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

Lucene example source code file (SnowballAnalyzer.java)

This example Lucene source code file (SnowballAnalyzer.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

deprecated, io, override, reader, savedstreams, savedstreams, set, snowballanalyzer, snowballanalyzer, standardtokenizer, stopfilter, string, string, tokenstream, tokenstream, util

The Lucene SnowballAnalyzer.java source code

package org.apache.lucene.analysis.snowball;

/**
 * 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 org.apache.lucene.analysis.*;
import org.apache.lucene.analysis.en.EnglishPossessiveFilter;
import org.apache.lucene.analysis.standard.*;
import org.apache.lucene.analysis.tr.TurkishLowerCaseFilter;
import org.apache.lucene.util.Version;

import java.io.IOException;
import java.io.Reader;
import java.util.Set;

/** Filters {@link StandardTokenizer} with {@link StandardFilter}, {@link
 * LowerCaseFilter}, {@link StopFilter} and {@link SnowballFilter}.
 *
 * Available stemmers are listed in org.tartarus.snowball.ext.  The name of a
 * stemmer is the part of the class name before "Stemmer", e.g., the stemmer in
 * {@link org.tartarus.snowball.ext.EnglishStemmer} is named "English".
 *
 * <p>NOTE: This class uses the same {@link Version}
 * dependent settings as {@link StandardAnalyzer}, with the following addition:
 * <ul>
 *   <li> As of 3.1, uses {@link TurkishLowerCaseFilter} for Turkish language.
 * </ul>
 * </p>
 * @deprecated Use the language-specific analyzer in contrib/analyzers instead. 
 * This analyzer will be removed in Lucene 5.0
 */
@Deprecated
public final class SnowballAnalyzer extends Analyzer {
  private String name;
  private Set<?> stopSet;
  private final Version matchVersion;

  /** Builds the named analyzer with no stop words. */
  public SnowballAnalyzer(Version matchVersion, String name) {
    this.name = name;
    this.matchVersion = matchVersion;
  }

  /** 
   * Builds the named analyzer with the given stop words.
   * @deprecated Use {@link #SnowballAnalyzer(Version, String, Set)} instead.  
   */
  @Deprecated
  public SnowballAnalyzer(Version matchVersion, String name, String[] stopWords) {
    this(matchVersion, name);
    stopSet = StopFilter.makeStopSet(matchVersion, stopWords);
  }
  
  /** Builds the named analyzer with the given stop words. */
  public SnowballAnalyzer(Version matchVersion, String name, Set<?> stopWords) {
    this(matchVersion, name);
    stopSet = CharArraySet.unmodifiableSet(CharArraySet.copy(matchVersion,
        stopWords));
  }

  /** Constructs a {@link StandardTokenizer} filtered by a {@link
      StandardFilter}, a {@link LowerCaseFilter}, a {@link StopFilter},
      and a {@link SnowballFilter} */
  @Override
  public TokenStream tokenStream(String fieldName, Reader reader) {
    TokenStream result = new StandardTokenizer(matchVersion, reader);
    result = new StandardFilter(matchVersion, result);
    // remove the possessive 's for english stemmers
    if (matchVersion.onOrAfter(Version.LUCENE_31) && 
        (name.equals("English") || name.equals("Porter") || name.equals("Lovins")))
      result = new EnglishPossessiveFilter(result);
    // Use a special lowercase filter for turkish, the stemmer expects it.
    if (matchVersion.onOrAfter(Version.LUCENE_31) && name.equals("Turkish"))
      result = new TurkishLowerCaseFilter(result);
    else
      result = new LowerCaseFilter(matchVersion, result);
    if (stopSet != null)
      result = new StopFilter(matchVersion,
                              result, stopSet);
    result = new SnowballFilter(result, name);
    return result;
  }
  
  private class SavedStreams {
    Tokenizer source;
    TokenStream result;
  }
  
  /** Returns a (possibly reused) {@link StandardTokenizer} filtered by a 
   * {@link StandardFilter}, a {@link LowerCaseFilter}, 
   * a {@link StopFilter}, and a {@link SnowballFilter} */
  @Override
  public TokenStream reusableTokenStream(String fieldName, Reader reader)
      throws IOException {
    SavedStreams streams = (SavedStreams) getPreviousTokenStream();
    if (streams == null) {
      streams = new SavedStreams();
      streams.source = new StandardTokenizer(matchVersion, reader);
      streams.result = new StandardFilter(matchVersion, streams.source);
      // Use a special lowercase filter for turkish, the stemmer expects it.
      if (matchVersion.onOrAfter(Version.LUCENE_31) && name.equals("Turkish"))
        streams.result = new TurkishLowerCaseFilter(streams.result);
      else
        streams.result = new LowerCaseFilter(matchVersion, streams.result);
      if (stopSet != null)
        streams.result = new StopFilter(matchVersion,
                                        streams.result, stopSet);
      streams.result = new SnowballFilter(streams.result, name);
      setPreviousTokenStream(streams);
    } else {
      streams.source.reset(reader);
    }
    return streams.result;
  }
}

Other Lucene examples (source code examples)

Here is a short list of links related to this Lucene SnowballAnalyzer.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.