Update PCRE version

src/plugins/PCREPlugin/Makefile.inc

@@ -1,5 +1,13 @@
 all: $(BUILDDIR)PCREPlugin$(DLSUFFICS) 
 
+pcre_maketables$(OBJSUFFICS): pcre_maketables.c
+	$(CC) $(DCFLAGS) $(CFLAGS) pcre_maketables.c
+
+pcre_table$(OBJSUFFICS): pcre_table.c
+	$(CC) $(DCFLAGS) $(CFLAGS) pcre_table.c
+
+pcre_ucd$(OBJSUFFICS): pcre_ucd.c
+	$(CC) $(DCFLAGS) $(CFLAGS) pcre_ucd.c
 
 pcre_compile$(OBJSUFFICS): pcre_compile.c
 	$(CC) $(DCFLAGS) $(CFLAGS) pcre_compile.c
@@ -22,12 +30,6 @@ pcre_get$(OBJSUFFICS): pcre_get.c
 pcre_globals$(OBJSUFFICS): pcre_globals.c
 	$(CC) $(DCFLAGS) $(CFLAGS)  pcre_globals.c
 
-pcre_info$(OBJSUFFICS): pcre_info.c
-	$(CC) $(DCFLAGS) $(CFLAGS)  pcre_info.c
-
-pcre_maketables$(OBJSUFFICS): pcre_maketables.c
-	$(CC) $(DCFLAGS) $(CFLAGS)  pcre_maketables.c
-
 pcre_newline$(OBJSUFFICS): pcre_newline.c
 	$(CC) $(DCFLAGS) $(CFLAGS)  pcre_newline.c
 
@@ -43,12 +45,6 @@ pcre_study$(OBJSUFFICS): pcre_study.c
 pcre_tables$(OBJSUFFICS): pcre_tables.c
 	$(CC) $(DCFLAGS) $(CFLAGS)  pcre_tables.c
 
-pcre_try_flipped$(OBJSUFFICS): pcre_try_flipped.c
-	$(CC) $(DCFLAGS) $(CFLAGS)  pcre_try_flipped.c
-
-pcre_ucp_searchfuncs$(OBJSUFFICS): pcre_ucp_searchfuncs.c
-	$(CC) $(DCFLAGS) $(CFLAGS)  pcre_ucp_searchfuncs.c
-
 pcre_valid_utf8$(OBJSUFFICS): pcre_valid_utf8.c
 	$(CC) $(DCFLAGS) $(CFLAGS)  pcre_valid_utf8.c
 
@@ -58,14 +54,9 @@ pcre_version$(OBJSUFFICS): pcre_version.c
 pcre_xclass$(OBJSUFFICS): pcre_xclass.c
 	$(CC) $(DCFLAGS) $(CFLAGS)  pcre_xclass.c
 
-pcre_dftables$(OBJSUFFICS): pcre_dftables.c
-	$(CC) $(DCFLAGS) $(CFLAGS) pcre_dftables.c
-
 pcre_plugin$(OBJSUFFICS): pcre_plugin.c
 	$(CC) $(DCFLAGS) $(CFLAGS) pcre_plugin.c
 
-pcreposix$(OBJSUFFICS): pcreposix.c
+$(BUILDDIR)PCREPlugin$(DLSUFFICS): pcre_compile$(OBJSUFFICS) pcre_config$(OBJSUFFICS) pcre_dfa_exec$(OBJSUFFICS) pcre_exec$(OBJSUFFICS) pcre_fullinfo$(OBJSUFFICS) pcre_get$(OBJSUFFICS) pcre_globals$(OBJSUFFICS) pcre_newline$(OBJSUFFICS) pcre_ord2utf8$(OBJSUFFICS) pcre_refcount$(OBJSUFFICS) pcre_study$(OBJSUFFICS) pcre_tables$(OBJSUFFICS) pcre_valid_utf8$(OBJSUFFICS) pcre_version$(OBJSUFFICS) pcre_xclass$(OBJSUFFICS) pcre_plugin$(OBJSUFFICS) pcre_maketables$(OBJSUFFICS) pcre_ucd$(OBJSUFFICS) pcre_table$(OBJSUFFICS)
-	$(CC) $(DCFLAGS) $(CFLAGS) pcreposix.c
+	$(LN) $(LNOUT)../../$(BUILDDIR)PCREPlugin$(DLSUFFICS) $(LDFLAGS) $(DLFLAGS) pcre_compile$(OBJSUFFICS) pcre_config$(OBJSUFFICS) pcre_dfa_exec$(OBJSUFFICS) pcre_exec$(OBJSUFFICS) pcre_fullinfo$(OBJSUFFICS) pcre_get$(OBJSUFFICS) pcre_globals$(OBJSUFFICS) pcre_newline$(OBJSUFFICS) pcre_ord2utf8$(OBJSUFFICS) pcre_refcount$(OBJSUFFICS) pcre_study$(OBJSUFFICS) pcre_tables$(OBJSUFFICS) pcre_valid_utf8$(OBJSUFFICS) pcre_version$(OBJSUFFICS) pcre_xclass$(OBJSUFFICS) pcre_plugin$(OBJSUFFICS) pcre_maketables$(OBJSUFFICS) pcre_ucd$(OBJSUFFICS) pcre_table$(OBJSUFFICS)
 
-$(BUILDDIR)PCREPlugin$(DLSUFFICS): pcre_compile$(OBJSUFFICS) pcre_config$(OBJSUFFICS) pcre_dfa_exec$(OBJSUFFICS) pcre_exec$(OBJSUFFICS) pcre_fullinfo$(OBJSUFFICS) pcre_get$(OBJSUFFICS) pcre_globals$(OBJSUFFICS) pcre_info$(OBJSUFFICS) pcre_maketables$(OBJSUFFICS) pcre_newline$(OBJSUFFICS) pcre_ord2utf8$(OBJSUFFICS) pcre_refcount$(OBJSUFFICS) pcre_study$(OBJSUFFICS) pcre_tables$(OBJSUFFICS) pcre_try_flipped$(OBJSUFFICS) pcre_ucp_searchfuncs$(OBJSUFFICS) pcre_valid_utf8$(OBJSUFFICS) pcre_version$(OBJSUFFICS) pcre_xclass$(OBJSUFFICS) pcre_dftables$(OBJSUFFICS) pcre_plugin$(OBJSUFFICS) pcreposix$(OBJSUFFICS)
-	$(LN) $(LNOUT)../../$(BUILDDIR)PCREPlugin$(DLSUFFICS) $(LDFLAGS) $(DLFLAGS) pcre_compile$(OBJSUFFICS) pcre_config$(OBJSUFFICS) pcre_dfa_exec$(OBJSUFFICS) pcre_exec$(OBJSUFFICS) pcre_fullinfo$(OBJSUFFICS) pcre_get$(OBJSUFFICS) pcre_globals$(OBJSUFFICS) pcre_info$(OBJSUFFICS) pcre_maketables$(OBJSUFFICS) pcre_newline$(OBJSUFFICS) pcre_ord2utf8$(OBJSUFFICS) pcre_refcount$(OBJSUFFICS) pcre_study$(OBJSUFFICS) pcre_tables$(OBJSUFFICS) pcre_try_flipped$(OBJSUFFICS) pcre_ucp_searchfuncs$(OBJSUFFICS) pcre_valid_utf8$(OBJSUFFICS) pcre_version$(OBJSUFFICS) pcre_xclass$(OBJSUFFICS) pcre_dftables$(OBJSUFFICS) pcre_plugin$(OBJSUFFICS) pcreposix$(OBJSUFFICS)

src/plugins/PCREPlugin/config.h

@@ -1,145 +1,350 @@
+#define PCRE_STATIC
+/* config.h.  Generated from config.h.in by configure.  */
+/* config.h.in.  Generated from configure.ac by autoheader.  */
 
-/* On Unix-like systems config.in is converted by "configure" into config.h.
+/* PCRE is written in Standard C, but there are a few non-standard things it
-Some other environments also support the use of "configure". PCRE is written in
+can cope with, allowing it to run on SunOS4 and other "close to standard"
-Standard C, but there are a few non-standard things it can cope with, allowing
+systems.
-it to run on SunOS4 and other "close to standard" systems.
 
-On a non-Unix-like system you should just copy this file into config.h, and set
+In environments that support the GNU autotools, config.h.in is converted into
-up the macros the way you need them. You should normally change the definitions
+config.h by the "configure" script. In environments that use CMake,
-of HAVE_STRERROR and HAVE_MEMMOVE to 1. Unfortunately, because of the way
+config-cmake.in is converted into config.h. If you are going to build PCRE "by
-autoconf works, these cannot be made the defaults. If your system has bcopy()
+hand" without using "configure" or CMake, you should copy the distributed
-and not memmove(), change the definition of HAVE_BCOPY instead of HAVE_MEMMOVE.
+config.h.generic to config.h, and edit the macro definitions to be the way you
-If your system has neither bcopy() nor memmove(), leave them both as 0; an
+need them. You must then add -DHAVE_CONFIG_H to all of your compile commands,
-emulation function will be used. */
+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,
+but if you do, default values will be taken from config.h for non-boolean
+macros that are not defined on the command line.
+
+Boolean macros such as HAVE_STDLIB_H and SUPPORT_PCRE8 should either be defined
+(conventionally to 1) for TRUE, and not defined at all for FALSE. All such
+macros are listed as a commented #undef in config.h.generic. Macros such as
+MATCH_LIMIT, whose actual value is relevant, have defaults defined, but are
+surrounded by #ifndef/#endif lines so that the value can be overridden by -D.
+
+PCRE uses memmove() if HAVE_MEMMOVE is defined; otherwise it uses bcopy() if
+HAVE_BCOPY is defined. If your system has neither bcopy() nor memmove(), make
+sure both macros are undefined; an emulation function will then be used. */
+
+/* By default, the \R escape sequence matches any Unicode line ending
+   character or sequence of characters. If BSR_ANYCRLF is defined (to any
+   value), 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. */
+/* #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",
+   character codes, define this macro to any value. You must also edit the
-this can be done via --enable-ebcdic. */
+   NEWLINE macro below to set a suitable EBCDIC newline, commonly 21 (0x15).
+   On systems that can use "configure" or CMake to set EBCDIC, NEWLINE is
+   automatically adjusted. When EBCDIC is set, PCRE assumes that all input
+   strings are in EBCDIC. If you do not define this macro, PCRE will assume
+   input strings are ASCII or UTF-8/16/32 Unicode. It is not possible to build
+   a version of PCRE that supports both EBCDIC and UTF-8/16/32. */
+/* #undef EBCDIC */
 
-#ifndef EBCDIC
+/* In an EBCDIC environment, define this macro to any value to arrange for the
-#define EBCDIC 0
+   NL character to be 0x25 instead of the default 0x15. NL plays the role that
-#endif
+   LF does in an ASCII/Unicode environment. The value must also be set in the
+   NEWLINE macro below. On systems that can use "configure" or CMake to set
+   EBCDIC_NL25, the adjustment of NEWLINE is automatic. */
+/* #undef EBCDIC_NL25 */
 
-#define PCRE_STATIC
+/* Define to 1 if you have the `bcopy' function. */
+/* #undef HAVE_BCOPY */
 
-/* If you are compiling for a system other than a Unix-like system or Win32,
+/* Define to 1 if you have the <bits/type_traits.h> header file. */
-and it needs some magic to be inserted before the definition of a function that
+/* #undef HAVE_BITS_TYPE_TRAITS_H */
-is exported by the library, define this macro to contain the relevant magic. If
-you do not define this macro, it defaults to "extern" for a C compiler and
-"extern C" for a C++ compiler on non-Win32 systems. This macro apears at the
-start of every exported function that is part of the external API. It does not
-appear on functions that are "external" in the C sense, but which are internal
-to the library. */
 
-/* #define PCRE_DATA_SCOPE */
+/* Define to 1 if you have the <bzlib.h> header file. */
+/* #undef HAVE_BZLIB_H */
 
-/* Define the following macro to empty if the "const" keyword does not work. */
+/* Define to 1 if you have the <dirent.h> header file. */
+/* #undef HAVE_DIRENT_H */
 
-#undef const
+/* Define to 1 if you have the <dlfcn.h> header file. */
+/* #undef HAVE_DLFCN_H */
 
-/* Define the following macro to "unsigned" if <stddef.h> does not define
+/* Define to 1 if you have the <editline/readline.h> header file. */
-size_t. */
+/* #undef HAVE_EDITLINE_READLINE_H */
 
-#undef size_t
+/* Define to 1 if you have the <edit/readline/readline.h> header file. */
+/* #undef HAVE_EDIT_READLINE_READLINE_H */
 
-/* The following two definitions are mainly for the benefit of SunOS4, which
+/* Define to 1 if you have the <inttypes.h> header file. */
-does not have the strerror() or memmove() functions that should be present in
+/* #undef HAVE_INTTYPES_H */
-all Standard C libraries. The macros HAVE_STRERROR and HAVE_MEMMOVE should
-normally be defined with the value 1 for other systems, but unfortunately we
-cannot make this the default because "configure" files generated by autoconf
-will only change 0 to 1; they won't change 1 to 0 if the functions are not
-found. */
 
-#define HAVE_STRERROR 0
+/* Define to 1 if you have the <limits.h> header file. */
-#define HAVE_MEMMOVE  0
+/* #undef HAVE_LIMITS_H */
 
-/* There are some non-Unix-like systems that don't even have bcopy(). If this
+/* Define to 1 if the system has the type `long long'. */
-macro is false, an emulation is used. If HAVE_MEMMOVE is set to 1, the value of
+/* #undef HAVE_LONG_LONG */
-HAVE_BCOPY is not relevant. */
 
-#define HAVE_BCOPY    0
+/* Define to 1 if you have the `memmove' function. */
+/* #undef HAVE_MEMMOVE */
 
-/* The value of NEWLINE determines the newline character. The default is to
+/* Define to 1 if you have the <memory.h> header file. */
-leave it up to the compiler, but some sites want to force a particular value.
+/* #undef HAVE_MEMORY_H */
-On Unix-like systems, "configure" can be used to override this default. */
 
-#ifndef NEWLINE
+/* Define if you have POSIX threads libraries and header files. */
-#define NEWLINE '\n'
+/* #undef HAVE_PTHREAD */
-#endif
 
-/* The value of LINK_SIZE determines the number of bytes used to store links as
+/* Have PTHREAD_PRIO_INHERIT. */
-offsets within the compiled regex. The default is 2, which allows for compiled
+/* #undef HAVE_PTHREAD_PRIO_INHERIT */
-patterns up to 64K long. This covers the vast majority of cases. However, PCRE
-can also be compiled to use 3 or 4 bytes instead. This allows for longer
-patterns in extreme cases. On systems that support it, "configure" can be used
-to override this default. */
 
+/* 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 */
+
+/* Define to 1 if you have the <stdlib.h> header file. */
+/* #undef HAVE_STDLIB_H */
+
+/* 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 */
+
+/* Define to 1 if you have the <string.h> header file. */
+/* #undef HAVE_STRING_H */
+
+/* Define to 1 if you have `strtoimax'. */
+/* #undef HAVE_STRTOIMAX */
+
+/* Define to 1 if you have `strtoll'. */
+/* #undef HAVE_STRTOLL */
+
+/* Define to 1 if you have `strtoq'. */
+/* #undef HAVE_STRTOQ */
+
+/* Define to 1 if you have the <sys/stat.h> header file. */
+/* #undef HAVE_SYS_STAT_H */
+
+/* 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 */
+
+/* Define to 1 if the system has the type `unsigned long long'. */
+/* #undef HAVE_UNSIGNED_LONG_LONG */
+
+/* Define to 1 if the compiler supports simple visibility declarations. */
+/* #undef HAVE_VISIBILITY */
+
+/* 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 `_strtoi64'. */
+/* #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.
+   However, PCRE can also be compiled to use 3 or 4 bytes instead. This allows
+   for longer patterns in extreme cases. */
 #ifndef LINK_SIZE
 #define LINK_SIZE 2
 #endif
 
-/* When calling PCRE via the POSIX interface, additional working storage is
+/* Define to the sub-directory where libtool stores uninstalled libraries. */
-required for holding the pointers to capturing substrings because PCRE requires
+/* This is ignored unless you are using libtool. */
-three integers per substring, whereas the POSIX interface provides only two. If
+#ifndef LT_OBJDIR
-the number of expected substrings is small, the wrapper function uses space on
+#define LT_OBJDIR ".libs/"
-the stack, because this is faster than using malloc() for each call. The
-threshold above which the stack is no longer used is defined by POSIX_MALLOC_
-THRESHOLD. On systems that support it, "configure" can be used to override this
-default. */
-
-#ifndef POSIX_MALLOC_THRESHOLD
-#define POSIX_MALLOC_THRESHOLD 10
 #endif
 
-/* PCRE uses recursive function calls to handle backtracking while matching.
+/* The value of MATCH_LIMIT determines the default number of times the
-This can sometimes be a problem on systems that have stacks of limited size.
+   internal match() function can be called during a single execution of
-Define NO_RECURSE to get a version that doesn't use recursion in the match()
+   pcre_exec(). There is a runtime interface for setting a different limit.
-function; instead it creates its own stack by steam using pcre_recurse_malloc()
+   The limit exists in order to catch runaway regular expressions that take
-to obtain memory from the heap. For more detail, see the comments and other
+   for ever to determine that they do not match. The default is set very large
-stuff just above the match() function. On systems that support it, "configure"
+   so that it does not accidentally catch legitimate cases. */
-can be used to set this in the Makefile (use --disable-stack-for-recursion). */
-
-/* #define NO_RECURSE */
-
-/* The value of MATCH_LIMIT determines the default number of times the internal
-match() function can be called during a single execution of pcre_exec(). There
-is a runtime interface for setting a different limit. The limit exists in order
-to catch runaway regular expressions that take for ever to determine that they
-do not match. The default is set very large so that it does not accidentally
-catch legitimate cases. On systems that support it, "configure" can be used to
-override this default default. */
-
 #ifndef MATCH_LIMIT
 #define MATCH_LIMIT 10000000
 #endif
 
 /* The above limit applies to all calls of match(), whether or not they
-increase the recursion depth. In some environments it is desirable to limit the
+   increase the recursion depth. In some environments it is desirable to limit
-depth of recursive calls of match() more strictly, in order to restrict the
+   the depth of recursive calls of match() more strictly, in order to restrict
-maximum amount of stack (or heap, if NO_RECURSE is defined) that is used. The
+   the maximum amount of stack (or heap, if NO_RECURSE is defined) that is
-value of MATCH_LIMIT_RECURSION applies only to recursive calls of match(). To
+   used. The value of MATCH_LIMIT_RECURSION applies only to recursive calls of
-have any useful effect, it must be less than the value of MATCH_LIMIT. There is
+   match(). To have any useful effect, it must be less than the value of
-a runtime method for setting a different limit. On systems that support it,
+   MATCH_LIMIT. The default is to use the same value as MATCH_LIMIT. There is
-"configure" can be used to override this default default. */
+   a runtime method for setting a different limit. */
-
 #ifndef MATCH_LIMIT_RECURSION
 #define MATCH_LIMIT_RECURSION MATCH_LIMIT
 #endif
 
-/* These three limits are parameterized just in case anybody ever wants to
+/* This limit is parameterized just in case anybody ever wants to change it.
-change them. Care must be taken if they are increased, because they guard
+   Care must be taken if it is increased, because it guards against integer
-against integer overflow caused by enormously large patterns. */
+   overflow caused by enormously large patterns. */
-
-#ifndef MAX_NAME_SIZE
-#define MAX_NAME_SIZE 32
-#endif
-
 #ifndef MAX_NAME_COUNT
 #define MAX_NAME_COUNT 10000
 #endif
 
-#ifndef MAX_DUPLENGTH
+/* This limit is parameterized just in case anybody ever wants to change it.
-#define MAX_DUPLENGTH 30000
+   Care must be taken if it is increased, because it guards against integer
+   overflow caused by enormously large patterns. */
+#ifndef MAX_NAME_SIZE
+#define MAX_NAME_SIZE 32
 #endif
 
-/* End */
+/* The value of NEWLINE determines the default newline character sequence.
+   PCRE client programs can override this by selecting other values at run
+   time. In ASCII environments, the value can be 10 (LF), 13 (CR), or 3338
+   (CRLF); in EBCDIC environments the value can be 21 or 37 (LF), 13 (CR), or
+   3349 or 3365 (CRLF) because there are two alternative codepoints (0x15 and
+   0x25) that are used as the NL line terminator that is equivalent to ASCII
+   LF. In both ASCII and EBCDIC environments the value can also be -1 (ANY),
+   or -2 (ANYCRLF). */
+#ifndef NEWLINE
+#define NEWLINE 10
+#endif
+
+/* PCRE uses recursive function calls to handle backtracking while matching.
+   This can sometimes be a problem on systems that have stacks of limited
+   size. Define NO_RECURSE to any value to get a version that doesn't use
+   recursion in the match() function; instead it creates its own stack by
+   steam using pcre_recurse_malloc() to obtain memory from the heap. For more
+   detail, see the comments and other stuff just above the match() function.
+   */
+/* #undef NO_RECURSE */
+
+/* Name of package */
+#define PACKAGE "pcre"
+
+/* Define to the address where bug reports for this package should be sent. */
+#define PACKAGE_BUGREPORT ""
+
+/* Define to the full name of this package. */
+#define PACKAGE_NAME "PCRE"
+
+/* Define to the full name and version of this package. */
+#define PACKAGE_STRING "PCRE 8.39"
+
+/* Define to the one symbol short name of this package. */
+#define PACKAGE_TARNAME "pcre"
+
+/* Define to the home page for this package. */
+#define PACKAGE_URL ""
+
+/* Define to the version of this package. */
+#define PACKAGE_VERSION "8.39"
+
+/* The value of PARENS_NEST_LIMIT specifies the maximum depth of nested
+   parentheses (of any kind) in a pattern. This limits the amount of system
+   stack that is used while compiling a pattern. */
+#ifndef PARENS_NEST_LIMIT
+#define PARENS_NEST_LIMIT 250
+#endif
+
+/* The value of PCREGREP_BUFSIZE determines the size of buffer used by
+   pcregrep to hold parts of the file it is searching. This is also the
+   minimum value. The actual amount of memory used by pcregrep is three times
+   this number, because it allows for the buffering of "before" and "after"
+   lines. */
+#ifndef PCREGREP_BUFSIZE
+#define PCREGREP_BUFSIZE 20480
+#endif
+
+/* If you are compiling for a system other than a Unix-like system or
+   Win32, and it needs some magic to be inserted before the definition
+   of a function that is exported by the library, define this macro to
+   contain the relevant magic. If you do not define this macro, a suitable
+    __declspec value is used for Windows systems; in other environments
+   "extern" is used for a C compiler and "extern C" for a C++ compiler.
+   This macro apears at the start of every exported function that is part
+   of the external API. It does not appear on functions that are "external"
+   in the C sense, but which are internal to the library. */
+/* #undef PCRE_EXP_DEFN */
+
+/* Define to any value if linking statically (TODO: make nice with Libtool) */
+/* #undef PCRE_STATIC */
+
+/* When calling PCRE via the POSIX interface, additional working storage is
+   required for holding the pointers to capturing substrings because PCRE
+   requires three integers per substring, whereas the POSIX interface provides
+   only two. If the number of expected substrings is small, the wrapper
+   function uses space on the stack, because this is faster than using
+   malloc() for each call. The threshold above which the stack is no longer
+   used is defined by POSIX_MALLOC_THRESHOLD. */
+#ifndef POSIX_MALLOC_THRESHOLD
+#define POSIX_MALLOC_THRESHOLD 10
+#endif
+
+/* Define to necessary symbol if this constant uses a non-standard name on
+   your system. */
+/* #undef PTHREAD_CREATE_JOINABLE */
+
+/* Define to 1 if you have the ANSI C header files. */
+/* #undef STDC_HEADERS */
+
+/* Define to any value to enable support for Just-In-Time compiling. */
+/* #undef SUPPORT_JIT */
+
+/* Define to any value to allow pcregrep to be linked with libbz2, so that it
+   is able to handle .bz2 files. */
+/* #undef SUPPORT_LIBBZ2 */
+
+/* Define to any value to allow pcretest to be linked with libedit. */
+/* #undef SUPPORT_LIBEDIT */
+
+/* Define to any value to allow pcretest to be linked with libreadline. */
+/* #undef SUPPORT_LIBREADLINE */
+
+/* Define to any value to allow pcregrep to be linked with libz, so that it is
+   able to handle .gz files. */
+/* #undef SUPPORT_LIBZ */
+
+/* Define to any value to enable the 16 bit PCRE library. */
+/* #undef SUPPORT_PCRE16 */
+
+/* Define to any value to enable the 32 bit PCRE library. */
+/* #undef SUPPORT_PCRE32 */
+
+/* Define to any value to enable the 8 bit PCRE library. */
+/* #undef SUPPORT_PCRE8 */
+
+/* Define to any value to enable JIT support in pcregrep. */
+/* #undef SUPPORT_PCREGREP_JIT */
+
+/* Define to any value to enable support for Unicode properties. */
+/* #undef SUPPORT_UCP */
+
+/* Define to any value to enable support for the UTF-8/16/32 Unicode encoding.
+   This will work even in an EBCDIC environment, but it is incompatible with
+   the EBCDIC macro. That is, PCRE can support *either* EBCDIC code *or*
+   ASCII/UTF-8/16/32, but not both at once. */
+/* #undef SUPPORT_UTF */
+
+/* Define to any value for valgrind support to find invalid memory reads. */
+/* #undef SUPPORT_VALGRIND */
+
+/* Version number of package */
+#define VERSION "8.39"
+
+/* Define to empty if `const' does not conform to ANSI C. */
+/* #undef const */
+
+/* Define to the type of a signed integer type of width exactly 64 bits if
+   such a type exists and the standard includes do not define it. */
+/* #undef int64_t */
+
+/* Define to `unsigned int' if <sys/types.h> does not define. */
+/* #undef size_t */

src/plugins/PCREPlugin/pcre.h

@@ -1,4 +1,3 @@
-#include "config.h"
 /*************************************************
 *       Perl-Compatible Regular Expressions      *
 *************************************************/
@@ -6,7 +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) 1997-2014 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -42,10 +41,10 @@ POSSIBILITY OF SUCH DAMAGE.
 
 /* The current PCRE version information. */
 
-#define PCRE_MAJOR          7
+#define PCRE_MAJOR          8
-#define PCRE_MINOR          4
+#define PCRE_MINOR          39
 #define PCRE_PRERELEASE     
-#define PCRE_DATE           2007-09-21
+#define PCRE_DATE           2016-06-14
 
 /* 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
@@ -96,35 +95,80 @@ it is needed here for malloc. */
 extern "C" {
 #endif
 
-/* Options */
+/* Public options. Some are compile-time only, some are run-time only, and some
+are both. Most of the compile-time options are saved with the compiled regex so
+that they can be inspected during studying (and therefore JIT compiling). Note
+that pcre_study() has its own set of options. Originally, all the options
+defined here used distinct bits. However, almost all the bits in a 32-bit word
+are now used, so in order to conserve them, option bits that were previously
+only recognized at matching time (i.e. by pcre_exec() or pcre_dfa_exec()) may
+also be used for compile-time options that affect only compiling and are not
+relevant for studying or JIT compiling.
 
-#define PCRE_CASELESS           0x00000001
+Some options for pcre_compile() change its behaviour but do not affect the
-#define PCRE_MULTILINE          0x00000002
+behaviour of the execution functions. Other options are passed through to the
-#define PCRE_DOTALL             0x00000004
+execution functions and affect their behaviour, with or without affecting the
-#define PCRE_EXTENDED           0x00000008
+behaviour of pcre_compile().
-#define PCRE_ANCHORED           0x00000010
+
-#define PCRE_DOLLAR_ENDONLY     0x00000020
+Options that can be passed to pcre_compile() are tagged Cx below, with these
-#define PCRE_EXTRA              0x00000040
+variants:
-#define PCRE_NOTBOL             0x00000080
+
-#define PCRE_NOTEOL             0x00000100
+C1   Affects compile only
-#define PCRE_UNGREEDY           0x00000200
+C2   Does not affect compile; affects exec, dfa_exec
-#define PCRE_NOTEMPTY           0x00000400
+C3   Affects compile, exec, dfa_exec
-#define PCRE_UTF8               0x00000800
+C4   Affects compile, exec, dfa_exec, study
-#define PCRE_NO_AUTO_CAPTURE    0x00001000
+C5   Affects compile, exec, study
-#define PCRE_NO_UTF8_CHECK      0x00002000
+
-#define PCRE_AUTO_CALLOUT       0x00004000
+Options that can be set for pcre_exec() and/or pcre_dfa_exec() are flagged with
-#define PCRE_PARTIAL            0x00008000
+E and D, respectively. They take precedence over C3, C4, and C5 settings passed
-#define PCRE_DFA_SHORTEST       0x00010000
+from pcre_compile(). Those that are compatible with JIT execution are flagged
-#define PCRE_DFA_RESTART        0x00020000
+with J. */
-#define PCRE_FIRSTLINE          0x00040000
+
-#define PCRE_DUPNAMES           0x00080000
+#define PCRE_CASELESS           0x00000001  /* C1       */
-#define PCRE_NEWLINE_CR         0x00100000
+#define PCRE_MULTILINE          0x00000002  /* C1       */
-#define PCRE_NEWLINE_LF         0x00200000
+#define PCRE_DOTALL             0x00000004  /* C1       */
-#define PCRE_NEWLINE_CRLF       0x00300000
+#define PCRE_EXTENDED           0x00000008  /* C1       */
-#define PCRE_NEWLINE_ANY        0x00400000
+#define PCRE_ANCHORED           0x00000010  /* C4 E D   */
-#define PCRE_NEWLINE_ANYCRLF    0x00500000
+#define PCRE_DOLLAR_ENDONLY     0x00000020  /* C2       */
-#define PCRE_BSR_ANYCRLF        0x00800000
+#define PCRE_EXTRA              0x00000040  /* C1       */
-#define PCRE_BSR_UNICODE        0x01000000
+#define PCRE_NOTBOL             0x00000080  /*    E D J */
+#define PCRE_NOTEOL             0x00000100  /*    E D J */
+#define PCRE_UNGREEDY           0x00000200  /* C1       */
+#define PCRE_NOTEMPTY           0x00000400  /*    E D J */
+#define PCRE_UTF8               0x00000800  /* C4        )          */
+#define PCRE_UTF16              0x00000800  /* C4        ) Synonyms */
+#define PCRE_UTF32              0x00000800  /* C4        )          */
+#define PCRE_NO_AUTO_CAPTURE    0x00001000  /* C1       */
+#define PCRE_NO_UTF8_CHECK      0x00002000  /* C1 E D J  )          */
+#define PCRE_NO_UTF16_CHECK     0x00002000  /* C1 E D J  ) Synonyms */
+#define PCRE_NO_UTF32_CHECK     0x00002000  /* C1 E D J  )          */
+#define PCRE_AUTO_CALLOUT       0x00004000  /* C1       */
+#define PCRE_PARTIAL_SOFT       0x00008000  /*    E D J  ) Synonyms */
+#define PCRE_PARTIAL            0x00008000  /*    E D J  )          */
+
+/* This pair use the same bit. */
+#define PCRE_NEVER_UTF          0x00010000  /* C1        ) Overlaid */
+#define PCRE_DFA_SHORTEST       0x00010000  /*      D    ) Overlaid */
+
+/* This pair use the same bit. */
+#define PCRE_NO_AUTO_POSSESS    0x00020000  /* C1        ) Overlaid */
+#define PCRE_DFA_RESTART        0x00020000  /*      D    ) Overlaid */
+
+#define PCRE_FIRSTLINE          0x00040000  /* C3       */
+#define PCRE_DUPNAMES           0x00080000  /* C1       */
+#define PCRE_NEWLINE_CR         0x00100000  /* C3 E D   */
+#define PCRE_NEWLINE_LF         0x00200000  /* C3 E D   */
+#define PCRE_NEWLINE_CRLF       0x00300000  /* C3 E D   */
+#define PCRE_NEWLINE_ANY        0x00400000  /* C3 E D   */
+#define PCRE_NEWLINE_ANYCRLF    0x00500000  /* C3 E D   */
+#define PCRE_BSR_ANYCRLF        0x00800000  /* C3 E D   */
+#define PCRE_BSR_UNICODE        0x01000000  /* C3 E D   */
+#define PCRE_JAVASCRIPT_COMPAT  0x02000000  /* C5       */
+#define PCRE_NO_START_OPTIMIZE  0x04000000  /* C2 E D    ) Synonyms */
+#define PCRE_NO_START_OPTIMISE  0x04000000  /* C2 E D    )          */
+#define PCRE_PARTIAL_HARD       0x08000000  /*    E D J */
+#define PCRE_NOTEMPTY_ATSTART   0x10000000  /*    E D J */
+#define PCRE_UCP                0x20000000  /* C3       */
 
 /* Exec-time and get/set-time error codes */
 
@@ -138,8 +182,11 @@ extern "C" {
 #define PCRE_ERROR_NOSUBSTRING      (-7)
 #define PCRE_ERROR_MATCHLIMIT       (-8)
 #define PCRE_ERROR_CALLOUT          (-9)  /* Never used by PCRE itself */
-#define PCRE_ERROR_BADUTF8        (-10)
+#define PCRE_ERROR_BADUTF8         (-10)  /* Same for 8/16/32 */
-#define PCRE_ERROR_BADUTF8_OFFSET (-11)
+#define PCRE_ERROR_BADUTF16        (-10)  /* Same for 8/16/32 */
+#define PCRE_ERROR_BADUTF32        (-10)  /* Same for 8/16/32 */
+#define PCRE_ERROR_BADUTF8_OFFSET  (-11)  /* Same for 8/16 */
+#define PCRE_ERROR_BADUTF16_OFFSET (-11)  /* Same for 8/16 */
 #define PCRE_ERROR_PARTIAL         (-12)
 #define PCRE_ERROR_BADPARTIAL      (-13)
 #define PCRE_ERROR_INTERNAL        (-14)
@@ -152,6 +199,58 @@ extern "C" {
 #define PCRE_ERROR_RECURSIONLIMIT  (-21)
 #define PCRE_ERROR_NULLWSLIMIT     (-22)  /* No longer actually used */
 #define PCRE_ERROR_BADNEWLINE      (-23)
+#define PCRE_ERROR_BADOFFSET       (-24)
+#define PCRE_ERROR_SHORTUTF8       (-25)
+#define PCRE_ERROR_SHORTUTF16      (-25)  /* Same for 8/16 */
+#define PCRE_ERROR_RECURSELOOP     (-26)
+#define PCRE_ERROR_JIT_STACKLIMIT  (-27)
+#define PCRE_ERROR_BADMODE         (-28)
+#define PCRE_ERROR_BADENDIANNESS   (-29)
+#define PCRE_ERROR_DFA_BADRESTART  (-30)
+#define PCRE_ERROR_JIT_BADOPTION   (-31)
+#define PCRE_ERROR_BADLENGTH       (-32)
+#define PCRE_ERROR_UNSET           (-33)
+
+/* Specific error codes for UTF-8 validity checks */
+
+#define PCRE_UTF8_ERR0               0
+#define PCRE_UTF8_ERR1               1
+#define PCRE_UTF8_ERR2               2
+#define PCRE_UTF8_ERR3               3
+#define PCRE_UTF8_ERR4               4
+#define PCRE_UTF8_ERR5               5
+#define PCRE_UTF8_ERR6               6
+#define PCRE_UTF8_ERR7               7
+#define PCRE_UTF8_ERR8               8
+#define PCRE_UTF8_ERR9               9
+#define PCRE_UTF8_ERR10             10
+#define PCRE_UTF8_ERR11             11
+#define PCRE_UTF8_ERR12             12
+#define PCRE_UTF8_ERR13             13
+#define PCRE_UTF8_ERR14             14
+#define PCRE_UTF8_ERR15             15
+#define PCRE_UTF8_ERR16             16
+#define PCRE_UTF8_ERR17             17
+#define PCRE_UTF8_ERR18             18
+#define PCRE_UTF8_ERR19             19
+#define PCRE_UTF8_ERR20             20
+#define PCRE_UTF8_ERR21             21
+#define PCRE_UTF8_ERR22             22  /* Unused (was non-character) */
+
+/* Specific error codes for UTF-16 validity checks */
+
+#define PCRE_UTF16_ERR0              0
+#define PCRE_UTF16_ERR1              1
+#define PCRE_UTF16_ERR2              2
+#define PCRE_UTF16_ERR3              3
+#define PCRE_UTF16_ERR4              4  /* Unused (was non-character) */
+
+/* Specific error codes for UTF-32 validity checks */
+
+#define PCRE_UTF32_ERR0              0
+#define PCRE_UTF32_ERR1              1
+#define PCRE_UTF32_ERR2              2  /* Unused (was non-character) */
+#define PCRE_UTF32_ERR3              3
 
 /* Request types for pcre_fullinfo() */
 
@@ -171,6 +270,17 @@ extern "C" {
 #define PCRE_INFO_OKPARTIAL         12
 #define PCRE_INFO_JCHANGED          13
 #define PCRE_INFO_HASCRORLF         14
+#define PCRE_INFO_MINLENGTH         15
+#define PCRE_INFO_JIT               16
+#define PCRE_INFO_JITSIZE           17
+#define PCRE_INFO_MAXLOOKBEHIND     18
+#define PCRE_INFO_FIRSTCHARACTER    19
+#define PCRE_INFO_FIRSTCHARACTERFLAGS 20
+#define PCRE_INFO_REQUIREDCHAR      21
+#define PCRE_INFO_REQUIREDCHARFLAGS 22
+#define PCRE_INFO_MATCHLIMIT        23
+#define PCRE_INFO_RECURSIONLIMIT    24
+#define PCRE_INFO_MATCH_EMPTY       25
 
 /* Request types for pcre_config(). Do not re-arrange, in order to remain
 compatible. */
@@ -184,8 +294,21 @@ compatible. */
 #define PCRE_CONFIG_UNICODE_PROPERTIES      6
 #define PCRE_CONFIG_MATCH_LIMIT_RECURSION   7
 #define PCRE_CONFIG_BSR                     8
+#define PCRE_CONFIG_JIT                     9
+#define PCRE_CONFIG_UTF16                  10
+#define PCRE_CONFIG_JITTARGET              11
+#define PCRE_CONFIG_UTF32                  12
+#define PCRE_CONFIG_PARENS_LIMIT           13
 
-/* Bit flags for the pcre_extra structure. Do not re-arrange or redefine
+/* Request types for pcre_study(). Do not re-arrange, in order to remain
+compatible. */
+
+#define PCRE_STUDY_JIT_COMPILE                0x0001
+#define PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE   0x0002
+#define PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE   0x0004
+#define PCRE_STUDY_EXTRA_NEEDED               0x0008
+
+/* Bit flags for the pcre[16|32]_extra structure. Do not re-arrange or redefine
 these bits, just add new ones on the end, in order to remain compatible. */
 
 #define PCRE_EXTRA_STUDY_DATA             0x0001
@@ -193,12 +316,51 @@ these bits, just add new ones on the end, in order to remain compatible. */
 #define PCRE_EXTRA_CALLOUT_DATA           0x0004
 #define PCRE_EXTRA_TABLES                 0x0008
 #define PCRE_EXTRA_MATCH_LIMIT_RECURSION  0x0010
+#define PCRE_EXTRA_MARK                   0x0020
+#define PCRE_EXTRA_EXECUTABLE_JIT         0x0040
 
 /* Types */
 
 struct real_pcre;                 /* declaration; the definition is private  */
 typedef struct real_pcre pcre;
 
+struct real_pcre16;               /* declaration; the definition is private  */
+typedef struct real_pcre16 pcre16;
+
+struct real_pcre32;               /* declaration; the definition is private  */
+typedef struct real_pcre32 pcre32;
+
+struct real_pcre_jit_stack;       /* declaration; the definition is private  */
+typedef struct real_pcre_jit_stack pcre_jit_stack;
+
+struct real_pcre16_jit_stack;     /* declaration; the definition is private  */
+typedef struct real_pcre16_jit_stack pcre16_jit_stack;
+
+struct real_pcre32_jit_stack;     /* declaration; the definition is private  */
+typedef struct real_pcre32_jit_stack pcre32_jit_stack;
+
+/* If PCRE is compiled with 16 bit character support, PCRE_UCHAR16 must contain
+a 16 bit wide signed data type. Otherwise it can be a dummy data type since
+pcre16 functions are not implemented. There is a check for this in pcre_internal.h. */
+#ifndef PCRE_UCHAR16
+#define PCRE_UCHAR16 unsigned short
+#endif
+
+#ifndef PCRE_SPTR16
+#define PCRE_SPTR16 const PCRE_UCHAR16 *
+#endif
+
+/* If PCRE is compiled with 32 bit character support, PCRE_UCHAR32 must contain
+a 32 bit wide signed data type. Otherwise it can be a dummy data type since
+pcre32 functions are not implemented. There is a check for this in pcre_internal.h. */
+#ifndef PCRE_UCHAR32
+#define PCRE_UCHAR32 unsigned int
+#endif
+
+#ifndef PCRE_SPTR32
+#define PCRE_SPTR32 const PCRE_UCHAR32 *
+#endif
+
 /* When PCRE is compiled as a C++ library, the subject pointer type can be
 replaced with a custom type. For conventional use, the public interface is a
 const char *. */
@@ -218,8 +380,36 @@ typedef struct pcre_extra {
   void *callout_data;             /* Data passed back in callouts */
   const unsigned char *tables;    /* Pointer to character tables */
   unsigned long int match_limit_recursion; /* Max recursive calls to match() */
+  unsigned char **mark;           /* For passing back a mark pointer */
+  void *executable_jit;           /* Contains a pointer to a compiled jit code */
 } pcre_extra;
 
+/* Same structure as above, but with 16 bit char pointers. */
+
+typedef struct pcre16_extra {
+  unsigned long int flags;        /* Bits for which fields are set */
+  void *study_data;               /* Opaque data from pcre_study() */
+  unsigned long int match_limit;  /* Maximum number of calls to match() */
+  void *callout_data;             /* Data passed back in callouts */
+  const unsigned char *tables;    /* Pointer to character tables */
+  unsigned long int match_limit_recursion; /* Max recursive calls to match() */
+  PCRE_UCHAR16 **mark;            /* For passing back a mark pointer */
+  void *executable_jit;           /* Contains a pointer to a compiled jit code */
+} pcre16_extra;
+
+/* Same structure as above, but with 32 bit char pointers. */
+
+typedef struct pcre32_extra {
+  unsigned long int flags;        /* Bits for which fields are set */
+  void *study_data;               /* Opaque data from pcre_study() */
+  unsigned long int match_limit;  /* Maximum number of calls to match() */
+  void *callout_data;             /* Data passed back in callouts */
+  const unsigned char *tables;    /* Pointer to character tables */
+  unsigned long int match_limit_recursion; /* Max recursive calls to match() */
+  PCRE_UCHAR32 **mark;            /* For passing back a mark pointer */
+  void *executable_jit;           /* Contains a pointer to a compiled jit code */
+} pcre32_extra;
+
 /* The structure for passing out data via the pcre_callout_function. We use a
 structure so that new fields can be added on the end in future versions,
 without changing the API of the function, thereby allowing old clients to work
@@ -240,9 +430,55 @@ typedef struct pcre_callout_block {
   /* ------------------- Added for Version 1 -------------------------- */
   int          pattern_position;  /* Offset to next item in the pattern */
   int          next_item_length;  /* Length of next item in the pattern */
+  /* ------------------- Added for Version 2 -------------------------- */
+  const unsigned char *mark;      /* Pointer to current mark or NULL    */
   /* ------------------------------------------------------------------ */
 } pcre_callout_block;
 
+/* Same structure as above, but with 16 bit char pointers. */
+
+typedef struct pcre16_callout_block {
+  int          version;           /* Identifies version of block */
+  /* ------------------------ Version 0 ------------------------------- */
+  int          callout_number;    /* Number compiled into pattern */
+  int         *offset_vector;     /* The offset vector */
+  PCRE_SPTR16  subject;           /* The subject being matched */
+  int          subject_length;    /* The length of the subject */
+  int          start_match;       /* Offset to start of this match attempt */
+  int          current_position;  /* Where we currently are in the subject */
+  int          capture_top;       /* Max current capture */
+  int          capture_last;      /* Most recently closed capture */
+  void        *callout_data;      /* Data passed in with the call */
+  /* ------------------- Added for Version 1 -------------------------- */
+  int          pattern_position;  /* Offset to next item in the pattern */
+  int          next_item_length;  /* Length of next item in the pattern */
+  /* ------------------- Added for Version 2 -------------------------- */
+  const PCRE_UCHAR16 *mark;       /* Pointer to current mark or NULL    */
+  /* ------------------------------------------------------------------ */
+} pcre16_callout_block;
+
+/* Same structure as above, but with 32 bit char pointers. */
+
+typedef struct pcre32_callout_block {
+  int          version;           /* Identifies version of block */
+  /* ------------------------ Version 0 ------------------------------- */
+  int          callout_number;    /* Number compiled into pattern */
+  int         *offset_vector;     /* The offset vector */
+  PCRE_SPTR32  subject;           /* The subject being matched */
+  int          subject_length;    /* The length of the subject */
+  int          start_match;       /* Offset to start of this match attempt */
+  int          current_position;  /* Where we currently are in the subject */
+  int          capture_top;       /* Max current capture */
+  int          capture_last;      /* Most recently closed capture */
+  void        *callout_data;      /* Data passed in with the call */
+  /* ------------------- Added for Version 1 -------------------------- */
+  int          pattern_position;  /* Offset to next item in the pattern */
+  int          next_item_length;  /* Length of next item in the pattern */
+  /* ------------------- Added for Version 2 -------------------------- */
+  const PCRE_UCHAR32 *mark;       /* Pointer to current mark or NULL    */
+  /* ------------------------------------------------------------------ */
+} pcre32_callout_block;
+
 /* Indirection for store get and free functions. These can be set to
 alternative malloc/free functions if required. Special ones are used in the
 non-recursive case for "frames". There is also an optional callout function
@@ -255,47 +491,184 @@ PCRE_EXP_DECL void  (*pcre_free)(void *);
 PCRE_EXP_DECL void *(*pcre_stack_malloc)(size_t);
 PCRE_EXP_DECL void  (*pcre_stack_free)(void *);
 PCRE_EXP_DECL int   (*pcre_callout)(pcre_callout_block *);
+PCRE_EXP_DECL int   (*pcre_stack_guard)(void);
+
+PCRE_EXP_DECL void *(*pcre16_malloc)(size_t);
+PCRE_EXP_DECL void  (*pcre16_free)(void *);
+PCRE_EXP_DECL void *(*pcre16_stack_malloc)(size_t);
+PCRE_EXP_DECL void  (*pcre16_stack_free)(void *);
+PCRE_EXP_DECL int   (*pcre16_callout)(pcre16_callout_block *);
+PCRE_EXP_DECL int   (*pcre16_stack_guard)(void);
+
+PCRE_EXP_DECL void *(*pcre32_malloc)(size_t);
+PCRE_EXP_DECL void  (*pcre32_free)(void *);
+PCRE_EXP_DECL void *(*pcre32_stack_malloc)(size_t);
+PCRE_EXP_DECL void  (*pcre32_stack_free)(void *);
+PCRE_EXP_DECL int   (*pcre32_callout)(pcre32_callout_block *);
+PCRE_EXP_DECL int   (*pcre32_stack_guard)(void);
 #else   /* VPCOMPAT */
 PCRE_EXP_DECL void *pcre_malloc(size_t);
 PCRE_EXP_DECL void  pcre_free(void *);
 PCRE_EXP_DECL void *pcre_stack_malloc(size_t);
 PCRE_EXP_DECL void  pcre_stack_free(void *);
 PCRE_EXP_DECL int   pcre_callout(pcre_callout_block *);
+PCRE_EXP_DECL int   pcre_stack_guard(void);
+
+PCRE_EXP_DECL void *pcre16_malloc(size_t);
+PCRE_EXP_DECL void  pcre16_free(void *);
+PCRE_EXP_DECL void *pcre16_stack_malloc(size_t);
+PCRE_EXP_DECL void  pcre16_stack_free(void *);
+PCRE_EXP_DECL int   pcre16_callout(pcre16_callout_block *);
+PCRE_EXP_DECL int   pcre16_stack_guard(void);
+
+PCRE_EXP_DECL void *pcre32_malloc(size_t);
+PCRE_EXP_DECL void  pcre32_free(void *);
+PCRE_EXP_DECL void *pcre32_stack_malloc(size_t);
+PCRE_EXP_DECL void  pcre32_stack_free(void *);
+PCRE_EXP_DECL int   pcre32_callout(pcre32_callout_block *);
+PCRE_EXP_DECL int   pcre32_stack_guard(void);
 #endif  /* VPCOMPAT */
 
+/* User defined callback which provides a stack just before the match starts. */
+
+typedef pcre_jit_stack *(*pcre_jit_callback)(void *);
+typedef pcre16_jit_stack *(*pcre16_jit_callback)(void *);
+typedef pcre32_jit_stack *(*pcre32_jit_callback)(void *);
+
 /* Exported PCRE functions */
 
 PCRE_EXP_DECL pcre *pcre_compile(const char *, int, const char **, int *,
                   const unsigned char *);
+PCRE_EXP_DECL pcre16 *pcre16_compile(PCRE_SPTR16, int, const char **, int *,
+                  const unsigned char *);
+PCRE_EXP_DECL pcre32 *pcre32_compile(PCRE_SPTR32, int, const char **, int *,
+                  const unsigned char *);
 PCRE_EXP_DECL pcre *pcre_compile2(const char *, int, int *, const char **,
                   int *, const unsigned char *);
+PCRE_EXP_DECL pcre16 *pcre16_compile2(PCRE_SPTR16, int, int *, const char **,
+                  int *, const unsigned char *);
+PCRE_EXP_DECL pcre32 *pcre32_compile2(PCRE_SPTR32, int, int *, const char **,
+                  int *, const unsigned char *);
 PCRE_EXP_DECL int  pcre_config(int, void *);
+PCRE_EXP_DECL int  pcre16_config(int, void *);
+PCRE_EXP_DECL int  pcre32_config(int, void *);
 PCRE_EXP_DECL int  pcre_copy_named_substring(const pcre *, const char *,
                   int *, int, const char *, char *, int);
-PCRE_EXP_DECL int  pcre_copy_substring(const char *, int *, int, int, char *,
+PCRE_EXP_DECL int  pcre16_copy_named_substring(const pcre16 *, PCRE_SPTR16,
-                  int);
+                  int *, int, PCRE_SPTR16, PCRE_UCHAR16 *, int);
+PCRE_EXP_DECL int  pcre32_copy_named_substring(const pcre32 *, PCRE_SPTR32,
+                  int *, int, PCRE_SPTR32, PCRE_UCHAR32 *, int);
+PCRE_EXP_DECL int  pcre_copy_substring(const char *, int *, int, int,
+                  char *, int);
+PCRE_EXP_DECL int  pcre16_copy_substring(PCRE_SPTR16, int *, int, int,
+                  PCRE_UCHAR16 *, int);
+PCRE_EXP_DECL int  pcre32_copy_substring(PCRE_SPTR32, int *, int, int,
+                  PCRE_UCHAR32 *, int);
 PCRE_EXP_DECL int  pcre_dfa_exec(const pcre *, const pcre_extra *,
                   const char *, int, int, int, int *, int , int *, int);
+PCRE_EXP_DECL int  pcre16_dfa_exec(const pcre16 *, const pcre16_extra *,
+                  PCRE_SPTR16, int, int, int, int *, int , int *, int);
+PCRE_EXP_DECL int  pcre32_dfa_exec(const pcre32 *, const pcre32_extra *,
+                  PCRE_SPTR32, int, int, int, int *, int , int *, int);
 PCRE_EXP_DECL int  pcre_exec(const pcre *, const pcre_extra *, PCRE_SPTR,
                    int, int, int, int *, int);
+PCRE_EXP_DECL int  pcre16_exec(const pcre16 *, const pcre16_extra *,
+                   PCRE_SPTR16, int, int, int, int *, int);
+PCRE_EXP_DECL int  pcre32_exec(const pcre32 *, const pcre32_extra *,
+                   PCRE_SPTR32, int, int, int, int *, int);
+PCRE_EXP_DECL int  pcre_jit_exec(const pcre *, const pcre_extra *,
+                   PCRE_SPTR, int, int, int, int *, int,
+                   pcre_jit_stack *);
+PCRE_EXP_DECL int  pcre16_jit_exec(const pcre16 *, const pcre16_extra *,
+                   PCRE_SPTR16, int, int, int, int *, int,
+                   pcre16_jit_stack *);
+PCRE_EXP_DECL int  pcre32_jit_exec(const pcre32 *, const pcre32_extra *,
+                   PCRE_SPTR32, int, int, int, int *, int,
+                   pcre32_jit_stack *);
 PCRE_EXP_DECL void pcre_free_substring(const char *);
+PCRE_EXP_DECL void pcre16_free_substring(PCRE_SPTR16);
+PCRE_EXP_DECL void pcre32_free_substring(PCRE_SPTR32);
 PCRE_EXP_DECL void pcre_free_substring_list(const char **);
+PCRE_EXP_DECL void pcre16_free_substring_list(PCRE_SPTR16 *);
+PCRE_EXP_DECL void pcre32_free_substring_list(PCRE_SPTR32 *);
 PCRE_EXP_DECL int  pcre_fullinfo(const pcre *, const pcre_extra *, int,
                   void *);
+PCRE_EXP_DECL int  pcre16_fullinfo(const pcre16 *, const pcre16_extra *, int,
+                  void *);
+PCRE_EXP_DECL int  pcre32_fullinfo(const pcre32 *, const pcre32_extra *, int,
+                  void *);
 PCRE_EXP_DECL int  pcre_get_named_substring(const pcre *, const char *,
                   int *, int, const char *, const char **);
+PCRE_EXP_DECL int  pcre16_get_named_substring(const pcre16 *, PCRE_SPTR16,
+                  int *, int, PCRE_SPTR16, PCRE_SPTR16 *);
+PCRE_EXP_DECL int  pcre32_get_named_substring(const pcre32 *, PCRE_SPTR32,
+                  int *, int, PCRE_SPTR32, PCRE_SPTR32 *);
 PCRE_EXP_DECL int  pcre_get_stringnumber(const pcre *, const char *);
+PCRE_EXP_DECL int  pcre16_get_stringnumber(const pcre16 *, PCRE_SPTR16);
+PCRE_EXP_DECL int  pcre32_get_stringnumber(const pcre32 *, PCRE_SPTR32);
 PCRE_EXP_DECL int  pcre_get_stringtable_entries(const pcre *, const char *,
                   char **, char **);
+PCRE_EXP_DECL int  pcre16_get_stringtable_entries(const pcre16 *, PCRE_SPTR16,
+                  PCRE_UCHAR16 **, PCRE_UCHAR16 **);
+PCRE_EXP_DECL int  pcre32_get_stringtable_entries(const pcre32 *, PCRE_SPTR32,
+                  PCRE_UCHAR32 **, PCRE_UCHAR32 **);
 PCRE_EXP_DECL int  pcre_get_substring(const char *, int *, int, int,
                   const char **);
+PCRE_EXP_DECL int  pcre16_get_substring(PCRE_SPTR16, int *, int, int,
+                  PCRE_SPTR16 *);
+PCRE_EXP_DECL int  pcre32_get_substring(PCRE_SPTR32, int *, int, int,
+                  PCRE_SPTR32 *);
 PCRE_EXP_DECL int  pcre_get_substring_list(const char *, int *, int,
                   const char ***);
-PCRE_EXP_DECL int  pcre_info(const pcre *, int *, int *);
+PCRE_EXP_DECL int  pcre16_get_substring_list(PCRE_SPTR16, int *, int,
+                  PCRE_SPTR16 **);
+PCRE_EXP_DECL int  pcre32_get_substring_list(PCRE_SPTR32, int *, int,
+                  PCRE_SPTR32 **);
 PCRE_EXP_DECL const unsigned char *pcre_maketables(void);
+PCRE_EXP_DECL const unsigned char *pcre16_maketables(void);
+PCRE_EXP_DECL const unsigned char *pcre32_maketables(void);
 PCRE_EXP_DECL int  pcre_refcount(pcre *, int);
+PCRE_EXP_DECL int  pcre16_refcount(pcre16 *, int);
+PCRE_EXP_DECL int  pcre32_refcount(pcre32 *, int);
 PCRE_EXP_DECL pcre_extra *pcre_study(const pcre *, int, const char **);
+PCRE_EXP_DECL pcre16_extra *pcre16_study(const pcre16 *, int, const char **);
+PCRE_EXP_DECL pcre32_extra *pcre32_study(const pcre32 *, int, const char **);
+PCRE_EXP_DECL void pcre_free_study(pcre_extra *);
+PCRE_EXP_DECL void pcre16_free_study(pcre16_extra *);
+PCRE_EXP_DECL void pcre32_free_study(pcre32_extra *);
 PCRE_EXP_DECL const char *pcre_version(void);
+PCRE_EXP_DECL const char *pcre16_version(void);
+PCRE_EXP_DECL const char *pcre32_version(void);
+
+/* Utility functions for byte order swaps. */
+PCRE_EXP_DECL int  pcre_pattern_to_host_byte_order(pcre *, pcre_extra *,
+                  const unsigned char *);
+PCRE_EXP_DECL int  pcre16_pattern_to_host_byte_order(pcre16 *, pcre16_extra *,
+                  const unsigned char *);
+PCRE_EXP_DECL int  pcre32_pattern_to_host_byte_order(pcre32 *, pcre32_extra *,
+                  const unsigned char *);
+PCRE_EXP_DECL int  pcre16_utf16_to_host_byte_order(PCRE_UCHAR16 *,
+                  PCRE_SPTR16, int, int *, int);
+PCRE_EXP_DECL int  pcre32_utf32_to_host_byte_order(PCRE_UCHAR32 *,
+                  PCRE_SPTR32, int, int *, int);
+
+/* JIT compiler related functions. */
+
+PCRE_EXP_DECL pcre_jit_stack *pcre_jit_stack_alloc(int, int);
+PCRE_EXP_DECL pcre16_jit_stack *pcre16_jit_stack_alloc(int, int);
+PCRE_EXP_DECL pcre32_jit_stack *pcre32_jit_stack_alloc(int, int);
+PCRE_EXP_DECL void pcre_jit_stack_free(pcre_jit_stack *);
+PCRE_EXP_DECL void pcre16_jit_stack_free(pcre16_jit_stack *);
+PCRE_EXP_DECL void pcre32_jit_stack_free(pcre32_jit_stack *);
+PCRE_EXP_DECL void pcre_assign_jit_stack(pcre_extra *,
+                  pcre_jit_callback, void *);
+PCRE_EXP_DECL void pcre16_assign_jit_stack(pcre16_extra *,
+                  pcre16_jit_callback, void *);
+PCRE_EXP_DECL void pcre32_assign_jit_stack(pcre32_extra *,
+                  pcre32_jit_callback, void *);
+PCRE_EXP_DECL void pcre_jit_free_unused_memory(void);
+PCRE_EXP_DECL void pcre16_jit_free_unused_memory(void);
+PCRE_EXP_DECL void pcre32_jit_free_unused_memory(void);
 
 #ifdef __cplusplus
 }  /* extern "C" */

src/plugins/PCREPlugin/pcre_config.c

@@ -1,3 +1,4 @@
+#define HAVE_CONFIG_H
 /*************************************************
 *      Perl-Compatible Regular Expressions       *
 *************************************************/
@@ -6,7 +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) 1997-2012 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -45,6 +46,9 @@ POSSIBILITY OF SUCH DAMAGE.
 #include "config.h"
 #endif
 
+/* Keep the original link size. */
+static int real_link_size = LINK_SIZE;
+
 #include "pcre_internal.h"
 
 
@@ -62,18 +66,57 @@ Arguments:
 Returns:           0 if data returned, negative on error
 */
 
-PCRE_EXP_DEFN int
+#if defined COMPILE_PCRE8
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
 pcre_config(int what, void *where)
+#elif defined COMPILE_PCRE16
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre16_config(int what, void *where)
+#elif defined COMPILE_PCRE32
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre32_config(int what, void *where)
+#endif
 {
 switch (what)
   {
   case PCRE_CONFIG_UTF8:
-#ifdef SUPPORT_UTF8
+#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32
+  *((int *)where) = 0;
+  return PCRE_ERROR_BADOPTION;
+#else
+#if defined SUPPORT_UTF
   *((int *)where) = 1;
 #else
   *((int *)where) = 0;
 #endif
   break;
+#endif
+
+  case PCRE_CONFIG_UTF16:
+#if defined COMPILE_PCRE8 || defined COMPILE_PCRE32
+  *((int *)where) = 0;
+  return PCRE_ERROR_BADOPTION;
+#else
+#if defined SUPPORT_UTF
+  *((int *)where) = 1;
+#else
+  *((int *)where) = 0;
+#endif
+  break;
+#endif
+
+  case PCRE_CONFIG_UTF32:
+#if defined COMPILE_PCRE8 || defined COMPILE_PCRE16
+  *((int *)where) = 0;
+  return PCRE_ERROR_BADOPTION;
+#else
+#if defined SUPPORT_UTF
+  *((int *)where) = 1;
+#else
+  *((int *)where) = 0;
+#endif
+  break;
+#endif
 
   case PCRE_CONFIG_UNICODE_PROPERTIES:
 #ifdef SUPPORT_UCP
@@ -83,6 +126,22 @@ switch (what)
 #endif
   break;
 
+  case PCRE_CONFIG_JIT:
+#ifdef SUPPORT_JIT
+  *((int *)where) = 1;
+#else
+  *((int *)where) = 0;
+#endif
+  break;
+
+  case PCRE_CONFIG_JITTARGET:
+#ifdef SUPPORT_JIT
+  *((const char **)where) = PRIV(jit_get_target)();
+#else
+  *((const char **)where) = NULL;
+#endif
+  break;
+
   case PCRE_CONFIG_NEWLINE:
   *((int *)where) = NEWLINE;
   break;
@@ -96,19 +155,23 @@ switch (what)
   break;
 
   case PCRE_CONFIG_LINK_SIZE:
-  *((int *)where) = LINK_SIZE;
+  *((int *)where) = real_link_size;
   break;
 
   case PCRE_CONFIG_POSIX_MALLOC_THRESHOLD:
   *((int *)where) = POSIX_MALLOC_THRESHOLD;
   break;
 
+  case PCRE_CONFIG_PARENS_LIMIT:
+  *((unsigned long int *)where) = PARENS_NEST_LIMIT;
+  break;
+
   case PCRE_CONFIG_MATCH_LIMIT:
-  *((unsigned int *)where) = MATCH_LIMIT;
+  *((unsigned long int *)where) = MATCH_LIMIT;
   break;
 
   case PCRE_CONFIG_MATCH_LIMIT_RECURSION:
-  *((unsigned int *)where) = MATCH_LIMIT_RECURSION;
+  *((unsigned long int *)where) = MATCH_LIMIT_RECURSION;
   break;
 
   case PCRE_CONFIG_STACKRECURSE:

src/plugins/PCREPlugin/pcre_fullinfo.c

@@ -1,3 +1,4 @@
+#define HAVE_CONFIG_H
 /*************************************************
 *      Perl-Compatible Regular Expressions       *
 *************************************************/
@@ -6,7 +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) 1997-2013 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -65,13 +66,21 @@ Arguments:
 Returns:           0 if data returned, negative on error
 */
 
-PCRE_EXP_DEFN int
+#if defined COMPILE_PCRE8
-pcre_fullinfo(const pcre *argument_re, const pcre_extra *extra_data, int what,
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
-  void *where)
+pcre_fullinfo(const pcre *argument_re, const pcre_extra *extra_data,
+  int what, void *where)
+#elif defined COMPILE_PCRE16
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre16_fullinfo(const pcre16 *argument_re, const pcre16_extra *extra_data,
+  int what, void *where)
+#elif defined COMPILE_PCRE32
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre32_fullinfo(const pcre32 *argument_re, const pcre32_extra *extra_data,
+  int what, void *where)
+#endif
 {
-real_pcre internal_re;
+const REAL_PCRE *re = (const REAL_PCRE *)argument_re;
-pcre_study_data internal_study;
-const real_pcre *re = (const real_pcre *)argument_re;
 const pcre_study_data *study = NULL;
 
 if (re == NULL || where == NULL) return PCRE_ERROR_NULL;
@@ -79,17 +88,23 @@ if (re == NULL || where == NULL) return PCRE_ERROR_NULL;
 if (extra_data != NULL && (extra_data->flags & PCRE_EXTRA_STUDY_DATA) != 0)
   study = (const pcre_study_data *)extra_data->study_data;
 
+/* Check that the first field in the block is the magic number. If it is not,
+return with PCRE_ERROR_BADMAGIC. However, if the magic number is equal to
+REVERSED_MAGIC_NUMBER we return with PCRE_ERROR_BADENDIANNESS, which
+means that the pattern is likely compiled with different endianness. */
+
 if (re->magic_number != MAGIC_NUMBER)
-  {
+  return re->magic_number == REVERSED_MAGIC_NUMBER?
-  re = _pcre_try_flipped(re, &internal_re, study, &internal_study);
+    PCRE_ERROR_BADENDIANNESS:PCRE_ERROR_BADMAGIC;
-  if (re == NULL) return PCRE_ERROR_BADMAGIC;
+
-  if (study != NULL) study = &internal_study;
+/* Check that this pattern was compiled in the correct bit mode */
-  }
+
+if ((re->flags & PCRE_MODE) == 0) return PCRE_ERROR_BADMODE;
 
 switch (what)
   {
   case PCRE_INFO_OPTIONS:
-  *((unsigned long int *)where) = re->options & PUBLIC_OPTIONS;
+  *((unsigned long int *)where) = re->options & PUBLIC_COMPILE_OPTIONS;
   break;
 
   case PCRE_INFO_SIZE:
@@ -100,6 +115,18 @@ switch (what)
   *((size_t *)where) = (study == NULL)? 0 : study->size;
   break;
 
+  case PCRE_INFO_JITSIZE:
+#ifdef SUPPORT_JIT
+  *((size_t *)where) =
+      (extra_data != NULL &&
+      (extra_data->flags & PCRE_EXTRA_EXECUTABLE_JIT) != 0 &&
+      extra_data->executable_jit != NULL)?
+    PRIV(jit_get_size)(extra_data->executable_jit) : 0;
+#else
+  *((size_t *)where) = 0;
+#endif
+  break;
+
   case PCRE_INFO_CAPTURECOUNT:
   *((int *)where) = re->top_bracket;
   break;
@@ -110,22 +137,55 @@ switch (what)
 
   case PCRE_INFO_FIRSTBYTE:
   *((int *)where) =
-    ((re->flags & PCRE_FIRSTSET) != 0)? re->first_byte :
+    ((re->flags & PCRE_FIRSTSET) != 0)? (int)re->first_char :
     ((re->flags & PCRE_STARTLINE) != 0)? -1 : -2;
   break;
 
+  case PCRE_INFO_FIRSTCHARACTER:
+    *((pcre_uint32 *)where) =
+      (re->flags & PCRE_FIRSTSET) != 0 ? re->first_char : 0;
+    break;
+
+  case PCRE_INFO_FIRSTCHARACTERFLAGS:
+    *((int *)where) =
+      ((re->flags & PCRE_FIRSTSET) != 0) ? 1 :
+      ((re->flags & PCRE_STARTLINE) != 0) ? 2 : 0;
+    break;
+
   /* Make sure we pass back the pointer to the bit vector in the external
   block, not the internal copy (with flipped integer fields). */
 
   case PCRE_INFO_FIRSTTABLE:
-  *((const uschar **)where) =
+  *((const pcre_uint8 **)where) =
-    (study != NULL && (study->options & PCRE_STUDY_MAPPED) != 0)?
+    (study != NULL && (study->flags & PCRE_STUDY_MAPPED) != 0)?
       ((const pcre_study_data *)extra_data->study_data)->start_bits : NULL;
   break;
 
+  case PCRE_INFO_MINLENGTH:
+  *((int *)where) =
+    (study != NULL && (study->flags & PCRE_STUDY_MINLEN) != 0)?
+      (int)(study->minlength) : -1;
+  break;
+
+  case PCRE_INFO_JIT:
+  *((int *)where) = extra_data != NULL &&
+                    (extra_data->flags & PCRE_EXTRA_EXECUTABLE_JIT) != 0 &&
+                    extra_data->executable_jit != NULL;
+  break;
+
   case PCRE_INFO_LASTLITERAL:
   *((int *)where) =
-    ((re->flags & PCRE_REQCHSET) != 0)? re->req_byte : -1;
+    ((re->flags & PCRE_REQCHSET) != 0)? (int)re->req_char : -1;
+  break;
+
+  case PCRE_INFO_REQUIREDCHAR:
+    *((pcre_uint32 *)where) =
+      ((re->flags & PCRE_REQCHSET) != 0) ? re->req_char : 0;
+    break;
+
+  case PCRE_INFO_REQUIREDCHARFLAGS:
+    *((int *)where) =
+      ((re->flags & PCRE_REQCHSET) != 0);
     break;
 
   case PCRE_INFO_NAMEENTRYSIZE:
@@ -137,13 +197,16 @@ switch (what)
   break;
 
   case PCRE_INFO_NAMETABLE:
-  *((const uschar **)where) = (const uschar *)re + re->name_table_offset;
+  *((const pcre_uchar **)where) = (const pcre_uchar *)re + re->name_table_offset;
   break;
 
   case PCRE_INFO_DEFAULT_TABLES:
-  *((const uschar **)where) = (const uschar *)(_pcre_default_tables);
+  *((const pcre_uint8 **)where) = (const pcre_uint8 *)(PRIV(default_tables));
   break;
 
+  /* From release 8.00 this will always return TRUE because NOPARTIAL is
+  no longer ever set (the restrictions have been removed). */
+
   case PCRE_INFO_OKPARTIAL:
   *((int *)where) = (re->flags & PCRE_NOPARTIAL) == 0;
   break;
@@ -156,6 +219,24 @@ switch (what)
   *((int *)where) = (re->flags & PCRE_HASCRORLF) != 0;
   break;
 
+  case PCRE_INFO_MAXLOOKBEHIND:
+  *((int *)where) = re->max_lookbehind;
+  break;
+
+  case PCRE_INFO_MATCHLIMIT:
+  if ((re->flags & PCRE_MLSET) == 0) return PCRE_ERROR_UNSET;
+  *((pcre_uint32 *)where) = re->limit_match;
+  break;
+
+  case PCRE_INFO_RECURSIONLIMIT:
+  if ((re->flags & PCRE_RLSET) == 0) return PCRE_ERROR_UNSET;
+  *((pcre_uint32 *)where) = re->limit_recursion;
+  break;
+
+  case PCRE_INFO_MATCH_EMPTY:
+  *((int *)where) = (re->flags & PCRE_MATCH_EMPTY) != 0;
+  break;
+
   default: return PCRE_ERROR_BADOPTION;
   }
 

src/plugins/PCREPlugin/pcre_get.c

@@ -1,3 +1,4 @@
+#define HAVE_CONFIG_H
 /*************************************************
 *      Perl-Compatible Regular Expressions       *
 *************************************************/
@@ -6,7 +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) 1997-2012 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -65,14 +66,23 @@ Returns:      the number of the named parentheses, or a negative number
                 (PCRE_ERROR_NOSUBSTRING) if not found
 */
 
-int
+#if defined COMPILE_PCRE8
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
 pcre_get_stringnumber(const pcre *code, const char *stringname)
+#elif defined COMPILE_PCRE16
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre16_get_stringnumber(const pcre16 *code, PCRE_SPTR16 stringname)
+#elif defined COMPILE_PCRE32
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre32_get_stringnumber(const pcre32 *code, PCRE_SPTR32 stringname)
+#endif
 {
 int rc;
 int entrysize;
 int top, bot;
-uschar *nametable;
+pcre_uchar *nametable;
 
+#ifdef COMPILE_PCRE8
 if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMECOUNT, &top)) != 0)
   return rc;
 if (top <= 0) return PCRE_ERROR_NOSUBSTRING;
@@ -81,14 +91,36 @@ if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMEENTRYSIZE, &entrysize)) != 0)
   return rc;
 if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMETABLE, &nametable)) != 0)
   return rc;
+#endif
+#ifdef COMPILE_PCRE16
+if ((rc = pcre16_fullinfo(code, NULL, PCRE_INFO_NAMECOUNT, &top)) != 0)
+  return rc;
+if (top <= 0) return PCRE_ERROR_NOSUBSTRING;
+
+if ((rc = pcre16_fullinfo(code, NULL, PCRE_INFO_NAMEENTRYSIZE, &entrysize)) != 0)
+  return rc;
+if ((rc = pcre16_fullinfo(code, NULL, PCRE_INFO_NAMETABLE, &nametable)) != 0)
+  return rc;
+#endif
+#ifdef COMPILE_PCRE32
+if ((rc = pcre32_fullinfo(code, NULL, PCRE_INFO_NAMECOUNT, &top)) != 0)
+  return rc;
+if (top <= 0) return PCRE_ERROR_NOSUBSTRING;
+
+if ((rc = pcre32_fullinfo(code, NULL, PCRE_INFO_NAMEENTRYSIZE, &entrysize)) != 0)
+  return rc;
+if ((rc = pcre32_fullinfo(code, NULL, PCRE_INFO_NAMETABLE, &nametable)) != 0)
+  return rc;
+#endif
 
 bot = 0;
 while (top > bot)
   {
   int mid = (top + bot) / 2;
-  uschar *entry = nametable + entrysize*mid;
+  pcre_uchar *entry = nametable + entrysize*mid;
-  int c = strcmp(stringname, (char *)(entry + 2));
+  int c = STRCMP_UC_UC((pcre_uchar *)stringname,
-  if (c == 0) return (entry[0] << 8) + entry[1];
+    (pcre_uchar *)(entry + IMM2_SIZE));
+  if (c == 0) return GET2(entry, 0);
   if (c > 0) bot = mid + 1; else top = mid;
   }
 
@@ -114,15 +146,26 @@ Returns:      the length of each entry, or a negative number
                 (PCRE_ERROR_NOSUBSTRING) if not found
 */
 
-int
+#if defined COMPILE_PCRE8
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
 pcre_get_stringtable_entries(const pcre *code, const char *stringname,
   char **firstptr, char **lastptr)
+#elif defined COMPILE_PCRE16
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre16_get_stringtable_entries(const pcre16 *code, PCRE_SPTR16 stringname,
+  PCRE_UCHAR16 **firstptr, PCRE_UCHAR16 **lastptr)
+#elif defined COMPILE_PCRE32
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre32_get_stringtable_entries(const pcre32 *code, PCRE_SPTR32 stringname,
+  PCRE_UCHAR32 **firstptr, PCRE_UCHAR32 **lastptr)
+#endif
 {
 int rc;
 int entrysize;
 int top, bot;
-uschar *nametable, *lastentry;
+pcre_uchar *nametable, *lastentry;
 
+#ifdef COMPILE_PCRE8
 if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMECOUNT, &top)) != 0)
   return rc;
 if (top <= 0) return PCRE_ERROR_NOSUBSTRING;
@@ -131,30 +174,62 @@ if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMEENTRYSIZE, &entrysize)) != 0)
   return rc;
 if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMETABLE, &nametable)) != 0)
   return rc;
+#endif
+#ifdef COMPILE_PCRE16
+if ((rc = pcre16_fullinfo(code, NULL, PCRE_INFO_NAMECOUNT, &top)) != 0)
+  return rc;
+if (top <= 0) return PCRE_ERROR_NOSUBSTRING;
+
+if ((rc = pcre16_fullinfo(code, NULL, PCRE_INFO_NAMEENTRYSIZE, &entrysize)) != 0)
+  return rc;
+if ((rc = pcre16_fullinfo(code, NULL, PCRE_INFO_NAMETABLE, &nametable)) != 0)
+  return rc;
+#endif
+#ifdef COMPILE_PCRE32
+if ((rc = pcre32_fullinfo(code, NULL, PCRE_INFO_NAMECOUNT, &top)) != 0)
+  return rc;
+if (top <= 0) return PCRE_ERROR_NOSUBSTRING;
+
+if ((rc = pcre32_fullinfo(code, NULL, PCRE_INFO_NAMEENTRYSIZE, &entrysize)) != 0)
+  return rc;
+if ((rc = pcre32_fullinfo(code, NULL, PCRE_INFO_NAMETABLE, &nametable)) != 0)
+  return rc;
+#endif
 
 lastentry = nametable + entrysize * (top - 1);
 bot = 0;
 while (top > bot)
   {
   int mid = (top + bot) / 2;
-  uschar *entry = nametable + entrysize*mid;
+  pcre_uchar *entry = nametable + entrysize*mid;
-  int c = strcmp(stringname, (char *)(entry + 2));
+  int c = STRCMP_UC_UC((pcre_uchar *)stringname,
+    (pcre_uchar *)(entry + IMM2_SIZE));
   if (c == 0)
     {
-    uschar *first = entry;
+    pcre_uchar *first = entry;
-    uschar *last = entry;
+    pcre_uchar *last = entry;
     while (first > nametable)
       {
-      if (strcmp(stringname, (char *)(first - entrysize + 2)) != 0) break;
+      if (STRCMP_UC_UC((pcre_uchar *)stringname,
+        (pcre_uchar *)(first - entrysize + IMM2_SIZE)) != 0) break;
       first -= entrysize;
       }
     while (last < lastentry)
       {
-      if (strcmp(stringname, (char *)(last + entrysize + 2)) != 0) break;
+      if (STRCMP_UC_UC((pcre_uchar *)stringname,
+        (pcre_uchar *)(last + entrysize + IMM2_SIZE)) != 0) break;
       last += entrysize;
       }
+#if defined COMPILE_PCRE8
     *firstptr = (char *)first;
     *lastptr = (char *)last;
+#elif defined COMPILE_PCRE16
+    *firstptr = (PCRE_UCHAR16 *)first;
+    *lastptr = (PCRE_UCHAR16 *)last;
+#elif defined COMPILE_PCRE32
+    *firstptr = (PCRE_UCHAR32 *)first;
+    *lastptr = (PCRE_UCHAR32 *)last;
+#endif
     return entrysize;
     }
   if (c > 0) bot = mid + 1; else top = mid;
@@ -176,29 +251,58 @@ Arguments:
   code         the compiled regex
   stringname   the name of the capturing substring
   ovector      the vector of matched substrings
+  stringcount  number of captured substrings
 
 Returns:       the number of the first that is set,
                or the number of the last one if none are set,
                or a negative number on error
 */
 
+#if defined COMPILE_PCRE8
 static int
-get_first_set(const pcre *code, const char *stringname, int *ovector)
+get_first_set(const pcre *code, const char *stringname, int *ovector,
+  int stringcount)
+#elif defined COMPILE_PCRE16
+static int
+get_first_set(const pcre16 *code, PCRE_SPTR16 stringname, int *ovector,
+  int stringcount)
+#elif defined COMPILE_PCRE32
+static int
+get_first_set(const pcre32 *code, PCRE_SPTR32 stringname, int *ovector,
+  int stringcount)
+#endif
 {
-const real_pcre *re = (const real_pcre *)code;
+const REAL_PCRE *re = (const REAL_PCRE *)code;
 int entrysize;
+pcre_uchar *entry;
+#if defined COMPILE_PCRE8
 char *first, *last;
-uschar *entry;
+#elif defined COMPILE_PCRE16
+PCRE_UCHAR16 *first, *last;
+#elif defined COMPILE_PCRE32
+PCRE_UCHAR32 *first, *last;
+#endif
+
+#if defined COMPILE_PCRE8
 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);
+#elif defined COMPILE_PCRE16
+if ((re->options & PCRE_DUPNAMES) == 0 && (re->flags & PCRE_JCHANGED) == 0)
+  return pcre16_get_stringnumber(code, stringname);
+entrysize = pcre16_get_stringtable_entries(code, stringname, &first, &last);
+#elif defined COMPILE_PCRE32
+if ((re->options & PCRE_DUPNAMES) == 0 && (re->flags & PCRE_JCHANGED) == 0)
+  return pcre32_get_stringnumber(code, stringname);
+entrysize = pcre32_get_stringtable_entries(code, stringname, &first, &last);
+#endif
 if (entrysize <= 0) return entrysize;
-for (entry = (uschar *)first; entry <= (uschar *)last; entry += entrysize)
+for (entry = (pcre_uchar *)first; entry <= (pcre_uchar *)last; entry += entrysize)
   {
-  int n = (entry[0] << 8) + entry[1];
+  int n = GET2(entry, 0);
-  if (ovector[n*2] >= 0) return n;
+  if (n < stringcount && ovector[n*2] >= 0) return n;
   }
-return (first[0] << 8) + first[1];
+return GET2(entry, 0);
 }
 
 
@@ -231,9 +335,19 @@ Returns:         if successful:
                    PCRE_ERROR_NOSUBSTRING (-7) no such captured substring
 */
 
-int
+#if defined COMPILE_PCRE8
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
 pcre_copy_substring(const char *subject, int *ovector, int stringcount,
   int stringnumber, char *buffer, int size)
+#elif defined COMPILE_PCRE16
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre16_copy_substring(PCRE_SPTR16 subject, int *ovector, int stringcount,
+  int stringnumber, PCRE_UCHAR16 *buffer, int size)
+#elif defined COMPILE_PCRE32
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre32_copy_substring(PCRE_SPTR32 subject, int *ovector, int stringcount,
+  int stringnumber, PCRE_UCHAR32 *buffer, int size)
+#endif
 {
 int yield;
 if (stringnumber < 0 || stringnumber >= stringcount)
@@ -241,7 +355,7 @@ if (stringnumber < 0 || stringnumber >= stringcount)
 stringnumber *= 2;
 yield = ovector[stringnumber+1] - ovector[stringnumber];
 if (size < yield + 1) return PCRE_ERROR_NOMEMORY;
-memcpy(buffer, subject + ovector[stringnumber], yield);
+memcpy(buffer, subject + ovector[stringnumber], IN_UCHARS(yield));
 buffer[yield] = 0;
 return yield;
 }
@@ -276,13 +390,32 @@ Returns:         if successful:
                    PCRE_ERROR_NOSUBSTRING (-7) no such captured substring
 */
 
-int
+#if defined COMPILE_PCRE8
-pcre_copy_named_substring(const pcre *code, const char *subject, int *ovector,
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
-  int stringcount, const char *stringname, char *buffer, int size)
+pcre_copy_named_substring(const pcre *code, const char *subject,
+  int *ovector, int stringcount, const char *stringname,
+  char *buffer, int size)
+#elif defined COMPILE_PCRE16
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre16_copy_named_substring(const pcre16 *code, PCRE_SPTR16 subject,
+  int *ovector, int stringcount, PCRE_SPTR16 stringname,
+  PCRE_UCHAR16 *buffer, int size)
+#elif defined COMPILE_PCRE32
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre32_copy_named_substring(const pcre32 *code, PCRE_SPTR32 subject,
+  int *ovector, int stringcount, PCRE_SPTR32 stringname,
+  PCRE_UCHAR32 *buffer, int size)
+#endif
 {
-int n = get_first_set(code, stringname, ovector);
+int n = get_first_set(code, stringname, ovector, stringcount);
 if (n <= 0) return n;
+#if defined COMPILE_PCRE8
 return pcre_copy_substring(subject, ovector, stringcount, n, buffer, size);
+#elif defined COMPILE_PCRE16
+return pcre16_copy_substring(subject, ovector, stringcount, n, buffer, size);
+#elif defined COMPILE_PCRE32
+return pcre32_copy_substring(subject, ovector, stringcount, n, buffer, size);
+#endif
 }
 
 
@@ -308,29 +441,48 @@ Returns:         if successful: 0
                    PCRE_ERROR_NOMEMORY (-6) failed to get store
 */
 
-int
+#if defined COMPILE_PCRE8
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
 pcre_get_substring_list(const char *subject, int *ovector, int stringcount,
   const char ***listptr)
+#elif defined COMPILE_PCRE16
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre16_get_substring_list(PCRE_SPTR16 subject, int *ovector, int stringcount,
+  PCRE_SPTR16 **listptr)
+#elif defined COMPILE_PCRE32
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre32_get_substring_list(PCRE_SPTR32 subject, int *ovector, int stringcount,
+  PCRE_SPTR32 **listptr)
+#endif
 {
 int i;
-int size = sizeof(char *);
+int size = sizeof(pcre_uchar *);
 int double_count = stringcount * 2;
-char **stringlist;
+pcre_uchar **stringlist;
-char *p;
+pcre_uchar *p;
-
-for (i = 0; i < double_count; i += 2)
-  size += sizeof(char *) + ovector[i+1] - ovector[i] + 1;
-
-stringlist = (char **)(pcre_malloc)(size);
-if (stringlist == NULL) return PCRE_ERROR_NOMEMORY;
-
-*listptr = (const char **)stringlist;
-p = (char *)(stringlist + stringcount + 1);
 
 for (i = 0; i < double_count; i += 2)
   {
-  int len = ovector[i+1] - ovector[i];
+  size += sizeof(pcre_uchar *) + IN_UCHARS(1);
-  memcpy(p, subject + ovector[i], len);
+  if (ovector[i+1] > ovector[i]) size += IN_UCHARS(ovector[i+1] - ovector[i]);
+  }
+
+stringlist = (pcre_uchar **)(PUBL(malloc))(size);
+if (stringlist == NULL) return PCRE_ERROR_NOMEMORY;
+
+#if defined COMPILE_PCRE8
+*listptr = (const char **)stringlist;
+#elif defined COMPILE_PCRE16
+*listptr = (PCRE_SPTR16 *)stringlist;
+#elif defined COMPILE_PCRE32
+*listptr = (PCRE_SPTR32 *)stringlist;
+#endif
+p = (pcre_uchar *)(stringlist + stringcount + 1);
+
+for (i = 0; i < double_count; i += 2)
+  {
+  int len = (ovector[i+1] > ovector[i])? (ovector[i+1] - ovector[i]) : 0;
+  memcpy(p, subject + ovector[i], IN_UCHARS(len));
   *stringlist++ = p;
   p += len;
   *p++ = 0;
@@ -347,16 +499,25 @@ return 0;
 *************************************************/
 
 /* This function exists for the benefit of people calling PCRE from non-C
-programs that can call its functions, but not free() or (pcre_free)() directly.
+programs that can call its functions, but not free() or (PUBL(free))()
+directly.
 
 Argument:   the result of a previous pcre_get_substring_list()
 Returns:    nothing
 */
 
-void
+#if defined COMPILE_PCRE8
+PCRE_EXP_DEFN void PCRE_CALL_CONVENTION
 pcre_free_substring_list(const char **pointer)
+#elif defined COMPILE_PCRE16
+PCRE_EXP_DEFN void PCRE_CALL_CONVENTION
+pcre16_free_substring_list(PCRE_SPTR16 *pointer)
+#elif defined COMPILE_PCRE32
+PCRE_EXP_DEFN void PCRE_CALL_CONVENTION
+pcre32_free_substring_list(PCRE_SPTR32 *pointer)
+#endif
 {
-(pcre_free)((void *)pointer);
+(PUBL(free))((void *)pointer);
 }
 
 
@@ -386,21 +547,37 @@ Returns:         if successful:
                    PCRE_ERROR_NOSUBSTRING (-7) substring not present
 */
 
-int
+#if defined COMPILE_PCRE8
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
 pcre_get_substring(const char *subject, int *ovector, int stringcount,
   int stringnumber, const char **stringptr)
+#elif defined COMPILE_PCRE16
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre16_get_substring(PCRE_SPTR16 subject, int *ovector, int stringcount,
+  int stringnumber, PCRE_SPTR16 *stringptr)
+#elif defined COMPILE_PCRE32
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre32_get_substring(PCRE_SPTR32 subject, int *ovector, int stringcount,
+  int stringnumber, PCRE_SPTR32 *stringptr)
+#endif
 {
 int yield;
-char *substring;
+pcre_uchar *substring;
 if (stringnumber < 0 || stringnumber >= stringcount)
   return PCRE_ERROR_NOSUBSTRING;
 stringnumber *= 2;
 yield = ovector[stringnumber+1] - ovector[stringnumber];
-substring = (char *)(pcre_malloc)(yield + 1);
+substring = (pcre_uchar *)(PUBL(malloc))(IN_UCHARS(yield + 1));
 if (substring == NULL) return PCRE_ERROR_NOMEMORY;
-memcpy(substring, subject + ovector[stringnumber], yield);
+memcpy(substring, subject + ovector[stringnumber], IN_UCHARS(yield));
 substring[yield] = 0;
-*stringptr = substring;
+#if defined COMPILE_PCRE8
+*stringptr = (const char *)substring;
+#elif defined COMPILE_PCRE16
+*stringptr = (PCRE_SPTR16)substring;
+#elif defined COMPILE_PCRE32
+*stringptr = (PCRE_SPTR32)substring;
+#endif
 return yield;
 }
 
@@ -433,13 +610,32 @@ Returns:         if successful:
                    PCRE_ERROR_NOSUBSTRING (-7) no such captured substring
 */
 
-int
+#if defined COMPILE_PCRE8
-pcre_get_named_substring(const pcre *code, const char *subject, int *ovector,
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
-  int stringcount, const char *stringname, const char **stringptr)
+pcre_get_named_substring(const pcre *code, const char *subject,
+  int *ovector, int stringcount, const char *stringname,
+  const char **stringptr)
+#elif defined COMPILE_PCRE16
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre16_get_named_substring(const pcre16 *code, PCRE_SPTR16 subject,
+  int *ovector, int stringcount, PCRE_SPTR16 stringname,
+  PCRE_SPTR16 *stringptr)
+#elif defined COMPILE_PCRE32
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre32_get_named_substring(const pcre32 *code, PCRE_SPTR32 subject,
+  int *ovector, int stringcount, PCRE_SPTR32 stringname,
+  PCRE_SPTR32 *stringptr)
+#endif
 {
-int n = get_first_set(code, stringname, ovector);
+int n = get_first_set(code, stringname, ovector, stringcount);
 if (n <= 0) return n;
+#if defined COMPILE_PCRE8
 return pcre_get_substring(subject, ovector, stringcount, n, stringptr);
+#elif defined COMPILE_PCRE16
+return pcre16_get_substring(subject, ovector, stringcount, n, stringptr);
+#elif defined COMPILE_PCRE32
+return pcre32_get_substring(subject, ovector, stringcount, n, stringptr);
+#endif
 }
 
 
@@ -450,16 +646,25 @@ return pcre_get_substring(subject, ovector, stringcount, n, stringptr);
 *************************************************/
 
 /* This function exists for the benefit of people calling PCRE from non-C
-programs that can call its functions, but not free() or (pcre_free)() directly.
+programs that can call its functions, but not free() or (PUBL(free))()
+directly.
 
 Argument:   the result of a previous pcre_get_substring()
 Returns:    nothing
 */
 
-void
+#if defined COMPILE_PCRE8
+PCRE_EXP_DEFN void PCRE_CALL_CONVENTION
 pcre_free_substring(const char *pointer)
+#elif defined COMPILE_PCRE16
+PCRE_EXP_DEFN void PCRE_CALL_CONVENTION
+pcre16_free_substring(PCRE_SPTR16 pointer)
+#elif defined COMPILE_PCRE32
+PCRE_EXP_DEFN void PCRE_CALL_CONVENTION
+pcre32_free_substring(PCRE_SPTR32 pointer)
+#endif
 {
-(pcre_free)((void *)pointer);
+(PUBL(free))((void *)pointer);
 }
 
 /* End of pcre_get.c */

src/plugins/PCREPlugin/pcre_globals.c

@@ -1,3 +1,4 @@
+#define HAVE_CONFIG_H
 /*************************************************
 *      Perl-Compatible Regular Expressions       *
 *************************************************/
@@ -6,7 +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) 1997-2014 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -43,8 +44,14 @@ PCRE is thread-clean and doesn't use any global variables in the normal sense.
 However, it calls memory allocation and freeing functions via the four
 indirections below, and it can optionally do callouts, using the fifth
 indirection. These values can be changed by the caller, but are shared between
-all threads. However, when compiling for Virtual Pascal, things are done
+all threads.
-differently, and global variables are not used (see pcre.in). */
+
+For MS Visual Studio and Symbian OS, there are problems in initializing these
+variables to non-local functions. In these cases, therefore, an indirection via
+a local function is used.
+
+Also, when compiling for Virtual Pascal, things are done differently, and
+global variables are not used. */
 
 #ifdef HAVE_CONFIG_H
 #include "config.h"
@@ -52,12 +59,29 @@ differently, and global variables are not used (see pcre.in). */
 
 #include "pcre_internal.h"
 
-#ifndef VPCOMPAT
+#if defined _MSC_VER || defined  __SYMBIAN32__
-PCRE_EXP_DATA_DEFN void *(*pcre_malloc)(size_t) = malloc;
+static void* LocalPcreMalloc(size_t aSize)
-PCRE_EXP_DATA_DEFN void  (*pcre_free)(void *) = free;
+  {
-PCRE_EXP_DATA_DEFN void *(*pcre_stack_malloc)(size_t) = malloc;
+  return malloc(aSize);
-PCRE_EXP_DATA_DEFN void  (*pcre_stack_free)(void *) = free;
+  }
-PCRE_EXP_DATA_DEFN int   (*pcre_callout)(pcre_callout_block *) = NULL;
+static void LocalPcreFree(void* aPtr)
+  {
+  free(aPtr);
+  }
+PCRE_EXP_DATA_DEFN void *(*PUBL(malloc))(size_t) = LocalPcreMalloc;
+PCRE_EXP_DATA_DEFN void  (*PUBL(free))(void *) = LocalPcreFree;
+PCRE_EXP_DATA_DEFN void *(*PUBL(stack_malloc))(size_t) = LocalPcreMalloc;
+PCRE_EXP_DATA_DEFN void  (*PUBL(stack_free))(void *) = LocalPcreFree;
+PCRE_EXP_DATA_DEFN int   (*PUBL(callout))(PUBL(callout_block) *) = NULL;
+PCRE_EXP_DATA_DEFN int   (*PUBL(stack_guard))(void) = NULL;
+
+#elif !defined VPCOMPAT
+PCRE_EXP_DATA_DEFN void *(*PUBL(malloc))(size_t) = malloc;
+PCRE_EXP_DATA_DEFN void  (*PUBL(free))(void *) = free;
+PCRE_EXP_DATA_DEFN void *(*PUBL(stack_malloc))(size_t) = malloc;
+PCRE_EXP_DATA_DEFN void  (*PUBL(stack_free))(void *) = free;
+PCRE_EXP_DATA_DEFN int   (*PUBL(callout))(PUBL(callout_block) *) = NULL;
+PCRE_EXP_DATA_DEFN int   (*PUBL(stack_guard))(void) = NULL;
 #endif
 
 /* End of pcre_globals.c */

src/plugins/PCREPlugin/pcre_info.c

@@ -1,93 +0,0 @@
-/*************************************************
-*      Perl-Compatible Regular Expressions       *
-*************************************************/
-
-/* 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
-
------------------------------------------------------------------------------
-Redistribution and use in source and binary forms, with or without
-modification, are permitted provided that the following conditions are met:
-
-    * Redistributions of source code must retain the above copyright notice,
-      this list of conditions and the following disclaimer.
-
-    * Redistributions in binary form must reproduce the above copyright
-      notice, this list of conditions and the following disclaimer in the
-      documentation and/or other materials provided with the distribution.
-
-    * Neither the name of the University of Cambridge nor the names of its
-      contributors may be used to endorse or promote products derived from
-      this software without specific prior written permission.
-
-THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
-AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
-IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
-ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
-LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
-CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
-SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
-INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
-CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
-ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
-POSSIBILITY OF SUCH DAMAGE.
------------------------------------------------------------------------------
-*/
-
-
-/* This module contains the external function pcre_info(), which gives some
-information about a compiled pattern. However, use of this function is now
-deprecated, as it has been superseded by pcre_fullinfo(). */
-
-
-#ifdef HAVE_CONFIG_H
-#include "config.h"
-#endif
-
-#include "pcre_internal.h"
-
-
-/*************************************************
-* (Obsolete) Return info about compiled pattern  *
-*************************************************/
-
-/* This is the original "info" function. It picks potentially useful data out
-of the private structure, but its interface was too rigid. It remains for
-backwards compatibility. The public options are passed back in an int - though
-the re->options field has been expanded to a long int, all the public options
-at the low end of it, and so even on 16-bit systems this will still be OK.
-Therefore, I haven't changed the API for pcre_info().
-
-Arguments:
-  argument_re   points to compiled code
-  optptr        where to pass back the options
-  first_byte    where to pass back the first character,
-                or -1 if multiline and all branches start ^,
-                or -2 otherwise
-
-Returns:        number of capturing subpatterns
-                or negative values on error
-*/
-
-PCRE_EXP_DEFN int
-pcre_info(const pcre *argument_re, int *optptr, int *first_byte)
-{
-real_pcre internal_re;
-const real_pcre *re = (const real_pcre *)argument_re;
-if (re == NULL) return PCRE_ERROR_NULL;
-if (re->magic_number != MAGIC_NUMBER)
-  {
-  re = _pcre_try_flipped(re, &internal_re, NULL, NULL);
-  if (re == NULL) return PCRE_ERROR_BADMAGIC;
-  }
-if (optptr != NULL) *optptr = (int)(re->options & PUBLIC_OPTIONS);
-if (first_byte != NULL)
-  *first_byte = ((re->flags & PCRE_FIRSTSET) != 0)? re->first_byte :
-     ((re->flags & PCRE_STARTLINE) != 0)? -1 : -2;
-return re->top_bracket;
-}
-
-/* End of pcre_info.c */

src/plugins/PCREPlugin/pcre_maketables.c

@@ -1,3 +1,4 @@
+#define HAVE_CONFIG_H
 /*************************************************
 *      Perl-Compatible Regular Expressions       *
 *************************************************/

src/plugins/PCREPlugin/pcre_newline.c

@@ -1,3 +1,4 @@
+#define HAVE_CONFIG_H
 /*************************************************
 *      Perl-Compatible Regular Expressions       *
 *************************************************/
@@ -6,7 +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) 1997-2012 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -67,23 +68,33 @@ Arguments:
   type         the newline type
   endptr       pointer to the end of the string
   lenptr       where to return the length
-  utf8         TRUE if in utf8 mode
+  utf          TRUE if in utf mode
 
 Returns:       TRUE or FALSE
 */
 
 BOOL
-_pcre_is_newline(const uschar *ptr, int type, const uschar *endptr,
+PRIV(is_newline)(PCRE_PUCHAR ptr, int type, PCRE_PUCHAR endptr, int *lenptr,
-  int *lenptr, BOOL utf8)
+  BOOL utf)
 {
-int c;
+pcre_uint32 c;
-if (utf8) { GETCHAR(c, ptr); } else c = *ptr;
+(void)utf;
+#ifdef SUPPORT_UTF
+if (utf)
+  {
+  GETCHAR(c, ptr);
+  }
+else
+#endif  /* SUPPORT_UTF */
+  c = *ptr;
+
+/* Note that this function is called only for ANY or ANYCRLF. */
 
 if (type == NLTYPE_ANYCRLF) switch(c)
   {
-  case 0x000a: *lenptr = 1; return TRUE;             /* LF */
+  case CHAR_LF: *lenptr = 1; return TRUE;
-  case 0x000d: *lenptr = (ptr < endptr - 1 && ptr[1] == 0x0a)? 2 : 1;
+  case CHAR_CR: *lenptr = (ptr < endptr - 1 && ptr[1] == CHAR_LF)? 2 : 1;
-               return TRUE;                          /* CR */
+               return TRUE;
   default: return FALSE;
   }
 
@@ -91,14 +102,29 @@ if (type == NLTYPE_ANYCRLF) switch(c)
 
 else switch(c)
   {
-  case 0x000a:                                       /* LF */
+#ifdef EBCDIC
-  case 0x000b:                                       /* VT */
+  case CHAR_NEL:
-  case 0x000c: *lenptr = 1; return TRUE;             /* FF */
+#endif
-  case 0x000d: *lenptr = (ptr < endptr - 1 && ptr[1] == 0x0a)? 2 : 1;
+  case CHAR_LF:
-               return TRUE;                          /* CR */
+  case CHAR_VT:
-  case 0x0085: *lenptr = utf8? 2 : 1; return TRUE;   /* NEL */
+  case CHAR_FF: *lenptr = 1; return TRUE;
+
+  case CHAR_CR:
+  *lenptr = (ptr < endptr - 1 && ptr[1] == CHAR_LF)? 2 : 1;
+  return TRUE;
+
+#ifndef EBCDIC
+#ifdef COMPILE_PCRE8
+  case CHAR_NEL: *lenptr = utf? 2 : 1; return TRUE;
   case 0x2028:                                       /* LS */
   case 0x2029: *lenptr = 3; return TRUE;             /* PS */
+#else /* COMPILE_PCRE16 || COMPILE_PCRE32 */
+  case CHAR_NEL:
+  case 0x2028:                                       /* LS */
+  case 0x2029: *lenptr = 1; return TRUE;             /* PS */
+#endif  /* COMPILE_PCRE8 */
+#endif  /* Not EBCDIC */
+
   default: return FALSE;
   }
 }
@@ -117,46 +143,67 @@ Arguments:
   type         the newline type
   startptr     pointer to the start of the string
   lenptr       where to return the length
-  utf8         TRUE if in utf8 mode
+  utf          TRUE if in utf mode
 
 Returns:       TRUE or FALSE
 */
 
 BOOL
-_pcre_was_newline(const uschar *ptr, int type, const uschar *startptr,
+PRIV(was_newline)(PCRE_PUCHAR ptr, int type, PCRE_PUCHAR startptr, int *lenptr,
-  int *lenptr, BOOL utf8)
+  BOOL utf)
 {
-int c;
+pcre_uint32 c;
+(void)utf;
 ptr--;
-#ifdef SUPPORT_UTF8
+#ifdef SUPPORT_UTF
-if (utf8)
+if (utf)
   {
   BACKCHAR(ptr);
   GETCHAR(c, ptr);
   }
-else c = *ptr;
+else
-#else   /* no UTF-8 support */
+#endif  /* SUPPORT_UTF */
   c = *ptr;
-#endif  /* SUPPORT_UTF8 */
+
+/* Note that this function is called only for ANY or ANYCRLF. */
 
 if (type == NLTYPE_ANYCRLF) switch(c)
   {
-  case 0x000a: *lenptr = (ptr > startptr && ptr[-1] == 0x0d)? 2 : 1;
+  case CHAR_LF:
-               return TRUE;                         /* LF */
+  *lenptr = (ptr > startptr && ptr[-1] == CHAR_CR)? 2 : 1;
-  case 0x000d: *lenptr = 1; return TRUE;            /* CR */
+  return TRUE;
+
+  case CHAR_CR: *lenptr = 1; return TRUE;
   default: return FALSE;
   }
 
+/* NLTYPE_ANY */
+
 else switch(c)
   {
-  case 0x000a: *lenptr = (ptr > startptr && ptr[-1] == 0x0d)? 2 : 1;
+  case CHAR_LF:
-               return TRUE;                         /* LF */
+  *lenptr = (ptr > startptr && ptr[-1] == CHAR_CR)? 2 : 1;
-  case 0x000b:                                      /* VT */
+  return TRUE;
-  case 0x000c:                                      /* FF */
+
-  case 0x000d: *lenptr = 1; return TRUE;            /* CR */
+#ifdef EBCDIC
-  case 0x0085: *lenptr = utf8? 2 : 1; return TRUE;  /* NEL */
+  case CHAR_NEL:
+#endif
+  case CHAR_VT:
+  case CHAR_FF:
+  case CHAR_CR: *lenptr = 1; return TRUE;
+
+#ifndef EBCDIC
+#ifdef COMPILE_PCRE8
+  case CHAR_NEL: *lenptr = utf? 2 : 1; return TRUE;
   case 0x2028:                                       /* LS */
   case 0x2029: *lenptr = 3; return TRUE;             /* PS */
+#else /* COMPILE_PCRE16 || COMPILE_PCRE32 */
+  case CHAR_NEL:
+  case 0x2028:                                       /* LS */
+  case 0x2029: *lenptr = 1; return TRUE;             /* PS */
+#endif  /* COMPILE_PCRE8 */
+#endif  /* NotEBCDIC */
+
   default: return FALSE;
   }
 }

src/plugins/PCREPlugin/pcre_ord2utf8.c

@@ -1,3 +1,4 @@
+#define HAVE_CONFIG_H
 /*************************************************
 *      Perl-Compatible Regular Expressions       *
 *************************************************/
@@ -6,7 +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) 1997-2012 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -45,41 +46,50 @@ character value into a UTF8 string. */
 #include "config.h"
 #endif
 
-#include "pcre_internal.h"
+#define COMPILE_PCRE8
 
+#include "pcre_internal.h"
 
 /*************************************************
 *       Convert character value to UTF-8         *
 *************************************************/
 
-/* This function takes an integer value in the range 0 - 0x7fffffff
+/* This function takes an integer value in the range 0 - 0x10ffff
-and encodes it as a UTF-8 character in 0 to 6 bytes.
+and encodes it as a UTF-8 character in 1 to 4 pcre_uchars.
 
 Arguments:
   cvalue     the character value
-  buffer     pointer to buffer for result - at least 6 bytes long
+  buffer     pointer to buffer for result - at least 6 pcre_uchars long
 
 Returns:     number of characters placed in the buffer
 */
 
+unsigned
 int
-_pcre_ord2utf8(int cvalue, uschar *buffer)
+PRIV(ord2utf)(pcre_uint32 cvalue, pcre_uchar *buffer)
 {
-#ifdef SUPPORT_UTF8
+#ifdef SUPPORT_UTF
+
 register int i, j;
-for (i = 0; i < _pcre_utf8_table1_size; i++)
+
-  if (cvalue <= _pcre_utf8_table1[i]) break;
+for (i = 0; i < PRIV(utf8_table1_size); i++)
+  if ((int)cvalue <= PRIV(utf8_table1)[i]) break;
 buffer += i;
 for (j = i; j > 0; j--)
  {
  *buffer-- = 0x80 | (cvalue & 0x3f);
  cvalue >>= 6;
  }
-*buffer = _pcre_utf8_table2[i] | cvalue;
+*buffer = PRIV(utf8_table2)[i] | cvalue;
 return i + 1;
+
 #else
-return 0;   /* Keep compiler happy; this function won't ever be */
+
-#endif      /* called when SUPPORT_UTF8 is not defined. */
+(void)(cvalue);  /* Keep compiler happy; this function won't ever be */
+(void)(buffer);  /* called when SUPPORT_UTF is not defined. */
+return 0;
+
+#endif
 }
 
 /* End of pcre_ord2utf8.c */

src/plugins/PCREPlugin/pcre_plugin.c

@@ -9,7 +9,6 @@
 #include "../../structures.h"
 #include <string.h>
 #include "pcre.h"
-#include "pcreposix.h"
 
 #ifdef  __cplusplus
 extern "C" {
@@ -349,12 +348,8 @@ static struct commands pcre_commandhandlers[] = {
 };
 
 static struct symbol regexp_symbols[] = {
-	{regexp_symbols+1, "regcomp", (void*) regcomp},
+	{regexp_symbols+1, "pcre_compile", (void*) pcre_compile},
-	{regexp_symbols+2, "regexec", (void*) regexec},
+	{regexp_symbols+2, "pcre_exec", (void*) pcre_exec},
-	{regexp_symbols+3, "regerror", (void*) regerror},
-	{regexp_symbols+4, "regfree", (void*) regfree},
-	{regexp_symbols+5, "pcre_compile", (void*) pcre_compile},
-	{regexp_symbols+6, "pcre_exec", (void*) pcre_exec},
 	{NULL, "pcre_free", NULL},
 };
 

src/plugins/PCREPlugin/pcre_refcount.c

@@ -1,3 +1,4 @@
+#define HAVE_CONFIG_H
 /*************************************************
 *      Perl-Compatible Regular Expressions       *
 *************************************************/
@@ -6,7 +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) 1997-2012 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -68,11 +69,21 @@ Returns:        the (possibly updated) count value (a non-negative number), or
                 a negative error number
 */
 
-PCRE_EXP_DEFN int
+#if defined COMPILE_PCRE8
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
 pcre_refcount(pcre *argument_re, int adjust)
+#elif defined COMPILE_PCRE16
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre16_refcount(pcre16 *argument_re, int adjust)
+#elif defined COMPILE_PCRE32
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre32_refcount(pcre32 *argument_re, int adjust)
+#endif
 {
-real_pcre *re = (real_pcre *)argument_re;
+REAL_PCRE *re = (REAL_PCRE *)argument_re;
 if (re == NULL) return PCRE_ERROR_NULL;
+if (re->magic_number != MAGIC_NUMBER) return PCRE_ERROR_BADMAGIC;
+if ((re->flags & PCRE_MODE) == 0) return PCRE_ERROR_BADMODE;
 re->ref_count = (-adjust > re->ref_count)? 0 :
                 (adjust + re->ref_count > 65535)? 65535 :
                 re->ref_count + adjust;

src/plugins/PCREPlugin/pcre_table.c

@@ -1,25 +1,27 @@
+#define HAVE_CONFIG_H
 /*************************************************
 *      Perl-Compatible Regular Expressions       *
 *************************************************/
 
-/* This file is automatically written by the dftables auxiliary 
+/* This file was automatically written by the dftables auxiliary
-program. If you edit it by hand, you might like to edit the Makefile to 
+program. It contains character tables that are used when no external
-prevent its ever being regenerated.
+tables are passed to PCRE by the application that calls it. The tables
+are used only for characters whose code values are less than 256.
 
-This file contains the default tables for characters with codes less than
+The following #includes are present because without them gcc 4.x may remove
-128 (ASCII characters). These tables are used when no external tables are
-passed to PCRE.
-
-The following #include is present because without it gcc 4.x may remove
 the array definition from the final binary if PCRE is built into a static
 library and dead code stripping is activated. This leads to link errors.
 Pulling in the header ensures that the array gets flagged as "someone
 outside this compilation unit might reference this" and so it will always
 be supplied to the linker. */
 
+#ifdef HAVE_CONFIG_H
+#include "config.h"
+#endif
+
 #include "pcre_internal.h"
 
-const unsigned char _pcre_default_tables[] = {
+const pcre_uint8 PRIV(default_tables)[] = {
 
 /* This table is a lower casing table. */
 
@@ -189,4 +191,4 @@ print, punct, and cntrl. Other classes are built from combinations. */
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 240-247 */
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */
 
-/* End of chartables.c */
+/* End of pcre_chartables.c */

src/plugins/PCREPlugin/pcre_tables.c

@@ -1,3 +1,4 @@
+#define HAVE_CONFIG_H
 /*************************************************
 *      Perl-Compatible Regular Expressions       *
 *************************************************/
@@ -6,7 +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) 1997-2012 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -37,6 +38,7 @@ POSSIBILITY OF SUCH DAMAGE.
 -----------------------------------------------------------------------------
 */
 
+#ifndef PCRE_INCLUDED
 
 /* This module contains some fixed tables that are used by more than one of the
 PCRE code modules. The tables are also #included by the pcretest program, which
@@ -50,11 +52,18 @@ clashes with the library. */
 
 #include "pcre_internal.h"
 
+#endif /* PCRE_INCLUDED */
 
 /* Table of sizes for the fixed-length opcodes. It's defined in a macro so that
 the definition is next to the definition of the opcodes in pcre_internal.h. */
 
-const uschar _pcre_OP_lengths[] = { OP_LENGTHS };
+const pcre_uint8 PRIV(OP_lengths)[] = { OP_LENGTHS };
+
+/* Tables of horizontal and vertical whitespace characters, suitable for
+adding to classes. */
+
+const pcre_uint32 PRIV(hspace_list)[] = { HSPACE_LIST };
+const pcre_uint32 PRIV(vspace_list)[] = { VSPACE_LIST };
 
 
 
@@ -65,28 +74,123 @@ const uschar _pcre_OP_lengths[] = { OP_LENGTHS };
 /* These are the breakpoints for different numbers of bytes in a UTF-8
 character. */
 
-#ifdef SUPPORT_UTF8
+#if (defined SUPPORT_UTF && defined COMPILE_PCRE8) \
+  || (defined PCRE_INCLUDED && (defined SUPPORT_PCRE16 || defined SUPPORT_PCRE32))
 
-const int _pcre_utf8_table1[] =
+/* These tables are also required by pcretest in 16- or 32-bit mode. */
+
+const int PRIV(utf8_table1)[] =
   { 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff};
 
-const int _pcre_utf8_table1_size = sizeof(_pcre_utf8_table1)/sizeof(int);
+const int PRIV(utf8_table1_size) = sizeof(PRIV(utf8_table1)) / sizeof(int);
 
 /* These are the indicator bits and the mask for the data bits to set in the
 first byte of a character, indexed by the number of additional bytes. */
 
-const int _pcre_utf8_table2[] = { 0,    0xc0, 0xe0, 0xf0, 0xf8, 0xfc};
+const int PRIV(utf8_table2)[] = { 0,    0xc0, 0xe0, 0xf0, 0xf8, 0xfc};
-const int _pcre_utf8_table3[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01};
+const int PRIV(utf8_table3)[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01};
 
 /* Table of the number of extra bytes, indexed by the first byte masked with
 0x3f. The highest number for a valid UTF-8 first byte is in fact 0x3d. */
 
-const uschar _pcre_utf8_table4[] = {
+const pcre_uint8 PRIV(utf8_table4)[] = {
   1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
   1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
   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 };
 
+#endif /* (SUPPORT_UTF && COMPILE_PCRE8) || (PCRE_INCLUDED && SUPPORT_PCRE[16|32])*/
+
+#ifdef SUPPORT_UTF
+
+/* Table to translate from particular type value to the general value. */
+
+const pcre_uint32 PRIV(ucp_gentype)[] = {
+  ucp_C, ucp_C, ucp_C, ucp_C, ucp_C,  /* Cc, Cf, Cn, Co, Cs */
+  ucp_L, ucp_L, ucp_L, ucp_L, ucp_L,  /* Ll, Lu, Lm, Lo, Lt */
+  ucp_M, ucp_M, ucp_M,                /* Mc, Me, Mn */
+  ucp_N, ucp_N, ucp_N,                /* Nd, Nl, No */
+  ucp_P, ucp_P, ucp_P, ucp_P, ucp_P,  /* Pc, Pd, Pe, Pf, Pi */
+  ucp_P, ucp_P,                       /* Ps, Po */
+  ucp_S, ucp_S, ucp_S, ucp_S,         /* Sc, Sk, Sm, So */
+  ucp_Z, ucp_Z, ucp_Z                 /* Zl, Zp, Zs */
+};
+
+/* This table encodes the rules for finding the end of an extended grapheme
+cluster. Every code point has a grapheme break property which is one of the
+ucp_gbXX values defined in ucp.h. The 2-dimensional table is indexed by the
+properties of two adjacent code points. The left property selects a word from
+the table, and the right property selects a bit from that word like this:
+
+  ucp_gbtable[left-property] & (1 << right-property)
+
+The value is non-zero if a grapheme break is NOT permitted between the relevant
+two code points. The breaking rules are as follows:
+
+1. Break at the start and end of text (pretty obviously).
+
+2. Do not break between a CR and LF; otherwise, break before and   after
+   controls.
+
+3. Do not break Hangul syllable sequences, the rules for which are:
+
+    L may be followed by L, V, LV or LVT
+    LV or V may be followed by V or T
+    LVT or T may be followed by T
+
+4. Do not break before extending characters.
+
+The next two rules are only for extended grapheme clusters (but that's what we
+are implementing).
+
+5. Do not break before SpacingMarks.
+
+6. Do not break after Prepend characters.
+
+7. Otherwise, break everywhere.
+*/
+
+const pcre_uint32 PRIV(ucp_gbtable[]) = {
+   (1<<ucp_gbLF),                                           /*  0 CR */
+   0,                                                       /*  1 LF */
+   0,                                                       /*  2 Control */
+   (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark),                /*  3 Extend */
+   (1<<ucp_gbExtend)|(1<<ucp_gbPrepend)|                    /*  4 Prepend */
+     (1<<ucp_gbSpacingMark)|(1<<ucp_gbL)|
+     (1<<ucp_gbV)|(1<<ucp_gbT)|(1<<ucp_gbLV)|
+     (1<<ucp_gbLVT)|(1<<ucp_gbOther),
+
+   (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark),                /*  5 SpacingMark */
+   (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbL)|   /*  6 L */
+     (1<<ucp_gbL)|(1<<ucp_gbV)|(1<<ucp_gbLV)|(1<<ucp_gbLVT),
+
+   (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbV)|   /*  7 V */
+     (1<<ucp_gbT),
+
+   (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbT),   /*  8 T */
+   (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbV)|   /*  9 LV */
+     (1<<ucp_gbT),
+
+   (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbT),   /* 10 LVT */
+   (1<<ucp_gbRegionalIndicator),                            /* 11 RegionalIndicator */
+   (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)                 /* 12 Other */
+};
+
+#ifdef SUPPORT_JIT
+/* This table reverses PRIV(ucp_gentype). We can save the cost
+of a memory load. */
+
+const int PRIV(ucp_typerange)[] = {
+  ucp_Cc, ucp_Cs,
+  ucp_Ll, ucp_Lu,
+  ucp_Mc, ucp_Mn,
+  ucp_Nd, ucp_No,
+  ucp_Pc, ucp_Ps,
+  ucp_Sc, ucp_So,
+  ucp_Zl, ucp_Zs,
+};
+#endif /* SUPPORT_JIT */
+
 /* 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
@@ -94,225 +198,531 @@ 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. */
+data are unlikely.
 
-const char _pcre_utt_names[] =
+July 2008: There is now a script called maint/GenerateUtt.py that can be used
-  "Any\0"
+to generate this data automatically instead of maintaining it by hand.
-  "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[] = {
+The script was updated in March 2009 to generate a new EBCDIC-compliant
+version. Like all other character and string literals that are compared against
+the regular expression pattern, we must use STR_ macros instead of literal
+strings to make sure that UTF-8 support works on EBCDIC platforms. */
+
+#define STRING_Any0 STR_A STR_n STR_y "\0"
+#define STRING_Arabic0 STR_A STR_r STR_a STR_b STR_i STR_c "\0"
+#define STRING_Armenian0 STR_A STR_r STR_m STR_e STR_n STR_i STR_a STR_n "\0"
+#define STRING_Avestan0 STR_A STR_v STR_e STR_s STR_t STR_a STR_n "\0"
+#define STRING_Balinese0 STR_B STR_a STR_l STR_i STR_n STR_e STR_s STR_e "\0"
+#define STRING_Bamum0 STR_B STR_a STR_m STR_u STR_m "\0"
+#define STRING_Bassa_Vah0 STR_B STR_a STR_s STR_s STR_a STR_UNDERSCORE STR_V STR_a STR_h "\0"
+#define STRING_Batak0 STR_B STR_a STR_t STR_a STR_k "\0"
+#define STRING_Bengali0 STR_B STR_e STR_n STR_g STR_a STR_l STR_i "\0"
+#define STRING_Bopomofo0 STR_B STR_o STR_p STR_o STR_m STR_o STR_f STR_o "\0"
+#define STRING_Brahmi0 STR_B STR_r STR_a STR_h STR_m STR_i "\0"
+#define STRING_Braille0 STR_B STR_r STR_a STR_i STR_l STR_l STR_e "\0"
+#define STRING_Buginese0 STR_B STR_u STR_g STR_i STR_n STR_e STR_s STR_e "\0"
+#define STRING_Buhid0 STR_B STR_u STR_h STR_i STR_d "\0"
+#define STRING_C0 STR_C "\0"
+#define STRING_Canadian_Aboriginal0 STR_C STR_a STR_n STR_a STR_d STR_i STR_a STR_n STR_UNDERSCORE STR_A STR_b STR_o STR_r STR_i STR_g STR_i STR_n STR_a STR_l "\0"
+#define STRING_Carian0 STR_C STR_a STR_r STR_i STR_a STR_n "\0"
+#define STRING_Caucasian_Albanian0 STR_C STR_a STR_u STR_c STR_a STR_s STR_i STR_a STR_n STR_UNDERSCORE STR_A STR_l STR_b STR_a STR_n STR_i STR_a STR_n "\0"
+#define STRING_Cc0 STR_C STR_c "\0"
+#define STRING_Cf0 STR_C STR_f "\0"
+#define STRING_Chakma0 STR_C STR_h STR_a STR_k STR_m STR_a "\0"
+#define STRING_Cham0 STR_C STR_h STR_a STR_m "\0"
+#define STRING_Cherokee0 STR_C STR_h STR_e STR_r STR_o STR_k STR_e STR_e "\0"
+#define STRING_Cn0 STR_C STR_n "\0"
+#define STRING_Co0 STR_C STR_o "\0"
+#define STRING_Common0 STR_C STR_o STR_m STR_m STR_o STR_n "\0"
+#define STRING_Coptic0 STR_C STR_o STR_p STR_t STR_i STR_c "\0"
+#define STRING_Cs0 STR_C STR_s "\0"
+#define STRING_Cuneiform0 STR_C STR_u STR_n STR_e STR_i STR_f STR_o STR_r STR_m "\0"
+#define STRING_Cypriot0 STR_C STR_y STR_p STR_r STR_i STR_o STR_t "\0"
+#define STRING_Cyrillic0 STR_C STR_y STR_r STR_i STR_l STR_l STR_i STR_c "\0"
+#define STRING_Deseret0 STR_D STR_e STR_s STR_e STR_r STR_e STR_t "\0"
+#define STRING_Devanagari0 STR_D STR_e STR_v STR_a STR_n STR_a STR_g STR_a STR_r STR_i "\0"
+#define STRING_Duployan0 STR_D STR_u STR_p STR_l STR_o STR_y STR_a STR_n "\0"
+#define STRING_Egyptian_Hieroglyphs0 STR_E STR_g STR_y STR_p STR_t STR_i STR_a STR_n STR_UNDERSCORE STR_H STR_i STR_e STR_r STR_o STR_g STR_l STR_y STR_p STR_h STR_s "\0"
+#define STRING_Elbasan0 STR_E STR_l STR_b STR_a STR_s STR_a STR_n "\0"
+#define STRING_Ethiopic0 STR_E STR_t STR_h STR_i STR_o STR_p STR_i STR_c "\0"
+#define STRING_Georgian0 STR_G STR_e STR_o STR_r STR_g STR_i STR_a STR_n "\0"
+#define STRING_Glagolitic0 STR_G STR_l STR_a STR_g STR_o STR_l STR_i STR_t STR_i STR_c "\0"
+#define STRING_Gothic0 STR_G STR_o STR_t STR_h STR_i STR_c "\0"
+#define STRING_Grantha0 STR_G STR_r STR_a STR_n STR_t STR_h STR_a "\0"
+#define STRING_Greek0 STR_G STR_r STR_e STR_e STR_k "\0"
+#define STRING_Gujarati0 STR_G STR_u STR_j STR_a STR_r STR_a STR_t STR_i "\0"
+#define STRING_Gurmukhi0 STR_G STR_u STR_r STR_m STR_u STR_k STR_h STR_i "\0"
+#define STRING_Han0 STR_H STR_a STR_n "\0"
+#define STRING_Hangul0 STR_H STR_a STR_n STR_g STR_u STR_l "\0"
+#define STRING_Hanunoo0 STR_H STR_a STR_n STR_u STR_n STR_o STR_o "\0"
+#define STRING_Hebrew0 STR_H STR_e STR_b STR_r STR_e STR_w "\0"
+#define STRING_Hiragana0 STR_H STR_i STR_r STR_a STR_g STR_a STR_n STR_a "\0"
+#define STRING_Imperial_Aramaic0 STR_I STR_m STR_p STR_e STR_r STR_i STR_a STR_l STR_UNDERSCORE STR_A STR_r STR_a STR_m STR_a STR_i STR_c "\0"
+#define STRING_Inherited0 STR_I STR_n STR_h STR_e STR_r STR_i STR_t STR_e STR_d "\0"
+#define STRING_Inscriptional_Pahlavi0 STR_I STR_n STR_s STR_c STR_r STR_i STR_p STR_t STR_i STR_o STR_n STR_a STR_l STR_UNDERSCORE STR_P STR_a STR_h STR_l STR_a STR_v STR_i "\0"
+#define STRING_Inscriptional_Parthian0 STR_I STR_n STR_s STR_c STR_r STR_i STR_p STR_t STR_i STR_o STR_n STR_a STR_l STR_UNDERSCORE STR_P STR_a STR_r STR_t STR_h STR_i STR_a STR_n "\0"
+#define STRING_Javanese0 STR_J STR_a STR_v STR_a STR_n STR_e STR_s STR_e "\0"
+#define STRING_Kaithi0 STR_K STR_a STR_i STR_t STR_h STR_i "\0"
+#define STRING_Kannada0 STR_K STR_a STR_n STR_n STR_a STR_d STR_a "\0"
+#define STRING_Katakana0 STR_K STR_a STR_t STR_a STR_k STR_a STR_n STR_a "\0"
+#define STRING_Kayah_Li0 STR_K STR_a STR_y STR_a STR_h STR_UNDERSCORE STR_L STR_i "\0"
+#define STRING_Kharoshthi0 STR_K STR_h STR_a STR_r STR_o STR_s STR_h STR_t STR_h STR_i "\0"
+#define STRING_Khmer0 STR_K STR_h STR_m STR_e STR_r "\0"
+#define STRING_Khojki0 STR_K STR_h STR_o STR_j STR_k STR_i "\0"
+#define STRING_Khudawadi0 STR_K STR_h STR_u STR_d STR_a STR_w STR_a STR_d STR_i "\0"
+#define STRING_L0 STR_L "\0"
+#define STRING_L_AMPERSAND0 STR_L STR_AMPERSAND "\0"
+#define STRING_Lao0 STR_L STR_a STR_o "\0"
+#define STRING_Latin0 STR_L STR_a STR_t STR_i STR_n "\0"
+#define STRING_Lepcha0 STR_L STR_e STR_p STR_c STR_h STR_a "\0"
+#define STRING_Limbu0 STR_L STR_i STR_m STR_b STR_u "\0"
+#define STRING_Linear_A0 STR_L STR_i STR_n STR_e STR_a STR_r STR_UNDERSCORE STR_A "\0"
+#define STRING_Linear_B0 STR_L STR_i STR_n STR_e STR_a STR_r STR_UNDERSCORE STR_B "\0"
+#define STRING_Lisu0 STR_L STR_i STR_s STR_u "\0"
+#define STRING_Ll0 STR_L STR_l "\0"
+#define STRING_Lm0 STR_L STR_m "\0"
+#define STRING_Lo0 STR_L STR_o "\0"
+#define STRING_Lt0 STR_L STR_t "\0"
+#define STRING_Lu0 STR_L STR_u "\0"
+#define STRING_Lycian0 STR_L STR_y STR_c STR_i STR_a STR_n "\0"
+#define STRING_Lydian0 STR_L STR_y STR_d STR_i STR_a STR_n "\0"
+#define STRING_M0 STR_M "\0"
+#define STRING_Mahajani0 STR_M STR_a STR_h STR_a STR_j STR_a STR_n STR_i "\0"
+#define STRING_Malayalam0 STR_M STR_a STR_l STR_a STR_y STR_a STR_l STR_a STR_m "\0"
+#define STRING_Mandaic0 STR_M STR_a STR_n STR_d STR_a STR_i STR_c "\0"
+#define STRING_Manichaean0 STR_M STR_a STR_n STR_i STR_c STR_h STR_a STR_e STR_a STR_n "\0"
+#define STRING_Mc0 STR_M STR_c "\0"
+#define STRING_Me0 STR_M STR_e "\0"
+#define STRING_Meetei_Mayek0 STR_M STR_e STR_e STR_t STR_e STR_i STR_UNDERSCORE STR_M STR_a STR_y STR_e STR_k "\0"
+#define STRING_Mende_Kikakui0 STR_M STR_e STR_n STR_d STR_e STR_UNDERSCORE STR_K STR_i STR_k STR_a STR_k STR_u STR_i "\0"
+#define STRING_Meroitic_Cursive0 STR_M STR_e STR_r STR_o STR_i STR_t STR_i STR_c STR_UNDERSCORE STR_C STR_u STR_r STR_s STR_i STR_v STR_e "\0"
+#define STRING_Meroitic_Hieroglyphs0 STR_M STR_e STR_r STR_o STR_i STR_t STR_i STR_c STR_UNDERSCORE STR_H STR_i STR_e STR_r STR_o STR_g STR_l STR_y STR_p STR_h STR_s "\0"
+#define STRING_Miao0 STR_M STR_i STR_a STR_o "\0"
+#define STRING_Mn0 STR_M STR_n "\0"
+#define STRING_Modi0 STR_M STR_o STR_d STR_i "\0"
+#define STRING_Mongolian0 STR_M STR_o STR_n STR_g STR_o STR_l STR_i STR_a STR_n "\0"
+#define STRING_Mro0 STR_M STR_r STR_o "\0"
+#define STRING_Myanmar0 STR_M STR_y STR_a STR_n STR_m STR_a STR_r "\0"
+#define STRING_N0 STR_N "\0"
+#define STRING_Nabataean0 STR_N STR_a STR_b STR_a STR_t STR_a STR_e STR_a STR_n "\0"
+#define STRING_Nd0 STR_N STR_d "\0"
+#define STRING_New_Tai_Lue0 STR_N STR_e STR_w STR_UNDERSCORE STR_T STR_a STR_i STR_UNDERSCORE STR_L STR_u STR_e "\0"
+#define STRING_Nko0 STR_N STR_k STR_o "\0"
+#define STRING_Nl0 STR_N STR_l "\0"
+#define STRING_No0 STR_N STR_o "\0"
+#define STRING_Ogham0 STR_O STR_g STR_h STR_a STR_m "\0"
+#define STRING_Ol_Chiki0 STR_O STR_l STR_UNDERSCORE STR_C STR_h STR_i STR_k STR_i "\0"
+#define STRING_Old_Italic0 STR_O STR_l STR_d STR_UNDERSCORE STR_I STR_t STR_a STR_l STR_i STR_c "\0"
+#define STRING_Old_North_Arabian0 STR_O STR_l STR_d STR_UNDERSCORE STR_N STR_o STR_r STR_t STR_h STR_UNDERSCORE STR_A STR_r STR_a STR_b STR_i STR_a STR_n "\0"
+#define STRING_Old_Permic0 STR_O STR_l STR_d STR_UNDERSCORE STR_P STR_e STR_r STR_m STR_i STR_c "\0"
+#define STRING_Old_Persian0 STR_O STR_l STR_d STR_UNDERSCORE STR_P STR_e STR_r STR_s STR_i STR_a STR_n "\0"
+#define STRING_Old_South_Arabian0 STR_O STR_l STR_d STR_UNDERSCORE STR_S STR_o STR_u STR_t STR_h STR_UNDERSCORE STR_A STR_r STR_a STR_b STR_i STR_a STR_n "\0"
+#define STRING_Old_Turkic0 STR_O STR_l STR_d STR_UNDERSCORE STR_T STR_u STR_r STR_k STR_i STR_c "\0"
+#define STRING_Oriya0 STR_O STR_r STR_i STR_y STR_a "\0"
+#define STRING_Osmanya0 STR_O STR_s STR_m STR_a STR_n STR_y STR_a "\0"
+#define STRING_P0 STR_P "\0"
+#define STRING_Pahawh_Hmong0 STR_P STR_a STR_h STR_a STR_w STR_h STR_UNDERSCORE STR_H STR_m STR_o STR_n STR_g "\0"
+#define STRING_Palmyrene0 STR_P STR_a STR_l STR_m STR_y STR_r STR_e STR_n STR_e "\0"
+#define STRING_Pau_Cin_Hau0 STR_P STR_a STR_u STR_UNDERSCORE STR_C STR_i STR_n STR_UNDERSCORE STR_H STR_a STR_u "\0"
+#define STRING_Pc0 STR_P STR_c "\0"
+#define STRING_Pd0 STR_P STR_d "\0"
+#define STRING_Pe0 STR_P STR_e "\0"
+#define STRING_Pf0 STR_P STR_f "\0"
+#define STRING_Phags_Pa0 STR_P STR_h STR_a STR_g STR_s STR_UNDERSCORE STR_P STR_a "\0"
+#define STRING_Phoenician0 STR_P STR_h STR_o STR_e STR_n STR_i STR_c STR_i STR_a STR_n "\0"
+#define STRING_Pi0 STR_P STR_i "\0"
+#define STRING_Po0 STR_P STR_o "\0"
+#define STRING_Ps0 STR_P STR_s "\0"
+#define STRING_Psalter_Pahlavi0 STR_P STR_s STR_a STR_l STR_t STR_e STR_r STR_UNDERSCORE STR_P STR_a STR_h STR_l STR_a STR_v STR_i "\0"
+#define STRING_Rejang0 STR_R STR_e STR_j STR_a STR_n STR_g "\0"
+#define STRING_Runic0 STR_R STR_u STR_n STR_i STR_c "\0"
+#define STRING_S0 STR_S "\0"
+#define STRING_Samaritan0 STR_S STR_a STR_m STR_a STR_r STR_i STR_t STR_a STR_n "\0"
+#define STRING_Saurashtra0 STR_S STR_a STR_u STR_r STR_a STR_s STR_h STR_t STR_r STR_a "\0"
+#define STRING_Sc0 STR_S STR_c "\0"
+#define STRING_Sharada0 STR_S STR_h STR_a STR_r STR_a STR_d STR_a "\0"
+#define STRING_Shavian0 STR_S STR_h STR_a STR_v STR_i STR_a STR_n "\0"
+#define STRING_Siddham0 STR_S STR_i STR_d STR_d STR_h STR_a STR_m "\0"
+#define STRING_Sinhala0 STR_S STR_i STR_n STR_h STR_a STR_l STR_a "\0"
+#define STRING_Sk0 STR_S STR_k "\0"
+#define STRING_Sm0 STR_S STR_m "\0"
+#define STRING_So0 STR_S STR_o "\0"
+#define STRING_Sora_Sompeng0 STR_S STR_o STR_r STR_a STR_UNDERSCORE STR_S STR_o STR_m STR_p STR_e STR_n STR_g "\0"
+#define STRING_Sundanese0 STR_S STR_u STR_n STR_d STR_a STR_n STR_e STR_s STR_e "\0"
+#define STRING_Syloti_Nagri0 STR_S STR_y STR_l STR_o STR_t STR_i STR_UNDERSCORE STR_N STR_a STR_g STR_r STR_i "\0"
+#define STRING_Syriac0 STR_S STR_y STR_r STR_i STR_a STR_c "\0"
+#define STRING_Tagalog0 STR_T STR_a STR_g STR_a STR_l STR_o STR_g "\0"
+#define STRING_Tagbanwa0 STR_T STR_a STR_g STR_b STR_a STR_n STR_w STR_a "\0"
+#define STRING_Tai_Le0 STR_T STR_a STR_i STR_UNDERSCORE STR_L STR_e "\0"
+#define STRING_Tai_Tham0 STR_T STR_a STR_i STR_UNDERSCORE STR_T STR_h STR_a STR_m "\0"
+#define STRING_Tai_Viet0 STR_T STR_a STR_i STR_UNDERSCORE STR_V STR_i STR_e STR_t "\0"
+#define STRING_Takri0 STR_T STR_a STR_k STR_r STR_i "\0"
+#define STRING_Tamil0 STR_T STR_a STR_m STR_i STR_l "\0"
+#define STRING_Telugu0 STR_T STR_e STR_l STR_u STR_g STR_u "\0"
+#define STRING_Thaana0 STR_T STR_h STR_a STR_a STR_n STR_a "\0"
+#define STRING_Thai0 STR_T STR_h STR_a STR_i "\0"
+#define STRING_Tibetan0 STR_T STR_i STR_b STR_e STR_t STR_a STR_n "\0"
+#define STRING_Tifinagh0 STR_T STR_i STR_f STR_i STR_n STR_a STR_g STR_h "\0"
+#define STRING_Tirhuta0 STR_T STR_i STR_r STR_h STR_u STR_t STR_a "\0"
+#define STRING_Ugaritic0 STR_U STR_g STR_a STR_r STR_i STR_t STR_i STR_c "\0"
+#define STRING_Vai0 STR_V STR_a STR_i "\0"
+#define STRING_Warang_Citi0 STR_W STR_a STR_r STR_a STR_n STR_g STR_UNDERSCORE STR_C STR_i STR_t STR_i "\0"
+#define STRING_Xan0 STR_X STR_a STR_n "\0"
+#define STRING_Xps0 STR_X STR_p STR_s "\0"
+#define STRING_Xsp0 STR_X STR_s STR_p "\0"
+#define STRING_Xuc0 STR_X STR_u STR_c "\0"
+#define STRING_Xwd0 STR_X STR_w STR_d "\0"
+#define STRING_Yi0 STR_Y STR_i "\0"
+#define STRING_Z0 STR_Z "\0"
+#define STRING_Zl0 STR_Z STR_l "\0"
+#define STRING_Zp0 STR_Z STR_p "\0"
+#define STRING_Zs0 STR_Z STR_s "\0"
+
+const char PRIV(utt_names)[] =
+  STRING_Any0
+  STRING_Arabic0
+  STRING_Armenian0
+  STRING_Avestan0
+  STRING_Balinese0
+  STRING_Bamum0
+  STRING_Bassa_Vah0
+  STRING_Batak0
+  STRING_Bengali0
+  STRING_Bopomofo0
+  STRING_Brahmi0
+  STRING_Braille0
+  STRING_Buginese0
+  STRING_Buhid0
+  STRING_C0
+  STRING_Canadian_Aboriginal0
+  STRING_Carian0
+  STRING_Caucasian_Albanian0
+  STRING_Cc0
+  STRING_Cf0
+  STRING_Chakma0
+  STRING_Cham0
+  STRING_Cherokee0
+  STRING_Cn0
+  STRING_Co0
+  STRING_Common0
+  STRING_Coptic0
+  STRING_Cs0
+  STRING_Cuneiform0
+  STRING_Cypriot0
+  STRING_Cyrillic0
+  STRING_Deseret0
+  STRING_Devanagari0
+  STRING_Duployan0
+  STRING_Egyptian_Hieroglyphs0
+  STRING_Elbasan0
+  STRING_Ethiopic0
+  STRING_Georgian0
+  STRING_Glagolitic0
+  STRING_Gothic0
+  STRING_Grantha0
+  STRING_Greek0
+  STRING_Gujarati0
+  STRING_Gurmukhi0
+  STRING_Han0
+  STRING_Hangul0
+  STRING_Hanunoo0
+  STRING_Hebrew0
+  STRING_Hiragana0
+  STRING_Imperial_Aramaic0
+  STRING_Inherited0
+  STRING_Inscriptional_Pahlavi0
+  STRING_Inscriptional_Parthian0
+  STRING_Javanese0
+  STRING_Kaithi0
+  STRING_Kannada0
+  STRING_Katakana0
+  STRING_Kayah_Li0
+  STRING_Kharoshthi0
+  STRING_Khmer0
+  STRING_Khojki0
+  STRING_Khudawadi0
+  STRING_L0
+  STRING_L_AMPERSAND0
+  STRING_Lao0
+  STRING_Latin0
+  STRING_Lepcha0
+  STRING_Limbu0
+  STRING_Linear_A0
+  STRING_Linear_B0
+  STRING_Lisu0
+  STRING_Ll0
+  STRING_Lm0
+  STRING_Lo0
+  STRING_Lt0
+  STRING_Lu0
+  STRING_Lycian0
+  STRING_Lydian0
+  STRING_M0
+  STRING_Mahajani0
+  STRING_Malayalam0
+  STRING_Mandaic0
+  STRING_Manichaean0
+  STRING_Mc0
+  STRING_Me0
+  STRING_Meetei_Mayek0
+  STRING_Mende_Kikakui0
+  STRING_Meroitic_Cursive0
+  STRING_Meroitic_Hieroglyphs0
+  STRING_Miao0
+  STRING_Mn0
+  STRING_Modi0
+  STRING_Mongolian0
+  STRING_Mro0
+  STRING_Myanmar0
+  STRING_N0
+  STRING_Nabataean0
+  STRING_Nd0
+  STRING_New_Tai_Lue0
+  STRING_Nko0
+  STRING_Nl0
+  STRING_No0
+  STRING_Ogham0
+  STRING_Ol_Chiki0
+  STRING_Old_Italic0
+  STRING_Old_North_Arabian0
+  STRING_Old_Permic0
+  STRING_Old_Persian0
+  STRING_Old_South_Arabian0
+  STRING_Old_Turkic0
+  STRING_Oriya0
+  STRING_Osmanya0
+  STRING_P0
+  STRING_Pahawh_Hmong0
+  STRING_Palmyrene0
+  STRING_Pau_Cin_Hau0
+  STRING_Pc0
+  STRING_Pd0
+  STRING_Pe0
+  STRING_Pf0
+  STRING_Phags_Pa0
+  STRING_Phoenician0
+  STRING_Pi0
+  STRING_Po0
+  STRING_Ps0
+  STRING_Psalter_Pahlavi0
+  STRING_Rejang0
+  STRING_Runic0
+  STRING_S0
+  STRING_Samaritan0
+  STRING_Saurashtra0
+  STRING_Sc0
+  STRING_Sharada0
+  STRING_Shavian0
+  STRING_Siddham0
+  STRING_Sinhala0
+  STRING_Sk0
+  STRING_Sm0
+  STRING_So0
+  STRING_Sora_Sompeng0
+  STRING_Sundanese0
+  STRING_Syloti_Nagri0
+  STRING_Syriac0
+  STRING_Tagalog0
+  STRING_Tagbanwa0
+  STRING_Tai_Le0
+  STRING_Tai_Tham0
+  STRING_Tai_Viet0
+  STRING_Takri0
+  STRING_Tamil0
+  STRING_Telugu0
+  STRING_Thaana0
+  STRING_Thai0
+  STRING_Tibetan0
+  STRING_Tifinagh0
+  STRING_Tirhuta0
+  STRING_Ugaritic0
+  STRING_Vai0
+  STRING_Warang_Citi0
+  STRING_Xan0
+  STRING_Xps0
+  STRING_Xsp0
+  STRING_Xuc0
+  STRING_Xwd0
+  STRING_Yi0
+  STRING_Z0
+  STRING_Zl0
+  STRING_Zp0
+  STRING_Zs0;
+
+const ucp_type_table PRIV(utt)[] = {
   {   0, PT_ANY, 0 },
   {   4, PT_SC, ucp_Arabic },
   {  11, PT_SC, ucp_Armenian },
-  { 20,  PT_SC, ucp_Balinese },
+  {  20, PT_SC, ucp_Avestan },
-  { 29,  PT_SC, ucp_Bengali },
+  {  28, PT_SC, ucp_Balinese },
-  { 37,  PT_SC, ucp_Bopomofo },
+  {  37, PT_SC, ucp_Bamum },
-  { 46,  PT_SC, ucp_Braille },
+  {  43, PT_SC, ucp_Bassa_Vah },
-  { 54,  PT_SC, ucp_Buginese },
+  {  53, PT_SC, ucp_Batak },
-  { 63,  PT_SC, ucp_Buhid },
+  {  59, PT_SC, ucp_Bengali },
-  { 69,  PT_GC, ucp_C },
+  {  67, PT_SC, ucp_Bopomofo },
-  { 71,  PT_SC, ucp_Canadian_Aboriginal },
+  {  76, PT_SC, ucp_Brahmi },
-  { 91,  PT_PC, ucp_Cc },
+  {  83, PT_SC, ucp_Braille },
-  { 94,  PT_PC, ucp_Cf },
+  {  91, PT_SC, ucp_Buginese },
-  { 97,  PT_SC, ucp_Cherokee },
+  { 100, PT_SC, ucp_Buhid },
-  { 106, PT_PC, ucp_Cn },
+  { 106, PT_GC, ucp_C },
-  { 109, PT_PC, ucp_Co },
+  { 108, PT_SC, ucp_Canadian_Aboriginal },
-  { 112, PT_SC, ucp_Common },
+  { 128, PT_SC, ucp_Carian },
-  { 119, PT_SC, ucp_Coptic },
+  { 135, PT_SC, ucp_Caucasian_Albanian },
-  { 126, PT_PC, ucp_Cs },
+  { 154, PT_PC, ucp_Cc },
-  { 129, PT_SC, ucp_Cuneiform },
+  { 157, PT_PC, ucp_Cf },
-  { 139, PT_SC, ucp_Cypriot },
+  { 160, PT_SC, ucp_Chakma },
-  { 147, PT_SC, ucp_Cyrillic },
+  { 167, PT_SC, ucp_Cham },
-  { 156, PT_SC, ucp_Deseret },
+  { 172, PT_SC, ucp_Cherokee },
-  { 164, PT_SC, ucp_Devanagari },
+  { 181, PT_PC, ucp_Cn },
-  { 175, PT_SC, ucp_Ethiopic },
+  { 184, PT_PC, ucp_Co },
-  { 184, PT_SC, ucp_Georgian },
+  { 187, PT_SC, ucp_Common },
-  { 193, PT_SC, ucp_Glagolitic },
+  { 194, PT_SC, ucp_Coptic },
-  { 204, PT_SC, ucp_Gothic },
+  { 201, PT_PC, ucp_Cs },
-  { 211, PT_SC, ucp_Greek },
+  { 204, PT_SC, ucp_Cuneiform },
-  { 217, PT_SC, ucp_Gujarati },
+  { 214, PT_SC, ucp_Cypriot },
-  { 226, PT_SC, ucp_Gurmukhi },
+  { 222, PT_SC, ucp_Cyrillic },
-  { 235, PT_SC, ucp_Han },
+  { 231, PT_SC, ucp_Deseret },
-  { 239, PT_SC, ucp_Hangul },
+  { 239, PT_SC, ucp_Devanagari },
-  { 246, PT_SC, ucp_Hanunoo },
+  { 250, PT_SC, ucp_Duployan },
-  { 254, PT_SC, ucp_Hebrew },
+  { 259, PT_SC, ucp_Egyptian_Hieroglyphs },
-  { 261, PT_SC, ucp_Hiragana },
+  { 280, PT_SC, ucp_Elbasan },
-  { 270, PT_SC, ucp_Inherited },
+  { 288, PT_SC, ucp_Ethiopic },
-  { 280, PT_SC, ucp_Kannada },
+  { 297, PT_SC, ucp_Georgian },
-  { 288, PT_SC, ucp_Katakana },
+  { 306, PT_SC, ucp_Glagolitic },
-  { 297, PT_SC, ucp_Kharoshthi },
+  { 317, PT_SC, ucp_Gothic },
-  { 308, PT_SC, ucp_Khmer },
+  { 324, PT_SC, ucp_Grantha },
-  { 314, PT_GC, ucp_L },
+  { 332, PT_SC, ucp_Greek },
-  { 316, PT_LAMP, 0 },
+  { 338, PT_SC, ucp_Gujarati },
-  { 319, PT_SC, ucp_Lao },
+  { 347, PT_SC, ucp_Gurmukhi },
-  { 323, PT_SC, ucp_Latin },
+  { 356, PT_SC, ucp_Han },
-  { 329, PT_SC, ucp_Limbu },
+  { 360, PT_SC, ucp_Hangul },
-  { 335, PT_SC, ucp_Linear_B },
+  { 367, PT_SC, ucp_Hanunoo },
-  { 344, PT_PC, ucp_Ll },
+  { 375, PT_SC, ucp_Hebrew },
-  { 347, PT_PC, ucp_Lm },
+  { 382, PT_SC, ucp_Hiragana },
-  { 350, PT_PC, ucp_Lo },
+  { 391, PT_SC, ucp_Imperial_Aramaic },
-  { 353, PT_PC, ucp_Lt },
+  { 408, PT_SC, ucp_Inherited },
-  { 356, PT_PC, ucp_Lu },
+  { 418, PT_SC, ucp_Inscriptional_Pahlavi },
-  { 359, PT_GC, ucp_M },
+  { 440, PT_SC, ucp_Inscriptional_Parthian },
-  { 361, PT_SC, ucp_Malayalam },
+  { 463, PT_SC, ucp_Javanese },
-  { 371, PT_PC, ucp_Mc },
+  { 472, PT_SC, ucp_Kaithi },
-  { 374, PT_PC, ucp_Me },
+  { 479, PT_SC, ucp_Kannada },
-  { 377, PT_PC, ucp_Mn },
+  { 487, PT_SC, ucp_Katakana },
-  { 380, PT_SC, ucp_Mongolian },
+  { 496, PT_SC, ucp_Kayah_Li },
-  { 390, PT_SC, ucp_Myanmar },
+  { 505, PT_SC, ucp_Kharoshthi },
-  { 398, PT_GC, ucp_N },
+  { 516, PT_SC, ucp_Khmer },
-  { 400, PT_PC, ucp_Nd },
+  { 522, PT_SC, ucp_Khojki },
-  { 403, PT_SC, ucp_New_Tai_Lue },
+  { 529, PT_SC, ucp_Khudawadi },
-  { 415, PT_SC, ucp_Nko },
+  { 539, PT_GC, ucp_L },
-  { 419, PT_PC, ucp_Nl },
+  { 541, PT_LAMP, 0 },
-  { 422, PT_PC, ucp_No },
+  { 544, PT_SC, ucp_Lao },
-  { 425, PT_SC, ucp_Ogham },
+  { 548, PT_SC, ucp_Latin },
-  { 431, PT_SC, ucp_Old_Italic },
+  { 554, PT_SC, ucp_Lepcha },
-  { 442, PT_SC, ucp_Old_Persian },
+  { 561, PT_SC, ucp_Limbu },
-  { 454, PT_SC, ucp_Oriya },
+  { 567, PT_SC, ucp_Linear_A },
-  { 460, PT_SC, ucp_Osmanya },
+  { 576, PT_SC, ucp_Linear_B },
-  { 468, PT_GC, ucp_P },
+  { 585, PT_SC, ucp_Lisu },
-  { 470, PT_PC, ucp_Pc },
+  { 590, PT_PC, ucp_Ll },
-  { 473, PT_PC, ucp_Pd },
+  { 593, PT_PC, ucp_Lm },
-  { 476, PT_PC, ucp_Pe },
+  { 596, PT_PC, ucp_Lo },
-  { 479, PT_PC, ucp_Pf },
+  { 599, PT_PC, ucp_Lt },
-  { 482, PT_SC, ucp_Phags_Pa },
+  { 602, PT_PC, ucp_Lu },
-  { 491, PT_SC, ucp_Phoenician },
+  { 605, PT_SC, ucp_Lycian },
-  { 502, PT_PC, ucp_Pi },
+  { 612, PT_SC, ucp_Lydian },
-  { 505, PT_PC, ucp_Po },
+  { 619, PT_GC, ucp_M },
-  { 508, PT_PC, ucp_Ps },
+  { 621, PT_SC, ucp_Mahajani },
-  { 511, PT_SC, ucp_Runic },
+  { 630, PT_SC, ucp_Malayalam },
-  { 517, PT_GC, ucp_S },
+  { 640, PT_SC, ucp_Mandaic },
-  { 519, PT_PC, ucp_Sc },
+  { 648, PT_SC, ucp_Manichaean },
-  { 522, PT_SC, ucp_Shavian },
+  { 659, PT_PC, ucp_Mc },
-  { 530, PT_SC, ucp_Sinhala },
+  { 662, PT_PC, ucp_Me },
-  { 538, PT_PC, ucp_Sk },
+  { 665, PT_SC, ucp_Meetei_Mayek },
-  { 541, PT_PC, ucp_Sm },
+  { 678, PT_SC, ucp_Mende_Kikakui },
-  { 544, PT_PC, ucp_So },
+  { 692, PT_SC, ucp_Meroitic_Cursive },
-  { 547, PT_SC, ucp_Syloti_Nagri },
+  { 709, PT_SC, ucp_Meroitic_Hieroglyphs },
-  { 560, PT_SC, ucp_Syriac },
+  { 730, PT_SC, ucp_Miao },
-  { 567, PT_SC, ucp_Tagalog },
+  { 735, PT_PC, ucp_Mn },
-  { 575, PT_SC, ucp_Tagbanwa },
+  { 738, PT_SC, ucp_Modi },
-  { 584, PT_SC, ucp_Tai_Le },
+  { 743, PT_SC, ucp_Mongolian },
-  { 591, PT_SC, ucp_Tamil },
+  { 753, PT_SC, ucp_Mro },
-  { 597, PT_SC, ucp_Telugu },
+  { 757, PT_SC, ucp_Myanmar },
-  { 604, PT_SC, ucp_Thaana },
+  { 765, PT_GC, ucp_N },
-  { 611, PT_SC, ucp_Thai },
+  { 767, PT_SC, ucp_Nabataean },
-  { 616, PT_SC, ucp_Tibetan },
+  { 777, PT_PC, ucp_Nd },
-  { 624, PT_SC, ucp_Tifinagh },
+  { 780, PT_SC, ucp_New_Tai_Lue },
-  { 633, PT_SC, ucp_Ugaritic },
+  { 792, PT_SC, ucp_Nko },
-  { 642, PT_SC, ucp_Yi },
+  { 796, PT_PC, ucp_Nl },
-  { 645, PT_GC, ucp_Z },
+  { 799, PT_PC, ucp_No },
-  { 647, PT_PC, ucp_Zl },
+  { 802, PT_SC, ucp_Ogham },
-  { 650, PT_PC, ucp_Zp },
+  { 808, PT_SC, ucp_Ol_Chiki },
-  { 653, PT_PC, ucp_Zs }
+  { 817, PT_SC, ucp_Old_Italic },
+  { 828, PT_SC, ucp_Old_North_Arabian },
+  { 846, PT_SC, ucp_Old_Permic },
+  { 857, PT_SC, ucp_Old_Persian },
+  { 869, PT_SC, ucp_Old_South_Arabian },
+  { 887, PT_SC, ucp_Old_Turkic },
+  { 898, PT_SC, ucp_Oriya },
+  { 904, PT_SC, ucp_Osmanya },
+  { 912, PT_GC, ucp_P },
+  { 914, PT_SC, ucp_Pahawh_Hmong },
+  { 927, PT_SC, ucp_Palmyrene },
+  { 937, PT_SC, ucp_Pau_Cin_Hau },
+  { 949, PT_PC, ucp_Pc },
+  { 952, PT_PC, ucp_Pd },
+  { 955, PT_PC, ucp_Pe },
+  { 958, PT_PC, ucp_Pf },
+  { 961, PT_SC, ucp_Phags_Pa },
+  { 970, PT_SC, ucp_Phoenician },
+  { 981, PT_PC, ucp_Pi },
+  { 984, PT_PC, ucp_Po },
+  { 987, PT_PC, ucp_Ps },
+  { 990, PT_SC, ucp_Psalter_Pahlavi },
+  { 1006, PT_SC, ucp_Rejang },
+  { 1013, PT_SC, ucp_Runic },
+  { 1019, PT_GC, ucp_S },
+  { 1021, PT_SC, ucp_Samaritan },
+  { 1031, PT_SC, ucp_Saurashtra },
+  { 1042, PT_PC, ucp_Sc },
+  { 1045, PT_SC, ucp_Sharada },
+  { 1053, PT_SC, ucp_Shavian },
+  { 1061, PT_SC, ucp_Siddham },
+  { 1069, PT_SC, ucp_Sinhala },
+  { 1077, PT_PC, ucp_Sk },
+  { 1080, PT_PC, ucp_Sm },
+  { 1083, PT_PC, ucp_So },
+  { 1086, PT_SC, ucp_Sora_Sompeng },
+  { 1099, PT_SC, ucp_Sundanese },
+  { 1109, PT_SC, ucp_Syloti_Nagri },
+  { 1122, PT_SC, ucp_Syriac },
+  { 1129, PT_SC, ucp_Tagalog },
+  { 1137, PT_SC, ucp_Tagbanwa },
+  { 1146, PT_SC, ucp_Tai_Le },
+  { 1153, PT_SC, ucp_Tai_Tham },
+  { 1162, PT_SC, ucp_Tai_Viet },
+  { 1171, PT_SC, ucp_Takri },
+  { 1177, PT_SC, ucp_Tamil },
+  { 1183, PT_SC, ucp_Telugu },
+  { 1190, PT_SC, ucp_Thaana },
+  { 1197, PT_SC, ucp_Thai },
+  { 1202, PT_SC, ucp_Tibetan },
+  { 1210, PT_SC, ucp_Tifinagh },
+  { 1219, PT_SC, ucp_Tirhuta },
+  { 1227, PT_SC, ucp_Ugaritic },
+  { 1236, PT_SC, ucp_Vai },
+  { 1240, PT_SC, ucp_Warang_Citi },
+  { 1252, PT_ALNUM, 0 },
+  { 1256, PT_PXSPACE, 0 },
+  { 1260, PT_SPACE, 0 },
+  { 1264, PT_UCNC, 0 },
+  { 1268, PT_WORD, 0 },
+  { 1272, PT_SC, ucp_Yi },
+  { 1275, PT_GC, ucp_Z },
+  { 1277, PT_PC, ucp_Zl },
+  { 1280, PT_PC, ucp_Zp },
+  { 1283, PT_PC, ucp_Zs }
 };
 
-const int _pcre_utt_size = sizeof(_pcre_utt)/sizeof(ucp_type_table);
+const int PRIV(utt_size) = sizeof(PRIV(utt)) / sizeof(ucp_type_table);
 
-#endif  /* SUPPORT_UTF8 */
+#endif /* SUPPORT_UTF */
 
 /* End of pcre_tables.c */

src/plugins/PCREPlugin/pcre_try_flipped.c

@@ -1,137 +0,0 @@
-/*************************************************
-*      Perl-Compatible Regular Expressions       *
-*************************************************/
-
-/* 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
-
------------------------------------------------------------------------------
-Redistribution and use in source and binary forms, with or without
-modification, are permitted provided that the following conditions are met:
-
-    * Redistributions of source code must retain the above copyright notice,
-      this list of conditions and the following disclaimer.
-
-    * Redistributions in binary form must reproduce the above copyright
-      notice, this list of conditions and the following disclaimer in the
-      documentation and/or other materials provided with the distribution.
-
-    * Neither the name of the University of Cambridge nor the names of its
-      contributors may be used to endorse or promote products derived from
-      this software without specific prior written permission.
-
-THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
-AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
-IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
-ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
-LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
-CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
-SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
-INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
-CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
-ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
-POSSIBILITY OF SUCH DAMAGE.
------------------------------------------------------------------------------
-*/
-
-
-/* This module contains an internal function that tests a compiled pattern to
-see if it was compiled with the opposite endianness. If so, it uses an
-auxiliary local function to flip the appropriate bytes. */
-
-
-#ifdef HAVE_CONFIG_H
-#include "config.h"
-#endif
-
-#include "pcre_internal.h"
-
-
-/*************************************************
-*         Flip bytes in an integer               *
-*************************************************/
-
-/* This function is called when the magic number in a regex doesn't match, in
-order to flip its bytes to see if we are dealing with a pattern that was
-compiled on a host of different endianness. If so, this function is used to
-flip other byte values.
-
-Arguments:
-  value        the number to flip
-  n            the number of bytes to flip (assumed to be 2 or 4)
-
-Returns:       the flipped value
-*/
-
-static unsigned long int
-byteflip(unsigned long int value, int n)
-{
-if (n == 2) return ((value & 0x00ff) << 8) | ((value & 0xff00) >> 8);
-return ((value & 0x000000ff) << 24) |
-       ((value & 0x0000ff00) <<  8) |
-       ((value & 0x00ff0000) >>  8) |
-       ((value & 0xff000000) >> 24);
-}
-
-
-
-/*************************************************
-*       Test for a byte-flipped compiled regex   *
-*************************************************/
-
-/* This function is called from pcre_exec(), pcre_dfa_exec(), and also from
-pcre_fullinfo(). Its job is to test whether the regex is byte-flipped - that
-is, it was compiled on a system of opposite endianness. The function is called
-only when the native MAGIC_NUMBER test fails. If the regex is indeed flipped,
-we flip all the relevant values into a different data block, and return it.
-
-Arguments:
-  re               points to the regex
-  study            points to study data, or NULL
-  internal_re      points to a new regex block
-  internal_study   points to a new study block
-
-Returns:           the new block if is is indeed a byte-flipped regex
-                   NULL if it is not
-*/
-
-real_pcre *
-_pcre_try_flipped(const real_pcre *re, real_pcre *internal_re,
-  const pcre_study_data *study, pcre_study_data *internal_study)
-{
-if (byteflip(re->magic_number, sizeof(re->magic_number)) != MAGIC_NUMBER)
-  return NULL;
-
-*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 =
-  (pcre_uint16)byteflip(re->top_backref, sizeof(re->top_backref));
-internal_re->first_byte =
-  (pcre_uint16)byteflip(re->first_byte, sizeof(re->first_byte));
-internal_re->req_byte =
-  (pcre_uint16)byteflip(re->req_byte, sizeof(re->req_byte));
-internal_re->name_table_offset =
-  (pcre_uint16)byteflip(re->name_table_offset, sizeof(re->name_table_offset));
-internal_re->name_entry_size =
-  (pcre_uint16)byteflip(re->name_entry_size, sizeof(re->name_entry_size));
-internal_re->name_count =
-  (pcre_uint16)byteflip(re->name_count, sizeof(re->name_count));
-
-if (study != NULL)
-  {
-  *internal_study = *study;   /* To copy other fields */
-  internal_study->size = byteflip(study->size, sizeof(study->size));
-  internal_study->options = byteflip(study->options, sizeof(study->options));
-  }
-
-return internal_re;
-}
-
-/* End of pcre_tryflipped.c */

src/plugins/PCREPlugin/pcre_ucp_searchfuncs.c

@@ -1,179 +0,0 @@
-/*************************************************
-*      Perl-Compatible Regular Expressions       *
-*************************************************/
-
-/* 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
-
------------------------------------------------------------------------------
-Redistribution and use in source and binary forms, with or without
-modification, are permitted provided that the following conditions are met:
-
-    * Redistributions of source code must retain the above copyright notice,
-      this list of conditions and the following disclaimer.
-
-    * Redistributions in binary form must reproduce the above copyright
-      notice, this list of conditions and the following disclaimer in the
-      documentation and/or other materials provided with the distribution.
-
-    * Neither the name of the University of Cambridge nor the names of its
-      contributors may be used to endorse or promote products derived from
-      this software without specific prior written permission.
-
-THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
-AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
-IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
-ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
-LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
-CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
-SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
-INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
-CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
-ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
-POSSIBILITY OF SUCH DAMAGE.
------------------------------------------------------------------------------
-*/
-
-
-/* This module contains code for searching the table of Unicode character
-properties. */
-
-#ifdef HAVE_CONFIG_H
-#include "config.h"
-#endif
-
-#include "pcre_internal.h"
-
-#include "ucp.h"               /* Category definitions */
-#include "ucpinternal.h"       /* Internal table details */
-#include "ucptable.h"          /* The table itself */
-
-
-/* Table to translate from particular type value to the general value. */
-
-static const int ucp_gentype[] = {
-  ucp_C, ucp_C, ucp_C, ucp_C, ucp_C,  /* Cc, Cf, Cn, Co, Cs */
-  ucp_L, ucp_L, ucp_L, ucp_L, ucp_L,  /* Ll, Lu, Lm, Lo, Lt */
-  ucp_M, ucp_M, ucp_M,                /* Mc, Me, Mn */
-  ucp_N, ucp_N, ucp_N,                /* Nd, Nl, No */
-  ucp_P, ucp_P, ucp_P, ucp_P, ucp_P,  /* Pc, Pd, Pe, Pf, Pi */
-  ucp_P, ucp_P,                       /* Ps, Po */
-  ucp_S, ucp_S, ucp_S, ucp_S,         /* Sc, Sk, Sm, So */
-  ucp_Z, ucp_Z, ucp_Z                 /* Zl, Zp, Zs */
-};
-
-
-
-/*************************************************
-*         Search table and return type           *
-*************************************************/
-
-/* Three values are returned: the category is ucp_C, ucp_L, etc. The detailed
-character type is ucp_Lu, ucp_Nd, etc. The script is ucp_Latin, etc.
-
-Arguments:
-  c           the character value
-  type_ptr    the detailed character type is returned here
-  script_ptr  the script is returned here
-
-Returns:      the character type category
-*/
-
-int
-_pcre_ucp_findprop(const unsigned int c, int *type_ptr, int *script_ptr)
-{
-int bot = 0;
-int top = sizeof(ucp_table)/sizeof(cnode);
-int mid;
-
-/* The table is searched using a binary chop. You might think that using
-intermediate variables to hold some of the common expressions would speed
-things up, but tests with gcc 3.4.4 on Linux showed that, on the contrary, it
-makes things a lot slower. */
-
-for (;;)
-  {
-  if (top <= bot)
-    {
-    *type_ptr = ucp_Cn;
-    *script_ptr = ucp_Common;
-    return ucp_C;
-    }
-  mid = (bot + top) >> 1;
-  if (c == (ucp_table[mid].f0 & f0_charmask)) break;
-  if (c < (ucp_table[mid].f0 & f0_charmask)) top = mid;
-  else
-    {
-    if ((ucp_table[mid].f0 & f0_rangeflag) != 0 &&
-        c <= (ucp_table[mid].f0 & f0_charmask) +
-             (ucp_table[mid].f1 & f1_rangemask)) break;
-    bot = mid + 1;
-    }
-  }
-
-/* Found an entry in the table. Set the script and detailed type values, and
-return the general type. */
-
-*script_ptr = (ucp_table[mid].f0 & f0_scriptmask) >> f0_scriptshift;
-*type_ptr = (ucp_table[mid].f1 & f1_typemask) >> f1_typeshift;
-
-return ucp_gentype[*type_ptr];
-}
-
-
-
-/*************************************************
-*       Search table and return other case       *
-*************************************************/
-
-/* If the given character is a letter, and there is another case for the
-letter, return the other case. Otherwise, return -1.
-
-Arguments:
-  c           the character value
-
-Returns:      the other case or NOTACHAR if none
-*/
-
-unsigned int
-_pcre_ucp_othercase(const unsigned int c)
-{
-int bot = 0;
-int top = sizeof(ucp_table)/sizeof(cnode);
-int mid, offset;
-
-/* The table is searched using a binary chop. You might think that using
-intermediate variables to hold some of the common expressions would speed
-things up, but tests with gcc 3.4.4 on Linux showed that, on the contrary, it
-makes things a lot slower. */
-
-for (;;)
-  {
-  if (top <= bot) return -1;
-  mid = (bot + top) >> 1;
-  if (c == (ucp_table[mid].f0 & f0_charmask)) break;
-  if (c < (ucp_table[mid].f0 & f0_charmask)) top = mid;
-  else
-    {
-    if ((ucp_table[mid].f0 & f0_rangeflag) != 0 &&
-        c <= (ucp_table[mid].f0 & f0_charmask) +
-             (ucp_table[mid].f1 & f1_rangemask)) break;
-    bot = mid + 1;
-    }
-  }
-
-/* Found an entry in the table. Return NOTACHAR for a range entry. Otherwise
-return the other case if there is one, else NOTACHAR. */
-
-if ((ucp_table[mid].f0 & f0_rangeflag) != 0) return NOTACHAR;
-
-offset = ucp_table[mid].f1 & f1_casemask;
-if ((offset & f1_caseneg) != 0) offset |= f1_caseneg;
-return (offset == 0)? NOTACHAR : c + offset;
-}
-
-
-/* End of pcre_ucp_searchfuncs.c */

src/plugins/PCREPlugin/pcre_valid_utf8.c

@@ -1,3 +1,4 @@
+#define HAVE_CONFIG_H
 /*************************************************
 *      Perl-Compatible Regular Expressions       *
 *************************************************/
@@ -6,7 +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) 1997-2013 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -54,109 +55,248 @@ strings. */
 *************************************************/
 
 /* This function is called (optionally) at the start of compile or match, to
-validate that a supposed UTF-8 string is actually valid. The early check means
+check that a supposed UTF-8 string is actually valid. The early check means
 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
+can be turned off for maximum performance, but the consequences of supplying an
-an invalid string are then undefined.
+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.
+subrange 0xd000 to 0xdfff is excluded. However, the format of 5-byte and 6-byte
+characters is still checked.
+
+From release 8.13 more information about the details of the error are passed
+back in the returned value:
+
+PCRE_UTF8_ERR0   No error
+PCRE_UTF8_ERR1   Missing 1 byte at the end of the string
+PCRE_UTF8_ERR2   Missing 2 bytes at the end of the string
+PCRE_UTF8_ERR3   Missing 3 bytes at the end of the string
+PCRE_UTF8_ERR4   Missing 4 bytes at the end of the string
+PCRE_UTF8_ERR5   Missing 5 bytes at the end of the string
+PCRE_UTF8_ERR6   2nd-byte's two top bits are not 0x80
+PCRE_UTF8_ERR7   3rd-byte's two top bits are not 0x80
+PCRE_UTF8_ERR8   4th-byte's two top bits are not 0x80
+PCRE_UTF8_ERR9   5th-byte's two top bits are not 0x80
+PCRE_UTF8_ERR10  6th-byte's two top bits are not 0x80
+PCRE_UTF8_ERR11  5-byte character is not permitted by RFC 3629
+PCRE_UTF8_ERR12  6-byte character is not permitted by RFC 3629
+PCRE_UTF8_ERR13  4-byte character with value > 0x10ffff is not permitted
+PCRE_UTF8_ERR14  3-byte character with value 0xd000-0xdfff is not permitted
+PCRE_UTF8_ERR15  Overlong 2-byte sequence
+PCRE_UTF8_ERR16  Overlong 3-byte sequence
+PCRE_UTF8_ERR17  Overlong 4-byte sequence
+PCRE_UTF8_ERR18  Overlong 5-byte sequence (won't ever occur)
+PCRE_UTF8_ERR19  Overlong 6-byte sequence (won't ever occur)
+PCRE_UTF8_ERR20  Isolated 0x80 byte (not within UTF-8 character)
+PCRE_UTF8_ERR21  Byte with the illegal value 0xfe or 0xff
+PCRE_UTF8_ERR22  Unused (was non-character)
 
 Arguments:
   string       points to the string
   length       length of string, or -1 if the string is zero-terminated
+  errp         pointer to an error position offset variable
 
-Returns:       < 0    if the string is a valid UTF-8 string
+Returns:       = 0    if the string is a valid UTF-8 string
-               >= 0   otherwise; the value is the offset of the bad byte
+               > 0    otherwise, setting the offset of the bad character
 */
 
 int
-_pcre_valid_utf8(const uschar *string, int length)
+PRIV(valid_utf)(PCRE_PUCHAR string, int length, int *erroroffset)
 {
-#ifdef SUPPORT_UTF8
+#ifdef SUPPORT_UTF
-register const uschar *p;
+register PCRE_PUCHAR p;
 
 if (length < 0)
   {
   for (p = string; *p != 0; p++);
-  length = p - string;
+  length = (int)(p - string);
   }
 
 for (p = string; length-- > 0; p++)
   {
-  register int ab;
+  register pcre_uchar ab, c, d;
-  register int c = *p;
+
-  if (c < 128) continue;
+  c = *p;
-  if (c < 0xc0) return p - string;
+  if (c < 128) continue;                /* ASCII character */
-  ab = _pcre_utf8_table4[c & 0x3f];     /* Number of additional bytes */
+
-  if (length < ab || ab > 3) return p - string;
+  if (c < 0xc0)                         /* Isolated 10xx xxxx byte */
-  length -= ab;
+    {
+    *erroroffset = (int)(p - string);
+    return PCRE_UTF8_ERR20;
+    }
+
+  if (c >= 0xfe)                        /* Invalid 0xfe or 0xff bytes */
+    {
+    *erroroffset = (int)(p - string);
+    return PCRE_UTF8_ERR21;
+    }
+
+  ab = PRIV(utf8_table4)[c & 0x3f];     /* Number of additional bytes */
+  if (length < ab)
+    {
+    *erroroffset = (int)(p - string);          /* Missing bytes */
+    return ab - length;                 /* Codes ERR1 to ERR5 */
+    }
+  length -= ab;                         /* Length remaining */
 
   /* Check top bits in the second byte */
-  if ((*(++p) & 0xc0) != 0x80) return p - string;
 
-  /* Check for overlong sequences for each different length, and for the
+  if (((d = *(++p)) & 0xc0) != 0x80)
-  excluded range 0xd000 to 0xdfff.  */
+    {
+    *erroroffset = (int)(p - string) - 1;
+    return PCRE_UTF8_ERR6;
+    }
+
+  /* For each length, check that the remaining bytes start with the 0x80 bit
+  set and not the 0x40 bit. Then check for an overlong sequence, and for the
+  excluded range 0xd800 to 0xdfff. */
 
   switch (ab)
     {
-    /* Check for xx00 000x (overlong sequence) */
+    /* 2-byte character. No further bytes to check for 0x80. Check first byte
+    for for xx00 000x (overlong sequence). */
 
-    case 1:
+    case 1: if ((c & 0x3e) == 0)
-    if ((c & 0x3e) == 0) return p - string;
+      {
-    continue;   /* We know there aren't any more bytes to check */
+      *erroroffset = (int)(p - string) - 1;
+      return PCRE_UTF8_ERR15;
+      }
+    break;
 
-    /* Check for 1110 0000, xx0x xxxx (overlong sequence) or
+    /* 3-byte character. Check third byte for 0x80. Then check first 2 bytes
-                 1110 1101, 1010 xxxx (0xd000 - 0xdfff) */
+      for 1110 0000, xx0x xxxx (overlong sequence) or
+          1110 1101, 1010 xxxx (0xd800 - 0xdfff) */
 
     case 2:
-    if ((c == 0xe0 && (*p & 0x20) == 0) ||
+    if ((*(++p) & 0xc0) != 0x80)     /* Third byte */
-        (c == 0xed && *p >= 0xa0))
+      {
-      return p - string;
+      *erroroffset = (int)(p - string) - 2;
+      return PCRE_UTF8_ERR7;
+      }
+    if (c == 0xe0 && (d & 0x20) == 0)
+      {
+      *erroroffset = (int)(p - string) - 2;
+      return PCRE_UTF8_ERR16;
+      }
+    if (c == 0xed && d >= 0xa0)
+      {
+      *erroroffset = (int)(p - string) - 2;
+      return PCRE_UTF8_ERR14;
+      }
     break;
 
-    /* Check for 1111 0000, xx00 xxxx (overlong sequence) or
+    /* 4-byte character. Check 3rd and 4th bytes for 0x80. Then check first 2
-       greater than 0x0010ffff (f4 8f bf bf) */
+       bytes for for 1111 0000, xx00 xxxx (overlong sequence), then check for a
+       character greater than 0x0010ffff (f4 8f bf bf) */
 
     case 3:
-    if ((c == 0xf0 && (*p & 0x30) == 0) ||
+    if ((*(++p) & 0xc0) != 0x80)     /* Third byte */
-        (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;
-    break;
-
-    /* Check for leading 0xfe or 0xff, and then for 1111 1100, xx00 00xx */
-    case 5:
-    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 */
-  while (--ab > 0)
       {
-    if ((*(++p) & 0xc0) != 0x80) return p - string;
+      *erroroffset = (int)(p - string) - 2;
+      return PCRE_UTF8_ERR7;
+      }
+    if ((*(++p) & 0xc0) != 0x80)     /* Fourth byte */
+      {
+      *erroroffset = (int)(p - string) - 3;
+      return PCRE_UTF8_ERR8;
+      }
+    if (c == 0xf0 && (d & 0x30) == 0)
+      {
+      *erroroffset = (int)(p - string) - 3;
+      return PCRE_UTF8_ERR17;
+      }
+    if (c > 0xf4 || (c == 0xf4 && d > 0x8f))
+      {
+      *erroroffset = (int)(p - string) - 3;
+      return PCRE_UTF8_ERR13;
+      }
+    break;
+
+    /* 5-byte and 6-byte characters are not allowed by RFC 3629, and will be
+    rejected by the length test below. However, we do the appropriate tests
+    here so that overlong sequences get diagnosed, and also in case there is
+    ever an option for handling these larger code points. */
+
+    /* 5-byte character. Check 3rd, 4th, and 5th bytes for 0x80. Then check for
+    1111 1000, xx00 0xxx */
+
+    case 4:
+    if ((*(++p) & 0xc0) != 0x80)     /* Third byte */
+      {
+      *erroroffset = (int)(p - string) - 2;
+      return PCRE_UTF8_ERR7;
+      }
+    if ((*(++p) & 0xc0) != 0x80)     /* Fourth byte */
+      {
+      *erroroffset = (int)(p - string) - 3;
+      return PCRE_UTF8_ERR8;
+      }
+    if ((*(++p) & 0xc0) != 0x80)     /* Fifth byte */
+      {
+      *erroroffset = (int)(p - string) - 4;
+      return PCRE_UTF8_ERR9;
+      }
+    if (c == 0xf8 && (d & 0x38) == 0)
+      {
+      *erroroffset = (int)(p - string) - 4;
+      return PCRE_UTF8_ERR18;
+      }
+    break;
+
+    /* 6-byte character. Check 3rd-6th bytes for 0x80. Then check for
+    1111 1100, xx00 00xx. */
+
+    case 5:
+    if ((*(++p) & 0xc0) != 0x80)     /* Third byte */
+      {
+      *erroroffset = (int)(p - string) - 2;
+      return PCRE_UTF8_ERR7;
+      }
+    if ((*(++p) & 0xc0) != 0x80)     /* Fourth byte */
+      {
+      *erroroffset = (int)(p - string) - 3;
+      return PCRE_UTF8_ERR8;
+      }
+    if ((*(++p) & 0xc0) != 0x80)     /* Fifth byte */
+      {
+      *erroroffset = (int)(p - string) - 4;
+      return PCRE_UTF8_ERR9;
+      }
+    if ((*(++p) & 0xc0) != 0x80)     /* Sixth byte */
+      {
+      *erroroffset = (int)(p - string) - 5;
+      return PCRE_UTF8_ERR10;
+      }
+    if (c == 0xfc && (d & 0x3c) == 0)
+      {
+      *erroroffset = (int)(p - string) - 5;
+      return PCRE_UTF8_ERR19;
+      }
+    break;
+    }
+
+  /* Character is valid under RFC 2279, but 4-byte and 5-byte characters are
+  excluded by RFC 3629. The pointer p is currently at the last byte of the
+  character. */
+
+  if (ab > 3)
+    {
+    *erroroffset = (int)(p - string) - ab;
+    return (ab == 4)? PCRE_UTF8_ERR11 : PCRE_UTF8_ERR12;
     }
   }
+
+#else  /* Not SUPPORT_UTF */
+(void)(string);  /* Keep picky compilers happy */
+(void)(length);
+(void)(erroroffset);
 #endif
 
-return -1;
+return PCRE_UTF8_ERR0;   /* This indicates success */
 }
 
 /* End of pcre_valid_utf8.c */

src/plugins/PCREPlugin/pcre_version.c

@@ -1,3 +1,4 @@
+#define HAVE_CONFIG_H
 /*************************************************
 *      Perl-Compatible Regular Expressions       *
 *************************************************/
@@ -6,7 +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) 1997-2012 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -79,8 +80,16 @@ I could find no way of detecting that a macro is defined as an empty string at
 pre-processor time. This hack uses a standard trick for avoiding calling
 the STRING macro with an empty argument when doing the test. */
 
-PCRE_EXP_DEFN const char *
+#if defined COMPILE_PCRE8
+PCRE_EXP_DEFN const char * PCRE_CALL_CONVENTION
 pcre_version(void)
+#elif defined COMPILE_PCRE16
+PCRE_EXP_DEFN const char * PCRE_CALL_CONVENTION
+pcre16_version(void)
+#elif defined COMPILE_PCRE32
+PCRE_EXP_DEFN const char * PCRE_CALL_CONVENTION
+pcre32_version(void)
+#endif
 {
 return (XSTRING(Z PCRE_PRERELEASE)[1] == 0)?
   XSTRING(PCRE_MAJOR.PCRE_MINOR PCRE_DATE) :

src/plugins/PCREPlugin/pcre_xclass.c

@@ -1,3 +1,4 @@
+#define HAVE_CONFIG_H
 /*************************************************
 *      Perl-Compatible Regular Expressions       *
 *************************************************/
@@ -6,7 +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) 1997-2013 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -39,8 +40,7 @@ POSSIBILITY OF SUCH DAMAGE.
 
 
 /* This module contains an internal function that is used to match an extended
-class (one that contains characters whose values are > 255). It is used by both
+class. It is used by both pcre_exec() and pcre_def_exec(). */
-pcre_exec() and pcre_def_exec(). */
 
 
 #ifdef HAVE_CONFIG_H
@@ -55,7 +55,7 @@ pcre_exec() and pcre_def_exec(). */
 *************************************************/
 
 /* This function is called to match a character against an extended class that
-might contain values > 255.
+might contain values > 255 and/or Unicode properties.
 
 Arguments:
   c           the character
@@ -65,18 +65,30 @@ Returns:      TRUE if character matches, else FALSE
 */
 
 BOOL
-_pcre_xclass(int c, const uschar *data)
+PRIV(xclass)(pcre_uint32 c, const pcre_uchar *data, BOOL utf)
 {
-int t;
+pcre_uchar t;
 BOOL negated = (*data & XCL_NOT) != 0;
 
+(void)utf;
+#ifdef COMPILE_PCRE8
+/* In 8 bit mode, this must always be TRUE. Help the compiler to know that. */
+utf = TRUE;
+#endif
+
 /* Character values < 256 are matched against a bitmap, if one is present. If
 not, we still carry on, because there may be ranges that start below 256 in the
 additional data. */
 
 if (c < 256)
   {
-  if ((*data & XCL_MAP) != 0 && (data[1 + c/8] & (1 << (c&7))) != 0)
+  if ((*data & XCL_HASPROP) == 0)
+    {
+    if ((*data & XCL_MAP) == 0) return negated;
+    return (((pcre_uint8 *)(data + 1))[c/8] & (1 << (c&7))) != 0;
+    }
+  if ((*data & XCL_MAP) != 0 &&
+    (((pcre_uint8 *)(data + 1))[c/8] & (1 << (c&7))) != 0)
     return !negated; /* char found */
   }
 
@@ -84,50 +96,159 @@ if (c < 256)
 properties or large chars or ranges that end with a large char. We won't ever
 encounter XCL_PROP or XCL_NOTPROP when UCP support is not compiled. */
 
-if ((*data++ & XCL_MAP) != 0) data += 32;
+if ((*data++ & XCL_MAP) != 0) data += 32 / sizeof(pcre_uchar);
 
 while ((t = *data++) != XCL_END)
   {
-  int x, y;
+  pcre_uint32 x, y;
   if (t == XCL_SINGLE)
     {
-    GETCHARINC(x, data);
+#ifdef SUPPORT_UTF
+    if (utf)
+      {
+      GETCHARINC(x, data); /* macro generates multiple statements */
+      }
+    else
+#endif
+      x = *data++;
     if (c == x) return !negated;
     }
   else if (t == XCL_RANGE)
     {
-    GETCHARINC(x, data);
+#ifdef SUPPORT_UTF
-    GETCHARINC(y, data);
+    if (utf)
+      {
+      GETCHARINC(x, data); /* macro generates multiple statements */
+      GETCHARINC(y, data); /* macro generates multiple statements */
+      }
+    else
+#endif
+      {
+      x = *data++;
+      y = *data++;
+      }
     if (c >= x && c <= y) return !negated;
     }
 
 #ifdef SUPPORT_UCP
   else  /* XCL_PROP & XCL_NOTPROP */
     {
-    int chartype, script;
+    const ucd_record *prop = GET_UCD(c);
-    int category = _pcre_ucp_findprop(c, &chartype, &script);
+    BOOL isprop = t == XCL_PROP;
 
     switch(*data)
       {
       case PT_ANY:
-      if (t == XCL_PROP) return !negated;
+      if (isprop) return !negated;
       break;
 
       case PT_LAMP:
-      if ((chartype == ucp_Lu || chartype == ucp_Ll || chartype == ucp_Lt) ==
+      if ((prop->chartype == ucp_Lu || prop->chartype == ucp_Ll ||
-          (t == XCL_PROP)) return !negated;
+           prop->chartype == ucp_Lt) == isprop) return !negated;
       break;
 
       case PT_GC:
-      if ((data[1] == category) == (t == XCL_PROP)) return !negated;
+      if ((data[1] == PRIV(ucp_gentype)[prop->chartype]) == isprop)
+        return !negated;
       break;
 
       case PT_PC:
-      if ((data[1] == chartype) == (t == XCL_PROP)) return !negated;
+      if ((data[1] == prop->chartype) == isprop) return !negated;
       break;
 
       case PT_SC:
-      if ((data[1] == script) == (t == XCL_PROP)) return !negated;
+      if ((data[1] == prop->script) == isprop) return !negated;
+      break;
+
+      case PT_ALNUM:
+      if ((PRIV(ucp_gentype)[prop->chartype] == ucp_L ||
+           PRIV(ucp_gentype)[prop->chartype] == ucp_N) == isprop)
+        return !negated;
+      break;
+
+      /* Perl space used to exclude VT, but from Perl 5.18 it is included,
+      which means that Perl space and POSIX space are now identical. PCRE
+      was changed at release 8.34. */
+
+      case PT_SPACE:    /* Perl space */
+      case PT_PXSPACE:  /* POSIX space */
+      switch(c)
+        {
+        HSPACE_CASES:
+        VSPACE_CASES:
+        if (isprop) return !negated;
+        break;
+
+        default:
+        if ((PRIV(ucp_gentype)[prop->chartype] == ucp_Z) == isprop)
+          return !negated;
+        break;
+        }
+      break;
+
+      case PT_WORD:
+      if ((PRIV(ucp_gentype)[prop->chartype] == ucp_L ||
+           PRIV(ucp_gentype)[prop->chartype] == ucp_N || c == CHAR_UNDERSCORE)
+             == isprop)
+        return !negated;
+      break;
+
+      case PT_UCNC:
+      if (c < 0xa0)
+        {
+        if ((c == CHAR_DOLLAR_SIGN || c == CHAR_COMMERCIAL_AT ||
+             c == CHAR_GRAVE_ACCENT) == isprop)
+          return !negated;
+        }
+      else
+        {
+        if ((c < 0xd800 || c > 0xdfff) == isprop)
+          return !negated;
+        }
+      break;
+
+      /* The following three properties can occur only in an XCLASS, as there
+      is no \p or \P coding for them. */
+
+      /* Graphic character. Implement this as not Z (space or separator) and
+      not C (other), except for Cf (format) with a few exceptions. This seems
+      to be what Perl does. The exceptional characters are:
+
+      U+061C           Arabic Letter Mark
+      U+180E           Mongolian Vowel Separator
+      U+2066 - U+2069  Various "isolate"s
+      */
+
+      case PT_PXGRAPH:
+      if ((PRIV(ucp_gentype)[prop->chartype] != ucp_Z &&
+            (PRIV(ucp_gentype)[prop->chartype] != ucp_C ||
+              (prop->chartype == ucp_Cf &&
+                c != 0x061c && c != 0x180e && (c < 0x2066 || c > 0x2069))
+         )) == isprop)
+        return !negated;
+      break;
+
+      /* Printable character: same as graphic, with the addition of Zs, i.e.
+      not Zl and not Zp, and U+180E. */
+
+      case PT_PXPRINT:
+      if ((prop->chartype != ucp_Zl &&
+           prop->chartype != ucp_Zp &&
+            (PRIV(ucp_gentype)[prop->chartype] != ucp_C ||
+              (prop->chartype == ucp_Cf &&
+                c != 0x061c && (c < 0x2066 || c > 0x2069))
+         )) == isprop)
+        return !negated;
+      break;
+
+      /* Punctuation: all Unicode punctuation, plus ASCII characters that
+      Unicode treats as symbols rather than punctuation, for Perl
+      compatibility (these are $+<=>^`|~). */
+
+      case PT_PXPUNCT:
+      if ((PRIV(ucp_gentype)[prop->chartype] == ucp_P ||
+            (c < 128 && PRIV(ucp_gentype)[prop->chartype] == ucp_S)) == isprop)
+        return !negated;
       break;
 
       /* This should never occur, but compilers may mutter if there is no

src/plugins/PCREPlugin/pcreposix.c

@@ -1,337 +0,0 @@
-/*************************************************
-*      Perl-Compatible Regular Expressions       *
-*************************************************/
-
-/* 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
-
------------------------------------------------------------------------------
-Redistribution and use in source and binary forms, with or without
-modification, are permitted provided that the following conditions are met:
-
-    * Redistributions of source code must retain the above copyright notice,
-      this list of conditions and the following disclaimer.
-
-    * Redistributions in binary form must reproduce the above copyright
-      notice, this list of conditions and the following disclaimer in the
-      documentation and/or other materials provided with the distribution.
-
-    * Neither the name of the University of Cambridge nor the names of its
-      contributors may be used to endorse or promote products derived from
-      this software without specific prior written permission.
-
-THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
-AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
-IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
-ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
-LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
-CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
-SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
-INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
-CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
-ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
-POSSIBILITY OF SUCH DAMAGE.
------------------------------------------------------------------------------
-*/
-
-
-/* This module is a wrapper that provides a POSIX API to the underlying PCRE
-functions. */
-
-
-#ifdef HAVE_CONFIG_H
-#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"
-
-
-/* Table to translate PCRE compile time error codes into POSIX error codes. */
-
-static const int eint[] = {
-  0,           /* no error */
-  REG_EESCAPE, /* \ at end of pattern */
-  REG_EESCAPE, /* \c at end of pattern */
-  REG_EESCAPE, /* unrecognized character follows \ */
-  REG_BADBR,   /* numbers out of order in {} quantifier */
-  REG_BADBR,   /* number too big in {} quantifier */
-  REG_EBRACK,  /* missing terminating ] for character class */
-  REG_ECTYPE,  /* invalid escape sequence in character class */
-  REG_ERANGE,  /* range out of order in character class */
-  REG_BADRPT,  /* nothing to repeat */
-  REG_BADRPT,  /* operand of unlimited repeat could match the empty string */
-  REG_ASSERT,  /* internal error: unexpected repeat */
-  REG_BADPAT,  /* unrecognized character after (? */
-  REG_BADPAT,  /* POSIX named classes are supported only within a class */
-  REG_EPAREN,  /* missing ) */
-  REG_ESUBREG, /* reference to non-existent subpattern */
-  REG_INVARG,  /* erroffset passed as NULL */
-  REG_INVARG,  /* unknown option bit(s) set */
-  REG_EPAREN,  /* missing ) after comment */
-  REG_ESIZE,   /* parentheses nested too deeply */
-  REG_ESIZE,   /* regular expression too large */
-  REG_ESPACE,  /* failed to get memory */
-  REG_EPAREN,  /* unmatched brackets */
-  REG_ASSERT,  /* internal error: code overflow */
-  REG_BADPAT,  /* unrecognized character after (?< */
-  REG_BADPAT,  /* lookbehind assertion is not fixed length */
-  REG_BADPAT,  /* malformed number or name after (?( */
-  REG_BADPAT,  /* conditional group contains more than two branches */
-  REG_BADPAT,  /* assertion expected after (?( */
-  REG_BADPAT,  /* (?R or (?[+-]digits must be followed by ) */
-  REG_ECTYPE,  /* unknown POSIX class name */
-  REG_BADPAT,  /* POSIX collating elements are not supported */
-  REG_INVARG,  /* this version of PCRE is not compiled with PCRE_UTF8 support */
-  REG_BADPAT,  /* spare error */
-  REG_BADPAT,  /* character value in \x{...} sequence is too large */
-  REG_BADPAT,  /* invalid condition (?(0) */
-  REG_BADPAT,  /* \C not allowed in lookbehind assertion */
-  REG_EESCAPE, /* PCRE does not support \L, \l, \N, \U, or \u */
-  REG_BADPAT,  /* number after (?C is > 255 */
-  REG_BADPAT,  /* closing ) for (?C expected */
-  REG_BADPAT,  /* recursive call could loop indefinitely */
-  REG_BADPAT,  /* unrecognized character after (?P */
-  REG_BADPAT,  /* syntax error in subpattern name (missing terminator) */
-  REG_BADPAT,  /* two named subpatterns have the same name */
-  REG_BADPAT,  /* invalid UTF-8 string */
-  REG_BADPAT,  /* support for \P, \p, and \X has not been compiled */
-  REG_BADPAT,  /* malformed \P or \p sequence */
-  REG_BADPAT,  /* unknown property name after \P or \p */
-  REG_BADPAT,  /* subpattern name is too long (maximum 32 characters) */
-  REG_BADPAT,  /* too many named subpatterns (maximum 10,000) */
-  REG_BADPAT,  /* repeated subpattern is too long */
-  REG_BADPAT,  /* octal value is greater than \377 (not in UTF-8 mode) */
-  REG_BADPAT,  /* internal error: overran compiling workspace */
-  REG_BADPAT,  /* internal error: previously-checked referenced subpattern not found */
-  REG_BADPAT,  /* DEFINE group contains more than one branch */
-  REG_BADPAT,  /* repeating a DEFINE group is not allowed */
-  REG_INVARG,  /* inconsistent NEWLINE options */
-  REG_BADPAT,  /* \g is not followed followed by an (optionally braced) non-zero number */
-  REG_BADPAT,  /* (?+ or (?- must be followed by a non-zero number */
-  REG_BADPAT   /* number is too big */
-};
-
-/* Table of texts corresponding to POSIX error codes */
-
-static const char *const pstring[] = {
-  "",                                /* Dummy for value 0 */
-  "internal error",                  /* REG_ASSERT */
-  "invalid repeat counts in {}",     /* BADBR      */
-  "pattern error",                   /* BADPAT     */
-  "? * + invalid",                   /* BADRPT     */
-  "unbalanced {}",                   /* EBRACE     */
-  "unbalanced []",                   /* EBRACK     */
-  "collation error - not relevant",  /* ECOLLATE   */
-  "bad class",                       /* ECTYPE     */
-  "bad escape sequence",             /* EESCAPE    */
-  "empty expression",                /* EMPTY      */
-  "unbalanced ()",                   /* EPAREN     */
-  "bad range inside []",             /* ERANGE     */
-  "expression too big",              /* ESIZE      */
-  "failed to get memory",            /* ESPACE     */
-  "bad back reference",              /* ESUBREG    */
-  "bad argument",                    /* INVARG     */
-  "match failed"                     /* NOMATCH    */
-};
-
-
-
-
-/*************************************************
-*          Translate error code to string        *
-*************************************************/
-
-PCREPOSIX_EXP_DEFN size_t
-regerror(int errcode, const regex_t *preg, char *errbuf, size_t errbuf_size)
-{
-const char *message, *addmessage;
-size_t length, addlength;
-
-message = (errcode >= (int)(sizeof(pstring)/sizeof(char *)))?
-  "unknown error code" : pstring[errcode];
-length = strlen(message) + 1;
-
-addmessage = " at offset ";
-addlength = (preg != NULL && (int)preg->re_erroffset != -1)?
-  strlen(addmessage) + 6 : 0;
-
-if (errbuf_size > 0)
-  {
-  if (addlength > 0 && errbuf_size >= length + addlength)
-    sprintf(errbuf, "%s%s%-6d", message, addmessage, (int)preg->re_erroffset);
-  else
-    {
-    strncpy(errbuf, message, errbuf_size - 1);
-    errbuf[errbuf_size-1] = 0;
-    }
-  }
-
-return length + addlength;
-}
-
-
-
-
-/*************************************************
-*           Free store held by a regex           *
-*************************************************/
-
-PCREPOSIX_EXP_DEFN void
-regfree(regex_t *preg)
-{
-(pcre_free)(preg->re_pcre);
-}
-
-
-
-
-/*************************************************
-*            Compile a regular expression        *
-*************************************************/
-
-/*
-Arguments:
-  preg        points to a structure for recording the compiled expression
-  pattern     the pattern to compile
-  cflags      compilation flags
-
-Returns:      0 on success
-              various non-zero codes on failure
-*/
-
-PCREPOSIX_EXP_DEFN int
-regcomp(regex_t *preg, const char *pattern, int cflags)
-{
-const char *errorptr;
-int erroffset;
-int errorcode;
-int options = 0;
-
-if ((cflags & REG_ICASE) != 0)   options |= PCRE_CASELESS;
-if ((cflags & REG_NEWLINE) != 0) options |= PCRE_MULTILINE;
-if ((cflags & REG_DOTALL) != 0)  options |= PCRE_DOTALL;
-if ((cflags & REG_NOSUB) != 0)   options |= PCRE_NO_AUTO_CAPTURE;
-if ((cflags & REG_UTF8) != 0)    options |= PCRE_UTF8;
-
-preg->re_pcre = pcre_compile2(pattern, options, &errorcode, &errorptr,
-  &erroffset, NULL);
-preg->re_erroffset = erroffset;
-
-if (preg->re_pcre == NULL) return eint[errorcode];
-
-preg->re_nsub = pcre_info((const pcre *)preg->re_pcre, NULL, NULL);
-return 0;
-}
-
-
-
-
-/*************************************************
-*              Match a regular expression        *
-*************************************************/
-
-/* Unfortunately, PCRE requires 3 ints of working space for each captured
-substring, so we have to get and release working store instead of just using
-the POSIX structures as was done in earlier releases when PCRE needed only 2
-ints. However, if the number of possible capturing brackets is small, use a
-block of store on the stack, to reduce the use of malloc/free. The threshold is
-in a macro that can be changed at configure time.
-
-If REG_NOSUB was specified at compile time, the PCRE_NO_AUTO_CAPTURE flag will
-be set. When this is the case, the nmatch and pmatch arguments are ignored, and
-the only result is yes/no/error. */
-
-PCREPOSIX_EXP_DEFN int
-regexec(const regex_t *preg, const char *string, size_t nmatch,
-  regmatch_t pmatch[], int eflags)
-{
-int rc;
-int options = 0;
-int *ovector = NULL;
-int small_ovector[POSIX_MALLOC_THRESHOLD * 3];
-BOOL allocated_ovector = FALSE;
-BOOL nosub =
-  (((const pcre *)preg->re_pcre)->options & PCRE_NO_AUTO_CAPTURE) != 0;
-
-if ((eflags & REG_NOTBOL) != 0) options |= PCRE_NOTBOL;
-if ((eflags & REG_NOTEOL) != 0) options |= PCRE_NOTEOL;
-
-((regex_t *)preg)->re_erroffset = (size_t)(-1);  /* Only has meaning after compile */
-
-/* When no string data is being returned, ensure that nmatch is zero.
-Otherwise, ensure the vector for holding the return data is large enough. */
-
-if (nosub) nmatch = 0;
-
-else if (nmatch > 0)
-  {
-  if (nmatch <= POSIX_MALLOC_THRESHOLD)
-    {
-    ovector = &(small_ovector[0]);
-    }
-  else
-    {
-    if (nmatch > INT_MAX/(sizeof(int) * 3)) return REG_ESPACE;
-    ovector = (int *)malloc(sizeof(int) * nmatch * 3);
-    if (ovector == NULL) return REG_ESPACE;
-    allocated_ovector = TRUE;
-    }
-  }
-
-rc = pcre_exec((const pcre *)preg->re_pcre, NULL, string, (int)strlen(string),
-  0, options, ovector, nmatch * 3);
-
-if (rc == 0) rc = nmatch;    /* All captured slots were filled in */
-
-if (rc >= 0)
-  {
-  size_t i;
-  if (!nosub)
-    {
-    for (i = 0; i < (size_t)rc; i++)
-      {
-      pmatch[i].rm_so = ovector[i*2];
-      pmatch[i].rm_eo = ovector[i*2+1];
-      }
-    if (allocated_ovector) free(ovector);
-    for (; i < nmatch; i++) pmatch[i].rm_so = pmatch[i].rm_eo = -1;
-    }
-  return 0;
-  }
-
-else
-  {
-  if (allocated_ovector) free(ovector);
-  switch(rc)
-    {
-    case PCRE_ERROR_NOMATCH: return REG_NOMATCH;
-    case PCRE_ERROR_NULL: return REG_INVARG;
-    case PCRE_ERROR_BADOPTION: return REG_INVARG;
-    case PCRE_ERROR_BADMAGIC: return REG_INVARG;
-    case PCRE_ERROR_UNKNOWN_NODE: return REG_ASSERT;
-    case PCRE_ERROR_NOMEMORY: return REG_ESPACE;
-    case PCRE_ERROR_MATCHLIMIT: return REG_ESPACE;
-    case PCRE_ERROR_BADUTF8: return REG_INVARG;
-    case PCRE_ERROR_BADUTF8_OFFSET: return REG_INVARG;
-    default: return REG_ASSERT;
-    }
-  }
-}
-
-/* End of pcreposix.c */

src/plugins/PCREPlugin/pcreposix.h

@@ -1,142 +0,0 @@
-/*************************************************
-*       Perl-Compatible Regular Expressions      *
-*************************************************/
-
-#ifndef _PCREPOSIX_H
-#define _PCREPOSIX_H
-
-/* This is the header for the POSIX wrapper interface to the PCRE Perl-
-Compatible Regular Expression library. It defines the things POSIX says should
-be there. I hope.
-
-            Copyright (c) 1997-2007 University of Cambridge
-
------------------------------------------------------------------------------
-Redistribution and use in source and binary forms, with or without
-modification, are permitted provided that the following conditions are met:
-
-    * Redistributions of source code must retain the above copyright notice,
-      this list of conditions and the following disclaimer.
-
-    * Redistributions in binary form must reproduce the above copyright
-      notice, this list of conditions and the following disclaimer in the
-      documentation and/or other materials provided with the distribution.
-
-    * Neither the name of the University of Cambridge nor the names of its
-      contributors may be used to endorse or promote products derived from
-      this software without specific prior written permission.
-
-THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
-AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
-IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
-ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
-LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
-CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
-SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
-INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
-CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
-ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
-POSSIBILITY OF SUCH DAMAGE.
------------------------------------------------------------------------------
-*/
-
-/* Have to include stdlib.h in order to ensure that size_t is defined. */
-
-#include <stdlib.h>
-
-/* Allow for C++ users */
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-/* Options, mostly defined by POSIX, but with a couple of extras. */
-
-#define REG_ICASE     0x0001
-#define REG_NEWLINE   0x0002
-#define REG_NOTBOL    0x0004
-#define REG_NOTEOL    0x0008
-#define REG_DOTALL    0x0010   /* NOT defined by POSIX. */
-#define REG_NOSUB     0x0020
-#define REG_UTF8      0x0040   /* NOT defined by POSIX. */
-
-/* This is not used by PCRE, but by defining it we make it easier
-to slot PCRE into existing programs that make POSIX calls. */
-
-#define REG_EXTENDED  0
-
-/* Error values. Not all these are relevant or used by the wrapper. */
-
-enum {
-  REG_ASSERT = 1,  /* internal error ? */
-  REG_BADBR,       /* invalid repeat counts in {} */
-  REG_BADPAT,      /* pattern error */
-  REG_BADRPT,      /* ? * + invalid */
-  REG_EBRACE,      /* unbalanced {} */
-  REG_EBRACK,      /* unbalanced [] */
-  REG_ECOLLATE,    /* collation error - not relevant */
-  REG_ECTYPE,      /* bad class */
-  REG_EESCAPE,     /* bad escape sequence */
-  REG_EMPTY,       /* empty expression */
-  REG_EPAREN,      /* unbalanced () */
-  REG_ERANGE,      /* bad range inside [] */
-  REG_ESIZE,       /* expression too big */
-  REG_ESPACE,      /* failed to get memory */
-  REG_ESUBREG,     /* bad back reference */
-  REG_INVARG,      /* bad argument */
-  REG_NOMATCH      /* match failed */
-};
-
-
-/* The structure representing a compiled regular expression. */
-
-typedef struct {
-  void *re_pcre;
-  size_t re_nsub;
-  size_t re_erroffset;
-} regex_t;
-
-/* The structure in which a captured offset is returned. */
-
-typedef int regoff_t;
-
-typedef struct {
-  regoff_t rm_so;
-  regoff_t rm_eo;
-} regmatch_t;
-
-/* 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, and are set in pcreposix.c before including this
-file. */
-
-#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. */
-
-#ifndef PCREPOSIX_EXP_DECL
-#  ifdef __cplusplus
-#    define PCREPOSIX_EXP_DECL  extern "C"
-#    define PCREPOSIX_EXP_DEFN  extern "C"
-#  else
-#    define PCREPOSIX_EXP_DECL  extern
-#    define PCREPOSIX_EXP_DEFN  extern
-#  endif
-#endif
-
-/* The functions */
-
-PCREPOSIX_EXP_DECL int regcomp(regex_t *, const char *, int);
-PCREPOSIX_EXP_DECL int regexec(const regex_t *, const char *, size_t,
-                     regmatch_t *, int);
-PCREPOSIX_EXP_DECL size_t regerror(int, const regex_t *, char *, size_t);
-PCREPOSIX_EXP_DECL void regfree(regex_t *);
-
-#ifdef __cplusplus
-}   /* extern "C" */
-#endif
-
-#endif /* End of pcreposix.h */

src/plugins/PCREPlugin/ucp.h

@@ -6,9 +6,15 @@
 #define _UCP_H
 
 /* This file contains definitions of the property values that are returned by
-the function _pcre_ucp_findprop(). New values that are added for new releases
+the UCD access macros. New values that are added for new releases of Unicode
-of Unicode should always be at the end of each enum, for backwards
+should always be at the end of each enum, for backwards compatibility.
-compatibility. */
+
+IMPORTANT: Note also that the specific numeric values of the enums have to be
+the same as the values that are generated by the maint/MultiStage2.py script,
+where the equivalent property descriptive names are listed in vectors.
+
+ALSO: The specific values of the first two enums are assumed for the table
+called catposstab in pcre_compile.c. */
 
 /* These are the general character categories. */
 
@@ -22,7 +28,7 @@ enum {
   ucp_Z      /* Separator */
 };
 
-/* These are the particular character types. */
+/* These are the particular character categories. */
 
 enum {
   ucp_Cc,    /* Control */
@@ -57,6 +63,26 @@ enum {
   ucp_Zs     /* Space separator */
 };
 
+/* These are grapheme break properties. Note that the code for processing them
+assumes that the values are less than 16. If more values are added that take
+the number to 16 or more, the code will have to be rewritten. */
+
+enum {
+  ucp_gbCR,                /*  0 */
+  ucp_gbLF,                /*  1 */
+  ucp_gbControl,           /*  2 */
+  ucp_gbExtend,            /*  3 */
+  ucp_gbPrepend,           /*  4 */
+  ucp_gbSpacingMark,       /*  5 */
+  ucp_gbL,                 /*  6 Hangul syllable type L */
+  ucp_gbV,                 /*  7 Hangul syllable type V */
+  ucp_gbT,                 /*  8 Hangul syllable type T */
+  ucp_gbLV,                /*  9 Hangul syllable type LV */
+  ucp_gbLVT,               /* 10 Hangul syllable type LVT */
+  ucp_gbRegionalIndicator, /* 11 */
+  ucp_gbOther              /* 12 */
+};
+
 /* These are the script identifications. */
 
 enum {
@@ -121,11 +147,76 @@ enum {
   ucp_Tifinagh,
   ucp_Ugaritic,
   ucp_Yi,
-  ucp_Balinese,      /* New for Unicode 5.0.0 */
+  /* New for Unicode 5.0: */
-  ucp_Cuneiform,     /* New for Unicode 5.0.0 */
+  ucp_Balinese,
-  ucp_Nko,           /* New for Unicode 5.0.0 */
+  ucp_Cuneiform,
-  ucp_Phags_Pa,      /* New for Unicode 5.0.0 */
+  ucp_Nko,
-  ucp_Phoenician     /* New for Unicode 5.0.0 */
+  ucp_Phags_Pa,
+  ucp_Phoenician,
+  /* New for Unicode 5.1: */
+  ucp_Carian,
+  ucp_Cham,
+  ucp_Kayah_Li,
+  ucp_Lepcha,
+  ucp_Lycian,
+  ucp_Lydian,
+  ucp_Ol_Chiki,
+  ucp_Rejang,
+  ucp_Saurashtra,
+  ucp_Sundanese,
+  ucp_Vai,
+  /* New for Unicode 5.2: */
+  ucp_Avestan,
+  ucp_Bamum,
+  ucp_Egyptian_Hieroglyphs,
+  ucp_Imperial_Aramaic,
+  ucp_Inscriptional_Pahlavi,
+  ucp_Inscriptional_Parthian,
+  ucp_Javanese,
+  ucp_Kaithi,
+  ucp_Lisu,
+  ucp_Meetei_Mayek,
+  ucp_Old_South_Arabian,
+  ucp_Old_Turkic,
+  ucp_Samaritan,
+  ucp_Tai_Tham,
+  ucp_Tai_Viet,
+  /* New for Unicode 6.0.0: */
+  ucp_Batak,
+  ucp_Brahmi,
+  ucp_Mandaic,
+  /* New for Unicode 6.1.0: */
+  ucp_Chakma,
+  ucp_Meroitic_Cursive,
+  ucp_Meroitic_Hieroglyphs,
+  ucp_Miao,
+  ucp_Sharada,
+  ucp_Sora_Sompeng,
+  ucp_Takri,
+  /* New for Unicode 7.0.0: */
+  ucp_Bassa_Vah,
+  ucp_Caucasian_Albanian,
+  ucp_Duployan,
+  ucp_Elbasan,
+  ucp_Grantha,
+  ucp_Khojki,
+  ucp_Khudawadi,
+  ucp_Linear_A,
+  ucp_Mahajani,
+  ucp_Manichaean,
+  ucp_Mende_Kikakui,
+  ucp_Modi,
+  ucp_Mro,
+  ucp_Nabataean,
+  ucp_Old_North_Arabian,
+  ucp_Old_Permic,
+  ucp_Pahawh_Hmong,
+  ucp_Palmyrene,
+  ucp_Psalter_Pahlavi,
+  ucp_Pau_Cin_Hau,
+  ucp_Siddham,
+  ucp_Tirhuta,
+  ucp_Warang_Citi
 };
 
 #endif

src/plugins/PCREPlugin/ucpinternal.h

@@ -1,92 +0,0 @@
-/*************************************************
-*           Unicode Property Table handler       *
-*************************************************/
-
-#ifndef _UCPINTERNAL_H
-#define _UCPINTERNAL_H
-
-/* Internal header file defining the layout of the bits in each pair of 32-bit
-words that form a data item in the table. */
-
-typedef struct cnode {
-  pcre_uint32 f0;
-  pcre_uint32 f1;
-} cnode;
-
-/* Things for the f0 field */
-
-#define f0_scriptmask   0xff000000  /* Mask for script field */
-#define f0_scriptshift          24  /* Shift for script value */
-#define f0_rangeflag    0x00f00000  /* Flag for a range item */
-#define f0_charmask     0x001fffff  /* Mask for code point value */
-
-/* Things for the f1 field */
-
-#define f1_typemask     0xfc000000  /* Mask for char type field */
-#define f1_typeshift            26  /* Shift for the type field */
-#define f1_rangemask    0x0000ffff  /* Mask for a range offset */
-#define f1_casemask     0x0000ffff  /* Mask for a case offset */
-#define f1_caseneg      0xffff8000  /* Bits for negation */
-
-/* The data consists of a vector of structures of type cnode. The two unsigned
-32-bit integers are used as follows:
-
-(f0) (1) The most significant byte holds the script number. The numbers are
-         defined by the enum in ucp.h.
-
-     (2) The 0x00800000 bit is set if this entry defines a range of characters.
-         It is not set if this entry defines a single character
-
-     (3) The 0x00600000 bits are spare.
-
-     (4) The 0x001fffff bits contain the code point. No Unicode code point will
-         ever be greater than 0x0010ffff, so this should be OK for ever.
-
-(f1) (1) The 0xfc000000 bits contain the character type number. The numbers are
-         defined by an enum in ucp.h.
-
-     (2) The 0x03ff0000 bits are spare.
-
-     (3) The 0x0000ffff bits contain EITHER the unsigned offset to the top of
-         range if this entry defines a range, OR the *signed* offset to the
-         character's "other case" partner if this entry defines a single
-         character. There is no partner if the value is zero.
-
--------------------------------------------------------------------------------
-| script (8) |.|.|.| codepoint (21) || type (6) |.|.| spare (8) | offset (16) |
--------------------------------------------------------------------------------
-              | | |                              | |
-              | | |-> spare                      | |-> spare
-              | |                                |
-              | |-> spare                        |-> spare
-              |
-              |-> range flag
-
-The upper/lower casing information is set only for characters that come in
-pairs. The non-one-to-one mappings in the Unicode data are ignored.
-
-When searching the data, proceed as follows:
-
-(1) Set up for a binary chop search.
-
-(2) If the top is not greater than the bottom, the character is not in the
-    table. Its type must therefore be "Cn" ("Undefined").
-
-(3) Find the middle vector element.
-
-(4) Extract the code point and compare. If equal, we are done.
-
-(5) If the test character is smaller, set the top to the current point, and
-    goto (2).
-
-(6) If the current entry defines a range, compute the last character by adding
-    the offset, and see if the test character is within the range. If it is,
-    we are done.
-
-(7) Otherwise, set the bottom to one element past the current point and goto
-    (2).
-*/
-
-#endif /* _UCPINTERNAL_H */
-
-/* End of ucpinternal.h */

src/version.h

@@ -1,2 +1,2 @@
 #define VERSION "3proxy-0.9-devel"
-#define BUILDDATE "161220233959"
+#define BUILDDATE "161222213124"