org.apache.lucene.analysis.icu.ICUCollationKeyAnalyzer Maven / Gradle / Ivy
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF 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.apache.lucene.analysis.icu;
import com.ibm.icu.text.Collator;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.core.KeywordTokenizer;
import org.apache.lucene.collation.CollationKeyAnalyzer;
/**
* Configures {@link KeywordTokenizer} with {@link ICUCollationAttributeFactory}.
*
* Converts the token into its {@link com.ibm.icu.text.CollationKey}, and then encodes the
* CollationKey directly to allow it to be stored as an index term.
*
*
WARNING: Make sure you use exactly the same Collator at index and query time
* -- CollationKeys are only comparable when produced by the same Collator. {@link
* com.ibm.icu.text.RuleBasedCollator}s are independently versioned, so it is safe to search against
* stored CollationKeys if the following are exactly the same (best practice is to store this
* information with the index and check that they remain the same at query time):
*
*
* - Collator version - see {@link Collator#getVersion()}
*
- The collation strength used - see {@link Collator#setStrength(int)}
*
*
* CollationKeys generated by ICU Collators are not compatible with those generated by
* java.text.Collators. Specifically, if you use ICUCollationKeyAnalyzer to generate index terms, do
* not use {@link CollationKeyAnalyzer} on the query side, or vice versa.
*
*
ICUCollationKeyAnalyzer is significantly faster and generates significantly shorter keys than
* CollationKeyAnalyzer. See http://site.icu-project.org/charts/collation-icu4j-sun for key generation timing and key
* length comparisons between ICU4J and java.text.Collator over several languages.
*
* @since 3.1
*/
public final class ICUCollationKeyAnalyzer extends Analyzer {
private final ICUCollationAttributeFactory factory;
/**
* Create a new ICUCollationKeyAnalyzer, using the specified collator.
*
* @param collator CollationKey generator
*/
public ICUCollationKeyAnalyzer(Collator collator) {
this.factory = new ICUCollationAttributeFactory(collator);
}
@Override
protected TokenStreamComponents createComponents(String fieldName) {
KeywordTokenizer tokenizer =
new KeywordTokenizer(factory, KeywordTokenizer.DEFAULT_BUFFER_SIZE);
return new TokenStreamComponents(tokenizer, tokenizer);
}
}