Package org.apache.lucene.analysis.snowball

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

143
144
145
146
147
148
149
150
    result = new ElisionFilter(result, DEFAULT_ARTICLES);
    result = new IrishLowerCaseFilter(result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new IrishStemmer());
    return new TokenStreamComponents(source, result);
  }
View Full Code Here
29
30
31
32
33
34
35
    this.stemmerName = stemmerName;
  }

  @Override
  public TokenFilter filter(TokenStream stream) {
    return new SnowballFilter(stream, stemmerName);
  }
View Full Code Here
36
37
38
39
40
41
42
    String stemmerName = properties.getProperty(STEMMER_NAME_PARAMETER);
    if( stemmerName == null )
      stemmerName = DEFAULT_STEMMER_NAME;
   
    return new SnowballFilter(tokenStream, stemmerName);
  }
View Full Code Here
825
826
827
828
829
830
831
832
833
834
835
        return doSnowballStemming(tokenizer);
    }

    public Set<String> doSnowballStemming(TokenStream ts) {
        Set<String> res = new LinkedHashSet<String>();
        ts = new SnowballFilter(ts, "English");
        try {
            while (ts.incrementToken()) {
                res.add(ts.getAttribute(TermAttribute.class).term());
            }
        } catch (IOException ex) {
View Full Code Here
145
146
147
148
149
150
151
152
    result = new ElisionFilter(result, DEFAULT_ARTICLES);
    result = new IrishLowerCaseFilter(result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new IrishStemmer());
    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 SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new SwedishStemmer());
    return new TokenStreamComponents(source, result);
  }
View Full Code Here
179
180
181
182
183
184
185
186
187
188
189
    result = new SetKeywordMarkerFilter(result, exclusionSet);
    if (matchVersion.onOrAfter(Version.LUCENE_36)) {
      result = new GermanNormalizationFilter(result);
      result = new GermanLightStemFilter(result);
    } else if (matchVersion.onOrAfter(Version.LUCENE_31)) {
      result = new SnowballFilter(result, new German2Stemmer());
    } else {
      result = new GermanStemFilter(result);
    }
    return new TokenStreamComponents(source, result);
  }
View Full Code Here
127
128
129
130
131
132
133
134
      result = new ApostropheFilter(result);
    result = new TurkishLowerCaseFilter(result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new TurkishStemmer());
    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 SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new NorwegianStemmer());
    return new TokenStreamComponents(source, result);
  }
View Full Code Here
134
135
136
137
138
139
140
141
142
    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    if (matchVersion.onOrAfter(Version.LUCENE_36)) {
      result = new SpanishLightStemFilter(result);
    } else {
      result = new SnowballFilter(result, new SpanishStemmer());
    }
    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.