mirrors/php-src
0
0
Fork 0
mirror of https://github.com/php/php-src.git synced 2024-11-28 04:14:26 +08:00
Code Issues Packages Projects Releases Wiki Activity

upgrade PCRE to version 7.2 RC3

Browse Source 
# I'll update to the final version early next week when its released
This commit is contained in:
Nuno Lopes 2007-06-15 19:09:26 +00:00
parent 17db5db759
commit 4e51d2ec73
77 changed files with 8713 additions and 10676 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
NEWS
View File

@ -1,6 +1,7 @@
PHP NEWS
|||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
?? ??? 2007, PHP 5.2.4
- Upgraded PCRE to version 7.2 (Nuno)
- HTTP 500 is sent to browser in case of PHP error instead of blank page.
(Dmitry, Andrei Nigmatulin)
- Improved fix for MOPB-03-2007. (Ilia)

2
ext/pcre/config.w32
View File

@ -5,7 +5,7 @@ ARG_WITH("pcre-regex", "Perl Compatible Regular Expressions", "yes");
if (PHP_PCRE_REGEX == "yes") {
EXTENSION("pcre", "php_pcre.c", PHP_PCRE_REGEX_SHARED,
"-DEXPORT= -DNEWLINE=10 -DSUPPORT_UTF8 -DSUPPORT_UCP -DLINK_SIZE=2 -DPOSIX_MALLOC_THRESHOLD=10 -DMATCH_LIMIT=10000000 -DMATCH_LIMIT_RECURSION=10000000 -DMAX_NAME_SIZE=32 -DMAX_NAME_COUNT=10000 -DMAX_DUPLENGTH=30000 -DEBCDIC=0 -DNO_RECURSE -Iext/pcre/pcrelib");
"-DNO_RECURSE -Iext/pcre/pcrelib");
ADD_SOURCES("ext/pcre/pcrelib", "pcre_chartables.c pcre_ucp_searchfuncs.c pcre_compile.c pcre_config.c pcre_exec.c pcre_fullinfo.c pcre_get.c pcre_globals.c pcre_info.c pcre_maketables.c pcre_newline.c pcre_ord2utf8.c pcre_refcount.c pcre_study.c pcre_tables.c pcre_try_flipped.c pcre_valid_utf8.c pcre_version.c pcre_xclass.c", "pcre");
ADD_DEF_FILE("ext\\pcre\\php_pcre.def");

4
ext/pcre/config0.m4
View File

@ -13,7 +13,7 @@ PHP_ARG_WITH(pcre-regex,for PCRE support,
if test "$PHP_PCRE_REGEX" != "no"; then
if test "$PHP_PCRE_REGEX" = "yes"; then
PHP_NEW_EXTENSION(pcre, pcrelib/pcre_chartables.c pcrelib/pcre_ucp_searchfuncs.c pcrelib/pcre_compile.c pcrelib/pcre_config.c pcrelib/pcre_exec.c pcrelib/pcre_fullinfo.c pcrelib/pcre_get.c pcrelib/pcre_globals.c pcrelib/pcre_info.c pcrelib/pcre_maketables.c pcrelib/pcre_newline.c pcrelib/pcre_ord2utf8.c pcrelib/pcre_refcount.c pcrelib/pcre_study.c pcrelib/pcre_tables.c pcrelib/pcre_try_flipped.c pcrelib/pcre_valid_utf8.c pcrelib/pcre_version.c pcrelib/pcre_xclass.c php_pcre.c, $ext_shared,,-DEXPORT= -DNEWLINE=10 -DSUPPORT_UTF8 -DSUPPORT_UCP -DLINK_SIZE=2 -DPOSIX_MALLOC_THRESHOLD=10 -DMATCH_LIMIT=10000000 -DMATCH_LIMIT_RECURSION=10000000 -DMAX_NAME_SIZE=32 -DMAX_NAME_COUNT=10000 -DMAX_DUPLENGTH=30000 -DEBCDIC=0 -I@ext_srcdir@/pcrelib)
PHP_NEW_EXTENSION(pcre, pcrelib/pcre_chartables.c pcrelib/pcre_ucp_searchfuncs.c pcrelib/pcre_compile.c pcrelib/pcre_config.c pcrelib/pcre_exec.c pcrelib/pcre_fullinfo.c pcrelib/pcre_get.c pcrelib/pcre_globals.c pcrelib/pcre_info.c pcrelib/pcre_maketables.c pcrelib/pcre_newline.c pcrelib/pcre_ord2utf8.c pcrelib/pcre_refcount.c pcrelib/pcre_study.c pcrelib/pcre_tables.c pcrelib/pcre_try_flipped.c pcrelib/pcre_valid_utf8.c pcrelib/pcre_version.c pcrelib/pcre_xclass.c php_pcre.c, $ext_shared,,-I@ext_srcdir@/pcrelib)
PHP_ADD_BUILD_DIR($ext_builddir/pcrelib)
PHP_INSTALL_HEADERS([ext/pcre], [php_pcre.h pcrelib/])
AC_DEFINE(HAVE_BUNDLED_PCRE, 1, [ ])
@ -51,7 +51,7 @@ if test "$PHP_PCRE_REGEX" != "no"; then
AC_DEFINE(HAVE_PCRE, 1, [ ])
PHP_ADD_INCLUDE($PCRE_INCDIR)
PHP_NEW_EXTENSION(pcre, php_pcre.c, $ext_shared,,-DEXPORT= -DNEWLINE=10 -DSUPPORT_UTF8 -DSUPPORT_UCP -DLINK_SIZE=2 -DPOSIX_MALLOC_THRESHOLD=10 -DMATCH_LIMIT=10000000 -DMATCH_LIMIT_RECURSION=10000000 -DMAX_NAME_SIZE=32 -DMAX_NAME_COUNT=10000 -DMAX_DUPLENGTH=30000)
PHP_NEW_EXTENSION(pcre, php_pcre.c, $ext_shared)
PHP_INSTALL_HEADERS([ext/pcre], [php_pcre.h])
PHP_SUBST(PCRE_SHARED_LIBADD)
fi

6
ext/pcre/pcrelib/AUTHORS
View File

@ -6,9 +6,9 @@ Email local part: ph10
Email domain: cam.ac.uk
University of Cambridge Computing Service,
Cambridge, England. Phone: +44 1223 334714.
Cambridge, England.
Copyright (c) 1997-2006 University of Cambridge
Copyright (c) 1997-2007 University of Cambridge
All rights reserved
@ -17,7 +17,7 @@ THE C++ WRAPPER LIBRARY
Written by: Google Inc.
Copyright (c) 2006 Google Inc
Copyright (c) 2007 Google Inc
All rights reserved
####

65
ext/pcre/pcrelib/COPYING
View File

@ -1,68 +1,5 @@
PCRE LICENCE
------------
PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Release 7 of PCRE is distributed under the terms of the "BSD" licence, as
specified below. The documentation for PCRE, supplied in the "doc"
directory, is distributed under the same terms as the software itself.
The basic library functions are written in C and are freestanding. Also
included in the distribution is a set of C++ wrapper functions.
THE BASIC LIBRARY FUNCTIONS
---------------------------
Written by: Philip Hazel
Email local part: ph10
Email domain: cam.ac.uk
University of Cambridge Computing Service,
Cambridge, England. Phone: +44 1223 334714.
Copyright (c) 1997-2006 University of Cambridge
All rights reserved.
THE C++ WRAPPER FUNCTIONS
-------------------------
Contributed by: Google Inc.
Copyright (c) 2006, Google Inc.
All rights reserved.
THE "BSD" LICENCE
-----------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the name of Google
Inc. nor the names of their contributors may be used to endorse or
promote products derived from this software without specific prior
written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
Please see the file LICENCE in the PCRE distribution for licensing details.
End

220
ext/pcre/pcrelib/ChangeLog
View File

@ -1,6 +1,226 @@
ChangeLog for PCRE
------------------
Version 7.2 13-June-07
---------------------
1. If the fr_FR locale cannot be found for test 3, try the "french" locale,
which is apparently normally available under Windows.
2. Re-jig the pcregrep tests with different newline settings in an attempt
to make them independent of the local environment's newline setting.
3. Add code to configure.ac to remove -g from the CFLAGS default settings.
4. Some of the "internals" tests were previously cut out when the link size
was not 2, because the output contained actual offsets. The recent new
"Z" feature of pcretest means that these can be cut out, making the tests
usable with all link sizes.
5. Implemented Stan Switzer's goto replacement for longjmp() when not using
stack recursion. This gives a massive performance boost under BSD, but just
a small improvement under Linux. However, it saves one field in the frame
in all cases.
6. Added more features from the forthcoming Perl 5.10:
(a) (?-n) (where n is a string of digits) is a relative subroutine or
recursion call. It refers to the nth most recently opened parentheses.
(b) (?+n) is also a relative subroutine call; it refers to the nth next
to be opened parentheses.
(c) Conditions that refer to capturing parentheses can be specified
relatively, for example, (?(-2)... or (?(+3)...
(d) \K resets the start of the current match so that everything before
is not part of it.
(e) \k{name} is synonymous with \k<name> and \k'name' (.NET compatible).
(f) \g{name} is another synonym - part of Perl 5.10's unification of
reference syntax.
(g) (?| introduces a group in which the numbering of parentheses in each
alternative starts with the same number.
(h) \h, \H, \v, and \V match horizontal and vertical whitespace.
7. Added two new calls to pcre_fullinfo(): PCRE_INFO_OKPARTIAL and
PCRE_INFO_JCHANGED.
8. A pattern such as (.*(.)?)* caused pcre_exec() to fail by either not
terminating or by crashing. Diagnosed by Viktor Griph; it was in the code
for detecting groups that can match an empty string.
9. A pattern with a very large number of alternatives (more than several
hundred) was running out of internal workspace during the pre-compile
phase, where pcre_compile() figures out how much memory will be needed. A
bit of new cunning has reduced the workspace needed for groups with
alternatives. The 1000-alternative test pattern now uses 12 bytes of
workspace instead of running out of the 4096 that are available.
10. Inserted some missing (unsigned int) casts to get rid of compiler warnings.
11. Applied patch from Google to remove an optimization that didn't quite work.
The report of the bug said:
pcrecpp::RE("a*").FullMatch("aaa") matches, while
pcrecpp::RE("a*?").FullMatch("aaa") does not, and
pcrecpp::RE("a*?\\z").FullMatch("aaa") does again.
Version 7.1 24-Apr-07
---------------------
1. Applied Bob Rossi and Daniel G's patches to convert the build system to one
that is more "standard", making use of automake and other Autotools. There
is some re-arrangement of the files and adjustment of comments consequent
on this.
2. Part of the patch fixed a problem with the pcregrep tests. The test of -r
for recursive directory scanning broke on some systems because the files
are not scanned in any specific order and on different systems the order
was different. A call to "sort" has been inserted into RunGrepTest for the
approprate test as a short-term fix. In the longer term there may be an
alternative.
3. I had an email from Eric Raymond about problems translating some of PCRE's
man pages to HTML (despite the fact that I distribute HTML pages, some
people do their own conversions for various reasons). The problems
concerned the use of low-level troff macros .br and .in. I have therefore
removed all such uses from the man pages (some were redundant, some could
be replaced by .nf/.fi pairs). The 132html script that I use to generate
HTML has been updated to handle .nf/.fi and to complain if it encounters
.br or .in.
4. Updated comments in configure.ac that get placed in config.h.in and also
arranged for config.h to be included in the distribution, with the name
config.h.generic, for the benefit of those who have to compile without
Autotools (compare pcre.h, which is now distributed as pcre.h.generic).
5. Updated the support (such as it is) for Virtual Pascal, thanks to Stefan
Weber: (1) pcre_internal.h was missing some function renames; (2) updated
makevp.bat for the current PCRE, using the additional files
makevp_c.txt, makevp_l.txt, and pcregexp.pas.
6. A Windows user reported a minor discrepancy with test 2, which turned out
to be caused by a trailing space on an input line that had got lost in his
copy. The trailing space was an accident, so I've just removed it.
7. Add -Wl,-R... flags in pcre-config.in for *BSD* systems, as I'm told
that is needed.
8. Mark ucp_table (in ucptable.h) and ucp_gentype (in pcre_ucp_searchfuncs.c)
as "const" (a) because they are and (b) because it helps the PHP
maintainers who have recently made a script to detect big data structures
in the php code that should be moved to the .rodata section. I remembered
to update Builducptable as well, so it won't revert if ucptable.h is ever
re-created.
9. Added some extra #ifdef SUPPORT_UTF8 conditionals into pcretest.c,
pcre_printint.src, pcre_compile.c, pcre_study.c, and pcre_tables.c, in
order to be able to cut out the UTF-8 tables in the latter when UTF-8
support is not required. This saves 1.5-2K of code, which is important in
some applications.
Later: more #ifdefs are needed in pcre_ord2utf8.c and pcre_valid_utf8.c
so as not to refer to the tables, even though these functions will never be
called when UTF-8 support is disabled. Otherwise there are problems with a
shared library.
10. Fixed two bugs in the emulated memmove() function in pcre_internal.h:
(a) It was defining its arguments as char * instead of void *.
(b) It was assuming that all moves were upwards in memory; this was true
a long time ago when I wrote it, but is no longer the case.
The emulated memove() is provided for those environments that have neither
memmove() nor bcopy(). I didn't think anyone used it these days, but that
is clearly not the case, as these two bugs were recently reported.
11. The script PrepareRelease is now distributed: it calls 132html, CleanTxt,
and Detrail to create the HTML documentation, the .txt form of the man
pages, and it removes trailing spaces from listed files. It also creates
pcre.h.generic and config.h.generic from pcre.h and config.h. In the latter
case, it wraps all the #defines with #ifndefs. This script should be run
before "make dist".
12. Fixed two fairly obscure bugs concerned with quantified caseless matching
with Unicode property support.
(a) For a maximizing quantifier, if the two different cases of the
character were of different lengths in their UTF-8 codings (there are
some cases like this - I found 11), and the matching function had to
back up over a mixture of the two cases, it incorrectly assumed they
were both the same length.
(b) When PCRE was configured to use the heap rather than the stack for
recursion during matching, it was not correctly preserving the data for
the other case of a UTF-8 character when checking ahead for a match
while processing a minimizing repeat. If the check also involved
matching a wide character, but failed, corruption could cause an
erroneous result when trying to check for a repeat of the original
character.
13. Some tidying changes to the testing mechanism:
(a) The RunTest script now detects the internal link size and whether there
is UTF-8 and UCP support by running ./pcretest -C instead of relying on
values substituted by "configure". (The RunGrepTest script already did
this for UTF-8.) The configure.ac script no longer substitutes the
relevant variables.
(b) The debugging options /B and /D in pcretest show the compiled bytecode
with length and offset values. This means that the output is different
for different internal link sizes. Test 2 is skipped for link sizes
other than 2 because of this, bypassing the problem. Unfortunately,
there was also a test in test 3 (the locale tests) that used /B and
failed for link sizes other than 2. Rather than cut the whole test out,
I have added a new /Z option to pcretest that replaces the length and
offset values with spaces. This is now used to make test 3 independent
of link size. (Test 2 will be tidied up later.)
14. If erroroffset was passed as NULL to pcre_compile, it provoked a
segmentation fault instead of returning the appropriate error message.
15. In multiline mode when the newline sequence was set to "any", the pattern
^$ would give a match between the \r and \n of a subject such as "A\r\nB".
This doesn't seem right; it now treats the CRLF combination as the line
ending, and so does not match in that case. It's only a pattern such as ^$
that would hit this one: something like ^ABC$ would have failed after \r
and then tried again after \r\n.
16. Changed the comparison command for RunGrepTest from "diff -u" to "diff -ub"
in an attempt to make files that differ only in their line terminators
compare equal. This works on Linux.
17. Under certain error circumstances pcregrep might try to free random memory
as it exited. This is now fixed, thanks to valgrind.
19. In pcretest, if the pattern /(?m)^$/g<any> was matched against the string
"abc\r\n\r\n", it found an unwanted second match after the second \r. This
was because its rules for how to advance for /g after matching an empty
string at the end of a line did not allow for this case. They now check for
it specially.
20. pcretest is supposed to handle patterns and data of any length, by
extending its buffers when necessary. It was getting this wrong when the
buffer for a data line had to be extended.
21. Added PCRE_NEWLINE_ANYCRLF which is like ANY, but matches only CR, LF, or
CRLF as a newline sequence.
22. Code for handling Unicode properties in pcre_dfa_exec() wasn't being cut
out by #ifdef SUPPORT_UCP. This did no harm, as it could never be used, but
I have nevertheless tidied it up.
23. Added some casts to kill warnings from HP-UX ia64 compiler.
24. Added a man page for pcre-config.
Version 7.0 19-Dec-06
---------------------

7
ext/pcre/pcrelib/doc/Tech.Notes → ext/pcre/pcrelib/HACKING
View File

@ -129,13 +129,18 @@ These items are all just one byte long
OP_ANYBYTE match any single byte, even in UTF-8 mode
OP_SOD match start of data: \A
OP_SOM, start of match (subject + offset): \G
OP_SET_SOM, set start of match (\K)
OP_CIRC ^ (start of data, or after \n in multiline)
OP_NOT_WORD_BOUNDARY \W
OP_WORD_BOUNDARY \w
OP_NOT_DIGIT \D
OP_DIGIT \d
OP_NOT_HSPACE \H
OP_HSPACE \h
OP_NOT_WHITESPACE \S
OP_WHITESPACE \s
OP_NOT_VSPACE \V
OP_VSPACE \v
OP_NOT_WORDCHAR \W
OP_WORDCHAR \w
OP_EODN match end of data or \n at end: \Z
@ -399,4 +404,4 @@ at compile time, and so does not cause anything to be put into the compiled
data.
Philip Hazel
November 2006
June 2007

6
ext/pcre/pcrelib/LICENCE
View File

@ -20,9 +20,9 @@ Email local part: ph10
Email domain: cam.ac.uk
University of Cambridge Computing Service,
Cambridge, England. Phone: +44 1223 334714.
Cambridge, England.
Copyright (c) 1997-2006 University of Cambridge
Copyright (c) 1997-2007 University of Cambridge
All rights reserved.
@ -31,7 +31,7 @@ THE C++ WRAPPER FUNCTIONS
Contributed by: Google Inc.
Copyright (c) 2006, Google Inc.
Copyright (c) 2007, Google Inc.
All rights reserved.

63
ext/pcre/pcrelib/NEWS
View File

@ -1,7 +1,68 @@
News about PCRE releases
------------------------
Release 7.0 23-Nov-06
Release 7.2 13-Jun-07
---------------------
WARNING: saved patterns that were compiled by earlier versions of PCRE must be
recompiled for use with 7.2 (necessitated by the addition of \K, \h, \H, \v,
and \V).
Correction to the notes for 7.1: the note about shared libraries for Windows is
wrong. Previously, three libraries were built, but each could function
independently. For example, the pcreposix library also included all the
functions from the basic pcre library. The change is that the three libraries
are no longer independent. They are like the Unix libraries. To use the
pcreposix functions, for example, you need to link with both the pcreposix and
the basic pcre library.
Some more features from Perl 5.10 have been added:
(?-n) and (?+n) relative references for recursion and subroutines.
(?(-n) and (?(+n) relative references as conditions.
\k{name} and \g{name} are synonyms for \k<name>.
\K to reset the start of the matched string; for example, (foo)\Kbar
matches bar preceded by foo, but only sets bar as the matched string.
(?| introduces a group where the capturing parentheses in each alternative
start from the same number; for example, (?|(abc)|(xyz)) sets capturing
parentheses number 1 in both cases.
\h, \H, \v, \V match horizontal and vertical whitespace, respectively.
Release 7.1 24-Apr-07
---------------------
There is only one new feature in this release: a linebreak setting of
PCRE_NEWLINE_ANYCRLF. It is a cut-down version of PCRE_NEWLINE_ANY, which
recognizes only CRLF, CR, and LF as linebreaks.
A few bugs are fixed (see ChangeLog for details), but the major change is a
complete re-implementation of the build system. This now has full Autotools
support and so is now "standard" in some sense. It should help with compiling
PCRE in a wide variety of environments.
NOTE: when building shared libraries for Windows, three dlls are now built,
called libpcre, libpcreposix, and libpcrecpp. Previously, everything was
included in a single dll.
Another important change is that the dftables auxiliary program is no longer
compiled and run at "make" time by default. Instead, a default set of character
tables (assuming ASCII coding) is used. If you want to use dftables to generate
the character tables as previously, add --enable-rebuild-chartables to the
"configure" command. You must do this if you are compiling PCRE to run on a
system that uses EBCDIC code.
There is a discussion about character tables in the README file. The default is
not to use dftables so that that there is no problem when cross-compiling.
Release 7.0 19-Dec-06
---------------------
This release has a new major number because there have been some internal

343
ext/pcre/pcrelib/NON-UNIX-USE
View File

@ -1,128 +1,121 @@
Compiling PCRE on non-Unix systems
----------------------------------
See below for comments on Cygwin or MinGW and OpenVMS usage. I (Philip Hazel)
have no knowledge of Windows or VMS sytems and how their libraries work. The
items in the PCRE Makefile that relate to anything other than Unix-like systems
have been contributed by PCRE users. There are some other comments and files in
the Contrib directory on the ftp site that you may find useful. See
This document contains the following sections:
General
Generic instructions for the PCRE C library
The C++ wrapper functions
Building for virtual Pascal
Comments about Win32 builds
Building under Windows with BCC5.5
Building PCRE on OpenVMS
GENERAL
I (Philip Hazel) have no knowledge of Windows or VMS sytems and how their
libraries work. The items in the PCRE distribution and Makefile that relate to
anything other than Unix-like systems are untested by me.
There are some other comments and files in the Contrib directory on the ftp
site that you may find useful. See
ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/Contrib
If you want to compile PCRE for a non-Unix system (or perhaps, more strictly,
for a system that does not support "configure" and "make" files), note that
the basic PCRE library consists entirely of code written in Standard C, and so
should compile successfully on any system that has a Standard C compiler and
library. The C++ wrapper functions are a separate issue (see below).
If you want to compile PCRE for a non-Unix system (especially for a system that
does not support "configure" and "make" files), note that the basic PCRE
library consists entirely of code written in Standard C, and so should compile
successfully on any system that has a Standard C compiler and library. The C++
wrapper functions are a separate issue (see below).
The PCRE distribution contains some experimental support for "cmake", but this
is incomplete and not documented. However if you are a "cmake" user you might
like to try building with "cmake".
GENERIC INSTRUCTIONS FOR THE C LIBRARY
GENERIC INSTRUCTIONS FOR THE PCRE C LIBRARY
The following are generic comments about building PCRE. The interspersed
indented commands are suggestions from Mark Tetrode as to which commands you
might use on a Windows system to build a static library.
The following are generic comments about building the PCRE C library "by hand".
(1) Copy or rename the file config.h.in as config.h, and change the macros that
define HAVE_STRERROR and HAVE_MEMMOVE to define them as 1 rather than 0.
Unfortunately, because of the way Unix autoconf works, the default setting has
to be 0. You may also want to make changes to other macros in config.h. In
particular, if you want to force a specific value for newline, you can define
the NEWLINE macro. The default is to use '\n', thereby using whatever value
your compiler gives to '\n'.
(1) Copy or rename the file config.h.generic as config.h, and edit the macro
settings that it contains to whatever is appropriate for your environment.
In particular, if you want to force a specific value for newline, you can
define the NEWLINE macro.
rem Mark Tetrode's commands
copy config.h.in config.h
rem Use write, because notepad cannot handle UNIX files. Change values.
write config.h
An alternative approach is not to edit config.h, but to use -D on the
compiler command line to make any changes that you need.
(2) Compile dftables.c as a stand-alone program, and then run it with
the single argument "pcre_chartables.c". This generates a set of standard
character tables and writes them to that file.
NOTE: There have been occasions when the way in which certain parameters in
config.h are used has changed between releases. (In the configure/make
world, this is handled automatically.) When upgrading to a new release, you
are strongly advised to review config.h.generic before re-using what you
had previously.
rem Mark Tetrode's commands
rem Compile & run
cl -DSUPPORT_UTF8 -DSUPPORT_UCP dftables.c
dftables.exe pcre_chartables.c
(2) Copy or rename the file pcre.h.generic as pcre.h.
(3) Compile the following source files:
(3) EITHER:
Copy or rename file pcre_chartables.c.dist as pcre_chartables.c.
pcre_chartables.c
pcre_compile.c
pcre_config.c
pcre_dfa_exec.c
pcre_exec.c
pcre_fullinfo.c
pcre_get.c
pcre_globals.c
pcre_info.c
pcre_maketables.c
pcre_newline.c
pcre_ord2utf8.c
pcre_refcount.c
pcre_study.c
pcre_tables.c
pcre_try_flipped.c
pcre_ucp_searchfuncs.c
pcre_valid_utf8.c
pcre_version.c
pcre_xclass.c
OR:
Compile dftables.c as a stand-alone program, and then run it with the
single argument "pcre_chartables.c". This generates a set of standard
character tables and writes them to that file. The tables are generated
using the default C locale for your system. If you want to use a locale
that is specified by LC_xxx environment variables, add the -L option to
the dftables command. You must use this method if you are building on
a system that uses EBCDIC code.
and link them all together into an object library in whichever form your system
keeps such libraries. This is the pcre C library. If your system has static and
shared libraries, you may have to do this once for each type.
The tables in pcre_chartables.c are defaults. The caller of PCRE can
specify alternative tables at run time.
rem These comments are out-of-date, referring to a previous release which
rem had fewer source files. Replace with the file names from above.
rem Mark Tetrode's commands, for a static library
rem Compile & lib
cl -DSUPPORT_UTF8 -DSUPPORT_UCP -DPOSIX_MALLOC_THRESHOLD=10 /c maketables.c get.c study.c pcre.c
lib /OUT:pcre.lib maketables.obj get.obj study.obj pcre.obj
(4) Compile the following source files:
(4) Similarly, compile pcreposix.c and link it (on its own) as the pcreposix
library.
pcre_chartables.c
pcre_compile.c
pcre_config.c
pcre_dfa_exec.c
pcre_exec.c
pcre_fullinfo.c
pcre_get.c
pcre_globals.c
pcre_info.c
pcre_maketables.c
pcre_newline.c
pcre_ord2utf8.c
pcre_refcount.c
pcre_study.c
pcre_tables.c
pcre_try_flipped.c
pcre_ucp_searchfuncs.c
pcre_valid_utf8.c
pcre_version.c
pcre_xclass.c
rem Mark Tetrode's commands, for a static library
rem Compile & lib
cl -DSUPPORT_UTF8 -DSUPPORT_UCP -DPOSIX_MALLOC_THRESHOLD=10 /c pcreposix.c
lib /OUT:pcreposix.lib pcreposix.obj
Now link them all together into an object library in whichever form your
system keeps such libraries. This is the basic PCRE C library. If your
system has static and shared libraries, you may have to do this once for
each type.
(5) Compile the test program pcretest.c. This needs the functions in the
pcre and pcreposix libraries when linking.
(5) Similarly, compile pcreposix.c and link it (on its own) as the pcreposix
library.
rem Mark Tetrode's commands
rem compile & link
cl /F0x400000 pcretest.c pcre.lib pcreposix.lib
(6) Compile the test program pcretest.c. This needs the functions in the
pcre and pcreposix libraries when linking.
(6) Run pcretest on the testinput files in the testdata directory, and check
that the output matches the corresponding testoutput files. Note that the
supplied files are in Unix format, with just LF characters as line terminators.
You may need to edit them to change this if your system uses a different
convention.
(7) Run pcretest on the testinput files in the testdata directory, and check
that the output matches the corresponding testoutput files. Note that the
supplied files are in Unix format, with just LF characters as line
terminators. You may need to edit them to change this if your system uses a
different convention.
rem Mark Tetrode's commands
pcretest testdata\testinput1 testdata\myoutput1
windiff testdata\testoutput1 testdata\myoutput1
pcretest -i testdata\testinput2 testdata\myoutput2
windiff testdata\testoutput2 testdata\myoutput2
pcretest testdata\testinput3 testdata\myoutput3
windiff testdata\testoutput3 testdata\myoutput3
pcretest testdata\testinput4 testdata\myoutput4
windiff testdata\testoutput4 testdata\myoutput4
pcretest testdata\testinput5 testdata\myoutput5
windiff testdata\testoutput5 testdata\myoutput5
pcretest testdata\testinput6 testdata\myoutput6
windiff testdata\testoutput6 testdata\myoutput6
Note that there are now three more tests (7, 8, 9) that did not exist when Mark
wrote those comments. The test the new pcre_dfa_exec() function.
(7) If you want to use the pcregrep command, compile and link pcregrep.c; it
uses only the basic PCRE library.
(8) If you want to use the pcregrep command, compile and link pcregrep.c; it
uses only the basic PCRE library (it does not need the pcreposix library).
THE C++ WRAPPER FUNCTIONS
The PCRE distribution now contains some C++ wrapper functions and tests,
The PCRE distribution also contains some C++ wrapper functions and tests,
contributed by Google Inc. On a system that can use "configure" and "make",
the functions are automatically built into a library called pcrecpp. It should
be straightforward to compile the .cc files manually on other systems. The
@ -130,11 +123,90 @@ files called xxx_unittest.cc are test programs for each of the corresponding
xxx.cc files.
FURTHER REMARKS
BUILDING FOR VIRTUAL PASCAL
If you have a system without "configure" but where you can use a Makefile, edit
Makefile.in to create Makefile, substituting suitable values for the variables
at the head of the file.
A script for building PCRE using Borland's C++ compiler for use with VPASCAL
was contributed by Alexander Tokarev. Stefan Weber updated the script and added
additional files. The following files in the distribution are for building PCRE
for use with VP/Borland: makevp_c.txt, makevp_l.txt, makevp.bat, pcregexp.pas.
COMMENTS ABOUT WIN32 BUILDS
There are two ways of building PCRE using the "configure, make, make install"
paradigm on Windows systems: using MinGW or using Cygwin. These are not at all
the same thing; they are completely different from each other. There is also
some experimental, undocumented support for building using "cmake", which you
might like to try if you are familiar with "cmake". However, at the present
time, the "cmake" process builds only a static library (not a dll), and the
tests are not automatically run.
The MinGW home page (http://www.mingw.org/) says this:
MinGW: A collection of freely available and freely distributable Windows
specific header files and import libraries combined with GNU toolsets that
allow one to produce native Windows programs that do not rely on any
3rd-party C runtime DLLs.
The Cygwin home page (http://www.cygwin.com/) says this:
Cygwin is a Linux-like environment for Windows. It consists of two parts:
. A DLL (cygwin1.dll) which acts as a Linux API emulation layer providing
substantial Linux API functionality
. A collection of tools which provide Linux look and feel.
The Cygwin DLL currently works with all recent, commercially released x86 32
bit and 64 bit versions of Windows, with the exception of Windows CE.
On both MinGW and Cygwin, PCRE should build correctly using:
./configure && make && make install
This should create two libraries called libpcre and libpcreposix, and, if you
have enabled building the C++ wrapper, a third one called libpcrecpp. These are
independent libraries: when you like with libpcreposix or libpcrecpp you must
also link with libpcre, which contains the basic functions. (Some earlier
releases of PCRE included the basic libpcre functions in libpcreposix. This no
longer happens.)
If you want to statically link your program against a non-dll .a file, you must
define PCRE_STATIC before including pcre.h, otherwise the pcre_malloc() and
pcre_free() exported functions will be declared __declspec(dllimport), with
unwanted results.
Using Cygwin's compiler generates libraries and executables that depend on
cygwin1.dll. If a library that is generated this way is distributed,
cygwin1.dll has to be distributed as well. Since cygwin1.dll is under the GPL
licence, this forces not only PCRE to be under the GPL, but also the entire
application. A distributor who wants to keep their own code proprietary must
purchase an appropriate Cygwin licence.
MinGW has no such restrictions. The MinGW compiler generates a library or
executable that can run standalone on Windows without any third party dll or
licensing issues.
But there is more complication:
If a Cygwin user uses the -mno-cygwin Cygwin gcc flag, what that really does is
to tell Cygwin's gcc to use the MinGW gcc. Cygwin's gcc is only acting as a
front end to MinGW's gcc (if you install Cygwin's gcc, you get both Cygwin's
gcc and MinGW's gcc). So, a user can:
. Build native binaries by using MinGW or by getting Cygwin and using
-mno-cygwin.
. Build binaries that depend on cygwin1.dll by using Cygwin with the normal
compiler flags.
The test files that are supplied with PCRE are in Unix format, with LF
characters as line terminators. It may be necessary to change the line
terminators in order to get some of the tests to work. We hope to improve
things in this area in future.
BUILDING UNDER WINDOWS WITH BCC5.5
Michael Roy sent these comments about building PCRE under Windows with BCC5.5:
@ -147,72 +219,6 @@ Michael Roy sent these comments about building PCRE under Windows with BCC5.5:
the libraries cw32.lib, cw32i.lib, cw32mt.lib, and cw32mti.lib on the command
line.
Some help in building a Win32 DLL of PCRE in GnuWin32 environments was
contributed by Paul Sokolovsky. These environments are Mingw32
(http://www.xraylith.wisc.edu/~khan/software/gnu-win32/) and CygWin
(http://sourceware.cygnus.com/cygwin/). Paul comments:
For CygWin, set CFLAGS=-mno-cygwin, and do 'make dll'. You'll get
pcre.dll (containing pcreposix also), libpcre.dll.a, and dynamically
linked pgrep and pcretest. If you have /bin/sh, run RunTest (three
main test go ok, locale not supported).
Changes to do MinGW with autoconf 2.50 were supplied by Fred Cox
<sailorFred@yahoo.com>, who comments as follows:
If you are using the PCRE DLL, the normal Unix style configure && make &&
make check && make install should just work[*]. If you want to statically
link against the .a file, you must define PCRE_STATIC before including
pcre.h, otherwise the pcre_malloc and pcre_free exported functions will be
declared __declspec(dllimport), with hilarious results. See the configure.in
and pcretest.c for how it is done for the static test.
Also, there will only be a libpcre.la, not a libpcreposix.la, as you
would expect from the Unix version. The single DLL includes the pcreposix
interface.
[*] But note that the supplied test files are in Unix format, with just LF
characters as line terminators. You will have to edit them to change to CR LF
terminators.
A script for building PCRE using Borland's C++ compiler for use with VPASCAL
was contributed by Alexander Tokarev. It is called makevp.bat.
These are some further comments about Win32 builds from Mark Evans. They
were contributed before Fred Cox's changes were made, so it is possible that
they may no longer be relevant.
"The documentation for Win32 builds is a bit shy. Under MSVC6 I
followed their instructions to the letter, but there were still
some things missing.
(1) Must #define STATIC for entire project if linking statically.
(I see no reason to use DLLs for code this compact.) This of
course is a project setting in MSVC under Preprocessor.
(2) Missing some #ifdefs relating to the function pointers
pcre_malloc and pcre_free. See my solution below. (The stubs
may not be mandatory but they made me feel better.)"
=========================
#ifdef _WIN32
#include <malloc.h>
void* malloc_stub(size_t N)
{ return malloc(N); }
void free_stub(void* p)
{ free(p); }
void *(*pcre_malloc)(size_t) = &malloc_stub;
void (*pcre_free)(void *) = &free_stub;
#else
void *(*pcre_malloc)(size_t) = malloc;
void (*pcre_free)(void *) = free;
#endif
=========================
BUILDING PCRE ON OPENVMS
@ -278,4 +284,5 @@ $! Locale could not be set to fr
$!
=========================
Last Updated: 13 June 2007
****

612
ext/pcre/pcrelib/README
View File

@ -5,51 +5,82 @@ The latest release of PCRE is always available from
ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.tar.gz
There is a mailing list for discussion about the development of PCRE at
pcre-dev@exim.org
Please read the NEWS file if you are upgrading from a previous release.
The contents of this README file are:
The PCRE APIs
Documentation for PCRE
Contributions by users of PCRE
Building PCRE on non-Unix systems
Building PCRE on Unix-like systems
Retrieving configuration information on Unix-like systems
Shared libraries on Unix-like systems
Cross-compiling on Unix-like systems
Using HP's ANSI C++ compiler (aCC)
Making new tarballs
Testing PCRE
Character tables
File manifest
The PCRE APIs
-------------
PCRE is written in C, and it has its own API. The distribution now includes a
set of C++ wrapper functions, courtesy of Google Inc. (see the pcrecpp man page
for details).
PCRE is written in C, and it has its own API. The distribution also includes a
set of C++ wrapper functions (see the pcrecpp man page for details), courtesy
of Google Inc.
Also included are a set of C wrapper functions that are based on the POSIX
API. These end up in the library called libpcreposix. Note that this just
provides a POSIX calling interface to PCRE: the regular expressions themselves
still follow Perl syntax and semantics. The header file for the POSIX-style
functions is called pcreposix.h. The official POSIX name is regex.h, but I
didn't want to risk possible problems with existing files of that name by
distributing it that way. To use it with an existing program that uses the
POSIX API, it will have to be renamed or pointed at by a link.
In addition, there is a set of C wrapper functions that are based on the POSIX
regular expression API (see the pcreposix man page). These end up in the
library called libpcreposix. Note that this just provides a POSIX calling
interface to PCRE; the regular expressions themselves still follow Perl syntax
and semantics. The POSIX API is restricted, and does not give full access to
all of PCRE's facilities.
The header file for the POSIX-style functions is called pcreposix.h. The
official POSIX name is regex.h, but I did not want to risk possible problems
with existing files of that name by distributing it that way. To use PCRE with
an existing program that uses the POSIX API, pcreposix.h will have to be
renamed or pointed at by a link.
If you are using the POSIX interface to PCRE and there is already a POSIX regex
library installed on your system, you must take care when linking programs to
library installed on your system, as well as worrying about the regex.h header
file (as mentioned above), you must also take care when linking programs to
ensure that they link with PCRE's libpcreposix library. Otherwise they may pick
up the "real" POSIX functions of the same name.
up the POSIX functions of the same name from the other library.
One way of avoiding this confusion is to compile PCRE with the addition of
-Dregcomp=PCREregcomp (and similarly for the other POSIX functions) to the
compiler flags (CFLAGS if you are using "configure" -- see below). This has the
effect of renaming the functions so that the names no longer clash. Of course,
you have to do the same thing for your applications, or write them using the
new names.
Documentation for PCRE
----------------------
If you install PCRE in the normal way, you will end up with an installed set of
man pages whose names all start with "pcre". The one that is just called "pcre"
lists all the others. In addition to these man pages, the PCRE documentation is
supplied in two other forms; however, as there is no standard place to install
them, they are left in the doc directory of the unpacked source distribution.
These forms are:
If you install PCRE in the normal way on a Unix-like system, you will end up
with a set of man pages whose names all start with "pcre". The one that is just
called "pcre" lists all the others. In addition to these man pages, the PCRE
documentation is supplied in two other forms:
1. Files called doc/pcre.txt, doc/pcregrep.txt, and doc/pcretest.txt. The
first of these is a concatenation of the text forms of all the section 3
man pages except those that summarize individual functions. The other two
are the text forms of the section 1 man pages for the pcregrep and
pcretest commands. Text forms are provided for ease of scanning with text
editors or similar tools.
1. There are files called doc/pcre.txt, doc/pcregrep.txt, and
doc/pcretest.txt in the source distribution. The first of these is a
concatenation of the text forms of all the section 3 man pages except
those that summarize individual functions. The other two are the text
forms of the section 1 man pages for the pcregrep and pcretest commands.
These text forms are provided for ease of scanning with text editors or
similar tools. They are installed in <prefix>/share/doc/pcre, where
<prefix> is the installation prefix (defaulting to /usr/local).
2. A subdirectory called doc/html contains all the documentation in HTML
form, hyperlinked in various ways, and rooted in a file called
doc/index.html.
2. A set of files containing all the documentation in HTML form, hyperlinked
in various ways, and rooted in a file called index.html, is distributed in
doc/html and installed in <prefix>/share/doc/pcre/html.
Contributions by users of PCRE
@ -59,27 +90,46 @@ You can find contributions from PCRE users in the directory
ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/Contrib
where there is also a README file giving brief descriptions of what they are.
Several of them provide support for compiling PCRE on various flavours of
Windows systems (I myself do not use Windows). Some are complete in themselves;
others are pointers to URLs containing relevant files.
There is a README file giving brief descriptions of what they are. Some are
complete in themselves; others are pointers to URLs containing relevant files.
Some of this material is likely to be well out-of-date. Several of the earlier
contributions provided support for compiling PCRE on various flavours of
Windows (I myself do not use Windows). Nowadays there is more Windows support
in the standard distribution, so these contibutions have been archived.
Building PCRE on a Unix-like system
-----------------------------------
Building PCRE on non-Unix systems
---------------------------------
For a non-Unix system, please read the comments in the file NON-UNIX-USE,
though if your system supports the use of "configure" and "make" you may be
able to build PCRE in the same way as for Unix-like systems.
PCRE has been compiled on many different operating systems. It should be
straightforward to build PCRE on any system that has a Standard C compiler and
library, because it uses only Standard C functions.
Building PCRE on Unix-like systems
----------------------------------
If you are using HP's ANSI C++ compiler (aCC), please see the special note
in the section entitled "Using HP's ANSI C++ compiler (aCC)" below.
The following instructions assume the use of the widely used "configure, make,
make install" process. There is also some experimental support for "cmake" in
the PCRE distribution, but it is incomplete and not documented. However, if you
are a "cmake" user, you might want to try it.
To build PCRE on a Unix-like system, first run the "configure" command from the
PCRE distribution directory, with your current directory set to the directory
where you want the files to be created. This command is a standard GNU
"autoconf" configuration script, for which generic instructions are supplied in
INSTALL.
the file INSTALL.
Most commonly, people build PCRE within its own distribution directory, and in
this case, on many systems, just running "./configure" is sufficient, but the
usual methods of changing standard defaults are available. For example:
this case, on many systems, just running "./configure" is sufficient. However,
the usual methods of changing standard defaults are available. For example:
CFLAGS='-O2 -Wall' ./configure --prefix=/opt/local
@ -103,8 +153,8 @@ library. You can read more about them in the pcrebuild man page.
. If you want to suppress the building of the C++ wrapper library, you can add
--disable-cpp to the "configure" command. Otherwise, when "configure" is run,
will try to find a C++ compiler and C++ header files, and if it succeeds, it
will try to build the C++ wrapper.
it will try to find a C++ compiler and C++ header files, and if it succeeds,
it will try to build the C++ wrapper.
. If you want to make use of the support for UTF-8 character strings in PCRE,
you must add --enable-utf8 to the "configure" command. Without it, the code
@ -119,16 +169,24 @@ library. You can read more about them in the pcrebuild man page.
supported.
. You can build PCRE to recognize either CR or LF or the sequence CRLF or any
of the Unicode newline sequences as indicating the end of a line. Whatever
you specify at build time is the default; the caller of PCRE can change the
selection at run time. The default newline indicator is a single LF character
(the Unix standard). You can specify the default newline indicator by adding
--newline-is-cr or --newline-is-lf or --newline-is-crlf or --newline-is-any
to the "configure" command, respectively.
of the preceding, or any of the Unicode newline sequences as indicating the
end of a line. Whatever you specify at build time is the default; the caller
of PCRE can change the selection at run time. The default newline indicator
is a single LF character (the Unix standard). You can specify the default
newline indicator by adding --enable-newline-is-cr or --enable-newline-is-lf
or --enable-newline-is-crlf or --enable-newline-is-anycrlf or
--enable-newline-is-any to the "configure" command, respectively.
If you specify --enable-newline-is-cr or --enable-newline-is-crlf, some of
the standard tests will fail, because the lines in the test files end with
LF. Even if the files are edited to change the line endings, there are likely
to be some failures. With --enable-newline-is-anycrlf or
--enable-newline-is-any, many tests should succeed, but there may be some
failures.
. When called via the POSIX interface, PCRE uses malloc() to get additional
storage for processing capturing parentheses if there are more than 10 of
them. You can increase this threshold by setting, for example,
them in a pattern. You can increase this threshold by setting, for example,
--with-posix-malloc-threshold=20
@ -141,8 +199,8 @@ library. You can read more about them in the pcrebuild man page.
--with-match-limit=500000
on the "configure" command. This is just the default; individual calls to
pcre_exec() can supply their own value. There is discussion on the pcreapi
man page.
pcre_exec() can supply their own value. There is more discussion on the
pcreapi man page.
. There is a separate counter that limits the depth of recursive function calls
during a matching process. This also has a default of ten million, which is
@ -157,37 +215,61 @@ library. You can read more about them in the pcrebuild man page.
. The default maximum compiled pattern size is around 64K. You can increase
this by adding --with-link-size=3 to the "configure" command. You can
increase it even more by setting --with-link-size=4, but this is unlikely
ever to be necessary. If you build PCRE with an increased link size, test 2
(and 5 if you are using UTF-8) will fail. Part of the output of these tests
is a representation of the compiled pattern, and this changes with the link
size.
ever to be necessary. Increasing the internal link size will reduce
performance.
. You can build PCRE so that its internal match() function that is called from
pcre_exec() does not call itself recursively. Instead, it uses blocks of data
from the heap via special functions pcre_stack_malloc() and pcre_stack_free()
to save data that would otherwise be saved on the stack. To build PCRE like
this, use
pcre_exec() does not call itself recursively. Instead, it uses memory blocks
obtained from the heap via the special functions pcre_stack_malloc() and
pcre_stack_free() to save data that would otherwise be saved on the stack. To
build PCRE like this, use
--disable-stack-for-recursion
on the "configure" command. PCRE runs more slowly in this mode, but it may be
necessary in environments with limited stack sizes. This applies only to the
pcre_exec() function; it does not apply to pcre_dfa_exec(), which does not
use deeply nested recursion.
use deeply nested recursion. There is a discussion about stack sizes in the
pcrestack man page.
The "configure" script builds eight files for the basic C library:
. For speed, PCRE uses four tables for manipulating and identifying characters
whose code point values are less than 256. By default, it uses a set of
tables for ASCII encoding that is part of the distribution. If you specify
--enable-rebuild-chartables
a program called dftables is compiled and run in the default C locale when
you obey "make". It builds a source file called pcre_chartables.c. If you do
not specify this option, pcre_chartables.c is created as a copy of
pcre_chartables.c.dist. See "Character tables" below for further information.
. It is possible to compile PCRE for use on systems that use EBCDIC as their
default character code (as opposed to ASCII) by specifying
--enable-ebcdic
This automatically implies --enable-rebuild-chartables (see above).
The "configure" script builds the following files for the basic C library:
. Makefile is the makefile that builds the library
. config.h contains build-time configuration options for the library
. pcre.h is the public PCRE header file
. pcre-config is a script that shows the settings of "configure" options
. libpcre.pc is data for the pkg-config command
. libtool is a script that builds shared and/or static libraries
. RunTest is a script for running tests on the library
. RunTest is a script for running tests on the basic C library
. RunGrepTest is a script for running tests on the pcregrep command
In addition, if a C++ compiler is found, the following are also built:
Versions of config.h and pcre.h are distributed in the PCRE tarballs under
the names config.h.generic and pcre.h.generic. These are provided for the
benefit of those who have to built PCRE without the benefit of "configure". If
you use "configure", the .generic versions are not used.
. pcrecpp.h is the header file for programs that call PCRE via the C++ wrapper
If a C++ compiler is found, the following files are also built:
. libpcrecpp.pc is data for the pkg-config command
. pcrecpparg.h is a header file for programs that call PCRE via the C++ wrapper
. pcre_stringpiece.h is the header for the C++ "stringpiece" functions
The "configure" script also creates config.status, which is an executable
@ -195,18 +277,65 @@ script that can be run to recreate the configuration, and config.log, which
contains compiler output from tests that "configure" runs.
Once "configure" has run, you can run "make". It builds two libraries, called
libpcre and libpcreposix, a test program called pcretest, and the pcregrep
command. If a C++ compiler was found on your system, it also builds the C++
wrapper library, which is called libpcrecpp, and some test programs called
pcrecpp_unittest, pcre_scanner_unittest, and pcre_stringpiece_unittest.
libpcre and libpcreposix, a test program called pcretest, a demonstration
program called pcredemo, and the pcregrep command. If a C++ compiler was found
on your system, "make" also builds the C++ wrapper library, which is called
libpcrecpp, and some test programs called pcrecpp_unittest,
pcre_scanner_unittest, and pcre_stringpiece_unittest. Building the C++ wrapper
can be disabled by adding --disable-cpp to the "configure" command.
The command "make test" runs all the appropriate tests. Details of the PCRE
tests are given in a separate section of this document, below.
The command "make check" runs all the appropriate tests. Details of the PCRE
tests are given below in a separate section of this document.
You can use "make install" to copy the libraries, the public header files
pcre.h, pcreposix.h, pcrecpp.h, and pcre_stringpiece.h (the last two only if
the C++ wrapper was built), and the man pages to appropriate live directories
on your system, in the normal way.
You can use "make install" to install PCRE into live directories on your
system. The following are installed (file names are all relative to the
<prefix> that is set when "configure" is run):
Commands (bin):
pcretest
pcregrep
pcre-config
Libraries (lib):
libpcre
libpcreposix
libpcrecpp (if C++ support is enabled)
Configuration information (lib/pkgconfig):
libpcre.pc
libpcrecpp.pc (if C++ support is enabled)
Header files (include):
pcre.h
pcreposix.h
pcre_scanner.h )
pcre_stringpiece.h ) if C++ support is enabled
pcrecpp.h )
pcrecpparg.h )
Man pages (share/man/man{1,3}):
pcregrep.1
pcretest.1
pcre.3
pcre*.3 (lots more pages, all starting "pcre")
HTML documentation (share/doc/pcre/html):
index.html
*.html (lots more pages, hyperlinked from index.html)
Text file documentation (share/doc/pcre):
AUTHORS
COPYING
ChangeLog
LICENCE
NEWS
README
pcre.txt (a concatenation of the man(3) pages)
pcretest.txt the pcretest man page
pcregrep.txt the pcregrep man page
Note that the pcredemo program that is built by "configure" is *not* installed
anywhere. It is a demonstration for programmers wanting to use PCRE.
If you want to remove PCRE from your system, you can run "make uninstall".
This removes all the files that "make install" installed. However, it does not
@ -216,9 +345,8 @@ remove any directories, because these are often shared with other programs.
Retrieving configuration information on Unix-like systems
---------------------------------------------------------
Running "make install" also installs the command pcre-config, which can be used
to recall information about the PCRE configuration and installation. For
example:
Running "make install" installs the command pcre-config, which can be used to
recall information about the PCRE configuration and installation. For example:
pcre-config --version
@ -237,7 +365,7 @@ single command is used. For example:
pkg-config --cflags pcre
The data is held in *.pc files that are installed in a directory called
pkgconfig.
<prefix>/lib/pkgconfig.
Shared libraries on Unix-like systems
@ -254,7 +382,7 @@ built. The programs pcretest and pcregrep are built to use these uninstalled
libraries (by means of wrapper scripts in the case of shared libraries). When
you use "make install" to install shared libraries, pcregrep and pcretest are
automatically re-built to use the newly installed shared libraries before being
installed themselves. However, the versions left in the source directory still
installed themselves. However, the versions left in the build directory still
use the uninstalled libraries.
To build PCRE using static libraries only you must use --disable-shared when
@ -266,25 +394,33 @@ Then run "make" in the usual way. Similarly, you can use --disable-static to
build only shared libraries.
Cross-compiling on a Unix-like system
-------------------------------------
Cross-compiling on Unix-like systems
------------------------------------
You can specify CC and CFLAGS in the normal way to the "configure" command, in
order to cross-compile PCRE for some other host. However, during the building
process, the dftables.c source file is compiled *and run* on the local host, in
order to generate the default character tables (the chartables.c file). It
therefore needs to be compiled with the local compiler, not the cross compiler.
You can do this by specifying CC_FOR_BUILD (and if necessary CFLAGS_FOR_BUILD;
there are also CXX_FOR_BUILD and CXXFLAGS_FOR_BUILD for the C++ wrapper)
when calling the "configure" command. If they are not specified, they default
to the values of CC and CFLAGS.
order to cross-compile PCRE for some other host. However, you should NOT
specify --enable-rebuild-chartables, because if you do, the dftables.c source
file is compiled and run on the local host, in order to generate the inbuilt
character tables (the pcre_chartables.c file). This will probably not work,
because dftables.c needs to be compiled with the local compiler, not the cross
compiler.
When --enable-rebuild-chartables is not specified, pcre_chartables.c is created
by making a copy of pcre_chartables.c.dist, which is a default set of tables
that assumes ASCII code. Cross-compiling with the default tables should not be
a problem.
If you need to modify the character tables when cross-compiling, you should
move pcre_chartables.c.dist out of the way, then compile dftables.c by hand and
run it on the local host to make a new version of pcre_chartables.c.dist.
Then when you cross-compile PCRE this new version of the tables will be used.
Using HP's ANSI C++ compiler (aCC)
----------------------------------
Unless C++ support is disabled by specifying the "--disable-cpp" option of the
"configure" script, you *must* include the "-AA" option in the CXXFLAGS
"configure" script, you must include the "-AA" option in the CXXFLAGS
environment variable in order for the C++ components to compile correctly.
Also, note that the aCC compiler on PA-RISC platforms may have a defect whereby
@ -296,34 +432,32 @@ running the "configure" script:
CXXLDFLAGS="-lstd_v2 -lCsup_v2"
Building on non-Unix systems
----------------------------
Making new tarballs
-------------------
For a non-Unix system, read the comments in the file NON-UNIX-USE, though if
the system supports the use of "configure" and "make" you may be able to build
PCRE in the same way as for Unix systems.
The command "make dist" creates three PCRE tarballs, in tar.gz, tar.bz2, and
zip formats. The command "make distcheck" does the same, but then does a trial
build of the new distribution to ensure that it works.
PCRE has been compiled on Windows systems and on Macintoshes, but I don't know
the details because I don't use those systems. It should be straightforward to
build PCRE on any system that has a Standard C compiler and library, because it
uses only Standard C functions.
If you have modified any of the man page sources in the doc directory, you
should first run the PrepareRelease script before making a distribution. This
script creates the .txt and HTML forms of the documentation from the man pages.
Testing PCRE
------------
To test PCRE on a Unix system, run the RunTest script that is created by the
configuring process. There is also a script called RunGrepTest that tests the
options of the pcregrep command. If the C++ wrapper library is build, three
test programs called pcrecpp_unittest, pcre_scanner_unittest, and
pcre_stringpiece_unittest are provided.
To test the basic PCRE library on a Unix system, run the RunTest script that is
created by the configuring process. There is also a script called RunGrepTest
that tests the options of the pcregrep command. If the C++ wrapper library is
built, three test programs called pcrecpp_unittest, pcre_scanner_unittest, and
pcre_stringpiece_unittest are also built.
Both the scripts and all the program tests are run if you obey "make runtest",
"make check", or "make test". For other systems, see the instructions in
NON-UNIX-USE.
Both the scripts and all the program tests are run if you obey "make check" or
"make test". For other systems, see the instructions in NON-UNIX-USE.
The RunTest script runs the pcretest test program (which is documented in its
own man page) on each of the testinput files (in the testdata directory) in
own man page) on each of the testinput files in the testdata directory in
turn, and compares the output with the contents of the corresponding testoutput
files. A file called testtry is used to hold the main output from pcretest
(testsavedregex is also used as a working file). To run pcretest on just one of
@ -331,14 +465,15 @@ the test files, give its number as an argument to RunTest, for example:
RunTest 2
The first test file can also be fed directly into the perltest script to check
that Perl gives the same results. The only difference you should see is in the
first few lines, where the Perl version is given instead of the PCRE version.
The first test file can also be fed directly into the perltest.pl script to
check that Perl gives the same results. The only difference you should see is
in the first few lines, where the Perl version is given instead of the PCRE
version.
The second set of tests check pcre_fullinfo(), pcre_info(), pcre_study(),
pcre_copy_substring(), pcre_get_substring(), pcre_get_substring_list(), error
detection, and run-time flags that are specific to PCRE, as well as the POSIX
wrapper API. It also uses the debugging flag to check some of the internals of
wrapper API. It also uses the debugging flags to check some of the internals of
pcre_compile().
If you build PCRE with a locale setting that is not the standard C locale, the
@ -364,6 +499,9 @@ is output to say why. If running this test produces instances of the error
in the comparison output, it means that locale is not available on your system,
despite being listed by "locale". This does not mean that PCRE is broken.
[If you are trying to run this test on Windows, you may be able to get it to
work by changing "fr_FR" to "french" everywhere it occurs.]
The fourth test checks the UTF-8 support. It is not run automatically unless
PCRE is built with UTF-8 support. To do this you must set --enable-utf8 when
running "configure". This file can be also fed directly to the perltest script,
@ -373,8 +511,8 @@ commented in the script, can be be used.)
The fifth test checks error handling with UTF-8 encoding, and internal UTF-8
features of PCRE that are not relevant to Perl.
The sixth and test checks the support for Unicode character properties. It it
not run automatically unless PCRE is built with Unicode property support. To to
The sixth test checks the support for Unicode character properties. It it not
run automatically unless PCRE is built with Unicode property support. To to
this you must set --enable-unicode-properties when running "configure".
The seventh, eighth, and ninth tests check the pcre_dfa_exec() alternative
@ -386,27 +524,42 @@ automatically unless PCRE is build with the relevant support.
Character tables
----------------
PCRE uses four tables for manipulating and identifying characters whose values
are less than 256. The final argument of the pcre_compile() function is a
pointer to a block of memory containing the concatenated tables. A call to
pcre_maketables() can be used to generate a set of tables in the current
locale. If the final argument for pcre_compile() is passed as NULL, a set of
default tables that is built into the binary is used.
For speed, PCRE uses four tables for manipulating and identifying characters
whose code point values are less than 256. The final argument of the
pcre_compile() function is a pointer to a block of memory containing the
concatenated tables. A call to pcre_maketables() can be used to generate a set
of tables in the current locale. If the final argument for pcre_compile() is
passed as NULL, a set of default tables that is built into the binary is used.
The source file called chartables.c contains the default set of tables. This is
not supplied in the distribution, but is built by the program dftables
(compiled from dftables.c), which uses the ANSI C character handling functions
such as isalnum(), isalpha(), isupper(), islower(), etc. to build the table
sources. This means that the default C locale which is set for your system will
control the contents of these default tables. You can change the default tables
by editing chartables.c and then re-building PCRE. If you do this, you should
probably also edit Makefile to ensure that the file doesn't ever get
re-generated.
The source file called pcre_chartables.c contains the default set of tables. By
default, this is created as a copy of pcre_chartables.c.dist, which contains
tables for ASCII coding. However, if --enable-rebuild-chartables is specified
for ./configure, a different version of pcre_chartables.c is built by the
program dftables (compiled from dftables.c), which uses the ANSI C character
handling functions such as isalnum(), isalpha(), isupper(), islower(), etc. to
build the table sources. This means that the default C locale which is set for
your system will control the contents of these default tables. You can change
the default tables by editing pcre_chartables.c and then re-building PCRE. If
you do this, you should take care to ensure that the file does not get
automatically re-generated. The best way to do this is to move
pcre_chartables.c.dist out of the way and replace it with your customized
tables.
When the dftables program is run as a result of --enable-rebuild-chartables,
it uses the default C locale that is set on your system. It does not pay
attention to the LC_xxx environment variables. In other words, it uses the
system's default locale rather than whatever the compiling user happens to have
set. If you really do want to build a source set of character tables in a
locale that is specified by the LC_xxx variables, you can run the dftables
program by hand with the -L option. For example:
./dftables -L pcre_chartables.c.special
The first two 256-byte tables provide lower casing and case flipping functions,
respectively. The next table consists of three 32-byte bit maps which identify
digits, "word" characters, and white space, respectively. These are used when
building 32-byte bit maps that represent character classes.
building 32-byte bit maps that represent character classes for code points less
than 256.
The final 256-byte table has bits indicating various character types, as
follows:
@ -422,108 +575,143 @@ You should not alter the set of characters that contain the 128 bit, as that
will cause PCRE to malfunction.
Manifest
--------
File manifest
-------------
The distribution should contain the following files:
(A) The actual source files of the PCRE library functions and their
headers:
(A) Source files of the PCRE library functions and their headers:
dftables.c auxiliary program for building chartables.c
dftables.c auxiliary program for building pcre_chartables.c
when --enable-rebuild-chartables is specified
pcreposix.c )
pcre_compile.c )
pcre_config.c )
pcre_dfa_exec.c )
pcre_exec.c )
pcre_fullinfo.c )
pcre_get.c ) sources for the functions in the library,
pcre_globals.c ) and some internal functions that they use
pcre_info.c )
pcre_maketables.c )
pcre_newline.c )
pcre_ord2utf8.c )
pcre_refcount.c )
pcre_study.c )
pcre_tables.c )
pcre_try_flipped.c )
pcre_ucp_searchfuncs.c)
pcre_valid_utf8.c )
pcre_version.c )
pcre_xclass.c )
ucptable.c )
pcre_chartables.c.dist a default set of character tables that assume ASCII
coding; used, unless --enable-rebuild-chartables is
specified, by copying to pcre_chartables.c
pcre_printint.src ) debugging function that is #included in pcretest, and
) can also be #included in pcre_compile()
pcreposix.c )
pcre_compile.c )
pcre_config.c )
pcre_dfa_exec.c )
pcre_exec.c )
pcre_fullinfo.c )
pcre_get.c ) sources for the functions in the library,
pcre_globals.c ) and some internal functions that they use
pcre_info.c )
pcre_maketables.c )
pcre_newline.c )
pcre_ord2utf8.c )
pcre_refcount.c )
pcre_study.c )
pcre_tables.c )
pcre_try_flipped.c )
pcre_ucp_searchfuncs.c )
pcre_valid_utf8.c )
pcre_version.c )
pcre_xclass.c )
pcre_printint.src ) debugging function that is #included in pcretest,
) and can also be #included in pcre_compile()
pcre.h.in template for pcre.h when built by "configure"
pcreposix.h header for the external POSIX wrapper API
pcre_internal.h header for internal use
ucp.h ) headers concerned with
ucpinternal.h ) Unicode property handling
ucptable.h ) (this one is the data table)
pcre.h the public PCRE header file
pcreposix.h header for the external POSIX wrapper API
pcre_internal.h header for internal use
ucp.h ) headers concerned with
ucpinternal.h ) Unicode property handling
config.in template for config.h, which is built by configure
config.h.in template for config.h, which is built by "configure"
pcrecpp.h the header file for the C++ wrapper
pcrecpparg.h.in "source" for another C++ header file
pcrecpp.cc )
pcre_scanner.cc ) source for the C++ wrapper library
pcrecpp.h public header file for the C++ wrapper
pcrecpparg.h.in template for another C++ header file
pcre_scanner.h public header file for C++ scanner functions
pcrecpp.cc )
pcre_scanner.cc ) source for the C++ wrapper library
pcre_stringpiece.h.in "source" for pcre_stringpiece.h, the header for the
C++ stringpiece functions
pcre_stringpiece.cc source for the C++ stringpiece functions
pcre_stringpiece.h.in template for pcre_stringpiece.h, the header for the
C++ stringpiece functions
pcre_stringpiece.cc source for the C++ stringpiece functions
(B) Auxiliary files:
(B) Source files for programs that use PCRE:
AUTHORS information about the author of PCRE
ChangeLog log of changes to the code
INSTALL generic installation instructions
LICENCE conditions for the use of PCRE
COPYING the same, using GNU's standard name
Makefile.in template for Unix Makefile, which is built by configure
NEWS important changes in this release
NON-UNIX-USE notes on building PCRE on non-Unix systems
README this file
RunTest.in template for a Unix shell script for running tests
RunGrepTest.in template for a Unix shell script for pcregrep tests
config.guess ) files used by libtool,
config.sub ) used only when building a shared library
config.h.in "source" for the config.h header file
configure a configuring shell script (built by autoconf)
configure.ac the autoconf input used to build configure
doc/Tech.Notes notes on the encoding
doc/*.3 man page sources for the PCRE functions
doc/*.1 man page sources for pcregrep and pcretest
doc/html/* HTML documentation
doc/pcre.txt plain text version of the man pages
doc/pcretest.txt plain text documentation of test program
doc/perltest.txt plain text documentation of Perl test program
install-sh a shell script for installing files
libpcre.pc.in "source" for libpcre.pc for pkg-config
ltmain.sh file used to build a libtool script
mkinstalldirs script for making install directories
pcretest.c comprehensive test program
pcredemo.c simple demonstration of coding calls to PCRE
perltest Perl test program
pcregrep.c source of a grep utility that uses PCRE
pcre-config.in source of script which retains PCRE information
pcrecpp_unittest.c )
pcre_scanner_unittest.c ) test programs for the C++ wrapper
pcre_stringpiece_unittest.c )
testdata/testinput* test data for main library tests
testdata/testoutput* expected test results
testdata/grep* input and output for pcregrep tests
pcredemo.c simple demonstration of coding calls to PCRE
pcregrep.c source of a grep utility that uses PCRE
pcretest.c comprehensive test program
(C) Auxiliary files for Win32 DLL
(C) Auxiliary files:
libpcre.def
libpcreposix.def
132html script to turn "man" pages into HTML
AUTHORS information about the author of PCRE
ChangeLog log of changes to the code
CleanTxt script to clean nroff output for txt man pages
Detrail script to remove trailing spaces
HACKING some notes about the internals of PCRE
INSTALL generic installation instructions
LICENCE conditions for the use of PCRE
COPYING the same, using GNU's standard name
Makefile.in ) template for Unix Makefile, which is built by
) "configure"
Makefile.am ) the automake input that was used to create
) Makefile.in
NEWS important changes in this release
NON-UNIX-USE notes on building PCRE on non-Unix systems
PrepareRelease script to make preparations for "make dist"
README this file
RunTest a Unix shell script for running tests
RunGrepTest a Unix shell script for pcregrep tests
aclocal.m4 m4 macros (generated by "aclocal")
config.guess ) files used by libtool,
config.sub ) used only when building a shared library
configure a configuring shell script (built by autoconf)
configure.ac ) the autoconf input that was used to build
) "configure" and config.h
depcomp ) script to find program dependencies, generated by
) automake
doc/*.3 man page sources for the PCRE functions
doc/*.1 man page sources for pcregrep and pcretest
doc/index.html.src the base HTML page
doc/html/* HTML documentation
doc/pcre.txt plain text version of the man pages
doc/pcretest.txt plain text documentation of test program
doc/perltest.txt plain text documentation of Perl test program
install-sh a shell script for installing files
libpcre.pc.in template for libpcre.pc for pkg-config
libpcrecpp.pc.in template for libpcrecpp.pc for pkg-config
ltmain.sh file used to build a libtool script
missing ) common stub for a few missing GNU programs while
) installing, generated by automake
mkinstalldirs script for making install directories
perltest.pl Perl test program
pcre-config.in source of script which retains PCRE information
pcrecpp_unittest.cc )
pcre_scanner_unittest.cc ) test programs for the C++ wrapper
pcre_stringpiece_unittest.cc )
testdata/testinput* test data for main library tests
testdata/testoutput* expected test results
testdata/grep* input and output for pcregrep tests
(D) Auxiliary file for VPASCAL
(D) Auxiliary files for cmake support
CMakeLists.txt
config-cmake.h.in
(E) Auxiliary files for VPASCAL
makevp.bat
makevp_c.txt
makevp_l.txt
pcregexp.pas
(F) Auxiliary files for building PCRE "by hand"
pcre.h.generic ) a version of the public PCRE header file
) for use in non-"configure" environments
config.h.generic ) a version of config.h for use in non-"configure"
) environments
(F) Miscellaneous
RunTest.bat a script for running tests under Windows
Philip Hazel
Email local part: ph10
Email domain: cam.ac.uk
November 2006
Last updated: 24 April 2007

282
ext/pcre/pcrelib/config.h Normal file
View File

@ -0,0 +1,282 @@
#include <php_compat.h>
#undef PACKAGE_NAME
#undef PACKAGE_VERSION
#undef PACKAGE_TARNAME
#undef PACKAGE_STRING
#define SUPPORT_UCP
#define SUPPORT_UTF8
/* config.h. Generated from config.h.in by configure. */
/* config.h.in. Generated from configure.ac by autoheader. */
/* On Unix-like systems config.h.in is converted by "configure" into config.h.
Some other environments also support the use of "configure". PCRE is written in
Standard C, but there are a few non-standard things it can cope with, allowing
it to run on SunOS4 and other "close to standard" systems.
If you are going to build PCRE "by hand" on a system without "configure" you
should copy the distributed config.h.generic to config.h, and then set up the
macros the way you need them. Alternatively, you can avoid editing by using -D
on the compiler command line to set the macro values.
PCRE uses memmove() if HAVE_MEMMOVE is set to 1; otherwise it uses bcopy() if
HAVE_BCOPY is set to 1. If your system has neither bcopy() nor memmove(), set
them both to 0; an emulation function will be used. */
/* If you are compiling for a system that uses EBCDIC instead of ASCII
character codes, define this macro as 1. On systems that can use
"configure", this can be done via --enable-ebcdic. */
/* #undef EBCDIC */
/* Define to 1 if you have the `bcopy' function. */
#ifndef HAVE_BCOPY
#define HAVE_BCOPY 1
#endif
/* Define to 1 if you have the <bits/type_traits.h> header file. */
/* #undef HAVE_BITS_TYPE_TRAITS_H */
/* Define to 1 if you have the <dirent.h> header file. */
#ifndef HAVE_DIRENT_H
#define HAVE_DIRENT_H 1
#endif
/* Define to 1 if you have the <dlfcn.h> header file. */
#ifndef HAVE_DLFCN_H
#define HAVE_DLFCN_H 1
#endif
/* Define to 1 if you have the <inttypes.h> header file. */
#ifndef HAVE_INTTYPES_H
#define HAVE_INTTYPES_H 1
#endif
/* Define to 1 if you have the <limits.h> header file. */
#ifndef HAVE_LIMITS_H
#define HAVE_LIMITS_H 1
#endif
/* Define to 1 if the system has the type `long long'. */
#ifndef HAVE_LONG_LONG
#define HAVE_LONG_LONG 1
#endif
/* Define to 1 if you have the `memmove' function. */
#ifndef HAVE_MEMMOVE
#define HAVE_MEMMOVE 1
#endif
/* Define to 1 if you have the <memory.h> header file. */
#ifndef HAVE_MEMORY_H
#define HAVE_MEMORY_H 1
#endif
/* Define to 1 if you have the <stdint.h> header file. */
#ifndef HAVE_STDINT_H
#define HAVE_STDINT_H 1
#endif
/* Define to 1 if you have the <stdlib.h> header file. */
#ifndef HAVE_STDLIB_H
#define HAVE_STDLIB_H 1
#endif
/* Define to 1 if you have the `strerror' function. */
#ifndef HAVE_STRERROR
#define HAVE_STRERROR 1
#endif
/* Define to 1 if you have the <string> header file. */
#ifndef HAVE_STRING
#define HAVE_STRING 1
#endif
/* Define to 1 if you have the <strings.h> header file. */
#ifndef HAVE_STRINGS_H
#define HAVE_STRINGS_H 1
#endif
/* Define to 1 if you have the <string.h> header file. */
#ifndef HAVE_STRING_H
#define HAVE_STRING_H 1
#endif
/* Define to 1 if you have the `strtoll' function. */
#ifndef HAVE_STRTOLL
#define HAVE_STRTOLL 1
#endif
/* Define to 1 if you have the `strtoq' function. */
#ifndef HAVE_STRTOQ
#define HAVE_STRTOQ 1
#endif
/* Define to 1 if you have the <sys/stat.h> header file. */
#ifndef HAVE_SYS_STAT_H
#define HAVE_SYS_STAT_H 1
#endif
/* Define to 1 if you have the <sys/types.h> header file. */
#ifndef HAVE_SYS_TYPES_H
#define HAVE_SYS_TYPES_H 1
#endif
/* Define to 1 if you have the <type_traits.h> header file. */
/* #undef HAVE_TYPE_TRAITS_H */
/* Define to 1 if you have the <unistd.h> header file. */
#ifndef HAVE_UNISTD_H
#define HAVE_UNISTD_H 1
#endif
/* Define to 1 if the system has the type `unsigned long long'. */
#ifndef HAVE_UNSIGNED_LONG_LONG
#define HAVE_UNSIGNED_LONG_LONG 1
#endif
/* Define to 1 if you have the <windows.h> header file. */
/* #undef HAVE_WINDOWS_H */
/* The value of LINK_SIZE determines the number of bytes used to store links
as offsets within the compiled regex. The default is 2, which allows for
compiled patterns up to 64K long. This covers the vast majority of cases.
However, PCRE can also be compiled to use 3 or 4 bytes instead. This allows
for longer patterns in extreme cases. On systems that support it,
"configure" can be used to override this default. */
#ifndef LINK_SIZE
#define LINK_SIZE 2
#endif
/* The value of MATCH_LIMIT determines the default number of times the
internal match() function can be called during a single execution of
pcre_exec(). There is a runtime interface for setting a different limit.
The limit exists in order to catch runaway regular expressions that take
for ever to determine that they do not match. The default is set very large
so that it does not accidentally catch legitimate cases. On systems that
support it, "configure" can be used to override this default default. */
#ifndef MATCH_LIMIT
#define MATCH_LIMIT 10000000
#endif
/* The above limit applies to all calls of match(), whether or not they
increase the recursion depth. In some environments it is desirable to limit
the depth of recursive calls of match() more strictly, in order to restrict
the maximum amount of stack (or heap, if NO_RECURSE is defined) that is
used. The value of MATCH_LIMIT_RECURSION applies only to recursive calls of
match(). To have any useful effect, it must be less than the value of
MATCH_LIMIT. The default is to use the same value as MATCH_LIMIT. There is
a runtime method for setting a different limit. On systems that support it,
"configure" can be used to override the default. */
#ifndef MATCH_LIMIT_RECURSION
#define MATCH_LIMIT_RECURSION MATCH_LIMIT
#endif
/* This limit is parameterized just in case anybody ever wants to change it.
Care must be taken if it is increased, because it guards against integer
overflow caused by enormously large patterns. */
#ifndef MAX_DUPLENGTH
#define MAX_DUPLENGTH 30000
#endif
/* This limit is parameterized just in case anybody ever wants to change it.
Care must be taken if it is increased, because it guards against integer
overflow caused by enormously large patterns. */
#ifndef MAX_NAME_COUNT
#define MAX_NAME_COUNT 10000
#endif
/* This limit is parameterized just in case anybody ever wants to change it.
Care must be taken if it is increased, because it guards against integer
overflow caused by enormously large patterns. */
#ifndef MAX_NAME_SIZE
#define MAX_NAME_SIZE 32
#endif
/* The value of NEWLINE determines the newline character sequence. On
Unix-like systems, "configure" can be used to override the default, which
is 10. The possible values are 10 (LF), 13 (CR), 3338 (CRLF), -1 (ANY), or
-2 (ANYCRLF). */
#ifndef NEWLINE
#define NEWLINE 10
#endif
/* PCRE uses recursive function calls to handle backtracking while matching.
This can sometimes be a problem on systems that have stacks of limited
size. Define NO_RECURSE to get a version that doesn't use recursion in the
match() function; instead it creates its own stack by steam using
pcre_recurse_malloc() to obtain memory from the heap. For more detail, see
the comments and other stuff just above the match() function. On systems
that support it, "configure" can be used to set this in the Makefile (use
--disable-stack-for-recursion). */
/* #undef NO_RECURSE */
/* Name of package */
#define PACKAGE "pcre"
/* Define to the address where bug reports for this package should be sent. */
#define PACKAGE_BUGREPORT ""
/* Define to the full name of this package. */
#define PACKAGE_NAME "PCRE"
/* Define to the full name and version of this package. */
#define PACKAGE_STRING "PCRE 7.2-RC3"
/* Define to the one symbol short name of this package. */
#define PACKAGE_TARNAME "pcre"
/* Define to the version of this package. */
#define PACKAGE_VERSION "7.2-RC3"
/* If you are compiling for a system other than a Unix-like system or
Win32, and it needs some magic to be inserted before the definition
of a function that is exported by the library, define this macro to
contain the relevant magic. If you do not define this macro, it
defaults to "extern" for a C compiler and "extern C" for a C++
compiler on non-Win32 systems. This macro apears at the start of
every exported function that is part of the external API. It does
not appear on functions that are "external" in the C sense, but
which are internal to the library. */
/* #undef PCRE_EXP_DEFN */
/* Define if linking statically (TODO: make nice with Libtool) */
/* #undef PCRE_STATIC */
/* When calling PCRE via the POSIX interface, additional working storage is
required for holding the pointers to capturing substrings because PCRE
requires three integers per substring, whereas the POSIX interface provides
only two. If the number of expected substrings is small, the wrapper
function uses space on the stack, because this is faster than using
malloc() for each call. The threshold above which the stack is no longer
used is defined by POSIX_MALLOC_THRESHOLD. On systems that support it,
"configure" can be used to override this default. */
#ifndef POSIX_MALLOC_THRESHOLD
#define POSIX_MALLOC_THRESHOLD 10
#endif
/* Define to 1 if you have the ANSI C header files. */
#ifndef STDC_HEADERS
#define STDC_HEADERS 1
#endif
/* Define to enable support for Unicode properties */
/* #undef SUPPORT_UCP */
/* Define to enable support for the UTF-8 Unicode encoding. */
/* #undef SUPPORT_UTF8 */
/* Version number of package */
#ifndef VERSION
#define VERSION "7.2-RC3"
#endif
/* Define to empty if `const' does not conform to ANSI C. */
/* #undef const */
/* Define to `unsigned int' if <sys/types.h> does not define. */
/* #undef size_t */

47
ext/pcre/pcrelib/dftables.c
View File

@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2006 University of Cambridge
Copyright (c) 1997-2007 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -38,14 +38,15 @@ POSSIBILITY OF SUCH DAMAGE.
*/
/* This is a freestanding support program to generate a file containing default
character tables for PCRE. The tables are built according to the default C
/* This is a freestanding support program to generate a file containing
character tables for PCRE. The tables are built according to the current
locale. Now that pcre_maketables is a function visible to the outside world, we
make use of its code from here in order to be consistent. */
#include <ctype.h>
#include <stdio.h>
#include <string.h>
#include <locale.h>
#include "pcre_internal.h"
@ -55,38 +56,48 @@ make use of its code from here in order to be consistent. */
int main(int argc, char **argv)
{
int i;
FILE *f;
const unsigned char *tables = pcre_maketables();
const unsigned char *base_of_tables = tables;
int i = 1;
const unsigned char *tables;
const unsigned char *base_of_tables;
if (argc != 2)
/* By default, the default C locale is used rather than what the building user
happens to have set. However, if the -L option is given, set the locale from
the LC_xxx environment variables. */
if (argc > 1 && strcmp(argv[1], "-L") == 0)
{
setlocale(LC_ALL, ""); /* Set from environment variables */
i++;
}
if (argc < i + 1)
{
fprintf(stderr, "dftables: one filename argument is required\n");
return 1;
}
f = fopen(argv[1], "wb");
tables = pcre_maketables();
base_of_tables = tables;
f = fopen(argv[i], "wb");
if (f == NULL)
{
fprintf(stderr, "dftables: failed to open %s for writing\n", argv[1]);
return 1;
}
/* There are two fprintf() calls here, because gcc in pedantic mode complains
about the very long string otherwise. */
/* There are several fprintf() calls here, because gcc in pedantic mode
complains about the very long string otherwise. */
fprintf(f,
"/*************************************************\n"
"* Perl-Compatible Regular Expressions *\n"
"*************************************************/\n\n"
"/* This file is automatically written by the dftables auxiliary \n"
"program. If you edit it by hand, you might like to edit the Makefile to \n"
"prevent its ever being regenerated.\n\n");
fprintf(f,
"This file contains the default tables for characters with codes less than\n"
"128 (ASCII characters). These tables are used when no external tables are\n"
"passed to PCRE.\n\n");
"/* This file was automatically written by the dftables auxiliary\n"
"program. It contains character tables that are used when no external\n"
"tables are passed to PCRE by the application that calls it. The tables\n"
"are used only for characters whose code values are less than 256.\n\n");
fprintf(f,
"The following #include is present because without it gcc 4.x may remove\n"
"the array definition from the final binary if PCRE is built into a static\n"
@ -171,7 +182,7 @@ if (isprint(i-8)) fprintf(f, " %c -", i-8);
else fprintf(f, "%3d-", i-8);
if (isprint(i-1)) fprintf(f, " %c ", i-1);
else fprintf(f, "%3d", i-1);
fprintf(f, " */\n\n/* End of chartables.c */\n");
fprintf(f, " */\n\n/* End of pcre_chartables.c */\n");
fclose(f);
free((void *)base_of_tables);

1532
ext/pcre/pcrelib/doc/pcre.txt
View File

File diff suppressed because it is too large Load Diff

20
ext/pcre/pcrelib/libpcre.def
View File

@ -1,20 +0,0 @@
LIBRARY libpcre
EXPORTS
pcre_malloc
pcre_free
pcre_config
pcre_callout
pcre_compile
pcre_copy_substring
pcre_dfa_exec
pcre_exec
pcre_get_substring
pcre_get_stringnumber
pcre_get_substring_list
pcre_free_substring
pcre_free_substring_list
pcre_info
pcre_fullinfo
pcre_maketables
pcre_study
pcre_version

25
ext/pcre/pcrelib/libpcreposix.def
View File

@ -1,25 +0,0 @@
LIBRARY libpcreposix
EXPORTS
pcre_malloc
pcre_free
pcre_config
pcre_callout
pcre_compile
pcre_copy_substring
pcre_dfa_exec
pcre_exec
pcre_get_substring
pcre_get_stringnumber
pcre_get_substring_list
pcre_free_substring
pcre_free_substring_list
pcre_info
pcre_fullinfo
pcre_maketables
pcre_study
pcre_version
regcomp
regexec
regerror
regfree

29
ext/pcre/pcrelib/pcre.def
View File

@ -1,29 +0,0 @@
EXPORTS
pcre_malloc DATA
pcre_free DATA
pcre_compile
pcre_compile2
pcre_config
pcre_copy_named_substring
pcre_copy_substring
pcre_dfa_exec
pcre_exec
pcre_free_substring
pcre_free_substring_list
pcre_fullinfo
pcre_get_named_substring
pcre_get_stringnumber
pcre_get_substring
pcre_get_substring_list
pcre_info
pcre_maketables
pcre_refcount
pcre_study
pcre_version
regcomp
regexec
regerror
regfree

108
ext/pcre/pcrelib/pcre.h
View File

@ -5,7 +5,7 @@
/* This is the public header file for the PCRE library, to be #included by
applications that call the PCRE functions.
Copyright (c) 1997-2006 University of Cambridge
Copyright (c) 1997-2007 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -39,48 +39,33 @@ POSSIBILITY OF SUCH DAMAGE.
#ifndef _PCRE_H
#define _PCRE_H
#include "php_compat.h"
/* The current PCRE version information. */
/* NOTES FOR FUTURE MAINTAINERS: Do not use numbers with leading zeros, because
they may be treated as octal constants. The PCRE_PRERELEASE feature is for
identifying release candidates. It might be defined as -RC2, for example. In
real releases, it should be defined empty. Do not change the alignment of these
statments. The code in ./configure greps out the version numbers by using "cut"
to get values from column 29 onwards. These are substituted into pcre-config
and libpcre.pc. The values are not put into configure.ac and substituted here
(which would simplify this issue) because that makes life harder for those who
cannot run ./configure. As it now stands, this file need not be edited in that
circumstance. */
#define PCRE_MAJOR 7
#define PCRE_MINOR 0
#define PCRE_PRERELEASE
#define PCRE_DATE 18-Dec-2006
#define PCRE_MINOR 2
#define PCRE_PRERELEASE -RC3
#define PCRE_DATE 2007-06-13
/* Win32 uses DLL by default; it needs special stuff for exported functions
when building PCRE. */
/* When an application links to a PCRE DLL in Windows, the symbols that are
imported have to be identified as such. When building PCRE, the appropriate
export setting is defined in pcre_internal.h, which includes this file. So we
don't change an existing definition of PCRE_EXP_DECL. */
#ifdef _WIN32
# ifdef PCRE_DEFINITION
# ifdef DLL_EXPORT
# define PCRE_DATA_SCOPE __declspec(dllexport)
# endif
# else
#ifndef PCRE_EXP_DECL
# ifdef _WIN32
# ifndef PCRE_STATIC
# define PCRE_DATA_SCOPE extern __declspec(dllimport)
# define PCRE_EXP_DECL extern __declspec(dllimport)
# endif
# endif
#endif
/* Otherwise, we use the standard "extern". */
/* By default, we use the standard "extern" declarations. */
#ifndef PCRE_DATA_SCOPE
#ifndef PCRE_EXP_DECL
# ifdef __cplusplus
# define PCRE_DATA_SCOPE extern "C"
# define PCRE_EXP_DECL extern "C"
# else
# define PCRE_DATA_SCOPE extern
# define PCRE_EXP_DECL extern
# endif
#endif
@ -121,6 +106,7 @@ extern "C" {
#define PCRE_NEWLINE_LF 0x00200000
#define PCRE_NEWLINE_CRLF 0x00300000
#define PCRE_NEWLINE_ANY 0x00400000
#define PCRE_NEWLINE_ANYCRLF 0x00500000
/* Exec-time and get/set-time error codes */
@ -164,6 +150,8 @@ extern "C" {
#define PCRE_INFO_NAMETABLE 9
#define PCRE_INFO_STUDYSIZE 10
#define PCRE_INFO_DEFAULT_TABLES 11
#define PCRE_INFO_OKPARTIAL 12
#define PCRE_INFO_JCHANGED 13
/* Request types for pcre_config(). Do not re-arrange, in order to remain
compatible. */
@ -242,52 +230,52 @@ that is triggered by the (?) regex item. For Virtual Pascal, these definitions
have to take another form. */
#ifndef VPCOMPAT
PCRE_DATA_SCOPE void *(*pcre_malloc)(size_t);
PCRE_DATA_SCOPE void (*pcre_free)(void *);
PCRE_DATA_SCOPE void *(*pcre_stack_malloc)(size_t);
PCRE_DATA_SCOPE void (*pcre_stack_free)(void *);
PCRE_DATA_SCOPE int (*pcre_callout)(pcre_callout_block *);
PCRE_EXP_DECL void *(*pcre_malloc)(size_t);
PCRE_EXP_DECL void (*pcre_free)(void *);
PCRE_EXP_DECL void *(*pcre_stack_malloc)(size_t);
PCRE_EXP_DECL void (*pcre_stack_free)(void *);
PCRE_EXP_DECL int (*pcre_callout)(pcre_callout_block *);
#else /* VPCOMPAT */
PCRE_DATA_SCOPE void *pcre_malloc(size_t);
PCRE_DATA_SCOPE void pcre_free(void *);
PCRE_DATA_SCOPE void *pcre_stack_malloc(size_t);
PCRE_DATA_SCOPE void pcre_stack_free(void *);
PCRE_DATA_SCOPE int pcre_callout(pcre_callout_block *);
PCRE_EXP_DECL void *pcre_malloc(size_t);
PCRE_EXP_DECL void pcre_free(void *);
PCRE_EXP_DECL void *pcre_stack_malloc(size_t);
PCRE_EXP_DECL void pcre_stack_free(void *);
PCRE_EXP_DECL int pcre_callout(pcre_callout_block *);
#endif /* VPCOMPAT */
/* Exported PCRE functions */
PCRE_DATA_SCOPE pcre *pcre_compile(const char *, int, const char **, int *,
PCRE_EXP_DECL pcre *pcre_compile(const char *, int, const char **, int *,
const unsigned char *);
PCRE_DATA_SCOPE pcre *pcre_compile2(const char *, int, int *, const char **,
PCRE_EXP_DECL pcre *pcre_compile2(const char *, int, int *, const char **,
int *, const unsigned char *);
PCRE_DATA_SCOPE int pcre_config(int, void *);
PCRE_DATA_SCOPE int pcre_copy_named_substring(const pcre *, const char *,
PCRE_EXP_DECL int pcre_config(int, void *);
PCRE_EXP_DECL int pcre_copy_named_substring(const pcre *, const char *,
int *, int, const char *, char *, int);
PCRE_DATA_SCOPE int pcre_copy_substring(const char *, int *, int, int, char *,
PCRE_EXP_DECL int pcre_copy_substring(const char *, int *, int, int, char *,
int);
PCRE_DATA_SCOPE int pcre_dfa_exec(const pcre *, const pcre_extra *,
PCRE_EXP_DECL int pcre_dfa_exec(const pcre *, const pcre_extra *,
const char *, int, int, int, int *, int , int *, int);
PCRE_DATA_SCOPE int pcre_exec(const pcre *, const pcre_extra *, PCRE_SPTR,
PCRE_EXP_DECL int pcre_exec(const pcre *, const pcre_extra *, PCRE_SPTR,
int, int, int, int *, int);
PCRE_DATA_SCOPE void pcre_free_substring(const char *);
PCRE_DATA_SCOPE void pcre_free_substring_list(const char **);
PCRE_DATA_SCOPE int pcre_fullinfo(const pcre *, const pcre_extra *, int,
PCRE_EXP_DECL void pcre_free_substring(const char *);
PCRE_EXP_DECL void pcre_free_substring_list(const char **);
PCRE_EXP_DECL int pcre_fullinfo(const pcre *, const pcre_extra *, int,
void *);
PCRE_DATA_SCOPE int pcre_get_named_substring(const pcre *, const char *,
PCRE_EXP_DECL int pcre_get_named_substring(const pcre *, const char *,
int *, int, const char *, const char **);
PCRE_DATA_SCOPE int pcre_get_stringnumber(const pcre *, const char *);
PCRE_DATA_SCOPE int pcre_get_stringtable_entries(const pcre *, const char *,
PCRE_EXP_DECL int pcre_get_stringnumber(const pcre *, const char *);
PCRE_EXP_DECL int pcre_get_stringtable_entries(const pcre *, const char *,
char **, char **);
PCRE_DATA_SCOPE int pcre_get_substring(const char *, int *, int, int,
PCRE_EXP_DECL int pcre_get_substring(const char *, int *, int, int,
const char **);
PCRE_DATA_SCOPE int pcre_get_substring_list(const char *, int *, int,
PCRE_EXP_DECL int pcre_get_substring_list(const char *, int *, int,
const char ***);
PCRE_DATA_SCOPE int pcre_info(const pcre *, int *, int *);
PCRE_DATA_SCOPE const unsigned char *pcre_maketables(void);
PCRE_DATA_SCOPE int pcre_refcount(pcre *, int);
PCRE_DATA_SCOPE pcre_extra *pcre_study(const pcre *, int, const char **);
PCRE_DATA_SCOPE const char *pcre_version(void);
PCRE_EXP_DECL int pcre_info(const pcre *, int *, int *);
PCRE_EXP_DECL const unsigned char *pcre_maketables(void);
PCRE_EXP_DECL int pcre_refcount(pcre *, int);
PCRE_EXP_DECL pcre_extra *pcre_study(const pcre *, int, const char **);
PCRE_EXP_DECL const char *pcre_version(void);
#ifdef __cplusplus
} /* extern "C" */

37
ext/pcre/pcrelib/pcre_chartables.c
View File

@ -2,13 +2,25 @@
* Perl-Compatible Regular Expressions *
*************************************************/
/* This file is automatically written by the dftables auxiliary
program. If you edit it by hand, you might like to edit the Makefile to
prevent its ever being regenerated.
/* This file contains character tables that are used when no external tables
are passed to PCRE by the application that calls it. The tables are used only
for characters whose code values are less than 256.
This file contains the default tables for characters with codes less than
128 (ASCII characters). These tables are used when no external tables are
passed to PCRE. */
This is a default version of the tables that assumes ASCII encoding. A program
called dftables (which is distributed with PCRE) can be used to build
alternative versions of this file. This is necessary if you are running in an
EBCDIC environment, or if you want to default to a different encoding, for
example ISO-8859-1. When dftables is run, it creates these tables in the
current locale. If PCRE is configured with --enable-rebuild-chartables, this
happens automatically.
The following #include is present because without it gcc 4.x may remove the
array definition from the final binary if PCRE is built into a static library
and dead code stripping is activated. This leads to link errors. Pulling in the
header ensures that the array gets flagged as "someone outside this compilation
unit might reference this" and so it will always be supplied to the linker. */
#include "pcre_internal.h"
const unsigned char _pcre_default_tables[] = {
@ -82,11 +94,10 @@ const unsigned char _pcre_default_tables[] = {
240,241,242,243,244,245,246,247,
248,249,250,251,252,253,254,255,
/* This table contains bit maps for various character classes.
Each map is 32 bytes long and the bits run from the least
significant end of each byte. The classes that have their own
maps are: space, xdigit, digit, upper, lower, word, graph
print, punct, and cntrl. Other classes are built from combinations. */
/* This table contains bit maps for various character classes. Each map is 32
bytes long and the bits run from the least significant end of each byte. The
classes that have their own maps are: space, xdigit, digit, upper, lower, word,
graph, print, punct, and cntrl. Other classes are built from combinations. */
0x00,0x3e,0x00,0x00,0x01,0x00,0x00,0x00,
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
@ -158,7 +169,7 @@ print, punct, and cntrl. Other classes are built from combinations. */
0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* @ - G */
0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* H - O */
0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* P - W */
0x12,0x12,0x12,0x80,0x00,0x00,0x80,0x10, /* X - _ */
0x12,0x12,0x12,0x80,0x80,0x00,0x80,0x10, /* X - _ */
0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* ` - g */
0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* h - o */
0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* p - w */
@ -180,4 +191,4 @@ print, punct, and cntrl. Other classes are built from combinations. */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 240-247 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */
/* End of chartables.c */
/* End of pcre_chartables.c */

544
ext/pcre/pcrelib/pcre_compile.c
View File

@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2006 University of Cambridge
Copyright (c) 1997-2007 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -58,6 +58,11 @@ used by pcretest. DEBUG is not defined when building a production library. */
#endif
/* Macro for setting individual bits in class bitmaps. */
#define SETBIT(a,b) a[b/8] |= (1 << (b%8))
/*************************************************
* Code parameters and static tables *
*************************************************/
@ -82,21 +87,21 @@ are simple data values; negative values are for special things like \d and so
on. Zero means further processing is needed (for things like \x), or the escape
is invalid. */
#if !EBCDIC /* This is the "normal" table for ASCII systems */
#ifndef EBCDIC /* This is the "normal" table for ASCII systems */
static const short int escapes[] = {
0, 0, 0, 0, 0, 0, 0, 0, /* 0 - 7 */
0, 0, ':', ';', '<', '=', '>', '?', /* 8 - ? */
'@', -ESC_A, -ESC_B, -ESC_C, -ESC_D, -ESC_E, 0, -ESC_G, /* @ - G */
0, 0, 0, 0, 0, 0, 0, 0, /* H - O */
-ESC_P, -ESC_Q, -ESC_R, -ESC_S, 0, 0, 0, -ESC_W, /* P - W */
-ESC_H, 0, 0, -ESC_K, 0, 0, 0, 0, /* H - O */
-ESC_P, -ESC_Q, -ESC_R, -ESC_S, 0, 0, -ESC_V, -ESC_W, /* P - W */
-ESC_X, 0, -ESC_Z, '[', '\\', ']', '^', '_', /* X - _ */
'`', 7, -ESC_b, 0, -ESC_d, ESC_e, ESC_f, 0, /* ` - g */
0, 0, 0, -ESC_k, 0, 0, ESC_n, 0, /* h - o */
-ESC_p, 0, ESC_r, -ESC_s, ESC_tee, 0, 0, -ESC_w, /* p - w */
-ESC_h, 0, 0, -ESC_k, 0, 0, ESC_n, 0, /* h - o */
-ESC_p, 0, ESC_r, -ESC_s, ESC_tee, 0, -ESC_v, -ESC_w, /* p - w */
0, 0, -ESC_z /* x - z */
};
#else /* This is the "abnormal" table for EBCDIC systems */
#else /* This is the "abnormal" table for EBCDIC systems */
static const short int escapes[] = {
/* 48 */ 0, 0, 0, '.', '<', '(', '+', '|',
/* 50 */ '&', 0, 0, 0, 0, 0, 0, 0,
@ -106,18 +111,18 @@ static const short int escapes[] = {
/* 70 */ 0, 0, 0, 0, 0, 0, 0, 0,
/* 78 */ 0, '`', ':', '#', '@', '\'', '=', '"',
/* 80 */ 0, 7, -ESC_b, 0, -ESC_d, ESC_e, ESC_f, 0,
/* 88 */ 0, 0, 0, '{', 0, 0, 0, 0,
/* 88 */-ESC_h, 0, 0, '{', 0, 0, 0, 0,
/* 90 */ 0, 0, -ESC_k, 'l', 0, ESC_n, 0, -ESC_p,
/* 98 */ 0, ESC_r, 0, '}', 0, 0, 0, 0,
/* A0 */ 0, '~', -ESC_s, ESC_tee, 0, 0, -ESC_w, 0,
/* A0 */ 0, '~', -ESC_s, ESC_tee, 0,-ESC_v, -ESC_w, 0,
/* A8 */ 0,-ESC_z, 0, 0, 0, '[', 0, 0,
/* B0 */ 0, 0, 0, 0, 0, 0, 0, 0,
/* B8 */ 0, 0, 0, 0, 0, ']', '=', '-',
/* C0 */ '{',-ESC_A, -ESC_B, -ESC_C, -ESC_D,-ESC_E, 0, -ESC_G,
/* C8 */ 0, 0, 0, 0, 0, 0, 0, 0,
/* C8 */-ESC_H, 0, 0, 0, 0, 0, 0, 0,
/* D0 */ '}', 0, 0, 0, 0, 0, 0, -ESC_P,
/* D8 */-ESC_Q,-ESC_R, 0, 0, 0, 0, 0, 0,
/* E0 */ '\\', 0, -ESC_S, 0, 0, 0, -ESC_W, -ESC_X,
/* E0 */ '\\', 0, -ESC_S, 0, 0,-ESC_V, -ESC_W, -ESC_X,
/* E8 */ 0,-ESC_Z, 0, 0, 0, 0, 0, 0,
/* F0 */ 0, 0, 0, 0, 0, 0, 0, 0,
/* F8 */ 0, 0, 0, 0, 0, 0, 0, 0
@ -208,7 +213,7 @@ static const char *error_texts[] = {
"malformed number or name after (?(",
"conditional group contains more than two branches",
"assertion expected after (?(",
"(?R or (?digits must be followed by )",
"(?R or (?[+-]digits must be followed by )",
/* 30 */
"unknown POSIX class name",
"POSIX collating elements are not supported",
@ -242,7 +247,8 @@ static const char *error_texts[] = {
/* 55 */
"repeating a DEFINE group is not allowed",
"inconsistent NEWLINE options",
"\\g is not followed by an (optionally braced) non-zero number"
"\\g is not followed by a braced name or an optionally braced non-zero number",
"(?+ or (?- or (?(+ or (?(- must be followed by a non-zero number"
};
@ -262,7 +268,7 @@ For convenience, we use the same bit definitions as in chartables:
Then we can use ctype_digit and ctype_xdigit in the code. */
#if !EBCDIC /* This is the "normal" case, for ASCII systems */
#ifndef EBCDIC /* This is the "normal" case, for ASCII systems */
static const unsigned char digitab[] =
{
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 */
@ -298,7 +304,7 @@ static const unsigned char digitab[] =
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 240-247 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */
#else /* This is the "abnormal" case, for EBCDIC systems */
#else /* This is the "abnormal" case, for EBCDIC systems */
static const unsigned char digitab[] =
{
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 0 */
@ -312,7 +318,7 @@ static const unsigned char digitab[] =
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - 71 40 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 72- | */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* & - 87 50 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 88- ¬ */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 88- 95 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - -103 60 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 104- ? */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 112-119 70 */
@ -346,7 +352,7 @@ static const unsigned char ebcdic_chartab[] = { /* chartable partial dup */
0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - 71 */
0x00,0x00,0x00,0x80,0x00,0x80,0x80,0x80, /* 72- | */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* & - 87 */
0x00,0x00,0x00,0x80,0x80,0x80,0x00,0x00, /* 88- ¬ */
0x00,0x00,0x00,0x80,0x80,0x80,0x00,0x00, /* 88- 95 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - -103 */
0x00,0x00,0x00,0x00,0x00,0x10,0x00,0x80, /* 104- ? */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 112-119 */
@ -373,8 +379,8 @@ static const unsigned char ebcdic_chartab[] = { /* chartable partial dup */
/* Definition to allow mutual recursion */
static BOOL
compile_regex(int, int, uschar **, const uschar **, int *, BOOL, int, int *,
int *, branch_chain *, compile_data *, int *);
compile_regex(int, int, uschar **, const uschar **, int *, BOOL, BOOL, int,
int *, int *, branch_chain *, compile_data *, int *);
@ -421,11 +427,11 @@ if (c == 0) *errorcodeptr = ERR1;
a table. A non-zero result is something that can be returned immediately.
Otherwise further processing may be required. */
#if !EBCDIC /* ASCII coding */
#ifndef EBCDIC /* ASCII coding */
else if (c < '0' || c > 'z') {} /* Not alphameric */
else if ((i = escapes[c - '0']) != 0) c = i;
#else /* EBCDIC coding */
#else /* EBCDIC coding */
else if (c < 'a' || (ebcdic_chartab[c] & 0x0E) == 0) {} /* Not alphameric */
else if ((i = escapes[c - 0x48]) != 0) c = i;
#endif
@ -452,11 +458,22 @@ else
/* \g must be followed by a number, either plain or braced. If positive, it
is an absolute backreference. If negative, it is a relative backreference.
This is a Perl 5.10 feature. */
This is a Perl 5.10 feature. Perl 5.10 also supports \g{name} as a
reference to a named group. This is part of Perl's movement towards a
unified syntax for back references. As this is synonymous with \k{name}, we
fudge it up by pretending it really was \k. */
case 'g':
if (ptr[1] == '{')
{
const uschar *p;
for (p = ptr+2; *p != 0 && *p != '}'; p++)
if (*p != '-' && (digitab[*p] & ctype_digit) == 0) break;
if (*p != 0 && *p != '}')
{
c = -ESC_k;
break;
}
braced = TRUE;
ptr++;
}
@ -562,10 +579,10 @@ else
if (c == 0 && cc == '0') continue; /* Leading zeroes */
count++;
#if !EBCDIC /* ASCII coding */
#ifndef EBCDIC /* ASCII coding */
if (cc >= 'a') cc -= 32; /* Convert to upper case */
c = (c << 4) + cc - ((cc < 'A')? '0' : ('A' - 10));
#else /* EBCDIC coding */
#else /* EBCDIC coding */
if (cc >= 'a' && cc <= 'z') cc += 64; /* Convert to upper case */
c = (c << 4) + cc - ((cc >= '0')? '0' : ('A' - 10));
#endif
@ -589,10 +606,10 @@ else
{
int cc; /* Some compilers don't like ++ */
cc = *(++ptr); /* in initializers */
#if !EBCDIC /* ASCII coding */
#ifndef EBCDIC /* ASCII coding */
if (cc >= 'a') cc -= 32; /* Convert to upper case */
c = c * 16 + cc - ((cc < 'A')? '0' : ('A' - 10));
#else /* EBCDIC coding */
#else /* EBCDIC coding */
if (cc <= 'z') cc += 64; /* Convert to upper case */
c = c * 16 + cc - ((cc >= '0')? '0' : ('A' - 10));
#endif
@ -611,10 +628,10 @@ else
return 0;
}
#if !EBCDIC /* ASCII coding */
#ifndef EBCDIC /* ASCII coding */
if (c >= 'a' && c <= 'z') c -= 32;
c ^= 0x40;
#else /* EBCDIC coding */
#else /* EBCDIC coding */
if (c >= 'a' && c <= 'z') c += 64;
c ^= 0xC0;
#endif
@ -1246,6 +1263,7 @@ for (;;)
else
{
code += _pcre_OP_lengths[c];
#ifdef SUPPORT_UTF8
if (utf8) switch(c)
{
case OP_CHAR:
@ -1266,6 +1284,7 @@ for (;;)
if (code[-1] >= 0xc0) code += _pcre_utf8_table4[code[-1] & 0x3f];
break;
}
#endif
}
}
}
@ -1309,6 +1328,7 @@ for (;;)
else
{
code += _pcre_OP_lengths[c];
#ifdef SUPPORT_UTF8
if (utf8) switch(c)
{
case OP_CHAR:
@ -1329,6 +1349,7 @@ for (;;)
if (code[-1] >= 0xc0) code += _pcre_utf8_table4[code[-1] & 0x3f];
break;
}
#endif
}
}
}
@ -1366,6 +1387,18 @@ for (code = first_significant_code(code + _pcre_OP_lengths[*code], NULL, 0, TRUE
c = *code;
/* Groups with zero repeats can of course be empty; skip them. */
if (c == OP_BRAZERO || c == OP_BRAMINZERO)
{
code += _pcre_OP_lengths[c];
do code += GET(code, 1); while (*code == OP_ALT);
c = *code;
continue;
}
/* For other groups, scan the branches. */
if (c == OP_BRA || c == OP_CBRA || c == OP_ONCE)
{
BOOL empty_branch;
@ -1382,12 +1415,7 @@ for (code = first_significant_code(code + _pcre_OP_lengths[*code], NULL, 0, TRUE
}
while (*code == OP_ALT);
if (!empty_branch) return FALSE; /* All branches are non-empty */
/* Move past the KET and fudge things so that the increment in the "for"
above has no effect. */
c = OP_END;
code += 1 + LINK_SIZE - _pcre_OP_lengths[c];
c = *code;
continue;
}
@ -1921,6 +1949,50 @@ if (next >= 0) switch(op_code)
case OP_NOT_WORDCHAR:
return next <= 127 && (cd->ctypes[next] & ctype_word) != 0;
case OP_HSPACE:
case OP_NOT_HSPACE:
switch(next)
{
case 0x09:
case 0x20:
case 0xa0:
case 0x1680:
case 0x180e:
case 0x2000:
case 0x2001:
case 0x2002:
case 0x2003:
case 0x2004:
case 0x2005:
case 0x2006:
case 0x2007:
case 0x2008:
case 0x2009:
case 0x200A:
case 0x202f:
case 0x205f:
case 0x3000:
return op_code != OP_HSPACE;
default:
return op_code == OP_HSPACE;
}
case OP_VSPACE:
case OP_NOT_VSPACE:
switch(next)
{
case 0x0a:
case 0x0b:
case 0x0c:
case 0x0d:
case 0x85:
case 0x2028:
case 0x2029:
return op_code != OP_VSPACE;
default:
return op_code == OP_VSPACE;
}
default:
return FALSE;
}
@ -1955,12 +2027,57 @@ switch(op_code)
case ESC_W:
return item <= 127 && (cd->ctypes[item] & ctype_word) != 0;
case ESC_h:
case ESC_H:
switch(item)
{
case 0x09:
case 0x20:
case 0xa0:
case 0x1680:
case 0x180e:
case 0x2000:
case 0x2001:
case 0x2002:
case 0x2003:
case 0x2004:
case 0x2005:
case 0x2006:
case 0x2007:
case 0x2008:
case 0x2009:
case 0x200A:
case 0x202f:
case 0x205f:
case 0x3000:
return -next != ESC_h;
default:
return -next == ESC_h;
}
case ESC_v:
case ESC_V:
switch(item)
{
case 0x0a:
case 0x0b:
case 0x0c:
case 0x0d:
case 0x85:
case 0x2028:
case 0x2029:
return -next != ESC_v;
default:
return -next == ESC_v;
}
default:
return FALSE;
}
case OP_DIGIT:
return next == -ESC_D || next == -ESC_s || next == -ESC_W;
return next == -ESC_D || next == -ESC_s || next == -ESC_W ||
next == -ESC_h || next == -ESC_v;
case OP_NOT_DIGIT:
return next == -ESC_d;
@ -1969,10 +2086,23 @@ switch(op_code)
return next == -ESC_S || next == -ESC_d || next == -ESC_w;
case OP_NOT_WHITESPACE:
return next == -ESC_s;
return next == -ESC_s || next == -ESC_h || next == -ESC_v;
case OP_HSPACE:
return next == -ESC_S || next == -ESC_H || next == -ESC_d || next == -ESC_w;
case OP_NOT_HSPACE:
return next == -ESC_h;
/* Can't have \S in here because VT matches \S (Perl anomaly) */
case OP_VSPACE:
return next == -ESC_V || next == -ESC_d || next == -ESC_w;
case OP_NOT_VSPACE:
return next == -ESC_v;
case OP_WORDCHAR:
return next == -ESC_W || next == -ESC_s;
return next == -ESC_W || next == -ESC_s || next == -ESC_h || next == -ESC_v;
case OP_NOT_WORDCHAR:
return next == -ESC_w || next == -ESC_d;
@ -2087,10 +2217,12 @@ for (;; ptr++)
BOOL possessive_quantifier;
BOOL is_quantifier;
BOOL is_recurse;
BOOL reset_bracount;
int class_charcount;
int class_lastchar;
int newoptions;
int recno;
int refsign;
int skipbytes;
int subreqbyte;
int subfirstbyte;
@ -2515,6 +2647,133 @@ for (;; ptr++)
else if (c == -ESC_d || c == -ESC_D || c == -ESC_w ||
c == -ESC_W || c == -ESC_s || c == -ESC_S) continue;
/* We need to deal with \H, \h, \V, and \v in both phases because
they use extra memory. */
if (-c == ESC_h)
{
SETBIT(classbits, 0x09); /* VT */
SETBIT(classbits, 0x20); /* SPACE */
SETBIT(classbits, 0xa0); /* NSBP */
#ifdef SUPPORT_UTF8
if (utf8)
{
class_utf8 = TRUE;
*class_utf8data++ = XCL_SINGLE;
class_utf8data += _pcre_ord2utf8(0x1680, class_utf8data);
*class_utf8data++ = XCL_SINGLE;
class_utf8data += _pcre_ord2utf8(0x180e, class_utf8data);
*class_utf8data++ = XCL_RANGE;
class_utf8data += _pcre_ord2utf8(0x2000, class_utf8data);
class_utf8data += _pcre_ord2utf8(0x200A, class_utf8data);
*class_utf8data++ = XCL_SINGLE;
class_utf8data += _pcre_ord2utf8(0x202f, class_utf8data);
*class_utf8data++ = XCL_SINGLE;
class_utf8data += _pcre_ord2utf8(0x205f, class_utf8data);
*class_utf8data++ = XCL_SINGLE;
class_utf8data += _pcre_ord2utf8(0x3000, class_utf8data);
}
#endif
continue;
}
if (-c == ESC_H)
{
for (c = 0; c < 32; c++)
{
int x = 0xff;
switch (c)
{
case 0x09/8: x ^= 1 << (0x09%8); break;
case 0x20/8: x ^= 1 << (0x20%8); break;
case 0xa0/8: x ^= 1 << (0xa0%8); break;
default: break;
}
classbits[c] |= x;
}
#ifdef SUPPORT_UTF8
if (utf8)
{
class_utf8 = TRUE;
*class_utf8data++ = XCL_RANGE;
class_utf8data += _pcre_ord2utf8(0x0100, class_utf8data);
class_utf8data += _pcre_ord2utf8(0x167f, class_utf8data);
*class_utf8data++ = XCL_RANGE;
class_utf8data += _pcre_ord2utf8(0x1681, class_utf8data);
class_utf8data += _pcre_ord2utf8(0x180d, class_utf8data);
*class_utf8data++ = XCL_RANGE;
class_utf8data += _pcre_ord2utf8(0x180f, class_utf8data);
class_utf8data += _pcre_ord2utf8(0x1fff, class_utf8data);
*class_utf8data++ = XCL_RANGE;
class_utf8data += _pcre_ord2utf8(0x200B, class_utf8data);
class_utf8data += _pcre_ord2utf8(0x202e, class_utf8data);
*class_utf8data++ = XCL_RANGE;
class_utf8data += _pcre_ord2utf8(0x2030, class_utf8data);
class_utf8data += _pcre_ord2utf8(0x205e, class_utf8data);
*class_utf8data++ = XCL_RANGE;
class_utf8data += _pcre_ord2utf8(0x2060, class_utf8data);
class_utf8data += _pcre_ord2utf8(0x2fff, class_utf8data);
*class_utf8data++ = XCL_RANGE;
class_utf8data += _pcre_ord2utf8(0x3001, class_utf8data);
class_utf8data += _pcre_ord2utf8(0x7fffffff, class_utf8data);
}
#endif
continue;
}
if (-c == ESC_v)
{
SETBIT(classbits, 0x0a); /* LF */
SETBIT(classbits, 0x0b); /* VT */
SETBIT(classbits, 0x0c); /* FF */
SETBIT(classbits, 0x0d); /* CR */
SETBIT(classbits, 0x85); /* NEL */
#ifdef SUPPORT_UTF8
if (utf8)
{
class_utf8 = TRUE;
*class_utf8data++ = XCL_RANGE;
class_utf8data += _pcre_ord2utf8(0x2028, class_utf8data);
class_utf8data += _pcre_ord2utf8(0x2029, class_utf8data);
}
#endif
continue;
}
if (-c == ESC_V)
{
for (c = 0; c < 32; c++)
{
int x = 0xff;
switch (c)
{
case 0x0a/8: x ^= 1 << (0x0a%8);
x ^= 1 << (0x0b%8);
x ^= 1 << (0x0c%8);
x ^= 1 << (0x0d%8);
break;
case 0x85/8: x ^= 1 << (0x85%8); break;
default: break;
}
classbits[c] |= x;
}
#ifdef SUPPORT_UTF8
if (utf8)
{
class_utf8 = TRUE;
*class_utf8data++ = XCL_RANGE;
class_utf8data += _pcre_ord2utf8(0x0100, class_utf8data);
class_utf8data += _pcre_ord2utf8(0x2027, class_utf8data);
*class_utf8data++ = XCL_RANGE;
class_utf8data += _pcre_ord2utf8(0x2029, class_utf8data);
class_utf8data += _pcre_ord2utf8(0x7fffffff, class_utf8data);
}
#endif
continue;
}
/* We need to deal with \P and \p in both phases. */
#ifdef SUPPORT_UCP
@ -2655,14 +2914,18 @@ for (;; ptr++)
unsigned int origd = d;
while (get_othercase_range(&cc, origd, &occ, &ocd))
{
if (occ >= c && ocd <= d) continue; /* Skip embedded ranges */
if (occ >= (unsigned int)c &&
ocd <= (unsigned int)d)
continue; /* Skip embedded ranges */
if (occ < c && ocd >= c - 1) /* Extend the basic range */
if (occ < (unsigned int)c &&
ocd >= (unsigned int)c - 1) /* Extend the basic range */
{ /* if there is overlap, */
c = occ; /* noting that if occ < c */
continue; /* we can't have ocd > d */
} /* because a subrange is */
if (ocd > d && occ <= d + 1) /* always shorter than */
if (ocd > (unsigned int)d &&
occ <= (unsigned int)d + 1) /* always shorter than */
{ /* the basic range. */
d = ocd;
continue;
@ -3560,6 +3823,7 @@ for (;; ptr++)
skipbytes = 0;
bravalue = OP_CBRA;
save_hwm = cd->hwm;
reset_bracount = FALSE;
if (*(++ptr) == '?')
{
@ -3581,6 +3845,11 @@ for (;; ptr++)
continue;
/* ------------------------------------------------------------ */
case '|': /* Reset capture count for each branch */
reset_bracount = TRUE;
/* Fall through */
/* ------------------------------------------------------------ */
case ':': /* Non-capturing bracket */
bravalue = OP_BRA;
@ -3617,6 +3886,7 @@ for (;; ptr++)
code[1+LINK_SIZE] = OP_CREF;
skipbytes = 3;
refsign = -1;
/* Check for a test for recursion in a named group. */
@ -3640,7 +3910,11 @@ for (;; ptr++)
terminator = '\'';
ptr++;
}
else terminator = 0;
else
{
terminator = 0;
if (ptr[1] == '-' || ptr[1] == '+') refsign = *(++ptr);
}
/* We now expect to read a name; any thing else is an error */
@ -3676,7 +3950,32 @@ for (;; ptr++)
if (lengthptr != NULL) break;
/* In the real compile we do the work of looking for the actual
reference. */
reference. If the string started with "+" or "-" we require the rest to
be digits, in which case recno will be set. */
if (refsign > 0)
{
if (recno <= 0)
{
*errorcodeptr = ERR58;
goto FAILED;
}
if (refsign == '-')
{
recno = cd->bracount - recno + 1;
if (recno <= 0)
{
*errorcodeptr = ERR15;
goto FAILED;
}
}
else recno += cd->bracount;
PUT2(code, 2+LINK_SIZE, recno);
break;
}
/* Otherwise (did not start with "+" or "-"), start by looking for the
name. */
slot = cd->name_table;
for (i = 0; i < cd->names_found; i++)
@ -3995,19 +4294,54 @@ for (;; ptr++)
/* ------------------------------------------------------------ */
case '-': case '+':
case '0': case '1': case '2': case '3': case '4': /* Recursion or */
case '5': case '6': case '7': case '8': case '9': /* subroutine */
{
const uschar *called;
if ((refsign = *ptr) == '+') ptr++;
else if (refsign == '-')
{
if ((digitab[ptr[1]] & ctype_digit) == 0)
goto OTHER_CHAR_AFTER_QUERY;
ptr++;
}
recno = 0;
while((digitab[*ptr] & ctype_digit) != 0)
recno = recno * 10 + *ptr++ - '0';
if (*ptr != ')')
{
*errorcodeptr = ERR29;
goto FAILED;
}
if (refsign == '-')
{
if (recno == 0)
{
*errorcodeptr = ERR58;
goto FAILED;
}
recno = cd->bracount - recno + 1;
if (recno <= 0)
{
*errorcodeptr = ERR15;
goto FAILED;
}
}
else if (refsign == '+')
{
if (recno == 0)
{
*errorcodeptr = ERR58;
goto FAILED;
}
recno += cd->bracount;
}
/* Come here from code above that handles a named recursion */
HANDLE_RECURSION:
@ -4080,6 +4414,7 @@ for (;; ptr++)
/* ------------------------------------------------------------ */
default: /* Other characters: check option setting */
OTHER_CHAR_AFTER_QUERY:
set = unset = 0;
optset = &set;
@ -4214,6 +4549,7 @@ for (;; ptr++)
errorcodeptr, /* Where to put an error message */
(bravalue == OP_ASSERTBACK ||
bravalue == OP_ASSERTBACK_NOT), /* TRUE if back assert */
reset_bracount, /* True if (?| group */
skipbytes, /* Skip over bracket number */
&subfirstbyte, /* For possible first char */
&subreqbyte, /* For possible last char */
@ -4230,9 +4566,11 @@ for (;; ptr++)
is on the bracket. */
/* If this is a conditional bracket, check that there are no more than
two branches in the group, or just one if it's a DEFINE group. */
two branches in the group, or just one if it's a DEFINE group. We do this
in the real compile phase, not in the pre-pass, where the whole group may
not be available. */
if (bravalue == OP_COND)
if (bravalue == OP_COND && lengthptr == NULL)
{
uschar *tc = code;
int condcount = 0;
@ -4392,12 +4730,13 @@ for (;; ptr++)
zerofirstbyte = firstbyte;
zeroreqbyte = reqbyte;
/* \k<name> or \k'name' is a back reference by name (Perl syntax) */
/* \k<name> or \k'name' is a back reference by name (Perl syntax).
We also support \k{name} (.NET syntax) */
if (-c == ESC_k && (ptr[1] == '<' || ptr[1] == '\''))
if (-c == ESC_k && (ptr[1] == '<' || ptr[1] == '\'' || ptr[1] == '{'))
{
is_recurse = FALSE;
terminator = (*(++ptr) == '<')? '>' : '\'';
terminator = (*(++ptr) == '<')? '>' : (*ptr == '\'')? '\'' : '}';
goto NAMED_REF_OR_RECURSE;
}
@ -4563,13 +4902,14 @@ This function is used during the pre-compile phase when we are trying to find
out the amount of memory needed, as well as during the real compile phase. The
value of lengthptr distinguishes the two phases.
Argument:
Arguments:
options option bits, including any changes for this subpattern
oldims previous settings of ims option bits
codeptr -> the address of the current code pointer
ptrptr -> the address of the current pattern pointer
errorcodeptr -> pointer to error code variable
lookbehind TRUE if this is a lookbehind assertion
reset_bracount TRUE to reset the count for each branch
skipbytes skip this many bytes at start (for brackets and OP_COND)
firstbyteptr place to put the first required character, or a negative number
reqbyteptr place to put the last required character, or a negative number
@ -4583,8 +4923,9 @@ Returns: TRUE on success
static BOOL
compile_regex(int options, int oldims, uschar **codeptr, const uschar **ptrptr,
int *errorcodeptr, BOOL lookbehind, int skipbytes, int *firstbyteptr,
int *reqbyteptr, branch_chain *bcptr, compile_data *cd, int *lengthptr)
int *errorcodeptr, BOOL lookbehind, BOOL reset_bracount, int skipbytes,
int *firstbyteptr, int *reqbyteptr, branch_chain *bcptr, compile_data *cd,
int *lengthptr)
{
const uschar *ptr = *ptrptr;
uschar *code = *codeptr;
@ -4594,6 +4935,8 @@ uschar *reverse_count = NULL;
int firstbyte, reqbyte;
int branchfirstbyte, branchreqbyte;
int length;
int orig_bracount;
int max_bracount;
branch_chain bc;
bc.outer = bcptr;
@ -4622,8 +4965,14 @@ code += 1 + LINK_SIZE + skipbytes;
/* Loop for each alternative branch */
orig_bracount = max_bracount = cd->bracount;
for (;;)
{
/* For a (?| group, reset the capturing bracket count so that each branch
uses the same numbers. */
if (reset_bracount) cd->bracount = orig_bracount;
/* Handle a change of ims options at the start of the branch */
if ((options & PCRE_IMS) != oldims)
@ -4653,6 +5002,11 @@ for (;;)
return FALSE;
}
/* Keep the highest bracket count in case (?| was used and some branch
has fewer than the rest. */
if (cd->bracount > max_bracount) max_bracount = cd->bracount;
/* In the real compile phase, there is some post-processing to be done. */
if (lengthptr == NULL)
@ -4716,26 +5070,29 @@ for (;;)
}
}
/* Reached end of expression, either ')' or end of pattern. Go back through
the alternative branches and reverse the chain of offsets, with the field in
the BRA item now becoming an offset to the first alternative. If there are
no alternatives, it points to the end of the group. The length in the
terminating ket is always the length of the whole bracketed item. If any of
the ims options were changed inside the group, compile a resetting op-code
following, except at the very end of the pattern. Return leaving the pointer
at the terminating char. */
/* Reached end of expression, either ')' or end of pattern. In the real
compile phase, go back through the alternative branches and reverse the chain
of offsets, with the field in the BRA item now becoming an offset to the
first alternative. If there are no alternatives, it points to the end of the
group. The length in the terminating ket is always the length of the whole
bracketed item. If any of the ims options were changed inside the group,
compile a resetting op-code following, except at the very end of the pattern.
Return leaving the pointer at the terminating char. */
if (*ptr != '|')
{
int branch_length = code - last_branch;
do
if (lengthptr == NULL)
{
int prev_length = GET(last_branch, 1);
PUT(last_branch, 1, branch_length);
branch_length = prev_length;
last_branch -= branch_length;
int branch_length = code - last_branch;
do
{
int prev_length = GET(last_branch, 1);
PUT(last_branch, 1, branch_length);
branch_length = prev_length;
last_branch -= branch_length;
}
while (branch_length > 0);
}
while (branch_length > 0);
/* Fill in the ket */
@ -4752,6 +5109,10 @@ for (;;)
length += 2;
}
/* Retain the highest bracket number, in case resetting was used. */
cd->bracount = max_bracount;
/* Set values to pass back */
*codeptr = code;
@ -4762,17 +5123,29 @@ for (;;)
return TRUE;
}
/* Another branch follows; insert an "or" node. Its length field points back
/* Another branch follows. In the pre-compile phase, we can move the code
pointer back to where it was for the start of the first branch. (That is,
pretend that each branch is the only one.)
In the real compile phase, insert an ALT node. Its length field points back
to the previous branch while the bracket remains open. At the end the chain
is reversed. It's done like this so that the start of the bracket has a
zero offset until it is closed, making it possible to detect recursion. */
*code = OP_ALT;
PUT(code, 1, code - last_branch);
bc.current = last_branch = code;
code += 1 + LINK_SIZE;
if (lengthptr != NULL)
{
code = *codeptr + 1 + LINK_SIZE + skipbytes;
length += 1 + LINK_SIZE;
}
else
{
*code = OP_ALT;
PUT(code, 1, code - last_branch);
bc.current = last_branch = code;
code += 1 + LINK_SIZE;
}
ptr++;
length += 1 + LINK_SIZE;
}
/* Control never reaches here */
}
@ -5039,7 +5412,7 @@ Returns: pointer to compiled data block, or NULL on error,
with errorptr and erroroffset set
*/
PCRE_DATA_SCOPE pcre *
PCRE_EXP_DEFN pcre *
pcre_compile(const char *pattern, int options, const char **errorptr,
int *erroroffset, const unsigned char *tables)
{
@ -5047,7 +5420,7 @@ return pcre_compile2(pattern, options, NULL, errorptr, erroroffset, tables);
}
PCRE_DATA_SCOPE pcre *
PCRE_EXP_DEFN pcre *
pcre_compile2(const char *pattern, int options, int *errorcodeptr,
const char **errorptr, int *erroroffset, const unsigned char *tables)
{
@ -5096,7 +5469,7 @@ if (errorcodeptr != NULL) *errorcodeptr = ERR0;
if (erroroffset == NULL)
{
errorcode = ERR16;
goto PCRE_EARLY_ERROR_RETURN;
goto PCRE_EARLY_ERROR_RETURN2;
}
*erroroffset = 0;
@ -5109,7 +5482,7 @@ if (utf8 && (options & PCRE_NO_UTF8_CHECK) == 0 &&
(*erroroffset = _pcre_valid_utf8((uschar *)pattern, -1)) >= 0)
{
errorcode = ERR44;
goto PCRE_UTF8_ERROR_RETURN;
goto PCRE_EARLY_ERROR_RETURN2;
}
#else
if ((options & PCRE_UTF8) != 0)
@ -5134,7 +5507,8 @@ cd->cbits = tables + cbits_offset;
cd->ctypes = tables + ctypes_offset;
/* Handle different types of newline. The three bits give seven cases. The
current code allows for fixed one- or two-byte sequences, plus "any". */
current code allows for fixed one- or two-byte sequences, plus "any" and
"anycrlf". */
switch (options & (PCRE_NEWLINE_CRLF | PCRE_NEWLINE_ANY))
{
@ -5144,10 +5518,15 @@ switch (options & (PCRE_NEWLINE_CRLF | PCRE_NEWLINE_ANY))
case PCRE_NEWLINE_CR+
PCRE_NEWLINE_LF: newline = ('\r' << 8) | '\n'; break;
case PCRE_NEWLINE_ANY: newline = -1; break;
case PCRE_NEWLINE_ANYCRLF: newline = -2; break;
default: errorcode = ERR56; goto PCRE_EARLY_ERROR_RETURN;
}
if (newline < 0)
if (newline == -2)
{
cd->nltype = NLTYPE_ANYCRLF;
}
else if (newline < 0)
{
cd->nltype = NLTYPE_ANY;
}
@ -5208,7 +5587,8 @@ outside can help speed up starting point checks. */
code = cworkspace;
*code = OP_BRA;
(void)compile_regex(cd->external_options, cd->external_options & PCRE_IMS,
&code, &ptr, &errorcode, FALSE, 0, &firstbyte, &reqbyte, NULL, cd, &length);
&code, &ptr, &errorcode, FALSE, FALSE, 0, &firstbyte, &reqbyte, NULL, cd,
&length);
if (errorcode != 0) goto PCRE_EARLY_ERROR_RETURN;
DPRINTF(("end pre-compile: length=%d workspace=%d\n", length,
@ -5276,7 +5656,7 @@ ptr = (const uschar *)pattern;
code = (uschar *)codestart;
*code = OP_BRA;
(void)compile_regex(re->options, re->options & PCRE_IMS, &code, &ptr,
&errorcode, FALSE, 0, &firstbyte, &reqbyte, NULL, cd, NULL);
&errorcode, FALSE, FALSE, 0, &firstbyte, &reqbyte, NULL, cd, NULL);
re->top_bracket = cd->bracount;
re->top_backref = cd->top_backref;
@ -5321,9 +5701,7 @@ if (errorcode != 0)
(pcre_free)(re);
PCRE_EARLY_ERROR_RETURN:
*erroroffset = ptr - (const uschar *)pattern;
#ifdef SUPPORT_UTF8
PCRE_UTF8_ERROR_RETURN:
#endif
PCRE_EARLY_ERROR_RETURN2:
*errorptr = error_texts[errorcode];
if (errorcodeptr != NULL) *errorcodeptr = errorcode;
return NULL;
@ -5413,7 +5791,7 @@ if ((re->options & PCRE_REQCHSET) != 0)
else printf("Req char = \\x%02x%s\n", ch, caseless);
}
pcre_printint(re, stdout);
pcre_printint(re, stdout, TRUE);
/* This check is done here in the debugging case so that the code that
was compiled can be seen. */

4
ext/pcre/pcrelib/pcre_config.c
View File

@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2006 University of Cambridge
Copyright (c) 1997-2007 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -58,7 +58,7 @@ Arguments:
Returns: 0 if data returned, negative on error
*/
PCRE_DATA_SCOPE int
PCRE_EXP_DEFN int
pcre_config(int what, void *where)
{
switch (what)

850
ext/pcre/pcrelib/pcre_exec.c
View File

File diff suppressed because it is too large Load Diff

12
ext/pcre/pcrelib/pcre_fullinfo.c
View File

@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2006 University of Cambridge
Copyright (c) 1997-2007 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -61,7 +61,7 @@ Arguments:
Returns: 0 if data returned, negative on error
*/
PCRE_DATA_SCOPE int
PCRE_EXP_DEFN int
pcre_fullinfo(const pcre *argument_re, const pcre_extra *extra_data, int what,
void *where)
{
@ -140,6 +140,14 @@ switch (what)
*((const uschar **)where) = (const uschar *)(_pcre_default_tables);
break;
case PCRE_INFO_OKPARTIAL:
*((int *)where) = (re->options & PCRE_NOPARTIAL) == 0;
break;
case PCRE_INFO_JCHANGED:
*((int *)where) = (re->options & PCRE_JCHANGED) != 0;
break;
default: return PCRE_ERROR_BADOPTION;
}

2
ext/pcre/pcrelib/pcre_get.c
View File

@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2006 University of Cambridge
Copyright (c) 1997-2007 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without

35
ext/pcre/pcrelib/pcre_globals.c
View File

@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2006 University of Cambridge
Copyright (c) 1997-2007 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -46,37 +46,14 @@ indirection. These values can be changed by the caller, but are shared between
all threads. However, when compiling for Virtual Pascal, things are done
differently, and global variables are not used (see pcre.in). */
#include "pcre_internal.h"
#ifndef VPCOMPAT
/**************************************************************************
This code used to be here for use when compiling as a C++ library. However,
according to Dair Grant it is not needed: "
Including 'extern "C"' in the declaration generates an "initialized and
declared `extern'" warning from gcc 4.0.1. Since we include pcre_internal.h,
which includes pcre.h, which declares these prototypes within an extern "C" {}
block, we shouldn't need the prefix here.
So, from Release 7.0 I have cut this out.
#ifdef __cplusplus
extern "C" void *(*pcre_malloc)(size_t) = malloc;
extern "C" void (*pcre_free)(void *) = free;
extern "C" void *(*pcre_stack_malloc)(size_t) = malloc;
extern "C" void (*pcre_stack_free)(void *) = free;
extern "C" int (*pcre_callout)(pcre_callout_block *) = NULL;
#else
**************************************************************************/
void *(*pcre_malloc)(size_t) = malloc;
void (*pcre_free)(void *) = free;
void *(*pcre_stack_malloc)(size_t) = malloc;
void (*pcre_stack_free)(void *) = free;
int (*pcre_callout)(pcre_callout_block *) = NULL;
PCRE_EXP_DATA_DEFN void *(*pcre_malloc)(size_t) = malloc;
PCRE_EXP_DATA_DEFN void (*pcre_free)(void *) = free;
PCRE_EXP_DATA_DEFN void *(*pcre_stack_malloc)(size_t) = malloc;
PCRE_EXP_DATA_DEFN void (*pcre_stack_free)(void *) = free;
PCRE_EXP_DATA_DEFN int (*pcre_callout)(pcre_callout_block *) = NULL;
#endif
/* End of pcre_globals.c */

4
ext/pcre/pcrelib/pcre_info.c
View File

@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2006 University of Cambridge
Copyright (c) 1997-2007 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -68,7 +68,7 @@ Returns: number of capturing subpatterns
or negative values on error
*/
PCRE_DATA_SCOPE int
PCRE_EXP_DEFN int
pcre_info(const pcre *argument_re, int *optptr, int *first_byte)
{
real_pcre internal_re;

360
ext/pcre/pcrelib/pcre_internal.h
View File

@ -7,7 +7,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2006 University of Cambridge
Copyright (c) 1997-2007 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -69,11 +69,7 @@ be absolutely sure we get our version. */
/* Get the definitions provided by running "configure" */
#ifdef PHP_WIN32
# include "config.w32.h"
#else
# include <php_config.h>
#endif
#include "config.h"
/* Standard C headers plus the external interface definition. The only time
setjmp and stdarg are used is when NO_RECURSE is set. */
@ -87,8 +83,58 @@ setjmp and stdarg are used is when NO_RECURSE is set. */
#include <stdlib.h>
#include <string.h>
#ifndef PCRE_SPY
#define PCRE_DEFINITION /* Win32 __declspec(export) trigger for .dll */
/* When compiling a DLL for Windows, the exported symbols have to be declared
using some MS magic. I found some useful information on this web page:
http://msdn2.microsoft.com/en-us/library/y4h7bcy6(VS.80).aspx. According to the
information there, using __declspec(dllexport) without "extern" we have a
definition; with "extern" we have a declaration. The settings here override the
setting in pcre.h (which is included below); it defines only PCRE_EXP_DECL,
which is all that is needed for applications (they just import the symbols). We
use:
PCRE_EXP_DECL for declarations
PCRE_EXP_DEFN for definitions of exported functions
PCRE_EXP_DATA_DEFN for definitions of exported variables
The reason for the two DEFN macros is that in non-Windows environments, one
does not want to have "extern" before variable definitions because it leads to
compiler warnings. So we distinguish between functions and variables. In
Windows, the two should always be the same.
The reason for wrapping this in #ifndef PCRE_EXP_DECL is so that pcretest,
which is an application, but needs to import this file in order to "peek" at
internals, can #include pcre.h first to get an application's-eye view.
In principle, people compiling for non-Windows, non-Unix-like (i.e. uncommon,
special-purpose environments) might want to stick other stuff in front of
exported symbols. That's why, in the non-Windows case, we set PCRE_EXP_DEFN and
PCRE_EXP_DATA_DEFN only if they are not already set. */
#ifndef PCRE_EXP_DECL
# ifdef _WIN32
# ifdef DLL_EXPORT
# define PCRE_EXP_DECL extern __declspec(dllexport)
# define PCRE_EXP_DEFN __declspec(dllexport)
# define PCRE_EXP_DATA_DEFN __declspec(dllexport)
# else
# define PCRE_EXP_DECL extern
# define PCRE_EXP_DEFN
# define PCRE_EXP_DATA_DEFN
# endif
#
# else
# ifdef __cplusplus
# define PCRE_EXP_DECL extern "C"
# else
# define PCRE_EXP_DECL extern
# endif
# ifndef PCRE_EXP_DEFN
# define PCRE_EXP_DEFN PCRE_EXP_DECL
# endif
# ifndef PCRE_EXP_DATA_DEFN
# define PCRE_EXP_DATA_DEFN
# endif
# endif
#endif
/* We need to have types that specify unsigned 16-bit and 32-bit integers. We
@ -129,21 +175,22 @@ characters only go up to 0x7fffffff (though Unicode doesn't go beyond
#define NOTACHAR 0xffffffff
/* PCRE is able to support several different kinds of newline (CR, LF, CRLF,
and "all" at present). The following macros are used to package up testing for
newlines. NLBLOCK, PSSTART, and PSEND are defined in the various modules to
indicate in which datablock the parameters exist, and what the start/end of
string field names are. */
"any" and "anycrlf" at present). The following macros are used to package up
testing for newlines. NLBLOCK, PSSTART, and PSEND are defined in the various
modules to indicate in which datablock the parameters exist, and what the
start/end of string field names are. */
#define NLTYPE_FIXED 0 /* Newline is a fixed length string */
#define NLTYPE_ANY 1 /* Newline is any Unicode line ending */
#define NLTYPE_FIXED 0 /* Newline is a fixed length string */
#define NLTYPE_ANY 1 /* Newline is any Unicode line ending */
#define NLTYPE_ANYCRLF 2 /* Newline is CR, LF, or CRLF */
/* This macro checks for a newline at the given position */
#define IS_NEWLINE(p) \
((NLBLOCK->nltype != NLTYPE_FIXED)? \
((p) < NLBLOCK->PSEND && \
_pcre_is_newline((p), NLBLOCK->PSEND, &(NLBLOCK->nllen), utf8) \
) \
_pcre_is_newline((p), NLBLOCK->nltype, NLBLOCK->PSEND, &(NLBLOCK->nllen),\
utf8)) \
: \
((p) <= NLBLOCK->PSEND - NLBLOCK->nllen && \
(p)[0] == NLBLOCK->nl[0] && \
@ -156,8 +203,8 @@ string field names are. */
#define WAS_NEWLINE(p) \
((NLBLOCK->nltype != NLTYPE_FIXED)? \
((p) > NLBLOCK->PSSTART && \
_pcre_was_newline((p), NLBLOCK->PSSTART, &(NLBLOCK->nllen), utf8) \
) \
_pcre_was_newline((p), NLBLOCK->nltype, NLBLOCK->PSSTART, \
&(NLBLOCK->nllen), utf8)) \
: \
((p) >= NLBLOCK->PSSTART + NLBLOCK->nllen && \
(p)[-NLBLOCK->nllen] == NLBLOCK->nl[0] && \
@ -182,10 +229,12 @@ must begin with PCRE_. */
#define USPTR const unsigned char *
#endif
/* Include the public PCRE header and the definitions of UCP character property
values. */
#include "pcre.h"
#include <pcre.h>
#include "ucp.h"
/* When compiling for use with the Virtual Pascal compiler, these functions
@ -193,7 +242,9 @@ need to have their names changed. PCRE must be compiled with the -DVPCOMPAT
option on the command line. */
#ifdef VPCOMPAT
#define strlen(s) _strlen(s)
#define strncmp(s1,s2,m) _strncmp(s1,s2,m)
#define memcmp(s,c,n) _memcmp(s,c,n)
#define memcpy(d,s,n) _memcpy(d,s,n)
#define memmove(d,s,n) _memmove(d,s,n)
#define memset(s,c,n) _memset(s,c,n)
@ -202,23 +253,31 @@ option on the command line. */
/* To cope with SunOS4 and other systems that lack memmove() but have bcopy(),
define a macro for memmove() if HAVE_MEMMOVE is false, provided that HAVE_BCOPY
is set. Otherwise, include an emulating function for those systems that have
neither (there some non-Unix environments where this is the case). This assumes
that all calls to memmove are moving strings upwards in store, which is the
case in PCRE. */
neither (there some non-Unix environments where this is the case). */
#if ! HAVE_MEMMOVE
#ifndef HAVE_MEMMOVE
#undef memmove /* some systems may have a macro */
#if HAVE_BCOPY
#ifdef HAVE_BCOPY
#define memmove(a, b, c) bcopy(b, a, c)
#else /* HAVE_BCOPY */
static void *
pcre_memmove(unsigned char *dest, const unsigned char *src, size_t n)
pcre_memmove(void *d, const void *s, size_t n)
{
size_t i;
dest += n;
src += n;
for (i = 0; i < n; ++i) *(--dest) = *(--src);
return dest;
unsigned char *dest = (unsigned char *)d;
const unsigned char *src = (const unsigned char *)s;
if (dest > src)
{
dest += n;
src += n;
for (i = 0; i < n; ++i) *(--dest) = *(--src);
return (void *)dest;
}
else
{
for (i = 0; i < n; ++i) *dest++ = *src++;
return (void *)(dest - n);
}
}
#define memmove(a, b, c) pcre_memmove(a, b, c)
#endif /* not HAVE_BCOPY */
@ -443,7 +502,8 @@ bits. */
/* Masks for identifying the public options that are permitted at compile
time, run time, or study time, respectively. */
#define PCRE_NEWLINE_BITS (PCRE_NEWLINE_CR|PCRE_NEWLINE_LF|PCRE_NEWLINE_ANY)
#define PCRE_NEWLINE_BITS (PCRE_NEWLINE_CR|PCRE_NEWLINE_LF|PCRE_NEWLINE_ANY| \
PCRE_NEWLINE_ANYCRLF)
#define PUBLIC_OPTIONS \
(PCRE_CASELESS|PCRE_EXTENDED|PCRE_ANCHORED|PCRE_MULTILINE| \
@ -545,9 +605,9 @@ ESC_Z to detect the types that may be repeated. These are the types that
consume characters. If any new escapes are put in between that don't consume a
character, that code will have to change. */
enum { ESC_A = 1, ESC_G, ESC_B, ESC_b, ESC_D, ESC_d, ESC_S, ESC_s, ESC_W,
ESC_w, ESC_dum1, ESC_C, ESC_P, ESC_p, ESC_R, ESC_X, ESC_Z, ESC_z,
ESC_E, ESC_Q, ESC_k, ESC_REF };
enum { ESC_A = 1, ESC_G, ESC_K, ESC_B, ESC_b, ESC_D, ESC_d, ESC_S, ESC_s,
ESC_W, ESC_w, ESC_dum1, ESC_C, ESC_P, ESC_p, ESC_R, ESC_H, ESC_h,
ESC_V, ESC_v, ESC_X, ESC_Z, ESC_z, ESC_E, ESC_Q, ESC_k, ESC_REF };
/* Opcode table: OP_BRA must be last, as all values >= it are used for brackets
@ -569,133 +629,138 @@ enum {
OP_SOD, /* 1 Start of data: \A */
OP_SOM, /* 2 Start of match (subject + offset): \G */
OP_NOT_WORD_BOUNDARY, /* 3 \B */
OP_WORD_BOUNDARY, /* 4 \b */
OP_NOT_DIGIT, /* 5 \D */
OP_DIGIT, /* 6 \d */
OP_NOT_WHITESPACE, /* 7 \S */
OP_WHITESPACE, /* 8 \s */
OP_NOT_WORDCHAR, /* 9 \W */
OP_WORDCHAR, /* 10 \w */
OP_ANY, /* 11 Match any character */
OP_ANYBYTE, /* 12 Match any byte (\C); different to OP_ANY for UTF-8 */
OP_NOTPROP, /* 13 \P (not Unicode property) */
OP_PROP, /* 14 \p (Unicode property) */
OP_ANYNL, /* 15 \R (any newline sequence) */
OP_EXTUNI, /* 16 \X (extended Unicode sequence */
OP_EODN, /* 17 End of data or \n at end of data: \Z. */
OP_EOD, /* 18 End of data: \z */
OP_SET_SOM, /* 3 Set start of match (\K) */
OP_NOT_WORD_BOUNDARY, /* 4 \B */
OP_WORD_BOUNDARY, /* 5 \b */
OP_NOT_DIGIT, /* 6 \D */
OP_DIGIT, /* 7 \d */
OP_NOT_WHITESPACE, /* 8 \S */
OP_WHITESPACE, /* 9 \s */
OP_NOT_WORDCHAR, /* 10 \W */
OP_WORDCHAR, /* 11 \w */
OP_ANY, /* 12 Match any character */
OP_ANYBYTE, /* 13 Match any byte (\C); different to OP_ANY for UTF-8 */
OP_NOTPROP, /* 14 \P (not Unicode property) */
OP_PROP, /* 15 \p (Unicode property) */
OP_ANYNL, /* 16 \R (any newline sequence) */
OP_NOT_HSPACE, /* 17 \H (not horizontal whitespace) */
OP_HSPACE, /* 18 \h (horizontal whitespace) */
OP_NOT_VSPACE, /* 19 \V (not vertical whitespace) */
OP_VSPACE, /* 20 \v (vertical whitespace) */
OP_EXTUNI, /* 21 \X (extended Unicode sequence */
OP_EODN, /* 22 End of data or \n at end of data: \Z. */
OP_EOD, /* 23 End of data: \z */
OP_OPT, /* 19 Set runtime options */
OP_CIRC, /* 20 Start of line - varies with multiline switch */
OP_DOLL, /* 21 End of line - varies with multiline switch */
OP_CHAR, /* 22 Match one character, casefully */
OP_CHARNC, /* 23 Match one character, caselessly */
OP_NOT, /* 24 Match one character, not the following one */
OP_OPT, /* 24 Set runtime options */
OP_CIRC, /* 25 Start of line - varies with multiline switch */
OP_DOLL, /* 26 End of line - varies with multiline switch */
OP_CHAR, /* 27 Match one character, casefully */
OP_CHARNC, /* 28 Match one character, caselessly */
OP_NOT, /* 29 Match one character, not the following one */
OP_STAR, /* 25 The maximizing and minimizing versions of */
OP_MINSTAR, /* 26 these six opcodes must come in pairs, with */
OP_PLUS, /* 27 the minimizing one second. */
OP_MINPLUS, /* 28 This first set applies to single characters.*/
OP_QUERY, /* 29 */
OP_MINQUERY, /* 30 */
OP_STAR, /* 30 The maximizing and minimizing versions of */
OP_MINSTAR, /* 31 these six opcodes must come in pairs, with */
OP_PLUS, /* 32 the minimizing one second. */
OP_MINPLUS, /* 33 This first set applies to single characters.*/
OP_QUERY, /* 34 */
OP_MINQUERY, /* 35 */
OP_UPTO, /* 31 From 0 to n matches */
OP_MINUPTO, /* 32 */
OP_EXACT, /* 33 Exactly n matches */
OP_UPTO, /* 36 From 0 to n matches */
OP_MINUPTO, /* 37 */
OP_EXACT, /* 38 Exactly n matches */
OP_POSSTAR, /* 34 Possessified star */
OP_POSPLUS, /* 35 Possessified plus */
OP_POSQUERY, /* 36 Posesssified query */
OP_POSUPTO, /* 37 Possessified upto */
OP_POSSTAR, /* 39 Possessified star */
OP_POSPLUS, /* 40 Possessified plus */
OP_POSQUERY, /* 41 Posesssified query */
OP_POSUPTO, /* 42 Possessified upto */
OP_NOTSTAR, /* 38 The maximizing and minimizing versions of */
OP_NOTMINSTAR, /* 39 these six opcodes must come in pairs, with */
OP_NOTPLUS, /* 40 the minimizing one second. They must be in */
OP_NOTMINPLUS, /* 41 exactly the same order as those above. */
OP_NOTQUERY, /* 42 This set applies to "not" single characters. */
OP_NOTMINQUERY, /* 43 */
OP_NOTSTAR, /* 43 The maximizing and minimizing versions of */
OP_NOTMINSTAR, /* 44 these six opcodes must come in pairs, with */
OP_NOTPLUS, /* 45 the minimizing one second. They must be in */
OP_NOTMINPLUS, /* 46 exactly the same order as those above. */
OP_NOTQUERY, /* 47 This set applies to "not" single characters. */
OP_NOTMINQUERY, /* 48 */
OP_NOTUPTO, /* 44 From 0 to n matches */
OP_NOTMINUPTO, /* 45 */
OP_NOTEXACT, /* 46 Exactly n matches */
OP_NOTUPTO, /* 49 From 0 to n matches */
OP_NOTMINUPTO, /* 50 */
OP_NOTEXACT, /* 51 Exactly n matches */
OP_NOTPOSSTAR, /* 47 Possessified versions */
OP_NOTPOSPLUS, /* 48 */
OP_NOTPOSQUERY, /* 49 */
OP_NOTPOSUPTO, /* 50 */
OP_NOTPOSSTAR, /* 52 Possessified versions */
OP_NOTPOSPLUS, /* 53 */
OP_NOTPOSQUERY, /* 54 */
OP_NOTPOSUPTO, /* 55 */
OP_TYPESTAR, /* 51 The maximizing and minimizing versions of */
OP_TYPEMINSTAR, /* 52 these six opcodes must come in pairs, with */
OP_TYPEPLUS, /* 53 the minimizing one second. These codes must */
OP_TYPEMINPLUS, /* 54 be in exactly the same order as those above. */
OP_TYPEQUERY, /* 55 This set applies to character types such as \d */
OP_TYPEMINQUERY, /* 56 */
OP_TYPESTAR, /* 56 The maximizing and minimizing versions of */
OP_TYPEMINSTAR, /* 57 these six opcodes must come in pairs, with */
OP_TYPEPLUS, /* 58 the minimizing one second. These codes must */
OP_TYPEMINPLUS, /* 59 be in exactly the same order as those above. */
OP_TYPEQUERY, /* 60 This set applies to character types such as \d */
OP_TYPEMINQUERY, /* 61 */
OP_TYPEUPTO, /* 57 From 0 to n matches */
OP_TYPEMINUPTO, /* 58 */
OP_TYPEEXACT, /* 59 Exactly n matches */
OP_TYPEUPTO, /* 62 From 0 to n matches */
OP_TYPEMINUPTO, /* 63 */
OP_TYPEEXACT, /* 64 Exactly n matches */
OP_TYPEPOSSTAR, /* 60 Possessified versions */
OP_TYPEPOSPLUS, /* 61 */
OP_TYPEPOSQUERY, /* 62 */
OP_TYPEPOSUPTO, /* 63 */
OP_TYPEPOSSTAR, /* 65 Possessified versions */
OP_TYPEPOSPLUS, /* 66 */
OP_TYPEPOSQUERY, /* 67 */
OP_TYPEPOSUPTO, /* 68 */
OP_CRSTAR, /* 64 The maximizing and minimizing versions of */
OP_CRMINSTAR, /* 65 all these opcodes must come in pairs, with */
OP_CRPLUS, /* 66 the minimizing one second. These codes must */
OP_CRMINPLUS, /* 67 be in exactly the same order as those above. */
OP_CRQUERY, /* 68 These are for character classes and back refs */
OP_CRMINQUERY, /* 69 */
OP_CRRANGE, /* 70 These are different to the three sets above. */
OP_CRMINRANGE, /* 71 */
OP_CRSTAR, /* 69 The maximizing and minimizing versions of */
OP_CRMINSTAR, /* 70 all these opcodes must come in pairs, with */
OP_CRPLUS, /* 71 the minimizing one second. These codes must */
OP_CRMINPLUS, /* 72 be in exactly the same order as those above. */
OP_CRQUERY, /* 73 These are for character classes and back refs */
OP_CRMINQUERY, /* 74 */
OP_CRRANGE, /* 75 These are different to the three sets above. */
OP_CRMINRANGE, /* 76 */
OP_CLASS, /* 72 Match a character class, chars < 256 only */
OP_NCLASS, /* 73 Same, but the bitmap was created from a negative
OP_CLASS, /* 77 Match a character class, chars < 256 only */
OP_NCLASS, /* 78 Same, but the bitmap was created from a negative
class - the difference is relevant only when a UTF-8
character > 255 is encountered. */
OP_XCLASS, /* 74 Extended class for handling UTF-8 chars within the
OP_XCLASS, /* 79 Extended class for handling UTF-8 chars within the
class. This does both positive and negative. */
OP_REF, /* 75 Match a back reference */
OP_RECURSE, /* 76 Match a numbered subpattern (possibly recursive) */
OP_CALLOUT, /* 77 Call out to external function if provided */
OP_REF, /* 80 Match a back reference */
OP_RECURSE, /* 81 Match a numbered subpattern (possibly recursive) */
OP_CALLOUT, /* 82 Call out to external function if provided */
OP_ALT, /* 78 Start of alternation */
OP_KET, /* 79 End of group that doesn't have an unbounded repeat */
OP_KETRMAX, /* 80 These two must remain together and in this */
OP_KETRMIN, /* 81 order. They are for groups the repeat for ever. */
OP_ALT, /* 83 Start of alternation */
OP_KET, /* 84 End of group that doesn't have an unbounded repeat */
OP_KETRMAX, /* 85 These two must remain together and in this */
OP_KETRMIN, /* 86 order. They are for groups the repeat for ever. */
/* The assertions must come before BRA, CBRA, ONCE, and COND.*/
OP_ASSERT, /* 82 Positive lookahead */
OP_ASSERT_NOT, /* 83 Negative lookahead */
OP_ASSERTBACK, /* 84 Positive lookbehind */
OP_ASSERTBACK_NOT, /* 85 Negative lookbehind */
OP_REVERSE, /* 86 Move pointer back - used in lookbehind assertions */
OP_ASSERT, /* 87 Positive lookahead */
OP_ASSERT_NOT, /* 88 Negative lookahead */
OP_ASSERTBACK, /* 89 Positive lookbehind */
OP_ASSERTBACK_NOT, /* 90 Negative lookbehind */
OP_REVERSE, /* 91 Move pointer back - used in lookbehind assertions */
/* ONCE, BRA, CBRA, and COND must come after the assertions, with ONCE first,
as there's a test for >= ONCE for a subpattern that isn't an assertion. */
OP_ONCE, /* 87 Atomic group */
OP_BRA, /* 88 Start of non-capturing bracket */
OP_CBRA, /* 89 Start of capturing bracket */
OP_COND, /* 90 Conditional group */
OP_ONCE, /* 92 Atomic group */
OP_BRA, /* 83 Start of non-capturing bracket */
OP_CBRA, /* 94 Start of capturing bracket */
OP_COND, /* 95 Conditional group */
/* These three must follow the previous three, in the same order. There's a
check for >= SBRA to distinguish the two sets. */
OP_SBRA, /* 91 Start of non-capturing bracket, check empty */
OP_SCBRA, /* 92 Start of capturing bracket, check empty */
OP_SCOND, /* 93 Conditional group, check empty */
OP_SBRA, /* 96 Start of non-capturing bracket, check empty */
OP_SCBRA, /* 97 Start of capturing bracket, check empty */
OP_SCOND, /* 98 Conditional group, check empty */
OP_CREF, /* 94 Used to hold a capture number as condition */
OP_RREF, /* 95 Used to hold a recursion number as condition */
OP_DEF, /* 96 The DEFINE condition */
OP_CREF, /* 99 Used to hold a capture number as condition */
OP_RREF, /* 100 Used to hold a recursion number as condition */
OP_DEF, /* 101 The DEFINE condition */
OP_BRAZERO, /* 97 These two must remain together and in this */
OP_BRAMINZERO /* 98 order. */
OP_BRAZERO, /* 102 These two must remain together and in this */
OP_BRAMINZERO /* 103 order. */
};
@ -703,10 +768,10 @@ enum {
for debugging. The macro is referenced only in pcre_printint.c. */
#define OP_NAME_LIST \
"End", "\\A", "\\G", "\\B", "\\b", "\\D", "\\d", \
"End", "\\A", "\\G", "\\K", "\\B", "\\b", "\\D", "\\d", \
"\\S", "\\s", "\\W", "\\w", "Any", "Anybyte", \
"notprop", "prop", "anynl", "extuni", \
"\\Z", "\\z", \
"notprop", "prop", "\\R", "\\H", "\\h", "\\V", "\\v", \
"extuni", "\\Z", "\\z", \
"Opt", "^", "$", "char", "charnc", "not", \
"*", "*?", "+", "+?", "?", "??", "{", "{", "{", \
"*+","++", "?+", "{", \
@ -733,9 +798,11 @@ in UTF-8 mode. The code that uses this table must know about such things. */
#define OP_LENGTHS \
1, /* End */ \
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* \A, \G, \B, \B, \D, \d, \S, \s, \W, \w */ \
1, 1, 1, 1, 1, /* \A, \G, \K, \B, \b */ \
1, 1, 1, 1, 1, 1, /* \D, \d, \S, \s, \W, \w */ \
1, 1, /* Any, Anybyte */ \
3, 3, 1, 1, /* NOTPROP, PROP, EXTUNI, ANYNL */ \
3, 3, 1, /* NOTPROP, PROP, EXTUNI */ \
1, 1, 1, 1, 1, /* \R, \H, \h, \V, \v */ \
1, 1, 2, 1, 1, /* \Z, \z, Opt, ^, $ */ \
2, /* Char - the minimum length */ \
2, /* Charnc - the minimum length */ \
@ -795,7 +862,7 @@ enum { ERR0, ERR1, ERR2, ERR3, ERR4, ERR5, ERR6, ERR7, ERR8, ERR9,
ERR20, ERR21, ERR22, ERR23, ERR24, ERR25, ERR26, ERR27, ERR28, ERR29,
ERR30, ERR31, ERR32, ERR33, ERR34, ERR35, ERR36, ERR37, ERR38, ERR39,
ERR40, ERR41, ERR42, ERR43, ERR44, ERR45, ERR46, ERR47, ERR48, ERR49,
ERR50, ERR51, ERR52, ERR53, ERR54, ERR55, ERR56, ERR57 };
ERR50, ERR51, ERR52, ERR53, ERR54, ERR55, ERR56, ERR57, ERR58 };
/* The real format of the start of the pcre block; the index of names and the
code vector run on as long as necessary after the end. We store an explicit
@ -884,21 +951,11 @@ typedef struct recursion_info {
struct recursion_info *prevrec; /* Previous recursion record (or NULL) */
int group_num; /* Number of group that was called */
const uschar *after_call; /* "Return value": points after the call in the expr */
USPTR save_start; /* Old value of md->start_match */
USPTR save_start; /* Old value of mstart */
int *offset_save; /* Pointer to start of saved offsets */
int saved_max; /* Number of saved offsets */
} recursion_info;
/* When compiling in a mode that doesn't use recursive calls to match(),
a structure is used to remember local variables on the heap. It is defined in
pcre_exec.c, close to the match() function, so that it is easy to keep it in
step with any changes of local variable. However, the pointer to the current
frame must be saved in some "static" place over a longjmp(). We declare the
structure here so that we can put a pointer in the match_data structure. NOTE:
This isn't used for a "normal" compilation of pcre. */
struct heapframe;
/* Structure for building a chain of data for holding the values of the subject
pointer at the start of each subpattern, so as to detect when an empty string
has been matched by a subpattern - to break infinite loops. */
@ -935,7 +992,7 @@ typedef struct match_data {
const uschar *start_code; /* For use when recursing */
USPTR start_subject; /* Start of the subject string */
USPTR end_subject; /* End of the subject string */
USPTR start_match; /* Start of this match attempt */
USPTR start_match_ptr; /* Start of matched string */
USPTR end_match_ptr; /* Subject position at end match */
int end_offset_top; /* Highwater mark at end of match */
int capture_last; /* Most recent capture number */
@ -944,7 +1001,6 @@ typedef struct match_data {
int eptrn; /* Next free eptrblock */
recursion_info *recursive; /* Linked list of recursion data */
void *callout_data; /* To pass back to callouts */
struct heapframe *thisframe; /* Used only when compiling for no recursion */
} match_data;
/* A similar structure is used for the same purpose by the DFA matching
@ -1030,16 +1086,16 @@ extern const uschar _pcre_OP_lengths[];
one of the exported public functions. They have to be "external" in the C
sense, but are not part of the PCRE public API. */
extern BOOL _pcre_is_newline(const uschar *, const uschar *, int *,
BOOL);
extern BOOL _pcre_is_newline(const uschar *, int, const uschar *,
int *, BOOL);
extern int _pcre_ord2utf8(int, uschar *);
extern real_pcre *_pcre_try_flipped(const real_pcre *, real_pcre *,
const pcre_study_data *, pcre_study_data *);
extern int _pcre_ucp_findprop(const unsigned int, int *, int *);
extern unsigned int _pcre_ucp_othercase(const unsigned int);
extern int _pcre_valid_utf8(const uschar *, int);
extern BOOL _pcre_was_newline(const uschar *, const uschar *, int *,
BOOL);
extern BOOL _pcre_was_newline(const uschar *, int, const uschar *,
int *, BOOL);
extern BOOL _pcre_xclass(int, const uschar *);
#endif

2
ext/pcre/pcrelib/pcre_maketables.c
View File

@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2006 University of Cambridge
Copyright (c) 1997-2007 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without

41
ext/pcre/pcrelib/pcre_newline.c
View File

@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2006 University of Cambridge
Copyright (c) 1997-2007 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -42,9 +42,8 @@ POSSIBILITY OF SUCH DAMAGE.
one kind of newline is to be recognized. When a newline is found, its length is
returned. In principle, we could implement several newline "types", each
referring to a different set of newline characters. At present, PCRE supports
only NLTYPE_FIXED, which gets handled without these functions, and NLTYPE_ALL,
so for now the type isn't passed into the functions. It can easily be added
later if required. The full list of Unicode newline characters is taken from
only NLTYPE_FIXED, which gets handled without these functions, NLTYPE_ANYCRLF,
and NLTYPE_ANY. The full list of Unicode newline characters is taken from
http://unicode.org/unicode/reports/tr18/. */
@ -61,6 +60,7 @@ string that is being processed.
Arguments:
ptr pointer to possible newline
type the newline type
endptr pointer to the end of the string
lenptr where to return the length
utf8 TRUE if in utf8 mode
@ -69,12 +69,23 @@ Returns: TRUE or FALSE
*/
BOOL
_pcre_is_newline(const uschar *ptr, const uschar *endptr, int *lenptr,
BOOL utf8)
_pcre_is_newline(const uschar *ptr, int type, const uschar *endptr,
int *lenptr, BOOL utf8)
{
int c;
if (utf8) { GETCHAR(c, ptr); } else c = *ptr;
switch(c)
if (type == NLTYPE_ANYCRLF) switch(c)
{
case 0x000a: *lenptr = 1; return TRUE; /* LF */
case 0x000d: *lenptr = (ptr < endptr - 1 && ptr[1] == 0x0a)? 2 : 1;
return TRUE; /* CR */
default: return FALSE;
}
/* NLTYPE_ANY */
else switch(c)
{
case 0x000a: /* LF */
case 0x000b: /* VT */
@ -99,6 +110,7 @@ the string that is being processed.
Arguments:
ptr pointer to possible newline
type the newline type
startptr pointer to the start of the string
lenptr where to return the length
utf8 TRUE if in utf8 mode
@ -107,8 +119,8 @@ Returns: TRUE or FALSE
*/
BOOL
_pcre_was_newline(const uschar *ptr, const uschar *startptr, int *lenptr,
BOOL utf8)
_pcre_was_newline(const uschar *ptr, int type, const uschar *startptr,
int *lenptr, BOOL utf8)
{
int c;
ptr--;
@ -118,7 +130,16 @@ if (utf8)
GETCHAR(c, ptr);
}
else c = *ptr;
switch(c)
if (type == NLTYPE_ANYCRLF) switch(c)
{
case 0x000a: *lenptr = (ptr > startptr && ptr[-1] == 0x0d)? 2 : 1;
return TRUE; /* LF */
case 0x000d: *lenptr = 1; return TRUE; /* CR */
default: return FALSE;
}
else switch(c)
{
case 0x000a: *lenptr = (ptr > startptr && ptr[-1] == 0x0d)? 2 : 1;
return TRUE; /* LF */

6
ext/pcre/pcrelib/pcre_ord2utf8.c
View File

@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2006 University of Cambridge
Copyright (c) 1997-2007 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -62,6 +62,7 @@ Returns: number of characters placed in the buffer
int
_pcre_ord2utf8(int cvalue, uschar *buffer)
{
#ifdef SUPPORT_UTF8
register int i, j;
for (i = 0; i < _pcre_utf8_table1_size; i++)
if (cvalue <= _pcre_utf8_table1[i]) break;
@ -73,6 +74,9 @@ for (j = i; j > 0; j--)
}
*buffer = _pcre_utf8_table2[i] | cvalue;
return i + 1;
#else
return 0; /* Keep compiler happy; this function won't ever be */
#endif /* called when SUPPORT_UTF8 is not defined. */
}
/* End of pcre_ord2utf8.c */

34
ext/pcre/pcrelib/pcre_printint.src
View File

@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2005 University of Cambridge
Copyright (c) 1997-2007 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -71,6 +71,12 @@ print_char(FILE *f, uschar *ptr, BOOL utf8)
{
int c = *ptr;
#ifndef SUPPORT_UTF8
utf8 = utf8; /* Avoid compiler warning */
if (PRINTABLE(c)) fprintf(f, "%c", c); else fprintf(f, "\\x%02x", c);
return 0;
#else
if (!utf8 || (c & 0xc0) != 0xc0)
{
if (PRINTABLE(c)) fprintf(f, "%c", c); else fprintf(f, "\\x%02x", c);
@ -102,6 +108,7 @@ else
if (c < 128) fprintf(f, "\\x%02x", c); else fprintf(f, "\\x{%x}", c);
return a;
}
#endif
}
@ -134,10 +141,13 @@ return (ptype == pvalue)? "??" : "??";
*************************************************/
/* Make this function work for a regex with integers either byte order.
However, we assume that what we are passed is a compiled regex. */
However, we assume that what we are passed is a compiled regex. The
print_lengths flag controls whether offsets and lengths of items are printed.
They can be turned off from pcretest so that automatic tests on bytecode can be
written that do not depend on the value of LINK_SIZE. */
static void
pcre_printint(pcre *external_re, FILE *f)
pcre_printint(pcre *external_re, FILE *f, BOOL print_lengths)
{
real_pcre *re = (real_pcre *)external_re;
uschar *codestart, *code;
@ -168,7 +178,10 @@ for(;;)
int c;
int extra = 0;
fprintf(f, "%3d ", (int)(code - codestart));
if (print_lengths)
fprintf(f, "%3d ", (int)(code - codestart));
else
fprintf(f, " ");
switch(*code)
{
@ -205,8 +218,9 @@ for(;;)
case OP_CBRA:
case OP_SCBRA:
fprintf(f, "%3d %s %d", GET(code, 1), OP_names[*code],
GET2(code, 1+LINK_SIZE));
if (print_lengths) fprintf(f, "%3d ", GET(code, 1));
else fprintf(f, " ");
fprintf(f, "%s %d", OP_names[*code], GET2(code, 1+LINK_SIZE));
break;
case OP_BRA:
@ -223,7 +237,9 @@ for(;;)
case OP_COND:
case OP_SCOND:
case OP_REVERSE:
fprintf(f, "%3d %s", GET(code, 1), OP_names[*code]);
if (print_lengths) fprintf(f, "%3d ", GET(code, 1));
else fprintf(f, " ");
fprintf(f, "%s", OP_names[*code]);
break;
case OP_CREF:
@ -339,7 +355,9 @@ for(;;)
break;
case OP_RECURSE:
fprintf(f, "%3d %s", GET(code, 1), OP_names[*code]);
if (print_lengths) fprintf(f, "%3d ", GET(code, 1));
else fprintf(f, " ");
fprintf(f, "%s", OP_names[*code]);
break;
case OP_REF:

4
ext/pcre/pcrelib/pcre_refcount.c
View File

@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2006 University of Cambridge
Copyright (c) 1997-2007 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -63,7 +63,7 @@ Returns: the (possibly updated) count value (a non-negative number), or
a negative error number
*/
PCRE_DATA_SCOPE int
PCRE_EXP_DEFN int
pcre_refcount(pcre *argument_re, int adjust)
{
real_pcre *re = (real_pcre *)argument_re;

194
ext/pcre/pcrelib/pcre_scanner.cc
View File

@ -1,194 +0,0 @@
// Copyright (c) 2005, Google Inc.
// All rights reserved.
//
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions are
// met:
//
// * Redistributions of source code must retain the above copyright
// notice, this list of conditions and the following disclaimer.
// * Redistributions in binary form must reproduce the above
// copyright notice, this list of conditions and the following disclaimer
// in the documentation and/or other materials provided with the
// distribution.
// * Neither the name of Google Inc. nor the names of its
// contributors may be used to endorse or promote products derived from
// this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
//
// Author: Sanjay Ghemawat
#include <vector>
#include <assert.h>
#include "config.h"
#include "pcre_scanner.h"
using std::vector;
namespace pcrecpp {
Scanner::Scanner()
: data_(),
input_(data_),
skip_(NULL),
should_skip_(false),
skip_repeat_(false),
save_comments_(false),
comments_(NULL),
comments_offset_(0) {
}
Scanner::Scanner(const string& in)
: data_(in),
input_(data_),
skip_(NULL),
should_skip_(false),
skip_repeat_(false),
save_comments_(false),
comments_(NULL),
comments_offset_(0) {
}
Scanner::~Scanner() {
delete skip_;
delete comments_;
}
void Scanner::SetSkipExpression(const char* re) {
delete skip_;
if (re != NULL) {
skip_ = new RE(re);
should_skip_ = true;
skip_repeat_ = true;
ConsumeSkip();
} else {
skip_ = NULL;
should_skip_ = false;
skip_repeat_ = false;
}
}
void Scanner::Skip(const char* re) {
delete skip_;
if (re != NULL) {
skip_ = new RE(re);
should_skip_ = true;
skip_repeat_ = false;
ConsumeSkip();
} else {
skip_ = NULL;
should_skip_ = false;
skip_repeat_ = false;
}
}
void Scanner::DisableSkip() {
assert(skip_ != NULL);
should_skip_ = false;
}
void Scanner::EnableSkip() {
assert(skip_ != NULL);
should_skip_ = true;
ConsumeSkip();
}
int Scanner::LineNumber() const {
// TODO: Make it more efficient by keeping track of the last point
// where we computed line numbers and counting newlines since then.
// We could use std:count, but not all systems have it. :-(
int count = 1;
for (const char* p = data_.data(); p < input_.data(); ++p)
if (*p == '\n')
++count;
return count;
}
int Scanner::Offset() const {
return input_.data() - data_.c_str();
}
bool Scanner::LookingAt(const RE& re) const {
int consumed;
return re.DoMatch(input_, RE::ANCHOR_START, &consumed, 0, 0);
}
bool Scanner::Consume(const RE& re,
const Arg& arg0,
const Arg& arg1,
const Arg& arg2) {
const bool result = re.Consume(&input_, arg0, arg1, arg2);
if (result && should_skip_) ConsumeSkip();
return result;
}
// helper function to consume *skip_ and honour save_comments_
void Scanner::ConsumeSkip() {
const char* start_data = input_.data();
while (skip_->Consume(&input_)) {
if (!skip_repeat_) {
// Only one skip allowed.
break;
}
}
if (save_comments_) {
if (comments_ == NULL) {
comments_ = new vector<StringPiece>;
}
// already pointing one past end, so no need to +1
int length = input_.data() - start_data;
if (length > 0) {
comments_->push_back(StringPiece(start_data, length));
}
}
}
void Scanner::GetComments(int start, int end, vector<StringPiece> *ranges) {
// short circuit out if we've not yet initialized comments_
// (e.g., when save_comments is false)
if (!comments_) {
return;
}
// TODO: if we guarantee that comments_ will contain StringPieces
// that are ordered by their start, then we can do a binary search
// for the first StringPiece at or past start and then scan for the
// ones contained in the range, quit early (use equal_range or
// lower_bound)
for (vector<StringPiece>::const_iterator it = comments_->begin();
it != comments_->end(); ++it) {
if ((it->data() >= data_.c_str() + start &&
it->data() + it->size() <= data_.c_str() + end)) {
ranges->push_back(*it);
}
}
}
void Scanner::GetNextComments(vector<StringPiece> *ranges) {
// short circuit out if we've not yet initialized comments_
// (e.g., when save_comments is false)
if (!comments_) {
return;
}
for (vector<StringPiece>::const_iterator it =
comments_->begin() + comments_offset_;
it != comments_->end(); ++it) {
ranges->push_back(*it);
++comments_offset_;
}
}
} // namespace pcrecpp

171
ext/pcre/pcrelib/pcre_scanner.h
View File

@ -1,171 +0,0 @@
// Copyright (c) 2005, Google Inc.
// All rights reserved.
//
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions are
// met:
//
// * Redistributions of source code must retain the above copyright
// notice, this list of conditions and the following disclaimer.
// * Redistributions in binary form must reproduce the above
// copyright notice, this list of conditions and the following disclaimer
// in the documentation and/or other materials provided with the
// distribution.
// * Neither the name of Google Inc. nor the names of its
// contributors may be used to endorse or promote products derived from
// this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
//
// Author: Sanjay Ghemawat
//
// Regular-expression based scanner for parsing an input stream.
//
// Example 1: parse a sequence of "var = number" entries from input:
//
// Scanner scanner(input);
// string var;
// int number;
// scanner.SetSkipExpression("\\s+"); // Skip any white space we encounter
// while (scanner.Consume("(\\w+) = (\\d+)", &var, &number)) {
// ...;
// }
#ifndef _PCRE_SCANNER_H
#define _PCRE_SCANNER_H
#include <assert.h>
#include <string>
#include <vector>
#include <pcrecpp.h>
#include <pcre_stringpiece.h>
namespace pcrecpp {
class Scanner {
public:
Scanner();
explicit Scanner(const std::string& input);
~Scanner();
// Return current line number. The returned line-number is
// one-based. I.e. it returns 1 + the number of consumed newlines.
//
// Note: this method may be slow. It may take time proportional to
// the size of the input.
int LineNumber() const;
// Return the byte-offset that the scanner is looking in the
// input data;
int Offset() const;
// Return true iff the start of the remaining input matches "re"
bool LookingAt(const RE& re) const;
// Return true iff all of the following are true
// a. the start of the remaining input matches "re",
// b. if any arguments are supplied, matched sub-patterns can be
// parsed and stored into the arguments.
// If it returns true, it skips over the matched input and any
// following input that matches the "skip" regular expression.
bool Consume(const RE& re,
const Arg& arg0 = no_arg,
const Arg& arg1 = no_arg,
const Arg& arg2 = no_arg
// TODO: Allow more arguments?
);
// Set the "skip" regular expression. If after consuming some data,
// a prefix of the input matches this RE, it is automatically
// skipped. For example, a programming language scanner would use
// a skip RE that matches white space and comments.
//
// scanner.SetSkipExpression("\\s+|//.*|/[*](.|\n)*?[*]/");
//
// Skipping repeats as long as it succeeds. We used to let people do
// this by writing "(...)*" in the regular expression, but that added
// up to lots of recursive calls within the pcre library, so now we
// control repetition explicitly via the function call API.
//
// You can pass NULL for "re" if you do not want any data to be skipped.
void Skip(const char* re); // DEPRECATED; does *not* repeat
void SetSkipExpression(const char* re);
// Temporarily pause "skip"ing. This
// Skip("Foo"); code ; DisableSkip(); code; EnableSkip()
// is similar to
// Skip("Foo"); code ; Skip(NULL); code ; Skip("Foo");
// but avoids creating/deleting new RE objects.
void DisableSkip();
// Reenable previously paused skipping. Any prefix of the input
// that matches the skip pattern is immediately dropped.
void EnableSkip();
/***** Special wrappers around SetSkip() for some common idioms *****/
// Arranges to skip whitespace, C comments, C++ comments.
// The overall RE is a disjunction of the following REs:
// \\s whitespace
// //.*\n C++ comment
// /[*](.|\n)*?[*]/ C comment (x*? means minimal repetitions of x)
// We get repetition via the semantics of SetSkipExpression, not by using *
void SkipCXXComments() {
SetSkipExpression("\\s|//.*\n|/[*](?:\n|.)*?[*]/");
}
void set_save_comments(bool comments) {
save_comments_ = comments;
}
bool save_comments() {
return save_comments_;
}
// Append to vector ranges the comments found in the
// byte range [start,end] (inclusive) of the input data.
// Only comments that were extracted entirely within that
// range are returned: no range splitting of atomically-extracted
// comments is performed.
void GetComments(int start, int end, std::vector<StringPiece> *ranges);
// Append to vector ranges the comments added
// since the last time this was called. This
// functionality is provided for efficiency when
// interleaving scanning with parsing.
void GetNextComments(std::vector<StringPiece> *ranges);
private:
std::string data_; // All the input data
StringPiece input_; // Unprocessed input
RE* skip_; // If non-NULL, RE for skipping input
bool should_skip_; // If true, use skip_
bool skip_repeat_; // If true, repeat skip_ as long as it works
bool save_comments_; // If true, aggregate the skip expression
// the skipped comments
// TODO: later consider requiring that the StringPieces be added
// in order by their start position
std::vector<StringPiece> *comments_;
// the offset into comments_ that has been returned by GetNextComments
int comments_offset_;
// helper function to consume *skip_ and honour
// save_comments_
void ConsumeSkip();
};
} // namespace pcrecpp
#endif /* _PCRE_SCANNER_H */

152
ext/pcre/pcrelib/pcre_scanner_unittest.cc
View File

@ -1,152 +0,0 @@
// Copyright (c) 2005, Google Inc.
// All rights reserved.
//
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions are
// met:
//
// * Redistributions of source code must retain the above copyright
// notice, this list of conditions and the following disclaimer.
// * Redistributions in binary form must reproduce the above
// copyright notice, this list of conditions and the following disclaimer
// in the documentation and/or other materials provided with the
// distribution.
// * Neither the name of Google Inc. nor the names of its
// contributors may be used to endorse or promote products derived from
// this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
//
// Author: Greg J. Badros
//
// Unittest for scanner, especially GetNextComments and GetComments()
// functionality.
#include <stdio.h>
#include <string>
#include <vector>
#include <pcre_stringpiece.h>
#include <pcre_scanner.h>
#define FLAGS_unittest_stack_size 49152
// Dies with a fatal error if the two values are not equal.
#define CHECK_EQ(a, b) do { \
if ( (a) != (b) ) { \
fprintf(stderr, "%s:%d: Check failed because %s != %s\n", \
__FILE__, __LINE__, #a, #b); \
exit(1); \
} \
} while (0)
using std::vector;
using pcrecpp::StringPiece;
using pcrecpp::Scanner;
static void TestScanner() {
const char input[] = "\n"
"alpha = 1; // this sets alpha\n"
"bravo = 2; // bravo is set here\n"
"gamma = 33; /* and here is gamma */\n";
const char *re = "(\\w+) = (\\d+);";
Scanner s(input);
string var;
int number;
s.SkipCXXComments();
s.set_save_comments(true);
vector<StringPiece> comments;
s.Consume(re, &var, &number);
CHECK_EQ(var, "alpha");
CHECK_EQ(number, 1);
CHECK_EQ(s.LineNumber(), 3);
s.GetNextComments(&comments);
CHECK_EQ(comments.size(), 1);
CHECK_EQ(comments[0].as_string(), " // this sets alpha\n");
comments.resize(0);
s.Consume(re, &var, &number);
CHECK_EQ(var, "bravo");
CHECK_EQ(number, 2);
s.GetNextComments(&comments);
CHECK_EQ(comments.size(), 1);
CHECK_EQ(comments[0].as_string(), " // bravo is set here\n");
comments.resize(0);
s.Consume(re, &var, &number);
CHECK_EQ(var, "gamma");
CHECK_EQ(number, 33);
s.GetNextComments(&comments);
CHECK_EQ(comments.size(), 1);
CHECK_EQ(comments[0].as_string(), " /* and here is gamma */\n");
comments.resize(0);
s.GetComments(0, sizeof(input), &comments);
CHECK_EQ(comments.size(), 3);
CHECK_EQ(comments[0].as_string(), " // this sets alpha\n");
CHECK_EQ(comments[1].as_string(), " // bravo is set here\n");
CHECK_EQ(comments[2].as_string(), " /* and here is gamma */\n");
comments.resize(0);
s.GetComments(0, strchr(input, '/') - input, &comments);
CHECK_EQ(comments.size(), 0);
comments.resize(0);
s.GetComments(strchr(input, '/') - input - 1, sizeof(input),
&comments);
CHECK_EQ(comments.size(), 3);
CHECK_EQ(comments[0].as_string(), " // this sets alpha\n");
CHECK_EQ(comments[1].as_string(), " // bravo is set here\n");
CHECK_EQ(comments[2].as_string(), " /* and here is gamma */\n");
comments.resize(0);
s.GetComments(strchr(input, '/') - input - 1,
strchr(input + 1, '\n') - input + 1, &comments);
CHECK_EQ(comments.size(), 1);
CHECK_EQ(comments[0].as_string(), " // this sets alpha\n");
comments.resize(0);
}
static void TestBigComment() {
string input;
for (int i = 0; i < 1024; ++i) {
char buf[1024];
snprintf(buf, sizeof(buf), " # Comment %d\n", i);
input += buf;
}
input += "name = value;\n";
Scanner s(input.c_str());
s.SetSkipExpression("\\s+|#.*\n");
string name;
string value;
s.Consume("(\\w+) = (\\w+);", &name, &value);
CHECK_EQ(name, "name");
CHECK_EQ(value, "value");
}
// TODO: also test scanner and big-comment in a thread with a
// small stack size
int main(int argc, char** argv) {
TestScanner();
TestBigComment();
// Done
printf("OK\n");
return 0;
}

39
ext/pcre/pcrelib/pcre_stringpiece.cc
View File

@ -1,39 +0,0 @@
// Copyright (c) 2005, Google Inc.
// All rights reserved.
//
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions are
// met:
//
// * Redistributions of source code must retain the above copyright
// notice, this list of conditions and the following disclaimer.
// * Redistributions in binary form must reproduce the above
// copyright notice, this list of conditions and the following disclaimer
// in the documentation and/or other materials provided with the
// distribution.
// * Neither the name of Google Inc. nor the names of its
// contributors may be used to endorse or promote products derived from
// this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
//
// Author: wilsonh@google.com (Wilson Hsieh)
//
#include <iostream>
#include "config.h"
#include "pcre_stringpiece.h"
std::ostream& operator<<(std::ostream& o, const pcrecpp::StringPiece& piece) {
return (o << piece.as_string());
}

172
ext/pcre/pcrelib/pcre_stringpiece.h
View File

@ -1,172 +0,0 @@
// Copyright (c) 2005, Google Inc.
// All rights reserved.
//
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions are
// met:
//
// * Redistributions of source code must retain the above copyright
// notice, this list of conditions and the following disclaimer.
// * Redistributions in binary form must reproduce the above
// copyright notice, this list of conditions and the following disclaimer
// in the documentation and/or other materials provided with the
// distribution.
// * Neither the name of Google Inc. nor the names of its
// contributors may be used to endorse or promote products derived from
// this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
//
// Author: Sanjay Ghemawat
//
// A string like object that points into another piece of memory.
// Useful for providing an interface that allows clients to easily
// pass in either a "const char*" or a "string".
//
// Arghh! I wish C++ literals were automatically of type "string".
#ifndef _PCRE_STRINGPIECE_H
#define _PCRE_STRINGPIECE_H
#include <string.h>
#include <string>
#include <iosfwd> // for ostream forward-declaration
#if 1
#define HAVE_TYPE_TRAITS
#include <type_traits.h>
#elif 0
#define HAVE_TYPE_TRAITS
#include <bits/type_traits.h>
#endif
using std::string;
namespace pcrecpp {
class StringPiece {
private:
const char* ptr_;
int length_;
public:
// We provide non-explicit singleton constructors so users can pass
// in a "const char*" or a "string" wherever a "StringPiece" is
// expected.
StringPiece()
: ptr_(NULL), length_(0) { }
StringPiece(const char* str)
: ptr_(str), length_(static_cast<int>(strlen(str))) { }
StringPiece(const string& str)
: ptr_(str.data()), length_(static_cast<int>(str.size())) { }
StringPiece(const char* offset, int len)
: ptr_(offset), length_(len) { }
// data() may return a pointer to a buffer with embedded NULs, and the
// returned buffer may or may not be null terminated. Therefore it is
// typically a mistake to pass data() to a routine that expects a NUL
// terminated string. Use "as_string().c_str()" if you really need to do
// this. Or better yet, change your routine so it does not rely on NUL
// termination.
const char* data() const { return ptr_; }
int size() const { return length_; }
bool empty() const { return length_ == 0; }
void clear() { ptr_ = NULL; length_ = 0; }
void set(const char* buffer, int len) { ptr_ = buffer; length_ = len; }
void set(const char* str) {
ptr_ = str;
length_ = static_cast<int>(strlen(str));
}
void set(const void* buffer, int len) {
ptr_ = reinterpret_cast<const char*>(buffer);
length_ = len;
}
char operator[](int i) const { return ptr_[i]; }
void remove_prefix(int n) {
ptr_ += n;
length_ -= n;
}
void remove_suffix(int n) {
length_ -= n;
}
bool operator==(const StringPiece& x) const {
return ((length_ == x.length_) &&
(memcmp(ptr_, x.ptr_, length_) == 0));
}
bool operator!=(const StringPiece& x) const {
return !(*this == x);
}
#define STRINGPIECE_BINARY_PREDICATE(cmp,auxcmp) \
bool operator cmp (const StringPiece& x) const { \
int r = memcmp(ptr_, x.ptr_, length_ < x.length_ ? length_ : x.length_); \
return ((r auxcmp 0) || ((r == 0) && (length_ cmp x.length_))); \
}
STRINGPIECE_BINARY_PREDICATE(<, <);
STRINGPIECE_BINARY_PREDICATE(<=, <);
STRINGPIECE_BINARY_PREDICATE(>=, >);
STRINGPIECE_BINARY_PREDICATE(>, >);
#undef STRINGPIECE_BINARY_PREDICATE
int compare(const StringPiece& x) const {
int r = memcmp(ptr_, x.ptr_, length_ < x.length_ ? length_ : x.length_);
if (r == 0) {
if (length_ < x.length_) r = -1;
else if (length_ > x.length_) r = +1;
}
return r;
}
string as_string() const {
return string(data(), size());
}
void CopyToString(string* target) const {
target->assign(ptr_, length_);
}
// Does "this" start with "x"
bool starts_with(const StringPiece& x) const {
return ((length_ >= x.length_) && (memcmp(ptr_, x.ptr_, x.length_) == 0));
}
};
} // namespace pcrecpp
// ------------------------------------------------------------------
// Functions used to create STL containers that use StringPiece
// Remember that a StringPiece's lifetime had better be less than
// that of the underlying string or char*. If it is not, then you
// cannot safely store a StringPiece into an STL container
// ------------------------------------------------------------------
#ifdef HAVE_TYPE_TRAITS
// This makes vector<StringPiece> really fast for some STL implementations
template<> struct __type_traits<pcrecpp::StringPiece> {
typedef __true_type has_trivial_default_constructor;
typedef __true_type has_trivial_copy_constructor;
typedef __true_type has_trivial_assignment_operator;
typedef __true_type has_trivial_destructor;
typedef __true_type is_POD_type;
};
#endif
// allow StringPiece to be logged
std::ostream& operator<<(std::ostream& o, const pcrecpp::StringPiece& piece);
#endif /* _PCRE_STRINGPIECE_H */

145
ext/pcre/pcrelib/pcre_stringpiece_unittest.cc
View File

@ -1,145 +0,0 @@
// Copyright 2003 and onwards Google Inc.
// Author: Sanjay Ghemawat
#include <stdio.h>
#include <map>
#include <algorithm> // for make_pair
#include <pcre_stringpiece.h>
// CHECK dies with a fatal error if condition is not true. It is *not*
// controlled by NDEBUG, so the check will be executed regardless of
// compilation mode. Therefore, it is safe to do things like:
// CHECK(fp->Write(x) == 4)
#define CHECK(condition) do { \
if (!(condition)) { \
fprintf(stderr, "%s:%d: Check failed: %s\n", \
__FILE__, __LINE__, #condition); \
exit(1); \
} \
} while (0)
using std::map;
using std::make_pair;
using pcrecpp::StringPiece;
static void CheckSTLComparator() {
string s1("foo");
string s2("bar");
string s3("baz");
StringPiece p1(s1);
StringPiece p2(s2);
StringPiece p3(s3);
typedef map<StringPiece, int> TestMap;
TestMap map;
map.insert(make_pair(p1, 0));
map.insert(make_pair(p2, 1));
map.insert(make_pair(p3, 2));
CHECK(map.size() == 3);
TestMap::const_iterator iter = map.begin();
CHECK(iter->second == 1);
++iter;
CHECK(iter->second == 2);
++iter;
CHECK(iter->second == 0);
++iter;
CHECK(iter == map.end());
TestMap::iterator new_iter = map.find("zot");
CHECK(new_iter == map.end());
new_iter = map.find("bar");
CHECK(new_iter != map.end());
map.erase(new_iter);
CHECK(map.size() == 2);
iter = map.begin();
CHECK(iter->second == 2);
++iter;
CHECK(iter->second == 0);
++iter;
CHECK(iter == map.end());
}
static void CheckComparisonOperators() {
#define CMP_Y(op, x, y) \
CHECK( (StringPiece((x)) op StringPiece((y)))); \
CHECK( (StringPiece((x)).compare(StringPiece((y))) op 0))
#define CMP_N(op, x, y) \
CHECK(!(StringPiece((x)) op StringPiece((y)))); \
CHECK(!(StringPiece((x)).compare(StringPiece((y))) op 0))
CMP_Y(==, "", "");
CMP_Y(==, "a", "a");
CMP_Y(==, "aa", "aa");
CMP_N(==, "a", "");
CMP_N(==, "", "a");
CMP_N(==, "a", "b");
CMP_N(==, "a", "aa");
CMP_N(==, "aa", "a");
CMP_N(!=, "", "");
CMP_N(!=, "a", "a");
CMP_N(!=, "aa", "aa");
CMP_Y(!=, "a", "");
CMP_Y(!=, "", "a");
CMP_Y(!=, "a", "b");
CMP_Y(!=, "a", "aa");
CMP_Y(!=, "aa", "a");
CMP_Y(<, "a", "b");
CMP_Y(<, "a", "aa");
CMP_Y(<, "aa", "b");
CMP_Y(<, "aa", "bb");
CMP_N(<, "a", "a");
CMP_N(<, "b", "a");
CMP_N(<, "aa", "a");
CMP_N(<, "b", "aa");
CMP_N(<, "bb", "aa");
CMP_Y(<=, "a", "a");
CMP_Y(<=, "a", "b");
CMP_Y(<=, "a", "aa");
CMP_Y(<=, "aa", "b");
CMP_Y(<=, "aa", "bb");
CMP_N(<=, "b", "a");
CMP_N(<=, "aa", "a");
CMP_N(<=, "b", "aa");
CMP_N(<=, "bb", "aa");
CMP_N(>=, "a", "b");
CMP_N(>=, "a", "aa");
CMP_N(>=, "aa", "b");
CMP_N(>=, "aa", "bb");
CMP_Y(>=, "a", "a");
CMP_Y(>=, "b", "a");
CMP_Y(>=, "aa", "a");
CMP_Y(>=, "b", "aa");
CMP_Y(>=, "bb", "aa");
CMP_N(>, "a", "a");
CMP_N(>, "a", "b");
CMP_N(>, "a", "aa");
CMP_N(>, "aa", "b");
CMP_N(>, "aa", "bb");
CMP_Y(>, "b", "a");
CMP_Y(>, "aa", "a");
CMP_Y(>, "b", "aa");
CMP_Y(>, "bb", "aa");
#undef CMP_Y
#undef CMP_N
}
int main(int argc, char** argv) {
CheckComparisonOperators();
CheckSTLComparator();
printf("OK\n");
return 0;
}

8
ext/pcre/pcrelib/pcre_study.c
View File

@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2006 University of Cambridge
Copyright (c) 1997-2007 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -394,11 +394,13 @@ do
character with a value > 255. */
case OP_NCLASS:
#ifdef SUPPORT_UTF8
if (utf8)
{
start_bits[24] |= 0xf0; /* Bits for 0xc4 - 0xc8 */
memset(start_bits+25, 0xff, 7); /* Bits for 0xc9 - 0xff */
}
#endif
/* Fall through */
case OP_CLASS:
@ -411,6 +413,7 @@ do
value is > 127. In fact, there are only two possible starting bytes for
characters in the range 128 - 255. */
#ifdef SUPPORT_UTF8
if (utf8)
{
for (c = 0; c < 16; c++) start_bits[c] |= tcode[c];
@ -428,6 +431,7 @@ do
/* In non-UTF-8 mode, the two bit maps are completely compatible. */
else
#endif
{
for (c = 0; c < 32; c++) start_bits[c] |= tcode[c];
}
@ -487,7 +491,7 @@ Returns: pointer to a pcre_extra block, with study_data filled in and the
NULL on error or if no optimization possible
*/
PCRE_DATA_SCOPE pcre_extra *
PCRE_EXP_DEFN pcre_extra *
pcre_study(const pcre *external_re, int options, const char **errorptr)
{
uschar start_bits[32];

6
ext/pcre/pcrelib/pcre_tables.c
View File

@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2006 University of Cambridge
Copyright (c) 1997-2007 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -61,6 +61,8 @@ const uschar _pcre_OP_lengths[] = { OP_LENGTHS };
/* These are the breakpoints for different numbers of bytes in a UTF-8
character. */
#ifdef SUPPORT_UTF8
const int _pcre_utf8_table1[] =
{ 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff};
@ -194,4 +196,6 @@ const ucp_type_table _pcre_utt[] = {
const int _pcre_utt_size = sizeof(_pcre_utt)/sizeof(ucp_type_table);
#endif /* SUPPORT_UTF8 */
/* End of pcre_tables.c */

2
ext/pcre/pcrelib/pcre_try_flipped.c
View File

@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2006 University of Cambridge
Copyright (c) 1997-2007 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without

6
ext/pcre/pcrelib/pcre_ucp_searchfuncs.c
View File

@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2006 University of Cambridge
Copyright (c) 1997-2007 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -45,12 +45,12 @@ properties. */
#include "ucp.h" /* Category definitions */
#include "ucpinternal.h" /* Internal table details */
#include "ucptable.c" /* The table itself */
#include "ucptable.h" /* The table itself */
/* Table to translate from particular type value to the general value. */
static int ucp_gentype[] = {
static const int ucp_gentype[] = {
ucp_C, ucp_C, ucp_C, ucp_C, ucp_C, /* Cc, Cf, Cn, Co, Cs */
ucp_L, ucp_L, ucp_L, ucp_L, ucp_L, /* Ll, Lu, Lm, Lo, Lt */
ucp_M, ucp_M, ucp_M, /* Mc, Me, Mn */

4
ext/pcre/pcrelib/pcre_valid_utf8.c
View File

@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2006 University of Cambridge
Copyright (c) 1997-2007 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -66,6 +66,7 @@ Returns: < 0 if the string is a valid UTF-8 string
int
_pcre_valid_utf8(const uschar *string, int length)
{
#ifdef SUPPORT_UTF8
register const uschar *p;
if (length < 0)
@ -123,6 +124,7 @@ for (p = string; length-- > 0; p++)
if ((*(++p) & 0xc0) != 0x80) return p - string;
}
}
#endif
return -1;
}

4
ext/pcre/pcrelib/pcre_version.c
View File

@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2006 University of Cambridge
Copyright (c) 1997-2007 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -75,7 +75,7 @@ I could find no way of detecting that a macro is defined as an empty string at
pre-processor time. This hack uses a standard trick for avoiding calling
the STRING macro with an empty argument when doing the test. */
PCRE_DATA_SCOPE const char *
PCRE_EXP_DEFN const char *
pcre_version(void)
{
return (XSTRING(Z PCRE_PRERELEASE)[1] == 0)?

2
ext/pcre/pcrelib/pcre_xclass.c
View File

@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2006 University of Cambridge
Copyright (c) 1997-2007 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without

857
ext/pcre/pcrelib/pcrecpp.cc
View File

@ -1,857 +0,0 @@
// Copyright (c) 2005, Google Inc.
// All rights reserved.
//
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions are
// met:
//
// * Redistributions of source code must retain the above copyright
// notice, this list of conditions and the following disclaimer.
// * Redistributions in binary form must reproduce the above
// copyright notice, this list of conditions and the following disclaimer
// in the documentation and/or other materials provided with the
// distribution.
// * Neither the name of Google Inc. nor the names of its
// contributors may be used to endorse or promote products derived from
// this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
//
// Author: Sanjay Ghemawat
#include <stdlib.h>
#include <stdio.h>
#include <ctype.h>
#include <limits.h> /* for SHRT_MIN, USHRT_MAX, etc */
#include <assert.h>
#include <errno.h>
#include <string>
#include <algorithm>
#include "config.h"
// We need this to compile the proper dll on windows/msys. This is copied
// from pcre_internal.h. It would probably be better just to include that.
#define PCRE_DEFINITION /* Win32 __declspec(export) trigger for .dll */
#include "pcre.h"
#include "pcre_stringpiece.h"
#include "pcrecpp.h"
namespace pcrecpp {
// Maximum number of args we can set
static const int kMaxArgs = 16;
static const int kVecSize = (1 + kMaxArgs) * 3; // results + PCRE workspace
// Special object that stands-in for no argument
Arg no_arg((void*)NULL);
// If a regular expression has no error, its error_ field points here
static const string empty_string;
// If the user doesn't ask for any options, we just use this one
static RE_Options default_options;
void RE::Init(const string& pat, const RE_Options* options) {
pattern_ = pat;
if (options == NULL) {
options_ = default_options;
} else {
options_ = *options;
}
error_ = &empty_string;
re_full_ = NULL;
re_partial_ = NULL;
re_partial_ = Compile(UNANCHORED);
if (re_partial_ != NULL) {
// Check for complicated patterns. The following change is
// conservative in that it may treat some "simple" patterns
// as "complex" (e.g., if the vertical bar is in a character
// class or is escaped). But it seems good enough.
if (strchr(pat.c_str(), '|') == NULL) {
// Simple pattern: we can use position-based checks to perform
// fully anchored matches
re_full_ = re_partial_;
} else {
// We need a special pattern for anchored matches
re_full_ = Compile(ANCHOR_BOTH);
}
}
}
void RE::Cleanup() {
if (re_full_ != NULL && re_full_ != re_partial_) (*pcre_free)(re_full_);
if (re_partial_ != NULL) (*pcre_free)(re_partial_);
if (error_ != &empty_string) delete error_;
}
RE::~RE() {
Cleanup();
}
pcre* RE::Compile(Anchor anchor) {
// First, convert RE_Options into pcre options
int pcre_options = 0;
pcre_options = options_.all_options();
// Special treatment for anchoring. This is needed because at
// runtime pcre only provides an option for anchoring at the
// beginning of a string (unless you use offset).
//
// There are three types of anchoring we want:
// UNANCHORED Compile the original pattern, and use
// a pcre unanchored match.
// ANCHOR_START Compile the original pattern, and use
// a pcre anchored match.
// ANCHOR_BOTH Tack a "\z" to the end of the original pattern
// and use a pcre anchored match.
const char* compile_error;
int eoffset;
pcre* re;
if (anchor != ANCHOR_BOTH) {
re = pcre_compile(pattern_.c_str(), pcre_options,
&compile_error, &eoffset, NULL);
} else {
// Tack a '\z' at the end of RE. Parenthesize it first so that
// the '\z' applies to all top-level alternatives in the regexp.
string wrapped = "(?:"; // A non-counting grouping operator
wrapped += pattern_;
wrapped += ")\\z";
re = pcre_compile(wrapped.c_str(), pcre_options,
&compile_error, &eoffset, NULL);
}
if (re == NULL) {
if (error_ == &empty_string) error_ = new string(compile_error);
}
return re;
}
/***** Matching interfaces *****/
bool RE::FullMatch(const StringPiece& text,
const Arg& ptr1,
const Arg& ptr2,
const Arg& ptr3,
const Arg& ptr4,
const Arg& ptr5,
const Arg& ptr6,
const Arg& ptr7,
const Arg& ptr8,
const Arg& ptr9,
const Arg& ptr10,
const Arg& ptr11,
const Arg& ptr12,
const Arg& ptr13,
const Arg& ptr14,
const Arg& ptr15,
const Arg& ptr16) const {
const Arg* args[kMaxArgs];
int n = 0;
if (&ptr1 == &no_arg) goto done; args[n++] = &ptr1;
if (&ptr2 == &no_arg) goto done; args[n++] = &ptr2;
if (&ptr3 == &no_arg) goto done; args[n++] = &ptr3;
if (&ptr4 == &no_arg) goto done; args[n++] = &ptr4;
if (&ptr5 == &no_arg) goto done; args[n++] = &ptr5;
if (&ptr6 == &no_arg) goto done; args[n++] = &ptr6;
if (&ptr7 == &no_arg) goto done; args[n++] = &ptr7;
if (&ptr8 == &no_arg) goto done; args[n++] = &ptr8;
if (&ptr9 == &no_arg) goto done; args[n++] = &ptr9;
if (&ptr10 == &no_arg) goto done; args[n++] = &ptr10;
if (&ptr11 == &no_arg) goto done; args[n++] = &ptr11;
if (&ptr12 == &no_arg) goto done; args[n++] = &ptr12;
if (&ptr13 == &no_arg) goto done; args[n++] = &ptr13;
if (&ptr14 == &no_arg) goto done; args[n++] = &ptr14;
if (&ptr15 == &no_arg) goto done; args[n++] = &ptr15;
if (&ptr16 == &no_arg) goto done; args[n++] = &ptr16;
done:
int consumed;
int vec[kVecSize];
return DoMatchImpl(text, ANCHOR_BOTH, &consumed, args, n, vec, kVecSize);
}
bool RE::PartialMatch(const StringPiece& text,
const Arg& ptr1,
const Arg& ptr2,
const Arg& ptr3,
const Arg& ptr4,
const Arg& ptr5,
const Arg& ptr6,
const Arg& ptr7,
const Arg& ptr8,
const Arg& ptr9,
const Arg& ptr10,
const Arg& ptr11,
const Arg& ptr12,
const Arg& ptr13,
const Arg& ptr14,
const Arg& ptr15,
const Arg& ptr16) const {
const Arg* args[kMaxArgs];
int n = 0;
if (&ptr1 == &no_arg) goto done; args[n++] = &ptr1;
if (&ptr2 == &no_arg) goto done; args[n++] = &ptr2;
if (&ptr3 == &no_arg) goto done; args[n++] = &ptr3;
if (&ptr4 == &no_arg) goto done; args[n++] = &ptr4;
if (&ptr5 == &no_arg) goto done; args[n++] = &ptr5;
if (&ptr6 == &no_arg) goto done; args[n++] = &ptr6;
if (&ptr7 == &no_arg) goto done; args[n++] = &ptr7;
if (&ptr8 == &no_arg) goto done; args[n++] = &ptr8;
if (&ptr9 == &no_arg) goto done; args[n++] = &ptr9;
if (&ptr10 == &no_arg) goto done; args[n++] = &ptr10;
if (&ptr11 == &no_arg) goto done; args[n++] = &ptr11;
if (&ptr12 == &no_arg) goto done; args[n++] = &ptr12;
if (&ptr13 == &no_arg) goto done; args[n++] = &ptr13;
if (&ptr14 == &no_arg) goto done; args[n++] = &ptr14;
if (&ptr15 == &no_arg) goto done; args[n++] = &ptr15;
if (&ptr16 == &no_arg) goto done; args[n++] = &ptr16;
done:
int consumed;
int vec[kVecSize];
return DoMatchImpl(text, UNANCHORED, &consumed, args, n, vec, kVecSize);
}
bool RE::Consume(StringPiece* input,
const Arg& ptr1,
const Arg& ptr2,
const Arg& ptr3,
const Arg& ptr4,
const Arg& ptr5,
const Arg& ptr6,
const Arg& ptr7,
const Arg& ptr8,
const Arg& ptr9,
const Arg& ptr10,
const Arg& ptr11,
const Arg& ptr12,
const Arg& ptr13,
const Arg& ptr14,
const Arg& ptr15,
const Arg& ptr16) const {
const Arg* args[kMaxArgs];
int n = 0;
if (&ptr1 == &no_arg) goto done; args[n++] = &ptr1;
if (&ptr2 == &no_arg) goto done; args[n++] = &ptr2;
if (&ptr3 == &no_arg) goto done; args[n++] = &ptr3;
if (&ptr4 == &no_arg) goto done; args[n++] = &ptr4;
if (&ptr5 == &no_arg) goto done; args[n++] = &ptr5;
if (&ptr6 == &no_arg) goto done; args[n++] = &ptr6;
if (&ptr7 == &no_arg) goto done; args[n++] = &ptr7;
if (&ptr8 == &no_arg) goto done; args[n++] = &ptr8;
if (&ptr9 == &no_arg) goto done; args[n++] = &ptr9;
if (&ptr10 == &no_arg) goto done; args[n++] = &ptr10;
if (&ptr11 == &no_arg) goto done; args[n++] = &ptr11;
if (&ptr12 == &no_arg) goto done; args[n++] = &ptr12;
if (&ptr13 == &no_arg) goto done; args[n++] = &ptr13;
if (&ptr14 == &no_arg) goto done; args[n++] = &ptr14;
if (&ptr15 == &no_arg) goto done; args[n++] = &ptr15;
if (&ptr16 == &no_arg) goto done; args[n++] = &ptr16;
done:
int consumed;
int vec[kVecSize];
if (DoMatchImpl(*input, ANCHOR_START, &consumed,
args, n, vec, kVecSize)) {
input->remove_prefix(consumed);
return true;
} else {
return false;
}
}
bool RE::FindAndConsume(StringPiece* input,
const Arg& ptr1,
const Arg& ptr2,
const Arg& ptr3,
const Arg& ptr4,
const Arg& ptr5,
const Arg& ptr6,
const Arg& ptr7,
const Arg& ptr8,
const Arg& ptr9,
const Arg& ptr10,
const Arg& ptr11,
const Arg& ptr12,
const Arg& ptr13,
const Arg& ptr14,
const Arg& ptr15,
const Arg& ptr16) const {
const Arg* args[kMaxArgs];
int n = 0;
if (&ptr1 == &no_arg) goto done; args[n++] = &ptr1;
if (&ptr2 == &no_arg) goto done; args[n++] = &ptr2;
if (&ptr3 == &no_arg) goto done; args[n++] = &ptr3;
if (&ptr4 == &no_arg) goto done; args[n++] = &ptr4;
if (&ptr5 == &no_arg) goto done; args[n++] = &ptr5;
if (&ptr6 == &no_arg) goto done; args[n++] = &ptr6;
if (&ptr7 == &no_arg) goto done; args[n++] = &ptr7;
if (&ptr8 == &no_arg) goto done; args[n++] = &ptr8;
if (&ptr9 == &no_arg) goto done; args[n++] = &ptr9;
if (&ptr10 == &no_arg) goto done; args[n++] = &ptr10;
if (&ptr11 == &no_arg) goto done; args[n++] = &ptr11;
if (&ptr12 == &no_arg) goto done; args[n++] = &ptr12;
if (&ptr13 == &no_arg) goto done; args[n++] = &ptr13;
if (&ptr14 == &no_arg) goto done; args[n++] = &ptr14;
if (&ptr15 == &no_arg) goto done; args[n++] = &ptr15;
if (&ptr16 == &no_arg) goto done; args[n++] = &ptr16;
done:
int consumed;
int vec[kVecSize];
if (DoMatchImpl(*input, UNANCHORED, &consumed,
args, n, vec, kVecSize)) {
input->remove_prefix(consumed);
return true;
} else {
return false;
}
}
bool RE::Replace(const StringPiece& rewrite,
string *str) const {
int vec[kVecSize];
int matches = TryMatch(*str, 0, UNANCHORED, vec, kVecSize);
if (matches == 0)
return false;
string s;
if (!Rewrite(&s, rewrite, *str, vec, matches))
return false;
assert(vec[0] >= 0);
assert(vec[1] >= 0);
str->replace(vec[0], vec[1] - vec[0], s);
return true;
}
// Returns PCRE_NEWLINE_CRLF, PCRE_NEWLINE_CR, or PCRE_NEWLINE_LF.
// Note that PCRE_NEWLINE_CRLF is defined to be P_N_CR | P_N_LF.
static int NewlineMode(int pcre_options) {
// TODO: if we can make it threadsafe, cache this var
int newline_mode = 0;
/* if (newline_mode) return newline_mode; */ // do this once it's cached
if (pcre_options & (PCRE_NEWLINE_CRLF|PCRE_NEWLINE_CR|PCRE_NEWLINE_LF)) {
newline_mode = (pcre_options &
(PCRE_NEWLINE_CRLF|PCRE_NEWLINE_CR|PCRE_NEWLINE_LF));
} else {
int newline;
pcre_config(PCRE_CONFIG_NEWLINE, &newline);
if (newline == 10)
newline_mode = PCRE_NEWLINE_LF;
else if (newline == 13)
newline_mode = PCRE_NEWLINE_CR;
else if (newline == 3338)
newline_mode = PCRE_NEWLINE_CRLF;
else
assert("" == "Unexpected return value from pcre_config(NEWLINE)");
}
return newline_mode;
}
int RE::GlobalReplace(const StringPiece& rewrite,
string *str) const {
int count = 0;
int vec[kVecSize];
string out;
int start = 0;
int lastend = -1;
for (; start <= static_cast<int>(str->length()); count++) {
int matches = TryMatch(*str, start, UNANCHORED, vec, kVecSize);
if (matches <= 0)
break;
int matchstart = vec[0], matchend = vec[1];
assert(matchstart >= start);
assert(matchend >= matchstart);
if (matchstart == matchend && matchstart == lastend) {
// advance one character if we matched an empty string at the same
// place as the last match occurred
matchend = start + 1;
// If the current char is CR and we're in CRLF mode, skip LF too.
// Note it's better to call pcre_fullinfo() than to examine
// all_options(), since options_ could have changed bewteen
// compile-time and now, but this is simpler and safe enough.
if (start+1 < static_cast<int>(str->length()) &&
(*str)[start] == '\r' && (*str)[start+1] == '\n' &&
NewlineMode(options_.all_options()) == PCRE_NEWLINE_CRLF) {
matchend++;
}
// We also need to advance more than one char if we're in utf8 mode.
#ifdef SUPPORT_UTF8
if (options_.utf8()) {
while (matchend < static_cast<int>(str->length()) &&
((*str)[matchend] & 0xc0) == 0x80)
matchend++;
}
#endif
if (matchend <= static_cast<int>(str->length()))
out.append(*str, start, matchend - start);
start = matchend;
} else {
out.append(*str, start, matchstart - start);
Rewrite(&out, rewrite, *str, vec, matches);
start = matchend;
lastend = matchend;
count++;
}
}
if (count == 0)
return 0;
if (start < static_cast<int>(str->length()))
out.append(*str, start, str->length() - start);
swap(out, *str);
return count;
}
bool RE::Extract(const StringPiece& rewrite,
const StringPiece& text,
string *out) const {
int vec[kVecSize];
int matches = TryMatch(text, 0, UNANCHORED, vec, kVecSize);
if (matches == 0)
return false;
out->erase();
return Rewrite(out, rewrite, text, vec, matches);
}
/*static*/ string RE::QuoteMeta(const StringPiece& unquoted) {
string result;
// Escape any ascii character not in [A-Za-z_0-9].
//
// Note that it's legal to escape a character even if it has no
// special meaning in a regular expression -- so this function does
// that. (This also makes it identical to the perl function of the
// same name; see `perldoc -f quotemeta`.)
for (int ii = 0; ii < unquoted.size(); ++ii) {
// Note that using 'isalnum' here raises the benchmark time from
// 32ns to 58ns:
if ((unquoted[ii] < 'a' || unquoted[ii] > 'z') &&
(unquoted[ii] < 'A' || unquoted[ii] > 'Z') &&
(unquoted[ii] < '0' || unquoted[ii] > '9') &&
unquoted[ii] != '_' &&
// If this is the part of a UTF8 or Latin1 character, we need
// to copy this byte without escaping. Experimentally this is
// what works correctly with the regexp library.
!(unquoted[ii] & 128)) {
result += '\\';
}
result += unquoted[ii];
}
return result;
}
/***** Actual matching and rewriting code *****/
int RE::TryMatch(const StringPiece& text,
int startpos,
Anchor anchor,
int *vec,
int vecsize) const {
pcre* re = (anchor == ANCHOR_BOTH) ? re_full_ : re_partial_;
if (re == NULL) {
//fprintf(stderr, "Matching against invalid re: %s\n", error_->c_str());
return 0;
}
pcre_extra extra = { 0 };
if (options_.match_limit() > 0) {
extra.flags |= PCRE_EXTRA_MATCH_LIMIT;
extra.match_limit = options_.match_limit();
}
if (options_.match_limit_recursion() > 0) {
extra.flags |= PCRE_EXTRA_MATCH_LIMIT_RECURSION;
extra.match_limit_recursion = options_.match_limit_recursion();
}
int rc = pcre_exec(re, // The regular expression object
&extra,
(text.data() == NULL) ? "" : text.data(),
text.size(),
startpos,
(anchor == UNANCHORED) ? 0 : PCRE_ANCHORED,
vec,
vecsize);
// Handle errors
if (rc == PCRE_ERROR_NOMATCH) {
return 0;
} else if (rc < 0) {
//fprintf(stderr, "Unexpected return code: %d when matching '%s'\n",
// re, pattern_.c_str());
return 0;
} else if (rc == 0) {
// pcre_exec() returns 0 as a special case when the number of
// capturing subpatterns exceeds the size of the vector.
// When this happens, there is a match and the output vector
// is filled, but we miss out on the positions of the extra subpatterns.
rc = vecsize / 2;
}
if ((anchor == ANCHOR_BOTH) && (re_full_ == re_partial_)) {
// We need an extra check to make sure that the match extended
// to the end of the input string
assert(vec[0] == 0); // PCRE_ANCHORED forces starting match
if (vec[1] != text.size()) return 0; // Did not get ending match
}
return rc;
}
bool RE::DoMatchImpl(const StringPiece& text,
Anchor anchor,
int* consumed,
const Arg* const* args,
int n,
int* vec,
int vecsize) const {
assert((1 + n) * 3 <= vecsize); // results + PCRE workspace
int matches = TryMatch(text, 0, anchor, vec, vecsize);
assert(matches >= 0); // TryMatch never returns negatives
if (matches == 0)
return false;
*consumed = vec[1];
if (n == 0 || args == NULL) {
// We are not interested in results
return true;
}
if (NumberOfCapturingGroups() < n) {
// RE has fewer capturing groups than number of arg pointers passed in
return false;
}
// If we got here, we must have matched the whole pattern.
// We do not need (can not do) any more checks on the value of 'matches' here
// -- see the comment for TryMatch.
for (int i = 0; i < n; i++) {
const int start = vec[2*(i+1)];
const int limit = vec[2*(i+1)+1];
if (!args[i]->Parse(text.data() + start, limit-start)) {
// TODO: Should we indicate what the error was?
return false;
}
}
return true;
}
bool RE::DoMatch(const StringPiece& text,
Anchor anchor,
int* consumed,
const Arg* const args[],
int n) const {
assert(n >= 0);
size_t const vecsize = (1 + n) * 3; // results + PCRE workspace
// (as for kVecSize)
int space[21]; // use stack allocation for small vecsize (common case)
int* vec = vecsize <= 21 ? space : new int[vecsize];
bool retval = DoMatchImpl(text, anchor, consumed, args, n, vec, vecsize);
if (vec != space) delete [] vec;
return retval;
}
bool RE::Rewrite(string *out, const StringPiece &rewrite,
const StringPiece &text, int *vec, int veclen) const {
for (const char *s = rewrite.data(), *end = s + rewrite.size();
s < end; s++) {
int c = *s;
if (c == '\\') {
c = *++s;
if (isdigit(c)) {
int n = (c - '0');
if (n >= veclen) {
//fprintf(stderr, requested group %d in regexp %.*s\n",
// n, rewrite.size(), rewrite.data());
return false;
}
int start = vec[2 * n];
if (start >= 0)
out->append(text.data() + start, vec[2 * n + 1] - start);
} else if (c == '\\') {
out->push_back('\\');
} else {
//fprintf(stderr, "invalid rewrite pattern: %.*s\n",
// rewrite.size(), rewrite.data());
return false;
}
} else {
out->push_back(c);
}
}
return true;
}
// Return the number of capturing subpatterns, or -1 if the
// regexp wasn't valid on construction.
int RE::NumberOfCapturingGroups() const {
if (re_partial_ == NULL) return -1;
int result;
int pcre_retval = pcre_fullinfo(re_partial_, // The regular expression object
NULL, // We did not study the pattern
PCRE_INFO_CAPTURECOUNT,
&result);
assert(pcre_retval == 0);
return result;
}
/***** Parsers for various types *****/
bool Arg::parse_null(const char* str, int n, void* dest) {
// We fail if somebody asked us to store into a non-NULL void* pointer
return (dest == NULL);
}
bool Arg::parse_string(const char* str, int n, void* dest) {
reinterpret_cast<string*>(dest)->assign(str, n);
return true;
}
bool Arg::parse_stringpiece(const char* str, int n, void* dest) {
reinterpret_cast<StringPiece*>(dest)->set(str, n);
return true;
}
bool Arg::parse_char(const char* str, int n, void* dest) {
if (n != 1) return false;
*(reinterpret_cast<char*>(dest)) = str[0];
return true;
}
bool Arg::parse_uchar(const char* str, int n, void* dest) {
if (n != 1) return false;
*(reinterpret_cast<unsigned char*>(dest)) = str[0];
return true;
}
// Largest number spec that we are willing to parse
static const int kMaxNumberLength = 32;
// REQUIRES "buf" must have length at least kMaxNumberLength+1
// REQUIRES "n > 0"
// Copies "str" into "buf" and null-terminates if necessary.
// Returns one of:
// a. "str" if no termination is needed
// b. "buf" if the string was copied and null-terminated
// c. "" if the input was invalid and has no hope of being parsed
static const char* TerminateNumber(char* buf, const char* str, int n) {
if ((n > 0) && isspace(*str)) {
// We are less forgiving than the strtoxxx() routines and do not
// allow leading spaces.
return "";
}
// See if the character right after the input text may potentially
// look like a digit.
if (isdigit(str[n]) ||
((str[n] >= 'a') && (str[n] <= 'f')) ||
((str[n] >= 'A') && (str[n] <= 'F'))) {
if (n > kMaxNumberLength) return ""; // Input too big to be a valid number
memcpy(buf, str, n);
buf[n] = '\0';
return buf;
} else {
// We can parse right out of the supplied string, so return it.
return str;
}
}
bool Arg::parse_long_radix(const char* str,
int n,
void* dest,
int radix) {
if (n == 0) return false;
char buf[kMaxNumberLength+1];
str = TerminateNumber(buf, str, n);
char* end;
errno = 0;
long r = strtol(str, &end, radix);
if (end != str + n) return false; // Leftover junk
if (errno) return false;
*(reinterpret_cast<long*>(dest)) = r;
return true;
}
bool Arg::parse_ulong_radix(const char* str,
int n,
void* dest,
int radix) {
if (n == 0) return false;
char buf[kMaxNumberLength+1];
str = TerminateNumber(buf, str, n);
if (str[0] == '-') return false; // strtoul() on a negative number?!
char* end;
errno = 0;
unsigned long r = strtoul(str, &end, radix);
if (end != str + n) return false; // Leftover junk
if (errno) return false;
*(reinterpret_cast<unsigned long*>(dest)) = r;
return true;
}
bool Arg::parse_short_radix(const char* str,
int n,
void* dest,
int radix) {
long r;
if (!parse_long_radix(str, n, &r, radix)) return false; // Could not parse
if (r < SHRT_MIN || r > SHRT_MAX) return false; // Out of range
*(reinterpret_cast<short*>(dest)) = r;
return true;
}
bool Arg::parse_ushort_radix(const char* str,
int n,
void* dest,
int radix) {
unsigned long r;
if (!parse_ulong_radix(str, n, &r, radix)) return false; // Could not parse
if (r > USHRT_MAX) return false; // Out of range
*(reinterpret_cast<unsigned short*>(dest)) = r;
return true;
}
bool Arg::parse_int_radix(const char* str,
int n,
void* dest,
int radix) {
long r;
if (!parse_long_radix(str, n, &r, radix)) return false; // Could not parse
if (r < INT_MIN || r > INT_MAX) return false; // Out of range
*(reinterpret_cast<int*>(dest)) = r;
return true;
}
bool Arg::parse_uint_radix(const char* str,
int n,
void* dest,
int radix) {
unsigned long r;
if (!parse_ulong_radix(str, n, &r, radix)) return false; // Could not parse
if (r > UINT_MAX) return false; // Out of range
*(reinterpret_cast<unsigned int*>(dest)) = r;
return true;
}
bool Arg::parse_longlong_radix(const char* str,
int n,
void* dest,
int radix) {
#ifndef HAVE_LONG_LONG
return false;
#else
if (n == 0) return false;
char buf[kMaxNumberLength+1];
str = TerminateNumber(buf, str, n);
char* end;
errno = 0;
#if defined HAVE_STRTOQ
long long r = strtoq(str, &end, radix);
#elif defined HAVE_STRTOLL
long long r = strtoll(str, &end, radix);
#else
#error parse_longlong_radix: cannot convert input to a long-long
#endif
if (end != str + n) return false; // Leftover junk
if (errno) return false;
*(reinterpret_cast<long long*>(dest)) = r;
return true;
#endif /* HAVE_LONG_LONG */
}
bool Arg::parse_ulonglong_radix(const char* str,
int n,
void* dest,
int radix) {
#ifndef HAVE_UNSIGNED_LONG_LONG
return false;
#else
if (n == 0) return false;
char buf[kMaxNumberLength+1];
str = TerminateNumber(buf, str, n);
if (str[0] == '-') return false; // strtoull() on a negative number?!
char* end;
errno = 0;
#if defined HAVE_STRTOQ
unsigned long long r = strtouq(str, &end, radix);
#elif defined HAVE_STRTOLL
unsigned long long r = strtoull(str, &end, radix);
#else
#error parse_ulonglong_radix: cannot convert input to a long-long
#endif
if (end != str + n) return false; // Leftover junk
if (errno) return false;
*(reinterpret_cast<unsigned long long*>(dest)) = r;
return true;
#endif /* HAVE_UNSIGNED_LONG_LONG */
}
bool Arg::parse_double(const char* str, int n, void* dest) {
if (n == 0) return false;
static const int kMaxLength = 200;
char buf[kMaxLength];
if (n >= kMaxLength) return false;
memcpy(buf, str, n);
buf[n] = '\0';
errno = 0;
char* end;
double r = strtod(buf, &end);
if (end != buf + n) return false; // Leftover junk
if (errno) return false;
*(reinterpret_cast<double*>(dest)) = r;
return true;
}
bool Arg::parse_float(const char* str, int n, void* dest) {
double r;
if (!parse_double(str, n, &r)) return false;
*(reinterpret_cast<float*>(dest)) = static_cast<float>(r);
return true;
}
#define DEFINE_INTEGER_PARSERS(name) \
bool Arg::parse_##name(const char* str, int n, void* dest) { \
return parse_##name##_radix(str, n, dest, 10); \
} \
bool Arg::parse_##name##_hex(const char* str, int n, void* dest) { \
return parse_##name##_radix(str, n, dest, 16); \
} \
bool Arg::parse_##name##_octal(const char* str, int n, void* dest) { \
return parse_##name##_radix(str, n, dest, 8); \
} \
bool Arg::parse_##name##_cradix(const char* str, int n, void* dest) { \
return parse_##name##_radix(str, n, dest, 0); \
}
DEFINE_INTEGER_PARSERS(short) /* */
DEFINE_INTEGER_PARSERS(ushort) /* */
DEFINE_INTEGER_PARSERS(int) /* Don't use semicolons after these */
DEFINE_INTEGER_PARSERS(uint) /* statements because they can cause */
DEFINE_INTEGER_PARSERS(long) /* compiler warnings if the checking */
DEFINE_INTEGER_PARSERS(ulong) /* level is turned up high enough. */
DEFINE_INTEGER_PARSERS(longlong) /* */
DEFINE_INTEGER_PARSERS(ulonglong) /* */
#undef DEFINE_INTEGER_PARSERS
} // namespace pcrecpp

695
ext/pcre/pcrelib/pcrecpp.h
View File

@ -1,695 +0,0 @@
// Copyright (c) 2005, Google Inc.
// All rights reserved.
//
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions are
// met:
//
// * Redistributions of source code must retain the above copyright
// notice, this list of conditions and the following disclaimer.
// * Redistributions in binary form must reproduce the above
// copyright notice, this list of conditions and the following disclaimer
// in the documentation and/or other materials provided with the
// distribution.
// * Neither the name of Google Inc. nor the names of its
// contributors may be used to endorse or promote products derived from
// this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
//
// Author: Sanjay Ghemawat
// Support for PCRE_XXX modifiers added by Giuseppe Maxia, July 2005
#ifndef _PCRECPP_H
#define _PCRECPP_H
// C++ interface to the pcre regular-expression library. RE supports
// Perl-style regular expressions (with extensions like \d, \w, \s,
// ...).
//
// -----------------------------------------------------------------------
// REGEXP SYNTAX:
//
// This module is part of the pcre library and hence supports its syntax
// for regular expressions.
//
// The syntax is pretty similar to Perl's. For those not familiar
// with Perl's regular expressions, here are some examples of the most
// commonly used extensions:
//
// "hello (\\w+) world" -- \w matches a "word" character
// "version (\\d+)" -- \d matches a digit
// "hello\\s+world" -- \s matches any whitespace character
// "\\b(\\w+)\\b" -- \b matches empty string at a word boundary
// "(?i)hello" -- (?i) turns on case-insensitive matching
// "/\\*(.*?)\\*/" -- .*? matches . minimum no. of times possible
//
// -----------------------------------------------------------------------
// MATCHING INTERFACE:
//
// The "FullMatch" operation checks that supplied text matches a
// supplied pattern exactly.
//
// Example: successful match
// pcrecpp::RE re("h.*o");
// re.FullMatch("hello");
//
// Example: unsuccessful match (requires full match):
// pcrecpp::RE re("e");
// !re.FullMatch("hello");
//
// Example: creating a temporary RE object:
// pcrecpp::RE("h.*o").FullMatch("hello");
//
// You can pass in a "const char*" or a "string" for "text". The
// examples below tend to use a const char*.
//
// You can, as in the different examples above, store the RE object
// explicitly in a variable or use a temporary RE object. The
// examples below use one mode or the other arbitrarily. Either
// could correctly be used for any of these examples.
//
// -----------------------------------------------------------------------
// MATCHING WITH SUB-STRING EXTRACTION:
//
// You can supply extra pointer arguments to extract matched subpieces.
//
// Example: extracts "ruby" into "s" and 1234 into "i"
// int i;
// string s;
// pcrecpp::RE re("(\\w+):(\\d+)");
// re.FullMatch("ruby:1234", &s, &i);
//
// Example: does not try to extract any extra sub-patterns
// re.FullMatch("ruby:1234", &s);
//
// Example: does not try to extract into NULL
// re.FullMatch("ruby:1234", NULL, &i);
//
// Example: integer overflow causes failure
// !re.FullMatch("ruby:1234567891234", NULL, &i);
//
// Example: fails because there aren't enough sub-patterns:
// !pcrecpp::RE("\\w+:\\d+").FullMatch("ruby:1234", &s);
//
// Example: fails because string cannot be stored in integer
// !pcrecpp::RE("(.*)").FullMatch("ruby", &i);
//
// The provided pointer arguments can be pointers to any scalar numeric
// type, or one of
// string (matched piece is copied to string)
// StringPiece (StringPiece is mutated to point to matched piece)
// T (where "bool T::ParseFrom(const char*, int)" exists)
// NULL (the corresponding matched sub-pattern is not copied)
//
// CAVEAT: An optional sub-pattern that does not exist in the matched
// string is assigned the empty string. Therefore, the following will
// return false (because the empty string is not a valid number):
// int number;
// pcrecpp::RE::FullMatch("abc", "[a-z]+(\\d+)?", &number);
//
// -----------------------------------------------------------------------
// DO_MATCH
//
// The matching interface supports at most 16 arguments per call.
// If you need more, consider using the more general interface
// pcrecpp::RE::DoMatch(). See pcrecpp.h for the signature for DoMatch.
//
// -----------------------------------------------------------------------
// PARTIAL MATCHES
//
// You can use the "PartialMatch" operation when you want the pattern
// to match any substring of the text.
//
// Example: simple search for a string:
// pcrecpp::RE("ell").PartialMatch("hello");
//
// Example: find first number in a string:
// int number;
// pcrecpp::RE re("(\\d+)");
// re.PartialMatch("x*100 + 20", &number);
// assert(number == 100);
//
// -----------------------------------------------------------------------
// UTF-8 AND THE MATCHING INTERFACE:
//
// By default, pattern and text are plain text, one byte per character.
// The UTF8 flag, passed to the constructor, causes both pattern
// and string to be treated as UTF-8 text, still a byte stream but
// potentially multiple bytes per character. In practice, the text
// is likelier to be UTF-8 than the pattern, but the match returned
// may depend on the UTF8 flag, so always use it when matching
// UTF8 text. E.g., "." will match one byte normally but with UTF8
// set may match up to three bytes of a multi-byte character.
//
// Example:
// pcrecpp::RE_Options options;
// options.set_utf8();
// pcrecpp::RE re(utf8_pattern, options);
// re.FullMatch(utf8_string);
//
// Example: using the convenience function UTF8():
// pcrecpp::RE re(utf8_pattern, pcrecpp::UTF8());
// re.FullMatch(utf8_string);
//
// NOTE: The UTF8 option is ignored if pcre was not configured with the
// --enable-utf8 flag.
//
// -----------------------------------------------------------------------
// PASSING MODIFIERS TO THE REGULAR EXPRESSION ENGINE
//
// PCRE defines some modifiers to change the behavior of the regular
// expression engine.
// The C++ wrapper defines an auxiliary class, RE_Options, as a vehicle
// to pass such modifiers to a RE class.
//
// Currently, the following modifiers are supported
//
// modifier description Perl corresponding
//
// PCRE_CASELESS case insensitive match /i
// PCRE_MULTILINE multiple lines match /m
// PCRE_DOTALL dot matches newlines /s
// PCRE_DOLLAR_ENDONLY $ matches only at end N/A
// PCRE_EXTRA strict escape parsing N/A
// PCRE_EXTENDED ignore whitespaces /x
// PCRE_UTF8 handles UTF8 chars built-in
// PCRE_UNGREEDY reverses * and *? N/A
// PCRE_NO_AUTO_CAPTURE disables matching parens N/A (*)
//
// (For a full account on how each modifier works, please check the
// PCRE API reference manual).
//
// (*) Both Perl and PCRE allow non matching parentheses by means of the
// "?:" modifier within the pattern itself. e.g. (?:ab|cd) does not
// capture, while (ab|cd) does.
//
// For each modifier, there are two member functions whose name is made
// out of the modifier in lowercase, without the "PCRE_" prefix. For
// instance, PCRE_CASELESS is handled by
// bool caseless(),
// which returns true if the modifier is set, and
// RE_Options & set_caseless(bool),
// which sets or unsets the modifier.
//
// Moreover, PCRE_EXTRA_MATCH_LIMIT can be accessed through the
// set_match_limit() and match_limit() member functions.
// Setting match_limit to a non-zero value will limit the executation of
// pcre to keep it from doing bad things like blowing the stack or taking
// an eternity to return a result. A value of 5000 is good enough to stop
// stack blowup in a 2MB thread stack. Setting match_limit to zero will
// disable match limiting. Alternately, you can set match_limit_recursion()
// which uses PCRE_EXTRA_MATCH_LIMIT_RECURSION to limit how much pcre
// recurses. match_limit() caps the number of matches pcre does;
// match_limit_recrusion() caps the depth of recursion.
//
// Normally, to pass one or more modifiers to a RE class, you declare
// a RE_Options object, set the appropriate options, and pass this
// object to a RE constructor. Example:
//
// RE_options opt;
// opt.set_caseless(true);
//
// if (RE("HELLO", opt).PartialMatch("hello world")) ...
//
// RE_options has two constructors. The default constructor takes no
// arguments and creates a set of flags that are off by default.
//
// The optional parameter 'option_flags' is to facilitate transfer
// of legacy code from C programs. This lets you do
// RE(pattern, RE_Options(PCRE_CASELESS|PCRE_MULTILINE)).PartialMatch(str);
//
// But new code is better off doing
// RE(pattern,
// RE_Options().set_caseless(true).set_multiline(true)).PartialMatch(str);
// (See below)
//
// If you are going to pass one of the most used modifiers, there are some
// convenience functions that return a RE_Options class with the
// appropriate modifier already set:
// CASELESS(), UTF8(), MULTILINE(), DOTALL(), EXTENDED()
//
// If you need to set several options at once, and you don't want to go
// through the pains of declaring a RE_Options object and setting several
// options, there is a parallel method that give you such ability on the
// fly. You can concatenate several set_xxxxx member functions, since each
// of them returns a reference to its class object. e.g.: to pass
// PCRE_CASELESS, PCRE_EXTENDED, and PCRE_MULTILINE to a RE with one
// statement, you may write
//
// RE(" ^ xyz \\s+ .* blah$", RE_Options()
// .set_caseless(true)
// .set_extended(true)
// .set_multiline(true)).PartialMatch(sometext);
//
// -----------------------------------------------------------------------
// SCANNING TEXT INCREMENTALLY
//
// The "Consume" operation may be useful if you want to repeatedly
// match regular expressions at the front of a string and skip over
// them as they match. This requires use of the "StringPiece" type,
// which represents a sub-range of a real string. Like RE, StringPiece
// is defined in the pcrecpp namespace.
//
// Example: read lines of the form "var = value" from a string.
// string contents = ...; // Fill string somehow
// pcrecpp::StringPiece input(contents); // Wrap in a StringPiece
//
// string var;
// int value;
// pcrecpp::RE re("(\\w+) = (\\d+)\n");
// while (re.Consume(&input, &var, &value)) {
// ...;
// }
//
// Each successful call to "Consume" will set "var/value", and also
// advance "input" so it points past the matched text.
//
// The "FindAndConsume" operation is similar to "Consume" but does not
// anchor your match at the beginning of the string. For example, you
// could extract all words from a string by repeatedly calling
// pcrecpp::RE("(\\w+)").FindAndConsume(&input, &word)
//
// -----------------------------------------------------------------------
// PARSING HEX/OCTAL/C-RADIX NUMBERS
//
// By default, if you pass a pointer to a numeric value, the
// corresponding text is interpreted as a base-10 number. You can
// instead wrap the pointer with a call to one of the operators Hex(),
// Octal(), or CRadix() to interpret the text in another base. The
// CRadix operator interprets C-style "0" (base-8) and "0x" (base-16)
// prefixes, but defaults to base-10.
//
// Example:
// int a, b, c, d;
// pcrecpp::RE re("(.*) (.*) (.*) (.*)");
// re.FullMatch("100 40 0100 0x40",
// pcrecpp::Octal(&a), pcrecpp::Hex(&b),
// pcrecpp::CRadix(&c), pcrecpp::CRadix(&d));
// will leave 64 in a, b, c, and d.
//
// -----------------------------------------------------------------------
// REPLACING PARTS OF STRINGS
//
// You can replace the first match of "pattern" in "str" with
// "rewrite". Within "rewrite", backslash-escaped digits (\1 to \9)
// can be used to insert text matching corresponding parenthesized
// group from the pattern. \0 in "rewrite" refers to the entire
// matching text. E.g.,
//
// string s = "yabba dabba doo";
// pcrecpp::RE("b+").Replace("d", &s);
//
// will leave "s" containing "yada dabba doo". The result is true if
// the pattern matches and a replacement occurs, or false otherwise.
//
// GlobalReplace() is like Replace(), except that it replaces all
// occurrences of the pattern in the string with the rewrite.
// Replacements are not subject to re-matching. E.g.,
//
// string s = "yabba dabba doo";
// pcrecpp::RE("b+").GlobalReplace("d", &s);
//
// will leave "s" containing "yada dada doo". It returns the number
// of replacements made.
//
// Extract() is like Replace(), except that if the pattern matches,
// "rewrite" is copied into "out" (an additional argument) with
// substitutions. The non-matching portions of "text" are ignored.
// Returns true iff a match occurred and the extraction happened
// successfully. If no match occurs, the string is left unaffected.
#include <string>
#include <pcrecpparg.h> // defines the Arg class
// These aren't technically needed here, but we include them
// anyway so folks who include pcrecpp.h don't have to include
// all these other header files as well.
#include <pcre.h>
#include <pcre_stringpiece.h>
namespace pcrecpp {
#define PCRE_SET_OR_CLEAR(b, o) \
if (b) all_options_ |= (o); else all_options_ &= ~(o); \
return *this
#define PCRE_IS_SET(o) \
(all_options_ & o) == o
// We convert user-passed pointers into special Arg objects
extern Arg no_arg;
/***** Compiling regular expressions: the RE class *****/
// RE_Options allow you to set options to be passed along to pcre,
// along with other options we put on top of pcre.
// Only 9 modifiers, plus match_limit and match_limit_recursion,
// are supported now.
class RE_Options {
public:
// constructor
RE_Options() : match_limit_(0), match_limit_recursion_(0), all_options_(0) {}
// alternative constructor.
// To facilitate transfer of legacy code from C programs
//
// This lets you do
// RE(pattern, RE_Options(PCRE_CASELESS|PCRE_MULTILINE)).PartialMatch(str);
// But new code is better off doing
// RE(pattern,
// RE_Options().set_caseless(true).set_multiline(true)).PartialMatch(str);
RE_Options(int option_flags) : match_limit_(0), match_limit_recursion_(0),
all_options_(option_flags) {}
// we're fine with the default destructor, copy constructor, etc.
// accessors and mutators
int match_limit() const { return match_limit_; };
RE_Options &set_match_limit(int limit) {
match_limit_ = limit;
return *this;
}
int match_limit_recursion() const { return match_limit_recursion_; };
RE_Options &set_match_limit_recursion(int limit) {
match_limit_recursion_ = limit;
return *this;
}
bool caseless() const {
return PCRE_IS_SET(PCRE_CASELESS);
}
RE_Options &set_caseless(bool x) {
PCRE_SET_OR_CLEAR(x, PCRE_CASELESS);
}
bool multiline() const {
return PCRE_IS_SET(PCRE_MULTILINE);
}
RE_Options &set_multiline(bool x) {
PCRE_SET_OR_CLEAR(x, PCRE_MULTILINE);
}
bool dotall() const {
return PCRE_IS_SET(PCRE_DOTALL);
}
RE_Options &set_dotall(bool x) {
PCRE_SET_OR_CLEAR(x,PCRE_DOTALL);
}
bool extended() const {
return PCRE_IS_SET(PCRE_EXTENDED);
}
RE_Options &set_extended(bool x) {
PCRE_SET_OR_CLEAR(x,PCRE_EXTENDED);
}
bool dollar_endonly() const {
return PCRE_IS_SET(PCRE_DOLLAR_ENDONLY);
}
RE_Options &set_dollar_endonly(bool x) {
PCRE_SET_OR_CLEAR(x,PCRE_DOLLAR_ENDONLY);
}
bool extra() const {
return PCRE_IS_SET( PCRE_EXTRA);
}
RE_Options &set_extra(bool x) {
PCRE_SET_OR_CLEAR(x, PCRE_EXTRA);
}
bool ungreedy() const {
return PCRE_IS_SET(PCRE_UNGREEDY);
}
RE_Options &set_ungreedy(bool x) {
PCRE_SET_OR_CLEAR(x, PCRE_UNGREEDY);
}
bool utf8() const {
return PCRE_IS_SET(PCRE_UTF8);
}
RE_Options &set_utf8(bool x) {
PCRE_SET_OR_CLEAR(x, PCRE_UTF8);
}
bool no_auto_capture() const {
return PCRE_IS_SET(PCRE_NO_AUTO_CAPTURE);
}
RE_Options &set_no_auto_capture(bool x) {
PCRE_SET_OR_CLEAR(x, PCRE_NO_AUTO_CAPTURE);
}
RE_Options &set_all_options(int opt) {
all_options_ = opt;
return *this;
}
int all_options() const {
return all_options_ ;
}
// TODO: add other pcre flags
private:
int match_limit_;
int match_limit_recursion_;
int all_options_;
};
// These functions return some common RE_Options
static inline RE_Options UTF8() {
return RE_Options().set_utf8(true);
}
static inline RE_Options CASELESS() {
return RE_Options().set_caseless(true);
}
static inline RE_Options MULTILINE() {
return RE_Options().set_multiline(true);
}
static inline RE_Options DOTALL() {
return RE_Options().set_dotall(true);
}
static inline RE_Options EXTENDED() {
return RE_Options().set_extended(true);
}
// Interface for regular expression matching. Also corresponds to a
// pre-compiled regular expression. An "RE" object is safe for
// concurrent use by multiple threads.
class RE {
public:
// We provide implicit conversions from strings so that users can
// pass in a string or a "const char*" wherever an "RE" is expected.
RE(const char* pat) { Init(pat, NULL); }
RE(const char *pat, const RE_Options& option) { Init(pat, &option); }
RE(const string& pat) { Init(pat, NULL); }
RE(const string& pat, const RE_Options& option) { Init(pat, &option); }
// Copy constructor & assignment - note that these are expensive
// because they recompile the expression.
RE(const RE& re) { Init(re.pattern_, &re.options_); }
const RE& operator=(const RE& re) {
if (this != &re) {
Cleanup();
// This is the code that originally came from Google
// Init(re.pattern_.c_str(), &re.options_);
// This is the replacement from Ari Pollak
Init(re.pattern_, &re.options_);
}
return *this;
}
~RE();
// The string specification for this RE. E.g.
// RE re("ab*c?d+");
// re.pattern(); // "ab*c?d+"
const string& pattern() const { return pattern_; }
// If RE could not be created properly, returns an error string.
// Else returns the empty string.
const string& error() const { return *error_; }
/***** The useful part: the matching interface *****/
// This is provided so one can do pattern.ReplaceAll() just as
// easily as ReplaceAll(pattern-text, ....)
bool FullMatch(const StringPiece& text,
const Arg& ptr1 = no_arg,
const Arg& ptr2 = no_arg,
const Arg& ptr3 = no_arg,
const Arg& ptr4 = no_arg,
const Arg& ptr5 = no_arg,
const Arg& ptr6 = no_arg,
const Arg& ptr7 = no_arg,
const Arg& ptr8 = no_arg,
const Arg& ptr9 = no_arg,
const Arg& ptr10 = no_arg,
const Arg& ptr11 = no_arg,
const Arg& ptr12 = no_arg,
const Arg& ptr13 = no_arg,
const Arg& ptr14 = no_arg,
const Arg& ptr15 = no_arg,
const Arg& ptr16 = no_arg) const;
bool PartialMatch(const StringPiece& text,
const Arg& ptr1 = no_arg,
const Arg& ptr2 = no_arg,
const Arg& ptr3 = no_arg,
const Arg& ptr4 = no_arg,
const Arg& ptr5 = no_arg,
const Arg& ptr6 = no_arg,
const Arg& ptr7 = no_arg,
const Arg& ptr8 = no_arg,
const Arg& ptr9 = no_arg,
const Arg& ptr10 = no_arg,
const Arg& ptr11 = no_arg,
const Arg& ptr12 = no_arg,
const Arg& ptr13 = no_arg,
const Arg& ptr14 = no_arg,
const Arg& ptr15 = no_arg,
const Arg& ptr16 = no_arg) const;
bool Consume(StringPiece* input,
const Arg& ptr1 = no_arg,
const Arg& ptr2 = no_arg,
const Arg& ptr3 = no_arg,
const Arg& ptr4 = no_arg,
const Arg& ptr5 = no_arg,
const Arg& ptr6 = no_arg,
const Arg& ptr7 = no_arg,
const Arg& ptr8 = no_arg,
const Arg& ptr9 = no_arg,
const Arg& ptr10 = no_arg,
const Arg& ptr11 = no_arg,
const Arg& ptr12 = no_arg,
const Arg& ptr13 = no_arg,
const Arg& ptr14 = no_arg,
const Arg& ptr15 = no_arg,
const Arg& ptr16 = no_arg) const;
bool FindAndConsume(StringPiece* input,
const Arg& ptr1 = no_arg,
const Arg& ptr2 = no_arg,
const Arg& ptr3 = no_arg,
const Arg& ptr4 = no_arg,
const Arg& ptr5 = no_arg,
const Arg& ptr6 = no_arg,
const Arg& ptr7 = no_arg,
const Arg& ptr8 = no_arg,
const Arg& ptr9 = no_arg,
const Arg& ptr10 = no_arg,
const Arg& ptr11 = no_arg,
const Arg& ptr12 = no_arg,
const Arg& ptr13 = no_arg,
const Arg& ptr14 = no_arg,
const Arg& ptr15 = no_arg,
const Arg& ptr16 = no_arg) const;
bool Replace(const StringPiece& rewrite,
string *str) const;
int GlobalReplace(const StringPiece& rewrite,
string *str) const;
bool Extract(const StringPiece &rewrite,
const StringPiece &text,
string *out) const;
// Escapes all potentially meaningful regexp characters in
// 'unquoted'. The returned string, used as a regular expression,
// will exactly match the original string. For example,
// 1.5-2.0?
// may become:
// 1\.5\-2\.0\?
static string QuoteMeta(const StringPiece& unquoted);
/***** Generic matching interface *****/
// Type of match (TODO: Should be restructured as part of RE_Options)
enum Anchor {
UNANCHORED, // No anchoring
ANCHOR_START, // Anchor at start only
ANCHOR_BOTH // Anchor at start and end
};
// General matching routine. Stores the length of the match in
// "*consumed" if successful.
bool DoMatch(const StringPiece& text,
Anchor anchor,
int* consumed,
const Arg* const* args, int n) const;
// Return the number of capturing subpatterns, or -1 if the
// regexp wasn't valid on construction.
int NumberOfCapturingGroups() const;
private:
void Init(const string& pattern, const RE_Options* options);
void Cleanup();
// Match against "text", filling in "vec" (up to "vecsize" * 2/3) with
// pairs of integers for the beginning and end positions of matched
// text. The first pair corresponds to the entire matched text;
// subsequent pairs correspond, in order, to parentheses-captured
// matches. Returns the number of pairs (one more than the number of
// the last subpattern with a match) if matching was successful
// and zero if the match failed.
// I.e. for RE("(foo)|(bar)|(baz)") it will return 2, 3, and 4 when matching
// against "foo", "bar", and "baz" respectively.
// When matching RE("(foo)|hello") against "hello", it will return 1.
// But the values for all subpattern are filled in into "vec".
int TryMatch(const StringPiece& text,
int startpos,
Anchor anchor,
int *vec,
int vecsize) const;
// Append the "rewrite" string, with backslash subsitutions from "text"
// and "vec", to string "out".
bool Rewrite(string *out,
const StringPiece& rewrite,
const StringPiece& text,
int *vec,
int veclen) const;
// internal implementation for DoMatch
bool DoMatchImpl(const StringPiece& text,
Anchor anchor,
int* consumed,
const Arg* const args[],
int n,
int* vec,
int vecsize) const;
// Compile the regexp for the specified anchoring mode
pcre* Compile(Anchor anchor);
string pattern_;
RE_Options options_;
pcre* re_full_; // For full matches
pcre* re_partial_; // For partial matches
const string* error_; // Error indicator (or points to empty string)
};
} // namespace pcrecpp
#endif /* _PCRECPP_H */

1227
ext/pcre/pcrelib/pcrecpp_unittest.cc
View File

File diff suppressed because it is too large Load Diff

171
ext/pcre/pcrelib/pcrecpparg.h
View File

@ -1,171 +0,0 @@
// Copyright (c) 2005, Google Inc.
// All rights reserved.
//
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions are
// met:
//
// * Redistributions of source code must retain the above copyright
// notice, this list of conditions and the following disclaimer.
// * Redistributions in binary form must reproduce the above
// copyright notice, this list of conditions and the following disclaimer
// in the documentation and/or other materials provided with the
// distribution.
// * Neither the name of Google Inc. nor the names of its
// contributors may be used to endorse or promote products derived from
// this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
//
// Author: Sanjay Ghemawat
#ifndef _PCRECPPARG_H
#define _PCRECPPARG_H
#include <stdlib.h> // for NULL
#include <string>
namespace pcrecpp {
class StringPiece;
// Hex/Octal/Binary?
// Special class for parsing into objects that define a ParseFrom() method
template <class T>
class _RE_MatchObject {
public:
static inline bool Parse(const char* str, int n, void* dest) {
T* object = reinterpret_cast<T*>(dest);
return object->ParseFrom(str, n);
}
};
class Arg {
public:
// Empty constructor so we can declare arrays of Arg
Arg();
// Constructor specially designed for NULL arguments
Arg(void*);
typedef bool (*Parser)(const char* str, int n, void* dest);
// Type-specific parsers
#define PCRE_MAKE_PARSER(type,name) \
Arg(type* p) : arg_(p), parser_(name) { } \
Arg(type* p, Parser parser) : arg_(p), parser_(parser) { }
PCRE_MAKE_PARSER(char, parse_char);
PCRE_MAKE_PARSER(unsigned char, parse_uchar);
PCRE_MAKE_PARSER(short, parse_short);
PCRE_MAKE_PARSER(unsigned short, parse_ushort);
PCRE_MAKE_PARSER(int, parse_int);
PCRE_MAKE_PARSER(unsigned int, parse_uint);
PCRE_MAKE_PARSER(long, parse_long);
PCRE_MAKE_PARSER(unsigned long, parse_ulong);
#if 1
PCRE_MAKE_PARSER(long long, parse_longlong);
#endif
#if 1
PCRE_MAKE_PARSER(unsigned long long, parse_ulonglong);
#endif
PCRE_MAKE_PARSER(float, parse_float);
PCRE_MAKE_PARSER(double, parse_double);
PCRE_MAKE_PARSER(std::string, parse_string);
PCRE_MAKE_PARSER(StringPiece, parse_stringpiece);
#undef PCRE_MAKE_PARSER
// Generic constructor
template <class T> Arg(T*, Parser parser);
// Generic constructor template
template <class T> Arg(T* p)
: arg_(p), parser_(_RE_MatchObject<T>::Parse) {
}
// Parse the data
bool Parse(const char* str, int n) const;
private:
void* arg_;
Parser parser_;
static bool parse_null (const char* str, int n, void* dest);
static bool parse_char (const char* str, int n, void* dest);
static bool parse_uchar (const char* str, int n, void* dest);
static bool parse_float (const char* str, int n, void* dest);
static bool parse_double (const char* str, int n, void* dest);
static bool parse_string (const char* str, int n, void* dest);
static bool parse_stringpiece (const char* str, int n, void* dest);
#define PCRE_DECLARE_INTEGER_PARSER(name) \
private: \
static bool parse_ ## name(const char* str, int n, void* dest); \
static bool parse_ ## name ## _radix( \
const char* str, int n, void* dest, int radix); \
public: \
static bool parse_ ## name ## _hex(const char* str, int n, void* dest); \
static bool parse_ ## name ## _octal(const char* str, int n, void* dest); \
static bool parse_ ## name ## _cradix(const char* str, int n, void* dest)
PCRE_DECLARE_INTEGER_PARSER(short);
PCRE_DECLARE_INTEGER_PARSER(ushort);
PCRE_DECLARE_INTEGER_PARSER(int);
PCRE_DECLARE_INTEGER_PARSER(uint);
PCRE_DECLARE_INTEGER_PARSER(long);
PCRE_DECLARE_INTEGER_PARSER(ulong);
PCRE_DECLARE_INTEGER_PARSER(longlong);
PCRE_DECLARE_INTEGER_PARSER(ulonglong);
#undef PCRE_DECLARE_INTEGER_PARSER
};
inline Arg::Arg() : arg_(NULL), parser_(parse_null) { }
inline Arg::Arg(void* p) : arg_(p), parser_(parse_null) { }
inline bool Arg::Parse(const char* str, int n) const {
return (*parser_)(str, n, arg_);
}
// This part of the parser, appropriate only for ints, deals with bases
#define MAKE_INTEGER_PARSER(type, name) \
inline Arg Hex(type* ptr) { \
return Arg(ptr, Arg::parse_ ## name ## _hex); } \
inline Arg Octal(type* ptr) { \
return Arg(ptr, Arg::parse_ ## name ## _octal); } \
inline Arg CRadix(type* ptr) { \
return Arg(ptr, Arg::parse_ ## name ## _cradix); }
MAKE_INTEGER_PARSER(short, short);
MAKE_INTEGER_PARSER(unsigned short, ushort);
MAKE_INTEGER_PARSER(int, int);
MAKE_INTEGER_PARSER(unsigned int, uint);
MAKE_INTEGER_PARSER(long, long);
MAKE_INTEGER_PARSER(unsigned long, ulong);
#if 1
MAKE_INTEGER_PARSER(long long, longlong);
#endif
#if 1
MAKE_INTEGER_PARSER(unsigned long long, ulonglong);
#endif
#undef PCRE_IS_SET
#undef PCRE_SET_OR_CLEAR
#undef MAKE_INTEGER_PARSER
} // namespace pcrecpp
#endif /* _PCRECPPARG_H */

4
ext/pcre/pcrelib/pcredemo.c
View File

@ -16,6 +16,10 @@ systems (e.g. Solaris) use the -R option.
*/
#ifdef HAVE_CONFIG_H
# include <config.h>
#endif
#include <stdio.h>
#include <string.h>
#include <pcre.h>

163
ext/pcre/pcrelib/pcregrep.c
View File

@ -6,7 +6,7 @@
its pattern matching. On a Unix or Win32 system it can recurse into
directories.
Copyright (c) 1997-2006 University of Cambridge
Copyright (c) 1997-2007 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -37,6 +37,10 @@ POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
#ifdef HAVE_CONFIG_H
# include <config.h>
#endif
#include <ctype.h>
#include <locale.h>
#include <stdio.h>
@ -46,17 +50,17 @@ POSSIBILITY OF SUCH DAMAGE.
#include <sys/types.h>
#include <sys/stat.h>
#include <unistd.h>
#ifdef HAVE_UNISTD_H
# include <unistd.h>
#endif
#include "config.h"
#include "pcre.h"
#include <pcre.h>
#define FALSE 0
#define TRUE 1
typedef int BOOL;
#define VERSION "4.4 29-Nov-2006"
#define MAX_PATTERN_COUNT 100
#if BUFSIZ > 8192
@ -84,7 +88,7 @@ enum { DEE_READ, DEE_SKIP };
/* Line ending types */
enum { EL_LF, EL_CR, EL_CRLF, EL_ANY };
enum { EL_LF, EL_CR, EL_CRLF, EL_ANY, EL_ANYCRLF };
@ -117,8 +121,8 @@ static char *locale = NULL;
static const unsigned char *pcretables = NULL;
static int pattern_count = 0;
static pcre **pattern_list;
static pcre_extra **hints_list;
static pcre **pattern_list = NULL;
static pcre_extra **hints_list = NULL;
static char *include_pattern = NULL;
static char *exclude_pattern = NULL;
@ -192,7 +196,7 @@ static option_item optionlist[] = {
{ OP_STRING, N_LABEL, &stdin_name, "label=name", "set name for standard input" },
{ OP_STRING, N_LOCALE, &locale, "locale=locale", "use the named locale" },
{ OP_NODATA, 'M', NULL, "multiline", "run in multiline mode" },
{ OP_STRING, 'N', &newline, "newline=type", "specify newline type (CR, LR, CRLF)" },
{ OP_STRING, 'N', &newline, "newline=type", "specify newline type (CR, LF, CRLF, ANYCRLF or ANY)" },
{ OP_NODATA, 'n', NULL, "line-number", "print line number with output lines" },
{ OP_NODATA, 'o', NULL, "only-matching", "show only the part of the line that matched" },
{ OP_NODATA, 'q', NULL, "quiet", "suppress output, just set return code" },
@ -222,7 +226,7 @@ static const char *prefix[] = {
static const char *suffix[] = {
"", "\\b", ")$", ")$", "\\E", "\\E\\b", "\\E)$", "\\E)$" };
/* UTF-8 tables - used only when the newline setting is "all". */
/* UTF-8 tables - used only when the newline setting is "any". */
const int utf8_table3[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01};
@ -244,7 +248,7 @@ although at present the only ones are for Unix, Win32, and for "no support". */
/************* Directory scanning in Unix ***********/
#if IS_UNIX
#if defined HAVE_SYS_STAT_H && defined HAVE_DIRENT_H && defined HAVE_SYS_TYPES_H
#include <sys/types.h>
#include <sys/stat.h>
#include <dirent.h>
@ -276,7 +280,7 @@ for (;;)
if (strcmp(dent->d_name, ".") != 0 && strcmp(dent->d_name, "..") != 0)
return dent->d_name;
}
return NULL; /* Keep compiler happy; never executed */
/* Control never reaches here */
}
static void
@ -314,7 +318,7 @@ Lionel Fourquaux. David Burgess added a patch to define INVALID_FILE_ATTRIBUTES
when it did not exist. */
#elif HAVE_WIN32API
#elif HAVE_WINDOWS_H
#ifndef STRICT
# define STRICT
@ -436,8 +440,8 @@ FALSE;
typedef void directory_type;
int isdirectory(char *filename) { return 0; }
directory_type * opendirectory(char *filename) {}
char *readdirectory(directory_type *dir) {}
directory_type * opendirectory(char *filename) { return (directory_type*)0;}
char *readdirectory(directory_type *dir) { return (char*)0;}
void closedirectory(directory_type *dir) {}
@ -461,7 +465,7 @@ return FALSE;
#if ! HAVE_STRERROR
#ifndef HAVE_STRERROR
/*************************************************
* Provide strerror() for non-ANSI libraries *
*************************************************/
@ -541,6 +545,50 @@ switch(endlinetype)
}
break;
case EL_ANYCRLF:
while (p < endptr)
{
int extra = 0;
register int c = *((unsigned char *)p);
if (utf8 && c >= 0xc0)
{
int gcii, gcss;
extra = utf8_table4[c & 0x3f]; /* Number of additional bytes */
gcss = 6*extra;
c = (c & utf8_table3[extra]) << gcss;
for (gcii = 1; gcii <= extra; gcii++)
{
gcss -= 6;
c |= (p[gcii] & 0x3f) << gcss;
}
}
p += 1 + extra;
switch (c)
{
case 0x0a: /* LF */
*lenptr = 1;
return p;
case 0x0d: /* CR */
if (p < endptr && *p == 0x0a)
{
*lenptr = 2;
p++;
}
else *lenptr = 1;
return p;
default:
break;
}
} /* End of loop for ANYCRLF case */
*lenptr = 0; /* Must have hit the end */
return endptr;
case EL_ANY:
while (p < endptr)
{
@ -639,6 +687,7 @@ switch(endlinetype)
return p; /* But control should never get here */
case EL_ANY:
case EL_ANYCRLF:
if (*(--p) == '\n' && p > startptr && p[-1] == '\r') p--;
if (utf8) while ((*p & 0xc0) == 0x80) p--;
@ -667,7 +716,17 @@ switch(endlinetype)
}
else c = *((unsigned char *)pp);
switch (c)
if (endlinetype == EL_ANYCRLF) switch (c)
{
case 0x0a: /* LF */
case 0x0d: /* CR */
return p;
default:
break;
}
else switch (c)
{
case 0x0a: /* LF */
case 0x0b: /* VT */
@ -1188,7 +1247,8 @@ if ((sep = isdirectory(pathname)) != 0)
while ((nextfile = readdirectory(dir)) != NULL)
{
int frc, blen;
blen = slprintf(buffer, sizeof(buffer), "%.512s%c%.128s", pathname, sep, nextfile);
sprintf(buffer, "%.512s%c%.128s", pathname, sep, nextfile);
blen = strlen(buffer);
if (exclude_compiled != NULL &&
pcre_exec(exclude_compiled, NULL, buffer, blen, 0, 0, NULL, 0) >= 0)
@ -1280,7 +1340,7 @@ for (op = optionlist; op->one_char != 0; op++)
{
int n;
char s[4];
if (op->one_char > 0) snprintf(s, sizeof(s), "-%c,", op->one_char); else strcpy(s, " ");
if (op->one_char > 0) sprintf(s, "-%c,", op->one_char); else strcpy(s, " ");
printf(" %s --%s%n", s, op->long_name, &n);
n = 30 - n;
if (n < 1) n = 1;
@ -1327,8 +1387,7 @@ switch(letter)
case 'x': process_options |= PO_LINE_MATCH; break;
case 'V':
fprintf(stderr, "pcregrep version %s using ", VERSION);
fprintf(stderr, "PCRE version %s\n", pcre_version());
fprintf(stderr, "pcregrep version %s\n", pcre_version());
exit(0);
break;
@ -1354,7 +1413,7 @@ ordin(int n)
{
static char buffer[8];
char *p = buffer;
snprintf(p, sizeof(buffer), "%d", n);
sprintf(p, "%d", n);
while (*p != 0) p++;
switch (n%10)
{
@ -1400,11 +1459,15 @@ if (pattern_count >= MAX_PATTERN_COUNT)
return FALSE;
}
snprintf(buffer, sizeof(buffer), "%s%.*s%s", prefix[process_options], MBUFTHIRD, pattern,
sprintf(buffer, "%s%.*s%s", prefix[process_options], MBUFTHIRD, pattern,
suffix[process_options]);
pattern_list[pattern_count] =
pcre_compile(buffer, options, &error, &errptr, pcretables);
if (pattern_list[pattern_count++] != NULL) return TRUE;
if (pattern_list[pattern_count] != NULL)
{
pattern_count++;
return TRUE;
}
/* Handle compile errors */
@ -1462,7 +1525,7 @@ if ((process_options & PO_FIXED_STRINGS) != 0)
char *p = end_of_line(pattern, eop, &ellength);
if (ellength == 0)
return compile_single_pattern(pattern, options, filename, count);
snprintf(buffer, sizeof(buffer), "%.*s", p - pattern - ellength, pattern);
sprintf(buffer, "%.*s", (int)(p - pattern - ellength), pattern);
pattern = p;
if (!compile_single_pattern(buffer, options, filename, count))
return FALSE;
@ -1486,6 +1549,7 @@ int i, j;
int rc = 1;
int pcre_options = 0;
int cmd_pattern_count = 0;
int hint_count = 0;
int errptr;
BOOL only_one_at_top;
char *patterns[MAX_PATTERN_COUNT];
@ -1503,6 +1567,7 @@ switch(i)
case '\r': newline = (char *)"cr"; break;
case ('\r' << 8) | '\n': newline = (char *)"crlf"; break;
case -1: newline = (char *)"any"; break;
case -2: newline = (char *)"anycrlf"; break;
}
/* Process the options */
@ -1578,9 +1643,9 @@ for (i = 1; i < argc; i++)
char buff1[24];
char buff2[24];
int baselen = opbra - op->long_name;
snprintf(buff1, sizeof(buff1), "%.*s", baselen, op->long_name);
snprintf(buff2, sizeof(buff2), "%s%.*s", buff1, strlen(op->long_name) - baselen - 2,
opbra + 1);
sprintf(buff1, "%.*s", baselen, op->long_name);
sprintf(buff2, "%s%.*s", buff1,
(int)strlen(op->long_name) - baselen - 2, opbra + 1);
if (strcmp(arg, buff1) == 0 || strcmp(arg, buff2) == 0)
break;
}
@ -1810,6 +1875,11 @@ else if (strcmp(newline, "any") == 0 || strcmp(newline, "ANY") == 0)
pcre_options |= PCRE_NEWLINE_ANY;
endlinetype = EL_ANY;
}
else if (strcmp(newline, "anycrlf") == 0 || strcmp(newline, "ANYCRLF") == 0)
{
pcre_options |= PCRE_NEWLINE_ANYCRLF;
endlinetype = EL_ANYCRLF;
}
else
{
fprintf(stderr, "pcregrep: Invalid newline specifier \"%s\"\n", newline);
@ -1864,7 +1934,7 @@ hints_list = (pcre_extra **)malloc(MAX_PATTERN_COUNT * sizeof(pcre_extra *));
if (pattern_list == NULL || hints_list == NULL)
{
fprintf(stderr, "pcregrep: malloc failed\n");
return 2;
goto EXIT2;
}
/* If no patterns were provided by -e, and there is no file provided by -f,
@ -1883,7 +1953,7 @@ for (j = 0; j < cmd_pattern_count; j++)
{
if (!compile_pattern(patterns[j], pcre_options, NULL,
(j == 0 && cmd_pattern_count == 1)? 0 : j + 1))
return 2;
goto EXIT2;
}
/* Compile the regular expressions that are provided in a file. */
@ -1907,7 +1977,7 @@ if (pattern_filename != NULL)
{
fprintf(stderr, "pcregrep: Failed to open %s: %s\n", pattern_filename,
strerror(errno));
return 2;
goto EXIT2;
}
filename = pattern_filename;
}
@ -1920,7 +1990,7 @@ if (pattern_filename != NULL)
linenumber++;
if (buffer[0] == 0) continue; /* Skip blank lines */
if (!compile_pattern(buffer, pcre_options, filename, linenumber))
return 2;
goto EXIT2;
}
if (f != stdin) fclose(f);
@ -1934,10 +2004,11 @@ for (j = 0; j < pattern_count; j++)
if (error != NULL)
{
char s[16];
if (pattern_count == 1) s[0] = 0; else snprintf(s, sizeof(s), " number %d", j);
if (pattern_count == 1) s[0] = 0; else sprintf(s, " number %d", j);
fprintf(stderr, "pcregrep: Error while studying regex%s: %s\n", s, error);
return 2;
goto EXIT2;
}
hint_count++;
}
/* If there are include or exclude patterns, compile them. */
@ -1950,7 +2021,7 @@ if (exclude_pattern != NULL)
{
fprintf(stderr, "pcregrep: Error in 'exclude' regex at offset %d: %s\n",
errptr, error);
return 2;
goto EXIT2;
}
}
@ -1962,14 +2033,17 @@ if (include_pattern != NULL)
{
fprintf(stderr, "pcregrep: Error in 'include' regex at offset %d: %s\n",
errptr, error);
return 2;
goto EXIT2;
}
}
/* If there are no further arguments, do the business on stdin and exit. */
if (i >= argc)
return pcregrep(stdin, (filenames > FN_DEFAULT)? stdin_name : NULL);
{
rc = pcregrep(stdin, (filenames > FN_DEFAULT)? stdin_name : NULL);
goto EXIT;
}
/* Otherwise, work through the remaining arguments as files or directories.
Pass in the fact that there is only one argument at top level - this suppresses
@ -1986,7 +2060,22 @@ for (; i < argc; i++)
else if (frc == 0 && rc == 1) rc = 0;
}
EXIT:
if (pattern_list != NULL)
{
for (i = 0; i < pattern_count; i++) free(pattern_list[i]);
free(pattern_list);
}
if (hints_list != NULL)
{
for (i = 0; i < hint_count; i++) free(hints_list[i]);
free(hints_list);
}
return rc;
EXIT2:
rc = 2;
goto EXIT;
}
/* End of pcregrep */

17
ext/pcre/pcrelib/pcreposix.c
View File

@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2006 University of Cambridge
Copyright (c) 1997-2007 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -80,7 +80,7 @@ static const int eint[] = {
REG_BADPAT, /* malformed number or name after (?( */
REG_BADPAT, /* conditional group contains more than two branches */
REG_BADPAT, /* assertion expected after (?( */
REG_BADPAT, /* (?R or (?digits must be followed by ) */
REG_BADPAT, /* (?R or (?[+-]digits must be followed by ) */
REG_ECTYPE, /* unknown POSIX class name */
REG_BADPAT, /* POSIX collating elements are not supported */
REG_INVARG, /* this version of PCRE is not compiled with PCRE_UTF8 support */
@ -108,7 +108,8 @@ static const int eint[] = {
REG_BADPAT, /* DEFINE group contains more than one branch */
REG_BADPAT, /* repeating a DEFINE group is not allowed */
REG_INVARG, /* inconsistent NEWLINE options */
REG_BADPAT /* \g is not followed followed by an (optionally braced) non-zero number */
REG_BADPAT, /* \g is not followed followed by an (optionally braced) non-zero number */
REG_BADPAT /* (?+ or (?- must be followed by a non-zero number */
};
/* Table of texts corresponding to POSIX error codes */
@ -141,7 +142,7 @@ static const char *const pstring[] = {
* Translate error code to string *
*************************************************/
PCRE_DATA_SCOPE size_t
PCREPOSIX_EXP_DEFN size_t
regerror(int errcode, const regex_t *preg, char *errbuf, size_t errbuf_size)
{
const char *message, *addmessage;
@ -158,7 +159,7 @@ addlength = (preg != NULL && (int)preg->re_erroffset != -1)?
if (errbuf_size > 0)
{
if (addlength > 0 && errbuf_size >= length + addlength)
snprintf(errbuf, errbuf_size, "%s%s%-6d", message, addmessage, (int)preg->re_erroffset);
sprintf(errbuf, "%s%s%-6d", message, addmessage, (int)preg->re_erroffset);
else
{
strncpy(errbuf, message, errbuf_size - 1);
@ -176,7 +177,7 @@ return length + addlength;
* Free store held by a regex *
*************************************************/
PCRE_DATA_SCOPE void
PCREPOSIX_EXP_DEFN void
regfree(regex_t *preg)
{
(pcre_free)(preg->re_pcre);
@ -199,7 +200,7 @@ Returns: 0 on success
various non-zero codes on failure
*/
PCRE_DATA_SCOPE int
PCREPOSIX_EXP_DEFN int
regcomp(regex_t *preg, const char *pattern, int cflags)
{
const char *errorptr;
@ -241,7 +242,7 @@ If REG_NOSUB was specified at compile time, the PCRE_NO_AUTO_CAPTURE flag will
be set. When this is the case, the nmatch and pmatch arguments are ignored, and
the only result is yes/no/error. */
PCRE_DATA_SCOPE int
PCREPOSIX_EXP_DEFN int
regexec(const regex_t *preg, const char *string, size_t nmatch,
regmatch_t pmatch[], int eflags)
{

40
ext/pcre/pcrelib/pcreposix.h
View File

@ -9,7 +9,7 @@
Compatible Regular Expression library. It defines the things POSIX says should
be there. I hope.
Copyright (c) 1997-2006 University of Cambridge
Copyright (c) 1997-2007 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -105,40 +105,36 @@ typedef struct {
regoff_t rm_eo;
} regmatch_t;
/* Win32 uses DLL by default; it needs special stuff for exported functions
when building PCRE. */
/* When an application links to a PCRE DLL in Windows, the symbols that are
imported have to be identified as such. When building PCRE, the appropriate
export settings are needed. */
#ifndef PCRE_DATA_SCOPE
#ifdef _WIN32
# ifdef PCRE_DEFINITION
# ifdef DLL_EXPORT
# define PCRE_DATA_SCOPE __declspec(dllexport)
# endif
# else
# ifndef PCRE_STATIC
# define PCRE_DATA_SCOPE extern __declspec(dllimport)
# endif
# ifndef PCREPOSIX_STATIC
# define PCREPOSIX_EXP_DECL extern __declspec(dllimport)
# define PCREPOSIX_EXP_DEFN __declspec(dllimport)
# endif
#endif
#endif
/* Otherwise, we use the standard "extern". */
/* By default, we use the standard "extern" declarations. */
#ifndef PCRE_DATA_SCOPE
#ifndef PCREPOSIX_EXP_DECL
# ifdef __cplusplus
# define PCRE_DATA_SCOPE extern "C"
# define PCREPOSIX_EXP_DECL extern "C"
# define PCREPOSIX_EXP_DEFN extern "C"
# else
# define PCRE_DATA_SCOPE extern
# define PCREPOSIX_EXP_DECL extern
# define PCREPOSIX_EXP_DEFN extern
# endif
#endif
/* The functions */
PCRE_DATA_SCOPE int regcomp(regex_t *, const char *, int);
PCRE_DATA_SCOPE int regexec(const regex_t *, const char *, size_t,
regmatch_t *, int);
PCRE_DATA_SCOPE size_t regerror(int, const regex_t *, char *, size_t);
PCRE_DATA_SCOPE void regfree(regex_t *);
PCREPOSIX_EXP_DECL int regcomp(regex_t *, const char *, int);
PCREPOSIX_EXP_DECL int regexec(const regex_t *, const char *, size_t,
regmatch_t *, int);
PCREPOSIX_EXP_DECL size_t regerror(int, const regex_t *, char *, size_t);
PCREPOSIX_EXP_DECL void regfree(regex_t *);
#ifdef __cplusplus
} /* extern "C" */

2305
ext/pcre/pcrelib/pcretest.c
View File

File diff suppressed because it is too large Load Diff

7
ext/pcre/pcrelib/testdata/grepinputx vendored
View File

@ -39,11 +39,4 @@ eighteen
nineteen
twenty
Here follows some CR/LF/CRLF test data.
abc
def
ghi
jkl
This is the last line of this file.

56
ext/pcre/pcrelib/testdata/grepoutput vendored
View File

@ -75,14 +75,7 @@ RC=1
39:nineteen
40:twenty
41:
42:Here follows some CR/LF/CRLF test data.
43:
44:abc
def
45:ghi
46:jkl
47:
48:This is the last line of this file.
42:This is the last line of this file.
---------------------------- Test 12 -----------------------------
Pattern
---------------------------- Test 13 -----------------------------
@ -164,8 +157,7 @@ eighteen
nineteen
twenty
Here follows some CR/LF/CRLF test data.
This is the last line of this file.
---------------------------- Test 25 -----------------------------
15-
16-complete pair
@ -215,8 +207,7 @@ eighteen
nineteen
twenty
Here follows some CR/LF/CRLF test data.
This is the last line of this file.
---------------------------- Test 27 -----------------------------
four
five
@ -236,10 +227,7 @@ eighteen
nineteen
twenty
Here follows some CR/LF/CRLF test data.
abc
def
This is the last line of this file.
---------------------------- Test 28 -----------------------------
14-of lines all by themselves.
15-
@ -291,12 +279,7 @@ eighteen
nineteen
twenty
Here follows some CR/LF/CRLF test data.
abc
def
ghi
jkl
This is the last line of this file.
---------------------------- Test 30 -----------------------------
./testdata/grepinput-4-features should be added at the end, because some of the tests involve the
./testdata/grepinput-5-output of line numbers, and we don't want these to change.
@ -345,8 +328,8 @@ RC=2
./testdata/grepinputx
RC=0
---------------------------- Test 36 -----------------------------
./testdata/grepinputx
./testdata/grepinput8
./testdata/grepinputx
RC=0
---------------------------- Test 37 -----------------------------
aaaaa0
@ -400,30 +383,3 @@ AB.VE
AB.VE the turtle
PUT NEW DATA ABOVE THIS LINE.
---------------------------- Test 49 ------------------------------
abc
def
ghi
jkl
---------------------------- Test 50 ------------------------------
def
---------------------------- Test 51 ------------------------------
ghi
jkl
This is the last line of this file.
---------------------------- Test 52 ------------------------------
def
ghi
jkl
This is the last line of this file.
---------------------------- Test 53 ------------------------------
ghi
jkl
This is the last line of this file.
---------------------------- Test 54 ------------------------------
44:abc
45:def
46:ghi
47:jkl

22
ext/pcre/pcrelib/testdata/grepoutputN vendored Normal file
View File

@ -0,0 +1,22 @@
---------------------------- Test N1 ------------------------------
1:abc
2:def
---------------------------- Test N2 ------------------------------
1:abc
def
2:ghi
jkl---------------------------- Test N3 ------------------------------
2:def
3:
ghi
jkl---------------------------- Test N4 ------------------------------
2:ghi
jkl---------------------------- Test N5 ------------------------------
1:abc
2:def
3:ghi
4:jkl---------------------------- Test N6 ------------------------------
1:abc
2:def
3:ghi
4:jkl

7
ext/pcre/pcrelib/testdata/testinput1 vendored
View File

@ -1494,8 +1494,8 @@
/(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)\12\123/
abcdefghijk\12S
/ab\hdef/
abhdef
/ab\idef/
abidef
/a{0}bc/
bc
@ -4018,4 +4018,7 @@
abc
abc\n
/(.*(.)?)*/
abcd
/ End of testinput1 /

104
ext/pcre/pcrelib/testdata/testinput10 vendored Normal file
View File

@ -0,0 +1,104 @@
/-- These are a few representative patterns whose lengths and offsets are to be
shown when the link size is 2. This is just a doublecheck test to ensure the
sizes don't go horribly wrong when something is changed. The pattern contents
are all themselves checked in other tests. --/
/((?i)b)/BM
/(?s)(.*X|^B)/BM
/(?s:.*X|^B)/BM
/^[[:alnum:]]/BM
/#/IxMD
/a#/IxMD
/x?+/BM
/x++/BM
/x{1,3}+/BM
/(x)*+/BM
/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/BM
|8J\$WE\<\.rX\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|BM
|\$\<\.X\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|BM
/(a(?1)b)/BM
/(a(?1)+b)/BM
/a(?P<name1>b|c)d(?P<longername2>e)/BM
/(?:a(?P<c>c(?P<d>d)))(?P<a>a)/BM
/(?P<a>a)...(?P=a)bbb(?P>a)d/BM
/abc(?C255)de(?C)f/BM
/abcde/CBM
/\x{100}/8BM
/\x{1000}/8BM
/\x{10000}/8BM
/\x{100000}/8BM
/\x{1000000}/8BM
/\x{4000000}/8BM
/\x{7fffFFFF}/8BM
/[\x{ff}]/8BM
/[\x{100}]/8BM
/\x80/8BM
/\xff/8BM
/\x{0041}\x{2262}\x{0391}\x{002e}/D8M
/\x{D55c}\x{ad6d}\x{C5B4}/D8M
/\x{65e5}\x{672c}\x{8a9e}/D8M
/[\x{100}]/8BM
/[Z\x{100}]/8BM
/^[\x{100}\E-\Q\E\x{150}]/B8M
/^[\QĀ\E-\QŐ\E]/B8M
/^[\QĀ\E-\QŐ\E/B8M
/[\p{L}]/BM
/[\p{^L}]/BM
/[\P{L}]/BM
/[\P{^L}]/BM
/[abc\p{L}\x{0660}]/8BM
/[\p{Nd}]/8BM
/[\p{Nd}+-]+/8BM
/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8iBM
/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8BM
/[\x{105}-\x{109}]/8iBM
/ End of testinput10 /

1146
ext/pcre/pcrelib/testdata/testinput2 vendored
View File

File diff suppressed because it is too large Load Diff

2
ext/pcre/pcrelib/testdata/testinput3 vendored
View File

@ -86,6 +86,6 @@
>>>\xaa<<<
>>>\xba<<<
/[[:alpha:]][[:lower:]][[:upper:]]/DLfr_FR
/[[:alpha:]][[:lower:]][[:upper:]]/DZLfr_FR
/ End of testinput3 /

186
ext/pcre/pcrelib/testdata/testinput5 vendored
View File

@ -1,20 +1,20 @@
/\x{100}/8DM
/\x{100}/8DZ
/\x{1000}/8DM
/\x{1000}/8DZ
/\x{10000}/8DM
/\x{10000}/8DZ
/\x{100000}/8DM
/\x{100000}/8DZ
/\x{1000000}/8DM
/\x{1000000}/8DZ
/\x{4000000}/8DM
/\x{4000000}/8DZ
/\x{7fffFFFF}/8DM
/\x{7fffFFFF}/8DZ
/[\x{ff}]/8DM
/[\x{ff}]/8DZ
/[\x{100}]/8DM
/[\x{100}]/8DZ
/\x{ffffffff}/8
@ -23,39 +23,39 @@
/^\x{100}a\x{1234}/8
\x{100}a\x{1234}bcd
/\x80/8D
/\x80/8DZ
/\xff/8D
/\xff/8DZ
/\x{0041}\x{2262}\x{0391}\x{002e}/D8
/\x{0041}\x{2262}\x{0391}\x{002e}/DZ8
\x{0041}\x{2262}\x{0391}\x{002e}
/\x{D55c}\x{ad6d}\x{C5B4}/D8
/\x{D55c}\x{ad6d}\x{C5B4}/DZ8
\x{D55c}\x{ad6d}\x{C5B4}
/\x{65e5}\x{672c}\x{8a9e}/D8
/\x{65e5}\x{672c}\x{8a9e}/DZ8
\x{65e5}\x{672c}\x{8a9e}
/\x{80}/D8
/\x{80}/DZ8
/\x{084}/D8
/\x{084}/DZ8
/\x{104}/D8
/\x{104}/DZ8
/\x{861}/D8
/\x{861}/DZ8
/\x{212ab}/D8
/\x{212ab}/DZ8
/.{3,5}X/D8
/.{3,5}X/DZ8
\x{212ab}\x{212ab}\x{212ab}\x{861}X
/.{3,5}?/D8
/.{3,5}?/DZ8
\x{212ab}\x{212ab}\x{212ab}\x{861}
/-- These tests are here rather than in testinput4 because Perl 5.6 has --/
/-- some problems with UTF-8 support, in the area of \x{..} where the --/
/-- value is < 255. It grumbles about invalid UTF-8 strings. --/
/-- These tests are here rather than in testinput4 because Perl 5.6 has some
problems with UTF-8 support, in the area of \x{..} where the value is < 255.
It grumbles about invalid UTF-8 strings. --/
/^[a\x{c0}]b/8
\x{c0}b
@ -80,29 +80,29 @@
/(?<=\C)X/8
Should produce an error diagnostic
/-- This one is here not because it's different to Perl, but because the --/
/-- way the captured single-byte is displayed. (In Perl it becomes a --/
/-- character, and you can't tell the difference.) --/
/-- This one is here not because it's different to Perl, but because the way
the captured single-byte is displayed. (In Perl it becomes a character, and you
can't tell the difference.) --/
/X(\C)(.*)/8
X\x{1234}
X\nabc
/^[ab]/8D
/^[ab]/8DZ
bar
*** Failers
c
\x{ff}
\x{100}
/^[^ab]/8D
/^[^ab]/8DZ
c
\x{ff}
\x{100}
*** Failers
aaa
/[^ab\xC0-\xF0]/8SD
/[^ab\xC0-\xF0]/8SDZ
\x{f1}
\x{bf}
\x{100}
@ -111,16 +111,16 @@
\x{c0}
\x{f0}
/Ä€{3,4}/8SD
/Ä€{3,4}/8SDZ
\x{100}\x{100}\x{100}\x{100\x{100}
/(\x{100}+|x)/8SD
/(\x{100}+|x)/8SDZ
/(\x{100}*a|x)/8SD
/(\x{100}*a|x)/8SDZ
/(\x{100}{0,2}a|x)/8SD
/(\x{100}{0,2}a|x)/8SDZ
/(\x{100}{1,2}a|x)/8SD
/(\x{100}{1,2}a|x)/8SDZ
/\x{100}*(\d+|"(?1)")/8
1234
@ -132,34 +132,34 @@
*** Failers
\x{100}\x{100}abcd
/\x{100}/8D
/\x{100}/8DZ
/\x{100}*/8D
/\x{100}*/8DZ
/a\x{100}*/8D
/a\x{100}*/8DZ
/ab\x{100}*/8D
/ab\x{100}*/8DZ
/a\x{100}\x{101}*/8D
/a\x{100}\x{101}*/8DZ
/a\x{100}\x{101}+/8D
/a\x{100}\x{101}+/8DZ
/\x{100}*A/8D
/\x{100}*A/8DZ
A
/\x{100}*\d(?R)/8D
/\x{100}*\d(?R)/8DZ
/[^\x{c4}]/D
/[^\x{c4}]/DZ
/[^\x{c4}]/8D
/[^\x{c4}]/8DZ
/[\x{100}]/8DM
/[\x{100}]/8DZ
\x{100}
Z\x{100}
\x{100}Z
*** Failers
/[Z\x{100}]/8DM
/[Z\x{100}]/8DZ
Z\x{100}
\x{100}
\x{100}Z
@ -174,21 +174,21 @@
\x{105}
\x{ff}
/[z-\x{100}]/8D
/[z-\x{100}]/8DZ
/[z\Qa-d]Ä€\E]/8D
/[z\Qa-d]Ä€\E]/8DZ
\x{100}
Ä€
/[\xFF]/D
/[\xFF]/DZ
>\xff<
/[\xff]/D8
/[\xff]/DZ8
>\x{ff}<
/[^\xFF]/D
/[^\xFF]/DZ
/[^\xff]/8D
/[^\xff]/8DZ
/[Ä-Ü]/8
Ö # Matches without Study
@ -212,7 +212,7 @@
/ÃÃÃxxx/8
/ÃÃÃxxx/8?D
/ÃÃÃxxx/8?DZ
/abc/8
Ã]
@ -239,19 +239,19 @@
\xfc\x84\x80\x80\x80\x80
\xfd\x83\x80\x80\x80\x80
/\x{100}abc(xyz(?1))/8D
/\x{100}abc(xyz(?1))/8DZ
/[^\x{100}]abc(xyz(?1))/8D
/[^\x{100}]abc(xyz(?1))/8DZ
/[ab\x{100}]abc(xyz(?1))/8D
/[ab\x{100}]abc(xyz(?1))/8DZ
/(\x{100}(b(?2)c))?/D8
/(\x{100}(b(?2)c))?/DZ8
/(\x{100}(b(?2)c)){0,2}/D8
/(\x{100}(b(?2)c)){0,2}/DZ8
/(\x{100}(b(?1)c))?/D8
/(\x{100}(b(?1)c))?/DZ8
/(\x{100}(b(?1)c)){0,2}/D8
/(\x{100}(b(?1)c)){0,2}/DZ8
/\W/8
A.B
@ -263,7 +263,7 @@
/a\x{1234}b/P8
a\x{1234}b
/^\ሴ/8D
/^\ሴ/8DZ
/\777/I
@ -271,23 +271,23 @@
\x{1ff}
\777
/\x{100}*\d/8D
/\x{100}*\d/8DZ
/\x{100}*\s/8D
/\x{100}*\s/8DZ
/\x{100}*\w/8D
/\x{100}*\w/8DZ
/\x{100}*\D/8D
/\x{100}*\D/8DZ
/\x{100}*\S/8D
/\x{100}*\S/8DZ
/\x{100}*\W/8D
/\x{100}*\W/8DZ
/\x{100}+\x{200}/8D
/\x{100}+\x{200}/8DZ
/\x{100}+X/8D
/\x{100}+X/8DZ
/X+\x{200}/8D
/X+\x{200}/8DZ
/()()()()()()()()()()
()()()()()()()()()()
@ -296,11 +296,11 @@
A (x) (?41) B/8x
AxxB
/^[\x{100}\E-\Q\E\x{150}]/B8
/^[\x{100}\E-\Q\E\x{150}]/BZ8
/^[\QÄ€\E-\QÅ<51>\E]/B8
/^[\QÄ€\E-\QÅ<51>\E]/BZ8
/^[\QÄ€\E-\QÅ<51>\E/B8
/^[\QÄ€\E-\QÅ<51>\E/BZ8
/^abc./mgx8<any>
abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x{0085}abc7 \x{2028}abc8 \x{2029}abc9 JUNK
@ -355,4 +355,42 @@
a\n\n\n\rb
a\r
/\H\h\V\v/8
X X\x0a
X\x09X\x0b
** Failers
\x{a0} X\x0a
/\H*\h+\V?\v{3,4}/8
\x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a
\x09\x20\x{a0}\x0a\x0b\x0c\x0d\x0a
\x09\x20\x{a0}\x0a\x0b\x0c
** Failers
\x09\x20\x{a0}\x0a\x0b
/\H\h\V\v/8
\x{3001}\x{3000}\x{2030}\x{2028}
X\x{180e}X\x{85}
** Failers
\x{2009} X\x0a
/\H*\h+\V?\v{3,4}/8
\x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x0c\x0d\x0a
\x09\x{205f}\x{a0}\x0a\x{2029}\x0c\x{2028}\x0a
\x09\x20\x{202f}\x0a\x0b\x0c
** Failers
\x09\x{200a}\x{a0}\x{2028}\x0b
/[\h]/8BZ
>\x{1680}
/[\h]{3,}/8BZ
>\x{1680}\x{180e}\x{2000}\x{2003}\x{200a}\x{202f}\x{205f}\x{3000}<
/[\v]/8BZ
/[\H]/8BZ
/[\V]/8BZ
/ End of testinput5 /

38
ext/pcre/pcrelib/testdata/testinput6 vendored
View File

@ -323,20 +323,20 @@
** Failers
WXYZ
/[\p{L}]/D
/[\p{L}]/DZ
/[\p{^L}]/D
/[\p{^L}]/DZ
/[\P{L}]/D
/[\P{L}]/DZ
/[\P{^L}]/D
/[\P{^L}]/DZ
/[abc\p{L}\x{0660}]/8D
/[abc\p{L}\x{0660}]/8DZ
/[\p{Nd}]/8DM
/[\p{Nd}]/8DZ
1234
/[\p{Nd}+-]+/8DM
/[\p{Nd}+-]+/8DZ
1234
12-34
12+\x{661}-34
@ -425,13 +425,13 @@
A\x{391}\x{10427}\x{ff5a}\x{1fb0}
A\x{391}\x{10427}\x{ff3a}\x{1fb8}
/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8iD
/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8iDZ
/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8D
/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8DZ
/AB\x{1fb0}/8D
/AB\x{1fb0}/8DZ
/AB\x{1fb0}/8Di
/AB\x{1fb0}/8DZi
/\x{391}+/8i
\x{391}\x{3b1}\x{3b1}\x{3b1}\x{391}
@ -452,7 +452,7 @@
\x{c0}
\x{e0}
/[\x{105}-\x{109}]/8iD
/[\x{105}-\x{109}]/8iDZ
\x{104}
\x{105}
\x{109}
@ -460,7 +460,7 @@
\x{100}
\x{10a}
/[z-\x{100}]/8iD
/[z-\x{100}]/8iDZ
Z
z
\x{39c}
@ -475,7 +475,7 @@
Y
y
/[z-\x{100}]/8Di
/[z-\x{100}]/8DZi
/^\X/8
A
@ -762,4 +762,14 @@ of case for anything other than the ASCII letters. /
/^\p{Balinese}\p{Cuneiform}\p{Nko}\p{Phags_Pa}\p{Phoenician}/8
\x{1b00}\x{12000}\x{7c0}\x{a840}\x{10900}
/The next two are special cases where the lengths of the different cases of the
same character differ. The first went wrong with heap fram storage; the 2nd
was broken in all cases./
/^\x{023a}+?(\x{0130}+)/8i
\x{023a}\x{2c65}\x{0130}
/^\x{023a}+([^X])/8i
\x{023a}\x{2c65}X
/ End of testinput6 /

73
ext/pcre/pcrelib/testdata/testinput7 vendored
View File

@ -1931,8 +1931,8 @@
/(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)\12\123/
abcdefghijk\12S
/ab\hdef/
abhdef
/ab\idef/
abidef
/a{0}bc/
bc
@ -4229,4 +4229,73 @@
\r\nfoo
\nfoo
/^$/mg<any>
abc\r\rxyz
abc\n\rxyz
** Failers
abc\r\nxyz
/^X/m
XABC
** Failers
XABC\B
/(?m)^$/<any>g+
abc\r\n\r\n
/(?m)^$|^\r\n/<any>g+
abc\r\n\r\n
/(?m)$/<any>g+
abc\r\n\r\n
/(?|(abc)|(xyz))/
>abc<
>xyz<
/(x)(?|(abc)|(xyz))(x)/
xabcx
xxyzx
/(x)(?|(abc)(pqr)|(xyz))(x)/
xabcpqrx
xxyzx
/(?|(abc)|(xyz))(?1)/
abcabc
xyzabc
** Failers
xyzxyz
/\H\h\V\v/
X X\x0a
X\x09X\x0b
** Failers
\xa0 X\x0a
/\H*\h+\V?\v{3,4}/
\x09\x20\xa0X\x0a\x0b\x0c\x0d\x0a
\x09\x20\xa0\x0a\x0b\x0c\x0d\x0a
\x09\x20\xa0\x0a\x0b\x0c
** Failers
\x09\x20\xa0\x0a\x0b
/\H{3,4}/
XY ABCDE
XY PQR ST
/.\h{3,4}./
XY AB PQRS
/\h*X\h?\H+Y\H?Z/
>XNNNYZ
> X NYQZ
** Failers
>XYZ
> X NY Z
/\v*X\v?Y\v+Z\V*\x0a\V+\x0b\V{2,3}\x0c/
>XY\x0aZ\x0aA\x0bNN\x0c
>\x0a\x0dX\x0aY\x0a\x0bZZZ\x0aAAA\x0bNNN\x0c
/ End of testinput7 /

38
ext/pcre/pcrelib/testdata/testinput8 vendored
View File

@ -590,4 +590,42 @@
a\n\n\n\rb
a\r
/\h+\V?\v{3,4}/8
\x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a
/\V?\v{3,4}/8
\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a
/\h+\V?\v{3,4}/8
>\x09\x20\x{a0}X\x0a\x0a\x0a<
/\V?\v{3,4}/8
>\x09\x20\x{a0}X\x0a\x0a\x0a<
/\H\h\V\v/8
X X\x0a
X\x09X\x0b
** Failers
\x{a0} X\x0a
/\H*\h+\V?\v{3,4}/8
\x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a
\x09\x20\x{a0}\x0a\x0b\x0c\x0d\x0a
\x09\x20\x{a0}\x0a\x0b\x0c
** Failers
\x09\x20\x{a0}\x0a\x0b
/\H\h\V\v/8
\x{3001}\x{3000}\x{2030}\x{2028}
X\x{180e}X\x{85}
** Failers
\x{2009} X\x0a
/\H*\h+\V?\v{3,4}/8
\x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x0c\x0d\x0a
\x09\x{205f}\x{a0}\x0a\x{2029}\x0c\x{2028}\x0a
\x09\x20\x{202f}\x0a\x0b\x0c
** Failers
\x09\x{200a}\x{a0}\x{2028}\x0b
/ End of testinput 8 /

6
ext/pcre/pcrelib/testdata/testinput9 vendored
View File

@ -813,4 +813,10 @@
\x{1c5}XY
AXY
/^\x{023a}+?(\x{0130}+)/8i
\x{023a}\x{2c65}\x{0130}
/^\x{023a}+([^X])/8i
\x{023a}\x{2c65}X
/ End /

11
ext/pcre/pcrelib/testdata/testoutput1 vendored
View File

@ -2189,9 +2189,9 @@ No match
10: j
11: k
/ab\hdef/
abhdef
0: abhdef
/ab\idef/
abidef
0: abidef
/a{0}bc/
bc
@ -6571,4 +6571,9 @@ No match
abc\n
No match
/(.*(.)?)*/
abcd
0: abcd
1:
/ End of testinput1 /

563
ext/pcre/pcrelib/testdata/testoutput10 vendored Normal file
View File

@ -0,0 +1,563 @@
/-- These are a few representative patterns whose lengths and offsets are to be
shown when the link size is 2. This is just a doublecheck test to ensure the
sizes don't go horribly wrong when something is changed. The pattern contents
are all themselves checked in other tests. --/
/((?i)b)/BM
Memory allocation (code space): 21
------------------------------------------------------------------
0 17 Bra 0
3 9 Bra 1
8 01 Opt
10 NC b
12 9 Ket
15 00 Opt
17 17 Ket
20 End
------------------------------------------------------------------
/(?s)(.*X|^B)/BM
Memory allocation (code space): 25
------------------------------------------------------------------
0 21 Bra 0
3 9 Bra 1
8 Any*
10 X
12 6 Alt
15 ^
16 B
18 15 Ket
21 21 Ket
24 End
------------------------------------------------------------------
/(?s:.*X|^B)/BM
Memory allocation (code space): 29
------------------------------------------------------------------
0 25 Bra 0
3 9 Bra 0
6 04 Opt
8 Any*
10 X
12 8 Alt
15 04 Opt
17 ^
18 B
20 17 Ket
23 00 Opt
25 25 Ket
28 End
------------------------------------------------------------------
/^[[:alnum:]]/BM
Memory allocation (code space): 41
------------------------------------------------------------------
0 37 Bra 0
3 ^
4 [0-9A-Za-z]
37 37 Ket
40 End
------------------------------------------------------------------
/#/IxMD
Memory allocation (code space): 7
------------------------------------------------------------------
0 3 Bra 0
3 3 Ket
6 End
------------------------------------------------------------------
Capturing subpattern count = 0
Options: extended
No first char
No need char
/a#/IxMD
Memory allocation (code space): 9
------------------------------------------------------------------
0 5 Bra 0
3 a
5 5 Ket
8 End
------------------------------------------------------------------
Capturing subpattern count = 0
Options: extended
First char = 'a'
No need char
/x?+/BM
Memory allocation (code space): 9
------------------------------------------------------------------
0 5 Bra 0
3 x?+
5 5 Ket
8 End
------------------------------------------------------------------
/x++/BM
Memory allocation (code space): 9
------------------------------------------------------------------
0 5 Bra 0
3 x++
5 5 Ket
8 End
------------------------------------------------------------------
/x{1,3}+/BM
Memory allocation (code space): 19
------------------------------------------------------------------
0 15 Bra 0
3 9 Once
6 x
8 x{0,2}
12 9 Ket
15 15 Ket
18 End
------------------------------------------------------------------
/(x)*+/BM
Memory allocation (code space): 24
------------------------------------------------------------------
0 20 Bra 0
3 14 Once
6 Brazero
7 7 Bra 1
12 x
14 7 KetRmax
17 14 Ket
20 20 Ket
23 End
------------------------------------------------------------------
/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/BM
Memory allocation (code space): 120
------------------------------------------------------------------
0 116 Bra 0
3 ^
4 109 Bra 1
9 7 Bra 2
14 a+
16 7 Ket
19 39 Bra 3
24 [ab]+?
58 39 Ket
61 39 Bra 4
66 [bc]+
100 39 Ket
103 7 Bra 5
108 \w*
110 7 Ket
113 109 Ket
116 116 Ket
119 End
------------------------------------------------------------------
|8J\$WE\<\.rX\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|BM
Memory allocation (code space): 826
------------------------------------------------------------------
0 822 Bra 0
3 8J$WE<.rX+ix[d1b!H#?vV0vrK:ZH1=2M>iV;?aPhFB<*vW@QW@sO9}cfZA-i'w%hKd6gt1UJP,15_#QY$M^Mss_U/]&LK9[5vQub^w[KDD<EjmhUZ?.akp2dF>qmj;2}YWFdYx.Ap]hjCPTP(n28k+3;o&WXqs/gOXdr$:r'do0;b4c(f_Gr="\4)[01T7ajQJvL$W~mL_sS/4h:x*[ZN=KLs&L5zX//>it,o:aU(;Z>pW&T7oP'2K^E:x9'c[%z-,64JQ5AeH_G#KijUKghQw^\vea3a?kka_G$8#`*kynsxzBLru']k_[7FrVx}^=$blx>s-N%j;D*aZDnsw:YKZ%Q.Kne9#hP?+b3(SOvL,^;&u5@?5C5Bhb=m-vEh_L15Jl]U)0RP6{q%L^_z5E'Dw6X
821 \b
822 822 Ket
825 End
------------------------------------------------------------------
|\$\<\.X\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|BM
Memory allocation (code space): 816
------------------------------------------------------------------
0 812 Bra 0
3 $<.X+ix[d1b!H#?vV0vrK:ZH1=2M>iV;?aPhFB<*vW@QW@sO9}cfZA-i'w%hKd6gt1UJP,15_#QY$M^Mss_U/]&LK9[5vQub^w[KDD<EjmhUZ?.akp2dF>qmj;2}YWFdYx.Ap]hjCPTP(n28k+3;o&WXqs/gOXdr$:r'do0;b4c(f_Gr="\4)[01T7ajQJvL$W~mL_sS/4h:x*[ZN=KLs&L5zX//>it,o:aU(;Z>pW&T7oP'2K^E:x9'c[%z-,64JQ5AeH_G#KijUKghQw^\vea3a?kka_G$8#`*kynsxzBLru']k_[7FrVx}^=$blx>s-N%j;D*aZDnsw:YKZ%Q.Kne9#hP?+b3(SOvL,^;&u5@?5C5Bhb=m-vEh_L15Jl]U)0RP6{q%L^_z5E'Dw6X
811 \b
812 812 Ket
815 End
------------------------------------------------------------------
/(a(?1)b)/BM
Memory allocation (code space): 28
------------------------------------------------------------------
0 24 Bra 0
3 18 Bra 1
8 a
10 6 Once
13 3 Recurse
16 6 Ket
19 b
21 18 Ket
24 24 Ket
27 End
------------------------------------------------------------------
/(a(?1)+b)/BM
Memory allocation (code space): 28
------------------------------------------------------------------
0 24 Bra 0
3 18 Bra 1
8 a
10 6 Once
13 3 Recurse
16 6 KetRmax
19 b
21 18 Ket
24 24 Ket
27 End
------------------------------------------------------------------
/a(?P<name1>b|c)d(?P<longername2>e)/BM
Memory allocation (code space): 42
------------------------------------------------------------------
0 32 Bra 0
3 a
5 7 Bra 1
10 b
12 5 Alt
15 c
17 12 Ket
20 d
22 7 Bra 2
27 e
29 7 Ket
32 32 Ket
35 End
------------------------------------------------------------------
/(?:a(?P<c>c(?P<d>d)))(?P<a>a)/BM
Memory allocation (code space): 54
------------------------------------------------------------------
0 41 Bra 0
3 25 Bra 0
6 a
8 17 Bra 1
13 c
15 7 Bra 2
20 d
22 7 Ket
25 17 Ket
28 25 Ket
31 7 Bra 3
36 a
38 7 Ket
41 41 Ket
44 End
------------------------------------------------------------------
/(?P<a>a)...(?P=a)bbb(?P>a)d/BM
Memory allocation (code space): 43
------------------------------------------------------------------
0 36 Bra 0
3 7 Bra 1
8 a
10 7 Ket
13 Any
14 Any
15 Any
16 \1
19 bbb
25 6 Once
28 3 Recurse
31 6 Ket
34 d
36 36 Ket
39 End
------------------------------------------------------------------
/abc(?C255)de(?C)f/BM
Memory allocation (code space): 31
------------------------------------------------------------------
0 27 Bra 0
3 abc
9 Callout 255 10 1
15 de
19 Callout 0 16 1
25 f
27 27 Ket
30 End
------------------------------------------------------------------
/abcde/CBM
Memory allocation (code space): 53
------------------------------------------------------------------
0 49 Bra 0
3 Callout 255 0 1
9 a
11 Callout 255 1 1
17 b
19 Callout 255 2 1
25 c
27 Callout 255 3 1
33 d
35 Callout 255 4 1
41 e
43 Callout 255 5 0
49 49 Ket
52 End
------------------------------------------------------------------
/\x{100}/8BM
Memory allocation (code space): 10
------------------------------------------------------------------
0 6 Bra 0
3 \x{100}
6 6 Ket
9 End
------------------------------------------------------------------
/\x{1000}/8BM
Memory allocation (code space): 11
------------------------------------------------------------------
0 7 Bra 0
3 \x{1000}
7 7 Ket
10 End
------------------------------------------------------------------
/\x{10000}/8BM
Memory allocation (code space): 12
------------------------------------------------------------------
0 8 Bra 0
3 \x{10000}
8 8 Ket
11 End
------------------------------------------------------------------
/\x{100000}/8BM
Memory allocation (code space): 12
------------------------------------------------------------------
0 8 Bra 0
3 \x{100000}
8 8 Ket
11 End
------------------------------------------------------------------
/\x{1000000}/8BM
Memory allocation (code space): 13
------------------------------------------------------------------
0 9 Bra 0
3 \x{1000000}
9 9 Ket
12 End
------------------------------------------------------------------
/\x{4000000}/8BM
Memory allocation (code space): 14
------------------------------------------------------------------
0 10 Bra 0
3 \x{4000000}
10 10 Ket
13 End
------------------------------------------------------------------
/\x{7fffFFFF}/8BM
Memory allocation (code space): 14
------------------------------------------------------------------
0 10 Bra 0
3 \x{7fffffff}
10 10 Ket
13 End
------------------------------------------------------------------
/[\x{ff}]/8BM
Memory allocation (code space): 10
------------------------------------------------------------------
0 6 Bra 0
3 \x{ff}
6 6 Ket
9 End
------------------------------------------------------------------
/[\x{100}]/8BM
Memory allocation (code space): 15
------------------------------------------------------------------
0 11 Bra 0
3 [\x{100}]
11 11 Ket
14 End
------------------------------------------------------------------
/\x80/8BM
Memory allocation (code space): 10
------------------------------------------------------------------
0 6 Bra 0
3 \x{80}
6 6 Ket
9 End
------------------------------------------------------------------
/\xff/8BM
Memory allocation (code space): 10
------------------------------------------------------------------
0 6 Bra 0
3 \x{ff}
6 6 Ket
9 End
------------------------------------------------------------------
/\x{0041}\x{2262}\x{0391}\x{002e}/D8M
Memory allocation (code space): 18
------------------------------------------------------------------
0 14 Bra 0
3 A\x{2262}\x{391}.
14 14 Ket
17 End
------------------------------------------------------------------
Capturing subpattern count = 0
Options: utf8
First char = 'A'
Need char = '.'
/\x{D55c}\x{ad6d}\x{C5B4}/D8M
Memory allocation (code space): 19
------------------------------------------------------------------
0 15 Bra 0
3 \x{d55c}\x{ad6d}\x{c5b4}
15 15 Ket
18 End
------------------------------------------------------------------
Capturing subpattern count = 0
Options: utf8
First char = 237
Need char = 180
/\x{65e5}\x{672c}\x{8a9e}/D8M
Memory allocation (code space): 19
------------------------------------------------------------------
0 15 Bra 0
3 \x{65e5}\x{672c}\x{8a9e}
15 15 Ket
18 End
------------------------------------------------------------------
Capturing subpattern count = 0
Options: utf8
First char = 230
Need char = 158
/[\x{100}]/8BM
Memory allocation (code space): 15
------------------------------------------------------------------
0 11 Bra 0
3 [\x{100}]
11 11 Ket
14 End
------------------------------------------------------------------
/[Z\x{100}]/8BM
Memory allocation (code space): 47
------------------------------------------------------------------
0 43 Bra 0
3 [Z\x{100}]
43 43 Ket
46 End
------------------------------------------------------------------
/^[\x{100}\E-\Q\E\x{150}]/B8M
Memory allocation (code space): 18
------------------------------------------------------------------
0 14 Bra 0
3 ^
4 [\x{100}-\x{150}]
14 14 Ket
17 End
------------------------------------------------------------------
/^[\QĀ\E-\QŐ\E]/B8M
Memory allocation (code space): 18
------------------------------------------------------------------
0 14 Bra 0
3 ^
4 [\x{100}-\x{150}]
14 14 Ket
17 End
------------------------------------------------------------------
/^[\QĀ\E-\QŐ\E/B8M
Failed: missing terminating ] for character class at offset 15
/[\p{L}]/BM
Memory allocation (code space): 15
------------------------------------------------------------------
0 11 Bra 0
3 [\p{L}]
11 11 Ket
14 End
------------------------------------------------------------------
/[\p{^L}]/BM
Memory allocation (code space): 15
------------------------------------------------------------------
0 11 Bra 0
3 [\P{L}]
11 11 Ket
14 End
------------------------------------------------------------------
/[\P{L}]/BM
Memory allocation (code space): 15
------------------------------------------------------------------
0 11 Bra 0
3 [\P{L}]
11 11 Ket
14 End
------------------------------------------------------------------
/[\P{^L}]/BM
Memory allocation (code space): 15
------------------------------------------------------------------
0 11 Bra 0
3 [\p{L}]
11 11 Ket
14 End
------------------------------------------------------------------
/[abc\p{L}\x{0660}]/8BM
Memory allocation (code space): 50
------------------------------------------------------------------
0 46 Bra 0
3 [a-c\p{L}\x{660}]
46 46 Ket
49 End
------------------------------------------------------------------
/[\p{Nd}]/8BM
Memory allocation (code space): 15
------------------------------------------------------------------
0 11 Bra 0
3 [\p{Nd}]
11 11 Ket
14 End
------------------------------------------------------------------
/[\p{Nd}+-]+/8BM
Memory allocation (code space): 48
------------------------------------------------------------------
0 44 Bra 0
3 [+\-\p{Nd}]+
44 44 Ket
47 End
------------------------------------------------------------------
/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8iBM
Memory allocation (code space): 25
------------------------------------------------------------------
0 21 Bra 0
3 NC A\x{391}\x{10427}\x{ff3a}\x{1fb0}
21 21 Ket
24 End
------------------------------------------------------------------
/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8BM
Memory allocation (code space): 25
------------------------------------------------------------------
0 21 Bra 0
3 A\x{391}\x{10427}\x{ff3a}\x{1fb0}
21 21 Ket
24 End
------------------------------------------------------------------
/[\x{105}-\x{109}]/8iBM
Memory allocation (code space): 17
------------------------------------------------------------------
0 13 Bra 0
3 [\x{104}-\x{109}]
13 13 Ket
16 End
------------------------------------------------------------------
/ End of testinput10 /

3912
ext/pcre/pcrelib/testdata/testoutput2 vendored
View File

File diff suppressed because it is too large Load Diff

14
ext/pcre/pcrelib/testdata/testoutput3 vendored
View File

@ -146,14 +146,14 @@ No match
>>>\xba<<<
0: º
/[[:alpha:]][[:lower:]][[:upper:]]/DLfr_FR
/[[:alpha:]][[:lower:]][[:upper:]]/DZLfr_FR
------------------------------------------------------------------
0 102 Bra 0
3 [A-Za-z\xaa\xb5\xba\xc0-\xd6\xd8-\xf6\xf8-\xff]
36 [a-z\xb5\xdf-\xf6\xf8-\xff]
69 [A-Z\xc0-\xd6\xd8-\xde]
102 102 Ket
105 End
Bra 0
[A-Za-z\xaa\xb5\xba\xc0-\xd6\xd8-\xf6\xf8-\xff]
[a-z\xb5\xdf-\xf6\xf8-\xff]
[A-Z\xc0-\xd6\xd8-\xde]
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
No options

1053
ext/pcre/pcrelib/testdata/testoutput5 vendored
View File

File diff suppressed because it is too large Load Diff

156
ext/pcre/pcrelib/testdata/testoutput6 vendored
View File

@ -548,73 +548,72 @@ No match
WXYZ
No match
/[\p{L}]/D
/[\p{L}]/DZ
------------------------------------------------------------------
0 11 Bra 0
3 [\p{L}]
11 11 Ket
14 End
Bra 0
[\p{L}]
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
No options
No first char
No need char
/[\p{^L}]/D
/[\p{^L}]/DZ
------------------------------------------------------------------
0 11 Bra 0
3 [\P{L}]
11 11 Ket
14 End
Bra 0
[\P{L}]
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
No options
No first char
No need char
/[\P{L}]/D
/[\P{L}]/DZ
------------------------------------------------------------------
0 11 Bra 0
3 [\P{L}]
11 11 Ket
14 End
Bra 0
[\P{L}]
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
No options
No first char
No need char
/[\P{^L}]/D
/[\P{^L}]/DZ
------------------------------------------------------------------
0 11 Bra 0
3 [\p{L}]
11 11 Ket
14 End
Bra 0
[\p{L}]
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
No options
No first char
No need char
/[abc\p{L}\x{0660}]/8D
/[abc\p{L}\x{0660}]/8DZ
------------------------------------------------------------------
0 46 Bra 0
3 [a-c\p{L}\x{660}]
46 46 Ket
49 End
Bra 0
[a-c\p{L}\x{660}]
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
Options: utf8
No first char
No need char
/[\p{Nd}]/8DM
Memory allocation (code space): 15
/[\p{Nd}]/8DZ
------------------------------------------------------------------
0 11 Bra 0
3 [\p{Nd}]
11 11 Ket
14 End
Bra 0
[\p{Nd}]
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
Options: utf8
@ -623,13 +622,12 @@ No need char
1234
0: 1
/[\p{Nd}+-]+/8DM
Memory allocation (code space): 48
/[\p{Nd}+-]+/8DZ
------------------------------------------------------------------
0 44 Bra 0
3 [+\-\p{Nd}]+
44 44 Ket
47 End
Bra 0
[+\-\p{Nd}]+
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
Partial matching not supported
@ -779,48 +777,48 @@ No match
A\x{391}\x{10427}\x{ff3a}\x{1fb8}
0: A\x{391}\x{10427}\x{ff3a}\x{1fb8}
/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8iD
/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8iDZ
------------------------------------------------------------------
0 21 Bra 0
3 NC A\x{391}\x{10427}\x{ff3a}\x{1fb0}
21 21 Ket
24 End
Bra 0
NC A\x{391}\x{10427}\x{ff3a}\x{1fb0}
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
Options: caseless utf8
First char = 'A' (caseless)
No need char
/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8D
/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8DZ
------------------------------------------------------------------
0 21 Bra 0
3 A\x{391}\x{10427}\x{ff3a}\x{1fb0}
21 21 Ket
24 End
Bra 0
A\x{391}\x{10427}\x{ff3a}\x{1fb0}
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
Options: utf8
First char = 'A'
Need char = 176
/AB\x{1fb0}/8D
/AB\x{1fb0}/8DZ
------------------------------------------------------------------
0 11 Bra 0
3 AB\x{1fb0}
11 11 Ket
14 End
Bra 0
AB\x{1fb0}
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
Options: utf8
First char = 'A'
Need char = 176
/AB\x{1fb0}/8Di
/AB\x{1fb0}/8DZi
------------------------------------------------------------------
0 11 Bra 0
3 NC AB\x{1fb0}
11 11 Ket
14 End
Bra 0
NC AB\x{1fb0}
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
Options: caseless utf8
@ -857,12 +855,12 @@ Need char = 'B' (caseless)
\x{e0}
0: \x{e0}
/[\x{105}-\x{109}]/8iD
/[\x{105}-\x{109}]/8iDZ
------------------------------------------------------------------
0 13 Bra 0
3 [\x{104}-\x{109}]
13 13 Ket
16 End
Bra 0
[\x{104}-\x{109}]
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
Options: caseless utf8
@ -881,12 +879,12 @@ No match
\x{10a}
No match
/[z-\x{100}]/8iD
/[z-\x{100}]/8iDZ
------------------------------------------------------------------
0 20 Bra 0
3 [Z\x{39c}\x{178}z-\x{101}]
20 20 Ket
23 End
Bra 0
[Z\x{39c}\x{178}z-\x{101}]
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
Options: caseless utf8
@ -919,12 +917,12 @@ No match
y
No match
/[z-\x{100}]/8Di
/[z-\x{100}]/8DZi
------------------------------------------------------------------
0 20 Bra 0
3 [Z\x{39c}\x{178}z-\x{101}]
20 20 Ket
23 End
Bra 0
[Z\x{39c}\x{178}z-\x{101}]
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
Options: caseless utf8
@ -1432,4 +1430,18 @@ of case for anything other than the ASCII letters. /
\x{1b00}\x{12000}\x{7c0}\x{a840}\x{10900}
0: \x{1b00}\x{12000}\x{7c0}\x{a840}\x{10900}
/The next two are special cases where the lengths of the different cases of the
same character differ. The first went wrong with heap fram storage; the 2nd
was broken in all cases./
/^\x{023a}+?(\x{0130}+)/8i
\x{023a}\x{2c65}\x{0130}
0: \x{23a}\x{2c65}\x{130}
1: \x{130}
/^\x{023a}+([^X])/8i
\x{023a}\x{2c65}X
0: \x{23a}\x{2c65}
1: \x{2c65}
/ End of testinput6 /

126
ext/pcre/pcrelib/testdata/testoutput7 vendored
View File

@ -3039,9 +3039,9 @@ No match
abcdefghijk\12S
0: abcdefghijk\x0aS
/ab\hdef/
abhdef
0: abhdef
/ab\idef/
abidef
0: abidef
/a{0}bc/
bc
@ -6952,4 +6952,124 @@ No match
\nfoo
0: \x0afoo
/^$/mg<any>
abc\r\rxyz
0:
abc\n\rxyz
0:
** Failers
No match
abc\r\nxyz
No match
/^X/m
XABC
0: X
** Failers
No match
XABC\B
No match
/(?m)^$/<any>g+
abc\r\n\r\n
0:
0+ \x0d\x0a
/(?m)^$|^\r\n/<any>g+
abc\r\n\r\n
0: \x0d\x0a
0+
1:
/(?m)$/<any>g+
abc\r\n\r\n
0:
0+ \x0d\x0a\x0d\x0a
0:
0+ \x0d\x0a
0:
0+
/(?|(abc)|(xyz))/
>abc<
0: abc
>xyz<
0: xyz
/(x)(?|(abc)|(xyz))(x)/
xabcx
0: xabcx
xxyzx
0: xxyzx
/(x)(?|(abc)(pqr)|(xyz))(x)/
xabcpqrx
0: xabcpqrx
xxyzx
0: xxyzx
/(?|(abc)|(xyz))(?1)/
abcabc
0: abcabc
xyzabc
0: xyzabc
** Failers
No match
xyzxyz
No match
/\H\h\V\v/
X X\x0a
0: X X\x0a
X\x09X\x0b
0: X\x09X\x0b
** Failers
No match
\xa0 X\x0a
No match
/\H*\h+\V?\v{3,4}/
\x09\x20\xa0X\x0a\x0b\x0c\x0d\x0a
0: \x09 \xa0X\x0a\x0b\x0c\x0d
1: \x09 \xa0X\x0a\x0b\x0c
\x09\x20\xa0\x0a\x0b\x0c\x0d\x0a
0: \x09 \xa0\x0a\x0b\x0c\x0d
1: \x09 \xa0\x0a\x0b\x0c
\x09\x20\xa0\x0a\x0b\x0c
0: \x09 \xa0\x0a\x0b\x0c
** Failers
No match
\x09\x20\xa0\x0a\x0b
No match
/\H{3,4}/
XY ABCDE
0: ABCD
1: ABC
XY PQR ST
0: PQR
/.\h{3,4}./
XY AB PQRS
0: B P
1: B
/\h*X\h?\H+Y\H?Z/
>XNNNYZ
0: XNNNYZ
> X NYQZ
0: X NYQZ
** Failers
No match
>XYZ
No match
> X NY Z
No match
/\v*X\v?Y\v+Z\V*\x0a\V+\x0b\V{2,3}\x0c/
>XY\x0aZ\x0aA\x0bNN\x0c
0: XY\x0aZ\x0aA\x0bNN\x0c
>\x0a\x0dX\x0aY\x0a\x0bZZZ\x0aAAA\x0bNNN\x0c
0: \x0a\x0dX\x0aY\x0a\x0bZZZ\x0aAAA\x0bNNN\x0c
/ End of testinput7 /

66
ext/pcre/pcrelib/testdata/testoutput8 vendored
View File

@ -1138,4 +1138,70 @@ No match
a\r
No match
/\h+\V?\v{3,4}/8
\x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a
0: \x{09} \x{a0}X\x{0a}\x{0b}\x{0c}\x{0d}
1: \x{09} \x{a0}X\x{0a}\x{0b}\x{0c}
/\V?\v{3,4}/8
\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a
0: X\x{0a}\x{0b}\x{0c}\x{0d}
1: X\x{0a}\x{0b}\x{0c}
/\h+\V?\v{3,4}/8
>\x09\x20\x{a0}X\x0a\x0a\x0a<
0: \x{09} \x{a0}X\x{0a}\x{0a}\x{0a}
/\V?\v{3,4}/8
>\x09\x20\x{a0}X\x0a\x0a\x0a<
0: X\x{0a}\x{0a}\x{0a}
/\H\h\V\v/8
X X\x0a
0: X X\x{0a}
X\x09X\x0b
0: X\x{09}X\x{0b}
** Failers
No match
\x{a0} X\x0a
No match
/\H*\h+\V?\v{3,4}/8
\x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a
0: \x{09} \x{a0}X\x{0a}\x{0b}\x{0c}\x{0d}
1: \x{09} \x{a0}X\x{0a}\x{0b}\x{0c}
\x09\x20\x{a0}\x0a\x0b\x0c\x0d\x0a
0: \x{09} \x{a0}\x{0a}\x{0b}\x{0c}\x{0d}
1: \x{09} \x{a0}\x{0a}\x{0b}\x{0c}
\x09\x20\x{a0}\x0a\x0b\x0c
0: \x{09} \x{a0}\x{0a}\x{0b}\x{0c}
** Failers
No match
\x09\x20\x{a0}\x0a\x0b
No match
/\H\h\V\v/8
\x{3001}\x{3000}\x{2030}\x{2028}
0: \x{3001}\x{3000}\x{2030}\x{2028}
X\x{180e}X\x{85}
0: X\x{180e}X\x{85}
** Failers
No match
\x{2009} X\x0a
No match
/\H*\h+\V?\v{3,4}/8
\x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x0c\x0d\x0a
0: \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x{0c}\x{0d}
1: \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x{0c}
\x09\x{205f}\x{a0}\x0a\x{2029}\x0c\x{2028}\x0a
0: \x{09}\x{205f}\x{a0}\x{0a}\x{2029}\x{0c}\x{2028}
1: \x{09}\x{205f}\x{a0}\x{0a}\x{2029}\x{0c}
\x09\x20\x{202f}\x0a\x0b\x0c
0: \x{09} \x{202f}\x{0a}\x{0b}\x{0c}
** Failers
No match
\x09\x{200a}\x{a0}\x{2028}\x0b
No match
/ End of testinput 8 /

8
ext/pcre/pcrelib/testdata/testoutput9 vendored
View File

@ -1624,4 +1624,12 @@ No match
AXY
No match
/^\x{023a}+?(\x{0130}+)/8i
\x{023a}\x{2c65}\x{0130}
0: \x{23a}\x{2c65}\x{130}
/^\x{023a}+([^X])/8i
\x{023a}\x{2c65}X
0: \x{23a}\x{2c65}
/ End /

2
ext/pcre/pcrelib/ucptable.c → ext/pcre/pcrelib/ucptable.h
View File

@ -2,7 +2,7 @@
property table. See ucpinternal.h for a description of the layout.
This version was made from the Unicode 5.0.0 tables. */
static cnode ucp_table[] = {
static const cnode ucp_table[] = {
{ 0x09800000, 0x0000001f },
{ 0x09000020, 0x74000000 },
{ 0x09800021, 0x54000002 },

102
ext/pcre/upgrade-pcre.php Normal file
View File

@ -0,0 +1,102 @@
<?php
// script to upgrade PCRE. just drop the pcre-x.x.tar.xx here and run the script
$pattern = 'pcre-*.tar.*';
$newpcre = glob($pattern);
if (count($newpcre) > 1) {
echo "more than one '$pattern' file. aborting\n";
print_r($newpcre);
exit;
}
if (count($newpcre) == 0) {
die("need one '$pattern' file. aborting.\n");
}
$newpcre = $newpcre[0];
if (strpos($newpcre, 'gz')) {
system("tar xfz $newpcre");
} elseif (strpos($newpcre, 'bz2')) {
system("tar xfj $newpcre");
} else {
die("file type not recognized: $newpcre\n");
}
$newpcre = substr($newpcre, 0, strpos($newpcre, '.tar'));
$dirlen = strlen('pcrelib');
function recurse($path)
{
global $newpcre, $dirlen;
foreach(scandir($path) as $file) {
if ($file[0] === '.' || $file === 'CVS') continue;
if (substr_compare($file, '.lo', -3, 3) == 0 || substr_compare($file, '.o', -2, 2) == 0) continue;
$file = "$path/$file";
if (is_dir($file)) {
recurse($file);
continue;
}
echo "processing $file... ";
$newfile = $newpcre . substr($file, $dirlen);
if (is_file($tmp = $newfile . '.generic') || is_file($tmp = $newfile . '.dist')) {
$newfile = $tmp;
}
if (!is_file($newfile)) {
die("$newfile is not available any more\n");
}
copy($newfile, $file);
echo "OK\n";
}
}
recurse('pcrelib');
$dirorig = scandir('pcrelib/testdata');
$k = array_search('CVS', $dirorig);
unset($dirorig[$k]);
$dirnew = scandir("$newpcre/testdata");
$diff = array_diff($dirorig, $dirnew);
foreach ($diff as $file) {
$file2 = 'pcrelib'.substr($file, strlen($newpcre));
copy($file, $file2);
}
// the config.h needs special care
$prepend_config_h = '
#include <php_compat.h>
#undef PACKAGE_NAME
#undef PACKAGE_VERSION
#undef PACKAGE_TARNAME
#undef PACKAGE_STRING
#define SUPPORT_UCP
#define SUPPORT_UTF8
';
file_put_contents('pcrelib/config.h', $prepend_config_h . file_get_contents('pcrelib/config.h'));
echo "\nThe End :-)\n\n"
?>