upgrade pcre to version 7.4

NEWS

@@ -14,6 +14,7 @@ PHP                                                                        NEWS
 - Added support for dynamic access of static members using $foo::myFunc().
   (Etienne Kneuss)
 - Added "compact" handler for Zend MM storage. (Dmitry)
+- Upgraded PCRE to version 7.4 (Nuno)
 
 - Improved php.ini handling: (Jani)
   . Added ".htaccess" style user-defined php.ini files support for CGI/FastCGI

ext/pcre/pcrelib/ChangeLog

@@ -1,6 +1,81 @@
 ChangeLog for PCRE
 ------------------
 
+Version 7.4 21-Sep-07
+---------------------
+
+1.  Change 7.3/28 was implemented for classes by looking at the bitmap. This
+    means that a class such as [\s] counted as "explicit reference to CR or
+    LF". That isn't really right - the whole point of the change was to try to
+    help when there was an actual mention of one of the two characters. So now
+    the change happens only if \r or \n (or a literal CR or LF) character is
+    encountered.
+
+2.  The 32-bit options word was also used for 6 internal flags, but the numbers
+    of both had grown to the point where there were only 3 bits left.
+    Fortunately, there was spare space in the data structure, and so I have
+    moved the internal flags into a new 16-bit field to free up more option
+    bits.
+
+3.  The appearance of (?J) at the start of a pattern set the DUPNAMES option,
+    but did not set the internal JCHANGED flag - either of these is enough to
+    control the way the "get" function works - but the PCRE_INFO_JCHANGED
+    facility is supposed to tell if (?J) was ever used, so now (?J) at the
+    start sets both bits.
+
+4.  Added options (at build time, compile time, exec time) to change \R from
+    matching any Unicode line ending sequence to just matching CR, LF, or CRLF.
+
+5.  doc/pcresyntax.html was missing from the distribution.
+
+6.  Put back the definition of PCRE_ERROR_NULLWSLIMIT, for backward
+    compatibility, even though it is no longer used.
+
+7.  Added macro for snprintf to pcrecpp_unittest.cc and also for strtoll and
+    strtoull to pcrecpp.cc to select the available functions in WIN32 when the
+    windows.h file is present (where different names are used). [This was
+    reversed later after testing - see 16 below.]
+
+8.  Changed all #include <config.h> to #include "config.h". There were also
+    some further <pcre.h> cases that I changed to "pcre.h".
+
+9.  When pcregrep was used with the --colour option, it missed the line ending
+    sequence off the lines that it output.
+
+10. It was pointed out to me that arrays of string pointers cause lots of
+    relocations when a shared library is dynamically loaded. A technique of
+    using a single long string with a table of offsets can drastically reduce
+    these. I have refactored PCRE in four places to do this. The result is
+    dramatic:
+
+      Originally:                          290
+      After changing UCP table:            187
+      After changing error message table:   43
+      After changing table of "verbs"       36
+      After changing table of Posix names   22
+
+    Thanks to the folks working on Gregex for glib for this insight.
+
+11. --disable-stack-for-recursion caused compiling to fail unless -enable-
+    unicode-properties was also set.
+
+12. Updated the tests so that they work when \R is defaulted to ANYCRLF.
+
+13. Added checks for ANY and ANYCRLF to pcrecpp.cc where it previously
+    checked only for CRLF.
+
+14. Added casts to pcretest.c to avoid compiler warnings.
+
+15. Added Craig's patch to various pcrecpp modules to avoid compiler warnings.
+
+16. Added Craig's patch to remove the WINDOWS_H tests, that were not working,
+    and instead check for _strtoi64 explicitly, and avoid the use of snprintf()
+    entirely. This removes changes made in 7 above.
+
+17. The CMake files have been updated, and there is now more information about
+    building with CMake in the NON-UNIX-USE document.
+
+
 Version 7.3 28-Aug-07
 ---------------------
 

ext/pcre/pcrelib/NEWS

@@ -2,6 +2,17 @@ News about PCRE releases
 ------------------------
 
 
+Release 7.4 21-Sep-07
+---------------------
+
+The only change of specification is the addition of options to control whether
+\R matches any Unicode line ending (the default) or just CR, LF, and CRLF.
+Otherwise, the changes are bug fixes and a refactoring to reduce the number of
+relocations needed in a shared library. There have also been some documentation
+updates, in particular, some more information about using CMake to build PCRE
+has been added to the NON-UNIX-USE file.
+
+
 Release 7.3 28-Aug-07
 ---------------------
 

ext/pcre/pcrelib/NON-UNIX-USE

@@ -9,6 +9,7 @@ This document contains the following sections:
   Building for virtual Pascal
   Stack size in Windows environments
   Comments about Win32 builds
+  Building PCRE with CMake
   Building under Windows with BCC5.5
   Building PCRE on OpenVMS
 
@@ -30,9 +31,10 @@ library consists entirely of code written in Standard C, and so should compile
 successfully on any system that has a Standard C compiler and library. The C++
 wrapper functions are a separate issue (see below).
 
-The PCRE distribution contains some experimental support for "cmake", but this
-is incomplete and not documented. However if you are a "cmake" user you might
-like to try building with "cmake".
+The PCRE distribution includes support for CMake. This support is relatively
+new, but has already been used successfully to build PCRE in multiple build
+environments on Windows. There are some instructions in the section entitled
+"Building PCRE with CMake" below.
 
 
 GENERIC INSTRUCTIONS FOR THE PCRE C LIBRARY
@@ -42,10 +44,13 @@ The following are generic comments about building the PCRE C library "by hand".
  (1) Copy or rename the file config.h.generic as config.h, and edit the macro
      settings that it contains to whatever is appropriate for your environment.
      In particular, if you want to force a specific value for newline, you can
-     define the NEWLINE macro.
+     define the NEWLINE macro. When you compile any of the PCRE modules, you
+     must specify -DHAVE_CONFIG_H to your compiler so that config.h is included
+     in the sources.
 
      An alternative approach is not to edit config.h, but to use -D on the
-     compiler command line to make any changes that you need.
+     compiler command line to make any changes that you need to the
+     configuration options. In this case -DHAVE_CONFIG_H must not be set.
 
      NOTE: There have been occasions when the way in which certain parameters
      in config.h are used has changed between releases. (In the configure/make
@@ -59,13 +64,14 @@ The following are generic comments about building the PCRE C library "by hand".
        Copy or rename file pcre_chartables.c.dist as pcre_chartables.c.
 
      OR:
-       Compile dftables.c as a stand-alone program, and then run it with the
-       single argument "pcre_chartables.c". This generates a set of standard
-       character tables and writes them to that file. The tables are generated
-       using the default C locale for your system. If you want to use a locale
-       that is specified by LC_xxx environment variables, add the -L option to
-       the dftables command. You must use this method if you are building on
-       a system that uses EBCDIC code.
+       Compile dftables.c as a stand-alone program (using -DHAVE_CONFIG_H if
+       you have set up config.h), and then run it with the single argument
+       "pcre_chartables.c". This generates a set of standard character tables
+       and writes them to that file. The tables are generated using the default
+       C locale for your system. If you want to use a locale that is specified
+       by LC_xxx environment variables, add the -L option to the dftables
+       command. You must use this method if you are building on a system that
+       uses EBCDIC code.
 
      The tables in pcre_chartables.c are defaults. The caller of PCRE can
      specify alternative tables at run time.
@@ -82,7 +88,9 @@ The following are generic comments about building the PCRE C library "by hand".
 
        pcre_printint.src
 
- (6) Compile the following source files:
+ (6) Compile the following source files, setting -DHAVE_CONFIG_H as a compiler
+     option if you have set up config.h with your configuration, or else use
+     other -D settings to change the configuration as required.
 
        pcre_chartables.c
        pcre_compile.c
@@ -115,18 +123,21 @@ The following are generic comments about building the PCRE C library "by hand".
      your system has static and shared libraries, you may have to do this once
      for each type.
 
- (8) Similarly, compile pcreposix.c and link the result (on its own) as the
-     pcreposix library.
+ (8) Similarly, compile pcreposix.c (remembering -DHAVE_CONFIG_H if necessary)
+     and link the result (on its own) as the pcreposix library.
 
- (9) Compile the test program pcretest.c. This needs the functions in the
-     pcre and pcreposix libraries when linking. It also needs the
-     pcre_printint.src source file, which it #includes.
+ (9) Compile the test program pcretest.c (again, don't forget -DHAVE_CONFIG_H).
+     This needs the functions in the pcre and pcreposix libraries when linking.
+     It also needs the pcre_printint.src source file, which it #includes.
 
 (10) Run pcretest on the testinput files in the testdata directory, and check
      that the output matches the corresponding testoutput files. Note that the
      supplied files are in Unix format, with just LF characters as line
      terminators. You may need to edit them to change this if your system uses
-     a different convention.
+     a different convention. If you are using Windows, you probably should use
+     the wintestinput3 file instead of testinput3 (and the corresponding output
+     file). This is a locale test; wintestinput3 sets the locale to "french"
+     rather than "fr_FR", and there some minor output differences.
 
 (11) If you want to use the pcregrep command, compile and link pcregrep.c; it
      uses only the basic PCRE library (it does not need the pcreposix library).
@@ -158,11 +169,15 @@ fail because of this. Normally, running out of stack causes a crash, but there
 have been cases where the test program has just died silently. See your linker
 documentation for how to increase stack size if you experience problems. The
 Linux default of 8Mb is a reasonable choice for the stack, though even that can
-be too small for some pattern/subject combinations. There is more about stack
-usage in the "pcrestack" documentation.
+be too small for some pattern/subject combinations.
+
+PCRE has a compile configuration option to disable the use of stack for
+recursion so that heap is used instead. However, pattern matching is
+significantly slower when this is done. There is more about stack usage in the
+"pcrestack" documentation.
 
 
-COMMENTS ABOUT WIN32 BUILDS
+COMMENTS ABOUT WIN32 BUILDS (see also "BUILDING PCRE WITH CMAKE" below)
 
 There are two ways of building PCRE using the "configure, make, make install"
 paradigm on Windows systems: using MinGW or using Cygwin. These are not at all
@@ -237,6 +252,60 @@ terminators in order to get some of the tests to work. We hope to improve
 things in this area in future.
 
 
+BUILDING PCRE WITH CMAKE
+
+CMake is an alternative build facility that can be used instead of the
+traditional Unix "configure". CMake version 2.4.7 supports Borland makefiles,
+MinGW makefiles, MSYS makefiles, NMake makefiles, UNIX makefiles, Visual Studio
+6, Visual Studio 7, Visual Studio 8, and Watcom W8. The following instructions
+were contributed by a PCRE user.
+
+1. Download CMake 2.4.7 or above from http://www.cmake.org/, install and ensure
+   that cmake\bin is on your path.
+
+2. Unzip (retaining folder structure) the PCRE source tree into a source
+   directory such as C:\pcre.
+
+3. Create a new, empty build directory: C:\pcre\build\
+
+4. Run CMakeSetup from the Shell envirornment of your build tool, e.g., Msys
+   for Msys/MinGW or Visual Studio Command Prompt for VC/VC++
+
+5. Enter C:\pcre\pcre-xx and C:\pcre\build for the source and build
+   directories, respectively
+
+6. Hit the "Configure" button.
+
+7. Select the particular IDE / build tool that you are using (Visual Studio,
+   MSYS makefiles, MinGW makefiles, etc.)
+
+8. The GUI will then list several configuration options. This is where you can
+   enable UTF-8 support, etc.
+
+9. Hit "Configure" again. The adjacent "OK" button should now be active.
+
+10. Hit "OK".
+
+11. The build directory should now contain a usable build system, be it a
+    solution file for Visual Studio, makefiles for MinGW, etc.
+
+Testing with RunTest.bat
+
+1. Copy RunTest.bat into the directory where pcretest.exe has been created.
+
+2. Edit RunTest.bat and insert a line that indentifies the relative location of
+   the pcre source, e.g.:
+
+   set srcdir=..\pcre-7.4-RC3
+
+3. Run RunTest.bat from a command shell environment. Test outputs will
+   automatically be compared to expected results, and discrepancies will
+   identified in the console output.
+
+4. To test pcrecpp, run pcrecpp_unittest.exe, pcre_stringpiece_unittest.exe and
+   pcre_scanner_unittest.exe.
+
+
 BUILDING UNDER WINDOWS WITH BCC5.5
 
 Michael Roy sent these comments about building PCRE under Windows with BCC5.5:
@@ -315,5 +384,5 @@ $!   Locale could not be set to fr
 $!
 =========================
 
-Last Updated: 01 August 2007
+Last Updated: 21 September 2007
 ****

ext/pcre/pcrelib/README

@@ -103,7 +103,9 @@ Building PCRE on non-Unix systems
 
 For a non-Unix system, please read the comments in the file NON-UNIX-USE,
 though if your system supports the use of "configure" and "make" you may be
-able to build PCRE in the same way as for Unix-like systems.
+able to build PCRE in the same way as for Unix-like systems. PCRE can also be
+configured in many platform environments using the GUI facility of CMake's
+CMakeSetup. It creates Makefiles, solution files, etc.
 
 PCRE has been compiled on many different operating systems. It should be
 straightforward to build PCRE on any system that has a Standard C compiler and
@@ -184,6 +186,12 @@ library. You can read more about them in the pcrebuild man page.
   --enable-newline-is-any, many tests should succeed, but there may be some
   failures.
 
+. By default, the sequence \R in a pattern matches any Unicode line ending
+  sequence. This is independent of the option specifying what PCRE considers to
+  be the end of a line (see above). However, the caller of PCRE can restrict \R
+  to match only CR, LF, or CRLF. You can make this the default by adding
+  --enable-bsr-anycrlf to the "configure" command (bsr = "backslash R").
+
 . When called via the POSIX interface, PCRE uses malloc() to get additional
   storage for processing capturing parentheses if there are more than 10 of
   them in a pattern. You can increase this threshold by setting, for example,
@@ -500,7 +508,10 @@ in the comparison output, it means that locale is not available on your system,
 despite being listed by "locale". This does not mean that PCRE is broken.
 
 [If you are trying to run this test on Windows, you may be able to get it to
-work by changing "fr_FR" to "french" everywhere it occurs.]
+work by changing "fr_FR" to "french" everywhere it occurs. Alternatively, use
+RunTest.bat. The version of RunTest.bat included with PCRE 7.4 and above uses
+Windows versions of test 2. More info on using RunTest.bat is included in the
+document entitled NON-UNIX-USE.]
 
 The fourth test checks the UTF-8 support. It is not run automatically unless
 PCRE is built with UTF-8 support. To do this you must set --enable-utf8 when
@@ -714,4 +725,4 @@ The distribution should contain the following files:
 Philip Hazel
 Email local part: ph10
 Email domain: cam.ac.uk
-Last updated: 24 April 2007
+Last updated: 21 September 2007

ext/pcre/pcrelib/config.h

@@ -20,13 +20,24 @@ it to run on SunOS4 and other "close to standard" systems.
 
 If you are going to build PCRE "by hand" on a system without "configure" you
 should copy the distributed config.h.generic to config.h, and then set up the
-macros the way you need them. Alternatively, you can avoid editing by using -D
-on the compiler command line to set the macro values.
+macro definitions the way you need them. You must then add -DHAVE_CONFIG_H to
+all of your compile commands, so that config.h is included at the start of
+every source.
+
+Alternatively, you can avoid editing by using -D on the compiler command line
+to set the macro values. In this case, you do not have to set -DHAVE_CONFIG_H.
 
 PCRE uses memmove() if HAVE_MEMMOVE is set to 1; otherwise it uses bcopy() if
 HAVE_BCOPY is set to 1. If your system has neither bcopy() nor memmove(), set
 them both to 0; an emulation function will be used. */
 
+/* By default, the \R escape sequence matches any Unicode line ending
+   character or sequence of characters. If BSR_ANYCRLF is defined, this is
+   changed so that backslash-R matches only CR, LF, or CRLF. The build- time
+   default can be overridden by the user of PCRE at runtime. On systems that
+   support it, "configure" can be used to override the default. */
+/* #undef BSR_ANYCRLF */
+
 /* If you are compiling for a system that uses EBCDIC instead of ASCII
    character codes, define this macro as 1. On systems that can use
    "configure", this can be done via --enable-ebcdic. */
@@ -141,6 +152,9 @@ them both to 0; an emulation function will be used. */
 /* Define to 1 if you have the <windows.h> header file. */
 /* #undef HAVE_WINDOWS_H */
 
+/* Define to 1 if you have the `_strtoi64' function. */
+/* #undef HAVE__STRTOI64 */
+
 /* The value of LINK_SIZE determines the number of bytes used to store links
    as offsets within the compiled regex. The default is 2, which allows for
    compiled patterns up to 64K long. This covers the vast majority of cases.
@@ -189,10 +203,10 @@ them both to 0; an emulation function will be used. */
 #define MAX_NAME_SIZE 32
 #endif
 
-/* The value of NEWLINE determines the newline character sequence. On
-   Unix-like systems, "configure" can be used to override the default, which
-   is 10. The possible values are 10 (LF), 13 (CR), 3338 (CRLF), -1 (ANY), or
-   -2 (ANYCRLF). */
+/* The value of NEWLINE determines the newline character sequence. On systems
+   that support it, "configure" can be used to override the default, which is
+   10. The possible values are 10 (LF), 13 (CR), 3338 (CRLF), -1 (ANY), or -2
+   (ANYCRLF). */
 #ifndef NEWLINE
 #define NEWLINE 10
 #endif
@@ -217,13 +231,13 @@ them both to 0; an emulation function will be used. */
 #define PACKAGE_NAME "PCRE"
 
 /* Define to the full name and version of this package. */
-#define PACKAGE_STRING "PCRE 7.3"
+#define PACKAGE_STRING "PCRE 7.4"
 
 /* Define to the one symbol short name of this package. */
 #define PACKAGE_TARNAME "pcre"
 
 /* Define to the version of this package. */
-#define PACKAGE_VERSION "7.3"
+#define PACKAGE_VERSION "7.4"
 
 
 /* If you are compiling for a system other than a Unix-like system or
@@ -265,7 +279,7 @@ them both to 0; an emulation function will be used. */
 
 /* Version number of package */
 #ifndef VERSION
-#define VERSION "7.3"
+#define VERSION "7.4"
 #endif
 
 /* Define to empty if `const' does not conform to ANSI C. */

ext/pcre/pcrelib/dftables.c

@@ -43,7 +43,7 @@ character tables for PCRE. The tables are built according to the current
 locale. Now that pcre_maketables is a function visible to the outside world, we
 make use of its code from here in order to be consistent. */
 
-#include <config.h>
+#include "config.h"
 
 #include <ctype.h>
 #include <stdio.h>
@@ -108,7 +108,7 @@ fprintf(f,
   "outside this compilation unit might reference this\" and so it will always\n"
   "be supplied to the linker. */\n\n"
   "#ifdef HAVE_CONFIG_H\n"
-  "#include <config.h>\n"
+  "#include \"config.h\"\n"
   "#endif\n\n"
   "#include \"pcre_internal.h\"\n\n");
 fprintf(f,

ext/pcre/pcrelib/pcre.h

@@ -42,9 +42,9 @@ POSSIBILITY OF SUCH DAMAGE.
 /* The current PCRE version information. */
 
 #define PCRE_MAJOR          7
-#define PCRE_MINOR          3
+#define PCRE_MINOR          4
 #define PCRE_PRERELEASE     
-#define PCRE_DATE           2007-08-28
+#define PCRE_DATE           2007-09-21
 
 /* When an application links to a PCRE DLL in Windows, the symbols that are
 imported have to be identified as such. When building PCRE, the appropriate
@@ -122,6 +122,8 @@ extern "C" {
 #define PCRE_NEWLINE_CRLF       0x00300000
 #define PCRE_NEWLINE_ANY        0x00400000
 #define PCRE_NEWLINE_ANYCRLF    0x00500000
+#define PCRE_BSR_ANYCRLF        0x00800000
+#define PCRE_BSR_UNICODE        0x01000000
 
 /* Exec-time and get/set-time error codes */
 
@@ -147,7 +149,7 @@ extern "C" {
 #define PCRE_ERROR_DFA_WSSIZE     (-19)
 #define PCRE_ERROR_DFA_RECURSE    (-20)
 #define PCRE_ERROR_RECURSIONLIMIT (-21)
-#define PCRE_ERROR_NOTUSED        (-22)
+#define PCRE_ERROR_NULLWSLIMIT    (-22)  /* No longer actually used */
 #define PCRE_ERROR_BADNEWLINE     (-23)
 
 /* Request types for pcre_fullinfo() */
@@ -180,6 +182,7 @@ compatible. */
 #define PCRE_CONFIG_STACKRECURSE            5
 #define PCRE_CONFIG_UNICODE_PROPERTIES      6
 #define PCRE_CONFIG_MATCH_LIMIT_RECURSION   7
+#define PCRE_CONFIG_BSR                     8
 
 /* Bit flags for the pcre_extra structure. Do not re-arrange or redefine
 these bits, just add new ones on the end, in order to remain compatible. */

ext/pcre/pcrelib/pcre_chartables.c

@@ -20,7 +20,7 @@ and dead code stripping is activated. This leads to link errors. Pulling in the
 header ensures that the array gets flagged as "someone outside this compilation
 unit might reference this" and so it will always be supplied to the linker. */
 
-#include <config.h>
+#include "config.h"
 
 #include "pcre_internal.h"
 

ext/pcre/pcrelib/pcre_compile.c

@@ -42,7 +42,7 @@ POSSIBILITY OF SUCH DAMAGE.
 supporting internal functions that are not used by other modules. */
 
 
-#include <config.h>
+#include "config.h"
 
 #define NLBLOCK cd             /* Block containing newline information */
 #define PSSTART start_pattern  /* Field containing processed string start */
@@ -138,35 +138,47 @@ static const short int escapes[] = {
 #endif
 
 
-/* Table of special "verbs" like (*PRUNE) */
+/* Table of special "verbs" like (*PRUNE). This is a short table, so it is
+searched linearly. Put all the names into a single string, in order to reduce
+the number of relocations when a shared library is dynamically linked. */
 
 typedef struct verbitem {
-  const char *name;
   int   len;
   int   op;
 } verbitem;
 
+static const char verbnames[] =
+  "ACCEPT\0"
+  "COMMIT\0"
+  "F\0"
+  "FAIL\0"
+  "PRUNE\0"
+  "SKIP\0"
+  "THEN";
+
 static verbitem verbs[] = {
-  { "ACCEPT", 6, OP_ACCEPT },
-  { "COMMIT", 6, OP_COMMIT },
-  { "F",      1, OP_FAIL },
-  { "FAIL",   4, OP_FAIL },
-  { "PRUNE",  5, OP_PRUNE },
-  { "SKIP",   4, OP_SKIP  },
-  { "THEN",   4, OP_THEN  }
+  { 6, OP_ACCEPT },
+  { 6, OP_COMMIT },
+  { 1, OP_FAIL },
+  { 4, OP_FAIL },
+  { 5, OP_PRUNE },
+  { 4, OP_SKIP  },
+  { 4, OP_THEN  }
 };
 
 static int verbcount = sizeof(verbs)/sizeof(verbitem);
 
 
-/* Tables of names of POSIX character classes and their lengths. The list is
-terminated by a zero length entry. The first three must be alpha, lower, upper,
-as this is assumed for handling case independence. */
+/* Tables of names of POSIX character classes and their lengths. The names are
+now all in a single string, to reduce the number of relocations when a shared
+library is dynamically loaded. The list of lengths is terminated by a zero
+length entry. The first three must be alpha, lower, upper, as this is assumed
+for handling case independence. */
 
-static const char *const posix_names[] = {
-  "alpha", "lower", "upper",
-  "alnum", "ascii", "blank", "cntrl", "digit", "graph",
-  "print", "punct", "space", "word",  "xdigit" };
+static const char posix_names[] =
+  "alpha\0"  "lower\0"  "upper\0"  "alnum\0"  "ascii\0"  "blank\0"
+  "cntrl\0"  "digit\0"  "graph\0"  "print\0"  "punct\0"  "space\0"
+  "word\0"   "xdigit";
 
 static const uschar posix_name_lengths[] = {
   5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 4, 6, 0 };
@@ -205,84 +217,88 @@ static const int posix_class_maps[] = {
 /* The texts of compile-time error messages. These are "char *" because they
 are passed to the outside world. Do not ever re-use any error number, because
 they are documented. Always add a new error instead. Messages marked DEAD below
-are no longer used. */
+are no longer used. This used to be a table of strings, but in order to reduce
+the number of relocations needed when a shared library is loaded dynamically,
+it is now one long string. We cannot use a table of offsets, because the
+lengths of inserts such as XSTRING(MAX_NAME_SIZE) are not known. Instead, we
+simply count through to the one we want - this isn't a performance issue
+because these strings are used only when there is a compilation error. */
 
-static const char *error_texts[] = {
-  "no error",
-  "\\ at end of pattern",
-  "\\c at end of pattern",
-  "unrecognized character follows \\",
-  "numbers out of order in {} quantifier",
+static const char error_texts[] =
+  "no error\0"
+  "\\ at end of pattern\0"
+  "\\c at end of pattern\0"
+  "unrecognized character follows \\\0"
+  "numbers out of order in {} quantifier\0"
   /* 5 */
-  "number too big in {} quantifier",
-  "missing terminating ] for character class",
-  "invalid escape sequence in character class",
-  "range out of order in character class",
-  "nothing to repeat",
+  "number too big in {} quantifier\0"
+  "missing terminating ] for character class\0"
+  "invalid escape sequence in character class\0"
+  "range out of order in character class\0"
+  "nothing to repeat\0"
   /* 10 */
-  "operand of unlimited repeat could match the empty string",  /** DEAD **/
-  "internal error: unexpected repeat",
-  "unrecognized character after (?",
-  "POSIX named classes are supported only within a class",
-  "missing )",
+  "operand of unlimited repeat could match the empty string\0"  /** DEAD **/
+  "internal error: unexpected repeat\0"
+  "unrecognized character after (?\0"
+  "POSIX named classes are supported only within a class\0"
+  "missing )\0"
   /* 15 */
-  "reference to non-existent subpattern",
-  "erroffset passed as NULL",
-  "unknown option bit(s) set",
-  "missing ) after comment",
-  "parentheses nested too deeply",  /** DEAD **/
+  "reference to non-existent subpattern\0"
+  "erroffset passed as NULL\0"
+  "unknown option bit(s) set\0"
+  "missing ) after comment\0"
+  "parentheses nested too deeply\0"  /** DEAD **/
   /* 20 */
-  "regular expression is too large",
-  "failed to get memory",
-  "unmatched parentheses",
-  "internal error: code overflow",
-  "unrecognized character after (?<",
+  "regular expression is too large\0"
+  "failed to get memory\0"
+  "unmatched parentheses\0"
+  "internal error: code overflow\0"
+  "unrecognized character after (?<\0"
   /* 25 */
-  "lookbehind assertion is not fixed length",
-  "malformed number or name after (?(",
-  "conditional group contains more than two branches",
-  "assertion expected after (?(",
-  "(?R or (?[+-]digits must be followed by )",
+  "lookbehind assertion is not fixed length\0"
+  "malformed number or name after (?(\0"
+  "conditional group contains more than two branches\0"
+  "assertion expected after (?(\0"
+  "(?R or (?[+-]digits must be followed by )\0"
   /* 30 */
-  "unknown POSIX class name",
-  "POSIX collating elements are not supported",
-  "this version of PCRE is not compiled with PCRE_UTF8 support",
-  "spare error",  /** DEAD **/
-  "character value in \\x{...} sequence is too large",
+  "unknown POSIX class name\0"
+  "POSIX collating elements are not supported\0"
+  "this version of PCRE is not compiled with PCRE_UTF8 support\0"
+  "spare error\0"  /** DEAD **/
+  "character value in \\x{...} sequence is too large\0"
   /* 35 */
-  "invalid condition (?(0)",
-  "\\C not allowed in lookbehind assertion",
-  "PCRE does not support \\L, \\l, \\N, \\U, or \\u",
-  "number after (?C is > 255",
-  "closing ) for (?C expected",
+  "invalid condition (?(0)\0"
+  "\\C not allowed in lookbehind assertion\0"
+  "PCRE does not support \\L, \\l, \\N, \\U, or \\u\0"
+  "number after (?C is > 255\0"
+  "closing ) for (?C expected\0"
   /* 40 */
-  "recursive call could loop indefinitely",
-  "unrecognized character after (?P",
-  "syntax error in subpattern name (missing terminator)",
-  "two named subpatterns have the same name",
-  "invalid UTF-8 string",
+  "recursive call could loop indefinitely\0"
+  "unrecognized character after (?P\0"
+  "syntax error in subpattern name (missing terminator)\0"
+  "two named subpatterns have the same name\0"
+  "invalid UTF-8 string\0"
   /* 45 */
-  "support for \\P, \\p, and \\X has not been compiled",
-  "malformed \\P or \\p sequence",
-  "unknown property name after \\P or \\p",
-  "subpattern name is too long (maximum " XSTRING(MAX_NAME_SIZE) " characters)",
-  "too many named subpatterns (maximum " XSTRING(MAX_NAME_COUNT) ")",
+  "support for \\P, \\p, and \\X has not been compiled\0"
+  "malformed \\P or \\p sequence\0"
+  "unknown property name after \\P or \\p\0"
+  "subpattern name is too long (maximum " XSTRING(MAX_NAME_SIZE) " characters)\0"
+  "too many named subpatterns (maximum " XSTRING(MAX_NAME_COUNT) ")\0"
   /* 50 */
-  "repeated subpattern is too long",    /** DEAD **/
-  "octal value is greater than \\377 (not in UTF-8 mode)",
-  "internal error: overran compiling workspace",
-  "internal error: previously-checked referenced subpattern not found",
-  "DEFINE group contains more than one branch",
+  "repeated subpattern is too long\0"    /** DEAD **/
+  "octal value is greater than \\377 (not in UTF-8 mode)\0"
+  "internal error: overran compiling workspace\0"
+  "internal error: previously-checked referenced subpattern not found\0"
+  "DEFINE group contains more than one branch\0"
   /* 55 */
-  "repeating a DEFINE group is not allowed",
-  "inconsistent NEWLINE options",
-  "\\g is not followed by a braced name or an optionally braced non-zero number",
-  "(?+ or (?- or (?(+ or (?(- must be followed by a non-zero number",
-  "(*VERB) with an argument is not supported",
+  "repeating a DEFINE group is not allowed\0"
+  "inconsistent NEWLINE options\0"
+  "\\g is not followed by a braced name or an optionally braced non-zero number\0"
+  "(?+ or (?- or (?(+ or (?(- must be followed by a non-zero number\0"
+  "(*VERB) with an argument is not supported\0"
   /* 60 */
-  "(*VERB) not recognized",
-  "number is too big"
-};
+  "(*VERB) not recognized\0"
+  "number is too big";
 
 
 /* Table to identify digits and hex digits. This is used when compiling
@@ -417,6 +433,28 @@ static BOOL
 
 
 
+/*************************************************
+*            Find an error text                  *
+*************************************************/
+
+/* The error texts are now all in one long string, to save on relocations. As
+some of the text is of unknown length, we can't use a table of offsets.
+Instead, just count through the strings. This is not a performance issue
+because it happens only when there has been a compilation error.
+
+Argument:   the error number
+Returns:    pointer to the error string
+*/
+
+static const char *
+find_error_text(int n)
+{
+const char *s = error_texts;
+for (; n > 0; n--) while (*s++ != 0);
+return s;
+}
+
+
 /*************************************************
 *            Handle escapes                      *
 *************************************************/
@@ -774,7 +812,7 @@ top = _pcre_utt_size;
 while (bot < top)
   {
   i = (bot + top) >> 1;
-  c = strcmp(name, _pcre_utt[i].name);
+  c = strcmp(name, _pcre_utt_names + _pcre_utt[i].name_offset);
   if (c == 0)
     {
     *dptr = _pcre_utt[i].value;
@@ -1731,11 +1769,13 @@ Returns:     a value representing the name, or -1 if unknown
 static int
 check_posix_name(const uschar *ptr, int len)
 {
+const char *pn = posix_names;
 register int yield = 0;
 while (posix_name_lengths[yield] != 0)
   {
   if (len == posix_name_lengths[yield] &&
-    strncmp((const char *)ptr, posix_names[yield], len) == 0) return yield;
+    strncmp((const char *)ptr, pn, len) == 0) return yield;
+  pn += posix_name_lengths[yield] + 1;
   yield++;
   }
 return -1;
@@ -2974,6 +3014,12 @@ for (;; ptr++)
 
       oldptr = ptr;
 
+      /* Remember \r or \n */
+
+      if (c == '\r' || c == '\n') cd->external_flags |= PCRE_HASCRORLF;
+
+      /* Check for range */
+
       if (!inescq && ptr[1] == '-')
         {
         int d;
@@ -3041,6 +3087,10 @@ for (;; ptr++)
 
         if (d == c) goto LONE_SINGLE_CHARACTER;  /* A few lines below */
 
+        /* Remember \r or \n */
+
+        if (d == '\r' || d == '\n') cd->external_flags |= PCRE_HASCRORLF;
+
         /* In UTF-8 mode, if the upper limit is > 255, or > 127 for caseless
         matching, we have to use an XCLASS with extra data items. Caseless
         matching for characters > 127 is available only if UCP support is
@@ -3194,16 +3244,24 @@ for (;; ptr++)
       goto FAILED;
       }
 
+
+/* This code has been disabled because it would mean that \s counts as
+an explicit \r or \n reference, and that's not really what is wanted. Now
+we set the flag only if there is a literal "\r" or "\n" in the class. */
+
+#if 0
     /* Remember whether \r or \n are in this class */
 
     if (negate_class)
       {
-      if ((classbits[1] & 0x24) != 0x24) cd->external_options |= PCRE_HASCRORLF;
+      if ((classbits[1] & 0x24) != 0x24) cd->external_flags |= PCRE_HASCRORLF;
       }
     else
       {
-      if ((classbits[1] & 0x24) != 0) cd->external_options |= PCRE_HASCRORLF;
+      if ((classbits[1] & 0x24) != 0) cd->external_flags |= PCRE_HASCRORLF;
       }
+#endif
+
 
     /* If class_charcount is 1, we saw precisely one character whose value is
     less than 256. As long as there were no characters >= 128 and there was no
@@ -3496,7 +3554,7 @@ for (;; ptr++)
       /* All real repeats make it impossible to handle partial matching (maybe
       one day we will be able to remove this restriction). */
 
-      if (repeat_max != 1) cd->nopartial = TRUE;
+      if (repeat_max != 1) cd->external_flags |= PCRE_NOPARTIAL;
 
       /* Combine the op_type with the repeat_type */
 
@@ -3646,7 +3704,7 @@ for (;; ptr++)
       /* All real repeats make it impossible to handle partial matching (maybe
       one day we will be able to remove this restriction). */
 
-      if (repeat_max != 1) cd->nopartial = TRUE;
+      if (repeat_max != 1) cd->external_flags |= PCRE_NOPARTIAL;
 
       if (repeat_min == 0 && repeat_max == -1)
         *code++ = OP_CRSTAR + repeat_type;
@@ -4004,6 +4062,7 @@ for (;; ptr++)
     if (*(++ptr) == '*' && (cd->ctypes[ptr[1]] & ctype_letter) != 0)
       {
       int i, namelen;
+      const char *vn = verbnames;
       const uschar *name = ++ptr;
       previous = NULL;
       while ((cd->ctypes[*++ptr] & ctype_letter) != 0);
@@ -4021,12 +4080,13 @@ for (;; ptr++)
       for (i = 0; i < verbcount; i++)
         {
         if (namelen == verbs[i].len &&
-            strncmp((char *)name, verbs[i].name, namelen) == 0)
+            strncmp((char *)name, vn, namelen) == 0)
           {
           *code = verbs[i].op;
           if (*code++ == OP_ACCEPT) cd->had_accept = TRUE;
           break;
           }
+        vn += verbs[i].len + 1;
         }
       if (i < verbcount) continue;
       *errorcodeptr = ERR60;
@@ -4643,7 +4703,7 @@ for (;; ptr++)
 
             case 'J':    /* Record that it changed in the external options */
             *optset |= PCRE_DUPNAMES;
-            cd->external_options |= PCRE_JCHANGED;
+            cd->external_flags |= PCRE_JCHANGED;
             break;
 
             case 'i': *optset |= PCRE_CASELESS; break;
@@ -5063,7 +5123,7 @@ for (;; ptr++)
     /* Remember if \r or \n were seen */
 
     if (mcbuffer[0] == '\r' || mcbuffer[0] == '\n')
-      cd->external_options |= PCRE_HASCRORLF;
+      cd->external_flags |= PCRE_HASCRORLF;
 
     /* Set the first and required bytes appropriately. If no previous first
     byte, set it from this character, but revert to none on a zero repeat.
@@ -5743,24 +5803,46 @@ cd->fcc = tables + fcc_offset;
 cd->cbits = tables + cbits_offset;
 cd->ctypes = tables + ctypes_offset;
 
-/* Check for newline settings at the start of the pattern, and remember the
-offset for later. */
+/* Check for global one-time settings at the start of the pattern, and remember
+the offset for later. */
 
-if (ptr[0] == '(' && ptr[1] == '*')
+while (ptr[skipatstart] == '(' && ptr[skipatstart+1] == '*')
   {
   int newnl = 0;
-  if (strncmp((char *)(ptr+2), "CR)", 3) == 0)
-    { skipatstart = 5; newnl = PCRE_NEWLINE_CR; }
-  else if (strncmp((char *)(ptr+2), "LF)", 3)  == 0)
-    { skipatstart = 5; newnl = PCRE_NEWLINE_LF; }
-  else if (strncmp((char *)(ptr+2), "CRLF)", 5)  == 0)
-    { skipatstart = 7; newnl = PCRE_NEWLINE_CR + PCRE_NEWLINE_LF; }
-  else if (strncmp((char *)(ptr+2), "ANY)", 4) == 0)
-    { skipatstart = 6; newnl = PCRE_NEWLINE_ANY; }
-  else if (strncmp((char *)(ptr+2), "ANYCRLF)", 8)  == 0)
-    { skipatstart = 10; newnl = PCRE_NEWLINE_ANYCRLF; }
-  if (skipatstart > 0)
+  int newbsr = 0;
+
+  if (strncmp((char *)(ptr+skipatstart+2), "CR)", 3) == 0)
+    { skipatstart += 5; newnl = PCRE_NEWLINE_CR; }
+  else if (strncmp((char *)(ptr+skipatstart+2), "LF)", 3)  == 0)
+    { skipatstart += 5; newnl = PCRE_NEWLINE_LF; }
+  else if (strncmp((char *)(ptr+skipatstart+2), "CRLF)", 5)  == 0)
+    { skipatstart += 7; newnl = PCRE_NEWLINE_CR + PCRE_NEWLINE_LF; }
+  else if (strncmp((char *)(ptr+skipatstart+2), "ANY)", 4) == 0)
+    { skipatstart += 6; newnl = PCRE_NEWLINE_ANY; }
+  else if (strncmp((char *)(ptr+skipatstart+2), "ANYCRLF)", 8)  == 0)
+    { skipatstart += 10; newnl = PCRE_NEWLINE_ANYCRLF; }
+
+  else if (strncmp((char *)(ptr+skipatstart+2), "BSR_ANYCRLF)", 12) == 0)
+    { skipatstart += 14; newbsr = PCRE_BSR_ANYCRLF; }
+  else if (strncmp((char *)(ptr+skipatstart+2), "BSR_UNICODE)", 12) == 0)
+    { skipatstart += 14; newbsr = PCRE_BSR_UNICODE; }
+
+  if (newnl != 0)
     options = (options & ~PCRE_NEWLINE_BITS) | newnl;
+  else if (newbsr != 0)
+    options = (options & ~(PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) | newbsr;
+  else break;
+  }
+
+/* Check validity of \R options. */
+
+switch (options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE))
+  {
+  case 0:
+  case PCRE_BSR_ANYCRLF:
+  case PCRE_BSR_UNICODE:
+  break;
+  default: errorcode = ERR56; goto PCRE_EARLY_ERROR_RETURN;
   }
 
 /* Handle different types of newline. The three bits give seven cases. The
@@ -5832,8 +5914,8 @@ cd->hwm = cworkspace;
 cd->start_pattern = (const uschar *)pattern;
 cd->end_pattern = (const uschar *)(pattern + strlen(pattern));
 cd->req_varyopt = 0;
-cd->nopartial = FALSE;
 cd->external_options = options;
+cd->external_flags = 0;
 
 /* Now do the pre-compile. On error, errorcode will be set non-zero, so we
 don't need to look at the result of the function here. The initial options have
@@ -5872,14 +5954,16 @@ if (re == NULL)
   goto PCRE_EARLY_ERROR_RETURN;
   }
 
-/* Put in the magic number, and save the sizes, initial options, and character
-table pointer. NULL is used for the default character tables. The nullpad field
-is at the end; it's there to help in the case when a regex compiled on a system
-with 4-byte pointers is run on another with 8-byte pointers. */
+/* Put in the magic number, and save the sizes, initial options, internal
+flags, and character table pointer. NULL is used for the default character
+tables. The nullpad field is at the end; it's there to help in the case when a
+regex compiled on a system with 4-byte pointers is run on another with 8-byte
+pointers. */
 
 re->magic_number = MAGIC_NUMBER;
 re->size = size;
 re->options = cd->external_options;
+re->flags = cd->external_flags;
 re->dummy1 = 0;
 re->first_byte = 0;
 re->req_byte = 0;
@@ -5904,7 +5988,6 @@ codestart = cd->name_table + re->name_entry_size * re->name_count;
 cd->start_code = codestart;
 cd->hwm = cworkspace;
 cd->req_varyopt = 0;
-cd->nopartial = FALSE;
 cd->had_accept = FALSE;
 
 /* Set up a starting, non-extracting bracket, then compile the expression. On
@@ -5918,8 +6001,8 @@ code = (uschar *)codestart;
   &errorcode, FALSE, FALSE, 0, &firstbyte, &reqbyte, NULL, cd, NULL);
 re->top_bracket = cd->bracount;
 re->top_backref = cd->top_backref;
+re->flags = cd->external_flags;
 
-if (cd->nopartial) re->options |= PCRE_NOPARTIAL;
 if (cd->had_accept) reqbyte = -1;   /* Must disable after (*ACCEPT) */
 
 /* If not reached end of pattern on success, there's an excess bracket. */
@@ -5962,7 +6045,7 @@ if (errorcode != 0)
   PCRE_EARLY_ERROR_RETURN:
   *erroroffset = ptr - (const uschar *)pattern;
   PCRE_EARLY_ERROR_RETURN2:
-  *errorptr = error_texts[errorcode];
+  *errorptr = find_error_text(errorcode);
   if (errorcodeptr != NULL) *errorcodeptr = errorcode;
   return NULL;
   }
@@ -5991,10 +6074,10 @@ if ((re->options & PCRE_ANCHORED) == 0)
       int ch = firstbyte & 255;
       re->first_byte = ((firstbyte & REQ_CASELESS) != 0 &&
          cd->fcc[ch] == ch)? ch : firstbyte;
-      re->options |= PCRE_FIRSTSET;
+      re->flags |= PCRE_FIRSTSET;
       }
     else if (is_startline(codestart, 0, cd->backref_map))
-      re->options |= PCRE_STARTLINE;
+      re->flags |= PCRE_STARTLINE;
     }
   }
 
@@ -6008,7 +6091,7 @@ if (reqbyte >= 0 &&
   int ch = reqbyte & 255;
   re->req_byte = ((reqbyte & REQ_CASELESS) != 0 &&
     cd->fcc[ch] == ch)? (reqbyte & ~REQ_CASELESS) : reqbyte;
-  re->options |= PCRE_REQCHSET;
+  re->flags |= PCRE_REQCHSET;
   }
 
 /* Print out the compiled data if debugging is enabled. This is never the
@@ -6021,7 +6104,7 @@ printf("Length = %d top_bracket = %d top_backref = %d\n",
 
 printf("Options=%08x\n", re->options);
 
-if ((re->options & PCRE_FIRSTSET) != 0)
+if ((re->flags & PCRE_FIRSTSET) != 0)
   {
   int ch = re->first_byte & 255;
   const char *caseless = ((re->first_byte & REQ_CASELESS) == 0)?
@@ -6030,7 +6113,7 @@ if ((re->options & PCRE_FIRSTSET) != 0)
     else printf("First char = \\x%02x%s\n", ch, caseless);
   }
 
-if ((re->options & PCRE_REQCHSET) != 0)
+if ((re->flags & PCRE_REQCHSET) != 0)
   {
   int ch = re->req_byte & 255;
   const char *caseless = ((re->req_byte & REQ_CASELESS) == 0)?
@@ -6047,7 +6130,7 @@ was compiled can be seen. */
 if (code - codestart > length)
   {
   (pcre_free)(re);
-  *errorptr = error_texts[ERR23];
+  *errorptr = find_error_text(ERR23);
   *erroroffset = ptr - (uschar *)pattern;
   if (errorcodeptr != NULL) *errorcodeptr = ERR23;
   return NULL;

ext/pcre/pcrelib/pcre_config.c

@@ -41,7 +41,7 @@ POSSIBILITY OF SUCH DAMAGE.
 /* This module contains the external function pcre_config(). */
 
 
-#include <config.h>
+#include "config.h"
 
 #include "pcre_internal.h"
 
@@ -85,6 +85,14 @@ switch (what)
   *((int *)where) = NEWLINE;
   break;
 
+  case PCRE_CONFIG_BSR:
+#ifdef BSR_ANYCRLF
+  *((int *)where) = 1;
+#else
+  *((int *)where) = 0;
+#endif
+  break;
+
   case PCRE_CONFIG_LINK_SIZE:
   *((int *)where) = LINK_SIZE;
   break;

ext/pcre/pcrelib/pcre_exec.c

@@ -42,7 +42,7 @@ POSSIBILITY OF SUCH DAMAGE.
 pattern matching using an NFA algorithm, trying to mimic Perl as closely as
 possible. There are also some static supporting functions. */
 
-#include <config.h>
+#include "config.h"
 
 #define NLBLOCK md             /* Block containing newline information */
 #define PSSTART start_subject  /* Field containing processed string start */
@@ -1524,12 +1524,16 @@ for (;;)
       case 0x000d:
       if (eptr < md->end_subject && *eptr == 0x0a) eptr++;
       break;
+
       case 0x000a:
+      break;
+
       case 0x000b:
       case 0x000c:
       case 0x0085:
       case 0x2028:
       case 0x2029:
+      if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH);
       break;
       }
     ecode++;
@@ -2952,12 +2956,16 @@ for (;;)
             case 0x000d:
             if (eptr < md->end_subject && *eptr == 0x0a) eptr++;
             break;
+
             case 0x000a:
+            break;
+
             case 0x000b:
             case 0x000c:
             case 0x0085:
             case 0x2028:
             case 0x2029:
+            if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH);
             break;
             }
           }
@@ -3170,9 +3178,12 @@ for (;;)
             if (eptr < md->end_subject && *eptr == 0x0a) eptr++;
             break;
             case 0x000a:
+            break;
+
             case 0x000b:
             case 0x000c:
             case 0x0085:
+            if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH);
             break;
             }
           }
@@ -3424,11 +3435,14 @@ for (;;)
               if (eptr < md->end_subject && *eptr == 0x0a) eptr++;
               break;
               case 0x000a:
+              break;
+
               case 0x000b:
               case 0x000c:
               case 0x0085:
               case 0x2028:
               case 0x2029:
+              if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH);
               break;
               }
             break;
@@ -3580,10 +3594,14 @@ for (;;)
               case 0x000d:
               if (eptr < md->end_subject && *eptr == 0x0a) eptr++;
               break;
+
               case 0x000a:
+              break;
+
               case 0x000b:
               case 0x000c:
               case 0x0085:
+              if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH);
               break;
               }
             break;
@@ -3881,8 +3899,10 @@ for (;;)
               }
             else
               {
-              if (c != 0x000a && c != 0x000b && c != 0x000c &&
-                  c != 0x0085 && c != 0x2028 && c != 0x2029)
+              if (c != 0x000a &&
+                  (md->bsr_anycrlf ||
+                   (c != 0x000b && c != 0x000c &&
+                    c != 0x0085 && c != 0x2028 && c != 0x2029)))
                 break;
               eptr += len;
               }
@@ -4072,7 +4092,9 @@ for (;;)
               }
             else
               {
-              if (c != 0x000a && c != 0x000b && c != 0x000c && c != 0x0085)
+              if (c != 0x000a &&
+                  (md->bsr_anycrlf ||
+                    (c != 0x000b && c != 0x000c && c != 0x0085)))
                 break;
               eptr++;
               }
@@ -4222,12 +4244,17 @@ HEAP_RETURN:
 switch (frame->Xwhere)
   {
   LBL( 1) LBL( 2) LBL( 3) LBL( 4) LBL( 5) LBL( 6) LBL( 7) LBL( 8)
-  LBL( 9) LBL(10) LBL(11) LBL(12) LBL(13) LBL(14) LBL(15) LBL(16)
-  LBL(17) LBL(18) LBL(19) LBL(20) LBL(21) LBL(22) LBL(23) LBL(24)
-  LBL(25) LBL(26) LBL(27) LBL(28) LBL(29) LBL(30) LBL(31) LBL(32)
-  LBL(33) LBL(34) LBL(35) LBL(36) LBL(37) LBL(38) LBL(39) LBL(40)
-  LBL(41) LBL(42) LBL(43) LBL(44) LBL(45) LBL(46) LBL(47) LBL(48)
-  LBL(49) LBL(50) LBL(51) LBL(52) LBL(53) LBL(54)
+  LBL( 9) LBL(10) LBL(11) LBL(12) LBL(13) LBL(14) LBL(15) LBL(17)
+  LBL(19) LBL(24) LBL(25) LBL(26) LBL(27) LBL(29) LBL(31) LBL(33)
+  LBL(35) LBL(43) LBL(47) LBL(48) LBL(49) LBL(50) LBL(51) LBL(52)
+  LBL(53) LBL(54)
+#ifdef SUPPORT_UTF8
+  LBL(16) LBL(18) LBL(20) LBL(21) LBL(22) LBL(23) LBL(28) LBL(30)
+  LBL(32) LBL(34) LBL(42) LBL(46)
+#ifdef SUPPORT_UCP
+  LBL(36) LBL(37) LBL(38) LBL(39) LBL(40) LBL(41) LBL(44) LBL(45)
+#endif  /* SUPPORT_UCP */
+#endif  /* SUPPORT_UTF8 */
   default:
   DPRINTF(("jump error in pcre match: label %d non-existent\n", frame->Xwhere));
   return PCRE_ERROR_INTERNAL;
@@ -4406,7 +4433,7 @@ if (re->magic_number != MAGIC_NUMBER)
 /* Set up other data */
 
 anchored = ((re->options | options) & PCRE_ANCHORED) != 0;
-startline = (re->options & PCRE_STARTLINE) != 0;
+startline = (re->flags & PCRE_STARTLINE) != 0;
 firstline = (re->options & PCRE_FIRSTLINE) != 0;
 
 /* The code starts after the real_pcre block and the capture name table. */
@@ -4433,11 +4460,37 @@ md->recursive = NULL;                   /* No recursion at top level */
 md->lcc = tables + lcc_offset;
 md->ctypes = tables + ctypes_offset;
 
+/* Handle different \R options. */
+
+switch (options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE))
+  {
+  case 0:
+  if ((re->options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) != 0)
+    md->bsr_anycrlf = (re->options & PCRE_BSR_ANYCRLF) != 0;
+  else
+#ifdef BSR_ANYCRLF
+  md->bsr_anycrlf = TRUE;
+#else
+  md->bsr_anycrlf = FALSE;
+#endif
+  break;
+
+  case PCRE_BSR_ANYCRLF:
+  md->bsr_anycrlf = TRUE;
+  break;
+
+  case PCRE_BSR_UNICODE:
+  md->bsr_anycrlf = FALSE;
+  break;
+
+  default: return PCRE_ERROR_BADNEWLINE;
+  }
+
 /* Handle different types of newline. The three bits give eight cases. If
 nothing is set at run time, whatever was used at compile time applies. */
 
-switch ((((options & PCRE_NEWLINE_BITS) == 0)? re->options : (pcre_uint32)options) &
-       PCRE_NEWLINE_BITS)
+switch ((((options & PCRE_NEWLINE_BITS) == 0)? re->options :
+        (pcre_uint32)options) & PCRE_NEWLINE_BITS)
   {
   case 0: newline = NEWLINE; break;   /* Compile-time default */
   case PCRE_NEWLINE_CR: newline = '\r'; break;
@@ -4476,7 +4529,7 @@ else
 /* Partial matching is supported only for a restricted set of regexes at the
 moment. */
 
-if (md->partial && (re->options & PCRE_NOPARTIAL) != 0)
+if (md->partial && (re->flags & PCRE_NOPARTIAL) != 0)
   return PCRE_ERROR_BADPARTIAL;
 
 /* Check a UTF-8 string if required. Unfortunately there's no way of passing
@@ -4553,7 +4606,7 @@ studied, there may be a bitmap of possible first characters. */
 
 if (!anchored)
   {
-  if ((re->options & PCRE_FIRSTSET) != 0)
+  if ((re->flags & PCRE_FIRSTSET) != 0)
     {
     first_byte = re->first_byte & 255;
     if ((first_byte_caseless = ((re->first_byte & REQ_CASELESS) != 0)) == TRUE)
@@ -4568,7 +4621,7 @@ if (!anchored)
 /* For anchored or unanchored matches, there may be a "last known required
 character" set. */
 
-if ((re->options & PCRE_REQCHSET) != 0)
+if ((re->flags & PCRE_REQCHSET) != 0)
   {
   req_byte = re->req_byte & 255;
   req_byte_caseless = (re->req_byte & REQ_CASELESS) != 0;
@@ -4790,7 +4843,7 @@ for(;;)
   if (start_match[-1] == '\r' &&
       start_match < end_subject &&
       *start_match == '\n' &&
-      (re->options & PCRE_HASCRORLF) == 0 &&
+      (re->flags & PCRE_HASCRORLF) == 0 &&
         (md->nltype == NLTYPE_ANY ||
          md->nltype == NLTYPE_ANYCRLF ||
          md->nllen == 2))

ext/pcre/pcrelib/pcre_fullinfo.c

@@ -42,7 +42,7 @@ POSSIBILITY OF SUCH DAMAGE.
 information about a compiled pattern. */
 
 
-#include <config.h>
+#include "config.h"
 
 #include "pcre_internal.h"
 
@@ -108,8 +108,8 @@ switch (what)
 
   case PCRE_INFO_FIRSTBYTE:
   *((int *)where) =
-    ((re->options & PCRE_FIRSTSET) != 0)? re->first_byte :
-    ((re->options & PCRE_STARTLINE) != 0)? -1 : -2;
+    ((re->flags & PCRE_FIRSTSET) != 0)? re->first_byte :
+    ((re->flags & PCRE_STARTLINE) != 0)? -1 : -2;
   break;
 
   /* Make sure we pass back the pointer to the bit vector in the external
@@ -123,7 +123,7 @@ switch (what)
 
   case PCRE_INFO_LASTLITERAL:
   *((int *)where) =
-    ((re->options & PCRE_REQCHSET) != 0)? re->req_byte : -1;
+    ((re->flags & PCRE_REQCHSET) != 0)? re->req_byte : -1;
   break;
 
   case PCRE_INFO_NAMEENTRYSIZE:
@@ -143,15 +143,15 @@ switch (what)
   break;
 
   case PCRE_INFO_OKPARTIAL:
-  *((int *)where) = (re->options & PCRE_NOPARTIAL) == 0;
+  *((int *)where) = (re->flags & PCRE_NOPARTIAL) == 0;
   break;
 
   case PCRE_INFO_JCHANGED:
-  *((int *)where) = (re->options & PCRE_JCHANGED) != 0;
+  *((int *)where) = (re->flags & PCRE_JCHANGED) != 0;
   break;
 
   case PCRE_INFO_HASCRORLF:
-  *((int *)where) = (re->options & PCRE_HASCRORLF) != 0;
+  *((int *)where) = (re->flags & PCRE_HASCRORLF) != 0;
   break;
 
   default: return PCRE_ERROR_BADOPTION;

ext/pcre/pcrelib/pcre_get.c

@@ -43,7 +43,7 @@ from the subject string after a regex match has succeeded. The original idea
 for these functions came from Scott Wimer. */
 
 
-#include <config.h>
+#include "config.h"
 
 #include "pcre_internal.h"
 
@@ -187,7 +187,7 @@ const real_pcre *re = (const real_pcre *)code;
 int entrysize;
 char *first, *last;
 uschar *entry;
-if ((re->options & (PCRE_DUPNAMES | PCRE_JCHANGED)) == 0)
+if ((re->options & PCRE_DUPNAMES) == 0 && (re->flags & PCRE_JCHANGED) == 0)
   return pcre_get_stringnumber(code, stringname);
 entrysize = pcre_get_stringtable_entries(code, stringname, &first, &last);
 if (entrysize <= 0) return entrysize;

ext/pcre/pcrelib/pcre_globals.c

@@ -46,7 +46,7 @@ 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 <config.h>
+#include "config.h"
 
 #include "pcre_internal.h"
 

ext/pcre/pcrelib/pcre_info.c

@@ -43,7 +43,7 @@ information about a compiled pattern. However, use of this function is now
 deprecated, as it has been superseded by pcre_fullinfo(). */
 
 
-#include <config.h>
+#include "config.h"
 
 #include "pcre_internal.h"
 
@@ -83,8 +83,8 @@ if (re->magic_number != MAGIC_NUMBER)
   }
 if (optptr != NULL) *optptr = (int)(re->options & PUBLIC_OPTIONS);
 if (first_byte != NULL)
-  *first_byte = ((re->options & PCRE_FIRSTSET) != 0)? re->first_byte :
-     ((re->options & PCRE_STARTLINE) != 0)? -1 : -2;
+  *first_byte = ((re->flags & PCRE_FIRSTSET) != 0)? re->first_byte :
+     ((re->flags & PCRE_STARTLINE) != 0)? -1 : -2;
 return re->top_bracket;
 }
 

ext/pcre/pcrelib/pcre_internal.h

@@ -481,18 +481,16 @@ Standard C system should have one. */
 
 #define PCRE_IMS (PCRE_CASELESS|PCRE_MULTILINE|PCRE_DOTALL)
 
-/* Private options flags start at the most significant end of the four bytes.
-The public options defined in pcre.h start at the least significant end. Make
-sure they don't overlap! The bits are getting a bit scarce now -- when we run
-out, there is a dummy word in the structure that could be used for the private
-bits. */
+/* Private flags containing information about the compiled regex. They used to
+live at the top end of the options word, but that got almost full, so now they
+are in a 16-bit flags word. */
 
-#define PCRE_NOPARTIAL     0x80000000  /* can't use partial with this regex */
-#define PCRE_FIRSTSET      0x40000000  /* first_byte is set */
-#define PCRE_REQCHSET      0x20000000  /* req_byte is set */
-#define PCRE_STARTLINE     0x10000000  /* start after \n for multiline */
-#define PCRE_JCHANGED      0x08000000  /* j option changes within regex */
-#define PCRE_HASCRORLF     0x04000000  /* explicit \r or \n in pattern */
+#define PCRE_NOPARTIAL     0x0001  /* can't use partial with this regex */
+#define PCRE_FIRSTSET      0x0002  /* first_byte is set */
+#define PCRE_REQCHSET      0x0004  /* req_byte is set */
+#define PCRE_STARTLINE     0x0008  /* start after \n for multiline */
+#define PCRE_JCHANGED      0x0010  /* j option used in regex */
+#define PCRE_HASCRORLF     0x0020  /* explicit \r or \n in pattern */
 
 /* Options for the "extra" block produced by pcre_study(). */
 
@@ -508,15 +506,16 @@ time, run time, or study time, respectively. */
   (PCRE_CASELESS|PCRE_EXTENDED|PCRE_ANCHORED|PCRE_MULTILINE| \
    PCRE_DOTALL|PCRE_DOLLAR_ENDONLY|PCRE_EXTRA|PCRE_UNGREEDY|PCRE_UTF8| \
    PCRE_NO_AUTO_CAPTURE|PCRE_NO_UTF8_CHECK|PCRE_AUTO_CALLOUT|PCRE_FIRSTLINE| \
-   PCRE_DUPNAMES|PCRE_NEWLINE_BITS)
+   PCRE_DUPNAMES|PCRE_NEWLINE_BITS|PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)
 
 #define PUBLIC_EXEC_OPTIONS \
   (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK| \
-   PCRE_PARTIAL|PCRE_NEWLINE_BITS)
+   PCRE_PARTIAL|PCRE_NEWLINE_BITS|PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)
 
 #define PUBLIC_DFA_EXEC_OPTIONS \
   (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK| \
-   PCRE_PARTIAL|PCRE_DFA_SHORTEST|PCRE_DFA_RESTART|PCRE_NEWLINE_BITS)
+   PCRE_PARTIAL|PCRE_DFA_SHORTEST|PCRE_DFA_RESTART|PCRE_NEWLINE_BITS| \
+   PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)
 
 #define PUBLIC_STUDY_OPTIONS 0   /* None defined */
 
@@ -894,9 +893,9 @@ NOTE NOTE NOTE:
 typedef struct real_pcre {
   pcre_uint32 magic_number;
   pcre_uint32 size;               /* Total that was malloced */
-  pcre_uint32 options;
-  pcre_uint32 dummy1;             /* For future use, maybe */
-
+  pcre_uint32 options;            /* Public options */
+  pcre_uint16 flags;              /* Private flags */
+  pcre_uint16 dummy1;             /* For future use */
   pcre_uint16 top_bracket;
   pcre_uint16 top_backref;
   pcre_uint16 first_byte;
@@ -939,8 +938,8 @@ typedef struct compile_data {
   int  top_backref;             /* Maximum back reference */
   unsigned int backref_map;     /* Bitmap of low back refs */
   int  external_options;        /* External (initial) options */
+  int  external_flags;          /* External flag bits to be set */
   int  req_varyopt;             /* "After variable item" flag for reqbyte */
-  BOOL nopartial;               /* Set TRUE if partial won't work */
   BOOL had_accept;              /* (*ACCEPT) encountered */
   int  nltype;                  /* Newline type */
   int  nllen;                   /* Newline string length */
@@ -1000,6 +999,7 @@ typedef struct match_data {
   BOOL   notempty;              /* Empty string match not wanted */
   BOOL   partial;               /* PARTIAL flag */
   BOOL   hitend;                /* Hit the end of the subject at some point */
+  BOOL   bsr_anycrlf;           /* \R is just any CRLF, not full Unicode */
   const uschar *start_code;     /* For use when recursing */
   USPTR  start_subject;         /* Start of the subject string */
   USPTR  end_subject;           /* End of the subject string */
@@ -1064,10 +1064,12 @@ total length. */
 #define tables_length (ctypes_offset + 256)
 
 /* Layout of the UCP type table that translates property names into types and
-codes. */
+codes. Each entry used to point directly to a name, but to reduce the number of
+relocations in shared libraries, it now has an offset into a single string
+instead. */
 
 typedef struct {
-  const char *name;
+  pcre_uint16 name_offset;
   pcre_uint16 type;
   pcre_uint16 value;
 } ucp_type_table;
@@ -1085,6 +1087,7 @@ extern const uschar _pcre_utf8_table4[];
 
 extern const int    _pcre_utf8_table1_size;
 
+extern const char   _pcre_utt_names[];
 extern const ucp_type_table _pcre_utt[];
 extern const int _pcre_utt_size;
 

ext/pcre/pcrelib/pcre_maketables.c

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

ext/pcre/pcrelib/pcre_newline.c

@@ -47,7 +47,7 @@ and NLTYPE_ANY. The full list of Unicode newline characters is taken from
 http://unicode.org/unicode/reports/tr18/. */
 
 
-#include <config.h>
+#include "config.h"
 
 #include "pcre_internal.h"
 

ext/pcre/pcrelib/pcre_ord2utf8.c

@@ -41,7 +41,7 @@ POSSIBILITY OF SUCH DAMAGE.
 /* This file contains a private PCRE function that converts an ordinal
 character value into a UTF8 string. */
 
-#include <config.h>
+#include "config.h"
 
 #include "pcre_internal.h"
 

ext/pcre/pcrelib/pcre_printint.src

@@ -126,7 +126,7 @@ for (i = _pcre_utt_size - 1; i >= 0; i--)
   {
   if (ptype == _pcre_utt[i].type && pvalue == _pcre_utt[i].value) break;
   }
-return (i >= 0)? _pcre_utt[i].name : "??";
+return (i >= 0)? _pcre_utt_names + _pcre_utt[i].name_offset : "??";
 #else
 /* It gets harder and harder to shut off unwanted compiler warnings. */
 ptype = ptype * pvalue;

ext/pcre/pcrelib/pcre_refcount.c

@@ -44,7 +44,7 @@ pattern data block. This might be helpful in applications where the block is
 shared by different users. */
 
 
-#include <config.h>
+#include "config.h"
 
 #include "pcre_internal.h"
 

ext/pcre/pcrelib/pcre_study.c

@@ -42,7 +42,7 @@ POSSIBILITY OF SUCH DAMAGE.
 supporting functions. */
 
 
-#include <config.h>
+#include "config.h"
 
 #include "pcre_internal.h"
 
@@ -525,7 +525,8 @@ code = (uschar *)re + re->name_table_offset +
 a multiline pattern that matches only at "line starts", no further processing
 at present. */
 
-if ((re->options & (PCRE_ANCHORED|PCRE_FIRSTSET|PCRE_STARTLINE)) != 0)
+if ((re->options & PCRE_ANCHORED) != 0 ||
+    (re->flags & (PCRE_FIRSTSET|PCRE_STARTLINE)) != 0)
   return NULL;
 
 /* Set the character tables in the block that is passed around */

ext/pcre/pcrelib/pcre_tables.c

@@ -44,7 +44,7 @@ uses macros to change their names from _pcre_xxx to xxxx, thereby avoiding name
 clashes with the library. */
 
 
-#include <config.h>
+#include "config.h"
 
 #include "pcre_internal.h"
 
@@ -85,115 +85,228 @@ const uschar _pcre_utf8_table4[] = {
   2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
   3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 };
 
-/* This table translates Unicode property names into type and code values. It
-is searched by binary chop, so must be in collating sequence of name. */
+/* The pcre_utt[] table below translates Unicode property names into type and
+code values. It is searched by binary chop, so must be in collating sequence of
+name. Originally, the table contained pointers to the name strings in the first
+field of each entry. However, that leads to a large number of relocations when
+a shared library is dynamically loaded. A significant reduction is made by
+putting all the names into a single, large string and then using offsets in the
+table itself. Maintenance is more error-prone, but frequent changes to this
+data is unlikely. */
+
+const char _pcre_utt_names[] =
+  "Any\0"
+  "Arabic\0"
+  "Armenian\0"
+  "Balinese\0"
+  "Bengali\0"
+  "Bopomofo\0"
+  "Braille\0"
+  "Buginese\0"
+  "Buhid\0"
+  "C\0"
+  "Canadian_Aboriginal\0"
+  "Cc\0"
+  "Cf\0"
+  "Cherokee\0"
+  "Cn\0"
+  "Co\0"
+  "Common\0"
+  "Coptic\0"
+  "Cs\0"
+  "Cuneiform\0"
+  "Cypriot\0"
+  "Cyrillic\0"
+  "Deseret\0"
+  "Devanagari\0"
+  "Ethiopic\0"
+  "Georgian\0"
+  "Glagolitic\0"
+  "Gothic\0"
+  "Greek\0"
+  "Gujarati\0"
+  "Gurmukhi\0"
+  "Han\0"
+  "Hangul\0"
+  "Hanunoo\0"
+  "Hebrew\0"
+  "Hiragana\0"
+  "Inherited\0"
+  "Kannada\0"
+  "Katakana\0"
+  "Kharoshthi\0"
+  "Khmer\0"
+  "L\0"
+  "L&\0"
+  "Lao\0"
+  "Latin\0"
+  "Limbu\0"
+  "Linear_B\0"
+  "Ll\0"
+  "Lm\0"
+  "Lo\0"
+  "Lt\0"
+  "Lu\0"
+  "M\0"
+  "Malayalam\0"
+  "Mc\0"
+  "Me\0"
+  "Mn\0"
+  "Mongolian\0"
+  "Myanmar\0"
+  "N\0"
+  "Nd\0"
+  "New_Tai_Lue\0"
+  "Nko\0"
+  "Nl\0"
+  "No\0"
+  "Ogham\0"
+  "Old_Italic\0"
+  "Old_Persian\0"
+  "Oriya\0"
+  "Osmanya\0"
+  "P\0"
+  "Pc\0"
+  "Pd\0"
+  "Pe\0"
+  "Pf\0"
+  "Phags_Pa\0"
+  "Phoenician\0"
+  "Pi\0"
+  "Po\0"
+  "Ps\0"
+  "Runic\0"
+  "S\0"
+  "Sc\0"
+  "Shavian\0"
+  "Sinhala\0"
+  "Sk\0"
+  "Sm\0"
+  "So\0"
+  "Syloti_Nagri\0"
+  "Syriac\0"
+  "Tagalog\0"
+  "Tagbanwa\0"
+  "Tai_Le\0"
+  "Tamil\0"
+  "Telugu\0"
+  "Thaana\0"
+  "Thai\0"
+  "Tibetan\0"
+  "Tifinagh\0"
+  "Ugaritic\0"
+  "Yi\0"
+  "Z\0"
+  "Zl\0"
+  "Zp\0"
+  "Zs\0";
 
 const ucp_type_table _pcre_utt[] = {
-  { "Any",                 PT_ANY,  0 },
-  { "Arabic",              PT_SC,   ucp_Arabic },
-  { "Armenian",            PT_SC,   ucp_Armenian },
-  { "Balinese",            PT_SC,   ucp_Balinese },
-  { "Bengali",             PT_SC,   ucp_Bengali },
-  { "Bopomofo",            PT_SC,   ucp_Bopomofo },
-  { "Braille",             PT_SC,   ucp_Braille },
-  { "Buginese",            PT_SC,   ucp_Buginese },
-  { "Buhid",               PT_SC,   ucp_Buhid },
-  { "C",                   PT_GC,   ucp_C },
-  { "Canadian_Aboriginal", PT_SC,   ucp_Canadian_Aboriginal },
-  { "Cc",                  PT_PC,   ucp_Cc },
-  { "Cf",                  PT_PC,   ucp_Cf },
-  { "Cherokee",            PT_SC,   ucp_Cherokee },
-  { "Cn",                  PT_PC,   ucp_Cn },
-  { "Co",                  PT_PC,   ucp_Co },
-  { "Common",              PT_SC,   ucp_Common },
-  { "Coptic",              PT_SC,   ucp_Coptic },
-  { "Cs",                  PT_PC,   ucp_Cs },
-  { "Cuneiform",           PT_SC,   ucp_Cuneiform },
-  { "Cypriot",             PT_SC,   ucp_Cypriot },
-  { "Cyrillic",            PT_SC,   ucp_Cyrillic },
-  { "Deseret",             PT_SC,   ucp_Deseret },
-  { "Devanagari",          PT_SC,   ucp_Devanagari },
-  { "Ethiopic",            PT_SC,   ucp_Ethiopic },
-  { "Georgian",            PT_SC,   ucp_Georgian },
-  { "Glagolitic",          PT_SC,   ucp_Glagolitic },
-  { "Gothic",              PT_SC,   ucp_Gothic },
-  { "Greek",               PT_SC,   ucp_Greek },
-  { "Gujarati",            PT_SC,   ucp_Gujarati },
-  { "Gurmukhi",            PT_SC,   ucp_Gurmukhi },
-  { "Han",                 PT_SC,   ucp_Han },
-  { "Hangul",              PT_SC,   ucp_Hangul },
-  { "Hanunoo",             PT_SC,   ucp_Hanunoo },
-  { "Hebrew",              PT_SC,   ucp_Hebrew },
-  { "Hiragana",            PT_SC,   ucp_Hiragana },
-  { "Inherited",           PT_SC,   ucp_Inherited },
-  { "Kannada",             PT_SC,   ucp_Kannada },
-  { "Katakana",            PT_SC,   ucp_Katakana },
-  { "Kharoshthi",          PT_SC,   ucp_Kharoshthi },
-  { "Khmer",               PT_SC,   ucp_Khmer },
-  { "L",                   PT_GC,   ucp_L },
-  { "L&",                  PT_LAMP, 0 },
-  { "Lao",                 PT_SC,   ucp_Lao },
-  { "Latin",               PT_SC,   ucp_Latin },
-  { "Limbu",               PT_SC,   ucp_Limbu },
-  { "Linear_B",            PT_SC,   ucp_Linear_B },
-  { "Ll",                  PT_PC,   ucp_Ll },
-  { "Lm",                  PT_PC,   ucp_Lm },
-  { "Lo",                  PT_PC,   ucp_Lo },
-  { "Lt",                  PT_PC,   ucp_Lt },
-  { "Lu",                  PT_PC,   ucp_Lu },
-  { "M",                   PT_GC,   ucp_M },
-  { "Malayalam",           PT_SC,   ucp_Malayalam },
-  { "Mc",                  PT_PC,   ucp_Mc },
-  { "Me",                  PT_PC,   ucp_Me },
-  { "Mn",                  PT_PC,   ucp_Mn },
-  { "Mongolian",           PT_SC,   ucp_Mongolian },
-  { "Myanmar",             PT_SC,   ucp_Myanmar },
-  { "N",                   PT_GC,   ucp_N },
-  { "Nd",                  PT_PC,   ucp_Nd },
-  { "New_Tai_Lue",         PT_SC,   ucp_New_Tai_Lue },
-  { "Nko",                 PT_SC,   ucp_Nko },
-  { "Nl",                  PT_PC,   ucp_Nl },
-  { "No",                  PT_PC,   ucp_No },
-  { "Ogham",               PT_SC,   ucp_Ogham },
-  { "Old_Italic",          PT_SC,   ucp_Old_Italic },
-  { "Old_Persian",         PT_SC,   ucp_Old_Persian },
-  { "Oriya",               PT_SC,   ucp_Oriya },
-  { "Osmanya",             PT_SC,   ucp_Osmanya },
-  { "P",                   PT_GC,   ucp_P },
-  { "Pc",                  PT_PC,   ucp_Pc },
-  { "Pd",                  PT_PC,   ucp_Pd },
-  { "Pe",                  PT_PC,   ucp_Pe },
-  { "Pf",                  PT_PC,   ucp_Pf },
-  { "Phags_Pa",            PT_SC,   ucp_Phags_Pa },
-  { "Phoenician",          PT_SC,   ucp_Phoenician },
-  { "Pi",                  PT_PC,   ucp_Pi },
-  { "Po",                  PT_PC,   ucp_Po },
-  { "Ps",                  PT_PC,   ucp_Ps },
-  { "Runic",               PT_SC,   ucp_Runic },
-  { "S",                   PT_GC,   ucp_S },
-  { "Sc",                  PT_PC,   ucp_Sc },
-  { "Shavian",             PT_SC,   ucp_Shavian },
-  { "Sinhala",             PT_SC,   ucp_Sinhala },
-  { "Sk",                  PT_PC,   ucp_Sk },
-  { "Sm",                  PT_PC,   ucp_Sm },
-  { "So",                  PT_PC,   ucp_So },
-  { "Syloti_Nagri",        PT_SC,   ucp_Syloti_Nagri },
-  { "Syriac",              PT_SC,   ucp_Syriac },
-  { "Tagalog",             PT_SC,   ucp_Tagalog },
-  { "Tagbanwa",            PT_SC,   ucp_Tagbanwa },
-  { "Tai_Le",              PT_SC,   ucp_Tai_Le },
-  { "Tamil",               PT_SC,   ucp_Tamil },
-  { "Telugu",              PT_SC,   ucp_Telugu },
-  { "Thaana",              PT_SC,   ucp_Thaana },
-  { "Thai",                PT_SC,   ucp_Thai },
-  { "Tibetan",             PT_SC,   ucp_Tibetan },
-  { "Tifinagh",            PT_SC,   ucp_Tifinagh },
-  { "Ugaritic",            PT_SC,   ucp_Ugaritic },
-  { "Yi",                  PT_SC,   ucp_Yi },
-  { "Z",                   PT_GC,   ucp_Z },
-  { "Zl",                  PT_PC,   ucp_Zl },
-  { "Zp",                  PT_PC,   ucp_Zp },
-  { "Zs",                  PT_PC,   ucp_Zs }
+  { 0,   PT_ANY, 0 },
+  { 4,   PT_SC, ucp_Arabic },
+  { 11,  PT_SC, ucp_Armenian },
+  { 20,  PT_SC, ucp_Balinese },
+  { 29,  PT_SC, ucp_Bengali },
+  { 37,  PT_SC, ucp_Bopomofo },
+  { 46,  PT_SC, ucp_Braille },
+  { 54,  PT_SC, ucp_Buginese },
+  { 63,  PT_SC, ucp_Buhid },
+  { 69,  PT_GC, ucp_C },
+  { 71,  PT_SC, ucp_Canadian_Aboriginal },
+  { 91,  PT_PC, ucp_Cc },
+  { 94,  PT_PC, ucp_Cf },
+  { 97,  PT_SC, ucp_Cherokee },
+  { 106, PT_PC, ucp_Cn },
+  { 109, PT_PC, ucp_Co },
+  { 112, PT_SC, ucp_Common },
+  { 119, PT_SC, ucp_Coptic },
+  { 126, PT_PC, ucp_Cs },
+  { 129, PT_SC, ucp_Cuneiform },
+  { 139, PT_SC, ucp_Cypriot },
+  { 147, PT_SC, ucp_Cyrillic },
+  { 156, PT_SC, ucp_Deseret },
+  { 164, PT_SC, ucp_Devanagari },
+  { 175, PT_SC, ucp_Ethiopic },
+  { 184, PT_SC, ucp_Georgian },
+  { 193, PT_SC, ucp_Glagolitic },
+  { 204, PT_SC, ucp_Gothic },
+  { 211, PT_SC, ucp_Greek },
+  { 217, PT_SC, ucp_Gujarati },
+  { 226, PT_SC, ucp_Gurmukhi },
+  { 235, PT_SC, ucp_Han },
+  { 239, PT_SC, ucp_Hangul },
+  { 246, PT_SC, ucp_Hanunoo },
+  { 254, PT_SC, ucp_Hebrew },
+  { 261, PT_SC, ucp_Hiragana },
+  { 270, PT_SC, ucp_Inherited },
+  { 280, PT_SC, ucp_Kannada },
+  { 288, PT_SC, ucp_Katakana },
+  { 297, PT_SC, ucp_Kharoshthi },
+  { 308, PT_SC, ucp_Khmer },
+  { 314, PT_GC, ucp_L },
+  { 316, PT_LAMP, 0 },
+  { 319, PT_SC, ucp_Lao },
+  { 323, PT_SC, ucp_Latin },
+  { 329, PT_SC, ucp_Limbu },
+  { 335, PT_SC, ucp_Linear_B },
+  { 344, PT_PC, ucp_Ll },
+  { 347, PT_PC, ucp_Lm },
+  { 350, PT_PC, ucp_Lo },
+  { 353, PT_PC, ucp_Lt },
+  { 356, PT_PC, ucp_Lu },
+  { 359, PT_GC, ucp_M },
+  { 361, PT_SC, ucp_Malayalam },
+  { 371, PT_PC, ucp_Mc },
+  { 374, PT_PC, ucp_Me },
+  { 377, PT_PC, ucp_Mn },
+  { 380, PT_SC, ucp_Mongolian },
+  { 390, PT_SC, ucp_Myanmar },
+  { 398, PT_GC, ucp_N },
+  { 400, PT_PC, ucp_Nd },
+  { 403, PT_SC, ucp_New_Tai_Lue },
+  { 415, PT_SC, ucp_Nko },
+  { 419, PT_PC, ucp_Nl },
+  { 422, PT_PC, ucp_No },
+  { 425, PT_SC, ucp_Ogham },
+  { 431, PT_SC, ucp_Old_Italic },
+  { 442, PT_SC, ucp_Old_Persian },
+  { 454, PT_SC, ucp_Oriya },
+  { 460, PT_SC, ucp_Osmanya },
+  { 468, PT_GC, ucp_P },
+  { 470, PT_PC, ucp_Pc },
+  { 473, PT_PC, ucp_Pd },
+  { 476, PT_PC, ucp_Pe },
+  { 479, PT_PC, ucp_Pf },
+  { 482, PT_SC, ucp_Phags_Pa },
+  { 491, PT_SC, ucp_Phoenician },
+  { 502, PT_PC, ucp_Pi },
+  { 505, PT_PC, ucp_Po },
+  { 508, PT_PC, ucp_Ps },
+  { 511, PT_SC, ucp_Runic },
+  { 517, PT_GC, ucp_S },
+  { 519, PT_PC, ucp_Sc },
+  { 522, PT_SC, ucp_Shavian },
+  { 530, PT_SC, ucp_Sinhala },
+  { 538, PT_PC, ucp_Sk },
+  { 541, PT_PC, ucp_Sm },
+  { 544, PT_PC, ucp_So },
+  { 547, PT_SC, ucp_Syloti_Nagri },
+  { 560, PT_SC, ucp_Syriac },
+  { 567, PT_SC, ucp_Tagalog },
+  { 575, PT_SC, ucp_Tagbanwa },
+  { 584, PT_SC, ucp_Tai_Le },
+  { 591, PT_SC, ucp_Tamil },
+  { 597, PT_SC, ucp_Telugu },
+  { 604, PT_SC, ucp_Thaana },
+  { 611, PT_SC, ucp_Thai },
+  { 616, PT_SC, ucp_Tibetan },
+  { 624, PT_SC, ucp_Tifinagh },
+  { 633, PT_SC, ucp_Ugaritic },
+  { 642, PT_SC, ucp_Yi },
+  { 645, PT_GC, ucp_Z },
+  { 647, PT_PC, ucp_Zl },
+  { 650, PT_PC, ucp_Zp },
+  { 653, PT_PC, ucp_Zs }
 };
 
 const int _pcre_utt_size = sizeof(_pcre_utt)/sizeof(ucp_type_table);

ext/pcre/pcrelib/pcre_try_flipped.c

@@ -43,7 +43,7 @@ see if it was compiled with the opposite endianness. If so, it uses an
 auxiliary local function to flip the appropriate bytes. */
 
 
-#include <config.h>
+#include "config.h"
 
 #include "pcre_internal.h"
 
@@ -106,6 +106,7 @@ if (byteflip(re->magic_number, sizeof(re->magic_number)) != MAGIC_NUMBER)
 *internal_re = *re;           /* To copy other fields */
 internal_re->size = byteflip(re->size, sizeof(re->size));
 internal_re->options = byteflip(re->options, sizeof(re->options));
+internal_re->flags = (pcre_uint16)byteflip(re->flags, sizeof(re->flags));
 internal_re->top_bracket =
   (pcre_uint16)byteflip(re->top_bracket, sizeof(re->top_bracket));
 internal_re->top_backref =

ext/pcre/pcrelib/pcre_ucp_searchfuncs.c

@@ -41,7 +41,7 @@ POSSIBILITY OF SUCH DAMAGE.
 /* This module contains code for searching the table of Unicode character
 properties. */
 
-#include <config.h>
+#include "config.h"
 
 #include "pcre_internal.h"
 

ext/pcre/pcrelib/pcre_valid_utf8.c

@@ -42,7 +42,7 @@ POSSIBILITY OF SUCH DAMAGE.
 strings. */
 
 
-#include <config.h>
+#include "config.h"
 
 #include "pcre_internal.h"
 

ext/pcre/pcrelib/pcre_version.c

@@ -42,7 +42,7 @@ POSSIBILITY OF SUCH DAMAGE.
 string that identifies the PCRE version that is in use. */
 
 
-#include <config.h>
+#include "config.h"
 
 #include "pcre_internal.h"
 

ext/pcre/pcrelib/pcre_xclass.c

@@ -43,7 +43,7 @@ class (one that contains characters whose values are > 255). It is used by both
 pcre_exec() and pcre_def_exec(). */
 
 
-#include <config.h>
+#include "config.h"
 
 #include "pcre_internal.h"
 

ext/pcre/pcrelib/pcregrep.c

@@ -37,7 +37,7 @@ POSSIBILITY OF SUCH DAMAGE.
 -----------------------------------------------------------------------------
 */
 
-#include <config.h>
+#include "config.h"
 
 #include <ctype.h>
 #include <locale.h>
@@ -53,7 +53,7 @@ POSSIBILITY OF SUCH DAMAGE.
 #include <unistd.h>
 #endif
 
-#include <pcre.h>
+#include "pcre.h"
 
 #define FALSE 0
 #define TRUE 1
@@ -1111,7 +1111,8 @@ while (ptr < endptr)
         fprintf(stdout, "%c[%sm", 0x1b, colour_string);
         fwrite(ptr + offsets[0], 1, offsets[1] - offsets[0], stdout);
         fprintf(stdout, "%c[00m", 0x1b);
-        fwrite(ptr + offsets[1], 1, linelength - offsets[1], stdout);
+        fwrite(ptr + offsets[1], 1, (linelength + endlinelength) - offsets[1],
+          stdout);
         }
       else fwrite(ptr, 1, linelength + endlinelength, stdout);
       }

ext/pcre/pcrelib/pcreposix.c

@@ -42,7 +42,7 @@ POSSIBILITY OF SUCH DAMAGE.
 functions. */
 
 
-#include <config.h>
+#include "config.h"
 
 
 /* Ensure that the PCREPOSIX_EXP_xxx macros are set appropriately for
@@ -55,12 +55,11 @@ previously been set. */
 #  define PCREPOSIX_EXP_DEFN __declspec(dllexport)
 #endif
 
-#include <pcre.h>
+#include "pcre.h"
 #include "pcre_internal.h"
 #include "pcreposix.h"
 
 
-
 /* Table to translate PCRE compile time error codes into POSIX error codes. */
 
 static const int eint[] = {

ext/pcre/pcrelib/testdata/grepoutput

@@ -385,3 +385,5 @@ PUT NEW DATA ABOVE THIS LINE.
 ---------------------------- Test 49 ------------------------------
 ---------------------------- Test 50 ------------------------------
 over the lazy dog.
+---------------------------- Test 51 ------------------------------
+fox jumps

ext/pcre/pcrelib/testdata/testinput2

@@ -1999,7 +1999,7 @@ a random value. /Ix
 
 /a/<any><crlf>
 
-/^a\Rb/
+/^a\Rb/<bsr_unicode>
     a\nb
     a\rb
     a\r\nb
@@ -2009,7 +2009,7 @@ a random value. /Ix
     ** Failers
     a\n\rb
 
-/^a\R*b/
+/^a\R*b/<bsr_unicode>
     ab
     a\nb
     a\rb
@@ -2020,7 +2020,7 @@ a random value. /Ix
     a\n\rb
     a\n\r\x85\x0cb
 
-/^a\R+b/
+/^a\R+b/<bsr_unicode>
     a\nb
     a\rb
     a\r\nb
@@ -2032,7 +2032,7 @@ a random value. /Ix
     ** Failers
     ab
 
-/^a\R{1,3}b/
+/^a\R{1,3}b/<bsr_unicode>
     a\nb
     a\n\rb
     a\n\r\x85b
@@ -2044,7 +2044,7 @@ a random value. /Ix
     a\n\n\n\rb
     a\r
 
-/^a[\R]b/
+/^a[\R]b/<bsr_unicode>
     aRb
     ** Failers
     a\nb
@@ -2464,4 +2464,75 @@ a random value. /Ix
     a\r\nb  
     a\x85b 
 
+/a\Rb/I<bsr_anycrlf>
+    a\rb
+    a\nb
+    a\r\nb
+    ** Failers
+    a\x85b
+    a\x0bb     
+
+/a\Rb/I<bsr_unicode>
+    a\rb
+    a\nb
+    a\r\nb
+    a\x85b
+    a\x0bb     
+    ** Failers 
+    a\x85b\<bsr_anycrlf>
+    a\x0bb\<bsr_anycrlf>
+    
+/a\R?b/I<bsr_anycrlf>
+    a\rb
+    a\nb
+    a\r\nb
+    ** Failers
+    a\x85b
+    a\x0bb     
+
+/a\R?b/I<bsr_unicode>
+    a\rb
+    a\nb
+    a\r\nb
+    a\x85b
+    a\x0bb     
+    ** Failers 
+    a\x85b\<bsr_anycrlf>
+    a\x0bb\<bsr_anycrlf>
+    
+/a\R{2,4}b/I<bsr_anycrlf>
+    a\r\n\nb
+    a\n\r\rb
+    a\r\n\r\n\r\n\r\nb
+    ** Failers
+    a\x85\85b
+    a\x0b\0bb     
+
+/a\R{2,4}b/I<bsr_unicode>
+    a\r\rb
+    a\n\n\nb
+    a\r\n\n\r\rb
+    a\x85\85b
+    a\x0b\0bb     
+    ** Failers 
+    a\r\r\r\r\rb 
+    a\x85\85b\<bsr_anycrlf>
+    a\x0b\0bb\<bsr_anycrlf>
+ 
+/(*BSR_ANYCRLF)a\Rb/I
+    a\nb
+    a\rb 
+
+/(*BSR_UNICODE)a\Rb/I
+    a\x85b
+
+/(*BSR_ANYCRLF)(*CRLF)a\Rb/I
+    a\nb
+    a\rb 
+
+/(*CRLF)(*BSR_UNICODE)a\Rb/I
+    a\x85b
+
+/(*CRLF)(*BSR_ANYCRLF)(*CR)ab/I
+
 / End of testinput2 /

ext/pcre/pcrelib/testdata/testinput5

@@ -312,7 +312,7 @@ can't tell the difference.) --/
 /abc.$/mgx8<any>
     abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x{0085} abc7\x{2028} abc8\x{2029} abc9
 
-/^a\Rb/8
+/^a\Rb/8<bsr_unicode>
     a\nb
     a\rb
     a\r\nb
@@ -324,7 +324,7 @@ can't tell the difference.) --/
     ** Failers
     a\n\rb    
 
-/^a\R*b/8
+/^a\R*b/8<bsr_unicode>
     ab
     a\nb
     a\rb
@@ -335,7 +335,7 @@ can't tell the difference.) --/
     a\n\rb    
     a\n\r\x{85}\x0cb 
 
-/^a\R+b/8
+/^a\R+b/8<bsr_unicode>
     a\nb
     a\rb
     a\r\nb
@@ -347,7 +347,7 @@ can't tell the difference.) --/
     ** Failers
     ab  
 
-/^a\R{1,3}b/8
+/^a\R{1,3}b/8<bsr_unicode>
     a\nb
     a\n\rb
     a\n\r\x{85}b
@@ -417,4 +417,40 @@ can't tell the difference.) --/
     \x{7fffffff} 
     \x{7fffffff}\? 
 
+/a\Rb/I8<bsr_anycrlf>
+    a\rb
+    a\nb
+    a\r\nb
+    ** Failers
+    a\x{85}b
+    a\x0bb     
+
+/a\Rb/I8<bsr_unicode>
+    a\rb
+    a\nb
+    a\r\nb
+    a\x{85}b
+    a\x0bb     
+    ** Failers 
+    a\x{85}b\<bsr_anycrlf>
+    a\x0bb\<bsr_anycrlf>
+    
+/a\R?b/I8<bsr_anycrlf>
+    a\rb
+    a\nb
+    a\r\nb
+    ** Failers
+    a\x{85}b
+    a\x0bb     
+
+/a\R?b/I8<bsr_unicode>
+    a\rb
+    a\nb
+    a\r\nb
+    a\x{85}b
+    a\x0bb     
+    ** Failers 
+    a\x{85}b\<bsr_anycrlf>
+    a\x0bb\<bsr_anycrlf>
+ 
 / End of testinput5 /

ext/pcre/pcrelib/testdata/testinput7

@@ -4156,7 +4156,7 @@
 /abc.$/mgx<any>
     abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x85 abc7\x{2028} abc8\x{2029} abc9
 
-/^a\Rb/
+/^a\Rb/<bsr_unicode>
     a\nb
     a\rb
     a\r\nb
@@ -4166,7 +4166,7 @@
     ** Failers
     a\n\rb    
 
-/^a\R*b/
+/^a\R*b/<bsr_unicode>
     ab
     a\nb
     a\rb
@@ -4177,7 +4177,7 @@
     a\n\rb    
     a\n\r\x85\x0cb 
 
-/^a\R+b/
+/^a\R+b/<bsr_unicode>
     a\nb
     a\rb
     a\r\nb
@@ -4189,7 +4189,7 @@
     ** Failers
     ab  
     
-/^a\R{1,3}b/
+/^a\R{1,3}b/<bsr_unicode>
     a\nb
     a\n\rb
     a\n\r\x85b
@@ -4201,7 +4201,7 @@
     a\n\n\n\rb
     a\r
 
-/^a[\R]b/
+/^a[\R]b/<bsr_unicode>
     aRb
     ** Failers
     a\nb  
@@ -4310,4 +4310,59 @@
 /(\r|\n)A/<crlf>
     \r\nA 
 
+/a\Rb/I<bsr_anycrlf>
+    a\rb
+    a\nb
+    a\r\nb
+    ** Failers
+    a\x85b
+    a\x0bb     
+
+/a\Rb/I<bsr_unicode>
+    a\rb
+    a\nb
+    a\r\nb
+    a\x85b
+    a\x0bb     
+    ** Failers 
+    a\x85b\<bsr_anycrlf>
+    a\x0bb\<bsr_anycrlf>
+    
+/a\R?b/I<bsr_anycrlf>
+    a\rb
+    a\nb
+    a\r\nb
+    ** Failers
+    a\x85b
+    a\x0bb     
+
+/a\R?b/I<bsr_unicode>
+    a\rb
+    a\nb
+    a\r\nb
+    a\x85b
+    a\x0bb     
+    ** Failers 
+    a\x85b\<bsr_anycrlf>
+    a\x0bb\<bsr_anycrlf>
+    
+/a\R{2,4}b/I<bsr_anycrlf>
+    a\r\n\nb
+    a\n\r\rb
+    a\r\n\r\n\r\n\r\nb
+    ** Failers
+    a\x85\85b
+    a\x0b\0bb     
+
+/a\R{2,4}b/I<bsr_unicode>
+    a\r\rb
+    a\n\n\nb
+    a\r\n\n\r\rb
+    a\x85\85b
+    a\x0b\0bb     
+    ** Failers 
+    a\r\r\r\r\rb 
+    a\x85\85b\<bsr_anycrlf>
+    a\x0b\0bb\<bsr_anycrlf>
+
 / End of testinput7 /

ext/pcre/pcrelib/testdata/testinput8

@@ -543,7 +543,7 @@
 /abc.$/mgx8<any>
     abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x{0085} abc7\x{2028} abc8\x{2029} abc9
 
-/^a\Rb/8
+/^a\Rb/8<bsr_unicode>
     a\nb
     a\rb
     a\r\nb
@@ -555,7 +555,7 @@
     ** Failers
     a\n\rb    
 
-/^a\R*b/8
+/^a\R*b/8<bsr_unicode>
     ab
     a\nb
     a\rb
@@ -566,7 +566,7 @@
     a\n\rb    
     a\n\r\x{85}\x0cb 
 
-/^a\R+b/8
+/^a\R+b/8<bsr_unicode>
     a\nb
     a\rb
     a\r\nb
@@ -578,7 +578,7 @@
     ** Failers
     ab  
 
-/^a\R{1,3}b/8
+/^a\R{1,3}b/8<bsr_unicode>
     a\nb
     a\n\rb
     a\n\r\x{85}b
@@ -628,4 +628,40 @@
     ** Failers 
     \x09\x{200a}\x{a0}\x{2028}\x0b
      
+/a\Rb/I8<bsr_anycrlf>
+    a\rb
+    a\nb
+    a\r\nb
+    ** Failers
+    a\x{85}b
+    a\x0bb     
+
+/a\Rb/I8<bsr_unicode>
+    a\rb
+    a\nb
+    a\r\nb
+    a\x{85}b
+    a\x0bb     
+    ** Failers 
+    a\x{85}b\<bsr_anycrlf>
+    a\x0bb\<bsr_anycrlf>
+    
+/a\R?b/I8<bsr_anycrlf>
+    a\rb
+    a\nb
+    a\r\nb
+    ** Failers
+    a\x{85}b
+    a\x0bb     
+
+/a\R?b/I8<bsr_unicode>
+    a\rb
+    a\nb
+    a\r\nb
+    a\x{85}b
+    a\x0bb     
+    ** Failers 
+    a\x{85}b\<bsr_anycrlf>
+    a\x0bb\<bsr_anycrlf>
+ 
 / End of testinput 8 / 

ext/pcre/pcrelib/testdata/testoutput2

@@ -166,7 +166,6 @@ Starting byte set: a b c d
 
 /(a|[^\dZ])/IS
 Capturing subpattern count = 1
-Contains explicit CR or LF match
 No options
 No first char
 No need char
@@ -403,7 +402,6 @@ Failed: missing terminating ] for character class at offset 4
 /[^aeiou ]{3,}/I
 Capturing subpattern count = 0
 Partial matching not supported
-Contains explicit CR or LF match
 No options
 No first char
 No need char
@@ -1440,7 +1438,6 @@ Need char = 'a'
 /"([^\\"]+|\\.)*"/I
 Capturing subpattern count = 1
 Partial matching not supported
-Contains explicit CR or LF match
 No options
 First char = '"'
 Need char = '"'
@@ -1716,7 +1713,6 @@ Study returned NULL
   /Ix
 Capturing subpattern count = 0
 Partial matching not supported
-Contains explicit CR or LF match
 Options: extended
 First char = '('
 Need char = ')'
@@ -1746,7 +1742,6 @@ No match
 /\(  ( (?>[^()]+) | (?R) )* \) /Ixg
 Capturing subpattern count = 1
 Partial matching not supported
-Contains explicit CR or LF match
 Options: extended
 First char = '('
 Need char = ')'
@@ -1762,7 +1757,6 @@ Need char = ')'
 /\(  (?: (?>[^()]+) | (?R) ) \) /Ix
 Capturing subpattern count = 0
 Partial matching not supported
-Contains explicit CR or LF match
 Options: extended
 First char = '('
 Need char = ')'
@@ -1782,7 +1776,6 @@ No match
 /\(  (?: (?>[^()]+) | (?R) )? \) /Ix
 Capturing subpattern count = 0
 Partial matching not supported
-Contains explicit CR or LF match
 Options: extended
 First char = '('
 Need char = ')'
@@ -1794,7 +1787,6 @@ Need char = ')'
 /\(  ( (?>[^()]+) | (?R) )* \) /Ix
 Capturing subpattern count = 1
 Partial matching not supported
-Contains explicit CR or LF match
 Options: extended
 First char = '('
 Need char = ')'
@@ -1805,7 +1797,6 @@ Need char = ')'
 /\( ( ( (?>[^()]+) | (?R) )* ) \) /Ix
 Capturing subpattern count = 2
 Partial matching not supported
-Contains explicit CR or LF match
 Options: extended
 First char = '('
 Need char = ')'
@@ -1817,7 +1808,6 @@ Need char = ')'
 /\( (123)? ( ( (?>[^()]+) | (?R) )* ) \) /Ix
 Capturing subpattern count = 3
 Partial matching not supported
-Contains explicit CR or LF match
 Options: extended
 First char = '('
 Need char = ')'
@@ -1835,7 +1825,6 @@ Need char = ')'
 /\( ( (123)? ( (?>[^()]+) | (?R) )* ) \) /Ix
 Capturing subpattern count = 3
 Partial matching not supported
-Contains explicit CR or LF match
 Options: extended
 First char = '('
 Need char = ')'
@@ -1853,7 +1842,6 @@ Need char = ')'
 /\( (((((((((( ( (?>[^()]+) | (?R) )* )))))))))) \) /Ix
 Capturing subpattern count = 11
 Partial matching not supported
-Contains explicit CR or LF match
 Options: extended
 First char = '('
 Need char = ')'
@@ -1874,7 +1862,6 @@ Need char = ')'
 /\( ( ( (?>[^()<>]+) | ((?>[^()]+)) | (?R) )* ) \) /Ix
 Capturing subpattern count = 3
 Partial matching not supported
-Contains explicit CR or LF match
 Options: extended
 First char = '('
 Need char = ')'
@@ -1887,7 +1874,6 @@ Need char = ')'
 /\( ( ( (?>[^()]+) | ((?R)) )* ) \) /Ix
 Capturing subpattern count = 3
 Partial matching not supported
-Contains explicit CR or LF match
 Options: extended
 First char = '('
 Need char = ')'
@@ -1924,7 +1910,6 @@ No need char
         End
 ------------------------------------------------------------------
 Capturing subpattern count = 0
-Contains explicit CR or LF match
 Options: anchored
 No first char
 No need char
@@ -1951,7 +1936,6 @@ No need char
         End
 ------------------------------------------------------------------
 Capturing subpattern count = 0
-Contains explicit CR or LF match
 Options: anchored
 No first char
 No need char
@@ -1973,7 +1957,6 @@ Starting byte set: A B C D E F G H I J K L M N O P Q R S T U V W X Y Z
         End
 ------------------------------------------------------------------
 Capturing subpattern count = 0
-Contains explicit CR or LF match
 Options: anchored
 No first char
 No need char
@@ -2013,7 +1996,6 @@ No need char
         End
 ------------------------------------------------------------------
 Capturing subpattern count = 0
-Contains explicit CR or LF match
 Options: anchored
 No first char
 No need char
@@ -2035,7 +2017,6 @@ Starting byte set: \x09 \x0a \x0b \x0c \x0d \x20
         End
 ------------------------------------------------------------------
 Capturing subpattern count = 0
-Contains explicit CR or LF match
 Options: anchored
 No first char
 No need char
@@ -2114,7 +2095,6 @@ No need char
         End
 ------------------------------------------------------------------
 Capturing subpattern count = 0
-Contains explicit CR or LF match
 Options: anchored
 No first char
 No need char
@@ -2180,7 +2160,6 @@ No need char
         End
 ------------------------------------------------------------------
 Capturing subpattern count = 0
-Contains explicit CR or LF match
 Options: anchored
 No first char
 No need char
@@ -2194,7 +2173,6 @@ No need char
         End
 ------------------------------------------------------------------
 Capturing subpattern count = 0
-Contains explicit CR or LF match
 Options: anchored
 No first char
 No need char
@@ -3083,7 +3061,6 @@ Need char = 'b'
 /([^()]++|\([^()]*\))+/I
 Capturing subpattern count = 1
 Partial matching not supported
-Contains explicit CR or LF match
 No options
 No first char
 No need char
@@ -3094,7 +3071,6 @@ No need char
 /\(([^()]++|\([^()]+\))+\)/I
 Capturing subpattern count = 1
 Partial matching not supported
-Contains explicit CR or LF match
 No options
 First char = '('
 Need char = ')'
@@ -3295,7 +3271,6 @@ No need char
         End
 ------------------------------------------------------------------
 Capturing subpattern count = 0
-Contains explicit CR or LF match
 No options
 No first char
 No need char
@@ -3308,7 +3283,6 @@ No need char
         End
 ------------------------------------------------------------------
 Capturing subpattern count = 0
-Contains explicit CR or LF match
 No options
 No first char
 No need char
@@ -3316,7 +3290,6 @@ No need char
 /< (?: (?(R) \d++  | [^<>]*+) | (?R)) * >/Ix
 Capturing subpattern count = 0
 Partial matching not supported
-Contains explicit CR or LF match
 Options: extended
 First char = '<'
 Need char = '>'
@@ -3531,7 +3504,6 @@ Starting byte set: a b
 
 /[^a]/I
 Capturing subpattern count = 0
-Contains explicit CR or LF match
 No options
 No first char
 No need char
@@ -3991,7 +3963,6 @@ Failed: recursive call could loop indefinitely at offset 16
 
 /^([^()]|\((?1)*\))*$/I
 Capturing subpattern count = 1
-Contains explicit CR or LF match
 Options: anchored
 No first char
 No need char
@@ -4011,7 +3982,6 @@ No match
 
 /^>abc>([^()]|\((?1)*\))*<xyz<$/I
 Capturing subpattern count = 1
-Contains explicit CR or LF match
 Options: anchored
 No first char
 Need char = '<'
@@ -4139,7 +4109,6 @@ No match
 /((< (?: (?(R) \d++  | [^<>]*+) | (?2)) * >))/Ix
 Capturing subpattern count = 2
 Partial matching not supported
-Contains explicit CR or LF match
 Options: extended
 First char = '<'
 Need char = '>'
@@ -5958,7 +5927,6 @@ Matched, but too many substrings
 /[^()]*(?:\((?R)\)[^()]*)*/I
 Capturing subpattern count = 0
 Partial matching not supported
-Contains explicit CR or LF match
 No options
 No first char
 No need char
@@ -5972,7 +5940,6 @@ No need char
 /[^()]*(?:\((?>(?R))\)[^()]*)*/I
 Capturing subpattern count = 0
 Partial matching not supported
-Contains explicit CR or LF match
 No options
 No first char
 No need char
@@ -5984,7 +5951,6 @@ No need char
 /[^()]*(?:\((?R)\))*[^()]*/I
 Capturing subpattern count = 0
 Partial matching not supported
-Contains explicit CR or LF match
 No options
 No first char
 No need char
@@ -5996,7 +5962,6 @@ No need char
 /(?:\((?R)\))*[^()]*/I
 Capturing subpattern count = 0
 Partial matching not supported
-Contains explicit CR or LF match
 No options
 No first char
 No need char
@@ -6010,7 +5975,6 @@ No need char
 /(?:\((?R)\))|[^()]*/I
 Capturing subpattern count = 0
 Partial matching not supported
-Contains explicit CR or LF match
 No options
 No first char
 No need char
@@ -6205,6 +6169,7 @@ Named capturing subpatterns:
   A   2
   A   3
 Options: anchored dupnames
+Duplicate name status changes
 No first char
 No need char
     a1b\CA
@@ -7913,7 +7878,7 @@ No match
 /a/<any><crlf>
 Failed: inconsistent NEWLINE options at offset 0
 
-/^a\Rb/
+/^a\Rb/<bsr_unicode>
     a\nb
  0: a\x0ab
     a\rb
@@ -7931,7 +7896,7 @@ No match
     a\n\rb
 No match
 
-/^a\R*b/
+/^a\R*b/<bsr_unicode>
     ab
  0: ab
     a\nb
@@ -7951,7 +7916,7 @@ No match
     a\n\r\x85\x0cb
  0: a\x0a\x0d\x85\x0cb
 
-/^a\R+b/
+/^a\R+b/<bsr_unicode>
     a\nb
  0: a\x0ab
     a\rb
@@ -7973,7 +7938,7 @@ No match
     ab
 No match
 
-/^a\R{1,3}b/
+/^a\R{1,3}b/<bsr_unicode>
     a\nb
  0: a\x0ab
     a\n\rb
@@ -7995,7 +7960,7 @@ No match
     a\r
 No match
 
-/^a[\R]b/
+/^a[\R]b/<bsr_unicode>
     aRb
  0: aRb
     ** Failers
@@ -9168,4 +9133,173 @@ No match
     a\x85b 
 No match
 
+/a\Rb/I<bsr_anycrlf>
+Capturing subpattern count = 0
+Options: bsr_anycrlf
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x0db
+    a\nb
+ 0: a\x0ab
+    a\r\nb
+ 0: a\x0d\x0ab
+    ** Failers
+No match
+    a\x85b
+No match
+    a\x0bb     
+No match
+
+/a\Rb/I<bsr_unicode>
+Capturing subpattern count = 0
+Options: bsr_unicode
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x0db
+    a\nb
+ 0: a\x0ab
+    a\r\nb
+ 0: a\x0d\x0ab
+    a\x85b
+ 0: a\x85b
+    a\x0bb     
+ 0: a\x0bb
+    ** Failers 
+No match
+    a\x85b\<bsr_anycrlf>
+No match
+    a\x0bb\<bsr_anycrlf>
+No match
+    
+/a\R?b/I<bsr_anycrlf>
+Capturing subpattern count = 0
+Options: bsr_anycrlf
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x0db
+    a\nb
+ 0: a\x0ab
+    a\r\nb
+ 0: a\x0d\x0ab
+    ** Failers
+No match
+    a\x85b
+No match
+    a\x0bb     
+No match
+
+/a\R?b/I<bsr_unicode>
+Capturing subpattern count = 0
+Options: bsr_unicode
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x0db
+    a\nb
+ 0: a\x0ab
+    a\r\nb
+ 0: a\x0d\x0ab
+    a\x85b
+ 0: a\x85b
+    a\x0bb     
+ 0: a\x0bb
+    ** Failers 
+No match
+    a\x85b\<bsr_anycrlf>
+No match
+    a\x0bb\<bsr_anycrlf>
+No match
+    
+/a\R{2,4}b/I<bsr_anycrlf>
+Capturing subpattern count = 0
+Partial matching not supported
+Options: bsr_anycrlf
+First char = 'a'
+Need char = 'b'
+    a\r\n\nb
+ 0: a\x0d\x0a\x0ab
+    a\n\r\rb
+ 0: a\x0a\x0d\x0db
+    a\r\n\r\n\r\n\r\nb
+ 0: a\x0d\x0a\x0d\x0a\x0d\x0a\x0d\x0ab
+    ** Failers
+No match
+    a\x85\85b
+No match
+    a\x0b\0bb     
+No match
+
+/a\R{2,4}b/I<bsr_unicode>
+Capturing subpattern count = 0
+Partial matching not supported
+Options: bsr_unicode
+First char = 'a'
+Need char = 'b'
+    a\r\rb
+ 0: a\x0d\x0db
+    a\n\n\nb
+ 0: a\x0a\x0a\x0ab
+    a\r\n\n\r\rb
+ 0: a\x0d\x0a\x0a\x0d\x0db
+    a\x85\85b
+No match
+    a\x0b\0bb     
+No match
+    ** Failers 
+No match
+    a\r\r\r\r\rb 
+No match
+    a\x85\85b\<bsr_anycrlf>
+No match
+    a\x0b\0bb\<bsr_anycrlf>
+No match
+ 
+/(*BSR_ANYCRLF)a\Rb/I
+Capturing subpattern count = 0
+Options: bsr_anycrlf
+First char = 'a'
+Need char = 'b'
+    a\nb
+ 0: a\x0ab
+    a\rb 
+ 0: a\x0db
+
+/(*BSR_UNICODE)a\Rb/I
+Capturing subpattern count = 0
+Options: bsr_unicode
+First char = 'a'
+Need char = 'b'
+    a\x85b
+ 0: a\x85b
+
+/(*BSR_ANYCRLF)(*CRLF)a\Rb/I
+Capturing subpattern count = 0
+Options: bsr_anycrlf
+Forced newline sequence: CRLF
+First char = 'a'
+Need char = 'b'
+    a\nb
+ 0: a\x0ab
+    a\rb 
+ 0: a\x0db
+
+/(*CRLF)(*BSR_UNICODE)a\Rb/I
+Capturing subpattern count = 0
+Options: bsr_unicode
+Forced newline sequence: CRLF
+First char = 'a'
+Need char = 'b'
+    a\x85b
+ 0: a\x85b
+
+/(*CRLF)(*BSR_ANYCRLF)(*CR)ab/I
+Capturing subpattern count = 0
+Options: bsr_anycrlf
+Forced newline sequence: CR
+First char = 'a'
+Need char = 'b'
+
 / End of testinput2 /

ext/pcre/pcrelib/testdata/testoutput5

@@ -364,7 +364,6 @@ No match
         End
 ------------------------------------------------------------------
 Capturing subpattern count = 0
-Contains explicit CR or LF match
 Options: anchored utf8
 No first char
 No need char
@@ -387,7 +386,6 @@ No match
         End
 ------------------------------------------------------------------
 Capturing subpattern count = 0
-Contains explicit CR or LF match
 Options: utf8
 No first char
 No need char
@@ -655,7 +653,6 @@ No need char
         End
 ------------------------------------------------------------------
 Capturing subpattern count = 0
-Contains explicit CR or LF match
 No options
 No first char
 No need char
@@ -668,7 +665,6 @@ No need char
         End
 ------------------------------------------------------------------
 Capturing subpattern count = 0
-Contains explicit CR or LF match
 Options: utf8
 No first char
 No need char
@@ -792,7 +788,6 @@ Need char = 191
         End
 ------------------------------------------------------------------
 Capturing subpattern count = 0
-Contains explicit CR or LF match
 No options
 No first char
 No need char
@@ -805,7 +800,6 @@ No need char
         End
 ------------------------------------------------------------------
 Capturing subpattern count = 0
-Contains explicit CR or LF match
 Options: utf8
 No first char
 No need char
@@ -942,7 +936,6 @@ Need char = 'z'
         End
 ------------------------------------------------------------------
 Capturing subpattern count = 1
-Contains explicit CR or LF match
 Options: utf8
 No first char
 Need char = 'z'
@@ -1314,7 +1307,7 @@ Failed: missing terminating ] for character class at offset 15
  0: abc8
  0: abc9
 
-/^a\Rb/8
+/^a\Rb/8<bsr_unicode>
     a\nb
  0: a\x{0a}b
     a\rb
@@ -1336,7 +1329,7 @@ No match
     a\n\rb    
 No match
 
-/^a\R*b/8
+/^a\R*b/8<bsr_unicode>
     ab
  0: ab
     a\nb
@@ -1356,7 +1349,7 @@ No match
     a\n\r\x{85}\x0cb 
  0: a\x{0a}\x{0d}\x{85}\x{0c}b
 
-/^a\R+b/8
+/^a\R+b/8<bsr_unicode>
     a\nb
  0: a\x{0a}b
     a\rb
@@ -1378,7 +1371,7 @@ No match
     ab  
 No match
 
-/^a\R{1,3}b/8
+/^a\R{1,3}b/8<bsr_unicode>
     a\nb
  0: a\x{0a}b
     a\n\rb
@@ -1522,4 +1515,84 @@ Error -10
     \x{7fffffff}\? 
 No match
 
+/a\Rb/I8<bsr_anycrlf>
+Capturing subpattern count = 0
+Options: bsr_anycrlf utf8
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x{0d}b
+    a\nb
+ 0: a\x{0a}b
+    a\r\nb
+ 0: a\x{0d}\x{0a}b
+    ** Failers
+No match
+    a\x{85}b
+No match
+    a\x0bb     
+No match
+
+/a\Rb/I8<bsr_unicode>
+Capturing subpattern count = 0
+Options: bsr_unicode utf8
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x{0d}b
+    a\nb
+ 0: a\x{0a}b
+    a\r\nb
+ 0: a\x{0d}\x{0a}b
+    a\x{85}b
+ 0: a\x{85}b
+    a\x0bb     
+ 0: a\x{0b}b
+    ** Failers 
+No match
+    a\x{85}b\<bsr_anycrlf>
+No match
+    a\x0bb\<bsr_anycrlf>
+No match
+    
+/a\R?b/I8<bsr_anycrlf>
+Capturing subpattern count = 0
+Options: bsr_anycrlf utf8
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x{0d}b
+    a\nb
+ 0: a\x{0a}b
+    a\r\nb
+ 0: a\x{0d}\x{0a}b
+    ** Failers
+No match
+    a\x{85}b
+No match
+    a\x0bb     
+No match
+
+/a\R?b/I8<bsr_unicode>
+Capturing subpattern count = 0
+Options: bsr_unicode utf8
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x{0d}b
+    a\nb
+ 0: a\x{0a}b
+    a\r\nb
+ 0: a\x{0d}\x{0a}b
+    a\x{85}b
+ 0: a\x{85}b
+    a\x0bb     
+ 0: a\x{0b}b
+    ** Failers 
+No match
+    a\x{85}b\<bsr_anycrlf>
+No match
+    a\x0bb\<bsr_anycrlf>
+No match
+ 
 / End of testinput5 /

ext/pcre/pcrelib/testdata/testoutput7

@@ -6824,7 +6824,7 @@ No match
  0: abc6
  0: abc9
 
-/^a\Rb/
+/^a\Rb/<bsr_unicode>
     a\nb
  0: a\x0ab
     a\rb
@@ -6842,7 +6842,7 @@ No match
     a\n\rb    
 No match
 
-/^a\R*b/
+/^a\R*b/<bsr_unicode>
     ab
  0: ab
     a\nb
@@ -6862,7 +6862,7 @@ No match
     a\n\r\x85\x0cb 
  0: a\x0a\x0d\x85\x0cb
 
-/^a\R+b/
+/^a\R+b/<bsr_unicode>
     a\nb
  0: a\x0ab
     a\rb
@@ -6884,7 +6884,7 @@ No match
     ab  
 No match
     
-/^a\R{1,3}b/
+/^a\R{1,3}b/<bsr_unicode>
     a\nb
  0: a\x0ab
     a\n\rb
@@ -6906,7 +6906,7 @@ No match
     a\r
 No match
 
-/^a[\R]b/
+/^a[\R]b/<bsr_unicode>
     aRb
  0: aRb
     ** Failers
@@ -7088,4 +7088,128 @@ No match
     \r\nA 
  0: \x0aA
 
+/a\Rb/I<bsr_anycrlf>
+Capturing subpattern count = 0
+Options: bsr_anycrlf
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x0db
+    a\nb
+ 0: a\x0ab
+    a\r\nb
+ 0: a\x0d\x0ab
+    ** Failers
+No match
+    a\x85b
+No match
+    a\x0bb     
+No match
+
+/a\Rb/I<bsr_unicode>
+Capturing subpattern count = 0
+Options: bsr_unicode
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x0db
+    a\nb
+ 0: a\x0ab
+    a\r\nb
+ 0: a\x0d\x0ab
+    a\x85b
+ 0: a\x85b
+    a\x0bb     
+ 0: a\x0bb
+    ** Failers 
+No match
+    a\x85b\<bsr_anycrlf>
+No match
+    a\x0bb\<bsr_anycrlf>
+No match
+    
+/a\R?b/I<bsr_anycrlf>
+Capturing subpattern count = 0
+Options: bsr_anycrlf
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x0db
+    a\nb
+ 0: a\x0ab
+    a\r\nb
+ 0: a\x0d\x0ab
+    ** Failers
+No match
+    a\x85b
+No match
+    a\x0bb     
+No match
+
+/a\R?b/I<bsr_unicode>
+Capturing subpattern count = 0
+Options: bsr_unicode
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x0db
+    a\nb
+ 0: a\x0ab
+    a\r\nb
+ 0: a\x0d\x0ab
+    a\x85b
+ 0: a\x85b
+    a\x0bb     
+ 0: a\x0bb
+    ** Failers 
+No match
+    a\x85b\<bsr_anycrlf>
+No match
+    a\x0bb\<bsr_anycrlf>
+No match
+    
+/a\R{2,4}b/I<bsr_anycrlf>
+Capturing subpattern count = 0
+Partial matching not supported
+Options: bsr_anycrlf
+First char = 'a'
+Need char = 'b'
+    a\r\n\nb
+ 0: a\x0d\x0a\x0ab
+    a\n\r\rb
+ 0: a\x0a\x0d\x0db
+    a\r\n\r\n\r\n\r\nb
+ 0: a\x0d\x0a\x0d\x0a\x0d\x0a\x0d\x0ab
+    ** Failers
+No match
+    a\x85\85b
+No match
+    a\x0b\0bb     
+No match
+
+/a\R{2,4}b/I<bsr_unicode>
+Capturing subpattern count = 0
+Partial matching not supported
+Options: bsr_unicode
+First char = 'a'
+Need char = 'b'
+    a\r\rb
+ 0: a\x0d\x0db
+    a\n\n\nb
+ 0: a\x0a\x0a\x0ab
+    a\r\n\n\r\rb
+ 0: a\x0d\x0a\x0a\x0d\x0db
+    a\x85\85b
+No match
+    a\x0b\0bb     
+No match
+    ** Failers 
+No match
+    a\r\r\r\r\rb 
+No match
+    a\x85\85b\<bsr_anycrlf>
+No match
+    a\x0b\0bb\<bsr_anycrlf>
+No match
+
 / End of testinput7 /

ext/pcre/pcrelib/testdata/testoutput8

@@ -1052,7 +1052,7 @@ No match
  0: abc8
  0: abc9
 
-/^a\Rb/8
+/^a\Rb/8<bsr_unicode>
     a\nb
  0: a\x{0a}b
     a\rb
@@ -1074,7 +1074,7 @@ No match
     a\n\rb    
 No match
 
-/^a\R*b/8
+/^a\R*b/8<bsr_unicode>
     ab
  0: ab
     a\nb
@@ -1094,7 +1094,7 @@ No match
     a\n\r\x{85}\x0cb 
  0: a\x{0a}\x{0d}\x{85}\x{0c}b
 
-/^a\R+b/8
+/^a\R+b/8<bsr_unicode>
     a\nb
  0: a\x{0a}b
     a\rb
@@ -1116,7 +1116,7 @@ No match
     ab  
 No match
 
-/^a\R{1,3}b/8
+/^a\R{1,3}b/8<bsr_unicode>
     a\nb
  0: a\x{0a}b
     a\n\rb
@@ -1204,4 +1204,84 @@ No match
     \x09\x{200a}\x{a0}\x{2028}\x0b
 No match
      
+/a\Rb/I8<bsr_anycrlf>
+Capturing subpattern count = 0
+Options: bsr_anycrlf utf8
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x{0d}b
+    a\nb
+ 0: a\x{0a}b
+    a\r\nb
+ 0: a\x{0d}\x{0a}b
+    ** Failers
+No match
+    a\x{85}b
+No match
+    a\x0bb     
+No match
+
+/a\Rb/I8<bsr_unicode>
+Capturing subpattern count = 0
+Options: bsr_unicode utf8
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x{0d}b
+    a\nb
+ 0: a\x{0a}b
+    a\r\nb
+ 0: a\x{0d}\x{0a}b
+    a\x{85}b
+ 0: a\x{85}b
+    a\x0bb     
+ 0: a\x{0b}b
+    ** Failers 
+No match
+    a\x{85}b\<bsr_anycrlf>
+No match
+    a\x0bb\<bsr_anycrlf>
+No match
+    
+/a\R?b/I8<bsr_anycrlf>
+Capturing subpattern count = 0
+Options: bsr_anycrlf utf8
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x{0d}b
+    a\nb
+ 0: a\x{0a}b
+    a\r\nb
+ 0: a\x{0d}\x{0a}b
+    ** Failers
+No match
+    a\x{85}b
+No match
+    a\x0bb     
+No match
+
+/a\R?b/I8<bsr_unicode>
+Capturing subpattern count = 0
+Options: bsr_unicode utf8
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x{0d}b
+    a\nb
+ 0: a\x{0a}b
+    a\r\nb
+ 0: a\x{0d}\x{0a}b
+    a\x{85}b
+ 0: a\x{85}b
+    a\x0bb     
+ 0: a\x{0b}b
+    ** Failers 
+No match
+    a\x{85}b\<bsr_anycrlf>
+No match
+    a\x0bb\<bsr_anycrlf>
+No match
+ 
 / End of testinput 8 /