This commit was manufactured by cvs2svn to create tag 'php_4_4_1'.

fix typo
export those functions and fix the build
2026-11-09 02:00:49 +00:00 · 2005-10-29 22:01:46 +00:00 · 2005-10-26 20:04:57 +00:00 · 2005-10-26 11:37:33 +00:00 · 2005-10-26 08:34:13 +00:00 · 2005-10-26 07:58:24 +00:00
301 changed files with 62535 additions and 15853 deletions
@@ -71,7 +71,7 @@ clean:

 distclean: clean
 	rm -f config.cache config.log config.status Makefile.objects Makefile.fragments libtool main/php_config.h stamp-h php4.spec sapi/apache/libphp4.module buildmk.stamp
-	egrep define'.*include/php' configure|sed 's/.*>//'|xargs rm -f
+	egrep define'.*include/php' $(top_srcdir)/configure|sed 's/.*>//'|xargs rm -f
 	find . -name Makefile | xargs rm -f

 .PHONY: all clean install distclean test
@@ -1,5 +1,155 @@
 PHP 4                                                                      NEWS
 |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
+31 Oct 2005, Version 4.4.1
+	
+- Added missing safe_mode checks for image* functions and cURL. (Ilia)
+- Added missing safe_mode/open_basedir checks for file uploads. (Ilia)
+- Fixed a memory corruption bug regarding included files. (Derick)
+- Fixed possible INI setting leak via virtual() in Apache 2 sapi. (Ilia)
+- Fixed possible crash and/or memory corruption in import_request_variables().
+  (Ilia)
+- Fixed potential GLOBALS overwrite via import_request_variables(). (Ilia)
+- Fixed possible GLOBALS variable override when register_globals are ON.
+  (Ilia, Stefan)
+- Fixed possible register_globals toggle via parse_str(). (Ilia, Stefan)
+- Added "new_link" parameter to mssql_connect(). Bug #34369. (Frank)
+- Fixed bug #34850 (--program-suffix and --program-prefix not included in 
+  man page names). (Jani)
+- Fixed bug #34790 (preg_match_all(), named capturing groups, variable
+  assignment/return => crash). (Dmitry)
+- Fixed bug #34742 (ftp wrapper failures caused from segmented command 
+  transfer). (Ilia)
+- Fixed bug #34704 (Infinite recursion due to corrupt JPEG). (Marcus)
+- Fixed bug #34645 (ctype corrupts memory when validating large numbers). (Ilia)
+- Fixed bug #34565 (mb_send_mail does not fetch mail.force_extra_parameters).
+  (Marco, Ilia)
+- Fixed bug #34557 (php -m exits with "error" 1). (Johannes)
+- Fixed bug #34456 (Possible crash inside pspell extension). (Ilia)
+- Fixed bug #34311 (unserialize() crashes with chars above 191 dec). (Nuno)
+- Fixed bug #34307 (on_modify handler not called to set the default value if
+  setting from php.ini was invalid). (Andrei)
+- Fixed bug #34302 (date('W') do not return leading zeros for week 1 to 9).
+  (Derick)
+- Fixed bug #34277 (array_filter() crashes with references and objects).
+  (Dmitry)
+- Fixed bug #34191 (ob_gzhandler does not enforce trailing \0). (Ilia)
+- Fixed bug #34156 (memory usage remains elevated after memory limit is 
+  reached). (Ilia)
+- Fixed bug #34148 (+,- and . not supported as parts of scheme). (Ilia)
+- Fixed bug #34137 (assigning array element by reference causes binary mess).
+  (Dmitry) 
+- Fixed bug #34068 (Numeric string as array key not cast to integer in 
+  wddx_deserialize()). (Ilia)
+- Fixed bug #34064 (arr[] as param to function is allowed only if function 
+  receives argument by reference). (Dmitry)
+- Fixed bug #33989 (extract($GLOBALS,EXTR_REFS) crashes PHP). (Dmitry)
+- Fixed bug #33987 (php script as ErrorDocument causes crash in Apache 2).
+  (Ilia)
+- Fixed bug #33940 (array_map() fails to pass by reference when called
+  recursively). (Dmitry)
+- Fixed bug #33690 (Crash setting some ini directives in httpd.conf). (Rasmus)
+- Fixed bug #33673 (Added detection for partially uploaded files). (Ilia)
+- Fixed bug #33648 (Using --with-regex=system causes compile failure). (Andrei)
+- Fixed bug #33558 (Warning with nested calls to functions returning by
+  reference). (Dmitry, Derick)
+- Fixed bug #33383 (crash when retrieving empty LOBs). (Tony)
+- Fixed bug #33156 (cygwin version of setitimer doesn't accept ITIMER_PROF).
+  (Nuno)
+- Fixed bug #32937 (open_basedir looses trailing / in the limiter). (Adam C.)
+- Fixed bug #32589 (possible crash inside imap_mail_compose() function). (Ilia)
+- Fixed bug #32179 (xmlrpc_encode() segfaults with recursive references). (Tony)
+- Fixed bug #32160 (copying a file into itself leads to data loss). (Ilia)
+- Fixed bug #31158 (array_splice on $GLOBALS crashes). (Dmitry)
+- Fixed bug #29983 (PHP does not explicitly set mime type & charset). (Ilia)
+- Fixed bug #29253 (array_diff with $GLOBALS argument fails). (Dmitry)
+- Fixed bug #21306 (ext/sesssion: catch bailouts of write handler during
+  RSHUTDOWN). (Jani, Xuefer at 21cn dot com)
+
+11 Jul 2005, Version 4.4.0
+- Added man pages for "phpize" and "php-config" scripts. (Jakub Vrana)
+- Added support for .cc files in extensions. (Brian)
+- Added the sorting flag SORT_LOCALE_STRING to the sort() functions which makes
+  them sort based on the current locale. (Derick)
+- Changed sha1_file() and md5_file() functions to use streams instead of 
+  low level IO. (Uwe)
+- Fixed memory corruptions when using references in a wrong way. (Marcus,
+  Dmitry, Derick)
+- Fixed memory corruption in pg_copy_from() in case the as_null parameter was
+  passed. (Derick)
+- Fixed memory corruption in stristr(). (Derick)
+- Fixed bug #32685, #29423 (Segfault when using assignment by reference within
+  function). (Dmitry, Derick)
+- Fixed bug #33242 (Mangled error message when stream fails). (Derick)
+- Fixed bug #33222 (segfault when CURL handle is closed in a callback). (Tony)
+- Fixed bug #33214 (odbc_next_result does not signal SQL errors with 
+  2-statement SQL batches). (rich at kastle dot com, Tony)
+- Fixed bug #33210 (relax jpeg recursive loop protection). (Ilia)
+- Fixed bug #33200 (preg_replace(): magic_quotes_sybase=On makes 'e' modifier
+  misbehave). (Jani)
+- Fixed bug #33150 (shtool: insecure temporary file creation). (Jani)
+- Fixed bug #33072 (Add a safemode/open_basedir check for runtime save_path 
+  change) (Rasmus)
+- Fixed bug #33070 (Improved performance of bzdecompress() by several orders
+  of magnitude). (Ilia)
+- Fixed bug #33057 (Don't send extraneous entity-headers on a 304 as per
+  RFC 2616 section 10.3.5) (Rasmus, Choitel)
+- Fixed bug #33019 (socket errors cause memory leaks in php_strerror()). 
+  (jwozniak23 at poczta dot onet dot pl, Tony).
+- Fixed bug #33017 ("make distclean" gives an error with VPATH build). (Jani)
+- Fixed bug #33013 ("next month" was handled wrong while parsing dates).
+  (Derick)
+- Fixed bug #32974 (pcntl calls malloc() from a signal handler). (Wez)
+- Fixed bug #32944 (Disabling session.use_cookies doesn't prevent reading 
+  session cookies). (Jani, Tony)
+- Fixed bug #32936 (http redirects URLs are not checked for control chars). (Ilia)
+- Fixed bug #32932 (Oracle LDAP: ldap_get_entries invalid pointer). (Jani)
+- Fixed bug #32904 (pg_get_notify() ignores result_type parameter). (Tony)
+- Fixed bug #32813 (parse_url() does not handle scheme-only urls properly). (Ilia)
+- Fixed bug #32810 (temporary files not using plain file wrapper). (Ilia)
+- Fixed bug #32802 (General cookie overrides more specific cookie). (Ilia)
+- Fixed bugs #32800, #32830 (ext/odbc: Problems with 64bit systems). (Jani)
+- Fixed bug #32773 (GMP functions break when second parameter is 0). (Stas)
+- Fixed bug #32742 (segmentation fault when the stream with a wrapper 
+  is not closed). (Tony, Dmitry)
+- Fixed bug #32730 (ext/crack.c fails to compile with cracklib-2.8.3). (Jani)
+- Fixed bug #32670 (foreach() does not issue warning on unset array arg). (Ilia)
+- Fixed bug #32699 (pg_affected_rows() was defined when it was not available).
+  (Derick)
+- Fixed bug #32682 (ext/mssql: Error on module shutdown when called from 
+  activescript). (Frank)
+- Fixed bug #32647 (Using register_shutdown_function() with invalid callback
+  can crash PHP). (Jani)
+- Fixed bug #32591 (ext/mysql: Unsatisfied symbol: ntohs with HP-UX). (Jani)
+- Fixed bug #32589 (Possible crash inside imap_mail_compose, with charsets).
+  (Ilia)
+- Fixed bug #32587 (Apache2: errors sent to error_log do not include
+  timestamps). (Jani)
+- Fixed bug #32567 (ext/gmp fails to compile in threadsafe mode). (Tony)
+- Fixed bug #32538 (ext/swf/swf.c does not compile with gcc-3.4.x or newer).
+  (adam dot greenfield at gmail dot com)
+- Fixed bug #32530 (chunk_split() does not append endstr if chunklen is  
+  longer then the original string). (Ilia)
+- Fixed bug #32491 (File upload error - unable to create a temporary file).
+  (Uwe Schindler)
+- Fixed bug #32311 (mb_encode_mimeheader() does not properly escape characters).
+  (Moriyoshi)
+- Fixed bug #32245 (xml_parser_free() in a function assigned to the xml parser
+  gives a segfault). (Rob)
+- Fixed bug #32116 (mysql compressed connection doesn't work under windows)
+  (Georg)
+- Fixed bug #31887 (ISAPI: Custom 5xx error does not return correct HTTP 
+  response message). (Jani) 
+- Fixed bug #31583 (php_std_date() uses short day names in non-y2k_compliance mode).
+  (mike at php dot net)
+- Fixed bug #31213 (Sideeffects caused by fix of bug #29493). (Dmitry)
+- Fixed bug #30052 (Crash on shutdown after odbc_pconnect()). (Edin)
+- Fixed bug #29975 (memory leaks when set_error_handler() is used inside error 
+  handler). (Tony)
+- Fixed bug #29944 (Function defined in switch, crashes). (Dmitry)
+- Fixed bug #29338 (unencoded spaces get ignored after certain tags). (Ilia)
+- Fixed bug #28605 (Need to use -[m]ieee option for Alpha CPUs). (Jani)
+- Fixed bug #28377 (debug_backtrace is intermittently passing args). (Dmitry)
+
 31 Mar 2005, Version 4.3.11
 - Added Oracle Instant Client support. (cjbj at hotmail dot com, Tony)
 - Added checks for negative values to gmp_sqrt(), gmp_powm(), gmp_sqrtrem()
@@ -428,8 +428,6 @@ TSRM_API THREAD_T tsrm_thread_id(void)
 {
 #ifdef TSRM_WIN32
 	return GetCurrentThreadId();
-#elif defined(NETWARE)
-	return NXThreadGetId();
 #elif defined(GNUPTH)
 	return pth_self();
 #elif defined(PTHREADS)
@@ -450,17 +448,9 @@ TSRM_API THREAD_T tsrm_thread_id(void)
 TSRM_API MUTEX_T tsrm_mutex_alloc(void)
 {
 	MUTEX_T mutexp;
-#ifdef NETWARE
-	long flags = 0;  /* Don't require NX_MUTEX_RECURSIVE, I guess */
-	NXHierarchy_t order = 0;
-	NX_LOCK_INFO_ALLOC (lockInfo, "PHP-TSRM", 0);
-#endif    
-
 #ifdef TSRM_WIN32
 	mutexp = malloc(sizeof(CRITICAL_SECTION));
 	InitializeCriticalSection(mutexp);
-#elif defined(NETWARE)
-	mutexp = NXMutexAlloc(flags, order, &lockInfo); /* return value ignored for now */
 #elif defined(GNUPTH)
 	mutexp = (MUTEX_T) malloc(sizeof(*mutexp));
 	pth_mutex_init(mutexp);
@@ -492,8 +482,6 @@ TSRM_API void tsrm_mutex_free(MUTEX_T mutexp)
 #ifdef TSRM_WIN32
 		DeleteCriticalSection(mutexp);
 		free(mutexp);
-#elif defined(NETWARE)
-		NXMutexFree(mutexp);
 #elif defined(GNUPTH)
 		free(mutexp);
 #elif defined(PTHREADS)
@@ -523,8 +511,6 @@ TSRM_API int tsrm_mutex_lock(MUTEX_T mutexp)
 #ifdef TSRM_WIN32
 	EnterCriticalSection(mutexp);
 	return 1;
-#elif defined(NETWARE)
-	return NXLock(mutexp);
 #elif defined(GNUPTH)
 	return pth_mutex_acquire(mutexp, 0, NULL);
 #elif defined(PTHREADS)
@@ -550,8 +536,6 @@ TSRM_API int tsrm_mutex_unlock(MUTEX_T mutexp)
 #ifdef TSRM_WIN32
 	LeaveCriticalSection(mutexp);
 	return 1;
-#elif defined(NETWARE)
-	return NXUnlock(mutexp);
 #elif defined(GNUPTH)
 	return pth_mutex_release(mutexp);
 #elif defined(PTHREADS)
@@ -14,7 +14,7 @@
 #define TSRM_H

 /* #ifndef WIN32 */
-#if !defined(WIN32) && !defined(NETWARE)
+#if !defined(WIN32)
 # include <tsrm_config.h>
 #endif

@@ -38,9 +38,6 @@

 #ifdef TSRM_WIN32
 # include <windows.h>
-#elif defined(NETWARE)
-# include <nks/thread.h>
-# include <nks/synch.h>
 #elif defined(GNUPTH)
 # include <pth.h>
 #elif defined(PTHREADS)
@@ -58,9 +55,6 @@ typedef int ts_rsrc_id;
 #ifdef TSRM_WIN32
 # define THREAD_T DWORD
 # define MUTEX_T CRITICAL_SECTION *
-#elif defined(NETWARE)
-# define THREAD_T NXThreadId_t
-# define MUTEX_T NXMutex_t *
 #elif defined(GNUPTH)
 # define THREAD_T pth_t
 # define MUTEX_T pth_mutex_t *
@@ -84,7 +84,15 @@ int main() {
  pthreads_working=yes
  ], [
  pthreads_working=no
-  ], pthreads_working=no ) ] )dnl
+  ], [
+  dnl For cross compiling running this test is of no use. NetWare supports pthreads
+  pthreads_working=no
+  case $host_alias in
+  *netware*)
+    pthreads_working=yes
+  esac
+]
+) ] )dnl
 dnl
 dnl PTHREADS_CHECK()
 dnl
@@ -37,8 +37,7 @@
 #endif

 #ifdef NETWARE
-/*#include "pipe.h"*/
-#include "tsrm_nw.h"
+#include <fsio.h>
 #endif

 #ifndef HAVE_REALPATH
@@ -137,15 +136,9 @@ static int php_check_dots(const char *element, int n)
 	
 static int php_is_dir_ok(const cwd_state *state) 
 {
-#if !(defined(NETWARE) && defined(CLIB_STAT_PATCH))
 	struct stat buf;

 	if (stat(state->cwd, &buf) == 0 && S_ISDIR(buf.st_mode))
-#else
-    struct stat_libc buf;
-
-    if (stat(state->cwd, (struct stat*)(&buf)) == 0 && S_ISDIR(buf.st_mode))
-#endif
 		return (0);

 	return (1);
@@ -153,15 +146,9 @@ static int php_is_dir_ok(const cwd_state *state)

 static int php_is_file_ok(const cwd_state *state) 
 {
-#if !(defined(NETWARE) && defined(CLIB_STAT_PATCH))
 	struct stat buf;

 	if (stat(state->cwd, &buf) == 0 && S_ISREG(buf.st_mode))
-#else
-    struct stat_libc buf;
-
-    if (stat(state->cwd, (struct stat*)(&buf)) == 0 && S_ISREG(buf.st_mode))
-#endif
 		return (0);

 	return (1);
@@ -196,8 +183,20 @@ CWD_API void virtual_cwd_startup(void)
 {
 	char cwd[MAXPATHLEN];
 	char *result;
-
-	result = getcwd(cwd, sizeof(cwd));	
+#ifdef NETWARE
+	result = getcwdpath(cwd, NULL, 1);
+	if(result)
+	{
+		char *c=cwd;
+		while(c = strchr(c, '\\'))
+		{
+			*c='/';
+			++c;
+		}
+	}
+#else
+	result = getcwd(cwd, sizeof(cwd));
+#endif
 	if (!result) {
 		cwd[0] = '\0';
 	}
@@ -210,7 +209,7 @@ CWD_API void virtual_cwd_startup(void)
 	cwd_globals_ctor(&cwd_globals TSRMLS_CC);
 #endif

-#if defined(TSRM_WIN32) && defined(ZTS)
+#if (defined(TSRM_WIN32) || defined(NETWARE)) && defined(ZTS)
 	cwd_mutex = tsrm_mutex_alloc();
 #endif
 }
@@ -220,7 +219,7 @@ CWD_API void virtual_cwd_shutdown(void)
 #ifndef ZTS
 	cwd_globals_dtor(&cwd_globals TSRMLS_CC);
 #endif
-#if defined(TSRM_WIN32) && defined(ZTS)
+#if (defined(TSRM_WIN32) || defined(NETWARE)) && defined(ZTS)
 	tsrm_mutex_free(cwd_mutex);
 #endif

@@ -418,8 +417,20 @@ CWD_API int virtual_file_ex(cwd_state *state, const char *path, verify_path_func
 					state->cwd[state->cwd_length++] = DEFAULT_SLASH;
 				}
 #elif defined(NETWARE)
-				/* If the token is a volume name, it will have colon at the end -- so, no slash before it */
-				if (ptr[ptr_length-1] != ':') {
+				/* 
+					Below code keeps appending to state->cwd a File system seperator
+					cases where this appending should not happen is given below,
+					a) sys: should just be left as it is
+					b) sys:system should just be left as it is,
+					Colon is allowed only in the first token as volume names alone can have the : in their names.
+					Files and Directories cannot have : in their names
+					So the check goes like this,
+					For second token and above simply append the DEFAULT_SLASH to the state->cwd.
+					For first token check for the existence of : 
+					if it exists don't append the DEFAULT_SLASH to the state->cwd.
+				*/
+				if(((state->cwd_length == 0) && (strchr(ptr, ':') == NULL)) || (state->cwd_length > 0))
+				{
 					state->cwd[state->cwd_length++] = DEFAULT_SLASH;
 				}
 #else
@@ -683,7 +694,6 @@ CWD_API int virtual_rename(char *oldname, char *newname TSRMLS_DC)
 	return retval;
 }

-#if !(defined(NETWARE) && defined(CLIB_STAT_PATCH))
 CWD_API int virtual_stat(const char *path, struct stat *buf TSRMLS_DC)
 {
 	cwd_state new_state;
@@ -697,23 +707,8 @@ CWD_API int virtual_stat(const char *path, struct stat *buf TSRMLS_DC)
 	CWD_STATE_FREE(&new_state);
 	return retval;
 }
-#else
-CWD_API int virtual_stat(const char *path, struct stat_libc *buf TSRMLS_DC)
-{
-	cwd_state new_state;
-	int retval;

-	CWD_STATE_COPY(&new_state, &CWDG(cwd));
-	virtual_file_ex(&new_state, path, NULL, 1);
-
-	retval = stat(new_state.cwd, (struct stat*)buf);
-
-	CWD_STATE_FREE(&new_state);
-	return retval;
-}
-#endif
-
-#if !defined(TSRM_WIN32) && !defined(NETWARE)
+#ifndef TSRM_WIN32
 CWD_API int virtual_lstat(const char *path, struct stat *buf TSRMLS_DC)
 {
 	cwd_state new_state;
@@ -74,10 +74,10 @@ typedef unsigned short mode_t;
 #define DEFAULT_SLASH '/'
 #define DEFAULT_DIR_SEPARATOR	';'
 #define IS_SLASH(c)	((c) == '/' || (c) == '\\')
-#define COPY_WHEN_ABSOLUTE(path) \
-    (strchr(path, ':') - path + 1)  /* Take the volume name which ends with a colon */
+#define IS_SLASH_P(c)	IS_SLASH(*(c))
+/* Colon indicates volume name, either first character should be forward slash or backward slash */
 #define IS_ABSOLUTE_PATH(path, len) \
-    (strchr(path, ':') != NULL) /* Colon indicates volume name */
+    ((strchr(path, ':') != NULL) || ((len >= 1) && ((path[0] == '/') || (path[0] == '\\'))))

 #else
 #ifdef HAVE_DIRENT_H
@@ -141,11 +141,7 @@ CWD_API FILE *virtual_fopen(const char *path, const char *mode TSRMLS_DC);
 CWD_API int virtual_open(const char *path TSRMLS_DC, int flags, ...);
 CWD_API int virtual_creat(const char *path, mode_t mode TSRMLS_DC);
 CWD_API int virtual_rename(char *oldname, char *newname TSRMLS_DC);
-#if !(defined(NETWARE) && defined(CLIB_STAT_PATCH))
 CWD_API int virtual_stat(const char *path, struct stat *buf TSRMLS_DC);
-#else
-CWD_API int virtual_stat(const char *path, struct stat_libc *buf TSRMLS_DC);
-#endif
 #if !defined(TSRM_WIN32) && !defined(NETWARE)
 CWD_API int virtual_lstat(const char *path, struct stat *buf TSRMLS_DC);
 #endif
@@ -217,7 +213,7 @@ typedef struct _virtual_cwd_globals {
 #define VCWD_REALPATH(path, real_path) virtual_realpath(path, real_path TSRMLS_CC)
 #define VCWD_RENAME(oldname, newname) virtual_rename(oldname, newname TSRMLS_CC)
 #define VCWD_STAT(path, buff) virtual_stat(path, buff TSRMLS_CC)
-#if !defined(TSRM_WIN32) && !defined(NETWARE)
+#ifndef TSRM_WIN32 
 #define VCWD_LSTAT(path, buff) virtual_lstat(path, buff TSRMLS_CC)
 #endif
 #define VCWD_UNLINK(path) virtual_unlink(path TSRMLS_CC)
@@ -143,7 +143,7 @@ dnl append to the array which has been dynamically chosen at m4 time
 dnl choose the right compiler/flags/etc. for the source-file
      case $ac_src in
 	  *.c[)] ac_comp="$b_c_pre $3 $ac_inc $b_c_meta -c $ac_srcdir$ac_src -o $ac_bdir$ac_obj.$b_lo $6$b_c_post" ;;
-	  *.cpp[)] ac_comp="$b_cxx_pre $3 $ac_inc $b_cxx_meta -c $ac_srcdir$ac_src -o $ac_bdir$ac_obj.$b_lo $6$b_cxx_post" ;;
+	  *.cpp|*.cc[)] ac_comp="$b_cxx_pre $3 $ac_inc $b_cxx_meta -c $ac_srcdir$ac_src -o $ac_bdir$ac_obj.$b_lo $6$b_cxx_post" ;;
      esac

 dnl create a rule for the object/source combo
@@ -1090,18 +1090,27 @@ AC_DEFUN([PHP_CHECK_CC_OPTION],[
  rm -rf conftest*
 ])

+
 AC_DEFUN([PHP_REGEX],[
-
-if test "$REGEX_TYPE" = "php"; then
-  AC_DEFINE(HSREGEX,1,[ ])
-  AC_DEFINE(REGEX,1,[ ])
-  PHP_ADD_SOURCES(regex, regcomp.c regexec.c regerror.c regfree.c)
-elif test "$REGEX_TYPE" = "system"; then
-  AC_DEFINE(REGEX,0,[ ])
-fi
-
-AC_MSG_CHECKING([which regex library to use])
-AC_MSG_RESULT([$REGEX_TYPE])
+  if test "$REGEX_TYPE" = "php"; then
+    AC_DEFINE(HAVE_REGEX_T_RE_MAGIC, 1, [ ])
+    AC_DEFINE(HSREGEX,1,[ ])
+    AC_DEFINE(REGEX,1,[ ])
+    PHP_ADD_SOURCES(regex, regcomp.c regexec.c regerror.c regfree.c)
+  elif test "$REGEX_TYPE" = "system"; then
+    AC_DEFINE(REGEX,0,[ ])
+    dnl Check if field re_magic exists in struct regex_t
+    AC_CACHE_CHECK([whether field re_magic exists in struct regex_t], ac_cv_regex_t_re_magic, [
+      AC_TRY_COMPILE([#include <sys/types.h>
+#include <regex.h>], [regex_t rt; rt.re_magic;],
+      [ac_cv_regex_t_re_magic=yes], [ac_cv_regex_t_re_magic=no])
+    ])
+    if test "$ac_cv_regex_t_re_magic" = "yes"; then
+      AC_DEFINE([HAVE_REGEX_T_RE_MAGIC], [ ], 1)
+    fi 
+  fi
+  AC_MSG_CHECKING([which regex library to use])
+  AC_MSG_RESULT([$REGEX_TYPE])
 ])

 dnl
@@ -1186,6 +1195,10 @@ AC_DEFUN([PHP_SHARED_MODULE],[
      suffix=so
      link_cmd='ifelse($4,,[$(CC)],[$(CXX)]) -dynamic -flat_namespace -bundle -undefined suppress $(COMMON_FLAGS) $(CFLAGS_CLEAN) $(EXTRA_CFLAGS) $(LDFLAGS) -o [$]@ $(EXTRA_LDFLAGS) $($2) $(translit($1,a-z_-,A-Z__)_SHARED_LIBADD)'
      ;;
+    *netware*[)]
+      suffix=nlm
+      link_cmd='$(LIBTOOL) --mode=link ifelse($4,,[$(CC)],[$(CXX)]) $(COMMON_FLAGS) $(CFLAGS_CLEAN) $(EXTRA_CFLAGS) $(LDFLAGS) -o [$]@ -shared -export-dynamic -avoid-version -prefer-pic -module -rpath $(phplibdir) $(EXTRA_LDFLAGS) $($2) ifelse($1, php4lib, , -L$(top_builddir)/netware -lphp4lib) $(translit(ifelse($1, php4lib, $1, m4_substr($1, 3)),a-z_-,A-Z__)_SHARED_LIBADD)'
+      ;;
    *[)]
      suffix=la
      link_cmd='$(LIBTOOL) --mode=link ifelse($4,,[$(CC)],[$(CXX)]) $(COMMON_FLAGS) $(CFLAGS_CLEAN) $(EXTRA_CFLAGS) $(LDFLAGS) -o [$]@ -export-dynamic -avoid-version -prefer-pic -module -rpath $(phplibdir) $(EXTRA_LDFLAGS) $($2) $(translit($1,a-z_-,A-Z__)_SHARED_LIBADD)'
@@ -1274,7 +1287,14 @@ dnl ---------------------------------------------- Static module
    if test "$3" = "shared" || test "$3" = "yes"; then
 dnl ---------------------------------------------- Shared module
      PHP_ADD_SOURCES_X(PHP_EXT_DIR($1),$2,$ac_extra,shared_objects_$1,yes)
-      PHP_SHARED_MODULE($1,shared_objects_$1, $ext_builddir, $6)
+      case $host_alias in
+      *netware*)
+       PHP_SHARED_MODULE(php$1,shared_objects_$1, $ext_builddir, $6)
+       ;;
+      *)
+       PHP_SHARED_MODULE($1,shared_objects_$1, $ext_builddir, $6)
+      ;;
+      esac
      AC_DEFINE_UNQUOTED([COMPILE_DL_]translit($1,a-z_-,A-Z__), 1, Whether to build $1 as dynamic module)
    fi
  fi
@@ -1684,6 +1704,10 @@ AC_DEFUN([PHP_SETUP_OPENSSL],[
  unset OPENSSL_INCDIR
  unset OPENSSL_LIBDIR

+  dnl Empty variable means 'no'
+  test -z "$PHP_OPENSSL" && PHP_OPENSSL=no
+  test -z "$PHP_IMAP_SSL" && PHP_IMAP_SSL=no
+
  dnl Fallbacks for different configure options
  if test "$PHP_OPENSSL" != "no"; then
    PHP_OPENSSL_DIR=$PHP_OPENSSL
@@ -14,7 +14,7 @@
 #  | Author: Sascha Schumann <sascha@schumann.cx>                         |
 #  +----------------------------------------------------------------------+
 #
-# $Id$ 
+# $Id$
 #

 include generated_lists
@@ -32,6 +32,9 @@ acconfig_h_SOURCES = acconfig.h.in $(config_h_files)

 targets = $(TOUCH_FILES) configure $(config_h_in)

+PHP_AUTOCONF ?= 'autoconf'
+PHP_AUTOHEADER ?= 'autoheader'
+
 SUPPRESS_WARNINGS ?= 2>&1 | (egrep -v '(AC_TRY_RUN called without default to allow cross compiling|AC_PROG_CXXCPP was called before AC_PROG_CXX|defined in acinclude.m4 but never used|AC_PROG_LEX invoked multiple times|AC_DECL_YYTEXT is expanded from...|the top level)'||true)

 all: $(targets)
@@ -45,7 +48,7 @@ $(config_h_in): configure acconfig.h
 # correctly otherwise (timestamps are not updated)
 	@echo rebuilding $@
 	@rm -f $@
-	autoheader $(SUPPRESS_WARNINGS)
+	$(PHP_AUTOHEADER) $(SUPPRESS_WARNINGS)

 $(TOUCH_FILES):
 	touch $(TOUCH_FILES)
@@ -56,5 +59,5 @@ aclocal.m4: configure.in acinclude.m4

 configure: aclocal.m4 configure.in $(config_m4_files)
 	@echo rebuilding $@
-	autoconf $(SUPPRESS_WARNINGS)
+	$(PHP_AUTOCONF) $(SUPPRESS_WARNINGS)

@@ -16,15 +16,20 @@
 #  |          Sascha Schumann <sascha@schumann.cx>                        |
 #  +----------------------------------------------------------------------+
 #
-# $Id: buildcheck.sh,v 1.21.2.11 2005-01-20 01:43:18 sniper Exp $ 
+# $Id: buildcheck.sh,v 1.21.2.13 2005-04-07 23:33:50 jon Exp $
 #

 echo "buildconf: checking installation..."

 stamp=$1

+# Allow the autoconf executable to be overridden by $PHP_AUTOCONF.
+if test -z "$PHP_AUTOCONF"; then
+  PHP_AUTOCONF='autoconf'
+fi
+
 # autoconf 2.13 or newer
-ac_version=`autoconf --version 2>/dev/null|head -n 1|sed -e 's/^[^0-9]*//' -e 's/[a-z]* *$//'`
+ac_version=`$PHP_AUTOCONF --version 2>/dev/null|head -n 1|sed -e 's/^[^0-9]*//' -e 's/[a-z]* *$//'`
 if test -z "$ac_version"; then
 echo "buildconf: autoconf not found."
 echo "           You need autoconf version 2.13 or newer installed"
@@ -42,7 +47,9 @@ echo "buildconf: autoconf version $ac_version (ok)"
 fi

 if test "$1" = "2" && test "$2" -ge "50"; then
-  echo "buildconf: running cvsclean."
+  echo "buildconf: Your version of autoconf likely contains buggy cache code."
+  echo "           Running cvsclean for you."
+  echo "           To avoid this, install autoconf-2.13 and automake-1.5."
  ./cvsclean
  stamp=
 fi
@@ -1,12 +1,12 @@
 #!/bin/sh
 ##
 ##  GNU shtool -- The GNU Portable Shell Tool
-##  Copyright (c) 1994-2002 Ralf S. Engelschall <rse@engelschall.com>
+##  Copyright (c) 1994-2005 Ralf S. Engelschall <rse@engelschall.com>
 ##
 ##  See http://www.gnu.org/software/shtool/ for more information.
 ##  See ftp://ftp.gnu.org/gnu/shtool/ for latest version.
 ##
-##  Version:  1.6.2 (02-Nov-2002)
+##  Version:  2.0.2 (15-Jun-2005)
 ##  Contents: 4/19 available modules
 ##

@@ -54,7 +54,7 @@
 ##    rotate     Logfile rotation
 ##    tarball    Roll distribution tarballs
 ##    subst      Apply sed(1) substitution operations
-##    guessos    Simple operating system guesser
+##    platform   Platform Identification Utility
 ##    arx        Extended archive command
 ##    slo        Separate linker options by library class
 ##    scpp       Sharing C Pre-Processor
@@ -66,9 +66,9 @@ if [ $# -eq 0 ]; then
    echo "$0:Hint:  run \`$0 -h' for usage" 1>&2
    exit 1
 fi
-if [ ".$1" = ".-h" -o ".$1" = ".--help" ]; then
-    echo "This is GNU shtool, version 1.6.2 (02-Nov-2002)"
-    echo "Copyright (c) 1994-2002 Ralf S. Engelschall <rse@engelschall.com>"
+if [ ".$1" = ".-h" ] || [ ".$1" = ".--help" ]; then
+    echo "This is GNU shtool, version 2.0.2 (15-Jun-2005)"
+    echo "Copyright (c) 1994-2005 Ralf S. Engelschall <rse@engelschall.com>"
    echo "Report bugs to <bug-shtool@gnu.org>"
    echo ''
    echo "Usage: shtool [<options>] [<cmd-name> [<cmd-options>] [<cmd-args>]]"
@@ -80,7 +80,7 @@ if [ ".$1" = ".-h" -o ".$1" = ".--help" ]; then
    echo '  -r, --recreate  recreate this shtool script via shtoolize'
    echo ''
    echo 'Available <cmd-name> [<cmd-options>] [<cmd-args>]:'
-    echo '  echo     [-n|--newline] [-e|--expand] [<str> ...]'
+    echo '  echo     [-n|--newline] [-e|--expand] [<string> ...]'
    echo '  install  [-v|--verbose] [-t|--trace] [-d|--mkdir] [-c|--copy]'
    echo '           [-C|--compare-copy] [-s|--strip] [-m|--mode <mode>]'
    echo '           [-o|--owner <owner>] [-g|--group <group>] [-e|--exec'
@@ -106,17 +106,21 @@ if [ ".$1" = ".-h" -o ".$1" = ".--help" ]; then
    echo '  rotate   [-v|--verbose] [-t|--trace] [-f|--force] [-n|--num-files'
    echo '           <count>] [-s|--size <size>] [-c|--copy] [-r|--remove]'
    echo '           [-a|--archive-dir <dir>] [-z|--compress [<tool>:]<level>]'
-    echo '           [-b|--background] [-d|--delay] [-p|--pad <len>] [-o|--owner'
-    echo '           <owner>] [-g|--group <group>] [-m|--mode <mode>] [-M|--migrate'
+    echo '           [-b|--background] [-d|--delay] [-p|--pad <len>] [-m|--mode'
+    echo '           <mode>] [-o|--owner <owner>] [-g|--group <group>] [-M|--migrate'
    echo '           <cmd>] [-P|--prolog <cmd>] [-E|--epilog <cmd>] <file> [...]'
    echo '  tarball  [-t|--trace] [-v|--verbose] [-o|--output <tarball>]'
    echo '           [-c|--compress <prog>] [-d|--directory <dir>] [-u|--user'
    echo '           <user>] [-g|--group <group>] [-e|--exclude <pattern>]'
    echo '           <path> [<path> ...]'
-    echo '  subst    [-v|--verbose] [-t|--trace] [-n|--nop] [-s|--stealth]'
-    echo '           [-i|--interactive] [-b|--backup <ext>] [-e|--exec <cmd>]'
-    echo '           [-f|--file <cmd-file>] [<file>] [...]'
-    echo '  guessos  '
+    echo '  subst    [-v|--verbose] [-t|--trace] [-n|--nop] [-w|--warning]'
+    echo '           [-q|--quiet] [-s|--stealth] [-i|--interactive] [-b|--backup'
+    echo '           <ext>] [-e|--exec <cmd>] [-f|--file <cmd-file>] [<file>]'
+    echo '           [...]'
+    echo '  platform [-F|--format <format>] [-S|--sep <string>] [-C|--conc'
+    echo '           <string>] [-L|--lower] [-U|--upper] [-v|--verbose]'
+    echo '           [-c|--concise] [-n|--no-newline] [-t|--type <type>]'
+    echo '           [-V|--version] [-h|--help]'
    echo '  arx      [-t|--trace] [-C|--command <cmd>] <op> <archive> [<file>'
    echo '           ...]'
    echo '  slo      [-p|--prefix <str>] -- -L<dir> -l<lib> [-L<dir> -l<lib>'
@@ -131,15 +135,15 @@ if [ ".$1" = ".-h" -o ".$1" = ".--help" ]; then
    echo ''
    exit 0
 fi
-if [ ".$1" = ".-v" -o ".$1" = ."--version" ]; then
-    echo "GNU shtool 1.6.2 (02-Nov-2002)"
+if [ ".$1" = ".-v" ] || [ ".$1" = ".--version" ]; then
+    echo "GNU shtool 2.0.2 (15-Jun-2005)"
    exit 0
 fi
-if [ ".$1" = ".-r" -o ".$1" = ."--recreate" ]; then
+if [ ".$1" = ".-r" ] || [ ".$1" = ".--recreate" ]; then
    shtoolize -oshtool echo install mkdir path
    exit 0
 fi
-if [ ".$1" = ".-d" -o ".$1" = ."--debug" ]; then
+if [ ".$1" = ".-d" ] || [ ".$1" = ".--debug" ]; then
    shift
    set -x
 fi
@@ -166,7 +170,7 @@ gen_tmpfile=no
 case $tool in
    echo )
        str_tool="echo"
-        str_usage="[-n|--newline] [-e|--expand] [<str> ...]"
+        str_usage="[-n|--newline] [-e|--expand] [<string> ...]"
        arg_spec="0+"
        opt_spec="n.e."
        opt_alias="n:newline,e:expand"
@@ -261,7 +265,7 @@ eval `echo h.$opt_spec |\

 #   parse option alias string
 eval `echo h:help,$opt_alias |\
-      tr 'x-' 'x_' | sed -e 's/\([a-zA-Z0-9]\):\([^,]*\),*/opt_ALIAS_\2=\1;/g'`
+      sed -e 's/-/_/g' -e 's/\([a-zA-Z0-9]\):\([^,]*\),*/opt_ALIAS_\2=\1;/g'`

 #   interate over argument line
 opt_PREV=''
@@ -286,12 +290,12 @@ while [ $# -gt 0 ]; do
            --[a-zA-Z0-9]*=*)
                eval `echo "x$1" |\
                      sed -e 's/^x--\([a-zA-Z0-9-]*\)=\(.*\)$/opt_OPT="\1";opt_ARG="\2"/'`
-                opt_STR=`echo $opt_OPT | tr 'x-' 'x_'`
+                opt_STR=`echo $opt_OPT | sed -e 's/-/_/g'`
                eval "opt_OPT=\${opt_ALIAS_${opt_STR}-${opt_OPT}}"
                ;;
            --[a-zA-Z0-9]*)
                opt_OPT=`echo "x$1" | cut -c4-`
-                opt_STR=`echo $opt_OPT | tr 'x-' 'x_'`
+                opt_STR=`echo $opt_OPT | sed -e 's/-/_/g'`
                eval "opt_OPT=\${opt_ALIAS_${opt_STR}-${opt_OPT}}"
                opt_ARG=''
                ;;
@@ -315,8 +319,8 @@ while [ $# -gt 0 ]; do

    #   determine whether option needs an argument
    eval "opt_MODE=\$opt_MODE_${opt_OPT}"
-    if [ ".$opt_ARG" = . -a ".$opt_ARG_OK" != .yes ]; then
-        if [ ".$opt_MODE" = ".:" -o ".$opt_MODE" = ".+" ]; then
+    if [ ".$opt_ARG" = . ] && [ ".$opt_ARG_OK" != .yes ]; then
+        if [ ".$opt_MODE" = ".:" ] || [ ".$opt_MODE" = ".+" ]; then
            opt_PREV="$opt_OPT"
            continue
        fi
@@ -375,6 +379,7 @@ esac

 #   establish a temporary file on request
 if [ ".$gen_tmpfile" = .yes ]; then
+    #   create (explicitly) secure temporary directory
    if [ ".$TMPDIR" != . ]; then
        tmpdir="$TMPDIR"
    elif [ ".$TEMPDIR" != . ]; then
@@ -382,12 +387,40 @@ if [ ".$gen_tmpfile" = .yes ]; then
    else
        tmpdir="/tmp"
    fi
-    tmpfile="$tmpdir/.shtool.$$"
-    rm -f $tmpfile >/dev/null 2>&1
-    touch $tmpfile
-    chmod 600 $tmpfile
+    tmpdir="$tmpdir/.shtool.$$"
+    ( umask 077
+      rm -rf "$tmpdir" >/dev/null 2>&1 || true
+      mkdir  "$tmpdir" >/dev/null 2>&1
+      if [ $? -ne 0 ]; then
+          echo "$msgprefix:Error: failed to create temporary directory \`$tmpdir'" 1>&2
+          exit 1
+      fi
+    )
+
+    #   create (implicitly) secure temporary file
+    tmpfile="$tmpdir/shtool.tmp"
+    touch "$tmpfile"
 fi

+#   utility function: map string to lower case
+util_lower () {
+    echo "$1" | tr 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' 'abcdefghijklmnopqrstuvwxyz'
+}
+
+#   utility function: map string to upper case
+util_upper () {
+    echo "$1" | tr 'abcdefghijklmnopqrstuvwxyz' 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
+}
+
+#   cleanup procedure
+shtool_exit () {
+    rc="$1"
+    if [ ".$gen_tmpfile" = .yes ]; then
+        rm -rf "$tmpdir" >/dev/null 2>&1 || true
+    fi
+    exit $rc
+}
+
 ##
 ##  DISPATCH INTO SCRIPT BODY
 ##
@@ -397,12 +430,11 @@ case $tool in
 echo )
    ##
    ##  echo -- Print string with optional construct expansion
-    ##  Copyright (c) 1998-2002 Ralf S. Engelschall <rse@engelschall.com>
-    ##  Originally written for WML as buildinfo
+    ##  Copyright (c) 1998-2005 Ralf S. Engelschall <rse@engelschall.com>
    ##
-    
+
    text="$*"
-    
+
    #   check for broken escape sequence expansion
    seo=''
    bytes=`echo '\1' | wc -c | awk '{ printf("%s", $1); }'`
@@ -412,18 +444,18 @@ echo )
            seo='-E'
        fi
    fi
-    
+
    #   check for existing -n option (to suppress newline)
    minusn=''
    bytes=`echo -n 123 2>/dev/null | wc -c | awk '{ printf("%s", $1); }'`
    if [ ".$bytes" = .3 ]; then
        minusn='-n'
    fi
-    
+
    #   determine terminal bold sequence
    term_bold=''
    term_norm=''
-    if [ ".$opt_e" = .yes -a ".`echo $text | egrep '%[Bb]'`" != . ]; then
+    if [ ".$opt_e" = .yes ] && [ ".`echo $text | grep '%[Bb]'`" != . ]; then
        case $TERM in
            #   for the most important terminal types we directly know the sequences
            xterm|xterm*|vt220|vt220*)
@@ -459,96 +491,139 @@ echo )
                            break
                        fi
                    done
-                    if [ ".$term_bold" != . -a ".$term_norm" != . ]; then
+                    if [ ".$term_bold" != . ] && [ ".$term_norm" != . ]; then
                        break;
                    fi
                done
                ;;
        esac
-        if [ ".$term_bold" = . -o ".$term_norm" = . ]; then
+        if [ ".$term_bold" = . ] || [ ".$term_norm" = . ]; then
            echo "$msgprefix:Warning: unable to determine terminal sequence for bold mode" 1>&2
            term_bold=''
            term_norm=''
        fi
    fi
-    
+
    #   determine user name
    username=''
-    if [ ".$opt_e" = .yes -a ".`echo $text | egrep '%[uUgG]'`" != . ]; then
-        username="$LOGNAME"
+    if [ ".$opt_e" = .yes ] && [ ".`echo $text | grep '%[uUgG]'`" != . ]; then
+        username="`(id -un) 2>/dev/null`"
        if [ ".$username" = . ]; then
-            username="$USER"
-            if [ ".$username" = . ]; then
-                username="`(whoami) 2>/dev/null |\
-                           awk '{ printf("%s", $1); }'`"
-                if [ ".$username" = . ]; then
-                    username="`(who am i) 2>/dev/null |\
-                               awk '{ printf("%s", $1); }'`"
-                    if [ ".$username" = . ]; then
-                        username='unknown'
-                    fi
-                fi
-            fi
-        fi
-    fi
-    
-    #   determine user id
-    userid=''
-    if [ ".$opt_e" = .yes -a ".`echo $text | egrep '%U'`" != . ]; then
-        userid="`(id -u) 2>/dev/null`"
-        if [ ".$userid" = . ]; then
            str="`(id) 2>/dev/null`"
            if [ ".`echo $str | grep '^uid[ 	]*=[ 	]*[0-9]*('`" != . ]; then
-                userid=`echo $str | sed -e 's/^uid[ 	]*=[ 	]*//' -e 's/(.*//'`
+                username=`echo $str | sed -e 's/^uid[ 	]*=[ 	]*[0-9]*(//' -e 's/).*$//'`
            fi
-            if [ ".$userid" = . ]; then
-                userid=`egrep "^${username}:" /etc/passwd 2>/dev/null | \
-                        sed -e 's/[^:]*:[^:]*://' -e 's/:.*$//'`
-                if [ ".$userid" = . ]; then
-                    userid=`(ypcat passwd) 2>/dev/null |
-                            egrep "^${username}:" | \
-                            sed -e 's/[^:]*:[^:]*://' -e 's/:.*$//'`
-                    if [ ".$userid" = . ]; then
-                        userid='?'
+            if [ ".$username" = . ]; then
+                username="$LOGNAME"
+                if [ ".$username" = . ]; then
+                    username="$USER"
+                    if [ ".$username" = . ]; then
+                        username="`(whoami) 2>/dev/null |\
+                                   awk '{ printf("%s", $1); }'`"
+                        if [ ".$username" = . ]; then
+                            username="`(who am i) 2>/dev/null |\
+                                       awk '{ printf("%s", $1); }'`"
+                            if [ ".$username" = . ]; then
+                                username='unknown'
+                            fi
+                        fi
                    fi
                fi
            fi
        fi
    fi
-    
+
+    #   determine user id
+    userid=''
+    if [ ".$opt_e" = .yes ] && [ ".`echo $text | grep '%U'`" != . ]; then
+        userid="`(id -u) 2>/dev/null`"
+        if [ ".$userid" = . ]; then
+            userid="`(id -u ${username}) 2>/dev/null`"
+            if [ ".$userid" = . ]; then
+                str="`(id) 2>/dev/null`"
+                if [ ".`echo $str | grep '^uid[ 	]*=[ 	]*[0-9]*('`" != . ]; then
+                    userid=`echo $str | sed -e 's/^uid[ 	]*=[ 	]*//' -e 's/(.*$//'`
+                fi
+                if [ ".$userid" = . ]; then
+                    userid=`(getent passwd ${username}) 2>/dev/null | \
+                            sed -e 's/[^:]*:[^:]*://' -e 's/:.*$//'`
+                    if [ ".$userid" = . ]; then
+                        userid=`grep "^${username}:" /etc/passwd 2>/dev/null | \
+                                sed -e 's/[^:]*:[^:]*://' -e 's/:.*$//'`
+                        if [ ".$userid" = . ]; then
+                            userid=`(ypcat passwd) 2>/dev/null |
+                                    grep "^${username}:" | \
+                                    sed -e 's/[^:]*:[^:]*://' -e 's/:.*$//'`
+                            if [ ".$userid" = . ]; then
+                                userid='?'
+                            fi
+                        fi
+                    fi
+                fi
+            fi
+        fi
+    fi
+
    #   determine (primary) group id
    groupid=''
-    if [ ".$opt_e" = .yes -a ".`echo $text | egrep '%[gG]'`" != . ]; then
-        groupid=`egrep "^${username}:" /etc/passwd 2>/dev/null | \
-                 sed -e 's/[^:]*:[^:]*:[^:]*://' -e 's/:.*$//'`
+    if [ ".$opt_e" = .yes ] && [ ".`echo $text | grep '%[gG]'`" != . ]; then
+        groupid="`(id -g ${username}) 2>/dev/null`"
        if [ ".$groupid" = . ]; then
-            groupid=`(ypcat passwd) 2>/dev/null | egrep "^${username}:" | \
-                     sed -e 's/[^:]*:[^:]*:[^:]*://' -e 's/:.*$//'`
+            str="`(id) 2>/dev/null`"
+            if [ ".`echo $str | grep 'gid[ 	]*=[ 	]*[0-9]*('`" != . ]; then
+                groupid=`echo $str | sed -e 's/^.*gid[ 	]*=[ 	]*//' -e 's/(.*$//'`
+            fi
            if [ ".$groupid" = . ]; then
-                groupid='?'
+                groupid=`(getent passwd ${username}) 2>/dev/null | \
+                         sed -e 's/[^:]*:[^:]*:[^:]*://' -e 's/:.*$//'`
+                if [ ".$groupid" = . ]; then
+                    groupid=`grep "^${username}:" /etc/passwd 2>/dev/null | \
+                             sed -e 's/[^:]*:[^:]*:[^:]*://' -e 's/:.*$//'`
+                    if [ ".$groupid" = . ]; then
+                        groupid=`(ypcat passwd) 2>/dev/null | grep "^${username}:" | \
+                                 sed -e 's/[^:]*:[^:]*:[^:]*://' -e 's/:.*$//'`
+                        if [ ".$groupid" = . ]; then
+                            groupid='?'
+                        fi
+                    fi
+                fi
            fi
        fi
    fi
-    
+
    #   determine (primary) group name
    groupname=''
-    if [ ".$opt_e" = .yes -a ".`echo $text | egrep '%g'`" != . ]; then
-        groupname=`egrep "^[^:]*:[^:]*:${groupid}:" /etc/group 2>/dev/null | \
-                   sed -e 's/:.*$//'`
+    if [ ".$opt_e" = .yes ] && [ ".`echo $text | grep '%g'`" != . ]; then
+        groupname="`(id -gn ${username}) 2>/dev/null`"
        if [ ".$groupname" = . ]; then
-            groupname=`(ypcat group) 2>/dev/null | \
-                       egrep "^[^:]*:[^:]*:${groupid}:" | \
-                       sed -e 's/:.*$//'`
+            str="`(id) 2>/dev/null`"
+            if [ ".`echo $str | grep 'gid[ 	]*=[ 	]*[0-9]*('`" != . ]; then
+                groupname=`echo $str | sed -e 's/^.*gid[ 	]*=[ 	]*[0-9]*(//' -e 's/).*$//'`
+            fi
            if [ ".$groupname" = . ]; then
-                groupname='?'
+                groupname=`(getent group) 2>/dev/null | \
+                           grep "^[^:]*:[^:]*:${groupid}:" | \
+                           sed -e 's/:.*$//'`
+                if [ ".$groupname" = . ]; then
+                    groupname=`grep "^[^:]*:[^:]*:${groupid}:" /etc/group 2>/dev/null | \
+                               sed -e 's/:.*$//'`
+                    if [ ".$groupname" = . ]; then
+                        groupname=`(ypcat group) 2>/dev/null | \
+                                   grep "^[^:]*:[^:]*:${groupid}:" | \
+                                   sed -e 's/:.*$//'`
+                        if [ ".$groupname" = . ]; then
+                            groupname='?'
+                        fi
+                    fi
+                fi
            fi
        fi
    fi
-    
+
    #   determine host and domain name
    hostname=''
    domainname=''
-    if [ ".$opt_e" = .yes -a ".`echo $text | egrep '%h'`" != . ]; then
+    if [ ".$opt_e" = .yes ] && [ ".`echo $text | grep '%h'`" != . ]; then
        hostname="`(uname -n) 2>/dev/null |\
                   awk '{ printf("%s", $1); }'`"
        if [ ".$hostname" = . ]; then
@@ -565,16 +640,16 @@ echo )
                ;;
        esac
    fi
-    if [ ".$opt_e" = .yes -a ".`echo $text | egrep '%d'`" != . ]; then
+    if [ ".$opt_e" = .yes ] && [ ".`echo $text | grep '%d'`" != . ]; then
        if [ ".$domainname" = . ]; then
            if [ -f /etc/resolv.conf ]; then
-                domainname="`egrep '^[ 	]*domain' /etc/resolv.conf | sed -e 'q' |\
+                domainname="`grep '^[ 	]*domain' /etc/resolv.conf | sed -e 'q' |\
                             sed -e 's/.*domain//' \
                                 -e 's/^[ 	]*//' -e 's/^ *//' -e 's/^	*//' \
                                 -e 's/^\.//' -e 's/^/./' |\
                             awk '{ printf("%s", $1); }'`"
                if [ ".$domainname" = . ]; then
-                    domainname="`egrep '^[ 	]*search' /etc/resolv.conf | sed -e 'q' |\
+                    domainname="`grep '^[ 	]*search' /etc/resolv.conf | sed -e 'q' |\
                                 sed -e 's/.*search//' \
                                     -e 's/^[ 	]*//' -e 's/^ *//' -e 's/^	*//' \
                                     -e 's/ .*//' -e 's/	.*//' \
@@ -584,13 +659,13 @@ echo )
            fi
        fi
    fi
-    
+
    #   determine current time
    time_day=''
    time_month=''
    time_year=''
    time_monthname=''
-    if [ ".$opt_e" = .yes -a ".`echo $text | egrep '%[DMYm]'`" != . ]; then
+    if [ ".$opt_e" = .yes ] && [ ".`echo $text | grep '%[DMYm]'`" != . ]; then
        time_day=`date '+%d'`
        time_month=`date '+%m'`
        time_year=`date '+%Y' 2>/dev/null`
@@ -616,7 +691,7 @@ echo )
              12) time_monthname='Dec' ;;
        esac
    fi
-    
+
    #   expand special ``%x'' constructs
    if [ ".$opt_e" = .yes ]; then
        text=`echo $seo "$text" |\
@@ -633,7 +708,7 @@ echo )
                  -e "s/%Y/${time_year}/g" \
                  -e "s/%m/${time_monthname}/g" 2>/dev/null`
    fi
-    
+
    #   create output
    if [ .$opt_n = .no ]; then
        echo $seo "$text"
@@ -646,15 +721,16 @@ echo )
            echo dummy | awk '{ printf("%s", TEXT); }' TEXT="$text"
        fi
    fi
+
+    shtool_exit 0
    ;;

 install )
    ##
    ##  install -- Install a program, script or datafile
-    ##  Copyright (c) 1997-2002 Ralf S. Engelschall <rse@engelschall.com>
-    ##  Originally written for shtool
+    ##  Copyright (c) 1997-2005 Ralf S. Engelschall <rse@engelschall.com>
    ##
-    
+
    #   special case: "shtool install -d <dir> [...]" internally
    #   maps to "shtool mkdir -f -p -m 755 <dir> [...]"
    if [ "$opt_d" = yes ]; then
@@ -672,11 +748,11 @@ install )
            cmd="$cmd -t"
        fi
        for dir in "$@"; do
-            eval "$cmd $dir" || exit $?
+            eval "$cmd $dir" || shtool_exit $?
        done
-        exit 0
+        shtool_exit 0
    fi
-    
+
    #   determine source(s) and destination
    argc=$#
    srcs=""
@@ -685,30 +761,30 @@ install )
        shift
    done
    dstpath="$1"
-    
+
    #   type check for destination
    dstisdir=0
    if [ -d $dstpath ]; then
        dstpath=`echo "$dstpath" | sed -e 's:/$::'`
        dstisdir=1
    fi
-    
+
    #   consistency check for destination
-    if [ $argc -gt 2 -a $dstisdir = 0 ]; then
+    if [ $argc -gt 2 ] && [ $dstisdir = 0 ]; then
        echo "$msgprefix:Error: multiple sources require destination to be directory" 1>&2
-        exit 1
+        shtool_exit 1
    fi
-    
+
    #   iterate over all source(s)
    for src in $srcs; do
        dst=$dstpath
-    
+
        #   if destination is a directory, append the input filename
        if [ $dstisdir = 1 ]; then
            dstfile=`echo "$src" | sed -e 's;.*/\([^/]*\)$;\1;'`
            dst="$dst/$dstfile"
        fi
-    
+
        #   check for correct arguments
        if [ ".$src" = ".$dst" ]; then
            echo "$msgprefix:Warning: source and destination are the same - skipped" 1>&2
@@ -718,17 +794,17 @@ install )
            echo "$msgprefix:Warning: source \`$src' is a directory - skipped" 1>&2
            continue
        fi
-    
+
        #   make a temp file name in the destination directory
        dsttmp=`echo $dst |\
                sed -e 's;[^/]*$;;' -e 's;\(.\)/$;\1;' -e 's;^$;.;' \
                    -e "s;\$;/#INST@$$#;"`
-    
+
        #   verbosity
        if [ ".$opt_v" = .yes ]; then
            echo "$src -> $dst" 1>&2
        fi
-    
+
        #   copy or move the file name to the temp name
        #   (because we might be not allowed to change the source)
        if [ ".$opt_C" = .yes ]; then
@@ -738,14 +814,14 @@ install )
            if [ ".$opt_t" = .yes ]; then
                echo "cp $src $dsttmp" 1>&2
            fi
-            cp $src $dsttmp || exit $?
+            cp $src $dsttmp || shtool_exit $?
        else
            if [ ".$opt_t" = .yes ]; then
                echo "mv $src $dsttmp" 1>&2
            fi
-            mv $src $dsttmp || exit $?
+            mv $src $dsttmp || shtool_exit $?
        fi
-    
+
        #   adjust the target file
        if [ ".$opt_e" != . ]; then
            sed='sed'
@@ -755,34 +831,35 @@ install )
                sed="$sed -e '$e'"
            done
            cp $dsttmp $dsttmp.old
-            eval "$sed <$dsttmp.old >$dsttmp" || exit $?
+            chmod u+w $dsttmp
+            eval "$sed <$dsttmp.old >$dsttmp" || shtool_exit $?
            rm -f $dsttmp.old
        fi
        if [ ".$opt_s" = .yes ]; then
            if [ ".$opt_t" = .yes ]; then
                echo "strip $dsttmp" 1>&2
            fi
-            strip $dsttmp || exit $?
+            strip $dsttmp || shtool_exit $?
        fi
        if [ ".$opt_o" != . ]; then
            if [ ".$opt_t" = .yes ]; then
                echo "chown $opt_o $dsttmp" 1>&2
            fi
-            chown $opt_o $dsttmp || exit $?
+            chown $opt_o $dsttmp || shtool_exit $?
        fi
        if [ ".$opt_g" != . ]; then
            if [ ".$opt_t" = .yes ]; then
                echo "chgrp $opt_g $dsttmp" 1>&2
            fi
-            chgrp $opt_g $dsttmp || exit $?
+            chgrp $opt_g $dsttmp || shtool_exit $?
        fi
        if [ ".$opt_m" != ".-" ]; then
            if [ ".$opt_t" = .yes ]; then
                echo "chmod $opt_m $dsttmp" 1>&2
            fi
-            chmod $opt_m $dsttmp || exit $?
+            chmod $opt_m $dsttmp || shtool_exit $?
        fi
-    
+
        #   determine whether to do a quick install
        #   (has to be done _after_ the strip was already done)
        quick=no
@@ -793,7 +870,7 @@ install )
                fi
            fi
        fi
-    
+
        #   finally, install the file to the real destination
        if [ $quick = yes ]; then
            if [ ".$opt_t" = .yes ]; then
@@ -807,21 +884,21 @@ install )
            rm -f $dst && mv $dsttmp $dst
        fi
    done
+
+    shtool_exit 0
    ;;

 mkdir )
    ##
    ##  mkdir -- Make one or more directories
-    ##  Copyright (c) 1996-2002 Ralf S. Engelschall <rse@engelschall.com>
-    ##  Originally written for public domain by Noah Friedman <friedman@prep.ai.mit.edu>
-    ##  Cleaned up and enhanced for shtool
+    ##  Copyright (c) 1996-2005 Ralf S. Engelschall <rse@engelschall.com>
    ##
-    
+
    errstatus=0
    for p in ${1+"$@"}; do
        #   if the directory already exists...
        if [ -d "$p" ]; then
-            if [ ".$opt_f" = .no -a ".$opt_p" = .no ]; then
+            if [ ".$opt_f" = .no ] && [ ".$opt_p" = .no ]; then
                echo "$msgprefix:Error: directory already exists: $p" 1>&2
                errstatus=1
                break
@@ -895,32 +972,32 @@ mkdir )
            done
        fi
    done
-    exit $errstatus
+
+    shtool_exit $errstatus
    ;;

 path )
    ##
    ##  path -- Deal with program paths
-    ##  Copyright (c) 1998-2002 Ralf S. Engelschall <rse@engelschall.com>
-    ##  Originally written for Apache
+    ##  Copyright (c) 1998-2005 Ralf S. Engelschall <rse@engelschall.com>
    ##
-    
+
    namelist="$*"
-    
+
    #   check whether the test command supports the -x option
    if [ -x /bin/sh ] 2>/dev/null; then
        minusx="-x"
    else
        minusx="-r"
    fi
-    
+
    #   split path string
    paths="`echo $opt_p |\
            sed -e 's/^:/.:/' \
                -e 's/::/:.:/g' \
                -e 's/:$/:./' \
                -e 's/:/ /g'`"
-    
+
    #   SPECIAL REQUEST
    #   translate forward to reverse path
    if [ ".$opt_r" = .yes ]; then
@@ -933,25 +1010,25 @@ path )
            done
        fi
        echo $rp | sed -e 's:/$::'
-        exit 0
+        shtool_exit 0
    fi
-    
+
    #   SPECIAL REQUEST
    #   strip out directory or base name
    if [ ".$opt_d" = .yes ]; then
        echo "$namelist" |\
        sed -e 's;[^/]*$;;' -e 's;\(.\)/$;\1;'
-        exit 0
+        shtool_exit 0
    fi
    if [ ".$opt_b" = .yes ]; then
        echo "$namelist" |\
        sed -e 's;.*/\([^/]*\)$;\1;'
-        exit 0
+        shtool_exit 0
    fi
-    
+
    #   MAGIC SITUATION
    #   Perl Interpreter (perl)
-    if [ ".$opt_m" = .yes  -a ".$namelist" = .perl ]; then
+    if [ ".$opt_m" = .yes ] && [ ".$namelist" = .perl ]; then
        rm -f $tmpfile >/dev/null 2>&1
        touch $tmpfile
        found=0
@@ -960,7 +1037,7 @@ path )
            dir=`echo $dir | sed -e 's;/*$;;'`
            nc=99
            for name in perl perl5 miniperl; do
-                 if [ $minusx "$dir/$name" -a ! -d "$dir/$name" ]; then
+                 if [ $minusx "$dir/$name" ] && [ ! -d "$dir/$name" ]; then
                     perl="$dir/$name"
                     pv=`$perl -e 'printf("%.3f", $]);'`
                     echo "$pv:$pc:$nc:$perl" >>$tmpfile
@@ -974,15 +1051,15 @@ path )
            perl="`cat $tmpfile | sort -r -u | sed -e 'q' | cut -d: -f4`"
            rm -f $tmpfile >/dev/null 2>&1
            echo "$perl"
-            exit 0
+            shtool_exit 0
        fi
        rm -f $tmpfile >/dev/null 2>&1
-        exit 1
+        shtool_exit 1
    fi
-    
+
    #   MAGIC SITUATION
    #   C pre-processor (cpp)
-    if [ ".$opt_m" = .yes -a ".$namelist" = .cpp ]; then
+    if [ ".$opt_m" = .yes ] && [ ".$namelist" = .cpp ]; then
        echo >$tmpfile.c "#include <assert.h>"
        echo >>$tmpfile.c "Syntax Error"
        #   1. try the standard cc -E approach
@@ -998,7 +1075,7 @@ path )
                #   3. try a standalone cpp command in path and lib dirs
                for path in $paths /lib /usr/lib /usr/local/lib; do
                    path=`echo $path | sed -e 's;/*$;;'`
-                    if [ $minusx "$path/cpp" -a ! -d "$path/cpp" ]; then
+                    if [ $minusx "$path/cpp" ] && [ ! -d "$path/cpp" ]; then
                        cpp="$path/cpp"
                        break
                    fi
@@ -1017,30 +1094,30 @@ path )
        rm -f $tmpfile.c $tmpfile.out >/dev/null 2>&1
        if [ ".$cpp" != . ]; then
            echo "$cpp"
-            exit 0
+            shtool_exit 0
        fi
-        exit 1
+        shtool_exit 1
    fi
-    
+
    #   STANDARD SITUATION
    #   iterate over names
    for name in $namelist; do
        #   iterate over paths
        for path in $paths; do
            path=`echo $path | sed -e 's;/*$;;'`
-            if [ $minusx "$path/$name" -a ! -d "$path/$name" ]; then
+            if [ $minusx "$path/$name" ] && [ ! -d "$path/$name" ]; then
                if [ ".$opt_s" != .yes ]; then
                    echo "$path/$name"
                fi
-                exit 0
+                shtool_exit 0
            fi
        done
    done
-    exit 1
+
+    shtool_exit 1
    ;;

 esac

-exit 0
+shtool_exit 0

-##EOF##
@@ -39,8 +39,8 @@ PHP_CANONICAL_HOST
 AC_CONFIG_HEADER(main/php_config.h)

 MAJOR_VERSION=4
-MINOR_VERSION=3
-RELEASE_VERSION=11
+MINOR_VERSION=4
+RELEASE_VERSION=1
 EXTRA_VERSION=""
 VERSION="$MAJOR_VERSION.$MINOR_VERSION.$RELEASE_VERSION$EXTRA_VERSION"

@@ -180,6 +180,17 @@ PHP_C_BIGENDIAN
 dnl Platform-specific compile settings.
 dnl -------------------------------------------------------------------------

+dnl See bug #28605
+case $host_cpu in
+alpha*)
+    if test "$GCC" = "yes"; then
+      CFLAGS="$CFLAGS -mieee"
+    else
+      CFLAGS="$CFLAGS -ieee"
+    fi
+    ;;
+esac
+
 case $host_alias in
 *solaris*)
    CPPFLAGS="$CPPFLAGS -D_POSIX_PTHREAD_SEMANTICS"
@@ -203,6 +214,15 @@ case $host_alias in
      CPPFLAGS="$CPPFLAGS -D_XOPEN_SOURCE_EXTENDED"  
    fi  
    ;;
+*netware*)
+    PHP_BUILD_PROGRAM
+    PHP_ADD_SOURCES(/main, internal_functions.c,,PHP_GLOBAL_OBJS)
+    PHP_ADD_SOURCES(win32, sendmail.c, -I$CFLAGS, PHP_GLOBAL_OBJS)
+    PHP4LIB_SHARED_LIBADD=\$\(EXTRA_LIBS\)
+    EXTENSION_DIR=sys:/php$MAJOR_VERSION/ext
+    PHP_SUBST(PHP4LIB_SHARED_LIBADD)
+    PHP_SHARED_MODULE(php4lib, PHP_GLOBAL_OBJS, netware)
+    ;;
 esac

 # Disable PIC mode by default where it is known to be safe to do so,
@@ -425,6 +445,12 @@ PHP_TM_GMTOFF
 PHP_STRUCT_FLOCK
 PHP_SOCKLEN_T

+AC_CHECK_SIZEOF(intmax_t, 0)
+AC_CHECK_SIZEOF(size_t, 8)
+AC_CHECK_SIZEOF(ssize_t, 8)
+AC_CHECK_SIZEOF(ptrdiff_t, 8)
+AC_CHECK_SIZEOF(long long, 8)
+AC_CHECK_SIZEOF(long long int, 8)
 AC_CHECK_SIZEOF(long, 8)
 AC_CHECK_SIZEOF(int, 4)

@@ -1065,10 +1091,20 @@ EXTRA_LDFLAGS_PROGRAM="$EXTRA_LDFLAGS_PROGRAM $PHP_LDFLAGS"

 PHP_BUILD_DATE=`date '+%Y-%m-%d'`
 AC_DEFINE_UNQUOTED(PHP_BUILD_DATE,"$PHP_BUILD_DATE",[PHP build date])
-PHP_UNAME=`uname -a | xargs`
-AC_DEFINE_UNQUOTED(PHP_UNAME,"$PHP_UNAME",[uname -a output])
-PHP_OS=`uname | xargs`
-AC_DEFINE_UNQUOTED(PHP_OS,"$PHP_OS",[uname output])
+case $host_alias in
+*netware*)
+    PHP_OS="NetWare"
+    PHP_UNAME="NetWare"
+    AC_DEFINE_UNQUOTED(PHP_OS,"$PHP_OS",[hardcode for each of the cross compiler host])
+    AC_DEFINE_UNQUOTED(PHP_UNAME,"$PHP_UNAME",[hardcode for each of the cross compiler host])
+    ;;
+*)
+    PHP_UNAME=`uname -a | xargs`
+    AC_DEFINE_UNQUOTED(PHP_UNAME,"$PHP_UNAME",[uname -a output])
+    PHP_OS=`uname | xargs`
+    AC_DEFINE_UNQUOTED(PHP_OS,"$PHP_OS",[uname output])
+    ;;
+esac

 if test "$disable_cli" != "1"; then
  PHP_CLI_TARGET="\$(SAPI_CLI_PATH)"
@@ -1226,7 +1262,15 @@ PHP_ADD_SOURCES(main, main.c snprintf.c spprintf.c php_sprintf.c \
       streams.c network.c php_open_temporary_file.c php_logos.c \
       output.c memory_streams.c user_streams.c)
 PHP_ADD_SOURCES(/main, internal_functions.c,, sapi)
-PHP_ADD_SOURCES(/main, internal_functions_cli.c,, cli)
+case $host_alias in
+*netware*)
+  PHP_ADD_BUILD_DIR(win32)
+  PHP_ADD_BUILD_DIR(netware)
+  ;;
+*)
+  PHP_ADD_SOURCES(/main, internal_functions_cli.c,, cli)
+  ;;
+esac

 PHP_ADD_SOURCES(/Zend, zend_language_parser.c zend_language_scanner.c \
    zend_ini_parser.c zend_ini_scanner.c)
@@ -1269,9 +1313,11 @@ AC_DEFINE([HAVE_BUILD_DEFS_H], 1, [ ])

 $php_shtool mkdir -p pear/scripts
 $php_shtool mkdir -p scripts
+$php_shtool mkdir -p scripts/man1

 ALL_OUTPUT_FILES="php4.spec main/build-defs.h \
-scripts/phpize scripts/php-config \
+scripts/phpize scripts/man1/phpize.1 \
+scripts/php-config scripts/man1/php-config.1 \
 $PHP_OUTPUT_FILES"

 AC_OUTPUT($ALL_OUTPUT_FILES, [], [
@@ -1,7 +1,5 @@
 #if PHP_WIN32
 #include "../../../../main/config.w32.h"
-#elif defined(NETWARE)
-#include "config.nw.h"
 #else
 #include <php_config.h>
 #endif
@@ -40,9 +40,6 @@
 #define PHP_BZ_ERRSTR  1
 #define PHP_BZ_ERRBOTH 2

-/* Blocksize of the decompression buffer */
-#define PHP_BZ_DECOMPRESS_SIZE 4096
-
 function_entry bz2_functions[] = {
 	PHP_FE(bzopen,       NULL)
 	PHP_FE(bzread,       NULL)
@@ -434,56 +431,53 @@ PHP_FUNCTION(bzcompress)
   Decompresses BZip2 compressed data */
 PHP_FUNCTION(bzdecompress)
 {
-	zval    **source,                             /* Source data to decompress */
-	        **zsmall;                             /* (Optional) user specified small */
-	char     *dest;                               /* Destination buffer, initially allocated */
-	int       error,                              /* Error container */
-	          iter = 1,                           /* Iteration count for the compression loop */
-			  size,                               /* Current size to realloc the dest buffer to */
-			  dest_len = PHP_BZ_DECOMPRESS_SIZE,  /* Size of the destination length */
-			  small    = 0,                       /* The actual small */
-			  argc     = ZEND_NUM_ARGS();         /* Argument count */
-	
-	if (argc < 1 || argc > 2 || zend_get_parameters_ex(argc, &source, &zsmall) == FAILURE) {
-		WRONG_PARAM_COUNT;
+	char *source, *dest;
+	int source_len, error;
+	long small = 0;
+#if defined(PHP_WIN32) && _MSC_VER < 1300
+	unsigned __int64 size = 0;
+#else	
+	unsigned long long size = 0;
+#endif	
+	bz_stream bzs;
+
+	if (FAILURE == zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "s|l", &source, &source_len, &small)) {
+		RETURN_FALSE;
 	}

-	convert_to_string_ex(source);
-	
-	/* optional small argument handling */
-	if (argc > 1) {
-		convert_to_long_ex(zsmall);
-		small = Z_LVAL_PP(zsmall);
+	bzs.bzalloc = NULL;
+	bzs.bzfree = NULL;
+
+	if (BZ2_bzDecompressInit(&bzs, 0, small) != BZ_OK) {
+		RETURN_FALSE;
 	}

-	/* Depending on the size of the source buffer, either allocate
-	  the length of the source buffer or the a default decompression
-	  size */
-	dest = emalloc(PHP_BZ_DECOMPRESS_SIZE > Z_STRLEN_PP(source) ? PHP_BZ_DECOMPRESS_SIZE : Z_STRLEN_PP(source));
+	bzs.next_in = source;
+	bzs.avail_in = source_len;

-	/* (de)Compression Loop */	
-	do {
-		/* Handle the (re)allocation of the buffer */
-		size = dest_len * iter;
-		if (iter > 1) {
-			dest = erealloc(dest, size);
-		}
-		++iter;
-
-		/* Perform the decompression */
-		error = BZ2_bzBuffToBuffDecompress(dest, &size, Z_STRVAL_PP(source), Z_STRLEN_PP(source), small, 0);
-	} while (error == BZ_OUTBUFF_FULL);
+	/* in most cases bz2 offers at least 2:1 compression, so we use that as our base */
+	bzs.avail_out = source_len * 2;
+	bzs.next_out = dest = emalloc(bzs.avail_out + 1);
 	
-	if (error != BZ_OK) {
-		efree(dest);
-		RETURN_LONG(error);
-	} else {
-		/* we might have allocated a little to much, so erealloc the buffer 
-		 down to size, before returning it */
+	while ((error = BZ2_bzDecompress(&bzs)) == BZ_OK && bzs.avail_in > 0) {
+		/* compression is better then 2:1, need to allocate more memory */
+		bzs.avail_out = source_len;
+		size = (bzs.total_out_hi32 * (unsigned int) -1) + bzs.total_out_lo32;
+		dest = erealloc(dest, size + bzs.avail_out + 1);
+		bzs.next_out = dest + size;
+	}
+
+	if (error == BZ_STREAM_END || error == BZ_OK) {
+		size = (bzs.total_out_hi32 * (unsigned int) -1) + bzs.total_out_lo32;
 		dest = erealloc(dest, size + 1);
-		dest[size] = 0;
-		RETURN_STRINGL(dest, size, 0);
+		dest[size] = '\0';
+		RETVAL_STRINGL(dest, size, 0);
+	} else { /* real error */
+		efree(dest);
+		RETVAL_LONG(error);
 	}
+
+	BZ2_bzDecompressEnd(&bzs);
 }
 /* }}} */

@@ -14,7 +14,7 @@
   +----------------------------------------------------------------------+
   | Authors: Shane Caraveo             <shane@caraveo.com>               | 
   |          Colin Viebrock            <colin@easydns.com>               |
-   |          Hartmut Holzgraefe        <hartmut@six.de>                  |
+   |          Hartmut Holzgraefe        <hholzgra@php.net>                |
   |          Wez Furlong               <wez@thebrainroom.com>            |
   +----------------------------------------------------------------------+
 */
@@ -34,7 +34,7 @@
 #include "sdncal.h"

 #include <stdio.h>
- 
+
 function_entry calendar_functions[] = {
 	PHP_FE(jdtogregorian, NULL)
 	PHP_FE(gregoriantojd, NULL)
@@ -48,10 +48,10 @@ function_entry calendar_functions[] = {
 	PHP_FE(jdmonthname, NULL)
 	PHP_FE(easter_date, NULL)
 	PHP_FE(easter_days, NULL)
-	PHP_FE(unixtojd,    NULL)
-	PHP_FE(jdtounix,    NULL)
-	PHP_FE(cal_to_jd,	NULL)
-	PHP_FE(cal_from_jd,	NULL)
+	PHP_FE(unixtojd, NULL)
+	PHP_FE(jdtounix, NULL)
+	PHP_FE(cal_to_jd, NULL)
+	PHP_FE(cal_from_jd, NULL)
 	PHP_FE(cal_days_in_month, NULL)
 	PHP_FE(cal_info, NULL)
 	{NULL, NULL, NULL}
@@ -60,8 +60,8 @@ function_entry calendar_functions[] = {

 zend_module_entry calendar_module_entry = {
 	STANDARD_MODULE_HEADER,
-	"calendar", 
-	calendar_functions, 
+	"calendar",
+	calendar_functions,
 	PHP_MINIT(calendar),
 	NULL,
 	NULL,
@@ -83,60 +83,76 @@ enum cal_name_type_t {
 	CAL_FRENCH,
 	CAL_NUM_CALS
 };
-typedef long int (*cal_to_jd_func_t)(int month, int day, int year);
-typedef void (*cal_from_jd_func_t)(long int jd, int* year, int* month, int* day);
-typedef char* (*cal_as_string_func_t)(int year, int month, int day);
+
+typedef long int (*cal_to_jd_func_t) (int month, int day, int year);
+typedef void (*cal_from_jd_func_t) (long int jd, int *year, int *month, int *day);
+typedef char *(*cal_as_string_func_t) (int year, int month, int day);

 struct cal_entry_t {
-	char 					*name;
-	char 					*symbol;
-	cal_to_jd_func_t		to_jd;
-	cal_from_jd_func_t		from_jd;
-	int 					num_months;
-	int 					max_days_in_month;
-	char					**month_name_short;
-	char					**month_name_long;
+	char *name;
+	char *symbol;
+	cal_to_jd_func_t to_jd;
+	cal_from_jd_func_t from_jd;
+	int num_months;
+	int max_days_in_month;
+	char **month_name_short;
+	char **month_name_long;
 };
+
 static struct cal_entry_t cal_conversion_table[CAL_NUM_CALS] = {
-	{ "Gregorian", "CAL_GREGORIAN", GregorianToSdn, SdnToGregorian, 12, 31, MonthNameShort, MonthNameLong },
-	{ "Julian", "CAL_JULIAN", JulianToSdn, SdnToJulian, 12, 31, MonthNameShort, MonthNameLong },
-	{ "Jewish", "CAL_JEWISH", JewishToSdn, SdnToJewish, 13, 30, JewishMonthName, JewishMonthName },
-	{ "French", "CAL_FRENCH", FrenchToSdn, SdnToFrench, 13, 30, FrenchMonthName, FrenchMonthName }
+	{"Gregorian", "CAL_GREGORIAN", GregorianToSdn, SdnToGregorian, 12, 31,
+	 MonthNameShort, MonthNameLong},
+	{"Julian", "CAL_JULIAN", JulianToSdn, SdnToJulian, 12, 31,
+	 MonthNameShort, MonthNameLong},
+	{"Jewish", "CAL_JEWISH", JewishToSdn, SdnToJewish, 13, 30,
+	 JewishMonthName, JewishMonthName},
+	{"French", "CAL_FRENCH", FrenchToSdn, SdnToFrench, 13, 30,
+	 FrenchMonthName, FrenchMonthName}
 };

 /* For jddayofweek */
-enum	{ CAL_DOW_DAYNO, CAL_DOW_SHORT, CAL_DOW_LONG };
+enum { CAL_DOW_DAYNO, CAL_DOW_SHORT, CAL_DOW_LONG };
+
 /* For jdmonthname */
-enum	{ CAL_MONTH_GREGORIAN_SHORT, CAL_MONTH_GREGORIAN_LONG,
+enum { CAL_MONTH_GREGORIAN_SHORT, CAL_MONTH_GREGORIAN_LONG,
 	CAL_MONTH_JULIAN_SHORT, CAL_MONTH_JULIAN_LONG, CAL_MONTH_JEWISH,
-	CAL_MONTH_FRENCH };
+	CAL_MONTH_FRENCH
+};

 /* for heb_number_to_chars */
 static char alef_bet[25] = "0àáâãäåæçèéëìîðñòôö÷øùú";
-	
+
+#define CAL_JEWISH_ADD_ALAFIM_GERESH 0x2
+#define CAL_JEWISH_ADD_ALAFIM 0x4
+#define CAL_JEWISH_ADD_GERESHAYIM 0x8
+
 PHP_MINIT_FUNCTION(calendar)
 {
-	REGISTER_LONG_CONSTANT("CAL_GREGORIAN", CAL_GREGORIAN, CONST_CS|CONST_PERSISTENT);
-	REGISTER_LONG_CONSTANT("CAL_JULIAN", CAL_JULIAN, CONST_CS|CONST_PERSISTENT);
-	REGISTER_LONG_CONSTANT("CAL_JEWISH", CAL_JEWISH, CONST_CS|CONST_PERSISTENT);
-	REGISTER_LONG_CONSTANT("CAL_FRENCH", CAL_FRENCH, CONST_CS|CONST_PERSISTENT);
-	REGISTER_LONG_CONSTANT("CAL_NUM_CALS", CAL_NUM_CALS, CONST_CS|CONST_PERSISTENT);
-	/* constants for jddayofweek */
-	REGISTER_LONG_CONSTANT("CAL_DOW_DAYNO", CAL_DOW_DAYNO, CONST_CS|CONST_PERSISTENT);
-	REGISTER_LONG_CONSTANT("CAL_DOW_SHORT", CAL_DOW_SHORT, CONST_CS|CONST_PERSISTENT);
-	REGISTER_LONG_CONSTANT("CAL_DOW_LONG",	CAL_DOW_LONG, CONST_CS|CONST_PERSISTENT);
-	/* constants for jdmonthname */
-	REGISTER_LONG_CONSTANT("CAL_MONTH_GREGORIAN_SHORT", CAL_MONTH_GREGORIAN_SHORT, CONST_CS|CONST_PERSISTENT);
-	REGISTER_LONG_CONSTANT("CAL_MONTH_GREGORIAN_LONG",	CAL_MONTH_GREGORIAN_LONG, CONST_CS|CONST_PERSISTENT);
-	REGISTER_LONG_CONSTANT("CAL_MONTH_JULIAN_SHORT",	CAL_MONTH_JULIAN_SHORT, CONST_CS|CONST_PERSISTENT);
-	REGISTER_LONG_CONSTANT("CAL_MONTH_JULIAN_LONG",		CAL_MONTH_JULIAN_LONG, CONST_CS|CONST_PERSISTENT);
-	REGISTER_LONG_CONSTANT("CAL_MONTH_JEWISH",			CAL_MONTH_JEWISH, CONST_CS|CONST_PERSISTENT);
-	REGISTER_LONG_CONSTANT("CAL_MONTH_FRENCH",			CAL_MONTH_FRENCH, CONST_CS|CONST_PERSISTENT);
-	/* constants for easter calculation */
-	REGISTER_LONG_CONSTANT("CAL_EASTER_DEFAULT",			CAL_EASTER_DEFAULT, CONST_CS | CONST_PERSISTENT);
-	REGISTER_LONG_CONSTANT("CAL_EASTER_ROMAN",				CAL_EASTER_ROMAN, CONST_CS | CONST_PERSISTENT);
-	REGISTER_LONG_CONSTANT("CAL_EASTER_ALWAYS_GREGORIAN",	CAL_EASTER_ALWAYS_GREGORIAN, CONST_CS | CONST_PERSISTENT);
-	REGISTER_LONG_CONSTANT("CAL_EASTER_ALWAYS_JULIAN",		CAL_EASTER_ALWAYS_JULIAN, CONST_CS | CONST_PERSISTENT);
+	REGISTER_LONG_CONSTANT("CAL_GREGORIAN", CAL_GREGORIAN, CONST_CS | CONST_PERSISTENT);
+	REGISTER_LONG_CONSTANT("CAL_JULIAN", CAL_JULIAN, CONST_CS | CONST_PERSISTENT);
+	REGISTER_LONG_CONSTANT("CAL_JEWISH", CAL_JEWISH, CONST_CS | CONST_PERSISTENT);
+	REGISTER_LONG_CONSTANT("CAL_FRENCH", CAL_FRENCH, CONST_CS | CONST_PERSISTENT);
+	REGISTER_LONG_CONSTANT("CAL_NUM_CALS", CAL_NUM_CALS, CONST_CS | CONST_PERSISTENT);
+/* constants for jddayofweek */
+	REGISTER_LONG_CONSTANT("CAL_DOW_DAYNO", CAL_DOW_DAYNO, CONST_CS | CONST_PERSISTENT);
+	REGISTER_LONG_CONSTANT("CAL_DOW_SHORT", CAL_DOW_SHORT, CONST_CS | CONST_PERSISTENT);
+	REGISTER_LONG_CONSTANT("CAL_DOW_LONG", CAL_DOW_LONG, CONST_CS | CONST_PERSISTENT);
+/* constants for jdmonthname */
+	REGISTER_LONG_CONSTANT("CAL_MONTH_GREGORIAN_SHORT", CAL_MONTH_GREGORIAN_SHORT, CONST_CS | CONST_PERSISTENT);
+	REGISTER_LONG_CONSTANT("CAL_MONTH_GREGORIAN_LONG", CAL_MONTH_GREGORIAN_LONG, CONST_CS | CONST_PERSISTENT);
+	REGISTER_LONG_CONSTANT("CAL_MONTH_JULIAN_SHORT", CAL_MONTH_JULIAN_SHORT, CONST_CS | CONST_PERSISTENT);
+	REGISTER_LONG_CONSTANT("CAL_MONTH_JULIAN_LONG", CAL_MONTH_JULIAN_LONG, CONST_CS | CONST_PERSISTENT);
+	REGISTER_LONG_CONSTANT("CAL_MONTH_JEWISH", CAL_MONTH_JEWISH, CONST_CS | CONST_PERSISTENT);
+	REGISTER_LONG_CONSTANT("CAL_MONTH_FRENCH", CAL_MONTH_FRENCH, CONST_CS | CONST_PERSISTENT);
+/* constants for easter calculation */
+	REGISTER_LONG_CONSTANT("CAL_EASTER_DEFAULT", CAL_EASTER_DEFAULT, CONST_CS | CONST_PERSISTENT);
+	REGISTER_LONG_CONSTANT("CAL_EASTER_ROMAN", CAL_EASTER_ROMAN, CONST_CS | CONST_PERSISTENT);
+	REGISTER_LONG_CONSTANT("CAL_EASTER_ALWAYS_GREGORIAN", CAL_EASTER_ALWAYS_GREGORIAN, CONST_CS | CONST_PERSISTENT);
+	REGISTER_LONG_CONSTANT("CAL_EASTER_ALWAYS_JULIAN", CAL_EASTER_ALWAYS_JULIAN, CONST_CS | CONST_PERSISTENT);
+/* constants for Jewish date formatting */
+	REGISTER_LONG_CONSTANT("CAL_JEWISH_ADD_ALAFIM_GERESH", CAL_JEWISH_ADD_ALAFIM_GERESH, CONST_CS | CONST_PERSISTENT);
+	REGISTER_LONG_CONSTANT("CAL_JEWISH_ADD_ALAFIM", CAL_JEWISH_ADD_ALAFIM, CONST_CS | CONST_PERSISTENT);
+	REGISTER_LONG_CONSTANT("CAL_JEWISH_ADD_GERESHAYIM", CAL_JEWISH_ADD_GERESHAYIM, CONST_CS | CONST_PERSISTENT);
 	return SUCCESS;
 }

@@ -147,42 +163,65 @@ PHP_MINFO_FUNCTION(calendar)
 	php_info_print_table_end();
 }

-/* {{{ proto array cal_info(int calendar)
-   Returns information about a particular calendar */
-PHP_FUNCTION(cal_info)
+static void _php_cal_info(int cal, zval **ret)
 {
-	zval ** cal;
-	zval * months, *smonths;
+	zval *months, *smonths;
 	int i;
-	struct cal_entry_t * calendar;
-	
-	if (ZEND_NUM_ARGS() != 1 || zend_get_parameters_ex(1, &cal) != SUCCESS) {
-		WRONG_PARAM_COUNT;
-	}
-	convert_to_long_ex(cal);
-	if (Z_LVAL_PP(cal) < 0 || Z_LVAL_PP(cal) >= CAL_NUM_CALS) {
-		zend_error(E_WARNING, "%s(): invalid calendar ID %ld", get_active_function_name(TSRMLS_C), Z_LVAL_PP(cal));
-		RETURN_FALSE;
-	}
+	struct cal_entry_t *calendar;

-	calendar = &cal_conversion_table[Z_LVAL_PP(cal)];
-	array_init(return_value);
+	calendar = &cal_conversion_table[cal];
+	array_init(*ret);

 	MAKE_STD_ZVAL(months);
 	MAKE_STD_ZVAL(smonths);
 	array_init(months);
 	array_init(smonths);
-	
-	for (i=1; i<= calendar->num_months; i++) {
+
+	for (i = 1; i <= calendar->num_months; i++) {
 		add_index_string(months, i, calendar->month_name_long[i], 1);
 		add_index_string(smonths, i, calendar->month_name_short[i], 1);
 	}
-	add_assoc_zval(return_value, "months", months);
-	add_assoc_zval(return_value, "abbrevmonths", smonths);
-	add_assoc_long(return_value, "maxdaysinmonth", calendar->max_days_in_month);
-	add_assoc_string(return_value, "calname", calendar->name, 1);
-	add_assoc_string(return_value, "calsymbol", calendar->symbol, 1);
+	add_assoc_zval(*ret, "months", months);
+	add_assoc_zval(*ret, "abbrevmonths", smonths);
+	add_assoc_long(*ret, "maxdaysinmonth", calendar->max_days_in_month);
+	add_assoc_string(*ret, "calname", calendar->name, 1);
+	add_assoc_string(*ret, "calsymbol", calendar->symbol, 1);
 	
+}
+
+/* {{{ proto array cal_info(int calendar)
+   Returns information about a particular calendar */
+PHP_FUNCTION(cal_info)
+{
+	long cal = -1;
+	
+
+	if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "|l", &cal) == FAILURE) {
+		RETURN_FALSE;
+	}
+
+	if (cal == -1) {
+		int i;
+		zval *val;
+
+		array_init(return_value);
+
+		for (i = 0; i < CAL_NUM_CALS; i++) {
+			MAKE_STD_ZVAL(val);
+			_php_cal_info(i, &val);
+			add_index_zval(return_value, i, val);
+		}
+		return;
+	}
+
+
+	if (cal != -1 && (cal < 0 || cal >= CAL_NUM_CALS)) {
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "invalid calendar ID %ld.", cal);
+		RETURN_FALSE;
+	}
+
+	_php_cal_info(cal, &return_value);
+
 }
 /* }}} */

@@ -190,34 +229,35 @@ PHP_FUNCTION(cal_info)
   Returns the number of days in a month for a given year and calendar */
 PHP_FUNCTION(cal_days_in_month)
 {
-	zval ** cal, **month, **year;
-	struct cal_entry_t * calendar;
+	long cal, month, year;
+	struct cal_entry_t *calendar;
 	long sdn_start, sdn_next;
-	
-	if (ZEND_NUM_ARGS() != 3 || zend_get_parameters_ex(3, &cal, &month, &year) != SUCCESS) {
-		WRONG_PARAM_COUNT;
-	}

-	convert_to_long_ex(cal);
-	convert_to_long_ex(month);
-	convert_to_long_ex(year);
-
-	if (Z_LVAL_PP(cal) < 0 || Z_LVAL_PP(cal) >= CAL_NUM_CALS) {
-		zend_error(E_WARNING, "%s(): invalid calendar ID %ld", get_active_function_name(TSRMLS_C), Z_LVAL_PP(cal));
+	if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "lll", &cal, &month, &year) == FAILURE) {
 		RETURN_FALSE;
 	}

-	calendar = &cal_conversion_table[Z_LVAL_PP(cal)];
-	
-	sdn_start = calendar->to_jd(Z_LVAL_PP(year), Z_LVAL_PP(month), 1);
-	
-	sdn_next = calendar->to_jd(Z_LVAL_PP(year), 1 + Z_LVAL_PP(month), 1);
-
-	if (sdn_next == 0)	{
-		/* if invalid, try first month of the next year... */
-		sdn_next = calendar->to_jd(Z_LVAL_PP(year) + 1, 1, 1);
+	if (cal < 0 || cal >= CAL_NUM_CALS) {
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "invalid calendar ID %ld.", cal);
+		RETURN_FALSE;
 	}
-	
+
+	calendar = &cal_conversion_table[cal];
+
+	sdn_start = calendar->to_jd(year, month, 1);
+
+	if (sdn_start == 0) {
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "invalid date.");
+		RETURN_FALSE;
+	}
+
+	sdn_next = calendar->to_jd(year, 1 + month, 1);
+
+	if (sdn_next == 0) {
+/* if invalid, try first month of the next year... */
+		sdn_next = calendar->to_jd(year + 1, 1, 1);
+	}
+
 	RETURN_LONG(sdn_next - sdn_start);
 }
 /* }}} */
@@ -226,26 +266,18 @@ PHP_FUNCTION(cal_days_in_month)
   Converts from a supported calendar to Julian Day Count */
 PHP_FUNCTION(cal_to_jd)
 {
-	zval ** cal, **month, **day, **year;
-	long jdate;
+	long cal, month, day, year;

-	if (ZEND_NUM_ARGS() != 4 || zend_get_parameters_ex(4, &cal, &month, &day, &year) != SUCCESS) {
-		WRONG_PARAM_COUNT;
-	}
-
-	convert_to_long_ex(cal);
-	convert_to_long_ex(month);
-	convert_to_long_ex(day);
-	convert_to_long_ex(year);
-
-	if (Z_LVAL_PP(cal) < 0 || Z_LVAL_PP(cal) >= CAL_NUM_CALS) {
-		zend_error(E_WARNING, "%s(): invalid calendar ID %ld", get_active_function_name(TSRMLS_C), Z_LVAL_PP(cal));
+	if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "llll", &cal, &month, &day, &year) != SUCCESS) {
 		RETURN_FALSE;
 	}

-	jdate = cal_conversion_table[Z_LVAL_PP(cal)].to_jd(
-			Z_LVAL_PP(year), Z_LVAL_PP(month), Z_LVAL_PP(day));
-	RETURN_LONG(jdate);
+	if (cal < 0 || cal >= CAL_NUM_CALS) {
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "invalid calendar ID %ld.", cal);
+		RETURN_FALSE;
+	}
+
+	RETURN_LONG(cal_conversion_table[cal].to_jd(year, month, day));
 }
 /* }}} */

@@ -253,42 +285,38 @@ PHP_FUNCTION(cal_to_jd)
   Converts from Julian Day Count to a supported calendar and return extended information */
 PHP_FUNCTION(cal_from_jd)
 {
-	zval ** jd, ** cal;
+	long jd, cal;
 	int month, day, year, dow;
 	char date[16];
-	struct cal_entry_t * calendar;
-	
-	if (ZEND_NUM_ARGS() != 2 || zend_get_parameters_ex(2, &jd, &cal) != SUCCESS) {
-		WRONG_PARAM_COUNT;
-	}
-	convert_to_long_ex(jd);
-	convert_to_long_ex(cal);
+	struct cal_entry_t *calendar;

-	if (Z_LVAL_PP(cal) < 0 || Z_LVAL_PP(cal) >= CAL_NUM_CALS) {
-		zend_error(E_WARNING, "%s(): invalid calendar ID %ld", get_active_function_name(TSRMLS_C), Z_LVAL_PP(cal));
+	if (zend_parse_parameters(ZEND_NUM_ARGS()TSRMLS_CC, "ll", &jd, &cal) == FAILURE) {
 		RETURN_FALSE;
 	}
-	calendar = &cal_conversion_table[Z_LVAL_PP(cal)];
+
+	if (cal < 0 || cal >= CAL_NUM_CALS) {
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "invalid calendar ID %ld", cal);
+		RETURN_FALSE;
+	}
+	calendar = &cal_conversion_table[cal];

 	array_init(return_value);

-	calendar->from_jd(
-			Z_LVAL_PP(jd),
-			&year, &month, &day);
+	calendar->from_jd(jd, &year, &month, &day);

 	sprintf(date, "%i/%i/%i", month, day, year);
 	add_assoc_string(return_value, "date", date, 1);
-	
+
 	add_assoc_long(return_value, "month", month);
 	add_assoc_long(return_value, "day", day);
 	add_assoc_long(return_value, "year", year);

-	/* day of week */
-	dow = DayOfWeek(Z_LVAL_PP(jd));
+/* day of week */
+	dow = DayOfWeek(jd);
 	add_assoc_long(return_value, "dow", dow);
 	add_assoc_string(return_value, "abbrevdayname", DayNameShort[dow], 1);
 	add_assoc_string(return_value, "dayname", DayNameLong[dow], 1);
-	/* month name */
+/* month name */
 	add_assoc_string(return_value, "abbrevmonth", calendar->month_name_short[month], 1);
 	add_assoc_string(return_value, "monthname", calendar->month_name_long[month], 1);
 }
@@ -298,16 +326,15 @@ PHP_FUNCTION(cal_from_jd)
   Converts a julian day count to a gregorian calendar date */
 PHP_FUNCTION(jdtogregorian)
 {
-	pval **julday;
+	long julday;
 	int year, month, day;
-	char date[10];
+	char date[16];

-	if (zend_get_parameters_ex(1, &julday) != SUCCESS) {
-		WRONG_PARAM_COUNT;
+	if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "l", &julday) == FAILURE) {
+		RETURN_FALSE;
 	}

-	convert_to_long_ex(julday);
-	SdnToGregorian(Z_LVAL_PP(julday), &year, &month, &day);
+	SdnToGregorian(julday, &year, &month, &day);
 	sprintf(date, "%i/%i/%i", month, day, year);

 	RETURN_STRING(date, 1);
@@ -318,37 +345,29 @@ PHP_FUNCTION(jdtogregorian)
   Converts a gregorian calendar date to julian day count */
 PHP_FUNCTION(gregoriantojd)
 {
-	pval **year, **month, **day;
-	int jdate;
+	long year, month, day;

-	if (zend_get_parameters_ex(3, &month, &day, &year) != SUCCESS) {
-		WRONG_PARAM_COUNT;
+	if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "lll", &month, &day, &year) == FAILURE) {
+		RETURN_FALSE;
 	}
-	
-	convert_to_long_ex(month);
-	convert_to_long_ex(day);
-	convert_to_long_ex(year);

-	jdate = GregorianToSdn(Z_LVAL_PP(year), Z_LVAL_PP(month), Z_LVAL_PP(day));
-
-	RETURN_LONG(jdate);
+	RETURN_LONG(GregorianToSdn(year, month, day));
 }
 /* }}} */

 /* {{{ proto string jdtojulian(int juliandaycount)
   Convert a julian day count to a julian calendar date */
-PHP_FUNCTION(jdtojulian) 
+PHP_FUNCTION(jdtojulian)
 {
-	pval **julday;
+	long julday;
 	int year, month, day;
-	char date[10];
+	char date[16];

-	if (zend_get_parameters_ex(1, &julday) != SUCCESS) {
-		WRONG_PARAM_COUNT;
+	if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "l", &julday) == FAILURE) {
+		RETURN_FALSE;
 	}

-	convert_to_long_ex(julday);
-	SdnToJulian(Z_LVAL_PP(julday), &year, &month, &day);
+	SdnToJulian(julday, &year, &month, &day);
 	sprintf(date, "%i/%i/%i", month, day, year);

 	RETURN_STRING(date, 1);
@@ -359,137 +378,146 @@ PHP_FUNCTION(jdtojulian)
   Converts a julian calendar date to julian day count */
 PHP_FUNCTION(juliantojd)
 {
-	pval **year, **month, **day;
-	int jdate;
+	long year, month, day;

-	if (zend_get_parameters_ex(3, &month, &day, &year) != SUCCESS) {
-		WRONG_PARAM_COUNT;
+	if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "lll", &month, &day, &year) == FAILURE) {
+		RETURN_FALSE;
 	}
-	
-	convert_to_long_ex(month);
-	convert_to_long_ex(day);
-	convert_to_long_ex(year);

-	jdate = JulianToSdn(Z_LVAL_PP(year), Z_LVAL_PP(month), Z_LVAL_PP(day));
-
-	RETURN_LONG(jdate);
+	RETURN_LONG(JulianToSdn(year, month, day));
 }
 /* }}} */

-/*	
-	caution: the hebrew format product non unique result.
-	for example both: year '5' and year '5000' product 'ä'.
-	use the numeric one for calculations. 
+/* {{{ heb_number_to_chars*/
+/*
+caution: the Hebrew format produces non unique result.
+for example both: year '5' and year '5000' produce 'ä'.
+use the numeric one for calculations. 
 */
-static char* heb_number_to_chars(int n, char **ret)
+static char *heb_number_to_chars(int n, int fl, char **ret)
 {
-	char *p, *old;
+	char *p, old[18], *endofalafim;

-	p = emalloc(10);
-	old = p;
-
-	/* 
-	   prevents the option breaking the jewish beliefs, and some other 
-	   critical resources ;)
-	   */
+	p = endofalafim = old;
+/* 
+   prevents the option breaking the jewish beliefs, and some other 
+   critical resources ;)
+ */
 	if (n > 9999 || n < 1) {
-		efree(old);
 		*ret = NULL;
 		return NULL;
 	}	

-	/* alafim case */
+/* alafim (thousands) case */
 	if (n / 1000) {
 		*p = alef_bet[n / 1000];
 		p++;
+
+		if (CAL_JEWISH_ADD_ALAFIM_GERESH & fl) {
+			*p = '\'';
+			p++;
+		}
+		if (CAL_JEWISH_ADD_ALAFIM & fl) {
+			strcpy(p, " àìôéí ");
+			p += 7;
+		}
+
+		endofalafim = p;
 		n = n % 1000;
 	}

-	/* taf-taf case */
+/* tav-tav (tav=400) case */
 	while (n >= 400) {
 		*p = alef_bet[22];
 		p++;
-		n-=400;
+		n -= 400;
 	}

-	/* meot case */
-	if (n >= 100) { 
-		*p = alef_bet[18+n/100];
+/* meot (hundreads) case */
+	if (n >= 100) {
+		*p = alef_bet[18 + n / 100];
 		p++;
 		n = n % 100;
 	}

-	/* tet-vav tet-zain case */
+/* tet-vav & tet-zain case (special case for 15 and 16) */
 	if (n == 15 || n == 16) {
 		*p = alef_bet[9];
 		p++;
-		*p = alef_bet[n-9];
+		*p = alef_bet[n - 9];
 		p++;
 	} else {
-		/* asarot case */
-		if (n >= 10) {       
-			*p = alef_bet[9+n/10];
+/* asarot (tens) case */
+		if (n >= 10) {
+			*p = alef_bet[9 + n / 10];
 			p++;
 			n = n % 10;
 		}

-		/* yeihot case */
+/* yehidot (ones) case */
 		if (n > 0) {
 			*p = alef_bet[n];
 			p++;
 		}
 	}

+	if (CAL_JEWISH_ADD_GERESHAYIM & fl) {
+		switch (p - endofalafim) {
+		case 0:
+			break;
+		case 1:
+			*p = '\'';
+			p++;
+			break;
+		default:
+			*(p) = *(p - 1);
+			*(p - 1) = '"';
+			p++;
+		}
+	}
+
 	*p = '\0';
 	*ret = estrndup(old, (p - old) + 1);
 	p = *ret;
-	efree(old);
 	return p;
 }
+/* }}} */

-/* {{{ proto string jdtojewish(int juliandaycount)
+/* {{{ proto string jdtojewish(int juliandaycount [, bool hebrew [, int fl]])
   Converts a julian day count to a jewish calendar date */
-PHP_FUNCTION(jdtojewish) 
+PHP_FUNCTION(jdtojewish)
 {
-	long julday, fl;
+	long julday, fl = 0;
+	zend_bool heb   = 0;
 	int year, month, day;
-	char date[10], hebdate[25];
+	char date[16], hebdate[25];
 	char *dayp, *yearp;
-	
-	if (ZEND_NUM_ARGS() == 1) {
-		if (zend_parse_parameters(1 TSRMLS_CC,"l", &julday) != SUCCESS) {
-			RETURN_FALSE;
-		}
-		fl=0;
-	} else if (ZEND_NUM_ARGS() == 2) {
-		if (zend_parse_parameters(2 TSRMLS_CC,"ll", &julday, &fl) != SUCCESS) {
-			RETURN_FALSE;
-		}
-	} else {
-		WRONG_PARAM_COUNT;
+
+	if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "l|bl", &julday, &heb, &fl) == FAILURE) {
+		RETURN_FALSE;
 	}
-	
-	
+
 	SdnToJewish(julday, &year, &month, &day);
-	if(!fl) {
+	if (!heb) {
 		sprintf(date, "%i/%i/%i", month, day, year);
 		RETURN_STRING(date, 1);
 	} else {
 		if (year <= 0 || year > 9999) {
-			php_error_docref(NULL TSRMLS_CC, E_WARNING, "Out of range year.");
+			php_error_docref(NULL TSRMLS_CC, E_WARNING, "Year out of range (0-9999).");
 			RETURN_FALSE;
 		}
-		
-		sprintf(hebdate, "%s %s %s", heb_number_to_chars(day, &dayp), JewishMonthHebName[month], heb_number_to_chars(year, &yearp));
-		
+
+		sprintf(hebdate, "%s %s %s", heb_number_to_chars(day, fl, &dayp), JewishMonthHebName[month], heb_number_to_chars(year, fl, &yearp));
+
 		if (dayp) {
 			efree(dayp);
 		}
 		if (yearp) {
-			efree(yearp);	
+			efree(yearp);
 		}
+
 		RETURN_STRING(hebdate, 1);
-		
+
 	}
 }
 /* }}} */
@@ -498,20 +526,13 @@ PHP_FUNCTION(jdtojewish)
   Converts a jewish calendar date to a julian day count */
 PHP_FUNCTION(jewishtojd)
 {
-	pval **year, **month, **day;
-	int jdate;
+	long year, month, day;

-	if (zend_get_parameters_ex(3, &month, &day, &year) != SUCCESS) {
-		WRONG_PARAM_COUNT;
+	if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "lll", &month, &day, &year) == FAILURE) {
+		RETURN_FALSE;
 	}

-	convert_to_long_ex(month);
-	convert_to_long_ex(day);
-	convert_to_long_ex(year);
-
-	jdate = JewishToSdn(Z_LVAL_PP(year), Z_LVAL_PP(month), Z_LVAL_PP(day));
-
-	RETURN_LONG(jdate);
+	RETURN_LONG(JewishToSdn(year, month, day));
 }
 /* }}} */

@@ -519,17 +540,15 @@ PHP_FUNCTION(jewishtojd)
   Converts a julian day count to a french republic calendar date */
 PHP_FUNCTION(jdtofrench)
 {
-	pval **julday;
+	long julday;
 	int year, month, day;
-	char date[10];
+	char date[16];

-	if (zend_get_parameters_ex(1, &julday) != SUCCESS) {
-		WRONG_PARAM_COUNT;
+	if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "l", &julday) == FAILURE) {
+		RETURN_FALSE;
 	}

-	convert_to_long_ex(julday);
-	
-	SdnToFrench(Z_LVAL_PP(julday), &year, &month, &day);
+	SdnToFrench(julday, &year, &month, &day);
 	sprintf(date, "%i/%i/%i", month, day, year);

 	RETURN_STRING(date, 1);
@@ -540,20 +559,13 @@ PHP_FUNCTION(jdtofrench)
   Converts a french republic calendar date to julian day count */
 PHP_FUNCTION(frenchtojd)
 {
-	pval **year, **month, **day;
-	int jdate;
+	long year, month, day;

-	if (zend_get_parameters_ex(3, &month, &day, &year) != SUCCESS) {
-		WRONG_PARAM_COUNT;
+	if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "lll", &month, &day, &year) == FAILURE) {
+		RETURN_FALSE;
 	}
-	
-	convert_to_long_ex(month);
-	convert_to_long_ex(day);
-	convert_to_long_ex(year);

-	jdate = FrenchToSdn(Z_LVAL_PP(year), Z_LVAL_PP(month), Z_LVAL_PP(day));
-
-	RETURN_LONG(jdate);
+	RETURN_LONG(FrenchToSdn(year, month, day));
 }
 /* }}} */

@@ -561,37 +573,30 @@ PHP_FUNCTION(frenchtojd)
   Returns name or number of day of week from julian day count */
 PHP_FUNCTION(jddayofweek)
 {
-	pval *julday, *mode;
+	long julday, mode = CAL_DOW_DAYNO;
 	int day;
 	char *daynamel, *daynames;
-	int myargc=ZEND_NUM_ARGS(), mymode=0;
-	
-	if ((myargc < 1) || (myargc > 2) || (zend_get_parameters(ht, myargc, &julday, &mode) != SUCCESS)) {
-		WRONG_PARAM_COUNT;
-	}
-	
-	convert_to_long(julday);
-	if(myargc==2) {
-	  convert_to_long(mode);
-	  mymode = Z_LVAL_P(mode);
-	} 

-	day = DayOfWeek(Z_LVAL_P(julday));
+	if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "l|l", &julday, &mode) == FAILURE) {
+		RETURN_FALSE;
+	}
+
+	day = DayOfWeek(julday);
 	daynamel = DayNameLong[day];
 	daynames = DayNameShort[day];

-		switch (mymode) {
-			case CAL_DOW_SHORT:
-				RETURN_STRING(daynamel, 1);
-				break;
-			case CAL_DOW_LONG:
-				RETURN_STRING(daynames, 1);
-				break;
-			case CAL_DOW_DAYNO:
-			default:
-				RETURN_LONG(day);
-				break;
-		}
+	switch (mode) {
+	case CAL_DOW_SHORT:
+		RETURN_STRING(daynamel, 1);
+		break;
+	case CAL_DOW_LONG:
+		RETURN_STRING(daynames, 1);
+		break;
+	case CAL_DOW_DAYNO:
+	default:
+		RETURN_LONG(day);
+		break;
+	}
 }
 /* }}} */

@@ -599,43 +604,40 @@ PHP_FUNCTION(jddayofweek)
   Returns name of month for julian day count */
 PHP_FUNCTION(jdmonthname)
 {
-	pval **julday, **mode;
+	long julday, mode;
 	char *monthname = NULL;
 	int month, day, year;

-	if (zend_get_parameters_ex(2, &julday, &mode) != SUCCESS) {
-		WRONG_PARAM_COUNT;
+	if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "ll", &julday, &mode) == FAILURE) {
+		RETURN_FALSE;
 	}

-	convert_to_long_ex(julday);
-	convert_to_long_ex(mode);
-
-	switch(Z_LVAL_PP(mode)) {
-		case CAL_MONTH_GREGORIAN_LONG:			/* gregorian or julian month */
-			SdnToGregorian(Z_LVAL_PP(julday), &year, &month, &day);
-			monthname = MonthNameLong[month];
-			break;
-		case CAL_MONTH_JULIAN_SHORT:			/* gregorian or julian month */
-			SdnToJulian(Z_LVAL_PP(julday), &year, &month, &day);
-			monthname = MonthNameShort[month];
-			break;
-		case CAL_MONTH_JULIAN_LONG:			/* gregorian or julian month */
-			SdnToJulian(Z_LVAL_PP(julday), &year, &month, &day);
-			monthname = MonthNameLong[month];
-			break;
-		case CAL_MONTH_JEWISH:			/* jewish month */
-			SdnToJewish(Z_LVAL_PP(julday), &year, &month, &day);
-			monthname = JewishMonthName[month];
-			break;
-		case CAL_MONTH_FRENCH:			/* french month */
-			SdnToFrench(Z_LVAL_PP(julday), &year, &month, &day);
-			monthname = FrenchMonthName[month];
-			break;
-		default:			/* default gregorian */
-		case CAL_MONTH_GREGORIAN_SHORT:			/* gregorian or julian month */
-			SdnToGregorian(Z_LVAL_PP(julday), &year, &month, &day);
-			monthname = MonthNameShort[month];
-			break;
+	switch (mode) {
+	case CAL_MONTH_GREGORIAN_LONG:	/* gregorian or julian month */
+		SdnToGregorian(julday, &year, &month, &day);
+		monthname = MonthNameLong[month];
+		break;
+	case CAL_MONTH_JULIAN_SHORT:	/* gregorian or julian month */
+		SdnToJulian(julday, &year, &month, &day);
+		monthname = MonthNameShort[month];
+		break;
+	case CAL_MONTH_JULIAN_LONG:	/* gregorian or julian month */
+		SdnToJulian(julday, &year, &month, &day);
+		monthname = MonthNameLong[month];
+		break;
+	case CAL_MONTH_JEWISH:		/* jewish month */
+		SdnToJewish(julday, &year, &month, &day);
+		monthname = JewishMonthName[month];
+		break;
+	case CAL_MONTH_FRENCH:		/* french month */
+		SdnToFrench(julday, &year, &month, &day);
+		monthname = FrenchMonthName[month];
+		break;
+	default:					/* default gregorian */
+	case CAL_MONTH_GREGORIAN_SHORT:	/* gregorian or julian month */
+		SdnToGregorian(julday, &year, &month, &day);
+		monthname = MonthNameShort[month];
+		break;
 	}

 	RETURN_STRING(monthname, 1);
@@ -29,6 +29,10 @@

 #include <packer.h>

+#ifndef STRINGSIZE
+#define STRINGSIZE 1024
+#endif
+
 extern char * FascistLook(PWDICT *pwp, char *instring);
 extern int PWClose(PWDICT *pwp);

@@ -92,34 +92,39 @@ PHP_MINFO_FUNCTION(ctype)
 /* {{{ ctype
 */
 #define CTYPE(iswhat) \
-	zval *c; \
+	zval *c, tmp; \
 	if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "z", &c) == FAILURE) \
 		return; \
- 	switch (Z_TYPE_P(c)) { \
-	case IS_LONG: \
+	if (Z_TYPE_P(c) == IS_LONG) { \
 		if (Z_LVAL_P(c) <= 255 && Z_LVAL_P(c) >= 0) { \
 			RETURN_BOOL(iswhat(Z_LVAL_P(c))); \
 		} else if (Z_LVAL_P(c) >= -128 && Z_LVAL_P(c) < 0) { \
 			RETURN_BOOL(iswhat(Z_LVAL_P(c) + 256)); \
 		} \
-		SEPARATE_ZVAL(&c);	\
-		convert_to_string(c);	\
-	case IS_STRING: \
-		{ \
-			char *p; \
-			int n, len; \
-			p=Z_STRVAL_P(c); \
-			len = Z_STRLEN_P(c); \
-			for(n=0;n<len;n++) { \
-				if(!iswhat((int)*(unsigned char *)(p++))) RETURN_FALSE; \
-			} \
-			RETURN_TRUE; \
-		} \
-	default: \
-		break; \
+		tmp = *c; \
+		zval_copy_ctor(&tmp); \
+		convert_to_string(&tmp); \
+	} else { \
+		tmp = *c; \
 	} \
-	RETURN_FALSE; 
- 
+	if (Z_TYPE(tmp) == IS_STRING) { \
+		char *p = Z_STRVAL(tmp), *e = Z_STRVAL(tmp) + Z_STRLEN(tmp); \
+		if (e == p) {	\
+			if (Z_TYPE_P(c) == IS_LONG) zval_dtor(&tmp); \
+			RETURN_FALSE;	\
+		}	\
+		while (p < e) { \
+			if(!iswhat((int)*(unsigned char *)(p++))) { \
+				if (Z_TYPE_P(c) == IS_LONG) zval_dtor(&tmp); \
+				RETURN_FALSE; \
+			} \
+		} \
+		if (Z_TYPE_P(c) == IS_LONG) zval_dtor(&tmp); \
+		RETURN_TRUE; \
+	} else { \
+		RETURN_FALSE; \
+	} \
+
 /* }}} */

 /* {{{ proto bool ctype_alnum(mixed c)
@@ -0,0 +1,11 @@
+--TEST--
+Bug #34645 (ctype corrupts memory when validating large numbers)
+--FILE--
+<?php
+$id = 394829384;
+var_dump(ctype_digit($id));
+var_dump($id);
+?>
+--EXPECT--
+bool(true)
+int(394829384)
@@ -66,7 +66,7 @@ static void _php_curl_close(zend_rsrc_list_entry *rsrc TSRMLS_DC);
 #define CAAZ(s, v) add_assoc_zval_ex(return_value, s, sizeof(s), (zval *) v);

 #define PHP_CURL_CHECK_OPEN_BASEDIR(str, len)													\
-	if (PG(open_basedir) && *PG(open_basedir) &&                                                \
+	if (((PG(open_basedir) && *PG(open_basedir)) || PG(safe_mode)) &&                                                \
 	    strncasecmp(str, "file://", sizeof("file://") - 1) == 0)								\
 	{ 																							\
 		php_url *tmp_url; 																		\
@@ -76,7 +76,7 @@ static void _php_curl_close(zend_rsrc_list_entry *rsrc TSRMLS_DC);
 			RETURN_FALSE; 																		\
 		} 																						\
 																								\
-		if (php_check_open_basedir(tmp_url->path TSRMLS_CC) || 									\
+		if (tmp_url->query || php_check_open_basedir(tmp_url->path TSRMLS_CC) || 									\
 			(PG(safe_mode) && !php_checkuid(tmp_url->path, "rb+", CHECKUID_CHECK_MODE_PARAM))	\
 		) { 																					\
 			php_url_free(tmp_url); 																\
@@ -436,10 +436,12 @@ static size_t curl_write(char *data, size_t size, size_t nmemb, void *ctx)
 		zend_list_addref(ch->id);
 		ZVAL_STRINGL(argv[1], data, length, 1);

+		ch->in_callback = 1;
 		error = call_user_function(EG(function_table),
 		                           NULL,
 		                           t->func,
 		                           retval, 2, argv TSRMLS_CC);
+		ch->in_callback = 0;
 		if (error == FAILURE) {
 			php_error(E_WARNING, "%s(): Couldn't call the CURLOPT_WRITEFUNCTION", 
 					  get_active_function_name(TSRMLS_C));
@@ -495,10 +497,12 @@ static size_t curl_read(char *data, size_t size, size_t nmemb, void *ctx)
 		zend_list_addref(t->fd);
 		ZVAL_LONG(argv[2], (int) size * nmemb);

+		ch->in_callback = 1;
 		error = call_user_function(EG(function_table),
 		                           NULL,
 		                           t->func,
 		                           retval, 3, argv TSRMLS_CC);
+		ch->in_callback = 0;
 		if (error == FAILURE) {
 			php_error(E_WARNING, "%s(): Cannot call the CURLOPT_READFUNCTION", 
 					  get_active_function_name(TSRMLS_C));
@@ -553,10 +557,12 @@ static size_t curl_write_header(char *data, size_t size, size_t nmemb, void *ctx
 			zend_list_addref(ch->id);
 			ZVAL_STRINGL(argv[1], data, length, 1);

+			ch->in_callback = 1;
 			error = call_user_function(EG(function_table),
 									   NULL,
 									   t->func,
 									   retval, 2, argv TSRMLS_CC);
+			ch->in_callback = 0;
 			if (error == FAILURE) {
 				php_error(E_WARNING, "%s(): Couldn't call the CURLOPT_HEADERFUNCTION", 
 						  get_active_function_name(TSRMLS_C));
@@ -606,10 +612,12 @@ static size_t curl_passwd(void *ctx, char *prompt, char *buf, int buflen)
 	ZVAL_STRING(argv[1], prompt, 1);
 	ZVAL_LONG(argv[2], buflen);

+	ch->in_callback = 1;
 	error = call_user_function(EG(function_table),
 	                           NULL,
 	                           func,
 	                           retval, 2, argv TSRMLS_CC);
+	ch->in_callback = 0;
 	if (error == FAILURE) {
 		php_error(E_WARNING, "%s(): Couldn't call the CURLOPT_PASSWDFUNCTION", get_active_function_name(TSRMLS_C));
 	} else if (Z_TYPE_P(retval) == IS_STRING) {
@@ -680,7 +688,9 @@ static void alloc_curl_handle(php_curl **ch)
 	(*ch)->handlers->write_header = ecalloc(1, sizeof(php_curl_write));
 	(*ch)->handlers->read  = ecalloc(1, sizeof(php_curl_read));
 	memset(&(*ch)->err, 0, sizeof((*ch)->err));
-	
+
+	(*ch)->in_callback = 0;
+
 	zend_llist_init(&(*ch)->to_free.str, sizeof(char *), 
 	                (void(*)(void *)) curl_free_string, 0);
 	zend_llist_init(&(*ch)->to_free.slist, sizeof(struct curl_slist),
@@ -982,10 +992,15 @@ PHP_FUNCTION(curl_setopt)
 				
 					postval = Z_STRVAL_PP(current);
 					if (*postval == '@') {
+						++postval;
+						/* safe_mode / open_basedir check */
+						if (php_check_open_basedir(postval TSRMLS_CC) || (PG(safe_mode) && !php_checkuid(postval, "rb+", CHECKUID_CHECK_MODE_PARAM))) {
+							RETURN_FALSE;
+						}
 						error = curl_formadd(&first, &last, 
 											 CURLFORM_COPYNAME, string_key,
 											 CURLFORM_NAMELENGTH, (long)string_key_len - 1,
-											 CURLFORM_FILE, ++postval, 
+											 CURLFORM_FILE, postval, 
 											 CURLFORM_END);
 					}
 					else {
@@ -1337,7 +1352,11 @@ PHP_FUNCTION(curl_close)
 		WRONG_PARAM_COUNT;
 	}
 	ZEND_FETCH_RESOURCE(ch, php_curl *, zid, -1, le_curl_name, le_curl);
-	
+
+	if (ch->in_callback) {
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "Attempt to close CURL handle from a callback");
+		return;
+	}
 	zend_list_delete(Z_LVAL_PP(zid));
 }
 /* }}} */
@@ -93,6 +93,7 @@ typedef struct {
 	struct _php_curl_free    to_free;
 	long                     id;
 	unsigned int             uses;
+	zend_bool                in_callback;
 } php_curl;

 /* streams support */
@@ -223,7 +223,7 @@ AC_ARG_WITH(db4,
        break
      fi
    done
-    PHP_DBA_DB_CHECK(4, db-4.2 db-4.1 db-4.0 db-4 db4 db, [(void)db_create((DB**)0, (DB_ENV*)0, 0)])
+    PHP_DBA_DB_CHECK(4, db-4.3 db-4.2 db-4.1 db-4.0 db-4 db4 db, [(void)db_create((DB**)0, (DB_ENV*)0, 0)])
  fi
 ])
 AC_DBA_STD_RESULT(db4,Berkeley DB4)
@@ -118,33 +118,33 @@ static PHP_MSHUTDOWN_FUNCTION(dbase)
   Opens a dBase-format database file */
 PHP_FUNCTION(dbase_open)
 {
-	pval *dbf_name, *options;
+	zval **dbf_name, **options;
 	dbhead_t *dbh;
 	int handle;
 	DBase_TLS_VARS;

-	if (ZEND_NUM_ARGS() != 2 || getParameters(ht, 2, &dbf_name, &options)==FAILURE) {
+	if (ZEND_NUM_ARGS() != 2 || zend_get_parameters_ex(2, &dbf_name, &options) == FAILURE) {
 		WRONG_PARAM_COUNT;
 	}
-	convert_to_string(dbf_name);
-	convert_to_long(options);
+	convert_to_string_ex(dbf_name);
+	convert_to_long_ex(options);

-	if (Z_LVAL_P(options) == 1) {
-		php_error(E_WARNING, "Cannot open %s in write-only mode", Z_STRVAL_P(dbf_name));
-		RETURN_FALSE;
-	}
-	
-	if (PG(safe_mode) && (!php_checkuid(Z_STRVAL_P(dbf_name), NULL, CHECKUID_CHECK_FILE_AND_DIR))) {
-		RETURN_FALSE;
-	}
-	
-	if (php_check_open_basedir(Z_STRVAL_P(dbf_name) TSRMLS_CC)) {
+	if (Z_LVAL_PP(options) == 1) {
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "Cannot open %s in write-only mode", Z_STRVAL_PP(dbf_name));
 		RETURN_FALSE;
 	}

-	dbh = dbf_open(Z_STRVAL_P(dbf_name), Z_LVAL_P(options) TSRMLS_CC);
+	if (PG(safe_mode) && (!php_checkuid(Z_STRVAL_PP(dbf_name), NULL, CHECKUID_CHECK_FILE_AND_DIR))) {
+		RETURN_FALSE;
+	}
+	
+	if (php_check_open_basedir(Z_STRVAL_PP(dbf_name) TSRMLS_CC)) {
+		RETURN_FALSE;
+	}
+
+	dbh = dbf_open(Z_STRVAL_PP(dbf_name), Z_LVAL_PP(options) TSRMLS_CC);
 	if (dbh == NULL) {
-		php_error(E_WARNING, "unable to open database %s", Z_STRVAL_P(dbf_name));
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "unable to open database %s", Z_STRVAL_PP(dbf_name));
 		RETURN_FALSE;
 	}

@@ -157,22 +157,22 @@ PHP_FUNCTION(dbase_open)
   Closes an open dBase-format database file */
 PHP_FUNCTION(dbase_close)
 {
-	pval *dbh_id;
+	zval **dbh_id;
 	dbhead_t *dbh;
 	int dbh_type;
 	DBase_TLS_VARS;

-	if (ZEND_NUM_ARGS() != 1 || getParameters(ht, 1, &dbh_id)==FAILURE) {
+	if (ZEND_NUM_ARGS() != 1 || (zend_get_parameters_ex(1, &dbh_id) == FAILURE)) {
 		WRONG_PARAM_COUNT;
 	}
-	convert_to_long(dbh_id);
-	dbh = zend_list_find(Z_LVAL_P(dbh_id), &dbh_type);
+	convert_to_long_ex(dbh_id);
+	dbh = zend_list_find(Z_LVAL_PP(dbh_id), &dbh_type);
 	if (!dbh || dbh_type != DBase_GLOBAL(le_dbhead)) {
-		php_error(E_WARNING, "Unable to find database for identifier %d", Z_LVAL_P(dbh_id));
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "Unable to find database for identifier %ld", Z_LVAL_PP(dbh_id));
 		RETURN_FALSE;
 	}

-	zend_list_delete(Z_LVAL_P(dbh_id));
+	zend_list_delete(Z_LVAL_PP(dbh_id));
 	RETURN_TRUE;
 }
 /* }}} */
@@ -181,18 +181,18 @@ PHP_FUNCTION(dbase_close)
   Returns the number of records in the database */
 PHP_FUNCTION(dbase_numrecords)
 {
-	pval *dbh_id;
+	zval **dbh_id;
 	dbhead_t *dbh;
 	int dbh_type;
 	DBase_TLS_VARS;

-	if (ZEND_NUM_ARGS() != 1 || getParameters(ht, 1, &dbh_id)==FAILURE) {
+	if (ZEND_NUM_ARGS() != 1 || (zend_get_parameters_ex(1, &dbh_id) == FAILURE)) {
 		WRONG_PARAM_COUNT;
 	}
-	convert_to_long(dbh_id);
-	dbh = zend_list_find(Z_LVAL_P(dbh_id), &dbh_type);
+	convert_to_long_ex(dbh_id);
+	dbh = zend_list_find(Z_LVAL_PP(dbh_id), &dbh_type);
 	if (!dbh || dbh_type != DBase_GLOBAL(le_dbhead)) {
-		php_error(E_WARNING, "Unable to find database for identifier %d", Z_LVAL_P(dbh_id));
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "Unable to find database for identifier %ld", Z_LVAL_PP(dbh_id));
 		RETURN_FALSE;
 	}

@@ -204,18 +204,18 @@ PHP_FUNCTION(dbase_numrecords)
   Returns the number of fields (columns) in the database */
 PHP_FUNCTION(dbase_numfields)
 {
-	pval *dbh_id;
+	zval **dbh_id;
 	dbhead_t *dbh;
 	int dbh_type;
 	DBase_TLS_VARS;

-	if (ZEND_NUM_ARGS() != 1 || getParameters(ht, 1, &dbh_id)==FAILURE) {
+	if (ZEND_NUM_ARGS() != 1 || zend_get_parameters_ex(1, &dbh_id) == FAILURE) {
 		WRONG_PARAM_COUNT;
 	}
-	convert_to_long(dbh_id);
-	dbh = zend_list_find(Z_LVAL_P(dbh_id), &dbh_type);
+	convert_to_long_ex(dbh_id);
+	dbh = zend_list_find(Z_LVAL_PP(dbh_id), &dbh_type);
 	if (!dbh || dbh_type != DBase_GLOBAL(le_dbhead)) {
-		php_error(E_WARNING, "Unable to find database for identifier %d", Z_LVAL_P(dbh_id));
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "Unable to find database for identifier %ld", Z_LVAL_PP(dbh_id));
 		RETURN_FALSE;
 	}

@@ -227,18 +227,18 @@ PHP_FUNCTION(dbase_numfields)
   Packs the database (deletes records marked for deletion) */
 PHP_FUNCTION(dbase_pack)
 {
-	pval *dbh_id;
+	zval **dbh_id;
 	dbhead_t *dbh;
 	int dbh_type;
 	DBase_TLS_VARS;

-	if (ZEND_NUM_ARGS() != 1 || getParameters(ht, 1, &dbh_id)==FAILURE) {
+	if (ZEND_NUM_ARGS() != 1 || zend_get_parameters_ex(1, &dbh_id) == FAILURE) {
 		WRONG_PARAM_COUNT;
 	}
-	convert_to_long(dbh_id);
-	dbh = zend_list_find(Z_LVAL_P(dbh_id), &dbh_type);
+	convert_to_long_ex(dbh_id);
+	dbh = zend_list_find(Z_LVAL_PP(dbh_id), &dbh_type);
 	if (!dbh || dbh_type != DBase_GLOBAL(le_dbhead)) {
-		php_error(E_WARNING, "Unable to find database for identifier %d", Z_LVAL_P(dbh_id));
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "Unable to find database for identifier %ld", Z_LVAL_PP(dbh_id));
 		RETURN_FALSE;
 	}

@@ -252,7 +252,7 @@ PHP_FUNCTION(dbase_pack)
   Adds a record to the database */
 PHP_FUNCTION(dbase_add_record)
 {
-	pval *dbh_id, *fields, **field;
+	zval **dbh_id, **fields, **field;
 	dbhead_t *dbh;
 	int dbh_type;

@@ -262,40 +262,36 @@ PHP_FUNCTION(dbase_add_record)
 	int i;
 	DBase_TLS_VARS;

-	if (ZEND_NUM_ARGS() != 2 || getParameters(ht, 2, &dbh_id, &fields)==FAILURE) {
+	if (ZEND_NUM_ARGS() != 2 || zend_get_parameters_ex(2, &dbh_id, &fields) == FAILURE) {
 		WRONG_PARAM_COUNT;
 	}
-	convert_to_long(dbh_id);
-	if (Z_TYPE_P(fields) != IS_ARRAY) {
-		php_error(E_WARNING, "Expected array as second parameter");
+	convert_to_long_ex(dbh_id);
+	if (Z_TYPE_PP(fields) != IS_ARRAY) {
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "Expected array as second parameter");
 		RETURN_FALSE;
 	}

-	dbh = zend_list_find(Z_LVAL_P(dbh_id), &dbh_type);
+	dbh = zend_list_find(Z_LVAL_PP(dbh_id), &dbh_type);
 	if (!dbh || dbh_type != DBase_GLOBAL(le_dbhead)) {
-		php_error(E_WARNING, "Unable to find database for identifier %d", Z_LVAL_P(dbh_id));
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "Unable to find database for identifier %ld", Z_LVAL_PP(dbh_id));
 		RETURN_FALSE;
 	}

-	num_fields = zend_hash_num_elements(Z_ARRVAL_P(fields));
+	num_fields = zend_hash_num_elements(Z_ARRVAL_PP(fields));

 	if (num_fields != dbh->db_nfields) {
-		php_error(E_WARNING, "Wrong number of fields specified");
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "Wrong number of fields specified");
 		RETURN_FALSE;
 	}

 	cp = t_cp = (char *)emalloc(dbh->db_rlen + 1);
-	if (!cp) {
-		php_error(E_WARNING, "unable to allocate memory");
-		RETURN_FALSE;
-	}
 	*t_cp++ = VALID_RECORD;

 	dbf = dbh->db_fields;
 	for (i = 0, cur_f = dbf; cur_f < &dbf[num_fields]; i++, cur_f++) {
 		zval tmp;
-		if (zend_hash_index_find(Z_ARRVAL_P(fields), i, (void **)&field) == FAILURE) {
-			php_error(E_WARNING, "unexpected error");
+		if (zend_hash_index_find(Z_ARRVAL_PP(fields), i, (void **)&field) == FAILURE) {
+			php_error_docref(NULL TSRMLS_CC, E_WARNING, "unexpected error");
 			efree(cp);
 			RETURN_FALSE;
 		}
@@ -310,7 +306,7 @@ PHP_FUNCTION(dbase_add_record)

 	dbh->db_records++;
 	if (put_dbf_record(dbh, dbh->db_records, cp) < 0) {
-		php_error(E_WARNING, "unable to put record at %ld", dbh->db_records);
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "unable to put record at %ld", dbh->db_records);
 		efree(cp);
 		RETURN_FALSE;
 	}
@@ -326,7 +322,7 @@ PHP_FUNCTION(dbase_add_record)
   Replaces a record to the database */
 PHP_FUNCTION(dbase_replace_record)
 {
-	pval *dbh_id, *fields, **field, *recnum;
+	zval **dbh_id, **fields, **field, **recnum;
 	dbhead_t *dbh;
 	int dbh_type;

@@ -336,40 +332,36 @@ PHP_FUNCTION(dbase_replace_record)
 	int i;
 	DBase_TLS_VARS;

-	if (ZEND_NUM_ARGS() != 3 || getParameters(ht, 3, &dbh_id, &fields, &recnum)==FAILURE) {
+	if (ZEND_NUM_ARGS() != 3 || zend_get_parameters_ex(3, &dbh_id, &fields, &recnum) == FAILURE) {
 		WRONG_PARAM_COUNT;
 	}
-	convert_to_long(dbh_id);
-	convert_to_long(recnum);
-	if (Z_TYPE_P(fields) != IS_ARRAY) {
-		php_error(E_WARNING, "Expected array as second parameter");
+	convert_to_long_ex(dbh_id);
+	convert_to_long_ex(recnum);
+	if (Z_TYPE_PP(fields) != IS_ARRAY) {
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "Expected array as second parameter");
 		RETURN_FALSE;
 	}

-	dbh = zend_list_find(Z_LVAL_P(dbh_id), &dbh_type);
+	dbh = zend_list_find(Z_LVAL_PP(dbh_id), &dbh_type);
 	if (!dbh || dbh_type != DBase_GLOBAL(le_dbhead)) {
-		php_error(E_WARNING, "Unable to find database for identifier %d", Z_LVAL_P(dbh_id));
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "Unable to find database for identifier %ld", Z_LVAL_PP(dbh_id));
 		RETURN_FALSE;
 	}

-	num_fields = zend_hash_num_elements(Z_ARRVAL_P(fields));
+	num_fields = zend_hash_num_elements(Z_ARRVAL_PP(fields));

 	if (num_fields != dbh->db_nfields) {
-		php_error(E_WARNING, "Wrong number of fields specified");
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "Wrong number of fields specified");
 		RETURN_FALSE;
 	}

 	cp = t_cp = (char *)emalloc(dbh->db_rlen + 1);
-	if (!cp) {
-		php_error(E_WARNING, "unable to allocate memory");
-		RETURN_FALSE;
-	}
 	*t_cp++ = VALID_RECORD;

 	dbf = dbh->db_fields;
 	for (i = 0, cur_f = dbf; cur_f < &dbf[num_fields]; i++, cur_f++) {
-		if (zend_hash_index_find(Z_ARRVAL_P(fields), i, (void **)&field) == FAILURE) {
-			php_error(E_WARNING, "unexpected error");
+		if (zend_hash_index_find(Z_ARRVAL_PP(fields), i, (void **)&field) == FAILURE) {
+			php_error_docref(NULL TSRMLS_CC, E_WARNING, "unexpected error");
 			efree(cp);
 			RETURN_FALSE;
 		}
@@ -378,8 +370,8 @@ PHP_FUNCTION(dbase_replace_record)
 		t_cp += cur_f->db_flen;
 	}

-	if (put_dbf_record(dbh, Z_LVAL_P(recnum), cp) < 0) {
-		php_error(E_WARNING, "unable to put record at %ld", dbh->db_records);
+	if (put_dbf_record(dbh, Z_LVAL_PP(recnum), cp) < 0) {
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "unable to put record at %ld", dbh->db_records);
 		efree(cp);
 		RETURN_FALSE;
 	}
@@ -395,28 +387,28 @@ PHP_FUNCTION(dbase_replace_record)
   Marks a record to be deleted */
 PHP_FUNCTION(dbase_delete_record)
 {
-	pval *dbh_id, *record;
+	zval **dbh_id, **record;
 	dbhead_t *dbh;
 	int dbh_type;
 	DBase_TLS_VARS;

-	if (ZEND_NUM_ARGS() != 2 || getParameters(ht, 2, &dbh_id, &record)==FAILURE) {
+	if (ZEND_NUM_ARGS() != 2 || (zend_get_parameters_ex(2, &dbh_id, &record) == FAILURE)) {
 		WRONG_PARAM_COUNT;
 	}
-	convert_to_long(dbh_id);
-	convert_to_long(record);
+	convert_to_long_ex(dbh_id);
+	convert_to_long_ex(record);

-	dbh = zend_list_find(Z_LVAL_P(dbh_id), &dbh_type);
+	dbh = zend_list_find(Z_LVAL_PP(dbh_id), &dbh_type);
 	if (!dbh || dbh_type != DBase_GLOBAL(le_dbhead)) {
-		php_error(E_WARNING, "Unable to find database for identifier %d", Z_LVAL_P(dbh_id));
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "Unable to find database for identifier %ld", Z_LVAL_PP(dbh_id));
 		RETURN_FALSE;
 	}

-	if (del_dbf_record(dbh, Z_LVAL_P(record)) < 0) {
-		if (Z_LVAL_P(record) > dbh->db_records) {
-			php_error(E_WARNING, "record %d out of bounds", Z_LVAL_P(record));
+	if (del_dbf_record(dbh, Z_LVAL_PP(record)) < 0) {
+		if (Z_LVAL_PP(record) > dbh->db_records) {
+			php_error_docref(NULL TSRMLS_CC, E_WARNING, "record %ld out of bounds", Z_LVAL_PP(record));
 		} else {
-			php_error(E_WARNING, "unable to delete record %d", Z_LVAL_P(record));
+			php_error_docref(NULL TSRMLS_CC, E_WARNING, "unable to delete record %ld", Z_LVAL_PP(record));
 		}
 		RETURN_FALSE;
 	}
@@ -430,7 +422,7 @@ PHP_FUNCTION(dbase_delete_record)
 */  
 static void php_dbase_get_record(INTERNAL_FUNCTION_PARAMETERS, int assoc)
 {
-	pval *dbh_id, *record;
+	zval **dbh_id, **record;
 	dbhead_t *dbh;
 	int dbh_type;
 	dbfield_t *dbf, *cur_f;
@@ -440,28 +432,26 @@ static void php_dbase_get_record(INTERNAL_FUNCTION_PARAMETERS, int assoc)
 	int errno_save;
 	DBase_TLS_VARS;

-	if (ZEND_NUM_ARGS() != 2 || getParameters(ht, 2, &dbh_id, &record)==FAILURE) {
+	if (ZEND_NUM_ARGS() != 2 || (zend_get_parameters_ex(2, &dbh_id, &record) == FAILURE)) {
 		WRONG_PARAM_COUNT;
 	}
-	convert_to_long(dbh_id);
-	convert_to_long(record);
+	convert_to_long_ex(dbh_id);
+	convert_to_long_ex(record);

-	dbh = zend_list_find(Z_LVAL_P(dbh_id), &dbh_type);
+	dbh = zend_list_find(Z_LVAL_PP(dbh_id), &dbh_type);
 	if (!dbh || dbh_type != DBase_GLOBAL(le_dbhead)) {
-		php_error(E_WARNING, "Unable to find database for identifier %d", Z_LVAL_P(dbh_id));
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "Unable to find database for identifier %ld", Z_LVAL_PP(dbh_id));
 		RETURN_FALSE;
 	}

-	if ((data = get_dbf_record(dbh, Z_LVAL_P(record))) == NULL) {
-		php_error(E_WARNING, "Tried to read bad record %d", Z_LVAL_P(record));
+	if ((data = get_dbf_record(dbh, Z_LVAL_PP(record))) == NULL) {
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "Tried to read bad record %ld", Z_LVAL_PP(record));
 		RETURN_FALSE;
 	}

 	dbf = dbh->db_fields;

-	if (array_init(return_value) == FAILURE) {
-		RETURN_FALSE;
-	}
+	array_init(return_value);

 	fnp = NULL;
 	for (cur_f = dbf; cur_f < &dbf[dbh->db_nfields]; cur_f++) {
@@ -582,7 +572,7 @@ PHP_FUNCTION(dbase_get_record_with_names)
   Creates a new dBase-format database file */
 PHP_FUNCTION(dbase_create)
 {
-	pval *filename, *fields, **field, **value;
+	zval **filename, **fields, **field, **value;
 	int fd;
 	dbhead_t *dbh;

@@ -591,37 +581,37 @@ PHP_FUNCTION(dbase_create)
 	int i, rlen, handle;
 	DBase_TLS_VARS;

-	if (ZEND_NUM_ARGS() != 2 || getParameters(ht, 2, &filename, &fields)==FAILURE) {
+	if (ZEND_NUM_ARGS() != 2 || (zend_get_parameters_ex(2, &filename, &fields) == FAILURE)) {
 		WRONG_PARAM_COUNT;
 	}
-	convert_to_string(filename);
+	convert_to_string_ex(filename);

-	if (Z_TYPE_P(fields) != IS_ARRAY) {
-		php_error(E_WARNING, "Expected array as second parameter");
+	if (Z_TYPE_PP(fields) != IS_ARRAY) {
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "Expected array as second parameter");
 		RETURN_FALSE;
 	}

-	if (PG(safe_mode) && (!php_checkuid(Z_STRVAL_P(filename), NULL, CHECKUID_CHECK_FILE_AND_DIR))) {
+	if (PG(safe_mode) && (!php_checkuid(Z_STRVAL_PP(filename), NULL, CHECKUID_CHECK_FILE_AND_DIR))) {
 		RETURN_FALSE;
 	}
 	
-	if (php_check_open_basedir(Z_STRVAL_P(filename) TSRMLS_CC)) {
+	if (php_check_open_basedir(Z_STRVAL_PP(filename) TSRMLS_CC)) {
 		RETURN_FALSE;
 	}

-	if ((fd = VCWD_OPEN_MODE(Z_STRVAL_P(filename), O_BINARY|O_RDWR|O_CREAT, 0644)) < 0) {
-		php_error(E_WARNING, "Unable to create database (%d): %s", errno, strerror(errno));
+	if ((fd = VCWD_OPEN_MODE(Z_STRVAL_PP(filename), O_BINARY|O_RDWR|O_CREAT, 0644)) < 0) {
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "Unable to create database (%d): %s", errno, strerror(errno));
 		RETURN_FALSE;
 	}

-	num_fields = zend_hash_num_elements(Z_ARRVAL_P(fields));
+	num_fields = zend_hash_num_elements(Z_ARRVAL_PP(fields));

 	/* have to use regular malloc() because this gets free()d by
 	   code in the dbase library */
 	dbh = (dbhead_t *)malloc(sizeof(dbhead_t));
 	dbf = (dbfield_t *)malloc(sizeof(dbfield_t) * num_fields);
 	if (!dbh || !dbf) {
-		php_error(E_WARNING, "Unable to allocate memory for header info");
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "Unable to allocate memory for header info");
 		RETURN_FALSE;
 	}
 	
@@ -651,27 +641,27 @@ PHP_FUNCTION(dbase_create)

 	for (i = 0, cur_f = dbf; i < num_fields; i++, cur_f++) {
 		/* look up the first field */
-		if (zend_hash_index_find(Z_ARRVAL_P(fields), i, (void **)&field) == FAILURE) {
-			php_error(E_WARNING, "unable to find field %d", i);
+		if (zend_hash_index_find(Z_ARRVAL_PP(fields), i, (void **)&field) == FAILURE) {
+			php_error_docref(NULL TSRMLS_CC, E_WARNING, "unable to find field %d", i);
 			free_dbf_head(dbh);
 			RETURN_FALSE;
 		}

 		if (Z_TYPE_PP (field) != IS_ARRAY) {
-			php_error(E_WARNING, "second parameter must be array of arrays");
+			php_error_docref(NULL TSRMLS_CC, E_WARNING, "second parameter must be array of arrays");
 			free_dbf_head(dbh);
 			RETURN_FALSE;
 		}

 		/* field name */
 		if (zend_hash_index_find(Z_ARRVAL_PP(field), 0, (void **)&value) == FAILURE) {
-			php_error(E_WARNING, "expected field name as first element of list in field %d", i);
+			php_error_docref(NULL TSRMLS_CC, E_WARNING, "expected field name as first element of list in field %d", i);
 			free_dbf_head(dbh);
 			RETURN_FALSE;
 		}
 		convert_to_string_ex(value);
 		if (Z_STRLEN_PP(value) > 10 || Z_STRLEN_PP(value) == 0) {
-			php_error(E_WARNING, "invalid field name '%s' (must be non-empty and less than or equal to 10 characters)", Z_STRVAL_PP(value));
+			php_error_docref(NULL TSRMLS_CC, E_WARNING, "invalid field name '%s' (must be non-empty and less than or equal to 10 characters)", Z_STRVAL_PP(value));
 			free_dbf_head(dbh);
 			RETURN_FALSE;
 		}
@@ -679,7 +669,7 @@ PHP_FUNCTION(dbase_create)

 		/* field type */
 		if (zend_hash_index_find(Z_ARRVAL_PP (field), 1, (void **)&value) == FAILURE) {
-			php_error(E_WARNING, "expected field type as second element of list in field %d", i);
+			php_error_docref(NULL TSRMLS_CC, E_WARNING, "expected field type as second element of list in field %d", i);
 			RETURN_FALSE;
 		}
 		convert_to_string_ex(value);
@@ -704,7 +694,7 @@ PHP_FUNCTION(dbase_create)
 		case 'C':
 			/* field length */
 			if (zend_hash_index_find(Z_ARRVAL_PP (field), 2, (void **)&value) == FAILURE) {
-				php_error(E_WARNING, "expected field length as third element of list in field %d", i);
+				php_error_docref(NULL TSRMLS_CC, E_WARNING, "expected field length as third element of list in field %d", i);
 				free_dbf_head(dbh);
 				RETURN_FALSE;
 			}
@@ -713,7 +703,7 @@ PHP_FUNCTION(dbase_create)

 			if (cur_f->db_type == 'N') {
 				if (zend_hash_index_find(Z_ARRVAL_PP (field), 3, (void **)&value) == FAILURE) {
-					php_error(E_WARNING, "expected field precision as fourth element of list in field %d", i);
+					php_error_docref(NULL TSRMLS_CC, E_WARNING, "expected field precision as fourth element of list in field %d", i);
 					free_dbf_head(dbh);
 					RETURN_FALSE;
 				}
@@ -722,7 +712,7 @@ PHP_FUNCTION(dbase_create)
 			}
 			break;
 		default:
-			php_error(E_WARNING, "unknown field type '%c'", cur_f->db_type);
+			php_error_docref(NULL TSRMLS_CC, E_WARNING, "unknown field type '%c'", cur_f->db_type);
 		}
 		cur_f->db_foffset = rlen;
 		rlen += cur_f->db_flen;
@@ -136,7 +136,8 @@ void pack_dbf(dbhead_t *dbh)

 	/* Try to truncate the file to the right size. */
 	if (ftruncate(dbh->db_fd, out_off) != 0) {
-	    php_error(E_WARNING, "dbase_pack() couldn't truncate the file to the right size. Some deleted records may still be left in there.");
+	    TSRMLS_FETCH();
+	    php_error_docref(NULL TSRMLS_CC, E_WARNING, "dbase_pack() couldn't truncate the file to the right size. Some deleted records may still be left in there.");
 	}

 	if (rec_cnt == 0)
@@ -167,16 +168,16 @@ void put_field_val(char *rp, dbfield_t *fldp, char *cp)
 */
 void out_rec(dbhead_t *dbh, dbfield_t *dbf, char *cp)
 {
-        dbfield_t       *cur_f;
-        int     nfields = dbh->db_nfields;
-        char    *fnp = (char *)malloc(dbh->db_rlen);
+	dbfield_t       *cur_f;
+	int     nfields = dbh->db_nfields;
+	char    *fnp = (char *)malloc(dbh->db_rlen);

-        printf("%c", *cp);
-        for (cur_f = dbf; cur_f < &dbf[nfields] ; cur_f++) {
-                printf(" ");
+	printf("%c", *cp);
+	for (cur_f = dbf; cur_f < &dbf[nfields] ; cur_f++) {
+		printf(" ");
 		printf(cur_f->db_format, get_field_val(cp, cur_f, fnp));
-        }
-        printf("\n");
+	}
+	printf("\n");
 	free(fnp);
 }

@@ -0,0 +1,26 @@
+--TEST--
+Bug #31754: (dbase_open() fails for mode = 1)
+--SKIPIF--
+<?php
+if (!extension_loaded('dbase')) {
+	die('skip dbase extension not available');
+}
+?>
+--FILE--
+<?php
+
+// database "definition"
+$def = array(
+	array("foo", "L")
+);
+
+// creation
+$dbh = dbase_create('/tmp/bug31754.dbf', array(array('foo', 'L')));
+dbase_close($dbh);
+
+$dbh = dbase_open('/tmp/bug31754.dbf', 1);
+unlink('/tmp/bug31754.dbf');
+
+?>
+--EXPECTF--
+Warning: dbase_open(): Cannot open /tmp/bug31754.dbf in write-only mode in %sbug31754.php on line %d
@@ -33,6 +33,8 @@ typedef struct {
 	int cflags;
 } reg_cache;

+static int reg_magic = 0;
+
 /* {{{ _php_regcomp
 */
 static int _php_regcomp(regex_t *preg, const char *pattern, int cflags)
@@ -42,8 +44,39 @@ static int _php_regcomp(regex_t *preg, const char *pattern, int cflags)
 	reg_cache *rc = NULL;
 	TSRMLS_FETCH();
 	
-	if(zend_hash_find(&REG(ht_rc), (char *) pattern, patlen+1, (void **) &rc) == FAILURE ||
-			rc->cflags != cflags) {
+	if(zend_hash_find(&REG(ht_rc), (char *) pattern, patlen+1, (void **) &rc) == SUCCESS
+	   && rc->cflags == cflags) {
+#ifdef HAVE_REGEX_T_RE_MAGIC
+		/*
+		 * We use a saved magic number to see whether cache is corrupted, and if it
+		 * is, we flush it and compile the pattern from scratch.
+		 */
+		if (rc->preg.re_magic != reg_magic) {
+			zend_hash_clean(&REG(ht_rc));
+		} else {
+			memcpy(preg, &rc->preg, sizeof(*preg));
+			return r;
+		}
+	}
+
+	r = regcomp(preg, pattern, cflags);
+	if(!r) {
+		reg_cache rcp;
+
+		rcp.cflags = cflags;
+		memcpy(&rcp.preg, preg, sizeof(*preg));
+		/*
+		 * Since we don't have access to the actual MAGIC1 definition in the private
+		 * header file, we save the magic value immediately after compilation. Hopefully,
+		 * it's good.
+		 */
+		if (!reg_magic) reg_magic = preg->re_magic;
+		zend_hash_update(&REG(ht_rc), (char *) pattern, patlen+1,
+						 (void *) &rcp, sizeof(rcp), NULL);
+	}
+#else
+		memcpy(preg, &rc->preg, sizeof(*preg));
+	} else {
 		r = regcomp(preg, pattern, cflags);
 		if(!r) {
 			reg_cache rcp;
@@ -51,12 +84,10 @@ static int _php_regcomp(regex_t *preg, const char *pattern, int cflags)
 			rcp.cflags = cflags;
 			memcpy(&rcp.preg, preg, sizeof(*preg));
 			zend_hash_update(&REG(ht_rc), (char *) pattern, patlen+1,
-					(void *) &rcp, sizeof(rcp), NULL);
+							 (void *) &rcp, sizeof(rcp), NULL);
 		}
-	} else {
-		memcpy(preg, &rc->preg, sizeof(*preg));
 	}
-	
+#endif
 	return r;
 }
 /* }}} */
@@ -3013,6 +3013,12 @@ static int exif_process_IFD_in_JPEG(image_info_type *ImageInfo, char *dir_start,
 			return FALSE;
 		}
 	}
+	/*
+	 * Ignore IFD2 if it purportedly exists
+	 */
+	if (section_index == SECTION_THUMBNAIL) {
+		return TRUE;
+	}
 	/*
 	 * Hack to make it process IDF1 I hope
 	 * There are 2 IDFs, the second one holds the keys (0x0201 and 0x0202) to the thumbnail
@@ -3722,7 +3728,11 @@ static int exif_read_file(image_info_type *ImageInfo, char *FileName, int read_t
 	if (php_stream_is(ImageInfo->infile, PHP_STREAM_IS_STDIO)) {
 		if (VCWD_STAT(FileName, &st) >= 0) {
 			/* Store file date/time. */
+#ifdef NETWARE
+			ImageInfo->FileDateTime = st.st_mtime.tv_sec;
+#else
 			ImageInfo->FileDateTime = st.st_mtime;
+#endif
 			ImageInfo->FileSize = st.st_size;
 			/*exif_error_docref(NULL TSRMLS_CC, ImageInfo, E_NOTICE, "open stream is file: %d", ImageInfo->FileSize);*/
 		}
@@ -0,0 +1,43 @@
+--TEST--
+Bug #34704 (Infinite recursion due to corrupt JPEG)
+--SKIPIF--
+<?php if (!extension_loaded('exif')) print 'skip exif extension not available';?>
+--INI--
+magic_quotes_runtime=0
+output_handler=
+zlib.output_compression=0 
+--FILE--
+<?php
+$infile = dirname(__FILE__).'/bug34704.jpg';
+var_dump(exif_read_data($infile));
+?>
+===DONE===
+--EXPECTF--
+array(7) {
+  ["FileName"]=>
+  string(12) "bug34704.jpg"
+  ["FileDateTime"]=>
+  int(%d)
+  ["FileSize"]=>
+  int(9976)
+  ["FileType"]=>
+  int(2)
+  ["MimeType"]=>
+  string(10) "image/jpeg"
+  ["SectionsFound"]=>
+  string(4) "IFD0"
+  ["COMPUTED"]=>
+  array(5) {
+    ["html"]=>
+    string(24) "width="386" height="488""
+    ["Height"]=>
+    int(488)
+    ["Width"]=>
+    int(386)
+    ["IsColor"]=>
+    int(1)
+    ["ByteOrderMotorola"]=>
+    int(0)
+  }
+}
+===DONE===
@@ -311,6 +311,7 @@ dnl These are always available with bundled library
  AC_DEFINE(HAVE_GD_IMAGEELLIPSE,     1, [ ])
  AC_DEFINE(HAVE_GD_FONTCACHESHUTDOWN,1, [ ])
  AC_DEFINE(HAVE_GD_DYNAMIC_CTX_EX,   1, [ ])
+  AC_DEFINE(HAVE_GD_GIF_CTX,          1, [ ])

 dnl Make sure the libgd/ is first in the include path
  GDLIB_CFLAGS="-DHAVE_LIBPNG"
@@ -1644,7 +1644,7 @@ static void _php_image_output(INTERNAL_FUNCTION_PARAMETERS, int image_type, char
 	}

 	if ((argc == 2) || (argc > 2 && Z_STRLEN_PP(file))) {
-		if (!fn || fn == empty_string || php_check_open_basedir(fn TSRMLS_CC)) {
+		if (!fn || fn == empty_string || php_check_open_basedir(fn TSRMLS_CC) || (PG(safe_mode) && !php_checkuid(fn, "rb+", CHECKUID_CHECK_FILE_AND_DIR))) {
 			php_error_docref(NULL TSRMLS_CC, E_WARNING, "Invalid filename '%s'", fn);
 			RETURN_FALSE;
 		}
@@ -1699,7 +1699,7 @@ static void _php_image_output(INTERNAL_FUNCTION_PARAMETERS, int image_type, char
 		char  buf[4096];
 		char *path;

-		tmp = php_open_temporary_file("", "", &path TSRMLS_CC);
+		tmp = php_open_temporary_file(NULL, NULL, &path TSRMLS_CC);
 		if (tmp == NULL) {
 			php_error_docref(NULL TSRMLS_CC, E_WARNING, "Unable to open temporary file");
 			RETURN_FALSE;
@@ -3017,7 +3017,8 @@ static void php_imagettftext_common(INTERNAL_FUNCTION_PARAMETERS, int mode, int
 {
 	zval *IM, *EXT = NULL;
 	gdImagePtr im=NULL;
-	int col = -1, x = -1, y = -1, str_len, fontname_len, i, brect[8];
+	long col = -1, x = -1, y = -1;
+	int str_len, fontname_len, i, brect[8];
 	double ptsize, angle;
 	unsigned char *str = NULL, *fontname = NULL;
 	char *error = NULL;
@@ -73,7 +73,7 @@ static void _php_image_output_ctx(INTERNAL_FUNCTION_PARAMETERS, int image_type,
 	}

 	if ((argc == 2) || (argc > 2 && Z_STRLEN_PP(file))) {
-		if (!fn || fn == empty_string || php_check_open_basedir(fn TSRMLS_CC)) {
+		if (!fn || fn == empty_string || php_check_open_basedir(fn TSRMLS_CC) || (PG(safe_mode) && !php_checkuid(fn, "rb+", CHECKUID_CHECK_FILE_AND_DIR))) {
 			php_error_docref(NULL TSRMLS_CC, E_WARNING, "Invalid filename '%s'", fn);
 			RETURN_FALSE;
 		}
@@ -1737,8 +1737,8 @@ void gdImageFilledEllipse (gdImagePtr im, int mx, int my, int w, int h, int c)
 	rx = r << 1;
 	ry = 0;
 	x = a;
-	old_y2=-1;
-	old_y1=-1;
+	old_y2=-2;
+	old_y1=-2;
 	while (x > 0){
 		if (r > 0) {
 			my1++;my2--;
@@ -2304,9 +2304,9 @@ void gdImageCopyMergeGray (gdImagePtr dst, gdImagePtr src, int dstX, int dstY, i
 				dc = gdImageGetPixel(dst, tox, toy);
 				g = (0.29900f * gdImageRed(dst, dc)) + (0.58700f * gdImageGreen(dst, dc)) + (0.11400f * gdImageBlue(dst, dc));

-				ncR = (int)(gdImageRed (src, c) * (pct / 100.0f) + gdImageRed(dst, dc) * g * ((100 - pct) / 100.0f));
-				ncG = (int)(gdImageGreen (src, c) * (pct / 100.0f) + gdImageGreen(dst, dc) * g * ((100 - pct) / 100.0f));
-				ncB = (int)(gdImageBlue (src, c) * (pct / 100.0f) + gdImageBlue(dst, dc) * g * ((100 - pct) / 100.0f));
+                                ncR = (int)(gdImageRed (src, c) * (pct / 100.0f) + g * ((100 - pct) / 100.0));
+                                ncG = (int)(gdImageGreen (src, c) * (pct / 100.0f) + g * ((100 - pct) / 100.0));
+                                ncB = (int)(gdImageBlue (src, c) * (pct / 100.0f) + g * ((100 - pct) / 100.0));

 				/* First look for an exact match */
 				nc = gdImageColorExact(dst, ncR, ncG, ncB);
@@ -259,13 +259,13 @@ DoExtension(gdIOCtx *fd, int label, int *Transparent)
               if ((buf[0] & 0x1) != 0)
                       *Transparent = buf[3];

-               while (GetDataBlock(fd, (unsigned char*) buf) != 0)
+               while (GetDataBlock(fd, (unsigned char*) buf) > 0)
                       ;
               return FALSE;
       default:
               break;
       }
-       while (GetDataBlock(fd, (unsigned char*) buf) != 0)
+       while (GetDataBlock(fd, (unsigned char*) buf) > 0)
               ;

       return FALSE;
@@ -337,7 +337,7 @@ GetCode_(gdIOCtx *fd, int code_size, int flag)
               buf[0] = buf[last_byte-2];
               buf[1] = buf[last_byte-1];

-               if ((count = GetDataBlock(fd, &buf[2])) == 0)
+               if ((count = GetDataBlock(fd, &buf[2])) <= 0)
                       done = TRUE;

               last_byte = 2 + count;
@@ -1,5 +1,5 @@
 --TEST--
-gdimagefill() function (Bug #19366 (fixed in bundled libgd))
+Bug #19366 (gdimagefill() function crashes (fixed in bundled libgd))
 --SKIPIF--
 <?php 
 	if (!extension_loaded('gd')) die("skip gd extension not available\n"); 
@@ -1,5 +1,5 @@
 --TEST--
-gdimagefill() function (Bug #19366 (fixed in bundled libgd))
+Bug #27582 (ImageFillToBorder() on alphablending image looses alpha on fill color)
 --SKIPIF--
 <?php
        if (!extension_loaded('gd')) die("skip gd extension not available\n");
@@ -205,7 +205,7 @@ ZEND_MODULE_INFO_D(gmp)
 if(Z_TYPE_PP(zval) == IS_RESOURCE) { \
 	ZEND_FETCH_RESOURCE(gmpnumber, mpz_t *, zval, -1, GMP_RESOURCE_NAME, le_gmp);\
 } else {\
-	if(convert_to_gmp(&gmpnumber, zval, 0) == FAILURE) {\
+	if(convert_to_gmp(&gmpnumber, zval, 0 TSRMLS_CC) == FAILURE) {\
 		RETURN_FALSE;\
 	}\
 	ZEND_REGISTER_RESOURCE(NULL, gmpnumber, le_gmp);\
@@ -217,7 +217,7 @@ if(Z_TYPE_PP(zval) == IS_RESOURCE) { \

 /* {{{ convert_to_gmp
 * Convert zval to be gmp number */
-static int convert_to_gmp(mpz_t * *gmpnumber, zval **val, int base) 
+static int convert_to_gmp(mpz_t * *gmpnumber, zval **val, int base TSRMLS_DC) 
 {
 	int ret = 0;
 	int skip_lead = 0;
@@ -280,8 +280,8 @@ typedef void (*gmp_binary_op2_t)(mpz_ptr, mpz_ptr, mpz_srcptr, mpz_srcptr);
 typedef unsigned long (*gmp_binary_ui_op2_t)(mpz_ptr, mpz_ptr, mpz_srcptr, unsigned long);
 /* }}} */

-#define gmp_zval_binary_ui_op(r, a, b, o, u) gmp_zval_binary_ui_op_ex(r, a, b, o, u, 0 TSRMLS_CC)
-#define gmp_zval_binary_ui_op2(r, a, b, o, u) gmp_zval_binary_ui_op2_ex(r, a, b, o, u, 0 TSRMLS_CC)
+#define gmp_zval_binary_ui_op(r, a, b, o, u) gmp_zval_binary_ui_op_ex(r, a, b, o, u, 0, 0 TSRMLS_CC)
+#define gmp_zval_binary_ui_op2(r, a, b, o, u) gmp_zval_binary_ui_op2_ex(r, a, b, o, u, 0, 0 TSRMLS_CC)

 #define gmp_binary_ui_op(op, uop) _gmp_binary_ui_op(INTERNAL_FUNCTION_PARAM_PASSTHRU, op, uop)
 #define gmp_binary_op(op)         _gmp_binary_ui_op(INTERNAL_FUNCTION_PARAM_PASSTHRU, op, NULL)
@@ -296,7 +296,7 @@ typedef unsigned long (*gmp_binary_ui_op2_t)(mpz_ptr, mpz_ptr, mpz_srcptr, unsig
   Execute GMP binary operation.
   May return GMP resource or long if operation allows this
 */
-static inline void gmp_zval_binary_ui_op_ex(zval *return_value, zval **a_arg, zval **b_arg, gmp_binary_op_t gmp_op, gmp_binary_ui_op_t gmp_ui_op, int allow_ui_return TSRMLS_DC) 
+static inline void gmp_zval_binary_ui_op_ex(zval *return_value, zval **a_arg, zval **b_arg, gmp_binary_op_t gmp_op, gmp_binary_ui_op_t gmp_ui_op, int allow_ui_return, int check_b_zero TSRMLS_DC) 
 {
 	mpz_t *gmpnum_a, *gmpnum_b, *gmpnum_result;
 	unsigned long long_result=0;
@@ -309,10 +309,20 @@ static inline void gmp_zval_binary_ui_op_ex(zval *return_value, zval **a_arg, zv
 		FETCH_GMP_ZVAL(gmpnum_b, b_arg);
 	}

-	if (!Z_LVAL_PP(b_arg)) {
-		RETURN_FALSE;
-	}
+	if(check_b_zero) {
+		int b_is_zero = 0;
+		if(use_ui) {
+			b_is_zero = (Z_LVAL_PP(b_arg) == 0);
+		} else {
+			b_is_zero = !mpz_cmp_ui(*gmpnum_b, 0);
+		}

+		if(b_is_zero) {
+			php_error_docref(NULL TSRMLS_CC, E_WARNING, "Zero operand not allowed");
+			RETURN_FALSE;
+		} 
+	}
+	
 	INIT_GMP_NUM(gmpnum_result);
 	if(use_ui && gmp_ui_op) {
 		if(allow_ui_return) {
@@ -337,7 +347,7 @@ static inline void gmp_zval_binary_ui_op_ex(zval *return_value, zval **a_arg, zv
   Execute GMP binary operation which returns 2 values.
   May return GMP resources or longs if operation allows this.
 */
-static inline void gmp_zval_binary_ui_op2_ex(zval *return_value, zval **a_arg, zval **b_arg, gmp_binary_op2_t gmp_op, gmp_binary_ui_op2_t gmp_ui_op, int allow_ui_return TSRMLS_DC)
+static inline void gmp_zval_binary_ui_op2_ex(zval *return_value, zval **a_arg, zval **b_arg, gmp_binary_op2_t gmp_op, gmp_binary_ui_op2_t gmp_ui_op, int allow_ui_return, int check_b_zero TSRMLS_DC)
 {
 	mpz_t *gmpnum_a, *gmpnum_b, *gmpnum_result1, *gmpnum_result2;
 	zval r;
@@ -352,10 +362,20 @@ static inline void gmp_zval_binary_ui_op2_ex(zval *return_value, zval **a_arg, z
 		FETCH_GMP_ZVAL(gmpnum_b, b_arg);
 	}

-	if (!Z_LVAL_PP(b_arg)) {
-		RETURN_FALSE;
-	}
+	if(check_b_zero) {
+		int b_is_zero = 0;
+		if(use_ui) {
+			b_is_zero = (Z_LVAL_PP(b_arg) == 0);
+		} else {
+			b_is_zero = !mpz_cmp_ui(*gmpnum_b, 0);
+		}

+		if(b_is_zero) {
+			php_error_docref(NULL TSRMLS_CC, E_WARNING, "Zero operand not allowed");
+			RETURN_FALSE;
+		} 
+	}
+	
 	INIT_GMP_NUM(gmpnum_result1);
 	INIT_GMP_NUM(gmpnum_result2);

@@ -509,7 +529,7 @@ ZEND_FUNCTION(gmp_init)
 		}
 	}

-	if(convert_to_gmp(&gmpnumber, number_arg, base) == FAILURE) {
+	if(convert_to_gmp(&gmpnumber, number_arg, base TSRMLS_CC) == FAILURE) {
 		RETURN_FALSE;
 	}

@@ -642,13 +662,13 @@ ZEND_FUNCTION(gmp_div_qr)

 	switch(round) {
 	case GMP_ROUND_ZERO:
-		gmp_zval_binary_ui_op2(return_value, a_arg, b_arg, mpz_tdiv_qr, (gmp_binary_ui_op2_t)mpz_tdiv_qr_ui);
+		gmp_zval_binary_ui_op2_ex(return_value, a_arg, b_arg, mpz_tdiv_qr, (gmp_binary_ui_op2_t)mpz_tdiv_qr_ui, 0, 1 TSRMLS_CC);
 		break;
 	case GMP_ROUND_PLUSINF:
-		gmp_zval_binary_ui_op2(return_value, a_arg, b_arg, mpz_cdiv_qr, (gmp_binary_ui_op2_t)mpz_cdiv_qr_ui);
+		gmp_zval_binary_ui_op2_ex(return_value, a_arg, b_arg, mpz_cdiv_qr, (gmp_binary_ui_op2_t)mpz_cdiv_qr_ui, 0, 1 TSRMLS_CC);
 		break;
 	case GMP_ROUND_MINUSINF:
-		gmp_zval_binary_ui_op2(return_value, a_arg, b_arg, mpz_fdiv_qr, (gmp_binary_ui_op2_t)mpz_fdiv_qr_ui);
+		gmp_zval_binary_ui_op2_ex(return_value, a_arg, b_arg, mpz_fdiv_qr, (gmp_binary_ui_op2_t)mpz_fdiv_qr_ui, 0, 1 TSRMLS_CC);
 		break;
 	}
 							   
@@ -677,15 +697,17 @@ ZEND_FUNCTION(gmp_div_r)
 			break;
 	}

+	
+	
 	switch(round) {
 	case GMP_ROUND_ZERO:
-		gmp_zval_binary_ui_op_ex(return_value, a_arg, b_arg, mpz_tdiv_r, (gmp_binary_ui_op_t)mpz_tdiv_r_ui, 1 TSRMLS_CC);
+		gmp_zval_binary_ui_op_ex(return_value, a_arg, b_arg, mpz_tdiv_r, (gmp_binary_ui_op_t)mpz_tdiv_r_ui, 1, 1 TSRMLS_CC);
 		break;
 	case GMP_ROUND_PLUSINF:
-		gmp_zval_binary_ui_op_ex(return_value, a_arg, b_arg, mpz_cdiv_r, (gmp_binary_ui_op_t)mpz_cdiv_r_ui, 1 TSRMLS_CC);
+		gmp_zval_binary_ui_op_ex(return_value, a_arg, b_arg, mpz_cdiv_r, (gmp_binary_ui_op_t)mpz_cdiv_r_ui, 1, 1 TSRMLS_CC);
 		break;
 	case GMP_ROUND_MINUSINF:
-		gmp_zval_binary_ui_op_ex(return_value, a_arg, b_arg, mpz_fdiv_r, (gmp_binary_ui_op_t)mpz_fdiv_r_ui, 1 TSRMLS_CC);
+		gmp_zval_binary_ui_op_ex(return_value, a_arg, b_arg, mpz_fdiv_r, (gmp_binary_ui_op_t)mpz_fdiv_r_ui, 1, 1 TSRMLS_CC);
 		break;
 	}
 }
@@ -715,13 +737,13 @@ ZEND_FUNCTION(gmp_div_q)

 	switch(round) {
 	case GMP_ROUND_ZERO:
-		gmp_zval_binary_ui_op(return_value, a_arg, b_arg, mpz_tdiv_q, (gmp_binary_ui_op_t)mpz_tdiv_q_ui);
+		gmp_zval_binary_ui_op_ex(return_value, a_arg, b_arg, mpz_tdiv_q, (gmp_binary_ui_op_t)mpz_tdiv_q_ui, 0, 1 TSRMLS_CC);
 		break;
 	case GMP_ROUND_PLUSINF:
-		gmp_zval_binary_ui_op(return_value, a_arg, b_arg, mpz_cdiv_q, (gmp_binary_ui_op_t)mpz_cdiv_q_ui);
+		gmp_zval_binary_ui_op_ex(return_value, a_arg, b_arg, mpz_cdiv_q, (gmp_binary_ui_op_t)mpz_cdiv_q_ui, 0, 1 TSRMLS_CC);
 		break;
 	case GMP_ROUND_MINUSINF:
-		gmp_zval_binary_ui_op(return_value, a_arg, b_arg, mpz_fdiv_q, (gmp_binary_ui_op_t)mpz_fdiv_q_ui);
+		gmp_zval_binary_ui_op_ex(return_value, a_arg, b_arg, mpz_fdiv_q, (gmp_binary_ui_op_t)mpz_fdiv_q_ui, 0, 1 TSRMLS_CC);
 		break;
 	}
 							   
@@ -738,7 +760,7 @@ ZEND_FUNCTION(gmp_mod)
 		WRONG_PARAM_COUNT;
 	}

-	gmp_zval_binary_ui_op_ex(return_value, a_arg, b_arg, mpz_mod, (gmp_binary_ui_op_t)mpz_mod_ui, 1 TSRMLS_CC);
+	gmp_zval_binary_ui_op_ex(return_value, a_arg, b_arg, mpz_mod, (gmp_binary_ui_op_t)mpz_mod_ui, 1, 1 TSRMLS_CC);
 }
 /* }}} */

@@ -984,7 +1006,7 @@ ZEND_FUNCTION(gmp_gcd)
 		WRONG_PARAM_COUNT;
 	}

-	gmp_zval_binary_ui_op_ex(return_value, a_arg, b_arg, mpz_gcd, (gmp_binary_ui_op_t)mpz_gcd_ui, 1 TSRMLS_CC);
+	gmp_zval_binary_ui_op_ex(return_value, a_arg, b_arg, mpz_gcd, (gmp_binary_ui_op_t)mpz_gcd_ui, 1, 0 TSRMLS_CC);
 }
 /* }}} */

@@ -0,0 +1,22 @@
+--TEST--
+Bug #32773 binary GMP functions returns unexpected value, when second parameter is int(0)
+--SKIPIF--
+<?php if (!extension_loaded("gmp")) print "skip"; ?>
+--FILE--
+<?php
+echo '10 + 0 = ', gmp_strval(gmp_add(10, 0)), "\n";
+echo '10 + "0" = ', gmp_strval(gmp_add(10, '0')), "\n";
+                                                                                                              
+echo gmp_strval(gmp_div(10, 0))."\n";
+echo gmp_strval(gmp_div_qr(10, 0))."\n";
+                                                                                                              
+?>
+--EXPECTF--
+10 + 0 = 10
+10 + "0" = 10
+
+Warning: gmp_div(): Zero operand not allowed in %s on line %d
+0
+
+Warning: gmp_div_qr(): Zero operand not allowed in %s on line %d
+0
@@ -97,7 +97,7 @@ LINK32=link.exe
 # PROP Ignore_Export_Lib 0
 # PROP Target_Dir ""
 # ADD BASE CPP /nologo /MTd /W3 /Gm /GX /ZI /Od /D "WIN32" /D "_DEBUG" /D "_WINDOWS" /D "_MBCS" /D "_USRDLL" /D "IMAP_EXPORTS" /FR /YX /FD /GZ /c
-# ADD CPP /nologo /MDd /W3 /Gm /GX /ZI /Od /I "..\..\\" /I "..\..\main" /I "..\..\Zend" /I "..\..\..\bindlib_w32" /I "..\..\TSRM" /D "ZTS" /D "_DEBUG" /D "IMAP_EXPORTS" /D "COMPILE_DL_IMAP" /D HAVE_IMAP=1 /D "WIN32" /D "_WINDOWS" /D "_MBCS" /D "_USRDLL" /D "ZEND_WIN32" /D "PHP_WIN32" /D ZEND_DEBUG=1 /FR /YX /FD /GZ /c
+# ADD CPP /nologo /MDd /W3 /Gm /GX /ZI /Od /I "..\..\\" /I "..\..\main" /I "..\..\Zend" /I "..\..\..\bindlib_w32" /I "..\..\TSRM" /D "ZTS" /D "_DEBUG" /D "IMAP_EXPORTS" /D "COMPILE_DL_IMAP" /D HAVE_IMAP=1 /D "WIN32" /D "_WINDOWS" /D "_MBCS" /D "_USRDLL" /D "ZEND_WIN32" /D "PHP_WIN32" /D ZEND_DEBUG=1 /D HAVE_IMAP2004=1 /D HAVE_IMAP_SSL=1 /FR /YX /FD /GZ /c
 # ADD BASE MTL /nologo /D "_DEBUG" /mktyplib203 /win32
 # ADD MTL /nologo /D "_DEBUG" /mktyplib203 /win32
 # ADD BASE RSC /l 0x40d /d "_DEBUG"
@@ -107,7 +107,7 @@ BSC32=bscmake.exe
 # ADD BSC32 /nologo
 LINK32=link.exe
 # ADD BASE LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /dll /debug /machine:I386 /pdbtype:sept
-# ADD LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib php4ts_debug.lib wsock32.lib winmm.lib cclient.lib /nologo /dll /debug /machine:I386 /out:"..\..\Debug_TS/php_imap.dll" /pdbtype:sept /libpath:"..\..\..\\" /libpath:"..\..\Debug_TS"
+# ADD LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib php4ts_debug.lib wsock32.lib winmm.lib cclient.lib crypt32.lib /nologo /dll /debug /machine:I386 /out:"..\..\Debug_TS/php_imap.dll" /pdbtype:sept /libpath:"..\..\..\\" /libpath:"..\..\Debug_TS"

 !ELSEIF  "$(CFG)" == "imap - Win32 Release_TS"

@@ -123,7 +123,7 @@ LINK32=link.exe
 # PROP Ignore_Export_Lib 0
 # PROP Target_Dir ""
 # ADD BASE CPP /nologo /MT /W3 /GX /O2 /D "WIN32" /D "NDEBUG" /D "_WINDOWS" /D "_MBCS" /D "_USRDLL" /D "IMAP_EXPORTS" /YX /FD /c
-# ADD CPP /nologo /MD /W3 /GX /O2 /I "..\..\\" /I "..\..\main" /I "..\..\Zend" /I "..\..\..\bindlib_w32" /I "..\..\TSRM" /I "..\..\..\php_build\imap\c-client" /D "ZTS" /D "NDEBUG" /D "IMAP_EXPORTS" /D "COMPILE_DL_IMAP" /D HAVE_IMAP=1 /D "WIN32" /D "_WINDOWS" /D "_MBCS" /D "_USRDLL" /D "ZEND_WIN32" /D "PHP_WIN32" /D ZEND_DEBUG=0 /D HAVE_IMAP2001=1 /FR /YX /FD /c
+# ADD CPP /nologo /MD /W3 /GX /O2 /I "..\..\\" /I "..\..\main" /I "..\..\Zend" /I "..\..\..\bindlib_w32" /I "..\..\TSRM" /I "..\..\..\php_build\imap\c-client" /D "ZTS" /D "NDEBUG" /D "IMAP_EXPORTS" /D "COMPILE_DL_IMAP" /D HAVE_IMAP=1 /D "WIN32" /D "_WINDOWS" /D "_MBCS" /D "_USRDLL" /D "ZEND_WIN32" /D "PHP_WIN32" /D ZEND_DEBUG=0 /D HAVE_IMAP2001=1 /D HAVE_IMAP2004=1 /D HAVE_IMAP_SSL=1 /FR /YX /FD /c
 # ADD BASE MTL /nologo /D "NDEBUG" /mktyplib203 /win32
 # ADD MTL /nologo /D "NDEBUG" /mktyplib203 /win32
 # ADD BASE RSC /l 0x40d /d "NDEBUG"
@@ -133,7 +133,7 @@ BSC32=bscmake.exe
 # ADD BSC32 /nologo
 LINK32=link.exe
 # ADD BASE LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /dll /machine:I386
-# ADD LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib php4ts.lib wsock32.lib winmm.lib cclient.lib Secur32.lib CertIdl.Lib /nologo /dll /machine:I386 /nodefaultlib:"LIBCMT" /out:"..\..\Release_TS/php_imap.dll" /libpath:"..\..\Release_TS" /libpath:"..\..\Release_TS_Inline" /libpath:"..\..\..\php_build\imap"
+# ADD LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib php4ts.lib wsock32.lib winmm.lib cclient.lib Secur32.lib CertIdl.Lib crypt32.lib /nologo /dll /machine:I386 /nodefaultlib:"LIBCMT" /out:"..\..\Release_TS/php_imap.dll" /libpath:"..\..\Release_TS" /libpath:"..\..\Release_TS_Inline" /libpath:"..\..\..\php_build\imap"
 # SUBTRACT LINK32 /nodefaultlib

 !ENDIF 
@@ -3015,7 +3015,8 @@ PHP_FUNCTION(imap_mail_compose)
 			if (zend_hash_find(Z_ARRVAL_PP(data), "charset", sizeof("charset"), (void **) &pvalue)== SUCCESS) {
 				convert_to_string_ex(pvalue);
 				tmp_param = mail_newbody_parameter();
-				tmp_param->value = cpystr(Z_STRVAL_PP(pvalue));
+				tmp_param->value = (char *) fs_get(Z_STRLEN_PP(pvalue) + 1);
+				memcpy(tmp_param->value, Z_STRVAL_PP(pvalue), Z_STRLEN_PP(pvalue) + 1);
 				tmp_param->attribute = "CHARSET";
 				tmp_param->next = bod->parameter;
 				bod->parameter = tmp_param;
@@ -1,3 +1,4 @@
+
 OVERALL_TARGET += $(srcdir)/ifx.c

 $(srcdir)/ifx.c: $(srcdir)/ifx.ec $(builddir)/libphpifx.a
@@ -44,8 +44,20 @@ if test "$PHP_INFORMIX" != "no"; then
  esac

  AC_MSG_CHECKING([Informix version])
+  IFX_IBM_VERSION=[`$INFORMIXDIR/bin/esql -V | grep "IBM Informix-ESQL Version" | sed -ne '1 s/\(.*\)ESQL Version \([0-9]*\)\.\([0-9]*\).*/\2\3/p'`]
  IFX_VERSION=[`$INFORMIXDIR/bin/esql -V | grep "ESQL Version" | sed -ne '1 s/\(.*\)ESQL Version \([0-9]*\)\.\([0-9]*\).*/\2\3/p'`]
-  AC_MSG_RESULT($IFX_VERSION)
+
+  if test "$IFX_IBM_VERSION"; then
+    if test $IFX_IBM_VERSION -ge "290" && test $IFX_IBM_VERSION -lt "300"; then
+      IFX_VERSION=960
+    else
+      IFX_VERSION=$IFX_IBM_VERSION
+    fi
+    AC_MSG_RESULT([IBM: $IFX_VERSION])
+  else
+    AC_MSG_RESULT([$IFX_VERSION])
+  fi
+
  AC_DEFINE_UNQUOTED(IFX_VERSION, $IFX_VERSION, [ ])

  if test $IFX_VERSION -ge "900"; then
@@ -29,7 +29,9 @@ if test "$PHP_INGRES" != "no"; then
    AC_MSG_ERROR(Cannot find libiiapi.a under $II_DIR/lib)
  fi

-  PHP_ADD_LIBRARY_WITH_PATH(iiapi, $II_LIB_DIR, II_SHARED_LIBADD)
-  PHP_ADD_LIBRARY_WITH_PATH(ingres, $II_LIB_DIR, II_SHARED_LIBADD)
+  PHP_ADD_LIBRARY_WITH_PATH(iiapi.1, $II_LIB_DIR, II_SHARED_LIBADD)
+  PHP_ADD_LIBRARY_WITH_PATH(q.1, $II_LIB_DIR, II_SHARED_LIBADD)
+  PHP_ADD_LIBRARY_WITH_PATH(frame.1, $II_LIB_DIR, II_SHARED_LIBADD)
+  PHP_ADD_LIBRARY_WITH_PATH(compat.1, $II_LIB_DIR, II_SHARED_LIBADD)
  PHP_ADD_INCLUDE($II_INC_DIR)
 fi
@@ -99,7 +99,9 @@ if test "$PHP_LDAP" != "no"; then
  elif test -f $LDAP_LIBDIR/libclntsh.$SHLIB_SUFFIX_NAME; then
    PHP_ADD_LIBRARY_WITH_PATH(clntsh, $LDAP_LIBDIR, LDAP_SHARED_LIBADD)
    AC_DEFINE(HAVE_ORALDAP,1,[ ])
-
+    if test -f $LDAP_LIBDIR/libclntsh.$SHLIB_SUFFIX_NAME.10.1; then
+      AC_DEFINE(HAVE_ORALDAP_10,1,[ ])
+    fi
  else
    AC_MSG_ERROR(Cannot find ldap libraries in $LDAP_LIBDIR.)
  fi
@@ -112,8 +114,6 @@ if test "$PHP_LDAP" != "no"; then
  _SAVE_CPPFLAGS=$CPPFLAGS
  _SAVE_LDFLAGS=$LDFLAGS
  CPPFLAGS="$CPPFLAGS -I$LDAP_INCDIR"
-  LDFLAGS="$LDFLAGS $LDAP_SHARED_LIBADD"
-
  AC_CACHE_CHECK([for 3 arg ldap_set_rebind_proc], ac_cv_3arg_setrebindproc,
  [AC_TRY_COMPILE([#include <ldap.h>], [ldap_set_rebind_proc(0,0,0)],
  ac_cv_3arg_setrebindproc=yes, ac_cv_3arg_setrebindproc=no)])
@@ -124,6 +124,16 @@ if test "$PHP_LDAP" != "no"; then

  dnl Solaris 2.8 claims to be 2004 API, but doesn't have
  dnl ldap_parse_reference() nor ldap_start_tls_s()
-  AC_CHECK_FUNCS([ldap_parse_reference ldap_start_tls_s])
+  AC_CHECK_FUNCS([ldap_parse_result ldap_parse_reference ldap_start_tls_s])
+  LDFLAGS=$_SAVE_LDFLAGS
+  
+  dnl
+  dnl Sanity check
+  dnl 
+  _SAVE_LDFLAGS=$LDFLAGS
+  LDFLAGS="$LDFLAGS $LDAP_SHARED_LIBADD"
+  AC_CHECK_FUNC(ldap_bind_s, [], [
+    AC_MSG_ERROR([LDAP build check failed. Please check config.log for more information.]) 
+  ])
  LDFLAGS=$_SAVE_LDFLAGS
 fi 
@@ -121,16 +121,18 @@ function_entry ldap_functions[] = {
 	PHP_FE(ldap_compare,								NULL)
 	PHP_FE(ldap_sort,									NULL)

-#if (LDAP_API_VERSION > 2000) || HAVE_NSLDAP
+#if (LDAP_API_VERSION > 2000) || HAVE_NSLDAP || HAVE_ORALDAP_10
+	PHP_FE(ldap_rename,									NULL)
 	PHP_FE(ldap_get_option,			third_argument_force_ref)
 	PHP_FE(ldap_set_option,								NULL)
-	PHP_FE(ldap_parse_result,			arg3to6of6_force_ref)
 	PHP_FE(ldap_first_reference,						NULL)
 	PHP_FE(ldap_next_reference,							NULL)
 #ifdef HAVE_LDAP_PARSE_REFERENCE
 	PHP_FE(ldap_parse_reference,	third_argument_force_ref)
 #endif
-	PHP_FE(ldap_rename,									NULL)
+#ifdef HAVE_LDAP_PARSE_RESULT
+	PHP_FE(ldap_parse_result,			arg3to6of6_force_ref)
+#endif
 #ifdef HAVE_LDAP_START_TLS_S
 	PHP_FE(ldap_start_tls,								NULL)
 #endif
@@ -223,7 +225,7 @@ PHP_MINIT_FUNCTION(ldap)
 	REGISTER_LONG_CONSTANT("LDAP_DEREF_FINDING", LDAP_DEREF_FINDING, CONST_PERSISTENT | CONST_CS);
 	REGISTER_LONG_CONSTANT("LDAP_DEREF_ALWAYS", LDAP_DEREF_ALWAYS, CONST_PERSISTENT | CONST_CS);

-#if (LDAP_API_VERSION > 2000) || HAVE_NSLDAP
+#if (LDAP_API_VERSION > 2000) || HAVE_NSLDAP || HAVE_ORALDAP_10
 	/* LDAP options */
 	REGISTER_LONG_CONSTANT("LDAP_OPT_DEREF", LDAP_OPT_DEREF, CONST_PERSISTENT | CONST_CS);
 	REGISTER_LONG_CONSTANT("LDAP_OPT_SIZELIMIT", LDAP_OPT_SIZELIMIT, CONST_PERSISTENT | CONST_CS);
@@ -234,7 +236,9 @@ PHP_MINIT_FUNCTION(ldap)
 #ifdef LDAP_OPT_RESTART
 	REGISTER_LONG_CONSTANT("LDAP_OPT_RESTART", LDAP_OPT_RESTART, CONST_PERSISTENT | CONST_CS);
 #endif
+#ifdef LDAP_OPT_HOST_NAME
 	REGISTER_LONG_CONSTANT("LDAP_OPT_HOST_NAME", LDAP_OPT_HOST_NAME, CONST_PERSISTENT | CONST_CS);
+#endif
 	REGISTER_LONG_CONSTANT("LDAP_OPT_ERROR_STRING", LDAP_OPT_ERROR_STRING, CONST_PERSISTENT | CONST_CS);
 #ifdef LDAP_OPT_MATCHED_DN
 	REGISTER_LONG_CONSTANT("LDAP_OPT_MATCHED_DN", LDAP_OPT_MATCHED_DN, CONST_PERSISTENT | CONST_CS);
@@ -414,7 +418,7 @@ PHP_FUNCTION(ldap_connect)
 static int _get_lderrno(LDAP *ldap)
 {
 #if !HAVE_NSLDAP
-#if LDAP_API_VERSION > 2000
+#if LDAP_API_VERSION > 2000 || HAVE_ORALDAP_10
 	int lderr;

 	/* New versions of OpenLDAP do it this way */
@@ -478,7 +482,7 @@ static void php_set_opts(LDAP *ldap, int sizelimit, int timelimit, int deref)
 {
 	/* sizelimit */
 	if (sizelimit > -1) {
-#if (LDAP_API_VERSION >= 2004) || HAVE_NSLDAP
+#if (LDAP_API_VERSION >= 2004) || HAVE_NSLDAP || HAVE_ORALDAP_10
 		ldap_set_option(ldap, LDAP_OPT_SIZELIMIT, &sizelimit);
 #else
 		ldap->ld_sizelimit = sizelimit; 
@@ -487,7 +491,7 @@ static void php_set_opts(LDAP *ldap, int sizelimit, int timelimit, int deref)

 	/* timelimit */
 	if (timelimit > -1) {
-#if (LDAP_API_VERSION >= 2004) || HAVE_NSLDAP
+#if (LDAP_API_VERSION >= 2004) || HAVE_NSLDAP || HAVE_ORALDAP_10
 		ldap_set_option(ldap, LDAP_OPT_TIMELIMIT, &timelimit);
 #else
 		ldap->ld_timelimit = timelimit; 
@@ -496,7 +500,7 @@ static void php_set_opts(LDAP *ldap, int sizelimit, int timelimit, int deref)

 	/* deref */
 	if (deref > -1) {
-#if (LDAP_API_VERSION >= 2004) || HAVE_NSLDAP
+#if (LDAP_API_VERSION >= 2004) || HAVE_NSLDAP || HAVE_ORALDAP_10
 		ldap_set_option(ldap, LDAP_OPT_DEREF, &deref);
 #else
 		ldap->ld_deref = deref; 
@@ -915,12 +919,12 @@ PHP_FUNCTION(ldap_get_entries)
 			add_index_string(tmp1, num_attrib, attribute, 1);

 			num_attrib++;
-#if (LDAP_API_VERSION > 2000) || HAVE_NSLDAP || WINDOWS
+#if (LDAP_API_VERSION > 2000) || HAVE_NSLDAP || HAVE_ORALDAP_10 || WINDOWS
 			ldap_memfree(attribute);
 #endif
 			attribute = ldap_next_attribute(ldap, ldap_result_entry, ber);
 		}
-#if (LDAP_API_VERSION > 2000) || HAVE_NSLDAP || WINDOWS
+#if (LDAP_API_VERSION > 2000) || HAVE_NSLDAP || HAVE_ORALDAP_10 || WINDOWS
 		if (ber != NULL)
 			ber_free(ber, 0);
 #endif
@@ -928,7 +932,7 @@ PHP_FUNCTION(ldap_get_entries)
 		add_assoc_long(tmp1, "count", num_attrib);
 		dn = ldap_get_dn(ldap, ldap_result_entry);
 		add_assoc_string(tmp1, "dn", dn, 1);
-#if (LDAP_API_VERSION > 2000) || HAVE_NSLDAP || WINDOWS
+#if (LDAP_API_VERSION > 2000) || HAVE_NSLDAP || HAVE_ORALDAP_10 || WINDOWS
 		ldap_memfree(dn);
 #else
 		free(dn);
@@ -968,7 +972,7 @@ PHP_FUNCTION(ldap_first_attribute)
 		ZEND_REGISTER_RESOURCE(*berp, ber, le_ber_entry);

 		RETVAL_STRING(attribute, 1);
-#if (LDAP_API_VERSION > 2000) || HAVE_NSLDAP || WINDOWS
+#if (LDAP_API_VERSION > 2000) || HAVE_NSLDAP || HAVE_ORALDAP_10 || WINDOWS
 		ldap_memfree(attribute);
 #endif
 	}
@@ -999,7 +1003,7 @@ PHP_FUNCTION(ldap_next_attribute)
 		ZEND_REGISTER_RESOURCE(*berp, ber, le_ber_entry);

 		RETVAL_STRING(attribute, 1);
-#if (LDAP_API_VERSION > 2000) || HAVE_NSLDAP || WINDOWS
+#if (LDAP_API_VERSION > 2000) || HAVE_NSLDAP || HAVE_ORALDAP_10 || WINDOWS
 		ldap_memfree(attribute);
 #endif
 	}
@@ -1046,12 +1050,12 @@ PHP_FUNCTION(ldap_get_attributes)
 		add_index_string(return_value, num_attrib, attribute, 1);

 		num_attrib++;
-#if (LDAP_API_VERSION > 2000) || HAVE_NSLDAP || WINDOWS
+#if (LDAP_API_VERSION > 2000) || HAVE_NSLDAP || HAVE_ORALDAP_10 || WINDOWS
 		ldap_memfree(attribute);
 #endif
 		attribute = ldap_next_attribute(ld->link, resultentry->data, ber);
 	}
-#if (LDAP_API_VERSION > 2000) || HAVE_NSLDAP || WINDOWS
+#if (LDAP_API_VERSION > 2000) || HAVE_NSLDAP || HAVE_ORALDAP_10 || WINDOWS
 		if (ber != NULL) {
 			ber_free(ber, 0);
 		}
@@ -1159,7 +1163,7 @@ PHP_FUNCTION(ldap_get_dn)
 	text = ldap_get_dn(ld->link, resultentry->data);
 	if (text != NULL) {
 		RETVAL_STRING(text, 1);
-#if (LDAP_API_VERSION > 2000) || HAVE_NSLDAP || WINDOWS
+#if (LDAP_API_VERSION > 2000) || HAVE_NSLDAP || HAVE_ORALDAP_10 || WINDOWS
 		ldap_memfree(text);
 #else
 		free(text);
@@ -1222,7 +1226,7 @@ PHP_FUNCTION(ldap_dn2ufn)
 	
 	if (ufn !=NULL) {
 		RETVAL_STRING(ufn, 1);
-#if (LDAP_API_VERSION > 2000) || HAVE_NSLDAP || WINDOWS
+#if (LDAP_API_VERSION > 2000) || HAVE_NSLDAP || HAVE_ORALDAP_10 || WINDOWS
 		ldap_memfree(ufn);
 #endif
 	} else {
@@ -1542,8 +1546,7 @@ PHP_FUNCTION(ldap_sort)
 }
 /* }}} */

-
-#if (LDAP_API_VERSION > 2000) || HAVE_NSLDAP
+#if (LDAP_API_VERSION > 2000) || HAVE_NSLDAP || HAVE_ORALDAP_10
 /* {{{ proto bool ldap_get_option(resource link, int option, mixed retval)
   Get the current value of various session-wide parameters */
 PHP_FUNCTION(ldap_get_option) 
@@ -1581,8 +1584,10 @@ PHP_FUNCTION(ldap_get_option)
 			ZVAL_LONG(*retval, val);
 		} break;
 	/* options with string value */
-	case LDAP_OPT_HOST_NAME:
 	case LDAP_OPT_ERROR_STRING:
+#ifdef LDAP_OPT_HOST_NAME
+	case LDAP_OPT_HOST_NAME:
+#endif
 #ifdef LDAP_OPT_MATCHED_DN
 	case LDAP_OPT_MATCHED_DN:
 #endif
@@ -1636,7 +1641,7 @@ PHP_FUNCTION(ldap_set_option)
 	opt = Z_LVAL_PP(option);

 	switch (opt) {
-		/* options with int value */
+	/* options with int value */
 	case LDAP_OPT_DEREF:
 	case LDAP_OPT_SIZELIMIT:
 	case LDAP_OPT_TIMELIMIT:
@@ -1653,9 +1658,11 @@ PHP_FUNCTION(ldap_set_option)
 				RETURN_FALSE;
 			}
 		} break;
-		/* options with string value */
-	case LDAP_OPT_HOST_NAME:
+	/* options with string value */
 	case LDAP_OPT_ERROR_STRING:
+#ifdef LDAP_OPT_HOST_NAME
+	case LDAP_OPT_HOST_NAME:
+#endif
 #ifdef LDAP_OPT_MATCHED_DN
 	case LDAP_OPT_MATCHED_DN:
 #endif
@@ -1751,6 +1758,7 @@ PHP_FUNCTION(ldap_set_option)
 }
 /* }}} */

+#ifdef HAVE_LDAP_PARSE_RESULT
 /* {{{ proto bool ldap_parse_result(resource link, resource result, int errcode, string matcheddn, string errmsg, array referrals)
   Extract information from result */
 PHP_FUNCTION(ldap_parse_result) 
@@ -1816,6 +1824,7 @@ PHP_FUNCTION(ldap_parse_result)
 	RETURN_TRUE;
 }
 /* }}} */
+#endif

 /* {{{ proto resource ldap_first_reference(resource link, resource result)
   Return first reference */
@@ -1928,7 +1937,7 @@ PHP_FUNCTION(ldap_rename)
 	convert_to_string_ex(newparent);
 	convert_to_boolean_ex(deleteoldrdn);

-#if (LDAP_API_VERSION > 2000) || HAVE_NSLDAP	
+#if (LDAP_API_VERSION > 2000) || HAVE_NSLDAP || HAVE_ORALDAP_10
 	rc = ldap_rename_s(ld->link, Z_STRVAL_PP(dn), Z_STRVAL_PP(newrdn), Z_STRVAL_PP(newparent), Z_BVAL_PP(deleteoldrdn), NULL, NULL);
 #else
 	if (Z_STRLEN_PP(newparent) != 0) {
@@ -1972,10 +1981,10 @@ PHP_FUNCTION(ldap_start_tls)
 }
 /* }}} */
 #endif
-#endif /* (LDAP_API_VERSION > 2000) || HAVE_NSLDAP */
+#endif /* (LDAP_API_VERSION > 2000) || HAVE_NSLDAP || HAVE_ORALDAP_10 */

 #if defined(LDAP_API_FEATURE_X_OPENLDAP) && defined(HAVE_3ARG_SETREBINDPROC)
-/* {{{ proto _ldap_rebind_proc()
+/* {{{ _ldap_rebind_proc()
 */
 int _ldap_rebind_proc(LDAP *ldap, const char *url, ber_tag_t req, ber_int_t msgid, void *params)
 {
@@ -34,59 +34,51 @@ extern zend_module_entry ldap_module_entry;
 /* LDAP functions */
 PHP_MINIT_FUNCTION(ldap);
 PHP_MSHUTDOWN_FUNCTION(ldap);
-
 PHP_MINFO_FUNCTION(ldap);

 PHP_FUNCTION(ldap_connect);
-
 PHP_FUNCTION(ldap_bind);
 PHP_FUNCTION(ldap_unbind);
-
 PHP_FUNCTION(ldap_read);
 PHP_FUNCTION(ldap_list);
 PHP_FUNCTION(ldap_search);
-
 PHP_FUNCTION(ldap_free_result);
 PHP_FUNCTION(ldap_count_entries);
-
 PHP_FUNCTION(ldap_first_entry);
 PHP_FUNCTION(ldap_next_entry);
 PHP_FUNCTION(ldap_get_entries);
 PHP_FUNCTION(ldap_first_attribute);
 PHP_FUNCTION(ldap_next_attribute);
 PHP_FUNCTION(ldap_get_attributes);
-
 PHP_FUNCTION(ldap_get_values);
 PHP_FUNCTION(ldap_get_values_len);
-
 PHP_FUNCTION(ber_free);
 PHP_FUNCTION(ldap_get_dn);
 PHP_FUNCTION(ldap_explode_dn);
 PHP_FUNCTION(ldap_dn2ufn);
-
 PHP_FUNCTION(ldap_add);
 PHP_FUNCTION(ldap_delete);
-
 PHP_FUNCTION(ldap_mod_add);
 PHP_FUNCTION(ldap_mod_replace);
 PHP_FUNCTION(ldap_mod_del);
-
 PHP_FUNCTION(ldap_errno);
 PHP_FUNCTION(ldap_err2str);
 PHP_FUNCTION(ldap_error);
-
 PHP_FUNCTION(ldap_compare);
-
 PHP_FUNCTION(ldap_sort);

-#if ( LDAP_API_VERSION > 2000 ) || HAVE_NSLDAP
+#if (LDAP_API_VERSION > 2000) || HAVE_NSLDAP || HAVE_ORALDAP_10
 PHP_FUNCTION(ldap_get_option);
 PHP_FUNCTION(ldap_set_option);
-PHP_FUNCTION(ldap_parse_result);
 PHP_FUNCTION(ldap_first_reference);
 PHP_FUNCTION(ldap_next_reference);
-PHP_FUNCTION(ldap_parse_reference);
 PHP_FUNCTION(ldap_rename);
+#ifdef HAVE_LDAP_PARSE_RESULT
+PHP_FUNCTION(ldap_parse_result);
+#endif
+#ifdef HAVE_LDAP_PARSE_REFERENCE
+PHP_FUNCTION(ldap_parse_reference);
+#endif
 #endif

 #if LDAP_API_VERSION > 2000
@@ -405,16 +405,16 @@ mbfl_encoding_detector_feed(mbfl_encoding_detector *identd, mbfl_string *string)
 		num = identd->filter_list_size;
 		n = string->len;
 		p = string->val;
+		bad = 0;
 		while (n > 0) {
-			i = 0;
-			bad = 0;
-			while (i < num) {
+			for (i = 0; i < num; i++) {
 				filter = identd->filter_list[i];
-				(*filter->filter_function)(*p, filter);
-				if (filter->flag) {
-					bad++;
+				if (!filter->flag) {
+					(*filter->filter_function)(*p, filter);
+					if (filter->flag) {
+						bad++;
+					}
 				}
-				i++;
 			}
 			if ((num - 1) <= bad) {
 				res = 1;
@@ -555,9 +555,11 @@ mbfl_identify_encoding(mbfl_string *string, enum mbfl_no_encoding *elist, int el
 		while (n > 0) {
 			for (i = 0; i < num; i++) {
 				filter = &flist[i];
-				(*filter->filter_function)(*p, filter);
-				if (filter->flag) {
-					bad++;
+				if (!filter->flag) {
+					(*filter->filter_function)(*p, filter);
+					if (filter->flag) {
+						bad++;
+					}
 				}
 			}
 			if ((num - 1) <= bad && !strict) {
@@ -1960,6 +1962,25 @@ mime_header_encoder_block_collector(int c, void *data)
 static int
 mime_header_encoder_collector(int c, void *data)
 {
+	static int qp_table[256] = {
+		1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* 0x00 */
+		1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* 0x00 */
+		1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 0x20 */
+		0, 0, 0, 0, 0, 0, 0 ,0, 0, 0, 0, 0, 0, 1, 0, 1, /* 0x10 */
+		0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 0x40 */
+		0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, /* 0x50 */
+		0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 0x60 */
+		0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, /* 0x70 */
+		1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* 0x80 */
+		1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* 0x90 */
+		1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* 0xA0 */
+		1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* 0xB0 */
+		1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* 0xC0 */
+		1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* 0xD0 */
+		1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* 0xE0 */
+		1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1  /* 0xF0 */
+	};
+
 	int n;
 	struct mime_header_encoder_data *pe = (struct mime_header_encoder_data *)data;

@@ -1969,7 +1990,7 @@ mime_header_encoder_collector(int c, void *data)
 		break;

 	default:	/* ASCII */
-		if (c >= 0x21 && c < 0x7f) {	/* ASCII exclude SPACE and CTLs */
+		if (!qp_table[(c & 0xff)]) { /* ordinary characters */
 			mbfl_memory_device_output(c, &pe->tmpdev);
 			pe->status1 = 1;
 		} else if (pe->status1 == 0 && c == 0x20) {	/* repeat SPACE */
@@ -55,6 +55,7 @@
 #include "mbstring.h"
 #include "ext/standard/php_string.h"
 #include "ext/standard/php_mail.h"
+#include "ext/standard/exec.h"
 #include "ext/standard/url.h"
 #include "main/php_output.h"
 #include "ext/standard/info.h"
@@ -3473,6 +3474,7 @@ PHP_FUNCTION(mb_send_mail)
 	    body_enc;	/* body transfar encoding */
 	mbfl_memory_device device;	/* automatic allocateable buffer for additional header */
 	const mbfl_language *lang;
+	char *force_extra_parameters = INI_STR("mail.force_extra_parameters");
 	int err = 0;

 	/* initialize */
@@ -3594,12 +3596,21 @@ PHP_FUNCTION(mb_send_mail)
 		extra_cmd = Z_STRVAL_PP(argv[4]);
 	}

+	if (force_extra_parameters) {
+		extra_cmd = estrdup(force_extra_parameters);
+	} else if (extra_cmd) {
+		extra_cmd = php_escape_shell_cmd(extra_cmd);
+	} 
+
 	if (!err && php_mail(to, subject, message, headers, extra_cmd TSRMLS_CC)) {
 		RETVAL_TRUE;
 	} else {
 		RETVAL_FALSE;
 	}

+	if (extra_cmd) {
+		efree(extra_cmd);
+	}
 	if (subject_buf) {
 		efree((void *)subject_buf);
 	}
@@ -4,28 +4,16 @@ php-users@php.gr.jp #16242
 <?php
 extension_loaded('mbstring') or die('skip mbstring not available');
 ?>
--FILE--
-<?php
-$ini = <<< HERE
+--INI--
 mbstring.language=Japanese
 mbstring.internal_encoding=UTF-8
+--FILE--
+<?php

-HERE;
+var_dump(ini_get('mbstring.language'));
+var_dump(ini_get('mbstring.internal_encoding'));
+var_dump(mb_internal_encoding());

-$tmpfile = tempnam(dirname(__FILE__), "t");
-$fp = fopen($tmpfile, 'w');
-fwrite($fp, $ini);
-fclose($fp);
-
-$cmd = 'echo "<?php ';
-$cmd .= "var_dump(ini_get('mbstring.language'));";
-$cmd .= "var_dump(ini_get('mbstring.internal_encoding'));";
-$cmd .= 'var_dump(mb_internal_encoding());';
-$cmd .= ' ?>" |'.getenv("TEST_PHP_EXECUTABLE").' -c '.$tmpfile;
-
-system($cmd);
-
-unlink($tmpfile);
 ?>
 --EXPECT--
 string(8) "Japanese"
@@ -27,8 +27,6 @@

 #if PHP_WIN32
 #include "config.w32.h"
-#elif defined NETWARE
-#include "config.nw.h"
 #else
 #include <php_config.h>
 #endif
@@ -43,7 +43,7 @@ RSC=rc.exe
 # PROP Ignore_Export_Lib 0
 # PROP Target_Dir ""
 # ADD BASE CPP /nologo /MT /W3 /GX /O2 /D "WIN32" /D "NDEBUG" /D "_WINDOWS" /D "_MBCS" /D "_USRDLL" /D "MING_EXPORTS" /YX /FD /c
-# ADD CPP /nologo /MD /W3 /GX /O2 /I "..\.." /I "..\..\Zend" /I "..\..\TSRM" /I "..\..\main" /I "..\..\win32" /I "..\..\..\bindlib_w32" /D "WIN32" /D "MING_EXPORTS" /D "COMPILE_DL_MING" /D "HAVE_MING" /D ZEND_DEBUG=0 /D "NDEBUG" /D "_WINDOWS" /D "ZEND_WIN32" /D "PHP_WIN32" /D ZTS=1 /YX /FD /c
+# ADD CPP /nologo /MD /W3 /GX /O2 /I "..\.." /I "..\..\Zend" /I "..\..\TSRM" /I "..\..\main" /I "..\..\win32" /I "..\..\..\bindlib_w32" /D "WIN32" /D "MING_EXPORTS" /D "COMPILE_DL_MING" /D "HAVE_MING" /D ZEND_DEBUG=0 /D "NDEBUG" /D "_WINDOWS" /D "ZEND_WIN32" /D "PHP_WIN32" /D ZTS=1 /D HAVE_NEW_MING=1 /D HAVE_SWFPREBUILTCLIP=1 /D HAVE_MING_ZLIB=1 /YX /FD /c
 # ADD BASE MTL /nologo /D "NDEBUG" /mktyplib203 /win32
 # ADD MTL /nologo /D "NDEBUG" /mktyplib203 /win32
 # ADD BASE RSC /l 0x407 /d "NDEBUG"
@@ -53,7 +53,7 @@ BSC32=bscmake.exe
 # ADD BSC32 /nologo
 LINK32=link.exe
 # ADD BASE LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /dll /machine:I386
-# ADD LINK32 php4ts.lib libming.lib zlib.lib kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /dll /machine:I386 /out:"..\..\Release_TS/php_ming.dll" /libpath:"..\..\Release_TS" /libpath:"..\..\Release_TS_Inline"
+# ADD LINK32 php4ts.lib libming.lib zlib.lib libungif.lib libpng.lib kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /dll /machine:I386 /out:"..\..\Release_TS/php_ming.dll" /libpath:"..\..\Release_TS" /libpath:"..\..\Release_TS_Inline"

 !ELSEIF  "$(CFG)" == "ming - Win32 Debug_TS"

@@ -317,7 +317,11 @@ PHP_MINIT_FUNCTION(mssql)
 PHP_MSHUTDOWN_FUNCTION(mssql)
 {
 	UNREGISTER_INI_ENTRIES();
+#ifndef HAVE_FREETDS
+	dbwinexit();
+#else
 	dbexit();
+#endif
 	return SUCCESS;
 }

@@ -372,7 +376,7 @@ static void php_mssql_do_connect(INTERNAL_FUNCTION_PARAMETERS, int persistent)
 {
 	char *user, *passwd, *host;
 	char *hashed_details;
-	int hashed_details_length;
+	int hashed_details_length, new_link = 0;
 	mssql_link mssql, *mssql_ptr;
 	char buffer[32];

@@ -430,6 +434,25 @@ static void php_mssql_do_connect(INTERNAL_FUNCTION_PARAMETERS, int persistent)
 				sprintf(hashed_details,"mssql_%s_%s_%s",Z_STRVAL_PP(yyhost),Z_STRVAL_PP(yyuser),Z_STRVAL_PP(yypasswd)); /* SAFE */
 			}
 			break;
+		case 4: {
+				zval **yyhost,**yyuser,**yypasswd, **yynew_link;
+			
+				if (zend_get_parameters_ex(4, &yyhost, &yyuser, &yypasswd, &yynew_link) == FAILURE) {
+					WRONG_PARAM_COUNT;
+				}
+				convert_to_string_ex(yyhost);
+				convert_to_string_ex(yyuser);
+				convert_to_string_ex(yypasswd);
+				convert_to_long_ex(yynew_link);
+				host = Z_STRVAL_PP(yyhost);
+				user = Z_STRVAL_PP(yyuser);
+				passwd = Z_STRVAL_PP(yypasswd);
+				new_link = Z_LVAL_PP(yynew_link);
+				hashed_details_length = Z_STRLEN_PP(yyhost)+Z_STRLEN_PP(yyuser)+Z_STRLEN_PP(yypasswd)+5+3;
+				hashed_details = (char *) emalloc(hashed_details_length+1);
+				sprintf(hashed_details,"mssql_%s_%s_%s",Z_STRVAL_PP(yyhost),Z_STRVAL_PP(yyuser),Z_STRVAL_PP(yypasswd)); /* SAFE */
+			}
+			break;
 		default:
 			WRONG_PARAM_COUNT;
 			break;
@@ -479,7 +502,7 @@ static void php_mssql_do_connect(INTERNAL_FUNCTION_PARAMETERS, int persistent)
 		list_entry *le;

 		/* try to find if we already have this link in our persistent list */
-		if (zend_hash_find(&EG(persistent_list), hashed_details, hashed_details_length + 1, (void **) &le)==FAILURE) {  /* we don't */
+		if (new_link || zend_hash_find(&EG(persistent_list), hashed_details, hashed_details_length + 1, (void **) &le)==FAILURE) {  /* we don't */
 			list_entry new_le;

 			if (MS_SQL_G(max_links) != -1 && MS_SQL_G(num_links) >= MS_SQL_G(max_links)) {
@@ -592,7 +615,7 @@ static void php_mssql_do_connect(INTERNAL_FUNCTION_PARAMETERS, int persistent)
 		 * if it doesn't, open a new mssql link, add it to the resource list,
 		 * and add a pointer to it with hashed_details as the key.
 		 */
-		if (zend_hash_find(&EG(regular_list), hashed_details, hashed_details_length + 1,(void **) &index_ptr)==SUCCESS) {
+		if (!new_link && zend_hash_find(&EG(regular_list), hashed_details, hashed_details_length + 1,(void **) &index_ptr)==SUCCESS) {
 			int type,link;
 			void *ptr;

@@ -682,7 +705,7 @@ static int php_mssql_get_default_link(INTERNAL_FUNCTION_PARAMETERS)
 	return MS_SQL_G(default_link);
 }

-/* {{{ proto int mssql_connect([string servername [, string username [, string password]]])
+/* {{{ proto int mssql_connect([string servername [, string username [, string password [, bool new_link]]]])
   Establishes a connection to a MS-SQL server */
 PHP_FUNCTION(mssql_connect)
 {
@@ -691,7 +714,7 @@ PHP_FUNCTION(mssql_connect)

 /* }}} */

-/* {{{ proto int mssql_pconnect([string servername [, string username [, string password]]])
+/* {{{ proto int mssql_pconnect([string servername [, string username [, string password [, bool new_link]]]])
   Establishes a persistent connection to a MS-SQL server */
 PHP_FUNCTION(mssql_pconnect)
 {
@@ -8,7 +8,7 @@ sinclude(libmysql/acinclude.m4)
 sinclude(libmysql/mysql.m4)

 AC_DEFUN([MYSQL_LIB_CHK], [
-  str="$MYSQL_DIR/$1/libmysqlclient.*"
+  str="$MYSQL_DIR/$1/lib$MY_LIBNAME.*"
  for j in `echo $str`; do
    if test -r $j; then
      MYSQL_LIB_DIR=$MYSQL_DIR/$1
@@ -114,19 +114,26 @@ elif test "$PHP_MYSQL" != "no"; then

  MYSQL_MODULE_TYPE=external

+  MY_LIBNAME=mysqlclient
+  case $host_alias in
+    *netware*[)]
+      MY_LIBNAME=mysql
+      ;;
+  esac
+
  for i in lib lib/mysql; do
    MYSQL_LIB_CHK($i)
  done

  if test -z "$MYSQL_LIB_DIR"; then
-    AC_MSG_ERROR(Cannot find mysqlclient library under $MYSQL_DIR)
+    AC_MSG_ERROR(Cannot find lib$MY_LIBNAME library under $MYSQL_DIR)
  fi

-  PHP_CHECK_LIBRARY(mysqlclient, mysql_close, [ ],
+  PHP_CHECK_LIBRARY($MY_LIBNAME, mysql_close, [ ],
  [
    if test "$PHP_ZLIB_DIR" != "no"; then
      PHP_ADD_LIBRARY_WITH_PATH(z, $PHP_ZLIB_DIR, MYSQL_SHARED_LIBADD)
-      PHP_CHECK_LIBRARY(mysqlclient, mysql_error, [], [
+      PHP_CHECK_LIBRARY($MY_LIBNAME, mysql_error, [], [
        AC_MSG_ERROR([mysql configure failed. Please check config.log for more information.])
      ], [
        -L$PHP_ZLIB_DIR/lib -L$MYSQL_LIB_DIR 
@@ -134,7 +141,7 @@ elif test "$PHP_MYSQL" != "no"; then
      MYSQL_LIBS="-L$PHP_ZLIB_DIR/lib -lz"
    else
      PHP_ADD_LIBRARY(z,, MYSQL_SHARED_LIBADD)
-      PHP_CHECK_LIBRARY(mysqlclient, mysql_errno, [], [
+      PHP_CHECK_LIBRARY($MY_LIBNAME, mysql_errno, [], [
        AC_MSG_ERROR([Try adding --with-zlib-dir=<DIR>. Please check config.log for more information.])
      ], [
        -L$MYSQL_LIB_DIR
@@ -145,8 +152,8 @@ elif test "$PHP_MYSQL" != "no"; then
    -L$MYSQL_LIB_DIR 
  ])

-  PHP_ADD_LIBRARY_WITH_PATH(mysqlclient, $MYSQL_LIB_DIR, MYSQL_SHARED_LIBADD)
-  MYSQL_LIBS="-L$MYSQL_LIB_DIR -lmysqlclient $MYSQL_LIBS"
+  PHP_ADD_LIBRARY_WITH_PATH($MY_LIBNAME, $MYSQL_LIB_DIR, MYSQL_SHARED_LIBADD)
+  MYSQL_LIBS="-L$MYSQL_LIB_DIR -l$MY_LIBNAME $MYSQL_LIBS"

  PHP_ADD_INCLUDE($MYSQL_INC_DIR)
  MYSQL_INCLUDE=-I$MYSQL_INC_DIR
@@ -239,7 +239,7 @@ inline double ulonglong2double(ulonglong value)
 #define HAVE_ALLOCA
 #define HAVE_STRPBRK
 #define HAVE_STRSTR
-/* #define HAVE_COMPRESS     -- not with PHP, please */ 
+#define HAVE_COMPRESS

 #ifdef NOT_USED
 #define HAVE_SNPRINTF		/* Gave link error */
@@ -51,6 +51,9 @@
 # endif
 # include <netdb.h>
 # include <netinet/in.h>
+# if HAVE_ARPA_INET_H
+#  include <arpa/inet.h>
+# endif
 #endif

 #include <mysql.h>
@@ -836,18 +836,18 @@ _oci_conn_list_dtor(oci_connection *connection TSRMLS_DC)
 					(ub4) OCI_HTYPE_SVCCTX));
 	}

-	if (connection->session && connection->session->exclusive) {
-		/* exclusive connection created via OCINLogon() close their 
-		   associated session when destructed */
-		zend_list_delete(connection->session->num);
-	}
-
 	if (connection->pError) {
 		CALL_OCI(OCIHandleFree(
 					(dvoid *) connection->pError, 
 					(ub4) OCI_HTYPE_ERROR));
 	}

+	if (connection->session && connection->session->exclusive) {
+		/* exclusive connection created via OCINLogon() close their 
+		   associated session when destructed */
+		zend_list_delete(connection->session->num);
+	}
+
 	oci_debug("END   _oci_conn_list_dtor: id=%d",connection->id);

 	efree(connection);
@@ -1285,7 +1285,12 @@ _oci_make_zval(zval *value,oci_statement *statement,oci_out_column *column, char
 			if (oci_loadlob(statement->conn,descr,&buffer,&loblen)) {
 				ZVAL_FALSE(value);
 			} else {
-				ZVAL_STRINGL(value,buffer,loblen,0);
+				if (loblen > 0) {
+					ZVAL_STRINGL(value,buffer,loblen,0);
+				}
+				else {
+					ZVAL_EMPTY_STRING(value);
+				}
 			} 
 		} else { 
 			/* return the locator */
@@ -1912,6 +1917,10 @@ oci_loadlob(oci_connection *connection, oci_descriptor *mydescr, char **buffer,u
 		return -1;
 	}

+	if (readlen == 0) {
+		return 0;
+	}
+	
 	buf = emalloc(readlen + 1);

 	while (readlen > 0) { /* thies loop should not be entered on readlen == 0 */
@@ -2527,7 +2536,7 @@ static oci_server *_oci_open_server(char *dbname,int persistent)
 			/* breakthru to open */
 		}
 	}
-	
+
 	server = calloc(1,sizeof(oci_server));

 	server->persistent = persistent;
@@ -2975,6 +2984,12 @@ break;
 			}
 			value_sz = sizeof(void*);
 			break;
+		case SQLT_CHR:
+			break;
+		default:
+			php_error_docref(NULL TSRMLS_CC, E_WARNING, "Unknown or unsupported datatype given: %u", ocitype);
+			RETURN_FALSE;
+			break;
 	}
 	
 	if ((ocitype == SQLT_CHR) && (value_sz == -1)) {
@@ -3280,7 +3295,12 @@ PHP_FUNCTION(ociloadlob)
 		}

 		if (!oci_loadlob(descr->conn,descr,&buffer,&loblen)) {
-	 		RETURN_STRINGL(buffer,loblen,0);
+			if (loblen > 0) {
+		 		RETURN_STRINGL(buffer,loblen,0);
+			}
+			else {
+				RETURN_EMPTY_STRING();
+			}
 		}
 	}

@@ -223,7 +223,7 @@ AC_MSG_CHECKING(for Empress support)
 AC_ARG_WITH(empress,
 [  --with-empress[=DIR]    Include Empress support.  DIR is the Empress base
                          install directory, defaults to \$EMPRESSPATH.
-                          From PHP4, this option only supports Empress Version
+                          From PHP 4, this option only supports Empress Version
                          8.60 and above],
 [
  PHP_WITH_SHARED
@@ -255,7 +255,7 @@ AC_ARG_WITH(empress-bcs,
 [  --with-empress-bcs[=DIR]
                          Include Empress Local Access support.  DIR is the 
                          Empress base install directory, defaults to 
-                          \$EMPRESSPATH.  From PHP4, this option only supports
+                          \$EMPRESSPATH.  From PHP 4, this option only supports
                          Empress Version 8.60 and above.],
 [
  PHP_WITH_SHARED
@@ -313,10 +313,35 @@ AC_ARG_WITH(birdstep,
        ODBC_INCDIR=$withval/include
        ODBC_LIBDIR=$withval/lib
    fi
+   
+    case $host_alias in
+      *aix*[)]
+        AC_DEFINE(AIX,1,[ ]);;
+      *hpux*[)]
+        AC_DEFINE(HPUX,1,[ ]);;
+      *linux*[)]
+        AC_DEFINE(LINUX,1,[ ]);;
+      *qnx*[)]
+        AC_DEFINE(NEUTRINO,1,[ ]);;
+      i?86-*-solaris*[)]
+        AC_DEFINE(ISOLARIS,1,[ ]);;
+      sparc-*-solaris*[)]
+        AC_DEFINE(SOLARIS,1,[ ]);;
+      *unixware*[)]
+        AC_DEFINE(UNIXWARE,1,[ ]);;
+    esac
+
    ODBC_INCLUDE=-I$ODBC_INCDIR
    ODBC_TYPE=birdstep
    ODBC_LFLAGS=-L$ODBC_LIBDIR
    ODBC_LIBS="-lCadm -lCdict -lCenc -lCrdm -lCrpc -lCrdbc -lCrm -lCuapi -lutil"
+    
+    if test -e "$ODBC_LIBDIR/libCrdbc32.$SHLIB_SUFFIX_NAME"; then
+      ODBC_LIBS="-lCrdbc32 -lCadm32 -lCncp32 -lCrm32 -lCsql32 -lCdict32 -lCrdm32 -lCrpc32 -lutil"
+    elif test -e "$ODBC_LIBDIR/libCrdbc.$SHLIB_SUFFIX_NAME"; then
+      ODBC_LIBS="-lCrdbc -lCadm -lCncp -lCrm -lCsql -lCdict -lCrdm -lCrpc -lutil"
+    fi
+
    AC_DEFINE(HAVE_BIRDSTEP,1,[ ])

    AC_MSG_RESULT(yes)
@@ -514,7 +539,9 @@ if test -n "$ODBC_TYPE"; then
  if test "$ODBC_TYPE" != "dbmaker"; then
    ext_shared=$shared
    PHP_EVAL_LIBLINE([$ODBC_LFLAGS $ODBC_LIBS], ODBC_SHARED_LIBADD)
-    AC_DEFINE(HAVE_SQLDATASOURCES,1,[ ])
+    if test "$ODBC_TYPE" != "birdstep"; then
+      AC_DEFINE(HAVE_SQLDATASOURCES,1,[ ])
+    fi
  fi

  AC_DEFINE(HAVE_UODBC,1,[ ])
@@ -245,7 +245,7 @@ static void _close_odbc_pconn(zend_rsrc_list_entry *rsrc TSRMLS_DC)
 	odbc_result *res;
 	odbc_connection *conn = (odbc_connection *)rsrc->ptr;

-	nument = zend_hash_next_free_element(&EG(regular_list));
+	nument = zend_hash_next_free_element(&EG(persistent_list));
 	for(i = 1; i < nument; i++) {
 		ptr = zend_list_find(i, &type);
 		if (ptr && (type == le_result)) {
@@ -2436,8 +2436,10 @@ PHP_FUNCTION(odbc_next_result)
 			result->values = NULL;
 		}
 		RETURN_TRUE;
-	}
-	else {
+	} else if (rc == SQL_NO_DATA_FOUND) {
+		RETURN_FALSE;
+	} else {
+		odbc_sql_error(result->conn_ptr, result->stmt, "SQLMoreResults");
 		RETURN_FALSE;
 	}
 }
@@ -33,7 +33,7 @@
 extern zend_module_entry odbc_module_entry;
 #define odbc_module_ptr &odbc_module_entry

-#if defined(HAVE_DBMAKER) || defined(PHP_WIN32) || defined(HAVE_IBMDB2) || defined(HAVE_UNIXODBC)
+#if defined(HAVE_DBMAKER) || defined(PHP_WIN32) || defined(HAVE_IBMDB2) || defined(HAVE_UNIXODBC) || defined(HAVE_BIRDSTEP)
 # define PHP_ODBC_HAVE_FETCH_HASH 1
 #endif

@@ -216,7 +216,7 @@ typedef struct odbc_connection {
 typedef struct odbc_result_value {
 	char name[32];
 	char *value;
-	long int vallen;
+	SDWORD vallen;
 	SDWORD coltype;
 } odbc_result_value;

@@ -2510,7 +2510,7 @@ PHP_FUNCTION(openssl_private_encrypt)
 	cryptedlen = EVP_PKEY_size(pkey);
 	cryptedbuf = emalloc(cryptedlen + 1);

-	switch (Z_TYPE_P(pkey)) {
+	switch (pkey->type) {
 		case EVP_PKEY_RSA:
 		case EVP_PKEY_RSA2:
 			successful =  (RSA_private_encrypt(data_len, 
@@ -2566,7 +2566,7 @@ PHP_FUNCTION(openssl_private_decrypt)
 	cryptedlen = EVP_PKEY_size(pkey);
 	crypttemp = emalloc(cryptedlen + 1);

-	switch (Z_TYPE_P(pkey)) {
+	switch (pkey->type) {
 		case EVP_PKEY_RSA:
 		case EVP_PKEY_RSA2:
 			cryptedlen = RSA_private_decrypt(data_len, 
@@ -2629,7 +2629,7 @@ PHP_FUNCTION(openssl_public_encrypt)
 	cryptedlen = EVP_PKEY_size(pkey);
 	cryptedbuf = emalloc(cryptedlen + 1);

-	switch (Z_TYPE_P(pkey)) {
+	switch (pkey->type) {
 		case EVP_PKEY_RSA:
 		case EVP_PKEY_RSA2:
 			successful = (RSA_public_encrypt(data_len, 
@@ -2686,7 +2686,7 @@ PHP_FUNCTION(openssl_public_decrypt)
 	cryptedlen = EVP_PKEY_size(pkey);
 	crypttemp = emalloc(cryptedlen + 1);

-	switch (Z_TYPE_P(pkey)) {
+	switch (pkey->type) {
 		case EVP_PKEY_RSA:
 		case EVP_PKEY_RSA2:
 			cryptedlen = RSA_public_decrypt(data_len, 
@@ -139,17 +139,13 @@ void php_register_signal_constants(INIT_FUNC_ARGS)

 static void php_pcntl_init_globals(zend_pcntl_globals *pcntl_globals)
 { 
-	/* Just in case ... */
-	memset(&pcntl_globals->php_signal_queue,0,sizeof(pcntl_globals->php_signal_queue));
-   
-	zend_llist_init(&pcntl_globals->php_signal_queue, sizeof (long),  NULL, 1);
-	pcntl_globals->signal_queue_ready = 0;
-	pcntl_globals->processing_signal_queue = 0;
+	memset(pcntl_globals, 0, sizeof(*pcntl_globals));
 }

 PHP_RINIT_FUNCTION(pcntl)
 {
-	zend_hash_init(&PCNTL_G(php_signal_table), 16, NULL, ZVAL_PTR_DTOR, 1);
+	zend_hash_init(&PCNTL_G(php_signal_table), 16, NULL, ZVAL_PTR_DTOR, 0);
+	PCNTL_G(head) = PCNTL_G(tail) = PCNTL_G(spares) = NULL;
 	return SUCCESS;
 }

@@ -164,13 +160,26 @@ PHP_MINIT_FUNCTION(pcntl)

 PHP_MSHUTDOWN_FUNCTION(pcntl)
 {
-	zend_llist_destroy(&PCNTL_G(php_signal_queue));
 	return SUCCESS;
 }

 PHP_RSHUTDOWN_FUNCTION(pcntl)
 {
+	struct php_pcntl_pending_signal *sig;
+
+	/* FIXME: if a signal is delivered after this point, things will go pear shaped;
+	 * need to remove signal handlers */
 	zend_hash_destroy(&PCNTL_G(php_signal_table));
+	while (PCNTL_G(head)) {
+		sig = PCNTL_G(head);
+		PCNTL_G(head) = sig->next;
+		efree(sig);
+	}
+	while (PCNTL_G(spares)) {
+		sig = PCNTL_G(spares);
+		PCNTL_G(spares) = sig->next;
+		efree(sig);
+	}
 	return SUCCESS;
 }

@@ -467,6 +476,19 @@ PHP_FUNCTION(pcntl_signal)
 		return;
 	}

+	if (!PCNTL_G(spares)) {
+		/* since calling malloc() from within a signal handler is not portable,
+		 * pre-allocate a few records for recording signals */
+		int i;
+		for (i = 0; i < 32; i++) {
+			struct php_pcntl_pending_signal *psig;
+
+			psig = emalloc(sizeof(*psig));
+			psig->next = PCNTL_G(spares);
+			PCNTL_G(spares) = psig;
+		}
+	}
+
 	/* Special long value case for SIG_DFL and SIG_IGN */
 	if (Z_TYPE_P(handle)==IS_LONG) {
 		if (Z_LVAL_P(handle)!= (long) SIG_DFL && Z_LVAL_P(handle) != (long) SIG_IGN) {
@@ -501,57 +523,63 @@ PHP_FUNCTION(pcntl_signal)
 /* Our custom signal handler that calls the appropriate php_function */
 static void pcntl_signal_handler(int signo)
 {
-	long signal_num = signo;
+	struct php_pcntl_pending_signal *psig;
 	TSRMLS_FETCH();
 	
-	IF_DEBUG(DEBUG_OUT("Caught signo %d\n", signo));
-	if (! PCNTL_G(processing_signal_queue)) {
-		zend_llist_add_element(&PCNTL_G(php_signal_queue), &signal_num);
-		PCNTL_G(signal_queue_ready) = 1;
-		IF_DEBUG(DEBUG_OUT("Added queue entry\n"));
+	psig = PCNTL_G(spares);
+	if (!psig) {
+		/* oops, too many signals for us to track, so we'll forget about this one */
+		return;
 	}
-	return;
+	PCNTL_G(spares) = psig->next;
+
+	psig->signo = signo;
+	psig->next = NULL;
+
+	/* the head check is important, as the tick handler cannot atomically clear both
+	 * the head and tail */
+	if (PCNTL_G(head) && PCNTL_G(tail)) {
+		PCNTL_G(tail)->next = psig;
+	} else {
+		PCNTL_G(head) = psig;
+	}
+	PCNTL_G(tail) = psig;
 }

 void pcntl_tick_handler()
 {
-	zend_llist_element *element;
 	zval *param, **handle, *retval;
+	struct php_pcntl_pending_signal *queue, *next;
 	TSRMLS_FETCH();

 	/* Bail if the queue is empty or if we are already playing the queue*/
-	if (! PCNTL_G(signal_queue_ready) || PCNTL_G(processing_signal_queue))
+	if (! PCNTL_G(head) || PCNTL_G(processing_signal_queue))
 		return;

-	/* Mark our queue empty */
-	PCNTL_G(signal_queue_ready) = 0;
-	
-	/* If for some reason our signal queue is empty then return */
-	if (zend_llist_count(&PCNTL_G(php_signal_queue)) <= 0) {
-		return;
-	}
-	
 	/* Prevent reentrant handler calls */
 	PCNTL_G(processing_signal_queue) = 1;

+	queue = PCNTL_G(head);
+	PCNTL_G(head) = NULL; /* simple stores are atomic */
+	
 	/* Allocate */
 	MAKE_STD_ZVAL(param);
 	MAKE_STD_ZVAL(retval);

-	/* Traverse through our signal queue and call the appropriate php functions */
-	for (element = (&PCNTL_G(php_signal_queue))->head; element; element = element->next) {
-		long *signal_num = (long *)&element->data;
-		if (zend_hash_index_find(&PCNTL_G(php_signal_table), *signal_num, (void **) &handle)==FAILURE) {
-			continue;
+	while (queue) {
+		if (zend_hash_index_find(&PCNTL_G(php_signal_table), queue->signo, (void **) &handle)==SUCCESS) {
+			ZVAL_LONG(param, queue->signo);
+
+			/* Call php signal handler - Note that we do not report errors, and we ignore the return value */
+			/* FIXME: this is probably broken when multiple signals are handled in this while loop (retval) */
+			call_user_function(EG(function_table), NULL, *handle, retval, 1, &param TSRMLS_CC);
 		}

-		ZVAL_LONG(param, *signal_num);
-		
-		/* Call php signal handler - Note that we do not report errors, and we ignore the eturn value */
-		call_user_function(EG(function_table), NULL, *handle, retval, 1, &param TSRMLS_CC);
+		next = queue->next;
+		queue->next = PCNTL_G(spares);
+		PCNTL_G(spares) = queue;
+		queue = next;
 	}
-	/* Clear */
-	zend_llist_clean(&PCNTL_G(php_signal_queue));

 	/* Re-enable queue */
 	PCNTL_G(processing_signal_queue) = 0;
@@ -51,12 +51,17 @@ PHP_FUNCTION(pcntl_wstopsig);
 PHP_FUNCTION(pcntl_signal);
 PHP_FUNCTION(pcntl_exec);

+struct php_pcntl_pending_signal {
+	struct php_pcntl_pending_signal *next;
+	long signo;
+};
+
 ZEND_BEGIN_MODULE_GLOBALS(pcntl)
 	HashTable php_signal_table;
-	zend_llist php_signal_queue;
-	int signal_queue_ready;
 	int processing_signal_queue;
+	struct php_pcntl_pending_signal *head, *tail, *spares;
 ZEND_END_MODULE_GLOBALS(pcntl)
+
 #ifdef ZTS
 #define PCNTL_G(v) TSRMG(pcntl_globals_id, zend_pcntl_globals *, v)
 #else
@@ -4,11 +4,11 @@
 declare(ticks=1);

 function alarm_handle($signal){
-	 if ($signal==SIGALRM) print "Caught SIGALRM!!!\n";
+	 if ($signal==SIGALRM) print "Child: Caught SIGALRM!!!\n";
 }

 function usr1_handle($signal){
-	if ($signal==SIGUSR1) print "Caught SIGUSR1!!!\n";
+	if ($signal==SIGUSR1) print "Child: Caught SIGUSR1!!!\n";
 }

 print "This test will demonstrate a fork followed by ipc via signals.\n";
@@ -23,6 +23,7 @@ if ($pid==0) {
 	sleep(100);
 	print "Child: Resetting Alarm handler to Ignore....\n";
 	pcntl_signal(SIGALRM, SIG_IGN);
+	print "Child: sleeping for 10 seconds....\n";
 	sleep(10);
 	print "Done\n";
 } else {
@@ -33,7 +34,7 @@ if ($pid==0) {
 	sleep(1);
 	print "Parent: Senging SIGUSR1 to Child\n";
 	posix_kill($pid,SIGUSR1);
-	sleep(1);
+	sleep(2);
 	print "Parent: Sending SIGALRM to Child\n";
 	pcntl_waitpid($pid, &$status, $options);
 }
@@ -13,7 +13,7 @@ PHP_ARG_WITH(pcre-regex,for PCRE support,

 if test "$PHP_PCRE_REGEX" != "no"; then
  if test "$PHP_PCRE_REGEX" = "yes"; then
-    PHP_NEW_EXTENSION(pcre, pcrelib/maketables.c pcrelib/get.c pcrelib/study.c pcrelib/pcre.c php_pcre.c, $ext_shared,,-DSUPPORT_UTF8 -DLINK_SIZE=2 -DPOSIX_MALLOC_THRESHOLD=10 -I@ext_srcdir@/pcrelib)
+    PHP_NEW_EXTENSION(pcre, pcrelib/pcre_chartables.c pcrelib/pcre_compile.c pcrelib/pcre_config.c pcrelib/pcre_dfa_exec.c pcrelib/pcre_exec.c pcrelib/pcre_fullinfo.c pcrelib/pcre_get.c pcrelib/pcre_globals.c pcrelib/pcre_info.c pcrelib/pcre_maketables.c pcrelib/pcre_ord2utf8.c pcrelib/pcre_printint.c pcrelib/pcre_refcount.c pcrelib/pcre_study.c pcrelib/pcre_tables.c pcrelib/pcre_try_flipped.c pcrelib/pcre_ucp_findchar.c pcrelib/pcre_valid_utf8.c pcrelib/pcre_version.c pcrelib/pcre_xclass.c php_pcre.c, $ext_shared,,-DEXPORT= -DNEWLINE=10 -DSUPPORT_UTF8 -DSUPPORT_UCP -DLINK_SIZE=2 -DPOSIX_MALLOC_THRESHOLD=10 -DMATCH_LIMIT=10000000 -I@ext_srcdir@/pcrelib)
    PHP_ADD_BUILD_DIR($ext_builddir/pcrelib)
    AC_DEFINE(HAVE_BUNDLED_PCRE, 1, [ ])
  else
@@ -50,7 +50,7 @@ if test "$PHP_PCRE_REGEX" != "no"; then
    
    AC_DEFINE(HAVE_PCRE, 1, [ ])
    PHP_ADD_INCLUDE($PCRE_INCDIR)
-    PHP_NEW_EXTENSION(pcre, php_pcre.c, $ext_shared,,-DSUPPORT_UTF8 -DLINK_SIZE=2 -DPOSIX_MALLOC_THRESHOLD=10)
+    PHP_NEW_EXTENSION(pcre, php_pcre.c, $ext_shared,,-DEXPORT= -DNEWLINE=10 -DSUPPORT_UTF8 -DSUPPORT_UCP -DLINK_SIZE=2 -DPOSIX_MALLOC_THRESHOLD=10 -DMATCH_LIMIT=10000000)
  fi
  PHP_SUBST(PCRE_SHARED_LIBADD)
 fi
@@ -1,6 +1,23 @@
-Written by: Philip Hazel <ph10@cam.ac.uk>
+THE MAIN PCRE LIBRARY
+---------------------
+
+Written by:       Philip Hazel
+Email local part: ph10
+Email domain:     cam.ac.uk

 University of Cambridge Computing Service,
 Cambridge, England. Phone: +44 1223 334714.

-Copyright (c) 1997-2003 University of Cambridge
+Copyright (c) 1997-2005 University of Cambridge
+All rights reserved
+
+
+THE C++ WRAPPER LIBRARY
+-----------------------
+
+Written by:       Google Inc.
+
+Copyright (c) 2005 Google Inc
+All rights reserved
+
+####
@@ -4,51 +4,65 @@ PCRE LICENCE
 PCRE is a library of functions to support regular expressions whose syntax
 and semantics are as close as possible to those of the Perl 5 language.

-Written by: Philip Hazel <ph10@cam.ac.uk>
+Release 6 of PCRE is distributed under the terms of the "BSD" licence, as
+specified below. The documentation for PCRE, supplied in the "doc"
+directory, is distributed under the same terms as the software itself.
+
+The basic library functions are written in C and are freestanding. Also
+included in the distribution is a set of C++ wrapper functions.
+
+
+THE BASIC LIBRARY FUNCTIONS
+---------------------------
+
+Written by:       Philip Hazel
+Email local part: ph10
+Email domain:     cam.ac.uk

 University of Cambridge Computing Service,
 Cambridge, England. Phone: +44 1223 334714.

-Copyright (c) 1997-2003 University of Cambridge
+Copyright (c) 1997-2005 University of Cambridge
+All rights reserved.

-Permission is granted to anyone to use this software for any purpose on any
-computer system, and to redistribute it freely, subject to the following
-restrictions:

-1. This software is distributed in the hope that it will be useful,
-   but WITHOUT ANY WARRANTY; without even the implied warranty of
-   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+THE C++ WRAPPER FUNCTIONS
+-------------------------

-2. The origin of this software must not be misrepresented, either by
-   explicit claim or by omission. In practice, this means that if you use
-   PCRE in software that you distribute to others, commercially or
-   otherwise, you must put a sentence like this
+Contributed by:   Google Inc.

-     Regular expression support is provided by the PCRE library package,
-     which is open source software, written by Philip Hazel, and copyright
-     by the University of Cambridge, England.
+Copyright (c) 2005, Google Inc.
+All rights reserved.

-   somewhere reasonably visible in your documentation and in any relevant
-   files or online help data or similar. A reference to the ftp site for
-   the source, that is, to

-     ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/
+THE "BSD" LICENCE
+-----------------

-   should also be given in the documentation. However, this condition is not
-   intended to apply to whole chains of software. If package A includes PCRE,
-   it must acknowledge it, but if package B is software that includes package
-   A, the condition is not imposed on package B (unless it uses PCRE
-   independently).
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:

-3. Altered versions must be plainly marked as such, and must not be
-   misrepresented as being the original software.
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.

-4. If PCRE is embedded in any software that is released under the GNU
-   General Purpose Licence (GPL), or Lesser General Purpose Licence (LGPL),
-   then the terms of that licence shall supersede any condition above with
-   which it is incompatible.
+    * 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.

-The documentation for PCRE, supplied in the "doc" directory, is distributed
-under the same terms as the software itself.
+    * Neither the name of the University of Cambridge nor the name of Google
+      Inc. nor the names of their contributors may be used to endorse or
+      promote products derived from this software without specific prior
+      written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.

 End
@@ -1,6 +1,357 @@
 ChangeLog for PCRE
 ------------------

+Version 6.2 01-Aug-05
+---------------------
+
+ 1. There was no test for integer overflow of quantifier values. A construction
+    such as {1111111111111111} would give undefined results. What is worse, if
+    a minimum quantifier for a parenthesized subpattern overflowed and became
+    negative, the calculation of the memory size went wrong. This could have
+    led to memory overwriting.
+
+ 2. Building PCRE using VPATH was broken. Hopefully it is now fixed.
+
+ 3. Added "b" to the 2nd argument of fopen() in dftables.c, for non-Unix-like
+    operating environments where this matters.
+
+ 4. Applied Giuseppe Maxia's patch to add additional features for controlling
+    PCRE options from within the C++ wrapper.
+
+ 5. Named capturing subpatterns were not being correctly counted when a pattern
+    was compiled. This caused two problems: (a) If there were more than 100
+    such subpatterns, the calculation of the memory needed for the whole
+    compiled pattern went wrong, leading to an overflow error. (b) Numerical
+    back references of the form \12, where the number was greater than 9, were
+    not recognized as back references, even though there were sufficient
+    previous subpatterns.
+
+ 6. Two minor patches to pcrecpp.cc in order to allow it to compile on older
+    versions of gcc, e.g. 2.95.4.
+
+
+Version 6.1 21-Jun-05
+---------------------
+
+ 1. There was one reference to the variable "posix" in pcretest.c that was not
+    surrounded by "#if !defined NOPOSIX".
+
+ 2. Make it possible to compile pcretest without DFA support, UTF8 support, or
+    the cross-check on the old pcre_info() function, for the benefit of the
+    cut-down version of PCRE that is currently imported into Exim.
+
+ 3. A (silly) pattern starting with (?i)(?-i) caused an internal space
+    allocation error. I've done the easy fix, which wastes 2 bytes for sensible
+    patterns that start (?i) but I don't think that matters. The use of (?i) is
+    just an example; this all applies to the other options as well.
+
+ 4. Since libtool seems to echo the compile commands it is issuing, the output
+    from "make" can be reduced a bit by putting "@" in front of each libtool
+    compile command.
+
+ 5. Patch from the folks at Google for configure.in to be a bit more thorough
+    in checking for a suitable C++ installation before trying to compile the
+    C++ stuff. This should fix a reported problem when a compiler was present,
+    but no suitable headers.
+
+ 6. The man pages all had just "PCRE" as their title. I have changed them to
+    be the relevant file name. I have also arranged that these names are
+    retained in the file doc/pcre.txt, which is a concatenation in text format
+    of all the man pages except the little individual ones for each function.
+
+ 7. The NON-UNIX-USE file had not been updated for the different set of source
+    files that come with release 6. I also added a few comments about the C++
+    wrapper.
+
+
+Version 6.0 07-Jun-05
+---------------------
+
+ 1. Some minor internal re-organization to help with my DFA experiments.
+
+ 2. Some missing #ifdef SUPPORT_UCP conditionals in pcretest and printint that
+    didn't matter for the library itself when fully configured, but did matter
+    when compiling without UCP support, or within Exim, where the ucp files are
+    not imported.
+
+ 3. Refactoring of the library code to split up the various functions into
+    different source modules. The addition of the new DFA matching code (see
+    below) to a single monolithic source would have made it really too
+    unwieldy, quite apart from causing all the code to be include in a
+    statically linked application, when only some functions are used. This is
+    relevant even without the DFA addition now that patterns can be compiled in
+    one application and matched in another.
+
+    The downside of splitting up is that there have to be some external
+    functions and data tables that are used internally in different modules of
+    the library but which are not part of the API. These have all had their
+    names changed to start with "_pcre_" so that they are unlikely to clash
+    with other external names.
+
+ 4. Added an alternate matching function, pcre_dfa_exec(), which matches using
+    a different (DFA) algorithm. Although it is slower than the original
+    function, it does have some advantages for certain types of matching
+    problem.
+
+ 5. Upgrades to pcretest in order to test the features of pcre_dfa_exec(),
+    including restarting after a partial match.
+
+ 6. A patch for pcregrep that defines INVALID_FILE_ATTRIBUTES if it is not
+    defined when compiling for Windows was sent to me. I have put it into the
+    code, though I have no means of testing or verifying it.
+
+ 7. Added the pcre_refcount() auxiliary function.
+
+ 8. Added the PCRE_FIRSTLINE option. This constrains an unanchored pattern to
+    match before or at the first newline in the subject string. In pcretest,
+    the /f option on a pattern can be used to set this.
+
+ 9. A repeated \w when used in UTF-8 mode with characters greater than 256
+    would behave wrongly. This has been present in PCRE since release 4.0.
+
+10. A number of changes to the pcregrep command:
+
+    (a) Refactored how -x works; insert ^(...)$ instead of setting
+        PCRE_ANCHORED and checking the length, in preparation for adding
+        something similar for -w.
+
+    (b) Added the -w (match as a word) option.
+
+    (c) Refactored the way lines are read and buffered so as to have more
+        than one at a time available.
+
+    (d) Implemented a pcregrep test script.
+
+    (e) Added the -M (multiline match) option. This allows patterns to match
+        over several lines of the subject. The buffering ensures that at least
+        8K, or the rest of the document (whichever is the shorter) is available
+        for matching (and similarly the previous 8K for lookbehind assertions).
+
+    (f) Changed the --help output so that it now says
+
+          -w, --word-regex(p)
+
+        instead of two lines, one with "regex" and the other with "regexp"
+        because that confused at least one person since the short forms are the
+        same. (This required a bit of code, as the output is generated
+        automatically from a table. It wasn't just a text change.)
+
+    (g) -- can be used to terminate pcregrep options if the next thing isn't an
+        option but starts with a hyphen. Could be a pattern or a path name
+        starting with a hyphen, for instance.
+
+    (h) "-" can be given as a file name to represent stdin.
+
+    (i) When file names are being printed, "(standard input)" is used for
+        the standard input, for compatibility with GNU grep. Previously
+        "<stdin>" was used.
+
+    (j) The option --label=xxx can be used to supply a name to be used for
+        stdin when file names are being printed. There is no short form.
+
+    (k) Re-factored the options decoding logic because we are going to add
+        two more options that take data. Such options can now be given in four
+        different ways, e.g. "-fname", "-f name", "--file=name", "--file name".
+
+    (l) Added the -A, -B, and -C options for requesting that lines of context
+        around matches be printed.
+
+    (m) Added the -L option to print the names of files that do not contain
+        any matching lines, that is, the complement of -l.
+
+    (n) The return code is 2 if any file cannot be opened, but pcregrep does
+        continue to scan other files.
+
+    (o) The -s option was incorrectly implemented. For compatibility with other
+        greps, it now suppresses the error message for a non-existent or non-
+        accessible file (but not the return code). There is a new option called
+        -q that suppresses the output of matching lines, which was what -s was
+        previously doing.
+
+    (p) Added --include and --exclude options to specify files for inclusion
+        and exclusion when recursing.
+
+11. The Makefile was not using the Autoconf-supported LDFLAGS macro properly.
+    Hopefully, it now does.
+
+12. Missing cast in pcre_study().
+
+13. Added an "uninstall" target to the makefile.
+
+14. Replaced "extern" in the function prototypes in Makefile.in with
+    "PCRE_DATA_SCOPE", which defaults to 'extern' or 'extern "C"' in the Unix
+    world, but is set differently for Windows.
+
+15. Added a second compiling function called pcre_compile2(). The only
+    difference is that it has an extra argument, which is a pointer to an
+    integer error code. When there is a compile-time failure, this is set
+    non-zero, in addition to the error test pointer being set to point to an
+    error message. The new argument may be NULL if no error number is required
+    (but then you may as well call pcre_compile(), which is now just a
+    wrapper). This facility is provided because some applications need a
+    numeric error indication, but it has also enabled me to tidy up the way
+    compile-time errors are handled in the POSIX wrapper.
+
+16. Added VPATH=.libs to the makefile; this should help when building with one
+    prefix path and installing with another. (Or so I'm told by someone who
+    knows more about this stuff than I do.)
+
+17. Added a new option, REG_DOTALL, to the POSIX function regcomp(). This
+    passes PCRE_DOTALL to the pcre_compile() function, making the "." character
+    match everything, including newlines. This is not POSIX-compatible, but
+    somebody wanted the feature. From pcretest it can be activated by using
+    both the P and the s flags.
+
+18. AC_PROG_LIBTOOL appeared twice in Makefile.in. Removed one.
+
+19. libpcre.pc was being incorrectly installed as executable.
+
+20. A couple of places in pcretest check for end-of-line by looking for '\n';
+    it now also looks for '\r' so that it will work unmodified on Windows.
+
+21. Added Google's contributed C++ wrapper to the distribution.
+
+22. Added some untidy missing memory free() calls in pcretest, to keep
+    Electric Fence happy when testing.
+
+
+
+Version 5.0 13-Sep-04
+---------------------
+
+ 1. Internal change: literal characters are no longer packed up into items
+    containing multiple characters in a single byte-string. Each character
+    is now matched using a separate opcode. However, there may be more than one
+    byte in the character in UTF-8 mode.
+
+ 2. The pcre_callout_block structure has two new fields: pattern_position and
+    next_item_length. These contain the offset in the pattern to the next match
+    item, and its length, respectively.
+
+ 3. The PCRE_AUTO_CALLOUT option for pcre_compile() requests the automatic
+    insertion of callouts before each pattern item. Added the /C option to
+    pcretest to make use of this.
+
+ 4. On the advice of a Windows user, the lines
+
+      #if defined(_WIN32) || defined(WIN32)
+      _setmode( _fileno( stdout ), 0x8000 );
+      #endif  /* defined(_WIN32) || defined(WIN32) */
+
+    have been added to the source of pcretest. This apparently does useful
+    magic in relation to line terminators.
+
+ 5. Changed "r" and "w" in the calls to fopen() in pcretest to "rb" and "wb"
+    for the benefit of those environments where the "b" makes a difference.
+
+ 6. The icc compiler has the same options as gcc, but "configure" doesn't seem
+    to know about it. I have put a hack into configure.in that adds in code
+    to set GCC=yes if CC=icc. This seems to end up at a point in the
+    generated configure script that is early enough to affect the setting of
+    compiler options, which is what is needed, but I have no means of testing
+    whether it really works. (The user who reported this had patched the
+    generated configure script, which of course I cannot do.)
+
+    LATER: After change 22 below (new libtool files), the configure script
+    seems to know about icc (and also ecc). Therefore, I have commented out
+    this hack in configure.in.
+
+ 7. Added support for pkg-config (2 patches were sent in).
+
+ 8. Negated POSIX character classes that used a combination of internal tables
+    were completely broken. These were [[:^alpha:]], [[:^alnum:]], and
+    [[:^ascii]]. Typically, they would match almost any characters. The other
+    POSIX classes were not broken in this way.
+
+ 9. Matching the pattern "\b.*?" against "ab cd", starting at offset 1, failed
+    to find the match, as PCRE was deluded into thinking that the match had to
+    start at the start point or following a newline. The same bug applied to
+    patterns with negative forward assertions or any backward assertions
+    preceding ".*" at the start, unless the pattern required a fixed first
+    character. This was a failing pattern: "(?!.bcd).*". The bug is now fixed.
+
+10. In UTF-8 mode, when moving forwards in the subject after a failed match
+    starting at the last subject character, bytes beyond the end of the subject
+    string were read.
+
+11. Renamed the variable "class" as "classbits" to make life easier for C++
+    users. (Previously there was a macro definition, but it apparently wasn't
+    enough.)
+
+12. Added the new field "tables" to the extra data so that tables can be passed
+    in at exec time, or the internal tables can be re-selected. This allows
+    a compiled regex to be saved and re-used at a later time by a different
+    program that might have everything at different addresses.
+
+13. Modified the pcre-config script so that, when run on Solaris, it shows a
+    -R library as well as a -L library.
+
+14. The debugging options of pcretest (-d on the command line or D on a
+    pattern) showed incorrect output for anything following an extended class
+    that contained multibyte characters and which was followed by a quantifier.
+
+15. Added optional support for general category Unicode character properties
+    via the \p, \P, and \X escapes. Unicode property support implies UTF-8
+    support. It adds about 90K to the size of the library. The meanings of the
+    inbuilt class escapes such as \d and \s have NOT been changed.
+
+16. Updated pcredemo.c to include calls to free() to release the memory for the
+    compiled pattern.
+
+17. The generated file chartables.c was being created in the source directory
+    instead of in the building directory. This caused the build to fail if the
+    source directory was different from the building directory, and was
+    read-only.
+
+18. Added some sample Win commands from Mark Tetrode into the NON-UNIX-USE
+    file. No doubt somebody will tell me if they don't make sense... Also added
+    Dan Mooney's comments about building on OpenVMS.
+
+19. Added support for partial matching via the PCRE_PARTIAL option for
+    pcre_exec() and the \P data escape in pcretest.
+
+20. Extended pcretest with 3 new pattern features:
+
+    (i)   A pattern option of the form ">rest-of-line" causes pcretest to
+          write the compiled pattern to the file whose name is "rest-of-line".
+          This is a straight binary dump of the data, with the saved pointer to
+          the character tables forced to be NULL. The study data, if any, is
+          written too. After writing, pcretest reads a new pattern.
+
+    (ii)  If, instead of a pattern, "<rest-of-line" is given, pcretest reads a
+          compiled pattern from the given file. There must not be any
+          occurrences of "<" in the file name (pretty unlikely); if there are,
+          pcretest will instead treat the initial "<" as a pattern delimiter.
+          After reading in the pattern, pcretest goes on to read data lines as
+          usual.
+
+    (iii) The F pattern option causes pcretest to flip the bytes in the 32-bit
+          and 16-bit fields in a compiled pattern, to simulate a pattern that
+          was compiled on a host of opposite endianness.
+
+21. The pcre-exec() function can now cope with patterns that were compiled on
+    hosts of opposite endianness, with this restriction:
+
+      As for any compiled expression that is saved and used later, the tables
+      pointer field cannot be preserved; the extra_data field in the arguments
+      to pcre_exec() should be used to pass in a tables address if a value
+      other than the default internal tables were used at compile time.
+
+22. Calling pcre_exec() with a negative value of the "ovecsize" parameter is
+    now diagnosed as an error. Previously, most of the time, a negative number
+    would have been treated as zero, but if in addition "ovector" was passed as
+    NULL, a crash could occur.
+
+23. Updated the files ltmain.sh, config.sub, config.guess, and aclocal.m4 with
+    new versions from the libtool 1.5 distribution (the last one is a copy of
+    a file called libtool.m4). This seems to have fixed the need to patch
+    "configure" to support Darwin 1.3 (which I used to do). However, I still
+    had to patch ltmain.sh to ensure that ${SED} is set (it isn't on my
+    workstation).
+
+24. Changed the PCRE licence to be the more standard "BSD" licence.
+
+
 Version 4.5 01-Dec-03
 ---------------------

@@ -4,51 +4,65 @@ PCRE LICENCE
 PCRE is a library of functions to support regular expressions whose syntax
 and semantics are as close as possible to those of the Perl 5 language.

-Written by: Philip Hazel <ph10@cam.ac.uk>
+Release 6 of PCRE is distributed under the terms of the "BSD" licence, as
+specified below. The documentation for PCRE, supplied in the "doc"
+directory, is distributed under the same terms as the software itself.
+
+The basic library functions are written in C and are freestanding. Also
+included in the distribution is a set of C++ wrapper functions.
+
+
+THE BASIC LIBRARY FUNCTIONS
+---------------------------
+
+Written by:       Philip Hazel
+Email local part: ph10
+Email domain:     cam.ac.uk

 University of Cambridge Computing Service,
 Cambridge, England. Phone: +44 1223 334714.

-Copyright (c) 1997-2003 University of Cambridge
+Copyright (c) 1997-2005 University of Cambridge
+All rights reserved.

-Permission is granted to anyone to use this software for any purpose on any
-computer system, and to redistribute it freely, subject to the following
-restrictions:

-1. This software is distributed in the hope that it will be useful,
-   but WITHOUT ANY WARRANTY; without even the implied warranty of
-   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+THE C++ WRAPPER FUNCTIONS
+-------------------------

-2. The origin of this software must not be misrepresented, either by
-   explicit claim or by omission. In practice, this means that if you use
-   PCRE in software that you distribute to others, commercially or
-   otherwise, you must put a sentence like this
+Contributed by:   Google Inc.

-     Regular expression support is provided by the PCRE library package,
-     which is open source software, written by Philip Hazel, and copyright
-     by the University of Cambridge, England.
+Copyright (c) 2005, Google Inc.
+All rights reserved.

-   somewhere reasonably visible in your documentation and in any relevant
-   files or online help data or similar. A reference to the ftp site for
-   the source, that is, to

-     ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/
+THE "BSD" LICENCE
+-----------------

-   should also be given in the documentation. However, this condition is not
-   intended to apply to whole chains of software. If package A includes PCRE,
-   it must acknowledge it, but if package B is software that includes package
-   A, the condition is not imposed on package B (unless it uses PCRE
-   independently).
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:

-3. Altered versions must be plainly marked as such, and must not be
-   misrepresented as being the original software.
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.

-4. If PCRE is embedded in any software that is released under the GNU
-   General Purpose Licence (GPL), or Lesser General Purpose Licence (LGPL),
-   then the terms of that licence shall supersede any condition above with
-   which it is incompatible.
+    * 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.

-The documentation for PCRE, supplied in the "doc" directory, is distributed
-under the same terms as the software itself.
+    * Neither the name of the University of Cambridge nor the name of Google
+      Inc. nor the names of their contributors may be used to endorse or
+      promote products derived from this software without specific prior
+      written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.

 End
@@ -1,6 +1,85 @@
 News about PCRE releases
 ------------------------

+Release 6.0 07-Jun-05
+---------------------
+
+The release number has been increased to 6.0 because of the addition of several
+major new pieces of functionality.
+
+A new function, pcre_dfa_exec(), which implements pattern matching using a DFA
+algorithm, has been added. This has a number of advantages for certain cases,
+though it does run more slowly, and lacks the ability to capture substrings. On
+the other hand, it does find all matches, not just the first, and it works
+better for partial matching. The pcrematching man page discusses the
+differences.
+
+The pcretest program has been enhanced so that it can make use of the new
+pcre_dfa_exec() matching function and the extra features it provides.
+
+The distribution now includes a C++ wrapper library. This is built
+automatically if a C++ compiler is found. The pcrecpp man page discusses this
+interface.
+
+The code itself has been re-organized into many more files, one for each
+function, so it no longer requires everything to be linked in when static
+linkage is used. As a consequence, some internal functions have had to have
+their names exposed. These functions all have names starting with _pcre_. They
+are undocumented, and are not intended for use by outside callers.
+
+The pcregrep program has been enhanced with new functionality such as
+multiline-matching and options for output more matching context. See the
+ChangeLog for a complete list of changes to the library and the utility
+programs.
+
+
+Release 5.0 13-Sep-04
+---------------------
+
+The licence under which PCRE is released has been changed to the more
+conventional "BSD" licence.
+
+In the code, some bugs have been fixed, and there are also some major changes
+in this release (which is why I've increased the number to 5.0). Some changes
+are internal rearrangements, and some provide a number of new facilities. The
+new features are:
+
+1. There's an "automatic callout" feature that inserts callouts before every
+   item in the regex, and there's a new callout field that gives the position
+   in the pattern - useful for debugging and tracing.
+
+2. The extra_data structure can now be used to pass in a set of character
+   tables at exec time. This is useful if compiled regex are saved and re-used
+   at a later time when the tables may not be at the same address. If the
+   default internal tables are used, the pointer saved with the compiled
+   pattern is now set to NULL, which means that you don't need to do anything
+   special unless you are using custom tables.
+
+3. It is possible, with some restrictions on the content of the regex, to
+   request "partial" matching. A special return code is given if all of the
+   subject string matched part of the regex. This could be useful for testing
+   an input field as it is being typed.
+
+4. There is now some optional support for Unicode character properties, which
+   means that the patterns items such as \p{Lu} and \X can now be used. Only
+   the general category properties are supported. If PCRE is compiled with this
+   support, an additional 90K data structure is include, which increases the
+   size of the library dramatically.
+
+5. There is support for saving compiled patterns and re-using them later.
+
+6. There is support for running regular expressions that were compiled on a
+   different host with the opposite endianness.
+
+7. The pcretest program has been extended to accommodate the new features.
+
+The main internal rearrangement is that sequences of literal characters are no
+longer handled as strings. Instead, each character is handled on its own. This
+makes some UTF-8 handling easier, and makes the support of partial matching
+possible. Compiled patterns containing long literal strings will be larger as a
+result of this change; I hope that performance will not be much affected.
+
+
 Release 4.5 01-Dec-03
 ---------------------

@@ -1,19 +1,25 @@
 Compiling PCRE on non-Unix systems
 ----------------------------------

-See below for comments on Cygwin or MinGW usage. I (Philip Hazel) have no
-knowledge of Windows sytems and how their libraries work. The items in the
-PCRE Makefile that relate to anything other than Unix-like systems have been
-contributed by PCRE users. There are some other comments and files in the
-Contrib directory on the ftp site that you may find useful.
+See below for comments on Cygwin or MinGW and OpenVMS usage. I (Philip Hazel)
+have no knowledge of Windows or VMS sytems and how their libraries work. The
+items in the PCRE Makefile that relate to anything other than Unix-like systems
+have been contributed by PCRE users. There are some other comments and files in
+the Contrib directory on the ftp site that you may find useful. See

-The following are generic comments about building PCRE:
+  ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/Contrib

 If you want to compile PCRE for a non-Unix system (or perhaps, more strictly,
-for a system that does not support "configure" and make files), note that PCRE
-consists entirely of code written in Standard C, and so should compile
-successfully on any machine with a Standard C compiler and library, using
-normal compiling commands to do the following:
+for a system that does not support "configure" and "make" files), note that
+PCRE consists entirely of code written in Standard C, and so should compile
+successfully on any system that has a Standard C compiler and library.
+
+
+GENERIC INSTRUCTIONS FOR THE C LIBRARY
+
+The following are generic comments about building PCRE. The interspersed
+indented commands are suggestions from Mark Tetrode as to which commands you
+might use on a Windows system to build a static library.

 (1) Copy or rename the file config.in as config.h, and change the macros that
 define HAVE_STRERROR and HAVE_MEMMOVE to define them as 1 rather than 0.
@@ -23,32 +29,116 @@ particular, if you want to force a specific value for newline, you can define
 the NEWLINE macro. The default is to use '\n', thereby using whatever value
 your compiler gives to '\n'.

+  rem Mark Tetrode's commands
+  copy config.in config.h
+  rem Use write, because notepad cannot handle UNIX files. Change values.
+  write config.h
+
 (2) Copy or rename the file pcre.in as pcre.h, and change the macro definitions
 for PCRE_MAJOR, PCRE_MINOR, and PCRE_DATE near its start to the values set in
 configure.in.

+  rem Mark Tetrode's commands
+  copy pcre.in pcre.h
+  rem Read values from configure.in
+  write configure.in
+  rem Change values
+  write pcre.h
+
 (3) Compile dftables.c as a stand-alone program, and then run it with
 the single argument "chartables.c". This generates a set of standard
 character tables and writes them to that file.

-(4) Compile maketables.c, get.c, study.c and pcre.c and link them all
-together into an object library in whichever form your system keeps such
-libraries. This is the pcre library (chartables.c is included by means of an
-#include directive). If your system has static and shared libraries, you may
-have to do this once for each type.
+  rem Mark Tetrode's commands
+  rem Compile & run
+  cl -DSUPPORT_UTF8 -DSUPPORT_UCP dftables.c
+  dftables.exe chartables.c
+
+(4) Compile the following source files:
+
+  pcre_chartables.c
+  pcre_compile.c
+  pcre_config.c
+  pcre_dfa_exec.c
+  pcre_exec.c
+  pcre_fullinfo.c
+  pcre_get.c
+  pcre_globals.c
+  pcre_info.c
+  pcre_maketables.c
+  pcre_ord2utf8.c
+  pcre_printint.c
+  pcre_refcount.c
+  pcre_study.c
+  pcre_tables.c
+  pcre_try_flipped.c
+  pcre_ucp_findchar.c
+  pcre_valid_utf8.c
+  pcre_version.c
+  pcre_xclass.c
+
+and link them all together into an object library in whichever form your system
+keeps such libraries. This is the pcre C library. If your system has static and
+shared libraries, you may have to do this once for each type.
+
+  rem These comments are out-of-date, referring to a previous release which
+  rem had fewer source files. Replace with the file names from above.
+  rem Mark Tetrode's commands, for a static library
+  rem Compile & lib
+  cl -DSUPPORT_UTF8 -DSUPPORT_UCP -DPOSIX_MALLOC_THRESHOLD=10 /c maketables.c get.c study.c pcre.c
+  lib /OUT:pcre.lib maketables.obj get.obj study.obj pcre.obj

 (5) Similarly, compile pcreposix.c and link it (on its own) as the pcreposix
 library.

+  rem Mark Tetrode's commands, for a static library
+  rem Compile & lib
+  cl -DSUPPORT_UTF8 -DSUPPORT_UCP -DPOSIX_MALLOC_THRESHOLD=10 /c pcreposix.c
+  lib /OUT:pcreposix.lib pcreposix.obj
+
 (6) Compile the test program pcretest.c. This needs the functions in the
 pcre and pcreposix libraries when linking.

+  rem Mark Tetrode's commands
+  rem compile & link
+  cl /F0x400000 pcretest.c pcre.lib pcreposix.lib
+
 (7) Run pcretest on the testinput files in the testdata directory, and check
 that the output matches the corresponding testoutput files. You must use the
 -i option when checking testinput2. Note that the supplied files are in Unix
 format, with just LF characters as line terminators. You may need to edit them
 to change this if your system uses a different convention.

+  rem Mark Tetrode's commands
+  pcretest testdata\testinput1 testdata\myoutput1
+  windiff testdata\testoutput1 testdata\myoutput1
+  pcretest -i testdata\testinput2 testdata\myoutput2
+  windiff testdata\testoutput2 testdata\myoutput2
+  pcretest testdata\testinput3 testdata\myoutput3
+  windiff testdata\testoutput3 testdata\myoutput3
+  pcretest testdata\testinput4 testdata\myoutput4
+  windiff testdata\testoutput4 testdata\myoutput4
+  pcretest testdata\testinput5 testdata\myoutput5
+  windiff testdata\testoutput5 testdata\myoutput5
+  pcretest testdata\testinput6 testdata\myoutput6
+  windiff testdata\testoutput6 testdata\myoutput6
+
+Note that there are now three more tests (7, 8, 9) that did not exist when Mark
+wrote those comments. The test the new pcre_dfa_exec() function.
+
+
+THE C++ WRAPPER FUNCTIONS
+
+The PCRE distribution now contains some C++ wrapper functions and tests,
+contributed by Google Inc. On a system that can use "configure" and "make",
+the functions are automatically built into a library called pcrecpp. It should
+be straightforward to compile the .cc files manually on other systems. The
+files called xxx_unittest.cc are test programs for each of the corresponding
+xxx.cc files.
+
+
+FURTHER REMARKS
+
 If you have a system without "configure" but where you can use a Makefile, edit
 Makefile.in to create Makefile, substituting suitable values for the variables
 at the head of the file.
@@ -119,4 +209,69 @@ void  (*pcre_free)(void *) = free;
 #endif
 =========================

+
+BUILDING PCRE ON OPENVMS
+
+Dan Mooney sent the following comments about building PCRE on OpenVMS. They
+relate to an older version of PCRE that used fewer source files, so the exact
+commands will need changing. See the current list of source files above.
+
+"It was quite easy to compile and link the library. I don't have a formal
+make file but the attached file [reproduced below] contains the OpenVMS DCL
+commands I used to build the library. I had to add #define
+POSIX_MALLOC_THRESHOLD 10 to pcre.h since it was not defined anywhere.
+
+The library was built on:
+O/S: HP OpenVMS v7.3-1
+Compiler: Compaq C v6.5-001-48BCD
+Linker: vA13-01
+
+The test results did not match 100% due to the issues you mention in your
+documentation regarding isprint(), iscntrl(), isgraph() and ispunct(). I
+modified some of the character tables temporarily and was able to get the
+results to match. Tests using the fr locale did not match since I don't have
+that locale loaded. The study size was always reported to be 3 less than the
+value in the standard test output files."
+
+=========================
+$! This DCL procedure builds PCRE on OpenVMS
+$!
+$! I followed the instructions in the non-unix-use file in the distribution.
+$!
+$ COMPILE == "CC/LIST/NOMEMBER_ALIGNMENT/PREFIX_LIBRARY_ENTRIES=ALL_ENTRIES
+$ COMPILE DFTABLES.C
+$ LINK/EXE=DFTABLES.EXE DFTABLES.OBJ
+$ RUN DFTABLES.EXE/OUTPUT=CHARTABLES.C
+$ COMPILE MAKETABLES.C
+$ COMPILE GET.C
+$ COMPILE STUDY.C
+$! I had to set POSIX_MALLOC_THRESHOLD to 10 in PCRE.H since the symbol
+$! did not seem to be defined anywhere.
+$! I edited pcre.h and added #DEFINE SUPPORT_UTF8 to enable UTF8 support.
+$ COMPILE PCRE.C
+$ LIB/CREATE PCRE MAKETABLES.OBJ, GET.OBJ, STUDY.OBJ, PCRE.OBJ
+$! I had to set POSIX_MALLOC_THRESHOLD to 10 in PCRE.H since the symbol
+$! did not seem to be defined anywhere.
+$ COMPILE PCREPOSIX.C
+$ LIB/CREATE PCREPOSIX PCREPOSIX.OBJ
+$ COMPILE PCRETEST.C
+$ LINK/EXE=PCRETEST.EXE PCRETEST.OBJ, PCRE/LIB, PCREPOSIX/LIB
+$! C programs that want access to command line arguments must be
+$! defined as a symbol
+$ PCRETEST :== "$ SYS$ROADSUSERS:[DMOONEY.REGEXP]PCRETEST.EXE"
+$! Arguments must be enclosed in quotes.
+$ PCRETEST "-C"
+$! Test results:
+$!
+$!   The test results did not match 100%. The functions isprint(), iscntrl(),
+$!   isgraph() and ispunct() on OpenVMS must not produce the same results
+$!   as the system that built the test output files provided with the
+$!   distribution.
+$!
+$!   The study size did not match and was always 3 less on OpenVMS.
+$!
+$!   Locale could not be set to fr
+$!
+=========================
+
 ****
@@ -7,14 +7,22 @@ The latest release of PCRE is always available from

 Please read the NEWS file if you are upgrading from a previous release.

-PCRE has its own native API, but a set of "wrapper" functions that are based on
-the POSIX API are also supplied in the library libpcreposix. Note that this
-just provides a POSIX calling interface to PCRE: the regular expressions
-themselves still follow Perl syntax and semantics. The header file
-for the POSIX-style functions is called pcreposix.h. The official POSIX name is
-regex.h, but I didn't want to risk possible problems with existing files of
-that name by distributing it that way. To use it with an existing program that
-uses the POSIX API, it will have to be renamed or pointed at by a link.
+
+The PCRE APIs
+-------------
+
+PCRE is written in C, and it has its own API. The distribution now includes a
+set of C++ wrapper functions, courtesy of Google Inc. (see the pcrecpp man page
+for details).
+
+Also included are a set of C wrapper functions that are based on the POSIX
+API. These end up in the library called libpcreposix. Note that this just
+provides a POSIX calling interface to PCRE: the regular expressions themselves
+still follow Perl syntax and semantics. The header file for the POSIX-style
+functions is called pcreposix.h. The official POSIX name is regex.h, but I
+didn't want to risk possible problems with existing files of that name by
+distributing it that way. To use it with an existing program that uses the
+POSIX API, it will have to be renamed or pointed at by a link.

 If you are using the POSIX interface to PCRE and there is already a POSIX regex
 library installed on your system, you must take care when linking programs to
@@ -22,6 +30,28 @@ ensure that they link with PCRE's libpcreposix library. Otherwise they may pick
 up the "real" POSIX functions of the same name.


+Documentation for PCRE
+----------------------
+
+If you install PCRE in the normal way, you will end up with an installed set of
+man pages whose names all start with "pcre". The one that is called "pcre"
+lists all the others. In addition to these man pages, the PCRE documentation is
+supplied in two other forms; however, as there is no standard place to install
+them, they are left in the doc directory of the unpacked source distribution.
+These forms are:
+
+  1. Files called doc/pcre.txt, doc/pcregrep.txt, and doc/pcretest.txt. The
+     first of these is a concatenation of the text forms of all the section 3
+     man pages except those that summarize individual functions. The other two
+     are the text forms of the section 1 man pages for the pcregrep and
+     pcretest commands. Text forms are provided for ease of scanning with text
+     editors or similar tools.
+
+  2. A subdirectory called doc/html contains all the documentation in HTML
+     form, hyperlinked in various ways, and rooted in a file called
+     doc/index.html.
+
+
 Contributions by users of PCRE
 ------------------------------

@@ -46,7 +76,7 @@ INSTALL.

 Most commonly, people build PCRE within its own distribution directory, and in
 this case, on many systems, just running "./configure" is sufficient, but the
-usual methods of changing standard defaults are available. For example,
+usual methods of changing standard defaults are available. For example:

 CFLAGS='-O2 -Wall' ./configure --prefix=/opt/local

@@ -69,6 +99,13 @@ library. You can read more about them in the pcrebuild man page.
  for handling UTF-8 is not included in the library. (Even when included, it
  still has to be enabled by an option at run time.)

+. If, in addition to support for UTF-8 character strings, you want to include
+  support for the \P, \p, and \X sequences that recognize Unicode character
+  properties, you must add --enable-unicode-properties to the "configure"
+  command. This adds about 90K to the size of the library (in the form of a
+  property table); only the basic two-letter properties such as Lu are
+  supported.
+
 . You can build PCRE to recognized CR or NL as the newline character, instead
  of whatever your compiler uses for "\n", by adding --newline-is-cr or
  --newline-is-nl to the "configure" command, respectively. Only do this if you
@@ -83,7 +120,7 @@ library. You can read more about them in the pcrebuild man page.

  on the "configure" command.

-. PCRE has a counter which can be set to limit the amount of resources it uses.
+. PCRE has a counter that can be set to limit the amount of resources it uses.
  If the limit is exceeded during a match, the match fails. The default is ten
  million. You can change the default by setting, for example,

@@ -101,51 +138,91 @@ library. You can read more about them in the pcrebuild man page.
  is a representation of the compiled pattern, and this changes with the link
  size.

-. You can build PCRE so that its match() function does not call itself
-  recursively. Instead, it uses blocks of data from the heap via special
-  functions pcre_stack_malloc() and pcre_stack_free() to save data that would
-  otherwise be saved on the stack. To build PCRE like this, use
+. You can build PCRE so that its internal match() function that is called from
+  pcre_exec() does not call itself recursively. Instead, it uses blocks of data
+  from the heap via special functions pcre_stack_malloc() and pcre_stack_free()
+  to save data that would otherwise be saved on the stack. To build PCRE like
+  this, use

  --disable-stack-for-recursion

  on the "configure" command. PCRE runs more slowly in this mode, but it may be
-  necessary in environments with limited stack sizes.
+  necessary in environments with limited stack sizes. This applies only to the
+  pcre_exec() function; it does not apply to pcre_dfa_exec(), which does not
+  use deeply nested recursion.

-The "configure" script builds five files:
+The "configure" script builds eight files for the basic C library:

+. pcre.h is the header file for C programs that call PCRE
+. Makefile is the makefile that builds the library
+. config.h contains build-time configuration options for the library
+. pcre-config is a script that shows the settings of "configure" options
+. libpcre.pc is data for the pkg-config command
 . libtool is a script that builds shared and/or static libraries
-. Makefile is built by copying Makefile.in and making substitutions.
-. config.h is built by copying config.in and making substitutions.
-. pcre-config is built by copying pcre-config.in and making substitutions.
-. RunTest is a script for running tests
+. RunTest is a script for running tests on the library
+. RunGrepTest is a script for running tests on the pcregrep command

-Once "configure" has run, you can run "make". It builds two libraries called
+In addition, if a C++ compiler is found, the following are also built:
+
+. pcrecpp.h is the header file for programs that call PCRE via the C++ wrapper
+. pcre_stringpiece.h is the header for the C++ "stringpiece" functions
+
+The "configure" script also creates config.status, which is an executable
+script that can be run to recreate the configuration, and config.log, which
+contains compiler output from tests that "configure" runs.
+
+Once "configure" has run, you can run "make". It builds two libraries, called
 libpcre and libpcreposix, a test program called pcretest, and the pcregrep
-command. You can use "make install" to copy these, the public header files
-pcre.h and pcreposix.h, and the man pages to appropriate live directories on
-your system, in the normal way.
+command. If a C++ compiler was found on your system, it also builds the C++
+wrapper library, which is called libpcrecpp, and some test programs called
+pcrecpp_unittest, pcre_scanner_unittest, and pcre_stringpiece_unittest.
+
+The command "make test" runs all the appropriate tests. Details of the PCRE
+tests are given in a separate section of this document, below.
+
+You can use "make install" to copy the libraries, the public header files
+pcre.h, pcreposix.h, pcrecpp.h, and pcre_stringpiece.h (the last two only if
+the C++ wrapper was built), and the man pages to appropriate live directories
+on your system, in the normal way.
+
+If you want to remove PCRE from your system, you can run "make uninstall".
+This removes all the files that "make install" installed. However, it does not
+remove any directories, because these are often shared with other programs.
+
+
+Retrieving configuration information on Unix-like systems
+---------------------------------------------------------

 Running "make install" also installs the command pcre-config, which can be used
 to recall information about the PCRE configuration and installation. For
-example,
+example:

  pcre-config --version

 prints the version number, and

- pcre-config --libs
+  pcre-config --libs

 outputs information about where the library is installed. This command can be
 included in makefiles for programs that use PCRE, saving the programmer from
 having to remember too many details.

+The pkg-config command is another system for saving and retrieving information
+about installed libraries. Instead of separate commands for each library, a
+single command is used. For example:
+
+  pkg-config --cflags pcre
+
+The data is held in *.pc files that are installed in a directory called
+pkgconfig.
+

 Shared libraries on Unix-like systems
 -------------------------------------

-The default distribution builds PCRE as two shared libraries and two static
-libraries, as long as the operating system supports shared libraries. Shared
-library support relies on the "libtool" script which is built as part of the
+The default distribution builds PCRE as shared libraries and static libraries,
+as long as the operating system supports shared libraries. Shared library
+support relies on the "libtool" script which is built as part of the
 "configure" process.

 The libtool script is used to compile and link both shared and static
@@ -158,7 +235,7 @@ installed themselves. However, the versions left in the source directory still
 use the uninstalled libraries.

 To build PCRE using static libraries only you must use --disable-shared when
-configuring it. For example
+configuring it. For example:

 ./configure --prefix=/usr/gnu --disable-shared

@@ -174,7 +251,8 @@ order to cross-compile PCRE for some other host. However, during the building
 process, the dftables.c source file is compiled *and run* on the local host, in
 order to generate the default character tables (the chartables.c file). It
 therefore needs to be compiled with the local compiler, not the cross compiler.
-You can do this by specifying CC_FOR_BUILD (and if necessary CFLAGS_FOR_BUILD)
+You can do this by specifying CC_FOR_BUILD (and if necessary CFLAGS_FOR_BUILD;
+there are also CXX_FOR_BUILD and CXXFLAGS_FOR_BUILD for the C++ wrapper)
 when calling the "configure" command. If they are not specified, they default
 to the values of CC and CFLAGS.

@@ -196,15 +274,21 @@ Testing PCRE
 ------------

 To test PCRE on a Unix system, run the RunTest script that is created by the
-configuring process. (This can also be run by "make runtest", "make check", or
-"make test".) For other systems, see the instructions in NON-UNIX-USE.
+configuring process. There is also a script called RunGrepTest that tests the
+options of the pcregrep command. If the C++ wrapper library is build, three
+test programs called pcrecpp_unittest, pcre_scanner_unittest, and
+pcre_stringpiece_unittest are provided.

-The script runs the pcretest test program (which is documented in its own man
-page) on each of the testinput files (in the testdata directory) in turn,
-and compares the output with the contents of the corresponding testoutput file.
-A file called testtry is used to hold the output from pcretest. To run pcretest
-on just one of the test files, give its number as an argument to RunTest, for
-example:
+Both the scripts and all the program tests are run if you obey "make runtest",
+"make check", or "make test". For other systems, see the instructions in
+NON-UNIX-USE.
+
+The RunTest script runs the pcretest test program (which is documented in its
+own man page) on each of the testinput files (in the testdata directory) in
+turn, and compares the output with the contents of the corresponding testoutput
+file. A file called testtry is used to hold the main output from pcretest
+(testsavedregex is also used as a working file). To run pcretest on just one of
+the test files, give its number as an argument to RunTest, for example:

  RunTest 2

@@ -247,19 +331,28 @@ running "configure". This file can be also fed directly to the perltest script,
 provided you are running Perl 5.8 or higher. (For Perl 5.6, a small patch,
 commented in the script, can be be used.)

-The fifth and final file tests error handling with UTF-8 encoding, and internal
-UTF-8 features of PCRE that are not relevant to Perl.
+The fifth test checks error handling with UTF-8 encoding, and internal UTF-8
+features of PCRE that are not relevant to Perl.
+
+The sixth and test checks the support for Unicode character properties. It it
+not run automatically unless PCRE is built with Unicode property support. To to
+this you must set --enable-unicode-properties when running "configure".
+
+The seventh, eighth, and ninth tests check the pcre_dfa_exec() alternative
+matching function, in non-UTF-8 mode, UTF-8 mode, and UTF-8 mode with Unicode
+property support, respectively. The eighth and ninth tests are not run
+automatically unless PCRE is build with the relevant support.


 Character tables
 ----------------

-PCRE uses four tables for manipulating and identifying characters. The final
-argument of the pcre_compile() function is a pointer to a block of memory
-containing the concatenated tables. A call to pcre_maketables() can be used to
-generate a set of tables in the current locale. If the final argument for
-pcre_compile() is passed as NULL, a set of default tables that is built into
-the binary is used.
+PCRE uses four tables for manipulating and identifying characters whose values
+are less than 256. The final argument of the pcre_compile() function is a
+pointer to a block of memory containing the concatenated tables. A call to
+pcre_maketables() can be used to generate a set of tables in the current
+locale. If the final argument for pcre_compile() is passed as NULL, a set of
+default tables that is built into the binary is used.

 The source file called chartables.c contains the default set of tables. This is
 not supplied in the distribution, but is built by the program dftables
@@ -299,18 +392,47 @@ The distribution should contain the following files:
    headers:

  dftables.c            auxiliary program for building chartables.c
-  get.c                 )
-  maketables.c          )
-  study.c               ) source of
-  pcre.c                )   the functions
+
  pcreposix.c           )
-  printint.c            )
+  pcre_compile.c        )
+  pcre_config.c         )
+  pcre_dfa_exec.c       )
+  pcre_exec.c           )
+  pcre_fullinfo.c       )
+  pcre_get.c            ) sources for the functions in the library,
+  pcre_globals.c        )   and some internal functions that they use
+  pcre_info.c           )
+  pcre_maketables.c     )
+  pcre_ord2utf8.c       )
+  pcre_printint.c       )
+  pcre_study.c          )
+  pcre_tables.c         )
+  pcre_try_flipped.c    )
+  pcre_ucp_findchar.c   )
+  pcre_valid_utf8.c     )
+  pcre_version.c        )
+  pcre_xclass.c         )
+
+  ucp_findchar.c        )
+  ucp.h                 ) source for the code that is used for
+  ucpinternal.h         )   Unicode property handling
+  ucptable.c            )
+  ucptypetable.c        )
+
  pcre.in               "source" for the header for the external API; pcre.h
                          is built from this by "configure"
  pcreposix.h           header for the external POSIX wrapper API
-  internal.h            header for internal use
+  pcre_internal.h       header for internal use
  config.in             template for config.h, which is built by configure

+  pcrecpp.h.in          "source" for the header file for the C++ wrapper
+  pcrecpp.cc            )
+  pcre_scanner.cc       ) source for the C++ wrapper library
+
+  pcre_stringpiece.h.in "source" for pcre_stringpiece.h, the header for the
+                          C++ stringpiece functions
+  pcre_stringpiece.cc   source for the C++ stringpiece functions
+
 (B) Auxiliary files:

  AUTHORS               information about the author of PCRE
@@ -323,6 +445,7 @@ The distribution should contain the following files:
  NON-UNIX-USE          notes on building PCRE on non-Unix systems
  README                this file
  RunTest.in            template for a Unix shell script for running tests
+  RunGrepTest.in        template for a Unix shell script for pcregrep tests
  config.guess          ) files used by libtool,
  config.sub            )   used only when building a shared library
  configure             a configuring shell script (built by autoconf)
@@ -335,31 +458,32 @@ The distribution should contain the following files:
  doc/pcretest.txt      plain text documentation of test program
  doc/perltest.txt      plain text documentation of Perl test program
  install-sh            a shell script for installing files
+  libpcre.pc.in         "source" for libpcre.pc for pkg-config
  ltmain.sh             file used to build a libtool script
+  mkinstalldirs         script for making install directories
  pcretest.c            comprehensive test program
  pcredemo.c            simple demonstration of coding calls to PCRE
  perltest              Perl test program
  pcregrep.c            source of a grep utility that uses PCRE
  pcre-config.in        source of script which retains PCRE information
-  testdata/testinput1   test data, compatible with Perl
-  testdata/testinput2   test data for error messages and non-Perl things
-  testdata/testinput3   test data for locale-specific tests
-  testdata/testinput4   test data for UTF-8 tests compatible with Perl
-  testdata/testinput5   test data for other UTF-8 tests
-  testdata/testoutput1  test results corresponding to testinput1
-  testdata/testoutput2  test results corresponding to testinput2
-  testdata/testoutput3  test results corresponding to testinput3
-  testdata/testoutput4  test results corresponding to testinput4
-  testdata/testoutput5  test results corresponding to testinput5
+  pcrecpp_unittest.c           )
+  pcre_scanner_unittest.c      ) test programs for the C++ wrapper
+  pcre_stringpiece_unittest.c  )
+  testdata/testinput*   test data for main library tests
+  testdata/testoutput*  expected test results
+  testdata/grep*        input and output for pcregrep tests

 (C) Auxiliary files for Win32 DLL

-  dll.mk
+  libpcre.def
+  libpcreposix.def
  pcre.def

 (D) Auxiliary file for VPASCAL

  makevp.bat

-Philip Hazel <ph10@cam.ac.uk>
-December 2003
+Philip Hazel
+Email local part: ph10
+Email domain: cam.ac.uk
+June 2005
@@ -2,52 +2,55 @@
 *      Perl-Compatible Regular Expressions       *
 *************************************************/

-/*
-PCRE is a library of functions to support regular expressions whose syntax
+/* PCRE is a library of functions to support regular expressions whose syntax
 and semantics are as close as possible to those of the Perl 5 language.

-Written by: Philip Hazel <ph10@cam.ac.uk>
-
-           Copyright (c) 1997-2003 University of Cambridge
+                       Written by Philip Hazel
+           Copyright (c) 1997-2005 University of Cambridge

 -----------------------------------------------------------------------------
-Permission is granted to anyone to use this software for any purpose on any
-computer system, and to redistribute it freely, subject to the following
-restrictions:
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:

-1. This software is distributed in the hope that it will be useful,
-   but WITHOUT ANY WARRANTY; without even the implied warranty of
-   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.

-2. The origin of this software must not be misrepresented, either by
-   explicit claim or by omission.
+    * 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.

-3. Altered versions must be plainly marked as such, and must not be
-   misrepresented as being the original software.
+    * 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.

-4. If PCRE is embedded in any software that is released under the GNU
-   General Purpose Licence (GPL), then the terms of that licence shall
-   supersede any condition above with which it is incompatible.
+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.
 -----------------------------------------------------------------------------
-
-See the file Tech.Notes for some information on the internals.
 */


-/* This is a support program to generate the file chartables.c, containing
-character tables of various kinds. They are built according to the default C
-locale and used as the default tables by PCRE. Now that pcre_maketables is
-a function visible to the outside world, we make use of its code from here in
-order to be consistent. */
+/* This is a freestanding support program to generate a file containing default
+character tables for PCRE. The tables are built according to the default C
+locale. Now that pcre_maketables is a function visible to the outside world, we
+make use of its code from here in order to be consistent. */

 #include <ctype.h>
 #include <stdio.h>
 #include <string.h>

-#include "internal.h"
+#include "pcre_internal.h"

-#define DFTABLES          /* maketables.c notices this */
-#include "maketables.c"
+#define DFTABLES          /* pcre_maketables.c notices this */
+#include "pcre_maketables.c"


 int main(int argc, char **argv)
@@ -55,6 +58,7 @@ int main(int argc, char **argv)
 int i;
 FILE *f;
 const unsigned char *tables = pcre_maketables();
+const unsigned char *base_of_tables = tables;

 if (argc != 2)
  {
@@ -62,7 +66,7 @@ if (argc != 2)
  return 1;
  }

-f = fopen(argv[1], "w");
+f = fopen(argv[1], "wb");
 if (f == NULL)
  {
  fprintf(stderr, "dftables: failed to open %s for writing\n", argv[1]);
@@ -80,10 +84,10 @@ fprintf(f,
  "program. If you edit it by hand, you might like to edit the Makefile to \n"
  "prevent its ever being regenerated.\n\n");
 fprintf(f,
-  "This file is #included in the compilation of pcre.c to build the default\n"
-  "character tables which are used when no tables are passed to the compile\n"
-  "function. */\n\n"
-  "static unsigned char pcre_default_tables[] = {\n\n"
+  "This file contains the default tables for characters with codes less than\n"
+  "128 (ASCII characters). These tables are used when no external tables are\n"
+  "passed to PCRE. */\n\n"
+  "const unsigned char _pcre_default_tables[] = {\n\n"
  "/* This table is a lower casing table. */\n\n");

 fprintf(f, "  ");
@@ -161,6 +165,7 @@ if (isprint(i-1)) fprintf(f, " %c ", i-1);
 fprintf(f, " */\n\n/* End of chartables.c */\n");

 fclose(f);
+free((void *)base_of_tables);
 return 0;
 }

@@ -1,6 +1,9 @@
 Technical Notes about PCRE
 --------------------------

+Historical note 1
+-----------------
+
 Many years ago I implemented some regular expression functions to an algorithm
 suggested by Martin Richards. These were not Unix-like in form, and were quite
 restricted in what they could do by comparison with Perl. The interesting part
@@ -9,12 +12,15 @@ form of an expression was known in advance. The code to apply an expression did
 not operate by backtracking, as the original Henry Spencer code and current
 Perl code does, but instead checked all possibilities simultaneously by keeping
 a list of current states and checking all of them as it advanced through the
-subject string. (In the terminology of Jeffrey Friedl's book, it was a "DFA
-algorithm".) When the pattern was all used up, all remaining states were
+subject string. In the terminology of Jeffrey Friedl's book, it was a "DFA
+algorithm". When the pattern was all used up, all remaining states were
 possible matches, and the one matching the longest subset of the subject string
 was chosen. This did not necessarily maximize the individual wild portions of
 the pattern, as is expected in Unix and Perl-style regular expressions.

+Historical note 2
+-----------------
+
 By contrast, the code originally written by Henry Spencer and subsequently
 heavily modified for Perl actually compiles the expression twice: once in a
 dummy mode in order to find out how much store will be needed, and then for
@@ -23,23 +29,58 @@ optionally, minimizing in Perl) the amount of the subject that matches
 individual wild portions of the pattern. This is an "NFA algorithm" in Friedl's
 terminology.

-For the set of functions that forms PCRE (which are unrelated to those
-mentioned above), I tried at first to invent an algorithm that used an amount
-of store bounded by a multiple of the number of characters in the pattern, to
-save on compiling time. However, because of the greater complexity in Perl
-regular expressions, I couldn't do this. In any case, a first pass through the
-pattern is needed, for a number of reasons. PCRE works by running a very
-degenerate first pass to calculate a maximum store size, and then a second pass
-to do the real compile - which may use a bit less than the predicted amount of
-store. The idea is that this is going to turn out faster because the first pass
-is degenerate and the second pass can just store stuff straight into the
-vector. It does make the compiling functions bigger, of course, but they have
-got quite big anyway to handle all the Perl stuff.
+OK, here's the real stuff
+-------------------------
+
+For the set of functions that form the "basic" PCRE library (which are
+unrelated to those mentioned above), I tried at first to invent an algorithm
+that used an amount of store bounded by a multiple of the number of characters
+in the pattern, to save on compiling time. However, because of the greater
+complexity in Perl regular expressions, I couldn't do this. In any case, a
+first pass through the pattern is needed, for a number of reasons. PCRE works
+by running a very degenerate first pass to calculate a maximum store size, and
+then a second pass to do the real compile - which may use a bit less than the
+predicted amount of store. The idea is that this is going to turn out faster
+because the first pass is degenerate and the second pass can just store stuff
+straight into the vector, which it knows is big enough. It does make the
+compiling functions bigger, of course, but they have got quite big anyway to
+handle all the Perl stuff.
+
+Traditional matching function
+-----------------------------
+
+The "traditional", and original, matching function is called pcre_exec(), and 
+it implements an NFA algorithm, similar to the original Henry Spencer algorithm 
+and the way that Perl works. Not surprising, since it is intended to be as 
+compatible with Perl as possible. This is the function most users of PCRE will 
+use most of the time.
+
+Supplementary matching function
+-------------------------------
+
+From PCRE 6.0, there is also a supplementary matching function called 
+pcre_dfa_exec(). This implements a DFA matching algorithm that searches 
+simultaneously for all possible matches that start at one point in the subject 
+string. (Going back to my roots: see Historical Note 1 above.) This function 
+intreprets the same compiled pattern data as pcre_exec(); however, not all the 
+facilities are available, and those that are don't always work in quite the 
+same way. See the user documentation for details.
+
+Format of compiled patterns
+---------------------------

 The compiled form of a pattern is a vector of bytes, containing items of
 variable length. The first byte in an item is an opcode, and the length of the
-item is either implicit in the opcode or contained in the data bytes which
-follow it. A list of all the opcodes follows:
+item is either implicit in the opcode or contained in the data bytes that
+follow it. 
+
+In many cases below "two-byte" data values are specified. This is in fact just
+a default. PCRE can be compiled to use 3-byte or 4-byte values (impairing the
+performance). This is necessary only when patterns whose compiled length is
+greater than 64K are going to be processed. In this description, we assume the 
+"normal" compilation options.
+
+A list of all the opcodes follows:

 Opcodes with no following data
 ------------------------------
@@ -48,7 +89,7 @@ These items are all just one byte long

  OP_END                 end of pattern
  OP_ANY                 match any character
-  OP_ANYBYTE             match any single byte, even in UTF-8 mode 
+  OP_ANYBYTE             match any single byte, even in UTF-8 mode
  OP_SOD                 match start of data: \A
  OP_SOM,                start of match (subject + offset): \G
  OP_CIRC                ^ (start of data, or after \n in multiline)
@@ -63,13 +104,14 @@ These items are all just one byte long
  OP_EODN                match end of data or \n at end: \Z
  OP_EOD                 match end of data: \z
  OP_DOLL                $ (end of data, or before \n in multiline)
-
+  OP_EXTUNI              match an extended Unicode character 
+  

 Repeating single characters
 ---------------------------

-The common repeats (*, +, ?) when applied to a single character appear as
-two-byte items using the following opcodes:
+The common repeats (*, +, ?) when applied to a single character use the
+following opcodes:

  OP_STAR
  OP_MINSTAR
@@ -78,6 +120,7 @@ two-byte items using the following opcodes:
  OP_QUERY
  OP_MINQUERY

+In ASCII mode, these are two-byte items; in UTF-8 mode, the length is variable.
 Those with "MIN" in their name are the minimizing versions. Each is followed by
 the character that is to be repeated. Other repeats make use of

@@ -109,39 +152,52 @@ byte. The opcodes are:
  OP_TYPEEXACT


-Matching a character string
+Match by Unicode property
+-------------------------
+
+OP_PROP and OP_NOTPROP are used for positive and negative matches of a 
+character by testing its Unicode property (the \p and \P escape sequences).
+Each is followed by a single byte that encodes the desired property value.
+
+Repeats of these items use the OP_TYPESTAR etc. set of opcodes, followed by two 
+bytes: OP_PROP or OP_NOTPROP and then the desired property value.
+
+
+Matching literal characters
 ---------------------------

-The OP_CHARS opcode is followed by a one-byte count and then that number of
-characters. If there are more than 255 characters in sequence, successive
-instances of OP_CHARS are used.
+The OP_CHAR opcode is followed by a single character that is to be matched 
+casefully. For caseless matching, OP_CHARNC is used. In UTF-8 mode, the 
+character may be more than one byte long. (Earlier versions of PCRE used 
+multi-character strings, but this was changed to allow some new features to be 
+added.)


 Character classes
 -----------------

-If there is only one character, OP_CHARS is used for a positive class,
-and OP_NOT for a negative one (that is, for something like [^a]). However, in 
-UTF-8 mode, this applies only to characters with values < 128, because OP_NOT 
-is confined to single bytes.
+If there is only one character, OP_CHAR or OP_CHARNC is used for a positive
+class, and OP_NOT for a negative one (that is, for something like [^a]).
+However, in UTF-8 mode, the use of OP_NOT applies only to characters with
+values < 128, because OP_NOT is confined to single bytes.

 Another set of repeating opcodes (OP_NOTSTAR etc.) are used for a repeated,
 negated, single-character class. The normal ones (OP_STAR etc.) are used for a
 repeated positive single-character class.

 When there's more than one character in a class and all the characters are less
-than 256, OP_CLASS is used for a positive class, and OP_NCLASS for a negative 
+than 256, OP_CLASS is used for a positive class, and OP_NCLASS for a negative
 one. In either case, the opcode is followed by a 32-byte bit map containing a 1
 bit for every character that is acceptable. The bits are counted from the least
 significant end of each byte.

-The reason for having both OP_CLASS and OP_NCLASS is so that, in UTF-8 mode, 
-subject characters with values greater than 256 can be handled correctly. For 
+The reason for having both OP_CLASS and OP_NCLASS is so that, in UTF-8 mode,
+subject characters with values greater than 256 can be handled correctly. For
 OP_CLASS they don't match, whereas for OP_NCLASS they do.

 For classes containing characters with values > 255, OP_XCLASS is used. It
 optionally uses a bit map (if any characters lie within it), followed by a list
-of pairs and single characters. There is a flag character than indicates 
+of pairs and single characters. There is a flag character than indicates
 whether it's a positive or a negative class.


@@ -191,15 +247,15 @@ number. This opcode is ignored while matching, but is fished out when handling
 the bracket itself. (They could have all been done like this, but I was making
 minimal changes.)

-A bracket opcode is followed by two bytes which give the offset to the next
-alternative OP_ALT or, if there aren't any branches, to the matching KET
-opcode. Each OP_ALT is followed by two bytes giving the offset to the next one,
-or to the KET opcode.
+A bracket opcode is followed by LINK_SIZE bytes which give the offset to the
+next alternative OP_ALT or, if there aren't any branches, to the matching
+OP_KET opcode. Each OP_ALT is followed by LINK_SIZE bytes giving the offset to
+the next one, or to the OP_KET opcode.

 OP_KET is used for subpatterns that do not repeat indefinitely, while
 OP_KETRMIN and OP_KETRMAX are used for indefinite repetitions, minimally or
-maximally respectively. All three are followed by two bytes giving (as a
-positive number) the offset back to the matching BRA opcode.
+maximally respectively. All three are followed by LINK_SIZE bytes giving (as a
+positive number) the offset back to the matching OP_BRA opcode.

 If a subpattern is quantified such that it is permitted to match zero times, it
 is preceded by one of OP_BRAZERO or OP_BRAMINZERO. These are single-byte
@@ -207,15 +263,14 @@ opcodes which tell the matcher that skipping this subpattern entirely is a
 valid branch.

 A subpattern with an indefinite maximum repetition is replicated in the
-compiled data its minimum number of times (or once with a BRAZERO if the
-minimum is zero), with the final copy terminating with a KETRMIN or KETRMAX as
-appropriate.
+compiled data its minimum number of times (or once with OP_BRAZERO if the
+minimum is zero), with the final copy terminating with OP_KETRMIN or OP_KETRMAX
+as appropriate.

 A subpattern with a bounded maximum repetition is replicated in a nested
-fashion up to the maximum number of times, with BRAZERO or BRAMINZERO before
-each replication after the minimum, so that, for example, (abc){2,5} is
-compiled as (abc)(abc)((abc)((abc)(abc)?)?)?. The 99 and 200 bracket limits do
-not apply to these internally generated brackets.
+fashion up to the maximum number of times, with OP_BRAZERO or OP_BRAMINZERO
+before each replication after the minimum, so that, for example, (abc){2,5} is
+compiled as (abc)(abc)((abc)((abc)(abc)?)?)?.


 Assertions
@@ -260,8 +315,11 @@ from the start of the whole pattern.
 Callout
 -------

-OP_CALLOUT is followed by one byte of data that holds a callout number in the 
-range 0 to 255.
+OP_CALLOUT is followed by one byte of data that holds a callout number in the
+range 0 to 254 for manual callouts, or 255 for an automatic callout. In both 
+cases there follows a two-byte value giving the offset in the pattern to the
+start of the following item, and another two-byte item giving the length of the
+next item.


 Changing options
@@ -278,4 +336,4 @@ at compile time, and so does not cause anything to be put into the compiled
 data.

 Philip Hazel
-August 2003
+March 2005
@@ -0,0 +1,20 @@
+LIBRARY libpcre
+EXPORTS
+pcre_malloc
+pcre_free
+pcre_config
+pcre_callout
+pcre_compile
+pcre_copy_substring
+pcre_dfa_exec
+pcre_exec
+pcre_get_substring
+pcre_get_stringnumber
+pcre_get_substring_list
+pcre_free_substring
+pcre_free_substring_list
+pcre_info
+pcre_fullinfo
+pcre_maketables
+pcre_study
+pcre_version
@@ -0,0 +1,25 @@
+LIBRARY libpcreposix
+EXPORTS
+pcre_malloc
+pcre_free
+pcre_config
+pcre_callout
+pcre_compile
+pcre_copy_substring
+pcre_dfa_exec
+pcre_exec
+pcre_get_substring
+pcre_get_stringnumber
+pcre_get_substring_list
+pcre_free_substring
+pcre_free_substring_list
+pcre_info
+pcre_fullinfo
+pcre_maketables
+pcre_study
+pcre_version
+
+regcomp
+regexec
+regerror
+regfree
@@ -5,6 +5,7 @@ pcre_free DATA

 pcre_compile
 pcre_copy_substring
+pcre_dfa_exec
 pcre_exec
 pcre_get_substring
 pcre_get_substring_list
@@ -2,7 +2,39 @@
 *       Perl-Compatible Regular Expressions      *
 *************************************************/

-/* Copyright (c) 1997-2003 University of Cambridge */
+/* In its original form, this is the .in file that is transformed by
+"configure" into pcre.h.
+
+           Copyright (c) 1997-2005 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.
+-----------------------------------------------------------------------------
+*/

 #ifndef _PCRE_H
 #define _PCRE_H
@@ -12,11 +44,11 @@ make changes to pcre.in. */

 #include "php_compat.h"

-#define PCRE_MAJOR          4
-#define PCRE_MINOR          5
-#define PCRE_DATE           01-December-2003
+#define PCRE_MAJOR          6
+#define PCRE_MINOR          2
+#define PCRE_DATE           01-Aug-2005

-/* Win32 uses DLL by default */
+/* Win32 uses DLL by default; it needs special stuff for exported functions. */

 #ifdef _WIN32
 #  ifdef PCRE_DEFINITION
@@ -29,8 +61,15 @@ make changes to pcre.in. */
 #    endif
 #  endif
 #endif
+
+/* For other operating systems, we use the standard "extern". */
+
 #ifndef PCRE_DATA_SCOPE
-#  define PCRE_DATA_SCOPE     extern
+#  ifdef __cplusplus
+#    define PCRE_DATA_SCOPE     extern "C"
+#  else
+#    define PCRE_DATA_SCOPE     extern
+#  endif
 #endif

 /* Have to include stdlib.h in order to ensure that size_t is defined;
@@ -46,20 +85,25 @@ extern "C" {

 /* Options */

-#define PCRE_CASELESS           0x0001
-#define PCRE_MULTILINE          0x0002
-#define PCRE_DOTALL             0x0004
-#define PCRE_EXTENDED           0x0008
-#define PCRE_ANCHORED           0x0010
-#define PCRE_DOLLAR_ENDONLY     0x0020
-#define PCRE_EXTRA              0x0040
-#define PCRE_NOTBOL             0x0080
-#define PCRE_NOTEOL             0x0100
-#define PCRE_UNGREEDY           0x0200
-#define PCRE_NOTEMPTY           0x0400
-#define PCRE_UTF8               0x0800
-#define PCRE_NO_AUTO_CAPTURE    0x1000
-#define PCRE_NO_UTF8_CHECK      0x2000
+#define PCRE_CASELESS           0x00000001
+#define PCRE_MULTILINE          0x00000002
+#define PCRE_DOTALL             0x00000004
+#define PCRE_EXTENDED           0x00000008
+#define PCRE_ANCHORED           0x00000010
+#define PCRE_DOLLAR_ENDONLY     0x00000020
+#define PCRE_EXTRA              0x00000040
+#define PCRE_NOTBOL             0x00000080
+#define PCRE_NOTEOL             0x00000100
+#define PCRE_UNGREEDY           0x00000200
+#define PCRE_NOTEMPTY           0x00000400
+#define PCRE_UTF8               0x00000800
+#define PCRE_NO_AUTO_CAPTURE    0x00001000
+#define PCRE_NO_UTF8_CHECK      0x00002000
+#define PCRE_AUTO_CALLOUT       0x00004000
+#define PCRE_PARTIAL            0x00008000
+#define PCRE_DFA_SHORTEST       0x00010000
+#define PCRE_DFA_RESTART        0x00020000
+#define PCRE_FIRSTLINE          0x00040000

 /* Exec-time and get/set-time error codes */

@@ -74,6 +118,15 @@ extern "C" {
 #define PCRE_ERROR_CALLOUT         (-9)  /* Never used by PCRE itself */
 #define PCRE_ERROR_BADUTF8        (-10)
 #define PCRE_ERROR_BADUTF8_OFFSET (-11)
+#define PCRE_ERROR_PARTIAL        (-12)
+#define PCRE_ERROR_BADPARTIAL     (-13)
+#define PCRE_ERROR_INTERNAL       (-14)
+#define PCRE_ERROR_BADCOUNT       (-15)
+#define PCRE_ERROR_DFA_UITEM      (-16)
+#define PCRE_ERROR_DFA_UCOND      (-17)
+#define PCRE_ERROR_DFA_UMLIMIT    (-18)
+#define PCRE_ERROR_DFA_WSSIZE     (-19)
+#define PCRE_ERROR_DFA_RECURSE    (-20)

 /* Request types for pcre_fullinfo() */

@@ -89,6 +142,7 @@ extern "C" {
 #define PCRE_INFO_NAMECOUNT          8
 #define PCRE_INFO_NAMETABLE          9
 #define PCRE_INFO_STUDYSIZE         10
+#define PCRE_INFO_DEFAULT_TABLES    11

 /* Request types for pcre_config() */

@@ -98,12 +152,14 @@ extern "C" {
 #define PCRE_CONFIG_POSIX_MALLOC_THRESHOLD  3
 #define PCRE_CONFIG_MATCH_LIMIT             4
 #define PCRE_CONFIG_STACKRECURSE            5
+#define PCRE_CONFIG_UNICODE_PROPERTIES      6

 /* Bit flags for the pcre_extra structure */

 #define PCRE_EXTRA_STUDY_DATA          0x0001
 #define PCRE_EXTRA_MATCH_LIMIT         0x0002
 #define PCRE_EXTRA_CALLOUT_DATA        0x0004
+#define PCRE_EXTRA_TABLES              0x0008

 /* Types */

@@ -111,13 +167,15 @@ struct real_pcre;                 /* declaration; the definition is private  */
 typedef struct real_pcre pcre;

 /* The structure for passing additional data to pcre_exec(). This is defined in
-such as way as to be extensible. */
+such as way as to be extensible. Always add new fields at the end, in order to
+remain compatible. */

 typedef struct pcre_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 */
 } pcre_extra;

 /* The structure for passing out data via the pcre_callout_function. We use a
@@ -133,19 +191,21 @@ typedef struct pcre_callout_block {
  const char  *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 */
+  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 */
  /* ------------------------------------------------------------------ */
 } pcre_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
-that is triggered by the (?) regex item. Some magic is required for Win32 DLL;
-it is null on other OS. For Virtual Pascal, these have to be different again.
-*/
+that is triggered by the (?) regex item. For Virtual Pascal, these definitions
+have to take another form. */

 #ifndef VPCOMPAT
 PCRE_DATA_SCOPE void *(*pcre_malloc)(size_t);
@@ -154,39 +214,44 @@ PCRE_DATA_SCOPE void *(*pcre_stack_malloc)(size_t);
 PCRE_DATA_SCOPE void  (*pcre_stack_free)(void *);
 PCRE_DATA_SCOPE int   (*pcre_callout)(pcre_callout_block *);
 #else   /* VPCOMPAT */
-extern void *pcre_malloc(size_t);
-extern void  pcre_free(void *);
-extern void *pcre_stack_malloc(size_t);
-extern void  pcre_stack_free(void *);
-extern int   pcre_callout(pcre_callout_block *);
+PCRE_DATA_SCOPE void *pcre_malloc(size_t);
+PCRE_DATA_SCOPE void  pcre_free(void *);
+PCRE_DATA_SCOPE void *pcre_stack_malloc(size_t);
+PCRE_DATA_SCOPE void  pcre_stack_free(void *);
+PCRE_DATA_SCOPE int   pcre_callout(pcre_callout_block *);
 #endif  /* VPCOMPAT */

 /* Exported PCRE functions */

-extern pcre *pcre_compile(const char *, int, const char **,
-              int *, const unsigned char *);
-extern int  pcre_config(int, void *);
-extern int  pcre_copy_named_substring(const pcre *, const char *,
-              int *, int, const char *, char *, int);
-extern int  pcre_copy_substring(const char *, int *, int, int,
-              char *, int);
-extern int  pcre_exec(const pcre *, const pcre_extra *,
-              const char *, int, int, int, int *, int);
-extern void pcre_free_substring(const char *);
-extern void pcre_free_substring_list(const char **);
-extern int  pcre_fullinfo(const pcre *, const pcre_extra *, int,
-              void *);
-extern int  pcre_get_named_substring(const pcre *, const char *,
-              int *, int,  const char *, const char **);
-extern int  pcre_get_stringnumber(const pcre *, const char *);
-extern int  pcre_get_substring(const char *, int *, int, int,
-              const char **);
-extern int  pcre_get_substring_list(const char *, int *, int,
-              const char ***);
-extern int  pcre_info(const pcre *, int *, int *);
-extern const unsigned char *pcre_maketables(void);
-extern pcre_extra *pcre_study(const pcre *, int, const char **);
-extern const char *pcre_version(void);
+PCRE_DATA_SCOPE pcre *pcre_compile(const char *, int, const char **, int *,
+                  const unsigned char *);
+PCRE_DATA_SCOPE pcre *pcre_compile2(const char *, int, int *, const char **,
+                  int *, const unsigned char *);
+PCRE_DATA_SCOPE int  pcre_config(int, void *);
+PCRE_DATA_SCOPE int  pcre_copy_named_substring(const pcre *, const char *,
+                  int *, int, const char *, char *, int);
+PCRE_DATA_SCOPE int  pcre_copy_substring(const char *, int *, int, int, char *,
+                  int);
+PCRE_DATA_SCOPE int  pcre_dfa_exec(const pcre *, const pcre_extra *,
+                  const char *, int, int, int, int *, int , int *, int);
+PCRE_DATA_SCOPE int  pcre_exec(const pcre *, const pcre_extra *, const char *,
+                   int, int, int, int *, int);
+PCRE_DATA_SCOPE void pcre_free_substring(const char *);
+PCRE_DATA_SCOPE void pcre_free_substring_list(const char **);
+PCRE_DATA_SCOPE int  pcre_fullinfo(const pcre *, const pcre_extra *, int,
+                  void *);
+PCRE_DATA_SCOPE int  pcre_get_named_substring(const pcre *, const char *,
+                  int *, int, const char *, const char **);
+PCRE_DATA_SCOPE int  pcre_get_stringnumber(const pcre *, const char *);
+PCRE_DATA_SCOPE int  pcre_get_substring(const char *, int *, int, int,
+                  const char **);
+PCRE_DATA_SCOPE int  pcre_get_substring_list(const char *, int *, int,
+                  const char ***);
+PCRE_DATA_SCOPE int  pcre_info(const pcre *, int *, int *);
+PCRE_DATA_SCOPE const unsigned char *pcre_maketables(void);
+PCRE_DATA_SCOPE int  pcre_refcount(pcre *, int);
+PCRE_DATA_SCOPE pcre_extra *pcre_study(const pcre *, int, const char **);
+PCRE_DATA_SCOPE const char *pcre_version(void);

 #ifdef __cplusplus
 }  /* extern "C" */
@@ -6,11 +6,11 @@
 program. If you edit it by hand, you might like to edit the Makefile to 
 prevent its ever being regenerated.

-This file is #included in the compilation of pcre.c to build the default
-character tables which are used when no tables are passed to the compile
-function. */
+This file contains the default tables for characters with codes less than
+128 (ASCII characters). These tables are used when no external tables are
+passed to PCRE. */

-static unsigned char pcre_default_tables[] = {
+const unsigned char _pcre_default_tables[] = {

 /* This table is a lower casing table. */

@@ -0,0 +1,112 @@
+/*************************************************
+*      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) 1997-2005 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_config(). */
+
+
+#include "pcre_internal.h"
+
+
+/*************************************************
+* Return info about what features are configured *
+*************************************************/
+
+/* This function has an extensible interface so that additional items can be
+added compatibly.
+
+Arguments:
+  what             what information is required
+  where            where to put the information
+
+Returns:           0 if data returned, negative on error
+*/
+
+EXPORT int
+pcre_config(int what, void *where)
+{
+switch (what)
+  {
+  case PCRE_CONFIG_UTF8:
+#ifdef SUPPORT_UTF8
+  *((int *)where) = 1;
+#else
+  *((int *)where) = 0;
+#endif
+  break;
+
+  case PCRE_CONFIG_UNICODE_PROPERTIES:
+#ifdef SUPPORT_UCP
+  *((int *)where) = 1;
+#else
+  *((int *)where) = 0;
+#endif
+  break;
+
+  case PCRE_CONFIG_NEWLINE:
+  *((int *)where) = NEWLINE;
+  break;
+
+  case PCRE_CONFIG_LINK_SIZE:
+  *((int *)where) = LINK_SIZE;
+  break;
+
+  case PCRE_CONFIG_POSIX_MALLOC_THRESHOLD:
+  *((int *)where) = POSIX_MALLOC_THRESHOLD;
+  break;
+
+  case PCRE_CONFIG_MATCH_LIMIT:
+  *((unsigned int *)where) = MATCH_LIMIT;
+  break;
+
+  case PCRE_CONFIG_STACKRECURSE:
+#ifdef NO_RECURSE
+  *((int *)where) = 0;
+#else
+  *((int *)where) = 1;
+#endif
+  break;
+
+  default: return PCRE_ERROR_BADOPTION;
+  }
+
+return 0;
+}
+
+/* End of pcre_config.c */
@@ -0,0 +1,149 @@
+/*************************************************
+*      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) 1997-2005 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_fullinfo(), which returns
+information about a compiled pattern. */
+
+
+#include "pcre_internal.h"
+
+
+/*************************************************
+*        Return info about compiled pattern      *
+*************************************************/
+
+/* This is a newer "info" function which has an extensible interface so
+that additional items can be added compatibly.
+
+Arguments:
+  argument_re      points to compiled code
+  extra_data       points extra data, or NULL
+  what             what information is required
+  where            where to put the information
+
+Returns:           0 if data returned, negative on error
+*/
+
+EXPORT int
+pcre_fullinfo(const pcre *argument_re, const pcre_extra *extra_data, int what,
+  void *where)
+{
+real_pcre internal_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;
+
+if (extra_data != NULL && (extra_data->flags & PCRE_EXTRA_STUDY_DATA) != 0)
+  study = (const pcre_study_data *)extra_data->study_data;
+
+if (re->magic_number != MAGIC_NUMBER)
+  {
+  re = _pcre_try_flipped(re, &internal_re, study, &internal_study);
+  if (re == NULL) return PCRE_ERROR_BADMAGIC;
+  if (study != NULL) study = &internal_study;
+  }
+
+switch (what)
+  {
+  case PCRE_INFO_OPTIONS:
+  *((unsigned long int *)where) = re->options & PUBLIC_OPTIONS;
+  break;
+
+  case PCRE_INFO_SIZE:
+  *((size_t *)where) = re->size;
+  break;
+
+  case PCRE_INFO_STUDYSIZE:
+  *((size_t *)where) = (study == NULL)? 0 : study->size;
+  break;
+
+  case PCRE_INFO_CAPTURECOUNT:
+  *((int *)where) = re->top_bracket;
+  break;
+
+  case PCRE_INFO_BACKREFMAX:
+  *((int *)where) = re->top_backref;
+  break;
+
+  case PCRE_INFO_FIRSTBYTE:
+  *((int *)where) =
+    ((re->options & PCRE_FIRSTSET) != 0)? re->first_byte :
+    ((re->options & PCRE_STARTLINE) != 0)? -1 : -2;
+  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) =
+    (study != NULL && (study->options & PCRE_STUDY_MAPPED) != 0)?
+      ((const pcre_study_data *)extra_data->study_data)->start_bits : NULL;
+  break;
+
+  case PCRE_INFO_LASTLITERAL:
+  *((int *)where) =
+    ((re->options & PCRE_REQCHSET) != 0)? re->req_byte : -1;
+  break;
+
+  case PCRE_INFO_NAMEENTRYSIZE:
+  *((int *)where) = re->name_entry_size;
+  break;
+
+  case PCRE_INFO_NAMECOUNT:
+  *((int *)where) = re->name_count;
+  break;
+
+  case PCRE_INFO_NAMETABLE:
+  *((const uschar **)where) = (const uschar *)re + re->name_table_offset;
+  break;
+
+  case PCRE_INFO_DEFAULT_TABLES:
+  *((const uschar **)where) = (const uschar *)(_pcre_default_tables);
+  break;
+
+  default: return PCRE_ERROR_BADOPTION;
+  }
+
+return 0;
+}
+
+/* End of pcre_fullinfo.c */
@@ -2,45 +2,48 @@
 *      Perl-Compatible Regular Expressions       *
 *************************************************/

-/*
-This 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. See
-the file Tech.Notes for some information on the internals.
+/* 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 <ph10@cam.ac.uk>
-
-           Copyright (c) 1997-2003 University of Cambridge
+                       Written by Philip Hazel
+           Copyright (c) 1997-2005 University of Cambridge

 -----------------------------------------------------------------------------
-Permission is granted to anyone to use this software for any purpose on any
-computer system, and to redistribute it freely, subject to the following
-restrictions:
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:

-1. This software is distributed in the hope that it will be useful,
-   but WITHOUT ANY WARRANTY; without even the implied warranty of
-   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.

-2. The origin of this software must not be misrepresented, either by
-   explicit claim or by omission.
+    * 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.

-3. Altered versions must be plainly marked as such, and must not be
-   misrepresented as being the original software.
+    * 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.

-4. If PCRE is embedded in any software that is released under the GNU
-   General Purpose Licence (GPL), then the terms of that licence shall
-   supersede any condition above with which it is incompatible.
+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 some convenience functions for extracting substrings
 from the subject string after a regex match has succeeded. The original idea
-for these functions came from Scott Wimer <scottw@cgibuilder.com>. */
+for these functions came from Scott Wimer. */


-/* Include the internals header, which itself includes Standard C headers plus
-the external pcre header. */
-
-#include "internal.h"
+#include "pcre_internal.h"


 /*************************************************
@@ -346,4 +349,4 @@ pcre_free_substring(const char *pointer)
 (pcre_free)((void *)pointer);
 }

-/* End of get.c */
+/* End of pcre_get.c */
@@ -0,0 +1,69 @@
+/*************************************************
+*      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) 1997-2005 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 global variables that are exported by the PCRE library.
+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
+differently, and global variables are not used (see pcre.in). */
+
+
+#include "pcre_internal.h"
+
+
+#ifndef VPCOMPAT
+#ifdef __cplusplus
+extern "C" void *(*pcre_malloc)(size_t) = malloc;
+extern "C" void  (*pcre_free)(void *) = free;
+extern "C" void *(*pcre_stack_malloc)(size_t) = malloc;
+extern "C" void  (*pcre_stack_free)(void *) = free;
+extern "C" int   (*pcre_callout)(pcre_callout_block *) = NULL;
+#else
+void *(*pcre_malloc)(size_t) = malloc;
+void  (*pcre_free)(void *) = free;
+void *(*pcre_stack_malloc)(size_t) = malloc;
+void  (*pcre_stack_free)(void *) = free;
+int   (*pcre_callout)(pcre_callout_block *) = NULL;
+#endif
+#endif
+
+/* End of pcre_globals.c */
@@ -0,0 +1,89 @@
+/*************************************************
+*      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) 1997-2005 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(). */
+
+
+#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
+*/
+
+EXPORT 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->options & PCRE_FIRSTSET) != 0)? re->first_byte :
+     ((re->options & PCRE_STARTLINE) != 0)? -1 : -2;
+return re->top_bracket;
+}
+
+/* End of pcre_info.c */
@@ -3,80 +3,129 @@
 *************************************************/


-/* This 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. See
-the file Tech.Notes for some information on the internals.
+/* 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 <ph10@cam.ac.uk>
-
-           Copyright (c) 1997-2003 University of Cambridge
+                       Written by Philip Hazel
+           Copyright (c) 1997-2005 University of Cambridge

 -----------------------------------------------------------------------------
-Permission is granted to anyone to use this software for any purpose on any
-computer system, and to redistribute it freely, subject to the following
-restrictions:
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:

-1. This software is distributed in the hope that it will be useful,
-   but WITHOUT ANY WARRANTY; without even the implied warranty of
-   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.

-2. The origin of this software must not be misrepresented, either by
-   explicit claim or by omission.
+    * 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.

-3. Altered versions must be plainly marked as such, and must not be
-   misrepresented as being the original software.
+    * 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.

-4. If PCRE is embedded in any software that is released under the GNU
-   General Purpose Licence (GPL), then the terms of that licence shall
-   supersede any condition above with which it is incompatible.
+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 header contains definitions that are shared between the different
-modules, but which are not relevant to the outside. */
+modules, but which are not relevant to the exported API. This includes some
+functions whose names all begin with "_pcre_". */
+
+
+/* Define DEBUG to get debugging output on stdout. */
+
+/****
+#define DEBUG
+****/
+
+/* Use a macro for debugging printing, 'cause that eliminates the use of #ifdef
+inline, and there are *still* stupid compilers about that don't like indented
+pre-processor statements, or at least there were when I first wrote this. After
+all, it had only been about 10 years then... */
+
+#ifdef DEBUG
+#define DPRINTF(p) printf p
+#else
+#define DPRINTF(p) /*nothing*/
+#endif
+

 /* Get the definitions provided by running "configure" */

 #ifdef PHP_WIN32
 # include "config.w32.h"
-#elif defined(NETWARE)
-# include "config.nw.h"
 #else
 # include <php_config.h>
 #endif

+/* Standard C headers plus the external interface definition. The only time
+setjmp and stdarg are used is when NO_RECURSE is set. */
+
+#include <ctype.h>
+#include <limits.h>
+#include <setjmp.h>
+#include <stdarg.h>
+#include <stddef.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
 #ifndef PCRE_SPY
 #define PCRE_DEFINITION       /* Win32 __declspec(export) trigger for .dll */
 #endif

-/* The value of NEWLINE determines the newline character. The default is to
-leave it up to the compiler, but some sites want to force a particular value.
-On Unix systems, "configure" can be used to override this default. */
+/* We need to have types that specify unsigned 16-bit and 32-bit integers. We
+cannot determine these outside the compilation (e.g. by running a program as
+part of "configure") because PCRE is often cross-compiled for use on other
+systems. Instead we make use of the maximum sizes that are available at
+preprocessor time in standard C environments. */

-#ifndef NEWLINE
-#define NEWLINE '\n'
+#if USHRT_MAX == 65535
+  typedef unsigned short pcre_uint16;
+#elif UINT_MAX == 65535
+  typedef unsigned int pcre_uint16;
+#else
+  #error Cannot determine a type for 16-bit unsigned integers
 #endif

-/* The value of MATCH_LIMIT determines the default number of times the match()
-function can be called during a single execution of pcre_exec(). (There is a
-runtime method of 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 Unix systems, "configure" can be used to override this
-default default. */
-
-#ifndef MATCH_LIMIT
-#define MATCH_LIMIT 10000000
+#if UINT_MAX == 4294967295
+  typedef unsigned int pcre_uint32;
+#elif ULONG_MAX == 4294967295
+  typedef unsigned long int pcre_uint32;
+#else
+  #error Cannot determine a type for 32-bit unsigned integers
 #endif

-/* If you are compiling for a system that needs some magic to be inserted
- * before the definition of an exported function, define this macro to contain
- * the relevant magic. It apears at the start of every exported function. */
-                                                                                                                                
-#define EXPORT
+/* All character handling must be done as unsigned characters. Otherwise there
+are problems with top-bit-set characters and functions such as isspace().
+However, we leave the interface to the outside world as char *, because that
+should make things easier for callers. We define a short type for unsigned char
+to save lots of typing. I tried "uchar", but it causes problems on Digital
+Unix, where it is defined in sys/types, so use "uschar" instead. */
+
+typedef unsigned char uschar;
+
+/* Include the public PCRE header */

 #include "pcre.h"

+/* Include the (copy of) the public ucp header, changing the external name into
+a private one. This does no harm, even if we aren't compiling UCP support. */
+
+#define ucp_findchar _pcre_ucp_findchar
+#include "ucp.h"
+
 /* When compiling for use with the Virtual Pascal compiler, these functions
 need to have their names changed. PCRE must be compiled with the -DVPCOMPAT
 option on the command line. */
@@ -95,18 +144,6 @@ neither (there some non-Unix environments where this is the case). This assumes
 that all calls to memmove are moving strings upwards in store, which is the
 case in PCRE. */

-/* Standard C headers plus the external interface definition. The only time
-setjmp and stdarg are used is when NO_RECURSE is set. */
-
-#include <ctype.h>
-#include <limits.h>
-#include <setjmp.h>
-#include <stdarg.h>
-#include <stddef.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-
 #if ! HAVE_MEMMOVE
 #undef  memmove        /* some systems may have a macro */
 #if HAVE_BCOPY
@@ -126,13 +163,14 @@ for (i = 0; i < n; ++i) *(--dest) =  *(--src);
 #endif   /* not VPCOMPAT */


-/* PCRE keeps offsets in its compiled code as 2-byte quantities by default.
-These are used, for example, to link from the start of a subpattern to its
-alternatives and its end. The use of 2 bytes per offset limits the size of the
-compiled regex to around 64K, which is big enough for almost everybody.
-However, I received a request for an even bigger limit. For this reason, and
-also to make the code easier to maintain, the storing and loading of offsets
-from the byte string is now handled by the macros that are defined here.
+/* PCRE keeps offsets in its compiled code as 2-byte quantities (always stored
+in big-endian order) by default. These are used, for example, to link from the
+start of a subpattern to its alternatives and its end. The use of 2 bytes per
+offset limits the size of the compiled regex to around 64K, which is big enough
+for almost everybody. However, I received a request for an even bigger limit.
+For this reason, and also to make the code easier to maintain, the storing and
+loading of offsets from the byte string is now handled by the macros that are
+defined here.

 The macros are controlled by the value of LINK_SIZE. This defaults to 2 in
 the config.h file, but can be overridden by using -D on the command line. This
@@ -201,6 +239,116 @@ capturing parenthesis numbers in back references. */
 #define PUT2INC(a,n,d)  PUT2(a,n,d), a += 2


+/* When UTF-8 encoding is being used, a character is no longer just a single
+byte. The macros for character handling generate simple sequences when used in
+byte-mode, and more complicated ones for UTF-8 characters. */
+
+#ifndef SUPPORT_UTF8
+#define GETCHAR(c, eptr) c = *eptr;
+#define GETCHARTEST(c, eptr) c = *eptr;
+#define GETCHARINC(c, eptr) c = *eptr++;
+#define GETCHARINCTEST(c, eptr) c = *eptr++;
+#define GETCHARLEN(c, eptr, len) c = *eptr;
+#define BACKCHAR(eptr)
+
+#else   /* SUPPORT_UTF8 */
+
+/* Get the next UTF-8 character, not advancing the pointer. This is called when
+we know we are in UTF-8 mode. */
+
+#define GETCHAR(c, eptr) \
+  c = *eptr; \
+  if ((c & 0xc0) == 0xc0) \
+    { \
+    int gcii; \
+    int gcaa = _pcre_utf8_table4[c & 0x3f];  /* Number of additional bytes */ \
+    int gcss = 6*gcaa; \
+    c = (c & _pcre_utf8_table3[gcaa]) << gcss; \
+    for (gcii = 1; gcii <= gcaa; gcii++) \
+      { \
+      gcss -= 6; \
+      c |= (eptr[gcii] & 0x3f) << gcss; \
+      } \
+    }
+
+/* Get the next UTF-8 character, testing for UTF-8 mode, and not advancing the
+pointer. */
+
+#define GETCHARTEST(c, eptr) \
+  c = *eptr; \
+  if (utf8 && (c & 0xc0) == 0xc0) \
+    { \
+    int gcii; \
+    int gcaa = _pcre_utf8_table4[c & 0x3f];  /* Number of additional bytes */ \
+    int gcss = 6*gcaa; \
+    c = (c & _pcre_utf8_table3[gcaa]) << gcss; \
+    for (gcii = 1; gcii <= gcaa; gcii++) \
+      { \
+      gcss -= 6; \
+      c |= (eptr[gcii] & 0x3f) << gcss; \
+      } \
+    }
+
+/* Get the next UTF-8 character, advancing the pointer. This is called when we
+know we are in UTF-8 mode. */
+
+#define GETCHARINC(c, eptr) \
+  c = *eptr++; \
+  if ((c & 0xc0) == 0xc0) \
+    { \
+    int gcaa = _pcre_utf8_table4[c & 0x3f];  /* Number of additional bytes */ \
+    int gcss = 6*gcaa; \
+    c = (c & _pcre_utf8_table3[gcaa]) << gcss; \
+    while (gcaa-- > 0) \
+      { \
+      gcss -= 6; \
+      c |= (*eptr++ & 0x3f) << gcss; \
+      } \
+    }
+
+/* Get the next character, testing for UTF-8 mode, and advancing the pointer */
+
+#define GETCHARINCTEST(c, eptr) \
+  c = *eptr++; \
+  if (utf8 && (c & 0xc0) == 0xc0) \
+    { \
+    int gcaa = _pcre_utf8_table4[c & 0x3f];  /* Number of additional bytes */ \
+    int gcss = 6*gcaa; \
+    c = (c & _pcre_utf8_table3[gcaa]) << gcss; \
+    while (gcaa-- > 0) \
+      { \
+      gcss -= 6; \
+      c |= (*eptr++ & 0x3f) << gcss; \
+      } \
+    }
+
+/* Get the next UTF-8 character, not advancing the pointer, incrementing length
+if there are extra bytes. This is called when we know we are in UTF-8 mode. */
+
+#define GETCHARLEN(c, eptr, len) \
+  c = *eptr; \
+  if ((c & 0xc0) == 0xc0) \
+    { \
+    int gcii; \
+    int gcaa = _pcre_utf8_table4[c & 0x3f];  /* Number of additional bytes */ \
+    int gcss = 6*gcaa; \
+    c = (c & _pcre_utf8_table3[gcaa]) << gcss; \
+    for (gcii = 1; gcii <= gcaa; gcii++) \
+      { \
+      gcss -= 6; \
+      c |= (eptr[gcii] & 0x3f) << gcss; \
+      } \
+    len += gcaa; \
+    }
+
+/* If the pointer is not at the start of a character, move it back until
+it is. Called only in UTF-8 mode. */
+
+#define BACKCHAR(eptr) while((*eptr & 0xc0) == 0x80) eptr--;
+
+#endif
+
+
 /* In case there is no definition of offsetof() provided - though any proper
 Standard C system should have one. */

@@ -208,6 +356,7 @@ Standard C system should have one. */
 #define offsetof(p_type,field) ((size_t)&(((p_type *)0)->field))
 #endif

+
 /* These are the public options that can change during matching. */

 #define PCRE_IMS (PCRE_CASELESS|PCRE_MULTILINE|PCRE_DOTALL)
@@ -215,32 +364,38 @@ Standard C system should have one. */
 /* Private options flags start at the most significant end of the four bytes,
 but skip the top bit so we can use ints for convenience without getting tangled
 with negative values. The public options defined in pcre.h start at the least
-significant end. Make sure they don't overlap, though now that we have expanded
-to four bytes there is plenty of space. */
+significant end. Make sure they don't overlap! */

 #define PCRE_FIRSTSET      0x40000000  /* first_byte is set */
 #define PCRE_REQCHSET      0x20000000  /* req_byte is set */
 #define PCRE_STARTLINE     0x10000000  /* start after \n for multiline */
 #define PCRE_ICHANGED      0x08000000  /* i option changes within regex */
+#define PCRE_NOPARTIAL     0x04000000  /* can't use partial with this regex */

 /* Options for the "extra" block produced by pcre_study(). */

 #define PCRE_STUDY_MAPPED   0x01     /* a map of starting chars exists */

-/* Masks for identifying the public options which are permitted at compile
-time, run time or study time, respectively. */
+/* Masks for identifying the public options that are permitted at compile
+time, run time, or study time, respectively. */

 #define PUBLIC_OPTIONS \
  (PCRE_CASELESS|PCRE_EXTENDED|PCRE_ANCHORED|PCRE_MULTILINE| \
   PCRE_DOTALL|PCRE_DOLLAR_ENDONLY|PCRE_EXTRA|PCRE_UNGREEDY|PCRE_UTF8| \
-   PCRE_NO_AUTO_CAPTURE|PCRE_NO_UTF8_CHECK)
+   PCRE_NO_AUTO_CAPTURE|PCRE_NO_UTF8_CHECK|PCRE_AUTO_CALLOUT|PCRE_FIRSTLINE)

 #define PUBLIC_EXEC_OPTIONS \
-  (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK)
+  (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK| \
+   PCRE_PARTIAL)
+
+#define PUBLIC_DFA_EXEC_OPTIONS \
+  (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK| \
+   PCRE_PARTIAL|PCRE_DFA_SHORTEST|PCRE_DFA_RESTART)

 #define PUBLIC_STUDY_OPTIONS 0   /* None defined */

-/* Magic number to provide a small check against being handed junk. */
+/* Magic number to provide a small check against being handed junk. Also used
+to detect whether a pattern was compiled on a host of different endianness. */

 #define MAGIC_NUMBER  0x50435245UL   /* 'PCRE' */

@@ -249,6 +404,11 @@ time, run time or study time, respectively. */
 #define REQ_UNSET (-2)
 #define REQ_NONE  (-1)

+/* The maximum remaining length of subject we are prepared to search for a
+req_byte match. */
+
+#define REQ_BYTE_MAX 1000
+
 /* Flags added to firstbyte or reqbyte; a "non-literal" item is either a
 variable-length repeat, or a anything other than literal characters. */

@@ -296,12 +456,13 @@ definitions below, up to ESC_z. There's a dummy for OP_ANY because it
 corresponds to "." rather than an escape sequence. The final one must be
 ESC_REF as subsequent values are used for \1, \2, \3, etc. There is are two
 tests in the code for an escape greater than ESC_b and less than ESC_Z to
-detect the types that may be repeated. These are the types that consume a
-character. If any new escapes are put in between that don't consume a
+detect the types that may be repeated. These are the types that consume
+characters. If any new escapes are put in between that don't consume a
 character, that code will have to change. */

 enum { ESC_A = 1, ESC_G, ESC_B, ESC_b, ESC_D, ESC_d, ESC_S, ESC_s, ESC_W,
-       ESC_w, ESC_dum1, ESC_C, ESC_Z, ESC_z, ESC_E, ESC_Q, ESC_REF };
+       ESC_w, ESC_dum1, ESC_C, ESC_P, ESC_p, ESC_X, ESC_Z, ESC_z, ESC_E,
+       ESC_Q, ESC_REF };

 /* Flag bits and data types for the extended class (OP_XCLASS) for classes that
 contain UTF-8 characters with values greater than 255. */
@@ -312,6 +473,8 @@ contain UTF-8 characters with values greater than 255. */
 #define XCL_END       0    /* Marks end of individual items */
 #define XCL_SINGLE    1    /* Single item (one multibyte char) follows */
 #define XCL_RANGE     2    /* A range (two multibyte chars) follows */
+#define XCL_PROP      3    /* Unicode property (one property code) follows */
+#define XCL_NOTPROP   4    /* Unicode inverted property (ditto) */


 /* Opcode table: OP_BRA must be last, as all values >= it are used for brackets
@@ -337,110 +500,123 @@ enum {
  OP_WORDCHAR,           /* 10 \w */
  OP_ANY,            /* 11 Match any character */
  OP_ANYBYTE,        /* 12 Match any byte (\C); different to OP_ANY for UTF-8 */
-  OP_EODN,           /* 13 End of data or \n at end of data: \Z. */
-  OP_EOD,            /* 14 End of data: \z */
+  OP_NOTPROP,        /* 13 \P (not Unicode property) */
+  OP_PROP,           /* 14 \p (Unicode property) */
+  OP_EXTUNI,         /* 15 \X (extended Unicode sequence */
+  OP_EODN,           /* 16 End of data or \n at end of data: \Z. */
+  OP_EOD,            /* 17 End of data: \z */

-  OP_OPT,            /* 15 Set runtime options */
-  OP_CIRC,           /* 16 Start of line - varies with multiline switch */
-  OP_DOLL,           /* 17 End of line - varies with multiline switch */
-  OP_CHARS,          /* 18 Match string of characters */
-  OP_NOT,            /* 19 Match anything but the following char */
+  OP_OPT,            /* 18 Set runtime options */
+  OP_CIRC,           /* 19 Start of line - varies with multiline switch */
+  OP_DOLL,           /* 20 End of line - varies with multiline switch */
+  OP_CHAR,           /* 21 Match one character, casefully */
+  OP_CHARNC,         /* 22 Match one character, caselessly */
+  OP_NOT,            /* 23 Match anything but the following char */

-  OP_STAR,           /* 20 The maximizing and minimizing versions of */
-  OP_MINSTAR,        /* 21 all these opcodes must come in pairs, with */
-  OP_PLUS,           /* 22 the minimizing one second. */
-  OP_MINPLUS,        /* 23 This first set applies to single characters */
-  OP_QUERY,          /* 24 */
-  OP_MINQUERY,       /* 25 */
-  OP_UPTO,           /* 26 From 0 to n matches */
-  OP_MINUPTO,        /* 27 */
-  OP_EXACT,          /* 28 Exactly n matches */
+  OP_STAR,           /* 24 The maximizing and minimizing versions of */
+  OP_MINSTAR,        /* 25 all these opcodes must come in pairs, with */
+  OP_PLUS,           /* 26 the minimizing one second. */
+  OP_MINPLUS,        /* 27 This first set applies to single characters */
+  OP_QUERY,          /* 28 */
+  OP_MINQUERY,       /* 29 */
+  OP_UPTO,           /* 30 From 0 to n matches */
+  OP_MINUPTO,        /* 31 */
+  OP_EXACT,          /* 32 Exactly n matches */

-  OP_NOTSTAR,        /* 29 The maximizing and minimizing versions of */
-  OP_NOTMINSTAR,     /* 30 all these opcodes must come in pairs, with */
-  OP_NOTPLUS,        /* 31 the minimizing one second. */
-  OP_NOTMINPLUS,     /* 32 This set applies to "not" single characters */
-  OP_NOTQUERY,       /* 33 */
-  OP_NOTMINQUERY,    /* 34 */
-  OP_NOTUPTO,        /* 35 From 0 to n matches */
-  OP_NOTMINUPTO,     /* 36 */
-  OP_NOTEXACT,       /* 37 Exactly n matches */
+  OP_NOTSTAR,        /* 33 The maximizing and minimizing versions of */
+  OP_NOTMINSTAR,     /* 34 all these opcodes must come in pairs, with */
+  OP_NOTPLUS,        /* 35 the minimizing one second. */
+  OP_NOTMINPLUS,     /* 36 This set applies to "not" single characters */
+  OP_NOTQUERY,       /* 37 */
+  OP_NOTMINQUERY,    /* 38 */
+  OP_NOTUPTO,        /* 39 From 0 to n matches */
+  OP_NOTMINUPTO,     /* 40 */
+  OP_NOTEXACT,       /* 41 Exactly n matches */

-  OP_TYPESTAR,       /* 38 The maximizing and minimizing versions of */
-  OP_TYPEMINSTAR,    /* 39 all these opcodes must come in pairs, with */
-  OP_TYPEPLUS,       /* 40 the minimizing one second. These codes must */
-  OP_TYPEMINPLUS,    /* 41 be in exactly the same order as those above. */
-  OP_TYPEQUERY,      /* 42 This set applies to character types such as \d */
-  OP_TYPEMINQUERY,   /* 43 */
-  OP_TYPEUPTO,       /* 44 From 0 to n matches */
-  OP_TYPEMINUPTO,    /* 45 */
-  OP_TYPEEXACT,      /* 46 Exactly n matches */
+  OP_TYPESTAR,       /* 42 The maximizing and minimizing versions of */
+  OP_TYPEMINSTAR,    /* 43 all these opcodes must come in pairs, with */
+  OP_TYPEPLUS,       /* 44 the minimizing one second. These codes must */
+  OP_TYPEMINPLUS,    /* 45 be in exactly the same order as those above. */
+  OP_TYPEQUERY,      /* 46 This set applies to character types such as \d */
+  OP_TYPEMINQUERY,   /* 47 */
+  OP_TYPEUPTO,       /* 48 From 0 to n matches */
+  OP_TYPEMINUPTO,    /* 49 */
+  OP_TYPEEXACT,      /* 50 Exactly n matches */

-  OP_CRSTAR,         /* 47 The maximizing and minimizing versions of */
-  OP_CRMINSTAR,      /* 48 all these opcodes must come in pairs, with */
-  OP_CRPLUS,         /* 49 the minimizing one second. These codes must */
-  OP_CRMINPLUS,      /* 50 be in exactly the same order as those above. */
-  OP_CRQUERY,        /* 51 These are for character classes and back refs */
-  OP_CRMINQUERY,     /* 52 */
-  OP_CRRANGE,        /* 53 These are different to the three seta above. */
-  OP_CRMINRANGE,     /* 54 */
+  OP_CRSTAR,         /* 51 The maximizing and minimizing versions of */
+  OP_CRMINSTAR,      /* 52 all these opcodes must come in pairs, with */
+  OP_CRPLUS,         /* 53 the minimizing one second. These codes must */
+  OP_CRMINPLUS,      /* 54 be in exactly the same order as those above. */
+  OP_CRQUERY,        /* 55 These are for character classes and back refs */
+  OP_CRMINQUERY,     /* 56 */
+  OP_CRRANGE,        /* 57 These are different to the three sets above. */
+  OP_CRMINRANGE,     /* 58 */

-  OP_CLASS,          /* 55 Match a character class, chars < 256 only */
-  OP_NCLASS,         /* 56 Same, but the bitmap was created from a negative
+  OP_CLASS,          /* 59 Match a character class, chars < 256 only */
+  OP_NCLASS,         /* 60 Same, but the bitmap was created from a negative
                           class - the difference is relevant only when a UTF-8
                           character > 255 is encountered. */

-  OP_XCLASS,         /* 57 Extended class for handling UTF-8 chars within the
+  OP_XCLASS,         /* 61 Extended class for handling UTF-8 chars within the
                           class. This does both positive and negative. */

-  OP_REF,            /* 58 Match a back reference */
-  OP_RECURSE,        /* 59 Match a numbered subpattern (possibly recursive) */
-  OP_CALLOUT,        /* 60 Call out to external function if provided */
+  OP_REF,            /* 62 Match a back reference */
+  OP_RECURSE,        /* 63 Match a numbered subpattern (possibly recursive) */
+  OP_CALLOUT,        /* 64 Call out to external function if provided */

-  OP_ALT,            /* 61 Start of alternation */
-  OP_KET,            /* 62 End of group that doesn't have an unbounded repeat */
-  OP_KETRMAX,        /* 63 These two must remain together and in this */
-  OP_KETRMIN,        /* 64 order. They are for groups the repeat for ever. */
+  OP_ALT,            /* 65 Start of alternation */
+  OP_KET,            /* 66 End of group that doesn't have an unbounded repeat */
+  OP_KETRMAX,        /* 67 These two must remain together and in this */
+  OP_KETRMIN,        /* 68 order. They are for groups the repeat for ever. */

  /* The assertions must come before ONCE and COND */

-  OP_ASSERT,         /* 65 Positive lookahead */
-  OP_ASSERT_NOT,     /* 66 Negative lookahead */
-  OP_ASSERTBACK,     /* 67 Positive lookbehind */
-  OP_ASSERTBACK_NOT, /* 68 Negative lookbehind */
-  OP_REVERSE,        /* 69 Move pointer back - used in lookbehind assertions */
+  OP_ASSERT,         /* 69 Positive lookahead */
+  OP_ASSERT_NOT,     /* 70 Negative lookahead */
+  OP_ASSERTBACK,     /* 71 Positive lookbehind */
+  OP_ASSERTBACK_NOT, /* 72 Negative lookbehind */
+  OP_REVERSE,        /* 73 Move pointer back - used in lookbehind assertions */

  /* ONCE and COND must come after the assertions, with ONCE first, as there's
  a test for >= ONCE for a subpattern that isn't an assertion. */

-  OP_ONCE,           /* 70 Once matched, don't back up into the subpattern */
-  OP_COND,           /* 71 Conditional group */
-  OP_CREF,           /* 72 Used to hold an extraction string number (cond ref) */
+  OP_ONCE,           /* 74 Once matched, don't back up into the subpattern */
+  OP_COND,           /* 75 Conditional group */
+  OP_CREF,           /* 76 Used to hold an extraction string number (cond ref) */

-  OP_BRAZERO,        /* 73 These two must remain together and in this */
-  OP_BRAMINZERO,     /* 74 order. */
+  OP_BRAZERO,        /* 77 These two must remain together and in this */
+  OP_BRAMINZERO,     /* 78 order. */

-  OP_BRANUMBER,      /* 75 Used for extracting brackets whose number is greater
+  OP_BRANUMBER,      /* 79 Used for extracting brackets whose number is greater
                           than can fit into an opcode. */

-  OP_BRA             /* 76 This and greater values are used for brackets that
-                           extract substrings up to a basic limit. After that,
-                           use is made of OP_BRANUMBER. */
+  OP_BRA             /* 80 This and greater values are used for brackets that
+                           extract substrings up to EXTRACT_BASIC_MAX. After
+                           that, use is made of OP_BRANUMBER. */
 };

-/* WARNING: There is an implicit assumption in study.c that all opcodes are
-less than 128 in value. This makes handling UTF-8 character sequences easier.
-*/
+/* WARNING WARNING WARNING: There is an implicit assumption in pcre.c and
+study.c that all opcodes are less than 128 in value. This makes handling UTF-8
+character sequences easier. */
+
+/* The highest extraction number before we have to start using additional
+bytes. (Originally PCRE didn't have support for extraction counts highter than
+this number.) The value is limited by the number of opcodes left after OP_BRA,
+i.e. 255 - OP_BRA. We actually set it a bit lower to leave room for additional
+opcodes. */
+
+#define EXTRACT_BASIC_MAX  100


-/* This macro defines textual names for all the opcodes. There are used only
-for debugging, in pcre.c when DEBUG is defined, and also in pcretest.c. The
-macro is referenced only in printint.c. */
+/* This macro defines textual names for all the opcodes. These are used only
+for debugging. The macro is referenced only in pcre_printint.c. */

 #define OP_NAME_LIST \
  "End", "\\A", "\\G", "\\B", "\\b", "\\D", "\\d",                \
-  "\\S", "\\s", "\\W", "\\w", "Any", "Anybyte", "\\Z", "\\z",     \
-  "Opt", "^", "$", "chars", "not",                                \
+  "\\S", "\\s", "\\W", "\\w", "Any", "Anybyte",                   \
+  "notprop", "prop", "extuni",                                    \
+  "\\Z", "\\z",                                                   \
+  "Opt", "^", "$", "char", "charnc", "not",                       \
  "*", "*?", "+", "+?", "?", "??", "{", "{", "{",                 \
  "*", "*?", "+", "+?", "?", "??", "{", "{", "{",                 \
  "*", "*?", "+", "+?", "?", "??", "{", "{", "{",                 \
@@ -454,7 +630,7 @@ macro is referenced only in printint.c. */
 /* This macro defines the length of fixed length operations in the compiled
 regex. The lengths are used when searching for specific things, and also in the
 debugging printing of a compiled regex. We use a macro so that it can be
-incorporated both into pcre.c and pcretest.c without being publicly exposed.
+defined close to the definitions of the opcodes themselves.

 As things have been extended, some of these are no longer fixed lenths, but are
 minima instead. For example, the length of a single-character repeat may vary
@@ -463,8 +639,11 @@ in UTF-8 mode. The code that uses this table must know about such things. */
 #define OP_LENGTHS \
  1,                             /* End                                    */ \
  1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  /* \A, \G, \B, \B, \D, \d, \S, \s, \W, \w */ \
-  1, 1, 1, 1, 2, 1, 1,           /* Any, Anybyte, \Z, \z, Opt, ^, $        */ \
-  2,                             /* Chars - the minimum length             */ \
+  1, 1,                          /* Any, Anybyte                           */ \
+  2, 2, 1,                       /* NOTPROP, PROP, EXTUNI                  */ \
+  1, 1, 2, 1, 1,                 /* \Z, \z, Opt, ^, $                      */ \
+  2,                             /* Char  - the minimum length             */ \
+  2,                             /* Charnc  - the minimum length           */ \
  2,                             /* not                                    */ \
  /* Positive single-char repeats                            ** These are  */ \
  2, 2, 2, 2, 2, 2,              /* *, *?, +, +?, ?, ??      ** minima in  */ \
@@ -483,7 +662,7 @@ in UTF-8 mode. The code that uses this table must know about such things. */
  0,                             /* XCLASS - variable length               */ \
  3,                             /* REF                                    */ \
  1+LINK_SIZE,                   /* RECURSE                                */ \
-  2,                             /* CALLOUT                                */ \
+  2+2*LINK_SIZE,                 /* CALLOUT                                */ \
  1+LINK_SIZE,                   /* Alt                                    */ \
  1+LINK_SIZE,                   /* Ket                                    */ \
  1+LINK_SIZE,                   /* KetRmax                                */ \
@@ -501,98 +680,61 @@ in UTF-8 mode. The code that uses this table must know about such things. */
  1+LINK_SIZE                    /* BRA                                    */ \


-/* The highest extraction number before we have to start using additional
-bytes. (Originally PCRE didn't have support for extraction counts highter than
-this number.) The value is limited by the number of opcodes left after OP_BRA,
-i.e. 255 - OP_BRA. We actually set it a bit lower to leave room for additional
-opcodes. */
-
-#define EXTRACT_BASIC_MAX  150
-
 /* A magic value for OP_CREF to indicate the "in recursion" condition. */

 #define CREF_RECURSE  0xffff

-/* The texts of compile-time error messages are defined as macros here so that
-they can be accessed by the POSIX wrapper and converted into error codes.  Yes,
-I could have used error codes in the first place, but didn't feel like changing
-just to accommodate the POSIX wrapper. */
+/* Error code numbers. They are given names so that they can more easily be
+tracked. */

-#define ERR1  "\\ at end of pattern"
-#define ERR2  "\\c at end of pattern"
-#define ERR3  "unrecognized character follows \\"
-#define ERR4  "numbers out of order in {} quantifier"
-#define ERR5  "number too big in {} quantifier"
-#define ERR6  "missing terminating ] for character class"
-#define ERR7  "invalid escape sequence in character class"
-#define ERR8  "range out of order in character class"
-#define ERR9  "nothing to repeat"
-#define ERR10 "operand of unlimited repeat could match the empty string"
-#define ERR11 "internal error: unexpected repeat"
-#define ERR12 "unrecognized character after (?"
-#define ERR13 "POSIX named classes are supported only within a class"
-#define ERR14 "missing )"
-#define ERR15 "reference to non-existent subpattern"
-#define ERR16 "erroffset passed as NULL"
-#define ERR17 "unknown option bit(s) set"
-#define ERR18 "missing ) after comment"
-#define ERR19 "parentheses nested too deeply"
-#define ERR20 "regular expression too large"
-#define ERR21 "failed to get memory"
-#define ERR22 "unmatched parentheses"
-#define ERR23 "internal error: code overflow"
-#define ERR24 "unrecognized character after (?<"
-#define ERR25 "lookbehind assertion is not fixed length"
-#define ERR26 "malformed number after (?("
-#define ERR27 "conditional group contains more than two branches"
-#define ERR28 "assertion expected after (?("
-#define ERR29 "(?R or (?digits must be followed by )"
-#define ERR30 "unknown POSIX class name"
-#define ERR31 "POSIX collating elements are not supported"
-#define ERR32 "this version of PCRE is not compiled with PCRE_UTF8 support"
-#define ERR33 "spare error"
-#define ERR34 "character value in \\x{...} sequence is too large"
-#define ERR35 "invalid condition (?(0)"
-#define ERR36 "\\C not allowed in lookbehind assertion"
-#define ERR37 "PCRE does not support \\L, \\l, \\N, \\P, \\p, \\U, \\u, or \\X"
-#define ERR38 "number after (?C is > 255"
-#define ERR39 "closing ) for (?C expected"
-#define ERR40 "recursive call could loop indefinitely"
-#define ERR41 "unrecognized character after (?P"
-#define ERR42 "syntax error after (?P"
-#define ERR43 "two named groups have the same name"
-#define ERR44 "invalid UTF-8 string"
-
-/* All character handling must be done as unsigned characters. Otherwise there
-are problems with top-bit-set characters and functions such as isspace().
-However, we leave the interface to the outside world as char *, because that
-should make things easier for callers. We define a short type for unsigned char
-to save lots of typing. I tried "uchar", but it causes problems on Digital
-Unix, where it is defined in sys/types, so use "uschar" instead. */
-
-typedef unsigned char uschar;
+enum { ERR0,  ERR1,  ERR2,  ERR3,  ERR4,  ERR5,  ERR6,  ERR7,  ERR8,  ERR9,
+       ERR10, ERR11, ERR12, ERR13, ERR14, ERR15, ERR16, ERR17, ERR18, ERR19,
+       ERR20, ERR21, ERR22, ERR23, ERR24, ERR25, ERR26, ERR27, ERR28, ERR29,
+       ERR30, ERR31, ERR32, ERR33, ERR34, ERR35, ERR36, ERR37, ERR38, ERR39,
+       ERR40, ERR41, ERR42, ERR43, ERR44, ERR45, ERR46, ERR47 };

 /* The real format of the start of the pcre block; the index of names and the
-code vector run on as long as necessary after the end. */
+code vector run on as long as necessary after the end. We store an explicit
+offset to the name table so that if a regex is compiled on one host, saved, and
+then run on another where the size of pointers is different, all might still
+be well. For the case of compiled-on-4 and run-on-8, we include an extra
+pointer that is always NULL. For future-proofing, a few dummy fields were
+originally included - even though you can never get this planning right - but
+there is only one left now.
+
+NOTE NOTE NOTE:
+Because people can now save and re-use compiled patterns, any additions to this
+structure should be made at the end, and something earlier (e.g. a new
+flag in the options or one of the dummy fields) should indicate that the new
+fields are present. Currently PCRE always sets the dummy fields to zero.
+NOTE NOTE NOTE:
+*/

 typedef struct real_pcre {
-  unsigned long int magic_number;
-  size_t size;                        /* Total that was malloced */
-  const unsigned char *tables;        /* Pointer to tables */
-  unsigned long int options;
-  unsigned short int top_bracket;
-  unsigned short int top_backref;
-  unsigned short int first_byte;
-  unsigned short int req_byte;
-  unsigned short int name_entry_size; /* Size of any name items; 0 => none */
-  unsigned short int name_count;      /* Number of name items */
+  pcre_uint32 magic_number;
+  pcre_uint32 size;               /* Total that was malloced */
+  pcre_uint32 options;
+  pcre_uint32 dummy1;             /* For future use, maybe */
+
+  pcre_uint16 top_bracket;
+  pcre_uint16 top_backref;
+  pcre_uint16 first_byte;
+  pcre_uint16 req_byte;
+  pcre_uint16 name_table_offset;  /* Offset to name table that follows */
+  pcre_uint16 name_entry_size;    /* Size of any name items */
+  pcre_uint16 name_count;         /* Number of name items */
+  pcre_uint16 ref_count;          /* Reference count */
+
+  const unsigned char *tables;    /* Pointer to tables or NULL for std */
+  const unsigned char *nullpad;   /* NULL padding */
 } real_pcre;

-/* The format of the block used to store data from pcre_study(). */
+/* The format of the block used to store data from pcre_study(). The same
+remark (see NOTE above) about extending this structure applies. */

 typedef struct pcre_study_data {
-  size_t size;                        /* Total that was malloced */
-  uschar options;
+  pcre_uint32 size;               /* Total that was malloced */
+  pcre_uint32 options;
  uschar start_bits[32];
 } pcre_study_data;

@@ -605,12 +747,14 @@ typedef struct compile_data {
  const uschar *cbits;          /* Points to character type table */
  const uschar *ctypes;         /* Points to table of type maps */
  const uschar *start_code;     /* The start of the compiled code */
+  const uschar *start_pattern;  /* The start of the pattern */
  uschar *name_table;           /* The name/number table */
  int  names_found;             /* Number of entries so far */
  int  name_entry_size;         /* Size of each entry */
  int  top_backref;             /* Maximum back reference */
  unsigned int backref_map;     /* Bitmap of low back refs */
  int  req_varyopt;             /* "After variable item" flag for reqbyte */
+  BOOL nopartial;               /* Set TRUE if partial won't work */
 } compile_data;

 /* Structure for maintaining a chain of pointers to the currently incomplete
@@ -644,7 +788,7 @@ NOTE: This isn't used for a "normal" compilation of pcre. */
 struct heapframe;

 /* Structure for passing "static" information around between the functions
-doing the matching, so that they are thread-safe. */
+doing traditional NFA matching, so that they are thread-safe. */

 typedef struct match_data {
  unsigned long int match_call_count; /* As it says */
@@ -660,6 +804,8 @@ typedef struct match_data {
  BOOL   utf8;                  /* UTF8 flag */
  BOOL   endonly;               /* Dollar not before final \n */
  BOOL   notempty;              /* Empty string match not wanted */
+  BOOL   partial;               /* PARTIAL flag */
+  BOOL   hitend;                /* Hit the end of the subject at some point */
  const uschar *start_code;     /* For use when recursing */
  const uschar *start_subject;  /* Start of the subject string */
  const uschar *end_subject;    /* End of the subject string */
@@ -673,6 +819,19 @@ typedef struct match_data {
  struct heapframe *thisframe;  /* Used only when compiling for no recursion */
 } match_data;

+/* A similar structure is used for the same purpose by the DFA matching
+functions. */
+
+typedef struct dfa_match_data {
+  const uschar *start_code;     /* Start of the compiled pattern */
+  const uschar *start_subject;  /* Start of the subject string */
+  const uschar *end_subject;    /* End of subject string */
+  const uschar *tables;         /* Character tables */
+  int   moptions;               /* Match options */
+  int   poptions;               /* Pattern options */
+  void  *callout_data;          /* To pass back to callouts */
+} dfa_match_data;
+
 /* Bit definitions for entries in the pcre_ctypes table. */

 #define ctype_space   0x01
@@ -706,4 +865,45 @@ total length. */
 #define ctypes_offset (cbits_offset + cbit_length)
 #define tables_length (ctypes_offset + 256)

-/* End of internal.h */
+/* Layout of the UCP type table that translates property names into codes for
+ucp_findchar(). */
+
+typedef struct {
+  const char *name;
+  int value;
+} ucp_type_table;
+
+
+/* Internal shared data tables. These are tables that are used by more than one
+of the exported public functions. They have to be "external" in the C sense,
+but are not part of the PCRE public API. The data for these tables is in the
+pcre_tables.c module. */
+
+extern const int    _pcre_utf8_table1[];
+extern const int    _pcre_utf8_table2[];
+extern const int    _pcre_utf8_table3[];
+extern const uschar _pcre_utf8_table4[];
+
+extern const int    _pcre_utf8_table1_size;
+
+extern const ucp_type_table _pcre_utt[];
+extern const int _pcre_utt_size;
+
+extern const uschar _pcre_default_tables[];
+
+extern const uschar _pcre_OP_lengths[];
+
+
+/* Internal shared functions. These are functions that are used by more than
+one of the exported public functions. They have to be "external" in the C
+sense, but are not part of the PCRE public API. */
+
+extern int         _pcre_ord2utf8(int, uschar *);
+extern void        _pcre_printint(pcre *, FILE *);
+extern real_pcre * _pcre_try_flipped(const real_pcre *, real_pcre *,
+                     const pcre_study_data *, pcre_study_data *);
+extern int         _pcre_ucp_findchar(const int, int *, int *);
+extern int         _pcre_valid_utf8(const uschar *, int);
+extern BOOL        _pcre_xclass(int, const uschar *);
+
+/* End of pcre_internal.h */
@@ -2,48 +2,53 @@
 *      Perl-Compatible Regular Expressions       *
 *************************************************/

-/*
-PCRE is a library of functions to support regular expressions whose syntax
+/* PCRE is a library of functions to support regular expressions whose syntax
 and semantics are as close as possible to those of the Perl 5 language.

-Written by: Philip Hazel <ph10@cam.ac.uk>
-
-           Copyright (c) 1997-2003 University of Cambridge
+                       Written by Philip Hazel
+           Copyright (c) 1997-2005 University of Cambridge

 -----------------------------------------------------------------------------
-Permission is granted to anyone to use this software for any purpose on any
-computer system, and to redistribute it freely, subject to the following
-restrictions:
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:

-1. This software is distributed in the hope that it will be useful,
-   but WITHOUT ANY WARRANTY; without even the implied warranty of
-   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.

-2. The origin of this software must not be misrepresented, either by
-   explicit claim or by omission.
+    * 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.

-3. Altered versions must be plainly marked as such, and must not be
-   misrepresented as being the original software.
+    * 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.

-4. If PCRE is embedded in any software that is released under the GNU
-   General Purpose Licence (GPL), then the terms of that licence shall
-   supersede any condition above with which it is incompatible.
+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.
 -----------------------------------------------------------------------------
-
-See the file Tech.Notes for some information on the internals.
 */


-/* This file is compiled on its own as part of the PCRE library. However,
-it is also included in the compilation of dftables.c, in which case the macro
-DFTABLES is defined. */
+/* This module contains the external function pcre_maketables(), which builds
+character tables for PCRE in the current locale. The file is compiled on its
+own as part of the PCRE library. However, it is also included in the
+compilation of dftables.c, in which case the macro DFTABLES is defined. */
+

 #ifndef DFTABLES
-#include "internal.h"
+#include "pcre_internal.h"
 #endif


-
 /*************************************************
 *           Create PCRE character tables         *
 *************************************************/
@@ -137,4 +142,4 @@ for (i = 0; i < 256; i++)
 return yield;
 }

-/* End of maketables.c */
+/* End of pcre_maketables.c */
@@ -0,0 +1,78 @@
+/*************************************************
+*      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) 1997-2005 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 file contains a private PCRE function that converts an ordinal
+character value into a UTF8 string. */
+
+
+#include "pcre_internal.h"
+
+
+/*************************************************
+*       Convert character value to UTF-8         *
+*************************************************/
+
+/* This function takes an integer value in the range 0 - 0x7fffffff
+and encodes it as a UTF-8 character in 0 to 6 bytes.
+
+Arguments:
+  cvalue     the character value
+  buffer     pointer to buffer for result - at least 6 bytes long
+
+Returns:     number of characters placed in the buffer
+*/
+
+EXPORT int
+_pcre_ord2utf8(int cvalue, uschar *buffer)
+{
+register int i, j;
+for (i = 0; i < _pcre_utf8_table1_size; i++)
+  if (cvalue <= _pcre_utf8_table1[i]) break;
+buffer += i;
+for (j = i; j > 0; j--)
+ {
+ *buffer-- = 0x80 | (cvalue & 0x3f);
+ cvalue >>= 6;
+ }
+*buffer = _pcre_utf8_table2[i] | cvalue;
+return i + 1;
+}
+
+/* End of pcre_ord2utf8.c */
@@ -0,0 +1,451 @@
+/*************************************************
+*      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) 1997-2005 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 PCRE private debugging function for printing out the
+internal form of a compiled regular expression, along with some supporting
+local functions. */
+
+
+#include "pcre_internal.h"
+
+
+static const char *OP_names[] = { OP_NAME_LIST };
+
+
+/*************************************************
+*       Print single- or multi-byte character    *
+*************************************************/
+
+static int
+print_char(FILE *f, uschar *ptr, BOOL utf8)
+{
+int c = *ptr;
+
+if (!utf8 || (c & 0xc0) != 0xc0)
+  {
+  if (isprint(c)) fprintf(f, "%c", c); else fprintf(f, "\\x%02x", c);
+  return 0;
+  }
+else
+  {
+  int i;
+  int a = _pcre_utf8_table4[c & 0x3f];  /* Number of additional bytes */
+  int s = 6*a;
+  c = (c & _pcre_utf8_table3[a]) << s;
+  for (i = 1; i <= a; i++)
+    {
+    /* This is a check for malformed UTF-8; it should only occur if the sanity
+    check has been turned off. Rather than swallow random bytes, just stop if
+    we hit a bad one. Print it with \X instead of \x as an indication. */
+
+    if ((ptr[i] & 0xc0) != 0x80)
+      {
+      fprintf(f, "\\X{%x}", c);
+      return i - 1;
+      }
+
+    /* The byte is OK */
+
+    s -= 6;
+    c |= (ptr[i] & 0x3f) << s;
+    }
+  if (c < 128) fprintf(f, "\\x%02x", c); else fprintf(f, "\\x{%x}", c);
+  return a;
+  }
+}
+
+
+
+/*************************************************
+*          Find Unicode property name            *
+*************************************************/
+
+static const char *
+get_ucpname(int property)
+{
+#ifdef SUPPORT_UCP
+int i;
+for (i = _pcre_utt_size; i >= 0; i--)
+  {
+  if (property == _pcre_utt[i].value) break;
+  }
+return (i >= 0)? _pcre_utt[i].name : "??";
+#else
+return "??";
+#endif
+}
+
+
+
+/*************************************************
+*         Print compiled regex                   *
+*************************************************/
+
+/* Make this function work for a regex with integers either byte order.
+However, we assume that what we are passed is a compiled regex. */
+
+EXPORT void
+_pcre_printint(pcre *external_re, FILE *f)
+{
+real_pcre *re = (real_pcre *)external_re;
+uschar *codestart, *code;
+BOOL utf8;
+
+unsigned int options = re->options;
+int offset = re->name_table_offset;
+int count = re->name_count;
+int size = re->name_entry_size;
+
+if (re->magic_number != MAGIC_NUMBER)
+  {
+  offset = ((offset << 8) & 0xff00) | ((offset >> 8) & 0xff);
+  count = ((count << 8) & 0xff00) | ((count >> 8) & 0xff);
+  size = ((size << 8) & 0xff00) | ((size >> 8) & 0xff);
+  options = ((options << 24) & 0xff000000) |
+            ((options <<  8) & 0x00ff0000) |
+            ((options >>  8) & 0x0000ff00) |
+            ((options >> 24) & 0x000000ff);
+  }
+
+code = codestart = (uschar *)re + offset + count * size;
+utf8 = (options & PCRE_UTF8) != 0;
+
+for(;;)
+  {
+  uschar *ccode;
+  int c;
+  int extra = 0;
+
+  fprintf(f, "%3d ", (int)(code - codestart));
+
+  if (*code >= OP_BRA)
+    {
+    if (*code - OP_BRA > EXTRACT_BASIC_MAX)
+      fprintf(f, "%3d Bra extra\n", GET(code, 1));
+    else
+      fprintf(f, "%3d Bra %d\n", GET(code, 1), *code - OP_BRA);
+    code += _pcre_OP_lengths[OP_BRA];
+    continue;
+    }
+
+  switch(*code)
+    {
+    case OP_END:
+    fprintf(f, "    %s\n", OP_names[*code]);
+    fprintf(f, "------------------------------------------------------------------\n");
+    return;
+
+    case OP_OPT:
+    fprintf(f, " %.2x %s", code[1], OP_names[*code]);
+    break;
+
+    case OP_CHAR:
+      {
+      fprintf(f, "    ");
+      do
+        {
+        code++;
+        code += 1 + print_char(f, code, utf8);
+        }
+      while (*code == OP_CHAR);
+      fprintf(f, "\n");
+      continue;
+      }
+    break;
+
+    case OP_CHARNC:
+      {
+      fprintf(f, " NC ");
+      do
+        {
+        code++;
+        code += 1 + print_char(f, code, utf8);
+        }
+      while (*code == OP_CHARNC);
+      fprintf(f, "\n");
+      continue;
+      }
+    break;
+
+    case OP_KETRMAX:
+    case OP_KETRMIN:
+    case OP_ALT:
+    case OP_KET:
+    case OP_ASSERT:
+    case OP_ASSERT_NOT:
+    case OP_ASSERTBACK:
+    case OP_ASSERTBACK_NOT:
+    case OP_ONCE:
+    case OP_COND:
+    case OP_REVERSE:
+    fprintf(f, "%3d %s", GET(code, 1), OP_names[*code]);
+    break;
+
+    case OP_BRANUMBER:
+    printf("%3d %s", GET2(code, 1), OP_names[*code]);
+    break;
+
+    case OP_CREF:
+    if (GET2(code, 1) == CREF_RECURSE)
+      fprintf(f, "    Cond recurse");
+    else
+      fprintf(f, "%3d %s", GET2(code,1), OP_names[*code]);
+    break;
+
+    case OP_STAR:
+    case OP_MINSTAR:
+    case OP_PLUS:
+    case OP_MINPLUS:
+    case OP_QUERY:
+    case OP_MINQUERY:
+    case OP_TYPESTAR:
+    case OP_TYPEMINSTAR:
+    case OP_TYPEPLUS:
+    case OP_TYPEMINPLUS:
+    case OP_TYPEQUERY:
+    case OP_TYPEMINQUERY:
+    fprintf(f, "    ");
+    if (*code >= OP_TYPESTAR)
+      {
+      fprintf(f, "%s", OP_names[code[1]]);
+      if (code[1] == OP_PROP || code[1] == OP_NOTPROP)
+        {
+        fprintf(f, " %s ", get_ucpname(code[2]));
+        extra = 1;
+        }
+      }
+    else extra = print_char(f, code+1, utf8);
+    fprintf(f, "%s", OP_names[*code]);
+    break;
+
+    case OP_EXACT:
+    case OP_UPTO:
+    case OP_MINUPTO:
+    fprintf(f, "    ");
+    extra = print_char(f, code+3, utf8);
+    fprintf(f, "{");
+    if (*code != OP_EXACT) fprintf(f, ",");
+    fprintf(f, "%d}", GET2(code,1));
+    if (*code == OP_MINUPTO) fprintf(f, "?");
+    break;
+
+    case OP_TYPEEXACT:
+    case OP_TYPEUPTO:
+    case OP_TYPEMINUPTO:
+    fprintf(f, "    %s", OP_names[code[3]]);
+    if (code[3] == OP_PROP || code[3] == OP_NOTPROP)
+      {
+      fprintf(f, " %s ", get_ucpname(code[4]));
+      extra = 1;
+      }
+    fprintf(f, "{");
+    if (*code != OP_TYPEEXACT) fprintf(f, "0,");
+    fprintf(f, "%d}", GET2(code,1));
+    if (*code == OP_TYPEMINUPTO) fprintf(f, "?");
+    break;
+
+    case OP_NOT:
+    if (isprint(c = code[1])) fprintf(f, "    [^%c]", c);
+      else fprintf(f, "    [^\\x%02x]", c);
+    break;
+
+    case OP_NOTSTAR:
+    case OP_NOTMINSTAR:
+    case OP_NOTPLUS:
+    case OP_NOTMINPLUS:
+    case OP_NOTQUERY:
+    case OP_NOTMINQUERY:
+    if (isprint(c = code[1])) fprintf(f, "    [^%c]", c);
+      else fprintf(f, "    [^\\x%02x]", c);
+    fprintf(f, "%s", OP_names[*code]);
+    break;
+
+    case OP_NOTEXACT:
+    case OP_NOTUPTO:
+    case OP_NOTMINUPTO:
+    if (isprint(c = code[3])) fprintf(f, "    [^%c]{", c);
+      else fprintf(f, "    [^\\x%02x]{", c);
+    if (*code != OP_NOTEXACT) fprintf(f, "0,");
+    fprintf(f, "%d}", GET2(code,1));
+    if (*code == OP_NOTMINUPTO) fprintf(f, "?");
+    break;
+
+    case OP_RECURSE:
+    fprintf(f, "%3d %s", GET(code, 1), OP_names[*code]);
+    break;
+
+    case OP_REF:
+    fprintf(f, "    \\%d", GET2(code,1));
+    ccode = code + _pcre_OP_lengths[*code];
+    goto CLASS_REF_REPEAT;
+
+    case OP_CALLOUT:
+    fprintf(f, "    %s %d %d %d", OP_names[*code], code[1], GET(code,2),
+      GET(code, 2 + LINK_SIZE));
+    break;
+
+    case OP_PROP:
+    case OP_NOTPROP:
+    fprintf(f, "    %s %s", OP_names[*code], get_ucpname(code[1]));
+    break;
+
+    /* OP_XCLASS can only occur in UTF-8 mode. However, there's no harm in
+    having this code always here, and it makes it less messy without all those
+    #ifdefs. */
+
+    case OP_CLASS:
+    case OP_NCLASS:
+    case OP_XCLASS:
+      {
+      int i, min, max;
+      BOOL printmap;
+
+      fprintf(f, "    [");
+
+      if (*code == OP_XCLASS)
+        {
+        extra = GET(code, 1);
+        ccode = code + LINK_SIZE + 1;
+        printmap = (*ccode & XCL_MAP) != 0;
+        if ((*ccode++ & XCL_NOT) != 0) fprintf(f, "^");
+        }
+      else
+        {
+        printmap = TRUE;
+        ccode = code + 1;
+        }
+
+      /* Print a bit map */
+
+      if (printmap)
+        {
+        for (i = 0; i < 256; i++)
+          {
+          if ((ccode[i/8] & (1 << (i&7))) != 0)
+            {
+            int j;
+            for (j = i+1; j < 256; j++)
+              if ((ccode[j/8] & (1 << (j&7))) == 0) break;
+            if (i == '-' || i == ']') fprintf(f, "\\");
+            if (isprint(i)) fprintf(f, "%c", i); else fprintf(f, "\\x%02x", i);
+            if (--j > i)
+              {
+              if (j != i + 1) fprintf(f, "-");
+              if (j == '-' || j == ']') fprintf(f, "\\");
+              if (isprint(j)) fprintf(f, "%c", j); else fprintf(f, "\\x%02x", j);
+              }
+            i = j;
+            }
+          }
+        ccode += 32;
+        }
+
+      /* For an XCLASS there is always some additional data */
+
+      if (*code == OP_XCLASS)
+        {
+        int ch;
+        while ((ch = *ccode++) != XCL_END)
+          {
+          if (ch == XCL_PROP)
+            {
+            fprintf(f, "\\p{%s}", get_ucpname(*ccode++));
+            }
+          else if (ch == XCL_NOTPROP)
+            {
+            fprintf(f, "\\P{%s}", get_ucpname(*ccode++));
+            }
+          else
+            {
+            ccode += 1 + print_char(f, ccode, TRUE);
+            if (ch == XCL_RANGE)
+              {
+              fprintf(f, "-");
+              ccode += 1 + print_char(f, ccode, TRUE);
+              }
+            }
+          }
+        }
+
+      /* Indicate a non-UTF8 class which was created by negation */
+
+      fprintf(f, "]%s", (*code == OP_NCLASS)? " (neg)" : "");
+
+      /* Handle repeats after a class or a back reference */
+
+      CLASS_REF_REPEAT:
+      switch(*ccode)
+        {
+        case OP_CRSTAR:
+        case OP_CRMINSTAR:
+        case OP_CRPLUS:
+        case OP_CRMINPLUS:
+        case OP_CRQUERY:
+        case OP_CRMINQUERY:
+        fprintf(f, "%s", OP_names[*ccode]);
+        extra += _pcre_OP_lengths[*ccode];
+        break;
+
+        case OP_CRRANGE:
+        case OP_CRMINRANGE:
+        min = GET2(ccode,1);
+        max = GET2(ccode,3);
+        if (max == 0) fprintf(f, "{%d,}", min);
+        else fprintf(f, "{%d,%d}", min, max);
+        if (*ccode == OP_CRMINRANGE) fprintf(f, "?");
+        extra += _pcre_OP_lengths[*ccode];
+        break;
+        }
+      }
+    break;
+
+    /* Anything else is just an item with no data*/
+
+    default:
+    fprintf(f, "    %s", OP_names[*code]);
+    break;
+    }
+
+  code += _pcre_OP_lengths[*code] + extra;
+  fprintf(f, "\n");
+  }
+}
+
+/* End of pcre_printint.c */
@@ -0,0 +1,77 @@
+/*************************************************
+*      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) 1997-2005 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_refcount(), which is an
+auxiliary function that can be used to maintain a reference count in a compiled
+pattern data block. This might be helpful in applications where the block is
+shared by different users. */
+
+#include "pcre_internal.h"
+
+
+/*************************************************
+*           Maintain reference count             *
+*************************************************/
+
+/* The reference count is a 16-bit field, initialized to zero. It is not
+possible to transfer a non-zero count from one host to a different host that
+has a different byte order - though I can't see why anyone in their right mind
+would ever want to do that!
+
+Arguments:
+  argument_re   points to compiled code
+  adjust        value to add to the count
+
+Returns:        the (possibly updated) count value (a non-negative number), or
+                a negative error number
+*/
+
+EXPORT int
+pcre_refcount(pcre *argument_re, int adjust)
+{
+real_pcre *re = (real_pcre *)argument_re;
+if (re == NULL) return PCRE_ERROR_NULL;
+re->ref_count = (-adjust > re->ref_count)? 0 :
+                (adjust + re->ref_count > 65535)? 65535 :
+                re->ref_count + adjust;
+return re->ref_count;
+}
+
+/* End of pcre_refcount.c */
@@ -0,0 +1,169 @@
+// Copyright (c) 2005, Google Inc.
+// All rights reserved.
+//
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions are
+// met:
+//
+//     * Redistributions of source code must retain the above copyright
+// notice, this list of conditions and the following disclaimer.
+//     * Redistributions in binary form must reproduce the above
+// copyright notice, this list of conditions and the following disclaimer
+// in the documentation and/or other materials provided with the
+// distribution.
+//     * Neither the name of Google Inc. nor the names of its
+// contributors may be used to endorse or promote products derived from
+// this software without specific prior written permission.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+//
+// Author: Sanjay Ghemawat
+
+#include <vector>
+#include <algorithm>     // for count()
+#include <assert.h>
+#include "config.h"
+#include "pcre_scanner.h"
+
+using std::vector;
+
+namespace pcrecpp {
+
+Scanner::Scanner()
+  : data_(),
+    input_(data_),
+    skip_(NULL),
+    should_skip_(false),
+    save_comments_(false),
+    comments_(NULL),
+    comments_offset_(0) {
+}
+
+Scanner::Scanner(const string& in)
+  : data_(in),
+    input_(data_),
+    skip_(NULL),
+    should_skip_(false),
+    save_comments_(false),
+    comments_(NULL),
+    comments_offset_(0) {
+}
+
+Scanner::~Scanner() {
+  delete skip_;
+  delete comments_;
+}
+
+void Scanner::Skip(const char* re) {
+  delete skip_;
+  if (re != NULL) {
+    skip_ = new RE(re);
+    should_skip_ = true;
+    ConsumeSkip();
+  } else {
+    skip_ = NULL;
+    should_skip_ = false;
+  }
+}
+
+void Scanner::DisableSkip() {
+  assert(skip_ != NULL);
+  should_skip_ = false;
+}
+
+void Scanner::EnableSkip() {
+  assert(skip_ != NULL);
+  should_skip_ = true;
+  ConsumeSkip();
+}
+
+int Scanner::LineNumber() const {
+  // TODO: Make it more efficient by keeping track of the last point
+  // where we computed line numbers and counting newlines since then.
+  return 1 + std::count(data_.data(), input_.data(), '\n');
+}
+
+int Scanner::Offset() const {
+  return input_.data() - data_.c_str();
+}
+
+bool Scanner::LookingAt(const RE& re) const {
+  int consumed;
+  return re.DoMatch(input_, RE::ANCHOR_START, &consumed, 0, 0);
+}
+
+
+bool Scanner::Consume(const RE& re,
+                      const Arg& arg0,
+                      const Arg& arg1,
+                      const Arg& arg2) {
+  const bool result = re.Consume(&input_, arg0, arg1, arg2);
+  if (result && should_skip_) ConsumeSkip();
+  return result;
+}
+
+// helper function to consume *skip_ and honour save_comments_
+void Scanner::ConsumeSkip() {
+  if (save_comments_) {
+    if (NULL == comments_) {
+      comments_ = new vector<StringPiece>;
+    }
+    const char *start_data = input_.data();
+    skip_->Consume(&input_);
+    // already pointing one past end, so no need to +1
+    int length = input_.data() - start_data;
+    if (length > 0) {
+      comments_->push_back(StringPiece(start_data, length));
+    }
+  } else {
+    skip_->Consume(&input_);
+  }
+}
+
+
+void Scanner::GetComments(int start, int end, vector<StringPiece> *ranges) {
+  // short circuit out if we've not yet initialized comments_
+  // (e.g., when save_comments is false)
+  if (!comments_) {
+    return;
+  }
+  // TODO: if we guarantee that comments_ will contain StringPieces
+  // that are ordered by their start, then we can do a binary search
+  // for the first StringPiece at or past start and then scan for the
+  // ones contained in the range, quit early (use equal_range or
+  // lower_bound)
+  for (vector<StringPiece>::const_iterator it = comments_->begin();
+       it != comments_->end(); ++it) {
+    if ((it->data() >= data_.c_str() + start &&
+         it->data() + it->size() <= data_.c_str() + end)) {
+      ranges->push_back(*it);
+    }
+  }
+}
+
+
+void Scanner::GetNextComments(vector<StringPiece> *ranges) {
+  // short circuit out if we've not yet initialized comments_
+  // (e.g., when save_comments is false)
+  if (!comments_) {
+    return;
+  }
+  for (vector<StringPiece>::const_iterator it =
+         comments_->begin() + comments_offset_;
+       it != comments_->end(); ++it) {
+    ranges->push_back(*it);
+    ++comments_offset_;
+  }
+}
+
+}   // namespace pcrecpp
@@ -0,0 +1,163 @@
+// Copyright (c) 2005, Google Inc.
+// All rights reserved.
+//
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions are
+// met:
+//
+//     * Redistributions of source code must retain the above copyright
+// notice, this list of conditions and the following disclaimer.
+//     * Redistributions in binary form must reproduce the above
+// copyright notice, this list of conditions and the following disclaimer
+// in the documentation and/or other materials provided with the
+// distribution.
+//     * Neither the name of Google Inc. nor the names of its
+// contributors may be used to endorse or promote products derived from
+// this software without specific prior written permission.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+//
+// Author: Sanjay Ghemawat
+//
+// Regular-expression based scanner for parsing an input stream.
+//
+// Example 1: parse a sequence of "var = number" entries from input:
+//
+//      Scanner scanner(input);
+//      string var;
+//      int number;
+//      scanner.Skip("\\s+");           // Skip any white space we encounter
+//      while (scanner.Consume("(\\w+) = (\\d+)", &var, &number)) {
+//        ...;
+//      }
+
+#ifndef _PCRE_SCANNER_H
+#define _PCRE_SCANNER_H
+
+#include <assert.h>
+#include <string>
+#include <vector>
+#include <pcrecpp.h>
+#include <pcre_stringpiece.h>
+
+namespace pcrecpp {
+
+class Scanner {
+ public:
+  Scanner();
+  explicit Scanner(const std::string& input);
+  ~Scanner();
+
+  // Return current line number.  The returned line-number is
+  // one-based.  I.e. it returns 1 + the number of consumed newlines.
+  //
+  // Note: this method may be slow.  It may take time proportional to
+  // the size of the input.
+  int LineNumber() const;
+
+  // Return the byte-offset that the scanner is looking in the
+  // input data;
+  int Offset() const;
+
+  // Return true iff the start of the remaining input matches "re"
+  bool LookingAt(const RE& re) const;
+
+  // Return true iff all of the following are true
+  //    a. the start of the remaining input matches "re",
+  //    b. if any arguments are supplied, matched sub-patterns can be
+  //       parsed and stored into the arguments.
+  // If it returns true, it skips over the matched input and any
+  // following input that matches the "skip" regular expression.
+  bool Consume(const RE& re,
+               const Arg& arg0 = no_arg,
+               const Arg& arg1 = no_arg,
+               const Arg& arg2 = no_arg
+               // TODO: Allow more arguments?
+               );
+
+  // Set the "skip" regular expression.  If after consuming some data,
+  // a prefix of the input matches this RE, it is automatically
+  // skipped.  For example, a programming language scanner would use
+  // a skip RE that matches white space and comments.
+  //
+  //    scanner.Skip("(\\s|//.*|/[*](.|\n)*?[*]/)*");
+  //
+  // You can pass NULL for "re" if you do not want any data to be skipped.
+  void Skip(const char* re);
+
+  // Temporarily pause "skip"ing. This
+  //   Skip("Foo"); code ; DisableSkip(); code; EnableSkip()
+  // is similar to
+  //   Skip("Foo"); code ; Skip(NULL); code ; Skip("Foo");
+  // but avoids creating/deleting new RE objects.
+  void DisableSkip();
+
+  // Reenable previously paused skipping.  Any prefix of the input
+  // that matches the skip pattern is immediately dropped.
+  void EnableSkip();
+
+  /***** Special wrappers around SetSkip() for some common idioms *****/
+
+  // Arranges to skip whitespace, C comments, C++ comments.
+  // The overall RE is a repeated disjunction of the following REs:
+  //    \\s                     whitespace
+  //    //.*\n                  C++ comment
+  //    /[*](.|\n)*?[*]/        C comment (x*? means minimal repetitions of x)
+  void SkipCXXComments() {
+    Skip("((\\s|//.*\n|/[*](.|\n)*?[*]/)*)");
+  }
+
+  void set_save_comments(bool comments) {
+    save_comments_ = comments;
+  }
+
+  bool save_comments() {
+    return save_comments_;
+  }
+
+  // Append to vector ranges the comments found in the
+  // byte range [start,end] (inclusive) of the input data.
+  // Only comments that were extracted entirely within that
+  // range are returned: no range splitting of atomically-extracted
+  // comments is performed.
+  void GetComments(int start, int end, std::vector<StringPiece> *ranges);
+
+  // Append to vector ranges the comments added
+  // since the last time this was called. This
+  // functionality is provided for efficiency when
+  // interleaving scanning with parsing.
+  void GetNextComments(std::vector<StringPiece> *ranges);
+
+ private:
+  std::string   data_;          // All the input data
+  StringPiece   input_;         // Unprocessed input
+  RE*           skip_;          // If non-NULL, RE for skipping input
+  bool          should_skip_;   // If true, use skip_
+  bool          save_comments_; // If true, aggregate the skip expression
+
+  // the skipped comments
+  // TODO: later consider requiring that the StringPieces be added
+  // in order by their start position
+  std::vector<StringPiece> *comments_;
+
+  // the offset into comments_ that has been returned by GetNextComments
+  int           comments_offset_;
+
+  // helper function to consume *skip_ and honour
+  // save_comments_
+  void ConsumeSkip();
+};
+
+}   // namespace pcrecpp
+
+#endif /* _PCRE_SCANNER_H */
@@ -0,0 +1,125 @@
+// Copyright (c) 2005, Google Inc.
+// All rights reserved.
+//
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions are
+// met:
+//
+//     * Redistributions of source code must retain the above copyright
+// notice, this list of conditions and the following disclaimer.
+//     * Redistributions in binary form must reproduce the above
+// copyright notice, this list of conditions and the following disclaimer
+// in the documentation and/or other materials provided with the
+// distribution.
+//     * Neither the name of Google Inc. nor the names of its
+// contributors may be used to endorse or promote products derived from
+// this software without specific prior written permission.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+//
+// Author: Greg J. Badros
+//
+// Unittest for scanner, especially GetNextComments and GetComments()
+// functionality.
+
+#include <stdio.h>
+#include <vector>
+#include <pcre_stringpiece.h>
+#include <pcre_scanner.h>
+
+// Dies with a fatal error if the two values are not equal.
+#define CHECK_EQ(a, b)  do {                                    \
+  if ( (a) != (b) ) {                                           \
+    fprintf(stderr, "%s:%d: Check failed because %s != %s\n",   \
+            __FILE__, __LINE__, #a, #b);                        \
+    exit(1);                                                    \
+  }                                                             \
+} while (0)
+
+using std::vector;
+using pcrecpp::StringPiece;
+using pcrecpp::Scanner;
+
+static void TestScanner() {
+  const char input[] = "\n"
+                       "alpha = 1; // this sets alpha\n"
+                       "bravo = 2; // bravo is set here\n"
+                       "gamma = 33; /* and here is gamma */\n";
+
+  const char *re = "(\\w+) = (\\d+);";
+
+  Scanner s(input);
+  string var;
+  int number;
+  s.SkipCXXComments();
+  s.set_save_comments(true);
+  vector<StringPiece> comments;
+
+  s.Consume(re, &var, &number);
+  CHECK_EQ(var, "alpha");
+  CHECK_EQ(number, 1);
+  s.GetNextComments(&comments);
+  CHECK_EQ(comments.size(), 1);
+  CHECK_EQ(comments[0].as_string(), " // this sets alpha\n");
+  comments.resize(0);
+
+  s.Consume(re, &var, &number);
+  CHECK_EQ(var, "bravo");
+  CHECK_EQ(number, 2);
+  s.GetNextComments(&comments);
+  CHECK_EQ(comments.size(), 1);
+  CHECK_EQ(comments[0].as_string(), " // bravo is set here\n");
+  comments.resize(0);
+
+  s.Consume(re, &var, &number);
+  CHECK_EQ(var, "gamma");
+  CHECK_EQ(number, 33);
+  s.GetNextComments(&comments);
+  CHECK_EQ(comments.size(), 1);
+  CHECK_EQ(comments[0].as_string(), " /* and here is gamma */\n");
+  comments.resize(0);
+
+  s.GetComments(0, sizeof(input), &comments);
+  CHECK_EQ(comments.size(), 3);
+  CHECK_EQ(comments[0].as_string(), " // this sets alpha\n");
+  CHECK_EQ(comments[1].as_string(), " // bravo is set here\n");
+  CHECK_EQ(comments[2].as_string(), " /* and here is gamma */\n");
+  comments.resize(0);
+
+  s.GetComments(0, strchr(input, '/') - input, &comments);
+  CHECK_EQ(comments.size(), 0);
+  comments.resize(0);
+
+  s.GetComments(strchr(input, '/') - input - 1, sizeof(input),
+                &comments);
+  CHECK_EQ(comments.size(), 3);
+  CHECK_EQ(comments[0].as_string(), " // this sets alpha\n");
+  CHECK_EQ(comments[1].as_string(), " // bravo is set here\n");
+  CHECK_EQ(comments[2].as_string(), " /* and here is gamma */\n");
+  comments.resize(0);
+
+  s.GetComments(strchr(input, '/') - input - 1,
+                strchr(input + 1, '\n') - input + 1, &comments);
+  CHECK_EQ(comments.size(), 1);
+  CHECK_EQ(comments[0].as_string(), " // this sets alpha\n");
+  comments.resize(0);
+}
+
+int main(int argc, char** argv) {
+  TestScanner();
+
+  // Done
+  printf("OK\n");
+
+  return 0;
+}
@@ -0,0 +1,39 @@
+// Copyright (c) 2005, Google Inc.
+// All rights reserved.
+//
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions are
+// met:
+//
+//     * Redistributions of source code must retain the above copyright
+// notice, this list of conditions and the following disclaimer.
+//     * Redistributions in binary form must reproduce the above
+// copyright notice, this list of conditions and the following disclaimer
+// in the documentation and/or other materials provided with the
+// distribution.
+//     * Neither the name of Google Inc. nor the names of its
+// contributors may be used to endorse or promote products derived from
+// this software without specific prior written permission.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+//
+// Author: wilsonh@google.com (Wilson Hsieh)
+//
+
+#include <iostream>
+#include "config.h"
+#include "pcre_stringpiece.h"
+
+std::ostream& operator<<(std::ostream& o, const pcrecpp::StringPiece& piece) {
+  return (o << piece.as_string());
+}
@@ -0,0 +1,172 @@
+// Copyright (c) 2005, Google Inc.
+// All rights reserved.
+//
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions are
+// met:
+//
+//     * Redistributions of source code must retain the above copyright
+// notice, this list of conditions and the following disclaimer.
+//     * Redistributions in binary form must reproduce the above
+// copyright notice, this list of conditions and the following disclaimer
+// in the documentation and/or other materials provided with the
+// distribution.
+//     * Neither the name of Google Inc. nor the names of its
+// contributors may be used to endorse or promote products derived from
+// this software without specific prior written permission.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+//
+// Author: Sanjay Ghemawat
+//
+// A string like object that points into another piece of memory.
+// Useful for providing an interface that allows clients to easily
+// pass in either a "const char*" or a "string".
+//
+// Arghh!  I wish C++ literals were automatically of type "string".
+
+#ifndef _PCRE_STRINGPIECE_H
+#define _PCRE_STRINGPIECE_H
+
+#include <string.h>
+#include <string>
+#include <iosfwd>    // for ostream forward-declaration
+
+#if 1
+#define HAVE_TYPE_TRAITS
+#include <type_traits.h>
+#elif 0
+#define HAVE_TYPE_TRAITS
+#include <bits/type_traits.h>
+#endif
+
+using std::string;
+
+namespace pcrecpp {
+
+class StringPiece {
+ private:
+  const char*   ptr_;
+  int           length_;
+
+ public:
+  // We provide non-explicit singleton constructors so users can pass
+  // in a "const char*" or a "string" wherever a "StringPiece" is
+  // expected.
+  StringPiece()
+    : ptr_(NULL), length_(0) { }
+  StringPiece(const char* str)
+    : ptr_(str), length_(static_cast<int>(strlen(str))) { }
+  StringPiece(const string& str)
+    : ptr_(str.data()), length_(static_cast<int>(str.size())) { }
+  StringPiece(const char* offset, int len)
+    : ptr_(offset), length_(len) { }
+
+  // data() may return a pointer to a buffer with embedded NULs, and the
+  // returned buffer may or may not be null terminated.  Therefore it is
+  // typically a mistake to pass data() to a routine that expects a NUL
+  // terminated string.  Use "as_string().c_str()" if you really need to do
+  // this.  Or better yet, change your routine so it does not rely on NUL
+  // termination.
+  const char* data() const { return ptr_; }
+  int size() const { return length_; }
+  bool empty() const { return length_ == 0; }
+
+  void clear() { ptr_ = NULL; length_ = 0; }
+  void set(const char* buffer, int len) { ptr_ = buffer; length_ = len; }
+  void set(const char* str) {
+    ptr_ = str;
+    length_ = static_cast<int>(strlen(str));
+  }
+  void set(const void* buffer, int len) {
+    ptr_ = reinterpret_cast<const char*>(buffer);
+    length_ = len;
+  }
+
+  char operator[](int i) const { return ptr_[i]; }
+
+  void remove_prefix(int n) {
+    ptr_ += n;
+    length_ -= n;
+  }
+
+  void remove_suffix(int n) {
+    length_ -= n;
+  }
+
+  bool operator==(const StringPiece& x) const {
+    return ((length_ == x.length_) &&
+            (memcmp(ptr_, x.ptr_, length_) == 0));
+  }
+  bool operator!=(const StringPiece& x) const {
+    return !(*this == x);
+  }
+
+#define STRINGPIECE_BINARY_PREDICATE(cmp,auxcmp)                             \
+  bool operator cmp (const StringPiece& x) const {                           \
+    int r = memcmp(ptr_, x.ptr_, length_ < x.length_ ? length_ : x.length_); \
+    return ((r auxcmp 0) || ((r == 0) && (length_ cmp x.length_)));          \
+  }
+  STRINGPIECE_BINARY_PREDICATE(<,  <);
+  STRINGPIECE_BINARY_PREDICATE(<=, <);
+  STRINGPIECE_BINARY_PREDICATE(>=, >);
+  STRINGPIECE_BINARY_PREDICATE(>,  >);
+#undef STRINGPIECE_BINARY_PREDICATE
+
+  int compare(const StringPiece& x) const {
+    int r = memcmp(ptr_, x.ptr_, length_ < x.length_ ? length_ : x.length_);
+    if (r == 0) {
+      if (length_ < x.length_) r = -1;
+      else if (length_ > x.length_) r = +1;
+    }
+    return r;
+  }
+
+  string as_string() const {
+    return string(data(), size());
+  }
+
+  void CopyToString(string* target) const {
+    target->assign(ptr_, length_);
+  }
+
+  // Does "this" start with "x"
+  bool starts_with(const StringPiece& x) const {
+    return ((length_ >= x.length_) && (memcmp(ptr_, x.ptr_, x.length_) == 0));
+  }
+};
+
+}   // namespace pcrecpp
+
+// ------------------------------------------------------------------
+// Functions used to create STL containers that use StringPiece
+//  Remember that a StringPiece's lifetime had better be less than
+//  that of the underlying string or char*.  If it is not, then you
+//  cannot safely store a StringPiece into an STL container
+// ------------------------------------------------------------------
+
+#ifdef HAVE_TYPE_TRAITS
+// This makes vector<StringPiece> really fast for some STL implementations
+template<> struct __type_traits<pcrecpp::StringPiece> {
+  typedef __true_type    has_trivial_default_constructor;
+  typedef __true_type    has_trivial_copy_constructor;
+  typedef __true_type    has_trivial_assignment_operator;
+  typedef __true_type    has_trivial_destructor;
+  typedef __true_type    is_POD_type;
+};
+#endif
+
+// allow StringPiece to be logged
+std::ostream& operator<<(std::ostream& o, const pcrecpp::StringPiece& piece);
+
+#endif /* _PCRE_STRINGPIECE_H */
@@ -0,0 +1,145 @@
+// Copyright 2003 and onwards Google Inc.
+// Author: Sanjay Ghemawat
+
+#include <stdio.h>
+#include <map>
+#include <algorithm>    // for make_pair
+#include <pcre_stringpiece.h>
+
+// CHECK dies with a fatal error if condition is not true.  It is *not*
+// controlled by NDEBUG, so the check will be executed regardless of
+// compilation mode.  Therefore, it is safe to do things like:
+//    CHECK(fp->Write(x) == 4)
+#define CHECK(condition) do {                           \
+  if (!(condition)) {                                   \
+    fprintf(stderr, "%s:%d: Check failed: %s\n",        \
+            __FILE__, __LINE__, #condition);            \
+    exit(1);                                            \
+  }                                                     \
+} while (0)
+
+using std::map;
+using std::make_pair;
+using pcrecpp::StringPiece;
+
+static void CheckSTLComparator() {
+  string s1("foo");
+  string s2("bar");
+  string s3("baz");
+
+  StringPiece p1(s1);
+  StringPiece p2(s2);
+  StringPiece p3(s3);
+
+  typedef map<StringPiece, int> TestMap;
+  TestMap map;
+
+  map.insert(make_pair(p1, 0));
+  map.insert(make_pair(p2, 1));
+  map.insert(make_pair(p3, 2));
+  CHECK(map.size() == 3);
+
+  TestMap::const_iterator iter = map.begin();
+  CHECK(iter->second == 1);
+  ++iter;
+  CHECK(iter->second == 2);
+  ++iter;
+  CHECK(iter->second == 0);
+  ++iter;
+  CHECK(iter == map.end());
+
+  TestMap::iterator new_iter = map.find("zot");
+  CHECK(new_iter == map.end());
+
+  new_iter = map.find("bar");
+  CHECK(new_iter != map.end());
+
+  map.erase(new_iter);
+  CHECK(map.size() == 2);
+
+  iter = map.begin();
+  CHECK(iter->second == 2);
+  ++iter;
+  CHECK(iter->second == 0);
+  ++iter;
+  CHECK(iter == map.end());
+}
+
+static void CheckComparisonOperators() {
+#define CMP_Y(op, x, y)                                         \
+  CHECK( (StringPiece((x)) op StringPiece((y))));               \
+  CHECK( (StringPiece((x)).compare(StringPiece((y))) op 0))
+
+#define CMP_N(op, x, y)                                         \
+  CHECK(!(StringPiece((x)) op StringPiece((y))));               \
+  CHECK(!(StringPiece((x)).compare(StringPiece((y))) op 0))
+
+  CMP_Y(==, "",   "");
+  CMP_Y(==, "a",  "a");
+  CMP_Y(==, "aa", "aa");
+  CMP_N(==, "a",  "");
+  CMP_N(==, "",   "a");
+  CMP_N(==, "a",  "b");
+  CMP_N(==, "a",  "aa");
+  CMP_N(==, "aa", "a");
+
+  CMP_N(!=, "",   "");
+  CMP_N(!=, "a",  "a");
+  CMP_N(!=, "aa", "aa");
+  CMP_Y(!=, "a",  "");
+  CMP_Y(!=, "",   "a");
+  CMP_Y(!=, "a",  "b");
+  CMP_Y(!=, "a",  "aa");
+  CMP_Y(!=, "aa", "a");
+
+  CMP_Y(<, "a",  "b");
+  CMP_Y(<, "a",  "aa");
+  CMP_Y(<, "aa", "b");
+  CMP_Y(<, "aa", "bb");
+  CMP_N(<, "a",  "a");
+  CMP_N(<, "b",  "a");
+  CMP_N(<, "aa", "a");
+  CMP_N(<, "b",  "aa");
+  CMP_N(<, "bb", "aa");
+
+  CMP_Y(<=, "a",  "a");
+  CMP_Y(<=, "a",  "b");
+  CMP_Y(<=, "a",  "aa");
+  CMP_Y(<=, "aa", "b");
+  CMP_Y(<=, "aa", "bb");
+  CMP_N(<=, "b",  "a");
+  CMP_N(<=, "aa", "a");
+  CMP_N(<=, "b",  "aa");
+  CMP_N(<=, "bb", "aa");
+
+  CMP_N(>=, "a",  "b");
+  CMP_N(>=, "a",  "aa");
+  CMP_N(>=, "aa", "b");
+  CMP_N(>=, "aa", "bb");
+  CMP_Y(>=, "a",  "a");
+  CMP_Y(>=, "b",  "a");
+  CMP_Y(>=, "aa", "a");
+  CMP_Y(>=, "b",  "aa");
+  CMP_Y(>=, "bb", "aa");
+
+  CMP_N(>, "a",  "a");
+  CMP_N(>, "a",  "b");
+  CMP_N(>, "a",  "aa");
+  CMP_N(>, "aa", "b");
+  CMP_N(>, "aa", "bb");
+  CMP_Y(>, "b",  "a");
+  CMP_Y(>, "aa", "a");
+  CMP_Y(>, "b",  "aa");
+  CMP_Y(>, "bb", "aa");
+
+#undef CMP_Y
+#undef CMP_N
+}
+
+int main(int argc, char** argv) {
+  CheckComparisonOperators();
+  CheckSTLComparator();
+
+  printf("OK\n");
+  return 0;
+}
@@ -2,42 +2,47 @@
 *      Perl-Compatible Regular Expressions       *
 *************************************************/

-/*
-This 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. See
-the file Tech.Notes for some information on the internals.
+/* 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 <ph10@cam.ac.uk>
-
-           Copyright (c) 1997-2003 University of Cambridge
+                       Written by Philip Hazel
+           Copyright (c) 1997-2005 University of Cambridge

 -----------------------------------------------------------------------------
-Permission is granted to anyone to use this software for any purpose on any
-computer system, and to redistribute it freely, subject to the following
-restrictions:
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:

-1. This software is distributed in the hope that it will be useful,
-   but WITHOUT ANY WARRANTY; without even the implied warranty of
-   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.

-2. The origin of this software must not be misrepresented, either by
-   explicit claim or by omission.
+    * 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.

-3. Altered versions must be plainly marked as such, and must not be
-   misrepresented as being the original software.
+    * 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.

-4. If PCRE is embedded in any software that is released under the GNU
-   General Purpose Licence (GPL), then the terms of that licence shall
-   supersede any condition above with which it is incompatible.
+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.
 -----------------------------------------------------------------------------
 */


-/* Include the internals header, which itself includes Standard C headers plus
-the external pcre header. */
+/* This module contains the external function pcre_study(), along with local
+supporting functions. */

-#include "internal.h"

+#include "pcre_internal.h"


 /*************************************************
@@ -57,7 +62,7 @@ Returns:        nothing
 */

 static void
-set_bit(uschar *start_bits, int c, BOOL caseless, compile_data *cd)
+set_bit(uschar *start_bits, unsigned int c, BOOL caseless, compile_data *cd)
 {
 start_bits[c/8] |= (1 << (c&7));
 if (caseless && (cd->ctypes[c] & ctype_letter) != 0)
@@ -123,7 +128,7 @@ do
      /* Skip over callout */

      case OP_CALLOUT:
-      tcode += 2;
+      tcode += 2 + 2*LINK_SIZE;
      break;

      /* Skip over extended extraction bracket number */
@@ -186,11 +191,10 @@ do
      /* At least one single char sets the bit and stops */

      case OP_EXACT:       /* Fall through */
-      tcode++;
-
-      case OP_CHARS:       /* Fall through */
-      tcode++;
+      tcode += 2;

+      case OP_CHAR:
+      case OP_CHARNC:
      case OP_PLUS:
      case OP_MINPLUS:
      set_bit(start_bits, tcode[1], caseless, cd);
@@ -403,8 +407,9 @@ pcre_study(const pcre *external_re, int options, const char **errorptr)
 uschar start_bits[32];
 pcre_extra *extra;
 pcre_study_data *study;
+const uschar *tables;
 const real_pcre *re = (const real_pcre *)external_re;
-uschar *code = (uschar *)re + sizeof(real_pcre) +
+uschar *code = (uschar *)re + re->name_table_offset +
  (re->name_count * re->name_entry_size);
 compile_data compile_block;

@@ -429,12 +434,17 @@ at present. */
 if ((re->options & (PCRE_ANCHORED|PCRE_FIRSTSET|PCRE_STARTLINE)) != 0)
  return NULL;

-/* Set the character tables in the block which is passed around */
+/* Set the character tables in the block that is passed around */

-compile_block.lcc = re->tables + lcc_offset;
-compile_block.fcc = re->tables + fcc_offset;
-compile_block.cbits = re->tables + cbits_offset;
-compile_block.ctypes = re->tables + ctypes_offset;
+tables = re->tables;
+if (tables == NULL)
+  (void)pcre_fullinfo(external_re, NULL, PCRE_INFO_DEFAULT_TABLES,
+  (void *)(&tables));
+
+compile_block.lcc = tables + lcc_offset;
+compile_block.fcc = tables + fcc_offset;
+compile_block.cbits = tables + cbits_offset;
+compile_block.ctypes = tables + ctypes_offset;

 /* See if we can find a fixed set of initial characters for the pattern. */

@@ -469,4 +479,4 @@ memcpy(study->start_bits, start_bits, sizeof(start_bits));
 return extra;
 }

-/* End of study.c */
+/* End of pcre_study.c */