org.elasticsearch.index.analysis.KeepWordFilterFactory Maven / Gradle / Ivy
package org.elasticsearch.index.analysis;
/*
* Licensed to ElasticSearch and Shay Banon 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.
*/
import java.util.Arrays;
import java.util.Map;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.miscellaneous.KeepWordFilter;
import org.apache.lucene.analysis.util.CharArraySet;
import org.elasticsearch.ElasticSearchIllegalArgumentException;
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 org.elasticsearch.indices.analysis.IndicesAnalysisService;
/**
* A {@link TokenFilterFactory} for {@link KeepWordFilter}. This filter only
* keep tokens that are contained in the term set configured via
* {@value #KEEP_WORDS_KEY} setting. This filter acts like an inverse stop
* filter.
*
* Configuration options:
*
*
* - {@value #KEEP_WORDS_KEY} the array of words / tokens to keep.
*
* - {@value #KEEP_WORDS_PATH_KEY} an reference to a file containing the words
* / tokens to keep. Note: this is an alternative to {@value #KEEP_WORDS_KEY} if
* both are set an exception will be thrown.
*
* - {@value #ENABLE_POS_INC_KEY}
true iff the filter should
* maintain position increments for dropped tokens. The default is
* true.
*
* - {@value #KEEP_WORDS_CASE_KEY} to use case sensitive keep words. The
* default is
false which corresponds to case-sensitive.
*
*
* @see StopTokenFilterFactory
*
*/
@AnalysisSettingsRequired
public class KeepWordFilterFactory extends AbstractTokenFilterFactory {
private Boolean enablePositionIncrements;
private CharArraySet keepWords;
private static final String KEEP_WORDS_KEY = "keep_words";
private static final String KEEP_WORDS_PATH_KEY = KEEP_WORDS_KEY + "_path";
private static final String KEEP_WORDS_CASE_KEY = KEEP_WORDS_KEY + "_case"; // for javadoc
private static final String ENABLE_POS_INC_KEY = "enable_position_increments";
@Inject
public KeepWordFilterFactory(Index index, @IndexSettings Settings indexSettings,
Environment env, IndicesAnalysisService indicesAnalysisService, Map tokenizerFactories,
@Assisted String name, @Assisted Settings settings) {
super(index, indexSettings, name, settings);
final String[] arrayKeepWords = settings.getAsArray(KEEP_WORDS_KEY);
final String keepWordsPath = settings.get(KEEP_WORDS_PATH_KEY, null);
if (!(arrayKeepWords == null ^ keepWordsPath == null)) {
// we don't allow both or non
throw new ElasticSearchIllegalArgumentException("keep requires either `" + KEEP_WORDS_KEY + "` or `"
+ KEEP_WORDS_PATH_KEY + "` to be configured");
}
this.enablePositionIncrements = settings.getAsBoolean(ENABLE_POS_INC_KEY, true);
this.keepWords = Analysis.getWordSet(env, settings, KEEP_WORDS_KEY, version);
}
@Override
public TokenStream create(TokenStream tokenStream) {
return new KeepWordFilter(enablePositionIncrements, tokenStream, keepWords);
}
}