All Downloads are FREE. Search and download functionalities are using the official Maven repository.

org.apache.lucene.analysis.cjk.CJKAnalyzer Maven / Gradle / Ivy

There is a newer version: 8.11.4
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.analysis.cjk;


import java.io.IOException;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.CharArraySet;
import org.apache.lucene.analysis.LowerCaseFilter;
import org.apache.lucene.analysis.StopFilter;
import org.apache.lucene.analysis.StopwordAnalyzerBase;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.standard.StandardTokenizer;

/**
 * An {@link Analyzer} that tokenizes text with {@link StandardTokenizer},
 * normalizes content with {@link CJKWidthFilter}, folds case with
 * {@link LowerCaseFilter}, forms bigrams of CJK with {@link CJKBigramFilter},
 * and filters stopwords with {@link StopFilter}
 *
 * @since 3.1
 */
public final class CJKAnalyzer extends StopwordAnalyzerBase {

  /**
   * File containing default CJK stopwords.
   * 

* Currently it contains some common English words that are not usually * useful for searching and some double-byte interpunctions. */ public final static String DEFAULT_STOPWORD_FILE = "stopwords.txt"; /** * Returns an unmodifiable instance of the default stop-words set. * @return an unmodifiable instance of the default stop-words set. */ public static CharArraySet getDefaultStopSet(){ return DefaultSetHolder.DEFAULT_STOP_SET; } private static class DefaultSetHolder { static final CharArraySet DEFAULT_STOP_SET; static { try { DEFAULT_STOP_SET = loadStopwordSet(false, CJKAnalyzer.class, DEFAULT_STOPWORD_FILE, "#"); } catch (IOException ex) { // default set should always be present as it is part of the // distribution (JAR) throw new RuntimeException("Unable to load default stopword set"); } } } /** * Builds an analyzer which removes words in {@link #getDefaultStopSet()}. */ public CJKAnalyzer() { this(DefaultSetHolder.DEFAULT_STOP_SET); } /** * Builds an analyzer with the given stop words * * @param stopwords * a stopword set */ public CJKAnalyzer(CharArraySet stopwords){ super(stopwords); } @Override protected TokenStreamComponents createComponents(String fieldName) { final Tokenizer source = new StandardTokenizer(); // run the widthfilter first before bigramming, it sometimes combines characters. TokenStream result = new CJKWidthFilter(source); result = new LowerCaseFilter(result); result = new CJKBigramFilter(result); return new TokenStreamComponents(source, new StopFilter(result, stopwords)); } @Override protected TokenStream normalize(String fieldName, TokenStream in) { TokenStream result = new CJKWidthFilter(in); result = new LowerCaseFilter(result); return result; } }





© 2015 - 2024 Weber Informatics LLC | Privacy Policy