org.apache.lucene.analysis.hi.HindiAnalyzer Maven / Gradle / Ivy
package org.apache.lucene.analysis.hi;
/*
* 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.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.analysis.core.LowerCaseFilter;
import org.apache.lucene.analysis.core.StopFilter;
import org.apache.lucene.analysis.in.IndicNormalizationFilter;
import org.apache.lucene.analysis.in.IndicTokenizer;
import org.apache.lucene.util.Version;
/**
* Analyzer for Hindi.
* You must specify the required {@link Version}
* compatibility when creating HindiAnalyzer:
*
* - As of 3.6, StandardTokenizer is used for tokenization
*
*/
public final class HindiAnalyzer extends StopwordAnalyzerBase {
private final CharArraySet stemExclusionSet;
/**
* File containing default Hindi 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";
private static final String STOPWORDS_COMMENT = "#";
/**
* 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, HindiAnalyzer.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 given stop words
*
* @param version lucene compatibility version
* @param stopwords a stopword set
* @param stemExclusionSet a stemming exclusion set
*/
public HindiAnalyzer(Version version, CharArraySet stopwords, CharArraySet stemExclusionSet) {
super(version, stopwords);
this.stemExclusionSet = CharArraySet.unmodifiableSet(
CharArraySet.copy(matchVersion, stemExclusionSet));
}
/**
* Builds an analyzer with the given stop words
*
* @param version lucene compatibility version
* @param stopwords a stopword set
*/
public HindiAnalyzer(Version version, CharArraySet stopwords) {
this(version, stopwords, CharArraySet.EMPTY_SET);
}
/**
* Builds an analyzer with the default stop words:
* {@link #DEFAULT_STOPWORD_FILE}.
*/
public HindiAnalyzer(Version version) {
this(version, DefaultSetHolder.DEFAULT_STOP_SET);
}
/**
* 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 LowerCaseFilter}, {@link IndicNormalizationFilter},
* {@link HindiNormalizationFilter}, {@link SetKeywordMarkerFilter}
* if a stem exclusion set is provided, {@link HindiStemFilter}, and
* Hindi Stop words
*/
@Override
protected TokenStreamComponents createComponents(String fieldName,
Reader reader) {
final Tokenizer source;
if (matchVersion.onOrAfter(Version.LUCENE_3_6)) {
source = new StandardTokenizer(matchVersion, reader);
} else {
source = new IndicTokenizer(matchVersion, reader);
}
TokenStream result = new LowerCaseFilter(matchVersion, source);
if (!stemExclusionSet.isEmpty())
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
result = new IndicNormalizationFilter(result);
result = new HindiNormalizationFilter(result);
result = new StopFilter(matchVersion, result, stopwords);
result = new HindiStemFilter(result);
return new TokenStreamComponents(source, result);
}
}