org.apache.lucene.collation.CollationAttributeFactory Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of lucene-analysis-common Show documentation
Apache Lucene (module: common)
There is a newer version: 10.1.0
Show newest version
/*
 * 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.collation;

import java.text.Collator;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.collation.tokenattributes.CollatedTermAttributeImpl;
import org.apache.lucene.util.AttributeFactory;

/**
 * Converts each token into its {@link java.text.CollationKey}, and then encodes the bytes 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. Since {@link
 * java.text.RuleBasedCollator}s are not independently versioned, it is unsafe to search against
 * stored CollationKeys unless 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):
 *
 * 

 *   JVM vendor
 *   
JVM version, including patch version
 *   
The language (and country and variant, if specified) of the Locale used when constructing
 *       the collator via {@link Collator#getInstance(java.util.Locale)}.
 *   
The collation strength used - see {@link Collator#setStrength(int)}
 * 
 *
 * The ICUCollationAttributeFactory in the analysis-icu package uses ICU4J's
 * Collator, which makes its version available, thus allowing collation to be versioned
 * independently from the JVM. ICUCollationAttributeFactory is also significantly faster and
 * generates significantly shorter keys than CollationAttributeFactory. 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.
 *
 * CollationKeys generated by java.text.Collators are not compatible with those those generated
 * by ICU Collators. Specifically, if you use CollationAttributeFactory to generate index terms, do
 * not use ICUCollationAttributeFactory on the query side, or vice versa.
 */
public class CollationAttributeFactory
    extends AttributeFactory.StaticImplementationAttributeFactory {
  private final Collator collator;

  /**
   * Create a CollationAttributeFactory, using {@link TokenStream#DEFAULT_TOKEN_ATTRIBUTE_FACTORY}
   * as the factory for all other attributes.
   *
   * @param collator CollationKey generator
   */
  public CollationAttributeFactory(Collator collator) {
    this(TokenStream.DEFAULT_TOKEN_ATTRIBUTE_FACTORY, collator);
  }

  /**
   * Create a CollationAttributeFactory, using the supplied Attribute Factory as the factory for all
   * other attributes.
   *
   * @param delegate Attribute Factory
   * @param collator CollationKey generator
   */
  public CollationAttributeFactory(AttributeFactory delegate, Collator collator) {
    super(delegate, CollatedTermAttributeImpl.class);
    this.collator = collator;
  }

  @Override
  public CollatedTermAttributeImpl createInstance() {
    return new CollatedTermAttributeImpl(collator);
  }
}