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

org.apache.lucene.analysis.th.ThaiAnalyzer Maven / Gradle / Ivy

There is a newer version: 8.11.3
Show newest version
package org.apache.lucene.analysis.th;

/**
 * Copyright 2006 The Apache Software Foundation
 *
 * Licensed 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.io.IOException;
import java.io.Reader;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.LowerCaseFilter;
import org.apache.lucene.analysis.core.StopAnalyzer;
import org.apache.lucene.analysis.core.StopFilter;
import org.apache.lucene.analysis.standard.StandardFilter;
import org.apache.lucene.analysis.standard.StandardTokenizer;
import org.apache.lucene.analysis.util.CharArraySet;
import org.apache.lucene.analysis.util.StopwordAnalyzerBase;
import org.apache.lucene.util.Version;

/**
 * {@link Analyzer} for Thai language. It uses {@link java.text.BreakIterator} to break words.
 * 

* *

You must specify the required {@link Version} * compatibility when creating ThaiAnalyzer: *

*/ public final class ThaiAnalyzer extends StopwordAnalyzerBase { /** File containing default Thai stopwords. */ public final static String DEFAULT_STOPWORD_FILE = "stopwords.txt"; /** * The comment character in the stopwords file. * All lines prefixed with this will be ignored. */ private static final String STOPWORDS_COMMENT = "#"; /** * Returns an unmodifiable instance of the default stop words set. * @return default stop words set. */ public static CharArraySet getDefaultStopSet(){ return DefaultSetHolder.DEFAULT_STOP_SET; } /** * Atomically loads the DEFAULT_STOP_SET in a lazy fashion once the outer class * accesses the static final set the first time.; */ private static class DefaultSetHolder { static final CharArraySet DEFAULT_STOP_SET; static { try { DEFAULT_STOP_SET = loadStopwordSet(false, ThaiAnalyzer.class, DEFAULT_STOPWORD_FILE, STOPWORDS_COMMENT); } 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 with the default stop words. * * @param matchVersion lucene compatibility version */ public ThaiAnalyzer(Version matchVersion) { this(matchVersion, matchVersion.onOrAfter(Version.LUCENE_3_6) ? DefaultSetHolder.DEFAULT_STOP_SET : StopAnalyzer.ENGLISH_STOP_WORDS_SET); } /** * Builds an analyzer with the given stop words. * * @param matchVersion lucene compatibility version * @param stopwords a stopword set */ public ThaiAnalyzer(Version matchVersion, CharArraySet stopwords) { super(matchVersion, stopwords); } /** * Creates * {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents} * used to tokenize all the text in the provided {@link Reader}. * * @return {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents} * built from a {@link StandardTokenizer} filtered with * {@link StandardFilter}, {@link LowerCaseFilter}, {@link ThaiWordFilter}, and * {@link StopFilter} */ @Override protected TokenStreamComponents createComponents(String fieldName, Reader reader) { if (matchVersion.onOrAfter(Version.LUCENE_4_8)) { final Tokenizer source = new ThaiTokenizer(reader); TokenStream result = new LowerCaseFilter(matchVersion, source); result = new StopFilter(matchVersion, result, stopwords); return new TokenStreamComponents(source, result); } else { final Tokenizer source = new StandardTokenizer(matchVersion, reader); TokenStream result = new StandardFilter(matchVersion, source); if (matchVersion.onOrAfter(Version.LUCENE_3_1)) result = new LowerCaseFilter(matchVersion, result); result = new ThaiWordFilter(matchVersion, result); return new TokenStreamComponents(source, new StopFilter(matchVersion, result, stopwords)); } } }




© 2015 - 2024 Weber Informatics LLC | Privacy Policy