More file tidies for 10.33-RC1

Author: PhilipHazel

CMakeLists.txt

@@ -88,7 +88,7 @@
 
 PROJECT(PCRE2 C)
 
-# Increased minimum to 2.8.0 to support newer add_test features. 
+# Increased minimum to 2.8.0 to support newer add_test features.
 CMAKE_MINIMUM_REQUIRED(VERSION 2.8.0)
 
 # Set policy CMP0026 to avoid warnings for the use of LOCATION in
@@ -324,7 +324,7 @@ ENDIF(PCRE2_SUPPORT_VALGRIND)
 
 IF(PCRE2_DISABLE_PERCENT_ZT)
         SET(DISABLE_PERCENT_ZT 1)
-ENDIF(PCRE2_DISABLE_PERCENT_ZT)         
+ENDIF(PCRE2_DISABLE_PERCENT_ZT)
 
 # This next one used to reference ${READLINE_LIBRARY})
 # but I was advised to add the NCURSES test as well, along with
@@ -459,7 +459,7 @@ SET(PCRE2_SOURCES
   src/pcre2_newline.c
   src/pcre2_ord2utf.c
   src/pcre2_pattern_info.c
-  src/pcre2_script_run.c 
+  src/pcre2_script_run.c
   src/pcre2_serialize.c
   src/pcre2_string_utils.c
   src/pcre2_study.c
@@ -651,10 +651,10 @@ IF(PCRE2_BUILD_TESTS)
 
   # exes in Debug location tested by the RunTest and RunGrepTest shell scripts
   # via "make test"
-  
+
   # The commented out code below provokes a warning about future removal
   # of the facility, and requires policy CMP0026 to be set to "OLD". I have
-  # got fed-up with the warnings, but my plea for help on the mailing list 
+  # got fed-up with the warnings, but my plea for help on the mailing list
   # produced no response. So, I've hacked. The new code below seems to work on
   # Linux.
 
@@ -857,9 +857,9 @@ IF(PCRE2_SHOW_REPORT)
   MESSAGE(STATUS "  Support Valgrind .................: ${PCRE2_SUPPORT_VALGRIND}")
   IF(PCRE2_DISABLE_PERCENT_ZT)
     MESSAGE(STATUS "  Use %zu and %td ..................: OFF" )
-  ELSE(PCRE2_DISABLE_PERCENT_ZT)   
+  ELSE(PCRE2_DISABLE_PERCENT_ZT)
     MESSAGE(STATUS "  Use %zu and %td ..................: AUTO" )
-  ENDIF(PCRE2_DISABLE_PERCENT_ZT)   
+  ENDIF(PCRE2_DISABLE_PERCENT_ZT)
 
   IF(MINGW AND NOT PCRE2_STATIC)
     MESSAGE(STATUS "  Non-standard dll names (prefix) . : ${NON_STANDARD_LIB_PREFIX}")

ChangeLog

@@ -14,11 +14,11 @@ a greater than 1 fixed quantifier. This issue was found by Yunho Kim.
 
 3. Added support for callouts from pcre2_substitute().
 
-4. The POSIX functions are now all called pcre2_regcomp() etc., with wrapper 
+4. The POSIX functions are now all called pcre2_regcomp() etc., with wrapper
 functions that use the standard POSIX names. However, in pcre2posix.h the POSIX
 names are defined as macros. This should help avoid linking with the wrong
 library in some environments while still exporting the POSIX names for
-pre-existing programs that use them. (The Debian alternative names are also 
+pre-existing programs that use them. (The Debian alternative names are also
 defined as macros, but not documented.)
 
 5. Fix an xclass matching issue in JIT.
@@ -33,29 +33,29 @@ new "is lower case letter" bit. At the same time, the now unused "is
 hexadecimal digit" bit was removed. The default tables in
 src/pcre2_chartables.c.dist are updated.
 
-8. Implement the new Perl "script run" features (*script_run:...) and 
+8. Implement the new Perl "script run" features (*script_run:...) and
 (*atomic_script_run:...) aka (*sr:...) and (*asr:...).
 
 9. Fixed two typos in change 22 for 10.21, which added special handling for
-ranges such as a-z in EBCDIC environments. The original code probably never 
-worked, though there were no bug reports. 
+ranges such as a-z in EBCDIC environments. The original code probably never
+worked, though there were no bug reports.
 
 10. Implement PCRE2_COPY_MATCHED_SUBJECT for pcre2_match() (including JIT via
 pcre2_match()) and pcre2_dfa_match(), but *not* the pcre2_jit_match() fast
-path. Also, when a match fails, set the subject field in the match data to NULL 
-for tidiness - none of the substring extractors should reference this after 
+path. Also, when a match fails, set the subject field in the match data to NULL
+for tidiness - none of the substring extractors should reference this after
 match failure.
 
-11. If a pattern started with a subroutine call that had a quantifier with a 
-minimum of zero, an incorrect "match must start with this character" could be 
-recorded. Example: /(?&xxx)*ABC(?<xxx>XYZ)/ would (incorrectly) expect 'A' to 
-be the first character of a match. 
+11. If a pattern started with a subroutine call that had a quantifier with a
+minimum of zero, an incorrect "match must start with this character" could be
+recorded. Example: /(?&xxx)*ABC(?<xxx>XYZ)/ would (incorrectly) expect 'A' to
+be the first character of a match.
 
-12. The heap limit checking code in pcre2_dfa_match() could suffer from 
-overflow if the heap limit was set very large. This could cause incorrect "heap 
-limit exceeded" errors. 
+12. The heap limit checking code in pcre2_dfa_match() could suffer from
+overflow if the heap limit was set very large. This could cause incorrect "heap
+limit exceeded" errors.
 
-13. Add "kibibytes" to the heap limit output from pcre2test -C to make the 
+13. Add "kibibytes" to the heap limit output from pcre2test -C to make the
 units clear.
 
 14. Add a call to pcre2_jit_free_unused_memory() in pcre2grep, for tidiness.
@@ -71,77 +71,77 @@ inttypes.h. This supports environments that do not have stdint.h but do have
 inttypes.h, which are known to exist. A note in the autotools documentation
 says (November 2018) that there are none known that are the other way round.
 
-17. Added --disable-percent-zt to "configure" (and equivalent to CMake) to 
-forcibly disable the use of %zu and %td in formatting strings because there is 
-at least one version of VMS that claims to be C99 but does not support these 
+17. Added --disable-percent-zt to "configure" (and equivalent to CMake) to
+forcibly disable the use of %zu and %td in formatting strings because there is
+at least one version of VMS that claims to be C99 but does not support these
 modifiers.
 
-18. Added --disable-pcre2grep-callout-fork, which restricts the callout support 
-in pcre2grep to the inbuilt echo facility. This may be useful in environments 
+18. Added --disable-pcre2grep-callout-fork, which restricts the callout support
+in pcre2grep to the inbuilt echo facility. This may be useful in environments
 that do not support fork().
 
-19. Fix two instances of <= 0 being applied to unsigned integers (the VMS 
+19. Fix two instances of <= 0 being applied to unsigned integers (the VMS
 compiler complains).
 
-20. Added "fork" support for VMS to pcre2grep, for running an external program 
+20. Added "fork" support for VMS to pcre2grep, for running an external program
 via a string callout.
 
 21. Improve MAP_JIT flag usage on MacOS. Patch by Rich Siegel.
 
-22. If a pattern started with (*MARK), (*COMMIT), (*PRUNE), (*SKIP), or (*THEN) 
+22. If a pattern started with (*MARK), (*COMMIT), (*PRUNE), (*SKIP), or (*THEN)
 followed by ^ it was not recognized as anchored.
 
-23. The RunGrepTest script used to cut out the test of NUL characters for 
-Solaris and MacOS as printf and sed can't handle them. It seems that the *BSD 
-systems can't either. I've inverted the test so that only those OS that are 
+23. The RunGrepTest script used to cut out the test of NUL characters for
+Solaris and MacOS as printf and sed can't handle them. It seems that the *BSD
+systems can't either. I've inverted the test so that only those OS that are
 known to work (currently only Linux) try to run this test.
 
-24. Some tests in RunGrepTest appended to testtrygrep from two different file 
-descriptors instead of redirecting stderr to stdout. This worked on Linux, but 
+24. Some tests in RunGrepTest appended to testtrygrep from two different file
+descriptors instead of redirecting stderr to stdout. This worked on Linux, but
 it was reported not to on other systems, causing the tests to fail.
 
 25. In the RunTest script, make the test for stack setting use the same value
 for the stack as it needs for -bigstack.
 
 26. Insert a cast in pcre2_dfa_match.c to suppress a compiler warning.
 
-26. With PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL set, escape sequences such as \s 
-which are valid in character classes, but not as the end of ranges, were being 
-treated as literals. An example is [_-\s] (but not [\s-_] because that gave an 
-error at the *start* of a range). Now an "invalid range" error is given 
+26. With PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL set, escape sequences such as \s
+which are valid in character classes, but not as the end of ranges, were being
+treated as literals. An example is [_-\s] (but not [\s-_] because that gave an
+error at the *start* of a range). Now an "invalid range" error is given
 independently of PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL.
 
-27. Related to 26 above, PCRE2_BAD_ESCAPE_IS_LITERAL was affecting known escape 
+27. Related to 26 above, PCRE2_BAD_ESCAPE_IS_LITERAL was affecting known escape
 sequences such as \eX when they appeared invalidly in a character class. Now
 the option applies only to unrecognized or malformed escape sequences.
 
 28. Fix word boundary in JIT compiler. Patch by Mike Munday.
 
 29. The pcre2_dfa_match() function was incorrectly handling conditional version
-tests such as (?(VERSION>=0)...) when the version test was true. Incorrect 
+tests such as (?(VERSION>=0)...) when the version test was true. Incorrect
 processing or a crash could result.
 
-30. When PCRE2_UTF is set, allow non-ASCII letters and decimal digits in group 
+30. When PCRE2_UTF is set, allow non-ASCII letters and decimal digits in group
 names, as Perl does. There was a small bug in this new code, found by
 ClusterFuzz 12950, fixed before release.
 
-31. Implemented PCRE2_EXTRA_ALT_BSUX to support ECMAScript 6's \u{hhh} 
+31. Implemented PCRE2_EXTRA_ALT_BSUX to support ECMAScript 6's \u{hhh}
 construct.
 
 32. Compile \p{Any} to be the same as . in DOTALL mode, so that it benefits
 from auto-anchoring if \p{Any}* starts a pattern.
 
 33. Compile invalid UTF check in JIT test when only pcre32 is enabled.
 
-34. For some time now, CMake has been warning about the setting of policy 
-CMP0026 to "OLD" in CmakeLists.txt, and hinting that the feature might be 
-removed in a future version. A request for CMake expertise on the list produced 
-no result, so I have now hacked CMakeLists.txt along the lines of some changes 
-I found on the Internet. The new code no longer needs the policy setting, and 
-it appears to work fine on Linux. 
+34. For some time now, CMake has been warning about the setting of policy
+CMP0026 to "OLD" in CmakeLists.txt, and hinting that the feature might be
+removed in a future version. A request for CMake expertise on the list produced
+no result, so I have now hacked CMakeLists.txt along the lines of some changes
+I found on the Internet. The new code no longer needs the policy setting, and
+it appears to work fine on Linux.
 
 35. Setting --enable-jit=auto for an out-of-tree build failed because the
-source directory wasn't in the search path for AC_TRY_COMPILE always. Patch 
+source directory wasn't in the search path for AC_TRY_COMPILE always. Patch
 from Ross Burton.
 
 

NEWS

@@ -5,7 +5,7 @@ News about PCRE2 releases
 Version 10.33-RC1 03-March-2019
 -------------------------------
 
-Yet more bugfixes, tidies, and a few enhancements, summarized here (see 
+Yet more bugfixes, tidies, and a few enhancements, summarized here (see
 ChangeLog for the full list):
 
 1. Callouts from pcre2_substitute() are now available.

NON-AUTOTOOLS-BUILD

@@ -47,7 +47,7 @@ can skip ahead to the CMake section.
      environment. In particular, you can alter the definition of the NEWLINE
      macro to specify what character(s) you want to be interpreted as line
      terminators by default.
-     
+
      When you subsequently compile any of the PCRE2 modules, you must specify
      -DHAVE_CONFIG_H to your compiler so that src/config.h is included in the
      sources.
@@ -61,7 +61,7 @@ can skip ahead to the CMake section.
      configure/make world, this is handled automatically.) When upgrading to a
      new release, you are strongly advised to review src/config.h.generic
      before re-using what you had previously.
-     
+
      Note also that the src/config.h.generic file is created from a config.h
      that was generated by Autotools, which automatically includes settings of
      a number of macros that are not actually used by PCRE2 (for example,
@@ -109,7 +109,7 @@ can skip ahead to the CMake section.
        pcre2_newline.c
        pcre2_ord2utf.c
        pcre2_pattern_info.c
-       pcre2_script_run.c 
+       pcre2_script_run.c
        pcre2_serialize.c
        pcre2_string_utils.c
        pcre2_study.c

README

@@ -53,7 +53,7 @@ The header file for the POSIX-style functions is called pcre2posix.h. The
 official POSIX name is regex.h, but I did not want to risk possible problems
 with existing files of that name by distributing it that way. To use PCRE2 with
 an existing program that uses the POSIX API, pcre2posix.h will have to be
-renamed or pointed at by a link (or the program modified, of course). See the 
+renamed or pointed at by a link (or the program modified, of course). See the
 pcre2posix documentation for more details.
 
 
@@ -311,10 +311,10 @@ library. They are also documented in the pcre2build man page.
 . There is support for calling external programs during matching in the
   pcre2grep command, using PCRE2's callout facility with string arguments. This
   support can be disabled by adding --disable-pcre2grep-callout to the
-  "configure" command. There are two kinds of callout: one that generates 
-  output from inbuilt code, and another that calls an external program. The 
-  latter has special support for Windows and VMS; otherwise it assumes the 
-  existence of the fork() function. This facility can be disabled by adding 
+  "configure" command. There are two kinds of callout: one that generates
+  output from inbuilt code, and another that calls an external program. The
+  latter has special support for Windows and VMS; otherwise it assumes the
+  existence of the fork() function. This facility can be disabled by adding
   --disable-pcre2grep-callout-fork to the "configure" command.
 
 . The pcre2grep program currently supports only 8-bit data files, and so
@@ -344,7 +344,7 @@ library. They are also documented in the pcre2build man page.
 
   The default is either 1048576 or the value of --with-pcre2grep-bufsize,
   whichever is the larger.
-  
+
 . It is possible to compile pcre2test so that it links with the libreadline
   or libedit libraries, by specifying, respectively,
 
@@ -367,14 +367,14 @@ library. They are also documented in the pcre2build man page.
   If you get error messages about missing functions tgetstr, tgetent, tputs,
   tgetflag, or tgoto, this is the problem, and linking with the ncurses library
   should fix it.
-  
-. The C99 standard defines formatting modifiers z and t for size_t and 
-  ptrdiff_t values, respectively. By default, PCRE2 uses these modifiers in 
-  environments other than Microsoft Visual Studio when __STDC_VERSION__ is 
+
+. The C99 standard defines formatting modifiers z and t for size_t and
+  ptrdiff_t values, respectively. By default, PCRE2 uses these modifiers in
+  environments other than Microsoft Visual Studio when __STDC_VERSION__ is
   defined and has a value greater than or equal to 199901L (indicating C99).
   However, there is at least one environment that claims to be C99 but does not
   support these modifiers. If --disable-percent-zt is specified, no use is made
-  of the z or t modifiers. Instead or %td or %zu, %lu is used, with a cast for 
+  of the z or t modifiers. Instead or %td or %zu, %lu is used, with a cast for
   size_t values.
 
 . There is a special option called --enable-fuzz-support for use by people who
@@ -790,7 +790,7 @@ The distribution should contain the files listed below.
   src/pcre2_newline.c      )
   src/pcre2_ord2utf.c      )
   src/pcre2_pattern_info.c )
-  src/pcre2_script_run.c   ) 
+  src/pcre2_script_run.c   )
   src/pcre2_serialize.c    )
   src/pcre2_string_utils.c )
   src/pcre2_study.c        )

RunGrepTest

@@ -753,7 +753,7 @@ if $valgrind $vjs $pcre2grep --help | $valgrind $vjs $pcre2grep -q 'callout scri
   else
     $cf $srcdir/testdata/grepoutputC testtrygrep
   fi
- 
+
   if [ $? != 0 ] ; then exit 1; fi
 else
   echo "Script callouts are not supported"

configure.ac

@@ -147,14 +147,14 @@ AC_ARG_ENABLE(jit,
 if test "$enable_jit" = "auto"; then
   AC_LANG(C)
   SAVE_CPPFLAGS=$CPPFLAGS
-  CPPFLAGS=-I$srcdir  
+  CPPFLAGS=-I$srcdir
   AC_COMPILE_IFELSE([AC_LANG_SOURCE([[
   #define SLJIT_CONFIG_AUTO 1
   #include "src/sljit/sljitConfigInternal.h"
   #if (defined SLJIT_CONFIG_UNSUPPORTED && SLJIT_CONFIG_UNSUPPORTED)
   #error unsupported
   #endif]])], enable_jit=yes, enable_jit=no)
-  CPPFLAGS=$SAVE_CPPFLAGS 
+  CPPFLAGS=$SAVE_CPPFLAGS
   echo checking for JIT support on this hardware... $enable_jit
 fi
 
@@ -607,7 +607,7 @@ if test "$enable_percent_zt" = "no"; then
     Define to any value to disable the use of the z and t modifiers in
     formatting settings such as %zu or %td (this is rarely needed).])
 else
-  enable_percent_zt=auto     
+  enable_percent_zt=auto
 fi
 
 # Unless running under Windows, JIT support requires pthreads.
@@ -647,13 +647,13 @@ if test "$enable_pcre2grep_callout" = "yes"; then
     fi
     AC_DEFINE([SUPPORT_PCRE2GREP_CALLOUT_FORK], [], [
       Define to any value to enable fork support in pcre2grep callout scripts.
-      This will have no effect unless SUPPORT_PCRE2GREP_CALLOUT is also 
-      defined.])  
+      This will have no effect unless SUPPORT_PCRE2GREP_CALLOUT is also
+      defined.])
   fi
   AC_DEFINE([SUPPORT_PCRE2GREP_CALLOUT], [], [
     Define to any value to enable callout script support in pcre2grep.])
 else
-  enable_pcre2grep_callout_fork="no"     
+  enable_pcre2grep_callout_fork="no"
 fi
 
 if test "$enable_unicode" = "yes"; then
@@ -1055,7 +1055,7 @@ $PACKAGE-$VERSION configuration summary:
     Build static libs .................. : ${enable_static}
     Use JIT in pcre2grep ............... : ${enable_pcre2grep_jit}
     Enable callouts in pcre2grep ....... : ${enable_pcre2grep_callout}
-    Enable fork in pcre2grep callouts .. : ${enable_pcre2grep_callout_fork} 
+    Enable fork in pcre2grep callouts .. : ${enable_pcre2grep_callout_fork}
     Initial buffer size for pcre2grep .. : ${with_pcre2grep_bufsize}
     Maximum buffer size for pcre2grep .. : ${with_pcre2grep_max_bufsize}
     Link pcre2grep with libz ........... : ${enable_pcre2grep_libz}