You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by rm...@apache.org on 2013/02/26 22:32:49 UTC
svn commit: r1450443 - in /lucene/dev/branches/branch_4x: ./ lucene/
lucene/test-framework/
lucene/test-framework/src/java/org/apache/lucene/analysis/MockTokenizer.java
Author: rmuir
Date: Tue Feb 26 21:32:49 2013
New Revision: 1450443
URL: http://svn.apache.org/r1450443
Log:
add back cjk range to this regex
Modified:
lucene/dev/branches/branch_4x/ (props changed)
lucene/dev/branches/branch_4x/lucene/ (props changed)
lucene/dev/branches/branch_4x/lucene/test-framework/ (props changed)
lucene/dev/branches/branch_4x/lucene/test-framework/src/java/org/apache/lucene/analysis/MockTokenizer.java
Modified: lucene/dev/branches/branch_4x/lucene/test-framework/src/java/org/apache/lucene/analysis/MockTokenizer.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/test-framework/src/java/org/apache/lucene/analysis/MockTokenizer.java?rev=1450443&r1=1450442&r2=1450443&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/test-framework/src/java/org/apache/lucene/analysis/MockTokenizer.java (original)
+++ lucene/dev/branches/branch_4x/lucene/test-framework/src/java/org/apache/lucene/analysis/MockTokenizer.java Tue Feb 26 21:32:49 2013
@@ -53,7 +53,7 @@ public class MockTokenizer extends Token
/** Acts like LetterTokenizer. */
// the ugly regex below is incomplete Unicode 5.2 [:Letter:]
public static final CharacterRunAutomaton SIMPLE =
- new CharacterRunAutomaton(new RegExp("[A-Za-zªµºÃ-ÃÃ-öø-Ë]+").toAutomaton());
+ new CharacterRunAutomaton(new RegExp("[A-Za-zªµºÃ-ÃÃ-öø-Ëä¸-é¿]+").toAutomaton());
private final CharacterRunAutomaton runAutomaton;
private final boolean lowerCase;