Package org.apache.lucene.analysis.snowball

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

192
193
194
195
196
197
198
199
200
201
202
      result = new StopFilter(matchVersion, result, stoptable);
      if (!excltable.isEmpty())
        result = new SetKeywordMarkerFilter(result, excltable);
      if (stemdict != null)
        result = new StemmerOverrideFilter(result, stemdict);
      result = new SnowballFilter(result, new org.tartarus.snowball.ext.DutchStemmer());
      return new TokenStreamComponents(source, result);
    } else {
      final Tokenizer source = new StandardTokenizer(matchVersion, aReader);
      TokenStream result = new StandardFilter(matchVersion, source);
      result = new StopFilter(matchVersion, result, stoptable);
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
198
199
200
201
202
203
204
205
206
207
208
      if(!excltable.isEmpty())
        result = new SetKeywordMarkerFilter(result, excltable);
      if (matchVersion.onOrAfter(Version.LUCENE_3_6)) {
        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
126
127
128
129
130
131
132
133
    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 RomanianStemmer());
    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_3_6)) {
      result = new PortugueseLightStemFilter(result);
    } else {
      result = new SnowballFilter(result, new PortugueseStemmer());
    }
    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_3_6)) {
      result = new GermanNormalizationFilter(result);
      result = new GermanLightStemFilter(result);
    } else if (matchVersion.onOrAfter(Version.LUCENE_3_1)) {
      result = new SnowballFilter(result, new German2Stemmer());
    } else {
      result = new GermanStemFilter(result);
    }
    return new TokenStreamComponents(source, result);
  }
View Full Code Here
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
        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
121
122
123
124
125
126
127
128
    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 ArmenianStemmer());
    return new TokenStreamComponents(source, result);
  }
View Full Code Here
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
    public void addWords(Object obj, Collection<String> features) {
        String document = obj.toString().toLowerCase();
        StandardTokenizer tokenizer = new StandardTokenizer(new StringReader(document));
        tokenizer.setMaxTokenLength(20);
        TokenFilter psf = new SnowballFilter(tokenizer, "English");
        Token t;
        StringBuilder sb = new StringBuilder();
        try {
            while ((t = psf.next()) != null) {
                sb.setLength(0);
                sb.append(t.termBuffer(), 0, t.termLength());
                //System.out.println(sb.toString());
                features.add(sb.toString());
            }
View Full Code Here
29
30
31
32
33
34
35
*/
@Deprecated
public class RussianStemFilterFactory extends BaseTokenFilterFactory {

  public TokenFilter create(TokenStream in) {
    return new SnowballFilter( in, new org.tartarus.snowball.ext.RussianStemmer() );
  }
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.