From 4e67c0c9e9cb5c5fa6a12fd78ce01b371c0e2013 Mon Sep 17 00:00:00 2001 From: "Philip.Hazel" Date: Tue, 2 Feb 2016 16:25:47 +0000 Subject: [PATCH] Tidy pcre2demo.c --- ChangeLog | 3 + doc/html/pcre2api.html | 8 +- doc/html/pcre2demo.html | 56 +- doc/html/pcre2pattern.html | 2 +- doc/html/pcre2posix.html | 31 +- doc/html/pcre2sample.html | 46 +- doc/html/pcre2test.html | 70 +- doc/pcre2.txt | 1549 ++++++++++++++++++------------------ doc/pcre2demo.3 | 56 +- doc/pcre2sample.3 | 45 +- doc/pcre2test.txt | 214 ++--- src/pcre2demo.c | 56 +- 12 files changed, 1116 insertions(+), 1020 deletions(-) diff --git a/ChangeLog b/ChangeLog index 91ea3b3..878b306 100644 --- a/ChangeLog +++ b/ChangeLog @@ -34,6 +34,9 @@ posix_nosub, to call regcomp() with REG_NOSUB. Previously the no_auto_capture modifier had this effect. That option is now ignored when the POSIX API is in use. +8. Minor tidies to the pcre2demo.c sample program, including more comments +about its 8-bit-ness. + Version 10.21 12-January-2016 ----------------------------- diff --git a/doc/html/pcre2api.html b/doc/html/pcre2api.html index bf1dd8e..d6c1b19 100644 --- a/doc/html/pcre2api.html +++ b/doc/html/pcre2api.html @@ -1282,7 +1282,9 @@ 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. +in Perl. Note that, if this option is set, references to capturing groups (back +references or recursion/subroutine calls) may only refer to named groups, +though the reference can be by name or by number. 
   PCRE2_NO_AUTO_POSSESS
@@ -3121,9 +3123,9 @@ Cambridge, England.


REVISION

-Last updated: 16 December 2015 +Last updated: 31 January 2016
-Copyright © 1997-2015 University of Cambridge. +Copyright © 1997-2016 University of Cambridge.

Return to the PCRE2 index page. diff --git a/doc/html/pcre2demo.html b/doc/html/pcre2demo.html index 5919117..d64e16b 100644 --- a/doc/html/pcre2demo.html +++ b/doc/html/pcre2demo.html @@ -20,28 +20,31 @@ please consult the man page, in case the conversion went wrong. *************************************************/ /* This is a demonstration program to illustrate a straightforward way of -calling the PCRE2 regular expression library from a C program. See the +using the PCRE2 regular expression library from a C program. See the pcre2sample documentation for a short discussion ("man pcre2sample" if you have the PCRE2 man pages installed). PCRE2 is a revised API for the library, and is incompatible with the original PCRE API. There are actually three libraries, each supporting a different code unit -width. This demonstration program uses the 8-bit library. +width. This demonstration program uses the 8-bit library. The default is to +process each code unit as a separate character, but if the pattern begins with +"(*UTF)", both it and the subject are treated as UTF-8 strings, where +characters may occupy multiple code units. In Unix-like environments, if PCRE2 is installed in your standard system libraries, you should be able to compile this program using this command: -gcc -Wall pcre2demo.c -lpcre2-8 -o pcre2demo +cc -Wall pcre2demo.c -lpcre2-8 -o pcre2demo If PCRE2 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 pcre2demo.c `pkg-config --cflags --libs libpcre2-8` -o pcre2demo +cc -Wall pcre2demo.c `pkg-config --cflags --libs libpcre2-8` -o pcre2demo -If you do not have pkg-config, you may have to use this: +If you do not have pkg-config, you may have to use something like this: -gcc -Wall pcre2demo.c -I/usr/local/include -L/usr/local/lib \ +cc -Wall pcre2demo.c -I/usr/local/include -L/usr/local/lib \ -R/usr/local/lib -lpcre2-8 -o pcre2demo Replace "/usr/local/include" and "/usr/local/lib" with wherever the include and @@ -56,9 +59,14 @@ the following line. */ /* #define PCRE2_STATIC */ -/* This macro must be defined before including pcre2.h. For a program that uses -only one code unit width, it makes it possible to use generic function names -such as pcre2_compile(). */ +/* The PCRE2_CODE_UNIT_WIDTH macro must be defined before including pcre2.h. +For a program that uses only one code unit width, setting it to 8, 16, or 32 +makes it possible to use generic function names such as pcre2_compile(). Note +that just changing 8 to 16 (for example) is not sufficient to convert this +program to process 16-bit characters. Even in a fully 16-bit environment, where +string-handling functions such as strcmp() and printf() work with 16-bit +characters, the code for handling the table of named substrings will still need +to be modified. */ #define PCRE2_CODE_UNIT_WIDTH 8 @@ -79,19 +87,19 @@ int main(int argc, char **argv) { pcre2_code *re; PCRE2_SPTR pattern; /* PCRE2_SPTR is a pointer to unsigned code units of */ -PCRE2_SPTR subject; /* the appropriate width (8, 16, or 32 bits). */ +PCRE2_SPTR subject; /* the appropriate width (in this case, 8 bits). */ PCRE2_SPTR name_table; int crlf_is_newline; int errornumber; int find_all; int i; -int namecount; -int name_entry_size; int rc; int utf8; uint32_t option_bits; +uint32_t namecount; +uint32_t name_entry_size; uint32_t newline; PCRE2_SIZE erroroffset; @@ -106,15 +114,19 @@ pcre2_match_data *match_data; * 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. * +* if the -g option is present. * **************************************************************************/ find_all = 0; for (i = 1; i < argc; i++) { if (strcmp(argv[i], "-g") == 0) find_all = 1; - else break; + else if (argv[i][0] == '-') + { + printf("Unrecognised option %s\n", argv[i]); + return 1; + } + else break; } /* After the options, we require exactly two arguments, which are the pattern, @@ -122,7 +134,7 @@ and the subject string. */ if (argc - i != 2) { - printf("Two arguments required: a regex and a subject string\n"); + printf("Exactly two arguments required: a regex and a subject string\n"); return 1; } @@ -201,7 +213,7 @@ if (rc < 0) stored. */ ovector = pcre2_get_ovector_pointer(match_data); -printf("\nMatch succeeded at offset %d\n", (int)ovector[0]); +printf("Match succeeded at offset %d\n", (int)ovector[0]); /************************************************************************* @@ -242,7 +254,7 @@ we have to extract the count of named parentheses from the pattern. */ PCRE2_INFO_NAMECOUNT, /* get the number of named substrings */ &namecount); /* where to put the answer */ -if (namecount <= 0) printf("No named substrings\n"); else +if (namecount == 0) printf("No named substrings\n"); else { PCRE2_SPTR tabptr; printf("Named substrings\n"); @@ -330,8 +342,8 @@ crlf_is_newline = newline == PCRE2_NEWLINE_ANY || for (;;) { - uint32_t options = 0; /* Normally no options */ - PCRE2_SIZE start_offset = ovector[1]; /* Start at end of previous match */ + uint32_t options = 0; /* Normally no options */ + PCRE2_SIZE 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 @@ -371,7 +383,7 @@ for (;;) { if (options == 0) break; /* All matches found */ ovector[1] = start_offset + 1; /* Advance one code unit */ - if (crlf_is_newline && /* If CRLF is newline & */ + if (crlf_is_newline && /* If CRLF is a newline & */ start_offset < subject_length - 1 && /* we are at CRLF, */ subject[start_offset] == '\r' && subject[start_offset + 1] == '\n') @@ -417,7 +429,7 @@ for (;;) printf("%2d: %.*s\n", i, (int)substring_length, (char *)substring_start); } - if (namecount <= 0) printf("No named substrings\n"); else + if (namecount == 0) printf("No named substrings\n"); else { PCRE2_SPTR tabptr = name_table; printf("Named substrings\n"); diff --git a/doc/html/pcre2pattern.html b/doc/html/pcre2pattern.html index c88e931..09cc470 100644 --- a/doc/html/pcre2pattern.html +++ b/doc/html/pcre2pattern.html @@ -1258,7 +1258,7 @@ PCRE2 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. Neither the alternative matching function -pcre2_dfa_match() not the JIT optimizer support \C in a UTF mode. The +pcre2_dfa_match() nor the JIT optimizer support \C in a UTF mode. The former gives a match-time error; the latter fails to optimize and so the match is always run using the interpreter.

diff --git a/doc/html/pcre2posix.html b/doc/html/pcre2posix.html index e16a4c3..d1ff260 100644 --- a/doc/html/pcre2posix.html +++ b/doc/html/pcre2posix.html @@ -48,7 +48,7 @@ This set of functions provides a POSIX-style API for the PCRE2 regular expression 8-bit library. See the pcre2api documentation for a description of PCRE2's native API, which contains much -additional functionality. There is no POSIX-style wrapper for PCRE2's 16-bit +additional functionality. There are no POSIX-style wrappers for PCRE2's 16-bit and 32-bit libraries.

@@ -67,9 +67,9 @@ POSIX interface often use it, this makes it easier to slot in PCRE2 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 -PCRE2-specific features via the POSIX calling interface. +There are also some options that are not defined by POSIX. These have been +added at the request of users who want to make use of certain PCRE2-specific +features via the POSIX calling interface.

When PCRE2 is called via these functions, it is only the API that is POSIX-like @@ -119,11 +119,11 @@ defined POSIX behaviour for REG_NEWLINE (see the following section). 

   REG_NOSUB
-The PCRE2_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. +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. Versions of the PCRE library prior to 10.22 used +to set the PCRE2_NO_AUTO_CAPTURE compile option, but this no longer happens +because it disables the use of back references. 
   REG_UCP
@@ -241,14 +241,15 @@ mutually exclusive; the error REG_INVARG is returned.

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. +regexec() are ignored (except possibly as input for REG_STARTEND).

-If the value of nmatch is zero, or if the value pmatch is NULL, -no data about any matched strings is returned. +The value of nmatch may be zero, and the value pmatch may be NULL +(unless REG_STARTEND is set); in both these cases no data about any matched +strings is returned.

-Otherwise,the portion of the string that was matched, and also any captured +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 byte offset to the first @@ -290,9 +291,9 @@ Cambridge, England.


REVISION

-Last updated: 29 November 2015 +Last updated: 31 January 2016
-Copyright © 1997-2015 University of Cambridge. +Copyright © 1997-2016 University of Cambridge.

Return to the PCRE2 index page. diff --git a/doc/html/pcre2sample.html b/doc/html/pcre2sample.html index 60a928b..c7d529b 100644 --- a/doc/html/pcre2sample.html +++ b/doc/html/pcre2sample.html @@ -24,12 +24,11 @@ documentation. If you do not have a copy of the PCRE2 distribution, you can save this listing to re-create the contents of pcre2demo.c.

-The demonstration program, which uses the PCRE2 8-bit library, compiles the -regular expression that is its first argument, and matches it against the -subject string in its second argument. No PCRE2 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. +The demonstration program compiles the regular expression that is its +first argument, and matches it against the subject string in its second +argument. No PCRE2 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 @@ -38,34 +37,39 @@ 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.

+The code in pcre2demo.c is an 8-bit program that uses the PCRE2 8-bit +library. It handles strings and characters that are stored in 8-bit code units. +By default, one character corresponds to one code unit, but if the pattern +starts with "(*UTF)", both it and the subject are treated as UTF-8 strings, +where characters may occupy multiple code units. +

+

If PCRE2 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: +a command like this: 

-  gcc -o pcre2demo pcre2demo.c -lpcre2-8
+  cc -o pcre2demo pcre2demo.c -lpcre2-8
If PCRE2 is installed elsewhere, you may need to add additional options to the command line. For example, on a Unix-like system that has PCRE2 installed in /usr/local, you can compile the demonstration program using a command like this: 
-  gcc -o pcre2demo -I/usr/local/include pcre2demo.c -L/usr/local/lib -lpcre2-8
-
-
-

-

-Once you have compiled and linked the demonstration program, you can run simple -tests like this: + cc -o pcre2demo -I/usr/local/include pcre2demo.c -L/usr/local/lib -lpcre2-8 + +Once you have built the demonstration program, you can run simple tests like +this: 

   ./pcre2demo 'cat|dog' 'the cat sat on the mat'
   ./pcre2demo -g 'cat|dog' 'the dog sat on the cat'
Note that there is a much more comprehensive test program, called pcre2test, -which supports many more facilities for testing regular expressions using the -PCRE2 libraries. The +which supports many more facilities for testing regular expressions using all +three PCRE2 libraries (8-bit, 16-bit, and 32-bit, though not all three need be +installed). The pcre2demo -program is provided as a simple coding example. +program is provided as a relatively simple coding example.

If you try to run @@ -73,7 +77,7 @@ If you try to run when PCRE2 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: libpcre2.so.0: open failed: No such file or directory
+  ld.so.1: pcre2demo: fatal: libpcre2-8.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 @@ -97,9 +101,9 @@ Cambridge, England. REVISION

-Last updated: 20 October 2014 +Last updated: 02 February 2016
-Copyright © 1997-2014 University of Cambridge. +Copyright © 1997-2016 University of Cambridge.

Return to the PCRE2 index page. diff --git a/doc/html/pcre2test.html b/doc/html/pcre2test.html index 537985d..0157962 100644 --- a/doc/html/pcre2test.html +++ b/doc/html/pcre2test.html @@ -98,10 +98,11 @@ further data is read.

For maximum portability, therefore, it is safest to avoid non-printing -characters in pcre2test input files. There is a facility for specifying a -pattern's characters as hexadecimal pairs, thus making it possible to include -binary zeroes in a pattern for testing purposes. Subject lines are processed -for backslash escapes, which makes it possible to include any data value. +characters in pcre2test input files. There is a facility for specifying +some or all of a pattern's characters as hexadecimal pairs, thus making it +possible to include binary zeroes in a pattern for testing purposes. Subject +lines are processed for backslash escapes, which makes it possible to include +any data value.


COMMAND LINE OPTIONS

@@ -559,7 +560,7 @@ about the pattern: debug same as info,fullbincode fullbincode show binary code with lengths /I info show info about compiled pattern - hex pattern is coded in hexadecimal + hex unquoted characters are hexadecimal jit[=<number>] use JIT jitfast use JIT fast path jitverify verify JIT use @@ -570,6 +571,7 @@ about the pattern: null_context compile with a NULL context parens_nest_limit=<n> set maximum parentheses depth posix use the POSIX API + posix_nosub use the POSIX API with REG_NOSUB push push compiled pattern onto the stack stackguard=<number> test the stackguard feature tables=[0|1|2] select internal tables @@ -655,20 +657,31 @@ testing that pcre2_compile() behaves correctly in this case (it uses default values).


-Specifying a pattern in hex +Specifying pattern characters in hexadecimal

-The hex modifier specifies that the characters of the pattern are to be -interpreted as pairs of hexadecimal digits. White space is permitted between -pairs. For example: +The hex modifier specifies that the characters of the pattern, except for +substrings enclosed in single or double quotes, are to be interpreted as pairs +of hexadecimal digits. This feature is provided as a way of creating patterns +that contain binary zeros and other non-printing characters. White space is +permitted between pairs of digits. For example, this pattern contains three +characters: 

   /ab 32 59/hex
-This feature is provided as a way of creating patterns that contain binary zero -and other non-printing characters. By default, pcre2test passes patterns -as zero-terminated strings to pcre2_compile(), giving the length as -PCRE2_ZERO_TERMINATED. However, for patterns specified in hexadecimal, the -actual length of the pattern is passed. +Parts of such a pattern are taken literally if quoted. This pattern contains +nine characters, only two of which are specified in hexadecimal: +
+  /ab "literal" 32/hex
+
+Either single or double quotes may be used. There is no way of including +the delimiter within a substring. +

+

+By default, pcre2test passes patterns as zero-terminated strings to +pcre2_compile(), giving the length as PCRE2_ZERO_TERMINATED. However, for +patterns specified with the hex modifier, the actual length of the +pattern is passed.


Generating long repetitive patterns @@ -821,16 +834,17 @@ variable can hold (essentially unlimited). Using the POSIX wrapper API

-The /posix modifier causes pcre2test to call PCRE2 via the POSIX -wrapper API rather than its native API. This supports only the 8-bit library. -Note that it does not imply POSIX matching semantics; for more detail see the +The /posix and posix_nosub modifiers cause pcre2test to call +PCRE2 via the POSIX wrapper API rather than its native API. When +posix_nosub is used, the POSIX option REG_NOSUB is passed to +regcomp(). The POSIX wrapper supports only the 8-bit library. Note that +it does not imply POSIX matching semantics; for more detail see the pcre2posix -documentation. When the POSIX API is being used, the following pattern -modifiers set options for the regcomp() function: +documentation. The following pattern modifiers set options for the +regcomp() function: 

   caseless           REG_ICASE
   multiline          REG_NEWLINE
-  no_auto_capture    REG_NOSUB
   dotall             REG_DOTALL     )
   ungreedy           REG_UNGREEDY   ) These options are not part of
   ucp                REG_UCP        )   the POSIX standard
@@ -847,7 +861,8 @@ large buffer is used.
 

 

 The aftertext and allaftertext subject modifiers work as described
-below. All other modifiers cause an error.
+below. All other modifiers are either ignored, with a warning message, or cause
+an error.
 

 

 Testing the stack guard feature
@@ -957,7 +972,7 @@ If the /posix modifier was present on the pattern, causing the POSIX
 wrapper API to be used, the only option-setting modifiers that have any effect
 are notbol, notempty, and noteol, causing REG_NOTBOL,
 REG_NOTEMPTY, and REG_NOTEOL, respectively, to be passed to regexec().
-Any other modifiers cause an error.
+The other modifiers are ignored, with a warning message.
 

 

 Setting match controls
@@ -1001,7 +1016,10 @@ pattern.
       substitute_unset_empty     use PCRE2_SUBSTITUTE_UNSET_EMPTY
       zero_terminate             pass the subject as zero-terminated
-The effects of these modifiers are described in the following sections. +The effects of these modifiers are described in the following sections. When +matching via the POSIX wrapper API, the aftertext, allaftertext, +and ovector subject modifiers work as described below. All other +modifiers are either ignored, with a warning message, or cause an error.


Showing more text @@ -1625,7 +1643,7 @@ usual by an empty line or end of file. This command may be followed by a modifier list containing only control modifiers that act after a pattern has been compiled. In particular, hex, -posix, and push are not allowed, nor are any +posix, posix_nosub, and push are not allowed, nor are any option-setting modifiers. The JIT modifiers are, however permitted. Here is an example that saves and reloads two patterns. @@ -1660,9 +1678,9 @@ Cambridge, England.


REVISION

-Last updated: 12 December 2015 +Last updated: 31 January 2016
-Copyright © 1997-2015 University of Cambridge. +Copyright © 1997-2016 University of Cambridge.

Return to the PCRE2 index page. diff --git a/doc/pcre2.txt b/doc/pcre2.txt index 9df2d47..6b53509 100644 --- a/doc/pcre2.txt +++ b/doc/pcre2.txt @@ -169,8 +169,8 @@ REVISION Last updated: 16 October 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2API(3) Library Functions Manual PCRE2API(3) @@ -1326,144 +1326,147 @@ COMPILING A PATTERN theses 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. + There is no equivalent of this option in Perl. Note that, if this + option is set, references to capturing groups (back references or + recursion/subroutine calls) may only refer to named groups, though the + reference can be by name or by number. PCRE2_NO_AUTO_POSSESS If this option is set, it disables "auto-possessification", which is an - optimization that, for example, turns a+b into a++b in order to avoid - backtracks into a+ that can never be successful. However, if callouts - are in use, auto-possessification means that some callouts are never + optimization that, for example, turns a+b into a++b in order to avoid + backtracks into a+ that can never be successful. However, if callouts + are in use, auto-possessification means that some callouts are never taken. You can set this option if you want the matching functions to do - a full unoptimized search and run all the callouts, but it is mainly + a full unoptimized search and run all the callouts, but it is mainly provided for testing purposes. PCRE2_NO_DOTSTAR_ANCHOR If this option is set, it disables an optimization that is applied when - .* is the first significant item in a top-level branch of a pattern, - and all the other branches also start with .* or with \A or \G or ^. - The optimization is automatically disabled for .* if it is inside an - atomic group or a capturing group that is the subject of a back refer- - ence, or if the pattern contains (*PRUNE) or (*SKIP). When the opti- - mization is not disabled, such a pattern is automatically anchored if + .* is the first significant item in a top-level branch of a pattern, + and all the other branches also start with .* or with \A or \G or ^. + The optimization is automatically disabled for .* if it is inside an + atomic group or a capturing group that is the subject of a back refer- + ence, or if the pattern contains (*PRUNE) or (*SKIP). When the opti- + mization is not disabled, such a pattern is automatically anchored if PCRE2_DOTALL is set for all the .* items and PCRE2_MULTILINE is not set - for any ^ items. Otherwise, the fact that any match must start either - at the start of the subject or following a newline is remembered. Like + for any ^ items. Otherwise, the fact that any match must start either + at the start of the subject or following a newline is remembered. Like other optimizations, this can cause callouts to be skipped. PCRE2_NO_START_OPTIMIZE - This is an option whose main effect is at matching time. It does not + This is an option whose main effect is at matching time. It does not change what pcre2_compile() generates, but it does affect the output of the JIT compiler. - There are a number of optimizations that may occur 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, the - matching code searches the subject for that character, and fails imme- - diately if it cannot find it, without actually running the main match- - ing 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. Also, 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 optimiza- - tions are in effect a pre-scan of the subject that takes place before + There are a number of optimizations that may occur 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, the + matching code searches the subject for that character, and fails imme- + diately if it cannot find it, without actually running the main match- + ing 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. Also, 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 optimiza- + tions are in effect a pre-scan of the subject that takes place before the pattern is run. The PCRE2_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 + 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. - Setting PCRE2_NO_START_OPTIMIZE may change the outcome of a matching + Setting PCRE2_NO_START_OPTIMIZE may change the outcome of a matching operation. Consider the pattern (*COMMIT)ABC - When this is compiled, PCRE2 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 pat- - tern must match the current starting position, which in this case, it - does. However, if the same match is run with PCRE2_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 + When this is compiled, PCRE2 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 pat- + tern must match the current starting position, which in this case, it + does. However, if the same match is run with PCRE2_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". There are also other start-up optimizations. 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 + The minimum length for a match is one character. If the subject is "ABC", there will be attempts to match "ABC", "BC", and "C". An attempt to match an empty string at the end of the subject does not take place, - because PCRE2 knows that the subject is now too short, and so the - (*MARK) is never encountered. In this case, the optimization does not + because PCRE2 knows that the subject is now too short, and so the + (*MARK) is never encountered. In this case, the optimization does not affect the overall match result, which is still "no match", but it does affect the auxiliary information that is returned. PCRE2_NO_UTF_CHECK - When PCRE2_UTF is set, the validity of the pattern as a UTF string is - automatically checked. There are discussions about the validity of - UTF-8 strings, UTF-16 strings, and UTF-32 strings in the pcre2unicode + When PCRE2_UTF is set, the validity of the pattern as a UTF string is + automatically checked. There are discussions about the validity of + UTF-8 strings, UTF-16 strings, and UTF-32 strings in the pcre2unicode document. If an invalid UTF sequence is found, pcre2_compile() returns a negative error code. If you know that your pattern is valid, and you want to skip this check - for performance reasons, you can set the PCRE2_NO_UTF_CHECK option. - When it is set, the effect of passing an invalid UTF string as a pat- - tern is undefined. It may cause your program to crash or loop. Note - that this option can also be passed to pcre2_match() and + for performance reasons, you can set the PCRE2_NO_UTF_CHECK option. + When it is set, the effect of passing an invalid UTF string as a pat- + tern is undefined. It may cause your program to crash or loop. Note + that this option can also be passed to pcre2_match() and pcre_dfa_match(), to suppress validity checking of the subject string. PCRE2_UCP This option changes the way PCRE2 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 PCRE2_UCP is set, Unicode properties - are used instead to classify characters. More details are given in the + \w, and some of the POSIX character classes. By default, only ASCII + characters are recognized, but if PCRE2_UCP is set, Unicode properties + are used instead to classify characters. More details are given in the section on generic character types in the pcre2pattern page. If you set - PCRE2_UCP, matching one of the items it affects takes much longer. The - option is available only if PCRE2 has been compiled with Unicode sup- + PCRE2_UCP, matching one of the items it affects takes much longer. The + option is available only if PCRE2 has been compiled with Unicode sup- port. PCRE2_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 + 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. PCRE2_USE_OFFSET_LIMIT This option must be set for pcre2_compile() if pcre2_set_offset_limit() - is going to be used to set a non-default offset limit in a match con- - text for matches that use this pattern. An error is generated if an - offset limit is set without this option. For more details, see the - description of pcre2_set_offset_limit() in the section that describes + is going to be used to set a non-default offset limit in a match con- + text for matches that use this pattern. An error is generated if an + offset limit is set without this option. For more details, see the + description of pcre2_set_offset_limit() in the section that describes match contexts. See also the PCRE2_FIRSTLINE option above. PCRE2_UTF - This option causes PCRE2 to regard both the pattern and the subject - strings that are subsequently processed as strings of UTF characters - instead of single-code-unit strings. It is available when PCRE2 is - built to include Unicode support (which is the default). If Unicode - support is not available, the use of this option provokes an error. - Details of how this option changes the behaviour of PCRE2 are given in + This option causes PCRE2 to regard both the pattern and the subject + strings that are subsequently processed as strings of UTF characters + instead of single-code-unit strings. It is available when PCRE2 is + built to include Unicode support (which is the default). If Unicode + support is not available, the use of this option provokes an error. + Details of how this option changes the behaviour of PCRE2 are given in the pcre2unicode page. COMPILATION ERROR CODES - There are over 80 positive error codes that pcre2_compile() may return + There are over 80 positive error codes that pcre2_compile() may return if it finds an error in the pattern. There are also some negative error - codes that are used for invalid UTF strings. These are the same as - given by pcre2_match() and pcre2_dfa_match(), and are described in the + codes that are used for invalid UTF strings. These are the same as + given by pcre2_match() and pcre2_dfa_match(), and are described in the pcre2unicode page. The pcre2_get_error_message() function can be called to obtain a textual error message from any error code. @@ -1487,53 +1490,53 @@ JUST-IN-TIME (JIT) COMPILATION void pcre2_jit_stack_free(pcre2_jit_stack *jit_stack); - These functions provide support for JIT compilation, which, if the - just-in-time compiler is available, further processes a compiled pat- + These functions provide support for JIT compilation, which, if the + just-in-time compiler is available, further processes a compiled pat- tern into machine code that executes much faster than the pcre2_match() - interpretive matching function. Full details are given in the pcre2jit + interpretive matching function. Full details are given in the pcre2jit documentation. - JIT compilation is a heavyweight optimization. It can take some time - for patterns to be analyzed, and for one-off matches and simple pat- - terns the benefit of faster execution might be offset by a much slower - compilation time. Most, but not all patterns can be optimized by the + JIT compilation is a heavyweight optimization. It can take some time + for patterns to be analyzed, and for one-off matches and simple pat- + terns the benefit of faster execution might be offset by a much slower + compilation time. Most, but not all patterns can be optimized by the JIT compiler. LOCALE SUPPORT - PCRE2 handles caseless matching, and determines whether characters are - letters, digits, or whatever, by reference to a set of tables, indexed - by character code point. This applies only to characters whose code - points are less than 256. By default, higher-valued code points never - match escapes such as \w or \d. However, if PCRE2 is built with UTF - support, all characters can be tested with \p and \P, or, alterna- - tively, the PCRE2_UCP option can be set when a pattern is compiled; - this causes \w and friends to use Unicode property support instead of + PCRE2 handles caseless matching, and determines whether characters are + letters, digits, or whatever, by reference to a set of tables, indexed + by character code point. This applies only to characters whose code + points are less than 256. By default, higher-valued code points never + match escapes such as \w or \d. However, if PCRE2 is built with UTF + support, all characters can be tested with \p and \P, or, alterna- + tively, the PCRE2_UCP option can be set when a pattern is compiled; + this causes \w and friends to use Unicode property support instead of the built-in tables. - The use of locales with Unicode is discouraged. If you are handling - characters with code points greater than 128, you should either use + The use of locales with Unicode is discouraged. If you are handling + characters with code points greater than 128, you should either use Unicode support, or use locales, but not try to mix the two. - PCRE2 contains an internal set of character tables that are used by - default. These are sufficient for many applications. Normally, the + PCRE2 contains an internal set of character tables that are used by + default. These are sufficient for many applications. Normally, the internal tables recognize only ASCII characters. However, when PCRE2 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 dif- ferent. - The internal tables can be overridden by tables supplied by the appli- - cation that calls PCRE2. These may be created in a different locale - from the default. As more and more applications change to using Uni- + The internal tables can be overridden by tables supplied by the appli- + cation that calls PCRE2. These may be created in a different locale + from the default. As more and more applications change to using Uni- code, the need for this locale support is expected to die away. - External tables are built by calling the pcre2_maketables() function, - in the relevant locale. The result can be passed to pcre2_compile() as - often as necessary, by creating a compile context and calling - pcre2_set_character_tables() to set the tables pointer therein. For - example, to build and use tables that are appropriate for the French - locale (where accented characters with values greater than 128 are + External tables are built by calling the pcre2_maketables() function, + in the relevant locale. The result can be passed to pcre2_compile() as + often as necessary, by creating a compile context and calling + pcre2_set_character_tables() to set the tables pointer therein. 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"); @@ -1542,15 +1545,15 @@ LOCALE SUPPORT pcre2_set_character_tables(ccontext, tables); re = pcre2_compile(..., ccontext); - 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". - It is the caller's responsibility to ensure that the memory containing + 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". + 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 (via the compile context) to pcre2_compile() - is saved with the compiled pattern, and the same tables are used by - pcre2_match() and pcre_dfa_match(). Thus, for any single pattern, com- - pilation, and matching all happen in the same locale, but different + is saved with the compiled pattern, and the same tables are used by + pcre2_match() and pcre_dfa_match(). Thus, for any single pattern, com- + pilation, and matching all happen in the same locale, but different patterns can be processed in different locales. @@ -1558,13 +1561,13 @@ INFORMATION ABOUT A COMPILED PATTERN int pcre2_pattern_info(const pcre2 *code, uint32_t what, void *where); - The pcre2_pattern_info() function returns general information about a + The pcre2_pattern_info() function returns general information about a compiled pattern. For information about callouts, see the next section. - The first argument for pcre2_pattern_info() is a pointer to the com- + The first argument for pcre2_pattern_info() is a pointer to the com- piled pattern. The second argument specifies which piece of information - is required, and the third argument is a pointer to a variable to - receive the data. If the third argument is NULL, the first argument is - ignored, and the function returns the size in bytes of the variable + is required, and the third argument is a pointer to a variable to + receive the data. If the third argument is NULL, the first argument is + ignored, and the function returns the size in bytes of the variable that is required for the information requested. Otherwise, The yield of the function is zero for success, or one of the following negative num- bers: @@ -1574,9 +1577,9 @@ INFORMATION ABOUT A COMPILED PATTERN PCRE2_ERROR_BADOPTION the value of what was invalid PCRE2_ERROR_UNSET the requested field is not set - The "magic number" is placed at the start of each compiled pattern as - an simple check against passing an arbitrary memory pointer. Here is a - typical call of pcre2_pattern_info(), to obtain the length of the com- + The "magic number" is placed at the start of each compiled pattern as + an simple check against passing an arbitrary memory pointer. Here is a + typical call of pcre2_pattern_info(), to obtain the length of the com- piled pattern: int rc; @@ -1593,14 +1596,14 @@ INFORMATION ABOUT A COMPILED PATTERN PCRE2_INFO_ARGOPTIONS Return a copy of the pattern's options. The third argument should point - to a uint32_t variable. PCRE2_INFO_ARGOPTIONS returns exactly the - options that were passed to pcre2_compile(), whereas PCRE2_INFO_ALLOP- - TIONS returns the compile options as modified by any top-level option - settings such as (*UTF) at the start of the pattern itself. For exam- - ple, if the pattern /(*UTF)abc/ is compiled with the PCRE2_EXTENDED + to a uint32_t variable. PCRE2_INFO_ARGOPTIONS returns exactly the + options that were passed to pcre2_compile(), whereas PCRE2_INFO_ALLOP- + TIONS returns the compile options as modified by any top-level option + settings such as (*UTF) at the start of the pattern itself. For exam- + ple, if the pattern /(*UTF)abc/ is compiled with the PCRE2_EXTENDED option, the result is PCRE2_EXTENDED and PCRE2_UTF. - A pattern compiled without PCRE2_ANCHORED is automatically anchored by + A pattern compiled without PCRE2_ANCHORED is automatically anchored by PCRE2 if the first significant item in every top-level branch is one of the following: @@ -1609,7 +1612,7 @@ INFORMATION ABOUT A COMPILED PATTERN \G always .* sometimes - see below - When .* is the first significant item, anchoring is possible only when + When .* is the first significant item, anchoring is possible only when all the following are true: .* is not in an atomic group @@ -1619,146 +1622,146 @@ INFORMATION ABOUT A COMPILED PATTERN Neither (*PRUNE) nor (*SKIP) appears in the pattern. PCRE2_NO_DOTSTAR_ANCHOR is not set. - For patterns that are auto-anchored, the PCRE2_ANCHORED bit is set in + For patterns that are auto-anchored, the PCRE2_ANCHORED bit is set in the options returned for PCRE2_INFO_ALLOPTIONS. PCRE2_INFO_BACKREFMAX - Return the number of the highest back reference in the pattern. The - third argument should point to an uint32_t variable. Named subpatterns - acquire numbers as well as names, and these count towards the highest - back reference. Back references such as \4 or \g{12} match the cap- - tured characters of the given group, but in addition, the check that a + Return the number of the highest back reference in the pattern. The + third argument should point to an uint32_t variable. Named subpatterns + acquire numbers as well as names, and these count towards the highest + back reference. Back references such as \4 or \g{12} match the cap- + tured characters of the given group, but in addition, the check that a capturing group is set in a conditional subpattern such as (?(3)a|b) is - also a back reference. Zero is returned if there are no back refer- + also a back reference. Zero is returned if there are no back refer- ences. PCRE2_INFO_BSR The output is a uint32_t whose value indicates what character sequences the \R escape sequence matches. A value of PCRE2_BSR_UNICODE means that - \R matches any Unicode line ending sequence; a value of PCRE2_BSR_ANY- + \R matches any Unicode line ending sequence; a value of PCRE2_BSR_ANY- CRLF means that \R matches only CR, LF, or CRLF. PCRE2_INFO_CAPTURECOUNT - Return the highest capturing subpattern number in the pattern. In pat- + Return the highest capturing subpattern number in the pattern. In pat- terns where (?| is not used, this is also the total number of capturing subpatterns. The third argument should point to an uint32_t variable. PCRE2_INFO_FIRSTBITMAP - In the absence of a single first code unit for a non-anchored pattern, - pcre2_compile() may construct a 256-bit table that defines a fixed set - of values for the first code unit in any match. For example, a pattern - that starts with [abc] results in a table with three bits set. When - code unit values greater than 255 are supported, the flag bit for 255 - means "any code unit of value 255 or above". If such a table was con- - structed, a pointer to it is returned. Otherwise NULL is returned. The + In the absence of a single first code unit for a non-anchored pattern, + pcre2_compile() may construct a 256-bit table that defines a fixed set + of values for the first code unit in any match. For example, a pattern + that starts with [abc] results in a table with three bits set. When + code unit values greater than 255 are supported, the flag bit for 255 + means "any code unit of value 255 or above". If such a table was con- + structed, a pointer to it is returned. Otherwise NULL is returned. The third argument should point to an const uint8_t * variable. PCRE2_INFO_FIRSTCODETYPE Return information about the first code unit of any matched string, for - a non-anchored pattern. The third argument should point to an uint32_t - variable. If there is a fixed first value, for example, the letter "c" + a non-anchored pattern. The third argument should point to an uint32_t + 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 charac- - ter value can be retrieved using PCRE2_INFO_FIRSTCODEUNIT. If there is - no fixed first value, but it is known that a match can occur only at - the start of the subject or following a newline in the subject, 2 is + ter value can be retrieved using PCRE2_INFO_FIRSTCODEUNIT. If there is + no fixed first value, but it is known that a match can occur only at + the start of the subject or following a newline in the subject, 2 is returned. Otherwise, and for anchored patterns, 0 is returned. PCRE2_INFO_FIRSTCODEUNIT - Return the value of the first code unit of any matched string in the + Return the value of the first code unit of any matched string in the situation where PCRE2_INFO_FIRSTCODETYPE returns 1; otherwise return 0. - The third argument should point to an uint32_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 + The third argument should point to an uint32_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. PCRE2_INFO_HASBACKSLASHC - Return 1 if the pattern contains any instances of \C, otherwise 0. The + Return 1 if the pattern contains any instances of \C, otherwise 0. The third argument should point to an uint32_t variable. PCRE2_INFO_HASCRORLF - Return 1 if the pattern contains any explicit matches for CR or LF + Return 1 if the pattern contains any explicit matches for CR or LF characters, otherwise 0. The third argument should point to an uint32_t - variable. An explicit match is either a literal CR or LF character, or + variable. An explicit match is either a literal CR or LF character, or \r or \n. PCRE2_INFO_JCHANGED - Return 1 if the (?J) or (?-J) option setting is used in the pattern, - otherwise 0. The third argument should point to an uint32_t variable. - (?J) and (?-J) set and unset the local PCRE2_DUPNAMES option, respec- + Return 1 if the (?J) or (?-J) option setting is used in the pattern, + otherwise 0. The third argument should point to an uint32_t variable. + (?J) and (?-J) set and unset the local PCRE2_DUPNAMES option, respec- tively. PCRE2_INFO_JITSIZE - If the compiled pattern was successfully processed by pcre2_jit_com- - pile(), return the size of the JIT compiled code, otherwise return + If the compiled pattern was successfully processed by pcre2_jit_com- + pile(), return the size of the JIT compiled code, otherwise return zero. The third argument should point to a size_t variable. PCRE2_INFO_LASTCODETYPE - Returns 1 if there is a rightmost literal code unit that must exist in - any matched string, other than at its start. The third argument should - point to an uint32_t variable. If there is no such value, 0 is - returned. When 1 is returned, the code unit value itself can be - retrieved using PCRE2_INFO_LASTCODEUNIT. 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 - 1 (with "z" returned from PCRE2_INFO_LASTCODEUNIT), but for /^a\dz\d/ + Returns 1 if there is a rightmost literal code unit that must exist in + any matched string, other than at its start. The third argument should + point to an uint32_t variable. If there is no such value, 0 is + returned. When 1 is returned, the code unit value itself can be + retrieved using PCRE2_INFO_LASTCODEUNIT. 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 + 1 (with "z" returned from PCRE2_INFO_LASTCODEUNIT), but for /^a\dz\d/ the returned value is 0. PCRE2_INFO_LASTCODEUNIT - 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 third argument should point to an uint32_t variable. If + 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 third argument should point to an uint32_t variable. If there is no such value, 0 is returned. PCRE2_INFO_MATCHEMPTY - Return 1 if the pattern might match an empty string, otherwise 0. The - third argument should point to an uint32_t variable. When a pattern + Return 1 if the pattern might match an empty string, otherwise 0. The + third argument should point to an uint32_t variable. When a pattern contains recursive subroutine calls it is not always possible to deter- - mine whether or not it can match an empty string. PCRE2 takes a cau- + mine whether or not it can match an empty string. PCRE2 takes a cau- tious approach and returns 1 in such cases. PCRE2_INFO_MATCHLIMIT - If the pattern set a match limit by including an item of the form - (*LIMIT_MATCH=nnnn) at the start, the value is returned. The third - argument should point to an unsigned 32-bit integer. If no such value - has been set, the call to pcre2_pattern_info() returns the error + If the pattern set a match limit by including an item of the form + (*LIMIT_MATCH=nnnn) at the start, the value is returned. The third + argument should point to an unsigned 32-bit integer. If no such value + has been set, the call to pcre2_pattern_info() returns the error PCRE2_ERROR_UNSET. PCRE2_INFO_MAXLOOKBEHIND Return the number of characters (not code units) in the longest lookbe- - hind assertion in the pattern. The third argument should point to an - unsigned 32-bit integer. This information is useful when doing multi- - segment matching using the partial matching facilities. Note that the + hind assertion in the pattern. The third argument should point to an + unsigned 32-bit integer. This information is useful when doing multi- + segment matching using the partial matching facilities. Note that the simple assertions \b and \B require a one-character lookbehind. \A also - registers a one-character lookbehind, though it does not actually - inspect the previous character. This is to ensure that at least one - character from the old segment is retained when a new segment is pro- + registers a one-character lookbehind, though it does not actually + inspect the previous character. This is to ensure that at least one + character from the old segment is retained when a new segment is pro- cessed. Otherwise, if there are no lookbehinds in the pattern, \A might match incorrectly at the start of a new segment. PCRE2_INFO_MINLENGTH - If a minimum length for matching subject strings was computed, its - value is returned. Otherwise the returned value is 0. The value is a - number of characters, which in UTF mode may be different from the num- - ber of code units. The third argument should point to an uint32_t - variable. The value is a lower bound to the length of any matching - string. There may not be any strings of that length that do actually + If a minimum length for matching subject strings was computed, its + value is returned. Otherwise the returned value is 0. The value is a + number of characters, which in UTF mode may be different from the num- + ber of code units. The third argument should point to an uint32_t + variable. The 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. PCRE2_INFO_NAMECOUNT @@ -1766,50 +1769,50 @@ INFORMATION ABOUT A COMPILED PATTERN PCRE2_INFO_NAMETABLE PCRE2 supports the use of named as well as numbered capturing parenthe- - ses. The names are just an additional way of identifying the parenthe- + ses. The names are just an additional way of identifying the parenthe- ses, which still acquire numbers. Several convenience functions such as - pcre2_substring_get_byname() are provided for extracting captured sub- - strings 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 pcre2_match() below). To - do the conversion, you need to use the name-to-number map, which is + pcre2_substring_get_byname() are provided for extracting captured sub- + strings 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 pcre2_match() 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. PCRE2_INFO_NAME- - COUNT gives the number of entries, and PCRE2_INFO_NAMEENTRYSIZE gives - the size of each entry in code units; both of these return a uint32_t + The map consists of a number of fixed-size entries. PCRE2_INFO_NAME- + COUNT gives the number of entries, and PCRE2_INFO_NAMEENTRYSIZE gives + the size of each entry in code units; both of these return a uint32_t value. The entry size depends on the length of the longest name. PCRE2_INFO_NAMETABLE returns a pointer to the first entry of the table. - This is a PCRE2_SPTR pointer to a block of code units. In the 8-bit - library, the first two bytes of each entry are the number of the cap- + This is a PCRE2_SPTR pointer to a block of code units. In the 8-bit + library, the first two bytes of each entry are the number of the cap- turing parenthesis, most significant byte first. In the 16-bit library, - the pointer points to 16-bit code units, the first of which contains - the parenthesis number. In the 32-bit library, the pointer points to - 32-bit code units, the first of which contains the parenthesis number. + the pointer points to 16-bit code units, the first of which contains + the parenthesis number. In the 32-bit library, the pointer points to + 32-bit code 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. If (?| is used to create multiple - groups with the same number, as described in the section on duplicate - subpattern numbers in the pcre2pattern page, the groups may be given - the same name, but there is only one entry in the table. Different + The names are in alphabetical order. If (?| is used to create multiple + groups with the same number, as described in the section on duplicate + subpattern numbers in the pcre2pattern page, the groups may be given + the same name, but there is only one entry in the table. Different names for groups of the same number are not permitted. - Duplicate names for subpatterns with different numbers are permitted, - but only if PCRE2_DUPNAMES is set. 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 + Duplicate names for subpatterns with different numbers are permitted, + but only if PCRE2_DUPNAMES is set. 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 PCRE2_EXTENDED + As a simple example of the name/number table, consider the following + pattern after compilation by the 8-bit library (assume PCRE2_EXTENDED is set, so white space - including newlines - is ignored): (? (?(\d\d)?\d\d) - (?\d\d) - (?\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, + 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 ??: @@ -1818,8 +1821,8 @@ INFORMATION ABOUT A COMPILED PATTERN 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 + 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. PCRE2_INFO_NEWLINE @@ -1832,27 +1835,27 @@ INFORMATION ABOUT A COMPILED PATTERN PCRE2_NEWLINE_ANY Any Unicode line ending PCRE2_NEWLINE_ANYCRLF Any of CR, LF, or CRLF - This specifies the default character sequence that will be recognized + This specifies the default character sequence that will be recognized as meaning "newline" while matching. PCRE2_INFO_RECURSIONLIMIT - If the pattern set a recursion limit by including an item of the form - (*LIMIT_RECURSION=nnnn) at the start, the value is returned. The third - argument should point to an unsigned 32-bit integer. If no such value - has been set, the call to pcre2_pattern_info() returns the error + If the pattern set a recursion limit by including an item of the form + (*LIMIT_RECURSION=nnnn) at the start, the value is returned. The third + argument should point to an unsigned 32-bit integer. If no such value + has been set, the call to pcre2_pattern_info() returns the error PCRE2_ERROR_UNSET. PCRE2_INFO_SIZE - Return the size of the compiled pattern in bytes (for all three - libraries). The third argument should point to a size_t variable. This - value includes the size of the general data block that precedes the - code units of the compiled pattern itself. The value that is used when - pcre2_compile() is getting memory in which to place the compiled pat- - tern may be slightly larger than the value returned by this option, - because there are cases where the code that calculates the size has to - over-estimate. Processing a pattern with the JIT compiler does not + Return the size of the compiled pattern in bytes (for all three + libraries). The third argument should point to a size_t variable. This + value includes the size of the general data block that precedes the + code units of the compiled pattern itself. The value that is used when + pcre2_compile() is getting memory in which to place the compiled pat- + tern may be slightly larger than the value returned by this option, + because there are cases where the code that calculates the size has to + over-estimate. Processing a pattern with the JIT compiler does not alter the value returned by this option. @@ -1863,22 +1866,22 @@ INFORMATION ABOUT A PATTERN'S CALLOUTS void *user_data); A script language that supports the use of string arguments in callouts - might like to scan all the callouts in a pattern before running the + might like to scan all the callouts in a pattern before running the match. This can be done by calling pcre2_callout_enumerate(). The first - argument is a pointer to a compiled pattern, the second points to a - callback function, and the third is arbitrary user data. The callback - function is called for every callout in the pattern in the order in + argument is a pointer to a compiled pattern, the second points to a + callback function, and the third is arbitrary user data. The callback + function is called for every callout in the pattern in the order in which they appear. Its first argument is a pointer to a callout enumer- - ation block, and its second argument is the user_data value that was - passed to pcre2_callout_enumerate(). The contents of the callout enu- - meration block are described in the pcre2callout documentation, which + ation block, and its second argument is the user_data value that was + passed to pcre2_callout_enumerate(). The contents of the callout enu- + meration block are described in the pcre2callout documentation, which also gives further details about callouts. SERIALIZATION AND PRECOMPILING - It is possible to save compiled patterns on disc or elsewhere, and - reload them later, subject to a number of restrictions. The functions + It is possible to save compiled patterns on disc or elsewhere, and + reload them later, subject to a number of restrictions. The functions whose names begin with pcre2_serialize_ are used for this purpose. They are described in the pcre2serialize documentation. @@ -1893,56 +1896,56 @@ THE MATCH DATA BLOCK void pcre2_match_data_free(pcre2_match_data *match_data); - Information about a successful or unsuccessful match is placed in a - match data block, which is an opaque structure that is accessed by - function calls. In particular, the match data block contains a vector - of offsets into the subject string that define the matched part of the - subject and any substrings that were captured. This is know as the + Information about a successful or unsuccessful match is placed in a + match data block, which is an opaque structure that is accessed by + function calls. In particular, the match data block contains a vector + of offsets into the subject string that define the matched part of the + subject and any substrings that were captured. This is know as the ovector. - Before calling pcre2_match(), pcre2_dfa_match(), or pcre2_jit_match() + Before calling pcre2_match(), pcre2_dfa_match(), or pcre2_jit_match() you must create a match data block by calling one of the creation func- - tions above. For pcre2_match_data_create(), the first argument is the - number of pairs of offsets in the ovector. One pair of offsets is - required to identify the string that matched the whole pattern, with - another pair for each captured substring. For example, a value of 4 - creates enough space to record the matched portion of the subject plus - three captured substrings. A minimum of at least 1 pair is imposed by + tions above. For pcre2_match_data_create(), the first argument is the + number of pairs of offsets in the ovector. One pair of offsets is + required to identify the string that matched the whole pattern, with + another pair for each captured substring. For example, a value of 4 + creates enough space to record the matched portion of the subject plus + three captured substrings. A minimum of at least 1 pair is imposed by pcre2_match_data_create(), so it is always possible to return the over- all matched string. The second argument of pcre2_match_data_create() is a pointer to a gen- - eral context, which can specify custom memory management for obtaining + eral context, which can specify custom memory management for obtaining the memory for the match data block. If you are not using custom memory management, pass NULL, which causes malloc() to be used. - For pcre2_match_data_create_from_pattern(), the first argument is a + For pcre2_match_data_create_from_pattern(), the first argument is a pointer to a compiled pattern. The ovector is created to be exactly the right size to hold all the substrings a pattern might capture. The sec- - ond argument is again a pointer to a general context, but in this case + ond argument is again a pointer to a general context, but in this case if NULL is passed, the memory is obtained using the same allocator that was used for the compiled pattern (custom or default). - A match data block can be used many times, with the same or different - compiled patterns. You can extract information from a match data block + A match data block can be used many times, with the same or different + compiled patterns. You can extract information from a match data block after a match operation has finished, using functions that are - described in the sections on matched strings and other match data + described in the sections on matched strings and other match data below. - When a call of pcre2_match() fails, valid data is available in the - match block only when the error is PCRE2_ERROR_NOMATCH, - PCRE2_ERROR_PARTIAL, or one of the error codes for an invalid UTF + When a call of pcre2_match() fails, valid data is available in the + match block only when the error is PCRE2_ERROR_NOMATCH, + PCRE2_ERROR_PARTIAL, or one of the error codes for an invalid UTF string. Exactly what is available depends on the error, and is detailed below. - When one of the matching functions is called, pointers to the compiled - pattern and the subject string are set in the match data block so that - they can be referenced by the extraction functions. After running a - match, you must not free a compiled pattern or a subject string until - after all operations on the match data block (for that match) have + When one of the matching functions is called, pointers to the compiled + pattern and the subject string are set in the match data block so that + they can be referenced by the extraction functions. After running a + match, you must not free a compiled pattern or a subject string until + after all operations on the match data block (for that match) have taken place. - When a match data block itself is no longer needed, it should be freed + When a match data block itself is no longer needed, it should be freed by calling pcre2_match_data_free(). @@ -1953,15 +1956,15 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION uint32_t options, pcre2_match_data *match_data, pcre2_match_context *mcontext); - The function pcre2_match() is called to match a subject string against - a compiled pattern, which is passed in the code argument. You can call + The function pcre2_match() is called to match a subject string against + a compiled pattern, which is passed in the code argument. You can call pcre2_match() with the same code argument as many times as you like, in - order to find multiple matches in the subject string or to match dif- + order to find multiple matches in the subject string or to match dif- ferent 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 + 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 pcre2_dfa_match() function. Here is an example of a simple call to pcre2_match(): @@ -1976,171 +1979,171 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION match_data, /* the match data block */ NULL); /* a match context; NULL means use defaults */ - If the subject string is zero-terminated, the length can be given as + If the subject string is zero-terminated, the length can be given as PCRE2_ZERO_TERMINATED. A match context must be provided if certain less common matching parameters are to be changed. For details, see the sec- tion on the match context above. The string to be matched by pcre2_match() - The subject string is passed to pcre2_match() as a pointer in subject, - a length in length, and a starting offset in startoffset. The length - and offset are in code units, not characters. That is, they are in - bytes for the 8-bit library, 16-bit code units for the 16-bit library, - and 32-bit code units for the 32-bit library, whether or not UTF pro- + The subject string is passed to pcre2_match() as a pointer in subject, + a length in length, and a starting offset in startoffset. The length + and offset are in code units, not characters. That is, they are in + bytes for the 8-bit library, 16-bit code units for the 16-bit library, + and 32-bit code units for the 32-bit library, whether or not UTF pro- cessing is enabled. If startoffset is greater than the length of the subject, pcre2_match() - returns PCRE2_ERROR_BADOFFSET. When the starting offset is zero, the - search for a match starts at the beginning of the subject, and this is + returns PCRE2_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 or UTF-16 mode, the starting off- - set must point to the start of a character, or to the end of the sub- - ject (in UTF-32 mode, one code unit equals one character, so all off- - sets are valid). Like the pattern string, the subject may contain + set must point to the start of a character, or to the end of the sub- + ject (in UTF-32 mode, one code unit equals one character, so all off- + sets are valid). Like the pattern string, the subject may contain binary zeroes. - A non-zero starting offset is useful when searching for another match - in the same subject by calling pcre2_match() again after a previous - success. Setting startoffset differs from passing over a shortened - string and setting PCRE2_NOTBOL in the case of a pattern that begins + A non-zero starting offset is useful when searching for another match + in the same subject by calling pcre2_match() again after a previous + success. Setting startoffset differs from passing over a shortened + string and setting PCRE2_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.) + 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 pcre2_match() - finds the first occurrence. If pcre2_match() is called again with just - the remainder of the subject, namely "issipi", it does not match, + finds the first occurrence. If pcre2_match() 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 pcre2_match() is passed the entire + to be a word boundary. However, if pcre2_match() is passed the entire string again, but with startoffset set to 4, it finds the second occur- - rence of "iss" because it is able to look behind the starting point to + rence 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 + 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 - PCRE2_NOTEMPTY_ATSTART and PCRE2_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 - pcre2demo 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 start- + first trying the match again at the same offset, with the + PCRE2_NOTEMPTY_ATSTART and PCRE2_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 + pcre2demo 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 start- ing offset by two characters instead of one. - If a non-zero starting offset is passed when the pattern is anchored, + 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 + if the pattern does not require the match to be at the start of the subject. Option bits for pcre2_match() The unused bits of the options argument for pcre2_match() must be zero. - The only bits that may be set are PCRE2_ANCHORED, PCRE2_NOTBOL, + The only bits that may be set are PCRE2_ANCHORED, PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART, - PCRE2_NO_UTF_CHECK, PCRE2_PARTIAL_HARD, and PCRE2_PARTIAL_SOFT. Their + PCRE2_NO_UTF_CHECK, PCRE2_PARTIAL_HARD, and PCRE2_PARTIAL_SOFT. Their action is described below. - Setting PCRE2_ANCHORED at match time is not supported by the just-in- - time (JIT) compiler. If it is set, JIT matching is disabled and the + Setting PCRE2_ANCHORED at match time is not supported by the just-in- + time (JIT) compiler. If it is set, JIT matching is disabled and the normal interpretive code in pcre2_match() is run. The remaining options are supported for JIT matching. PCRE2_ANCHORED The PCRE2_ANCHORED option limits pcre2_match() to matching at the first - matching position. If a pattern was compiled with PCRE2_ANCHORED, or - turned out to be anchored by virtue of its contents, it cannot be made - unachored at matching time. Note that setting the option at match time + matching position. If a pattern was compiled with PCRE2_ANCHORED, or + turned out to be anchored by virtue of its contents, it cannot be made + unachored at matching time. Note that setting the option at match time disables JIT matching. PCRE2_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 having set PCRE2_MULTILINE at + the beginning of a line, so the circumflex metacharacter should not + match before it. Setting this without having set PCRE2_MULTILINE at compile time causes circumflex never to match. This option affects only the behaviour of the circumflex metacharacter. It does not affect \A. PCRE2_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 with- - out having set PCRE2_MULTILINE at compile time causes dollar never to + of a line, so the dollar metacharacter should not match it nor (except + in multiline mode) a newline immediately before it. Setting this with- + out having set PCRE2_MULTILINE at compile time causes dollar never to match. This option affects only the behaviour of the dollar metacharac- ter. It does not affect \Z or \z. PCRE2_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 + 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 + is applied to a string not beginning with "a" or "b", it matches an empty string at the start of the subject. With PCRE2_NOTEMPTY set, this - match is not valid, so pcre2_match() searches further into the string + match is not valid, so pcre2_match() searches further into the string for occurrences of "a" or "b". PCRE2_NOTEMPTY_ATSTART - This is like PCRE2_NOTEMPTY, except that it locks out an empty string + This is like PCRE2_NOTEMPTY, except that it locks out an empty string match only at the first matching position, that is, at the start of the - subject plus the starting offset. An empty string match later in the - subject is permitted. If the pattern is anchored, such a match can + subject plus the starting offset. An empty string match later in the + subject is permitted. If the pattern is anchored, such a match can occur only if the pattern contains \K. PCRE2_NO_UTF_CHECK When PCRE2_UTF is set at compile time, the validity of the subject as a - UTF string is checked by default when pcre2_match() is subsequently - called. If a non-zero starting offset is given, the check is applied - only to that part of the subject that could be inspected during match- - ing, and there is a check that the starting offset points to the first - code unit of a character or to the end of the subject. If there are no - lookbehind assertions in the pattern, the check starts at the starting - offset. Otherwise, it starts at the length of the longest lookbehind + UTF string is checked by default when pcre2_match() is subsequently + called. If a non-zero starting offset is given, the check is applied + only to that part of the subject that could be inspected during match- + ing, and there is a check that the starting offset points to the first + code unit of a character or to the end of the subject. If there are no + lookbehind assertions in the pattern, the check starts at the starting + offset. Otherwise, it starts at the length of the longest lookbehind before the starting offset, or at the start of the subject if there are - not that many characters before the starting offset. Note that the + not that many characters before the starting offset. Note that the sequences \b and \B are one-character lookbehinds. The check is carried out before any other processing takes place, and a - negative error code is returned if the check fails. There are several - UTF error codes for each code unit width, corresponding to different - problems with the code unit sequence. There are discussions about the - validity of UTF-8 strings, UTF-16 strings, and UTF-32 strings in the + negative error code is returned if the check fails. There are several + UTF error codes for each code unit width, corresponding to different + problems with the code unit sequence. There are discussions about the + validity of UTF-8 strings, UTF-16 strings, and UTF-32 strings in the pcre2unicode page. - If you know that your subject is valid, and you want to skip these - checks for performance reasons, you can set the PCRE2_NO_UTF_CHECK - option when calling pcre2_match(). You might want to do this for the + If you know that your subject is valid, and you want to skip these + checks for performance reasons, you can set the PCRE2_NO_UTF_CHECK + option when calling pcre2_match(). You might want to do this for the second and subsequent calls to pcre2_match() if you are making repeated calls to find all the matches in a single subject string. - NOTE: When PCRE2_NO_UTF_CHECK is set, the effect of passing an invalid - string as a subject, or an invalid value of startoffset, is undefined. + NOTE: When PCRE2_NO_UTF_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 or loop indefinitely. PCRE2_PARTIAL_HARD PCRE2_PARTIAL_SOFT - These options turn on the partial matching feature. 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 PCRE2_PARTIAL_SOFT (but not PCRE2_PARTIAL_HARD) is set, - matching continues by testing any remaining alternatives. Only if no - complete match can be found is PCRE2_ERROR_PARTIAL returned instead of - PCRE2_ERROR_NOMATCH. In other words, PCRE2_PARTIAL_SOFT specifies that - the caller is prepared to handle a partial match, but only if no com- + These options turn on the partial matching feature. 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 PCRE2_PARTIAL_SOFT (but not PCRE2_PARTIAL_HARD) is set, + matching continues by testing any remaining alternatives. Only if no + complete match can be found is PCRE2_ERROR_PARTIAL returned instead of + PCRE2_ERROR_NOMATCH. In other words, PCRE2_PARTIAL_SOFT specifies that + the caller is prepared to handle a partial match, but only if no com- plete match can be found. - If PCRE2_PARTIAL_HARD is set, it overrides PCRE2_PARTIAL_SOFT. In this - case, if a partial match is found, pcre2_match() immediately returns - PCRE2_ERROR_PARTIAL, without considering any other alternatives. In + If PCRE2_PARTIAL_HARD is set, it overrides PCRE2_PARTIAL_SOFT. In this + case, if a partial match is found, pcre2_match() immediately returns + PCRE2_ERROR_PARTIAL, without considering any other alternatives. In other words, when PCRE2_PARTIAL_HARD is set, a partial match is consid- ered to be more important that an alternative complete match. @@ -2150,37 +2153,37 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION NEWLINE HANDLING WHEN MATCHING - When PCRE2 is built, a default newline convention is set; this is usu- - ally the standard convention for the operating system. The default can - be overridden in a compile context by calling pcre2_set_newline(). It - can also be overridden by starting a pattern string with, for example, - (*CRLF), as described in the section on newline conventions in the - pcre2pattern page. During matching, the newline choice affects the be- - haviour of the dot, circumflex, and dollar metacharacters. It may also - alter the way the match starting position is advanced after a match + When PCRE2 is built, a default newline convention is set; this is usu- + ally the standard convention for the operating system. The default can + be overridden in a compile context by calling pcre2_set_newline(). It + can also be overridden by starting a pattern string with, for example, + (*CRLF), as described in the section on newline conventions in the + pcre2pattern page. During matching, the newline choice affects the be- + haviour of the dot, circumflex, and dollar metacharacters. It may also + alter the way the match starting position is advanced after a match failure for an unanchored pattern. When PCRE2_NEWLINE_CRLF, PCRE2_NEWLINE_ANYCRLF, or PCRE2_NEWLINE_ANY is - set as the newline convention, and a match attempt for an unanchored + set as the newline convention, and a match attempt for an unanchored pattern fails when the current starting 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 + 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 PCRE2_DOTALL + expected. For example, if the pattern is .+A (and the PCRE2_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 con- + 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 con- tains an explicit CR or LF reference, and so advances only by one char- acter after the first failure. An explicit match for CR of LF is either a literal appearance of one of - those characters in the pattern, or one of the \r or \n escape - sequences. Implicit matches such as [^X] do not count, nor does \s, + those characters in the pattern, or one of the \r or \n escape + sequences. Implicit matches such as [^X] do not count, nor does \s, even though it includes CR and LF in the characters that it matches. - Notwithstanding the above, anomalous effects may still occur when CRLF + 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. @@ -2191,85 +2194,85 @@ HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS PCRE2_SIZE *pcre2_get_ovector_pointer(pcre2_match_data *match_data); - In general, a pattern matches a certain portion of the subject, and in - addition, further substrings from the subject may be picked out by - parenthesized parts of the pattern. Following the usage in Jeffrey - Friedl's book, this is called "capturing" in what follows, and the - phrase "capturing subpattern" or "capturing group" is used for a frag- - ment of a pattern that picks out a substring. PCRE2 supports several + In general, a pattern matches a certain portion of the subject, and in + addition, further substrings from the subject may be picked out by + parenthesized parts of the pattern. Following the usage in Jeffrey + Friedl's book, this is called "capturing" in what follows, and the + phrase "capturing subpattern" or "capturing group" is used for a frag- + ment of a pattern that picks out a substring. PCRE2 supports several other kinds of parenthesized subpattern that do not cause substrings to - be captured. The pcre2_pattern_info() function can be used to find out + be captured. The pcre2_pattern_info() function can be used to find out how many capturing subpatterns there are in a compiled pattern. - You can use auxiliary functions for accessing captured substrings by + You can use auxiliary functions for accessing captured substrings by number or by name, as described in sections below. Alternatively, you can make direct use of the vector of PCRE2_SIZE val- - ues, called the ovector, which contains the offsets of captured - strings. It is part of the match data block. The function - pcre2_get_ovector_pointer() returns the address of the ovector, and + ues, called the ovector, which contains the offsets of captured + strings. It is part of the match data block. The function + pcre2_get_ovector_pointer() returns the address of the ovector, and pcre2_get_ovector_count() returns the number of pairs of values it con- tains. Within the ovector, the first in each pair of values is set to the off- set of the first code unit of a substring, and the second is set to the - offset of the first code unit after the end of a substring. These val- - ues are always code unit offsets, not character offsets. That is, they - are byte offsets in the 8-bit library, 16-bit offsets in the 16-bit + offset of the first code unit after the end of a substring. These val- + ues are always code unit offsets, not character offsets. That is, they + are byte offsets in the 8-bit library, 16-bit offsets in the 16-bit library, and 32-bit offsets in the 32-bit library. - After a partial match (error return PCRE2_ERROR_PARTIAL), only the - first pair of offsets (that is, ovector[0] and ovector[1]) are set. - They identify the part of the subject that was partially matched. See + After a partial match (error return PCRE2_ERROR_PARTIAL), only the + first pair of offsets (that is, ovector[0] and ovector[1]) are set. + They identify the part of the subject that was partially matched. See the pcre2partial documentation for details of partial matching. After a successful match, the first pair of offsets identifies the por- - tion of the subject string that was matched by the entire pattern. The - next pair is used for the first capturing subpattern, and so on. The - value returned by pcre2_match() is one more than the highest numbered - pair that has been set. For example, if two substrings have been cap- - tured, the returned value is 3. If there are no capturing subpatterns, + tion of the subject string that was matched by the entire pattern. The + next pair is used for the first capturing subpattern, and so on. The + value returned by pcre2_match() is one more than the highest numbered + pair that has been set. For example, if two substrings have been cap- + tured, 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 pattern uses the \K escape sequence within a positive assertion, + If a pattern uses the \K escape sequence within a positive assertion, the reported start of a successful match can be greater than the end of - the match. For example, if the pattern (?=ab\K) is matched against + the match. For example, if the pattern (?=ab\K) is matched against "ab", the start and end offset values for the match are 2 and 0. - If a capturing subpattern group is matched repeatedly within a single - match operation, it is the last portion of the subject that it matched + If a capturing subpattern group is matched repeatedly within a single + match operation, it is the last portion of the subject that it matched that is returned. If the ovector is too small to hold all the captured substring offsets, - as much as possible is filled in, and the function returns a value of - zero. If captured substrings are not of interest, pcre2_match() may be + as much as possible is filled in, and the function returns a value of + zero. If captured substrings are not of interest, pcre2_match() may be called with a match data block whose ovector is of minimum length (that is, one pair). However, if the pattern contains back references and the ovector is not big enough to remember the related substrings, PCRE2 has - to get additional memory for use during matching. Thus it is usually + to get additional memory for use during matching. Thus it is usually advisable to set up a match data block containing an ovector of reason- able size. - It is possible for capturing subpattern number n+1 to match some part + 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 + 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 corre- + 2 is not. When this happens, both values in the offset pairs corre- sponding to unused subpatterns are set to PCRE2_UNSET. - Offset values that correspond to unused subpatterns at the end of the - expression are also set to PCRE2_UNSET. For example, if the string + Offset values that correspond to unused subpatterns at the end of the + expression are also set to PCRE2_UNSET. 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 high- + are not matched. The return from the function is 2, because the high- est used capturing subpattern number is 1. The offsets for for the sec- - ond and third capturing subpatterns (assuming the vector is large + ond and third capturing subpatterns (assuming the vector is large enough, of course) are set to PCRE2_UNSET. Elements in the ovector that do not correspond to capturing parentheses in the pattern are never changed. That is, if a pattern contains n cap- turing parentheses, no more than ovector[0] to ovector[2n+1] are set by - pcre2_match(). The other elements retain whatever values they previ- + pcre2_match(). The other elements retain whatever values they previ- ously had. @@ -2279,54 +2282,54 @@ OTHER INFORMATION ABOUT A MATCH PCRE2_SIZE pcre2_get_startchar(pcre2_match_data *match_data); - As well as the offsets in the ovector, other information about a match - is retained in the match data block and can be retrieved by the above - functions in appropriate circumstances. If they are called at other + As well as the offsets in the ovector, other information about a match + is retained in the match data block and can be retrieved by the above + functions in appropriate circumstances. If they are called at other times, the result is undefined. - After a successful match, a partial match (PCRE2_ERROR_PARTIAL), or a - failure to match (PCRE2_ERROR_NOMATCH), a (*MARK) name may be avail- - able, and pcre2_get_mark() can be called. It returns a pointer to the - zero-terminated name, which is within the compiled pattern. Otherwise - NULL is returned. The length of the (*MARK) name (excluding the termi- - nating zero) is stored in the code unit that preceeds the name. You - should use this instead of relying on the terminating zero if the + After a successful match, a partial match (PCRE2_ERROR_PARTIAL), or a + failure to match (PCRE2_ERROR_NOMATCH), a (*MARK) name may be avail- + able, and pcre2_get_mark() can be called. It returns a pointer to the + zero-terminated name, which is within the compiled pattern. Otherwise + NULL is returned. The length of the (*MARK) name (excluding the termi- + nating zero) is stored in the code unit that preceeds the name. You + should use this instead of relying on the terminating zero if the (*MARK) name might contain a binary zero. After a successful match, the (*MARK) name that is returned is the last - one encountered on the matching path through the pattern. After a "no - match" or a partial match, the last encountered (*MARK) name is + one encountered on the matching path through the pattern. After a "no + match" or a partial match, the last encountered (*MARK) name is returned. For example, consider this pattern: ^(*MARK:A)((*MARK:B)a|b)c - When it matches "bc", the returned mark is A. The B mark is "seen" in - the first branch of the group, but it is not on the matching path. On - the other hand, when this pattern fails to match "bx", the returned + When it matches "bc", the returned mark is A. The B mark is "seen" in + the first branch of the group, but it is not on the matching path. On + the other hand, when this pattern fails to match "bx", the returned mark is B. - After a successful match, a partial match, or one of the invalid UTF - errors (for example, PCRE2_ERROR_UTF8_ERR5), pcre2_get_startchar() can + After a successful match, a partial match, or one of the invalid UTF + errors (for example, PCRE2_ERROR_UTF8_ERR5), pcre2_get_startchar() can be called. After a successful or partial match it returns the code unit - offset of the character at which the match started. For a non-partial - match, this can be different to the value of ovector[0] if the pattern - contains the \K escape sequence. After a partial match, however, this - value is always the same as ovector[0] because \K does not affect the + offset of the character at which the match started. For a non-partial + match, this can be different to the value of ovector[0] if the pattern + contains the \K escape sequence. After a partial match, however, this + value is always the same as ovector[0] because \K does not affect the result of a partial match. - After a UTF check failure, pcre2_get_startchar() can be used to obtain + After a UTF check failure, pcre2_get_startchar() can be used to obtain the code unit offset of the invalid UTF character. Details are given in the pcre2unicode page. ERROR RETURNS FROM pcre2_match() - If pcre2_match() fails, it returns a negative number. This can be con- - verted to a text string by calling pcre2_get_error_message(). Negative - error codes are also returned by other functions, and are documented + If pcre2_match() fails, it returns a negative number. This can be con- + verted to a text string by calling pcre2_get_error_message(). Negative + error codes are also returned by other functions, and are documented with them. The codes are given names in the header file. If UTF check- ing is in force and an invalid UTF subject string is detected, one of a - number of UTF-specific negative error codes is returned. Details are + number of UTF-specific negative error codes is returned. Details are given in the pcre2unicode page. The following are the other errors that may be returned by pcre2_match(): @@ -2336,19 +2339,19 @@ ERROR RETURNS FROM pcre2_match() PCRE2_ERROR_PARTIAL - The subject string did not match, but it did match partially. See the + The subject string did not match, but it did match partially. See the pcre2partial documentation for details of partial matching. PCRE2_ERROR_BADMAGIC PCRE2 stores a 4-byte "magic number" at the start of the compiled code, - to catch the case when it is passed a junk pointer. This is the error + to catch the case when it is passed a junk pointer. This is the error that is returned when the magic number is not present. PCRE2_ERROR_BADMODE - This error is given when a pattern that was compiled by the 8-bit - library is passed to a 16-bit or 32-bit library function, or vice + This error is given when a pattern that was compiled by the 8-bit + library is passed to a 16-bit or 32-bit library function, or vice versa. PCRE2_ERROR_BADOFFSET @@ -2362,35 +2365,35 @@ ERROR RETURNS FROM pcre2_match() PCRE2_ERROR_BADUTFOFFSET The UTF code unit sequence that was passed as a subject was checked and - found to be valid (the PCRE2_NO_UTF_CHECK option was not set), but the - value of startoffset did not point to the beginning of a UTF character + found to be valid (the PCRE2_NO_UTF_CHECK option was not set), but the + value of startoffset did not point to the beginning of a UTF character or the end of the subject. PCRE2_ERROR_CALLOUT - This error is never generated by pcre2_match() itself. It is provided - for use by callout functions that want to cause pcre2_match() or - pcre2_callout_enumerate() to return a distinctive error code. See the + This error is never generated by pcre2_match() itself. It is provided + for use by callout functions that want to cause pcre2_match() or + pcre2_callout_enumerate() to return a distinctive error code. See the pcre2callout documentation for details. PCRE2_ERROR_INTERNAL - An unexpected internal error has occurred. This error could be caused + An unexpected internal error has occurred. This error could be caused by a bug in PCRE2 or by overwriting of the compiled pattern. PCRE2_ERROR_JIT_BADOPTION - This error is returned when a pattern that was successfully studied - using JIT 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 + This error is returned when a pattern that was successfully studied + using JIT 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 pcre2jit documentation for more details. PCRE2_ERROR_JIT_STACKLIMIT - This error is returned when a pattern that was successfully studied - using JIT is being matched, but the memory available for the just-in- - time processing stack is not large enough. See the pcre2jit documenta- + This error is returned when a pattern that was successfully studied + using JIT is being matched, but the memory available for the just-in- + time processing stack is not large enough. See the pcre2jit documenta- tion for more details. PCRE2_ERROR_MATCHLIMIT @@ -2399,10 +2402,10 @@ ERROR RETURNS FROM pcre2_match() PCRE2_ERROR_NOMEMORY - If a pattern contains back references, but the ovector is not big - enough to remember the referenced substrings, PCRE2 gets a block of + If a pattern contains back references, but the ovector is not big + enough to remember the referenced substrings, PCRE2 gets a block of memory at the start of matching to use for this purpose. There are some - other special cases where extra memory is needed during matching. This + other special cases where extra memory is needed during matching. This error is given when memory cannot be obtained. PCRE2_ERROR_NULL @@ -2411,12 +2414,12 @@ ERROR RETURNS FROM pcre2_match() PCRE2_ERROR_RECURSELOOP - This error is returned when pcre2_match() detects a recursion loop - within the pattern. Specifically, it means that either the whole pat- + This error is returned when pcre2_match() detects a recursion loop + within the pattern. Specifically, it means that either the whole pat- tern 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 com- - plicated cases, in particular mutual recursions between two different + the same position in the subject string. Some simple patterns that + might do this are detected and faulted at compile time, but more com- + plicated cases, in particular mutual recursions between two different subpatterns, cannot be detected until matching is attempted. PCRE2_ERROR_RECURSIONLIMIT @@ -2439,39 +2442,39 @@ EXTRACTING CAPTURED SUBSTRINGS BY NUMBER void pcre2_substring_free(PCRE2_UCHAR *buffer); - Captured substrings can be accessed directly by using the ovector as + Captured substrings can be accessed directly by using the ovector as described above. For convenience, auxiliary functions are provided for - extracting captured substrings as new, separate, zero-terminated + extracting captured substrings as new, separate, zero-terminated strings. 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 + and has a further zero added on the end, but the result is not, of course, a C string. The functions in this section identify substrings by number. The number zero refers to the entire matched substring, with higher numbers refer- - ring to substrings captured by parenthesized groups. After a partial - match, only substring zero is available. An attempt to extract any - other substring gives the error PCRE2_ERROR_PARTIAL. The next section + ring to substrings captured by parenthesized groups. After a partial + match, only substring zero is available. An attempt to extract any + other substring gives the error PCRE2_ERROR_PARTIAL. The next section describes similar functions for extracting captured substrings by name. - If a pattern uses the \K escape sequence within a positive assertion, + If a pattern uses the \K escape sequence within a positive assertion, the reported start of a successful match can be greater than the end of - the match. For example, if the pattern (?=ab\K) is matched against - "ab", the start and end offset values for the match are 2 and 0. In - this situation, calling these functions with a zero substring number + the match. For example, if the pattern (?=ab\K) is matched against + "ab", the start and end offset values for the match are 2 and 0. In + this situation, calling these functions with a zero substring number extracts a zero-length empty string. - You can find the length in code units of a captured substring without - extracting it by calling pcre2_substring_length_bynumber(). The first - argument is a pointer to the match data block, the second is the group - number, and the third is a pointer to a variable into which the length - is placed. If you just want to know whether or not the substring has + You can find the length in code units of a captured substring without + extracting it by calling pcre2_substring_length_bynumber(). The first + argument is a pointer to the match data block, the second is the group + number, and the third is a pointer to a variable into which the length + is placed. If you just want to know whether or not the substring has been captured, you can pass the third argument as NULL. - The pcre2_substring_copy_bynumber() function copies a captured sub- - string into a supplied buffer, whereas pcre2_substring_get_bynumber() - copies it into new memory, obtained using the same memory allocation - function that was used for the match data block. The first two argu- - ments of these functions are a pointer to the match data block and a + The pcre2_substring_copy_bynumber() function copies a captured sub- + string into a supplied buffer, whereas pcre2_substring_get_bynumber() + copies it into new memory, obtained using the same memory allocation + function that was used for the match data block. The first two argu- + ments of these functions are a pointer to the match data block and a capturing group number. The final arguments of pcre2_substring_copy_bynumber() are a pointer to @@ -2480,25 +2483,25 @@ EXTRACTING CAPTURED SUBSTRINGS BY NUMBER for the extracted substring, excluding the terminating zero. For pcre2_substring_get_bynumber() the third and fourth arguments point - to variables that are updated with a pointer to the new memory and the - number of code units that comprise the substring, again excluding the - terminating zero. When the substring is no longer needed, the memory + to variables that are updated with a pointer to the new memory and the + number of code units that comprise the substring, again excluding the + terminating zero. When the substring is no longer needed, the memory should be freed by calling pcre2_substring_free(). - The return value from all these functions is zero for success, or a - negative error code. If the pattern match failed, the match failure - code is returned. If a substring number greater than zero is used - after a partial match, PCRE2_ERROR_PARTIAL is returned. Other possible + The return value from all these functions is zero for success, or a + negative error code. If the pattern match failed, the match failure + code is returned. If a substring number greater than zero is used + after a partial match, PCRE2_ERROR_PARTIAL is returned. Other possible error codes are: PCRE2_ERROR_NOMEMORY - The buffer was too small for pcre2_substring_copy_bynumber(), or the + The buffer was too small for pcre2_substring_copy_bynumber(), or the attempt to get memory failed for pcre2_substring_get_bynumber(). PCRE2_ERROR_NOSUBSTRING - There is no substring with that number in the pattern, that is, the + There is no substring with that number in the pattern, that is, the number is greater than the number of capturing parentheses. PCRE2_ERROR_UNAVAILABLE @@ -2509,8 +2512,8 @@ EXTRACTING CAPTURED SUBSTRINGS BY NUMBER PCRE2_ERROR_UNSET - The substring did not participate in the match. For example, if the - pattern is (abc)|(def) and the subject is "def", and the ovector con- + The substring did not participate in the match. For example, if the + pattern is (abc)|(def) and the subject is "def", and the ovector con- tains at least two capturing slots, substring number 1 is unset. @@ -2521,32 +2524,32 @@ EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS void pcre2_substring_list_free(PCRE2_SPTR *list); - The pcre2_substring_list_get() function extracts all available sub- - strings and builds a list of pointers to them. It also (optionally) - builds a second list that contains their lengths (in code units), + The pcre2_substring_list_get() function extracts all available sub- + strings and builds a list of pointers to them. It also (optionally) + builds a second list that contains their lengths (in code units), excluding a terminating zero that is added to each of them. All this is done in a single block of memory that is obtained using the same memory allocation function that was used to get the match data block. - This function must be called only after a successful match. If called + This function must be called only after a successful match. If called after a partial match, the error code PCRE2_ERROR_PARTIAL is returned. - The address of the memory block is returned via listptr, which is also + 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 address of the list of lengths is returned via - lengthsptr. If your strings do not contain binary zeros and you do not + by a NULL pointer. The address of the list of lengths is returned via + lengthsptr. If your strings do not contain binary zeros and you do not therefore need the lengths, you may supply NULL as the lengthsptr argu- - ment to disable the creation of a list of lengths. The yield of the - function is zero if all went well, or PCRE2_ERROR_NOMEMORY if the mem- - ory block could not be obtained. When the list is no longer needed, it + ment to disable the creation of a list of lengths. The yield of the + function is zero if all went well, or PCRE2_ERROR_NOMEMORY if the mem- + ory block could not be obtained. When the list is no longer needed, it should be freed by calling pcre2_substring_list_free(). If this function encounters 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, it returns an empty string. - This can be distinguished from a genuine zero-length substring by + when capturing subpattern number n+1 matches some part of the subject, + but subpattern n has not been used at all, it returns an empty string. + This can be distinguished from a genuine zero-length substring by inspecting the appropriate offset in the ovector, which contain - PCRE2_UNSET for unset substrings, or by calling pcre2_sub- + PCRE2_UNSET for unset substrings, or by calling pcre2_sub- string_length_bynumber(). @@ -2566,39 +2569,39 @@ EXTRACTING CAPTURED SUBSTRINGS BY NAME void pcre2_substring_free(PCRE2_UCHAR *buffer); - To extract a substring by name, you first have to find associated num- + To extract a substring by name, you first have to find associated num- ber. For example, for this pattern: (a+)b(?\d+)... the number of the subpattern called "xxx" is 2. If the name is known to - be unique (PCRE2_DUPNAMES was not set), you can find the number from + be unique (PCRE2_DUPNAMES was not set), you can find the number from the name by calling pcre2_substring_number_from_name(). The first argu- - ment is the compiled pattern, and the second is the name. The yield of + ment is the compiled pattern, and the second is the name. The yield of the function is the subpattern number, PCRE2_ERROR_NOSUBSTRING if there - is no subpattern of that name, or PCRE2_ERROR_NOUNIQUESUBSTRING if - there is more than one subpattern of that name. Given the number, you - can extract the substring directly, or use one of the functions + is no subpattern of that name, or PCRE2_ERROR_NOUNIQUESUBSTRING if + there is more than one subpattern of that name. Given the number, you + can extract the substring directly, or use one of the functions described above. - For convenience, there are also "byname" functions that correspond to - the "bynumber" functions, the only difference being that the second - argument is a name instead of a number. If PCRE2_DUPNAMES is set and + For convenience, there are also "byname" functions that correspond to + the "bynumber" functions, the only difference being that the second + argument is a name instead of a number. If PCRE2_DUPNAMES is set and there are duplicate names, these functions scan all the groups with the given name, and return the first named string that is set. - If there are no groups with the given name, PCRE2_ERROR_NOSUBSTRING is - returned. If all groups with the name have numbers that are greater - than the number of slots in the ovector, PCRE2_ERROR_UNAVAILABLE is - returned. If there is at least one group with a slot in the ovector, + If there are no groups with the given name, PCRE2_ERROR_NOSUBSTRING is + returned. If all groups with the name have numbers that are greater + than the number of slots in the ovector, PCRE2_ERROR_UNAVAILABLE is + returned. If there is at least one group with a slot in the ovector, but no group is found to be set, PCRE2_ERROR_UNSET is returned. Warning: If the pattern uses the (?| feature to set up multiple subpat- - terns with the same number, as described in the section on duplicate - subpattern numbers in the pcre2pattern 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 + terns with the same number, as described in the section on duplicate + subpattern numbers in the pcre2pattern 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. @@ -2611,52 +2614,52 @@ CREATING A NEW STRING WITH SUBSTITUTIONS PCRE2_SIZE rlength, PCRE2_UCHAR *outputbufferP, PCRE2_SIZE *outlengthptr); - This function calls pcre2_match() and then makes a copy of the subject - string in outputbuffer, replacing the part that was matched with the - replacement string, whose length is supplied in rlength. This can be + This function calls pcre2_match() and then makes a copy of the subject + string in outputbuffer, replacing the part that was matched with the + replacement string, whose length is supplied in rlength. This can be given as PCRE2_ZERO_TERMINATED for a zero-terminated string. Matches in - which a \K item in a lookahead in the pattern causes the match to end + which a \K item in a lookahead in the pattern causes the match to end before it starts are not supported, and give rise to an error return. - The first seven arguments of pcre2_substitute() are the same as for + The first seven arguments of pcre2_substitute() are the same as for pcre2_match(), except that the partial matching options are not permit- - ted, and match_data may be passed as NULL, in which case a match data - block is obtained and freed within this function, using memory manage- - ment functions from the match context, if provided, or else those that + ted, and match_data may be passed as NULL, in which case a match data + block is obtained and freed within this function, using memory manage- + ment functions from the match context, if provided, or else those that were used to allocate memory for the compiled code. - The outlengthptr argument must point to a variable that contains the - length, in code units, of the output buffer. If the function is suc- - cessful, the value is updated to contain the length of the new string, + The outlengthptr argument must point to a variable that contains the + length, in code units, of the output buffer. If the function is suc- + cessful, the value is updated to contain the length of the new string, excluding the trailing zero that is automatically added. - If the function is not successful, the value set via outlengthptr - depends on the type of error. For syntax errors in the replacement - string, the value is the offset in the replacement string where the - error was detected. For other errors, the value is PCRE2_UNSET by - default. This includes the case of the output buffer being too small, - unless PCRE2_SUBSTITUTE_OVERFLOW_LENGTH is set (see below), in which - case the value is the minimum length needed, including space for the - trailing zero. Note that in order to compute the required length, - pcre2_substitute() has to simulate all the matching and copying, + If the function is not successful, the value set via outlengthptr + depends on the type of error. For syntax errors in the replacement + string, the value is the offset in the replacement string where the + error was detected. For other errors, the value is PCRE2_UNSET by + default. This includes the case of the output buffer being too small, + unless PCRE2_SUBSTITUTE_OVERFLOW_LENGTH is set (see below), in which + case the value is the minimum length needed, including space for the + trailing zero. Note that in order to compute the required length, + pcre2_substitute() has to simulate all the matching and copying, instead of giving an error return as soon as the buffer overflows. Note also that the length is in code units, not bytes. - In the replacement string, which is interpreted as a UTF string in UTF - mode, and is checked for UTF validity unless the PCRE2_NO_UTF_CHECK + In the replacement string, which is interpreted as a UTF string in UTF + mode, and is checked for UTF validity unless the PCRE2_NO_UTF_CHECK option is set, a dollar character is an escape character that can spec- - ify the insertion of characters from capturing groups or (*MARK) items + ify the insertion of characters from capturing groups or (*MARK) items in the pattern. The following forms are always recognized: $$ insert a dollar character $ or ${} insert the contents of group $*MARK or ${*MARK} insert the name of the last (*MARK) encountered - Either a group number or a group name can be given for . Curly - brackets are required only if the following character would be inter- + Either a group number or a group name can be given for . Curly + brackets are required only if the following character would be inter- preted as part of the number or name. The number may be zero to include - the entire matched string. For example, if the pattern a(b)c is - matched with "=abc=" and the replacement string "+$1$0$1+", the result + the entire matched string. For example, if the pattern a(b)c is + matched with "=abc=" and the replacement string "+$1$0$1+", the result is "=+babcb+=". The facility for inserting a (*MARK) name can be used to perform simple @@ -2666,92 +2669,92 @@ CREATING A NEW STRING WITH SUBSTITUTIONS apple lemon 2: pear orange - As well as the usual options for pcre2_match(), a number of additional + As well as the usual options for pcre2_match(), a number of additional options can be set in the options argument. PCRE2_SUBSTITUTE_GLOBAL causes the function to iterate over the subject - string, replacing every matching substring. If this is not set, only - the first matching substring is replaced. If any matched substring has - zero length, after the substitution has happened, an attempt to find a - non-empty match at the same position is performed. If this is not suc- - cessful, the current position is advanced by one character except when - CRLF is a valid newline sequence and the next two characters are CR, + string, replacing every matching substring. If this is not set, only + the first matching substring is replaced. If any matched substring has + zero length, after the substitution has happened, an attempt to find a + non-empty match at the same position is performed. If this is not suc- + cessful, the current position is advanced by one character except when + CRLF is a valid newline sequence and the next two characters are CR, LF. In this case, the current position is advanced by two characters. - PCRE2_SUBSTITUTE_OVERFLOW_LENGTH changes what happens when the output + PCRE2_SUBSTITUTE_OVERFLOW_LENGTH changes what happens when the output buffer is too small. The default action is to return PCRE2_ERROR_NOMEM- - ORY immediately. If this option is set, however, pcre2_substitute() + ORY immediately. If this option is set, however, pcre2_substitute() continues to go through the motions of matching and substituting (with- - out, of course, writing anything) in order to compute the size of buf- - fer that is needed. This value is passed back via the outlengthptr - variable, with the result of the function still being + out, of course, writing anything) in order to compute the size of buf- + fer that is needed. This value is passed back via the outlengthptr + variable, with the result of the function still being PCRE2_ERROR_NOMEMORY. - Passing a buffer size of zero is a permitted way of finding out how - much memory is needed for given substitution. However, this does mean + Passing a buffer size of zero is a permitted way of finding out how + much memory is needed for given substitution. However, this does mean that the entire operation is carried out twice. Depending on the appli- - cation, it may be more efficient to allocate a large buffer and free - the excess afterwards, instead of using PCRE2_SUBSTITUTE_OVER- + cation, it may be more efficient to allocate a large buffer and free + the excess afterwards, instead of using PCRE2_SUBSTITUTE_OVER- FLOW_LENGTH. - PCRE2_SUBSTITUTE_UNKNOWN_UNSET causes references to capturing groups - that do not appear in the pattern to be treated as unset groups. This - option should be used with care, because it means that a typo in a - group name or number no longer causes the PCRE2_ERROR_NOSUBSTRING + PCRE2_SUBSTITUTE_UNKNOWN_UNSET causes references to capturing groups + that do not appear in the pattern to be treated as unset groups. This + option should be used with care, because it means that a typo in a + group name or number no longer causes the PCRE2_ERROR_NOSUBSTRING error. - PCRE2_SUBSTITUTE_UNSET_EMPTY causes unset capturing groups (including + PCRE2_SUBSTITUTE_UNSET_EMPTY causes unset capturing groups (including unknown groups when PCRE2_SUBSTITUTE_UNKNOWN_UNSET is set) to be - treated as empty strings when inserted as described above. If this - option is not set, an attempt to insert an unset group causes the - PCRE2_ERROR_UNSET error. This option does not influence the extended + treated as empty strings when inserted as described above. If this + option is not set, an attempt to insert an unset group causes the + PCRE2_ERROR_UNSET error. This option does not influence the extended substitution syntax described below. - PCRE2_SUBSTITUTE_EXTENDED causes extra processing to be applied to the - replacement string. Without this option, only the dollar character is - special, and only the group insertion forms listed above are valid. + PCRE2_SUBSTITUTE_EXTENDED causes extra processing to be applied to the + replacement string. Without this option, only the dollar character is + special, and only the group insertion forms listed above are valid. When PCRE2_SUBSTITUTE_EXTENDED is set, two things change: - Firstly, backslash in a replacement string is interpreted as an escape + Firstly, backslash in a replacement string is interpreted as an escape character. The usual forms such as \n or \x{ddd} can be used to specify - particular character codes, and backslash followed by any non-alphanu- - meric character quotes that character. Extended quoting can be coded + particular character codes, and backslash followed by any non-alphanu- + meric character quotes that character. Extended quoting can be coded using \Q...\E, exactly as in pattern strings. - There are also four escape sequences for forcing the case of inserted - letters. The insertion mechanism has three states: no case forcing, + There are also four escape sequences for forcing the case of inserted + letters. The insertion mechanism has three states: no case forcing, force upper case, and force lower case. The escape sequences change the current state: \U and \L change to upper or lower case forcing, respec- - tively, and \E (when not terminating a \Q quoted sequence) reverts to - no case forcing. The sequences \u and \l force the next character (if - it is a letter) to upper or lower case, respectively, and then the + tively, and \E (when not terminating a \Q quoted sequence) reverts to + no case forcing. The sequences \u and \l force the next character (if + it is a letter) to upper or lower case, respectively, and then the state automatically reverts to no case forcing. Case forcing applies to all inserted characters, including those from captured groups and let- ters within \Q...\E quoted sequences. Note that case forcing sequences such as \U...\E do not nest. For exam- - ple, the result of processing "\Uaa\LBB\Ecc\E" is "AAbbcc"; the final + ple, the result of processing "\Uaa\LBB\Ecc\E" is "AAbbcc"; the final \E has no effect. - The second effect of setting PCRE2_SUBSTITUTE_EXTENDED is to add more - flexibility to group substitution. The syntax is similar to that used + The second effect of setting PCRE2_SUBSTITUTE_EXTENDED is to add more + flexibility to group substitution. The syntax is similar to that used by Bash: ${:-} ${:+:} - As before, may be a group number or a name. The first form speci- - fies a default value. If group is set, its value is inserted; if - not, is expanded and the result inserted. The second form - specifies strings that are expanded and inserted when group is set - or unset, respectively. The first form is just a convenient shorthand + As before, may be a group number or a name. The first form speci- + fies a default value. If group is set, its value is inserted; if + not, is expanded and the result inserted. The second form + specifies strings that are expanded and inserted when group is set + or unset, respectively. The first form is just a convenient shorthand for ${:+${}:} - Backslash can be used to escape colons and closing curly brackets in - the replacement strings. A change of the case forcing state within a - replacement string remains in force afterwards, as shown in this + Backslash can be used to escape colons and closing curly brackets in + the replacement strings. A change of the case forcing state within a + replacement string remains in force afterwards, as shown in this pcre2test example: /(some)?(body)/substitute_extended,replace=${1:+\U:\L}HeLLo @@ -2760,37 +2763,37 @@ CREATING A NEW STRING WITH SUBSTITUTIONS somebody 1: HELLO - The PCRE2_SUBSTITUTE_UNSET_EMPTY option does not affect these extended - substitutions. However, PCRE2_SUBSTITUTE_UNKNOWN_UNSET does cause + The PCRE2_SUBSTITUTE_UNSET_EMPTY option does not affect these extended + substitutions. However, PCRE2_SUBSTITUTE_UNKNOWN_UNSET does cause unknown groups in the extended syntax forms to be treated as unset. - If successful, pcre2_substitute() returns the number of replacements + If successful, pcre2_substitute() returns the number of replacements that were made. This may be zero if no matches were found, and is never greater than 1 unless PCRE2_SUBSTITUTE_GLOBAL is set. In the event of an error, a negative error code is returned. Except for - PCRE2_ERROR_NOMATCH (which is never returned), errors from + PCRE2_ERROR_NOMATCH (which is never returned), errors from pcre2_match() are passed straight back. PCRE2_ERROR_NOSUBSTRING is returned for a non-existent substring inser- tion, unless PCRE2_SUBSTITUTE_UNKNOWN_UNSET is set. PCRE2_ERROR_UNSET is returned for an unset substring insertion (includ- - ing an unknown substring when PCRE2_SUBSTITUTE_UNKNOWN_UNSET is set) + ing an unknown substring when PCRE2_SUBSTITUTE_UNKNOWN_UNSET is set) when the simple (non-extended) syntax is used and PCRE2_SUBSTI- TUTE_UNSET_EMPTY is not set. - PCRE2_ERROR_NOMEMORY is returned if the output buffer is not big + PCRE2_ERROR_NOMEMORY is returned if the output buffer is not big enough. If the PCRE2_SUBSTITUTE_OVERFLOW_LENGTH option is set, the size - of buffer that is needed is returned via outlengthptr. Note that this + of buffer that is needed is returned via outlengthptr. Note that this does not happen by default. - PCRE2_ERROR_BADREPLACEMENT is used for miscellaneous syntax errors in + PCRE2_ERROR_BADREPLACEMENT is used for miscellaneous syntax errors in the replacement string, with more particular errors being - PCRE2_ERROR_BADREPESCAPE (invalid escape sequence), PCRE2_ERROR_REP- - MISSING_BRACE (closing curly bracket not found), PCRE2_BADSUBSTITUTION - (syntax error in extended group substitution), and PCRE2_BADSUBPATTERN - (the pattern match ended before it started, which can happen if \K is + PCRE2_ERROR_BADREPESCAPE (invalid escape sequence), PCRE2_ERROR_REP- + MISSING_BRACE (closing curly bracket not found), PCRE2_BADSUBSTITUTION + (syntax error in extended group substitution), and PCRE2_BADSUBPATTERN + (the pattern match ended before it started, which can happen if \K is used in an assertion). As for all PCRE2 errors, a text message that describes the error can be @@ -2802,56 +2805,56 @@ DUPLICATE SUBPATTERN NAMES int pcre2_substring_nametable_scan(const pcre2_code *code, PCRE2_SPTR name, PCRE2_SPTR *first, PCRE2_SPTR *last); - When a pattern is compiled with the PCRE2_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 + When a pattern is compiled with the PCRE2_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 + only one of the named subpatterns participates. An example is shown in the pcre2pattern documentation. - When duplicates are present, pcre2_substring_copy_byname() and - pcre2_substring_get_byname() return the first substring corresponding - to the given name that is set. Only if none are set is - PCRE2_ERROR_UNSET is returned. The pcre2_substring_number_from_name() + When duplicates are present, pcre2_substring_copy_byname() and + pcre2_substring_get_byname() return the first substring corresponding + to the given name that is set. Only if none are set is + PCRE2_ERROR_UNSET is returned. The pcre2_substring_number_from_name() function returns the error PCRE2_ERROR_NOUNIQUESUBSTRING when there are duplicate names. - If you want to get full details of all captured substrings for a given - name, you must use the pcre2_substring_nametable_scan() function. The - first argument is the compiled pattern, and the second is the name. If - the third and fourth arguments are NULL, the function returns a group + If you want to get full details of all captured substrings for a given + name, you must use the pcre2_substring_nametable_scan() function. The + first argument is the compiled pattern, and the second is the name. If + the third and fourth arguments are NULL, the function returns a group number for a unique name, or PCRE2_ERROR_NOUNIQUESUBSTRING otherwise. When the third and fourth arguments are not NULL, they must be pointers - to variables that are updated by the function. After it has run, they + to variables that 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, and the function returns the length of each entry in code - units. In both cases, PCRE2_ERROR_NOSUBSTRING is returned if there are + given name, and the function returns the length of each entry in code + units. In both cases, PCRE2_ERROR_NOSUBSTRING is returned if there are no entries for the given name. The format of the name table is described above in the section entitled - Information about a pattern. Given all the relevant entries for the - name, you can extract each of their numbers, and hence the captured + Information about a pattern. Given all the relevant entries for the + name, you can extract each of their numbers, and hence the captured data. FINDING ALL POSSIBLE MATCHES AT ONE POSITION - The traditional matching function uses a similar algorithm to Perl, - which stops when it finds the first match at a given point in the sub- + The traditional matching function uses a similar algorithm to Perl, + which stops when it finds the first match at a given point in the sub- ject. If you want to find all possible matches, or the longest possible - match at a given position, consider using the alternative matching - function (see below) instead. If you cannot use the alternative func- + match at a given position, consider using the alternative matching + function (see below) instead. If you cannot use the alternative func- tion, you can kludge it up by making use of the callout facility, which is described in the pcre2callout documentation. What you have to do is to insert a callout right at the end of the pat- - tern. When your callout function is called, extract and save the cur- - rent matched substring. Then return 1, which forces pcre2_match() to - backtrack and try other alternatives. Ultimately, when it runs out of + tern. When your callout function is called, extract and save the cur- + rent matched substring. Then return 1, which forces pcre2_match() to + backtrack and try other alternatives. Ultimately, when it runs out of matches, pcre2_match() will yield PCRE2_ERROR_NOMATCH. @@ -2863,26 +2866,26 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION pcre2_match_context *mcontext, int *workspace, PCRE2_SIZE wscount); - The function pcre2_dfa_match() 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 PCRE2 patterns are not supported. Never- - theless, there are times when this kind of matching can be useful. For - a discussion of the two matching algorithms, and a list of features + The function pcre2_dfa_match() 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 PCRE2 patterns are not supported. Never- + theless, 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 pcre2_dfa_match() does not support, see the pcre2matching documen- tation. - The arguments for the pcre2_dfa_match() function are the same as for + The arguments for the pcre2_dfa_match() function are the same as for pcre2_match(), plus two extras. The ovector within the match data block is used in a different way, and this is described below. The other com- - mon arguments are used in the same way as for pcre2_match(), so their + mon arguments are used in the same way as for pcre2_match(), 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 + 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 is needed for patterns and subjects where there are a lot of + workspace is needed for patterns and subjects where there are a lot of potential matches. Here is an example of a simple call to pcre2_dfa_match(): @@ -2902,45 +2905,45 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION Option bits for pcre_dfa_match() - The unused bits of the options argument for pcre2_dfa_match() must be - zero. The only bits that may be set are PCRE2_ANCHORED, PCRE2_NOTBOL, + The unused bits of the options argument for pcre2_dfa_match() must be + zero. The only bits that may be set are PCRE2_ANCHORED, PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART, PCRE2_NO_UTF_CHECK, PCRE2_PARTIAL_HARD, PCRE2_PARTIAL_SOFT, - PCRE2_DFA_SHORTEST, and PCRE2_DFA_RESTART. All but the last four of - these are exactly the same as for pcre2_match(), so their description + PCRE2_DFA_SHORTEST, and PCRE2_DFA_RESTART. All but the last four of + these are exactly the same as for pcre2_match(), so their description is not repeated here. PCRE2_PARTIAL_HARD PCRE2_PARTIAL_SOFT - These have the same general effect as they do for pcre2_match(), but - the details are slightly different. When PCRE2_PARTIAL_HARD is set for - pcre2_dfa_match(), it returns PCRE2_ERROR_PARTIAL if the end of the + These have the same general effect as they do for pcre2_match(), but + the details are slightly different. When PCRE2_PARTIAL_HARD is set for + pcre2_dfa_match(), it returns PCRE2_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 already been found. When PCRE2_PARTIAL_SOFT is set, the - return code PCRE2_ERROR_NOMATCH is converted into PCRE2_ERROR_PARTIAL - if the end of the subject is reached, there have been no complete + matches have already been found. When PCRE2_PARTIAL_SOFT is set, the + return code PCRE2_ERROR_NOMATCH is converted into PCRE2_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 por- - tion of the string that was inspected when the longest partial match + tion 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 + more detailed discussion of partial and multi-segment matching, with examples, in the pcre2partial documentation. PCRE2_DFA_SHORTEST - Setting the PCRE2_DFA_SHORTEST option causes the matching algorithm to + Setting the PCRE2_DFA_SHORTEST option causes the matching algorithm to stop as soon as it has found one match. Because of the way the alterna- - tive algorithm works, this is necessarily the shortest possible match + tive algorithm works, this is necessarily the shortest possible match at the first possible matching point in the subject string. PCRE2_DFA_RESTART - When pcre2_dfa_match() returns a partial match, it is possible to call + When pcre2_dfa_match() returns a partial match, it is possible to call it again, with additional subject characters, and have it continue with the same match. The PCRE2_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 + 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 pcre2partial documentation. @@ -2948,8 +2951,8 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION When pcre2_dfa_match() succeeds, it may have matched more than one sub- string 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, + 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 <.*> @@ -2964,17 +2967,17 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION - On success, the yield of the function is a number greater than zero, - which is the number of matched substrings. The offsets of the sub- - strings are returned in the ovector, and can be extracted by number in - the same way as for pcre2_match(), but the numbers bear no relation to - any capturing groups that may exist in the pattern, because DFA match- + On success, the yield of the function is a number greater than zero, + which is the number of matched substrings. The offsets of the sub- + strings are returned in the ovector, and can be extracted by number in + the same way as for pcre2_match(), but the numbers bear no relation to + any capturing groups that may exist in the pattern, because DFA match- ing does not support group capture. - Calls to the convenience functions that extract substrings by name - return the error PCRE2_ERROR_DFA_UFUNC (unsupported function) if used + Calls to the convenience functions that extract substrings by name + return the error PCRE2_ERROR_DFA_UFUNC (unsupported function) if used after a DFA match. The convenience functions that extract substrings by - number never return PCRE2_ERROR_NOSUBSTRING, and the meanings of some + number never return PCRE2_ERROR_NOSUBSTRING, and the meanings of some other errors are slightly different: PCRE2_ERROR_UNAVAILABLE @@ -2984,64 +2987,64 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION PCRE2_ERROR_UNSET - There is a slot in the ovector for this substring, but there were + There is a slot in the ovector for this substring, but there were insufficient matches to fill it. - The matched strings are stored in the ovector in reverse order of - length; that is, the longest matching string is first. If there were - too many matches to fit into the ovector, the yield of the function is + The matched strings are stored in the ovector in reverse order of + length; that is, the longest matching string is first. If there were + too many matches to fit into the ovector, the yield of the function is zero, and the vector is filled with the longest matches. - NOTE: PCRE2's "auto-possessification" optimization usually applies to - character repeats at the end of a pattern (as well as internally). For - example, the pattern "a\d+" is compiled as if it were "a\d++". For DFA - matching, this means that only one possible match is found. If you - really do want multiple matches in such cases, either use an ungreedy - repeat auch as "a\d+?" or set the PCRE2_NO_AUTO_POSSESS option when + NOTE: PCRE2's "auto-possessification" optimization usually applies to + character repeats at the end of a pattern (as well as internally). For + example, the pattern "a\d+" is compiled as if it were "a\d++". For DFA + matching, this means that only one possible match is found. If you + really do want multiple matches in such cases, either use an ungreedy + repeat auch as "a\d+?" or set the PCRE2_NO_AUTO_POSSESS option when compiling. Error returns from pcre2_dfa_match() The pcre2_dfa_match() function returns a negative number when it fails. - Many of the errors are the same as for pcre2_match(), as described + Many of the errors are the same as for pcre2_match(), as described above. There are in addition the following errors that are specific to pcre2_dfa_match(): PCRE2_ERROR_DFA_UITEM - This return is given if pcre2_dfa_match() encounters an item in the - pattern that it does not support, for instance, the use of \C in a UTF + This return is given if pcre2_dfa_match() encounters an item in the + pattern that it does not support, for instance, the use of \C in a UTF mode or a back reference. PCRE2_ERROR_DFA_UCOND - This return is given if pcre2_dfa_match() encounters a condition item - that uses a back reference for the condition, or a test for recursion + This return is given if pcre2_dfa_match() 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. PCRE2_ERROR_DFA_WSSIZE - This return is given if pcre2_dfa_match() runs out of space in the + This return is given if pcre2_dfa_match() runs out of space in the workspace vector. PCRE2_ERROR_DFA_RECURSE - When a recursive subpattern is processed, the matching function calls + When a recursive subpattern is processed, the matching function calls itself recursively, using private memory for the ovector and workspace. - This error is given if the internal ovector is not large enough. This + This error is given if the internal ovector is not large enough. This should be extremely rare, as a vector of size 1000 is used. PCRE2_ERROR_DFA_BADRESTART - When pcre2_dfa_match() is called with the PCRE2_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 + When pcre2_dfa_match() is called with the PCRE2_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. SEE ALSO - pcre2build(3), pcre2callout(3), pcre2demo(3), pcre2matching(3), + pcre2build(3), pcre2callout(3), pcre2demo(3), pcre2matching(3), pcre2partial(3), pcre2posix(3), pcre2sample(3), pcre2stack(3), pcre2unicode(3). @@ -3055,11 +3058,11 @@ AUTHOR REVISION - Last updated: 16 December 2015 - Copyright (c) 1997-2015 University of Cambridge. + Last updated: 31 January 2016 + Copyright (c) 1997-2016 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2BUILD(3) Library Functions Manual PCRE2BUILD(3) @@ -3542,8 +3545,8 @@ REVISION Last updated: 16 October 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2CALLOUT(3) Library Functions Manual PCRE2CALLOUT(3) @@ -3906,8 +3909,8 @@ REVISION Last updated: 23 March 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2COMPAT(3) Library Functions Manual PCRE2COMPAT(3) @@ -4091,8 +4094,8 @@ REVISION Last updated: 15 March 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2JIT(3) Library Functions Manual PCRE2JIT(3) @@ -4484,8 +4487,8 @@ REVISION Last updated: 14 November 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2LIMITS(3) Library Functions Manual PCRE2LIMITS(3) @@ -4562,8 +4565,8 @@ REVISION Last updated: 05 November 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2MATCHING(3) Library Functions Manual PCRE2MATCHING(3) @@ -4781,8 +4784,8 @@ REVISION Last updated: 29 September 2014 Copyright (c) 1997-2014 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2PARTIAL(3) Library Functions Manual PCRE2PARTIAL(3) @@ -5221,8 +5224,8 @@ REVISION Last updated: 22 December 2014 Copyright (c) 1997-2014 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2PATTERN(3) Library Functions Manual PCRE2PATTERN(3) @@ -6231,7 +6234,7 @@ MATCHING A SINGLE CODE UNIT PCRE2 does not allow \C to appear in lookbehind assertions (described below) in a UTF mode, because this would make it impossible to calcu- late the length of the lookbehind. Neither the alternative matching - function pcre2_dfa_match() not the JIT optimizer support \C in a UTF + function pcre2_dfa_match() nor the JIT optimizer support \C in a UTF mode. The former gives a match-time error; the latter fails to optimize and so the match is always run using the interpreter. @@ -8257,8 +8260,8 @@ REVISION Last updated: 13 November 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2PERFORM(3) Library Functions Manual PCRE2PERFORM(3) @@ -8430,8 +8433,8 @@ REVISION Last updated: 02 January 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2POSIX(3) Library Functions Manual PCRE2POSIX(3) @@ -8460,7 +8463,7 @@ DESCRIPTION This set of functions provides a POSIX-style API for the PCRE2 regular expression 8-bit library. See the pcre2api documentation for a descrip- tion of PCRE2's native API, which contains much additional functional- - ity. There is no POSIX-style wrapper for PCRE2's 16-bit and 32-bit + ity. There are no POSIX-style wrappers for PCRE2's 16-bit and 32-bit libraries. The functions described here are just wrapper functions that ultimately @@ -8478,8 +8481,8 @@ DESCRIPTION easier to slot in PCRE2 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 + There are also some options that are not defined by POSIX. These have + been added at the request of users who want to make use of certain PCRE2-specific features via the POSIX calling interface. When PCRE2 is called via these functions, it is only the API that is @@ -8530,11 +8533,11 @@ COMPILING A PATTERN REG_NOSUB - The PCRE2_NO_AUTO_CAPTURE option is set when the regular expression is - passed for compilation to the native function. In addition, when a pat- - tern that is compiled with this flag is passed to regexec() for match- - ing, the nmatch and pmatch arguments are ignored, and no captured - strings are returned. + When a pattern that is compiled with this flag is passed to regexec() + for matching, the nmatch and pmatch arguments are ignored, and no cap- + tured strings are returned. Versions of the PCRE library prior to 10.22 + used to set the PCRE2_NO_AUTO_CAPTURE compile option, but this no + longer happens because it disables the use of back references. REG_UCP @@ -8653,43 +8656,44 @@ MATCHING A PATTERN 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. + regexec() are ignored (except possibly as input for REG_STARTEND). - If the value of nmatch is zero, or if the value pmatch is NULL, no data - about any matched strings is returned. + The value of nmatch may be zero, and the value pmatch may be NULL + (unless REG_STARTEND is set); in both these cases no data about any + matched strings is returned. - Otherwise,the portion of the string that was matched, and also any cap- - tured substrings, are returned via the pmatch argument, which points to - an array of nmatch structures of type regmatch_t, containing the mem- - bers rm_so and rm_eo. These contain the byte offset to the first char- - acter 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 + 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 byte 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" + 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. ERROR MESSAGES The regerror() function maps a non-zero errorcode from either regcomp() - or regexec() to a printable message. If preg is not NULL, the error + 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. If the buffer is too short, only + by a binary zero is placed in errbuf. If the buffer is too short, only the first errbuf_size - 1 characters of the error message are used. The - yield of the function is the size of buffer needed to hold the whole - message, including the terminating zero. This value is greater than + yield of the function is the size of buffer needed to hold the whole + message, including the terminating zero. This value is greater than errbuf_size if the message was truncated. MEMORY USAGE - Compiling a regular expression causes memory to be allocated and asso- - ciated with the preg structure. The function regfree() frees all such - memory, after which preg may no longer be used as a compiled expres- + Compiling a regular expression causes memory to be allocated and asso- + ciated with the preg structure. The function regfree() frees all such + memory, after which preg may no longer be used as a compiled expres- sion. @@ -8702,11 +8706,11 @@ AUTHOR REVISION - Last updated: 29 November 2015 - Copyright (c) 1997-2015 University of Cambridge. + Last updated: 31 January 2016 + Copyright (c) 1997-2016 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2SAMPLE(3) Library Functions Manual PCRE2SAMPLE(3) @@ -8722,12 +8726,12 @@ PCRE2 SAMPLE PROGRAM documentation. If you do not have a copy of the PCRE2 distribution, you can save this listing to re-create the contents of pcre2demo.c. - The demonstration program, which uses the PCRE2 8-bit library, compiles - the regular expression that is its first argument, and matches it - against the subject string in its second argument. No PCRE2 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. + The demonstration program compiles the regular expression that is its + first argument, and matches it against the subject string in its second + argument. No PCRE2 options are set, and default character tables are + used. If matching succeeds, the program outputs the portion of the sub- + ject that matched, together with the contents of any captured sub- + strings. 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 @@ -8735,38 +8739,45 @@ PCRE2 SAMPLE PROGRAM bility of matching an empty string. Comments in the code explain what is going on. - If PCRE2 is installed in the standard include and library directories - for your operating system, you should be able to compile the demonstra- - tion program using this command: + The code in pcre2demo.c is an 8-bit program that uses the PCRE2 8-bit + library. It handles strings and characters that are stored in 8-bit + code units. By default, one character corresponds to one code unit, + but if the pattern starts with "(*UTF)", both it and the subject are + treated as UTF-8 strings, where characters may occupy multiple code + units. - gcc -o pcre2demo pcre2demo.c -lpcre2-8 + If PCRE2 is installed in the standard include and library directories + for your operating system, you should be able to compile the demonstra- + tion program using a command like this: + + cc -o pcre2demo pcre2demo.c -lpcre2-8 If PCRE2 is installed elsewhere, you may need to add additional options - to the command line. For example, on a Unix-like system that has PCRE2 - installed in /usr/local, you can compile the demonstration program + to the command line. For example, on a Unix-like system that has PCRE2 + installed in /usr/local, you can compile the demonstration program using a command like this: - gcc -o pcre2demo -I/usr/local/include pcre2demo.c \ - -L/usr/local/lib -lpcre2-8 + cc -o pcre2demo -I/usr/local/include pcre2demo.c \ + -L/usr/local/lib -lpcre2-8 - - Once you have compiled and linked the demonstration program, you can - run simple tests like this: + Once you have built the demonstration program, you can run simple tests + like this: ./pcre2demo 'cat|dog' 'the cat sat on the mat' ./pcre2demo -g 'cat|dog' 'the dog sat on the cat' - Note that there is a much more comprehensive test program, called - pcre2test, which supports many more facilities for testing regular - expressions using the PCRE2 libraries. The pcre2demo program is pro- - vided as a simple coding example. + Note that there is a much more comprehensive test program, called + pcre2test, which supports many more facilities for testing regular + expressions using all three PCRE2 libraries (8-bit, 16-bit, and 32-bit, + though not all three need be installed). The pcre2demo program is pro- + vided as a relatively simple coding example. If you try to run pcre2demo when PCRE2 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: libpcre2.so.0: open failed: No such file or - directory + ld.so.1: pcre2demo: fatal: libpcre2-8.so.0: open failed: No such file + or directory This is caused by the way shared library support works on those sys- tems. You need to add @@ -8785,8 +8796,8 @@ AUTHOR REVISION - Last updated: 20 October 2014 - Copyright (c) 1997-2014 University of Cambridge. + Last updated: 02 February 2016 + Copyright (c) 1997-2016 University of Cambridge. ------------------------------------------------------------------------------ PCRE2SERIALIZE(3) Library Functions Manual PCRE2SERIALIZE(3) @@ -8954,8 +8965,8 @@ REVISION Last updated: 03 November 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2STACK(3) Library Functions Manual PCRE2STACK(3) @@ -9120,8 +9131,8 @@ REVISION Last updated: 21 November 2014 Copyright (c) 1997-2014 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2SYNTAX(3) Library Functions Manual PCRE2SYNTAX(3) @@ -9556,8 +9567,8 @@ REVISION Last updated: 16 October 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2UNICODE(3) Library Functions Manual PCRE2UNICODE(3) @@ -9795,5 +9806,5 @@ REVISION Last updated: 16 October 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + diff --git a/doc/pcre2demo.3 b/doc/pcre2demo.3 index 5deed0a..c02dcd9 100644 --- a/doc/pcre2demo.3 +++ b/doc/pcre2demo.3 @@ -20,28 +20,31 @@ *************************************************/ /* This is a demonstration program to illustrate a straightforward way of -calling the PCRE2 regular expression library from a C program. See the +using the PCRE2 regular expression library from a C program. See the pcre2sample documentation for a short discussion ("man pcre2sample" if you have the PCRE2 man pages installed). PCRE2 is a revised API for the library, and is incompatible with the original PCRE API. There are actually three libraries, each supporting a different code unit -width. This demonstration program uses the 8-bit library. +width. This demonstration program uses the 8-bit library. The default is to +process each code unit as a separate character, but if the pattern begins with +"(*UTF)", both it and the subject are treated as UTF-8 strings, where +characters may occupy multiple code units. In Unix-like environments, if PCRE2 is installed in your standard system libraries, you should be able to compile this program using this command: -gcc -Wall pcre2demo.c -lpcre2-8 -o pcre2demo +cc -Wall pcre2demo.c -lpcre2-8 -o pcre2demo If PCRE2 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 pcre2demo.c `pkg-config --cflags --libs libpcre2-8` -o pcre2demo +cc -Wall pcre2demo.c `pkg-config --cflags --libs libpcre2-8` -o pcre2demo -If you do not have pkg-config, you may have to use this: +If you do not have pkg-config, you may have to use something like this: -gcc -Wall pcre2demo.c -I/usr/local/include -L/usr/local/lib \e +cc -Wall pcre2demo.c -I/usr/local/include -L/usr/local/lib \e -R/usr/local/lib -lpcre2-8 -o pcre2demo Replace "/usr/local/include" and "/usr/local/lib" with wherever the include and @@ -56,9 +59,14 @@ the following line. */ /* #define PCRE2_STATIC */ -/* This macro must be defined before including pcre2.h. For a program that uses -only one code unit width, it makes it possible to use generic function names -such as pcre2_compile(). */ +/* The PCRE2_CODE_UNIT_WIDTH macro must be defined before including pcre2.h. +For a program that uses only one code unit width, setting it to 8, 16, or 32 +makes it possible to use generic function names such as pcre2_compile(). Note +that just changing 8 to 16 (for example) is not sufficient to convert this +program to process 16-bit characters. Even in a fully 16-bit environment, where +string-handling functions such as strcmp() and printf() work with 16-bit +characters, the code for handling the table of named substrings will still need +to be modified. */ #define PCRE2_CODE_UNIT_WIDTH 8 @@ -79,19 +87,19 @@ int main(int argc, char **argv) { pcre2_code *re; PCRE2_SPTR pattern; /* PCRE2_SPTR is a pointer to unsigned code units of */ -PCRE2_SPTR subject; /* the appropriate width (8, 16, or 32 bits). */ +PCRE2_SPTR subject; /* the appropriate width (in this case, 8 bits). */ PCRE2_SPTR name_table; int crlf_is_newline; int errornumber; int find_all; int i; -int namecount; -int name_entry_size; int rc; int utf8; uint32_t option_bits; +uint32_t namecount; +uint32_t name_entry_size; uint32_t newline; PCRE2_SIZE erroroffset; @@ -106,15 +114,19 @@ pcre2_match_data *match_data; * 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. * +* if the -g option is present. * **************************************************************************/ find_all = 0; for (i = 1; i < argc; i++) { if (strcmp(argv[i], "-g") == 0) find_all = 1; - else break; + else if (argv[i][0] == '-') + { + printf("Unrecognised option %s\en", argv[i]); + return 1; + } + else break; } /* After the options, we require exactly two arguments, which are the pattern, @@ -122,7 +134,7 @@ and the subject string. */ if (argc - i != 2) { - printf("Two arguments required: a regex and a subject string\en"); + printf("Exactly two arguments required: a regex and a subject string\en"); return 1; } @@ -201,7 +213,7 @@ if (rc < 0) stored. */ ovector = pcre2_get_ovector_pointer(match_data); -printf("\enMatch succeeded at offset %d\en", (int)ovector[0]); +printf("Match succeeded at offset %d\en", (int)ovector[0]); /************************************************************************* @@ -242,7 +254,7 @@ we have to extract the count of named parentheses from the pattern. */ PCRE2_INFO_NAMECOUNT, /* get the number of named substrings */ &namecount); /* where to put the answer */ -if (namecount <= 0) printf("No named substrings\en"); else +if (namecount == 0) printf("No named substrings\en"); else { PCRE2_SPTR tabptr; printf("Named substrings\en"); @@ -330,8 +342,8 @@ crlf_is_newline = newline == PCRE2_NEWLINE_ANY || for (;;) { - uint32_t options = 0; /* Normally no options */ - PCRE2_SIZE start_offset = ovector[1]; /* Start at end of previous match */ + uint32_t options = 0; /* Normally no options */ + PCRE2_SIZE 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 @@ -371,7 +383,7 @@ for (;;) { if (options == 0) break; /* All matches found */ ovector[1] = start_offset + 1; /* Advance one code unit */ - if (crlf_is_newline && /* If CRLF is newline & */ + if (crlf_is_newline && /* If CRLF is a newline & */ start_offset < subject_length - 1 && /* we are at CRLF, */ subject[start_offset] == '\er' && subject[start_offset + 1] == '\en') @@ -417,7 +429,7 @@ for (;;) printf("%2d: %.*s\en", i, (int)substring_length, (char *)substring_start); } - if (namecount <= 0) printf("No named substrings\en"); else + if (namecount == 0) printf("No named substrings\en"); else { PCRE2_SPTR tabptr = name_table; printf("Named substrings\en"); diff --git a/doc/pcre2sample.3 b/doc/pcre2sample.3 index 7b46935..6e54ef0 100644 --- a/doc/pcre2sample.3 +++ b/doc/pcre2sample.3 @@ -1,4 +1,4 @@ -.TH PCRE2SAMPLE 3 "20 October 2014" "PCRE2 10.00" +.TH PCRE2SAMPLE 3 "02 February 2016" "PCRE2 10.22" .SH NAME PCRE2 - Perl-compatible regular expressions (revised API) .SH "PCRE2 SAMPLE PROGRAM" @@ -13,23 +13,28 @@ distribution. A listing of this program is given in the documentation. If you do not have a copy of the PCRE2 distribution, you can save this listing to re-create the contents of \fIpcre2demo.c\fP. .P -The demonstration program, which uses the PCRE2 8-bit library, compiles the -regular expression that is its first argument, and matches it against the -subject string in its second argument. No PCRE2 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. +The demonstration program compiles the regular expression that is its +first argument, and matches it against the subject string in its second +argument. No PCRE2 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. .P 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. .P +The code in \fBpcre2demo.c\fP is an 8-bit program that uses the PCRE2 8-bit +library. It handles strings and characters that are stored in 8-bit code units. +By default, one character corresponds to one code unit, but if the pattern +starts with "(*UTF)", both it and the subject are treated as UTF-8 strings, +where characters may occupy multiple code units. +.P If PCRE2 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: +a command like this: .sp - gcc -o pcre2demo pcre2demo.c -lpcre2-8 + cc -o pcre2demo pcre2demo.c -lpcre2-8 .sp If PCRE2 is installed elsewhere, you may need to add additional options to the command line. For example, on a Unix-like system that has PCRE2 installed in @@ -37,12 +42,11 @@ command line. For example, on a Unix-like system that has PCRE2 installed in like this: .sp .\" JOINSH - gcc -o pcre2demo -I/usr/local/include pcre2demo.c \e - -L/usr/local/lib -lpcre2-8 + cc -o pcre2demo -I/usr/local/include pcre2demo.c \e + -L/usr/local/lib -lpcre2-8 .sp -.P -Once you have compiled and linked the demonstration program, you can run simple -tests like this: +Once you have built the demonstration program, you can run simple tests like +this: .sp ./pcre2demo 'cat|dog' 'the cat sat on the mat' ./pcre2demo -g 'cat|dog' 'the dog sat on the cat' @@ -51,12 +55,13 @@ Note that there is a much more comprehensive test program, called .\" HREF \fBpcre2test\fP, .\" -which supports many more facilities for testing regular expressions using the -PCRE2 libraries. The +which supports many more facilities for testing regular expressions using all +three PCRE2 libraries (8-bit, 16-bit, and 32-bit, though not all three need be +installed). The .\" HREF \fBpcre2demo\fP .\" -program is provided as a simple coding example. +program is provided as a relatively simple coding example. .P If you try to run .\" HREF @@ -65,7 +70,7 @@ If you try to run when PCRE2 is not installed in the standard library directory, you may get an error like this on some operating systems (e.g. Solaris): .sp - ld.so.1: a.out: fatal: libpcre2.so.0: open failed: No such file or directory + ld.so.1: pcre2demo: fatal: libpcre2-8.so.0: open failed: No such file or directory .sp This is caused by the way shared library support works on those systems. You need to add @@ -89,6 +94,6 @@ Cambridge, England. .rs .sp .nf -Last updated: 20 October 2014 -Copyright (c) 1997-2014 University of Cambridge. +Last updated: 02 February 2016 +Copyright (c) 1997-2016 University of Cambridge. .fi diff --git a/doc/pcre2test.txt b/doc/pcre2test.txt index d9dbc4d..0446452 100644 --- a/doc/pcre2test.txt +++ b/doc/pcre2test.txt @@ -67,10 +67,10 @@ INPUT ENCODING For maximum portability, therefore, it is safest to avoid non-printing characters in pcre2test input files. There is a facility for specifying - a pattern's characters as hexadecimal pairs, thus making it possible to - include binary zeroes in a pattern for testing purposes. Subject lines - are processed for backslash escapes, which makes it possible to include - any data value. + some or all of a pattern's characters as hexadecimal pairs, thus making + it possible to include binary zeroes in a pattern for testing purposes. + Subject lines are processed for backslash escapes, which makes it pos- + sible to include any data value. COMMAND LINE OPTIONS @@ -505,7 +505,7 @@ PATTERN MODIFIERS debug same as info,fullbincode fullbincode show binary code with lengths /I info show info about compiled pattern - hex pattern is coded in hexadecimal + hex unquoted characters are hexadecimal jit[=] use JIT jitfast use JIT fast path jitverify verify JIT use @@ -516,6 +516,7 @@ PATTERN MODIFIERS null_context compile with a NULL context parens_nest_limit= set maximum parentheses depth posix use the POSIX API + posix_nosub use the POSIX API with REG_NOSUB push push compiled pattern onto the stack stackguard= test the stackguard feature tables=[0|1|2] select internal tables @@ -591,59 +592,70 @@ PATTERN MODIFIERS testing that pcre2_compile() behaves correctly in this case (it uses default values). - Specifying a pattern in hex + Specifying pattern characters in hexadecimal - The hex modifier specifies that the characters of the pattern are to be - interpreted as pairs of hexadecimal digits. White space is permitted - between pairs. For example: + The hex modifier specifies that the characters of the pattern, except + for substrings enclosed in single or double quotes, are to be inter- + preted as pairs of hexadecimal digits. This feature is provided as a + way of creating patterns that contain binary zeros and other non-print- + ing characters. White space is permitted between pairs of digits. For + example, this pattern contains three characters: /ab 32 59/hex - This feature is provided as a way of creating patterns that contain - binary zero and other non-printing characters. By default, pcre2test - passes patterns as zero-terminated strings to pcre2_compile(), giving - the length as PCRE2_ZERO_TERMINATED. However, for patterns specified in - hexadecimal, the actual length of the pattern is passed. + Parts of such a pattern are taken literally if quoted. This pattern + contains nine characters, only two of which are specified in hexadeci- + mal: + + /ab "literal" 32/hex + + Either single or double quotes may be used. There is no way of includ- + ing the delimiter within a substring. + + By default, pcre2test passes patterns as zero-terminated strings to + pcre2_compile(), giving the length as PCRE2_ZERO_TERMINATED. However, + for patterns specified with the hex modifier, the actual length of the + pattern is passed. Generating long repetitive patterns - Some tests use long patterns that are very repetitive. Instead of cre- - ating a very long input line for such a pattern, you can use a special - repetition feature, similar to the one described for subject lines - above. If the expand modifier is present on a pattern, parts of the + Some tests use long patterns that are very repetitive. Instead of cre- + ating a very long input line for such a pattern, you can use a special + repetition feature, similar to the one described for subject lines + above. If the expand modifier is present on a pattern, parts of the pattern that have the form \[]{} are expanded before the pattern is passed to pcre2_compile(). For exam- ple, \[AB]{6000} is expanded to "ABAB..." 6000 times. This construction - cannot be nested. An initial "\[" sequence is recognized only if "]{" - followed by decimal digits and "}" is found later in the pattern. If + cannot be nested. An initial "\[" sequence is recognized only if "]{" + followed by decimal digits and "}" is found later in the pattern. If not, the characters remain in the pattern unaltered. - If part of an expanded pattern looks like an expansion, but is really + If part of an expanded pattern looks like an expansion, but is really part of the actual pattern, unwanted expansion can be avoided by giving two values in the quantifier. For example, \[AB]{6000,6000} is not rec- ognized as an expansion item. - If the info modifier is set on an expanded pattern, the result of the + If the info modifier is set on an expanded pattern, the result of the expansion is included in the information that is output. JIT compilation - Just-in-time (JIT) compiling is a heavyweight optimization that can - greatly speed up pattern matching. See the pcre2jit documentation for - details. JIT compiling happens, optionally, after a pattern has been - successfully compiled into an internal form. The JIT compiler converts + Just-in-time (JIT) compiling is a heavyweight optimization that can + greatly speed up pattern matching. See the pcre2jit documentation for + details. JIT compiling happens, optionally, after a pattern has been + successfully compiled into an internal form. The JIT compiler converts this to optimized machine code. It needs to know whether the match-time options PCRE2_PARTIAL_HARD and PCRE2_PARTIAL_SOFT are going to be used, - because different code is generated for the different cases. See the - partial modifier in "Subject Modifiers" below for details of how these + because different code is generated for the different cases. See the + partial modifier in "Subject Modifiers" below for details of how these options are specified for each match attempt. - JIT compilation is requested by the /jit pattern modifier, which may + JIT compilation is requested by the /jit pattern modifier, which may optionally be followed by an equals sign and a number in the range 0 to - 7. The three bits that make up the number specify which of the three + 7. The three bits that make up the number specify which of the three JIT operating modes are to be compiled: 1 compile JIT code for non-partial matching @@ -660,31 +672,31 @@ PATTERN MODIFIERS 6 soft and hard partial matching only 7 all three modes - If no number is given, 7 is assumed. The phrase "partial matching" + If no number is given, 7 is assumed. The phrase "partial matching" means a call to pcre2_match() with either the PCRE2_PARTIAL_SOFT or the - PCRE2_PARTIAL_HARD option set. Note that such a call may return a com- + PCRE2_PARTIAL_HARD option set. Note that such a call may return a com- plete match; the options enable the possibility of a partial match, but - do not require it. Note also that if you request JIT compilation only - for partial matching (for example, /jit=2) but do not set the partial - modifier on a subject line, that match will not use JIT code because + do not require it. Note also that if you request JIT compilation only + for partial matching (for example, /jit=2) but do not set the partial + modifier on a subject line, that match will not use JIT code because none was compiled for non-partial matching. - If JIT compilation is successful, the compiled JIT code will automati- - cally be used when an appropriate type of match is run, except when - incompatible run-time options are specified. For more details, see the - pcre2jit documentation. See also the jitstack modifier below for a way + If JIT compilation is successful, the compiled JIT code will automati- + cally be used when an appropriate type of match is run, except when + incompatible run-time options are specified. For more details, see the + pcre2jit documentation. See also the jitstack modifier below for a way of setting the size of the JIT stack. - If the jitfast modifier is specified, matching is done using the JIT - "fast path" interface, pcre2_jit_match(), which skips some of the san- - ity checks that are done by pcre2_match(), and of course does not work - when JIT is not supported. If jitfast is specified without jit, jit=7 + If the jitfast modifier is specified, matching is done using the JIT + "fast path" interface, pcre2_jit_match(), which skips some of the san- + ity checks that are done by pcre2_match(), and of course does not work + when JIT is not supported. If jitfast is specified without jit, jit=7 is assumed. - If the jitverify modifier is specified, information about the compiled - pattern shows whether JIT compilation was or was not successful. If - jitverify is specified without jit, jit=7 is assumed. If JIT compila- - tion is successful when jitverify is set, the text "(JIT)" is added to + If the jitverify modifier is specified, information about the compiled + pattern shows whether JIT compilation was or was not successful. If + jitverify is specified without jit, jit=7 is assumed. If JIT compila- + tion is successful when jitverify is set, the text "(JIT)" is added to the first output line after a match or non match when JIT-compiled code was actually used in the match. @@ -695,18 +707,18 @@ PATTERN MODIFIERS /pattern/locale=fr_FR The given locale is set, pcre2_maketables() is called to build a set of - character tables for the locale, and this is then passed to pcre2_com- - pile() when compiling the regular expression. The same tables are used + character tables for the locale, and this is then passed to pcre2_com- + pile() when compiling the regular expression. The same tables are used when matching the following subject lines. The /locale modifier applies only to the pattern on which it appears, but can be given in a #pattern - command if a default is needed. Setting a locale and alternate charac- + command if a default is needed. Setting a locale and alternate charac- ter tables are mutually exclusive. Showing pattern memory - The /memory modifier causes the size in bytes of the memory used to - hold the compiled pattern to be output. This does not include the size - of the pcre2_code block; it is just the actual compiled data. If the + The /memory modifier causes the size in bytes of the memory used to + hold the compiled pattern to be output. This does not include the size + of the pcre2_code block; it is just the actual compiled data. If the pattern is subsequently passed to the JIT compiler, the size of the JIT compiled code is also output. Here is an example: @@ -717,31 +729,31 @@ PATTERN MODIFIERS Limiting nested parentheses - The parens_nest_limit modifier sets a limit on the depth of nested - parentheses in a pattern. Breaching the limit causes a compilation - error. The default for the library is set when PCRE2 is built, but - pcre2test sets its own default of 220, which is required for running + The parens_nest_limit modifier sets a limit on the depth of nested + parentheses in a pattern. Breaching the limit causes a compilation + error. The default for the library is set when PCRE2 is built, but + pcre2test sets its own default of 220, which is required for running the standard test suite. Limiting the pattern length - The max_pattern_length modifier sets a limit, in code units, to the + The max_pattern_length modifier sets a limit, in code units, to the length of pattern that pcre2_compile() will accept. Breaching the limit - causes a compilation error. The default is the largest number a + causes a compilation error. The default is the largest number a PCRE2_SIZE variable can hold (essentially unlimited). Using the POSIX wrapper API - The /posix modifier causes pcre2test to call PCRE2 via the POSIX wrap- - per API rather than its native API. This supports only the 8-bit - library. Note that it does not imply POSIX matching semantics; for - more detail see the pcre2posix documentation. When the POSIX API is - being used, the following pattern modifiers set options for the reg- - comp() function: + The /posix and posix_nosub modifiers cause pcre2test to call PCRE2 via + the POSIX wrapper API rather than its native API. When posix_nosub is + used, the POSIX option REG_NOSUB is passed to regcomp(). The POSIX + wrapper supports only the 8-bit library. Note that it does not imply + POSIX matching semantics; for more detail see the pcre2posix documenta- + tion. The following pattern modifiers set options for the regcomp() + function: caseless REG_ICASE multiline REG_NEWLINE - no_auto_capture REG_NOSUB dotall REG_DOTALL ) ungreedy REG_UNGREEDY ) These options are not part of ucp REG_UCP ) the POSIX standard @@ -758,23 +770,24 @@ PATTERN MODIFIERS been set, a large buffer is used. The aftertext and allaftertext subject modifiers work as described - below. All other modifiers cause an error. + below. All other modifiers are either ignored, with a warning message, + or cause an error. Testing the stack guard feature - The /stackguard modifier is used to test the use of pcre2_set_com- - pile_recursion_guard(), a function that is provided to enable stack - availability to be checked during compilation (see the pcre2api docu- - mentation for details). If the number specified by the modifier is + The /stackguard modifier is used to test the use of pcre2_set_com- + pile_recursion_guard(), a function that is provided to enable stack + availability to be checked during compilation (see the pcre2api docu- + mentation for details). If the number specified by the modifier is greater than zero, pcre2_set_compile_recursion_guard() is called to set - up callback from pcre2_compile() to a local function. The argument it - receives is the current nesting parenthesis depth; if this is greater + up callback from pcre2_compile() to a local function. The argument it + receives is the current nesting parenthesis depth; if this is greater than the value given by the modifier, non-zero is returned, causing the compilation to be aborted. Using alternative character tables - The value specified for the /tables modifier must be one of the digits + The value specified for the /tables modifier must be one of the digits 0, 1, or 2. It causes a specific set of built-in character tables to be passed to pcre2_compile(). This is used in the PCRE2 tests to check be- haviour with different character tables. The digit specifies the tables @@ -785,15 +798,15 @@ PATTERN MODIFIERS pcre2_chartables.c.dist 2 a set of tables defining ISO 8859 characters - In table 2, some characters whose codes are greater than 128 are iden- - tified as letters, digits, spaces, etc. Setting alternate character + In table 2, some characters whose codes are greater than 128 are iden- + tified as letters, digits, spaces, etc. Setting alternate character tables and a locale are mutually exclusive. Setting certain match controls The following modifiers are really subject modifiers, and are described - below. However, they may be included in a pattern's modifier list, in - which case they are applied to every subject line that is processed + below. However, they may be included in a pattern's modifier list, in + which case they are applied to every subject line that is processed with that pattern. They may not appear in #pattern commands. These mod- ifiers do not affect the compilation process. @@ -810,20 +823,20 @@ PATTERN MODIFIERS substitute_unknown_unset use PCRE2_SUBSTITUTE_UNKNOWN_UNSET substitute_unset_empty use PCRE2_SUBSTITUTE_UNSET_EMPTY - These modifiers may not appear in a #pattern command. If you want them + These modifiers may not appear in a #pattern command. If you want them as defaults, set them in a #subject command. Saving a compiled pattern - When a pattern with the push modifier is successfully compiled, it is - pushed onto a stack of compiled patterns, and pcre2test expects the - next line to contain a new pattern (or a command) instead of a subject + When a pattern with the push modifier is successfully compiled, it is + pushed onto a stack of compiled patterns, and pcre2test expects the + next line to contain a new pattern (or a command) instead of a subject line. This facility is used when saving compiled patterns to a file, as - described in the section entitled "Saving and restoring compiled pat- + described in the section entitled "Saving and restoring compiled pat- terns" below. The push modifier is incompatible with compilation modi- fiers such as global that act at match time. Any that are specified are - ignored, with a warning message, except for replace, which causes an - error. Note that, jitverify, which is allowed, does not carry through + ignored, with a warning message, except for replace, which causes an + error. Note that, jitverify, which is allowed, does not carry through to any subsequent matching that uses this pattern. @@ -834,7 +847,7 @@ SUBJECT MODIFIERS Setting match options - The following modifiers set options for pcre2_match() or + The following modifiers set options for pcre2_match() or pcre2_dfa_match(). See pcreapi for a description of their effects. anchored set PCRE2_ANCHORED @@ -848,20 +861,20 @@ SUBJECT MODIFIERS partial_hard (or ph) set PCRE2_PARTIAL_HARD partial_soft (or ps) set PCRE2_PARTIAL_SOFT - The partial matching modifiers are provided with abbreviations because + The partial matching modifiers are provided with abbreviations because they appear frequently in tests. - If the /posix modifier was present on the pattern, causing the POSIX + If the /posix modifier was present on the pattern, causing the POSIX wrapper API to be used, the only option-setting modifiers that have any - effect are notbol, notempty, and noteol, causing REG_NOTBOL, - REG_NOTEMPTY, and REG_NOTEOL, respectively, to be passed to regexec(). - Any other modifiers cause an error. + effect are notbol, notempty, and noteol, causing REG_NOTBOL, + REG_NOTEMPTY, and REG_NOTEOL, respectively, to be passed to regexec(). + The other modifiers are ignored, with a warning message. Setting match controls - The following modifiers affect the matching process or request addi- - tional information. Some of them may also be specified on a pattern - line (see above), in which case they apply to every subject line that + The following modifiers affect the matching process or request addi- + tional information. Some of them may also be specified on a pattern + line (see above), in which case they apply to every subject line that is matched against that pattern. aftertext show text after match @@ -898,6 +911,9 @@ SUBJECT MODIFIERS zero_terminate pass the subject as zero-terminated The effects of these modifiers are described in the following sections. + When matching via the POSIX wrapper API, the aftertext, allaftertext, + and ovector subject modifiers work as described below. All other modi- + fiers are either ignored, with a warning message, or cause an error. Showing more text @@ -1472,9 +1488,9 @@ SAVING AND RESTORING COMPILED PATTERNS matched with the pattern, terminated as usual by an empty line or end of file. This command may be followed by a modifier list containing only control modifiers that act after a pattern has been compiled. In - particular, hex, posix, and push are not allowed, nor are any option- - setting modifiers. The JIT modifiers are, however permitted. Here is - an example that saves and reloads two patterns. + particular, hex, posix, posix_nosub, and push are not allowed, nor are + any option-setting modifiers. The JIT modifiers are, however permit- + ted. Here is an example that saves and reloads two patterns. /abc/push /xyz/push @@ -1505,5 +1521,5 @@ AUTHOR REVISION - Last updated: 12 December 2015 - Copyright (c) 1997-2015 University of Cambridge. + Last updated: 31 January 2016 + Copyright (c) 1997-2016 University of Cambridge. diff --git a/src/pcre2demo.c b/src/pcre2demo.c index ec51cf1..8ae49f1 100644 --- a/src/pcre2demo.c +++ b/src/pcre2demo.c @@ -3,28 +3,31 @@ *************************************************/ /* This is a demonstration program to illustrate a straightforward way of -calling the PCRE2 regular expression library from a C program. See the +using the PCRE2 regular expression library from a C program. See the pcre2sample documentation for a short discussion ("man pcre2sample" if you have the PCRE2 man pages installed). PCRE2 is a revised API for the library, and is incompatible with the original PCRE API. There are actually three libraries, each supporting a different code unit -width. This demonstration program uses the 8-bit library. +width. This demonstration program uses the 8-bit library. The default is to +process each code unit as a separate character, but if the pattern begins with +"(*UTF)", both it and the subject are treated as UTF-8 strings, where +characters may occupy multiple code units. In Unix-like environments, if PCRE2 is installed in your standard system libraries, you should be able to compile this program using this command: -gcc -Wall pcre2demo.c -lpcre2-8 -o pcre2demo +cc -Wall pcre2demo.c -lpcre2-8 -o pcre2demo If PCRE2 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 pcre2demo.c `pkg-config --cflags --libs libpcre2-8` -o pcre2demo +cc -Wall pcre2demo.c `pkg-config --cflags --libs libpcre2-8` -o pcre2demo -If you do not have pkg-config, you may have to use this: +If you do not have pkg-config, you may have to use something like this: -gcc -Wall pcre2demo.c -I/usr/local/include -L/usr/local/lib \ +cc -Wall pcre2demo.c -I/usr/local/include -L/usr/local/lib \ -R/usr/local/lib -lpcre2-8 -o pcre2demo Replace "/usr/local/include" and "/usr/local/lib" with wherever the include and @@ -39,9 +42,14 @@ the following line. */ /* #define PCRE2_STATIC */ -/* This macro must be defined before including pcre2.h. For a program that uses -only one code unit width, it makes it possible to use generic function names -such as pcre2_compile(). */ +/* The PCRE2_CODE_UNIT_WIDTH macro must be defined before including pcre2.h. +For a program that uses only one code unit width, setting it to 8, 16, or 32 +makes it possible to use generic function names such as pcre2_compile(). Note +that just changing 8 to 16 (for example) is not sufficient to convert this +program to process 16-bit characters. Even in a fully 16-bit environment, where +string-handling functions such as strcmp() and printf() work with 16-bit +characters, the code for handling the table of named substrings will still need +to be modified. */ #define PCRE2_CODE_UNIT_WIDTH 8 @@ -62,19 +70,19 @@ int main(int argc, char **argv) { pcre2_code *re; PCRE2_SPTR pattern; /* PCRE2_SPTR is a pointer to unsigned code units of */ -PCRE2_SPTR subject; /* the appropriate width (8, 16, or 32 bits). */ +PCRE2_SPTR subject; /* the appropriate width (in this case, 8 bits). */ PCRE2_SPTR name_table; int crlf_is_newline; int errornumber; int find_all; int i; -int namecount; -int name_entry_size; int rc; int utf8; uint32_t option_bits; +uint32_t namecount; +uint32_t name_entry_size; uint32_t newline; PCRE2_SIZE erroroffset; @@ -89,15 +97,19 @@ pcre2_match_data *match_data; * 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. * +* if the -g option is present. * **************************************************************************/ find_all = 0; for (i = 1; i < argc; i++) { if (strcmp(argv[i], "-g") == 0) find_all = 1; - else break; + else if (argv[i][0] == '-') + { + printf("Unrecognised option %s\n", argv[i]); + return 1; + } + else break; } /* After the options, we require exactly two arguments, which are the pattern, @@ -105,7 +117,7 @@ and the subject string. */ if (argc - i != 2) { - printf("Two arguments required: a regex and a subject string\n"); + printf("Exactly two arguments required: a regex and a subject string\n"); return 1; } @@ -184,7 +196,7 @@ if (rc < 0) stored. */ ovector = pcre2_get_ovector_pointer(match_data); -printf("\nMatch succeeded at offset %d\n", (int)ovector[0]); +printf("Match succeeded at offset %d\n", (int)ovector[0]); /************************************************************************* @@ -225,7 +237,7 @@ we have to extract the count of named parentheses from the pattern. */ PCRE2_INFO_NAMECOUNT, /* get the number of named substrings */ &namecount); /* where to put the answer */ -if (namecount <= 0) printf("No named substrings\n"); else +if (namecount == 0) printf("No named substrings\n"); else { PCRE2_SPTR tabptr; printf("Named substrings\n"); @@ -313,8 +325,8 @@ crlf_is_newline = newline == PCRE2_NEWLINE_ANY || for (;;) { - uint32_t options = 0; /* Normally no options */ - PCRE2_SIZE start_offset = ovector[1]; /* Start at end of previous match */ + uint32_t options = 0; /* Normally no options */ + PCRE2_SIZE 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 @@ -354,7 +366,7 @@ for (;;) { if (options == 0) break; /* All matches found */ ovector[1] = start_offset + 1; /* Advance one code unit */ - if (crlf_is_newline && /* If CRLF is newline & */ + if (crlf_is_newline && /* If CRLF is a newline & */ start_offset < subject_length - 1 && /* we are at CRLF, */ subject[start_offset] == '\r' && subject[start_offset + 1] == '\n') @@ -400,7 +412,7 @@ for (;;) printf("%2d: %.*s\n", i, (int)substring_length, (char *)substring_start); } - if (namecount <= 0) printf("No named substrings\n"); else + if (namecount == 0) printf("No named substrings\n"); else { PCRE2_SPTR tabptr = name_table; printf("Named substrings\n");