Bug ID: JDK-6451717 Regex: Nodes (Not)?Single[A|U] report wrong hitEnd status when failed to match/find (5.0)

Type: Bug
Component: core-libs
Sub-Component: java.util.regex
Affected Version: 5.0

Priority: P3
Status: Resolved
Resolution: Fixed
OS: generic
CPU: generic

Submitted: 2006-07-21
Updated: 2010-04-02
Resolved: 2006-08-03

Other
5.0u10 b01Fixed

Regex nodes SingleA, NotSingleA, SingleU and NotSingleU always report the
hitEnd() to be true when match/find failed, even the "end" has not been reached.

The cases below show the problem.

        // SingleA
	p = Pattern.compile("^a", Pattern.CASE_INSENSITIVE);
	m = p.matcher("bcd");
	if (m.find() || m.hitEnd()) {
	    failCount++;
	}

        // NotSingleA
	p = Pattern.compile("^[^\u4e00]", Pattern.CASE_INSENSITIVE);
	m = p.matcher("\u4e00cd");
	if (m.find() || m.hitEnd()) {
	    failCount++;
	}

        // SingleU
	p = Pattern.compile("^\u4e00", Pattern.CASE_INSENSITIVE |Pattern.UNICODE_CASE);
	m = p.matcher("abc");
	if (m.find() || m.hitEnd()) {
	    failCount++;
	}

        // NotSingleU
	p = Pattern.compile("^[^\u03b2]", Pattern.CASE_INSENSITIVE |Pattern.UNICODE_CASE);
	m = p.matcher("\u0392bc");
	if (m.find() || m.hitEnd()) {
	    failCount++;
	}

EVALUATION Removed the "mustang" entry from SRs since this issue has already been addressed in 6.0 release as the side-effect of other changes.

18-01-2008

EVALUATION For 5.0u9. This problem does not exit in Mustang (has been sideeffectly fixed by other changes)

21-07-2006

SUGGESTED FIX --- Pattern.java Fri Jul 21 15:29:06 2006 *************** *** 3366,3378 **** return new SingleA(ch); } boolean match(Matcher matcher, int i, CharSequence seq) { ! if (i < matcher.to) { int c = seq.charAt(i); if (c == ch || ASCII.toLower(c) == ch) { return next.match(matcher, i+1, seq); } } - matcher.hitEnd = true; return false; } --- 3366,3379 ---- return new SingleA(ch); } boolean match(Matcher matcher, int i, CharSequence seq) { ! if (i >= matcher.to) { ! matcher.hitEnd = true; ! } else { int c = seq.charAt(i); if (c == ch || ASCII.toLower(c) == ch) { return next.match(matcher, i+1, seq); } } return false; } *************** *** 3395,3407 **** return new NotSingleA(ch); } boolean match(Matcher matcher, int i, CharSequence seq) { ! if (i < matcher.to) { int c = Character.codePointAt(seq, i); if (c != ch && ASCII.toLower(c) != ch) { return next.match(matcher, i+Character.charCount(c), seq); } } - matcher.hitEnd = true; return false; } --- 3396,3409 ---- return new NotSingleA(ch); } boolean match(Matcher matcher, int i, CharSequence seq) { ! if (i >= matcher.to) { ! matcher.hitEnd = true; ! } else { int c = Character.codePointAt(seq, i); if (c != ch && ASCII.toLower(c) != ch) { return next.match(matcher, i+Character.charCount(c), seq); } } return false; } *************** *** 3429,3435 **** return new SingleU(ch); } boolean match(Matcher matcher, int i, CharSequence seq) { ! if (i < matcher.to) { int c = Character.codePointAt(seq, i); if (c == ch) return next.match(matcher, i+len, seq); --- 3431,3439 ---- return new SingleU(ch); } boolean match(Matcher matcher, int i, CharSequence seq) { ! if (i >= matcher.to) { ! matcher.hitEnd = true; ! } else { int c = Character.codePointAt(seq, i); if (c == ch) return next.match(matcher, i+len, seq); *************** *** 3438,3444 **** if (cc == ch) return next.match(matcher, i+Character.charCount(c), seq); } - matcher.hitEnd = true; return false; } boolean study(TreeInfo info) { --- 3442,3447 ---- *************** *** 3463,3478 **** return new NotSingleU(ch); } boolean match(Matcher matcher, int i, CharSequence seq) { ! if (i < matcher.to) { int c = Character.codePointAt(seq, i); if (c == ch) return false; int cc = Character.toUpperCase(c); cc = Character.toLowerCase(cc); if (cc != ch) return next.match(matcher, i+Character.charCount(c), seq); } - matcher.hitEnd = true; return false; } boolean study(TreeInfo info) { --- 3466,3483 ---- return new NotSingleU(ch); } boolean match(Matcher matcher, int i, CharSequence seq) { ! if (i >= matcher.to) { ! matcher.hitEnd = true; ! } else { int c = Character.codePointAt(seq, i); if (c == ch) return false; int cc = Character.toUpperCase(c); cc = Character.toLowerCase(cc); + if (cc != ch) return next.match(matcher, i+Character.charCount(c), seq); } return false; } boolean study(TreeInfo info) {

21-07-2006