eu.dicodeproject.analysis.lucene.StemmerFactory Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of integration Show documentation

The examples module provides glue code implementation for extracting common phrases, key word distributions and more from tweets stored on HDFS/HBase. It builds on Mahout for more sophisticated analysis.

The newest version!

/**
 * Copyright (C) 2010, 2011 Neofonie GmbH
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of 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.
 */
package eu.dicodeproject.analysis.lucene;

import eu.dicodeproject.analysis.util.Language;

import org.apache.lucene.analysis.PorterStemFilter;
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.de.GermanStemFilter;
import org.apache.lucene.analysis.id.IndonesianStemFilter;
import org.apache.lucene.analysis.snowball.SnowballFilter;
import org.apache.lucene.analysis.standard.StandardFilter;
import org.apache.lucene.util.Version;
import org.tartarus.snowball.ext.DutchStemmer;
import org.tartarus.snowball.ext.FrenchStemmer;
import org.tartarus.snowball.ext.German2Stemmer;
import org.tartarus.snowball.ext.ItalianStemmer;
import org.tartarus.snowball.ext.PortugueseStemmer;
import org.tartarus.snowball.ext.RussianStemmer;
import org.tartarus.snowball.ext.SpanishStemmer;
import org.tartarus.snowball.ext.TurkishStemmer;

/**
 * @author jakob
 */
public class StemmerFactory {

  public static TokenFilter getStemmer(Language language, Version matchVersion, TokenStream result) {
    if (language == Language.ENGLISH) {
      return new PorterStemFilter(result);
    }
    else if (language == Language.SPANISH) {
      return new SnowballFilter(result, new SpanishStemmer());
    }
    else if (language == Language.PORTUGUESE) {
      return new SnowballFilter(result, new PortugueseStemmer());
    }
    else if (language == Language.FRENCH) {
      return new SnowballFilter(result, new FrenchStemmer());
    }
    else if (language == Language.DUTCH) {
      return new SnowballFilter(result, new DutchStemmer());
    }
    else if (language == Language.GERMAN) {
      if (matchVersion.onOrAfter(Version.LUCENE_31)) {
        return new SnowballFilter(result, new German2Stemmer());
      }
      else {
        return new GermanStemFilter(result);
      }
    }
    else if (language == Language.INDONESIAN) {
      return new IndonesianStemFilter(result);
    }
    else if (language == Language.ITALIAN) {
      return new SnowballFilter(result, new ItalianStemmer());
    }
    else if (language == Language.RUSSIAN) {
      return new SnowballFilter(result, new RussianStemmer());
    }
    else if (language == Language.TURKISH) {
      return new SnowballFilter(result, new TurkishStemmer());
    }

    return new StandardFilter(matchVersion, result);
  }

}