released 4.5.0

- add 7zip archive search with option -z, fix #185
- apply Unicode normalization to combining characters in regex patterns, fix #298
- improved TUI TAB directory navigation when searching from the FS root
- updated ugrep.exe option -P to use PCRE2 10.42

Author: genivia-inc

Makefile.am

@@ -1,4 +1,4 @@
-SUBDIRS = lib src
+SUBDIRS = lib lzma/C src
 
 man1_MANS = man/ugrep.1
 

Makefile.in

@@ -382,7 +382,7 @@ target_alias = @target_alias@
 top_build_prefix = @top_build_prefix@
 top_builddir = @top_builddir@
 top_srcdir = @top_srcdir@
-SUBDIRS = lib src
+SUBDIRS = lib lzma/C src
 man1_MANS = man/ugrep.1
 EXTRA_DIST = README.md LICENSE.txt CONTRIBUTING.md CODE_OF_CONDUCT.md
 UGREP = $(shell pwd)/$(top_builddir)/bin/ugrep$(EXEEXT)

README.md

@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.71 for ugrep 4.4.
+# Generated by GNU Autoconf 2.71 for ugrep 4.5.
 #
 #
 # Copyright (C) 1992-1996, 1998-2017, 2020-2021 Free Software Foundation,
@@ -610,8 +610,8 @@ MAKEFLAGS=
 # Identity of this package.
 PACKAGE_NAME='ugrep'
 PACKAGE_TARNAME='ugrep'
-PACKAGE_VERSION='4.4'
-PACKAGE_STRING='ugrep 4.4'
+PACKAGE_VERSION='4.5'
+PACKAGE_STRING='ugrep 4.5'
 PACKAGE_BUGREPORT=''
 PACKAGE_URL=''
 
@@ -796,6 +796,7 @@ with_lzma
 with_lz4
 with_zstd
 with_brotli
+enable_7zip
 with_bzip3
 with_bash_completion_dir
 with_fish_completion_dir
@@ -1379,7 +1380,7 @@ if test "$ac_init_help" = "long"; then
   # Omit some internal or obsolete options to make the list less imposing.
   # This message is too long to be a string in the A/UX 3.1 sh.
   cat <<_ACEOF
-\`configure' configures ugrep 4.4 to adapt to many kinds of systems.
+\`configure' configures ugrep 4.5 to adapt to many kinds of systems.
 
 Usage: $0 [OPTION]... [VAR=VALUE]...
 
@@ -1450,7 +1451,7 @@ fi
 
 if test -n "$ac_init_help"; then
   case $ac_init_help in
-     short | recursive ) echo "Configuration of ugrep 4.4:";;
+     short | recursive ) echo "Configuration of ugrep 4.5:";;
    esac
   cat <<\_ACEOF
 
@@ -1464,6 +1465,8 @@ Optional Features:
                           do not reject slow dependency extractors
   --disable-dependency-tracking
                           speeds up one-time build
+  --disable-7zip          to disable 7zip and no longer search .7z files (7z
+                          requires more memory and takes long to decompress)
   --disable-auto-color    disable automatic colors, otherwise colors are
                           enabled by default
   --enable-color          deprecated, use --disable-auto-color
@@ -1623,7 +1626,7 @@ fi
 test -n "$ac_init_help" && exit $ac_status
 if $ac_init_version; then
   cat <<\_ACEOF
-ugrep configure 4.4
+ugrep configure 4.5
 generated by GNU Autoconf 2.71
 
 Copyright (C) 2021 Free Software Foundation, Inc.
@@ -2160,7 +2163,7 @@ cat >config.log <<_ACEOF
 This file contains any messages produced by compilers while
 running configure, to aid debugging if configure makes a mistake.
 
-It was created by ugrep $as_me 4.4, which was
+It was created by ugrep $as_me 4.5, which was
 generated by GNU Autoconf 2.71.  Invocation command line was
 
   $ $0$ac_configure_args_raw
@@ -3647,7 +3650,7 @@ fi
 
 # Define the identity of the package.
  PACKAGE='ugrep'
- VERSION='4.4'
+ VERSION='4.5'
 
 
 printf "%s\n" "#define PACKAGE \"$PACKAGE\"" >>confdefs.h
@@ -8094,6 +8097,8 @@ printf "%s\n" "#define HAVE_LIBZ 1" >>confdefs.h
 fi
 
 
+if test -n "${zlib_places}"; then
+
 #
 # Handle user hints
 #
@@ -8759,6 +8764,28 @@ printf "%s\n" "#define HAVE_LIBBROTLI 1" >>confdefs.h
 fi
 
 
+# Check whether --enable-7zip was given.
+if test ${enable_7zip+y}
+then :
+  enableval=$enable_7zip; with_no_7zip="yes"
+else $as_nop
+  with_no_7zip="no"
+fi
+
+{ printf "%s\n" "$as_me:${as_lineno-$LINENO}: checking for --disable-7zip" >&5
+printf %s "checking for --disable-7zip... " >&6; }
+if test "x$with_no_7zip" = "xno"; then
+  { printf "%s\n" "$as_me:${as_lineno-$LINENO}: result: no" >&5
+printf "%s\n" "no" >&6; }
+  CPPFLAGS="$CPPFLAGS -I../lzma/C"
+  LDFLAGS="$LDFLAGS -L../lzma/C"
+  LIBS="-lviiz $LIBS"
+else
+  EXTRA_CFLAGS="-DWITH_NO_7ZIP ${EXTRA_CFLAGS}"
+  { printf "%s\n" "$as_me:${as_lineno-$LINENO}: result: yes" >&5
+printf "%s\n" "yes" >&6; }
+fi
+
 
 # Check whether --with-bzip3 was given.
 if test ${with_bzip3+y}
@@ -8906,6 +8933,8 @@ fi
 
 fi
 
+fi
+
 
 # Check whether --with-bash-completion-dir was given.
 if test ${with_bash_completion_dir+y}
@@ -9642,7 +9671,7 @@ PTHREAD_CFLAGS=""
 PTHREAD_LIBS="-lpthread"
 
 
-ac_config_files="$ac_config_files Makefile lib/Makefile src/Makefile"
+ac_config_files="$ac_config_files Makefile lib/Makefile src/Makefile lzma/C/Makefile"
 
 
 cat >confcache <<\_ACEOF
@@ -10188,7 +10217,7 @@ cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1
 # report actual input values of CONFIG_FILES etc. instead of their
 # values after options handling.
 ac_log="
-This file was extended by ugrep $as_me 4.4, which was
+This file was extended by ugrep $as_me 4.5, which was
 generated by GNU Autoconf 2.71.  Invocation command line was
 
   CONFIG_FILES    = $CONFIG_FILES
@@ -10256,7 +10285,7 @@ ac_cs_config_escaped=`printf "%s\n" "$ac_cs_config" | sed "s/^ //; s/'/'\\\\\\\\
 cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
 ac_cs_config='$ac_cs_config_escaped'
 ac_cs_version="\\
-ugrep config.status 4.4
+ugrep config.status 4.5
 configured by $0, generated by GNU Autoconf 2.71,
   with options \\"\$ac_cs_config\\"
 
@@ -10390,6 +10419,7 @@ do
     "Makefile") CONFIG_FILES="$CONFIG_FILES Makefile" ;;
     "lib/Makefile") CONFIG_FILES="$CONFIG_FILES lib/Makefile" ;;
     "src/Makefile") CONFIG_FILES="$CONFIG_FILES src/Makefile" ;;
+    "lzma/C/Makefile") CONFIG_FILES="$CONFIG_FILES lzma/C/Makefile" ;;
 
   *) as_fn_error $? "invalid argument: \`$ac_config_target'" "$LINENO" 5;;
   esac

bin/win32/ug.exe

@@ -1,4 +1,4 @@
-AC_INIT([ugrep],[4.4])
+AC_INIT([ugrep],[4.5])
 AM_INIT_AUTOMAKE([foreign])
 AC_CONFIG_HEADERS([config.h])
 AC_COPYRIGHT([Copyright (C) 2019-2023 Robert van Engelen, Genivia Inc.])
@@ -70,6 +70,8 @@ fi
 
 AX_CHECK_ZLIB([], [echo "recommended zlib not found: ugrep option -z is disabled"])
 
+if test -n "${zlib_places}"; then
+
 AX_CHECK_BZ2LIB([], [echo "recommended libbz2 not found: ugrep option -z cannot search .bz and .bz2 files"])
 
 AX_CHECK_LZMALIB([], [echo "recommended liblzma not found: ugrep option -z cannot search .lzma and .xz files"])
@@ -80,6 +82,22 @@ AX_CHECK_ZSTDLIB([], [echo "optional libzstd not found: install if you want ugre
 
 AX_CHECK_BROTLILIB([], [echo "optional brotli library not found: install if you want ugrep option -z to search .br files"])
 
+AC_ARG_ENABLE(7zip,
+  [AS_HELP_STRING([--disable-7zip],
+                  [to disable 7zip and no longer search .7z files (7z requires more memory and takes long to decompress)])],
+  [with_no_7zip="yes"],
+  [with_no_7zip="no"])
+AC_MSG_CHECKING(for --disable-7zip)
+if test "x$with_no_7zip" = "xno"; then
+  AC_MSG_RESULT(no)
+  CPPFLAGS="$CPPFLAGS -I../lzma/C"
+  LDFLAGS="$LDFLAGS -L../lzma/C"
+  LIBS="-lviiz $LIBS"
+else
+  EXTRA_CFLAGS="-DWITH_NO_7ZIP ${EXTRA_CFLAGS}"
+  AC_MSG_RESULT(yes)
+fi
+
 AC_ARG_WITH(bzip3,
   [AS_HELP_STRING([--with-bzip3],
                   [to enable bzip3 library to decompress .bz3 files])],
@@ -92,6 +110,8 @@ if test "x$with_bzip3_library" != "x"; then
   AX_CHECK_BZIP3LIB([], [echo "optional libbzip3 not found: install if you want ugrep option -z to search .bz3 files"])
 fi
 
+fi
+
 AC_ARG_WITH([bash-completion-dir],
   [AS_HELP_STRING([--with-bash-completion-dir[=PATH]],
                   [install the bash auto-completion script in this directory. @<:@default=yes@:>@])],
@@ -353,6 +373,6 @@ AC_SUBST(SIMD_AVX512BW_FLAGS)
 AC_SUBST([PTHREAD_CFLAGS], [""])
 AC_SUBST([PTHREAD_LIBS], ["-lpthread"])
 
-AC_CONFIG_FILES([Makefile lib/Makefile src/Makefile])
+AC_CONFIG_FILES([Makefile lib/Makefile src/Makefile lzma/C/Makefile])
 
 AC_OUTPUT

bin/win32/ugrep.exe

@@ -56,8 +56,8 @@ class Tables {
 
 const int * range(const char *);
 
-}
+} // namespace Posix
 
-}
+} // namesapce reflex
 
 #endif

bin/win64/ug.exe

@@ -265,7 +265,7 @@ struct lazy_intersection {
     {
       return !operator==(rhs);
     }
-    void find(void)
+    void find()
     {
       while (i1 != i1_end && i2 != i2_end)
       {
@@ -277,7 +277,7 @@ struct lazy_intersection {
           break;
       }
     }
-    void next(void)
+    void next()
     {
       if (i1 != i1_end)
         i1++;
@@ -295,11 +295,11 @@ struct lazy_intersection {
       s1(s1),
       s2(s2)
   { }
-  const_iterator begin(void) const
+  const_iterator begin() const
   {
     return const_iterator(s1, s2);
   }
-  const_iterator end(void) const
+  const_iterator end() const
   {
     return const_iterator(s1.end(), s2.end());
   }
@@ -358,7 +358,7 @@ struct lazy_union {
     {
       return !operator==(rhs);
     }
-    void find(void)
+    void find()
     {
       if (i1 == i1_end)
       {
@@ -370,7 +370,7 @@ struct lazy_union {
           ++i2;
       }
     }
-    void next(void)
+    void next()
     {
       if (i1 == i1_end)
       {
@@ -428,11 +428,11 @@ struct lazy_union {
       s1(s1),
       s2(s2)
   { }
-  const_iterator begin(void) const
+  const_iterator begin() const
   {
     return const_iterator(s1, s2);
   }
-  const_iterator end(void) const
+  const_iterator end() const
   {
     return const_iterator(s1.end(), s2.end());
   }

bin/win64/ugrep.exe

@@ -46,16 +46,20 @@ namespace Unicode {
 class Tables : public Posix::Tables {
  public:
   Tables();
+  typedef std::map<int,const int*> Compose;
+  Compose compose;
  private:
-  void block_scripts(void);
-  void language_scripts(void);
-  void letter_scripts(void);
+  void block_scripts();
+  void language_scripts();
+  void letter_scripts();
+  void composer();
 };
 
 const int * range(const char *);
+int compose(int, int);
 
 } // namespace Unicode
 
-} // namespace reflex;
+} // namespace reflex
 
 #endif

configure

@@ -1,6 +1,6 @@
 noinst_LIBRARIES      = libreflex.a
 libreflex_a_CPPFLAGS  = -I$(top_srcdir)/include $(SIMD_FLAGS) -DWITH_NO_INDENT -DWITH_NO_CODEGEN
-libreflex_a_SOURCES   = $(top_srcdir)/include/reflex/abslexer.h $(top_srcdir)/include/reflex/absmatcher.h $(top_srcdir)/include/reflex/bits.h $(top_srcdir)/include/reflex/boostmatcher.h $(top_srcdir)/include/reflex/convert.h $(top_srcdir)/include/reflex/debug.h $(top_srcdir)/include/reflex/error.h $(top_srcdir)/include/reflex/flexlexer.h $(top_srcdir)/include/reflex/input.h $(top_srcdir)/include/reflex/matcher.h $(top_srcdir)/include/reflex/pattern.h $(top_srcdir)/include/reflex/posix.h $(top_srcdir)/include/reflex/ranges.h $(top_srcdir)/include/reflex/setop.h $(top_srcdir)/include/reflex/simd.h $(top_srcdir)/include/reflex/stdmatcher.h $(top_srcdir)/include/reflex/timer.h $(top_srcdir)/include/reflex/traits.h $(top_srcdir)/include/reflex/unicode.h $(top_srcdir)/include/reflex/utf8.h convert.cpp debug.cpp error.cpp input.cpp matcher.cpp matcher_avx2.cpp matcher_avx512bw.cpp pattern.cpp posix.cpp simd_avx2.cpp simd_avx512bw.cpp unicode.cpp utf8.cpp block_scripts.cpp language_scripts.cpp letter_scripts.cpp
+libreflex_a_SOURCES   = $(top_srcdir)/include/reflex/abslexer.h $(top_srcdir)/include/reflex/absmatcher.h $(top_srcdir)/include/reflex/bits.h $(top_srcdir)/include/reflex/boostmatcher.h $(top_srcdir)/include/reflex/convert.h $(top_srcdir)/include/reflex/debug.h $(top_srcdir)/include/reflex/error.h $(top_srcdir)/include/reflex/flexlexer.h $(top_srcdir)/include/reflex/input.h $(top_srcdir)/include/reflex/matcher.h $(top_srcdir)/include/reflex/pattern.h $(top_srcdir)/include/reflex/posix.h $(top_srcdir)/include/reflex/ranges.h $(top_srcdir)/include/reflex/setop.h $(top_srcdir)/include/reflex/simd.h $(top_srcdir)/include/reflex/stdmatcher.h $(top_srcdir)/include/reflex/timer.h $(top_srcdir)/include/reflex/traits.h $(top_srcdir)/include/reflex/unicode.h $(top_srcdir)/include/reflex/utf8.h convert.cpp debug.cpp error.cpp input.cpp matcher.cpp matcher_avx2.cpp matcher_avx512bw.cpp pattern.cpp posix.cpp simd_avx2.cpp simd_avx512bw.cpp unicode.cpp utf8.cpp block_scripts.cpp language_scripts.cpp letter_scripts.cpp composer.cpp
 
 # separately compile matcher_avx2.cpp and matcher_avx512bw (with the same content as matcher.cpp) with AVX optimizations enabled
 libreflex_a-matcher_avx2.$(OBJEXT)     : CXXFLAGS += $(SIMD_AVX2_FLAGS)