released 6.2.0

fix #407 fix #408 update #409
Genivia · Jul 9, 2024 · 148290c · 148290c
1 parent 2f961aa
commit 148290c
Show file tree

Hide file tree

Showing 44 changed files with 519 additions and 597 deletions.
diff --git a/README.md b/README.md
@@ -1616,12 +1616,11 @@ same line, like XOR:
 ### Search this but not that with -v, -e, -N, -f, -L, -w, -x
 
     -e PATTERN, --regexp=PATTERN
-            Specify a PATTERN used during the search of the input: an input
-            line is selected if it matches any of the specified patterns.
-            Note that longer patterns take precedence over shorter patterns.
-            This option is most useful when multiple -e options are used to
-            specify multiple patterns, when a pattern begins with a dash (`-'),
-            to specify a pattern after option -f or after the FILE arguments.
+            Specify a PATTERN to search the input.  An input line is selected
+            if it matches any of the specified patterns.  This option is useful
+            when multiple -e options are used to specify multiple patterns, or
+            when a pattern begins with a dash (`-'), or to specify a pattern
+            after option -f or after the FILE arguments.
     -f FILE, --file=FILE
             Read newline-separated patterns from FILE.  White space in patterns
             is significant.  Empty lines in FILE are ignored.  If FILE does not
@@ -4189,11 +4188,10 @@ in markdown:
 
            -e PATTERN, --regexp=PATTERN
                   Specify a PATTERN to search the input.  An input line is selected
-                  if it matches any of the specified patterns.  Note that longer
-                  patterns take precedence over shorter patterns.  This option is
-                  most useful when multiple -e options are used to specify multiple
-                  patterns, when a pattern begins with a dash (`-'), to specify a
-                  pattern after option -f or after the FILE arguments.
+                  if it matches any of the specified patterns.  This option is
+                  useful when multiple -e options are used to specify multiple
+                  patterns, or when a pattern begins with a dash (`-'), or to
+                  specify a pattern after option -f or after the FILE arguments.
 
            --encoding=ENCODING
                   The encoding format of the input.  The default ENCODING is binary
@@ -5297,7 +5295,7 @@ in markdown:
 
                   $ ugrep -e FIXME -f cpp/zap_strings myfile.cpp
 
-           Find lines with `FIXME' or `TODO', showing line numberes:
+           Find lines with `FIXME' or `TODO', showing line numbers:
 
                   $ ugrep -n -e FIXME -e TODO myfile.cpp
 
@@ -5380,7 +5378,7 @@ in markdown:
                   $ ugrep --help fuzzy
 
     COPYRIGHT
-           Copyright (c) 2021-2024 Robert A. van Engelen <[email protected]>
+           Copyright (c) 2021,2024 Robert A. van Engelen <[email protected]>
 
            ugrep is released under the BSD-3 license.  All parts of the software
            have reasonable copyright terms permitting free redistribution.  This
@@ -5394,7 +5392,7 @@ in markdown:
 
 
 
-    ugrep 6.1.0                       June 3, 2024                          UGREP(1)
+    ugrep 6.2.0                       July 9, 2024                          UGREP(1)
 
 🔝 [Back to table of contents](#toc)
 

diff --git a/bin/README.md b/bin/README.md
@@ -1,6 +1,5 @@
-Binaries for Windows 32-bit and 64-bit ugrep.exe are included in the
-repository: building ugrep on Windows takes some serious effort to install and
+Binaries for Windows 32-bit and 64-bit ugrep.exe and ugrep-indexer.exe are
+included: building ugrep on Windows takes some serious effort to install and
 compile PCRE2 and all of the compression libraries together with ugrep with the
-proper configuration settings of C++ dev tools.
-
-Visual Studio ugrep.exe build instructions can be found in vs/ugrep/README.txt
+proper configuration settings of C++ dev tools.  Visual Studio ugrep.exe build
+instructions can be found in vs/ugrep/README.txt
diff --git a/bin/linux_amd64/README.md b/bin/linux_amd64/README.md
diff --git a/bin/linux_amd64/ugrep b/bin/linux_amd64/ugrep
diff --git a/bin/linux_amd64/ugrep-indexer b/bin/linux_amd64/ugrep-indexer
diff --git a/bin/linux_arm64/README.md b/bin/linux_arm64/README.md
diff --git a/bin/linux_arm64/ugrep b/bin/linux_arm64/ugrep
diff --git a/bin/linux_arm64/ugrep-indexer b/bin/linux_arm64/ugrep-indexer
diff --git a/bin/win32/ug.exe b/bin/win32/ug.exe
diff --git a/bin/win32/ugrep-indexer.exe b/bin/win32/ugrep-indexer.exe
diff --git a/bin/win32/ugrep.exe b/bin/win32/ugrep.exe
diff --git a/bin/win64/ug.exe b/bin/win64/ug.exe
diff --git a/bin/win64/ugrep-indexer.exe b/bin/win64/ugrep-indexer.exe
diff --git a/bin/win64/ugrep.exe b/bin/win64/ugrep.exe
diff --git a/completions/zsh/_ug b/completions/zsh/_ug
@@ -7,17 +7,17 @@ local matchers='(--extended-regexp --fixed-strings --basic-regexp --perl-regexp
 local arguments=(
 '(-e --regexp -f --file)1: :_guard "^-*" pattern'
 '*: :_files'
-{-A,--after-context=-}'[Output NUM lines of trailing context after matching lines]'
+{-A,--after-context=-}'[Output NUM lines of trailing context after matching lines]:NUM:( )'
 {-a,--text}'[Process a binary file as if it were text]'
 {--all,-@}'[Search all files except hidden: cancel previous file and directory search restrictions and cancel --ignore-binary and --ignore-files when specified]'
 '(1)*'--and'[Specify additional PATTERN that must match]'
 '(1)*'--andnot'[Combines --and --not]'
-{-B,--before-context=-}'[Output NUM lines of leading context before matching lines]'
+{-B,--before-context=-}'[Output NUM lines of leading context before matching lines]:NUM:( )'
 {-b,--byte-offset}'[The offset in bytes of a pattern match is displayed in front of the respective matched line]'
 --binary-files=-'[Controls searching and reporting pattern matches in binary files]'
 {--bool,-%,-%%}'[Specifies Boolean query patterns]'
 --break'[Adds a line break between results from different files]'
-{-C,--context=-}'[Output NUM lines of leading and trailing context surrounding each matching line]'
+{-C,--context=-}'[Output NUM lines of leading and trailing context surrounding each matching line]:NUM:( )'
 {-c,--count}'[Only a count of selected lines is written to standard output]'
 {--color,--colour}'[Mark up the matching text with the colors specified with option --colors or the GREP_COLOR or GREP_COLORS environment variable]'
 {--colors=-,--colours=-}'[Use COLORS to mark up text]'

diff --git a/completions/zsh/_ug+ b/completions/zsh/_ug+
@@ -7,17 +7,17 @@ local matchers='(--extended-regexp --fixed-strings --basic-regexp --perl-regexp
 local arguments=(
 '(-e --regexp -f --file)1: :_guard "^-*" pattern'
 '*: :_files'
-{-A,--after-context=-}'[Output NUM lines of trailing context after matching lines]'
+{-A,--after-context=-}'[Output NUM lines of trailing context after matching lines]:NUM:( )'
 {-a,--text}'[Process a binary file as if it were text]'
 {--all,-@}'[Search all files except hidden: cancel previous file and directory search restrictions and cancel --ignore-binary and --ignore-files when specified]'
 '(1)*'--and'[Specify additional PATTERN that must match]'
 '(1)*'--andnot'[Combines --and --not]'
-{-B,--before-context=-}'[Output NUM lines of leading context before matching lines]'
+{-B,--before-context=-}'[Output NUM lines of leading context before matching lines]:NUM:( )'
 {-b,--byte-offset}'[The offset in bytes of a pattern match is displayed in front of the respective matched line]'
 --binary-files=-'[Controls searching and reporting pattern matches in binary files]'
 {--bool,-%,-%%}'[Specifies Boolean query patterns]'
 --break'[Adds a line break between results from different files]'
-{-C,--context=-}'[Output NUM lines of leading and trailing context surrounding each matching line]'
+{-C,--context=-}'[Output NUM lines of leading and trailing context surrounding each matching line]:NUM:( )'
 {-c,--count}'[Only a count of selected lines is written to standard output]'
 {--color,--colour}'[Mark up the matching text with the colors specified with option --colors or the GREP_COLOR or GREP_COLORS environment variable]'
 {--colors=-,--colours=-}'[Use COLORS to mark up text]'

diff --git a/completions/zsh/_ugrep b/completions/zsh/_ugrep
@@ -7,17 +7,17 @@ local matchers='(--extended-regexp --fixed-strings --basic-regexp --perl-regexp
 local arguments=(
 '(-e --regexp -f --file)1: :_guard "^-*" pattern'
 '*: :_files'
-{-A,--after-context=-}'[Output NUM lines of trailing context after matching lines]'
+{-A,--after-context=-}'[Output NUM lines of trailing context after matching lines]:NUM:( )'
 {-a,--text}'[Process a binary file as if it were text]'
 {--all,-@}'[Search all files except hidden: cancel previous file and directory search restrictions and cancel --ignore-binary and --ignore-files when specified]'
 '(1)*'--and'[Specify additional PATTERN that must match]'
 '(1)*'--andnot'[Combines --and --not]'
-{-B,--before-context=-}'[Output NUM lines of leading context before matching lines]'
+{-B,--before-context=-}'[Output NUM lines of leading context before matching lines]:NUM:( )'
 {-b,--byte-offset}'[The offset in bytes of a pattern match is displayed in front of the respective matched line]'
 --binary-files=-'[Controls searching and reporting pattern matches in binary files]'
 {--bool,-%,-%%}'[Specifies Boolean query patterns]'
 --break'[Adds a line break between results from different files]'
-{-C,--context=-}'[Output NUM lines of leading and trailing context surrounding each matching line]'
+{-C,--context=-}'[Output NUM lines of leading and trailing context surrounding each matching line]:NUM:( )'
 {-c,--count}'[Only a count of selected lines is written to standard output]'
 {--color,--colour}'[Mark up the matching text with the colors specified with option --colors or the GREP_COLOR or GREP_COLORS environment variable]'
 {--colors=-,--colours=-}'[Use COLORS to mark up text]'

diff --git a/completions/zsh/_ugrep+ b/completions/zsh/_ugrep+
@@ -7,17 +7,17 @@ local matchers='(--extended-regexp --fixed-strings --basic-regexp --perl-regexp
 local arguments=(
 '(-e --regexp -f --file)1: :_guard "^-*" pattern'
 '*: :_files'
-{-A,--after-context=-}'[Output NUM lines of trailing context after matching lines]'
+{-A,--after-context=-}'[Output NUM lines of trailing context after matching lines]:NUM:( )'
 {-a,--text}'[Process a binary file as if it were text]'
 {--all,-@}'[Search all files except hidden: cancel previous file and directory search restrictions and cancel --ignore-binary and --ignore-files when specified]'
 '(1)*'--and'[Specify additional PATTERN that must match]'
 '(1)*'--andnot'[Combines --and --not]'
-{-B,--before-context=-}'[Output NUM lines of leading context before matching lines]'
+{-B,--before-context=-}'[Output NUM lines of leading context before matching lines]:NUM:( )'
 {-b,--byte-offset}'[The offset in bytes of a pattern match is displayed in front of the respective matched line]'
 --binary-files=-'[Controls searching and reporting pattern matches in binary files]'
 {--bool,-%,-%%}'[Specifies Boolean query patterns]'
 --break'[Adds a line break between results from different files]'
-{-C,--context=-}'[Output NUM lines of leading and trailing context surrounding each matching line]'
+{-C,--context=-}'[Output NUM lines of leading and trailing context surrounding each matching line]:NUM:( )'
 {-c,--count}'[Only a count of selected lines is written to standard output]'
 {--color,--colour}'[Mark up the matching text with the colors specified with option --colors or the GREP_COLOR or GREP_COLORS environment variable]'
 {--colors=-,--colours=-}'[Use COLORS to mark up text]'

diff --git a/completions/zsh/compgen.sh b/completions/zsh/compgen.sh
@@ -49,7 +49,7 @@ $UGREP --help 2>&1 \
     | sed -E -e "s/ /'[/" -e "s/\.?$/\]/" \
     | sed -E -e "s/--hexdump/--hexdump=-/" -e "s/--sort'/--sort=-'/" -e "s/-Z,--fuzzy/-Z-,--fuzzy=-/" \
     | sed -E -e "/\{-D/s/$/:ACTION:(read skip)/" -e "/\{-d/s/$/:ACTION:(read recurse skip)/" \
-    | sed -E -e "/\{-g/s/$/:GLOB:( )/" -e "/\{-[eMN]/s/$/:PATTERN:( )/" -e "/\{-f/s/$/:FILE:_files/" -e "/\{-J/s/$/:NUM:( )/" -e "/\{-[Km]/s/$/:MIN,MAX:( )/" -e "/\{-O/s/$/:EXT:( )/" \
+    | sed -E -e "/\{-g/s/$/:GLOB:( )/" -e "/\{-[eMN]/s/$/:PATTERN:( )/" -e "/\{-f/s/$/:FILE:_files/" -e "/\{-[ABCJ]/s/$/:NUM:( )/" -e "/\{-[Km]/s/$/:MIN,MAX:( )/" -e "/\{-O/s/$/:EXT:( )/" \
     | sed -E -e "/\{-t/s/$/:TYPES:($TYPES)/" -e "/--encoding/s/$/:ENCODING:($ENCODING)/" \
     | sed -E -e "/--hexdump/s/$/:NUM:(1a 2a 4ah 6ah 8ah 1aC1 2aC1 4ahC1 6ahC1 8ahC1)/" \
     | sed -E -e "/\{-m/s/$/::(1 1, 1,10)/" \

diff --git a/configure b/configure
@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.72 for ugrep 6.1.0.
+# Generated by GNU Autoconf 2.72 for ugrep 6.2.0.
 #
 # Report bugs to <https://github.com/Genivia/ugrep/issues>.
 #
@@ -606,8 +606,8 @@ MAKEFLAGS=
 # Identity of this package.
 PACKAGE_NAME='ugrep'
 PACKAGE_TARNAME='ugrep'
-PACKAGE_VERSION='6.1.0'
-PACKAGE_STRING='ugrep 6.1.0'
+PACKAGE_VERSION='6.2.0'
+PACKAGE_STRING='ugrep 6.2.0'
 PACKAGE_BUGREPORT='https://github.com/Genivia/ugrep/issues'
 PACKAGE_URL='https://ugrep.com'
 
@@ -1382,7 +1382,7 @@ 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 6.1.0 to adapt to many kinds of systems.
+'configure' configures ugrep 6.2.0 to adapt to many kinds of systems.
 
 Usage: $0 [OPTION]... [VAR=VALUE]...
 
@@ -1453,7 +1453,7 @@ fi
 
 if test -n "$ac_init_help"; then
   case $ac_init_help in
-     short | recursive ) echo "Configuration of ugrep 6.1.0:";;
+     short | recursive ) echo "Configuration of ugrep 6.2.0:";;
    esac
   cat <<\_ACEOF
 
@@ -1630,7 +1630,7 @@ fi
 test -n "$ac_init_help" && exit $ac_status
 if $ac_init_version; then
   cat <<\_ACEOF
-ugrep configure 6.1.0
+ugrep configure 6.2.0
 generated by GNU Autoconf 2.72
 
 Copyright (C) 2023 Free Software Foundation, Inc.
@@ -2184,7 +2184,7 @@ 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 6.1.0, which was
+It was created by ugrep $as_me 6.2.0, which was
 generated by GNU Autoconf 2.72.  Invocation command line was
 
   $ $0$ac_configure_args_raw
@@ -3694,7 +3694,7 @@ fi
 
 # Define the identity of the package.
  PACKAGE='ugrep'
- VERSION='6.1.0'
+ VERSION='6.2.0'
 
 
 printf "%s\n" "#define PACKAGE \"$PACKAGE\"" >>confdefs.h
@@ -11790,7 +11790,7 @@ cat >>$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 6.1.0, which was
+This file was extended by ugrep $as_me 6.2.0, which was
 generated by GNU Autoconf 2.72.  Invocation command line was
 
   CONFIG_FILES    = $CONFIG_FILES
@@ -11863,7 +11863,7 @@ ac_cs_config_escaped=`printf "%s\n" "$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 6.1.0
+ugrep config.status 6.2.0
 configured by $0, generated by GNU Autoconf 2.72,
   with options \\"\$ac_cs_config\\"
 

diff --git a/configure.ac b/configure.ac
@@ -1,4 +1,4 @@
-AC_INIT([ugrep],[6.1.0],[https://github.com/Genivia/ugrep/issues],[ugrep],[https://ugrep.com])
+AC_INIT([ugrep],[6.2.0],[https://github.com/Genivia/ugrep/issues],[ugrep],[https://ugrep.com])
 AM_INIT_AUTOMAKE([foreign subdir-objects dist-xz no-dist-gzip])
 AC_CONFIG_HEADERS([config.h])
 AC_COPYRIGHT([Copyright (C) 2019-2024 Robert van Engelen, Genivia Inc.])

diff --git a/include/reflex/pattern.h b/include/reflex/pattern.h
@@ -355,28 +355,28 @@ class Pattern {
     return ams_;
   }
   /// Returns true when match is predicted, based on s[0..3..e-1] (e >= s + 4).
-  static inline bool predict_match(const Pred pmh[], const char *s, size_t n)
+  inline bool predict_match(const char *s, size_t n) const
   {
     Hash h = static_cast<uint8_t>(*s);
-    Pred f = pmh[h] & 1;
+    Pred f = pmh_[h] & 1;
     h = hash(h, static_cast<uint8_t>(*++s));
-    f |= pmh[h] & 2;
+    f |= pmh_[h] & 2;
     h = hash(h, static_cast<uint8_t>(*++s));
-    f |= pmh[h] & 4;
+    f |= pmh_[h] & 4;
     h = hash(h, static_cast<uint8_t>(*++s));
-    f |= pmh[h] & 8;
+    f |= pmh_[h] & 8;
     const char *e = s + n - 3;
     Pred m = 16;
     while (f == 0 && ++s < e)
     {
       h = hash(h, static_cast<uint8_t>(*s));
-      f = pmh[h] & m;
+      f = pmh_[h] & m;
       m <<= 1;
     }
     return f == 0;
   }
-  /// Returns zero when match is predicted (removed shift distance return, now just returns 0 or 1).
-  static inline size_t predict_match(const Pred pma[], const char *s)
+  /// Returns true when match is predicted using my PM4 logic.
+  inline bool predict_match(const char *s) const
   {
     uint8_t b0 = s[0];
     uint8_t b1 = s[1];
@@ -385,13 +385,9 @@ class Pattern {
     Hash h1 = hash(b0, b1);
     Hash h2 = hash(h1, b2);
     Hash h3 = hash(h2, b3);
-    Pred a0 = pma[b0];
-    Pred a1 = pma[h1];
-    Pred a2 = pma[h2];
-    Pred a3 = pma[h3];
-    Pred p = (a0 & 0xc0) | (a1 & 0x30) | (a2 & 0x0c) | (a3 & 0x03);
+    Pred p = (pma_[b0] & 0xc0) | (pma_[h1] & 0x30) | (pma_[h2] & 0x0c) | (pma_[h3] & 0x03);
     Pred m = ((((((p >> 2) | p) >> 2) | p) >> 1) | p);
-    return m == 0xff;
+    return m != 0xff;
   }
   /// Relative frequency of English letters with upper/lower-case ratio = 0.0563, punctuation and UTF-8 bytes.
   static uint8_t frequency(uint8_t c)

diff --git a/include/reflex/pcre2matcher.h b/include/reflex/pcre2matcher.h
@@ -50,7 +50,7 @@ class PCRE2Matcher : public PatternMatcher<std::string> {
   template<typename T>
   static std::string convert(T regex, convert_flag_type flags = convert_flag::none, bool *multiline = NULL)
   {
-    return reflex::convert(regex, "imPRsx!#<>=&|'(0123456789*:abcdefghnrstvwxzABCDGHKNQRSVWXZ0123456789?+", flags, multiline);
+    return reflex::convert(regex, "iJmnPRsUx!#<>=&|'(0123456789*:abcdefghnrstvwxzABCDGHKNQRSVWXZ0123456789?+", flags, multiline);
   }
   /// Default constructor.
   PCRE2Matcher()
@@ -465,7 +465,7 @@ class PCRE2UTFMatcher : public PCRE2Matcher {
   template<typename T>
   static std::string convert(T regex, convert_flag_type flags = convert_flag::none, bool *multiline = NULL)
   {
-    return reflex::convert(regex, "imPRsx!#<>=&|'(0123456789*:abcdefghknprstvwxzABCDGHKNPQRSVWXZ0123456789?+", flags, multiline);
+    return reflex::convert(regex, "iJmnPRsUx!#<>=&|'(0123456789*:abcdefghknprstvwxzABCDGHKNPQRSVWXZ0123456789?+", flags, multiline);
   }
   /// Default constructor.
   PCRE2UTFMatcher() : PCRE2Matcher()

diff --git a/include/reflex/simd.h b/include/reflex/simd.h
@@ -60,7 +60,9 @@
 #ifdef _MSC_VER
 # define cpuidex __cpuidex
 #else
-# include <cpuid.h>
+# ifndef __cpuid_count
+#  include <cpuid.h>
+# endif
 # define cpuidex(CPUInfo, id, subid) __cpuid_count(id, subid, CPUInfo[0], CPUInfo[1], CPUInfo[2], CPUInfo[3])
 #endif
 

diff --git a/lib/error.cpp b/lib/error.cpp
@@ -69,13 +69,16 @@ std::string regex_error::regex_error_message_code(regex_error_type code, const c
 
 std::string regex_error::regex_error_message(const char *message, const char *pattern, size_t pos)
 {
+  const char *p = strrchr(pattern, '\n');
+  if (p != NULL)
+    pattern = p + 1;
   size_t l = strlen(pattern);
   if (pos > l)
     pos = l;
   l = strlen(message);
   size_t n = pos / 40;
   size_t k = pos % 40 + (n == 0 ? 0 : 20);
-  const char *p = n == 0 ? pattern : pattern + 40 * n - 20;
+  p = n == 0 ? pattern : pattern + 40 * n - 20;
   while (p > pattern && (*p & 0xc0) == 0x80)
   {
     --p;

diff --git a/lib/input.cpp b/lib/input.cpp
@@ -28,7 +28,7 @@
 
 /**
 @file      input.cpp
-@brief     RE/flex input character sequence class and simd.h CPUID check
+@brief     RE/flex input character sequence class
 @author    Robert van Engelen - [email protected]
 @copyright (c) 2016-2020, Robert van Engelen, Genivia Inc. All rights reserved.
 @copyright (c) BSD-3 License - see LICENSE.txt