Revision: 655
http://www.exim.org/viewvc/pcre2?view=rev&revision=655
Author: ph10
Date: 2017-01-16 17:40:47 +0000 (Mon, 16 Jan 2017)
Log Message:
-----------
File tidies for 10.23-RC1
Modified Paths:
--------------
code/trunk/AUTHORS
code/trunk/ChangeLog
code/trunk/LICENCE
code/trunk/Makefile.am
code/trunk/NEWS
code/trunk/README
code/trunk/RunTest
code/trunk/configure.ac
code/trunk/doc/html/README.txt
code/trunk/doc/html/pcre2_code_copy_with_tables.html
code/trunk/doc/html/pcre2_dfa_match.html
code/trunk/doc/html/pcre2api.html
code/trunk/doc/html/pcre2build.html
code/trunk/doc/html/pcre2callout.html
code/trunk/doc/html/pcre2compat.html
code/trunk/doc/html/pcre2grep.html
code/trunk/doc/html/pcre2limits.html
code/trunk/doc/html/pcre2pattern.html
code/trunk/doc/html/pcre2stack.html
code/trunk/doc/html/pcre2syntax.html
code/trunk/doc/html/pcre2test.html
code/trunk/doc/pcre2.txt
code/trunk/doc/pcre2_code_copy_with_tables.3
code/trunk/doc/pcre2api.3
code/trunk/doc/pcre2build.3
code/trunk/doc/pcre2callout.3
code/trunk/doc/pcre2compat.3
code/trunk/doc/pcre2grep.1
code/trunk/doc/pcre2grep.txt
code/trunk/doc/pcre2limits.3
code/trunk/doc/pcre2pattern.3
code/trunk/doc/pcre2stack.3
code/trunk/doc/pcre2syntax.3
code/trunk/doc/pcre2test.1
code/trunk/doc/pcre2test.txt
code/trunk/src/config.h.generic
code/trunk/src/pcre2.h
code/trunk/src/pcre2.h.generic
code/trunk/src/pcre2_auto_possess.c
code/trunk/src/pcre2_compile.c
code/trunk/src/pcre2_dfa_match.c
code/trunk/src/pcre2_error.c
code/trunk/src/pcre2_intmodedep.h
code/trunk/src/pcre2grep.c
Modified: code/trunk/AUTHORS
===================================================================
--- code/trunk/AUTHORS 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/AUTHORS 2017-01-16 17:40:47 UTC (rev 655)
@@ -8,7 +8,7 @@
University of Cambridge Computing Service,
Cambridge, England.
-Copyright (c) 1997-2016 University of Cambridge
+Copyright (c) 1997-2017 University of Cambridge
All rights reserved
@@ -19,7 +19,7 @@
Email local part: hzmester
Emain domain: freemail.hu
-Copyright(c) 2010-2016 Zoltan Herczeg
+Copyright(c) 2010-2017 Zoltan Herczeg
All rights reserved.
@@ -30,7 +30,7 @@
Email local part: hzmester
Emain domain: freemail.hu
-Copyright(c) 2009-2016 Zoltan Herczeg
+Copyright(c) 2009-2017 Zoltan Herczeg
All rights reserved.
####
Modified: code/trunk/ChangeLog
===================================================================
--- code/trunk/ChangeLog 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/ChangeLog 2017-01-16 17:40:47 UTC (rev 655)
@@ -2,8 +2,8 @@
--------------------
-Version 10.23 xx-xxxxxx-2016
-----------------------------
+Version 10.23 16-January-2017
+-----------------------------
1. Extended pcre2test with the utf8_input modifier so that it is able to
generate all possible 16-bit and 32-bit code unit values in non-UTF modes.
@@ -37,12 +37,12 @@
(f) When testing zero-terminated patterns under valgrind, the terminating
zero is now marked "no access". This catches bugs that would otherwise
show up only with non-zero-terminated patterns.
-
- (g) A hyphen appearing immediately after a POSIX character class (for example
- /[[:ascii:]-z]/) now generates an error. Perl does accept this as a
- literal, but gives a warning, so it seems best to fail it in PCRE.
-
- (h) An empty \Q\E sequence may appear after a callout that precedes an
+
+ (g) A hyphen appearing immediately after a POSIX character class (for example
+ /[[:ascii:]-z]/) now generates an error. Perl does accept this as a
+ literal, but gives a warning, so it seems best to fail it in PCRE.
+
+ (h) An empty \Q\E sequence may appear after a callout that precedes an
assertion condition (it is, of course, ignored).
One effect of the refactoring is that some error numbers and messages have
@@ -125,9 +125,9 @@
(r) If a character whose code point was greater than 0xffff appeared within
a lookbehind that was within another lookbehind, the calculation of the
lookbehind length went wrong and could provoke an internal error.
-
+
(t) The sequence \E- or \Q\E- after a POSIX class in a character class caused
- an internal error. Now the hyphen is treated as a literal.
+ an internal error. Now the hyphen is treated as a literal.
4. Back references are now permitted in lookbehind assertions when there are
no duplicated group numbers (that is, (?| has not been used), and, if the
@@ -269,14 +269,14 @@
pattern with PCRE2_UCP set without PCRE2_UTF if a class required all wide
characters to match (for example, /[\s[:^ascii:]]/).
-40. The callout_error modifier has been added to pcre2test to make it possible
+40. The callout_error modifier has been added to pcre2test to make it possible
to return PCRE2_ERROR_CALLOUT from a callout.
-41. A minor change to pcre2grep: colour reset is now "<esc>[0m" instead of
+41. A minor change to pcre2grep: colour reset is now "<esc>[0m" instead of
"<esc>[00m".
-42. The limit in the auto-possessification code that was intended to catch
-overly-complicated patterns and not spend too much time auto-possessifying was
+42. The limit in the auto-possessification code that was intended to catch
+overly-complicated patterns and not spend too much time auto-possessifying was
being reset too often, resulting in very long compile times for some patterns.
Now such patterns are no longer completely auto-possessified.
@@ -284,10 +284,10 @@
44. Added a new Windows script RunGrepTest.bat, courtesy of Jason Hood.
-45. Minor cosmetic fix to pcre2test: move a variable that is not used under
+45. Minor cosmetic fix to pcre2test: move a variable that is not used under
Windows into the "not Windows" code.
-46. Applied Jason Hood's patches to upgrade pcre2grep under Windows and tidy
+46. Applied Jason Hood's patches to upgrade pcre2grep under Windows and tidy
some of the code:
* normalised the Windows condition by ensuring WIN32 is defined;
@@ -306,27 +306,27 @@
* fixes a typo.
In addition, colour settings containing anything other than digits and
-semicolon are ignored, and the colour controls are no longer output for empty
+semicolon are ignored, and the colour controls are no longer output for empty
strings.
47. Detecting patterns that are too large inside the length-measuring loop
saves processing ridiculously long patterns to their end.
-48. Ignore PCRE2_CASELESS when processing \h, \H, \v, and \V in classes as it
+48. Ignore PCRE2_CASELESS when processing \h, \H, \v, and \V in classes as it
just wastes time. In the UTF case it can also produce redundant entries in
XCLASS lists caused by characters with multiple other cases and pairs of
characters in the same "not-x" sublists.
-49. A pattern such as /(?=(a\K))/ can report the end of the match being before
-its start; pcre2test was not handling this correctly when using the POSIX
+49. A pattern such as /(?=(a\K))/ can report the end of the match being before
+its start; pcre2test was not handling this correctly when using the POSIX
interface (it was OK with the native interface).
-50. In pcre2grep, ignore all JIT compile errors. This means that pcre2grep will
-continue to work, falling back to interpretation if anything goes wrong with
+50. In pcre2grep, ignore all JIT compile errors. This means that pcre2grep will
+continue to work, falling back to interpretation if anything goes wrong with
JIT.
-51. Applied patches from Christian Persch to configure.ac to make use of the
-AC_USE_SYSTEM_EXTENSIONS macro and to test for functions used by the JIT
+51. Applied patches from Christian Persch to configure.ac to make use of the
+AC_USE_SYSTEM_EXTENSIONS macro and to test for functions used by the JIT
modules.
52. Minor fixed to pcre2grep from Jason Hood:
@@ -335,7 +335,7 @@
to use appropriate quotes [in an example];
* LC_ALL was displayed as "LCC_ALL";
* numbers 11, 12 & 13 should end in "th".
- * use double quotes in usage message
+ * use double quotes in usage message
Version 10.22 29-July-2016
Modified: code/trunk/LICENCE
===================================================================
--- code/trunk/LICENCE 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/LICENCE 2017-01-16 17:40:47 UTC (rev 655)
@@ -25,7 +25,7 @@
University of Cambridge Computing Service,
Cambridge, England.
-Copyright (c) 1997-2016 University of Cambridge
+Copyright (c) 1997-2017 University of Cambridge
All rights reserved.
@@ -36,7 +36,7 @@
Email local part: hzmester
Emain domain: freemail.hu
-Copyright(c) 2010-2016 Zoltan Herczeg
+Copyright(c) 2010-2017 Zoltan Herczeg
All rights reserved.
@@ -47,7 +47,7 @@
Email local part: hzmester
Emain domain: freemail.hu
-Copyright(c) 2009-2016 Zoltan Herczeg
+Copyright(c) 2009-2017 Zoltan Herczeg
All rights reserved.
Modified: code/trunk/Makefile.am
===================================================================
--- code/trunk/Makefile.am 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/Makefile.am 2017-01-16 17:40:47 UTC (rev 655)
@@ -3,6 +3,10 @@
AUTOMAKE_OPTIONS = subdir-objects
ACLOCAL_AMFLAGS = -I m4
+## This seems to have become necessary for building in non-source directory.
+
+AM_CPPFLAGS="-I$(srcdir)/src"
+
## Specify the documentation files that are distributed.
dist_doc_DATA = \
Modified: code/trunk/NEWS
===================================================================
--- code/trunk/NEWS 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/NEWS 2017-01-16 17:40:47 UTC (rev 655)
@@ -1,6 +1,42 @@
News about PCRE2 releases
-------------------------
+Version 10.23 16-January-2017
+-----------------------------
+
+1. ChangeLog has the details of a lot of bug fixes and tidies.
+
+2. There has been a major re-factoring of the pcre2_compile.c file. Most syntax
+checking is now done in the pre-pass that identifies capturing groups. This has
+reduced the amount of duplication and made the code tidier. While doing this,
+some minor bugs and Perl incompatibilities were fixed (see ChangeLog for
+details.)
+
+3. Back references are now permitted in lookbehind assertions when there are
+no duplicated group numbers (that is, (?| has not been used), and, if the
+reference is by name, there is only one group of that name. The referenced
+group must, of course be of fixed length.
+
+4. \g{+<number>} (e.g. \g{+2} ) is now supported. It is a "forward back
+reference" and can be useful in repetitions (compare \g{-<number>} ). Perl does
+not recognize this syntax.
+
+5. pcre2grep now automatically expands its buffer up to a maximum set by
+--max-buffer-size.
+
+6. The -t option (grand total) has been added to pcre2grep.
+
+7. A new function called pcre2_code_copy_with_tables() exists to copy a
+compiled pattern along with a private copy of the character tables that is
+uses.
+
+8. A user supplied a number of patches to upgrade pcre2grep under Windows and
+tidy the code.
+
+9. Several updates have been made to pcre2test and test scripts (see
+ChangeLog).
+
+
Version 10.22 29-July-2016
--------------------------
Modified: code/trunk/README
===================================================================
--- code/trunk/README 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/README 2017-01-16 17:40:47 UTC (rev 655)
@@ -337,19 +337,19 @@
--with-pcre2grep-bufsize=51200
- The value must be a plain integer. The default is 20480. The amount of memory
- used by pcre2grep is actually three times this number, to allow for "before"
- and "after" lines. If very long lines are encountered, the buffer is
+ The value must be a plain integer. The default is 20480. The amount of memory
+ used by pcre2grep is actually three times this number, to allow for "before"
+ and "after" lines. If very long lines are encountered, the buffer is
automatically enlarged, up to a fixed maximum size.
-
-. The default maximum size of pcre2grep's internal buffer can be set by, for
+
+. The default maximum size of pcre2grep's internal buffer can be set by, for
example:
-
+
--with-pcre2grep-max-bufsize=2097152
-
- The default is either 1048576 or the value of --with-pcre2grep-bufsize,
- whichever is the larger.
+ The default is either 1048576 or the value of --with-pcre2grep-bufsize,
+ whichever is the larger.
+
. It is possible to compile pcre2test so that it links with the libreadline
or libedit libraries, by specifying, respectively,
@@ -372,21 +372,21 @@
If you get error messages about missing functions tgetstr, tgetent, tputs,
tgetflag, or tgoto, this is the problem, and linking with the ncurses library
should fix it.
-
-. There is a special option called --enable-fuzz-support for use by people who
- want to run fuzzing tests on PCRE2. At present this applies only to the 8-bit
- library. If set, it causes an extra library called libpcre2-fuzzsupport.a to
+
+. There is a special option called --enable-fuzz-support for use by people who
+ want to run fuzzing tests on PCRE2. At present this applies only to the 8-bit
+ library. If set, it causes an extra library called libpcre2-fuzzsupport.a to
be built, but not installed. This contains a single function called
- LLVMFuzzerTestOneInput() whose arguments are a pointer to a string and the
- length of the string. When called, this function tries to compile the string
- as a pattern, and if that succeeds, to match it. This is done both with no
+ LLVMFuzzerTestOneInput() whose arguments are a pointer to a string and the
+ length of the string. When called, this function tries to compile the string
+ as a pattern, and if that succeeds, to match it. This is done both with no
options and with some random options bits that are generated from the string.
Setting --enable-fuzz-support also causes a binary called pcre2fuzzcheck to
be created. This is normally run under valgrind or used when PCRE2 is
compiled with address sanitizing enabled. It calls the fuzzing function and
- outputs information about it is doing. The input strings are specified by
- arguments: if an argument starts with "=" the rest of it is a literal input
- string. Otherwise, it is assumed to be a file name, and the contents of the
+ outputs information about it is doing. The input strings are specified by
+ arguments: if an argument starts with "=" the rest of it is a literal input
+ string. Otherwise, it is assumed to be a file name, and the contents of the
file are the test string.
The "configure" script builds the following files for the basic C library:
@@ -777,7 +777,7 @@
src/pcre2_xclass.c )
src/pcre2_printint.c debugging function that is used by pcre2test,
- src/pcre2_fuzzsupport.c function for (optional) fuzzing support
+ src/pcre2_fuzzsupport.c function for (optional) fuzzing support
src/config.h.in template for config.h, when built by "configure"
src/pcre2.h.in template for pcre2.h when built by "configure"
Modified: code/trunk/RunTest
===================================================================
--- code/trunk/RunTest 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/RunTest 2017-01-16 17:40:47 UTC (rev 655)
@@ -520,7 +520,7 @@
echo $title2 "(excluding UTF-$bits) (64M stack)"
$sim $valgrind ${opt:+$vjs} ./pcre2test -q -S 64 $bmode $opt $testdata/testinput2 testtry
if [ $? = 0 ] ; then
- $sim $valgrind ${opt:+$vjs} ./pcre2test -q $bmode $opt -error -63,-62,-2,-1,0,100,188,189 >>testtry
+ $sim $valgrind ${opt:+$vjs} ./pcre2test -q $bmode $opt -error -63,-62,-2,-1,0,100,188,189,190,191 >>testtry
checkresult $? 2 "$opt"
else
echo " "
Modified: code/trunk/configure.ac
===================================================================
--- code/trunk/configure.ac 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/configure.ac 2017-01-16 17:40:47 UTC (rev 655)
@@ -11,16 +11,16 @@
m4_define(pcre2_major, [10])
m4_define(pcre2_minor, [23])
m4_define(pcre2_prerelease, [-RC1])
-m4_define(pcre2_date, [2016-08-01])
+m4_define(pcre2_date, [2017-01-16])
# NOTE: The CMakeLists.txt file searches for the above variables in the first
# 50 lines of this file. Please update that if the variables above are moved.
# Libtool shared library interface versions (current:revision:age)
-m4_define(libpcre2_8_version, [4:0:4])
-m4_define(libpcre2_16_version, [4:0:4])
-m4_define(libpcre2_32_version, [4:0:4])
-m4_define(libpcre2_posix_version, [1:0:0])
+m4_define(libpcre2_8_version, [5:0:5])
+m4_define(libpcre2_16_version, [5:0:5])
+m4_define(libpcre2_32_version, [5:0:5])
+m4_define(libpcre2_posix_version, [1:1:0])
AC_PREREQ(2.57)
AC_INIT(PCRE2, pcre2_major.pcre2_minor[]pcre2_prerelease, , pcre2)
@@ -630,7 +630,7 @@
AC_DEFINE_UNQUOTED([PCRE2GREP_BUFSIZE], [$with_pcre2grep_bufsize], [
The value of PCRE2GREP_BUFSIZE is the starting size of the buffer used by
pcre2grep to hold parts of the file it is searching. The buffer will be
- expanded up to PCRE2GREP_MAX_BUFSIZE if necessary, for files containing very
+ expanded up to PCRE2GREP_MAX_BUFSIZE if necessary, for files containing very
long lines. The actual amount of memory used by pcre2grep is three times this
number, because it allows for the buffering of "before" and "after" lines.])
@@ -936,7 +936,7 @@
C compiler flags ................... : ${CFLAGS} ${VISIBILITY_CFLAGS}
Linker flags ....................... : ${LDFLAGS}
Extra libraries .................... : ${LIBS}
-
+
Build 8-bit pcre2 library .......... : ${enable_pcre2_8}
Build 16-bit pcre2 library ......... : ${enable_pcre2_16}
Build 32-bit pcre2 library ......... : ${enable_pcre2_32}
@@ -966,7 +966,7 @@
Link pcre2test with libreadline .... : ${enable_pcre2test_libreadline}
Valgrind support ................... : ${enable_valgrind}
Code coverage ...................... : ${enable_coverage}
- Fuzzer support ..................... : ${enable_fuzz_support}
+ Fuzzer support ..................... : ${enable_fuzz_support}
EOF
Modified: code/trunk/doc/html/README.txt
===================================================================
--- code/trunk/doc/html/README.txt 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/doc/html/README.txt 2017-01-16 17:40:47 UTC (rev 655)
@@ -337,19 +337,19 @@
--with-pcre2grep-bufsize=51200
- The value must be a plain integer. The default is 20480. The amount of memory
- used by pcre2grep is actually three times this number, to allow for "before"
- and "after" lines. If very long lines are encountered, the buffer is
+ The value must be a plain integer. The default is 20480. The amount of memory
+ used by pcre2grep is actually three times this number, to allow for "before"
+ and "after" lines. If very long lines are encountered, the buffer is
automatically enlarged, up to a fixed maximum size.
-
-. The default maximum size of pcre2grep's internal buffer can be set by, for
+
+. The default maximum size of pcre2grep's internal buffer can be set by, for
example:
-
+
--with-pcre2grep-max-bufsize=2097152
-
- The default is either 1048576 or the value of --with-pcre2grep-bufsize,
- whichever is the larger.
+ The default is either 1048576 or the value of --with-pcre2grep-bufsize,
+ whichever is the larger.
+
. It is possible to compile pcre2test so that it links with the libreadline
or libedit libraries, by specifying, respectively,
@@ -372,21 +372,21 @@
If you get error messages about missing functions tgetstr, tgetent, tputs,
tgetflag, or tgoto, this is the problem, and linking with the ncurses library
should fix it.
-
-. There is a special option called --enable-fuzz-support for use by people who
- want to run fuzzing tests on PCRE2. At present this applies only to the 8-bit
- library. If set, it causes an extra library called libpcre2-fuzzsupport.a to
+
+. There is a special option called --enable-fuzz-support for use by people who
+ want to run fuzzing tests on PCRE2. At present this applies only to the 8-bit
+ library. If set, it causes an extra library called libpcre2-fuzzsupport.a to
be built, but not installed. This contains a single function called
- LLVMFuzzerTestOneInput() whose arguments are a pointer to a string and the
- length of the string. When called, this function tries to compile the string
- as a pattern, and if that succeeds, to match it. This is done both with no
+ LLVMFuzzerTestOneInput() whose arguments are a pointer to a string and the
+ length of the string. When called, this function tries to compile the string
+ as a pattern, and if that succeeds, to match it. This is done both with no
options and with some random options bits that are generated from the string.
Setting --enable-fuzz-support also causes a binary called pcre2fuzzcheck to
be created. This is normally run under valgrind or used when PCRE2 is
compiled with address sanitizing enabled. It calls the fuzzing function and
- outputs information about it is doing. The input strings are specified by
- arguments: if an argument starts with "=" the rest of it is a literal input
- string. Otherwise, it is assumed to be a file name, and the contents of the
+ outputs information about it is doing. The input strings are specified by
+ arguments: if an argument starts with "=" the rest of it is a literal input
+ string. Otherwise, it is assumed to be a file name, and the contents of the
file are the test string.
The "configure" script builds the following files for the basic C library:
@@ -777,7 +777,7 @@
src/pcre2_xclass.c )
src/pcre2_printint.c debugging function that is used by pcre2test,
- src/pcre2_fuzzsupport.c function for (optional) fuzzing support
+ src/pcre2_fuzzsupport.c function for (optional) fuzzing support
src/config.h.in template for config.h, when built by "configure"
src/pcre2.h.in template for pcre2.h when built by "configure"
Modified: code/trunk/doc/html/pcre2_code_copy_with_tables.html
===================================================================
--- code/trunk/doc/html/pcre2_code_copy_with_tables.html 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/doc/html/pcre2_code_copy_with_tables.html 2017-01-16 17:40:47 UTC (rev 655)
@@ -27,7 +27,7 @@
<P>
This function makes a copy of the memory used for a compiled pattern, excluding
any memory used by the JIT compiler. Without a subsequent call to
-<b>pcre2_jit_compile()</b>, the copy can be used only for non-JIT matching.
+<b>pcre2_jit_compile()</b>, the copy can be used only for non-JIT matching.
Unlike <b>pcre2_code_copy()</b>, a separate copy of the character tables is also
made, with the new code pointing to it. This memory will be automatically freed
when <b>pcre2_code_free()</b> is called. The yield of the function is NULL if
Modified: code/trunk/doc/html/pcre2_dfa_match.html
===================================================================
--- code/trunk/doc/html/pcre2_dfa_match.html 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/doc/html/pcre2_dfa_match.html 2017-01-16 17:40:47 UTC (rev 655)
@@ -45,8 +45,8 @@
<i>wscount</i> Number of elements in the vector
</pre>
For <b>pcre2_dfa_match()</b>, a match context is needed only if you want to set
-up a callout function. The <i>length</i> and <i>startoffset</i> values are code
-units, not characters. The options are:
+up a callout function or specify the recursion limit. The <i>length</i> and
+<i>startoffset</i> values are code units, not characters. The options are:
<pre>
PCRE2_ANCHORED Match only at the first position
PCRE2_NOTBOL Subject is not the beginning of a line
Modified: code/trunk/doc/html/pcre2api.html
===================================================================
--- code/trunk/doc/html/pcre2api.html 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/doc/html/pcre2api.html 2017-01-16 17:40:47 UTC (rev 655)
@@ -570,7 +570,7 @@
(perhaps waiting to see if the pattern is used often enough) similar logic is
required. JIT compilation updates a pointer within the compiled code block, so
a thread must gain unique write access to the pointer before calling
-<b>pcre2_jit_compile()</b>. Alternatively, <b>pcre2_code_copy()</b> or
+<b>pcre2_jit_compile()</b>. Alternatively, <b>pcre2_code_copy()</b> or
<b>pcre2_code_copy_with_tables()</b> can be used to obtain a private copy of the
compiled code.
</P>
@@ -740,7 +740,7 @@
<br>
This parameter ajusts the limit, set when PCRE2 is built (default 250), on the
depth of parenthesis nesting in a pattern. This limit stops rogue patterns
-using up too much system stack when being compiled. The limit applies to
+using up too much system stack when being compiled. The limit applies to
parentheses of all kinds, not just capturing parentheses.
<b>int pcre2_set_compile_recursion_guard(pcre2_compile_context *<i>ccontext</i>,</b>
<b> int (*<i>guard_function</i>)(uint32_t, void *), void *<i>user_data</i>);</b>
@@ -879,21 +879,23 @@
Limiting the recursion depth limits the amount of system stack that can be
used, or, when PCRE2 has been compiled to use memory on the heap instead of the
stack, the amount of heap memory that can be used. This limit is not relevant,
-and is ignored, when matching is done using JIT compiled code or by the
-<b>pcre2_dfa_match()</b> function.
+and is ignored, when matching is done using JIT compiled code. However, it is
+supported by <b>pcre2_dfa_match()</b>, which uses recursive function calls less
+frequently than <b>pcre2_match()</b>, but which can be caused to use a lot of
+stack by a recursive pattern such as /(.)(?1)/ matched to a very long string.
</P>
<P>
The default value for <i>recursion_limit</i> can be set when PCRE2 is built; the
default default is the same value as the default for <i>match_limit</i>. If the
-limit is exceeded, <b>pcre2_match()</b> returns PCRE2_ERROR_RECURSIONLIMIT. A
-value for the recursion limit may also be supplied by an item at the start of a
-pattern of the form
+limit is exceeded, <b>pcre2_match()</b> and <b>pcre2_dfa_match()</b> return
+PCRE2_ERROR_RECURSIONLIMIT. A value for the recursion limit may also be
+supplied by an item at the start of a pattern of the form
<pre>
(*LIMIT_RECURSION=ddd)
</pre>
where ddd is a decimal number. However, such a setting is ignored unless ddd is
-less than the limit set by the caller of <b>pcre2_match()</b> or, if no such
-limit is set, less than the default.
+less than the limit set by the caller of <b>pcre2_match()</b> or
+<b>pcre2_dfa_match()</b> or, if no such limit is set, less than the default.
<b>int pcre2_set_recursion_memory_management(</b>
<b> pcre2_match_context *<i>mcontext</i>,</b>
<b> void *(*<i>private_malloc</i>)(PCRE2_SIZE, void *),</b>
@@ -1087,20 +1089,20 @@
<a href="#jitcompiling">below),</a>
the JIT information cannot be copied (because it is position-dependent).
The new copy can initially be used only for non-JIT matching, though it can be
-passed to <b>pcre2_jit_compile()</b> if required.
+passed to <b>pcre2_jit_compile()</b> if required.
</P>
<P>
The <b>pcre2_code_copy()</b> function provides a way for individual threads in a
-multithreaded application to acquire a private copy of shared compiled code.
-However, it does not make a copy of the character tables used by the compiled
+multithreaded application to acquire a private copy of shared compiled code.
+However, it does not make a copy of the character tables used by the compiled
pattern; the new pattern code points to the same tables as the original code.
(See
<a href="#jitcompiling">"Locale Support"</a>
below for details of these character tables.) In many applications the same
-tables are used throughout, so this behaviour is appropriate. Nevertheless,
-there are occasions when a copy of a compiled pattern and the relevant tables
-are needed. The <b>pcre2_code_copy_with_tables()</b> provides this facility.
-Copies of both the code and the tables are made, with the new code pointing to
+tables are used throughout, so this behaviour is appropriate. Nevertheless,
+there are occasions when a copy of a compiled pattern and the relevant tables
+are needed. The <b>pcre2_code_copy_with_tables()</b> provides this facility.
+Copies of both the code and the tables are made, with the new code pointing to
the new tables. The memory for the new tables is automatically freed when
<b>pcre2_code_free()</b> is called for the new copy of the compiled code.
</P>
@@ -1140,7 +1142,7 @@
error code and an offset (number of code units) within the pattern,
respectively, when <b>pcre2_compile()</b> returns NULL because a compilation
error has occurred. The values are not defined when compilation is successful
-and <b>pcre2_compile()</b> returns a non-NULL value.
+and <b>pcre2_compile()</b> returns a non-NULL value.
</P>
<P>
The value returned in <i>erroroffset</i> is an indication of where in the
@@ -1976,7 +1978,7 @@
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 <i>ovector</i>.
+captured. This is known as the <i>ovector</i>.
</P>
<P>
Before calling <b>pcre2_match()</b>, <b>pcre2_dfa_match()</b>, or
@@ -3263,7 +3265,7 @@
</P>
<br><a name="SEC41" href="#TOC1">REVISION</a><br>
<P>
-Last updated: 22 November 2016
+Last updated: 23 December 2016
<br>
Copyright © 1997-2016 University of Cambridge.
<br>
Modified: code/trunk/doc/html/pcre2build.html
===================================================================
--- code/trunk/doc/html/pcre2build.html 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/doc/html/pcre2build.html 2017-01-16 17:40:47 UTC (rev 655)
@@ -380,15 +380,15 @@
finds a match. The starting size of the buffer is controlled by a parameter
whose default value is 20K. The buffer itself is three times this size, but
because of the way it is used for holding "before" lines, the longest line that
-is guaranteed to be processable is the parameter size. If a longer line is
+is guaranteed to be processable is the parameter size. If a longer line is
encountered, <b>pcre2grep</b> automatically expands the buffer, up to a
specified maximum size, whose default is 1M or the starting size, whichever is
the larger. You can change the default parameter values by adding, for example,
<pre>
--with-pcre2grep-bufsize=51200
- --with-pcre2grep-max-bufsize=2097152
+ --with-pcre2grep-max-bufsize=2097152
</pre>
-to the <b>configure</b> command. The caller of \fPpcre2grep\fP can override
+to the <b>configure</b> command. The caller of \fPpcre2grep\fP can override
these values by using --buffer-size and --max-buffer-size on the command line.
</P>
<br><a name="SEC18" href="#TOC1">PCRE2TEST OPTION FOR LIBREADLINE SUPPORT</a><br>
Modified: code/trunk/doc/html/pcre2callout.html
===================================================================
--- code/trunk/doc/html/pcre2callout.html 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/doc/html/pcre2callout.html 2017-01-16 17:40:47 UTC (rev 655)
@@ -64,7 +64,7 @@
</pre>
it is processed as if it were
<pre>
- (?C255)A(?C3)B(?C255)
+ (?C255)A(?C3)B(?C255)
</pre>
Here is a more complicated example:
<pre>
Modified: code/trunk/doc/html/pcre2compat.html
===================================================================
--- code/trunk/doc/html/pcre2compat.html 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/doc/html/pcre2compat.html 2017-01-16 17:40:47 UTC (rev 655)
@@ -133,8 +133,8 @@
<P>
14. Perl used to recognize comments in some places that PCRE2 does not, for
example, between the ( and ? at the start of a subpattern. If the /x modifier
-is set, Perl allowed white space between ( and ? though the latest Perls give
-an error (for a while it was just deprecated). There may still be some cases
+is set, Perl allowed white space between ( and ? though the latest Perls give
+an error (for a while it was just deprecated). There may still be some cases
where Perl behaves differently.
</P>
<P>
@@ -159,7 +159,7 @@
<br>
(a) Although lookbehind assertions in PCRE2 must match fixed length strings,
each alternative branch of a lookbehind assertion can match a different length
-of string. Perl requires them all to have the same length.
+of string. Perl requires them all to have the same length.
<br>
<br>
(b) From PCRE2 10.23, back references to groups of fixed length are supported
Modified: code/trunk/doc/html/pcre2grep.html
===================================================================
--- code/trunk/doc/html/pcre2grep.html 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/doc/html/pcre2grep.html 2017-01-16 17:40:47 UTC (rev 655)
@@ -91,7 +91,7 @@
</P>
<P>
The block of memory that is actually used is three times the "buffer size", to
-allow for buffering "before" and "after" lines. If the buffer size is too
+allow for buffering "before" and "after" lines. If the buffer size is too
small, fewer than requested "before" and "after" lines may be output.
</P>
<P>
@@ -178,8 +178,8 @@
</P>
<P>
<b>-B</b> <i>number</i>, <b>--before-context=</b><i>number</i>
-Output up to <i>number</i> lines of context before each matching line. Fewer
-lines are output if the previous match or the start of the file is within
+Output up to <i>number</i> lines of context before each matching line. Fewer
+lines are output if the previous match or the start of the file is within
<i>number</i> lines, or if the processing buffer size has been set too small. If
file names and/or line numbers are being output, a hyphen separator is used
instead of a colon for the context lines. A line containing "--" is output
@@ -202,8 +202,8 @@
</P>
<P>
<b>--buffer-size=</b><i>number</i>
-Set the parameter that controls how much memory is obtained at the start of
-processing for buffering files that are being scanned. See also
+Set the parameter that controls how much memory is obtained at the start of
+processing for buffering files that are being scanned. See also
<b>--max-buffer-size</b> below.
</P>
<P>
@@ -222,7 +222,7 @@
<br>
<br>
If no lines are selected, the number zero is output. If several files are are
-being scanned, a count is output for each of them and the <b>-t</b> option can
+being scanned, a count is output for each of them and the <b>-t</b> option can
be used to cause a total to be output at the end. However, if the
<b>--files-with-matches</b> option is also used, only those files whose counts
are greater than zero are listed. When <b>-c</b> is used, the <b>-A</b>,
@@ -245,13 +245,23 @@
just one, in order to colour them all.
<br>
<br>
-The colour that is used can be specified by setting the environment variable
-PCRE2GREP_COLOUR or PCRE2GREP_COLOR. If neither of these are set,
-<b>pcre2grep</b> looks for GREP_COLOUR or GREP_COLOR. The value of the variable
-should be a string of two numbers, separated by a semicolon. They are copied
-directly into the control string for setting colour on a terminal, so it is
-your responsibility to ensure that they make sense. If neither of the
-environment variables is set, the default is "1;31", which gives red.
+The colour that is used can be specified by setting one of the environment
+variables PCRE2GREP_COLOUR, PCRE2GREP_COLOR, PCREGREP_COLOUR, or
+PCREGREP_COLOR, which are checked in that order. If none of these are set,
+<b>pcre2grep</b> looks for GREP_COLORS or GREP_COLOR (in that order). The value
+of the variable should be a string of two numbers, separated by a semicolon,
+except in the case of GREP_COLORS, which must start with "ms=" or "mt="
+followed by two semicolon-separated colours, terminated by the end of the
+string or by a colon. If GREP_COLORS does not start with "ms=" or "mt=" it is
+ignored, and GREP_COLOR is checked.
+<br>
+<br>
+If the string obtained from one of the above variables contains any characters
+other than semicolon or digits, the setting is ignored and the default colour
+is used. The string is copied directly into the control string for setting
+colour on a terminal, so it is your responsibility to ensure that the values
+make sense. If no relevant environment variable is set, the default is "1;31",
+which gives red.
</P>
<P>
<b>-D</b> <i>action</i>, <b>--devices=</b><i>action</i>
@@ -353,7 +363,7 @@
command line; all arguments are treated as the names of paths to be searched.
</P>
<P>
-<b>--file-list</b>=<i>filename</i>
+<b>--file-list</b>=<i>filename</i>
Read a list of files and/or directories that are to be scanned from the given
file, one per line. Trailing white space is removed from each line, and blank
lines are ignored. These paths are processed before any that are listed on the
@@ -518,8 +528,8 @@
</P>
<P>
\fB--max-buffer-size=<i>number</i>
-This limits the expansion of the processing buffer, whose initial size can be
-set by <b>--buffer-size</b>. The maximum buffer size is silently forced to be no
+This limits the expansion of the processing buffer, whose initial size can be
+set by <b>--buffer-size</b>. The maximum buffer size is silently forced to be no
smaller than the starting buffer size.
</P>
<P>
@@ -619,7 +629,7 @@
match, nothing is output unless the file name or line number are being output.
<br>
<br>
-If this option is given multiple times, multiple substrings are output for each
+If this option is given multiple times, multiple substrings are output for each
match, in the order the options are given, and all on one line. For example,
-o3 -o1 -o3 causes the substrings matched by capturing parentheses 3 and 1 and
then 3 again to be output. By default, there is no separator (but see the next
@@ -693,7 +703,7 @@
<P>
<b>-x</b>, <b>--line-regex</b>, <b>--line-regexp</b>
Force the patterns to be anchored (each must start matching at the beginning of
-a line) and in addition, require them to match entire lines. In multiline mode
+a line) and in addition, require them to match entire lines. In multiline mode
the match may be more than one line. This is equivalent to having \A and \Z
characters at the start and end of each alternative top-level branch in every
pattern. This option applies only to the patterns that are matched against the
@@ -773,12 +783,12 @@
</P>
<br><a name="SEC10" href="#TOC1">CALLING EXTERNAL SCRIPTS</a><br>
<P>
-On non-Windows systems, <b>pcre2grep</b> has, by default, support for calling
-external programs or scripts during matching by making use of PCRE2's callout
-facility. However, this support can be disabled when <b>pcre2grep</b> is built.
-You can find out whether your binary has support for callouts by running it
-with the <b>--help</b> option. If the support is not enabled, all callouts in
-patterns are ignored by <b>pcre2grep</b>.
+<b>pcre2grep</b> has, by default, support for calling external programs or
+scripts during matching by making use of PCRE2's callout facility. However,
+this support can be disabled when <b>pcre2grep</b> is built. You can find out
+whether your binary has support for callouts by running it with the <b>--help</b>
+option. If the support is not enabled, all callouts in patterns are ignored by
+<b>pcre2grep</b>.
</P>
<P>
A callout in a PCRE2 pattern is of the form (?C<arg>) where the argument is
@@ -860,7 +870,7 @@
</P>
<br><a name="SEC15" href="#TOC1">REVISION</a><br>
<P>
-Last updated: 31 October 2016
+Last updated: 31 December 2016
<br>
Copyright © 1997-2016 University of Cambridge.
<br>
Modified: code/trunk/doc/html/pcre2limits.html
===================================================================
--- code/trunk/doc/html/pcre2limits.html 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/doc/html/pcre2limits.html 2017-01-16 17:40:47 UTC (rev 655)
@@ -62,8 +62,8 @@
no more than 65535 capturing subpatterns. There is, however, a limit to the
depth of nesting of parenthesized subpatterns of all kinds. This is imposed in
order to limit the amount of system stack used at compile time. The default
-limit can be specified when PCRE2 is built; the default default is 250. An
-application can change this limit by calling pcre2_set_parens_nest_limit() to
+limit can be specified when PCRE2 is built; the default default is 250. An
+application can change this limit by calling pcre2_set_parens_nest_limit() to
set the limit in a compile context.
</P>
<P>
@@ -76,7 +76,7 @@
32-bit libraries.
</P>
<P>
-The maximum length of a string argument to a callout is the largest number a
+The maximum length of a string argument to a callout is the largest number a
32-bit unsigned integer can hold.
</P>
<br><b>
Modified: code/trunk/doc/html/pcre2pattern.html
===================================================================
--- code/trunk/doc/html/pcre2pattern.html 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/doc/html/pcre2pattern.html 2017-01-16 17:40:47 UTC (rev 655)
@@ -190,6 +190,12 @@
for it to have any effect. In other words, the pattern writer can lower the
limits set by the programmer, but not raise them. If there is more than one
setting of one of these limits, the lower value is used.
+</P>
+<P>
+The match limit is used (but in a different way) when JIT is being used, but it
+is not relevant, and is ignored, when matching with <b>pcre2_dfa_match()</b>.
+However, the recursion limit is relevant for DFA matching, which does use some
+function recursion, in particular, for recursions within the pattern.
<a name="newlines"></a></P>
<br><b>
Newline conventions
@@ -1347,10 +1353,10 @@
b to d, a hyphen character, or z.
</P>
<P>
-Perl treats a hyphen as a literal if it appears before a POSIX class (see
-below) or a character type escape such as as \d, but gives a warning in its
-warning mode, as this is most likely a user error. As PCRE2 has no facility for
-warning, an error is given in these cases.
+Perl treats a hyphen as a literal if it appears before or after a POSIX class
+(see below) or a character type escape such as as \d, but gives a warning in
+its warning mode, as this is most likely a user error. As PCRE2 has no facility
+for warning, an error is given in these cases.
</P>
<P>
It is not possible to have the literal character "]" as the end character of a
@@ -2087,7 +2093,7 @@
</P>
<P>
Another way of avoiding the ambiguity inherent in the use of digits following a
-backslash is to use the \g escape sequence. This escape must be followed by a
+backslash is to use the \g escape sequence. This escape must be followed by a
signed or unsigned number, optionally enclosed in braces. These examples are
all identical:
<pre>
@@ -2108,8 +2114,8 @@
joining together fragments that contain references within themselves.
</P>
<P>
-The sequence \g{+1} is a reference to the next capturing subpattern. This kind
-of forward reference can be useful it patterns that repeat. Perl does not
+The sequence \g{+1} is a reference to the next capturing subpattern. This kind
+of forward reference can be useful it patterns that repeat. Perl does not
support the use of + in this way.
</P>
<P>
@@ -2212,11 +2218,11 @@
always, does do capturing in negative assertions.)
</P>
<P>
-WARNING: If a positive assertion containing one or more capturing subpatterns
-succeeds, but failure to match later in the pattern causes backtracking over
-this assertion, the captures within the assertion are reset only if no higher
-numbered captures are already set. This is, unfortunately, a fundamental
-limitation of the current implementation; it may get removed in a future
+WARNING: If a positive assertion containing one or more capturing subpatterns
+succeeds, but failure to match later in the pattern causes backtracking over
+this assertion, the captures within the assertion are reset only if no higher
+numbered captures are already set. This is, unfortunately, a fundamental
+limitation of the current implementation; it may get removed in a future
reworking.
</P>
<P>
@@ -2478,7 +2484,7 @@
<P>
Perl uses the syntax (?(<name>)...) or (?('name')...) to test for a used
subpattern by name. For compatibility with earlier versions of PCRE1, which had
-this facility before Perl, the syntax (?(name)...) is also recognized. Note,
+this facility before Perl, the syntax (?(name)...) is also recognized. Note,
however, that undelimited names consisting of the letter R followed by digits
are ambiguous (see the following section).
</P>
@@ -2508,7 +2514,7 @@
the condition is true if matching is currently in a recursion or subroutine
call to the whole pattern or any subpattern. If digits follow the letter R, and
there is no subpattern with that name, the condition is true if the most recent
-call is into a subpattern with the given number, which must exist somewhere in
+call is into a subpattern with the given number, which must exist somewhere in
the overall pattern. This is a contrived example that is equivalent to a+b:
<pre>
((?(R1)a+|(?1)b))
@@ -2523,11 +2529,11 @@
<pre>
(?(R&name)...)
</pre>
-the condition is true if the most recent recursion is into a subpattern of that
+the condition is true if the most recent recursion is into a subpattern of that
name (which must exist within the pattern).
</P>
<P>
-This condition does not check the entire recursion stack. It tests only the
+This condition does not check the entire recursion stack. It tests only the
current level. If the name used in a condition of this kind is a duplicate, the
test is applied to all subpatterns of the same name, and is true if any one of
them is the most recent recursion.
@@ -3008,14 +3014,14 @@
By default, for compatibility with Perl, a name is any sequence of characters
that does not include a closing parenthesis. The name is not processed in
any way, and it is not possible to include a closing parenthesis in the name.
-This can be changed by setting the PCRE2_ALT_VERBNAMES option, but the result
-is no longer Perl-compatible.
+This can be changed by setting the PCRE2_ALT_VERBNAMES option, but the result
+is no longer Perl-compatible.
</P>
<P>
When PCRE2_ALT_VERBNAMES is set, backslash processing is applied to verb names
-and only an unescaped closing parenthesis terminates the name. However, the
-only backslash items that are permitted are \Q, \E, and sequences such as
-\x{100} that define character code points. Character type escapes such as \d
+and only an unescaped closing parenthesis terminates the name. However, the
+only backslash items that are permitted are \Q, \E, and sequences such as
+\x{100} that define character code points. Character type escapes such as \d
are faulted.
</P>
<P>
@@ -3022,7 +3028,7 @@
A closing parenthesis can be included in a name either as \) or between \Q
and \E. In addition to backslash processing, if the PCRE2_EXTENDED option is
also set, unescaped whitespace in verb names is skipped, and #-comments are
-recognized, exactly as in the rest of the pattern. PCRE2_EXTENDED does not
+recognized, exactly as in the rest of the pattern. PCRE2_EXTENDED does not
affect verb names unless PCRE2_ALT_VERBNAMES is also set.
</P>
<P>
@@ -3446,7 +3452,7 @@
</P>
<br><a name="SEC30" href="#TOC1">REVISION</a><br>
<P>
-Last updated: 23 October 2016
+Last updated: 27 December 2016
<br>
Copyright © 1997-2016 University of Cambridge.
<br>
Modified: code/trunk/doc/html/pcre2stack.html
===================================================================
--- code/trunk/doc/html/pcre2stack.html 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/doc/html/pcre2stack.html 2017-01-16 17:40:47 UTC (rev 655)
@@ -57,12 +57,13 @@
Normally, these are never very deep, and the limit on the complexity of
<b>pcre2_dfa_match()</b> is controlled by the amount of workspace it is given.
However, it is possible to write patterns with runaway infinite recursions;
-such patterns will cause <b>pcre2_dfa_match()</b> to run out of stack. At
-present, there is no protection against this.
+such patterns will cause <b>pcre2_dfa_match()</b> to run out of stack unless a
+limit is applied (see below).
</P>
<P>
-The comments that follow do NOT apply to <b>pcre2_dfa_match()</b>; they are
-relevant only for <b>pcre2_match()</b> without the JIT optimization.
+The comments in the next three sections do not apply to
+<b>pcre2_dfa_match()</b>; they are relevant only for <b>pcre2_match()</b> without
+the JIT optimization.
</P>
<br><b>
Reducing <b>pcre2_match()</b>'s stack usage
@@ -115,7 +116,7 @@
in the
<a href="pcre2api.html"><b>pcre2api</b></a>
documentation. Since the block sizes are always the same, it may be possible to
-implement customized a memory handler that is more efficient than the standard
+implement a customized memory handler that is more efficient than the standard
function. The memory blocks obtained for this purpose are retained and re-used
if possible while <b>pcre2_match()</b> is running. They are all freed just
before it exits.
@@ -151,6 +152,15 @@
different limits.
</P>
<br><b>
+Limiting <b>pcre2_dfa_match()</b>'s stack usage
+</b><br>
+<P>
+The recursion limit, as described above for <b>pcre2_match()</b>, also applies
+to <b>pcre2_dfa_match()</b>, whose use of recursive function calls for
+recursions in the pattern can lead to runaway stack usage. The non-recursive
+match limit is not relevant for DFA matching, and is ignored.
+</P>
+<br><b>
Changing stack size in Unix-like systems
</b><br>
<P>
@@ -198,9 +208,9 @@
REVISION
</b><br>
<P>
-Last updated: 21 November 2014
+Last updated: 23 December 2016
<br>
-Copyright © 1997-2014 University of Cambridge.
+Copyright © 1997-2016 University of Cambridge.
<br>
<p>
Return to the <a href="index.html">PCRE2 index page</a>.
Modified: code/trunk/doc/html/pcre2syntax.html
===================================================================
--- code/trunk/doc/html/pcre2syntax.html 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/doc/html/pcre2syntax.html 2017-01-16 17:40:47 UTC (rev 655)
@@ -451,9 +451,10 @@
(*UCP) set PCRE2_UCP (use Unicode properties for \d etc)
</pre>
Note that LIMIT_MATCH and LIMIT_RECURSION can only reduce the value of the
-limits set by the caller of pcre2_match(), not increase them. The application
-can lock out the use of (*UTF) and (*UCP) by setting the PCRE2_NEVER_UTF or
-PCRE2_NEVER_UCP options, respectively, at compile time.
+limits set by the caller of <b>pcre2_match()</b> or <b>pcre2_dfa_match()</b>, not
+increase them. The application can lock out the use of (*UTF) and (*UCP) by
+setting the PCRE2_NEVER_UTF or PCRE2_NEVER_UCP options, respectively, at
+compile time.
</P>
<br><a name="SEC17" href="#TOC1">NEWLINE CONVENTION</a><br>
<P>
@@ -494,7 +495,7 @@
\g{n} reference by number
\g+n relative reference by number (PCRE2 extension)
\g-n relative reference by number
- \g{+n} relative reference by number (PCRE2 extension)
+ \g{+n} relative reference by number (PCRE2 extension)
\g{-n} relative reference by number
\k<name> reference by name (Perl)
\k'name' reference by name (Perl)
@@ -541,7 +542,7 @@
(?(VERSION[>]=n.m) test PCRE2 version
(?(assert) assertion condition
</pre>
-Note the ambiguity of (?(R) and (?(Rn) which might be named reference
+Note the ambiguity of (?(R) and (?(Rn) which might be named reference
conditions or recursion tests. Such a condition is interpreted as a reference
condition if the relevant named group exists.
</P>
@@ -595,7 +596,7 @@
</P>
<br><a name="SEC27" href="#TOC1">REVISION</a><br>
<P>
-Last updated: 28 September 2016
+Last updated: 23 December 2016
<br>
Copyright © 1997-2016 University of Cambridge.
<br>
Modified: code/trunk/doc/html/pcre2test.html
===================================================================
--- code/trunk/doc/html/pcre2test.html 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/doc/html/pcre2test.html 2017-01-16 17:40:47 UTC (rev 655)
@@ -114,7 +114,7 @@
when the <b>utf</b> modifier (see
<a href="#optionmodifiers">"Setting compilation options"</a>
below) is set, the pattern and any following subject lines are interpreted as
-UTF-8 strings and translated to UTF-16 or UTF-32 as appropriate.
+UTF-8 strings and translated to UTF-16 or UTF-32 as appropriate.
</P>
<P>
For non-UTF testing of wide characters, the <b>utf8_input</b> modifier can be
@@ -153,8 +153,13 @@
has not been built, this option causes an error.
</P>
<P>
+<b>-ac</b>
+Behave as if each pattern has the <b>auto_callout</b> modifier, that is, insert
+automatic callouts into every pattern that is compiled.
+</P>
+<P>
<b>-b</b>
-Behave as if each pattern has the <b>/fullbincode</b> modifier; the full
+Behave as if each pattern has the <b>fullbincode</b> modifier; the full
internal binary form of the pattern is output after compilation.
</P>
<P>
@@ -220,7 +225,7 @@
</P>
<P>
<b>-i</b>
-Behave as if each pattern has the <b>/info</b> modifier; information about the
+Behave as if each pattern has the <b>info</b> modifier; information about the
compiled pattern is given after compilation.
</P>
<P>
@@ -582,7 +587,7 @@
As well as turning on the PCRE2_UTF option, the <b>utf</b> modifier causes all
non-printing characters in output strings to be printed using the \x{hh...}
notation. Otherwise, those less than 0x100 are output in hex without the curly
-brackets. Setting <b>utf</b> in 16-bit or 32-bit mode also causes pattern and
+brackets. Setting <b>utf</b> in 16-bit or 32-bit mode also causes pattern and
subject strings to be translated to UTF-16 or UTF-32, respectively, before
being passed to library functions.
<a name="controlmodifiers"></a></P>
@@ -615,8 +620,8 @@
pushcopy push a copy onto the stack
stackguard=<number> test the stackguard feature
tables=[0|1|2] select internal tables
- use_length do not zero-terminate the pattern
- utf8_input treat input as UTF-8
+ use_length do not zero-terminate the pattern
+ utf8_input treat input as UTF-8
</pre>
The effects of these modifiers are described in the following sections.
</P>
@@ -705,7 +710,7 @@
By default, patterns are passed to the compiling functions as zero-terminated
strings. When using the POSIX wrapper API, there is no other option. However,
when using PCRE2's native API, patterns can be passed by length instead of
-being zero-terminated. The <b>use_length</b> modifier causes this to happen.
+being zero-terminated. The <b>use_length</b> modifier causes this to happen.
Using a length happens automatically (whether or not <b>use_length</b> is set)
when <b>hex</b> is set, because patterns specified in hexadecimal may contain
binary zeros.
@@ -733,9 +738,9 @@
mutually exclusive.
</P>
<P>
-The POSIX API cannot be used with patterns specified in hexadecimal because
-they may contain binary zeros, which conflicts with <b>regcomp()</b>'s
-requirement for a zero-terminated string. Such patterns are always passed to
+The POSIX API cannot be used with patterns specified in hexadecimal because
+they may contain binary zeros, which conflicts with <b>regcomp()</b>'s
+requirement for a zero-terminated string. Such patterns are always passed to
<b>pcre2_compile()</b> as a string with a length, not as zero-terminated.
</P>
<br><b>
@@ -742,8 +747,8 @@
Specifying wide characters in 16-bit and 32-bit modes
</b><br>
<P>
-In 16-bit and 32-bit modes, all input is automatically treated as UTF-8 and
-translated to UTF-16 or UTF-32 when the <b>utf</b> modifier is set. For testing
+In 16-bit and 32-bit modes, all input is automatically treated as UTF-8 and
+translated to UTF-16 or UTF-32 when the <b>utf</b> modifier is set. For testing
the 16-bit and 32-bit libraries in non-UTF mode, the <b>utf8_input</b> modifier
can be used. It is mutually exclusive with <b>utf</b>. Input lines are
interpreted as UTF-8 as a means of specifying wide characters. More details are
@@ -806,7 +811,7 @@
2 compile JIT code for soft partial matching
4 compile JIT code for hard partial matching
</pre>
-The possible values for the <b>/jit</b> modifier are therefore:
+The possible values for the <b>jit</b> modifier are therefore:
<pre>
0 disable JIT
1 normal matching only
@@ -852,7 +857,7 @@
Setting a locale
</b><br>
<P>
-The <b>/locale</b> modifier must specify the name of a locale, for example:
+The <b>locale</b> modifier must specify the name of a locale, for example:
<pre>
/pattern/locale=fr_FR
</pre>
@@ -859,7 +864,7 @@
The given locale is set, <b>pcre2_maketables()</b> is called to build a set of
character tables for the locale, and this is then passed to
<b>pcre2_compile()</b> when compiling the regular expression. The same tables
-are used when matching the following subject lines. The <b>/locale</b> modifier
+are used when matching the following subject lines. The <b>locale</b> modifier
applies only to the pattern on which it appears, but can be given in a
<b>#pattern</b> command if a default is needed. Setting a locale and alternate
character tables are mutually exclusive.
@@ -868,7 +873,7 @@
Showing pattern memory
</b><br>
<P>
-The <b>/memory</b> modifier causes the size in bytes of the memory used to hold
+The <b>memory</b> 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
<b>pcre2_code</b> 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
@@ -937,7 +942,7 @@
Testing the stack guard feature
</b><br>
<P>
-The <b>/stackguard</b> modifier is used to test the use of
+The <b>stackguard</b> modifier is used to test the use of
<b>pcre2_set_compile_recursion_guard()</b>, a function that is provided to
enable stack availability to be checked during compilation (see the
<a href="pcre2api.html"><b>pcre2api</b></a>
@@ -952,7 +957,7 @@
Using alternative character tables
</b><br>
<P>
-The value specified for the <b>/tables</b> modifier must be one of the digits 0,
+The value specified for the <b>tables</b> 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
<b>pcre2_compile()</b>. This is used in the PCRE2 tests to check behaviour with
different character tables. The digit specifies the tables as follows:
@@ -1042,7 +1047,7 @@
appear frequently in tests.
</P>
<P>
-If the <b>/posix</b> modifier was present on the pattern, causing the POSIX
+If the <b>posix</b> modifier was present on the pattern, causing the POSIX
wrapper API to be used, the only option-setting modifiers that have any effect
are <b>notbol</b>, <b>notempty</b>, and <b>noteol</b>, causing REG_NOTBOL,
REG_NOTEMPTY, and REG_NOTEOL, respectively, to be passed to <b>regexec()</b>.
@@ -1064,6 +1069,7 @@
altglobal alternative global matching
callout_capture show captures at callout time
callout_data=<n> set a value to pass via callouts
+ callout_error=<n>[:<m>] control callout error
callout_fail=<n>[:<m>] control callout failure
callout_none do not supply a callout function
copy=<number or name> copy captured substring
@@ -1159,17 +1165,24 @@
<P>
A callout function is supplied when <b>pcre2test</b> calls the library matching
functions, unless <b>callout_none</b> is specified. If <b>callout_capture</b> is
-set, the current captured groups are output when a callout occurs.
+set, the current captured groups are output when a callout occurs. The default
+return from the callout function is zero, which allows matching to continue.
</P>
<P>
The <b>callout_fail</b> modifier can be given one or two numbers. If there is
-only one number, 1 is returned instead of 0 when a callout of that number is
-reached. If two numbers are given, 1 is returned when callout <n> is reached
-for the <m>th time. Note that callouts with string arguments are always given
-the number zero. See "Callouts" below for a description of the output when a
-callout it taken.
+only one number, 1 is returned instead of 0 (causing matching to backtrack)
+when a callout of that number is reached. If two numbers (<n>:<m>) are given, 1
+is returned when callout <n> is reached and there have been at least <m>
+callouts. The <b>callout_error</b> modifier is similar, except that
+PCRE2_ERROR_CALLOUT is returned, causing the entire matching process to be
+aborted. If both these modifiers are set for the same callout number,
+<b>callout_error</b> takes precedence.
</P>
<P>
+Note that callouts with string arguments are always given the number zero. See
+"Callouts" below for a description of the output when a callout it taken.
+</P>
+<P>
The <b>callout_data</b> modifier can be given an unsigned or a negative number.
This is set as the "user data" that is passed to the matching function, and
passed back when the callout function is invoked. Any value other than zero is
@@ -1180,7 +1193,7 @@
</b><br>
<P>
Searching for all possible matches within a subject can be requested by the
-<b>global</b> or <b>/altglobal</b> modifier. After finding a match, the matching
+<b>global</b> or <b>altglobal</b> modifier. After finding a match, the matching
function is called again to search the remainder of the subject. The difference
between <b>global</b> and <b>altglobal</b> is that the former uses the
<i>start_offset</i> argument to <b>pcre2_match()</b> or <b>pcre2_dfa_match()</b>
@@ -1480,7 +1493,7 @@
If the strings contain any non-printing characters, they are output as \xhh
escapes if the value is less than 256 and UTF mode is not set. Otherwise they
are output as \x{hh...} escapes. See below for the definition of non-printing
-characters. If the <b>/aftertext</b> modifier is set, the output for substring
+characters. If the <b>aftertext</b> modifier is set, the output for substring
0 is followed by the the rest of the subject string, identified by "0+" like
this:
<pre>
@@ -1673,7 +1686,7 @@
<P>
When <b>pcre2test</b> is outputting text that is a matched part of a subject
string, it behaves in the same way, unless a different locale has been set for
-the pattern (using the <b>/locale</b> modifier). In this case, the
+the pattern (using the <b>locale</b> modifier). In this case, the
<b>isprint()</b> function is used to distinguish printing and non-printing
characters.
<a name="saverestore"></a></P>
@@ -1766,7 +1779,7 @@
</P>
<br><a name="SEC21" href="#TOC1">REVISION</a><br>
<P>
-Last updated: 04 November 2016
+Last updated: 28 December 2016
<br>
Copyright © 1997-2016 University of Cambridge.
<br>
Modified: code/trunk/doc/pcre2.txt
===================================================================
--- code/trunk/doc/pcre2.txt 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/doc/pcre2.txt 2017-01-16 17:40:47 UTC (rev 655)
@@ -169,8 +169,8 @@
Last updated: 16 October 2015
Copyright (c) 1997-2015 University of Cambridge.
------------------------------------------------------------------------------
-
-
+
+
PCRE2API(3) Library Functions Manual PCRE2API(3)
@@ -922,19 +922,22 @@
be used, or, when PCRE2 has been compiled to use memory on the heap
instead of the stack, the amount of heap memory that can be used. This
limit is not relevant, and is ignored, when matching is done using JIT
- compiled code or by the pcre2_dfa_match() function.
+ compiled code. However, it is supported by pcre2_dfa_match(), which
+ uses recursive function calls less frequently than pcre2_match(), but
+ which can be caused to use a lot of stack by a recursive pattern such
+ as /(.)(?1)/ matched to a very long string.
- The default value for recursion_limit can be set when PCRE2 is built;
- the default default is the same value as the default for match_limit.
- If the limit is exceeded, pcre2_match() returns PCRE2_ERROR_RECURSION-
- LIMIT. A value for the recursion limit may also be supplied by an item
- at the start of a pattern of the form
+ The default value for recursion_limit can be set when PCRE2 is built;
+ the default default is the same value as the default for match_limit.
+ If the limit is exceeded, pcre2_match() and pcre2_dfa_match() return
+ PCRE2_ERROR_RECURSIONLIMIT. A value for the recursion limit may also be
+ supplied by an item at the start of a pattern of the form
(*LIMIT_RECURSION=ddd)
- where ddd is a decimal number. However, such a setting is ignored
- unless ddd is less than the limit set by the caller of pcre2_match()
- or, if no such limit is set, less than the default.
+ where ddd is a decimal number. However, such a setting is ignored
+ unless ddd is less than the limit set by the caller of pcre2_match() or
+ pcre2_dfa_match() or, if no such limit is set, less than the default.
int pcre2_set_recursion_memory_management(
pcre2_match_context *mcontext,
@@ -942,21 +945,21 @@
void (*private_free)(void *, void *), void *memory_data);
This function sets up two additional custom memory management functions
- for use by pcre2_match() when PCRE2 is compiled to use the heap for
+ for use by pcre2_match() when PCRE2 is compiled to use the heap for
remembering backtracking data, instead of recursive function calls that
- use the system stack. There is a discussion about PCRE2's stack usage
- in the pcre2stack documentation. See the pcre2build documentation for
+ use the system stack. There is a discussion about PCRE2's stack usage
+ in the pcre2stack documentation. See the pcre2build documentation for
details of how to build PCRE2.
- Using the heap for recursion is a non-standard way of building PCRE2,
- for use in environments that have limited stacks. Because of the
+ Using the heap for recursion is a non-standard way of building PCRE2,
+ for use in environments that have limited stacks. Because of the
greater use of memory management, pcre2_match() runs more slowly. Func-
- tions that are different to the general custom memory functions are
- provided so that special-purpose external code can be used for this
- case, because the memory blocks are all the same size. The blocks are
+ tions that are different to the general custom memory functions are
+ provided so that special-purpose external code can be used for this
+ case, because the memory blocks are all the same size. The blocks are
retained by pcre2_match() until it is about to exit so that they can be
- re-used when possible during the match. In the absence of these func-
- tions, the normal custom memory management functions are used, if sup-
+ re-used when possible during the match. In the absence of these func-
+ tions, the normal custom memory management functions are used, if sup-
plied, otherwise the system functions.
@@ -964,75 +967,75 @@
int pcre2_config(uint32_t what, void *where);
- The function pcre2_config() makes it possible for a PCRE2 client to
- discover which optional features have been compiled into the PCRE2
- library. The pcre2build documentation has more details about these
+ The function pcre2_config() makes it possible for a PCRE2 client to
+ discover which optional features have been compiled into the PCRE2
+ library. The pcre2build documentation has more details about these
optional features.
- The first argument for pcre2_config() specifies which information is
- required. The second argument is a pointer to memory into which the
- information is placed. If NULL is passed, the function returns the
- amount of memory that is needed for the requested information. For
- calls that return numerical values, the value is in bytes; when
- requesting these values, where should point to appropriately aligned
- memory. For calls that return strings, the required length is given in
+ The first argument for pcre2_config() specifies which information is
+ required. The second argument is a pointer to memory into which the
+ information is placed. If NULL is passed, the function returns the
+ amount of memory that is needed for the requested information. For
+ calls that return numerical values, the value is in bytes; when
+ requesting these values, where should point to appropriately aligned
+ memory. For calls that return strings, the required length is given in
code units, not counting the terminating zero.
- When requesting information, the returned value from pcre2_config() is
- non-negative on success, or the negative error code PCRE2_ERROR_BADOP-
- TION if the value in the first argument is not recognized. The follow-
+ When requesting information, the returned value from pcre2_config() is
+ non-negative on success, or the negative error code PCRE2_ERROR_BADOP-
+ TION if the value in the first argument is not recognized. The follow-
ing information is available:
PCRE2_CONFIG_BSR
- The output is a uint32_t integer whose value indicates what character
- sequences the \R escape sequence matches by default. A value of
+ The output is a uint32_t integer whose value indicates what character
+ sequences the \R escape sequence matches by default. A value of
PCRE2_BSR_UNICODE means that \R matches any Unicode line ending
- sequence; a value of PCRE2_BSR_ANYCRLF means that \R matches only CR,
+ sequence; a value of PCRE2_BSR_ANYCRLF means that \R matches only CR,
LF, or CRLF. The default can be overridden when a pattern is compiled.
PCRE2_CONFIG_JIT
- The output is a uint32_t integer that is set to one if support for
+ The output is a uint32_t integer that is set to one if support for
just-in-time compiling is available; otherwise it is set to zero.
PCRE2_CONFIG_JITTARGET
- The where argument should point to a buffer that is at least 48 code
- units long. (The exact length required can be found by calling
- pcre2_config() with where set to NULL.) The buffer is filled with a
- string that contains the name of the architecture for which the JIT
- compiler is configured, for example "x86 32bit (little endian +
- unaligned)". If JIT support is not available, PCRE2_ERROR_BADOPTION is
- returned, otherwise the number of code units used is returned. This is
+ The where argument should point to a buffer that is at least 48 code
+ units long. (The exact length required can be found by calling
+ pcre2_config() with where set to NULL.) The buffer is filled with a
+ string that contains the name of the architecture for which the JIT
+ compiler is configured, for example "x86 32bit (little endian +
+ unaligned)". If JIT support is not available, PCRE2_ERROR_BADOPTION is
+ returned, otherwise the number of code units used is returned. This is
the length of the string, plus one unit for the terminating zero.
PCRE2_CONFIG_LINKSIZE
The output is a uint32_t integer that contains the number of bytes used
- for internal linkage in compiled regular expressions. When PCRE2 is
- configured, the value can be set to 2, 3, or 4, with the default being
- 2. This is the value that is returned by pcre2_config(). However, when
- the 16-bit library is compiled, a value of 3 is rounded up to 4, and
- when the 32-bit library is compiled, internal linkages always use 4
+ for internal linkage in compiled regular expressions. When PCRE2 is
+ configured, the value can be set to 2, 3, or 4, with the default being
+ 2. This is the value that is returned by pcre2_config(). However, when
+ the 16-bit library is compiled, a value of 3 is rounded up to 4, and
+ when the 32-bit library is compiled, internal linkages always use 4
bytes, so the configured value is not relevant.
The default value of 2 for the 8-bit and 16-bit libraries is sufficient
- for all but the most massive patterns, since it allows the size of the
+ for all but the most massive patterns, since it allows the size of the
compiled pattern to be up to 64K code units. Larger values allow larger
- regular expressions to be compiled by those two libraries, but at the
+ regular expressions to be compiled by those two libraries, but at the
expense of slower matching.
PCRE2_CONFIG_MATCHLIMIT
- The output is a uint32_t integer that gives the default limit for the
- number of internal matching function calls in a pcre2_match() execu-
+ The output is a uint32_t integer that gives the default limit for the
+ number of internal matching function calls in a pcre2_match() execu-
tion. Further details are given with pcre2_match() below.
PCRE2_CONFIG_NEWLINE
- The output is a uint32_t integer whose value specifies the default
- character sequence that is recognized as meaning "newline". The values
+ The output is a uint32_t integer whose value specifies the default
+ character sequence that is recognized as meaning "newline". The values
are:
PCRE2_NEWLINE_CR Carriage return (CR)
@@ -1041,56 +1044,56 @@
PCRE2_NEWLINE_ANY Any Unicode line ending
PCRE2_NEWLINE_ANYCRLF Any of CR, LF, or CRLF
- The default should normally correspond to the standard sequence for
+ The default should normally correspond to the standard sequence for
your operating system.
PCRE2_CONFIG_PARENSLIMIT
- The output is a uint32_t integer that gives the maximum depth of nest-
+ The output is a uint32_t integer that gives the maximum depth of nest-
ing of parentheses (of any kind) in a pattern. This limit is imposed to
- cap the amount of system stack used when a pattern is compiled. It is
- specified when PCRE2 is built; the default is 250. This limit does not
- take into account the stack that may already be used by the calling
- application. For finer control over compilation stack usage, see
+ cap the amount of system stack used when a pattern is compiled. It is
+ specified when PCRE2 is built; the default is 250. This limit does not
+ take into account the stack that may already be used by the calling
+ application. For finer control over compilation stack usage, see
pcre2_set_compile_recursion_guard().
PCRE2_CONFIG_RECURSIONLIMIT
- The output is a uint32_t integer that gives the default limit for the
- depth of recursion when calling the internal matching function in a
- pcre2_match() execution. Further details are given with pcre2_match()
+ The output is a uint32_t integer that gives the default limit for the
+ depth of recursion when calling the internal matching function in a
+ pcre2_match() execution. Further details are given with pcre2_match()
below.
PCRE2_CONFIG_STACKRECURSE
- The output is a uint32_t integer that is set to one if internal recur-
- sion when running pcre2_match() is implemented by recursive function
- calls that use the system stack to remember their state. This is the
- usual way that PCRE2 is compiled. The output is zero if PCRE2 was com-
- piled to use blocks of data on the heap instead of recursive function
+ The output is a uint32_t integer that is set to one if internal recur-
+ sion when running pcre2_match() is implemented by recursive function
+ calls that use the system stack to remember their state. This is the
+ usual way that PCRE2 is compiled. The output is zero if PCRE2 was com-
+ piled to use blocks of data on the heap instead of recursive function
calls.
PCRE2_CONFIG_UNICODE_VERSION
- The where argument should point to a buffer that is at least 24 code
- units long. (The exact length required can be found by calling
- pcre2_config() with where set to NULL.) If PCRE2 has been compiled
- without Unicode support, the buffer is filled with the text "Unicode
- not supported". Otherwise, the Unicode version string (for example,
- "8.0.0") is inserted. The number of code units used is returned. This
+ The where argument should point to a buffer that is at least 24 code
+ units long. (The exact length required can be found by calling
+ pcre2_config() with where set to NULL.) If PCRE2 has been compiled
+ without Unicode support, the buffer is filled with the text "Unicode
+ not supported". Otherwise, the Unicode version string (for example,
+ "8.0.0") is inserted. The number of code units used is returned. This
is the length of the string plus one unit for the terminating zero.
PCRE2_CONFIG_UNICODE
- The output is a uint32_t integer that is set to one if Unicode support
- is available; otherwise it is set to zero. Unicode support implies UTF
+ The output is a uint32_t integer that is set to one if Unicode support
+ is available; otherwise it is set to zero. Unicode support implies UTF
support.
PCRE2_CONFIG_VERSION
- The where argument should point to a buffer that is at least 12 code
- units long. (The exact length required can be found by calling
- pcre2_config() with where set to NULL.) The buffer is filled with the
+ The where argument should point to a buffer that is at least 12 code
+ units long. (The exact length required can be found by calling
+ pcre2_config() with where set to NULL.) The buffer is filled with the
PCRE2 version string, zero-terminated. The number of code units used is
returned. This is the length of the string plus one unit for the termi-
nating zero.
@@ -1108,89 +1111,89 @@
pcre2_code *pcre2_code_copy_with_tables(const pcre2_code *code);
- The pcre2_compile() function compiles a pattern into an internal form.
- The pattern is defined by a pointer to a string of code units and a
- length. If the pattern is zero-terminated, the length can be specified
- as PCRE2_ZERO_TERMINATED. The function returns a pointer to a block of
- memory that contains the compiled pattern and related data, or NULL if
+ The pcre2_compile() function compiles a pattern into an internal form.
+ The pattern is defined by a pointer to a string of code units and a
+ length. If the pattern is zero-terminated, the length can be specified
+ as PCRE2_ZERO_TERMINATED. The function returns a pointer to a block of
+ memory that contains the compiled pattern and related data, or NULL if
an error occurred.
- If the compile context argument ccontext is NULL, memory for the com-
- piled pattern is obtained by calling malloc(). Otherwise, it is
- obtained from the same memory function that was used for the compile
- context. The caller must free the memory by calling pcre2_code_free()
+ If the compile context argument ccontext is NULL, memory for the com-
+ piled pattern is obtained by calling malloc(). Otherwise, it is
+ obtained from the same memory function that was used for the compile
+ context. The caller must free the memory by calling pcre2_code_free()
when it is no longer needed.
The function pcre2_code_copy() makes a copy of the compiled code in new
- memory, using the same memory allocator as was used for the original.
- However, if the code has been processed by the JIT compiler (see
- below), the JIT information cannot be copied (because it is position-
+ memory, using the same memory allocator as was used for the original.
+ However, if the code has been processed by the JIT compiler (see
+ below), the JIT information cannot be copied (because it is position-
dependent). The new copy can initially be used only for non-JIT match-
ing, though it can be passed to pcre2_jit_compile() if required.
The pcre2_code_copy() function provides a way for individual threads in
- a multithreaded application to acquire a private copy of shared com-
- piled code. However, it does not make a copy of the character tables
- used by the compiled pattern; the new pattern code points to the same
- tables as the original code. (See "Locale Support" below for details
- of these character tables.) In many applications the same tables are
- used throughout, so this behaviour is appropriate. Nevertheless, there
+ a multithreaded application to acquire a private copy of shared com-
+ piled code. However, it does not make a copy of the character tables
+ used by the compiled pattern; the new pattern code points to the same
+ tables as the original code. (See "Locale Support" below for details
+ of these character tables.) In many applications the same tables are
+ used throughout, so this behaviour is appropriate. Nevertheless, there
are occasions when a copy of a compiled pattern and the relevant tables
- are needed. The pcre2_code_copy_with_tables() provides this facility.
- Copies of both the code and the tables are made, with the new code
- pointing to the new tables. The memory for the new tables is automati-
- cally freed when pcre2_code_free() is called for the new copy of the
+ are needed. The pcre2_code_copy_with_tables() provides this facility.
+ Copies of both the code and the tables are made, with the new code
+ pointing to the new tables. The memory for the new tables is automati-
+ cally freed when pcre2_code_free() is called for the new copy of the
compiled code.
- NOTE: When one of the matching functions is called, pointers to the
+ NOTE: 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 substring extraction functions.
- After running a match, you must not free a compiled pattern (or a sub-
- ject string) until after all operations on the match data block have
+ so that they can be referenced by the substring extraction functions.
+ After running a match, you must not free a compiled pattern (or a sub-
+ ject string) until after all operations on the match data block have
taken place.
- The options argument for pcre2_compile() contains various bit settings
- that affect the compilation. It should be zero if no options are
- required. The available options are described below. Some of them (in
- particular, those that are compatible with Perl, but some others as
- well) can also be set and unset from within the pattern (see the
+ The options argument for pcre2_compile() contains various bit settings
+ that affect the compilation. It should be zero if no options are
+ required. The available options are described below. Some of them (in
+ particular, those that are compatible with Perl, but some others as
+ well) can also be set and unset from within the pattern (see the
detailed description in the pcre2pattern documentation).
- For those options that can be different in different parts of the pat-
- tern, the contents of the options argument specifies their settings at
- the start of compilation. The PCRE2_ANCHORED and PCRE2_NO_UTF_CHECK
+ For those options that can be different in different parts of the pat-
+ tern, the contents of the options argument specifies their settings at
+ the start of compilation. The PCRE2_ANCHORED and PCRE2_NO_UTF_CHECK
options can be set at the time of matching as well as at compile time.
- Other, less frequently required compile-time parameters (for example,
+ Other, less frequently required compile-time parameters (for example,
the newline setting) can be provided in a compile context (as described
above).
If errorcode or erroroffset is NULL, pcre2_compile() returns NULL imme-
- diately. Otherwise, the variables to which these point are set to an
- error code and an offset (number of code units) within the pattern,
- respectively, when pcre2_compile() returns NULL because a compilation
+ diately. Otherwise, the variables to which these point are set to an
+ error code and an offset (number of code units) within the pattern,
+ respectively, when pcre2_compile() returns NULL because a compilation
error has occurred. The values are not defined when compilation is suc-
cessful and pcre2_compile() returns a non-NULL value.
The value returned in erroroffset is an indication of where in the pat-
- tern the error occurred. It is not necessarily the furthest point in
- the pattern that was read. For example, after the error "lookbehind
+ tern the error occurred. It is not necessarily the furthest point in
+ the pattern that was read. For example, after the error "lookbehind
assertion is not fixed length", the error offset points to the start of
the failing assertion.
- The pcre2_get_error_message() function (see "Obtaining a textual error
- message" below) provides a textual message for each error code. Compi-
+ The pcre2_get_error_message() function (see "Obtaining a textual error
+ message" below) provides a textual message for each error code. Compi-
lation errors have positive error codes; UTF formatting error codes are
- negative. For an invalid UTF-8 or UTF-16 string, the offset is that of
+ negative. For an invalid UTF-8 or UTF-16 string, the offset is that of
the first code unit of the failing character.
- Some errors are not detected until the whole pattern has been scanned;
- in these cases, the offset passed back is the length of the pattern.
- Note that the offset is in code units, not characters, even in a UTF
+ Some errors are not detected until the whole pattern has been scanned;
+ in these cases, the offset passed back is the length of the pattern.
+ Note that the offset is in code units, not characters, even in a UTF
mode. It may sometimes point into the middle of a UTF-8 or UTF-16 char-
acter.
- This code fragment shows a typical straightforward call to pcre2_com-
+ This code fragment shows a typical straightforward call to pcre2_com-
pile():
pcre2_code *re;
@@ -1204,28 +1207,28 @@
&erroffset, /* for error offset */
NULL); /* no compile context */
- The following names for option bits are defined in the pcre2.h header
+ The following names for option bits are defined in the pcre2.h header
file:
PCRE2_ANCHORED
If this bit is set, the pattern is forced to be "anchored", that is, it
- is constrained to match only at the first matching point in the string
- that is being searched (the "subject string"). This effect can also be
- achieved by appropriate constructs in the pattern itself, which is the
+ is constrained to match only at the first matching point in the string
+ that is being searched (the "subject string"). This effect can also be
+ achieved by appropriate constructs in the pattern itself, which is the
only way to do it in Perl.
PCRE2_ALLOW_EMPTY_CLASS
- By default, for compatibility with Perl, a closing square bracket that
- immediately follows an opening one is treated as a data character for
- the class. When PCRE2_ALLOW_EMPTY_CLASS is set, it terminates the
+ By default, for compatibility with Perl, a closing square bracket that
+ immediately follows an opening one is treated as a data character for
+ the class. When PCRE2_ALLOW_EMPTY_CLASS is set, it terminates the
class, which therefore contains no characters and so can never match.
PCRE2_ALT_BSUX
- This option request alternative handling of three escape sequences,
- which makes PCRE2's behaviour more like ECMAscript (aka JavaScript).
+ This option request alternative handling of three escape sequences,
+ which makes PCRE2's behaviour more like ECMAscript (aka JavaScript).
When it is set:
(1) \U matches an upper case "U" character; by default \U causes a com-
@@ -1232,13 +1235,13 @@
pile time error (Perl uses \U to upper case subsequent characters).
(2) \u matches a lower case "u" character unless it is followed by four
- hexadecimal digits, in which case the hexadecimal number defines the
- code point to match. By default, \u causes a compile time error (Perl
+ hexadecimal digits, in which case the hexadecimal number defines the
+ code point to match. By default, \u causes a compile time error (Perl
uses it to upper case the following character).
- (3) \x matches a lower case "x" character unless it is followed by two
- hexadecimal digits, in which case the hexadecimal number defines the
- code point to match. By default, as in Perl, a hexadecimal number is
+ (3) \x matches a lower case "x" character unless it is followed by two
+ hexadecimal digits, in which case the hexadecimal number defines the
+ code point to match. By default, as in Perl, a hexadecimal number is
always expected after \x, but it may have zero, one, or two digits (so,
for example, \xz matches a binary zero character followed by z).
@@ -1245,54 +1248,54 @@
PCRE2_ALT_CIRCUMFLEX
In multiline mode (when PCRE2_MULTILINE is set), the circumflex
- metacharacter matches at the start of the subject (unless PCRE2_NOTBOL
- is set), and also after any internal newline. However, it does not
+ metacharacter matches at the start of the subject (unless PCRE2_NOTBOL
+ is set), and also after any internal newline. However, it does not
match after a newline at the end of the subject, for compatibility with
- Perl. If you want a multiline circumflex also to match after a termi-
+ Perl. If you want a multiline circumflex also to match after a termi-
nating newline, you must set PCRE2_ALT_CIRCUMFLEX.
PCRE2_ALT_VERBNAMES
- By default, for compatibility with Perl, the name in any verb sequence
- such as (*MARK:NAME) is any sequence of characters that does not
- include a closing parenthesis. The name is not processed in any way,
- and it is not possible to include a closing parenthesis in the name.
- However, if the PCRE2_ALT_VERBNAMES option is set, normal backslash
- processing is applied to verb names and only an unescaped closing
- parenthesis terminates the name. A closing parenthesis can be included
- in a name either as \) or between \Q and \E. If the PCRE2_EXTENDED
+ By default, for compatibility with Perl, the name in any verb sequence
+ such as (*MARK:NAME) is any sequence of characters that does not
+ include a closing parenthesis. The name is not processed in any way,
+ and it is not possible to include a closing parenthesis in the name.
+ However, if the PCRE2_ALT_VERBNAMES option is set, normal backslash
+ processing is applied to verb names and only an unescaped closing
+ parenthesis terminates the name. A closing parenthesis can be included
+ in a name either as \) or between \Q and \E. If the PCRE2_EXTENDED
option is set, unescaped whitespace in verb names is skipped and #-com-
ments are recognized, exactly as in the rest of the pattern.
PCRE2_AUTO_CALLOUT
- If this bit is set, pcre2_compile() automatically inserts callout
- items, all with number 255, before each pattern item, except immedi-
- ately before or after a callout in the pattern. For discussion of the
+ If this bit is set, pcre2_compile() automatically inserts callout
+ items, all with number 255, before each pattern item, except immedi-
+ ately before or after a callout in the pattern. For discussion of the
callout facility, see the pcre2callout documentation.
PCRE2_CASELESS
- If this bit is set, letters in the pattern match both upper and lower
- case letters in the subject. It is equivalent to Perl's /i option, and
+ If this bit is set, letters in the pattern match both upper and lower
+ case letters in the subject. It is equivalent to Perl's /i option, and
it can be changed within a pattern by a (?i) option setting.
PCRE2_DOLLAR_ENDONLY
- If this bit is set, a dollar metacharacter in the pattern matches only
- at the end of the subject string. Without this option, a dollar also
- matches immediately before a newline at the end of the string (but not
- before any other newlines). The PCRE2_DOLLAR_ENDONLY option is ignored
- if PCRE2_MULTILINE is set. There is no equivalent to this option in
+ If this bit is set, a dollar metacharacter in the pattern matches only
+ at the end of the subject string. Without this option, a dollar also
+ matches immediately before a newline at the end of the string (but not
+ before any other newlines). The PCRE2_DOLLAR_ENDONLY option is ignored
+ if PCRE2_MULTILINE is set. There is no equivalent to this option in
Perl, and no way to set it within a pattern.
PCRE2_DOTALL
- If this bit is set, a dot metacharacter in the pattern matches any
- character, including one that indicates a newline. However, it only
+ If this bit is set, a dot metacharacter in the pattern matches any
+ character, including one that indicates a newline. However, it only
ever matches one character, even if newlines are coded as CRLF. Without
this option, a dot does not match when the current position in the sub-
- ject is at a newline. This option is equivalent to Perl's /s option,
+ ject is at a newline. This option is equivalent to Perl's /s option,
and it can be changed within a pattern by a (?s) option setting. A neg-
ative class such as [^a] always matches newline characters, independent
of the setting of this option.
@@ -1299,181 +1302,181 @@
PCRE2_DUPNAMES
- If this bit is set, names used to identify capturing subpatterns need
+ If this bit is set, names used to identify capturing subpatterns need
not be unique. This can be helpful for certain types of pattern when it
- is known that only one instance of the named subpattern can ever be
- matched. There are more details of named subpatterns below; see also
+ is known that only one instance of the named subpattern can ever be
+ matched. There are more details of named subpatterns below; see also
the pcre2pattern documentation.
PCRE2_EXTENDED
- If this bit is set, most white space characters in the pattern are
- totally ignored except when escaped or inside a character class. How-
- ever, white space is not allowed within sequences such as (?> that
+ If this bit is set, most white space characters in the pattern are
+ totally ignored except when escaped or inside a character class. How-
+ ever, white space is not allowed within sequences such as (?> that
introduce various parenthesized subpatterns, nor within numerical quan-
- tifiers such as {1,3}. Ignorable white space is permitted between an
- item and a following quantifier and between a quantifier and a follow-
+ tifiers such as {1,3}. Ignorable white space is permitted between an
+ item and a following quantifier and between a quantifier and a follow-
ing + that indicates possessiveness.
- PCRE2_EXTENDED also causes characters between an unescaped # outside a
- character class and the next newline, inclusive, to be ignored, which
+ PCRE2_EXTENDED also causes characters between an unescaped # outside a
+ character class and the next newline, inclusive, to be ignored, which
makes it possible to include comments inside complicated patterns. Note
- that the end of this type of comment is a literal newline sequence in
+ that the end of this type of comment is a literal newline sequence in
the pattern; escape sequences that happen to represent a newline do not
- count. PCRE2_EXTENDED is equivalent to Perl's /x option, and it can be
+ count. PCRE2_EXTENDED is equivalent to Perl's /x option, and it can be
changed within a pattern by a (?x) option setting.
Which characters are interpreted as newlines can be specified by a set-
- ting in the compile context that is passed to pcre2_compile() or by a
- special sequence at the start of the pattern, as described in the sec-
- tion entitled "Newline conventions" in the pcre2pattern documentation.
+ ting in the compile context that is passed to pcre2_compile() or by a
+ special sequence at the start of the pattern, as described in the sec-
+ tion entitled "Newline conventions" in the pcre2pattern documentation.
A default is defined when PCRE2 is built.
PCRE2_FIRSTLINE
- If this option is set, an unanchored pattern is required to match
- before or at the first newline in the subject string, though the
- matched text may continue over the newline. See also PCRE2_USE_OFF-
- SET_LIMIT, which provides a more general limiting facility. If
- PCRE2_FIRSTLINE is set with an offset limit, a match must occur in the
- first line and also within the offset limit. In other words, whichever
+ If this option is set, an unanchored pattern is required to match
+ before or at the first newline in the subject string, though the
+ matched text may continue over the newline. See also PCRE2_USE_OFF-
+ SET_LIMIT, which provides a more general limiting facility. If
+ PCRE2_FIRSTLINE is set with an offset limit, a match must occur in the
+ first line and also within the offset limit. In other words, whichever
limit comes first is used.
PCRE2_MATCH_UNSET_BACKREF
- If this option is set, a back reference to an unset subpattern group
- matches an empty string (by default this causes the current matching
- alternative to fail). A pattern such as (\1)(a) succeeds when this
- option is set (assuming it can find an "a" in the subject), whereas it
- fails by default, for Perl compatibility. Setting this option makes
+ If this option is set, a back reference to an unset subpattern group
+ matches an empty string (by default this causes the current matching
+ alternative to fail). A pattern such as (\1)(a) succeeds when this
+ option is set (assuming it can find an "a" in the subject), whereas it
+ fails by default, for Perl compatibility. Setting this option makes
PCRE2 behave more like ECMAscript (aka JavaScript).
PCRE2_MULTILINE
- By default, for the purposes of matching "start of line" and "end of
- line", PCRE2 treats the subject string as consisting of a single line
- of characters, even if it actually contains newlines. The "start of
- line" metacharacter (^) matches only at the start of the string, and
- the "end of line" metacharacter ($) matches only at the end of the
+ By default, for the purposes of matching "start of line" and "end of
+ line", PCRE2 treats the subject string as consisting of a single line
+ of characters, even if it actually contains newlines. The "start of
+ line" metacharacter (^) matches only at the start of the string, and
+ the "end of line" metacharacter ($) matches only at the end of the
string, or before a terminating newline (except when PCRE2_DOL-
- LAR_ENDONLY is set). Note, however, that unless PCRE2_DOTALL is set,
+ LAR_ENDONLY is set). Note, however, that unless PCRE2_DOTALL is set,
the "any character" metacharacter (.) does not match at a newline. This
behaviour (for ^, $, and dot) is the same as Perl.
- When PCRE2_MULTILINE it is set, the "start of line" and "end of line"
- constructs match immediately following or immediately before internal
- newlines in the subject string, respectively, as well as at the very
- start and end. This is equivalent to Perl's /m option, and it can be
+ When PCRE2_MULTILINE it is set, the "start of line" and "end of line"
+ constructs match immediately following or immediately before internal
+ newlines in the subject string, respectively, as well as at the very
+ start and end. This is equivalent to Perl's /m option, and it can be
changed within a pattern by a (?m) option setting. Note that the "start
of line" metacharacter does not match after a newline at the end of the
- subject, for compatibility with Perl. However, you can change this by
- setting the PCRE2_ALT_CIRCUMFLEX option. If there are no newlines in a
- subject string, or no occurrences of ^ or $ in a pattern, setting
+ subject, for compatibility with Perl. However, you can change this by
+ setting the PCRE2_ALT_CIRCUMFLEX option. If there are no newlines in a
+ subject string, or no occurrences of ^ or $ in a pattern, setting
PCRE2_MULTILINE has no effect.
PCRE2_NEVER_BACKSLASH_C
- This option locks out the use of \C in the pattern that is being com-
- piled. This escape can cause unpredictable behaviour in UTF-8 or
- UTF-16 modes, because it may leave the current matching point in the
- middle of a multi-code-unit character. This option may be useful in
- applications that process patterns from external sources. Note that
+ This option locks out the use of \C in the pattern that is being com-
+ piled. This escape can cause unpredictable behaviour in UTF-8 or
+ UTF-16 modes, because it may leave the current matching point in the
+ middle of a multi-code-unit character. This option may be useful in
+ applications that process patterns from external sources. Note that
there is also a build-time option that permanently locks out the use of
\C.
PCRE2_NEVER_UCP
- This option locks out the use of Unicode properties for handling \B,
+ This option locks out the use of Unicode properties for handling \B,
\b, \D, \d, \S, \s, \W, \w, and some of the POSIX character classes, as
- described for the PCRE2_UCP option below. In particular, it prevents
- the creator of the pattern from enabling this facility by starting the
- pattern with (*UCP). This option may be useful in applications that
+ described for the PCRE2_UCP option below. In particular, it prevents
+ the creator of the pattern from enabling this facility by starting the
+ pattern with (*UCP). This option may be useful in applications that
process patterns from external sources. The option combination PCRE_UCP
and PCRE_NEVER_UCP causes an error.
PCRE2_NEVER_UTF
- This option locks out interpretation of the pattern as UTF-8, UTF-16,
+ This option locks out interpretation of the pattern as UTF-8, UTF-16,
or UTF-32, depending on which library is in use. In particular, it pre-
- vents the creator of the pattern from switching to UTF interpretation
- by starting the pattern with (*UTF). This option may be useful in
- applications that process patterns from external sources. The combina-
+ vents the creator of the pattern from switching to UTF interpretation
+ by starting the pattern with (*UTF). This option may be useful in
+ applications that process patterns from external sources. The combina-
tion of PCRE2_UTF and PCRE2_NEVER_UTF causes an error.
PCRE2_NO_AUTO_CAPTURE
If this option is set, it disables the use of numbered capturing paren-
- 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. 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
+ 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. 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
@@ -1480,75 +1483,75 @@
(*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
- (via errorcode) 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
+ There are over 80 positive error codes that pcre2_compile() may return
+ (via errorcode) 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 pcre2unicode page. The pcre2_get_error_message() func-
- tion (see "Obtaining a textual error message" below) can be called to
+ tion (see "Obtaining a textual error message" below) can be called to
obtain a textual error message from any error code.
@@ -1571,53 +1574,53 @@
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");
@@ -1626,15 +1629,15 @@
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.
@@ -1642,13 +1645,13 @@
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:
@@ -1658,9 +1661,9 @@
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;
@@ -1677,19 +1680,19 @@
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 (*XXX)
+ 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 (*XXX)
option settings such as (*UTF) at the start of the pattern itself.
- For example, if the pattern /(*UTF)abc/ is compiled with the
- PCRE2_EXTENDED option, the result for PCRE2_INFO_ALLOPTIONS is
- PCRE2_EXTENDED and PCRE2_UTF. Option settings such as (?i) that can
- change within a pattern do not affect the result of PCRE2_INFO_ALLOP-
+ For example, if the pattern /(*UTF)abc/ is compiled with the
+ PCRE2_EXTENDED option, the result for PCRE2_INFO_ALLOPTIONS is
+ PCRE2_EXTENDED and PCRE2_UTF. Option settings such as (?i) that can
+ change within a pattern do not affect the result of PCRE2_INFO_ALLOP-
TIONS, even if they appear right at the start of the pattern. (This was
different in some earlier releases.)
- 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:
@@ -1698,7 +1701,7 @@
\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
@@ -1708,18 +1711,18 @@
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
@@ -1726,128 +1729,128 @@
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
@@ -1855,50 +1858,50 @@
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):
(?<date> (?<year>(\d\d)?\d\d) -
(?<month>\d\d) - (?<day>\d\d) )
- There are four named subpatterns, so the table has four entries, and
- each entry in the table is eight bytes long. The table is as follows,
+ 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 ??:
@@ -1907,8 +1910,8 @@
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
@@ -1921,27 +1924,27 @@
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.
@@ -1952,22 +1955,22 @@
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.
@@ -1982,56 +1985,56 @@
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 known 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().
@@ -2042,15 +2045,15 @@
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():
@@ -2065,7 +2068,7 @@
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.
@@ -2072,84 +2075,84 @@
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,
- PCRE2_NOTEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART, PCRE2_NO_JIT,
- PCRE2_NO_UTF_CHECK, PCRE2_PARTIAL_HARD, and PCRE2_PARTIAL_SOFT. Their
+ The only bits that may be set are PCRE2_ANCHORED, PCRE2_NOTBOL,
+ PCRE2_NOTEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART, PCRE2_NO_JIT,
+ 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
- normal interpretive code in pcre2_match() is run. Apart from
- PCRE2_NO_JIT (obviously), the remaining options are supported for JIT
+ 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. Apart from
+ PCRE2_NO_JIT (obviously), 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.
@@ -2156,9 +2159,9 @@
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.
@@ -2165,79 +2168,79 @@
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_JIT
- By default, if a pattern has been successfully processed by
- pcre2_jit_compile(), JIT is automatically used when pcre2_match() is
- called with options that JIT supports. Setting PCRE2_NO_JIT disables
+ By default, if a pattern has been successfully processed by
+ pcre2_jit_compile(), JIT is automatically used when pcre2_match() is
+ called with options that JIT supports. Setting PCRE2_NO_JIT disables
the use of JIT; it forces matching to be done by the interpreter.
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.
@@ -2247,37 +2250,37 @@
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.
@@ -2288,85 +2291,85 @@
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.
@@ -2376,42 +2379,42 @@
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.
@@ -2418,14 +2421,14 @@
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 the pcre2_get_error_message() func-
- tion (see "Obtaining a textual error message" below). 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 checking is
+ If pcre2_match() fails, it returns a negative number. This can be con-
+ verted to a text string by calling the pcre2_get_error_message() func-
+ tion (see "Obtaining a textual error message" below). 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 checking 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 given in
- the pcre2unicode page. The following are the other errors that may be
+ 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():
PCRE2_ERROR_NOMATCH
@@ -2434,19 +2437,19 @@
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
@@ -2460,35 +2463,35 @@
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
@@ -2497,10 +2500,10 @@
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
@@ -2509,12 +2512,12 @@
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
@@ -2527,19 +2530,19 @@
int pcre2_get_error_message(int errorcode, PCRE2_UCHAR *buffer,
PCRE2_SIZE bufflen);
- A text message for an error code from any PCRE2 function (compile,
- match, or auxiliary) can be obtained by calling pcre2_get_error_mes-
- sage(). The code is passed as the first argument, with the remaining
- two arguments specifying a code unit buffer and its length, into which
- the text message is placed. Note that the message is returned in code
+ A text message for an error code from any PCRE2 function (compile,
+ match, or auxiliary) can be obtained by calling pcre2_get_error_mes-
+ sage(). The code is passed as the first argument, with the remaining
+ two arguments specifying a code unit buffer and its length, into which
+ the text message is placed. Note that the message is returned in code
units of the appropriate width for the library that is being used.
- The returned message is terminated with a trailing zero, and the func-
- tion returns the number of code units used, excluding the trailing
+ The returned message is terminated with a trailing zero, and the func-
+ tion returns the number of code units used, excluding the trailing
zero. If the error number is unknown, the negative error code
- PCRE2_ERROR_BADDATA is returned. If the buffer is too small, the mes-
- sage is truncated (but still with a trailing zero), and the negative
- error code PCRE2_ERROR_NOMEMORY is returned. None of the messages are
+ PCRE2_ERROR_BADDATA is returned. If the buffer is too small, the mes-
+ sage is truncated (but still with a trailing zero), and the negative
+ error code PCRE2_ERROR_NOMEMORY is returned. None of the messages are
very long; a buffer size of 120 code units is ample.
@@ -2558,39 +2561,39 @@
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
@@ -2599,25 +2602,25 @@
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
@@ -2628,8 +2631,8 @@
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.
@@ -2640,32 +2643,32 @@
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().
@@ -2685,39 +2688,39 @@
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(?<xxx>\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.
@@ -2730,41 +2733,41 @@
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
@@ -2771,11 +2774,11 @@
$<n> or ${<n>} insert the contents of group <n>
$*MARK or ${*MARK} insert the name of the last (*MARK) encountered
- Either a group number or a group name can be given for <n>. Curly
- brackets are required only if the following character would be inter-
+ Either a group number or a group name can be given for <n>. 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
@@ -2785,92 +2788,92 @@
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:
${<n>:-<string>}
${<n>:+<string1>:<string2>}
- As before, <n> may be a group number or a name. The first form speci-
- fies a default value. If group <n> is set, its value is inserted; if
- not, <string> is expanded and the result inserted. The second form
- specifies strings that are expanded and inserted when group <n> is set
- or unset, respectively. The first form is just a convenient shorthand
+ As before, <n> may be a group number or a name. The first form speci-
+ fies a default value. If group <n> is set, its value is inserted; if
+ not, <string> is expanded and the result inserted. The second form
+ specifies strings that are expanded and inserted when group <n> is set
+ or unset, respectively. The first form is just a convenient shorthand
for
${<n>:+${<n>}:<string>}
- 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
@@ -2879,16 +2882,16 @@
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-
@@ -2895,25 +2898,25 @@
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
- obtained by calling the pcre2_get_error_message() function (see
+ obtained by calling the pcre2_get_error_message() function (see
"Obtaining a textual error message" above).
@@ -2922,56 +2925,56 @@
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.
@@ -2983,26 +2986,26 @@
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():
@@ -3022,45 +3025,45 @@
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.
@@ -3068,8 +3071,8 @@
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
<.*>
@@ -3084,17 +3087,17 @@
<something> <something else>
<something>
- 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
@@ -3104,64 +3107,64 @@
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).
@@ -3175,11 +3178,11 @@
REVISION
- Last updated: 22 November 2016
+ Last updated: 23 December 2016
Copyright (c) 1997-2016 University of Cambridge.
------------------------------------------------------------------------------
-
-
+
+
PCRE2BUILD(3) Library Functions Manual PCRE2BUILD(3)
@@ -3699,8 +3702,8 @@
Last updated: 01 November 2016
Copyright (c) 1997-2016 University of Cambridge.
------------------------------------------------------------------------------
-
-
+
+
PCRE2CALLOUT(3) Library Functions Manual PCRE2CALLOUT(3)
@@ -4079,8 +4082,8 @@
Last updated: 29 September 2016
Copyright (c) 1997-2016 University of Cambridge.
------------------------------------------------------------------------------
-
-
+
+
PCRE2COMPAT(3) Library Functions Manual PCRE2COMPAT(3)
@@ -4269,8 +4272,8 @@
Last updated: 18 October 2016
Copyright (c) 1997-2016 University of Cambridge.
------------------------------------------------------------------------------
-
-
+
+
PCRE2JIT(3) Library Functions Manual PCRE2JIT(3)
@@ -4666,8 +4669,8 @@
Last updated: 05 June 2016
Copyright (c) 1997-2016 University of Cambridge.
------------------------------------------------------------------------------
-
-
+
+
PCRE2LIMITS(3) Library Functions Manual PCRE2LIMITS(3)
@@ -4743,8 +4746,8 @@
Last updated: 26 October 2016
Copyright (c) 1997-2016 University of Cambridge.
------------------------------------------------------------------------------
-
-
+
+
PCRE2MATCHING(3) Library Functions Manual PCRE2MATCHING(3)
@@ -4962,8 +4965,8 @@
Last updated: 29 September 2014
Copyright (c) 1997-2014 University of Cambridge.
------------------------------------------------------------------------------
-
-
+
+
PCRE2PARTIAL(3) Library Functions Manual PCRE2PARTIAL(3)
@@ -5402,8 +5405,8 @@
Last updated: 22 December 2014
Copyright (c) 1997-2014 University of Cambridge.
------------------------------------------------------------------------------
-
-
+
+
PCRE2PATTERN(3) Library Functions Manual PCRE2PATTERN(3)
@@ -5537,6 +5540,12 @@
If there is more than one setting of one of these limits, the lower
value is used.
+ The match limit is used (but in a different way) when JIT is being
+ used, but it is not relevant, and is ignored, when matching with
+ pcre2_dfa_match(). However, the recursion limit is relevant for DFA
+ matching, which does use some function recursion, in particular, for
+ recursions within the pattern.
+
Newline conventions
PCRE2 supports five different conventions for indicating line breaks in
@@ -6497,10 +6506,10 @@
example, [b-d-z] matches letters in the range b to d, a hyphen charac-
ter, or z.
- Perl treats a hyphen as a literal if it appears before a POSIX class
- (see below) or a character type escape such as as \d, but gives a warn-
- ing in its warning mode, as this is most likely a user error. As PCRE2
- has no facility for warning, an error is given in these cases.
+ Perl treats a hyphen as a literal if it appears before or after a POSIX
+ class (see below) or a character type escape such as as \d, but gives a
+ warning in its warning mode, as this is most likely a user error. As
+ PCRE2 has no facility for warning, an error is given in these cases.
It is not possible to have the literal character "]" as the end charac-
ter of a range. A pattern such as [W-]46] is interpreted as a class of
@@ -8487,11 +8496,11 @@
REVISION
- Last updated: 23 October 2016
+ Last updated: 27 December 2016
Copyright (c) 1997-2016 University of Cambridge.
------------------------------------------------------------------------------
-
-
+
+
PCRE2PERFORM(3) Library Functions Manual PCRE2PERFORM(3)
@@ -8663,8 +8672,8 @@
Last updated: 02 January 2015
Copyright (c) 1997-2015 University of Cambridge.
------------------------------------------------------------------------------
-
-
+
+
PCRE2POSIX(3) Library Functions Manual PCRE2POSIX(3)
@@ -8939,8 +8948,8 @@
Last updated: 31 January 2016
Copyright (c) 1997-2016 University of Cambridge.
------------------------------------------------------------------------------
-
-
+
+
PCRE2SAMPLE(3) Library Functions Manual PCRE2SAMPLE(3)
@@ -9205,8 +9214,8 @@
Last updated: 24 May 2016
Copyright (c) 1997-2016 University of Cambridge.
------------------------------------------------------------------------------
-
-
+
+
PCRE2STACK(3) Library Functions Manual PCRE2STACK(3)
@@ -9255,80 +9264,88 @@
limit on the complexity of pcre2_dfa_match() is controlled by the
amount of workspace it is given. However, it is possible to write pat-
terns with runaway infinite recursions; such patterns will cause
- pcre2_dfa_match() to run out of stack. At present, there is no protec-
- tion against this.
+ pcre2_dfa_match() to run out of stack unless a limit is applied (see
+ below).
- The comments that follow do NOT apply to pcre2_dfa_match(); they are
- relevant only for pcre2_match() without the JIT optimization.
+ The comments in the next three sections do not apply to
+ pcre2_dfa_match(); they are relevant only for pcre2_match() without the
+ JIT optimization.
Reducing pcre2_match()'s stack usage
- You can often reduce the amount of recursion, and therefore the amount
- of stack used, by modifying the pattern that is being matched. Con-
+ You can often reduce the amount of recursion, and therefore the amount
+ of stack used, by modifying the pattern that is being matched. Con-
sider, for example, this pattern:
([^<]|<(?!inet))+
- It matches from wherever it starts until it encounters "<inet" or the
- end of the data, and is the kind of pattern that might be used when
+ It matches from wherever it starts until it encounters "<inet" or the
+ end of the data, and is the kind of pattern that might be used when
processing an XML file. Each iteration of the outer parentheses matches
- either one character that is not "<" or a "<" that is not followed by
- "inet". However, each time a parenthesis is processed, a recursion
+ either one character that is not "<" or a "<" that is not followed by
+ "inet". However, each time a parenthesis is processed, a recursion
occurs, so this formulation uses a stack frame for each matched charac-
- ter. For a long string, a lot of stack is required. Consider now this
+ ter. For a long string, a lot of stack is required. Consider now this
rewritten pattern, which matches exactly the same strings:
([^<]++|<(?!inet))+
- This uses very much less stack, because runs of characters that do not
- contain "<" are "swallowed" in one item inside the parentheses. Recur-
- sion happens only when a "<" character that is not followed by "inet"
- is encountered (and we assume this is relatively rare). A possessive
- quantifier is used to stop any backtracking into the runs of non-"<"
+ This uses very much less stack, because runs of characters that do not
+ contain "<" are "swallowed" in one item inside the parentheses. Recur-
+ sion happens only when a "<" character that is not followed by "inet"
+ is encountered (and we assume this is relatively rare). A possessive
+ quantifier is used to stop any backtracking into the runs of non-"<"
characters, but that is not related to stack usage.
- This example shows that one way of avoiding stack problems when match-
+ This example shows that one way of avoiding stack problems when match-
ing long subject strings is to write repeated parenthesized subpatterns
to match more than one character whenever possible.
Compiling PCRE2 to use heap instead of stack for pcre2_match()
- In environments where stack memory is constrained, you might want to
+ In environments where stack memory is constrained, you might want to
compile PCRE2 to use heap memory instead of stack for remembering back-
up points when pcre2_match() is running. This makes it run more slowly,
however. Details of how to do this are given in the pcre2build documen-
- tation. When built in this way, instead of using the stack, PCRE2 gets
- memory for remembering backup points from the heap. By default, the
+ tation. When built in this way, instead of using the stack, PCRE2 gets
+ memory for remembering backup points from the heap. By default, the
memory is obtained by calling the system malloc() function, but you can
arrange to supply your own memory management function. For details, see
the section entitled "The match context" in the pcre2api documentation.
Since the block sizes are always the same, it may be possible to imple-
- ment customized a memory handler that is more efficient than the stan-
+ ment a customized memory handler that is more efficient than the stan-
dard function. The memory blocks obtained for this purpose are retained
- and re-used if possible while pcre2_match() is running. They are all
+ and re-used if possible while pcre2_match() is running. They are all
freed just before it exits.
Limiting pcre2_match()'s stack usage
You can set limits on the number of times the internal match() function
- is called, both in total and recursively. If a limit is exceeded,
- pcre2_match() returns an error code. Setting suitable limits should
- prevent it from running out of stack. The default values of the limits
- are very large, and unlikely ever to operate. They can be changed when
- PCRE2 is built, and they can also be set when pcre2_match() is called.
- For details of these interfaces, see the pcre2build documentation and
+ is called, both in total and recursively. If a limit is exceeded,
+ pcre2_match() returns an error code. Setting suitable limits should
+ prevent it from running out of stack. The default values of the limits
+ are very large, and unlikely ever to operate. They can be changed when
+ PCRE2 is built, and they can also be set when pcre2_match() is called.
+ For details of these interfaces, see the pcre2build documentation and
the section entitled "The match context" in the pcre2api documentation.
As a very rough rule of thumb, you should reckon on about 500 bytes per
- recursion. Thus, if you want to limit your stack usage to 8Mb, you
- should set the limit at 16000 recursions. A 64Mb stack, on the other
+ recursion. Thus, if you want to limit your stack usage to 8Mb, you
+ should set the limit at 16000 recursions. A 64Mb stack, on the other
hand, can support around 128000 recursions.
- The pcre2test test program has a modifier called "find_limits" which,
- if applied to a subject line, causes it to find the smallest limits
- that allow a a pattern to match. This is done by calling pcre2_match()
+ The pcre2test test program has a modifier called "find_limits" which,
+ if applied to a subject line, causes it to find the smallest limits
+ that allow a a pattern to match. This is done by calling pcre2_match()
repeatedly with different limits.
+ Limiting pcre2_dfa_match()'s stack usage
+
+ The recursion limit, as described above for pcre2_match(), also applies
+ to pcre2_dfa_match(), whose use of recursive function calls for recur-
+ sions in the pattern can lead to runaway stack usage. The non-recursive
+ match limit is not relevant for DFA matching, and is ignored.
+
Changing stack size in Unix-like systems
In Unix-like environments, there is not often a problem with the stack
@@ -9368,11 +9385,11 @@
REVISION
- Last updated: 21 November 2014
- Copyright (c) 1997-2014 University of Cambridge.
+ Last updated: 23 December 2016
+ Copyright (c) 1997-2016 University of Cambridge.
------------------------------------------------------------------------------
-
-
+
+
PCRE2SYNTAX(3) Library Functions Manual PCRE2SYNTAX(3)
@@ -9667,10 +9684,10 @@
(*UCP) set PCRE2_UCP (use Unicode properties for \d etc)
Note that LIMIT_MATCH and LIMIT_RECURSION can only reduce the value of
- the limits set by the caller of pcre2_match(), not increase them. The
- application can lock out the use of (*UTF) and (*UCP) by setting the
- PCRE2_NEVER_UTF or PCRE2_NEVER_UCP options, respectively, at compile
- time.
+ the limits set by the caller of pcre2_match() or pcre2_dfa_match(), not
+ increase them. The application can lock out the use of (*UTF) and
+ (*UCP) by setting the PCRE2_NEVER_UTF or PCRE2_NEVER_UCP options,
+ respectively, at compile time.
NEWLINE CONVENTION
@@ -9811,11 +9828,11 @@
REVISION
- Last updated: 28 September 2016
+ Last updated: 23 December 2016
Copyright (c) 1997-2016 University of Cambridge.
------------------------------------------------------------------------------
-
-
+
+
PCRE2UNICODE(3) Library Functions Manual PCRE2UNICODE(3)
@@ -10057,5 +10074,5 @@
Last updated: 03 July 2016
Copyright (c) 1997-2016 University of Cambridge.
------------------------------------------------------------------------------
-
-
+
+
Modified: code/trunk/doc/pcre2_code_copy_with_tables.3
===================================================================
--- code/trunk/doc/pcre2_code_copy_with_tables.3 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/doc/pcre2_code_copy_with_tables.3 2017-01-16 17:40:47 UTC (rev 655)
@@ -15,7 +15,7 @@
.sp
This function makes a copy of the memory used for a compiled pattern, excluding
any memory used by the JIT compiler. Without a subsequent call to
-\fBpcre2_jit_compile()\fP, the copy can be used only for non-JIT matching.
+\fBpcre2_jit_compile()\fP, the copy can be used only for non-JIT matching.
Unlike \fBpcre2_code_copy()\fP, a separate copy of the character tables is also
made, with the new code pointing to it. This memory will be automatically freed
when \fBpcre2_code_free()\fP is called. The yield of the function is NULL if
Modified: code/trunk/doc/pcre2api.3
===================================================================
--- code/trunk/doc/pcre2api.3 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/doc/pcre2api.3 2017-01-16 17:40:47 UTC (rev 655)
@@ -511,7 +511,7 @@
(perhaps waiting to see if the pattern is used often enough) similar logic is
required. JIT compilation updates a pointer within the compiled code block, so
a thread must gain unique write access to the pointer before calling
-\fBpcre2_jit_compile()\fP. Alternatively, \fBpcre2_code_copy()\fP or
+\fBpcre2_jit_compile()\fP. Alternatively, \fBpcre2_code_copy()\fP or
\fBpcre2_code_copy_with_tables()\fP can be used to obtain a private copy of the
compiled code.
.
@@ -696,7 +696,7 @@
.sp
This parameter ajusts the limit, set when PCRE2 is built (default 250), on the
depth of parenthesis nesting in a pattern. This limit stops rogue patterns
-using up too much system stack when being compiled. The limit applies to
+using up too much system stack when being compiled. The limit applies to
parentheses of all kinds, not just capturing parentheses.
.sp
.nf
@@ -840,9 +840,9 @@
Limiting the recursion depth limits the amount of system stack that can be
used, or, when PCRE2 has been compiled to use memory on the heap instead of the
stack, the amount of heap memory that can be used. This limit is not relevant,
-and is ignored, when matching is done using JIT compiled code. However, it is
+and is ignored, when matching is done using JIT compiled code. However, it is
supported by \fBpcre2_dfa_match()\fP, which uses recursive function calls less
-frequently than \fBpcre2_match()\fP, but which can be caused to use a lot of
+frequently than \fBpcre2_match()\fP, but which can be caused to use a lot of
stack by a recursive pattern such as /(.)(?1)/ matched to a very long string.
.P
The default value for \fIrecursion_limit\fP can be set when PCRE2 is built; the
@@ -1056,11 +1056,11 @@
.\"
the JIT information cannot be copied (because it is position-dependent).
The new copy can initially be used only for non-JIT matching, though it can be
-passed to \fBpcre2_jit_compile()\fP if required.
+passed to \fBpcre2_jit_compile()\fP if required.
.P
The \fBpcre2_code_copy()\fP function provides a way for individual threads in a
-multithreaded application to acquire a private copy of shared compiled code.
-However, it does not make a copy of the character tables used by the compiled
+multithreaded application to acquire a private copy of shared compiled code.
+However, it does not make a copy of the character tables used by the compiled
pattern; the new pattern code points to the same tables as the original code.
(See
.\" HTML <a href="#jitcompiling">
@@ -1068,10 +1068,10 @@
"Locale Support"
.\"
below for details of these character tables.) In many applications the same
-tables are used throughout, so this behaviour is appropriate. Nevertheless,
-there are occasions when a copy of a compiled pattern and the relevant tables
-are needed. The \fBpcre2_code_copy_with_tables()\fP provides this facility.
-Copies of both the code and the tables are made, with the new code pointing to
+tables are used throughout, so this behaviour is appropriate. Nevertheless,
+there are occasions when a copy of a compiled pattern and the relevant tables
+are needed. The \fBpcre2_code_copy_with_tables()\fP provides this facility.
+Copies of both the code and the tables are made, with the new code pointing to
the new tables. The memory for the new tables is automatically freed when
\fBpcre2_code_free()\fP is called for the new copy of the compiled code.
.P
@@ -1114,7 +1114,7 @@
error code and an offset (number of code units) within the pattern,
respectively, when \fBpcre2_compile()\fP returns NULL because a compilation
error has occurred. The values are not defined when compilation is successful
-and \fBpcre2_compile()\fP returns a non-NULL value.
+and \fBpcre2_compile()\fP returns a non-NULL value.
.P
The value returned in \fIerroroffset\fP is an indication of where in the
pattern the error occurred. It is not necessarily the furthest point in the
Modified: code/trunk/doc/pcre2build.3
===================================================================
--- code/trunk/doc/pcre2build.3 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/doc/pcre2build.3 2017-01-16 17:40:47 UTC (rev 655)
@@ -388,15 +388,15 @@
finds a match. The starting size of the buffer is controlled by a parameter
whose default value is 20K. The buffer itself is three times this size, but
because of the way it is used for holding "before" lines, the longest line that
-is guaranteed to be processable is the parameter size. If a longer line is
+is guaranteed to be processable is the parameter size. If a longer line is
encountered, \fBpcre2grep\fP automatically expands the buffer, up to a
specified maximum size, whose default is 1M or the starting size, whichever is
the larger. You can change the default parameter values by adding, for example,
.sp
--with-pcre2grep-bufsize=51200
- --with-pcre2grep-max-bufsize=2097152
+ --with-pcre2grep-max-bufsize=2097152
.sp
-to the \fBconfigure\fP command. The caller of \fPpcre2grep\fP can override
+to the \fBconfigure\fP command. The caller of \fPpcre2grep\fP can override
these values by using --buffer-size and --max-buffer-size on the command line.
.
.
@@ -522,7 +522,7 @@
PCRE2:
.sp
--enable-fuzz-support
-.sp
+.sp
At present this applies only to the 8-bit library. If set, it causes an extra
library called libpcre2-fuzzsupport.a to be built, but not installed. This
contains a single function called LLVMFuzzerTestOneInput() whose arguments are
Modified: code/trunk/doc/pcre2callout.3
===================================================================
--- code/trunk/doc/pcre2callout.3 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/doc/pcre2callout.3 2017-01-16 17:40:47 UTC (rev 655)
@@ -47,7 +47,7 @@
.sp
it is processed as if it were
.sp
- (?C255)A(?C3)B(?C255)
+ (?C255)A(?C3)B(?C255)
.sp
Here is a more complicated example:
.sp
Modified: code/trunk/doc/pcre2compat.3
===================================================================
--- code/trunk/doc/pcre2compat.3 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/doc/pcre2compat.3 2017-01-16 17:40:47 UTC (rev 655)
@@ -118,8 +118,8 @@
.P
14. Perl used to recognize comments in some places that PCRE2 does not, for
example, between the ( and ? at the start of a subpattern. If the /x modifier
-is set, Perl allowed white space between ( and ? though the latest Perls give
-an error (for a while it was just deprecated). There may still be some cases
+is set, Perl allowed white space between ( and ? though the latest Perls give
+an error (for a while it was just deprecated). There may still be some cases
where Perl behaves differently.
.P
15. Perl, when in warning mode, gives warnings for character classes such as
@@ -140,7 +140,7 @@
.sp
(a) Although lookbehind assertions in PCRE2 must match fixed length strings,
each alternative branch of a lookbehind assertion can match a different length
-of string. Perl requires them all to have the same length.
+of string. Perl requires them all to have the same length.
.sp
(b) From PCRE2 10.23, back references to groups of fixed length are supported
in lookbehinds, provided that there is no possibility of referencing a
Modified: code/trunk/doc/pcre2grep.1
===================================================================
--- code/trunk/doc/pcre2grep.1 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/doc/pcre2grep.1 2017-01-16 17:40:47 UTC (rev 655)
@@ -62,7 +62,7 @@
if a line is too long and the buffer can no longer be expanded.
.P
The block of memory that is actually used is three times the "buffer size", to
-allow for buffering "before" and "after" lines. If the buffer size is too
+allow for buffering "before" and "after" lines. If the buffer size is too
small, fewer than requested "before" and "after" lines may be output.
.P
Patterns can be no longer than 8K or BUFSIZ bytes, whichever is the greater.
@@ -146,8 +146,8 @@
\fB--binary-files\fP=\fItext\fP.
.TP
\fB-B\fP \fInumber\fP, \fB--before-context=\fP\fInumber\fP
-Output up to \fInumber\fP lines of context before each matching line. Fewer
-lines are output if the previous match or the start of the file is within
+Output up to \fInumber\fP lines of context before each matching line. Fewer
+lines are output if the previous match or the start of the file is within
\fInumber\fP lines, or if the processing buffer size has been set too small. If
file names and/or line numbers are being output, a hyphen separator is used
instead of a colon for the context lines. A line containing "--" is output
@@ -168,8 +168,8 @@
return code.
.TP
\fB--buffer-size=\fP\fInumber\fP
-Set the parameter that controls how much memory is obtained at the start of
-processing for buffering files that are being scanned. See also
+Set the parameter that controls how much memory is obtained at the start of
+processing for buffering files that are being scanned. See also
\fB--max-buffer-size\fP below.
.TP
\fB-C\fP \fInumber\fP, \fB--context=\fP\fInumber\fP
@@ -185,7 +185,7 @@
suppressed lines than the count (that is, the number of matches).
.sp
If no lines are selected, the number zero is output. If several files are are
-being scanned, a count is output for each of them and the \fB-t\fP option can
+being scanned, a count is output for each of them and the \fB-t\fP option can
be used to cause a total to be output at the end. However, if the
\fB--files-with-matches\fP option is also used, only those files whose counts
are greater than zero are listed. When \fB-c\fP is used, the \fB-A\fP,
@@ -209,14 +209,14 @@
variables PCRE2GREP_COLOUR, PCRE2GREP_COLOR, PCREGREP_COLOUR, or
PCREGREP_COLOR, which are checked in that order. If none of these are set,
\fBpcre2grep\fP looks for GREP_COLORS or GREP_COLOR (in that order). The value
-of the variable should be a string of two numbers, separated by a semicolon,
+of the variable should be a string of two numbers, separated by a semicolon,
except in the case of GREP_COLORS, which must start with "ms=" or "mt="
followed by two semicolon-separated colours, terminated by the end of the
-string or by a colon. If GREP_COLORS does not start with "ms=" or "mt=" it is
+string or by a colon. If GREP_COLORS does not start with "ms=" or "mt=" it is
ignored, and GREP_COLOR is checked.
.sp
If the string obtained from one of the above variables contains any characters
-other than semicolon or digits, the setting is ignored and the default colour
+other than semicolon or digits, the setting is ignored and the default colour
is used. The string is copied directly into the control string for setting
colour on a terminal, so it is your responsibility to ensure that the values
make sense. If no relevant environment variable is set, the default is "1;31",
@@ -311,7 +311,7 @@
tested before the file's patterns. However, no other pattern is taken from the
command line; all arguments are treated as the names of paths to be searched.
.TP
-\fB--file-list\fP=\fIfilename\fP
+\fB--file-list\fP=\fIfilename\fP
Read a list of files and/or directories that are to be scanned from the given
file, one per line. Trailing white space is removed from each line, and blank
lines are ignored. These paths are processed before any that are listed on the
@@ -456,8 +456,8 @@
when the PCRE2 library is compiled, with the default default being 10 million.
.TP
\fB--max-buffer-size=\fInumber\fP
-This limits the expansion of the processing buffer, whose initial size can be
-set by \fB--buffer-size\fP. The maximum buffer size is silently forced to be no
+This limits the expansion of the processing buffer, whose initial size can be
+set by \fB--buffer-size\fP. The maximum buffer size is silently forced to be no
smaller than the starting buffer size.
.TP
\fB-M\fP, \fB--multiline\fP
@@ -547,7 +547,7 @@
capturing parentheses do not exist in the pattern, or were not set in the
match, nothing is output unless the file name or line number are being output.
.sp
-If this option is given multiple times, multiple substrings are output for each
+If this option is given multiple times, multiple substrings are output for each
match, in the order the options are given, and all on one line. For example,
-o3 -o1 -o3 causes the substrings matched by capturing parentheses 3 and 1 and
then 3 again to be output. By default, there is no separator (but see the next
@@ -610,7 +610,7 @@
.TP
\fB-x\fP, \fB--line-regex\fP, \fB--line-regexp\fP
Force the patterns to be anchored (each must start matching at the beginning of
-a line) and in addition, require them to match entire lines. In multiline mode
+a line) and in addition, require them to match entire lines. In multiline mode
the match may be more than one line. This is equivalent to having \eA and \eZ
characters at the start and end of each alternative top-level branch in every
pattern. This option applies only to the patterns that are matched against the
Modified: code/trunk/doc/pcre2grep.txt
===================================================================
--- code/trunk/doc/pcre2grep.txt 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/doc/pcre2grep.txt 2017-01-16 17:40:47 UTC (rev 655)
@@ -219,16 +219,26 @@
possible matches in a line, not just one, in order to colour
them all.
- The colour that is used can be specified by setting the envi-
- ronment variable PCRE2GREP_COLOUR or PCRE2GREP_COLOR. If nei-
- ther of these are set, pcre2grep looks for GREP_COLOUR or
- GREP_COLOR. The value of the variable should be a string of
- two numbers, separated by a semicolon. They are copied
- directly into the control string for setting colour on a ter-
- minal, so it is your responsibility to ensure that they make
- sense. If neither of the environment variables is set, the
- default is "1;31", which gives red.
+ The colour that is used can be specified by setting one of
+ the environment variables PCRE2GREP_COLOUR, PCRE2GREP_COLOR,
+ PCREGREP_COLOUR, or PCREGREP_COLOR, which are checked in that
+ order. If none of these are set, pcre2grep looks for
+ GREP_COLORS or GREP_COLOR (in that order). The value of the
+ variable should be a string of two numbers, separated by a
+ semicolon, except in the case of GREP_COLORS, which must
+ start with "ms=" or "mt=" followed by two semicolon-separated
+ colours, terminated by the end of the string or by a colon.
+ If GREP_COLORS does not start with "ms=" or "mt=" it is
+ ignored, and GREP_COLOR is checked.
+ If the string obtained from one of the above variables con-
+ tains any characters other than semicolon or digits, the set-
+ ting is ignored and the default colour is used. The string is
+ copied directly into the control string for setting colour on
+ a terminal, so it is your responsibility to ensure that the
+ values make sense. If no relevant environment variable is
+ set, the default is "1;31", which gives red.
+
-D action, --devices=action
If an input path is not a regular file or a directory,
"action" specifies how it is to be processed. Valid values
@@ -763,12 +773,12 @@
CALLING EXTERNAL SCRIPTS
- On non-Windows systems, pcre2grep has, by default, support for calling
- external programs or scripts during matching by making use of PCRE2's
- callout facility. However, this support can be disabled when pcre2grep
- is built. You can find out whether your binary has support for call-
- outs by running it with the --help option. If the support is not
- enabled, all callouts in patterns are ignored by pcre2grep.
+ pcre2grep has, by default, support for calling external programs or
+ scripts during matching by making use of PCRE2's callout facility. How-
+ ever, this support can be disabled when pcre2grep is built. You can
+ find out whether your binary has support for callouts by running it
+ with the --help option. If the support is not enabled, all callouts in
+ patterns are ignored by pcre2grep.
A callout in a PCRE2 pattern is of the form (?C<arg>) where the argu-
ment is either a number or a quoted string (see the pcre2callout docu-
@@ -852,5 +862,5 @@
REVISION
- Last updated: 31 October 2016
+ Last updated: 31 December 2016
Copyright (c) 1997-2016 University of Cambridge.
Modified: code/trunk/doc/pcre2limits.3
===================================================================
--- code/trunk/doc/pcre2limits.3 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/doc/pcre2limits.3 2017-01-16 17:40:47 UTC (rev 655)
@@ -47,8 +47,8 @@
no more than 65535 capturing subpatterns. There is, however, a limit to the
depth of nesting of parenthesized subpatterns of all kinds. This is imposed in
order to limit the amount of system stack used at compile time. The default
-limit can be specified when PCRE2 is built; the default default is 250. An
-application can change this limit by calling pcre2_set_parens_nest_limit() to
+limit can be specified when PCRE2 is built; the default default is 250. An
+application can change this limit by calling pcre2_set_parens_nest_limit() to
set the limit in a compile context.
.P
The maximum length of name for a named subpattern is 32 code units, and the
@@ -58,7 +58,7 @@
is 255 code units for the 8-bit library and 65535 code units for the 16-bit and
32-bit libraries.
.P
-The maximum length of a string argument to a callout is the largest number a
+The maximum length of a string argument to a callout is the largest number a
32-bit unsigned integer can hold.
.
.
Modified: code/trunk/doc/pcre2pattern.3
===================================================================
--- code/trunk/doc/pcre2pattern.3 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/doc/pcre2pattern.3 2017-01-16 17:40:47 UTC (rev 655)
@@ -159,9 +159,9 @@
limits set by the programmer, but not raise them. If there is more than one
setting of one of these limits, the lower value is used.
.P
-The match limit is used (but in a different way) when JIT is being used, but it
-is not relevant, and is ignored, when matching with \fBpcre2_dfa_match()\fP.
-However, the recursion limit is relevant for DFA matching, which does use some
+The match limit is used (but in a different way) when JIT is being used, but it
+is not relevant, and is ignored, when matching with \fBpcre2_dfa_match()\fP.
+However, the recursion limit is relevant for DFA matching, which does use some
function recursion, in particular, for recursions within the pattern.
.
.
@@ -2096,7 +2096,7 @@
subpattern is possible using named parentheses (see below).
.P
Another way of avoiding the ambiguity inherent in the use of digits following a
-backslash is to use the \eg escape sequence. This escape must be followed by a
+backslash is to use the \eg escape sequence. This escape must be followed by a
signed or unsigned number, optionally enclosed in braces. These examples are
all identical:
.sp
@@ -2116,8 +2116,8 @@
can be helpful in long patterns, and also in patterns that are created by
joining together fragments that contain references within themselves.
.P
-The sequence \eg{+1} is a reference to the next capturing subpattern. This kind
-of forward reference can be useful it patterns that repeat. Perl does not
+The sequence \eg{+1} is a reference to the next capturing subpattern. This kind
+of forward reference can be useful it patterns that repeat. Perl does not
support the use of + in this way.
.P
A back reference matches whatever actually matched the capturing subpattern in
@@ -2227,11 +2227,11 @@
capturing is carried out only for positive assertions. (Perl sometimes, but not
always, does do capturing in negative assertions.)
.P
-WARNING: If a positive assertion containing one or more capturing subpatterns
-succeeds, but failure to match later in the pattern causes backtracking over
-this assertion, the captures within the assertion are reset only if no higher
-numbered captures are already set. This is, unfortunately, a fundamental
-limitation of the current implementation; it may get removed in a future
+WARNING: If a positive assertion containing one or more capturing subpatterns
+succeeds, but failure to match later in the pattern causes backtracking over
+this assertion, the captures within the assertion are reset only if no higher
+numbered captures are already set. This is, unfortunately, a fundamental
+limitation of the current implementation; it may get removed in a future
reworking.
.P
For compatibility with Perl, most assertion subpatterns may be repeated; though
@@ -2497,7 +2497,7 @@
.sp
Perl uses the syntax (?(<name>)...) or (?('name')...) to test for a used
subpattern by name. For compatibility with earlier versions of PCRE1, which had
-this facility before Perl, the syntax (?(name)...) is also recognized. Note,
+this facility before Perl, the syntax (?(name)...) is also recognized. Note,
however, that undelimited names consisting of the letter R followed by digits
are ambiguous (see the following section).
.P
@@ -2531,11 +2531,11 @@
the condition is true if matching is currently in a recursion or subroutine
call to the whole pattern or any subpattern. If digits follow the letter R, and
there is no subpattern with that name, the condition is true if the most recent
-call is into a subpattern with the given number, which must exist somewhere in
+call is into a subpattern with the given number, which must exist somewhere in
the overall pattern. This is a contrived example that is equivalent to a+b:
.sp
((?(R1)a+|(?1)b))
-.sp
+.sp
However, in both cases, if there is a subpattern with a matching name, the
condition tests for its being set, as described in the section above, instead
of testing for recursion. For example, creating a group with the name R1 by
@@ -2545,10 +2545,10 @@
.sp
(?(R&name)...)
.sp
-the condition is true if the most recent recursion is into a subpattern of that
+the condition is true if the most recent recursion is into a subpattern of that
name (which must exist within the pattern).
.P
-This condition does not check the entire recursion stack. It tests only the
+This condition does not check the entire recursion stack. It tests only the
current level. If the name used in a condition of this kind is a duplicate, the
test is applied to all subpatterns of the same name, and is true if any one of
them is the most recent recursion.
@@ -3039,19 +3039,19 @@
By default, for compatibility with Perl, a name is any sequence of characters
that does not include a closing parenthesis. The name is not processed in
any way, and it is not possible to include a closing parenthesis in the name.
-This can be changed by setting the PCRE2_ALT_VERBNAMES option, but the result
-is no longer Perl-compatible.
+This can be changed by setting the PCRE2_ALT_VERBNAMES option, but the result
+is no longer Perl-compatible.
.P
When PCRE2_ALT_VERBNAMES is set, backslash processing is applied to verb names
-and only an unescaped closing parenthesis terminates the name. However, the
-only backslash items that are permitted are \eQ, \eE, and sequences such as
-\ex{100} that define character code points. Character type escapes such as \ed
+and only an unescaped closing parenthesis terminates the name. However, the
+only backslash items that are permitted are \eQ, \eE, and sequences such as
+\ex{100} that define character code points. Character type escapes such as \ed
are faulted.
.P
A closing parenthesis can be included in a name either as \e) or between \eQ
and \eE. In addition to backslash processing, if the PCRE2_EXTENDED option is
also set, unescaped whitespace in verb names is skipped, and #-comments are
-recognized, exactly as in the rest of the pattern. PCRE2_EXTENDED does not
+recognized, exactly as in the rest of the pattern. PCRE2_EXTENDED does not
affect verb names unless PCRE2_ALT_VERBNAMES is also set.
.P
The maximum length of a name is 255 in the 8-bit library and 65535 in the
Modified: code/trunk/doc/pcre2stack.3
===================================================================
--- code/trunk/doc/pcre2stack.3 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/doc/pcre2stack.3 2017-01-16 17:40:47 UTC (rev 655)
@@ -43,8 +43,8 @@
Normally, these are never very deep, and the limit on the complexity of
\fBpcre2_dfa_match()\fP is controlled by the amount of workspace it is given.
However, it is possible to write patterns with runaway infinite recursions;
-such patterns will cause \fBpcre2_dfa_match()\fP to run out of stack unless a
-limit is applied (see below).
+such patterns will cause \fBpcre2_dfa_match()\fP to run out of stack unless a
+limit is applied (see below).
.P
The comments in the next three sections do not apply to
\fBpcre2_dfa_match()\fP; they are relevant only for \fBpcre2_match()\fP without
@@ -151,9 +151,9 @@
.SS "Limiting \fBpcre2_dfa_match()\fP's stack usage"
.rs
.sp
-The recursion limit, as described above for \fBpcre2_match()\fP, also applies
+The recursion limit, as described above for \fBpcre2_match()\fP, also applies
to \fBpcre2_dfa_match()\fP, whose use of recursive function calls for
-recursions in the pattern can lead to runaway stack usage. The non-recursive
+recursions in the pattern can lead to runaway stack usage. The non-recursive
match limit is not relevant for DFA matching, and is ignored.
.
.
Modified: code/trunk/doc/pcre2syntax.3
===================================================================
--- code/trunk/doc/pcre2syntax.3 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/doc/pcre2syntax.3 2017-01-16 17:40:47 UTC (rev 655)
@@ -476,7 +476,7 @@
\eg{n} reference by number
\eg+n relative reference by number (PCRE2 extension)
\eg-n relative reference by number
- \eg{+n} relative reference by number (PCRE2 extension)
+ \eg{+n} relative reference by number (PCRE2 extension)
\eg{-n} relative reference by number
\ek<name> reference by name (Perl)
\ek'name' reference by name (Perl)
@@ -523,7 +523,7 @@
(?(VERSION[>]=n.m) test PCRE2 version
(?(assert) assertion condition
.sp
-Note the ambiguity of (?(R) and (?(Rn) which might be named reference
+Note the ambiguity of (?(R) and (?(Rn) which might be named reference
conditions or recursion tests. Such a condition is interpreted as a reference
condition if the relevant named group exists.
.
Modified: code/trunk/doc/pcre2test.1
===================================================================
--- code/trunk/doc/pcre2test.1 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/doc/pcre2test.1 2017-01-16 17:40:47 UTC (rev 655)
@@ -88,7 +88,7 @@
"Setting compilation options"
.\"
below) is set, the pattern and any following subject lines are interpreted as
-UTF-8 strings and translated to UTF-16 or UTF-32 as appropriate.
+UTF-8 strings and translated to UTF-16 or UTF-32 as appropriate.
.P
For non-UTF testing of wide characters, the \fButf8_input\fP modifier can be
used. This is mutually exclusive with \fButf\fP, and is allowed only in 16-bit
@@ -125,7 +125,7 @@
has not been built, this option causes an error.
.TP 10
\fB-ac\fP
-Behave as if each pattern has the \fBauto_callout\fP modifier, that is, insert
+Behave as if each pattern has the \fBauto_callout\fP modifier, that is, insert
automatic callouts into every pattern that is compiled.
.TP 10
\fB-b\fP
@@ -550,7 +550,7 @@
As well as turning on the PCRE2_UTF option, the \fButf\fP modifier causes all
non-printing characters in output strings to be printed using the \ex{hh...}
notation. Otherwise, those less than 0x100 are output in hex without the curly
-brackets. Setting \fButf\fP in 16-bit or 32-bit mode also causes pattern and
+brackets. Setting \fButf\fP in 16-bit or 32-bit mode also causes pattern and
subject strings to be translated to UTF-16 or UTF-32, respectively, before
being passed to library functions.
.
@@ -584,8 +584,8 @@
pushcopy push a copy onto the stack
stackguard=<number> test the stackguard feature
tables=[0|1|2] select internal tables
- use_length do not zero-terminate the pattern
- utf8_input treat input as UTF-8
+ use_length do not zero-terminate the pattern
+ utf8_input treat input as UTF-8
.sp
The effects of these modifiers are described in the following sections.
.
@@ -669,7 +669,7 @@
By default, patterns are passed to the compiling functions as zero-terminated
strings. When using the POSIX wrapper API, there is no other option. However,
when using PCRE2's native API, patterns can be passed by length instead of
-being zero-terminated. The \fBuse_length\fP modifier causes this to happen.
+being zero-terminated. The \fBuse_length\fP modifier causes this to happen.
Using a length happens automatically (whether or not \fBuse_length\fP is set)
when \fBhex\fP is set, because patterns specified in hexadecimal may contain
binary zeros.
@@ -696,9 +696,9 @@
the delimiter within a substring. The \fBhex\fP and \fBexpand\fP modifiers are
mutually exclusive.
.P
-The POSIX API cannot be used with patterns specified in hexadecimal because
-they may contain binary zeros, which conflicts with \fBregcomp()\fP's
-requirement for a zero-terminated string. Such patterns are always passed to
+The POSIX API cannot be used with patterns specified in hexadecimal because
+they may contain binary zeros, which conflicts with \fBregcomp()\fP's
+requirement for a zero-terminated string. Such patterns are always passed to
\fBpcre2_compile()\fP as a string with a length, not as zero-terminated.
.
.
@@ -705,8 +705,8 @@
.SS "Specifying wide characters in 16-bit and 32-bit modes"
.rs
.sp
-In 16-bit and 32-bit modes, all input is automatically treated as UTF-8 and
-translated to UTF-16 or UTF-32 when the \fButf\fP modifier is set. For testing
+In 16-bit and 32-bit modes, all input is automatically treated as UTF-8 and
+translated to UTF-16 or UTF-32 when the \fButf\fP modifier is set. For testing
the 16-bit and 32-bit libraries in non-UTF mode, the \fButf8_input\fP modifier
can be used. It is mutually exclusive with \fButf\fP. Input lines are
interpreted as UTF-8 as a means of specifying wide characters. More details are
@@ -1134,7 +1134,7 @@
.sp
A callout function is supplied when \fBpcre2test\fP calls the library matching
functions, unless \fBcallout_none\fP is specified. If \fBcallout_capture\fP is
-set, the current captured groups are output when a callout occurs. The default
+set, the current captured groups are output when a callout occurs. The default
return from the callout function is zero, which allows matching to continue.
.P
The \fBcallout_fail\fP modifier can be given one or two numbers. If there is
@@ -1141,8 +1141,8 @@
only one number, 1 is returned instead of 0 (causing matching to backtrack)
when a callout of that number is reached. If two numbers (<n>:<m>) are given, 1
is returned when callout <n> is reached and there have been at least <m>
-callouts. The \fBcallout_error\fP modifier is similar, except that
-PCRE2_ERROR_CALLOUT is returned, causing the entire matching process to be
+callouts. The \fBcallout_error\fP modifier is similar, except that
+PCRE2_ERROR_CALLOUT is returned, causing the entire matching process to be
aborted. If both these modifiers are set for the same callout number,
\fBcallout_error\fP takes precedence.
.P
Modified: code/trunk/doc/pcre2test.txt
===================================================================
--- code/trunk/doc/pcre2test.txt 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/doc/pcre2test.txt 2017-01-16 17:40:47 UTC (rev 655)
@@ -116,7 +116,11 @@
is the default. If the 32-bit library has not been built,
this option causes an error.
- -b Behave as if each pattern has the /fullbincode modifier; the
+ -ac Behave as if each pattern has the auto_callout modifier, that
+ is, insert automatic callouts into every pattern that is com-
+ piled.
+
+ -b Behave as if each pattern has the fullbincode modifier; the
full internal binary form of the pattern is output after com-
pilation.
@@ -174,7 +178,7 @@
-help Output a brief summary these options and then exit.
- -i Behave as if each pattern has the /info modifier; information
+ -i Behave as if each pattern has the info modifier; information
about the compiled pattern is given after compilation.
-jit Behave as if each pattern line has the jit modifier; after
@@ -724,7 +728,7 @@
2 compile JIT code for soft partial matching
4 compile JIT code for hard partial matching
- The possible values for the /jit modifier are therefore:
+ The possible values for the jit modifier are therefore:
0 disable JIT
1 normal matching only
@@ -764,7 +768,7 @@
Setting a locale
- The /locale modifier must specify the name of a locale, for example:
+ The locale modifier must specify the name of a locale, for example:
/pattern/locale=fr_FR
@@ -771,7 +775,7 @@
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
- when matching the following subject lines. The /locale modifier applies
+ 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-
ter tables are mutually exclusive.
@@ -778,10 +782,10 @@
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
- pattern is subsequently passed to the JIT compiler, the size of the JIT
+ 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 pat-
+ tern is subsequently passed to the JIT compiler, the size of the JIT
compiled code is also output. Here is an example:
re> /a(b)c/jit,memory
@@ -837,7 +841,7 @@
Testing the stack guard feature
- The /stackguard modifier is used to test the use of pcre2_set_com-
+ 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
@@ -849,7 +853,7 @@
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
@@ -931,7 +935,7 @@
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().
@@ -951,6 +955,7 @@
altglobal alternative global matching
callout_capture show captures at callout time
callout_data=<n> set a value to pass via callouts
+ callout_error=<n>[:<m>] control callout error
callout_fail=<n>[:<m>] control callout failure
callout_none do not supply a callout function
copy=<number or name> copy captured substring
@@ -1042,15 +1047,23 @@
A callout function is supplied when pcre2test calls the library match-
ing functions, unless callout_none is specified. If callout_capture is
- set, the current captured groups are output when a callout occurs.
+ set, the current captured groups are output when a callout occurs. The
+ default return from the callout function is zero, which allows matching
+ to continue.
The callout_fail modifier can be given one or two numbers. If there is
- only one number, 1 is returned instead of 0 when a callout of that num-
- ber is reached. If two numbers are given, 1 is returned when callout
- <n> is reached for the <m>th time. Note that callouts with string argu-
- ments are always given the number zero. See "Callouts" below for a
- description of the output when a callout it taken.
+ only one number, 1 is returned instead of 0 (causing matching to back-
+ track) when a callout of that number is reached. If two numbers
+ (<n>:<m>) are given, 1 is returned when callout <n> is reached and
+ there have been at least <m> callouts. The callout_error modifier is
+ similar, except that PCRE2_ERROR_CALLOUT is returned, causing the
+ entire matching process to be aborted. If both these modifiers are set
+ for the same callout number, callout_error takes precedence.
+ Note that callouts with string arguments are always given the number
+ zero. See "Callouts" below for a description of the output when a call-
+ out it taken.
+
The callout_data modifier can be given an unsigned or a negative num-
ber. This is set as the "user data" that is passed to the matching
function, and passed back when the callout function is invoked. Any
@@ -1060,7 +1073,7 @@
Finding all matches in a string
Searching for all possible matches within a subject can be requested by
- the global or /altglobal modifier. After finding a match, the matching
+ the global or altglobal modifier. After finding a match, the matching
function is called again to search the remainder of the subject. The
difference between global and altglobal is that the former uses the
start_offset argument to pcre2_match() or pcre2_dfa_match() to start
@@ -1329,7 +1342,7 @@
If the strings contain any non-printing characters, they are output as
\xhh escapes if the value is less than 256 and UTF mode is not set.
Otherwise they are output as \x{hh...} escapes. See below for the defi-
- nition of non-printing characters. If the /aftertext modifier is set,
+ nition of non-printing characters. If the aftertext modifier is set,
the output for substring 0 is followed by the the rest of the subject
string, identified by "0+" like this:
@@ -1512,7 +1525,7 @@
When pcre2test is outputting text that is a matched part of a subject
string, it behaves in the same way, unless a different locale has been
- set for the pattern (using the /locale modifier). In this case, the
+ set for the pattern (using the locale modifier). In this case, the
isprint() function is used to distinguish printing and non-printing
characters.
@@ -1601,5 +1614,5 @@
REVISION
- Last updated: 04 November 2016
+ Last updated: 28 December 2016
Copyright (c) 1997-2016 University of Cambridge.
Modified: code/trunk/src/config.h.generic
===================================================================
--- code/trunk/src/config.h.generic 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/src/config.h.generic 2017-01-16 17:40:47 UTC (rev 655)
@@ -78,6 +78,9 @@
/* Define to 1 if you have the <memory.h> header file. */
/* #undef HAVE_MEMORY_H */
+/* Define to 1 if you have the `mkostemp' function. */
+/* #undef HAVE_MKOSTEMP */
+
/* Define if you have POSIX threads libraries and header files. */
/* #undef HAVE_PTHREAD */
@@ -90,6 +93,9 @@
/* Define to 1 if you have the <readline/readline.h> header file. */
/* #undef HAVE_READLINE_READLINE_H */
+/* Define to 1 if you have the `secure_getenv' function. */
+/* #undef HAVE_SECURE_GETENV */
+
/* Define to 1 if you have the <stdint.h> header file. */
/* #undef HAVE_STDINT_H */
@@ -308,9 +314,40 @@
/* Define to any value for valgrind support to find invalid memory reads. */
/* #undef SUPPORT_VALGRIND */
+/* Enable extensions on AIX 3, Interix. */
+#ifndef _ALL_SOURCE
+# define _ALL_SOURCE 1
+#endif
+/* Enable GNU extensions on systems that have them. */
+#ifndef _GNU_SOURCE
+# define _GNU_SOURCE 1
+#endif
+/* Enable threading extensions on Solaris. */
+#ifndef _POSIX_PTHREAD_SEMANTICS
+# define _POSIX_PTHREAD_SEMANTICS 1
+#endif
+/* Enable extensions on HP NonStop. */
+#ifndef _TANDEM_SOURCE
+# define _TANDEM_SOURCE 1
+#endif
+/* Enable general extensions on Solaris. */
+#ifndef __EXTENSIONS__
+# define __EXTENSIONS__ 1
+#endif
+
/* Version number of package */
#define VERSION "10.23-RC1"
+/* Define to 1 if on MINIX. */
+/* #undef _MINIX */
+
+/* Define to 2 if the system does not provide POSIX.1 features except with
+ this defined. */
+/* #undef _POSIX_1_SOURCE */
+
+/* Define to 1 if you need to in order for `stat' and other things to work. */
+/* #undef _POSIX_SOURCE */
+
/* Define to empty if `const' does not conform to ANSI C. */
/* #undef const */
Modified: code/trunk/src/pcre2.h
===================================================================
--- code/trunk/src/pcre2.h 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/src/pcre2.h 2017-01-16 17:40:47 UTC (rev 655)
@@ -44,7 +44,7 @@
#define PCRE2_MAJOR 10
#define PCRE2_MINOR 23
#define PCRE2_PRERELEASE -RC1
-#define PCRE2_DATE 2016-08-01
+#define PCRE2_DATE 2017-01-16
/* When an application links to a PCRE DLL in Windows, the symbols that are
imported have to be identified as such. When building PCRE2, the appropriate
Modified: code/trunk/src/pcre2.h.generic
===================================================================
--- code/trunk/src/pcre2.h.generic 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/src/pcre2.h.generic 2017-01-16 17:40:47 UTC (rev 655)
@@ -44,7 +44,7 @@
#define PCRE2_MAJOR 10
#define PCRE2_MINOR 23
#define PCRE2_PRERELEASE -RC1
-#define PCRE2_DATE 2016-08-01
+#define PCRE2_DATE 2017-01-16
/* When an application links to a PCRE DLL in Windows, the symbols that are
imported have to be identified as such. When building PCRE2, the appropriate
@@ -465,7 +465,9 @@
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
pcre2_code_free(pcre2_code *); \
PCRE2_EXP_DECL pcre2_code PCRE2_CALL_CONVENTION \
- *pcre2_code_copy(const pcre2_code *);
+ *pcre2_code_copy(const pcre2_code *); \
+PCRE2_EXP_DECL pcre2_code PCRE2_CALL_CONVENTION \
+ *pcre2_code_copy_with_tables(const pcre2_code *);
/* Functions that give information about a compiled pattern. */
@@ -629,6 +631,7 @@
#define pcre2_callout_enumerate PCRE2_SUFFIX(pcre2_callout_enumerate_)
#define pcre2_code_copy PCRE2_SUFFIX(pcre2_code_copy_)
+#define pcre2_code_copy_with_tables PCRE2_SUFFIX(pcre2_code_copy_with_tables_)
#define pcre2_code_free PCRE2_SUFFIX(pcre2_code_free_)
#define pcre2_compile PCRE2_SUFFIX(pcre2_compile_)
#define pcre2_compile_context_copy PCRE2_SUFFIX(pcre2_compile_context_copy_)
Modified: code/trunk/src/pcre2_auto_possess.c
===================================================================
--- code/trunk/src/pcre2_auto_possess.c 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/src/pcre2_auto_possess.c 2017-01-16 17:40:47 UTC (rev 655)
@@ -1047,8 +1047,8 @@
/* Replaces single character iterations with their possessive alternatives
if appropriate. This function modifies the compiled opcode! Hitting a
non-existent opcode may indicate a bug in PCRE2, but it can also be caused if a
-bad UTF string was compiled with PCRE2_NO_UTF_CHECK. The rec_limit catches
-overly complicated or large patterns. In these cases, the check just stops,
+bad UTF string was compiled with PCRE2_NO_UTF_CHECK. The rec_limit catches
+overly complicated or large patterns. In these cases, the check just stops,
leaving the remainder of the pattern unpossessified.
Arguments:
Modified: code/trunk/src/pcre2_compile.c
===================================================================
--- code/trunk/src/pcre2_compile.c 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/src/pcre2_compile.c 2017-01-16 17:40:47 UTC (rev 655)
@@ -116,9 +116,11 @@
/* Function definitions to allow mutual recursion */
+#ifdef SUPPORT_UNICODE
static unsigned int
- add_list_to_class_internal(uint8_t *, PCRE2_UCHAR **, uint32_t, compile_block *,
- const uint32_t *, unsigned int);
+ add_list_to_class_internal(uint8_t *, PCRE2_UCHAR **, uint32_t,
+ compile_block *, const uint32_t *, unsigned int);
+#endif
static int
compile_regex(uint32_t, PCRE2_UCHAR **, uint32_t **, int *, uint32_t,
@@ -4381,16 +4383,14 @@
+#ifdef SUPPORT_UNICODE
/*************************************************
* Add a list of characters to a class (internal) *
*************************************************/
/* This function is used for adding a list of case-equivalent characters to a
-class, and also for adding a list of horizontal or vertical whitespace. If the
-list is in order (which it should be), ranges of characters are detected and
-handled appropriately. This function is called (sometimes recursively) only
-from within the "add to class" set of functions. The external entry point is
-add_list_to_class().
+class when in UTF mode. This function is called only from within
+add_to_class_internal(), with which it is mutually recursive.
Arguments:
classbits the bit map for characters < 256
@@ -4423,6 +4423,7 @@
}
return n8;
}
+#endif
@@ -4459,8 +4460,11 @@
* External entry point for add list to class *
*************************************************/
-/* This function sets the overall range so that the internal functions can try
-to avoid duplication when handling case-independence.
+/* This function is used for adding a list of horizontal or vertical whitespace
+characters to a class. The list must be in order so that ranges of characters
+can be detected and handled appropriately. This function sets the overall range
+so that the internal functions can try to avoid duplication when handling
+case-independence.
Arguments:
classbits the bit map for characters < 256
Modified: code/trunk/src/pcre2_dfa_match.c
===================================================================
--- code/trunk/src/pcre2_dfa_match.c 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/src/pcre2_dfa_match.c 2017-01-16 17:40:47 UTC (rev 655)
@@ -3216,7 +3216,7 @@
{
mb->callout = NULL;
mb->memctl = re->memctl;
- mb->match_limit_recursion = PRIV(default_match_context).recursion_limit;
+ mb->match_limit_recursion = PRIV(default_match_context).recursion_limit;
}
else
{
@@ -3229,7 +3229,7 @@
mb->callout = mcontext->callout;
mb->callout_data = mcontext->callout_data;
mb->memctl = mcontext->memctl;
- mb->match_limit_recursion = mcontext->recursion_limit;
+ mb->match_limit_recursion = mcontext->recursion_limit;
}
if (mb->match_limit_recursion > re->limit_recursion)
mb->match_limit_recursion = re->limit_recursion;
Modified: code/trunk/src/pcre2_error.c
===================================================================
--- code/trunk/src/pcre2_error.c 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/src/pcre2_error.c 2017-01-16 17:40:47 UTC (rev 655)
@@ -173,9 +173,9 @@
"regular expression is too complicated\0"
"lookbehind assertion is too long\0"
"pattern string is longer than the limit set by the application\0"
- "internal error: unknown code in parsed pattern\0"
+ "internal error: unknown code in parsed pattern\0"
/* 90 */
- "internal error: bad code value in parsed_skip()\0"
+ "internal error: bad code value in parsed_skip()\0"
;
/* Match-time and UTF error texts are in the same format. */
Modified: code/trunk/src/pcre2_intmodedep.h
===================================================================
--- code/trunk/src/pcre2_intmodedep.h 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/src/pcre2_intmodedep.h 2017-01-16 17:40:47 UTC (rev 655)
@@ -648,7 +648,7 @@
#ifndef PCRE2_PCRE2TEST
-/* Structures for checking for mutual recursion when scanning compiled or
+/* Structures for checking for mutual recursion when scanning compiled or
parsed code. */
typedef struct recurse_check {
@@ -702,7 +702,7 @@
PCRE2_UCHAR *name_table; /* The name/number table */
PCRE2_SIZE workspace_size; /* Size of workspace */
PCRE2_SIZE small_ref_offset[10]; /* Offsets for \1 to \9 */
- PCRE2_SIZE erroroffset; /* Offset of error in pattern */
+ PCRE2_SIZE erroroffset; /* Offset of error in pattern */
uint16_t names_found; /* Number of entries so far */
uint16_t name_entry_size; /* Size of each entry */
open_capitem *open_caps; /* Chain of open capture items */
@@ -711,9 +711,9 @@
uint32_t external_options; /* External (initial) options */
uint32_t external_flags; /* External flag bits to be set */
uint32_t bracount; /* Count of capturing parentheses */
- uint32_t lastcapture; /* Last capture encountered */
- uint32_t *parsed_pattern; /* Parsed pattern buffer */
- uint32_t *parsed_pattern_end; /* Parsed pattern should not get here */
+ uint32_t lastcapture; /* Last capture encountered */
+ uint32_t *parsed_pattern; /* Parsed pattern buffer */
+ uint32_t *parsed_pattern_end; /* Parsed pattern should not get here */
uint32_t *groupinfo; /* Group info vector */
uint32_t top_backref; /* Maximum back reference */
uint32_t backref_map; /* Bitmap of low back refs */
@@ -720,7 +720,7 @@
uint32_t nltype; /* Newline type */
uint32_t nllen; /* Newline string length */
uint32_t class_range_start; /* Overall class range start */
- uint32_t class_range_end; /* Overall class range end */
+ uint32_t class_range_end; /* Overall class range end */
PCRE2_UCHAR nl[4]; /* Newline string when fixed length */
int max_lookbehind; /* Maximum lookbehind (characters) */
int parens_depth; /* Depth of nested parentheses */
Modified: code/trunk/src/pcre2grep.c
===================================================================
--- code/trunk/src/pcre2grep.c 2017-01-16 15:06:57 UTC (rev 654)
+++ code/trunk/src/pcre2grep.c 2017-01-16 17:40:47 UTC (rev 655)
@@ -1937,6 +1937,8 @@
fill_buffer(void *handle, int frtype, char *buffer, int length,
BOOL input_line_buffered)
{
+(void)frtype; /* Avoid warning when not used */
+
#ifdef SUPPORT_LIBZ
if (frtype == FR_LIBZ)
return gzread((gzFile)handle, buffer, length);
@@ -3015,8 +3017,8 @@
p->compiled = pcre2_compile(buffer, PCRE2_ZERO_TERMINATED, options, &errcode,
&erroffset, compile_context);
-/* Handle successful compile. Try JIT-compiling if supported and enabled. We
-ignore any JIT compiler errors, relying falling back to interpreting if
+/* Handle successful compile. Try JIT-compiling if supported and enabled. We
+ignore any JIT compiler errors, relying falling back to interpreting if
anything goes wrong with JIT. */
if (p->compiled != NULL)
@@ -3577,10 +3579,10 @@
if (cs == NULL) cs = getenv("PCREGREP_COLOR");
if (cs == NULL) cs = parse_grep_colors(getenv("GREP_COLORS"));
if (cs == NULL) cs = getenv("GREP_COLOR");
- if (cs != NULL)
+ if (cs != NULL)
{
if (strspn(cs, ";0123456789") == strlen(cs)) colour_string = cs;
- }
+ }
#ifdef WIN32
init_colour_output();
#endif
