Package org.apache.lucene.analysis.snowball

Examples of org.apache.lucene.analysis.snowball.SnowballFilter


        TokenStream result = new StandardFilter(matchVersion, source);
        result = new LowerCaseFilter(matchVersion, result);
        result = new StopFilter(matchVersion, result, stopwords);
        if (!stemExclusionSet.isEmpty()) result = new SetKeywordMarkerFilter(
            result, stemExclusionSet);
        result = new SnowballFilter(result, new org.tartarus.snowball.ext.RussianStemmer());
        return new TokenStreamComponents(source, result);
      } else {
        final Tokenizer source = new RussianLetterTokenizer(matchVersion, reader);
        TokenStream result = new LowerCaseFilter(matchVersion, source);
        result = new StopFilter(matchVersion, result, stopwords);
        if (!stemExclusionSet.isEmpty()) result = new SetKeywordMarkerFilter(
          result, stemExclusionSet);
        result = new SnowballFilter(result, new org.tartarus.snowball.ext.RussianStemmer());
        return new TokenStreamComponents(source, result);
      }
    }
View Full Code Here


      if(!excltable.isEmpty())
        result = new SetKeywordMarkerFilter(result, excltable);
      if (matchVersion.onOrAfter(Version.LUCENE_36)) {
        result = new FrenchLightStemFilter(result);
      } else {
        result = new SnowballFilter(result, new org.tartarus.snowball.ext.FrenchStemmer());
      }
      return new TokenStreamComponents(source, result);
    } else {
      final Tokenizer source = new StandardTokenizer(matchVersion, reader);
      TokenStream result = new StandardFilter(matchVersion, source);
View Full Code Here

    TokenStream result = new StandardFilter(matchVersion, source);
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new DanishStemmer());
    return new TokenStreamComponents(source, result);
  }
View Full Code Here

    TokenStream result = new StandardFilter(matchVersion, source);
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new HungarianStemmer());
    return new TokenStreamComponents(source, result);
  }
View Full Code Here

    TokenStream result = new StandardFilter(matchVersion, source);
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new FinnishStemmer());
    return new TokenStreamComponents(source, result);
  }
View Full Code Here

    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    if (matchVersion.onOrAfter(Version.LUCENE_36)) {
      result = new PortugueseLightStemFilter(result);
    } else {
      result = new SnowballFilter(result, new PortugueseStemmer());
    }
    return new TokenStreamComponents(source, result);
  }
View Full Code Here

    TokenStream result = new StandardFilter(matchVersion, source);
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new BasqueStemmer());
    return new TokenStreamComponents(source, result);
  }
View Full Code Here

    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    if (matchVersion.onOrAfter(Version.LUCENE_36)) {
      result = new ItalianLightStemFilter(result);
    } else {
      result = new SnowballFilter(result, new ItalianStemmer());
    }
    return new TokenStreamComponents(source, result);
  }
View Full Code Here

  @Test
  public void testCreateTokenFilter() throws Exception{
    Properties properties = new Properties();
    properties.setProperty(SnowballFilterFactory.STEMMER_NAME_PARAMETER, PORTER);
   
    SnowballFilter snowballFilter = (SnowballFilter) snowballFilterFactory.createTokenFilter(tokenStream, properties );
    assertNotNull(snowballFilter);
  }
View Full Code Here

import java.io.StringReader;

public class TestKeywordRepeatFilter extends BaseTokenStreamTestCase {

  public void testBasic() throws IOException {
    TokenStream ts = new RemoveDuplicatesTokenFilter(new SnowballFilter(new KeywordRepeatFilter(
        new MockTokenizer(new StringReader("the birds are flying"), MockTokenizer.WHITESPACE, false)), "English"));
    assertTokenStreamContents(ts, new String[] { "the", "birds", "bird", "are", "flying", "fli"}, new int[] {1,1,0,1,1,0});
  }
View Full Code Here

TOP

Related Classes of org.apache.lucene.analysis.snowball.SnowballFilter

Copyright © 2018 www.massapicom. All rights reserved.
All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.