Upgrade to PCRE version 6.2.

# Don't worry, upgrade for other branches is coming

ext/pcre/config.m4

@@ -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 -DSUPPORT_UCP -DLINK_SIZE=2 -DPOSIX_MALLOC_THRESHOLD=10 -DMATCH_LIMIT=10000000 -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 -DSUPPORT_UCP -DLINK_SIZE=2 -DPOSIX_MALLOC_THRESHOLD=10 -DMATCH_LIMIT=10000000)
+    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

ext/pcre/config0.m4

@@ -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 -DSUPPORT_UCP -DLINK_SIZE=2 -DPOSIX_MALLOC_THRESHOLD=10 -DMATCH_LIMIT=10000000 -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 -DSUPPORT_UCP -DLINK_SIZE=2 -DPOSIX_MALLOC_THRESHOLD=10 -DMATCH_LIMIT=10000000)
+    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

ext/pcre/pcrelib/AUTHORS

@@ -1,6 +1,23 @@
-Written by: Philip Hazel <[email protected]>
+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) 1997-2004 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
+
+####

ext/pcre/pcrelib/COPYING

@@ -4,18 +4,40 @@ PCRE LICENCE
 PCRE is a library of functions to support regular expressions whose syntax
 and semantics are as close as possible to those of the Perl 5 language.
 
-Release 5 of PCRE is distributed under the terms of the "BSD" licence, as
+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.
 
-Written by: Philip Hazel <[email protected]>
+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) 1997-2004 University of Cambridge
+Copyright (c) 1997-2005 University of Cambridge
+All rights reserved.
+
+
+THE C++ WRAPPER FUNCTIONS
+-------------------------
+
+Contributed by:   Google Inc.
+
+Copyright (c) 2005, Google Inc.
 All rights reserved.
 
+
+THE "BSD" LICENCE
+-----------------
+
 Redistribution and use in source and binary forms, with or without
 modification, are permitted provided that the following conditions are met:
 
@@ -26,9 +48,10 @@ modification, are permitted provided that the following conditions are met:
       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.
+    * 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

ext/pcre/pcrelib/ChangeLog

@@ -1,6 +1,221 @@
 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
 ---------------------
 

ext/pcre/pcrelib/LICENCE

@@ -4,18 +4,40 @@ PCRE LICENCE
 PCRE is a library of functions to support regular expressions whose syntax
 and semantics are as close as possible to those of the Perl 5 language.
 
-Release 5 of PCRE is distributed under the terms of the "BSD" licence, as
+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.
 
-Written by: Philip Hazel <[email protected]>
+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) 1997-2004 University of Cambridge
+Copyright (c) 1997-2005 University of Cambridge
+All rights reserved.
+
+
+THE C++ WRAPPER FUNCTIONS
+-------------------------
+
+Contributed by:   Google Inc.
+
+Copyright (c) 2005, Google Inc.
 All rights reserved.
 
+
+THE "BSD" LICENCE
+-----------------
+
 Redistribution and use in source and binary forms, with or without
 modification, are permitted provided that the following conditions are met:
 
@@ -26,9 +48,10 @@ modification, are permitted provided that the following conditions are met:
       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.
+    * 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