++The function regexec() is called to match a compiled pattern preg +against a given string, which is by default terminated by a zero byte +(but see REG_STARTEND below), subject to the options in eflags. These can +be: +
+ REG_NOTBOL ++The PCRE_NOTBOL option is set when calling the underlying PCRE matching +function. +
+ REG_NOTEMPTY ++The PCRE_NOTEMPTY option is set when calling the underlying PCRE matching +function. Note that REG_NOTEMPTY is not part of the POSIX standard. However, +setting this option can give more POSIX-like behaviour in some situations. +
+ REG_NOTEOL ++The PCRE_NOTEOL option is set when calling the underlying PCRE matching +function. +
+ REG_STARTEND ++The string is considered to start at string + pmatch[0].rm_so and +to have a terminating NUL located at string + pmatch[0].rm_eo +(there need not actually be a NUL at that location), regardless of the value of +nmatch. This is a BSD extension, compatible with but not specified by +IEEE Standard 1003.2 (POSIX.2), and should be used with caution in software +intended to be portable to other systems. Note that a non-zero rm_so does +not imply REG_NOTBOL; REG_STARTEND affects only the location of the string, not +how it is matched. + +
+If the pattern was compiled with the REG_NOSUB flag, no data about any matched +strings is returned. The nmatch and pmatch arguments of +regexec() are ignored. +
++If the value of nmatch is zero, or if the value pmatch is NULL, +no data about any matched strings is returned. +
++Otherwise,the portion of the string that was matched, and also any captured +substrings, are returned via the pmatch argument, which points to an +array of nmatch structures of type regmatch_t, containing the +members rm_so and rm_eo. These contain the offset to the first +character of each substring and the offset to the first character after the end +of each substring, respectively. The 0th element of the vector relates to the +entire portion of string that was matched; subsequent elements relate to +the capturing subpatterns of the regular expression. Unused entries in the +array have both structure members set to -1. +
++A successful match yields a zero return; various error codes are defined in the +header file, of which REG_NOMATCH is the "expected" failure code. +
++The regerror() function maps a non-zero errorcode from either +regcomp() or regexec() to a printable message. If preg is not +NULL, the error should have arisen from the use of that structure. A message +terminated by a binary zero is placed in errbuf. The length of the +message, including the zero, is limited to errbuf_size. The yield of the +function is the size of buffer needed to hold the whole message. +
++Compiling a regular expression causes memory to be allocated and associated +with the preg structure. The function regfree() frees all such +memory, after which preg may no longer be used as a compiled expression. +
+
+Philip Hazel
+
+University Computing Service
+
+Cambridge CB2 3QH, England.
+
+
+Last updated: 09 January 2012
+
+Copyright © 1997-2012 University of Cambridge.
+
+
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcreprecompile.html b/tools/pcre/doc/html/pcreprecompile.html new file mode 100644 index 00000000..beb9e242 --- /dev/null +++ b/tools/pcre/doc/html/pcreprecompile.html @@ -0,0 +1,158 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+If you are running an application that uses a large number of regular +expression patterns, it may be useful to store them in a precompiled form +instead of having to compile them every time the application is run. +If you are not using any private character tables (see the +pcre_maketables() +documentation), this is relatively straightforward. If you are using private +tables, it is a little bit more complicated. However, if you are using the +just-in-time optimization feature, it is not possible to save and reload the +JIT data. +
++If you save compiled patterns to a file, you can copy them to a different host +and run them there. If the two hosts have different endianness (byte order), +you should run the pcre[16|32]_pattern_to_host_byte_order() function on the +new host before trying to match the pattern. The matching functions return +PCRE_ERROR_BADENDIANNESS if they detect a pattern with the wrong endianness. +
++Compiling regular expressions with one version of PCRE for use with a different +version is not guaranteed to work and may cause crashes, and saving and +restoring a compiled pattern loses any JIT optimization data. +
++The value returned by pcre[16|32]_compile() points to a single block of +memory that holds the compiled pattern and associated data. You can find the +length of this block in bytes by calling pcre[16|32]_fullinfo() with an +argument of PCRE_INFO_SIZE. You can then save the data in any appropriate +manner. Here is sample code for the 8-bit library that compiles a pattern and +writes it to a file. It assumes that the variable fd refers to a file +that is open for output: +
+ int erroroffset, rc, size;
+ char *error;
+ pcre *re;
+
+ re = pcre_compile("my pattern", 0, &error, &erroroffset, NULL);
+ if (re == NULL) { ... handle errors ... }
+ rc = pcre_fullinfo(re, NULL, PCRE_INFO_SIZE, &size);
+ if (rc < 0) { ... handle errors ... }
+ rc = fwrite(re, 1, size, fd);
+ if (rc != size) { ... handle errors ... }
+
+In this example, the bytes that comprise the compiled pattern are copied
+exactly. Note that this is binary data that may contain any of the 256 possible
+byte values. On systems that make a distinction between binary and non-binary
+data, be sure that the file is opened for binary output.
+
++If you want to write more than one pattern to a file, you will have to devise a +way of separating them. For binary data, preceding each pattern with its length +is probably the most straightforward approach. Another possibility is to write +out the data in hexadecimal instead of binary, one pattern to a line. +
++Saving compiled patterns in a file is only one possible way of storing them for +later use. They could equally well be saved in a database, or in the memory of +some daemon process that passes them via sockets to the processes that want +them. +
++If the pattern has been studied, it is also possible to save the normal study +data in a similar way to the compiled pattern itself. However, if the +PCRE_STUDY_JIT_COMPILE was used, the just-in-time data that is created cannot +be saved because it is too dependent on the current environment. When studying +generates additional information, pcre[16|32]_study() returns a pointer to a +pcre[16|32]_extra data block. Its format is defined in the +section on matching a pattern +in the +pcreapi +documentation. The study_data field points to the binary study data, and +this is what you must save (not the pcre[16|32]_extra block itself). The +length of the study data can be obtained by calling pcre[16|32]_fullinfo() +with an argument of PCRE_INFO_STUDYSIZE. Remember to check that +pcre[16|32]_study() did return a non-NULL value before trying to save the +study data. +
++Re-using a precompiled pattern is straightforward. Having reloaded it into main +memory, called pcre[16|32]_pattern_to_host_byte_order() if necessary, +you pass its pointer to pcre[16|32]_exec() or pcre[16|32]_dfa_exec() in +the usual way. +
++However, if you passed a pointer to custom character tables when the pattern +was compiled (the tableptr argument of pcre[16|32]_compile()), you +must now pass a similar pointer to pcre[16|32]_exec() or +pcre[16|32]_dfa_exec(), because the value saved with the compiled pattern +will obviously be nonsense. A field in a pcre[16|32]_extra() block is used +to pass this data, as described in the +section on matching a pattern +in the +pcreapi +documentation. +
++If you did not provide custom character tables when the pattern was compiled, +the pointer in the compiled pattern is NULL, which causes the matching +functions to use PCRE's internal tables. Thus, you do not need to take any +special action at run time in this case. +
++If you saved study data with the compiled pattern, you need to create your own +pcre[16|32]_extra data block and set the study_data field to point to the +reloaded study data. You must also set the PCRE_EXTRA_STUDY_DATA bit in the +flags field to indicate that study data is present. Then pass the +pcre[16|32]_extra block to the matching function in the usual way. If the +pattern was studied for just-in-time optimization, that data cannot be saved, +and so is lost by a save/restore cycle. +
++In general, it is safest to recompile all saved patterns when you update to a +new PCRE release, though not all updates actually require this. +
+
+Philip Hazel
+
+University Computing Service
+
+Cambridge CB2 3QH, England.
+
+
+Last updated: 24 June 2012
+
+Copyright © 1997-2012 University of Cambridge.
+
+
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcresample.html b/tools/pcre/doc/html/pcresample.html new file mode 100644 index 00000000..aca9184e --- /dev/null +++ b/tools/pcre/doc/html/pcresample.html @@ -0,0 +1,110 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+PCRE SAMPLE PROGRAM
+
+
+A simple, complete demonstration program, to get you started with using PCRE, +is supplied in the file pcredemo.c in the PCRE distribution. A listing of +this program is given in the +pcredemo +documentation. If you do not have a copy of the PCRE distribution, you can save +this listing to re-create pcredemo.c. +
++The demonstration program, which uses the original PCRE 8-bit library, compiles +the regular expression that is its first argument, and matches it against the +subject string in its second argument. No PCRE options are set, and default +character tables are used. If matching succeeds, the program outputs the +portion of the subject that matched, together with the contents of any captured +substrings. +
++If the -g option is given on the command line, the program then goes on to +check for further matches of the same regular expression in the same subject +string. The logic is a little bit tricky because of the possibility of matching +an empty string. Comments in the code explain what is going on. +
++If PCRE is installed in the standard include and library directories for your +operating system, you should be able to compile the demonstration program using +this command: +
+ gcc -o pcredemo pcredemo.c -lpcre ++If PCRE is installed elsewhere, you may need to add additional options to the +command line. For example, on a Unix-like system that has PCRE installed in +/usr/local, you can compile the demonstration program using a command +like this: +
+ gcc -o pcredemo -I/usr/local/include pcredemo.c -L/usr/local/lib -lpcre ++In a Windows environment, if you want to statically link the program against a +non-dll pcre.a file, you must uncomment the line that defines PCRE_STATIC +before including pcre.h, because otherwise the pcre_malloc() and +pcre_free() exported functions will be declared +__declspec(dllimport), with unwanted results. + +
+Once you have compiled and linked the demonstration program, you can run simple +tests like this: +
+ ./pcredemo 'cat|dog' 'the cat sat on the mat' + ./pcredemo -g 'cat|dog' 'the dog sat on the cat' ++Note that there is a much more comprehensive test program, called +pcretest, +which supports many more facilities for testing regular expressions and both +PCRE libraries. The +pcredemo +program is provided as a simple coding example. + +
+If you try to run +pcredemo +when PCRE is not installed in the standard library directory, you may get an +error like this on some operating systems (e.g. Solaris): +
+ ld.so.1: a.out: fatal: libpcre.so.0: open failed: No such file or directory ++This is caused by the way shared library support works on those systems. You +need to add +
+ -R/usr/local/lib ++(for example) to the compile command to get round this problem. + +
+Philip Hazel
+
+University Computing Service
+
+Cambridge CB2 3QH, England.
+
+
+Last updated: 10 January 2012
+
+Copyright © 1997-2012 University of Cambridge.
+
+
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcrestack.html b/tools/pcre/doc/html/pcrestack.html new file mode 100644 index 00000000..af6406d0 --- /dev/null +++ b/tools/pcre/doc/html/pcrestack.html @@ -0,0 +1,225 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+PCRE DISCUSSION OF STACK USAGE
+
+
+When you call pcre[16|32]_exec(), it makes use of an internal function +called match(). This calls itself recursively at branch points in the +pattern, in order to remember the state of the match so that it can back up and +try a different alternative if the first one fails. As matching proceeds deeper +and deeper into the tree of possibilities, the recursion depth increases. The +match() function is also called in other circumstances, for example, +whenever a parenthesized sub-pattern is entered, and in certain cases of +repetition. +
++Not all calls of match() increase the recursion depth; for an item such +as a* it may be called several times at the same level, after matching +different numbers of a's. Furthermore, in a number of cases where the result of +the recursive call would immediately be passed back as the result of the +current call (a "tail recursion"), the function is just restarted instead. +
++The above comments apply when pcre[16|32]_exec() is run in its normal +interpretive manner. If the pattern was studied with the +PCRE_STUDY_JIT_COMPILE option, and just-in-time compiling was successful, and +the options passed to pcre[16|32]_exec() were not incompatible, the matching +process uses the JIT-compiled code instead of the match() function. In +this case, the memory requirements are handled entirely differently. See the +pcrejit +documentation for details. +
++The pcre[16|32]_dfa_exec() function operates in an entirely different way, +and uses recursion only when there is a regular expression recursion or +subroutine call in the pattern. This includes the processing of assertion and +"once-only" subpatterns, which are handled like subroutine calls. Normally, +these are never very deep, and the limit on the complexity of +pcre[16|32]_dfa_exec() is controlled by the amount of workspace it is given. +However, it is possible to write patterns with runaway infinite recursions; +such patterns will cause pcre[16|32]_dfa_exec() to run out of stack. At +present, there is no protection against this. +
++The comments that follow do NOT apply to pcre[16|32]_dfa_exec(); they are +relevant only for pcre[16|32]_exec() without the JIT optimization. +
++Each time that match() is actually called recursively, it uses memory +from the process stack. For certain kinds of pattern and data, very large +amounts of stack may be needed, despite the recognition of "tail recursion". +You can often reduce the amount of recursion, and therefore the amount of stack +used, by modifying the pattern that is being matched. Consider, for example, +this pattern: +
+ ([^<]|<(?!inet))+ ++It matches from wherever it starts until it encounters "<inet" or the end of +the data, and is the kind of pattern that might be used when processing an XML +file. Each iteration of the outer parentheses matches either one character that +is not "<" or a "<" that is not followed by "inet". However, each time a +parenthesis is processed, a recursion occurs, so this formulation uses a stack +frame for each matched character. For a long string, a lot of stack is +required. Consider now this rewritten pattern, which matches exactly the same +strings: +
+ ([^<]++|<(?!inet))+ ++This uses very much less stack, because runs of characters that do not contain +"<" are "swallowed" in one item inside the parentheses. Recursion happens only +when a "<" character that is not followed by "inet" is encountered (and we +assume this is relatively rare). A possessive quantifier is used to stop any +backtracking into the runs of non-"<" characters, but that is not related to +stack usage. + +
+This example shows that one way of avoiding stack problems when matching long +subject strings is to write repeated parenthesized subpatterns to match more +than one character whenever possible. +
++In environments where stack memory is constrained, you might want to compile +PCRE to use heap memory instead of stack for remembering back-up points when +pcre[16|32]_exec() is running. This makes it run a lot more slowly, however. +Details of how to do this are given in the +pcrebuild +documentation. When built in this way, instead of using the stack, PCRE obtains +and frees memory by calling the functions that are pointed to by the +pcre[16|32]_stack_malloc and pcre[16|32]_stack_free variables. By +default, these point to malloc() and free(), but you can replace +the pointers to cause PCRE to use your own functions. Since the block sizes are +always the same, and are always freed in reverse order, it may be possible to +implement customized memory handlers that are more efficient than the standard +functions. +
++You can set limits on the number of times that match() is called, both in +total and recursively. If a limit is exceeded, pcre[16|32]_exec() returns an +error code. Setting suitable limits should prevent it from running out of +stack. The default values of the limits are very large, and unlikely ever to +operate. They can be changed when PCRE is built, and they can also be set when +pcre[16|32]_exec() is called. For details of these interfaces, see the +pcrebuild +documentation and the +section on extra data for pcre[16|32]_exec() +in the +pcreapi +documentation. +
++As a very rough rule of thumb, you should reckon on about 500 bytes per +recursion. Thus, if you want to limit your stack usage to 8Mb, you should set +the limit at 16000 recursions. A 64Mb stack, on the other hand, can support +around 128000 recursions. +
++In Unix-like environments, the pcretest test program has a command line +option (-S) that can be used to increase the size of its stack. As long +as the stack is large enough, another option (-M) can be used to find the +smallest limits that allow a particular pattern to match a given subject +string. This is done by calling pcre[16|32]_exec() repeatedly with different +limits. +
++The actual amount of stack used per recursion can vary quite a lot, depending +on the compiler that was used to build PCRE and the optimization or debugging +options that were set for it. The rule of thumb value of 500 bytes mentioned +above may be larger or smaller than what is actually needed. A better +approximation can be obtained by running this command: +
+ pcretest -m -C ++The -C option causes pcretest to output information about the +options with which PCRE was compiled. When -m is also given (before +-C), information about stack use is given in a line like this: +
+ Match recursion uses stack: approximate frame size = 640 bytes ++The value is approximate because some recursions need a bit more (up to perhaps +16 more bytes). + +
+If the above command is given when PCRE is compiled to use the heap instead of +the stack for recursion, the value that is output is the size of each block +that is obtained from the heap. +
++In Unix-like environments, there is not often a problem with the stack unless +very long strings are involved, though the default limit on stack size varies +from system to system. Values from 8Mb to 64Mb are common. You can find your +default limit by running the command: +
+ ulimit -s ++Unfortunately, the effect of running out of stack is often SIGSEGV, though +sometimes a more explicit error message is given. You can normally increase the +limit on stack size by code such as this: +
+ struct rlimit rlim; + getrlimit(RLIMIT_STACK, &rlim); + rlim.rlim_cur = 100*1024*1024; + setrlimit(RLIMIT_STACK, &rlim); ++This reads the current limits (soft and hard) using getrlimit(), then +attempts to increase the soft limit to 100Mb using setrlimit(). You must +do this before calling pcre[16|32]_exec(). + +
+Using setrlimit(), as described above, should also work on Mac OS X. It +is also possible to set a stack size when linking a program. There is a +discussion about stack sizes in Mac OS X at this web site: +http://developer.apple.com/qa/qa2005/qa1419.html. +
+
+Philip Hazel
+
+University Computing Service
+
+Cambridge CB2 3QH, England.
+
+
+Last updated: 24 June 2012
+
+Copyright © 1997-2012 University of Cambridge.
+
+
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcresyntax.html b/tools/pcre/doc/html/pcresyntax.html new file mode 100644 index 00000000..22a253e2 --- /dev/null +++ b/tools/pcre/doc/html/pcresyntax.html @@ -0,0 +1,521 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+The full syntax and semantics of the regular expressions that are supported by +PCRE are described in the +pcrepattern +documentation. This document contains a quick-reference summary of the syntax. +
++
+ \x where x is non-alphanumeric is a literal x + \Q...\E treat enclosed characters as literal ++ +
+
+ \a alarm, that is, the BEL character (hex 07)
+ \cx "control-x", where x is any ASCII character
+ \e escape (hex 1B)
+ \f form feed (hex 0C)
+ \n newline (hex 0A)
+ \r carriage return (hex 0D)
+ \t tab (hex 09)
+ \ddd character with octal code ddd, or backreference
+ \xhh character with hex code hh
+ \x{hhh..} character with hex code hhh..
+
+
++
+ . any character except newline;
+ in dotall mode, any character whatsoever
+ \C one data unit, even in UTF mode (best avoided)
+ \d a decimal digit
+ \D a character that is not a decimal digit
+ \h a horizontal white space character
+ \H a character that is not a horizontal white space character
+ \N a character that is not a newline
+ \p{xx} a character with the xx property
+ \P{xx} a character without the xx property
+ \R a newline sequence
+ \s a white space character
+ \S a character that is not a white space character
+ \v a vertical white space character
+ \V a character that is not a vertical white space character
+ \w a "word" character
+ \W a "non-word" character
+ \X a Unicode extended grapheme cluster
+
+In PCRE, by default, \d, \D, \s, \S, \w, and \W recognize only ASCII
+characters, even in a UTF mode. However, this can be changed by setting the
+PCRE_UCP option.
+
++
+ C Other + Cc Control + Cf Format + Cn Unassigned + Co Private use + Cs Surrogate + + L Letter + Ll Lower case letter + Lm Modifier letter + Lo Other letter + Lt Title case letter + Lu Upper case letter + L& Ll, Lu, or Lt + + M Mark + Mc Spacing mark + Me Enclosing mark + Mn Non-spacing mark + + N Number + Nd Decimal number + Nl Letter number + No Other number + + P Punctuation + Pc Connector punctuation + Pd Dash punctuation + Pe Close punctuation + Pf Final punctuation + Pi Initial punctuation + Po Other punctuation + Ps Open punctuation + + S Symbol + Sc Currency symbol + Sk Modifier symbol + Sm Mathematical symbol + So Other symbol + + Z Separator + Zl Line separator + Zp Paragraph separator + Zs Space separator ++ +
+
+ Xan Alphanumeric: union of properties L and N + Xps POSIX space: property Z or tab, NL, VT, FF, CR + Xsp Perl space: property Z or tab, NL, FF, CR + Xwd Perl word: property Xan or underscore ++ +
+Arabic, +Armenian, +Avestan, +Balinese, +Bamum, +Batak, +Bengali, +Bopomofo, +Brahmi, +Braille, +Buginese, +Buhid, +Canadian_Aboriginal, +Carian, +Chakma, +Cham, +Cherokee, +Common, +Coptic, +Cuneiform, +Cypriot, +Cyrillic, +Deseret, +Devanagari, +Egyptian_Hieroglyphs, +Ethiopic, +Georgian, +Glagolitic, +Gothic, +Greek, +Gujarati, +Gurmukhi, +Han, +Hangul, +Hanunoo, +Hebrew, +Hiragana, +Imperial_Aramaic, +Inherited, +Inscriptional_Pahlavi, +Inscriptional_Parthian, +Javanese, +Kaithi, +Kannada, +Katakana, +Kayah_Li, +Kharoshthi, +Khmer, +Lao, +Latin, +Lepcha, +Limbu, +Linear_B, +Lisu, +Lycian, +Lydian, +Malayalam, +Mandaic, +Meetei_Mayek, +Meroitic_Cursive, +Meroitic_Hieroglyphs, +Miao, +Mongolian, +Myanmar, +New_Tai_Lue, +Nko, +Ogham, +Old_Italic, +Old_Persian, +Old_South_Arabian, +Old_Turkic, +Ol_Chiki, +Oriya, +Osmanya, +Phags_Pa, +Phoenician, +Rejang, +Runic, +Samaritan, +Saurashtra, +Sharada, +Shavian, +Sinhala, +Sora_Sompeng, +Sundanese, +Syloti_Nagri, +Syriac, +Tagalog, +Tagbanwa, +Tai_Le, +Tai_Tham, +Tai_Viet, +Takri, +Tamil, +Telugu, +Thaana, +Thai, +Tibetan, +Tifinagh, +Ugaritic, +Vai, +Yi. +
++
+ [...] positive character class + [^...] negative character class + [x-y] range (can be used for hex characters) + [[:xxx:]] positive POSIX named set + [[:^xxx:]] negative POSIX named set + + alnum alphanumeric + alpha alphabetic + ascii 0-127 + blank space or tab + cntrl control character + digit decimal digit + graph printing, excluding space + lower lower case letter + print printing, including space + punct printing, excluding alphanumeric + space white space + upper upper case letter + word same as \w + xdigit hexadecimal digit ++In PCRE, POSIX character set names recognize only ASCII characters by default, +but some of them use Unicode properties if PCRE_UCP is set. You can use +\Q...\E inside a character class. + +
+
+ ? 0 or 1, greedy
+ ?+ 0 or 1, possessive
+ ?? 0 or 1, lazy
+ * 0 or more, greedy
+ *+ 0 or more, possessive
+ *? 0 or more, lazy
+ + 1 or more, greedy
+ ++ 1 or more, possessive
+ +? 1 or more, lazy
+ {n} exactly n
+ {n,m} at least n, no more than m, greedy
+ {n,m}+ at least n, no more than m, possessive
+ {n,m}? at least n, no more than m, lazy
+ {n,} n or more, greedy
+ {n,}+ n or more, possessive
+ {n,}? n or more, lazy
+
+
++
+ \b word boundary + \B not a word boundary + ^ start of subject + also after internal newline in multiline mode + \A start of subject + $ end of subject + also before newline at end of subject + also before internal newline in multiline mode + \Z end of subject + also before newline at end of subject + \z end of subject + \G first matching position in subject ++ +
+
+ \K reset start of match ++ +
+
+ expr|expr|expr... ++ +
+
+ (...) capturing group + (?<name>...) named capturing group (Perl) + (?'name'...) named capturing group (Perl) + (?P<name>...) named capturing group (Python) + (?:...) non-capturing group + (?|...) non-capturing group; reset group numbers for + capturing groups in each alternative ++ +
+
+ (?>...) atomic, non-capturing group ++ +
+
+ (?#....) comment (not nestable) ++ +
+
+ (?i) caseless + (?J) allow duplicate names + (?m) multiline + (?s) single line (dotall) + (?U) default ungreedy (lazy) + (?x) extended (ignore white space) + (?-...) unset option(s) ++The following are recognized only at the start of a pattern or after one of the +newline-setting options with similar syntax: +
+ (*NO_START_OPT) no start-match optimization (PCRE_NO_START_OPTIMIZE) + (*UTF8) set UTF-8 mode: 8-bit library (PCRE_UTF8) + (*UTF16) set UTF-16 mode: 16-bit library (PCRE_UTF16) + (*UTF32) set UTF-32 mode: 32-bit library (PCRE_UTF32) + (*UTF) set appropriate UTF mode for the library in use + (*UCP) set PCRE_UCP (use Unicode properties for \d etc) ++ +
+
+ (?=...) positive look ahead + (?!...) negative look ahead + (?<=...) positive look behind + (?<!...) negative look behind ++Each top-level branch of a look behind must be of a fixed length. + +
+
+ \n reference by number (can be ambiguous)
+ \gn reference by number
+ \g{n} reference by number
+ \g{-n} relative reference by number
+ \k<name> reference by name (Perl)
+ \k'name' reference by name (Perl)
+ \g{name} reference by name (Perl)
+ \k{name} reference by name (.NET)
+ (?P=name) reference by name (Python)
+
+
++
+ (?R) recurse whole pattern + (?n) call subpattern by absolute number + (?+n) call subpattern by relative number + (?-n) call subpattern by relative number + (?&name) call subpattern by name (Perl) + (?P>name) call subpattern by name (Python) + \g<name> call subpattern by name (Oniguruma) + \g'name' call subpattern by name (Oniguruma) + \g<n> call subpattern by absolute number (Oniguruma) + \g'n' call subpattern by absolute number (Oniguruma) + \g<+n> call subpattern by relative number (PCRE extension) + \g'+n' call subpattern by relative number (PCRE extension) + \g<-n> call subpattern by relative number (PCRE extension) + \g'-n' call subpattern by relative number (PCRE extension) ++ +
+
+ (?(condition)yes-pattern)
+ (?(condition)yes-pattern|no-pattern)
+
+ (?(n)... absolute reference condition
+ (?(+n)... relative reference condition
+ (?(-n)... relative reference condition
+ (?(<name>)... named reference condition (Perl)
+ (?('name')... named reference condition (Perl)
+ (?(name)... named reference condition (PCRE)
+ (?(R)... overall recursion condition
+ (?(Rn)... specific group recursion condition
+ (?(R&name)... specific recursion condition
+ (?(DEFINE)... define subpattern for reference
+ (?(assert)... assertion condition
+
+
++The following act immediately they are reached: +
+ (*ACCEPT) force successful match + (*FAIL) force backtrack; synonym (*F) + (*MARK:NAME) set name to be passed back; synonym (*:NAME) ++The following act only when a subsequent match failure causes a backtrack to +reach them. They all force a match failure, but they differ in what happens +afterwards. Those that advance the start-of-match point do so only if the +pattern is not anchored. +
+ (*COMMIT) overall failure, no advance of starting point + (*PRUNE) advance to next starting character + (*PRUNE:NAME) equivalent to (*MARK:NAME)(*PRUNE) + (*SKIP) advance to current matching position + (*SKIP:NAME) advance to position corresponding to an earlier + (*MARK:NAME); if not found, the (*SKIP) is ignored + (*THEN) local failure, backtrack to next alternation + (*THEN:NAME) equivalent to (*MARK:NAME)(*THEN) ++ +
+These are recognized only at the very start of the pattern or after a +(*BSR_...), (*UTF8), (*UTF16), (*UTF32) or (*UCP) option. +
+ (*CR) carriage return only + (*LF) linefeed only + (*CRLF) carriage return followed by linefeed + (*ANYCRLF) all three of the above + (*ANY) any Unicode newline sequence ++ +
+These are recognized only at the very start of the pattern or after a +(*...) option that sets the newline convention or a UTF or UCP mode. +
+ (*BSR_ANYCRLF) CR, LF, or CRLF + (*BSR_UNICODE) any Unicode newline sequence ++ +
+
+ (?C) callout + (?Cn) callout with data n ++ +
+pcrepattern(3), pcreapi(3), pcrecallout(3), +pcrematching(3), pcre(3). +
+
+Philip Hazel
+
+University Computing Service
+
+Cambridge CB2 3QH, England.
+
+
+Last updated: 11 November 2012
+
+Copyright © 1997-2012 University of Cambridge.
+
+
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcretest.html b/tools/pcre/doc/html/pcretest.html new file mode 100644 index 00000000..8423ba5a --- /dev/null +++ b/tools/pcre/doc/html/pcretest.html @@ -0,0 +1,1082 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+pcretest [options] [input file [output file]]
+
+
+pcretest was written as a test program for the PCRE regular expression
+library itself, but it can also be used for experimenting with regular
+expressions. This document describes the features of the test program; for
+details of the regular expressions themselves, see the
+pcrepattern
+documentation. For details of the PCRE library function calls and their
+options, see the
+pcreapi
+,
+pcre16
+and
+pcre32
+documentation.
+
+The input for pcretest is a sequence of regular expression patterns and +strings to be matched, as described below. The output shows the result of each +match. Options on the command line and the patterns control PCRE options and +exactly what is output. +
++As PCRE has evolved, it has acquired many different features, and as a result, +pcretest now has rather a lot of obscure options for testing every +possible feature. Some of these options are specifically designed for use in +conjunction with the test script and data files that are distributed as part of +PCRE, and are unlikely to be of use otherwise. They are all documented here, +but without much justification. +
++From release 8.30, two separate PCRE libraries can be built. The original one +supports 8-bit character strings, whereas the newer 16-bit library supports +character strings encoded in 16-bit units. From release 8.32, a third +library can be built, supporting character strings encoded in 32-bit units. +The pcretest program can be +used to test all three libraries. However, it is itself still an 8-bit program, +reading 8-bit input and writing 8-bit output. When testing the 16-bit or 32-bit +library, the patterns and data strings are converted to 16- or 32-bit format +before being passed to the PCRE library functions. Results are converted to +8-bit for output. +
++References to functions and structures of the form pcre[16|32]_xx below +mean "pcre_xx when using the 8-bit library or pcre16_xx when using +the 16-bit library". +
++-8 +If both the 8-bit library has been built, this option causes the 8-bit library +to be used (which is the default); if the 8-bit library has not been built, +this option causes an error. +
++-16 +If both the 8-bit or the 32-bit, and the 16-bit libraries have been built, this +option causes the 16-bit library to be used. If only the 16-bit library has been +built, this is the default (so has no effect). If only the 8-bit or the 32-bit +library has been built, this option causes an error. +
++-32 +If both the 8-bit or the 16-bit, and the 32-bit libraries have been built, this +option causes the 32-bit library to be used. If only the 32-bit library has been +built, this is the default (so has no effect). If only the 8-bit or the 16-bit +library has been built, this option causes an error. +
++-b +Behave as if each pattern has the /B (show byte code) modifier; the +internal form is output after compilation. +
++-C +Output the version number of the PCRE library, and all available information +about the optional features that are included, and then exit. All other options +are ignored. +
++-C option +Output information about a specific build-time option, then exit. This +functionality is intended for use in scripts such as RunTest. The +following options output the value indicated: +
+ ebcdic-nl the code for LF (= NL) in an EBCDIC environment: + 0x15 or 0x25 + 0 if used in an ASCII environment + linksize the internal link size (2, 3, or 4) + newline the default newline setting: + CR, LF, CRLF, ANYCRLF, or ANY ++The following options output 1 for true or zero for false: +
+ ebcdic compiled for an EBCDIC environment + jit just-in-time support is available + pcre16 the 16-bit library was built + pcre32 the 32-bit library was built + pcre8 the 8-bit library was built + ucp Unicode property support is available + utf UTF-8 and/or UTF-16 and/or UTF-32 support is available ++ +
+-d +Behave as if each pattern has the /D (debug) modifier; the internal +form and information about the compiled pattern is output after compilation; +-d is equivalent to -b -i. +
++-dfa +Behave as if each data line contains the \D escape sequence; this causes the +alternative matching function, pcre[16|32]_dfa_exec(), to be used instead +of the standard pcre[16|32]_exec() function (more detail is given below). +
++-help +Output a brief summary these options and then exit. +
++-i +Behave as if each pattern has the /I modifier; information about the +compiled pattern is given after compilation. +
++-M +Behave as if each data line contains the \M escape sequence; this causes +PCRE to discover the minimum MATCH_LIMIT and MATCH_LIMIT_RECURSION settings by +calling pcre[16|32]_exec() repeatedly with different limits. +
++-m +Output the size of each compiled pattern after it has been compiled. This is +equivalent to adding /M to each regular expression. The size is given in +bytes for both libraries. +
++-o osize +Set the number of elements in the output vector that is used when calling +pcre[16|32]_exec() or pcre[16|32]_dfa_exec() to be osize. The +default value is 45, which is enough for 14 capturing subexpressions for +pcre[16|32]_exec() or 22 different matches for +pcre[16|32]_dfa_exec(). +The vector size can be changed for individual matching calls by including \O +in the data line (see below). +
++-p +Behave as if each pattern has the /P modifier; the POSIX wrapper API is +used to call PCRE. None of the other options has any effect when -p is +set. This option can be used only with the 8-bit library. +
++-q +Do not output the version number of pcretest at the start of execution. +
++-S size +On Unix-like systems, set the size of the run-time stack to size +megabytes. +
++-s or -s+ +Behave as if each pattern has the /S modifier; in other words, force each +pattern to be studied. If -s+ is used, all the JIT compile options are +passed to pcre[16|32]_study(), causing just-in-time optimization to be set +up if it is available, for both full and partial matching. Specific JIT compile +options can be selected by following -s+ with a digit in the range 1 to +7, which selects the JIT compile modes as follows: +
+ 1 normal match only + 2 soft partial match only + 3 normal match and soft partial match + 4 hard partial match only + 6 soft and hard partial match + 7 all three modes (default) ++If -s++ is used instead of -s+ (with or without a following digit), +the text "(JIT)" is added to the first output line after a match or no match +when JIT-compiled code was actually used. +
+-t +Run each compile, study, and match many times with a timer, and output +resulting time per compile or match (in milliseconds). Do not set -m with +-t, because you will then get the size output a zillion times, and the +timing will be distorted. You can control the number of iterations that are +used for timing by following -t with a number (as a separate item on the +command line). For example, "-t 1000" would iterate 1000 times. The default is +to iterate 500000 times. +
++-tm +This is like -t except that it times only the matching phase, not the +compile or study phases. +
++If pcretest is given two filename arguments, it reads from the first and +writes to the second. If it is given only one filename argument, it reads from +that file and writes to stdout. Otherwise, it reads from stdin and writes to +stdout, and prompts for each line of input, using "re>" to prompt for regular +expressions, and "data>" to prompt for data lines. +
++When pcretest is built, a configuration option can specify that it should +be linked with the libreadline library. When this is done, if the input +is from a terminal, it is read using the readline() function. This +provides line-editing and history facilities. The output from the -help +option states whether or not readline() will be used. +
++The program handles any number of sets of input on a single input file. Each +set starts with a regular expression, and continues with any number of data +lines to be matched against the pattern. +
++Each data line is matched separately and independently. If you want to do +multi-line matches, you have to use the \n escape sequence (or \r or \r\n, +etc., depending on the newline setting) in a single line of input to encode the +newline sequences. There is no limit on the length of data lines; the input +buffer is automatically extended if it is too small. +
++An empty line signals the end of the data lines, at which point a new regular +expression is read. The regular expressions are given enclosed in any +non-alphanumeric delimiters other than backslash, for example: +
+ /(a|bc)x+yz/ ++White space before the initial delimiter is ignored. A regular expression may +be continued over several input lines, in which case the newline characters are +included within it. It is possible to include the delimiter within the pattern +by escaping it, for example +
+ /abc\/def/ ++If you do so, the escape and the delimiter form part of the pattern, but since +delimiters are always non-alphanumeric, this does not affect its interpretation. +If the terminating delimiter is immediately followed by a backslash, for +example, +
+ /abc/\ ++then a backslash is added to the end of the pattern. This is done to provide a +way of testing the error condition that arises if a pattern finishes with a +backslash, because +
+ /abc\/ ++is interpreted as the first line of a pattern that starts with "abc/", causing +pcretest to read the next line as a continuation of the regular expression. + +
+A pattern may be followed by any number of modifiers, which are mostly single +characters, though some of these can be qualified by further characters. +Following Perl usage, these are referred to below as, for example, "the +/i modifier", even though the delimiter of the pattern need not always be +a slash, and no slash is used when writing modifiers. White space may appear +between the final pattern delimiter and the first modifier, and between the +modifiers themselves. For reference, here is a complete list of modifiers. They +fall into several groups that are described in detail in the following +sections. +
+ /8 set UTF mode + /? disable UTF validity check + /+ show remainder of subject after match + /= show all captures (not just those that are set) + + /A set PCRE_ANCHORED + /B show compiled code + /C set PCRE_AUTO_CALLOUT + /D same as /B plus /I + /E set PCRE_DOLLAR_ENDONLY + /F flip byte order in compiled pattern + /f set PCRE_FIRSTLINE + /G find all matches (shorten string) + /g find all matches (use startoffset) + /I show information about pattern + /i set PCRE_CASELESS + /J set PCRE_DUPNAMES + /K show backtracking control names + /L set locale + /M show compiled memory size + /m set PCRE_MULTILINE + /N set PCRE_NO_AUTO_CAPTURE + /P use the POSIX wrapper + /S study the pattern after compilation + /s set PCRE_DOTALL + /T select character tables + /U set PCRE_UNGREEDY + /W set PCRE_UCP + /X set PCRE_EXTRA + /x set PCRE_EXTENDED + /Y set PCRE_NO_START_OPTIMIZE + /Z don't show lengths in /B output + + /<any> set PCRE_NEWLINE_ANY + /<anycrlf> set PCRE_NEWLINE_ANYCRLF + /<cr> set PCRE_NEWLINE_CR + /<crlf> set PCRE_NEWLINE_CRLF + /<lf> set PCRE_NEWLINE_LF + /<bsr_anycrlf> set PCRE_BSR_ANYCRLF + /<bsr_unicode> set PCRE_BSR_UNICODE + /<JS> set PCRE_JAVASCRIPT_COMPAT + ++ +
+The /i, /m, /s, and /x modifiers set the PCRE_CASELESS, +PCRE_MULTILINE, PCRE_DOTALL, or PCRE_EXTENDED options, respectively, when +pcre[16|32]_compile() is called. These four modifier letters have the same +effect as they do in Perl. For example: +
+ /caseless/i + ++ +
+The following table shows additional modifiers for setting PCRE compile-time +options that do not correspond to anything in Perl: +
+ /8 PCRE_UTF8 ) when using the 8-bit + /? PCRE_NO_UTF8_CHECK ) library + + /8 PCRE_UTF16 ) when using the 16-bit + /? PCRE_NO_UTF16_CHECK ) library + + /8 PCRE_UTF32 ) when using the 32-bit + /? PCRE_NO_UTF32_CHECK ) library + + /A PCRE_ANCHORED + /C PCRE_AUTO_CALLOUT + /E PCRE_DOLLAR_ENDONLY + /f PCRE_FIRSTLINE + /J PCRE_DUPNAMES + /N PCRE_NO_AUTO_CAPTURE + /U PCRE_UNGREEDY + /W PCRE_UCP + /X PCRE_EXTRA + /Y PCRE_NO_START_OPTIMIZE + /<any> PCRE_NEWLINE_ANY + /<anycrlf> PCRE_NEWLINE_ANYCRLF + /<cr> PCRE_NEWLINE_CR + /<crlf> PCRE_NEWLINE_CRLF + /<lf> PCRE_NEWLINE_LF + /<bsr_anycrlf> PCRE_BSR_ANYCRLF + /<bsr_unicode> PCRE_BSR_UNICODE + /<JS> PCRE_JAVASCRIPT_COMPAT ++The modifiers that are enclosed in angle brackets are literal strings as shown, +including the angle brackets, but the letters within can be in either case. +This example sets multiline matching with CRLF as the line ending sequence: +
+ /^abc/m<CRLF> ++As well as turning on the PCRE_UTF8/16/32 option, the /8 modifier causes +all non-printing characters in output strings to be printed using the +\x{hh...} notation. Otherwise, those less than 0x100 are output in hex without +the curly brackets. + +
+Full details of the PCRE options are given in the +pcreapi +documentation. +
++Searching for all possible matches within each subject string can be requested +by the /g or /G modifier. After finding a match, PCRE is called +again to search the remainder of the subject string. The difference between +/g and /G is that the former uses the startoffset argument to +pcre[16|32]_exec() to start searching at a new point within the entire +string (which is in effect what Perl does), whereas the latter passes over a +shortened substring. This makes a difference to the matching process if the +pattern begins with a lookbehind assertion (including \b or \B). +
++If any call to pcre[16|32]_exec() in a /g or /G sequence matches +an empty string, the next call is done with the PCRE_NOTEMPTY_ATSTART and +PCRE_ANCHORED flags set in order to search for another, non-empty, match at the +same point. If this second match fails, the start offset is advanced, and the +normal match is retried. This imitates the way Perl handles such cases when +using the /g modifier or the split() function. Normally, the start +offset is advanced by one character, but if the newline convention recognizes +CRLF as a newline, and the current character is CR followed by LF, an advance +of two is used. +
++There are yet more modifiers for controlling the way pcretest +operates. +
++The /+ modifier requests that as well as outputting the substring that +matched the entire pattern, pcretest should in addition output the +remainder of the subject string. This is useful for tests where the subject +contains multiple copies of the same substring. If the + modifier appears +twice, the same action is taken for captured substrings. In each case the +remainder is output on the following line with a plus character following the +capture number. Note that this modifier must not immediately follow the /S +modifier because /S+ and /S++ have other meanings. +
++The /= modifier requests that the values of all potential captured +parentheses be output after a match. By default, only those up to the highest +one actually used in the match are output (corresponding to the return code +from pcre[16|32]_exec()). Values in the offsets vector corresponding to +higher numbers should be set to -1, and these are output as "<unset>". This +modifier gives a way of checking that this is happening. +
++The /B modifier is a debugging feature. It requests that pcretest +output a representation of the compiled code after compilation. Normally this +information contains length and offset values; however, if /Z is also +present, this data is replaced by spaces. This is a special feature for use in +the automatic test scripts; it ensures that the same output is generated for +different internal link sizes. +
++The /D modifier is a PCRE debugging feature, and is equivalent to +/BI, that is, both the /B and the /I modifiers. +
++The /F modifier causes pcretest to flip the byte order of the +2-byte and 4-byte fields in the compiled pattern. This facility is for testing +the feature in PCRE that allows it to execute patterns that were compiled on a +host with a different endianness. This feature is not available when the POSIX +interface to PCRE is being used, that is, when the /P pattern modifier is +specified. See also the section about saving and reloading compiled patterns +below. +
++The /I modifier requests that pcretest output information about the +compiled pattern (whether it is anchored, has a fixed first character, and +so on). It does this by calling pcre[16|32]_fullinfo() after compiling a +pattern. If the pattern is studied, the results of that are also output. +
++The /K modifier requests pcretest to show names from backtracking +control verbs that are returned from calls to pcre[16|32]_exec(). It causes +pcretest to create a pcre[16|32]_extra block if one has not already +been created by a call to pcre[16|32]_study(), and to set the +PCRE_EXTRA_MARK flag and the mark field within it, every time that +pcre[16|32]_exec() is called. If the variable that the mark field +points to is non-NULL for a match, non-match, or partial match, pcretest +prints the string to which it points. For a match, this is shown on a line by +itself, tagged with "MK:". For a non-match it is added to the message. +
++The /L modifier must be followed directly by the name of a locale, for +example, +
+ /pattern/Lfr_FR ++For this reason, it must be the last modifier. The given locale is set, +pcre[16|32]_maketables() is called to build a set of character tables for +the locale, and this is then passed to pcre[16|32]_compile() when compiling +the regular expression. Without an /L (or /T) modifier, NULL is +passed as the tables pointer; that is, /L applies only to the expression +on which it appears. + +
+The /M modifier causes the size in bytes of the memory block used to hold +the compiled pattern to be output. This does not include the size of the +pcre[16|32] block; it is just the actual compiled data. If the pattern is +successfully studied with the PCRE_STUDY_JIT_COMPILE option, the size of the +JIT compiled code is also output. +
++The /S modifier causes pcre[16|32]_study() to be called after the +expression has been compiled, and the results used when the expression is +matched. There are a number of qualifying characters that may follow /S. +They may appear in any order. +
++If S is followed by an exclamation mark, pcre[16|32]_study() is called +with the PCRE_STUDY_EXTRA_NEEDED option, causing it always to return a +pcre_extra block, even when studying discovers no useful information. +
++If /S is followed by a second S character, it suppresses studying, even +if it was requested externally by the -s command line option. This makes +it possible to specify that certain patterns are always studied, and others are +never studied, independently of -s. This feature is used in the test +files in a few cases where the output is different when the pattern is studied. +
++If the /S modifier is followed by a + character, the call to +pcre[16|32]_study() is made with all the JIT study options, requesting +just-in-time optimization support if it is available, for both normal and +partial matching. If you want to restrict the JIT compiling modes, you can +follow /S+ with a digit in the range 1 to 7: +
+ 1 normal match only + 2 soft partial match only + 3 normal match and soft partial match + 4 hard partial match only + 6 soft and hard partial match + 7 all three modes (default) ++If /S++ is used instead of /S+ (with or without a following digit), +the text "(JIT)" is added to the first output line after a match or no match +when JIT-compiled code was actually used. + +
+Note that there is also an independent /+ modifier; it must not be given +immediately after /S or /S+ because this will be misinterpreted. +
++If JIT studying is successful, the compiled JIT code will automatically be used +when pcre[16|32]_exec() is run, except when incompatible run-time options +are specified. For more details, see the +pcrejit +documentation. See also the \J escape sequence below for a way of +setting the size of the JIT stack. +
++Finally, if /S is followed by a minus character, JIT compilation is +suppressed, even if it was requested externally by the -s command line +option. This makes it possible to specify that JIT is never to be used for +certain patterns. +
++The /T modifier must be followed by a single digit. It causes a specific +set of built-in character tables to be passed to pcre[16|32]_compile(). It +is used in the standard PCRE tests to check behaviour with different character +tables. The digit specifies the tables as follows: +
+ 0 the default ASCII tables, as distributed in + pcre_chartables.c.dist + 1 a set of tables defining ISO 8859 characters ++In table 1, some characters whose codes are greater than 128 are identified as +letters, digits, spaces, etc. + +
+The /P modifier causes pcretest to call PCRE via the POSIX wrapper +API rather than its native API. This supports only the 8-bit library. When +/P is set, the following modifiers set options for the regcomp() +function: +
+ /i REG_ICASE + /m REG_NEWLINE + /N REG_NOSUB + /s REG_DOTALL ) + /U REG_UNGREEDY ) These options are not part of + /W REG_UCP ) the POSIX standard + /8 REG_UTF8 ) ++The /+ modifier works as described above. All other modifiers are +ignored. + +
+Before each data line is passed to pcre[16|32]_exec(), leading and trailing +white space is removed, and it is then scanned for \ escapes. Some of these +are pretty esoteric features, intended for checking out some of the more +complicated features of PCRE. If you are just testing "ordinary" regular +expressions, you probably don't need any of these. The following escapes are +recognized: +
+ \a alarm (BEL, \x07)
+ \b backspace (\x08)
+ \e escape (\x27)
+ \f form feed (\x0c)
+ \n newline (\x0a)
+ \qdd set the PCRE_MATCH_LIMIT limit to dd (any number of digits)
+ \r carriage return (\x0d)
+ \t tab (\x09)
+ \v vertical tab (\x0b)
+ \nnn octal character (up to 3 octal digits); always
+ a byte unless > 255 in UTF-8 or 16-bit or 32-bit mode
+ \xhh hexadecimal byte (up to 2 hex digits)
+ \x{hh...} hexadecimal character (any number of hex digits)
+ \A pass the PCRE_ANCHORED option to pcre[16|32]_exec() or pcre[16|32]_dfa_exec()
+ \B pass the PCRE_NOTBOL option to pcre[16|32]_exec() or pcre[16|32]_dfa_exec()
+ \Cdd call pcre[16|32]_copy_substring() for substring dd after a successful match (number less than 32)
+ \Cname call pcre[16|32]_copy_named_substring() for substring "name" after a successful match (name termin-
+ ated by next non alphanumeric character)
+ \C+ show the current captured substrings at callout time
+ \C- do not supply a callout function
+ \C!n return 1 instead of 0 when callout number n is reached
+ \C!n!m return 1 instead of 0 when callout number n is reached for the nth time
+ \C*n pass the number n (may be negative) as callout data; this is used as the callout return value
+ \D use the pcre[16|32]_dfa_exec() match function
+ \F only shortest match for pcre[16|32]_dfa_exec()
+ \Gdd call pcre[16|32]_get_substring() for substring dd after a successful match (number less than 32)
+ \Gname call pcre[16|32]_get_named_substring() for substring "name" after a successful match (name termin-
+ ated by next non-alphanumeric character)
+ \Jdd set up a JIT stack of dd kilobytes maximum (any number of digits)
+ \L call pcre[16|32]_get_substringlist() after a successful match
+ \M discover the minimum MATCH_LIMIT and MATCH_LIMIT_RECURSION settings
+ \N pass the PCRE_NOTEMPTY option to pcre[16|32]_exec() or pcre[16|32]_dfa_exec(); if used twice, pass the
+ PCRE_NOTEMPTY_ATSTART option
+ \Odd set the size of the output vector passed to pcre[16|32]_exec() to dd (any number of digits)
+ \P pass the PCRE_PARTIAL_SOFT option to pcre[16|32]_exec() or pcre[16|32]_dfa_exec(); if used twice, pass the
+ PCRE_PARTIAL_HARD option
+ \Qdd set the PCRE_MATCH_LIMIT_RECURSION limit to dd (any number of digits)
+ \R pass the PCRE_DFA_RESTART option to pcre[16|32]_dfa_exec()
+ \S output details of memory get/free calls during matching
+ \Y pass the PCRE_NO_START_OPTIMIZE option to pcre[16|32]_exec() or pcre[16|32]_dfa_exec()
+ \Z pass the PCRE_NOTEOL option to pcre[16|32]_exec() or pcre[16|32]_dfa_exec()
+ \? pass the PCRE_NO_UTF[8|16|32]_CHECK option to pcre[16|32]_exec() or pcre[16|32]_dfa_exec()
+ \>dd start the match at offset dd (optional "-"; then any number of digits); this sets the startoffset
+ argument for pcre[16|32]_exec() or pcre[16|32]_dfa_exec()
+ \<cr> pass the PCRE_NEWLINE_CR option to pcre[16|32]_exec() or pcre[16|32]_dfa_exec()
+ \<lf> pass the PCRE_NEWLINE_LF option to pcre[16|32]_exec() or pcre[16|32]_dfa_exec()
+ \<crlf> pass the PCRE_NEWLINE_CRLF option to pcre[16|32]_exec() or pcre[16|32]_dfa_exec()
+ \<anycrlf> pass the PCRE_NEWLINE_ANYCRLF option to pcre[16|32]_exec() or pcre[16|32]_dfa_exec()
+ \<any> pass the PCRE_NEWLINE_ANY option to pcre[16|32]_exec() or pcre[16|32]_dfa_exec()
+
+The use of \x{hh...} is not dependent on the use of the /8 modifier on
+the pattern. It is recognized always. There may be any number of hexadecimal
+digits inside the braces; invalid values provoke error messages.
+
++Note that \xhh specifies one byte rather than one character in UTF-8 mode; +this makes it possible to construct invalid UTF-8 sequences for testing +purposes. On the other hand, \x{hh} is interpreted as a UTF-8 character in +UTF-8 mode, generating more than one byte if the value is greater than 127. +When testing the 8-bit library not in UTF-8 mode, \x{hh} generates one byte +for values less than 256, and causes an error for greater values. +
++In UTF-16 mode, all 4-digit \x{hhhh} values are accepted. This makes it +possible to construct invalid UTF-16 sequences for testing purposes. +
++In UTF-32 mode, all 4- to 8-digit \x{...} values are accepted. This makes it +possible to construct invalid UTF-32 sequences for testing purposes. +
++The escapes that specify line ending sequences are literal strings, exactly as +shown. No more than one newline setting should be present in any data line. +
++A backslash followed by anything else just escapes the anything else. If +the very last character is a backslash, it is ignored. This gives a way of +passing an empty line as data, since a real empty line terminates the data +input. +
++The \J escape provides a way of setting the maximum stack size that is +used by the just-in-time optimization code. It is ignored if JIT optimization +is not being used. Providing a stack that is larger than the default 32K is +necessary only for very complicated patterns. +
++If \M is present, pcretest calls pcre[16|32]_exec() several times, +with different values in the match_limit and match_limit_recursion +fields of the pcre[16|32]_extra data structure, until it finds the minimum +numbers for each parameter that allow pcre[16|32]_exec() to complete without +error. Because this is testing a specific feature of the normal interpretive +pcre[16|32]_exec() execution, the use of any JIT optimization that might +have been set up by the /S+ qualifier of -s+ option is disabled. +
++The match_limit number is a measure of the amount of backtracking +that takes place, and checking it out can be instructive. For most simple +matches, the number is quite small, but for patterns with very large numbers of +matching possibilities, it can become large very quickly with increasing length +of subject string. The match_limit_recursion number is a measure of how +much stack (or, if PCRE is compiled with NO_RECURSE, how much heap) memory is +needed to complete the match attempt. +
++When \O is used, the value specified may be higher or lower than the size set +by the -O command line option (or defaulted to 45); \O applies only to +the call of pcre[16|32]_exec() for the line in which it appears. +
++If the /P modifier was present on the pattern, causing the POSIX wrapper +API to be used, the only option-setting sequences that have any effect are \B, +\N, and \Z, causing REG_NOTBOL, REG_NOTEMPTY, and REG_NOTEOL, respectively, +to be passed to regexec(). +
++By default, pcretest uses the standard PCRE matching function, +pcre[16|32]_exec() to match each data line. PCRE also supports an +alternative matching function, pcre[16|32]_dfa_test(), which operates in a +different way, and has some restrictions. The differences between the two +functions are described in the +pcrematching +documentation. +
++If a data line contains the \D escape sequence, or if the command line +contains the -dfa option, the alternative matching function is used. +This function finds all possible matches at a given point. If, however, the \F +escape sequence is present in the data line, it stops after the first match is +found. This is always the shortest possible match. +
++This section describes the output when the normal matching function, +pcre[16|32]_exec(), is being used. +
++When a match succeeds, pcretest outputs the list of captured substrings +that pcre[16|32]_exec() returns, starting with number 0 for the string that +matched the whole pattern. Otherwise, it outputs "No match" when the return is +PCRE_ERROR_NOMATCH, and "Partial match:" followed by the partially matching +substring when pcre[16|32]_exec() returns PCRE_ERROR_PARTIAL. (Note that +this is the entire substring that was inspected during the partial match; it +may include characters before the actual match start if a lookbehind assertion, +\K, \b, or \B was involved.) For any other return, pcretest outputs +the PCRE negative error number and a short descriptive phrase. If the error is +a failed UTF string check, the offset of the start of the failing character and +the reason code are also output, provided that the size of the output vector is +at least two. Here is an example of an interactive pcretest run. +
+ $ pcretest + PCRE version 8.13 2011-04-30 + + re> /^abc(\d+)/ + data> abc123 + 0: abc123 + 1: 123 + data> xyz + No match ++Unset capturing substrings that are not followed by one that is set are not +returned by pcre[16|32]_exec(), and are not shown by pcretest. In the +following example, there are two capturing substrings, but when the first data +line is matched, the second, unset substring is not shown. An "internal" unset +substring is shown as "<unset>", as for the second data line. +
+ re> /(a)|(b)/ + data> a + 0: a + 1: a + data> b + 0: b + 1: <unset> + 2: b ++If the strings contain any non-printing characters, they are output as \xhh +escapes if the value is less than 256 and UTF mode is not set. Otherwise they +are output as \x{hh...} escapes. See below for the definition of non-printing +characters. If the pattern has the /+ modifier, the output for substring +0 is followed by the the rest of the subject string, identified by "0+" like +this: +
+ re> /cat/+ + data> cataract + 0: cat + 0+ aract ++If the pattern has the /g or /G modifier, the results of successive +matching attempts are output in sequence, like this: +
+ re> /\Bi(\w\w)/g + data> Mississippi + 0: iss + 1: ss + 0: iss + 1: ss + 0: ipp + 1: pp ++"No match" is output only if the first match attempt fails. Here is an example +of a failure message (the offset 4 that is specified by \>4 is past the end of +the subject string): +
+ re> /xyz/ + data> xyz\>4 + Error -24 (bad offset value) ++ +
+If any of the sequences \C, \G, or \L are present in a +data line that is successfully matched, the substrings extracted by the +convenience functions are output with C, G, or L after the string number +instead of a colon. This is in addition to the normal full list. The string +length (that is, the return from the extraction function) is given in +parentheses after each string for \C and \G. +
++Note that whereas patterns can be continued over several lines (a plain ">" +prompt is used for continuations), data lines may not. However newlines can be +included in data by means of the \n escape (or \r, \r\n, etc., depending on +the newline sequence setting). +
++When the alternative matching function, pcre[16|32]_dfa_exec(), is used (by +means of the \D escape sequence or the -dfa command line option), the +output consists of a list of all the matches that start at the first point in +the subject where there is at least one match. For example: +
+ re> /(tang|tangerine|tan)/ + data> yellow tangerine\D + 0: tangerine + 1: tang + 2: tan ++(Using the normal matching function on this data finds only "tang".) The +longest matching string is always given first (and numbered zero). After a +PCRE_ERROR_PARTIAL return, the output is "Partial match:", followed by the +partially matching substring. (Note that this is the entire substring that was +inspected during the partial match; it may include characters before the actual +match start if a lookbehind assertion, \K, \b, or \B was involved.) + +
+If /g is present on the pattern, the search for further matches resumes +at the end of the longest match. For example: +
+ re> /(tang|tangerine|tan)/g + data> yellow tangerine and tangy sultana\D + 0: tangerine + 1: tang + 2: tan + 0: tang + 1: tan + 0: tan ++Since the matching function does not support substring capture, the escape +sequences that are concerned with captured substrings are not relevant. + +
+When the alternative matching function has given the PCRE_ERROR_PARTIAL return, +indicating that the subject partially matched the pattern, you can restart the +match with additional subject data by means of the \R escape sequence. For +example: +
+ re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/ + data> 23ja\P\D + Partial match: 23ja + data> n05\R\D + 0: n05 ++For further information about partial matching, see the +pcrepartial +documentation. + +
+If the pattern contains any callout requests, pcretest's callout function +is called during matching. This works with both matching functions. By default, +the called function displays the callout number, the start and current +positions in the text at the callout time, and the next pattern item to be +tested. For example: +
+ --->pqrabcdef + 0 ^ ^ \d ++This output indicates that callout number 0 occurred for a match attempt +starting at the fourth character of the subject string, when the pointer was at +the seventh character of the data, and when the next pattern item was \d. Just +one circumflex is output if the start and current positions are the same. + +
+Callouts numbered 255 are assumed to be automatic callouts, inserted as a +result of the /C pattern modifier. In this case, instead of showing the +callout number, the offset in the pattern, preceded by a plus, is output. For +example: +
+ re> /\d?[A-E]\*/C + data> E* + --->E* + +0 ^ \d? + +3 ^ [A-E] + +8 ^^ \* + +10 ^ ^ + 0: E* ++If a pattern contains (*MARK) items, an additional line is output whenever +a change of latest mark is passed to the callout function. For example: +
+ re> /a(*MARK:X)bc/C + data> abc + --->abc + +0 ^ a + +1 ^^ (*MARK:X) + +10 ^^ b + Latest Mark: X + +11 ^ ^ c + +12 ^ ^ + 0: abc ++The mark changes between matching "a" and "b", but stays the same for the rest +of the match, so nothing more is output. If, as a result of backtracking, the +mark reverts to being unset, the text "<unset>" is output. + +
+The callout function in pcretest returns zero (carry on matching) by +default, but you can use a \C item in a data line (as described above) to +change this and other parameters of the callout. +
++Inserting callouts can be helpful when using pcretest to check +complicated regular expressions. For further information about callouts, see +the +pcrecallout +documentation. +
++When pcretest is outputting text in the compiled version of a pattern, +bytes other than 32-126 are always treated as non-printing characters are are +therefore shown as hex escapes. +
++When pcretest is outputting text that is a matched part of a subject +string, it behaves in the same way, unless a different locale has been set for +the pattern (using the /L modifier). In this case, the isprint() +function to distinguish printing and non-printing characters. +
++The facilities described in this section are not available when the POSIX +interface to PCRE is being used, that is, when the /P pattern modifier is +specified. +
++When the POSIX interface is not in use, you can cause pcretest to write a +compiled pattern to a file, by following the modifiers with > and a file name. +For example: +
+ /pattern/im >/some/file ++See the +pcreprecompile +documentation for a discussion about saving and re-using compiled patterns. +Note that if the pattern was successfully studied with JIT optimization, the +JIT data cannot be saved. + +
+The data that is written is binary. The first eight bytes are the length of the +compiled pattern data followed by the length of the optional study data, each +written as four bytes in big-endian order (most significant byte first). If +there is no study data (either the pattern was not studied, or studying did not +return any data), the second length is zero. The lengths are followed by an +exact copy of the compiled pattern. If there is additional study data, this +(excluding any JIT data) follows immediately after the compiled pattern. After +writing the file, pcretest expects to read a new pattern. +
++A saved pattern can be reloaded into pcretest by specifying < and a file +name instead of a pattern. The name of the file must not contain a < character, +as otherwise pcretest will interpret the line as a pattern delimited by < +characters. +For example: +
+ re> </some/file + Compiled pattern loaded from /some/file + No study data ++If the pattern was previously studied with the JIT optimization, the JIT +information cannot be saved and restored, and so is lost. When the pattern has +been loaded, pcretest proceeds to read data lines in the usual way. + +
+You can copy a file written by pcretest to a different host and reload it +there, even if the new host has opposite endianness to the one on which the +pattern was compiled. For example, you can compile on an i86 machine and run on +a SPARC machine. When a pattern is reloaded on a host with different +endianness, the confirmation message is changed to: +
+ Compiled pattern (byte-inverted) loaded from /some/file ++The test suite contains some saved pre-compiled patterns with different +endianness. These are reloaded using "<!" instead of just "<". This suppresses +the "(byte-inverted)" text so that the output is the same on all hosts. It also +forces debugging output once the pattern has been reloaded. + +
+File names for saving and reloading can be absolute or relative, but note that +the shell facility of expanding a file name that starts with a tilde (~) is not +available. +
++The ability to save and reload files in pcretest is intended for testing +and experimentation. It is not intended for production use because only a +single pattern can be written to a file. Furthermore, there is no facility for +supplying custom character tables for use with a reloaded pattern. If the +original pattern was compiled with custom tables, an attempt to match a subject +string using a reloaded pattern is likely to cause pcretest to crash. +Finally, if you attempt to load a file that is not in the correct format, the +result is undefined. +
++pcre(3), pcre16(3), pcre32(3), pcreapi(3), +pcrecallout(3), +pcrejit, pcrematching(3), pcrepartial(d), +pcrepattern(3), pcreprecompile(3). +
+
+Philip Hazel
+
+University Computing Service
+
+Cambridge CB2 3QH, England.
+
+
+Last updated: 10 September 2012
+
+Copyright © 1997-2012 University of Cambridge.
+
+
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/html/pcreunicode.html b/tools/pcre/doc/html/pcreunicode.html new file mode 100644 index 00000000..c3c51eac --- /dev/null +++ b/tools/pcre/doc/html/pcreunicode.html @@ -0,0 +1,270 @@ + + ++Return to the PCRE index page. +
+
+This page is part of the PCRE HTML documentation. It was generated automatically
+from the original man page. If there is any nonsense in it, please consult the
+man page, in case the conversion went wrong.
+
+
+UTF-8, UTF-16, UTF-32, AND UNICODE PROPERTY SUPPORT
+
+
+As well as UTF-8 support, PCRE also supports UTF-16 (from release 8.30) and +UTF-32 (from release 8.32), by means of two additional libraries. They can be +built as well as, or instead of, the 8-bit library. +
++In order process UTF-8 strings, you must build PCRE's 8-bit library with UTF +support, and, in addition, you must call +pcre_compile() +with the PCRE_UTF8 option flag, or the pattern must start with the sequence +(*UTF8) or (*UTF). When either of these is the case, both the pattern and any +subject strings that are matched against it are treated as UTF-8 strings +instead of strings of individual 1-byte characters. +
++In order process UTF-16 or UTF-32 strings, you must build PCRE's 16-bit or +32-bit library with UTF support, and, in addition, you must call +pcre16_compile() +or +pcre32_compile() +with the PCRE_UTF16 or PCRE_UTF32 option flag, as appropriate. Alternatively, +the pattern must start with the sequence (*UTF16), (*UTF32), as appropriate, or +(*UTF), which can be used with either library. When UTF mode is set, both the +pattern and any subject strings that are matched against it are treated as +UTF-16 or UTF-32 strings instead of strings of individual 16-bit or 32-bit +characters. +
++If you compile PCRE with UTF support, but do not use it at run time, the +library will be a bit bigger, but the additional run time overhead is limited +to testing the PCRE_UTF[8|16|32] flag occasionally, so should not be very big. +
++If PCRE is built with Unicode character property support (which implies UTF +support), the escape sequences \p{..}, \P{..}, and \X can be used. +The available properties that can be tested are limited to the general +category properties such as Lu for an upper case letter or Nd for a decimal +number, the Unicode script names such as Arabic or Han, and the derived +properties Any and L&. Full lists is given in the +pcrepattern +and +pcresyntax +documentation. Only the short names for properties are supported. For example, +\p{L} matches a letter. Its Perl synonym, \p{Letter}, is not supported. +Furthermore, in Perl, many properties may optionally be prefixed by "Is", for +compatibility with Perl 5.6. PCRE does not support this. +
++When you set the PCRE_UTF8 flag, the byte strings passed as patterns and +subjects are (by default) checked for validity on entry to the relevant +functions. The entire string is checked before any other processing takes +place. From release 7.3 of PCRE, the check is according the rules of RFC 3629, +which are themselves derived from the Unicode specification. Earlier releases +of PCRE followed the rules of RFC 2279, which allows the full range of 31-bit +values (0 to 0x7FFFFFFF). The current check allows only values in the range U+0 +to U+10FFFF, excluding the surrogate area and the non-characters. +
++Characters in the "Surrogate Area" of Unicode are reserved for use by UTF-16, +where they are used in pairs to encode codepoints with values greater than +0xFFFF. The code points that are encoded by UTF-16 pairs are available +independently in the UTF-8 and UTF-32 encodings. (In other words, the whole +surrogate thing is a fudge for UTF-16 which unfortunately messes up UTF-8 and +UTF-32.) +
++Also excluded are the "Non-Character" code points, which are U+FDD0 to U+FDEF +and the last two code points in each plane, U+??FFFE and U+??FFFF. +
++If an invalid UTF-8 string is passed to PCRE, an error return is given. At +compile time, the only additional information is the offset to the first byte +of the failing character. The run-time functions pcre_exec() and +pcre_dfa_exec() also pass back this information, as well as a more +detailed reason code if the caller has provided memory in which to do this. +
++In some situations, you may already know that your strings are valid, and +therefore want to skip these checks in order to improve performance, for +example in the case of a long subject string that is being scanned repeatedly. +If you set the PCRE_NO_UTF8_CHECK flag at compile time or at run time, PCRE +assumes that the pattern or subject it is given (respectively) contains only +valid UTF-8 codes. In this case, it does not diagnose an invalid UTF-8 string. +
++Note that passing PCRE_NO_UTF8_CHECK to pcre_compile() just disables the +check for the pattern; it does not also apply to subject strings. If you want +to disable the check for a subject string you must pass this option to +pcre_exec() or pcre_dfa_exec(). +
++If you pass an invalid UTF-8 string when PCRE_NO_UTF8_CHECK is set, the result +is undefined and your program may crash. +
++When you set the PCRE_UTF16 flag, the strings of 16-bit data units that are +passed as patterns and subjects are (by default) checked for validity on entry +to the relevant functions. Values other than those in the surrogate range +U+D800 to U+DFFF are independent code points. Values in the surrogate range +must be used in pairs in the correct manner. +
++Excluded are the "Non-Character" code points, which are U+FDD0 to U+FDEF +and the last two code points in each plane, U+??FFFE and U+??FFFF. +
++If an invalid UTF-16 string is passed to PCRE, an error return is given. At +compile time, the only additional information is the offset to the first data +unit of the failing character. The run-time functions pcre16_exec() and +pcre16_dfa_exec() also pass back this information, as well as a more +detailed reason code if the caller has provided memory in which to do this. +
++In some situations, you may already know that your strings are valid, and +therefore want to skip these checks in order to improve performance. If you set +the PCRE_NO_UTF16_CHECK flag at compile time or at run time, PCRE assumes that +the pattern or subject it is given (respectively) contains only valid UTF-16 +sequences. In this case, it does not diagnose an invalid UTF-16 string. +However, if an invalid string is passed, the result is undefined. +
++When you set the PCRE_UTF32 flag, the strings of 32-bit data units that are +passed as patterns and subjects are (by default) checked for validity on entry +to the relevant functions. This check allows only values in the range U+0 +to U+10FFFF, excluding the surrogate area U+D800 to U+DFFF, and the +"Non-Character" code points, which are U+FDD0 to U+FDEF and the last two +characters in each plane, U+??FFFE and U+??FFFF. +
++If an invalid UTF-32 string is passed to PCRE, an error return is given. At +compile time, the only additional information is the offset to the first data +unit of the failing character. The run-time functions pcre32_exec() and +pcre32_dfa_exec() also pass back this information, as well as a more +detailed reason code if the caller has provided memory in which to do this. +
++In some situations, you may already know that your strings are valid, and +therefore want to skip these checks in order to improve performance. If you set +the PCRE_NO_UTF32_CHECK flag at compile time or at run time, PCRE assumes that +the pattern or subject it is given (respectively) contains only valid UTF-32 +sequences. In this case, it does not diagnose an invalid UTF-32 string. +However, if an invalid string is passed, the result is undefined. +
++1. Codepoints less than 256 can be specified in patterns by either braced or +unbraced hexadecimal escape sequences (for example, \x{b3} or \xb3). Larger +values have to use braced sequences. +
++2. Octal numbers up to \777 are recognized, and in UTF-8 mode they match +two-byte characters for values greater than \177. +
++3. Repeat quantifiers apply to complete UTF characters, not to individual +data units, for example: \x{100}{3}. +
++4. The dot metacharacter matches one UTF character instead of a single data +unit. +
++5. The escape sequence \C can be used to match a single byte in UTF-8 mode, or +a single 16-bit data unit in UTF-16 mode, or a single 32-bit data unit in +UTF-32 mode, but its use can lead to some strange effects because it breaks up +multi-unit characters (see the description of \C in the +pcrepattern +documentation). The use of \C is not supported in the alternative matching +function pcre[16|32]_dfa_exec(), nor is it supported in UTF mode by the +JIT optimization of pcre[16|32]_exec(). If JIT optimization is requested +for a UTF pattern that contains \C, it will not succeed, and so the matching +will be carried out by the normal interpretive function. +
++6. The character escapes \b, \B, \d, \D, \s, \S, \w, and \W correctly +test characters of any code value, but, by default, the characters that PCRE +recognizes as digits, spaces, or word characters remain the same set as in +non-UTF mode, all with values less than 256. This remains true even when PCRE +is built to include Unicode property support, because to do otherwise would +slow down PCRE in many common cases. Note in particular that this applies to +\b and \B, because they are defined in terms of \w and \W. If you really +want to test for a wider sense of, say, "digit", you can use explicit Unicode +property tests such as \p{Nd}. Alternatively, if you set the PCRE_UCP option, +the way that the character escapes work is changed so that Unicode properties +are used to determine which characters match. There are more details in the +section on +generic character types +in the +pcrepattern +documentation. +
++7. Similarly, characters that match the POSIX named character classes are all +low-valued characters, unless the PCRE_UCP option is set. +
++8. However, the horizontal and vertical white space matching escapes (\h, \H, +\v, and \V) do match all the appropriate Unicode characters, whether or not +PCRE_UCP is set. +
++9. Case-insensitive matching applies only to characters whose values are less +than 128, unless PCRE is built with Unicode property support. A few Unicode +characters such as Greek sigma have more than two codepoints that are +case-equivalent. Up to and including PCRE release 8.31, only one-to-one case +mappings were supported, but later releases (with Unicode property support) do +treat as case-equivalent all versions of characters such as Greek sigma. +
+
+Philip Hazel
+
+University Computing Service
+
+Cambridge CB2 3QH, England.
+
+
+Last updated: 11 November 2012
+
+Copyright © 1997-2012 University of Cambridge.
+
+
+Return to the PCRE index page. +
diff --git a/tools/pcre/doc/index.html.src b/tools/pcre/doc/index.html.src new file mode 100644 index 00000000..c7bc196b --- /dev/null +++ b/tools/pcre/doc/index.html.src @@ -0,0 +1,180 @@ + + + ++The HTML documentation for PCRE comprises the following pages: +
+ +| pcre | +Introductory page |
| pcre16 | +Discussion of the 16-bit PCRE library |
| pcre32 | +Discussion of the 32-bit PCRE library |
| pcre-config | +Information about the installation configuration |
| pcreapi | +PCRE's native API |
| pcrebuild | +Options for building PCRE |
| pcrecallout | +The callout facility |
| pcrecompat | +Compability with Perl |
| pcrecpp | +The C++ wrapper for the PCRE library |
| pcredemo | +A demonstration C program that uses the PCRE library |
| pcregrep | +The pcregrep command |
| pcrejit | +Discussion of the just-in-time optimization support |
| pcrelimits | +Details of size and other limits |
| pcrematching | +Discussion of the two matching algorithms |
| pcrepartial | +Using PCRE for partial matching |
| pcrepattern | +Specification of the regular expressions supported by PCRE |
| pcreperform | +Some comments on performance |
| pcreposix | +The POSIX API to the PCRE library |
| pcreprecompile | +How to save and re-use compiled patterns |
| pcresample | +Discussion of the pcredemo program |
| pcrestack | +Discussion of PCRE's stack usage |
| pcresyntax | +Syntax quick-reference summary |
| pcretest | +The pcretest command for testing PCRE |
| pcreunicode | +Discussion of Unicode and UTF-8/UTF-16/UTF-32 support |
+There are also individual pages that summarize the interface for each function +in the library. There is a single page for each triple of 8-bit/16-bit/32-bit +functions. +
+ +| pcre_assign_jit_stack | +Assign stack for JIT matching |
| pcre_compile | +Compile a regular expression |
| pcre_compile2 | +Compile a regular expression (alternate interface) |
| pcre_config | +Show build-time configuration options |
| pcre_copy_named_substring | +Extract named substring into given buffer |
| pcre_copy_substring | +Extract numbered substring into given buffer |
| pcre_dfa_exec | +Match a compiled pattern to a subject string + (DFA algorithm; not Perl compatible) |
| pcre_free_study | +Free study data |
| pcre_exec | +Match a compiled pattern to a subject string + (Perl compatible) |
| pcre_free_substring | +Free extracted substring |
| pcre_free_substring_list | +Free list of extracted substrings |
| pcre_fullinfo | +Extract information about a pattern |
| pcre_get_named_substring | +Extract named substring into new memory |
| pcre_get_stringnumber | +Convert captured string name to number |
| pcre_get_substring | +Extract numbered substring into new memory |
| pcre_get_substring_list | +Extract all substrings into new memory |
| pcre_info | +Obsolete information extraction function |
| pcre_jit_stack_alloc | +Create a stack for JIT matching |
| pcre_jit_stack_free | +Free a JIT matching stack |
| pcre_maketables | +Build character tables in current locale |
| pcre_pattern_to_host_byte_order | +Convert compiled pattern to host byte order if necessary |
| pcre_refcount | +Maintain reference count in compiled pattern |
| pcre_study | +Study a compiled pattern |
| pcre_utf16_to_host_byte_order | +Convert UTF-16 string to host byte order if necessary |
| pcre_utf32_to_host_byte_order | +Convert UTF-32 string to host byte order if necessary |
| pcre_version | +Return PCRE version and release date |