Package org.apache.lucene.analysis.standard

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

111
112
113
114
115
116
117
118
119
120
  }

  @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
44
45
46
47
48
49
50
51
52
53
54
  }
 
  @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
69
70
71
72
73
74
75
76
77
78
79
   
    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);
    } else {
View Full Code Here
197
198
199
200
201
202
203
204
205
206
207
   *         {@link GermanStemFilter}
   */
  @Override
  public 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, stopSet);
    result = new GermanStemFilter(result, exclusionSet);
    return result;
View Full Code Here
231
232
233
234
235
236
237
238
239
240
241
   
    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);
      setPreviousTokenStream(streams);
View Full Code Here
187
188
189
190
191
192
193
194
195
196
197
      protected TokenStreamComponents createComponents(String field, Reader reader) {
        final CharArraySet keywords = new CharArraySet(version, 1, false);
        keywords.add("liście");

        final Tokenizer src = new StandardTokenizer(TEST_VERSION_CURRENT, reader);
        TokenStream result = new StandardFilter(TEST_VERSION_CURRENT, src);
        result = new SetKeywordMarkerFilter(result, keywords);
        result = new MorfologikFilter(result, TEST_VERSION_CURRENT);

        return new TokenStreamComponents(src, result);
      }
View Full Code Here
27
28
29
30
31
32
33
34
35
36
37
  private final Pattern alphabets = Pattern.compile("[a-z]+");
 
  @Override
  public TokenStream tokenStream(String fieldName, Reader reader) {
    TokenStream result = new StandardTokenizer(Version.LUCENE_CURRENT, reader);
    result = new StandardFilter(result);
    result = new LowerCaseFilter(result);
    result = new StopFilter(true, result, StandardAnalyzer.STOP_WORDS_SET);
   
    TermAttribute termAtt = (TermAttribute) result.addAttribute(TermAttribute.class);
    StringBuilder buf = new StringBuilder();
View Full Code Here
39
40
41
42
43
44
45
    super.init(args);
    assureMatchVersion();
  }
 
  public StandardFilter create(TokenStream input) {
    return new StandardFilter(luceneMatchVersion, input);
  }
View Full Code Here
64
65
66
67
68
69
70
71
72
73
74
  @Override
  protected TokenStreamComponents createComponents(final String fieldName, final Reader reader) {
    final StandardTokenizer src = new StandardTokenizer(matchVersion, reader);
    src.setMaxTokenLength(maxTokenLength);
    TokenStream tok = new StandardFilter(matchVersion, src);
    tok = new LowerCaseFilter(matchVersion, tok);
    tok = new StopFilter(matchVersion, tok, stopwords);
    return new TokenStreamComponents(src, tok) {
      @Override
      protected void setReader(final Reader reader) throws IOException {
View Full Code Here
178
179
180
181
182
183
184
185
186
187
   *   filtered with {@link StandardFilter}, {@link StopFilter},
   *   and {@link DutchStemFilter}
   */
  public TokenStream tokenStream(String fieldName, Reader reader) {
    TokenStream result = new StandardTokenizer(reader);
    result = new StandardFilter(result);
    result = new StopFilter(result, stoptable);
    result = new DutchStemFilter(result, excltable, stemdict);
    return result;
  }
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.