PenTest/nmap
1
0
Fork 0
mirror of https://github.com/nmap/nmap.git synced 2025-12-06 04:31:29 +00:00
Code Issues Projects Releases Wiki Activity

Upgrading libpcre from version 7.2 to 7.4. Tested on Linux and Windows

Browse Source
This commit is contained in:
kris
2007-12-20 22:24:53 +00:00
parent aa94d1e9d1
commit a1654beda6
38 changed files with 1728 additions and 712 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
CHANGELOG
View File

@@ -42,6 +42,8 @@ o Nmap's output options (-oA, -oX, etc.) now support strftime()-like
means that "-oX 'scan-%T-%D.xml'" uses an XML file in the form of
"scan-144840-121307.xml". [Kris]
o Upgraded the shipped LibPCRE from version 7.2 to 7.4 [Kris]
o Added a new NSE script (MySQLinfo) which prints MySQL server information
such as the protocol and version numbers, status, thread id, capabilities,
and password salt. [Kris]

1
libpcre/Makefile.am
View File

@@ -80,4 +80,3 @@ nodist_libpcre_a_SOURCES = pcre_chartables.c
# A compatibility line, the old build system worked with 'make test'
test: check ;
## end Makefile.am

12
libpcre/Makefile.in
View File

@@ -40,10 +40,12 @@ noinst_PROGRAMS = $(am__EXEEXT_1)
@WITH_REBUILD_CHARTABLES_TRUE@am__append_1 = dftables
subdir = .
DIST_COMMON = README $(am__configure_deps) $(include_HEADERS) \
$(srcdir)/Makefile.am $(srcdir)/Makefile.in \
$(srcdir)/config.h.in $(srcdir)/pcre-config.in \
$(srcdir)/pcre.h.in $(top_srcdir)/configure AUTHORS INSTALL \
config.guess config.sub depcomp install-sh missing
$(srcdir)/../config.guess $(srcdir)/../config.sub \
$(srcdir)/../depcomp $(srcdir)/../install-sh \
$(srcdir)/../missing $(srcdir)/Makefile.am \
$(srcdir)/Makefile.in $(srcdir)/config.h.in \
$(srcdir)/pcre-config.in $(srcdir)/pcre.h.in \
$(top_srcdir)/configure AUTHORS INSTALL
ACLOCAL_M4 = $(top_srcdir)/aclocal.m4
am__aclocal_m4_deps = $(top_srcdir)/configure.ac
am__configure_deps = $(am__aclocal_m4_deps) $(CONFIGURE_DEPENDENCIES) \
@@ -92,7 +94,7 @@ dftables_LDADD = $(LDADD)
binSCRIPT_INSTALL = $(INSTALL_SCRIPT)
SCRIPTS = $(bin_SCRIPTS)
DEFAULT_INCLUDES = -I.@am__isrc@
depcomp = $(SHELL) $(top_srcdir)/depcomp
depcomp = $(SHELL) $(top_srcdir)/../depcomp
am__depfiles_maybe = depfiles
COMPILE = $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) \
$(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS)

80
libpcre/NMAP_MODIFICATIONS
View File

@@ -1,4 +1,4 @@
This directory conains a version of LibPCRE 7.2 that has been stripped
This directory contains a version of LibPCRE 7.4 that has been stripped
down to less than a third of its original uncompressed size. So if you
want docs, tests and such, you should go to the PCRE website at
http://www.pcre.org . Here are the changes for the Nmap version:
@@ -30,13 +30,14 @@ makevp_c.txt
makevp_l.txt
pcregexp.pas
ltmain.sh
CleanTxt
ChangeLog
NEWS
HACKING
COPYING [Look at LICENCE]
o Got rid of the C++ wrapper, which included this step:
rm -f *.cc pcrecpparg.h.in pcrecpp.h pcre_scanner.h pcre_stringpiece.h.in
rm -f *.cc pcrecpparg.h.in pcrecpp.h pcrecpp_internal.h pcre_scanner.h pcre_stringpiece.h.in
o Copied pcre.h.generic to pcre.h and pcre_chartables.c.dist to, you
guessed it, pcre_chartables.c (for Windows). Running ./configure in
@@ -56,17 +57,17 @@ o Stripped down Makefile.am and configure.ac substantially to remove
o Removed config.sub, config.guess, depcomp, install-sh, and missing.
These files are found in the parent (i.e., Nmap's) directory.
o Comment out some build configuration lines from pcre-internal.h because Nmap
o Comment out some build configuration lines from pcre_internal.h because Nmap
builds a static library:
--- pcre-7.2/pcre_internal.h 2007-06-12 08:39:55.000000000 -0500
+++ libpcre/pcre_internal.h 2007-08-15 18:56:18.000000000 -0500
@@ -112,15 +112,19 @@ PCRE_EXP_DATA_DEFN only if they are not
--- pcre-7.4/pcre_internal.h 2007-09-13 04:22:27.000000000 -0500
+++ libpcre/pcre_internal.h 2007-12-19 22:28:33.000000000 -0600
@@ -108,15 +108,19 @@ PCRE_EXP_DATA_DEFN only if they are not
#ifndef PCRE_EXP_DECL
# ifdef _WIN32
+/* COMMENTED OUT AS IT'S COMPILED STATICALLY
# ifdef DLL_EXPORT
# ifndef PCRE_STATIC
# define PCRE_EXP_DECL extern __declspec(dllexport)
# define PCRE_EXP_DEFN __declspec(dllexport)
# define PCRE_EXP_DATA_DEFN __declspec(dllexport)
@@ -78,25 +79,25 @@ o Comment out some build configuration lines from pcre-internal.h because Nmap
+/*
# endif
+*/
#
# else
# ifdef __cplusplus
# define PCRE_EXP_DECL extern "C"
...and pcre.h.in/pcre.h.generic/pcre.h:
--- pcre-7.2/pcre.h.in 2007-06-04 05:18:02.000000000 -0500
+++ libpcre/pcre.h.in 2007-08-15 19:24:46.000000000 -0500
--- pcre-7.4/pcre.h.in 2007-09-11 06:24:35.000000000 -0500
+++ libpcre/pcre.h.in 2007-12-19 22:30:32.000000000 -0600
@@ -51,6 +51,7 @@ imported have to be identified as such.
export setting is defined in pcre_internal.h, which includes this file. So we
don't change an existing definition of PCRE_EXP_DECL. */
don't change existing definitions of PCRE_EXP_DECL and PCRECPP_EXP_DECL. */
+/*
#ifndef PCRE_EXP_DECL
# ifdef _WIN32
# ifndef PCRE_STATIC
@@ -58,6 +59,7 @@ don't change an existing definition of P
#if defined(_WIN32) && !defined(PCRE_STATIC)
# ifndef PCRE_EXP_DECL
# define PCRE_EXP_DECL extern __declspec(dllimport)
@@ -64,6 +65,7 @@ don't change existing definitions of PCR
# endif
# endif
#endif
@@ -108,44 +109,41 @@ o Comment out some build configuration lines from pcre-internal.h because Nmap
..and pcreposix.h:
--- pcre-7.2/pcreposix.h 2007-04-04 09:04:40.000000000 -0500
+++ libpcre/pcreposix.h 2007-08-15 20:31:42.000000000 -0500
@@ -109,12 +109,14 @@ typedef struct {
imported have to be identified as such. When building PCRE, the appropriate
export settings are needed. */
--- pcre-7.4/pcreposix.h 2007-08-01 04:06:39.000000000 -0500
+++ libpcre/pcreposix.h 2007-12-19 22:31:14.000000000 -0600
@@ -110,10 +110,12 @@ imported have to be identified as such.
export settings are needed, and are set in pcreposix.c before including this
file. */
+/*
#ifdef _WIN32
# ifndef PCREPOSIX_STATIC
# define PCREPOSIX_EXP_DECL extern __declspec(dllimport)
# define PCREPOSIX_EXP_DEFN __declspec(dllimport)
# endif
#if defined(_WIN32) && !defined(PCRE_STATIC) && !defined(PCREPOSIX_EXP_DECL)
# define PCREPOSIX_EXP_DECL extern __declspec(dllimport)
# define PCREPOSIX_EXP_DEFN __declspec(dllimport)
#endif
+*/
/* By default, we use the standard "extern" declarations. */
o Added pcre_winconfig.h, and include it in pcre_internal.h instead of config.h:
o Added pcre_winconfig.h for Windows. LibPCRE used to include config.h in
pcre_internal.h, and we'd include this winconfig there instead of config.h
if WIN32 is defined. Now, however, they've moved config.h includes to a
bunch of different files, so we have to change them. We could remove the
other includes and move it back to pcre_internal.h, but they must've moved
them for a reason, so we'll follow them. Occurrences of
--- pcre-7.2/pcre_internal.h 2007-06-12 08:39:55.000000000 -0500
+++ libpcre/pcre_internal.h 2007-08-15 20:33:48.000000000 -0500
@@ -69,7 +69,11 @@ be absolutely sure we get our version. *
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
/* Get the definitions provided by running "configure" */
get changed to
+#ifdef WIN32
+#include "pcre_winconfig.h"
+#else
#include "config.h"
+#endif
#ifdef WIN32
#include "pcre_winconfig.h"
#else
#include "config.h"
#endif
/* Standard C headers plus the external interface definition. The only time
setjmp and stdarg are used is when NO_RECURSE is set. */
o Change the pcre.h #include in pcre_internal.h from <pcre.h> to "pcre.h".
This seems to be needed on Windows.
o Regenerated everything with 'automake; aclocal; autoconf'

232
libpcre/NON-UNIX-USE
View File

@@ -7,14 +7,16 @@ This document contains the following sections:
Generic instructions for the PCRE C library
The C++ wrapper functions
Building for virtual Pascal
Stack size in Windows environments
Comments about Win32 builds
Building PCRE with CMake
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
I (Philip Hazel) have no experience 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.
@@ -29,88 +31,116 @@ 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".
The PCRE distribution includes support for CMake. This support is relatively
new, but has already been used successfully to build PCRE in multiple build
environments on Windows. There are some instructions in the section entitled
"Building PCRE with CMake" below.
GENERIC INSTRUCTIONS FOR THE PCRE C LIBRARY
The following are generic comments about building the PCRE C library "by hand".
(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.
(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. When you compile any of the PCRE modules, you
must specify -DHAVE_CONFIG_H to your compiler so that config.h is included
in the sources.
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.
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 to the
configuration options. In this case -DHAVE_CONFIG_H must not be set.
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.
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.
(2) Copy or rename the file pcre.h.generic as pcre.h.
(2) Copy or rename the file pcre.h.generic as pcre.h.
(3) EITHER:
Copy or rename file pcre_chartables.c.dist as pcre_chartables.c.
(3) EITHER:
Copy or rename file pcre_chartables.c.dist as pcre_chartables.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.
OR:
Compile dftables.c as a stand-alone program (using -DHAVE_CONFIG_H if
you have set up config.h), 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.
The tables in pcre_chartables.c are defaults. The caller of PCRE can
specify alternative tables at run time.
The tables in pcre_chartables.c are defaults. The caller of PCRE can
specify alternative tables at run time.
(4) Compile the following source files:
(4) Ensure that you have the following header files:
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
pcre_internal.h
ucp.h
ucpinternal.h
ucptable.h
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) Also ensure that you have the following file, which is #included as source
when building a debugging version of PCRE and is also used by pcretest.
(5) Similarly, compile pcreposix.c and link it (on its own) as the pcreposix
library.
pcre_printint.src
(6) Compile the test program pcretest.c. This needs the functions in the
pcre and pcreposix libraries when linking.
(6) Compile the following source files, setting -DHAVE_CONFIG_H as a compiler
option if you have set up config.h with your configuration, or else use
other -D settings to change the configuration as required.
(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.
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
(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).
Make sure that you include -I. in the compiler command (or equivalent for
an unusual compiler) so that all included PCRE header files are first
sought in the current directory. Otherwise you run the risk of picking up
a previously-installed file from somewhere else.
(7) Now link all the compiled code 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.
(8) Similarly, compile pcreposix.c (remembering -DHAVE_CONFIG_H if necessary)
and link the result (on its own) as the pcreposix library.
(9) Compile the test program pcretest.c (again, don't forget -DHAVE_CONFIG_H).
This needs the functions in the pcre and pcreposix libraries when linking.
It also needs the pcre_printint.src source file, which it #includes.
(10) 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. If you are using Windows, you probably should use
the wintestinput3 file instead of testinput3 (and the corresponding output
file). This is a locale test; wintestinput3 sets the locale to "french"
rather than "fr_FR", and there some minor output differences.
(11) 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
@@ -131,7 +161,23 @@ 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
STACK SIZE IN WINDOWS ENVIRONMENTS
The default processor stack size of 1Mb in some Windows environments is too
small for matching patterns that need much recursion. In particular, test 2 may
fail because of this. Normally, running out of stack causes a crash, but there
have been cases where the test program has just died silently. See your linker
documentation for how to increase stack size if you experience problems. The
Linux default of 8Mb is a reasonable choice for the stack, though even that can
be too small for some pattern/subject combinations.
PCRE has a compile configuration option to disable the use of stack for
recursion so that heap is used instead. However, pattern matching is
significantly slower when this is done. There is more about stack usage in the
"pcrestack" documentation.
COMMENTS ABOUT WIN32 BUILDS (see also "BUILDING PCRE WITH CMAKE" below)
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
@@ -206,6 +252,60 @@ terminators in order to get some of the tests to work. We hope to improve
things in this area in future.
BUILDING PCRE WITH CMAKE
CMake is an alternative build facility that can be used instead of the
traditional Unix "configure". CMake version 2.4.7 supports Borland makefiles,
MinGW makefiles, MSYS makefiles, NMake makefiles, UNIX makefiles, Visual Studio
6, Visual Studio 7, Visual Studio 8, and Watcom W8. The following instructions
were contributed by a PCRE user.
1. Download CMake 2.4.7 or above from http://www.cmake.org/, install and ensure
that cmake\bin is on your path.
2. Unzip (retaining folder structure) the PCRE source tree into a source
directory such as C:\pcre.
3. Create a new, empty build directory: C:\pcre\build\
4. Run CMakeSetup from the Shell envirornment of your build tool, e.g., Msys
for Msys/MinGW or Visual Studio Command Prompt for VC/VC++
5. Enter C:\pcre\pcre-xx and C:\pcre\build for the source and build
directories, respectively
6. Hit the "Configure" button.
7. Select the particular IDE / build tool that you are using (Visual Studio,
MSYS makefiles, MinGW makefiles, etc.)
8. The GUI will then list several configuration options. This is where you can
enable UTF-8 support, etc.
9. Hit "Configure" again. The adjacent "OK" button should now be active.
10. Hit "OK".
11. The build directory should now contain a usable build system, be it a
solution file for Visual Studio, makefiles for MinGW, etc.
Testing with RunTest.bat
1. Copy RunTest.bat into the directory where pcretest.exe has been created.
2. Edit RunTest.bat and insert a line that indentifies the relative location of
the pcre source, e.g.:
set srcdir=..\pcre-7.4-RC3
3. Run RunTest.bat from a command shell environment. Test outputs will
automatically be compared to expected results, and discrepancies will
identified in the console output.
4. To test pcrecpp, run pcrecpp_unittest.exe, pcre_stringpiece_unittest.exe and
pcre_scanner_unittest.exe.
BUILDING UNDER WINDOWS WITH BCC5.5
Michael Roy sent these comments about building PCRE under Windows with BCC5.5:
@@ -284,5 +384,5 @@ $! Locale could not be set to fr
$!
=========================
Last Updated: 13 June 2007
Last Updated: 21 September 2007
****

17
libpcre/README
View File

@@ -103,7 +103,9 @@ 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.
able to build PCRE in the same way as for Unix-like systems. PCRE can also be
configured in many platform environments using the GUI facility of CMake's
CMakeSetup. It creates Makefiles, solution files, etc.
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
@@ -184,6 +186,12 @@ library. You can read more about them in the pcrebuild man page.
--enable-newline-is-any, many tests should succeed, but there may be some
failures.
. By default, the sequence \R in a pattern matches any Unicode line ending
sequence. This is independent of the option specifying what PCRE considers to
be the end of a line (see above). However, the caller of PCRE can restrict \R
to match only CR, LF, or CRLF. You can make this the default by adding
--enable-bsr-anycrlf to the "configure" command (bsr = "backslash R").
. 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 in a pattern. You can increase this threshold by setting, for example,
@@ -500,7 +508,10 @@ 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.]
work by changing "fr_FR" to "french" everywhere it occurs. Alternatively, use
RunTest.bat. The version of RunTest.bat included with PCRE 7.4 and above uses
Windows versions of test 2. More info on using RunTest.bat is included in the
document entitled NON-UNIX-USE.]
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
@@ -714,4 +725,4 @@ The distribution should contain the following files:
Philip Hazel
Email local part: ph10
Email domain: cam.ac.uk
Last updated: 24 April 2007
Last updated: 21 September 2007

39
libpcre/config.h.generic
View File

@@ -9,13 +9,24 @@ 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.
macro definitions the way you need them. You must then add -DHAVE_CONFIG_H to
all of your compile commands, so that config.h is included at the start of
every source.
Alternatively, you can avoid editing by using -D on the compiler command line
to set the macro values. In this case, you do not have to set -DHAVE_CONFIG_H.
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. */
/* By default, the \R escape sequence matches any Unicode line ending
character or sequence of characters. If BSR_ANYCRLF is defined, this is
changed so that backslash-R matches only CR, LF, or CRLF. The build- time
default can be overridden by the user of PCRE at runtime. On systems that
support it, "configure" can be used to override the default. */
/* #undef BSR_ANYCRLF */
/* 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. */
@@ -130,6 +141,9 @@ them both to 0; an emulation function will be used. */
/* Define to 1 if you have the <windows.h> header file. */
/* #undef HAVE_WINDOWS_H */
/* Define to 1 if you have the `_strtoi64' function. */
/* #undef HAVE__STRTOI64 */
/* 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.
@@ -164,13 +178,6 @@ them both to 0; an emulation function will be used. */
#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. */
@@ -185,10 +192,10 @@ them both to 0; an emulation function will be used. */
#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). */
/* The value of NEWLINE determines the newline character sequence. On systems
that support it, "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
@@ -213,13 +220,13 @@ them both to 0; an emulation function will be used. */
#define PACKAGE_NAME "PCRE"
/* Define to the full name and version of this package. */
#define PACKAGE_STRING "PCRE 7.2"
#define PACKAGE_STRING "PCRE 7.4"
/* 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"
#define PACKAGE_VERSION "7.4"
/* If you are compiling for a system other than a Unix-like system or
@@ -261,7 +268,7 @@ them both to 0; an emulation function will be used. */
/* Version number of package */
#ifndef VERSION
#define VERSION "7.2"
#define VERSION "7.4"
#endif
/* Define to empty if `const' does not conform to ANSI C. */

46
libpcre/config.h.in
View File

@@ -8,13 +8,24 @@ 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.
macro definitions the way you need them. You must then add -DHAVE_CONFIG_H to
all of your compile commands, so that config.h is included at the start of
every source.
Alternatively, you can avoid editing by using -D on the compiler command line
to set the macro values. In this case, you do not have to set -DHAVE_CONFIG_H.
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. */
/* By default, the \R escape sequence matches any Unicode line ending
character or sequence of characters. If BSR_ANYCRLF is defined, this is
changed so that backslash-R matches only CR, LF, or CRLF. The build- time
default can be overridden by the user of PCRE at runtime. On systems that
support it, "configure" can be used to override the default. */
#undef BSR_ANYCRLF
/* 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. */
@@ -23,15 +34,9 @@ them both to 0; an emulation function will be used. */
/* Define to 1 if you have the `bcopy' function. */
#undef HAVE_BCOPY
/* 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. */
#undef HAVE_DIRENT_H
/* Define to 1 if you have the <dlfcn.h> header file. */
#undef HAVE_DLFCN_H
/* Define to 1 if you have the <inttypes.h> header file. */
#undef HAVE_INTTYPES_H
@@ -56,9 +61,6 @@ them both to 0; an emulation function will be used. */
/* Define to 1 if you have the `strerror' function. */
#undef HAVE_STRERROR
/* Define to 1 if you have the <string> header file. */
#undef HAVE_STRING
/* Define to 1 if you have the <strings.h> header file. */
#undef HAVE_STRINGS_H
@@ -77,9 +79,6 @@ them both to 0; an emulation function will be used. */
/* Define to 1 if you have the <sys/types.h> header file. */
#undef HAVE_SYS_TYPES_H
/* 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. */
#undef HAVE_UNISTD_H
@@ -89,6 +88,9 @@ them both to 0; an emulation function will be used. */
/* Define to 1 if you have the <windows.h> header file. */
#undef HAVE_WINDOWS_H
/* Define to 1 if you have the `_strtoi64' function. */
#undef HAVE__STRTOI64
/* 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.
@@ -97,6 +99,9 @@ them both to 0; an emulation function will be used. */
"configure" can be used to override this default. */
#undef LINK_SIZE
/* Mac OS X on Intel */
#undef MACOSX
/* 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.
@@ -117,11 +122,6 @@ them both to 0; an emulation function will be used. */
"configure" can be used to override the default. */
#undef MATCH_LIMIT_RECURSION
/* 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. */
#undef MAX_DUPLENGTH
/* 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. */
@@ -132,10 +132,10 @@ them both to 0; an emulation function will be used. */
overflow caused by enormously large patterns. */
#undef MAX_NAME_SIZE
/* 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). */
/* The value of NEWLINE determines the newline character sequence. On systems
that support it, "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). */
#undef NEWLINE
/* PCRE uses recursive function calls to handle backtracking while matching.

58
libpcre/configure vendored
View File

@@ -1,6 +1,6 @@
#! /bin/sh
# Guess values for system-dependent variables and create Makefiles.
# Generated by GNU Autoconf 2.61 for PCRE 7.2.
# Generated by GNU Autoconf 2.61 for PCRE 7.4.
#
# Copyright (C) 1992, 1993, 1994, 1995, 1996, 1998, 1999, 2000, 2001,
# 2002, 2003, 2004, 2005, 2006 Free Software Foundation, Inc.
@@ -572,8 +572,8 @@ SHELL=${CONFIG_SHELL-/bin/sh}
# Identity of this package.
PACKAGE_NAME='PCRE'
PACKAGE_TARNAME='pcre'
PACKAGE_VERSION='7.2'
PACKAGE_STRING='PCRE 7.2'
PACKAGE_VERSION='7.4'
PACKAGE_STRING='PCRE 7.4'
PACKAGE_BUGREPORT=''
ac_unique_file="pcre.h.in"
@@ -1226,7 +1226,7 @@ if test "$ac_init_help" = "long"; then
# Omit some internal or obsolete options to make the list less imposing.
# This message is too long to be a string in the A/UX 3.1 sh.
cat <<_ACEOF
\`configure' configures PCRE 7.2 to adapt to many kinds of systems.
\`configure' configures PCRE 7.4 to adapt to many kinds of systems.
Usage: $0 [OPTION]... [VAR=VALUE]...
@@ -1296,7 +1296,7 @@ fi
if test -n "$ac_init_help"; then
case $ac_init_help in
short | recursive ) echo "Configuration of PCRE 7.2:";;
short | recursive ) echo "Configuration of PCRE 7.4:";;
esac
cat <<\_ACEOF
@@ -1318,8 +1318,10 @@ Optional Features:
--enable-newline-is-anycrlf
use CR, LF, or CRLF as newline sequence
--enable-newline-is-any use any valid Unicode newline sequence
--enable-ebcdic assume EBCDIC coding rather than ASCII (implies
--enable-rebuild-chartables)
--enable-bsr-anycrlf \R matches only CR, LF, CRLF by default
--enable-ebcdic assume EBCDIC coding rather than ASCII; use this
only in (uncommon) EBCDIC environments; it implies
--enable-rebuild-chartables
--disable-stack-for-recursion
don't use stack recursion when matching
@@ -1407,7 +1409,7 @@ fi
test -n "$ac_init_help" && exit $ac_status
if $ac_init_version; then
cat <<\_ACEOF
PCRE configure 7.2
PCRE configure 7.4
generated by GNU Autoconf 2.61
Copyright (C) 1992, 1993, 1994, 1995, 1996, 1998, 1999, 2000, 2001,
@@ -1421,7 +1423,7 @@ cat >config.log <<_ACEOF
This file contains any messages produced by compilers while
running configure, to aid debugging if configure makes a mistake.
It was created by PCRE $as_me 7.2, which was
It was created by PCRE $as_me 7.4, which was
generated by GNU Autoconf 2.61. Invocation command line was
$ $0 $@
@@ -2112,7 +2114,7 @@ fi
# Define the identity of the package.
PACKAGE='pcre'
VERSION='7.2'
VERSION='7.4'
cat >>confdefs.h <<_ACEOF
@@ -3563,9 +3565,9 @@ fi
PCRE_MAJOR="7"
PCRE_MINOR="2"
PCRE_MINOR="4"
PCRE_PRERELEASE=""
PCRE_DATE="2007-06-19"
PCRE_DATE="2007-09-21"
@@ -3636,6 +3638,15 @@ fi
enable_newline="$ac_pcre_newline"
# Handle --enable-bsr-anycrlf
# Check whether --enable-bsr-anycrlf was given.
if test "${enable_bsr_anycrlf+set}" = set; then
enableval=$enable_bsr_anycrlf;
else
enable_bsr_anycrlf=no
fi
# Handle --enable-ebcdic
# Check whether --enable-ebcdic was given.
if test "${enable_ebcdic+set}" = set; then
@@ -4861,7 +4872,8 @@ fi
for ac_func in bcopy memmove strerror strtoq strtoll
for ac_func in bcopy memmove strerror strtoq strtoll _strtoi64
do
as_ac_var=`echo "ac_cv_func_$ac_func" | $as_tr_sh`
{ echo "$as_me:$LINENO: checking for $ac_func" >&5
@@ -4996,6 +5008,14 @@ cat >>confdefs.h <<_ACEOF
_ACEOF
if test "$enable_bsr_anycrlf" = "yes"; then
cat >>confdefs.h <<\_ACEOF
#define BSR_ANYCRLF
_ACEOF
fi
cat >>confdefs.h <<_ACEOF
#define LINK_SIZE $with_link_size
@@ -5033,12 +5053,6 @@ _ACEOF
cat >>confdefs.h <<\_ACEOF
#define MAX_DUPLENGTH 30000
_ACEOF
if test "$enable_ebcdic" = "yes"; then
@@ -5141,7 +5155,7 @@ cat >>confdefs.h <<\_ACEOF
#define MACOSX
_ACEOF
CFLAGS="$CFLAGS -fno-thread-jumps"
CFLAGS="$CFLAGS -fno-jump-threads"
;;
esac
@@ -5584,7 +5598,7 @@ exec 6>&1
# report actual input values of CONFIG_FILES etc. instead of their
# values after options handling.
ac_log="
This file was extended by PCRE $as_me 7.2, which was
This file was extended by PCRE $as_me 7.4, which was
generated by GNU Autoconf 2.61. Invocation command line was
CONFIG_FILES = $CONFIG_FILES
@@ -5637,7 +5651,7 @@ Report bugs to <bug-autoconf@gnu.org>."
_ACEOF
cat >>$CONFIG_STATUS <<_ACEOF
ac_cs_version="\\
PCRE config.status 7.2
PCRE config.status 7.4
configured by $0, generated by GNU Autoconf 2.61,
with options \\"`echo "$ac_configure_args" | sed 's/^ //; s/[\\""\`\$]/\\\\&/g'`\\"

47
libpcre/configure.ac
View File

@@ -7,9 +7,9 @@ dnl be defined as -RC2, for example. For real releases, it should be defined
dnl empty.
m4_define(pcre_major, [7])
m4_define(pcre_minor, [2])
m4_define(pcre_minor, [4])
m4_define(pcre_prerelease, [])
m4_define(pcre_date, [2007-06-19])
m4_define(pcre_date, [2007-09-21])
AC_PREREQ(2.57)
AC_INIT(PCRE, pcre_major.pcre_minor[]pcre_prerelease, , pcre)
@@ -110,10 +110,16 @@ AC_ARG_ENABLE(newline-is-any,
ac_pcre_newline=any)
enable_newline="$ac_pcre_newline"
# Handle --enable-bsr-anycrlf
AC_ARG_ENABLE(bsr-anycrlf,
AS_HELP_STRING([--enable-bsr-anycrlf],
[\R matches only CR, LF, CRLF by default]),
, enable_bsr_anycrlf=no)
# Handle --enable-ebcdic
AC_ARG_ENABLE(ebcdic,
AS_HELP_STRING([--enable-ebcdic],
[assume EBCDIC coding rather than ASCII (implies --enable-rebuild-chartables)]),
[assume EBCDIC coding rather than ASCII; use this only in (uncommon) EBCDIC environments; it implies --enable-rebuild-chartables]),
, enable_ebcdic=no)
# Handle --disable-stack-for-recursion
@@ -205,8 +211,12 @@ it to run on SunOS4 and other "close to standard" systems.
If you are going to build PCRE "by hand" on a system without "configure" you
should copy the distributed config.h.generic to config.h, and then set up the
macros the way you need them. Alternatively, you can avoid editing by using -D
on the compiler command line to set the macro values.
macro definitions the way you need them. You must then add -DHAVE_CONFIG_H to
all of your compile commands, so that config.h is included at the start of
every source.
Alternatively, you can avoid editing by using -D on the compiler command line
to set the macro values. In this case, you do not have to set -DHAVE_CONFIG_H.
PCRE uses memmove() if HAVE_MEMMOVE is set to 1; otherwise it uses bcopy() if
HAVE_BCOPY is set to 1. If your system has neither bcopy() nor memmove(), set
@@ -239,7 +249,7 @@ AC_SUBST(pcre_have_ulong_long)
# Checks for library functions.
AC_CHECK_FUNCS(bcopy memmove strerror strtoq strtoll)
AC_CHECK_FUNCS(bcopy memmove strerror strtoq strtoll _strtoi64)
# This facilitates -ansi builds under Linux
dnl AC_DEFINE([_GNU_SOURCE], [], [Enable GNU extensions in glibc])
@@ -275,9 +285,19 @@ fi
AC_DEFINE_UNQUOTED([NEWLINE], [$ac_pcre_newline_value], [
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).])
systems that support it, "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).])
if test "$enable_bsr_anycrlf" = "yes"; then
AC_DEFINE([BSR_ANYCRLF], [], [
By default, the \R escape sequence matches any Unicode line ending
character or sequence of characters. If BSR_ANYCRLF is defined, this is
changed so that backslash-R matches only CR, LF, or CRLF. The build-
time default can be overridden by the user of PCRE at runtime. On
systems that support it, "configure" can be used to override the
default.])
fi
AC_DEFINE_UNQUOTED([LINK_SIZE], [$with_link_size], [
The value of LINK_SIZE determines the number of bytes used to store
@@ -330,11 +350,6 @@ AC_DEFINE([MAX_NAME_COUNT], [10000], [
change it. Care must be taken if it is increased, because it guards
against integer overflow caused by enormously large patterns.])
AC_DEFINE([MAX_DUPLENGTH], [30000], [
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.])
AH_VERBATIM([PCRE_EXP_DEFN], [
/* 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
@@ -354,14 +369,14 @@ if test "$enable_ebcdic" = "yes"; then
"configure", this can be done via --enable-ebcdic.])
fi
dnl Mac OS X on Intel hack to remove thread jumps
dnl Mac OS X on Intel hack to remove jump threads
AC_CANONICAL_HOST
case "$host" in
i386-apple-darwin*)
macosx=yes
AC_DEFINE(MACOSX, [], [Mac OS X on Intel])
CFLAGS="$CFLAGS -fno-thread-jumps"
CFLAGS="$CFLAGS -fno-jump-threads"
;;
esac

13
libpcre/dftables.c
View File

@@ -43,6 +43,12 @@ 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. */
#ifdef WIN32
#include "pcre_winconfig.h"
#else
#include "config.h"
#endif
#include <ctype.h>
#include <stdio.h>
#include <string.h>
@@ -99,12 +105,17 @@ fprintf(f,
"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 following #includes are present because without them gcc 4.x may remove\n"
"the array definition from the final binary if PCRE is built into a static\n"
"library and dead code stripping is activated. This leads to link errors.\n"
"Pulling in the header ensures that the array gets flagged as \"someone\n"
"outside this compilation unit might reference this\" and so it will always\n"
"be supplied to the linker. */\n\n"
"#ifdef WIN32\n"
"#include \"pcre_winconfig.h\"\n"
"#else\n"
"#include \"config.h\"\n"
"#endif\n\n"
"#include \"pcre_internal.h\"\n\n");
fprintf(f,
"const unsigned char _pcre_default_tables[] = {\n\n"

39
libpcre/pcre.h
View File

@@ -42,20 +42,26 @@ POSSIBILITY OF SUCH DAMAGE.
/* The current PCRE version information. */
#define PCRE_MAJOR 7
#define PCRE_MINOR 2
#define PCRE_MINOR 4
#define PCRE_PRERELEASE
#define PCRE_DATE 2007-06-19
#define PCRE_DATE 2007-09-21
/* 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. */
don't change existing definitions of PCRE_EXP_DECL and PCRECPP_EXP_DECL. */
/*
#ifndef PCRE_EXP_DECL
# ifdef _WIN32
# ifndef PCRE_STATIC
# define PCRE_EXP_DECL extern __declspec(dllimport)
#if defined(_WIN32) && !defined(PCRE_STATIC)
# ifndef PCRE_EXP_DECL
# define PCRE_EXP_DECL extern __declspec(dllimport)
# endif
# ifdef __cplusplus
# ifndef PCRECPP_EXP_DECL
# define PCRECPP_EXP_DECL extern __declspec(dllimport)
# endif
# ifndef PCRECPP_EXP_DEFN
# define PCRECPP_EXP_DEFN __declspec(dllimport)
# endif
# endif
#endif
@@ -65,9 +71,18 @@ don't change an existing definition of PCRE_EXP_DECL. */
#ifndef PCRE_EXP_DECL
# ifdef __cplusplus
# define PCRE_EXP_DECL extern "C"
# define PCRE_EXP_DECL extern "C"
# else
# define PCRE_EXP_DECL extern
# define PCRE_EXP_DECL extern
# endif
#endif
#ifdef __cplusplus
# ifndef PCRECPP_EXP_DECL
# define PCRECPP_EXP_DECL extern
# endif
# ifndef PCRECPP_EXP_DEFN
# define PCRECPP_EXP_DEFN
# endif
#endif
@@ -109,6 +124,8 @@ extern "C" {
#define PCRE_NEWLINE_CRLF 0x00300000
#define PCRE_NEWLINE_ANY 0x00400000
#define PCRE_NEWLINE_ANYCRLF 0x00500000
#define PCRE_BSR_ANYCRLF 0x00800000
#define PCRE_BSR_UNICODE 0x01000000
/* Exec-time and get/set-time error codes */
@@ -134,7 +151,7 @@ extern "C" {
#define PCRE_ERROR_DFA_WSSIZE (-19)
#define PCRE_ERROR_DFA_RECURSE (-20)
#define PCRE_ERROR_RECURSIONLIMIT (-21)
#define PCRE_ERROR_NULLWSLIMIT (-22)
#define PCRE_ERROR_NULLWSLIMIT (-22) /* No longer actually used */
#define PCRE_ERROR_BADNEWLINE (-23)
/* Request types for pcre_fullinfo() */
@@ -154,6 +171,7 @@ extern "C" {
#define PCRE_INFO_DEFAULT_TABLES 11
#define PCRE_INFO_OKPARTIAL 12
#define PCRE_INFO_JCHANGED 13
#define PCRE_INFO_HASCRORLF 14
/* Request types for pcre_config(). Do not re-arrange, in order to remain
compatible. */
@@ -166,6 +184,7 @@ compatible. */
#define PCRE_CONFIG_STACKRECURSE 5
#define PCRE_CONFIG_UNICODE_PROPERTIES 6
#define PCRE_CONFIG_MATCH_LIMIT_RECURSION 7
#define PCRE_CONFIG_BSR 8
/* Bit flags for the pcre_extra structure. Do not re-arrange or redefine
these bits, just add new ones on the end, in order to remain compatible. */

39
libpcre/pcre.h.generic
View File

@@ -42,20 +42,26 @@ POSSIBILITY OF SUCH DAMAGE.
/* The current PCRE version information. */
#define PCRE_MAJOR 7
#define PCRE_MINOR 2
#define PCRE_MINOR 4
#define PCRE_PRERELEASE
#define PCRE_DATE 2007-06-19
#define PCRE_DATE 2007-09-21
/* 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. */
don't change existing definitions of PCRE_EXP_DECL and PCRECPP_EXP_DECL. */
/*
#ifndef PCRE_EXP_DECL
# ifdef _WIN32
# ifndef PCRE_STATIC
# define PCRE_EXP_DECL extern __declspec(dllimport)
#if defined(_WIN32) && !defined(PCRE_STATIC)
# ifndef PCRE_EXP_DECL
# define PCRE_EXP_DECL extern __declspec(dllimport)
# endif
# ifdef __cplusplus
# ifndef PCRECPP_EXP_DECL
# define PCRECPP_EXP_DECL extern __declspec(dllimport)
# endif
# ifndef PCRECPP_EXP_DEFN
# define PCRECPP_EXP_DEFN __declspec(dllimport)
# endif
# endif
#endif
@@ -65,9 +71,18 @@ don't change an existing definition of PCRE_EXP_DECL. */
#ifndef PCRE_EXP_DECL
# ifdef __cplusplus
# define PCRE_EXP_DECL extern "C"
# define PCRE_EXP_DECL extern "C"
# else
# define PCRE_EXP_DECL extern
# define PCRE_EXP_DECL extern
# endif
#endif
#ifdef __cplusplus
# ifndef PCRECPP_EXP_DECL
# define PCRECPP_EXP_DECL extern
# endif
# ifndef PCRECPP_EXP_DEFN
# define PCRECPP_EXP_DEFN
# endif
#endif
@@ -109,6 +124,8 @@ extern "C" {
#define PCRE_NEWLINE_CRLF 0x00300000
#define PCRE_NEWLINE_ANY 0x00400000
#define PCRE_NEWLINE_ANYCRLF 0x00500000
#define PCRE_BSR_ANYCRLF 0x00800000
#define PCRE_BSR_UNICODE 0x01000000
/* Exec-time and get/set-time error codes */
@@ -134,7 +151,7 @@ extern "C" {
#define PCRE_ERROR_DFA_WSSIZE (-19)
#define PCRE_ERROR_DFA_RECURSE (-20)
#define PCRE_ERROR_RECURSIONLIMIT (-21)
#define PCRE_ERROR_NULLWSLIMIT (-22)
#define PCRE_ERROR_NULLWSLIMIT (-22) /* No longer actually used */
#define PCRE_ERROR_BADNEWLINE (-23)
/* Request types for pcre_fullinfo() */
@@ -154,6 +171,7 @@ extern "C" {
#define PCRE_INFO_DEFAULT_TABLES 11
#define PCRE_INFO_OKPARTIAL 12
#define PCRE_INFO_JCHANGED 13
#define PCRE_INFO_HASCRORLF 14
/* Request types for pcre_config(). Do not re-arrange, in order to remain
compatible. */
@@ -166,6 +184,7 @@ compatible. */
#define PCRE_CONFIG_STACKRECURSE 5
#define PCRE_CONFIG_UNICODE_PROPERTIES 6
#define PCRE_CONFIG_MATCH_LIMIT_RECURSION 7
#define PCRE_CONFIG_BSR 8
/* Bit flags for the pcre_extra structure. Do not re-arrange or redefine
these bits, just add new ones on the end, in order to remain compatible. */

35
libpcre/pcre.h.in
View File

@@ -49,13 +49,19 @@ POSSIBILITY OF SUCH DAMAGE.
/* 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. */
don't change existing definitions of PCRE_EXP_DECL and PCRECPP_EXP_DECL. */
/*
#ifndef PCRE_EXP_DECL
# ifdef _WIN32
# ifndef PCRE_STATIC
# define PCRE_EXP_DECL extern __declspec(dllimport)
#if defined(_WIN32) && !defined(PCRE_STATIC)
# ifndef PCRE_EXP_DECL
# define PCRE_EXP_DECL extern __declspec(dllimport)
# endif
# ifdef __cplusplus
# ifndef PCRECPP_EXP_DECL
# define PCRECPP_EXP_DECL extern __declspec(dllimport)
# endif
# ifndef PCRECPP_EXP_DEFN
# define PCRECPP_EXP_DEFN __declspec(dllimport)
# endif
# endif
#endif
@@ -65,9 +71,18 @@ don't change an existing definition of PCRE_EXP_DECL. */
#ifndef PCRE_EXP_DECL
# ifdef __cplusplus
# define PCRE_EXP_DECL extern "C"
# define PCRE_EXP_DECL extern "C"
# else
# define PCRE_EXP_DECL extern
# define PCRE_EXP_DECL extern
# endif
#endif
#ifdef __cplusplus
# ifndef PCRECPP_EXP_DECL
# define PCRECPP_EXP_DECL extern
# endif
# ifndef PCRECPP_EXP_DEFN
# define PCRECPP_EXP_DEFN
# endif
#endif
@@ -109,6 +124,8 @@ extern "C" {
#define PCRE_NEWLINE_CRLF 0x00300000
#define PCRE_NEWLINE_ANY 0x00400000
#define PCRE_NEWLINE_ANYCRLF 0x00500000
#define PCRE_BSR_ANYCRLF 0x00800000
#define PCRE_BSR_UNICODE 0x01000000
/* Exec-time and get/set-time error codes */
@@ -134,7 +151,7 @@ extern "C" {
#define PCRE_ERROR_DFA_WSSIZE (-19)
#define PCRE_ERROR_DFA_RECURSE (-20)
#define PCRE_ERROR_RECURSIONLIMIT (-21)
#define PCRE_ERROR_NULLWSLIMIT (-22)
#define PCRE_ERROR_NULLWSLIMIT (-22) /* No longer actually used */
#define PCRE_ERROR_BADNEWLINE (-23)
/* Request types for pcre_fullinfo() */
@@ -154,6 +171,7 @@ extern "C" {
#define PCRE_INFO_DEFAULT_TABLES 11
#define PCRE_INFO_OKPARTIAL 12
#define PCRE_INFO_JCHANGED 13
#define PCRE_INFO_HASCRORLF 14
/* Request types for pcre_config(). Do not re-arrange, in order to remain
compatible. */
@@ -166,6 +184,7 @@ compatible. */
#define PCRE_CONFIG_STACKRECURSE 5
#define PCRE_CONFIG_UNICODE_PROPERTIES 6
#define PCRE_CONFIG_MATCH_LIMIT_RECURSION 7
#define PCRE_CONFIG_BSR 8
/* Bit flags for the pcre_extra structure. Do not re-arrange or redefine
these bits, just add new ones on the end, in order to remain compatible. */

8
libpcre/pcre_chartables.c
View File

@@ -14,12 +14,18 @@ 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
The following #includes are present because without the 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. */
#ifdef WIN32
#include "pcre_winconfig.h"
#else
#include "config.h"
#endif
#include "pcre_internal.h"
const unsigned char _pcre_default_tables[] = {

8
libpcre/pcre_chartables.c.dist
View File

@@ -14,12 +14,18 @@ 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
The following #includes are present because without the 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. */
#ifdef WIN32
#include "pcre_winconfig.h"
#else
#include "config.h"
#endif
#include "pcre_internal.h"
const unsigned char _pcre_default_tables[] = {

665
libpcre/pcre_compile.c
View File

File diff suppressed because it is too large Load Diff

14
libpcre/pcre_config.c
View File

@@ -41,6 +41,12 @@ POSSIBILITY OF SUCH DAMAGE.
/* This module contains the external function pcre_config(). */
#ifdef WIN32
#include "pcre_winconfig.h"
#else
#include "config.h"
#endif
#include "pcre_internal.h"
@@ -83,6 +89,14 @@ switch (what)
*((int *)where) = NEWLINE;
break;
case PCRE_CONFIG_BSR:
#ifdef BSR_ANYCRLF
*((int *)where) = 1;
#else
*((int *)where) = 0;
#endif
break;
case PCRE_CONFIG_LINK_SIZE:
*((int *)where) = LINK_SIZE;
break;

92
libpcre/pcre_dfa_exec.c
View File

@@ -44,6 +44,12 @@ FSM). This is NOT Perl- compatible, but it has advantages in certain
applications. */
#ifdef WIN32
#include "pcre_winconfig.h"
#else
#include "config.h"
#endif
#define NLBLOCK md /* Block containing newline information */
#define PSSTART start_subject /* Field containing processed string start */
#define PSEND end_subject /* Field containing processed string end */
@@ -126,7 +132,9 @@ static uschar coptable[] = {
0, /* CREF */
0, /* RREF */
0, /* DEF */
0, 0 /* BRAZERO, BRAMINZERO */
0, 0, /* BRAZERO, BRAMINZERO */
0, 0, 0, 0, /* PRUNE, SKIP, THEN, COMMIT */
0, 0 /* FAIL, ACCEPT */
};
/* These 2 tables allow for compact code for testing for \D, \d, \S, \s, \W,
@@ -1074,15 +1082,20 @@ for (;;)
int ncount = 0;
switch (c)
{
case 0x000d:
if (ptr + 1 < end_subject && ptr[1] == 0x0a) ncount = 1;
/* Fall through */
case 0x000a:
case 0x000b:
case 0x000c:
case 0x0085:
case 0x2028:
case 0x2029:
if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break;
goto ANYNL01;
case 0x000d:
if (ptr + 1 < end_subject && ptr[1] == 0x0a) ncount = 1;
/* Fall through */
ANYNL01:
case 0x000a:
if (count > 0 && codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSPLUS)
{
active_count--; /* Remove non-match possibility */
@@ -1091,6 +1104,7 @@ for (;;)
count++;
ADD_NEW_DATA(-state_offset, count, ncount);
break;
default:
break;
}
@@ -1307,15 +1321,20 @@ for (;;)
int ncount = 0;
switch (c)
{
case 0x000d:
if (ptr + 1 < end_subject && ptr[1] == 0x0a) ncount = 1;
/* Fall through */
case 0x000a:
case 0x000b:
case 0x000c:
case 0x0085:
case 0x2028:
case 0x2029:
if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break;
goto ANYNL02;
case 0x000d:
if (ptr + 1 < end_subject && ptr[1] == 0x0a) ncount = 1;
/* Fall through */
ANYNL02:
case 0x000a:
if (codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSSTAR ||
codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSQUERY)
{
@@ -1324,6 +1343,7 @@ for (;;)
}
ADD_NEW_DATA(-(state_offset + count), 0, ncount);
break;
default:
break;
}
@@ -1539,15 +1559,20 @@ for (;;)
int ncount = 0;
switch (c)
{
case 0x000d:
if (ptr + 1 < end_subject && ptr[1] == 0x0a) ncount = 1;
/* Fall through */
case 0x000a:
case 0x000b:
case 0x000c:
case 0x0085:
case 0x2028:
case 0x2029:
if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break;
goto ANYNL03;
case 0x000d:
if (ptr + 1 < end_subject && ptr[1] == 0x0a) ncount = 1;
/* Fall through */
ANYNL03:
case 0x000a:
if (codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSUPTO)
{
active_count--; /* Remove non-match possibility */
@@ -1558,6 +1583,7 @@ for (;;)
else
{ ADD_NEW_DATA(-state_offset, count, ncount); }
break;
default:
break;
}
@@ -1738,14 +1764,17 @@ for (;;)
case OP_ANYNL:
if (clen > 0) switch(c)
{
case 0x000a:
case 0x000b:
case 0x000c:
case 0x0085:
case 0x2028:
case 0x2029:
if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break;
case 0x000a:
ADD_NEW(state_offset + 1, 0);
break;
case 0x000d:
if (ptr + 1 < end_subject && ptr[1] == 0x0a)
{
@@ -2568,6 +2597,18 @@ md->end_subject = end_subject;
md->moptions = options;
md->poptions = re->options;
/* If the BSR option is not set at match time, copy what was set
at compile time. */
if ((md->moptions & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) == 0)
{
if ((re->options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) != 0)
md->moptions |= re->options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE);
#ifdef BSR_ANYCRLF
else md->moptions |= PCRE_BSR_ANYCRLF;
#endif
}
/* Handle different types of newline. The three bits give eight cases. If
nothing is set at run time, whatever was used at compile time applies. */
@@ -2638,7 +2679,7 @@ if (md->tables == NULL) md->tables = _pcre_default_tables;
used in a loop when finding where to start. */
lcc = md->tables + lcc_offset;
startline = (re->options & PCRE_STARTLINE) != 0;
startline = (re->flags & PCRE_STARTLINE) != 0;
firstline = (re->options & PCRE_FIRSTLINE) != 0;
/* Set up the first character to match, if available. The first_byte value is
@@ -2649,7 +2690,7 @@ studied, there may be a bitmap of possible first characters. */
if (!anchored)
{
if ((re->options & PCRE_FIRSTSET) != 0)
if ((re->flags & PCRE_FIRSTSET) != 0)
{
first_byte = re->first_byte & 255;
if ((first_byte_caseless = ((re->first_byte & REQ_CASELESS) != 0)) == TRUE)
@@ -2666,7 +2707,7 @@ if (!anchored)
/* For anchored or unanchored matches, there may be a "last known required
character" set. */
if ((re->options & PCRE_REQCHSET) != 0)
if ((re->flags & PCRE_REQCHSET) != 0)
{
req_byte = re->req_byte & 255;
req_byte_caseless = (re->req_byte & REQ_CASELESS) != 0;
@@ -2836,16 +2877,17 @@ for (;;)
}
if (current_subject > end_subject) break;
/* If we have just passed a CR and the newline option is CRLF or ANY or
ANYCRLF, and we are now at a LF, advance the match position by one more
character. */
/* If we have just passed a CR and we are now at a LF, and the pattern does
not contain any explicit matches for \r or \n, and the newline option is CRLF
or ANY or ANYCRLF, advance the match position by one more character. */
if (current_subject[-1] == '\r' &&
(md->nltype == NLTYPE_ANY ||
md->nltype == NLTYPE_ANYCRLF ||
md->nllen == 2) &&
current_subject < end_subject &&
*current_subject == '\n')
current_subject < end_subject &&
*current_subject == '\n' &&
(re->flags & PCRE_HASCRORLF) == 0 &&
(md->nltype == NLTYPE_ANY ||
md->nltype == NLTYPE_ANYCRLF ||
md->nllen == 2))
current_subject++;
} /* "Bumpalong" loop */

363
libpcre/pcre_exec.c
View File

@@ -42,6 +42,12 @@ POSSIBILITY OF SUCH DAMAGE.
pattern matching using an NFA algorithm, trying to mimic Perl as closely as
possible. There are also some static supporting functions. */
#ifdef WIN32
#include "pcre_winconfig.h"
#else
#include "config.h"
#endif
#define NLBLOCK md /* Block containing newline information */
#define PSSTART start_subject /* Field containing processed string start */
#define PSEND end_subject /* Field containing processed string end */
@@ -53,16 +59,10 @@ possible. There are also some static supporting functions. */
#undef min
#undef max
/* The chain of eptrblocks for tail recursions uses memory in stack workspace,
obtained at top level, the size of which is defined by EPTR_WORK_SIZE. */
#define EPTR_WORK_SIZE (1000)
/* Flag bits for the match() function */
#define match_condassert 0x01 /* Called to check a condition assertion */
#define match_cbegroup 0x02 /* Could-be-empty unlimited repeat group */
#define match_tail_recursed 0x04 /* Tail recursive call */
/* Non-error returns from the match() function. Error returns are externally
defined PCRE_ERROR_xxx codes, which are all negative. */
@@ -70,6 +70,14 @@ defined PCRE_ERROR_xxx codes, which are all negative. */
#define MATCH_MATCH 1
#define MATCH_NOMATCH 0
/* Special internal returns from the match() function. Make them sufficiently
negative to avoid the external error codes. */
#define MATCH_COMMIT (-999)
#define MATCH_PRUNE (-998)
#define MATCH_SKIP (-997)
#define MATCH_THEN (-996)
/* Maximum number of ints of offset to save on the stack for recursive calls.
If the offset vector is bigger, malloc is used. This should be a multiple of 3,
because the offset vector is always a multiple of 3 long. */
@@ -205,15 +213,15 @@ variable instead of being passed in the frame.
****************************************************************************
***************************************************************************/
/* Numbers for RMATCH calls */
/* Numbers for RMATCH calls. When this list is changed, the code at HEAP_RETURN
below must be updated in sync. */
enum { RM1=1, RM2, RM3, RM4, RM5, RM6, RM7, RM8, RM9, RM10,
RM11, RM12, RM13, RM14, RM15, RM16, RM17, RM18, RM19, RM20,
RM21, RM22, RM23, RM24, RM25, RM26, RM27, RM28, RM29, RM30,
RM31, RM32, RM33, RM34, RM35, RM36, RM37, RM38, RM39, RM40,
RM41, RM42, RM43, RM44, RM45, RM46, RM47 };
RM41, RM42, RM43, RM44, RM45, RM46, RM47, RM48, RM49, RM50,
RM51, RM52, RM53, RM54 };
/* These versions of the macros use the stack, as normal. There are debugging
versions and production versions. Note that the "rw" argument of RMATCH isn't
@@ -384,7 +392,6 @@ Arguments:
match_condassert - this is an assertion condition
match_cbegroup - this is the start of an unlimited repeat
group that can match an empty string
match_tail_recursed - this is a tail_recursed group
rdepth the recursion depth
Returns: MATCH_MATCH if matched ) these values are >= 0
@@ -586,22 +593,16 @@ original_ims = ims; /* Save for resetting on ')' */
string, the match_cbegroup flag is set. When this is the case, add the current
subject pointer to the chain of such remembered pointers, to be checked when we
hit the closing ket, in order to break infinite loops that match no characters.
When match() is called in other circumstances, don't add to the chain. If this
is a tail recursion, use a block from the workspace, as the one on the stack is
already used. */
When match() is called in other circumstances, don't add to the chain. The
match_cbegroup flag must NOT be used with tail recursion, because the memory
block that is used is on the stack, so a new one may be required for each
match(). */
if ((flags & match_cbegroup) != 0)
{
eptrblock *p;
if ((flags & match_tail_recursed) != 0)
{
if (md->eptrn >= EPTR_WORK_SIZE) RRETURN(PCRE_ERROR_NULLWSLIMIT);
p = md->eptrchain + md->eptrn++;
}
else p = &newptrb;
p->epb_saved_eptr = eptr;
p->epb_prev = eptrb;
eptrb = p;
newptrb.epb_saved_eptr = eptr;
newptrb.epb_prev = eptrb;
eptrb = &newptrb;
}
/* Now start processing the opcodes. */
@@ -621,6 +622,34 @@ for (;;)
switch(op)
{
case OP_FAIL:
RRETURN(MATCH_NOMATCH);
case OP_PRUNE:
RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md,
ims, eptrb, flags, RM51);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
RRETURN(MATCH_PRUNE);
case OP_COMMIT:
RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md,
ims, eptrb, flags, RM52);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
RRETURN(MATCH_COMMIT);
case OP_SKIP:
RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md,
ims, eptrb, flags, RM53);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
md->start_match_ptr = eptr; /* Pass back current position */
RRETURN(MATCH_SKIP);
case OP_THEN:
RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md,
ims, eptrb, flags, RM54);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
RRETURN(MATCH_THEN);
/* Handle a capturing bracket. If there is space in the offset vector, save
the current subject position in the working slot at the top of the vector.
We mustn't change the current values of the data slot, because they may be
@@ -662,7 +691,7 @@ for (;;)
{
RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md,
ims, eptrb, flags, RM1);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc);
md->capture_last = save_capture_last;
ecode += GET(ecode, 1);
}
@@ -677,15 +706,22 @@ for (;;)
RRETURN(MATCH_NOMATCH);
}
/* Insufficient room for saving captured contents. Treat as a non-capturing
bracket. */
/* FALL THROUGH ... Insufficient room for saving captured contents. Treat
as a non-capturing bracket. */
/* VVVVVVVVVVVVVVVVVVVVVVVVV */
/* VVVVVVVVVVVVVVVVVVVVVVVVV */
DPRINTF(("insufficient capture room: treat as non-capturing\n"));
/* VVVVVVVVVVVVVVVVVVVVVVVVV */
/* VVVVVVVVVVVVVVVVVVVVVVVVV */
/* Non-capturing bracket. Loop for all the alternatives. When we get to the
final alternative within the brackets, we would return the result of a
recursive call to match() whatever happened. We can reduce stack usage by
turning this into a tail recursion. */
turning this into a tail recursion, except in the case when match_cbegroup
is set.*/
case OP_BRA:
case OP_SBRA:
@@ -693,12 +729,20 @@ for (;;)
flags = (op >= OP_SBRA)? match_cbegroup : 0;
for (;;)
{
if (ecode[GET(ecode, 1)] != OP_ALT)
if (ecode[GET(ecode, 1)] != OP_ALT) /* Final alternative */
{
ecode += _pcre_OP_lengths[*ecode];
flags |= match_tail_recursed;
DPRINTF(("bracket 0 tail recursion\n"));
goto TAIL_RECURSE;
if (flags == 0) /* Not a possibly empty group */
{
ecode += _pcre_OP_lengths[*ecode];
DPRINTF(("bracket 0 tail recursion\n"));
goto TAIL_RECURSE;
}
/* Possibly empty group; can't use tail recursion. */
RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, ims,
eptrb, flags, RM48);
RRETURN(rrc);
}
/* For non-final alternatives, continue the loop for a NOMATCH result;
@@ -706,7 +750,7 @@ for (;;)
RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, ims,
eptrb, flags, RM2);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc);
ecode += GET(ecode, 1);
}
/* Control never reaches here. */
@@ -754,7 +798,7 @@ for (;;)
ecode += 1 + LINK_SIZE + GET(ecode, LINK_SIZE + 2);
while (*ecode == OP_ALT) ecode += GET(ecode, 1);
}
else if (rrc != MATCH_NOMATCH)
else if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN)
{
RRETURN(rrc); /* Need braces because of following else */
}
@@ -766,25 +810,36 @@ for (;;)
}
/* We are now at the branch that is to be obeyed. As there is only one,
we can use tail recursion to avoid using another stack frame. If the second
alternative doesn't exist, we can just plough on. */
we can use tail recursion to avoid using another stack frame, except when
match_cbegroup is required for an unlimited repeat of a possibly empty
group. If the second alternative doesn't exist, we can just plough on. */
if (condition || *ecode == OP_ALT)
{
ecode += 1 + LINK_SIZE;
flags = match_tail_recursed | ((op == OP_SCOND)? match_cbegroup : 0);
goto TAIL_RECURSE;
if (op == OP_SCOND) /* Possibly empty group */
{
RMATCH(eptr, ecode, offset_top, md, ims, eptrb, match_cbegroup, RM49);
RRETURN(rrc);
}
else /* Group must match something */
{
flags = 0;
goto TAIL_RECURSE;
}
}
else
else /* Condition false & no 2nd alternative */
{
ecode += 1 + LINK_SIZE;
}
break;
/* End of the pattern. If we are in a top-level recursion, we should
restore the offsets appropriately and continue from after the call. */
/* End of the pattern, either real or forced. If we are in a top-level
recursion, we should restore the offsets appropriately and continue from
after the call. */
case OP_ACCEPT:
case OP_END:
if (md->recursive != NULL && md->recursive->group_num == 0)
{
@@ -805,7 +860,7 @@ for (;;)
if (md->notempty && eptr == mstart) RRETURN(MATCH_NOMATCH);
md->end_match_ptr = eptr; /* Record where we ended */
md->end_offset_top = offset_top; /* and how many extracts were taken */
md->start_match_ptr = mstart; /* and the start (\K can modify) */
md->start_match_ptr = mstart; /* and the start (\K can modify) */
RRETURN(MATCH_MATCH);
/* Change option settings */
@@ -829,7 +884,7 @@ for (;;)
RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, 0,
RM4);
if (rrc == MATCH_MATCH) break;
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc);
ecode += GET(ecode, 1);
}
while (*ecode == OP_ALT);
@@ -856,7 +911,7 @@ for (;;)
RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, 0,
RM5);
if (rrc == MATCH_MATCH) RRETURN(MATCH_NOMATCH);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc);
ecode += GET(ecode,1);
}
while (*ecode == OP_ALT);
@@ -880,7 +935,7 @@ for (;;)
{
eptr--;
if (eptr < md->start_subject) RRETURN(MATCH_NOMATCH);
BACKCHAR(eptr)
BACKCHAR(eptr);
}
}
else
@@ -993,7 +1048,7 @@ for (;;)
(pcre_free)(new_recursive.offset_save);
RRETURN(MATCH_MATCH);
}
else if (rrc != MATCH_NOMATCH)
else if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN)
{
DPRINTF(("Recursion gave error %d\n", rrc));
RRETURN(rrc);
@@ -1027,10 +1082,9 @@ for (;;)
do
{
RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims,
eptrb, 0, RM7);
RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, 0, RM7);
if (rrc == MATCH_MATCH) break;
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc);
ecode += GET(ecode,1);
}
while (*ecode == OP_ALT);
@@ -1073,11 +1127,10 @@ for (;;)
if (*ecode == OP_KETRMIN)
{
RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, 0,
RM8);
RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, 0, RM8);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
ecode = prev;
flags = match_tail_recursed;
flags = 0;
goto TAIL_RECURSE;
}
else /* OP_KETRMAX */
@@ -1085,7 +1138,7 @@ for (;;)
RMATCH(eptr, prev, offset_top, md, ims, eptrb, match_cbegroup, RM9);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
ecode += 1 + LINK_SIZE;
flags = match_tail_recursed;
flags = 0;
goto TAIL_RECURSE;
}
/* Control never gets here */
@@ -1216,17 +1269,21 @@ for (;;)
/* The repeating kets try the rest of the pattern or restart from the
preceding bracket, in the appropriate order. In the second case, we can use
tail recursion to avoid using another stack frame. */
tail recursion to avoid using another stack frame, unless we have an
unlimited repeat of a group that can match an empty string. */
flags = (*prev >= OP_SBRA)? match_cbegroup : 0;
if (*ecode == OP_KETRMIN)
{
RMATCH(eptr, ecode + 1+LINK_SIZE, offset_top, md, ims, eptrb, 0,
RM12);
RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, 0, RM12);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (flags != 0) /* Could match an empty string */
{
RMATCH(eptr, prev, offset_top, md, ims, eptrb, flags, RM50);
RRETURN(rrc);
}
ecode = prev;
flags |= match_tail_recursed;
goto TAIL_RECURSE;
}
else /* OP_KETRMAX */
@@ -1234,7 +1291,7 @@ for (;;)
RMATCH(eptr, prev, offset_top, md, ims, eptrb, flags, RM13);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
ecode += 1 + LINK_SIZE;
flags = match_tail_recursed;
flags = 0;
goto TAIL_RECURSE;
}
/* Control never gets here */
@@ -1471,12 +1528,16 @@ for (;;)
case 0x000d:
if (eptr < md->end_subject && *eptr == 0x0a) eptr++;
break;
case 0x000a:
break;
case 0x000b:
case 0x000c:
case 0x0085:
case 0x2028:
case 0x2029:
if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH);
break;
}
ecode++;
@@ -2033,7 +2094,7 @@ for (;;)
RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM21);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (eptr-- == pp) break; /* Stop if tried at original pos */
BACKCHAR(eptr)
if (utf8) BACKCHAR(eptr);
}
RRETURN(MATCH_NOMATCH);
}
@@ -2899,12 +2960,16 @@ for (;;)
case 0x000d:
if (eptr < md->end_subject && *eptr == 0x0a) eptr++;
break;
case 0x000a:
break;
case 0x000b:
case 0x000c:
case 0x0085:
case 0x2028:
case 0x2029:
if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH);
break;
}
}
@@ -3038,9 +3103,9 @@ for (;;)
for (i = 1; i <= min; i++)
{
if (eptr >= md->end_subject ||
(*eptr < 128 && (md->ctypes[*eptr++] & ctype_space) != 0))
(*eptr < 128 && (md->ctypes[*eptr] & ctype_space) != 0))
RRETURN(MATCH_NOMATCH);
while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++;
while (++eptr < md->end_subject && (*eptr & 0xc0) == 0x80);
}
break;
@@ -3058,9 +3123,9 @@ for (;;)
for (i = 1; i <= min; i++)
{
if (eptr >= md->end_subject ||
(*eptr < 128 && (md->ctypes[*eptr++] & ctype_word) != 0))
(*eptr < 128 && (md->ctypes[*eptr] & ctype_word) != 0))
RRETURN(MATCH_NOMATCH);
while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++;
while (++eptr < md->end_subject && (*eptr & 0xc0) == 0x80);
}
break;
@@ -3117,9 +3182,12 @@ for (;;)
if (eptr < md->end_subject && *eptr == 0x0a) eptr++;
break;
case 0x000a:
break;
case 0x000b:
case 0x000c:
case 0x0085:
if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH);
break;
}
}
@@ -3371,11 +3439,14 @@ for (;;)
if (eptr < md->end_subject && *eptr == 0x0a) eptr++;
break;
case 0x000a:
break;
case 0x000b:
case 0x000c:
case 0x0085:
case 0x2028:
case 0x2029:
if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH);
break;
}
break;
@@ -3527,10 +3598,14 @@ for (;;)
case 0x000d:
if (eptr < md->end_subject && *eptr == 0x0a) eptr++;
break;
case 0x000a:
break;
case 0x000b:
case 0x000c:
case 0x0085:
if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH);
break;
}
break;
@@ -3702,7 +3777,7 @@ for (;;)
RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM44);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (eptr-- == pp) break; /* Stop if tried at original pos */
BACKCHAR(eptr);
if (utf8) BACKCHAR(eptr);
}
}
@@ -3741,9 +3816,9 @@ for (;;)
for (;;) /* Move back over one extended */
{
int len = 1;
BACKCHAR(eptr);
if (!utf8) c = *eptr; else
{
BACKCHAR(eptr);
GETCHARLEN(c, eptr, len);
}
prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);
@@ -3764,11 +3839,6 @@ for (;;)
switch(ctype)
{
case OP_ANY:
/* Special code is required for UTF8, but when the maximum is
unlimited we don't need it, so we repeat the non-UTF8 code. This is
probably worth it, because .* is quite a common idiom. */
if (max < INT_MAX)
{
if ((ims & PCRE_DOTALL) == 0)
@@ -3801,15 +3871,12 @@ for (;;)
{
if (eptr >= md->end_subject || IS_NEWLINE(eptr)) break;
eptr++;
while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++;
}
break;
}
else
{
c = max - min;
if (c > (unsigned int)(md->end_subject - eptr))
c = md->end_subject - eptr;
eptr += c;
eptr = md->end_subject;
}
}
break;
@@ -3836,8 +3903,10 @@ for (;;)
}
else
{
if (c != 0x000a && c != 0x000b && c != 0x000c &&
c != 0x0085 && c != 0x2028 && c != 0x2029)
if (c != 0x000a &&
(md->bsr_anycrlf ||
(c != 0x000b && c != 0x000c &&
c != 0x0085 && c != 0x2028 && c != 0x2029)))
break;
eptr += len;
}
@@ -3990,7 +4059,7 @@ for (;;)
}
}
else
#endif
#endif /* SUPPORT_UTF8 */
/* Not UTF-8 mode */
{
@@ -4027,7 +4096,9 @@ for (;;)
}
else
{
if (c != 0x000a && c != 0x000b && c != 0x000c && c != 0x0085)
if (c != 0x000a &&
(md->bsr_anycrlf ||
(c != 0x000b && c != 0x000c && c != 0x0085)))
break;
eptr++;
}
@@ -4177,11 +4248,17 @@ HEAP_RETURN:
switch (frame->Xwhere)
{
LBL( 1) LBL( 2) LBL( 3) LBL( 4) LBL( 5) LBL( 6) LBL( 7) LBL( 8)
LBL( 9) LBL(10) LBL(11) LBL(12) LBL(13) LBL(14) LBL(15) LBL(16)
LBL(17) LBL(18) LBL(19) LBL(20) LBL(21) LBL(22) LBL(23) LBL(24)
LBL(25) LBL(26) LBL(27) LBL(28) LBL(29) LBL(30) LBL(31) LBL(32)
LBL(33) LBL(34) LBL(35) LBL(36) LBL(37) LBL(38) LBL(39) LBL(40)
LBL(41) LBL(42) LBL(43) LBL(44) LBL(45) LBL(46) LBL(47)
LBL( 9) LBL(10) LBL(11) LBL(12) LBL(13) LBL(14) LBL(15) LBL(17)
LBL(19) LBL(24) LBL(25) LBL(26) LBL(27) LBL(29) LBL(31) LBL(33)
LBL(35) LBL(43) LBL(47) LBL(48) LBL(49) LBL(50) LBL(51) LBL(52)
LBL(53) LBL(54)
#ifdef SUPPORT_UTF8
LBL(16) LBL(18) LBL(20) LBL(21) LBL(22) LBL(23) LBL(28) LBL(30)
LBL(32) LBL(34) LBL(42) LBL(46)
#ifdef SUPPORT_UCP
LBL(36) LBL(37) LBL(38) LBL(39) LBL(40) LBL(41) LBL(44) LBL(45)
#endif /* SUPPORT_UCP */
#endif /* SUPPORT_UTF8 */
default:
DPRINTF(("jump error in pcre match: label %d non-existent\n", frame->Xwhere));
return PCRE_ERROR_INTERNAL;
@@ -4298,7 +4375,6 @@ const uschar *start_bits = NULL;
USPTR start_match = (USPTR)subject + start_offset;
USPTR end_subject;
USPTR req_byte_ptr = start_match - 1;
eptrblock eptrchain[EPTR_WORK_SIZE];
pcre_study_data internal_study;
const pcre_study_data *study;
@@ -4361,7 +4437,7 @@ if (re->magic_number != MAGIC_NUMBER)
/* Set up other data */
anchored = ((re->options | options) & PCRE_ANCHORED) != 0;
startline = (re->options & PCRE_STARTLINE) != 0;
startline = (re->flags & PCRE_STARTLINE) != 0;
firstline = (re->options & PCRE_FIRSTLINE) != 0;
/* The code starts after the real_pcre block and the capture name table. */
@@ -4384,16 +4460,41 @@ md->partial = (options & PCRE_PARTIAL) != 0;
md->hitend = FALSE;
md->recursive = NULL; /* No recursion at top level */
md->eptrchain = eptrchain; /* Make workspace generally available */
md->lcc = tables + lcc_offset;
md->ctypes = tables + ctypes_offset;
/* Handle different \R options. */
switch (options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE))
{
case 0:
if ((re->options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) != 0)
md->bsr_anycrlf = (re->options & PCRE_BSR_ANYCRLF) != 0;
else
#ifdef BSR_ANYCRLF
md->bsr_anycrlf = TRUE;
#else
md->bsr_anycrlf = FALSE;
#endif
break;
case PCRE_BSR_ANYCRLF:
md->bsr_anycrlf = TRUE;
break;
case PCRE_BSR_UNICODE:
md->bsr_anycrlf = FALSE;
break;
default: return PCRE_ERROR_BADNEWLINE;
}
/* Handle different types of newline. The three bits give eight cases. If
nothing is set at run time, whatever was used at compile time applies. */
switch ((((options & PCRE_NEWLINE_BITS) == 0)? re->options : (pcre_uint32)options) &
PCRE_NEWLINE_BITS)
switch ((((options & PCRE_NEWLINE_BITS) == 0)? re->options :
(pcre_uint32)options) & PCRE_NEWLINE_BITS)
{
case 0: newline = NEWLINE; break; /* Compile-time default */
case PCRE_NEWLINE_CR: newline = '\r'; break;
@@ -4432,7 +4533,7 @@ else
/* Partial matching is supported only for a restricted set of regexes at the
moment. */
if (md->partial && (re->options & PCRE_NOPARTIAL) != 0)
if (md->partial && (re->flags & PCRE_NOPARTIAL) != 0)
return PCRE_ERROR_BADPARTIAL;
/* Check a UTF-8 string if required. Unfortunately there's no way of passing
@@ -4509,7 +4610,7 @@ studied, there may be a bitmap of possible first characters. */
if (!anchored)
{
if ((re->options & PCRE_FIRSTSET) != 0)
if ((re->flags & PCRE_FIRSTSET) != 0)
{
first_byte = re->first_byte & 255;
if ((first_byte_caseless = ((re->first_byte & REQ_CASELESS) != 0)) == TRUE)
@@ -4524,7 +4625,7 @@ if (!anchored)
/* For anchored or unanchored matches, there may be a "last known required
character" set. */
if ((re->options & PCRE_REQCHSET) != 0)
if ((re->flags & PCRE_REQCHSET) != 0)
{
req_byte = re->req_byte & 255;
req_byte_caseless = (re->req_byte & REQ_CASELESS) != 0;
@@ -4540,6 +4641,7 @@ the loop runs just once. */
for(;;)
{
USPTR save_end_subject = end_subject;
USPTR new_start_match;
/* Reset the maximum number of extractions we might see. */
@@ -4680,15 +4782,48 @@ for(;;)
/* OK, we can now run the match. */
md->start_match_ptr = start_match; /* Insurance */
md->start_match_ptr = start_match;
md->match_call_count = 0;
md->eptrn = 0; /* Next free eptrchain slot */
rc = match(start_match, md->start_code, start_match, 2, md,
ims, NULL, 0, 0);
rc = match(start_match, md->start_code, start_match, 2, md, ims, NULL, 0, 0);
/* Any return other than MATCH_NOMATCH breaks the loop. */
switch(rc)
{
/* NOMATCH and PRUNE advance by one character. THEN at this level acts
exactly like PRUNE. */
if (rc != MATCH_NOMATCH) break;
case MATCH_NOMATCH:
case MATCH_PRUNE:
case MATCH_THEN:
new_start_match = start_match + 1;
#ifdef SUPPORT_UTF8
if (utf8)
while(new_start_match < end_subject && (*new_start_match & 0xc0) == 0x80)
new_start_match++;
#endif
break;
/* SKIP passes back the next starting point explicitly. */
case MATCH_SKIP:
new_start_match = md->start_match_ptr;
break;
/* COMMIT disables the bumpalong, but otherwise behaves as NOMATCH. */
case MATCH_COMMIT:
rc = MATCH_NOMATCH;
goto ENDLOOP;
/* Any other return is some kind of error. */
default:
goto ENDLOOP;
}
/* Control reaches here for the various types of "no match at this point"
result. Reset the code to MATCH_NOMATCH for subsequent checking. */
rc = MATCH_NOMATCH;
/* If PCRE_FIRSTLINE is set, the match must happen before or at the first
newline in the subject (though it may continue over the newline). Therefore,
@@ -4696,30 +4831,26 @@ for(;;)
if (firstline && IS_NEWLINE(start_match)) break;
/* Advance the match position by one character. */
/* Advance to new matching position */
start_match++;
#ifdef SUPPORT_UTF8
if (utf8)
while(start_match < end_subject && (*start_match & 0xc0) == 0x80)
start_match++;
#endif
start_match = new_start_match;
/* Break the loop if the pattern is anchored or if we have passed the end of
the subject. */
if (anchored || start_match > end_subject) break;
/* If we have just passed a CR and the newline option is CRLF or ANY or
ANYCRLF, and we are now at a LF, advance the match position by one more
character. */
/* If we have just passed a CR and we are now at a LF, and the pattern does
not contain any explicit matches for \r or \n, and the newline option is CRLF
or ANY or ANYCRLF, advance the match position by one more character. */
if (start_match[-1] == '\r' &&
(md->nltype == NLTYPE_ANY ||
md->nltype == NLTYPE_ANYCRLF ||
md->nllen == 2) &&
start_match < end_subject &&
*start_match == '\n')
start_match < end_subject &&
*start_match == '\n' &&
(re->flags & PCRE_HASCRORLF) == 0 &&
(md->nltype == NLTYPE_ANY ||
md->nltype == NLTYPE_ANYCRLF ||
md->nllen == 2))
start_match++;
} /* End of for(;;) "bumpalong" loop */
@@ -4729,7 +4860,7 @@ for(;;)
/* We reach here when rc is not MATCH_NOMATCH, or if one of the stopping
conditions is true:
(1) The pattern is anchored;
(1) The pattern is anchored or the match was failed by (*COMMIT);
(2) We are past the end of the subject;
@@ -4744,6 +4875,8 @@ processing, copy those that we can. In this case there need not be overflow if
certain parts of the pattern were not used, even though there are more
capturing parentheses than vector slots. */
ENDLOOP:
if (rc == MATCH_MATCH)
{
if (using_temporary_offsets)

20
libpcre/pcre_fullinfo.c
View File

@@ -42,6 +42,12 @@ POSSIBILITY OF SUCH DAMAGE.
information about a compiled pattern. */
#ifdef WIN32
#include "pcre_winconfig.h"
#else
#include "config.h"
#endif
#include "pcre_internal.h"
@@ -106,8 +112,8 @@ switch (what)
case PCRE_INFO_FIRSTBYTE:
*((int *)where) =
((re->options & PCRE_FIRSTSET) != 0)? re->first_byte :
((re->options & PCRE_STARTLINE) != 0)? -1 : -2;
((re->flags & PCRE_FIRSTSET) != 0)? re->first_byte :
((re->flags & PCRE_STARTLINE) != 0)? -1 : -2;
break;
/* Make sure we pass back the pointer to the bit vector in the external
@@ -121,7 +127,7 @@ switch (what)
case PCRE_INFO_LASTLITERAL:
*((int *)where) =
((re->options & PCRE_REQCHSET) != 0)? re->req_byte : -1;
((re->flags & PCRE_REQCHSET) != 0)? re->req_byte : -1;
break;
case PCRE_INFO_NAMEENTRYSIZE:
@@ -141,11 +147,15 @@ switch (what)
break;
case PCRE_INFO_OKPARTIAL:
*((int *)where) = (re->options & PCRE_NOPARTIAL) == 0;
*((int *)where) = (re->flags & PCRE_NOPARTIAL) == 0;
break;
case PCRE_INFO_JCHANGED:
*((int *)where) = (re->options & PCRE_JCHANGED) != 0;
*((int *)where) = (re->flags & PCRE_JCHANGED) != 0;
break;
case PCRE_INFO_HASCRORLF:
*((int *)where) = (re->flags & PCRE_HASCRORLF) != 0;
break;
default: return PCRE_ERROR_BADOPTION;

8
libpcre/pcre_get.c
View File

@@ -43,6 +43,12 @@ from the subject string after a regex match has succeeded. The original idea
for these functions came from Scott Wimer. */
#ifdef WIN32
#include "pcre_winconfig.h"
#else
#include "config.h"
#endif
#include "pcre_internal.h"
@@ -185,7 +191,7 @@ const real_pcre *re = (const real_pcre *)code;
int entrysize;
char *first, *last;
uschar *entry;
if ((re->options & (PCRE_DUPNAMES | PCRE_JCHANGED)) == 0)
if ((re->options & PCRE_DUPNAMES) == 0 && (re->flags & PCRE_JCHANGED) == 0)
return pcre_get_stringnumber(code, stringname);
entrysize = pcre_get_stringtable_entries(code, stringname, &first, &last);
if (entrysize <= 0) return entrysize;

6
libpcre/pcre_globals.c
View File

@@ -46,6 +46,12 @@ 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). */
#ifdef WIN32
#include "pcre_winconfig.h"
#else
#include "config.h"
#endif
#include "pcre_internal.h"
#ifndef VPCOMPAT

10
libpcre/pcre_info.c
View File

@@ -43,6 +43,12 @@ information about a compiled pattern. However, use of this function is now
deprecated, as it has been superseded by pcre_fullinfo(). */
#ifdef WIN32
#include "pcre_winconfig.h"
#else
#include "config.h"
#endif
#include "pcre_internal.h"
@@ -81,8 +87,8 @@ if (re->magic_number != MAGIC_NUMBER)
}
if (optptr != NULL) *optptr = (int)(re->options & PUBLIC_OPTIONS);
if (first_byte != NULL)
*first_byte = ((re->options & PCRE_FIRSTSET) != 0)? re->first_byte :
((re->options & PCRE_STARTLINE) != 0)? -1 : -2;
*first_byte = ((re->flags & PCRE_FIRSTSET) != 0)? re->first_byte :
((re->flags & PCRE_STARTLINE) != 0)? -1 : -2;
return re->top_bracket;
}

98
libpcre/pcre_internal.h
View File

@@ -67,14 +67,6 @@ be absolutely sure we get our version. */
#endif
/* Get the definitions provided by running "configure" */
#ifdef WIN32
#include "pcre_winconfig.h"
#else
#include "config.h"
#endif
/* Standard C headers plus the external interface definition. The only time
setjmp and stdarg are used is when NO_RECURSE is set. */
@@ -117,7 +109,7 @@ PCRE_EXP_DATA_DEFN only if they are not already set. */
#ifndef PCRE_EXP_DECL
# ifdef _WIN32
/* COMMENTED OUT AS IT'S COMPILED STATICALLY
# ifdef DLL_EXPORT
# ifndef PCRE_STATIC
# define PCRE_EXP_DECL extern __declspec(dllexport)
# define PCRE_EXP_DEFN __declspec(dllexport)
# define PCRE_EXP_DATA_DEFN __declspec(dllexport)
@@ -129,7 +121,6 @@ PCRE_EXP_DATA_DEFN only if they are not already set. */
/*
# endif
*/
#
# else
# ifdef __cplusplus
# define PCRE_EXP_DECL extern "C"
@@ -371,7 +362,9 @@ capturing parenthesis numbers in back references. */
/* When UTF-8 encoding is being used, a character is no longer just a single
byte. The macros for character handling generate simple sequences when used in
byte-mode, and more complicated ones for UTF-8 characters. */
byte-mode, and more complicated ones for UTF-8 characters. BACKCHAR should
never be called in byte mode. To make sure it can never even appear when UTF-8
support is omitted, we don't even define it. */
#ifndef SUPPORT_UTF8
#define GETCHAR(c, eptr) c = *eptr;
@@ -379,7 +372,7 @@ byte-mode, and more complicated ones for UTF-8 characters. */
#define GETCHARINC(c, eptr) c = *eptr++;
#define GETCHARINCTEST(c, eptr) c = *eptr++;
#define GETCHARLEN(c, eptr, len) c = *eptr;
#define BACKCHAR(eptr)
/* #define BACKCHAR(eptr) */
#else /* SUPPORT_UTF8 */
@@ -472,9 +465,10 @@ if there are extra bytes. This is called when we know we are in UTF-8 mode. */
}
/* If the pointer is not at the start of a character, move it back until
it is. Called only in UTF-8 mode. */
it is. This is called only in UTF-8 mode - we don't put a test within the macro
because almost all calls are already within a block of UTF-8 only code. */
#define BACKCHAR(eptr) while((*eptr & 0xc0) == 0x80) eptr--;
#define BACKCHAR(eptr) while((*eptr & 0xc0) == 0x80) eptr--
#endif
@@ -491,17 +485,16 @@ Standard C system should have one. */
#define PCRE_IMS (PCRE_CASELESS|PCRE_MULTILINE|PCRE_DOTALL)
/* Private options flags start at the most significant end of the four bytes.
The public options defined in pcre.h start at the least significant end. Make
sure they don't overlap! The bits are getting a bit scarce now -- when we run
out, there is a dummy word in the structure that could be used for the private
bits. */
/* Private flags containing information about the compiled regex. They used to
live at the top end of the options word, but that got almost full, so now they
are in a 16-bit flags word. */
#define PCRE_NOPARTIAL 0x80000000 /* can't use partial with this regex */
#define PCRE_FIRSTSET 0x40000000 /* first_byte is set */
#define PCRE_REQCHSET 0x20000000 /* req_byte is set */
#define PCRE_STARTLINE 0x10000000 /* start after \n for multiline */
#define PCRE_JCHANGED 0x08000000 /* j option changes within regex */
#define PCRE_NOPARTIAL 0x0001 /* can't use partial with this regex */
#define PCRE_FIRSTSET 0x0002 /* first_byte is set */
#define PCRE_REQCHSET 0x0004 /* req_byte is set */
#define PCRE_STARTLINE 0x0008 /* start after \n for multiline */
#define PCRE_JCHANGED 0x0010 /* j option used in regex */
#define PCRE_HASCRORLF 0x0020 /* explicit \r or \n in pattern */
/* Options for the "extra" block produced by pcre_study(). */
@@ -517,15 +510,16 @@ time, run time, or study time, respectively. */
(PCRE_CASELESS|PCRE_EXTENDED|PCRE_ANCHORED|PCRE_MULTILINE| \
PCRE_DOTALL|PCRE_DOLLAR_ENDONLY|PCRE_EXTRA|PCRE_UNGREEDY|PCRE_UTF8| \
PCRE_NO_AUTO_CAPTURE|PCRE_NO_UTF8_CHECK|PCRE_AUTO_CALLOUT|PCRE_FIRSTLINE| \
PCRE_DUPNAMES|PCRE_NEWLINE_BITS)
PCRE_DUPNAMES|PCRE_NEWLINE_BITS|PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)
#define PUBLIC_EXEC_OPTIONS \
(PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK| \
PCRE_PARTIAL|PCRE_NEWLINE_BITS)
PCRE_PARTIAL|PCRE_NEWLINE_BITS|PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)
#define PUBLIC_DFA_EXEC_OPTIONS \
(PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK| \
PCRE_PARTIAL|PCRE_DFA_SHORTEST|PCRE_DFA_RESTART|PCRE_NEWLINE_BITS)
PCRE_PARTIAL|PCRE_DFA_SHORTEST|PCRE_DFA_RESTART|PCRE_NEWLINE_BITS| \
PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)
#define PUBLIC_STUDY_OPTIONS 0 /* None defined */
@@ -618,14 +612,9 @@ enum { ESC_A = 1, ESC_G, ESC_K, ESC_B, ESC_b, ESC_D, ESC_d, ESC_S, ESC_s,
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
that extract substrings. Starting from 1 (i.e. after OP_END), the values up to
/* Opcode table: Starting from 1 (i.e. after OP_END), the values up to
OP_EOD must correspond in order to the list of escapes immediately above.
To keep stored, compiled patterns compatible, new opcodes should be added
immediately before OP_BRA, where (since release 7.0) a gap is left for this
purpose.
*** NOTE NOTE NOTE *** Whenever this list is updated, the two macro definitions
that follow must also be updated to match. There is also a table called
"coptable" in pcre_dfa_exec.c that must be updated. */
@@ -752,7 +741,7 @@ enum {
as there's a test for >= ONCE for a subpattern that isn't an assertion. */
OP_ONCE, /* 92 Atomic group */
OP_BRA, /* 83 Start of non-capturing bracket */
OP_BRA, /* 93 Start of non-capturing bracket */
OP_CBRA, /* 94 Start of capturing bracket */
OP_COND, /* 95 Conditional group */
@@ -768,7 +757,19 @@ enum {
OP_DEF, /* 101 The DEFINE condition */
OP_BRAZERO, /* 102 These two must remain together and in this */
OP_BRAMINZERO /* 103 order. */
OP_BRAMINZERO, /* 103 order. */
/* These are backtracking control verbs */
OP_PRUNE, /* 104 */
OP_SKIP, /* 105 */
OP_THEN, /* 106 */
OP_COMMIT, /* 107 */
/* These are forced failure and success verbs */
OP_FAIL, /* 108 */
OP_ACCEPT /* 109 */
};
@@ -791,8 +792,9 @@ for debugging. The macro is referenced only in pcre_printint.c. */
"class", "nclass", "xclass", "Ref", "Recurse", "Callout", \
"Alt", "Ket", "KetRmax", "KetRmin", "Assert", "Assert not", \
"AssertB", "AssertB not", "Reverse", \
"Once", "Bra 0", "Bra", "Cond", "SBra 0", "SBra", "SCond", \
"Cond ref", "Cond rec", "Cond def", "Brazero", "Braminzero"
"Once", "Bra", "CBra", "Cond", "SBra", "SCBra", "SCond", \
"Cond ref", "Cond rec", "Cond def", "Brazero", "Braminzero", \
"*PRUNE", "*SKIP", "*THEN", "*COMMIT", "*FAIL", "*ACCEPT"
/* This macro defines the length of fixed length operations in the compiled
@@ -856,6 +858,8 @@ in UTF-8 mode. The code that uses this table must know about such things. */
3, /* RREF */ \
1, /* DEF */ \
1, 1, /* BRAZERO, BRAMINZERO */ \
1, 1, 1, 1, /* PRUNE, SKIP, THEN, COMMIT, */ \
1, 1 /* FAIL, ACCEPT */
/* A magic value for OP_RREF to indicate the "any recursion" condition. */
@@ -870,7 +874,8 @@ 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, ERR58 };
ERR50, ERR51, ERR52, ERR53, ERR54, ERR55, ERR56, ERR57, ERR58, ERR59,
ERR60, ERR61 };
/* 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
@@ -892,9 +897,9 @@ NOTE NOTE NOTE:
typedef struct real_pcre {
pcre_uint32 magic_number;
pcre_uint32 size; /* Total that was malloced */
pcre_uint32 options;
pcre_uint32 dummy1; /* For future use, maybe */
pcre_uint32 options; /* Public options */
pcre_uint16 flags; /* Private flags */
pcre_uint16 dummy1; /* For future use */
pcre_uint16 top_bracket;
pcre_uint16 top_backref;
pcre_uint16 first_byte;
@@ -937,8 +942,9 @@ typedef struct compile_data {
int top_backref; /* Maximum back reference */
unsigned int backref_map; /* Bitmap of low back refs */
int external_options; /* External (initial) options */
int external_flags; /* External flag bits to be set */
int req_varyopt; /* "After variable item" flag for reqbyte */
BOOL nopartial; /* Set TRUE if partial won't work */
BOOL had_accept; /* (*ACCEPT) encountered */
int nltype; /* Newline type */
int nllen; /* Newline string length */
uschar nl[4]; /* Newline string when fixed length */
@@ -997,6 +1003,7 @@ typedef struct match_data {
BOOL notempty; /* Empty string match not wanted */
BOOL partial; /* PARTIAL flag */
BOOL hitend; /* Hit the end of the subject at some point */
BOOL bsr_anycrlf; /* \R is just any CRLF, not full Unicode */
const uschar *start_code; /* For use when recursing */
USPTR start_subject; /* Start of the subject string */
USPTR end_subject; /* End of the subject string */
@@ -1061,10 +1068,12 @@ total length. */
#define tables_length (ctypes_offset + 256)
/* Layout of the UCP type table that translates property names into types and
codes. */
codes. Each entry used to point directly to a name, but to reduce the number of
relocations in shared libraries, it now has an offset into a single string
instead. */
typedef struct {
const char *name;
pcre_uint16 name_offset;
pcre_uint16 type;
pcre_uint16 value;
} ucp_type_table;
@@ -1082,6 +1091,7 @@ extern const uschar _pcre_utf8_table4[];
extern const int _pcre_utf8_table1_size;
extern const char _pcre_utt_names[];
extern const ucp_type_table _pcre_utt[];
extern const int _pcre_utt_size;

7
libpcre/pcre_maketables.c
View File

@@ -45,7 +45,12 @@ compilation of dftables.c, in which case the macro DFTABLES is defined. */
#ifndef DFTABLES
#include "pcre_internal.h"
# ifdef WIN32
# include "pcre_winconfig.h"
# else
# include "config.h"
# endif
# include "pcre_internal.h"
#endif

10
libpcre/pcre_newline.c
View File

@@ -47,6 +47,12 @@ and NLTYPE_ANY. The full list of Unicode newline characters is taken from
http://unicode.org/unicode/reports/tr18/. */
#ifdef WIN32
#include "pcre_winconfig.h"
#else
#include "config.h"
#endif
#include "pcre_internal.h"
@@ -124,12 +130,16 @@ _pcre_was_newline(const uschar *ptr, int type, const uschar *startptr,
{
int c;
ptr--;
#ifdef SUPPORT_UTF8
if (utf8)
{
BACKCHAR(ptr);
GETCHAR(c, ptr);
}
else c = *ptr;
#else /* no UTF-8 support */
c = *ptr;
#endif /* SUPPORT_UTF8 */
if (type == NLTYPE_ANYCRLF) switch(c)
{

5
libpcre/pcre_ord2utf8.c
View File

@@ -41,6 +41,11 @@ POSSIBILITY OF SUCH DAMAGE.
/* This file contains a private PCRE function that converts an ordinal
character value into a UTF8 string. */
#ifdef WIN32
#include "pcre_winconfig.h"
#else
#include "config.h"
#endif
#include "pcre_internal.h"

7
libpcre/pcre_refcount.c
View File

@@ -43,6 +43,13 @@ auxiliary function that can be used to maintain a reference count in a compiled
pattern data block. This might be helpful in applications where the block is
shared by different users. */
#ifdef WIN32
#include "pcre_winconfig.h"
#else
#include "config.h"
#endif
#include "pcre_internal.h"

9
libpcre/pcre_study.c
View File

@@ -42,6 +42,12 @@ POSSIBILITY OF SUCH DAMAGE.
supporting functions. */
#ifdef WIN32
#include "pcre_winconfig.h"
#else
#include "config.h"
#endif
#include "pcre_internal.h"
@@ -523,7 +529,8 @@ code = (uschar *)re + re->name_table_offset +
a multiline pattern that matches only at "line starts", no further processing
at present. */
if ((re->options & (PCRE_ANCHORED|PCRE_FIRSTSET|PCRE_STARTLINE)) != 0)
if ((re->options & PCRE_ANCHORED) != 0 ||
(re->flags & (PCRE_FIRSTSET|PCRE_STARTLINE)) != 0)
return NULL;
/* Set the character tables in the block that is passed around */

333
libpcre/pcre_tables.c
View File

@@ -44,6 +44,12 @@ uses macros to change their names from _pcre_xxx to xxxx, thereby avoiding name
clashes with the library. */
#ifdef WIN32
#include "pcre_winconfig.h"
#else
#include "config.h"
#endif
#include "pcre_internal.h"
@@ -83,115 +89,228 @@ const uschar _pcre_utf8_table4[] = {
2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 };
/* This table translates Unicode property names into type and code values. It
is searched by binary chop, so must be in collating sequence of name. */
/* The pcre_utt[] table below translates Unicode property names into type and
code values. It is searched by binary chop, so must be in collating sequence of
name. Originally, the table contained pointers to the name strings in the first
field of each entry. However, that leads to a large number of relocations when
a shared library is dynamically loaded. A significant reduction is made by
putting all the names into a single, large string and then using offsets in the
table itself. Maintenance is more error-prone, but frequent changes to this
data is unlikely. */
const char _pcre_utt_names[] =
"Any\0"
"Arabic\0"
"Armenian\0"
"Balinese\0"
"Bengali\0"
"Bopomofo\0"
"Braille\0"
"Buginese\0"
"Buhid\0"
"C\0"
"Canadian_Aboriginal\0"
"Cc\0"
"Cf\0"
"Cherokee\0"
"Cn\0"
"Co\0"
"Common\0"
"Coptic\0"
"Cs\0"
"Cuneiform\0"
"Cypriot\0"
"Cyrillic\0"
"Deseret\0"
"Devanagari\0"
"Ethiopic\0"
"Georgian\0"
"Glagolitic\0"
"Gothic\0"
"Greek\0"
"Gujarati\0"
"Gurmukhi\0"
"Han\0"
"Hangul\0"
"Hanunoo\0"
"Hebrew\0"
"Hiragana\0"
"Inherited\0"
"Kannada\0"
"Katakana\0"
"Kharoshthi\0"
"Khmer\0"
"L\0"
"L&\0"
"Lao\0"
"Latin\0"
"Limbu\0"
"Linear_B\0"
"Ll\0"
"Lm\0"
"Lo\0"
"Lt\0"
"Lu\0"
"M\0"
"Malayalam\0"
"Mc\0"
"Me\0"
"Mn\0"
"Mongolian\0"
"Myanmar\0"
"N\0"
"Nd\0"
"New_Tai_Lue\0"
"Nko\0"
"Nl\0"
"No\0"
"Ogham\0"
"Old_Italic\0"
"Old_Persian\0"
"Oriya\0"
"Osmanya\0"
"P\0"
"Pc\0"
"Pd\0"
"Pe\0"
"Pf\0"
"Phags_Pa\0"
"Phoenician\0"
"Pi\0"
"Po\0"
"Ps\0"
"Runic\0"
"S\0"
"Sc\0"
"Shavian\0"
"Sinhala\0"
"Sk\0"
"Sm\0"
"So\0"
"Syloti_Nagri\0"
"Syriac\0"
"Tagalog\0"
"Tagbanwa\0"
"Tai_Le\0"
"Tamil\0"
"Telugu\0"
"Thaana\0"
"Thai\0"
"Tibetan\0"
"Tifinagh\0"
"Ugaritic\0"
"Yi\0"
"Z\0"
"Zl\0"
"Zp\0"
"Zs\0";
const ucp_type_table _pcre_utt[] = {
{ "Any", PT_ANY, 0 },
{ "Arabic", PT_SC, ucp_Arabic },
{ "Armenian", PT_SC, ucp_Armenian },
{ "Balinese", PT_SC, ucp_Balinese },
{ "Bengali", PT_SC, ucp_Bengali },
{ "Bopomofo", PT_SC, ucp_Bopomofo },
{ "Braille", PT_SC, ucp_Braille },
{ "Buginese", PT_SC, ucp_Buginese },
{ "Buhid", PT_SC, ucp_Buhid },
{ "C", PT_GC, ucp_C },
{ "Canadian_Aboriginal", PT_SC, ucp_Canadian_Aboriginal },
{ "Cc", PT_PC, ucp_Cc },
{ "Cf", PT_PC, ucp_Cf },
{ "Cherokee", PT_SC, ucp_Cherokee },
{ "Cn", PT_PC, ucp_Cn },
{ "Co", PT_PC, ucp_Co },
{ "Common", PT_SC, ucp_Common },
{ "Coptic", PT_SC, ucp_Coptic },
{ "Cs", PT_PC, ucp_Cs },
{ "Cuneiform", PT_SC, ucp_Cuneiform },
{ "Cypriot", PT_SC, ucp_Cypriot },
{ "Cyrillic", PT_SC, ucp_Cyrillic },
{ "Deseret", PT_SC, ucp_Deseret },
{ "Devanagari", PT_SC, ucp_Devanagari },
{ "Ethiopic", PT_SC, ucp_Ethiopic },
{ "Georgian", PT_SC, ucp_Georgian },
{ "Glagolitic", PT_SC, ucp_Glagolitic },
{ "Gothic", PT_SC, ucp_Gothic },
{ "Greek", PT_SC, ucp_Greek },
{ "Gujarati", PT_SC, ucp_Gujarati },
{ "Gurmukhi", PT_SC, ucp_Gurmukhi },
{ "Han", PT_SC, ucp_Han },
{ "Hangul", PT_SC, ucp_Hangul },
{ "Hanunoo", PT_SC, ucp_Hanunoo },
{ "Hebrew", PT_SC, ucp_Hebrew },
{ "Hiragana", PT_SC, ucp_Hiragana },
{ "Inherited", PT_SC, ucp_Inherited },
{ "Kannada", PT_SC, ucp_Kannada },
{ "Katakana", PT_SC, ucp_Katakana },
{ "Kharoshthi", PT_SC, ucp_Kharoshthi },
{ "Khmer", PT_SC, ucp_Khmer },
{ "L", PT_GC, ucp_L },
{ "L&", PT_LAMP, 0 },
{ "Lao", PT_SC, ucp_Lao },
{ "Latin", PT_SC, ucp_Latin },
{ "Limbu", PT_SC, ucp_Limbu },
{ "Linear_B", PT_SC, ucp_Linear_B },
{ "Ll", PT_PC, ucp_Ll },
{ "Lm", PT_PC, ucp_Lm },
{ "Lo", PT_PC, ucp_Lo },
{ "Lt", PT_PC, ucp_Lt },
{ "Lu", PT_PC, ucp_Lu },
{ "M", PT_GC, ucp_M },
{ "Malayalam", PT_SC, ucp_Malayalam },
{ "Mc", PT_PC, ucp_Mc },
{ "Me", PT_PC, ucp_Me },
{ "Mn", PT_PC, ucp_Mn },
{ "Mongolian", PT_SC, ucp_Mongolian },
{ "Myanmar", PT_SC, ucp_Myanmar },
{ "N", PT_GC, ucp_N },
{ "Nd", PT_PC, ucp_Nd },
{ "New_Tai_Lue", PT_SC, ucp_New_Tai_Lue },
{ "Nko", PT_SC, ucp_Nko },
{ "Nl", PT_PC, ucp_Nl },
{ "No", PT_PC, ucp_No },
{ "Ogham", PT_SC, ucp_Ogham },
{ "Old_Italic", PT_SC, ucp_Old_Italic },
{ "Old_Persian", PT_SC, ucp_Old_Persian },
{ "Oriya", PT_SC, ucp_Oriya },
{ "Osmanya", PT_SC, ucp_Osmanya },
{ "P", PT_GC, ucp_P },
{ "Pc", PT_PC, ucp_Pc },
{ "Pd", PT_PC, ucp_Pd },
{ "Pe", PT_PC, ucp_Pe },
{ "Pf", PT_PC, ucp_Pf },
{ "Phags_Pa", PT_SC, ucp_Phags_Pa },
{ "Phoenician", PT_SC, ucp_Phoenician },
{ "Pi", PT_PC, ucp_Pi },
{ "Po", PT_PC, ucp_Po },
{ "Ps", PT_PC, ucp_Ps },
{ "Runic", PT_SC, ucp_Runic },
{ "S", PT_GC, ucp_S },
{ "Sc", PT_PC, ucp_Sc },
{ "Shavian", PT_SC, ucp_Shavian },
{ "Sinhala", PT_SC, ucp_Sinhala },
{ "Sk", PT_PC, ucp_Sk },
{ "Sm", PT_PC, ucp_Sm },
{ "So", PT_PC, ucp_So },
{ "Syloti_Nagri", PT_SC, ucp_Syloti_Nagri },
{ "Syriac", PT_SC, ucp_Syriac },
{ "Tagalog", PT_SC, ucp_Tagalog },
{ "Tagbanwa", PT_SC, ucp_Tagbanwa },
{ "Tai_Le", PT_SC, ucp_Tai_Le },
{ "Tamil", PT_SC, ucp_Tamil },
{ "Telugu", PT_SC, ucp_Telugu },
{ "Thaana", PT_SC, ucp_Thaana },
{ "Thai", PT_SC, ucp_Thai },
{ "Tibetan", PT_SC, ucp_Tibetan },
{ "Tifinagh", PT_SC, ucp_Tifinagh },
{ "Ugaritic", PT_SC, ucp_Ugaritic },
{ "Yi", PT_SC, ucp_Yi },
{ "Z", PT_GC, ucp_Z },
{ "Zl", PT_PC, ucp_Zl },
{ "Zp", PT_PC, ucp_Zp },
{ "Zs", PT_PC, ucp_Zs }
{ 0, PT_ANY, 0 },
{ 4, PT_SC, ucp_Arabic },
{ 11, PT_SC, ucp_Armenian },
{ 20, PT_SC, ucp_Balinese },
{ 29, PT_SC, ucp_Bengali },
{ 37, PT_SC, ucp_Bopomofo },
{ 46, PT_SC, ucp_Braille },
{ 54, PT_SC, ucp_Buginese },
{ 63, PT_SC, ucp_Buhid },
{ 69, PT_GC, ucp_C },
{ 71, PT_SC, ucp_Canadian_Aboriginal },
{ 91, PT_PC, ucp_Cc },
{ 94, PT_PC, ucp_Cf },
{ 97, PT_SC, ucp_Cherokee },
{ 106, PT_PC, ucp_Cn },
{ 109, PT_PC, ucp_Co },
{ 112, PT_SC, ucp_Common },
{ 119, PT_SC, ucp_Coptic },
{ 126, PT_PC, ucp_Cs },
{ 129, PT_SC, ucp_Cuneiform },
{ 139, PT_SC, ucp_Cypriot },
{ 147, PT_SC, ucp_Cyrillic },
{ 156, PT_SC, ucp_Deseret },
{ 164, PT_SC, ucp_Devanagari },
{ 175, PT_SC, ucp_Ethiopic },
{ 184, PT_SC, ucp_Georgian },
{ 193, PT_SC, ucp_Glagolitic },
{ 204, PT_SC, ucp_Gothic },
{ 211, PT_SC, ucp_Greek },
{ 217, PT_SC, ucp_Gujarati },
{ 226, PT_SC, ucp_Gurmukhi },
{ 235, PT_SC, ucp_Han },
{ 239, PT_SC, ucp_Hangul },
{ 246, PT_SC, ucp_Hanunoo },
{ 254, PT_SC, ucp_Hebrew },
{ 261, PT_SC, ucp_Hiragana },
{ 270, PT_SC, ucp_Inherited },
{ 280, PT_SC, ucp_Kannada },
{ 288, PT_SC, ucp_Katakana },
{ 297, PT_SC, ucp_Kharoshthi },
{ 308, PT_SC, ucp_Khmer },
{ 314, PT_GC, ucp_L },
{ 316, PT_LAMP, 0 },
{ 319, PT_SC, ucp_Lao },
{ 323, PT_SC, ucp_Latin },
{ 329, PT_SC, ucp_Limbu },
{ 335, PT_SC, ucp_Linear_B },
{ 344, PT_PC, ucp_Ll },
{ 347, PT_PC, ucp_Lm },
{ 350, PT_PC, ucp_Lo },
{ 353, PT_PC, ucp_Lt },
{ 356, PT_PC, ucp_Lu },
{ 359, PT_GC, ucp_M },
{ 361, PT_SC, ucp_Malayalam },
{ 371, PT_PC, ucp_Mc },
{ 374, PT_PC, ucp_Me },
{ 377, PT_PC, ucp_Mn },
{ 380, PT_SC, ucp_Mongolian },
{ 390, PT_SC, ucp_Myanmar },
{ 398, PT_GC, ucp_N },
{ 400, PT_PC, ucp_Nd },
{ 403, PT_SC, ucp_New_Tai_Lue },
{ 415, PT_SC, ucp_Nko },
{ 419, PT_PC, ucp_Nl },
{ 422, PT_PC, ucp_No },
{ 425, PT_SC, ucp_Ogham },
{ 431, PT_SC, ucp_Old_Italic },
{ 442, PT_SC, ucp_Old_Persian },
{ 454, PT_SC, ucp_Oriya },
{ 460, PT_SC, ucp_Osmanya },
{ 468, PT_GC, ucp_P },
{ 470, PT_PC, ucp_Pc },
{ 473, PT_PC, ucp_Pd },
{ 476, PT_PC, ucp_Pe },
{ 479, PT_PC, ucp_Pf },
{ 482, PT_SC, ucp_Phags_Pa },
{ 491, PT_SC, ucp_Phoenician },
{ 502, PT_PC, ucp_Pi },
{ 505, PT_PC, ucp_Po },
{ 508, PT_PC, ucp_Ps },
{ 511, PT_SC, ucp_Runic },
{ 517, PT_GC, ucp_S },
{ 519, PT_PC, ucp_Sc },
{ 522, PT_SC, ucp_Shavian },
{ 530, PT_SC, ucp_Sinhala },
{ 538, PT_PC, ucp_Sk },
{ 541, PT_PC, ucp_Sm },
{ 544, PT_PC, ucp_So },
{ 547, PT_SC, ucp_Syloti_Nagri },
{ 560, PT_SC, ucp_Syriac },
{ 567, PT_SC, ucp_Tagalog },
{ 575, PT_SC, ucp_Tagbanwa },
{ 584, PT_SC, ucp_Tai_Le },
{ 591, PT_SC, ucp_Tamil },
{ 597, PT_SC, ucp_Telugu },
{ 604, PT_SC, ucp_Thaana },
{ 611, PT_SC, ucp_Thai },
{ 616, PT_SC, ucp_Tibetan },
{ 624, PT_SC, ucp_Tifinagh },
{ 633, PT_SC, ucp_Ugaritic },
{ 642, PT_SC, ucp_Yi },
{ 645, PT_GC, ucp_Z },
{ 647, PT_PC, ucp_Zl },
{ 650, PT_PC, ucp_Zp },
{ 653, PT_PC, ucp_Zs }
};
const int _pcre_utt_size = sizeof(_pcre_utt)/sizeof(ucp_type_table);

7
libpcre/pcre_try_flipped.c
View File

@@ -43,6 +43,12 @@ see if it was compiled with the opposite endianness. If so, it uses an
auxiliary local function to flip the appropriate bytes. */
#ifdef WIN32
#include "pcre_winconfig.h"
#else
#include "config.h"
#endif
#include "pcre_internal.h"
@@ -104,6 +110,7 @@ if (byteflip(re->magic_number, sizeof(re->magic_number)) != MAGIC_NUMBER)
*internal_re = *re; /* To copy other fields */
internal_re->size = byteflip(re->size, sizeof(re->size));
internal_re->options = byteflip(re->options, sizeof(re->options));
internal_re->flags = (pcre_uint16)byteflip(re->flags, sizeof(re->flags));
internal_re->top_bracket =
(pcre_uint16)byteflip(re->top_bracket, sizeof(re->top_bracket));
internal_re->top_backref =

6
libpcre/pcre_ucp_searchfuncs.c
View File

@@ -41,6 +41,12 @@ POSSIBILITY OF SUCH DAMAGE.
/* This module contains code for searching the table of Unicode character
properties. */
#ifdef WIN32
#include "pcre_winconfig.h"
#else
#include "config.h"
#endif
#include "pcre_internal.h"
#include "ucp.h" /* Category definitions */

48
libpcre/pcre_valid_utf8.c
View File

@@ -42,6 +42,12 @@ POSSIBILITY OF SUCH DAMAGE.
strings. */
#ifdef WIN32
#include "pcre_winconfig.h"
#else
#include "config.h"
#endif
#include "pcre_internal.h"
@@ -55,6 +61,13 @@ that subsequent code can assume it is dealing with a valid string. The check
can be turned off for maximum performance, but the consequences of supplying
an invalid string are then undefined.
Originally, this function checked according to RFC 2279, allowing for values in
the range 0 to 0x7fffffff, up to 6 bytes long, but ensuring that they were in
the canonical format. Once somebody had pointed out RFC 3629 to me (it
obsoletes 2279), additional restrictions were applies. The values are now
limited to be between 0 and 0x0010ffff, no more than 4 bytes long, and the
subrange 0xd000 to 0xdfff is excluded.
Arguments:
string points to the string
length length of string, or -1 if the string is zero-terminated
@@ -81,31 +94,48 @@ for (p = string; length-- > 0; p++)
register int c = *p;
if (c < 128) continue;
if (c < 0xc0) return p - string;
ab = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */
if (length < ab) return p - string;
ab = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */
if (length < ab || ab > 3) return p - string;
length -= ab;
/* Check top bits in the second byte */
if ((*(++p) & 0xc0) != 0x80) return p - string;
/* Check for overlong sequences for each different length */
/* Check for overlong sequences for each different length, and for the
excluded range 0xd000 to 0xdfff. */
switch (ab)
{
/* Check for xx00 000x */
/* Check for xx00 000x (overlong sequence) */
case 1:
if ((c & 0x3e) == 0) return p - string;
continue; /* We know there aren't any more bytes to check */
/* Check for 1110 0000, xx0x xxxx */
/* Check for 1110 0000, xx0x xxxx (overlong sequence) or
1110 1101, 1010 xxxx (0xd000 - 0xdfff) */
case 2:
if (c == 0xe0 && (*p & 0x20) == 0) return p - string;
if ((c == 0xe0 && (*p & 0x20) == 0) ||
(c == 0xed && *p >= 0xa0))
return p - string;
break;
/* Check for 1111 0000, xx00 xxxx */
/* Check for 1111 0000, xx00 xxxx (overlong sequence) or
greater than 0x0010ffff (f4 8f bf bf) */
case 3:
if (c == 0xf0 && (*p & 0x30) == 0) return p - string;
if ((c == 0xf0 && (*p & 0x30) == 0) ||
(c > 0xf4 ) ||
(c == 0xf4 && *p > 0x8f))
return p - string;
break;
#if 0
/* These cases can no longer occur, as we restrict to a maximum of four
bytes nowadays. Leave the code here in case we ever want to add an option
for longer sequences. */
/* Check for 1111 1000, xx00 0xxx */
case 4:
if (c == 0xf8 && (*p & 0x38) == 0) return p - string;
@@ -116,6 +146,8 @@ for (p = string; length-- > 0; p++)
if (c == 0xfe || c == 0xff ||
(c == 0xfc && (*p & 0x3c) == 0)) return p - string;
break;
#endif
}
/* Check for valid bytes after the 2nd, if any; all must start 10 */

6
libpcre/pcre_version.c
View File

@@ -42,6 +42,12 @@ POSSIBILITY OF SUCH DAMAGE.
string that identifies the PCRE version that is in use. */
#ifdef WIN32
#include "pcre_winconfig.h"
#else
#include "config.h"
#endif
#include "pcre_internal.h"

6
libpcre/pcre_xclass.c
View File

@@ -43,6 +43,12 @@ class (one that contains characters whose values are > 255). It is used by both
pcre_exec() and pcre_def_exec(). */
#ifdef WIN32
#include "pcre_winconfig.h"
#else
#include "config.h"
#endif
#include "pcre_internal.h"

23
libpcre/pcreposix.c
View File

@@ -42,10 +42,26 @@ POSSIBILITY OF SUCH DAMAGE.
functions. */
#ifdef WIN32
#include "pcre_winconfig.h"
#else
#include "config.h"
#endif
/* Ensure that the PCREPOSIX_EXP_xxx macros are set appropriately for
compiling these functions. This must come before including pcreposix.h, where
they are set for an application (using these functions) if they have not
previously been set. */
#if defined(_WIN32) && !defined(PCRE_STATIC)
# define PCREPOSIX_EXP_DECL extern __declspec(dllexport)
# define PCREPOSIX_EXP_DEFN __declspec(dllexport)
#endif
#include "pcre.h"
#include "pcre_internal.h"
#include "pcreposix.h"
#include "stdlib.h"
/* Table to translate PCRE compile time error codes into POSIX error codes. */
@@ -109,7 +125,8 @@ static const int eint[] = {
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 /* (?+ or (?- must be followed by a non-zero number */
REG_BADPAT, /* (?+ or (?- must be followed by a non-zero number */
REG_BADPAT /* number is too big */
};
/* Table of texts corresponding to POSIX error codes */

11
libpcre/pcreposix.h
View File

@@ -107,14 +107,13 @@ typedef struct {
/* 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. */
export settings are needed, and are set in pcreposix.c before including this
file. */
/*
#ifdef _WIN32
# ifndef PCREPOSIX_STATIC
# define PCREPOSIX_EXP_DECL extern __declspec(dllimport)
# define PCREPOSIX_EXP_DEFN __declspec(dllimport)
# endif
#if defined(_WIN32) && !defined(PCRE_STATIC) && !defined(PCREPOSIX_EXP_DECL)
# define PCREPOSIX_EXP_DECL extern __declspec(dllimport)
# define PCREPOSIX_EXP_DEFN __declspec(dllimport)
#endif
*/