Package org.apache.lucene.analysis.snowball

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

33
34
35
36
37
38
39
40
41
    assertTokenStreamContents(ts, new String[] { "the", "birds", "bird", "are", "flying", "fli"}, new int[] {1,1,0,1,1,0});
  }


  public void testComposition() throws IOException {
    TokenStream ts = new RemoveDuplicatesTokenFilter(new SnowballFilter(new KeywordRepeatFilter(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
124
125
126
127
128
129
130
131
    TokenStream result = new StandardFilter(matchVersion, source);
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new KeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new HungarianStemmer());
    return new TokenStreamComponents(source, result);
  }
View Full Code Here
124
125
126
127
128
129
130
131
    TokenStream result = new StandardFilter(matchVersion, source);
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new KeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new DanishStemmer());
    return new TokenStreamComponents(source, result);
  }
View Full Code Here
124
125
126
127
128
129
130
131
    TokenStream result = new StandardFilter(matchVersion, source);
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new KeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new FinnishStemmer());
    return new TokenStreamComponents(source, result);
  }
View Full Code Here
124
125
126
127
128
129
130
131
    TokenStream result = new StandardFilter(matchVersion, source);
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new KeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new SwedishStemmer());
    return new TokenStreamComponents(source, result);
  }
View Full Code Here
245
246
247
248
249
250
251
252
253
254
255
      result = new ElisionFilter(matchVersion, result);
      result = new LowerCaseFilter(matchVersion, result);
      result = new StopFilter(matchVersion, result, stopwords);
      if(!excltable.isEmpty())
        result = new KeywordMarkerFilter(result, excltable);
      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);
      result = new StopFilter(matchVersion, result, stopwords);
View Full Code Here
124
125
126
127
128
129
130
131
    TokenStream result = new StandardFilter(matchVersion, source);
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new KeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new PortugueseStemmer());
    return new TokenStreamComponents(source, result);
  }
View Full Code Here
249
250
251
252
253
254
255
256
257
258
259
      if(!excltable.isEmpty())
        result = new KeywordMarkerFilter(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
134
135
136
137
138
139
140
141
142
    if(!stemExclusionSet.isEmpty())
      result = new KeywordMarkerFilter(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
124
125
126
127
128
129
130
131
    TokenStream result = new StandardFilter(matchVersion, source);
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new KeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new NorwegianStemmer());
    return new TokenStreamComponents(source, result);
  }
View Full Code Here
TOP

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

  • com.enigmastation.extractors.impl.LuceneStemmingWordLister
  • com.flaptor.indextank.query.analyzers.StemmerFilter
  • de.jetwick.es.JetwickQuery
  • org.apache.lucene.analysis.ca.CatalanAnalyzer
  • org.apache.lucene.analysis.da.DanishAnalyzer
  • org.apache.lucene.analysis.de.GermanAnalyzer
  • org.apache.lucene.analysis.es.SpanishAnalyzer
  • org.apache.lucene.analysis.eu.BasqueAnalyzer
  • org.apache.lucene.analysis.fi.FinnishAnalyzer
  • org.apache.lucene.analysis.fr.FrenchAnalyzer
    • 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.