/*
* 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.CharArraySet;
import org.apache.lucene.analysis.StopFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.ja.JapaneseAnalyzer;
import org.apache.lucene.search.suggest.analyzing.SuggestStopFilter;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.env.Environment;
import org.elasticsearch.index.IndexSettings;
import java.util.Map;
import java.util.Set;
import static java.util.Collections.singletonMap;
public class JapaneseStopTokenFilterFactory extends AbstractTokenFilterFactory{
private static final Map<String, Set<?>> NAMED_STOP_WORDS = singletonMap("_japanese_", JapaneseAnalyzer.getDefaultStopSet());
private final CharArraySet stopWords;
private final boolean ignoreCase;
private final boolean removeTrailing;
public JapaneseStopTokenFilterFactory(IndexSettings indexSettings, Environment env, String name, Settings settings) {
super(indexSettings, name, settings);
this.ignoreCase = settings.getAsBooleanLenientForPreEs6Indices(indexSettings.getIndexVersionCreated(), "ignore_case", false, deprecationLogger);
this.removeTrailing = settings
.getAsBooleanLenientForPreEs6Indices(indexSettings.getIndexVersionCreated(), "remove_trailing", true, deprecationLogger);
this.stopWords = Analysis.parseWords(env, settings, "stopwords", JapaneseAnalyzer.getDefaultStopSet(), NAMED_STOP_WORDS, ignoreCase);
}
@Override
public TokenStream create(TokenStream tokenStream) {
if (removeTrailing) {
return new StopFilter(tokenStream, stopWords);
} else {
return new SuggestStopFilter(tokenStream, stopWords);
}
}
public Set<?> stopWords() {
return stopWords;
}
public boolean ignoreCase() {
return ignoreCase;
}
}