[cp-patches] RFC: gnu.regexp fix to avoid unwanted PatternSyntaxException

[Ito Kazumitsu]

This fixes the bug #25616.

I have updated the mauve test
  gnu/testlet/java/util/regex/Pattern/matches.java
for testing this fix.

ChangeLog:
2006-01-05  Ito Kazumitsu  <address@hidden>

        * gnu/regexp/RE.java(initialize): Allow repeat.empty.token.

        * gnu/regexp/RETokenRepeated.java(match): Break the loop
        when an empty string matched an empty token.    

Index: classpath/gnu/regexp/RE.java
===================================================================
RCS file: /cvsroot/classpath/classpath/gnu/regexp/RE.java,v
retrieving revision 1.7
diff -u -r1.7 RE.java
--- classpath/gnu/regexp/RE.java        2 Jul 2005 20:32:15 -0000       1.7
+++ classpath/gnu/regexp/RE.java        5 Jan 2006 14:28:33 -0000
@@ -386,8 +386,10 @@
             throw new 
REException(getLocalizedMessage("repeat.chained"),REException.REG_BADRPT,newIndex);
           if (currentToken instanceof RETokenWordBoundary || currentToken 
instanceof RETokenWordBoundary)
             throw new 
REException(getLocalizedMessage("repeat.assertion"),REException.REG_BADRPT,newIndex);
-          if ((currentToken.getMinimumLength() == 0) && (minMax.second == 
Integer.MAX_VALUE))
-            throw new 
REException(getLocalizedMessage("repeat.empty.token"),REException.REG_BADRPT,newIndex);
+         // Allow repeat.empty.token
+          // if ((currentToken.getMinimumLength() == 0) && (minMax.second == 
Integer.MAX_VALUE)) {
+            // throw new 
REException(getLocalizedMessage("repeat.empty.token"),REException.REG_BADRPT,newIndex);
+         // }
           index = newIndex;
           currentToken = 
setRepeated(currentToken,minMax.first,minMax.second,index); 
         }
@@ -624,8 +626,10 @@
           throw new 
REException(getLocalizedMessage("repeat.chained"),REException.REG_BADRPT,index);
        if (currentToken instanceof RETokenWordBoundary || currentToken 
instanceof RETokenWordBoundary)
          throw new 
REException(getLocalizedMessage("repeat.assertion"),REException.REG_BADRPT,index);
-       if (currentToken.getMinimumLength() == 0)
-         throw new 
REException(getLocalizedMessage("repeat.empty.token"),REException.REG_BADRPT,index);
+       // Allow repeat.empty.token
+       // if (currentToken.getMinimumLength() == 0) {
+         // throw new 
REException(getLocalizedMessage("repeat.empty.token"),REException.REG_BADRPT,index);
+       // }
        currentToken = setRepeated(currentToken,0,Integer.MAX_VALUE,index);
       }
 
@@ -648,8 +652,10 @@
        }
        else if (currentToken instanceof RETokenWordBoundary || currentToken 
instanceof RETokenWordBoundary)
          throw new 
REException(getLocalizedMessage("repeat.assertion"),REException.REG_BADRPT,index);
-       else if (currentToken.getMinimumLength() == 0)
-         throw new 
REException(getLocalizedMessage("repeat.empty.token"),REException.REG_BADRPT,index);
+       // Allow repeat.empty.token
+       // else if (currentToken.getMinimumLength() == 0) {
+         // throw new 
REException(getLocalizedMessage("repeat.empty.token"),REException.REG_BADRPT,index);
+       // }
        else
          currentToken = setRepeated(currentToken,1,Integer.MAX_VALUE,index);
       }
Index: classpath/gnu/regexp/RETokenRepeated.java
===================================================================
RCS file: /cvsroot/classpath/classpath/gnu/regexp/RETokenRepeated.java,v
retrieving revision 1.3
diff -u -r1.3 RETokenRepeated.java
--- classpath/gnu/regexp/RETokenRepeated.java   2 Jul 2005 20:32:15 -0000       
1.3
+++ classpath/gnu/regexp/RETokenRepeated.java   5 Jan 2006 14:28:33 -0000
@@ -108,6 +108,7 @@
        REMatch doables;
        REMatch doablesLast;
        REMatch recurrent;
+       int lastIndex = mymatch.index;
 
        do {
            // Check for stingy match for each possibility.
@@ -151,6 +152,14 @@
            ++numRepeats;
            
            positions.addElement(newMatch);
+
+           // doables.index == lastIndex means an empty string
+           // was the longest that matched this token.
+           // We break here, otherwise we will fall into an endless loop.
+           if (doables.index == lastIndex && numRepeats >= min) {
+               break;
+           }           
+           lastIndex = doables.index;
        } while (numRepeats < max);
        
        // If there aren't enough repeats, then fail