released 6.4.1

fix #417

README.md

@@ -5441,7 +5441,7 @@ in markdown:
 
 
 
-    ugrep 6.4.0                      August 7, 2024                         UGREP(1)
+    ugrep 6.4.1                      August 8, 2024                         UGREP(1)
 
 🔝 [Back to table of contents](#toc)
 

configure

@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.72 for ugrep 6.4.0.
+# Generated by GNU Autoconf 2.72 for ugrep 6.4.1.
 #
 # 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='6.4.0'
-PACKAGE_STRING='ugrep 6.4.0'
+PACKAGE_VERSION='6.4.1'
+PACKAGE_STRING='ugrep 6.4.1'
 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 6.4.0 to adapt to many kinds of systems.
+'configure' configures ugrep 6.4.1 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 6.4.0:";;
+     short | recursive ) echo "Configuration of ugrep 6.4.1:";;
    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 6.4.0
+ugrep configure 6.4.1
 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 6.4.0, which was
+It was created by ugrep $as_me 6.4.1, 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='6.4.0'
+ VERSION='6.4.1'
 
 
 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 6.4.0, which was
+This file was extended by ugrep $as_me 6.4.1, 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 6.4.0
+ugrep config.status 6.4.1
 configured by $0, generated by GNU Autoconf 2.72,
   with options \\"\$ac_cs_config\\"
 

configure.ac

@@ -1,4 +1,4 @@
-AC_INIT([ugrep],[6.4.0],[https://github.com/Genivia/ugrep/issues],[ugrep],[https://ugrep.com])
+AC_INIT([ugrep],[6.4.1],[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.])

include/reflex/pattern.h

@@ -676,16 +676,17 @@ class Pattern {
       Tree::Node *tnode;  ///< the corresponding tree DFA node, when applicable
 #endif
       Edges       edges;  ///< state transitions
+      Lookaheads  heads;  ///< lookahead head set
+      Lookaheads  tails;  ///< lookahead tail set
       Index       first;  ///< index of this state in the opcode table in the first assembly pass, also used in breadth-first search to cut DFA for predict match
       Index       index;  ///< index of this state in the opcode table, also used in HFA construction
       Accept      accept; ///< nonzero if final state, the index of an accepted/captured subpattern
-      Lookaheads  heads;  ///< lookahead head set
-      Lookaheads  tails;  ///< lookahead tail set
       bool        redo;   ///< true if this is a final state of a negative pattern
     };
     typedef std::list<State*> List;
     static const uint16_t ALLOC = 1024;           ///< allocate 1024 DFA states at a time, to improve performance
     static const uint16_t MAX_DEPTH = 256;        ///< analyze DFA up to states this deep to improve predict match
+    static const Index MAX_STATES = Const::GMAX;  ///< maximum number of states
     static const Index DEAD_PATH = 1;             ///< state marker "path always and only reaches backedges" (a dead end)
     static const Index KEEP_PATH = MAX_DEPTH;     ///< state marker "required path" (from a newline edge)
     static const Index LOOP_PATH = MAX_DEPTH + 1; ///< state marker "path reaches a backedge" (collect lookback chars)
@@ -1161,8 +1162,8 @@ class Pattern {
   std::string           rex_; ///< regular expression string
   std::vector<Location> end_; ///< entries point to the subpattern's ending '|' or '\0'
   std::vector<bool>     acc_; ///< true if subpattern n is accepting (state is reachable)
-  size_t                vno_; ///< number of finite state machine vertices |V|
-  size_t                eno_; ///< number of finite state machine edges |E|
+  size_t                vno_; ///< number of finite state machine vertices |V| (nodes)
+  size_t                eno_; ///< number of finite state machine edges |E| (arrows)
   size_t                hno_; ///< number of indexing hash tables (HFA edges)
   const Opcode         *opc_; ///< points to the table with compiled finite state machine opcodes
   FSM                   fsm_; ///< function pointer to FSM code

lib/pattern.cpp

@@ -636,7 +636,7 @@ void Pattern::parse(
 {
   DBGLOG("BEGIN parse()");
   if (rex_.size() > Position::MAXLOC)
-    throw regex_error(regex_error::exceeds_length, rex_, Position::MAXLOC);
+    error(regex_error::exceeds_length, Position::MAXLOC);
   Location   len = static_cast<Location>(rex_.size());
   Location   loc = 0;
   Accept     choice = 1;
@@ -773,6 +773,8 @@ void Pattern::parse(
           t = target_state;
           ++eno_;
           ++vno_;
+          if (vno_ > DFA::MAX_STATES)
+            error(regex_error::exceeds_limits, loc);
         }
         else
         {
@@ -2118,6 +2120,8 @@ void Pattern::compile(
     if (state->accept > 0 && state->accept <= end_.size())
       acc_[state->accept - 1] = true;
     ++vno_;
+    if (vno_ > DFA::MAX_STATES)
+      error(regex_error::exceeds_limits, rex_.size());
   }
   delete[] table;
   vms_ = timer_elapsed(vt) - ems_;
@@ -2791,7 +2795,7 @@ void Pattern::encode_dfa(DFA::State *start)
 #endif
     nop_ += static_cast<Index>(state->heads.size() + state->tails.size() + (state->accept > 0 || state->redo));
     if (!valid_goto_index(nop_))
-      throw regex_error(regex_error::exceeds_limits, rex_, rex_.size());
+      error(regex_error::exceeds_limits, rex_.size());
   }
   if (nop_ > Const::LONG)
   {
@@ -2853,7 +2857,7 @@ void Pattern::encode_dfa(DFA::State *start)
 #endif
       nop_ += static_cast<Index>(state->heads.size() + state->tails.size() + (state->accept > 0 || state->redo));
       if (!valid_goto_index(nop_))
-        throw regex_error(regex_error::exceeds_limits, rex_, rex_.size());
+        error(regex_error::exceeds_limits, rex_.size());
     }
   }
   Opcode *opcode = new Opcode[nop_];
@@ -2872,13 +2876,13 @@ void Pattern::encode_dfa(DFA::State *start)
     for (Lookaheads::const_iterator i = state->tails.begin(); i != state->tails.end(); ++i)
     {
       if (!valid_lookahead_index(static_cast<Index>(*i)))
-        throw regex_error(regex_error::exceeds_limits, rex_, rex_.size());
+        error(regex_error::exceeds_limits, rex_.size());
       opcode[pc++] = opcode_tail(static_cast<Index>(*i));
     }
     for (Lookaheads::const_iterator i = state->heads.begin(); i != state->heads.end(); ++i)
     {
       if (!valid_lookahead_index(static_cast<Index>(*i)))
-        throw regex_error(regex_error::exceeds_limits, rex_, rex_.size());
+        error(regex_error::exceeds_limits, rex_.size());
       opcode[pc++] = opcode_head(static_cast<Index>(*i));
     }
 #if WITH_COMPACT_DFA == -1
@@ -3906,7 +3910,7 @@ void Pattern::analyze_dfa(DFA::State *start)
           count = static_cast<uint16_t>(next_chars.count()); // never more than 256
         }
         // save the previous metrics
-        cut_states = states;
+        cut_states.swap(states);
         cut_fin_states = fin_states;
         cut_count = count + fin_count;
         cut_chars += chars;

man/ug.1

@@ -1,4 +1,4 @@
-.TH UGREP "1" "August 07, 2024" "ugrep 6.4.0" "User Commands"
+.TH UGREP "1" "August 08, 2024" "ugrep 6.4.1" "User Commands"
 .SH NAME
 \fBugrep\fR, \fBug\fR -- file pattern searcher
 .SH SYNOPSIS

man/ugrep-indexer.1

@@ -1,4 +1,4 @@
-.TH UGREP-INDEXER "1" "August 07, 2024" "ugrep-indexer 6.4.0" "User Commands"
+.TH UGREP-INDEXER "1" "August 08, 2024" "ugrep-indexer 6.4.1" "User Commands"
 .SH NAME
 \fBugrep-indexer\fR -- file indexer to accelerate recursive searching
 .SH SYNOPSIS

man/ugrep.1

@@ -1,4 +1,4 @@
-.TH UGREP "1" "August 07, 2024" "ugrep 6.4.0" "User Commands"
+.TH UGREP "1" "August 08, 2024" "ugrep 6.4.1" "User Commands"
 .SH NAME
 \fBugrep\fR, \fBug\fR -- file pattern searcher
 .SH SYNOPSIS

src/cnf.hpp

@@ -143,6 +143,69 @@ class CNF {
   // return the first ALT-terms of the CNF
   std::string first() const;
 
+  // quote a pattern with \Q and \E
+  static void quote(std::string& pattern)
+  {
+    // when empty then nothing to quote
+    if (pattern.empty())
+      return;
+
+    size_t from = 0;
+    size_t to;
+
+    // replace each \E in the pattern with \E\\E\Q
+    while ((to = pattern.find("\\E", from)) != std::string::npos)
+    {
+      pattern.insert(to + 2, "\\\\E\\Q");
+      from = to + 7;
+    }
+
+    // enclose in \Q and \E
+    pattern.insert(0, "\\Q").append("\\E");
+  }
+
+  // anchor a pattern, when specified with -w or -x
+  static void anchor(std::string& pattern)
+  {
+    // patterns that start with ^ or end with $ are already anchored
+    if (pattern.empty())
+    {
+      // -x: empty regex matches empty lines with ^$
+      if (flag_line_regexp)
+        pattern.assign("^$");
+    }
+    else if (flag_line_regexp)
+    {
+      // -x: make the regex line-anchored
+      // -G requires \( \) instead of ( )
+      const char *xleft = flag_basic_regexp ? "^\\(" : "^(?:";
+      const char *xright = flag_basic_regexp ? "\\)$" : ")$";
+      pattern.insert(0, xleft).append(xright);
+    }
+    else if (flag_word_regexp)
+    {
+      // -w: make the regex word-anchored (or implicitly done with matcher option W instead of \< and \>)
+      if (flag_perl_regexp)
+      {
+        // -P requires (?<!\w) (?!\w) instead of \< and \>
+#if defined(HAVE_PCRE2)
+        // PCRE2_EXTRA_MATCH_WORD does not work and \b(?:regex)\b is not correct anyway, so we roll out our own
+        const char *wleft = pattern.front() != '^' ? "(?<!\\w)(?:" : "(?:";
+        const char *wright = pattern.back() != '$' ? ")(?!\\w)" : ")";
+#else // Boost.Regex
+        const char *wleft = pattern.front() != '^' ? "(?<![[:word:]])(?:" : "(?:";
+        const char *wright = pattern.back() != '$' ? ")(?![[:word:]])" : ")";
+#endif
+        pattern.insert(0, wleft).append(wright);
+      }
+    }
+    else if (pattern.front() == '^' || pattern.back() == '$')
+    {
+      // enable -Y to match empty
+      flag_empty = true;
+    }
+  }
+
  protected:
 
   struct OpTree {
@@ -247,63 +310,6 @@ class CNF {
 
   };
 
-  // quote a pattern with \Q and \E
-  static void quote(std::string& pattern)
-  {
-    // when empty then nothing to quote
-    if (pattern.empty())
-      return;
-
-    size_t from = 0;
-    size_t to;
-
-    // replace each \E in the pattern with \E\\E\Q
-    while ((to = pattern.find("\\E", from)) != std::string::npos)
-    {
-      pattern.insert(to + 2, "\\\\E\\Q");
-      from = to + 7;
-    }
-
-    // enclose in \Q and \E
-    pattern.insert(0, "\\Q").append("\\E");
-  }
-
-  // anchor a pattern, when specified with -w or -x
-  static void anchor(std::string& pattern)
-  {
-    // -G requires \( \) instead of ( ) and -P requires (?<!\w) (?!\w) instead of \< and \>
-    const char *xleft = flag_basic_regexp ? "^\\(" : "^(?:";
-    const char *xright = flag_basic_regexp ? "\\)$" : ")$";
-#if defined(HAVE_PCRE2)
-    // PCRE2_EXTRA_MATCH_WORD does not work and \b(?:regex)\b is not correct anyway, so we roll out our own
-    const char *wleft = flag_perl_regexp ? "(?<!\\w)(?:" : NULL;
-    const char *wright = flag_perl_regexp ? ")(?!\\w)" : NULL;
-#else // Boost.Regex
-    const char *wleft = flag_perl_regexp ? "(?<![[:word:]])(?:" : NULL;
-    const char *wright = flag_perl_regexp ? ")(?![[:word:]])" : NULL;
-#endif
-
-    // patterns that start with ^ or end with $ are already anchored
-    if (!pattern.empty() && (pattern.front() == '^' || pattern.back() == '$'))
-    {
-      // enable -Y to match empty
-      flag_empty = true;
-    }
-    else if (flag_line_regexp)
-    {
-      // make the regex line-anchored
-      if (!pattern.empty())
-        pattern.insert(0, xleft).append(xright);
-      else
-        pattern.assign("^$");
-    }
-    else if (!pattern.empty() && flag_word_regexp && wleft != NULL && wright != NULL)
-    {
-      // make the regex word-anchored (or done with matcher option W instead of \< and \>)
-      pattern.insert(0, wleft).append(wright);
-    }
-  }
-
   // CNF terms, an AND-list of ALT-term lists of string/NULL patterns
   Terms terms;
 

src/ugrep-indexer.cpp

@@ -35,7 +35,7 @@
 */
 
 // DO NOT ALTER THIS LINE: updated by makemake.sh and we need it physically here for MSVC++ build from source
-#define UGREP_VERSION "6.4.0"
+#define UGREP_VERSION "6.4.1"
 
 // use a task-parallel thread to decompress the stream into a pipe to search, also handles nested archives
 #define WITH_DECOMPRESSION_THREAD