-
Notifications
You must be signed in to change notification settings - Fork 34
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
* can use a predefined "_japanese_" stop words
* can not use other predefined stop words
Closes #45
- Loading branch information
Showing
4 changed files
with
110 additions
and
2 deletions.
There are no files selected for viewing
90 changes: 90 additions & 0 deletions
90
src/main/java/org/elasticsearch/index/analysis/JapaneseStopTokenFilterFactory.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,90 @@ | ||
/* | ||
* Licensed to Elasticsearch under one or more contributor | ||
* license agreements. See the NOTICE file distributed with | ||
* this work for additional information regarding copyright | ||
* ownership. Elasticsearch licenses this file to you under | ||
* the Apache License, Version 2.0 (the "License"); you may | ||
* not use this file except in compliance with the License. | ||
* You may obtain a copy of the License at | ||
* | ||
* http://www.apache.org/licenses/LICENSE-2.0 | ||
* | ||
* Unless required by applicable law or agreed to in writing, | ||
* software distributed under the License is distributed on an | ||
* "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY | ||
* KIND, either express or implied. See the License for the | ||
* specific language governing permissions and limitations | ||
* under the License. | ||
*/ | ||
|
||
package org.elasticsearch.index.analysis; | ||
|
||
|
||
import org.apache.lucene.analysis.TokenStream; | ||
import org.apache.lucene.analysis.core.StopFilter; | ||
import org.apache.lucene.analysis.ja.JapaneseAnalyzer; | ||
import org.apache.lucene.analysis.util.CharArraySet; | ||
import org.apache.lucene.search.suggest.analyzing.SuggestStopFilter; | ||
import org.apache.lucene.util.Version; | ||
import org.elasticsearch.ElasticsearchIllegalArgumentException; | ||
import org.elasticsearch.common.collect.ImmutableMap; | ||
import org.elasticsearch.common.collect.MapBuilder; | ||
import org.elasticsearch.common.inject.Inject; | ||
import org.elasticsearch.common.inject.assistedinject.Assisted; | ||
import org.elasticsearch.common.settings.Settings; | ||
import org.elasticsearch.env.Environment; | ||
import org.elasticsearch.index.Index; | ||
import org.elasticsearch.index.settings.IndexSettings; | ||
|
||
import java.util.Set; | ||
|
||
public class JapaneseStopTokenFilterFactory extends AbstractTokenFilterFactory{ | ||
|
||
|
||
private final CharArraySet stopWords; | ||
|
||
private final boolean ignoreCase; | ||
|
||
private final boolean enablePositionIncrements; | ||
private final boolean removeTrailing; | ||
|
||
@Inject | ||
public JapaneseStopTokenFilterFactory(Index index, @IndexSettings Settings indexSettings, Environment env, @Assisted String name, @Assisted Settings settings) { | ||
super(index, indexSettings, name, settings); | ||
this.ignoreCase = settings.getAsBoolean("ignore_case", false); | ||
this.removeTrailing = settings.getAsBoolean("remove_trailing", true); | ||
ImmutableMap<String, Set<?>> namedStopWords = MapBuilder.<String, Set<?>>newMapBuilder() | ||
.put("_japanese_", JapaneseAnalyzer.getDefaultStopSet()) | ||
.immutableMap(); | ||
this.stopWords = Analysis.parseWords(env, settings, "stopwords", JapaneseAnalyzer.getDefaultStopSet(), namedStopWords, version, ignoreCase); | ||
this.enablePositionIncrements = settings.getAsBoolean("enable_position_increments", true); | ||
if (!enablePositionIncrements && version.onOrAfter(Version.LUCENE_44)) { | ||
throw new ElasticsearchIllegalArgumentException("[enable_position_increments: false] is not supported anymore as of Lucene 4.4 as it can create broken token streams." | ||
+ " Please fix your analysis chain or use an older compatibility version (<=4.3) but beware that it might cause unexpected behavior."); | ||
} | ||
} | ||
|
||
@Override | ||
public TokenStream create(TokenStream tokenStream) { | ||
if (removeTrailing) { | ||
StopFilter filter = new StopFilter(version, tokenStream, stopWords); | ||
filter.setEnablePositionIncrements(enablePositionIncrements); | ||
return filter; | ||
} else { | ||
return new SuggestStopFilter(tokenStream, stopWords); | ||
} | ||
} | ||
|
||
public Set<?> stopWords() { | ||
return stopWords; | ||
} | ||
|
||
public boolean ignoreCase() { | ||
return ignoreCase; | ||
} | ||
|
||
public boolean enablePositionIncrements() { | ||
return this.enablePositionIncrements; | ||
} | ||
|
||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters