home | career | drupal | java | mac | mysql | perl | scala | uml | unix  

Lucene example source code file (HindiAnalyzer.java)

This example Lucene source code file (HindiAnalyzer.java) is included in the DevDaily.com "Java Source Code Warehouse" project. The intent of this project is to help you "Learn Java by Example" TM.

Java - Lucene tags/keywords

default_stop_set, default_stopword_file, hindianalyzer, hindianalyzer, indicnormalizationfilter, io, reader, set, set, stopfilter, stopwords_comment, stopwords_comment, string, string, tokenstreamcomponents, util

The Lucene HindiAnalyzer.java source code

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 java.util.Set;

import org.apache.lucene.analysis.LowerCaseFilter;
import org.apache.lucene.analysis.CharArraySet;
import org.apache.lucene.analysis.KeywordMarkerFilter;
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.in.IndicNormalizationFilter;
import org.apache.lucene.analysis.in.IndicTokenizer;
import org.apache.lucene.util.Version;

/**
 * Analyzer for Hindi.
 */
public final class HindiAnalyzer extends StopwordAnalyzerBase {
  private final Set<?> 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 Set<?> 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 Set<?> 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, Set<?> stopwords, Set 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, Set<?> 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.ReusableAnalyzerBase.TokenStreamComponents}
   * used to tokenize all the text in the provided {@link Reader}.
   * 
   * @return {@link org.apache.lucene.analysis.ReusableAnalyzerBase.TokenStreamComponents}
   *         built from a {@link IndicTokenizer} filtered with
   *         {@link LowerCaseFilter}, {@link IndicNormalizationFilter},
   *         {@link HindiNormalizationFilter}, {@link KeywordMarkerFilter}
   *         if a stem exclusion set is provided, {@link HindiStemFilter}, and
   *         Hindi Stop words
   */
  @Override
  protected TokenStreamComponents createComponents(String fieldName,
      Reader reader) {
    final Tokenizer source = new IndicTokenizer(matchVersion, reader);
    TokenStream result = new LowerCaseFilter(matchVersion, source);
    if (!stemExclusionSet.isEmpty())
      result = new KeywordMarkerFilter(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);
  }
}

Other Lucene examples (source code examples)

Here is a short list of links related to this Lucene HindiAnalyzer.java source code file:



my book on functional programming

 

new blog posts

 

Copyright 1998-2019 Alvin Alexander, alvinalexander.com
All Rights Reserved.

A percentage of advertising revenue from
pages under the /java/jwarehouse URI on this website is
paid back to open source projects.