Skip to content

M
MariaDB
Commit aaac2477 authored by Sergei Golubchik's avatar Sergei Golubchik
Browse files
Options

Merge remote-tracking branch 'merge/merge-pcre' into 10.2

parents a32373b6 4683ce82
Show whitespace changes
Inline Side-by-side
Showing with 151 additions and 114 deletions
pcre/AUTHORS
View file @ aaac2477
......@@ -2,13 +2,13 @@ THE MAIN PCRE LIBRARY
---------------------
Written by: Philip Hazel
Email local part: ph10
Email domain: cam.ac.uk
Email local part: Philip.Hazel
Email domain: gmail.com
University of Cambridge Computing Service,
Cambridge, England.
Copyright (c) 1997-2020 University of Cambridge
Copyright (c) 1997-2021 University of Cambridge
All rights reserved
......@@ -19,7 +19,7 @@ Written by: Zoltan Herczeg
Email local part: hzmester
Emain domain: freemail.hu
Copyright(c) 2010-2020 Zoltan Herczeg
Copyright(c) 2010-2021 Zoltan Herczeg
All rights reserved.
......@@ -30,7 +30,7 @@ Written by: Zoltan Herczeg
Email local part: hzmester
Emain domain: freemail.hu
Copyright(c) 2009-2020 Zoltan Herczeg
Copyright(c) 2009-2021 Zoltan Herczeg
All rights reserved.
......
pcre/CMakeLists.txt
View file @ aaac2477
......@@ -67,10 +67,17 @@
# 2013-11-05 PH added support for PARENS_NEST_LIMIT
# 2016-03-01 PH applied Chris Wilson's patch for MSVC static build
# 2016-06-24 PH applied Chris Wilson's revised patch (adds a separate option)
# 2021-06-14 PH changed CMAKE_MODULE_PATH definition to add, not replace
# 2021-06-14 PH applied Wolfgang Stöggl's patch for generating pcre-config and
# libpcre*.pc files (Bugzilla #2583)
PROJECT(PCRE C CXX)
SET(CMAKE_MODULE_PATH ${PROJECT_SOURCE_DIR}/cmake) # for FindReadline.cmake
# For FindReadline.cmake. This was changed to allow setting CMAKE_MODULE_PATH
# on the command line.
# SET(CMAKE_MODULE_PATH ${PROJECT_SOURCE_DIR}/cmake) # for FindReadline.cmake
LIST(APPEND CMAKE_MODULE_PATH ${PROJECT_SOURCE_DIR}/cmake)
# Enable Unicode properties
OPTION(PCRE_SUPPORT_UNICODE_PROPERTIES "Unicode properties" ON)
......@@ -83,6 +90,7 @@ INCLUDE(CheckIncludeFile)
INCLUDE(CheckIncludeFileCXX)
INCLUDE(CheckFunctionExists)
INCLUDE(CheckTypeSize)
INCLUDE(GNUInstallDirs) # for CMAKE_INSTALL_LIBDIR
CHECK_INCLUDE_FILE(dirent.h HAVE_DIRENT_H)
CHECK_INCLUDE_FILE(stdint.h HAVE_STDINT_H)
......@@ -255,7 +263,7 @@ foreach(configure_line ${configure_lines})
foreach(_substitution_variable ${SEARCHED_VARIABLES})
string(TOUPPER ${_substitution_variable} _substitution_variable_upper)
if (NOT ${_substitution_variable_upper})
string(REGEX MATCH "m4_define\\(${_substitution_variable}, \\[(.*)\\]" MACTHED_STRING ${configure_line})
string(REGEX MATCH "m4_define\\(${_substitution_variable}, \\[(.*)\\]" MATCHED_STRING ${configure_line})
if (CMAKE_MATCH_1)
set(${_substitution_variable_upper} ${CMAKE_MATCH_1})
endif()
......@@ -469,7 +477,6 @@ MARK_AS_ADVANCED(PCRE_POSIX_MALLOC_THRESHOLD)
MARK_AS_ADVANCED(PCRE_SUPPORT_BSR_ANYCRLF)
MARK_AS_ADVANCED(PCRE_SUPPORT_UNICODE_PROPERTIES)
IF(PCRE_SHOW_REPORT)
STRING(TOUPPER "${CMAKE_BUILD_TYPE}" buildtype)
IF (CMAKE_C_FLAGS)
......@@ -480,7 +487,7 @@ IF(PCRE_SHOW_REPORT)
ENDIF(CMAKE_CXX_FLAGS)
MESSAGE(STATUS "")
MESSAGE(STATUS "")
MESSAGE(STATUS "PCRE configuration summary:")
MESSAGE(STATUS "PCRE-${PCRE_MAJOR}.${PCRE_MINOR} configuration summary:")
MESSAGE(STATUS "")
# MESSAGE(STATUS " Install prefix .................. : ${CMAKE_INSTALL_PREFIX}")
MESSAGE(STATUS " C compiler ...................... : ${CMAKE_C_COMPILER}")
......
pcre/ChangeLog
View file @ aaac2477
ChangeLog for PCRE
------------------
Note that the PCRE 8.xx series (PCRE1) is now in a bugfix-only state. All
development is happening in the PCRE2 10.xx series.
Note that the PCRE 8.xx series (PCRE1) is now at end of life. All development
is happening in the PCRE2 10.xx series.
Version 8.45 15-June-2021
-------------------------
This is the final release of PCRE1. A few minor tidies are included.
1. CMakeLists.txt has two user-supplied patches applied, one to allow for the
setting of MODULE_PATH, and the other to support the generation of pcre-config
file and libpcre*.pc files.
2. There was a memory leak if a compile error occurred when there were more
than 20 named groups (Bugzilla #2613).
3. Fixed some typos in code and documentation.
4. Fixed a small (*MARK) bug in the interpreter (Bugzilla #2771).
Version 8.44 12 February-2020
......
pcre/LICENCE
View file @ aaac2477
......@@ -19,13 +19,13 @@ THE BASIC LIBRARY FUNCTIONS
---------------------------
Written by: Philip Hazel
Email local part: ph10
Email domain: cam.ac.uk
Email local part: Philip.Hazel
Email domain: gmail.com
University of Cambridge Computing Service,
Cambridge, England.
Copyright (c) 1997-2020 University of Cambridge
Copyright (c) 1997-2021 University of Cambridge
All rights reserved.
......@@ -36,7 +36,7 @@ Written by: Zoltan Herczeg
Email local part: hzmester
Email domain: freemail.hu
Copyright(c) 2010-2020 Zoltan Herczeg
Copyright(c) 2010-2021 Zoltan Herczeg
All rights reserved.
......@@ -47,7 +47,7 @@ Written by: Zoltan Herczeg
Email local part: hzmester
Email domain: freemail.hu
Copyright(c) 2009-2020 Zoltan Herczeg
Copyright(c) 2009-2021 Zoltan Herczeg
All rights reserved.
......
pcre/NEWS
View file @ aaac2477
News about PCRE releases
------------------------
Note that this library (now called PCRE1) is now being maintained for bug fixes
only. New projects are advised to use the new PCRE2 libraries.
Note that this library (now called PCRE1) is no longer being maintained. New
projects are advised to use the PCRE2 libraries.
Release 8.45 15-June-2021
-----------------------------
This is the final PCRE1 release. A very few small issues have been fixed.
Release 8.44 12-February-2020
......
pcre/NON-AUTOTOOLS-BUILD
View file @ aaac2477
......@@ -5,8 +5,8 @@ NOTE: This document relates to PCRE releases that use the original API, with
library names libpcre, libpcre16, and libpcre32. January 2015 saw the first
release of a new API, known as PCRE2, with release numbers starting at 10.00
and library names libpcre2-8, libpcre2-16, and libpcre2-32. The old libraries
(now called PCRE1) are still being maintained for bug fixes, but there will be
no new development. New projects are advised to use the new PCRE2 libraries.
(now called PCRE1) are now at end of life, and 8.45 is the final release. New
projects are advised to use the new PCRE2 libraries.
This document contains the following sections:
......@@ -768,6 +768,6 @@ Everything, source and executable, is in EBCDIC and native z/OS file formats.
However, this software is not maintained and will not be upgraded. If you are
new to PCRE you should be looking at PCRE2 (version 10.30 or later).
===============================
Last Updated: 13 September 2017
===============================
==========================
Last Updated: 15 June 2021
==========================
pcre/README
View file @ aaac2477
......@@ -5,9 +5,8 @@ NOTE: This set of files relates to PCRE releases that use the original API,
with library names libpcre, libpcre16, and libpcre32. January 2015 saw the
first release of a new API, known as PCRE2, with release numbers starting at
10.00 and library names libpcre2-8, libpcre2-16, and libpcre2-32. The old
libraries (now called PCRE1) are still being maintained for bug fixes, but
there will be no new development. New projects are advised to use the new PCRE2
libraries.
libraries (now called PCRE1) are now at end of life, and 8.45 is the final
release. New projects are advised to use the new PCRE2 libraries.
The latest release of PCRE1 is always available in three alternative formats
......@@ -998,6 +997,6 @@ pcre_xxx, one with the name pcre16_xx, and a third with the name pcre32_xxx.
RunTest.bat a script for running tests under Windows
Philip Hazel
Email local part: ph10
Email domain: cam.ac.uk
Last updated: 12 February 2020
Email local part: Philip.Hazel
Email domain: gmail.com
Last updated: 15 June 2021
pcre/configure.ac
View file @ aaac2477
......@@ -9,17 +9,17 @@ dnl The PCRE_PRERELEASE feature is for identifying release candidates. It might
dnl be defined as -RC2, for example. For real releases, it should be empty.
m4_define(pcre_major, [8])
m4_define(pcre_minor, [44])
m4_define(pcre_minor, [45])
m4_define(pcre_prerelease, [])
m4_define(pcre_date, [2020-02-12])
m4_define(pcre_date, [2021-06-15])
# 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(libpcre_version, [3:12:2])
m4_define(libpcre16_version, [2:12:2])
m4_define(libpcre32_version, [0:12:0])
m4_define(libpcre_version, [3:13:2])
m4_define(libpcre16_version, [2:13:2])
m4_define(libpcre32_version, [0:13:0])
m4_define(libpcreposix_version, [0:7:0])
m4_define(libpcrecpp_version, [0:2:0])
......
pcre/doc/html/NON-AUTOTOOLS-BUILD.txt
View file @ aaac2477
......@@ -5,8 +5,8 @@ NOTE: This document relates to PCRE releases that use the original API, with
library names libpcre, libpcre16, and libpcre32. January 2015 saw the first
release of a new API, known as PCRE2, with release numbers starting at 10.00
and library names libpcre2-8, libpcre2-16, and libpcre2-32. The old libraries
(now called PCRE1) are still being maintained for bug fixes, but there will be
no new development. New projects are advised to use the new PCRE2 libraries.
(now called PCRE1) are now at end of life, and 8.45 is the final release. New
projects are advised to use the new PCRE2 libraries.
This document contains the following sections:
......@@ -768,6 +768,6 @@ Everything, source and executable, is in EBCDIC and native z/OS file formats.
However, this software is not maintained and will not be upgraded. If you are
new to PCRE you should be looking at PCRE2 (version 10.30 or later).
===============================
Last Updated: 13 September 2017
===============================
==========================
Last Updated: 15 June 2021
==========================
pcre/doc/html/README.txt
View file @ aaac2477
......@@ -5,9 +5,8 @@ NOTE: This set of files relates to PCRE releases that use the original API,
with library names libpcre, libpcre16, and libpcre32. January 2015 saw the
first release of a new API, known as PCRE2, with release numbers starting at
10.00 and library names libpcre2-8, libpcre2-16, and libpcre2-32. The old
libraries (now called PCRE1) are still being maintained for bug fixes, but
there will be no new development. New projects are advised to use the new PCRE2
libraries.
libraries (now called PCRE1) are now at end of life, and 8.45 is the final
release. New projects are advised to use the new PCRE2 libraries.
The latest release of PCRE1 is always available in three alternative formats
......@@ -998,6 +997,6 @@ pcre_xxx, one with the name pcre16_xx, and a third with the name pcre32_xxx.
RunTest.bat a script for running tests under Windows
Philip Hazel
Email local part: ph10
Email domain: cam.ac.uk
Last updated: 12 February 2020
Email local part: Philip.Hazel
Email domain: gmail.com
Last updated: 15 June 2021
pcre/doc/html/pcre.html
View file @ aaac2477
......@@ -22,13 +22,12 @@ man page, in case the conversion went wrong.
</ul>
<br><a name="SEC1" href="#TOC1">PLEASE TAKE NOTE</a><br>
<P>
This document relates to PCRE releases that use the original API,
with library names libpcre, libpcre16, and libpcre32. January 2015 saw the
first release of a new API, known as PCRE2, with release numbers starting at
10.00 and library names libpcre2-8, libpcre2-16, and libpcre2-32. The old
libraries (now called PCRE1) are still being maintained for bug fixes, but
there will be no new development. New projects are advised to use the new PCRE2
libraries.
This document relates to PCRE releases that use the original API, with library
names libpcre, libpcre16, and libpcre32. January 2015 saw the first release of
a new API, known as PCRE2, with release numbers starting at 10.00 and library
names libpcre2-8, libpcre2-16, and libpcre2-32. The old libraries (now called
PCRE1) are now at end of life, and 8.45 is the final release. New projects are
advised to use the new PCRE2 libraries.
</P>
<br><a name="SEC2" href="#TOC1">INTRODUCTION</a><br>
<P>
......@@ -215,9 +214,9 @@ two digits 10, at the domain cam.ac.uk.
</P>
<br><a name="SEC6" href="#TOC1">REVISION</a><br>
<P>
Last updated: 10 February 2015
Last updated: 14 June 2021
<br>
Copyright &copy; 1997-2015 University of Cambridge.
Copyright &copy; 1997-2021 University of Cambridge.
<br>
<p>
Return to the <a href="index.html">PCRE index page</a>.
......
pcre/doc/html/pcreapi.html
View file @ aaac2477
......@@ -1718,7 +1718,7 @@ very long time, and so the <i>match_limit</i> value is also used in this case
<P>
The default value for the limit can be set when PCRE is built; the default
default is 10 million, which handles all but the most extreme cases. You can
override the default by suppling <b>pcre_exec()</b> with a <b>pcre_extra</b>
override the default by supplying <b>pcre_exec()</b> with a <b>pcre_extra</b>
block in which <i>match_limit</i> is set, and PCRE_EXTRA_MATCH_LIMIT is set in
the <i>flags</i> field. If the limit is exceeded, <b>pcre_exec()</b> returns
PCRE_ERROR_MATCHLIMIT.
......@@ -1749,7 +1749,7 @@ and is ignored, when matching is done using JIT compiled code.
<P>
The default value for <i>match_limit_recursion</i> can be set when PCRE is
built; the default default is the same value as the default for
<i>match_limit</i>. You can override the default by suppling <b>pcre_exec()</b>
<i>match_limit</i>. You can override the default by supplying <b>pcre_exec()</b>
with a <b>pcre_extra</b> block in which <i>match_limit_recursion</i> is set, and
PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the <i>flags</i> field. If the limit
is exceeded, <b>pcre_exec()</b> returns PCRE_ERROR_RECURSIONLIMIT.
......@@ -2063,10 +2063,10 @@ lookbehind. For example, consider the pattern
</pre>
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 <b>pcre_exec()</b> finds the first
the string "Mississippi" the first call to <b>pcre_exec()</b> finds the first
occurrence. If <b>pcre_exec()</b> 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
subject, namely "issippi", 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
<b>pcre_exec()</b> is passed the entire string again, but with <i>startoffset</i>
set to 4, it finds the second occurrence of "iss" because it is able to look
behind the starting point to discover that it is preceded by a letter.
......
pcre/doc/html/pcredemo.html
View file @ aaac2477
......@@ -161,7 +161,7 @@ if (rc &lt; 0)
return 1;
}
/* Match succeded */
/* Match succeeded */
printf("\nMatch succeeded at offset %d\n", ovector[0]);
......@@ -379,7 +379,7 @@ for (;;)
return 1;
}
/* Match succeded */
/* Match succeeded */
printf("\nMatch succeeded again at offset %d\n", ovector[0]);
......
pcre/doc/html/pcrejit.html
View file @ aaac2477
......@@ -299,7 +299,7 @@ recommended.
This is a suggestion for how a multithreaded program that needs to set up
non-default JIT stacks might operate:
<pre>
During thread initalization
During thread initialization
thread_local_var = pcre_jit_stack_alloc(...)
During thread exit
......
pcre/doc/html/pcrepattern.html
View file @ aaac2477
......@@ -655,7 +655,7 @@ recognized.
<P>
It is possible to restrict \R to match only CR, LF, or CRLF (instead of the
complete set of Unicode line endings) by setting the option PCRE_BSR_ANYCRLF
either at compile time or when the pattern is matched. (BSR is an abbrevation
either at compile time or when the pattern is matched. (BSR is an abbreviation
for "backslash R".) This can be made the default when PCRE is built; if this is
the case, the other behaviour can be requested via the PCRE_BSR_UNICODE option.
It is also possible to specify these settings by starting a pattern string with
......@@ -972,7 +972,7 @@ additional characters according to the following rules for ending a cluster:
3. Do not break Hangul (a Korean script) syllable sequences. Hangul characters
are of five types: L, V, T, LV, and LVT. An L character may be followed by an
L, V, LV, or LVT character; an LV or V character may be followed by a V or T
character; an LVT or T character may be follwed only by a T character.
character; an LVT or T character may be followed only by a T character.
</P>
<P>
4. Do not end before extending characters or spacing marks. Characters with
......@@ -3080,7 +3080,7 @@ successful match. Consider:
</pre>
If the subject is "aaaac...", after the first match attempt fails (starting at
the first character in the string), the starting point skips on to start the
next attempt at "c". Note that a possessive quantifer does not have the same
next attempt at "c". Note that a possessive quantifier does not have the same
effect as this example; although it would suppress backtracking during the
first match attempt, the second attempt would start at the second character
instead of skipping on to "c".
......
pcre/doc/html/pcresyntax.html
View file @ aaac2477
......@@ -157,7 +157,7 @@ is changed to use Unicode properties and they match many more characters.
Xan Alphanumeric: union of properties L and N
Xps POSIX space: property Z or tab, NL, VT, FF, CR
Xsp Perl space: property Z or tab, NL, VT, FF, CR
Xuc Univerally-named character: one that can be
Xuc Universally-named character: one that can be
represented by a Universal Character Name
Xwd Perl word: property Xan or underscore
</pre>
......
pcre/doc/pcre.3
View file @ aaac2477
.TH PCRE 3 "10 February 2015" "PCRE 8.37"
.TH PCRE 3 "14 June 2021" "PCRE 8.45"
.SH NAME
PCRE - Perl-compatible regular expressions (original API)
.SH "PLEASE TAKE NOTE"
.rs
.sp
This document relates to PCRE releases that use the original API,
with library names libpcre, libpcre16, and libpcre32. January 2015 saw the
first release of a new API, known as PCRE2, with release numbers starting at
10.00 and library names libpcre2-8, libpcre2-16, and libpcre2-32. The old
libraries (now called PCRE1) are still being maintained for bug fixes, but
there will be no new development. New projects are advised to use the new PCRE2
libraries.
This document relates to PCRE releases that use the original API, with library
names libpcre, libpcre16, and libpcre32. January 2015 saw the first release of
a new API, known as PCRE2, with release numbers starting at 10.00 and library
names libpcre2-8, libpcre2-16, and libpcre2-32. The old libraries (now called
PCRE1) are now at end of life, and 8.45 is the final release. New projects are
advised to use the new PCRE2 libraries.
.
.
.SH INTRODUCTION
......@@ -225,6 +224,6 @@ two digits 10, at the domain cam.ac.uk.
.rs
.sp
.nf
Last updated: 10 February 2015
Copyright (c) 1997-2015 University of Cambridge.
Last updated: 14 June 2021
Copyright (c) 1997-2021 University of Cambridge.
.fi
pcre/doc/pcre.txt
View file @ aaac2477
......@@ -21,9 +21,9 @@ PLEASE TAKE NOTE
library names libpcre, libpcre16, and libpcre32. January 2015 saw the
first release of a new API, known as PCRE2, with release numbers start-
ing at 10.00 and library names libpcre2-8, libpcre2-16, and
libpcre2-32. The old libraries (now called PCRE1) are still being main-
tained for bug fixes, but there will be no new development. New
projects are advised to use the new PCRE2 libraries.
libpcre2-32. The old libraries (now called PCRE1) are now at end of
life, and 8.45 is the final release. New projects are advised to use
the new PCRE2 libraries.
INTRODUCTION
......@@ -190,8 +190,8 @@ AUTHOR
REVISION
Last updated: 10 February 2015
Copyright (c) 1997-2015 University of Cambridge.
Last updated: 14 June 2021
Copyright (c) 1997-2021 University of Cambridge.
------------------------------------------------------------------------------
......@@ -3155,7 +3155,7 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION
The default value for the limit can be set when PCRE is built; the de-
fault default is 10 million, which handles all but the most extreme
cases. You can override the default by suppling pcre_exec() with a
cases. You can override the default by supplying pcre_exec() with a
pcre_extra block in which match_limit is set, and PCRE_EX-
TRA_MATCH_LIMIT is set in the flags field. If the limit is exceeded,
pcre_exec() returns PCRE_ERROR_MATCHLIMIT.
......@@ -3183,7 +3183,7 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION
The default value for match_limit_recursion can be set when PCRE is
built; the default default is the same value as the default for
match_limit. You can override the default by suppling pcre_exec() with
match_limit. You can override the default by supplying pcre_exec() with
a pcre_extra block in which match_limit_recursion is set, and PCRE_EX-
TRA_MATCH_LIMIT_RECURSION is set in the flags field. If the limit is
exceeded, pcre_exec() returns PCRE_ERROR_RECURSIONLIMIT.
......@@ -3475,9 +3475,9 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION
which finds occurrences of "iss" in the middle of words. (\B matches
only if the current position in the subject is not a word boundary.)
When applied to the string "Mississipi" the first call to pcre_exec()
When applied to the string "Mississippi" the first call to pcre_exec()
finds the first occurrence. If pcre_exec() is called again with just
the remainder of the subject, namely "issipi", it does not match, be-
the remainder of the subject, namely "issippi", it does not match, be-
cause \B is always false at the start of the subject, which is deemed
to be a word boundary. However, if pcre_exec() is passed the entire
string again, but with startoffset set to 4, it finds the second occur-
......@@ -5292,11 +5292,11 @@ BACKSLASH
It is possible to restrict \R to match only CR, LF, or CRLF (instead of
the complete set of Unicode line endings) by setting the option
PCRE_BSR_ANYCRLF either at compile time or when the pattern is matched.
(BSR is an abbrevation for "backslash R".) This can be made the default
when PCRE is built; if this is the case, the other behaviour can be re-
quested via the PCRE_BSR_UNICODE option. It is also possible to spec-
ify these settings by starting a pattern string with one of the follow-
ing sequences:
(BSR is an abbreviation for "backslash R".) This can be made the de-
fault when PCRE is built; if this is the case, the other behaviour can
be requested via the PCRE_BSR_UNICODE option. It is also possible to
specify these settings by starting a pattern string with one of the
following sequences:
(*BSR_ANYCRLF) CR, LF, or CRLF only
(*BSR_UNICODE) any Unicode newline sequence
......@@ -5488,8 +5488,8 @@ BACKSLASH
3. Do not break Hangul (a Korean script) syllable sequences. Hangul
characters are of five types: L, V, T, LV, and LVT. An L character may
be followed by an L, V, LV, or LVT character; an LV or V character may
be followed by a V or T character; an LVT or T character may be follwed
only by a T character.
be followed by a V or T character; an LVT or T character may be fol-
lowed only by a T character.
4. Do not end before extending characters or spacing marks. Characters
with the "mark" property always have the "extend" grapheme breaking
......@@ -7494,7 +7494,7 @@ BACKTRACKING CONTROL
If the subject is "aaaac...", after the first match attempt fails
(starting at the first character in the string), the starting point
skips on to start the next attempt at "c". Note that a possessive quan-
tifer does not have the same effect as this example; although it would
tifier does not have the same effect as this example; although it would
suppress backtracking during the first match attempt, the second at-
tempt would start at the second character instead of skipping on to
"c".
......@@ -7793,7 +7793,7 @@ PCRE SPECIAL CATEGORY PROPERTIES FOR \p and \P
Xan Alphanumeric: union of properties L and N
Xps POSIX space: property Z or tab, NL, VT, FF, CR
Xsp Perl space: property Z or tab, NL, VT, FF, CR
Xuc Univerally-named character: one that can be
Xuc Universally-named character: one that can be
represented by a Universal Character Name
Xwd Perl word: property Xan or underscore
......@@ -8571,7 +8571,7 @@ CONTROLLING THE JIT STACK
This is a suggestion for how a multithreaded program that needs to set
up non-default JIT stacks might operate:
During thread initalization
During thread initialization
thread_local_var = pcre_jit_stack_alloc(...)
During thread exit
......
pcre/doc/pcreapi.3
View file @ aaac2477
......@@ -1699,7 +1699,7 @@ very long time, and so the \fImatch_limit\fP value is also used in this case
.P
The default value for the limit can be set when PCRE is built; the default
default is 10 million, which handles all but the most extreme cases. You can
override the default by suppling \fBpcre_exec()\fP with a \fBpcre_extra\fP
override the default by supplying \fBpcre_exec()\fP with a \fBpcre_extra\fP
block in which \fImatch_limit\fP is set, and PCRE_EXTRA_MATCH_LIMIT is set in
the \fIflags\fP field. If the limit is exceeded, \fBpcre_exec()\fP returns
PCRE_ERROR_MATCHLIMIT.
......@@ -1726,7 +1726,7 @@ and is ignored, when matching is done using JIT compiled code.
.P
The default value for \fImatch_limit_recursion\fP can be set when PCRE is
built; the default default is the same value as the default for
\fImatch_limit\fP. You can override the default by suppling \fBpcre_exec()\fP
\fImatch_limit\fP. You can override the default by supplying \fBpcre_exec()\fP
with a \fBpcre_extra\fP block in which \fImatch_limit_recursion\fP is set, and
PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the \fIflags\fP field. If the limit
is exceeded, \fBpcre_exec()\fP returns PCRE_ERROR_RECURSIONLIMIT.
......@@ -2044,10 +2044,10 @@ lookbehind. For example, consider the pattern
.sp
which finds occurrences of "iss" in the middle of words. (\eB matches only if
the current position in the subject is not a word boundary.) When applied to
the string "Mississipi" the first call to \fBpcre_exec()\fP finds the first
the string "Mississippi" the first call to \fBpcre_exec()\fP finds the first
occurrence. If \fBpcre_exec()\fP is called again with just the remainder of the
subject, namely "issipi", it does not match, because \eB is always false at the
start of the subject, which is deemed to be a word boundary. However, if
subject, namely "issippi", it does not match, because \eB is always false at
the start of the subject, which is deemed to be a word boundary. However, if
\fBpcre_exec()\fP is passed the entire string again, but with \fIstartoffset\fP
set to 4, it finds the second occurrence of "iss" because it is able to look
behind the starting point to discover that it is preceded by a letter.
......
pcre/doc/pcredemo.3
View file @ aaac2477
......@@ -161,7 +161,7 @@ if (rc < 0)
return 1;
}
/* Match succeded */
/* Match succeeded */
printf("\enMatch succeeded at offset %d\en", ovector[0]);
......@@ -379,7 +379,7 @@ for (;;)
return 1;
}
/* Match succeded */
/* Match succeeded */
printf("\enMatch succeeded again at offset %d\en", ovector[0]);
......
pcre/doc/pcrejit.3
View file @ aaac2477
......@@ -285,7 +285,7 @@ recommended.
This is a suggestion for how a multithreaded program that needs to set up
non-default JIT stacks might operate:
.sp
During thread initalization
During thread initialization
thread_local_var = pcre_jit_stack_alloc(...)
.sp
During thread exit
......
pcre/doc/pcrepattern.3
View file @ aaac2477
......@@ -656,7 +656,7 @@ recognized.
.P
It is possible to restrict \eR to match only CR, LF, or CRLF (instead of the
complete set of Unicode line endings) by setting the option PCRE_BSR_ANYCRLF
either at compile time or when the pattern is matched. (BSR is an abbrevation
either at compile time or when the pattern is matched. (BSR is an abbreviation
for "backslash R".) This can be made the default when PCRE is built; if this is
the case, the other behaviour can be requested via the PCRE_BSR_UNICODE option.
It is also possible to specify these settings by starting a pattern string with
......@@ -968,7 +968,7 @@ additional characters according to the following rules for ending a cluster:
3. Do not break Hangul (a Korean script) syllable sequences. Hangul characters
are of five types: L, V, T, LV, and LVT. An L character may be followed by an
L, V, LV, or LVT character; an LV or V character may be followed by a V or T
character; an LVT or T character may be follwed only by a T character.
character; an LVT or T character may be followed only by a T character.
.P
4. Do not end before extending characters or spacing marks. Characters with
the "mark" property always have the "extend" grapheme breaking property.
......@@ -3115,7 +3115,7 @@ successful match. Consider:
.sp
If the subject is "aaaac...", after the first match attempt fails (starting at
the first character in the string), the starting point skips on to start the
next attempt at "c". Note that a possessive quantifer does not have the same
next attempt at "c". Note that a possessive quantifier does not have the same
effect as this example; although it would suppress backtracking during the
first match attempt, the second attempt would start at the second character
instead of skipping on to "c".
......
pcre/doc/pcresyntax.3
View file @ aaac2477
......@@ -123,7 +123,7 @@ is changed to use Unicode properties and they match many more characters.
Xan Alphanumeric: union of properties L and N
Xps POSIX space: property Z or tab, NL, VT, FF, CR
Xsp Perl space: property Z or tab, NL, VT, FF, CR
Xuc Univerally-named character: one that can be
Xuc Universally-named character: one that can be
represented by a Universal Character Name
Xwd Perl word: property Xan or underscore
.sp
......
pcre/pcre_compile.c
View file @ aaac2477
......@@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2020 University of Cambridge
Copyright (c) 1997-2021 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
......@@ -9102,6 +9102,8 @@ pcre_uchar cworkspace[COMPILE_WORK_SIZE];
similar way to cworkspace, it can be expanded using malloc() if necessary. */
named_group named_groups[NAMED_GROUP_LIST_SIZE];
cd->named_groups = named_groups;
cd->named_group_list_size = NAMED_GROUP_LIST_SIZE;
/* Set this early so that early errors get offset 0. */
......@@ -9375,8 +9377,6 @@ cd->hwm = cworkspace;
cd->iscondassert = FALSE;
cd->start_workspace = cworkspace;
cd->workspace_size = COMPILE_WORK_SIZE;
cd->named_groups = named_groups;
cd->named_group_list_size = NAMED_GROUP_LIST_SIZE;
cd->start_pattern = (const pcre_uchar *)pattern;
cd->end_pattern = (const pcre_uchar *)(pattern + STRLEN_UC((const pcre_uchar *)pattern));
cd->req_varyopt = 0;
......@@ -9487,6 +9487,7 @@ if (cd->names_found > 0)
add_name(cd, ng->name, ng->length, ng->number);
if (cd->named_group_list_size > NAMED_GROUP_LIST_SIZE)
(PUBL(free))((void *)cd->named_groups);
cd->named_group_list_size = 0; /* So we don't free it twice */
}
/* Set up a starting, non-extracting bracket, then compile the expression. On
......@@ -9637,6 +9638,8 @@ if (errorcode != 0)
{
(PUBL(free))(re);
PCRE_EARLY_ERROR_RETURN:
if (cd->named_group_list_size > NAMED_GROUP_LIST_SIZE)
(PUBL(free))((void *)cd->named_groups);
*erroroffset = (int)(ptr - (const pcre_uchar *)pattern);
PCRE_EARLY_ERROR_RETURN2:
*errorptr = find_error_text(errorcode);
......
pcre/pcre_exec.c
View file @ aaac2477
......@@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2018 University of Cambridge
Copyright (c) 1997-2021 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
......@@ -764,7 +764,7 @@ for (;;)
md->mark = NULL; /* In case previously set by assertion */
RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode] + ecode[1], offset_top, md,
eptrb, RM55);
if ((rrc == MATCH_MATCH || rrc == MATCH_ACCEPT) &&
if ((rrc == MATCH_MATCH || rrc == MATCH_ACCEPT || rrc == MATCH_KETRPOS) &&
md->mark == NULL) md->mark = ecode + 2;
/* A return of MATCH_SKIP_ARG means that matching failed at SKIP with an
......
pcre/pcredemo.c
View file @ aaac2477
......@@ -144,7 +144,7 @@ if (rc < 0)
return 1;
}
/* Match succeded */
/* Match succeeded */
printf("\nMatch succeeded at offset %d\n", ovector[0]);
......@@ -362,7 +362,7 @@ for (;;)
return 1;
}
/* Match succeded */
/* Match succeeded */
printf("\nMatch succeeded again at offset %d\n", ovector[0]);
......
pcre/testdata/testinput1
View file @ aaac2477
......@@ -5757,4 +5757,7 @@ AbcdCBefgBhiBqz
/(?&word)* \. (?<word> \w+ )/xi
pokus.hokus
/(?:A(*:X))*+/K
A
/-- End of testinput1 --/
pcre/testdata/testoutput1
View file @ aaac2477
......@@ -9470,4 +9470,9 @@ No match
0: pokus.hokus
1: hokus
/(?:A(*:X))*+/K
A
0: A
MK: X
/-- End of testinput1 --/
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7