Package org.apache.lucene.analysis.standard

Examples of org.apache.lucene.analysis.standard.StandardFilter

47
48
49
50
51
52
53
54
55
public StandardBgramAnalyzer() { }
public TokenStream tokenStream (String fieldName, Reader reader)
{
   TokenStream ts = (extractEntities) ?
     new EntFilter ( new BgramFilter( new LowerCaseFilter( new StandardFilter( new StandardTokenizer(reader) ) ) ) ):
                     new BgramFilter( new LowerCaseFilter( new StandardFilter( new StandardTokenizer(reader) ) ) );
   return (ts);
}
View Full Code Here
208
209
210
211
212
213
214
215
216
217
218
   *         {@link FrenchStemFilter} and {@link LowerCaseFilter}
   */
  @Override
  public final TokenStream tokenStream(String fieldName, Reader reader) {
    TokenStream result = new StandardTokenizer(matchVersion, reader);
    result = new StandardFilter(result);
    result = new StopFilter(StopFilter.getEnablePositionIncrementsVersionDefault(matchVersion),
                            result, stoptable);
    result = new FrenchStemFilter(result, excltable);
    // Convert to lowercase after stemming!
    result = new LowerCaseFilter(result);
View Full Code Here
237
238
239
240
241
242
243
244
245
246
247
      throws IOException {
    SavedStreams streams = (SavedStreams) getPreviousTokenStream();
    if (streams == null) {
      streams = new SavedStreams();
      streams.source = new StandardTokenizer(matchVersion, reader);
      streams.result = new StandardFilter(streams.source);
      streams.result = new StopFilter(StopFilter.getEnablePositionIncrementsVersionDefault(matchVersion),
                                      streams.result, stoptable);
      streams.result = new FrenchStemFilter(streams.result, excltable);
      // Convert to lowercase after stemming!
      streams.result = new LowerCaseFilter(streams.result);
View Full Code Here
219
220
221
222
223
224
225
226
227
228
229
   *   and {@link DutchStemFilter}
   */
  @Override
  public TokenStream tokenStream(String fieldName, Reader reader) {
    TokenStream result = new StandardTokenizer(matchVersion, reader);
    result = new StandardFilter(result);
    result = new StopFilter(StopFilter.getEnablePositionIncrementsVersionDefault(matchVersion),
                            result, stoptable);
    result = new DutchStemFilter(result, excltable, stemdict);
    return result;
  }
View Full Code Here
253
254
255
256
257
258
259
260
261
262
263
   
    SavedStreams streams = (SavedStreams) getPreviousTokenStream();
    if (streams == null) {
      streams = new SavedStreams();
      streams.source = new StandardTokenizer(matchVersion, reader);
      streams.result = new StandardFilter(streams.source);
      streams.result = new StopFilter(StopFilter.getEnablePositionIncrementsVersionDefault(matchVersion),
                                      streams.result, stoptable);
      streams.result = new DutchStemFilter(streams.result, excltable, stemdict);
      setPreviousTokenStream(streams);
    } else {
View Full Code Here
198
199
200
201
202
203
204
205
206
207
208
   */
  @Override
  public final TokenStream tokenStream(String fieldName, Reader reader) {
                TokenStream result = new StandardTokenizer( matchVersion, reader );
    result = new LowerCaseFilter( result );
    result = new StandardFilter( result );
    result = new StopFilter( StopFilter.getEnablePositionIncrementsVersionDefault(matchVersion),
                                         result, stoptable );
    result = new BrazilianStemFilter( result, excltable );
    return result;
  }
View Full Code Here
226
227
228
229
230
231
232
233
234
235
236
      SavedStreams streams = (SavedStreams) getPreviousTokenStream();
      if (streams == null) {
        streams = new SavedStreams();
        streams.source = new StandardTokenizer(matchVersion, reader);
        streams.result = new LowerCaseFilter(streams.source);
        streams.result = new StandardFilter(streams.result);
        streams.result = new StopFilter(StopFilter.getEnablePositionIncrementsVersionDefault(matchVersion),
                                        streams.result, stoptable);
        streams.result = new BrazilianStemFilter(streams.result, excltable);
        setPreviousTokenStream(streams);
      } else {
View Full Code Here
178
179
180
181
182
183
184
185
186
187
188
   *       {@link StandardFilter}, {@link LowerCaseFilter}, and {@link StopFilter}
   */
  @Override
  public final TokenStream tokenStream( String fieldName, Reader reader ) {
                TokenStream result = new StandardTokenizer( matchVersion, reader );
    result = new StandardFilter( result );
    result = new LowerCaseFilter( result );
    result = new StopFilter( StopFilter.getEnablePositionIncrementsVersionDefault(matchVersion),
                                         result, stoptable );
    return result;
  }
View Full Code Here
204
205
206
207
208
209
210
211
212
213
214
      throws IOException {
      SavedStreams streams = (SavedStreams) getPreviousTokenStream();
      if (streams == null) {
        streams = new SavedStreams();
        streams.source = new StandardTokenizer(matchVersion, reader);
        streams.result = new StandardFilter(streams.source);
        streams.result = new LowerCaseFilter(streams.result);
        streams.result = new StopFilter(StopFilter.getEnablePositionIncrementsVersionDefault(matchVersion),
                                        streams.result, stoptable);
        setPreviousTokenStream(streams);
      } else {
View Full Code Here
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
      System.out.println("-----Tokens: " + tokCount[k] + "-----");
      for (int i = 0; i < tokCount[k]; i++) {
        buffer.append(English.intToEnglish(i).toUpperCase()).append(' ');
      }
      //make sure we produce the same tokens
      TeeSinkTokenFilter teeStream = new TeeSinkTokenFilter(new StandardFilter(new StandardTokenizer(Version.LUCENE_CURRENT, new StringReader(buffer.toString()))));
      TokenStream sink = teeStream.newSinkTokenStream(new ModuloSinkFilter(100));
      teeStream.consumeAllTokens();
      TokenStream stream = new ModuloTokenFilter(new StandardFilter(new StandardTokenizer(Version.LUCENE_CURRENT, new StringReader(buffer.toString()))), 100);
      TermAttribute tfTok = stream.addAttribute(TermAttribute.class);
      TermAttribute sinkTok = sink.addAttribute(TermAttribute.class);
      for (int i=0; stream.incrementToken(); i++) {
        assertTrue(sink.incrementToken());
        assertTrue(tfTok + " is not equal to " + sinkTok + " at token: " + i, tfTok.equals(sinkTok) == true);
      }
     
      //simulate two fields, each being analyzed once, for 20 documents
      for (int j = 0; j < modCounts.length; j++) {
        int tfPos = 0;
        long start = System.currentTimeMillis();
        for (int i = 0; i < 20; i++) {
          stream = new StandardFilter(new StandardTokenizer(Version.LUCENE_CURRENT, new StringReader(buffer.toString())));
          PositionIncrementAttribute posIncrAtt = stream.getAttribute(PositionIncrementAttribute.class);
          while (stream.incrementToken()) {
            tfPos += posIncrAtt.getPositionIncrement();
          }
          stream = new ModuloTokenFilter(new StandardFilter(new StandardTokenizer(Version.LUCENE_CURRENT, new StringReader(buffer.toString()))), modCounts[j]);
          posIncrAtt = stream.getAttribute(PositionIncrementAttribute.class);
          while (stream.incrementToken()) {
            tfPos += posIncrAtt.getPositionIncrement();
          }
        }
        long finish = System.currentTimeMillis();
        System.out.println("ModCount: " + modCounts[j] + " Two fields took " + (finish - start) + " ms");
        int sinkPos = 0;
        //simulate one field with one sink
        start = System.currentTimeMillis();
        for (int i = 0; i < 20; i++) {
          teeStream = new TeeSinkTokenFilter(new StandardFilter(new StandardTokenizer(Version.LUCENE_CURRENT, new StringReader(buffer.toString()))));
          sink = teeStream.newSinkTokenStream(new ModuloSinkFilter(modCounts[j]));
          PositionIncrementAttribute posIncrAtt = teeStream.getAttribute(PositionIncrementAttribute.class);
          while (teeStream.incrementToken()) {
            sinkPos += posIncrAtt.getPositionIncrement();
          }
View Full Code Here
TOP

Related Classes of org.apache.lucene.analysis.standard.StandardFilter

  • com.foundationdb.server.service.text.SelectiveCaseAnalyzer
  • com.gentics.cr.lucene.autocomplete.AutocompleteAnalyzer
  • com.github.pmerienne.trident.ml.preprocessing.EnglishTokenizer$EnglishSpecialAnalyzer
  • com.googlecode.lucene.PorterAnalyzer
  • com.livingsocial.hive.udf.Tokenize$MyAnalyzer
  • com.mozilla.grouperfish.lucene.analysis.en.EnglishAnalyzer
  • com.mozilla.grouperfish.lucene.analysis.en.NGramEnglishAnalyzer
  • com.mozilla.grouperfish.transforms.coclustering.lucene.analysis.en.EnglishAnalyzer
  • com.mozilla.grouperfish.transforms.coclustering.lucene.analysis.en.NGramEnglishAnalyzer
  • edu.wiki.index.WikipediaAnalyzer
    • 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.