Package org.apache.lucene.analysis.standard

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

148
149
150
151
152
153
154
155
156
157
158
    public TokenStream reusableTokenStream(String fieldName, Reader reader)
      throws IOException {
      SavedStreams streams = (SavedStreams) getPreviousTokenStream();
      if (streams == null) {
        streams = new SavedStreams();
        streams.source = new StandardTokenizer(matchVersion, reader);
        streams.result = new GreekLowerCaseFilter(streams.source);
        streams.result = new StopFilter(StopFilter.getEnablePositionIncrementsVersionDefault(matchVersion),
                                        streams.result, stopSet);
        setPreviousTokenStream(streams);
      } else {
View Full Code Here
177
178
179
180
181
182
183
184
185
186
187
   * @return  A {@link TokenStream} built from a {@link StandardTokenizer} filtered with
   *       {@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
203
204
205
206
207
208
209
210
211
212
213
  public TokenStream reusableTokenStream(String fieldName, Reader reader)
      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);
View Full Code Here
148
149
150
151
152
153
154
155
156
157
    public MultiAnalyzer() {
    }

    @Override
    public TokenStream tokenStream(String fieldName, Reader reader) {
      TokenStream result = new StandardTokenizer(Version.LUCENE_CURRENT, reader);
      result = new TestFilter(result);
      result = new LowerCaseFilter(result);
      return result;
    }
View Full Code Here
218
219
220
221
222
223
224
225
226
227
    public PosIncrementAnalyzer() {
    }

    @Override
    public TokenStream tokenStream(String fieldName, Reader reader) {
      TokenStream result = new StandardTokenizer(Version.LUCENE_CURRENT, reader);
      result = new TestPosIncrementFilter(result);
      result = new LowerCaseFilter(result);
      return result;
    }
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
110
111
112
113
114
115
116
117
118
119
120
  public ASCIIAnalyzer() {
  }

  @Override
  public TokenStream tokenStream(String fieldName, Reader reader) {
    TokenStream result = new StandardTokenizer(Version.LUCENE_CURRENT, reader);
    result = new StandardFilter(result);
    result = new ASCIIFoldingFilter(result);
    result = new LowerCaseFilter(result);
    return result;
  }
View Full Code Here
43
44
45
46
47
48
49
50
51
52
53
    this.matchVersion = matchVersion;
  }
 
  @Override
  public TokenStream tokenStream(String fieldName, Reader reader) {
    TokenStream ts = new StandardTokenizer(matchVersion, reader);
    ts = new StandardFilter(ts);
    ts = new ThaiWordFilter(ts);
    ts = new StopFilter(StopFilter.getEnablePositionIncrementsVersionDefault(matchVersion),
                        ts, StopAnalyzer.ENGLISH_STOP_WORDS_SET);
    return ts;
View Full Code Here
68
69
70
71
72
73
74
75
76
77
78
    }
   
    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 ThaiWordFilter(streams.result);
      streams.result = new StopFilter(StopFilter.getEnablePositionIncrementsVersionDefault(matchVersion),
                                      streams.result, StopAnalyzer.ENGLISH_STOP_WORDS_SET);
      setPreviousTokenStream(streams);
View Full Code Here
230
231
232
233
234
235
236
237
238
239
240
    }
   
    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, stopSet);
      streams.result = new GermanStemFilter(streams.result, exclusionSet);
View Full Code Here
TOP

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

  • com.enigmastation.extractors.impl.LuceneStemmingWordLister
  • com.ikanow.infinit.e.api.knowledge.SearchHandler
  • com.livingsocial.hive.udf.Tokenize$MyAnalyzer
  • com.mozilla.grouperfish.lucene.analysis.en.EnglishAnalyzer
  • com.mozilla.grouperfish.lucene.analysis.en.NGramEnglishAnalyzer
  • com.tamingtext.util.StringUtilTest
  • ivory.core.tokenize.LuceneAnalyzer
  • ivory.core.tokenize.LuceneArabicAnalyzer
  • org.apache.lucene.analysis.ar.ArabicAnalyzer
  • org.apache.lucene.analysis.bg.BulgarianAnalyzer
    • 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.