Upgrading libpcre from 7.4 to 7.6. Tested on Linux and Windows XP.

CHANGELOG

@@ -77,6 +77,8 @@ o Fixed a man page bug related to our DocBook to Nroff translation
   uses the ".nse" string which was being confused with the Nroff
   no-space mode command. [Fyodor]
 
+o Upgraded the shipped LibPCRE from version 7.4 to 7.6. [Kris]
+
 o The Zenmap man page is now installed on Unix when "make install" is
   run.  This was supposed to work before, but didn't. [Kris]
 

libpcre/AUTHORS

@@ -8,7 +8,7 @@ Email domain:     cam.ac.uk
 University of Cambridge Computing Service,
 Cambridge, England.
 
-Copyright (c) 1997-2007 University of Cambridge
+Copyright (c) 1997-2008 University of Cambridge
 All rights reserved
 
 
@@ -17,7 +17,7 @@ THE C++ WRAPPER LIBRARY
 
 Written by:       Google Inc.
 
-Copyright (c) 2007 Google Inc
+Copyright (c) 2007-2008 Google Inc
 All rights reserved
 
 ####

libpcre/LICENCE

@@ -22,7 +22,7 @@ Email domain:     cam.ac.uk
 University of Cambridge Computing Service,
 Cambridge, England.
 
-Copyright (c) 1997-2007 University of Cambridge
+Copyright (c) 1997-2008 University of Cambridge
 All rights reserved.
 
 
@@ -31,7 +31,7 @@ THE C++ WRAPPER FUNCTIONS
 
 Contributed by:   Google Inc.
 
-Copyright (c) 2007, Google Inc.
+Copyright (c) 2007-2008, Google Inc.
 All rights reserved.
 
 

libpcre/Makefile.in

@@ -45,7 +45,7 @@ DIST_COMMON = README $(am__configure_deps) $(include_HEADERS) \
 	$(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
+	$(top_srcdir)/configure AUTHORS COPYING ChangeLog INSTALL NEWS
 ACLOCAL_M4 = $(top_srcdir)/aclocal.m4
 am__aclocal_m4_deps = $(top_srcdir)/configure.ac
 am__configure_deps = $(am__aclocal_m4_deps) $(CONFIGURE_DEPENDENCIES) \
@@ -271,15 +271,15 @@ $(srcdir)/Makefile.in:  $(srcdir)/Makefile.am  $(am__configure_deps)
 	@for dep in $?; do \
 	  case '$(am__configure_deps)' in \
 	    *$$dep*) \
-	      echo ' cd $(srcdir) && $(AUTOMAKE) --foreign '; \
+	      echo ' cd $(srcdir) && $(AUTOMAKE) --gnu '; \
-	      cd $(srcdir) && $(AUTOMAKE) --foreign  \
+	      cd $(srcdir) && $(AUTOMAKE) --gnu  \
 		&& exit 0; \
 	      exit 1;; \
 	  esac; \
 	done; \
-	echo ' cd $(top_srcdir) && $(AUTOMAKE) --foreign  Makefile'; \
+	echo ' cd $(top_srcdir) && $(AUTOMAKE) --gnu  Makefile'; \
 	cd $(top_srcdir) && \
-	  $(AUTOMAKE) --foreign  Makefile
+	  $(AUTOMAKE) --gnu  Makefile
 .PRECIOUS: Makefile
 Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status
 	@case '$?' in \

libpcre/NMAP_MODIFICATIONS

@@ -1,4 +1,4 @@
-This directory contains a version of LibPCRE 7.4 that has been stripped
+This directory contains a version of LibPCRE 7.6 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:
@@ -6,6 +6,7 @@ http://www.pcre.org .  Here are the changes for the Nmap version:
 o Started this NMAP_MODIFICATIONS file
 
 o Removed these directories:
+cmake
 doc
 testdata
 
@@ -60,8 +61,8 @@ o Removed config.sub, config.guess, depcomp, install-sh, and missing.
 o Comment out some build configuration lines from pcre_internal.h because Nmap
   builds a static library:
 
---- pcre-7.4/pcre_internal.h	2007-09-13 04:22:27.000000000 -0500
+--- pcre-7.6/pcre_internal.h	2008-01-20 13:59:21.000000000 -0600
-+++ libpcre/pcre_internal.h	2007-12-19 22:28:33.000000000 -0600
++++ libpcre/pcre_internal.h	2008-02-15 18:12:28.000000000 -0600
 @@ -108,15 +108,19 @@ PCRE_EXP_DATA_DEFN only if they are not 
  
  #ifndef PCRE_EXP_DECL
@@ -87,8 +88,8 @@ o Comment out some build configuration lines from pcre_internal.h because Nmap
 ...and pcre.h.in/pcre.h.generic/pcre.h:
 
 
---- pcre-7.4/pcre.h.in	2007-09-11 06:24:35.000000000 -0500
+--- pcre-7.6/pcre.h.in	2008-01-20 14:01:08.000000000 -0600
-+++ libpcre/pcre.h.in	2007-12-19 22:30:32.000000000 -0600
++++ libpcre/pcre.h.in	2008-02-15 18:12:54.000000000 -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 existing definitions of PCRE_EXP_DECL and PCRECPP_EXP_DECL. */
@@ -109,8 +110,8 @@ o Comment out some build configuration lines from pcre_internal.h because Nmap
 ..and pcreposix.h:
 
 
---- pcre-7.4/pcreposix.h	2007-08-01 04:06:39.000000000 -0500
+--- pcre-7.6/pcreposix.h	2008-01-20 13:56:29.000000000 -0600
-+++ libpcre/pcreposix.h	2007-12-19 22:31:14.000000000 -0600
++++ libpcre/pcreposix.h	2008-02-15 18:13:29.000000000 -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. */

libpcre/NON-UNIX-USE

@@ -8,8 +8,11 @@ This document contains the following sections:
   The C++ wrapper functions
   Building for virtual Pascal
   Stack size in Windows environments
+  Linking programs in Windows environments
   Comments about Win32 builds
-  Building PCRE with CMake
+  Building PCRE on Windows with CMake
+  Use of relative paths with CMake on Windows
+  Testing with runtest.bat
   Building under Windows with BCC5.5
   Building PCRE on OpenVMS
 
@@ -31,10 +34,12 @@ 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 includes support for CMake. This support is relatively
+The PCRE distribution includes a "configure" file for use by the Configure/Make
-new, but has already been used successfully to build PCRE in multiple build
+build system, as found in many Unix-like environments. There is also support
-environments on Windows. There are some instructions in the section entitled
+support for CMake, which some users prefer, in particular in Windows
-"Building PCRE with CMake" below.
+environments. There are some instructions for CMake under Windows in the
+section entitled "Building PCRE with CMake" below. CMake can also be used to
+build PCRE in Unix-like systems.
 
 
 GENERIC INSTRUCTIONS FOR THE PCRE C LIBRARY
@@ -84,7 +89,7 @@ The following are generic comments about building the PCRE C library "by hand".
        ucptable.h
 
  (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.
+     when building a debugging version of PCRE, and is also used by pcretest.
 
        pcre_printint.src
 
@@ -177,15 +182,22 @@ significantly slower when this is done. There is more about stack usage in the
 "pcrestack" documentation.
 
 
+LINKING PROGRAMS IN WINDOWS ENVIRONMENTS
+
+If you want to statically link a program against a PCRE library in the form of
+a non-dll .a file, you must define PCRE_STATIC before including pcre.h,
+otherwise the pcre_malloc() and pcre_free() exported functions will be declared
+__declspec(dllimport), with unwanted results.
+
+
 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
 the same thing; they are completely different from each other. There is also
-some experimental, undocumented support for building using "cmake", which you
+support for building using CMake, which some users find a more straightforward
-might like to try if you are familiar with "cmake". However, at the present
+way of building PCRE under Windows. However, the tests are not run
-time, the "cmake" process builds only a static library (not a dll), and the
+automatically when CMake is used.
-tests are not automatically run.
 
 The MinGW home page (http://www.mingw.org/) says this:
 
@@ -217,10 +229,13 @@ also link with libpcre, which contains the basic functions. (Some earlier
 releases of PCRE included the basic libpcre functions in libpcreposix. This no
 longer happens.)
 
-If you want to statically link your program against a non-dll .a file, you must
+A user submitted a special-purpose patch that makes it easy to create
-define PCRE_STATIC before including pcre.h, otherwise the pcre_malloc() and
+"pcre.dll" under mingw32 using the "msys" environment. It provides "pcre.dll"
-pcre_free() exported functions will be declared __declspec(dllimport), with
+as a special target. If you use this target, no other files are built, and in
-unwanted results.
+particular, the pcretest and pcregrep programs are not built. An example of how
+this might be used is:
+
+  ./configure --enable-utf --disable-cpp CFLAGS="-03 -s"; make pcre.dll
 
 Using Cygwin's compiler generates libraries and executables that depend on
 cygwin1.dll. If a library that is generated this way is distributed,
@@ -252,7 +267,7 @@ 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
+BUILDING PCRE ON WINDOWS 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,
@@ -289,7 +304,36 @@ were contributed by a PCRE user.
 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
+
+USE OF RELATIVE PATHS WITH CMAKE ON WINDOWS
+
+A PCRE user comments as follows:
+
+I thought that others may want to know the current state of
+CMAKE_USE_RELATIVE_PATHS support on Windows.
+
+Here it is:
+-- AdditionalIncludeDirectories is only partially modified (only the
+first path - see below)
+-- Only some of the contained file paths are modified - shown below for
+pcre.vcproj
+-- It properly modifies
+
+I am sure CMake people can fix that if they want to. Until then one will
+need to replace existing absolute paths in project files with relative
+paths manually (e.g. from VS) - relative to project file location. I did
+just that before being told to try CMAKE_USE_RELATIVE_PATHS. Not a big
+deal.
+
+AdditionalIncludeDirectories="E:\builds\pcre\build;E:\builds\pcre\pcre-7.5;"
+AdditionalIncludeDirectories=".;E:\builds\pcre\pcre-7.5;"
+
+RelativePath="pcre.h">
+RelativePath="pcre_chartables.c">
+RelativePath="pcre_chartables.c.rule">
+
+
+TESTING WITH RUNTEST.BAT
 
 1. Copy RunTest.bat into the directory where pcretest.exe has been created.
 
@@ -384,5 +428,5 @@ $!   Locale could not be set to fr
 $!
 =========================
 
-Last Updated: 21 September 2007
+Last Updated: 25 January 2008
 ****

libpcre/README

@@ -119,9 +119,9 @@ If you are using HP's ANSI C++ compiler (aCC), please see the special note
 in the section entitled "Using HP's ANSI C++ compiler (aCC)" below.
 
 The following instructions assume the use of the widely used "configure, make,
-make install" process. There is also some experimental support for "cmake" in
+make install" process. There is also support for CMake in the PCRE
-the PCRE distribution, but it is incomplete and not documented. However, if you
+distribution; there are some comments about using CMake in the NON-UNIX-USE
-are a "cmake" user, you might want to try it.
+file, though it can also be used in Unix-like systems.
 
 To build PCRE on a Unix-like system, first run the "configure" command from the
 PCRE distribution directory, with your current directory set to the directory
@@ -258,6 +258,24 @@ library. You can read more about them in the pcrebuild man page.
 
   This automatically implies --enable-rebuild-chartables (see above).
 
+. It is possible to compile pcregrep to use libz and/or libbz2, in order to
+  read .gz and .bz2 files (respectively), by specifying one or both of
+
+  --enable-pcregrep-libz
+  --enable-pcregrep-libbz2
+
+  Of course, the relevant libraries must be installed on your system.
+
+. It is possible to compile pcretest so that it links with the libreadline
+  library, by specifying
+
+  --enable-pcretest-libreadline
+
+  If this is done, when pcretest's input is from a terminal, it reads it using
+  the readline() function. This provides line-editing and history facilities.
+  Note that libreadline is GPL-licenced, so if you distribute a binary of
+  pcretest linked in this way, there may be licensing issues.
+
 The "configure" script builds the following files for the basic C library:
 
 . Makefile is the makefile that builds the library
@@ -285,12 +303,12 @@ script that can be run to recreate the configuration, and config.log, which
 contains compiler output from tests that "configure" runs.
 
 Once "configure" has run, you can run "make". It builds two libraries, called
-libpcre and libpcreposix, a test program called pcretest, a demonstration
+libpcre and libpcreposix, a test program called pcretest, and the pcregrep
-program called pcredemo, and the pcregrep command. If a C++ compiler was found
+command. If a C++ compiler was found on your system, "make" also builds the C++
-on your system, "make" also builds the C++ wrapper library, which is called
+wrapper library, which is called libpcrecpp, and some test programs called
-libpcrecpp, and some test programs called pcrecpp_unittest,
+pcrecpp_unittest, pcre_scanner_unittest, and pcre_stringpiece_unittest.
-pcre_scanner_unittest, and pcre_stringpiece_unittest. Building the C++ wrapper
+Building the C++ wrapper can be disabled by adding --disable-cpp to the
-can be disabled by adding --disable-cpp to the "configure" command.
+"configure" command.
 
 The command "make check" runs all the appropriate tests. Details of the PCRE
 tests are given below in a separate section of this document.
@@ -342,9 +360,6 @@ system. The following are installed (file names are all relative to the
     pcretest.txt   the pcretest man page
     pcregrep.txt   the pcregrep man page
 
-Note that the pcredemo program that is built by "configure" is *not* installed
-anywhere. It is a demonstration for programmers wanting to use PCRE.
-
 If you want to remove PCRE from your system, you can run "make uninstall".
 This removes all the files that "make install" installed. However, it does not
 remove any directories, because these are often shared with other programs.
@@ -725,4 +740,4 @@ The distribution should contain the following files:
 Philip Hazel
 Email local part: ph10
 Email domain: cam.ac.uk
-Last updated: 21 September 2007
+Last updated: 25 January 2008

libpcre/aclocal.m4

@@ -11,8 +11,8 @@
 # even the implied warranty of MERCHANTABILITY or FITNESS FOR A
 # PARTICULAR PURPOSE.
 
-m4_if(m4_PACKAGE_VERSION, [2.60],,
+m4_if(m4_PACKAGE_VERSION, [2.61],,
-[m4_fatal([this file was generated for autoconf 2.60.
+[m4_fatal([this file was generated for autoconf 2.61.
 You have another version of autoconf.  If you want to use that,
 you should regenerate the build system entirely.], [63])])
 

libpcre/config.h.generic

@@ -40,6 +40,11 @@ them both to 0; an emulation function will be used. */
 /* 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 <bzlib.h> header file. */
+#ifndef HAVE_BZLIB_H
+#define HAVE_BZLIB_H 1
+#endif
+
 /* Define to 1 if you have the <dirent.h> header file. */
 #ifndef HAVE_DIRENT_H
 #define HAVE_DIRENT_H 1
@@ -75,6 +80,16 @@ them both to 0; an emulation function will be used. */
 #define HAVE_MEMORY_H 1
 #endif
 
+/* Define to 1 if you have the <readline/history.h> header file. */
+#ifndef HAVE_READLINE_HISTORY_H
+#define HAVE_READLINE_HISTORY_H 1
+#endif
+
+/* Define to 1 if you have the <readline/readline.h> header file. */
+#ifndef HAVE_READLINE_READLINE_H
+#define HAVE_READLINE_READLINE_H 1
+#endif
+
 /* Define to 1 if you have the <stdint.h> header file. */
 #ifndef HAVE_STDINT_H
 #define HAVE_STDINT_H 1
@@ -141,6 +156,11 @@ 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 <zlib.h> header file. */
+#ifndef HAVE_ZLIB_H
+#define HAVE_ZLIB_H 1
+#endif
+
 /* Define to 1 if you have the `_strtoi64' function. */
 /* #undef HAVE__STRTOI64 */
 
@@ -220,13 +240,13 @@ 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 7.4"
+#define PACKAGE_STRING "PCRE 7.6"
 
 /* Define to the one symbol short name of this package. */
 #define PACKAGE_TARNAME "pcre"
 
 /* Define to the version of this package. */
-#define PACKAGE_VERSION "7.4"
+#define PACKAGE_VERSION "7.6"
 
 
 /* If you are compiling for a system other than a Unix-like system or
@@ -260,6 +280,17 @@ them both to 0; an emulation function will be used. */
 #define STDC_HEADERS 1
 #endif
 
+/* Define to allow pcregrep to be linked with libbz2, so that it is able to
+   handle .bz2 files. */
+/* #undef SUPPORT_LIBBZ2 */
+
+/* Define to allow pcretest to be linked with libreadline. */
+/* #undef SUPPORT_LIBREADLINE */
+
+/* Define to allow pcregrep to be linked with libz, so that it is able to
+   handle .gz files. */
+/* #undef SUPPORT_LIBZ */
+
 /* Define to enable support for Unicode properties */
 /* #undef SUPPORT_UCP */
 
@@ -268,7 +299,7 @@ them both to 0; an emulation function will be used. */
 
 /* Version number of package */
 #ifndef VERSION
-#define VERSION "7.4"
+#define VERSION "7.6"
 #endif
 
 /* Define to empty if `const' does not conform to ANSI C. */

libpcre/config.h.in

@@ -34,6 +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 <bzlib.h> header file. */
+#undef HAVE_BZLIB_H
+
 /* Define to 1 if you have the <dirent.h> header file. */
 #undef HAVE_DIRENT_H
 
@@ -52,6 +55,12 @@ them both to 0; an emulation function will be used. */
 /* Define to 1 if you have the <memory.h> header file. */
 #undef HAVE_MEMORY_H
 
+/* Define to 1 if you have the <readline/history.h> header file. */
+#undef HAVE_READLINE_HISTORY_H
+
+/* Define to 1 if you have the <readline/readline.h> header file. */
+#undef HAVE_READLINE_READLINE_H
+
 /* Define to 1 if you have the <stdint.h> header file. */
 #undef HAVE_STDINT_H
 
@@ -88,6 +97,9 @@ 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 <zlib.h> header file. */
+#undef HAVE_ZLIB_H
+
 /* Define to 1 if you have the `_strtoi64' function. */
 #undef HAVE__STRTOI64
 
@@ -194,6 +206,17 @@ them both to 0; an emulation function will be used. */
 /* Define to 1 if you have the ANSI C header files. */
 #undef STDC_HEADERS
 
+/* Define to allow pcregrep to be linked with libbz2, so that it is able to
+   handle .bz2 files. */
+#undef SUPPORT_LIBBZ2
+
+/* Define to allow pcretest to be linked with libreadline. */
+#undef SUPPORT_LIBREADLINE
+
+/* Define to allow pcregrep to be linked with libz, so that it is able to
+   handle .gz files. */
+#undef SUPPORT_LIBZ
+
 /* Define to enable support for Unicode properties */
 #undef SUPPORT_UCP
 

libpcre/configure.ac

@@ -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, [4])
+m4_define(pcre_minor, [6])
 m4_define(pcre_prerelease, [])
-m4_define(pcre_date, [2007-09-21])
+m4_define(pcre_date, [2008-01-28])
 
 AC_PREREQ(2.57)
 AC_INIT(PCRE, pcre_major.pcre_minor[]pcre_prerelease, , pcre)
@@ -128,6 +128,24 @@ AC_ARG_ENABLE(stack-for-recursion,
                              [don't use stack recursion when matching]),
               , enable_stack_for_recursion=yes)
 
+# Handle --enable-pcregrep-libz
+AC_ARG_ENABLE(pcregrep-libz,
+              AS_HELP_STRING([--enable-pcregrep-libz],
+                             [link pcregrep with libz to handle .gz files]),
+              , enable_pcregrep_libz=no)
+
+# Handle --enable-pcregrep-libbz2
+AC_ARG_ENABLE(pcregrep-libbz2,
+              AS_HELP_STRING([--enable-pcregrep-libbz2],
+                             [link pcregrep with libbz2 to handle .bz2 files]),
+              , enable_pcregrep_libbz2=no)
+
+# Handle --enable-pcretest-libreadline
+AC_ARG_ENABLE(pcretest-libreadline,
+              AS_HELP_STRING([--enable-pcretest-libreadline],
+                             [link pcretest with libreadline]),
+              , enable_pcretest_libreadline=no)
+
 # Handle --with-posix-malloc-threshold=NBYTES
 AC_ARG_WITH(posix-malloc-threshold,
             AS_HELP_STRING([--with-posix-malloc-threshold=NBYTES],
@@ -251,6 +269,22 @@ AC_SUBST(pcre_have_ulong_long)
 
 AC_CHECK_FUNCS(bcopy memmove strerror strtoq strtoll _strtoi64)
 
+# Check for the availability of libz (aka zlib)
+
+AC_CHECK_HEADERS([zlib.h], [HAVE_ZLIB_H=1])
+AC_CHECK_LIB([z], [gzopen], [HAVE_LIBZ=1])
+
+# Check for the availability of libbz2
+
+AC_CHECK_HEADERS([bzlib.h], [HAVE_BZLIB_H=1])
+AC_CHECK_LIB([bz2], [BZ2_bzopen], [HAVE_LIBBZ2=1])
+
+# Check for the availabiity of libreadline
+
+AC_CHECK_HEADERS([readline/readline.h], [HAVE_READLINE_H=1])
+AC_CHECK_HEADERS([readline/history.h], [HAVE_HISTORY_H=1])
+AC_CHECK_LIB([readline], [readline], [HAVE_LIB_READLINE=1])
+
 # This facilitates -ansi builds under Linux
 dnl AC_DEFINE([_GNU_SOURCE], [], [Enable GNU extensions in glibc])
 
@@ -283,6 +317,23 @@ if test "$enable_stack_for_recursion" = "no"; then
     (use --disable-stack-for-recursion).])
 fi
 
+if test "$enable_pcregrep_libz" = "yes"; then
+  AC_DEFINE([SUPPORT_LIBZ], [], [
+    Define to allow pcregrep to be linked with libz, so that it is
+    able to handle .gz files.])
+fi
+
+if test "$enable_pcregrep_libbz2" = "yes"; then
+  AC_DEFINE([SUPPORT_LIBBZ2], [], [
+    Define to allow pcregrep to be linked with libbz2, so that it is
+    able to handle .bz2 files.])
+fi
+
+if test "$enable_pcretest_libreadline" = "yes"; then
+  AC_DEFINE([SUPPORT_LIBREADLINE], [], [
+    Define to allow pcretest to be linked with libreadline.])
+fi
+
 AC_DEFINE_UNQUOTED([NEWLINE], [$ac_pcre_newline_value], [
   The value of NEWLINE determines the newline character sequence. On
   systems that support it, "configure" can be used to override the
@@ -389,6 +440,47 @@ EXTRA_LIBPCRE_LDFLAGS="$NO_UNDEFINED -version-info libpcre_version"
 
 AC_SUBST(EXTRA_LIBPCRE_LDFLAGS)
 
+# Check that, if --enable-pcregrep-libz or --enable-pcregrep-libbz2 is
+# specified, the relevant library is available. If so, add it to LIBS.
+
+if test "$enable_pcregrep_libz" = "yes"; then
+  if test "$HAVE_ZLIB_H" != "1"; then
+    echo "** Cannot --enable-pcregrep-libz because zlib.h was not found"
+    exit 1
+  fi
+  if test "$HAVE_LIBZ" != "1"; then
+    echo "** Cannot --enable-pcregrep-libz because libz was not found"
+    exit 1
+  fi
+  if test "$LIBS" = ""; then LIBS=-lz; else LIBS="$LIBS -lz"; fi
+fi
+
+if test "$enable_pcregrep_libbz2" = "yes"; then
+  if test "$HAVE_BZLIB_H" != "1"; then
+    echo "** Cannot --enable-pcregrep-libbz2 because bzlib.h was not found"
+    exit 1
+  fi
+  if test "$HAVE_LIBBZ2" != "1"; then
+    echo "** Cannot --enable-pcregrep-libbz2 because libbz2 was not found"
+    exit 1
+  fi
+  if test "$LIBS" = ""; then LIBS=-lbz2; else LIBS="$LIBS -lbz2"; fi
+fi
+
+# Similarly for --enable-pcretest-readline
+
+if test "$enable_pcretest_libreadline" = "yes"; then
+  if test "$HAVE_READLINE_H" != "1"; then
+    echo "** Cannot --enable-pcretest-readline because readline/readline.h was not found."
+    exit 1
+  fi
+  if test "$HAVE_HISTORY_H" != "1"; then
+    echo "** Cannot --enable-pcretest-readline because readline/history.h was not found."
+    exit 1
+  fi
+  if test "$LIBS" = ""; then LIBS=-lreadline; else LIBS="$LIBS -lreadline"; fi
+fi
+
 # Produce these files, in addition to config.h.
 AC_CONFIG_FILES(
 	Makefile

libpcre/dftables.c

@@ -6,7 +6,7 @@
 and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2007 University of Cambridge
+           Copyright (c) 1997-2008 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without

libpcre/pcre.h

@@ -5,7 +5,7 @@
 /* This is the public header file for the PCRE library, to be #included by
 applications that call the PCRE functions.
 
-           Copyright (c) 1997-2007 University of Cambridge
+           Copyright (c) 1997-2008 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -42,9 +42,9 @@ POSSIBILITY OF SUCH DAMAGE.
 /* The current PCRE version information. */
 
 #define PCRE_MAJOR          7
-#define PCRE_MINOR          4
+#define PCRE_MINOR          6
 #define PCRE_PRERELEASE     
-#define PCRE_DATE           2007-09-21
+#define PCRE_DATE           2008-01-28
 
 /* 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

libpcre/pcre.h.generic

@@ -5,7 +5,7 @@
 /* This is the public header file for the PCRE library, to be #included by
 applications that call the PCRE functions.
 
-           Copyright (c) 1997-2007 University of Cambridge
+           Copyright (c) 1997-2008 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -42,9 +42,9 @@ POSSIBILITY OF SUCH DAMAGE.
 /* The current PCRE version information. */
 
 #define PCRE_MAJOR          7
-#define PCRE_MINOR          4
+#define PCRE_MINOR          6
 #define PCRE_PRERELEASE     
-#define PCRE_DATE           2007-09-21
+#define PCRE_DATE           2008-01-28
 
 /* 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

libpcre/pcre.h.in

@@ -5,7 +5,7 @@
 /* This is the public header file for the PCRE library, to be #included by
 applications that call the PCRE functions.
 
-           Copyright (c) 1997-2007 University of Cambridge
+           Copyright (c) 1997-2008 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without

libpcre/pcre_compile.c

@@ -6,7 +6,7 @@
 and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2007 University of Cambridge
+           Copyright (c) 1997-2008 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -48,6 +48,7 @@ supporting internal functions that are not used by other modules. */
 #include "config.h"
 #endif
 
+
 #define NLBLOCK cd             /* Block containing newline information */
 #define PSSTART start_pattern  /* Field containing processed string start */
 #define PSEND   end_pattern    /* Field containing processed string end */
@@ -243,7 +244,7 @@ static const char error_texts[] =
   /* 10 */
   "operand of unlimited repeat could match the empty string\0"  /** DEAD **/
   "internal error: unexpected repeat\0"
-  "unrecognized character after (?\0"
+  "unrecognized character after (? or (?-\0"
   "POSIX named classes are supported only within a class\0"
   "missing )\0"
   /* 15 */
@@ -302,7 +303,9 @@ static const char error_texts[] =
   "(*VERB) with an argument is not supported\0"
   /* 60 */
   "(*VERB) not recognized\0"
-  "number is too big";
+  "number is too big\0"
+  "subpattern name expected\0"
+  "digit expected after (?+";
 
 
 /* Table to identify digits and hex digits. This is used when compiling
@@ -498,16 +501,16 @@ ptr--;                            /* Set pointer back to the last byte */
 
 if (c == 0) *errorcodeptr = ERR1;
 
-/* Non-alphamerics are literals. For digits or letters, do an initial lookup in
+/* Non-alphanumerics are literals. For digits or letters, do an initial lookup
-a table. A non-zero result is something that can be returned immediately.
+in a table. A non-zero result is something that can be returned immediately.
 Otherwise further processing may be required. */
 
 #ifndef EBCDIC  /* ASCII coding */
-else if (c < '0' || c > 'z') {}                           /* Not alphameric */
+else if (c < '0' || c > 'z') {}                           /* Not alphanumeric */
 else if ((i = escapes[c - '0']) != 0) c = i;
 
 #else           /* EBCDIC coding */
-else if (c < 'a' || (ebcdic_chartab[c] & 0x0E) == 0) {}   /* Not alphameric */
+else if (c < 'a' || (ebcdic_chartab[c] & 0x0E) == 0) {}   /* Not alphanumeric */
 else if ((i = escapes[c - 0x48]) != 0)  c = i;
 #endif
 
@@ -724,10 +727,10 @@ else
     break;
 
     /* PCRE_EXTRA enables extensions to Perl in the matter of escapes. Any
-    other alphameric following \ is an error if PCRE_EXTRA was set; otherwise,
+    other alphanumeric following \ is an error if PCRE_EXTRA was set;
-    for Perl compatibility, it is a literal. This code looks a bit odd, but
+    otherwise, for Perl compatibility, it is a literal. This code looks a bit
-    there used to be some cases other than the default, and there may be again
+    odd, but there used to be some cases other than the default, and there may
-    in future, so I haven't "optimized" it. */
+    be again in future, so I haven't "optimized" it. */
 
     default:
     if ((options & PCRE_EXTRA) != 0) switch(c)
@@ -1508,8 +1511,9 @@ for (;;)
 can match the empty string or not. It is called from could_be_empty()
 below and from compile_branch() when checking for an unlimited repeat of a
 group that can match nothing. Note that first_significant_code() skips over
-assertions. If we hit an unclosed bracket, we return "empty" - this means we've
+backward and negative forward assertions when its final argument is TRUE. If we
-struck an inner bracket whose current branch will already have been scanned.
+hit an unclosed bracket, we return "empty" - this means we've struck an inner
+bracket whose current branch will already have been scanned.
 
 Arguments:
   code        points to start of search
@@ -1531,6 +1535,16 @@ for (code = first_significant_code(code + _pcre_OP_lengths[*code], NULL, 0, TRUE
 
   c = *code;
 
+  /* Skip over forward assertions; the other assertions are skipped by
+  first_significant_code() with a TRUE final argument. */
+
+  if (c == OP_ASSERT)
+    {
+    do code += GET(code, 1); while (*code == OP_ALT);
+    c = *code;
+    continue;
+    }
+
   /* Groups with zero repeats can of course be empty; skip them. */
 
   if (c == OP_BRAZERO || c == OP_BRAMINZERO)
@@ -1726,30 +1740,49 @@ return TRUE;
 *************************************************/
 
 /* This function is called when the sequence "[:" or "[." or "[=" is
-encountered in a character class. It checks whether this is followed by an
+encountered in a character class. It checks whether this is followed by a
-optional ^ and then a sequence of letters, terminated by a matching ":]" or
+sequence of characters terminated by a matching ":]" or ".]" or "=]". If we
-".]" or "=]".
+reach an unescaped ']' without the special preceding character, return FALSE.
 
-Argument:
+Originally, this function only recognized a sequence of letters between the
+terminators, but it seems that Perl recognizes any sequence of characters,
+though of course unknown POSIX names are subsequently rejected. Perl gives an
+"Unknown POSIX class" error for [:f\oo:] for example, where previously PCRE
+didn't consider this to be a POSIX class. Likewise for [:1234:].
+
+The problem in trying to be exactly like Perl is in the handling of escapes. We
+have to be sure that [abc[:x\]pqr] is *not* treated as containing a POSIX
+class, but [abc[:x\]pqr:]] is (so that an error can be generated). The code
+below handles the special case of \], but does not try to do any other escape
+processing. This makes it different from Perl for cases such as [:l\ower:]
+where Perl recognizes it as the POSIX class "lower" but PCRE does not recognize
+"l\ower". This is a lesser evil that not diagnosing bad classes when Perl does,
+I think.
+
+Arguments:
   ptr      pointer to the initial [
   endptr   where to return the end pointer
-  cd       pointer to compile data
 
 Returns:   TRUE or FALSE
 */
 
 static BOOL
-check_posix_syntax(const uschar *ptr, const uschar **endptr, compile_data *cd)
+check_posix_syntax(const uschar *ptr, const uschar **endptr)
 {
 int terminator;          /* Don't combine these lines; the Solaris cc */
 terminator = *(++ptr);   /* compiler warns about "non-constant" initializer. */
-if (*(++ptr) == '^') ptr++;
+for (++ptr; *ptr != 0; ptr++)
-while ((cd->ctypes[*ptr] & ctype_letter) != 0) ptr++;
+  {
-if (*ptr == terminator && ptr[1] == ']')
+  if (*ptr == '\\' && ptr[1] == ']') ptr++; else
+    {
+    if (*ptr == ']') return FALSE;
+    if (*ptr == terminator && ptr[1] == ']')
       {
       *endptr = ptr;
       return TRUE;
       }
+    }
+  }
 return FALSE;
 }
 
@@ -2346,6 +2379,7 @@ uschar classbits[32];
 BOOL class_utf8;
 BOOL utf8 = (options & PCRE_UTF8) != 0;
 uschar *class_utf8data;
+uschar *class_utf8data_base;
 uschar utf8_char[6];
 #else
 BOOL utf8 = FALSE;
@@ -2385,6 +2419,7 @@ req_caseopt = ((options & PCRE_CASELESS) != 0)? REQ_CASELESS : 0;
 for (;; ptr++)
   {
   BOOL negate_class;
+  BOOL should_flip_negation;
   BOOL possessive_quantifier;
   BOOL is_quantifier;
   BOOL is_recurse;
@@ -2608,7 +2643,7 @@ for (;; ptr++)
     they are encountered at the top level, so we'll do that too. */
 
     if ((ptr[1] == ':' || ptr[1] == '.' || ptr[1] == '=') &&
-        check_posix_syntax(ptr, &tempptr, cd))
+        check_posix_syntax(ptr, &tempptr))
       {
       *errorcodeptr = (ptr[1] == ':')? ERR13 : ERR31;
       goto FAILED;
@@ -2633,6 +2668,12 @@ for (;; ptr++)
       else break;
       }
 
+    /* If a class contains a negative special such as \S, we need to flip the
+    negation flag at the end, so that support for characters > 255 works
+    correctly (they are all included in the class). */
+
+    should_flip_negation = FALSE;
+
     /* Keep a count of chars with values < 256 so that we can optimize the case
     of just a single character (as long as it's < 256). However, For higher
     valued UTF-8 characters, we don't yet do any optimization. */
@@ -2650,6 +2691,7 @@ for (;; ptr++)
 #ifdef SUPPORT_UTF8
     class_utf8 = FALSE;                       /* No chars >= 256 */
     class_utf8data = code + LINK_SIZE + 2;    /* For UTF-8 items */
+    class_utf8data_base = class_utf8data;     /* For resetting in pass 1 */
 #endif
 
     /* Process characters until ] is reached. By writing this as a "do" it
@@ -2665,6 +2707,18 @@ for (;; ptr++)
         {                           /* Braces are required because the */
         GETCHARLEN(c, ptr, ptr);    /* macro generates multiple statements */
         }
+
+      /* In the pre-compile phase, accumulate the length of any UTF-8 extra
+      data and reset the pointer. This is so that very large classes that
+      contain a zillion UTF-8 characters no longer overwrite the work space
+      (which is on the stack). */
+
+      if (lengthptr != NULL)
+        {
+        *lengthptr += class_utf8data - class_utf8data_base;
+        class_utf8data = class_utf8data_base;
+        }
+
 #endif
 
       /* Inside \Q...\E everything is literal except \E */
@@ -2688,7 +2742,7 @@ for (;; ptr++)
 
       if (c == '[' &&
           (ptr[1] == ':' || ptr[1] == '.' || ptr[1] == '=') &&
-          check_posix_syntax(ptr, &tempptr, cd))
+          check_posix_syntax(ptr, &tempptr))
         {
         BOOL local_negate = FALSE;
         int posix_class, taboffset, tabopt;
@@ -2705,6 +2759,7 @@ for (;; ptr++)
         if (*ptr == '^')
           {
           local_negate = TRUE;
+          should_flip_negation = TRUE;  /* Note negative special */
           ptr++;
           }
 
@@ -2779,7 +2834,7 @@ for (;; ptr++)
         c = check_escape(&ptr, errorcodeptr, cd->bracount, options, TRUE);
         if (*errorcodeptr != 0) goto FAILED;
 
-        if (-c == ESC_b) c = '\b';       /* \b is backslash in a class */
+        if (-c == ESC_b) c = '\b';       /* \b is backspace in a class */
         else if (-c == ESC_X) c = 'X';   /* \X is literal X in a class */
         else if (-c == ESC_R) c = 'R';   /* \R is literal R in a class */
         else if (-c == ESC_Q)            /* Handle start of quoted string */
@@ -2807,6 +2862,7 @@ for (;; ptr++)
             continue;
 
             case ESC_D:
+            should_flip_negation = TRUE;
             for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_digit];
             continue;
 
@@ -2815,6 +2871,7 @@ for (;; ptr++)
             continue;
 
             case ESC_W:
+            should_flip_negation = TRUE;
             for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_word];
             continue;
 
@@ -2824,13 +2881,11 @@ for (;; ptr++)
             continue;
 
             case ESC_S:
+            should_flip_negation = TRUE;
             for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_space];
             classbits[1] |= 0x08;    /* Perl 5.004 onwards omits VT from \s */
             continue;
 
-            case ESC_E: /* Perl ignores an orphan \E */
-            continue;
-
             default:    /* Not recognized; fall through */
             break;      /* Need "default" setting to stop compiler warning. */
             }
@@ -3065,7 +3120,7 @@ for (;; ptr++)
           d = check_escape(&ptr, errorcodeptr, cd->bracount, options, TRUE);
           if (*errorcodeptr != 0) goto FAILED;
 
-          /* \b is backslash; \X is literal X; \R is literal R; any other
+          /* \b is backspace; \X is literal X; \R is literal R; any other
           special means the '-' was literal */
 
           if (d < 0)
@@ -3329,11 +3384,14 @@ we set the flag only if there is a literal "\r" or "\n" in the class. */
     zeroreqbyte = reqbyte;
 
     /* If there are characters with values > 255, we have to compile an
-    extended class, with its own opcode. If there are no characters < 256,
+    extended class, with its own opcode, unless there was a negated special
-    we can omit the bitmap in the actual compiled code. */
+    such as \S in the class, because in that case all characters > 255 are in
+    the class, so any that were explicitly given as well can be ignored. If
+    (when there are explicit characters > 255 that must be listed) there are no
+    characters < 256, we can omit the bitmap in the actual compiled code. */
 
 #ifdef SUPPORT_UTF8
-    if (class_utf8)
+    if (class_utf8 && !should_flip_negation)
       {
       *class_utf8data++ = XCL_END;    /* Marks the end of extra data */
       *code++ = OP_XCLASS;
@@ -3359,20 +3417,19 @@ we set the flag only if there is a literal "\r" or "\n" in the class. */
       }
 #endif
 
-    /* If there are no characters > 255, negate the 32-byte map if necessary,
+    /* If there are no characters > 255, set the opcode to OP_CLASS or
-    and copy it into the code vector. If this is the first thing in the branch,
+    OP_NCLASS, depending on whether the whole class was negated and whether
-    there can be no first char setting, whatever the repeat count. Any reqbyte
+    there were negative specials such as \S in the class. Then copy the 32-byte
-    setting must remain unchanged after any kind of repeat. */
+    map into the code vector, negating it if necessary. */
 
+    *code++ = (negate_class == should_flip_negation) ? OP_CLASS : OP_NCLASS;
     if (negate_class)
       {
-      *code++ = OP_NCLASS;
       if (lengthptr == NULL)    /* Save time in the pre-compile phase */
         for (c = 0; c < 32; c++) code[c] = ~classbits[c];
       }
     else
       {
-      *code++ = OP_CLASS;
       memcpy(code, classbits, 32);
       }
     code += 32;
@@ -4008,7 +4065,9 @@ we set the flag only if there is a literal "\r" or "\n" in the class. */
       int len;
       if (*tempcode == OP_EXACT || *tempcode == OP_TYPEEXACT ||
           *tempcode == OP_NOTEXACT)
-        tempcode += _pcre_OP_lengths[*tempcode];
+        tempcode += _pcre_OP_lengths[*tempcode] +
+          ((*tempcode == OP_TYPEEXACT &&
+             (tempcode[3] == OP_PROP || tempcode[3] == OP_NOTPROP))? 2:0);
       len = code - tempcode;
       if (len > 0) switch (*tempcode)
         {
@@ -4235,16 +4294,13 @@ we set the flag only if there is a literal "\r" or "\n" in the class. */
             *errorcodeptr = ERR58;
             goto FAILED;
             }
-          if (refsign == '-')
+          recno = (refsign == '-')?
-            {
+            cd->bracount - recno + 1 : recno +cd->bracount;
-            recno = cd->bracount - recno + 1;
+          if (recno <= 0 || recno > cd->final_bracount)
-            if (recno <= 0)
             {
             *errorcodeptr = ERR15;
             goto FAILED;
             }
-            }
-          else recno += cd->bracount;
           PUT2(code, 2+LINK_SIZE, recno);
           break;
           }
@@ -4316,9 +4372,10 @@ we set the flag only if there is a literal "\r" or "\n" in the class. */
           skipbytes = 1;
           }
 
-        /* Check for the "name" actually being a subpattern number. */
+        /* Check for the "name" actually being a subpattern number. We are
+        in the second pass here, so final_bracount is set. */
 
-        else if (recno > 0)
+        else if (recno > 0 && recno <= cd->final_bracount)
           {
           PUT2(code, 2+LINK_SIZE, recno);
           }
@@ -4512,7 +4569,9 @@ we set the flag only if there is a literal "\r" or "\n" in the class. */
 
         /* We come here from the Python syntax above that handles both
         references (?P=name) and recursion (?P>name), as well as falling
-        through from the Perl recursion syntax (?&name). */
+        through from the Perl recursion syntax (?&name). We also come here from
+        the Perl \k<name> or \k'name' back reference syntax and the \k{name}
+        .NET syntax. */
 
         NAMED_REF_OR_RECURSE:
         name = ++ptr;
@@ -4524,6 +4583,11 @@ we set the flag only if there is a literal "\r" or "\n" in the class. */
 
         if (lengthptr != NULL)
           {
+          if (namelen == 0)
+            {
+            *errorcodeptr = ERR62;
+            goto FAILED;
+            }
           if (*ptr != terminator)
             {
             *errorcodeptr = ERR42;
@@ -4537,14 +4601,19 @@ we set the flag only if there is a literal "\r" or "\n" in the class. */
           recno = 0;
           }
 
-        /* In the real compile, seek the name in the table */
+        /* In the real compile, seek the name in the table. We check the name
+        first, and then check that we have reached the end of the name in the
+        table. That way, if the name that is longer than any in the table,
+        the comparison will fail without reading beyond the table entry. */
 
         else
           {
           slot = cd->name_table;
           for (i = 0; i < cd->names_found; i++)
             {
-            if (strncmp((char *)name, (char *)slot+2, namelen) == 0) break;
+            if (strncmp((char *)name, (char *)slot+2, namelen) == 0 &&
+                slot[2+namelen] == 0)
+              break;
             slot += cd->name_entry_size;
             }
 
@@ -4581,7 +4650,15 @@ we set the flag only if there is a literal "\r" or "\n" in the class. */
           {
           const uschar *called;
 
-          if ((refsign = *ptr) == '+') ptr++;
+          if ((refsign = *ptr) == '+')
+            {
+            ptr++;
+            if ((digitab[*ptr] & ctype_digit) == 0)
+              {
+              *errorcodeptr = ERR63;
+              goto FAILED;
+              }
+            }
           else if (refsign == '-')
             {
             if ((digitab[ptr[1]] & ctype_digit) == 0)
@@ -5747,7 +5824,6 @@ to fill in forward references to subpatterns. */
 
 uschar cworkspace[COMPILE_WORK_SIZE];
 
-
 /* Set this early so that early errors get offset 0. */
 
 ptr = (const uschar *)pattern;
@@ -5908,7 +5984,7 @@ to compile parts of the pattern into; the compiled code is discarded when it is
 no longer needed, so hopefully this workspace will never overflow, though there
 is a test for its doing so. */
 
-cd->bracount = 0;
+cd->bracount = cd->final_bracount = 0;
 cd->names_found = 0;
 cd->name_entry_size = 0;
 cd->name_table = NULL;
@@ -5985,6 +6061,7 @@ field. Reset the bracket count and the names_found field. Also reset the hwm
 field; this time it's used for remembering forward references to subpatterns.
 */
 
+cd->final_bracount = cd->bracount;  /* Save for checking forward references */
 cd->bracount = 0;
 cd->names_found = 0;
 cd->name_table = (uschar *)re + re->name_table_offset;

libpcre/pcre_config.c

@@ -6,7 +6,7 @@
 and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2007 University of Cambridge
+           Copyright (c) 1997-2008 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without

libpcre/pcre_dfa_exec.c

@@ -6,7 +6,7 @@
 and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2007 University of Cambridge
+           Copyright (c) 1997-2008 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without

libpcre/pcre_exec.c

@@ -6,7 +6,7 @@
 and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2007 University of Cambridge
+           Copyright (c) 1997-2008 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -4672,10 +4672,10 @@ for(;;)
     if (first_byte_caseless)
       while (start_match < end_subject &&
              md->lcc[*start_match] != first_byte)
-        start_match++;
+        { NEXTCHAR(start_match); }
     else
       while (start_match < end_subject && *start_match != first_byte)
-        start_match++;
+        { NEXTCHAR(start_match); }
     }
 
   /* Or to just after a linebreak for a multiline match if possible */
@@ -4685,7 +4685,7 @@ for(;;)
     if (start_match > md->start_subject + start_offset)
       {
       while (start_match <= end_subject && !WAS_NEWLINE(start_match))
-        start_match++;
+        { NEXTCHAR(start_match); }
 
       /* If we have just passed a CR and the newline option is ANY or ANYCRLF,
       and we are now at a LF, advance the match position by one more character.
@@ -4706,7 +4706,9 @@ for(;;)
     while (start_match < end_subject)
       {
       register unsigned int c = *start_match;
-      if ((start_bits[c/8] & (1 << (c&7))) == 0) start_match++; else break;
+      if ((start_bits[c/8] & (1 << (c&7))) == 0)
+        { NEXTCHAR(start_match); }
+      else break;
       }
     }
 

libpcre/pcre_fullinfo.c

@@ -2,11 +2,11 @@
 *      Perl-Compatible Regular Expressions       *
 *************************************************/
 
-/*PCRE is a library of functions to support regular expressions whose syntax
+/* PCRE is a library of functions to support regular expressions whose syntax
 and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2007 University of Cambridge
+           Copyright (c) 1997-2008 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without

libpcre/pcre_get.c

@@ -6,7 +6,7 @@
 and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2007 University of Cambridge
+           Copyright (c) 1997-2008 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without

libpcre/pcre_globals.c

@@ -6,7 +6,7 @@
 and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2007 University of Cambridge
+           Copyright (c) 1997-2008 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without

libpcre/pcre_info.c

@@ -6,7 +6,7 @@
 and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2007 University of Cambridge
+           Copyright (c) 1997-2008 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without

libpcre/pcre_internal.h

@@ -7,7 +7,7 @@
 and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2007 University of Cambridge
+           Copyright (c) 1997-2008 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -367,6 +367,7 @@ 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 NEXTCHAR(p) p++;
 #define GETCHAR(c, eptr) c = *eptr;
 #define GETCHARTEST(c, eptr) c = *eptr;
 #define GETCHARINC(c, eptr) c = *eptr++;
@@ -376,6 +377,13 @@ support is omitted, we don't even define it. */
 
 #else   /* SUPPORT_UTF8 */
 
+/* Advance a character pointer one byte in non-UTF-8 mode and by one character
+in UTF-8 mode. */
+
+#define NEXTCHAR(p) \
+  p++; \
+  if (utf8) { while((*p & 0xc0) == 0x80) p++; }
+
 /* Get the next UTF-8 character, not advancing the pointer. This is called when
 we know we are in UTF-8 mode. */
 
@@ -875,7 +883,7 @@ enum { ERR0,  ERR1,  ERR2,  ERR3,  ERR4,  ERR5,  ERR6,  ERR7,  ERR8,  ERR9,
        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, ERR59,
-       ERR60, ERR61 };
+       ERR60, ERR61, ERR62, ERR63 };
 
 /* 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
@@ -938,7 +946,8 @@ typedef struct compile_data {
   uschar *name_table;           /* The name/number table */
   int  names_found;             /* Number of entries so far */
   int  name_entry_size;         /* Size of each entry */
-  int  bracount;                /* Count of capturing parens */
+  int  bracount;                /* Count of capturing parens as we compile */
+  int  final_bracount;          /* Saved value after first pass */
   int  top_backref;             /* Maximum back reference */
   unsigned int backref_map;     /* Bitmap of low back refs */
   int  external_options;        /* External (initial) options */
@@ -1040,7 +1049,7 @@ typedef struct dfa_match_data {
 #define ctype_letter  0x02
 #define ctype_digit   0x04
 #define ctype_xdigit  0x08
-#define ctype_word    0x10   /* alphameric or '_' */
+#define ctype_word    0x10   /* alphanumeric or '_' */
 #define ctype_meta    0x80   /* regexp meta char or zero (end pattern) */
 
 /* Offsets for the bitmap tables in pcre_cbits. Each table contains a set

libpcre/pcre_maketables.c

@@ -6,7 +6,7 @@
 and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2007 University of Cambridge
+           Copyright (c) 1997-2008 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without

libpcre/pcre_newline.c

@@ -6,7 +6,7 @@
 and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2007 University of Cambridge
+           Copyright (c) 1997-2008 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without

libpcre/pcre_ord2utf8.c

@@ -6,7 +6,7 @@
 and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2007 University of Cambridge
+           Copyright (c) 1997-2008 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without

libpcre/pcre_refcount.c

@@ -6,7 +6,7 @@
 and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2007 University of Cambridge
+           Copyright (c) 1997-2008 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without

libpcre/pcre_study.c

@@ -6,7 +6,7 @@
 and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2007 University of Cambridge
+           Copyright (c) 1997-2008 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without

libpcre/pcre_tables.c

@@ -6,7 +6,7 @@
 and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2007 University of Cambridge
+           Copyright (c) 1997-2008 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without

libpcre/pcre_try_flipped.c

@@ -6,7 +6,7 @@
 and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2007 University of Cambridge
+           Copyright (c) 1997-2008 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without

libpcre/pcre_ucp_searchfuncs.c

@@ -6,7 +6,7 @@
 and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2007 University of Cambridge
+           Copyright (c) 1997-2008 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without

libpcre/pcre_valid_utf8.c

@@ -6,7 +6,7 @@
 and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2007 University of Cambridge
+           Copyright (c) 1997-2008 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -64,7 +64,7 @@ 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
+obsoletes 2279), additional restrictions were applied. 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.
 

libpcre/pcre_version.c

@@ -6,7 +6,7 @@
 and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2007 University of Cambridge
+           Copyright (c) 1997-2008 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without

libpcre/pcre_xclass.c

@@ -6,7 +6,7 @@
 and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2007 University of Cambridge
+           Copyright (c) 1997-2008 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without

libpcre/pcreposix.c

@@ -6,7 +6,7 @@
 and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2007 University of Cambridge
+           Copyright (c) 1997-2008 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -126,7 +126,9 @@ static const int eint[] = {
   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   /* number is too big */
+  REG_BADPAT,  /* number is too big */
+  REG_BADPAT,  /* subpattern name expected */
+  REG_BADPAT   /* digit expected after (?+ */
 };
 
 /* Table of texts corresponding to POSIX error codes */

libpcre/pcreposix.h

@@ -9,7 +9,7 @@
 Compatible Regular Expression library. It defines the things POSIX says should
 be there. I hope.
 
-            Copyright (c) 1997-2007 University of Cambridge
+            Copyright (c) 1997-2008 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without

libpcre/ucptable.h

@@ -539,7 +539,8 @@ static const cnode ucp_table[] = {
   { 0x21000293, 0x14000000 },
   { 0x21000294, 0x1c000000 },
   { 0x21800295, 0x1400001a },
-  { 0x218002b0, 0x18000011 },
+  { 0x218002b0, 0x18000008 },
+  { 0x098002b9, 0x18000008 },
   { 0x098002c2, 0x60000003 },
   { 0x098002c6, 0x1800000b },
   { 0x098002d2, 0x6000000d },
@@ -1039,15 +1040,18 @@ static const cnode ucp_table[] = {
   { 0x198005f3, 0x54000001 },
   { 0x09800600, 0x04000003 },
   { 0x0000060b, 0x5c000000 },
-  { 0x0980060c, 0x54000001 },
+  { 0x0900060c, 0x54000000 },
+  { 0x0000060d, 0x54000000 },
   { 0x0080060e, 0x68000001 },
   { 0x00800610, 0x30000005 },
   { 0x0900061b, 0x54000000 },
-  { 0x0080061e, 0x54000001 },
+  { 0x0000061e, 0x54000000 },
+  { 0x0900061f, 0x54000000 },
   { 0x00800621, 0x1c000019 },
   { 0x09000640, 0x18000000 },
   { 0x00800641, 0x1c000009 },
-  { 0x1b80064b, 0x30000013 },
+  { 0x1b80064b, 0x3000000a },
+  { 0x00800656, 0x30000008 },
   { 0x09800660, 0x34000009 },
   { 0x0080066a, 0x54000003 },
   { 0x0080066e, 0x1c000001 },
@@ -1074,7 +1078,8 @@ static const cnode ucp_table[] = {
   { 0x31000711, 0x30000000 },
   { 0x31800712, 0x1c00001d },
   { 0x31800730, 0x3000001a },
-  { 0x3180074d, 0x1c000020 },
+  { 0x3180074d, 0x1c000002 },
+  { 0x00800750, 0x1c00001d },
   { 0x37800780, 0x1c000025 },
   { 0x378007a6, 0x3000000a },
   { 0x370007b1, 0x1c000000 },
@@ -1460,7 +1465,10 @@ static const cnode ucp_table[] = {
   { 0x1f0017dd, 0x30000000 },
   { 0x1f8017e0, 0x34000009 },
   { 0x1f8017f0, 0x3c000009 },
-  { 0x25801800, 0x54000005 },
+  { 0x25801800, 0x54000001 },
+  { 0x09801802, 0x54000001 },
+  { 0x25001804, 0x54000000 },
+  { 0x09001805, 0x54000000 },
   { 0x25001806, 0x44000000 },
   { 0x25801807, 0x54000003 },
   { 0x2580180b, 0x30000002 },
@@ -1513,14 +1521,20 @@ static const cnode ucp_table[] = {
   { 0x3d801b61, 0x68000009 },
   { 0x3d801b6b, 0x30000008 },
   { 0x3d801b74, 0x68000008 },
-  { 0x21801d00, 0x1400002b },
+  { 0x21801d00, 0x14000025 },
-  { 0x21801d2c, 0x18000035 },
+  { 0x13801d26, 0x14000004 },
-  { 0x21801d62, 0x14000015 },
+  { 0x0c001d2b, 0x14000000 },
+  { 0x21801d2c, 0x18000030 },
+  { 0x13801d5d, 0x18000004 },
+  { 0x21801d62, 0x14000003 },
+  { 0x13801d66, 0x14000004 },
+  { 0x21801d6b, 0x1400000c },
   { 0x0c001d78, 0x18000000 },
   { 0x21801d79, 0x14000003 },
   { 0x21001d7d, 0x14000ee6 },
   { 0x21801d7e, 0x1400001c },
-  { 0x21801d9b, 0x18000024 },
+  { 0x21801d9b, 0x18000023 },
+  { 0x13001dbf, 0x18000000 },
   { 0x1b801dc0, 0x3000000a },
   { 0x1b801dfe, 0x30000001 },
   { 0x21001e00, 0x24000001 },
@@ -1982,7 +1996,9 @@ static const cnode ucp_table[] = {
   { 0x13001ffc, 0x2000fff7 },
   { 0x13801ffd, 0x60000001 },
   { 0x09802000, 0x7400000a },
-  { 0x0980200b, 0x04000004 },
+  { 0x0900200b, 0x04000000 },
+  { 0x1b80200c, 0x04000001 },
+  { 0x0980200e, 0x04000001 },
   { 0x09802010, 0x44000005 },
   { 0x09802016, 0x54000001 },
   { 0x09002018, 0x50000000 },
@@ -2615,7 +2631,8 @@ static const cnode ucp_table[] = {
   { 0x090030a0, 0x44000000 },
   { 0x1d8030a1, 0x1c000059 },
   { 0x090030fb, 0x54000000 },
-  { 0x098030fc, 0x18000002 },
+  { 0x090030fc, 0x18000000 },
+  { 0x1d8030fd, 0x18000001 },
   { 0x1d0030ff, 0x1c000000 },
   { 0x03803105, 0x1c000027 },
   { 0x17803131, 0x1c00005d },
@@ -2630,7 +2647,8 @@ static const cnode ucp_table[] = {
   { 0x0980322a, 0x68000019 },
   { 0x09003250, 0x68000000 },
   { 0x09803251, 0x3c00000e },
-  { 0x17803260, 0x6800001f },
+  { 0x17803260, 0x6800001d },
+  { 0x0980327e, 0x68000001 },
   { 0x09803280, 0x3c000009 },
   { 0x0980328a, 0x68000026 },
   { 0x098032b1, 0x3c00000e },
@@ -2678,7 +2696,8 @@ static const cnode ucp_table[] = {
   { 0x1900fb3e, 0x1c000000 },
   { 0x1980fb40, 0x1c000001 },
   { 0x1980fb43, 0x1c000001 },
-  { 0x1980fb46, 0x1c00006b },
+  { 0x1980fb46, 0x1c000009 },
+  { 0x0080fb50, 0x1c000061 },
   { 0x0080fbd3, 0x1c00016a },
   { 0x0900fd3e, 0x58000000 },
   { 0x0900fd3f, 0x48000000 },
@@ -2944,7 +2963,8 @@ static const cnode ucp_table[] = {
   { 0x0d01044d, 0x1400ffd8 },
   { 0x0d01044e, 0x1400ffd8 },
   { 0x0d01044f, 0x1400ffd8 },
-  { 0x2e810450, 0x1c00004d },
+  { 0x2e810450, 0x1c00002f },
+  { 0x2c810480, 0x1c00001d },
   { 0x2c8104a0, 0x34000009 },
   { 0x0b810800, 0x1c000005 },
   { 0x0b010808, 0x1c000000 },