org.apache.lucene.analysis.ar.ArabicAnalyzer Maven / Gradle / Ivy
package org.apache.lucene.analysis.ar;
/*
* 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.
*/
import java.io.IOException;
import java.io.Reader;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.core.LowerCaseFilter;
import org.apache.lucene.analysis.core.StopFilter;
import org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter;
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.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.util.Version;
/**
* {@link Analyzer} for Arabic.
*
* This analyzer implements light-stemming as specified by:
*
* Light Stemming for Arabic Information Retrieval
*
* http://www.mtholyoke.edu/~lballest/Pubs/arab_stem05.pdf
*
* The analysis package contains three primary components:
*
* - {@link ArabicNormalizationFilter}: Arabic orthographic normalization.
*
- {@link ArabicStemFilter}: Arabic light stemming
*
- Arabic stop words file: a set of default Arabic stop words.
*
*
*/
public final class ArabicAnalyzer extends StopwordAnalyzerBase {
/**
* File containing default Arabic stopwords.
*
* Default stopword list is from http://members.unine.ch/jacques.savoy/clef/index.html
* The stopword list is BSD-Licensed.
*/
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;
}
/**
* 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, ArabicAnalyzer.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");
}
}
}
private final CharArraySet stemExclusionSet;
/**
* Builds an analyzer with the default stop words: {@link #DEFAULT_STOPWORD_FILE}.
*/
public ArabicAnalyzer(Version matchVersion) {
this(matchVersion, DefaultSetHolder.DEFAULT_STOP_SET);
}
/**
* Builds an analyzer with the given stop words
*
* @param matchVersion
* lucene compatibility version
* @param stopwords
* a stopword set
*/
public ArabicAnalyzer(Version matchVersion, CharArraySet stopwords){
this(matchVersion, stopwords, CharArraySet.EMPTY_SET);
}
/**
* Builds an analyzer with the given stop word. If a none-empty stem exclusion set is
* provided this analyzer will add a {@link SetKeywordMarkerFilter} before
* {@link ArabicStemFilter}.
*
* @param matchVersion
* lucene compatibility version
* @param stopwords
* a stopword set
* @param stemExclusionSet
* a set of terms not to be stemmed
*/
public ArabicAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionSet){
super(matchVersion, stopwords);
this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(
matchVersion, stemExclusionSet));
}
/**
* 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 an {@link StandardTokenizer} filtered with
* {@link LowerCaseFilter}, {@link StopFilter},
* {@link ArabicNormalizationFilter}, {@link SetKeywordMarkerFilter}
* if a stem exclusion set is provided and {@link ArabicStemFilter}.
*/
@Override
protected TokenStreamComponents createComponents(String fieldName,
Reader reader) {
final Tokenizer source = matchVersion.onOrAfter(Version.LUCENE_3_1) ?
new StandardTokenizer(matchVersion, reader) : new ArabicLetterTokenizer(matchVersion, reader);
TokenStream result = new LowerCaseFilter(matchVersion, source);
// the order here is important: the stopword list is not normalized!
result = new StopFilter( matchVersion, result, stopwords);
// TODO maybe we should make ArabicNormalization filter also KeywordAttribute aware?!
result = new ArabicNormalizationFilter(result);
if(!stemExclusionSet.isEmpty()) {
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
}
return new TokenStreamComponents(source, new ArabicStemFilter(result));
}
}