You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@jackrabbit.apache.org by mr...@apache.org on 2011/06/30 23:07:21 UTC
svn commit: r1141717 - in /jackrabbit/trunk/jackrabbit-core/src:
main/java/org/apache/jackrabbit/core/query/lucene/JackrabbitQueryParser.java
test/java/org/apache/jackrabbit/core/query/FulltextQueryTest.java
Author: mreutegg
Date: Thu Jun 30 21:07:20 2011
New Revision: 1141717
URL: http://svn.apache.org/viewvc?rev=1141717&view=rev
Log:
JCR-3009: Prefix fulltext queries with Japanese or Chinese characters fail to match
Modified:
jackrabbit/trunk/jackrabbit-core/src/main/java/org/apache/jackrabbit/core/query/lucene/JackrabbitQueryParser.java
jackrabbit/trunk/jackrabbit-core/src/test/java/org/apache/jackrabbit/core/query/FulltextQueryTest.java
Modified: jackrabbit/trunk/jackrabbit-core/src/main/java/org/apache/jackrabbit/core/query/lucene/JackrabbitQueryParser.java
URL: http://svn.apache.org/viewvc/jackrabbit/trunk/jackrabbit-core/src/main/java/org/apache/jackrabbit/core/query/lucene/JackrabbitQueryParser.java?rev=1141717&r1=1141716&r2=1141717&view=diff
==============================================================================
--- jackrabbit/trunk/jackrabbit-core/src/main/java/org/apache/jackrabbit/core/query/lucene/JackrabbitQueryParser.java (original)
+++ jackrabbit/trunk/jackrabbit-core/src/main/java/org/apache/jackrabbit/core/query/lucene/JackrabbitQueryParser.java Thu Jun 30 21:07:20 2011
@@ -16,10 +16,19 @@
*/
package org.apache.jackrabbit.core.query.lucene;
+import java.io.IOException;
+import java.io.StringReader;
import java.util.List;
import java.util.ArrayList;
+import javax.xml.stream.events.EndDocument;
+
import org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.analysis.Token;
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.Tokenizer;
+import org.apache.lucene.analysis.standard.StandardTokenizer;
+import org.apache.lucene.analysis.tokenattributes.TypeAttribute;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.search.Query;
@@ -149,7 +158,33 @@ public class JackrabbitQueryParser exten
*/
protected Query getPrefixQuery(String field, String termStr)
throws ParseException {
- return getWildcardQuery(field, termStr + "*");
+ // only create a prefix query when the term is a single word / token
+ Analyzer a = getAnalyzer();
+ TokenStream ts = a.tokenStream(field, new StringReader(termStr));
+ int count = 0;
+ boolean isCJ = false;
+ try {
+ TypeAttribute t = ts.addAttribute(TypeAttribute.class);
+ ts.reset();
+ while (ts.incrementToken()) {
+ count++;
+ isCJ = StandardTokenizer.TOKEN_TYPES[StandardTokenizer.CJ].equals(t.type());
+ }
+ ts.end();
+ } catch (IOException e) {
+ throw new ParseException(e.getMessage());
+ } finally {
+ try {
+ ts.close();
+ } catch (IOException e) {
+ // ignore
+ }
+ }
+ if (count > 1 && isCJ) {
+ return getFieldQuery(field, termStr);
+ } else {
+ return getWildcardQuery(field, termStr + "*");
+ }
}
/**
Modified: jackrabbit/trunk/jackrabbit-core/src/test/java/org/apache/jackrabbit/core/query/FulltextQueryTest.java
URL: http://svn.apache.org/viewvc/jackrabbit/trunk/jackrabbit-core/src/test/java/org/apache/jackrabbit/core/query/FulltextQueryTest.java?rev=1141717&r1=1141716&r2=1141717&view=diff
==============================================================================
--- jackrabbit/trunk/jackrabbit-core/src/test/java/org/apache/jackrabbit/core/query/FulltextQueryTest.java (original)
+++ jackrabbit/trunk/jackrabbit-core/src/test/java/org/apache/jackrabbit/core/query/FulltextQueryTest.java Thu Jun 30 21:07:20 2011
@@ -263,6 +263,12 @@ public class FulltextQueryTest extends A
}
+ public void testMultiByte() throws RepositoryException {
+ String content = "some text with multi byte \u7530\u4e2d characters.";
+
+ executeContainsQuery("\u7530\u4e2d*", content, true);
+ }
+
public void testPredefinedEntityReference() throws RepositoryException {
String content = "Max&Moritz";