Package org.apache.lucene.analysis.core

Examples of org.apache.lucene.analysis.core.StopFilter
106
107
108
109
110
111
112
113
114
115
116
    TokenStream result = new StandardFilter(matchVersion, source);
    // prior to this we get the classic behavior, standardfilter does it for us.
    if (matchVersion.onOrAfter(Version.LUCENE_3_1))
      result = new EnglishPossessiveFilter(matchVersion, result);
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new PorterStemFilter(result);
    return new TokenStreamComponents(source, result);
  }
View Full Code Here
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
    if (matchVersion.onOrAfter(Version.LUCENE_3_1)) {
      final Tokenizer source = new StandardTokenizer(matchVersion, reader);
      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_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);
      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
123
124
125
126
127
128
129
130
131
132
133
  protected TokenStreamComponents createComponents(String fieldName,
      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);
    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new RomanianStemmer());
    return new TokenStreamComponents(source, result);
  }
View Full Code Here
278
279
280
281
282
283
284
285
286
287
288
    Analyzer a3 = new Analyzer() {
      @Override
      public TokenStreamComponents createComponents(String field, Reader reader) {
        Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
        StopFilter filter = new StopFilter(TEST_VERSION_CURRENT,
            tokenizer, StandardAnalyzer.STOP_WORDS_SET);
        return new TokenStreamComponents(tokenizer, new WordDelimiterFilter(TEST_VERSION_CURRENT, filter, flags, protWords));
      }
    };
View Full Code Here
129
130
131
132
133
134
135
    result = new PersianNormalizationFilter(result);
    /*
     * the order here is important: the stopword list is normalized with the
     * above!
     */
    return new TokenStreamComponents(source, new StopFilter(matchVersion, result, stopwords));
  }
View Full Code Here
128
129
130
131
132
133
134
135
136
137
138
  protected TokenStreamComponents createComponents(String fieldName,
      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);
    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    if (matchVersion.onOrAfter(Version.LUCENE_3_6)) {
      result = new PortugueseLightStemFilter(result);
    } else {
View Full Code Here
173
174
175
176
177
178
179
180
181
182
183
  protected TokenStreamComponents createComponents(String fieldName,
      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_3_6)) {
      result = new GermanNormalizationFilter(result);
      result = new GermanLightStemFilter(result);
    } else if (matchVersion.onOrAfter(Version.LUCENE_3_1)) {
View Full Code Here
114
115
116
117
118
119
120
121
122
123
      Reader reader) {
    final Tokenizer source = new StandardTokenizer(matchVersion, reader);
    TokenStream result = new GreekLowerCaseFilter(matchVersion, source);
    if (matchVersion.onOrAfter(Version.LUCENE_3_1))
      result = new StandardFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if (matchVersion.onOrAfter(Version.LUCENE_3_1))
      result = new GreekStemFilter(result);
    return new TokenStreamComponents(source, result);
  }
View Full Code Here
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
        Reader reader) {
      if (matchVersion.onOrAfter(Version.LUCENE_3_1)) {
        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
118
119
120
121
122
123
124
125
126
127
128
  protected TokenStreamComponents createComponents(String fieldName,
      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);
    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new ArmenianStemmer());
    return new TokenStreamComponents(source, result);
  }
View Full Code Here
TOP

Related Classes of org.apache.lucene.analysis.core.StopFilter

  • com.foundationdb.server.service.text.SelectiveCaseAnalyzer
  • com.googlecode.lucene.PorterAnalyzer
  • com.livingsocial.hive.udf.Tokenize$MyAnalyzer
  • gov.nysenate.openleg.lucene.OpenLegislationAnalyzer
  • org.apache.blur.analysis.NoStopWordStandardAnalyzer
  • org.apache.lucene.analysis.ar.ArabicAnalyzer
  • org.apache.lucene.analysis.bg.BulgarianAnalyzer
  • org.apache.lucene.analysis.br.BrazilianAnalyzer
  • org.apache.lucene.analysis.ca.CatalanAnalyzer
  • org.apache.lucene.analysis.cjk.CJKAnalyzer
    • 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.