/*
* 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.compound;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.compound.DictionaryCompoundWordTokenFilter;
import org.apache.lucene.analysis.compound.Lucene43DictionaryCompoundWordTokenFilter;
import org.apache.lucene.util.Version;
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.analysis.AnalysisSettingsRequired;
import org.elasticsearch.index.settings.IndexSettings;
/**
* Uses the {@link org.apache.lucene.analysis.compound.DictionaryCompoundWordTokenFilter} to decompound tokens using a dictionary.
*
* @see org.apache.lucene.analysis.compound.DictionaryCompoundWordTokenFilter
*/
@AnalysisSettingsRequired
public class DictionaryCompoundWordTokenFilterFactory extends AbstractCompoundWordTokenFilterFactory {
@Inject
public DictionaryCompoundWordTokenFilterFactory(Index index, @IndexSettings Settings indexSettings, Environment env, @Assisted String name, @Assisted Settings settings) {
super(index, indexSettings, env, name, settings);
}
@Override
public TokenStream create(TokenStream tokenStream) {
if (version.onOrAfter(Version.LUCENE_4_4_0)) {
return new DictionaryCompoundWordTokenFilter(tokenStream, wordList, minWordSize,
minSubwordSize, maxSubwordSize, onlyLongestMatch);
} else {
return new Lucene43DictionaryCompoundWordTokenFilter(tokenStream, wordList, minWordSize,
minSubwordSize, maxSubwordSize, onlyLongestMatch);
}
}
}