From: Ito Kazumitsu <[EMAIL PROTECTED]>
Subject: Re: [cp-patches] RFC: java.util.regex.Matcher#hitEnd()
Date: Mon, 07 Aug 2006 02:13:34 +0900 (JST)
> I have made a patch and a mauve test for this, and put it at
> http://www.jsdi.or.jp/~maczuka/programs/regex-patched.tar.gz,
> but I will be on vacation soon and have no time to prepare an RFC
> message.
Here it is.
ChangeLog:
2006-08-16 Ito Kazumitsu <[EMAIL PROTECTED]>
Fixes bug #28412
* gnu/java/util/regex/CharIndexed.java(move1, setHitEnd, hitEnd):
New methods.
* gnu/java/util/regex/CharIndexedCharSequence.java,
gnu/java/util/regex/CharIndexedInputStream.java: Implemented the
new methods above.
* gnu/java/util/regex/RE.java(REG_FIX_STARTING_POSITION): New flag,
(match): call the new method setHitEnd of the input,
(getMatchImpl): Handle the new flag REG_FIX_STARTING_POSITION,
Some optimization commented out, Use CharIndexed#move1 instead of move.
* gnu/java/util/regex/REMatch.java: Made some debugging methods public.
* gnu/java/util/regex/REToken.java(match): The method body has been
moved to an internal private method, (matchFake): New method,
(setHitEnd): New method.
* gnu/java/util/regex/RETokenChar.java(matchThis): Call setHitEnd
if the match is not complete, (matchOneString): Count the number of
characters which matched the pattern.
* gnu/java/util/regex/RETokenEnd.java(fake): New field,
(setFake): New method, (match): Call super.match or super.matchFake.
* gnu/java/util/regex/RETokenEndSub.java(setHitEnd): New method.
* gnu/java/util/regex/RETokenOneOf.java(match): call the new method
setHitEnd of the input,
* gnu/java/util/regex/RETokenRepeated.java(match): Likewise.
* java/util/regex/Matcher.java(lookingAt, match): Use the new flag
RE.REG_FIX_STARTING_POSITION, (hitEnd, toString): New methods.
Index: classpath/gnu/java/util/regex/CharIndexed.java
===================================================================
RCS file: /cvsroot/classpath/classpath/gnu/java/util/regex/CharIndexed.java,v
retrieving revision 1.1
diff -u -r1.1 CharIndexed.java
--- classpath/gnu/java/util/regex/CharIndexed.java 7 Jun 2006 19:30:06
-0000 1.1
+++ classpath/gnu/java/util/regex/CharIndexed.java 16 Aug 2006 00:12:58
-0000
@@ -77,6 +77,13 @@
boolean move(int index);
/**
+ * Shifts the input buffer by a given number of positions. Returns
+ * true if the new cursor position is valid or cursor position is at
+ * the end of input.
+ */
+ boolean move1(int index); // I cannot think of a better name for this.
+
+ /**
* Returns true if the most recent move() operation placed the cursor
* position at a valid position in the input.
*/
@@ -105,6 +112,16 @@
REMatch getLastMatch();
/**
+ * Sets the information used for hitEnd().
+ */
+ void setHitEnd(REMatch match);
+
+ /**
+ * Returns whether the matcher has hit the end of input.
+ */
+ boolean hitEnd();
+
+ /**
* Returns the anchor.
*/
int getAnchor();
Index: classpath/gnu/java/util/regex/CharIndexedCharSequence.java
===================================================================
RCS file:
/cvsroot/classpath/classpath/gnu/java/util/regex/CharIndexedCharSequence.java,v
retrieving revision 1.1
diff -u -r1.1 CharIndexedCharSequence.java
--- classpath/gnu/java/util/regex/CharIndexedCharSequence.java 7 Jun 2006
19:30:06 -0000 1.1
+++ classpath/gnu/java/util/regex/CharIndexedCharSequence.java 16 Aug 2006
00:12:58 -0000
@@ -62,6 +62,10 @@
return ((anchor += index) < len);
}
+ public boolean move1(int index) {
+ return ((anchor += index) <= len);
+ }
+
public CharIndexed lookBehind(int index, int length) {
if (length > (anchor + index)) length = anchor + index;
return new CharIndexedCharSequence(s, anchor + index - length);
@@ -77,6 +81,15 @@
lastMatch.anchor = anchor;
}
public REMatch getLastMatch() { return lastMatch; }
+
+ private int rightmostTriedPosition = 0;
+ public void setHitEnd(REMatch match) {
+ int pos = anchor + match.index;
+ if (pos > rightmostTriedPosition) rightmostTriedPosition = pos;
+ }
+ public boolean hitEnd() { return rightmostTriedPosition >= len; }
+
public int getAnchor() { return anchor; }
public void setAnchor(int anchor) { this.anchor = anchor; }
+
}
Index: classpath/gnu/java/util/regex/CharIndexedInputStream.java
===================================================================
RCS file:
/cvsroot/classpath/classpath/gnu/java/util/regex/CharIndexedInputStream.java,v
retrieving revision 1.1
diff -u -r1.1 CharIndexedInputStream.java
--- classpath/gnu/java/util/regex/CharIndexedInputStream.java 7 Jun 2006
19:30:06 -0000 1.1
+++ classpath/gnu/java/util/regex/CharIndexedInputStream.java 16 Aug 2006
00:12:58 -0000
@@ -166,6 +166,16 @@
"difficult to support getLastMatch for an input stream");
}
+ public void setHitEnd(REMatch match) {
+ throw new UnsupportedOperationException(
+ "difficult to support setHitEnd for an input stream");
+ }
+
+ public boolean hitEnd() {
+ throw new UnsupportedOperationException(
+ "difficult to support hitEnd for an input stream");
+ }
+
public int getAnchor() {
throw new UnsupportedOperationException(
"difficult to support getAnchor for an input stream");
@@ -176,6 +186,10 @@
"difficult to support setAnchor for an input stream");
}
+ public boolean move1(int index) {
+ throw new UnsupportedOperationException(
+ "difficult to support move1 for an input stream");
+ }
}
Index: classpath/gnu/java/util/regex/RE.java
===================================================================
RCS file: /cvsroot/classpath/classpath/gnu/java/util/regex/RE.java,v
retrieving revision 1.3
diff -u -r1.3 RE.java
--- classpath/gnu/java/util/regex/RE.java 25 Jul 2006 14:34:51 -0000
1.3
+++ classpath/gnu/java/util/regex/RE.java 16 Aug 2006 00:12:59 -0000
@@ -252,6 +252,13 @@
*/
public static final int REG_ICASE_USASCII = 0x0800;
+ /**
+ * Execution flag.
+ * Do not move the position at which the search begins. If not set,
+ * the starting position will be moved until a match is found.
+ */
+ public static final int REG_FIX_STARTING_POSITION = 0x1000;
+
/** Returns a string representing the version of the gnu.regexp package. */
public static final String version() {
return VERSION;
@@ -1643,6 +1650,7 @@
/* Implements abstract method REToken.match() */
boolean match(CharIndexed input, REMatch mymatch) {
+ input.setHitEnd(mymatch);
if (firstToken == null) {
return next(input, mymatch);
}
@@ -1720,15 +1728,23 @@
REMatch getMatchImpl(CharIndexed input, int anchor, int eflags, StringBuffer
buffer) {
boolean tryEntireMatch = ((eflags & REG_TRY_ENTIRE_MATCH) != 0);
+ boolean doMove = ((eflags & REG_FIX_STARTING_POSITION) == 0);
RE re = (tryEntireMatch ? (RE) this.clone() : this);
if (tryEntireMatch) {
- re.chain(new RETokenEnd(0, null));
+ RETokenEnd reEnd = new RETokenEnd(0, null);
+ reEnd.setFake(true);
+ re.chain(reEnd);
}
// Create a new REMatch to hold results
REMatch mymatch = new REMatch(numSubs, anchor, eflags);
do {
+ /* The following potimization is commented out because
+ the matching should be tried even if the length of
+ input is obviously too short in order that
+ java.util.regex.Matcher#hitEnd() may work correctly.
// Optimization: check if anchor + minimumLength > length
if (minimumLength == 0 || input.charAt(minimumLength-1) !=
CharIndexed.OUT_OF_BOUNDS) {
+ */
if (re.match(input, mymatch)) {
REMatch best = mymatch;
// We assume that the match that coms first is the best.
@@ -1749,13 +1765,17 @@
input.setLastMatch(best);
return best;
}
- }
+ /* End of the optimization commented out
+ }
+ */
mymatch.clear(++anchor);
// Append character to buffer if needed
if (buffer != null && input.charAt(0) != CharIndexed.OUT_OF_BOUNDS) {
buffer.append(input.charAt(0));
}
- } while (input.move(1));
+ // java.util.regex.Matcher#hitEnd() requires that the search should
+ // be tried at the end of input, so we use move1(1) instead of move(1)
+ } while (doMove && input.move1(1));
// Special handling at end of input for e.g. "$"
if (minimumLength == 0) {
Index: classpath/gnu/java/util/regex/REMatch.java
===================================================================
RCS file: /cvsroot/classpath/classpath/gnu/java/util/regex/REMatch.java,v
retrieving revision 1.1
diff -u -r1.1 REMatch.java
--- classpath/gnu/java/util/regex/REMatch.java 7 Jun 2006 19:30:06 -0000
1.1
+++ classpath/gnu/java/util/regex/REMatch.java 16 Aug 2006 00:12:59 -0000
@@ -307,12 +307,12 @@
}
/* The following are used for debugging purpose
- static String d(REMatch m) {
+ public static String d(REMatch m) {
if (m == null) return "null";
else return "[" + m.index + "]";
}
- String substringUptoIndex(CharIndexed input) {
+ public String substringUptoIndex(CharIndexed input) {
StringBuffer sb = new StringBuffer();
for (int i = 0; i < index; i++) {
sb.append(input.charAt(i));
Index: classpath/gnu/java/util/regex/REToken.java
===================================================================
RCS file: /cvsroot/classpath/classpath/gnu/java/util/regex/REToken.java,v
retrieving revision 1.1
diff -u -r1.1 REToken.java
--- classpath/gnu/java/util/regex/REToken.java 7 Jun 2006 19:30:06 -0000
1.1
+++ classpath/gnu/java/util/regex/REToken.java 16 Aug 2006 00:12:59 -0000
@@ -72,6 +72,16 @@
/** Returns true if the match succeeded, false if it failed. */
boolean match(CharIndexed input, REMatch mymatch) {
+ return match(input, mymatch, false);
+ }
+ boolean matchFake(CharIndexed input, REMatch mymatch) {
+ return match(input, mymatch, true);
+ }
+
+ private boolean match(CharIndexed input, REMatch mymatch, boolean fake) {
+ if (!fake) {
+ setHitEnd(input, mymatch);
+ }
REMatch m = matchThis(input, mymatch);
if (m == null) return false;
if (next(input, m)) {
@@ -81,6 +91,11 @@
return false;
}
+ /** Sets whether the matching occurs at the end of input */
+ void setHitEnd(CharIndexed input, REMatch mymatch) {
+ input.setHitEnd(mymatch);
+ }
+
/** Returns true if the match succeeded, false if it failed.
* The matching is done against this REToken only. Chained
* tokens are not checked.
Index: classpath/gnu/java/util/regex/RETokenChar.java
===================================================================
RCS file: /cvsroot/classpath/classpath/gnu/java/util/regex/RETokenChar.java,v
retrieving revision 1.1
diff -u -r1.1 RETokenChar.java
--- classpath/gnu/java/util/regex/RETokenChar.java 7 Jun 2006 19:30:06
-0000 1.1
+++ classpath/gnu/java/util/regex/RETokenChar.java 16 Aug 2006 00:12:59
-0000
@@ -58,15 +58,20 @@
}
REMatch matchThis(CharIndexed input, REMatch mymatch) {
- int z = ch.length;
if (matchOneString(input, mymatch.index)) {
- mymatch.index += z;
+ mymatch.index += matchedLength;
return mymatch;
}
+ // java.util.regex.Matcher#hitEnd() requires that the length of
+ // partial match be counted.
+ mymatch.index += matchedLength;
+ input.setHitEnd(mymatch);
return null;
}
- boolean matchOneString(CharIndexed input, int index) {
+ private int matchedLength;
+ private boolean matchOneString(CharIndexed input, int index) {
+ matchedLength = 0;
int z = ch.length;
char c;
for (int i=0; i<z; i++) {
@@ -74,6 +79,7 @@
if (! charEquals(c, ch[i])) {
return false;
}
+ ++matchedLength;
}
return true;
}
Index: classpath/gnu/java/util/regex/RETokenEnd.java
===================================================================
RCS file: /cvsroot/classpath/classpath/gnu/java/util/regex/RETokenEnd.java,v
retrieving revision 1.2
diff -u -r1.2 RETokenEnd.java
--- classpath/gnu/java/util/regex/RETokenEnd.java 25 Jul 2006 14:34:51
-0000 1.2
+++ classpath/gnu/java/util/regex/RETokenEnd.java 16 Aug 2006 00:12:59
-0000
@@ -45,6 +45,12 @@
private String newline;
private boolean check_java_line_terminators;
+ /**
+ * Indicates whether this token is a real one generated at compile time,
+ * or a fake one temporarily added by RE#getMatchImpl.
+ */
+ private boolean fake = false;
+
RETokenEnd(int subIndex,String newline) {
super(subIndex);
this.newline = newline;
@@ -57,10 +63,19 @@
this.check_java_line_terminators = b;
}
+ void setFake(boolean fake) {
+ this.fake = fake;
+ }
+
int getMaximumLength() {
return 0;
}
+ boolean match(CharIndexed input, REMatch mymatch) {
+ if (!fake) return super.match(input, mymatch);
+ return super.matchFake(input, mymatch);
+ }
+
REMatch matchThis(CharIndexed input, REMatch mymatch) {
char ch = input.charAt(mymatch.index);
if (ch == CharIndexed.OUT_OF_BOUNDS)
Index: classpath/gnu/java/util/regex/RETokenEndSub.java
===================================================================
RCS file: /cvsroot/classpath/classpath/gnu/java/util/regex/RETokenEndSub.java,v
retrieving revision 1.1
diff -u -r1.1 RETokenEndSub.java
--- classpath/gnu/java/util/regex/RETokenEndSub.java 7 Jun 2006 19:30:06
-0000 1.1
+++ classpath/gnu/java/util/regex/RETokenEndSub.java 16 Aug 2006 00:12:59
-0000
@@ -58,6 +58,10 @@
return super.findMatch(input, mymatch);
}
+ void setHitEnd(CharIndexed input, REMatch mymatch) {
+ // Do nothing
+ }
+
void dump(StringBuffer os) {
// handled by RE
// But add something for debugging.
Index: classpath/gnu/java/util/regex/RETokenOneOf.java
===================================================================
RCS file: /cvsroot/classpath/classpath/gnu/java/util/regex/RETokenOneOf.java,v
retrieving revision 1.1
diff -u -r1.1 RETokenOneOf.java
--- classpath/gnu/java/util/regex/RETokenOneOf.java 7 Jun 2006 19:30:06
-0000 1.1
+++ classpath/gnu/java/util/regex/RETokenOneOf.java 16 Aug 2006 00:12:59
-0000
@@ -120,6 +120,7 @@
}
boolean match(CharIndexed input, REMatch mymatch) {
+ setHitEnd(input, mymatch);
if (matchesOneChar) return matchOneChar(input, mymatch);
else return matchOneRE(input, mymatch);
}
Index: classpath/gnu/java/util/regex/RETokenRepeated.java
===================================================================
RCS file:
/cvsroot/classpath/classpath/gnu/java/util/regex/RETokenRepeated.java,v
retrieving revision 1.1
diff -u -r1.1 RETokenRepeated.java
--- classpath/gnu/java/util/regex/RETokenRepeated.java 7 Jun 2006 19:30:06
-0000 1.1
+++ classpath/gnu/java/util/regex/RETokenRepeated.java 16 Aug 2006 00:12:59
-0000
@@ -318,6 +318,7 @@
}
boolean match(CharIndexed input, REMatch mymatch) {
+ setHitEnd(input, mymatch);
REMatch m1 = findMatch(input, mymatch);
if (m1 != null) {
mymatch.assignFrom(m1);
Index: classpath/java/util/regex/Matcher.java
===================================================================
RCS file: /cvsroot/classpath/classpath/java/util/regex/Matcher.java,v
retrieving revision 1.17
diff -u -r1.17 Matcher.java
--- classpath/java/util/regex/Matcher.java 7 Jun 2006 19:30:06 -0000
1.17
+++ classpath/java/util/regex/Matcher.java 16 Aug 2006 00:12:59 -0000
@@ -218,7 +218,7 @@
public boolean lookingAt ()
{
- match = pattern.getRE().getMatch(inputCharIndexed, 0);
+ match = pattern.getRE().getMatch(inputCharIndexed, 0,
RE.REG_FIX_STARTING_POSITION, null);
if (match != null)
{
if (match.getStartIndex() == 0)
@@ -243,7 +243,7 @@
*/
public boolean matches ()
{
- match = pattern.getRE().getMatch(inputCharIndexed, 0,
RE.REG_TRY_ENTIRE_MATCH);
+ match = pattern.getRE().getMatch(inputCharIndexed, 0,
RE.REG_TRY_ENTIRE_MATCH|RE.REG_FIX_STARTING_POSITION, null);
if (match != null)
{
if (match.getStartIndex() == 0)
@@ -309,6 +309,28 @@
return match.getStartIndex(group);
}
+ /**
+ * @return True if and only if the matcher hit the end of input.
+ */
+ public boolean hitEnd()
+ {
+ return inputCharIndexed.hitEnd();
+ }
+
+ /**
+ * @return A string expression of this matcher.
+ */
+ public String toString()
+ {
+ StringBuilder sb = new StringBuilder();
+ sb.append(this.getClass().getName())
+ .append("[pattern=").append(pattern.pattern())
+ .append(" region=").append("0").append(",").append(input.length())
+ .append(" lastmatch=").append(match == null ? "" : match.toString())
+ .append("]");
+ return sb.toString();
+ }
+
private void assertMatchOp()
{
if (match == null) throw new IllegalStateException();
