released 4.1.1

minor update to correct a DFA construction problem for POSIX regex lazy quantifiers matching too much in some cases

README.md

@@ -590,6 +590,7 @@ Changelog
 - Feb 17, 2024: 4.0.0 faster `Matcher::find()` with a new DFA cut algorithm to optimize match prediction speed and accuracy, see also ugrep 5.0; apply Unicode pattern canonicalization with `reflex::convert(..., reflex::convert_flag::unicode)`.
 - Feb 23, 2024: 4.0.1 new `rawk` example to demonstrate awk-like fast search in C++; enable `<<EOF>>` rules for option `find` to generate a fast search engine.
 - Mar  5, 2024: 4.1.0 improved lazy quantifiers for POSIX regex lazy matching in linear time using an advanced DFA transformation algorithm introduced in RE/flex in 2016.
+- Mar 11, 2024: 4.1.1 minor update to correct a DFA construction problem for POSIX regex lazy quantifiers matching too much in some cases.
 
 [logo-url]: https://www.genivia.com/images/reflex-logo.png
 [reflex-url]: https://www.genivia.com/reflex.html

doc/man/reflex.1

@@ -1,4 +1,4 @@
-.TH REFLEX "1" "March 05, 2024" "reflex 4.1.0" "User Commands"
+.TH REFLEX "1" "March 11, 2024" "reflex 4.1.1" "User Commands"
 .SH NAME
 \fBreflex\fR -- regex\-centric, fast and flexible lexical analyzer generator
 .SH SYNOPSIS

lib/pattern.cpp

@@ -944,13 +944,23 @@ void Pattern::parse2(
         iter = iter1;
     }
   }
-  for (Positions::const_iterator p = a_pos.begin(); p != a_pos.end(); ++p)
+  for (Positions::iterator p = a_pos.begin(); p != a_pos.end(); ++p)
   {
     for (Positions::const_iterator k = lastpos.begin(); k != lastpos.end(); ++k)
       if (at(k->loc()) == ')' && lookahead.find(k->loc()) != lookahead.end())
         pos_add(followpos[p->pos()], *k);
-    for (Positions::const_iterator k = lastpos.begin(); k != lastpos.end(); ++k)
-      pos_add(followpos[k->pos()], p->anchor(!nullable || k->pos() != p->pos()));
+    if (lazypos.empty())
+    {
+      for (Positions::const_iterator k = lastpos.begin(); k != lastpos.end(); ++k)
+        pos_add(followpos[k->pos()], p->anchor(!nullable || k->pos() != p->pos()));
+    }
+    else
+    {
+      // make the starting anchors at positions a_pos lazy
+      for (Lazypos::const_iterator l = lazypos.begin(); l != lazypos.end(); ++l)
+        for (Positions::const_iterator k = lastpos.begin(); k != lastpos.end(); ++k)
+          pos_add(followpos[k->pos()], p->lazy(l->lazy()).anchor(!nullable || k->pos() != p->pos()));
+    }
     lastpos.clear();
     pos_add(lastpos, *p);
     if (nullable || firstpos.empty())
@@ -2179,9 +2189,10 @@ void Pattern::trim_lazy(Positions *pos, const Lazypos& lazypos) const
         if (p->lazy() == l->lazy())
           if (max < l->loc())
             max = l->loc();
-    for (Positions::iterator p = pos->begin(); p != pos->end(); ++p)
-      if (p->loc() > max)
-        *p = p->lazy(0);
+    if (max > 0)
+      for (Positions::iterator p = pos->begin(); p != pos->end(); ++p)
+        if (p->loc() > max)
+          *p = p->lazy(0);
   }
 #ifdef DEBUG
   DBGLOG("END trim_lazy({");

src/reflex.h

@@ -72,7 +72,7 @@
 #endif
 
 // DO NOT ALTER THIS LINE: the makemake.sh script updates the version
-#define REFLEX_VERSION "4.1.0"
+#define REFLEX_VERSION "4.1.1"
 
 /// RE/flex scanner generator class, a variation of the classic "lex" tool to generate scanners.
 /**