Package org.apache.lucene.analysis.miscellaneous

Examples of org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter

174
175
176
177
178
179
180
181
182
183
184
      Reader reader) {
    final Tokenizer source = new StandardTokenizer(matchVersion, reader);
    TokenStream result = new StandardFilter(matchVersion, source);
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter( matchVersion, result, stopwords);
    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());
View Full Code Here
120
121
122
123
124
125
126
127
128
    final Tokenizer source = new StandardTokenizer(matchVersion, reader);
    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);
    }
    return new TokenStreamComponents(source, new IndonesianStemFilter(result));
  }
View Full Code Here
126
127
128
129
130
131
132
133
134
    if(matchVersion.onOrAfter(Version.LUCENE_48))
      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
140
141
142
143
144
145
146
147
148
149
    TokenStream result = new StandardFilter(matchVersion, source);
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter( matchVersion, result, stopwords);
    if (matchVersion.onOrAfter(Version.LUCENE_31)) {
      if(!this.stemExclusionTable.isEmpty())
        result = new SetKeywordMarkerFilter(result, stemExclusionTable);
      result = new CzechStemFilter(result);
    }
    return new TokenStreamComponents(source, result);
  }
View Full Code Here
123
124
125
126
127
128
129
130
131
    final Tokenizer source = new StandardTokenizer(matchVersion, reader);
    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
132
133
134
135
136
137
138
139
140
141
142
    } else {
      source = new IndicTokenizer(matchVersion, reader);
    }
    TokenStream result = new LowerCaseFilter(matchVersion, source);
    if (!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new IndicNormalizationFilter(result);
    result = new HindiNormalizationFilter(result);
    result = new StopFilter(matchVersion, result, stopwords);
    result = new HindiStemFilter(result);
    return new TokenStreamComponents(source, result);
View Full Code Here
130
131
132
133
134
135
136
137
138
139
140
    final Tokenizer source = new StandardTokenizer(matchVersion, reader);
    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);
    if (matchVersion.onOrAfter(Version.LUCENE_36)) {
      result = new SpanishLightStemFilter(result);
    } else {
      result = new SnowballFilter(result, new SpanishStemmer());
    }
View Full Code Here
145
146
147
148
149
150
151
152
153
    final Tokenizer source = new StandardTokenizer(matchVersion, reader);
    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 StempelFilter(result, new StempelStemmer(stemTable));
    return new TokenStreamComponents(source, result);
  }
View Full Code Here
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
      TokenStream result = new StandardFilter(matchVersion, source);
      result = new ElisionFilter(result, DEFAULT_ARTICLES);
      result = new LowerCaseFilter(matchVersion, result);
      result = new StopFilter(matchVersion, result, stopwords);
      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);
      result = new StopFilter(matchVersion, result, stopwords);
      if(!excltable.isEmpty())
        result = new SetKeywordMarkerFilter(result, excltable);
      result = new FrenchStemFilter(result);
      // Convert to lowercase after stemming!
      return new TokenStreamComponents(source, new LowerCaseFilter(matchVersion, result));
    }
  }
View Full Code Here
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
      if (matchVersion.onOrAfter(Version.LUCENE_31)) {
        final Tokenizer source = new StandardTokenizer(matchVersion, reader);
        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
TOP

Related Classes of org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter

  • org.apache.lucene.analysis.ar.ArabicAnalyzer
  • org.apache.lucene.analysis.ar.TestArabicStemFilter
  • org.apache.lucene.analysis.bg.BulgarianAnalyzer
  • org.apache.lucene.analysis.bg.TestBulgarianStemmer
  • org.apache.lucene.analysis.br.BrazilianAnalyzer
  • org.apache.lucene.analysis.br.TestBrazilianStemmer
  • org.apache.lucene.analysis.ca.CatalanAnalyzer
  • org.apache.lucene.analysis.ckb.SoraniAnalyzer
  • org.apache.lucene.analysis.cz.CzechAnalyzer
  • org.apache.lucene.analysis.cz.TestCzechStemmer
    • 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.