Package org.apache.lucene.analysis

Examples of org.apache.lucene.analysis.StopFilter

34
35
36
37
38
39
40
    @Inject public MyFilterTokenFilterFactory(Index index, @IndexSettings Settings indexSettings, String name) {
        super(index, indexSettings, name, ImmutableSettings.Builder.EMPTY_SETTINGS);
    }

    @Override public TokenStream create(TokenStream tokenStream) {
        return new StopFilter(version, tokenStream, StopAnalyzer.ENGLISH_STOP_WORDS_SET);
    }
View Full Code Here
118
119
120
121
122
123
124
125
126
    Tokenizer tokenizer = new StandardTokenizer(Version.LUCENE_31, reader);
    TokenStream result = new StandardFilter(Version.LUCENE_31, tokenizer);
    result = new LowerCaseFilter(Version.LUCENE_31, result);
    result = new ASCIIFoldingFilter(result);
    result = new AlphaNumericMaxLengthFilter(result);
    result = new StopFilter(Version.LUCENE_31, result, stopwords);
    result = new PorterStemFilter(result);
    return new TokenStreamComponents(tokenizer, result);
  }
View Full Code Here
44
45
46
47
48
49
50
51
  @Override
  protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
    Tokenizer tokenizer = new WikipediaTokenizer(reader);
    TokenStream result = new StandardFilter(Version.LUCENE_31, tokenizer);
    result = new LowerCaseFilter(Version.LUCENE_31, result);
    result = new StopFilter(Version.LUCENE_31, result, stopwords);
    return new TokenStreamComponents(tokenizer, result);
  }
View Full Code Here
77
78
79
80
81
82
83
84
85
  public Set getStopWords() {
    return stopWords;
  }

  public StopFilter create(TokenStream input) {
    StopFilter stopFilter = new StopFilter(input,stopWords,ignoreCase);
    stopFilter.setEnablePositionIncrements(enablePositionIncrements);
    return stopFilter;
  }
View Full Code Here
44
45
46
47
48
49
50
51
  @Override
  public TokenStream tokenStream(String fieldName, Reader reader) {
    TokenStream result = new WikipediaTokenizer(reader);
    result = new StandardFilter(result);
    result = new LowerCaseFilter(result);
    result = new StopFilter(true, result, stopSet);
    return result;
  }
View Full Code Here
11
12
13
14
15
16
17
18
19
20
21
final class Oscar3Filters extends TokenStream {

  TokenStream ts;
 
  Oscar3Filters(TokenStream ts) {
    if(false) ts = new StopFilter(ts, StandardAnalyzer.STOP_WORDS, true);
    ts = new Oscar3CaseFilter(ts);
    if(false) ts = new PunctuationFilter(ts);
    if(false) ts = new SnowballFilter(ts, "Porter");
    this.ts = ts;
  }
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 KeywordMarkerFilter(result, stemExclusionSet);
    result = new LatvianStemFilter(result);
    return new TokenStreamComponents(source, result);
  }
View Full Code Here
238
239
240
241
242
243
244
245
      this.enablePositionIncrements = enablePositionIncrements;
    }
    @Override
    public TokenStream tokenStream(String fieldName, Reader reader) {
      TokenStream ts = a.tokenStream(fieldName,reader);
      return new StopFilter(enablePositionIncrements?TEST_VERSION_CURRENT:Version.LUCENE_24, ts,
          new CharArraySet(TEST_VERSION_CURRENT, Collections.singleton("stop"), true));
    }
View Full Code Here
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
      Reader aReader) {
    if (matchVersion.onOrAfter(Version.LUCENE_31)) {
      final Tokenizer source = new StandardTokenizer(matchVersion, aReader);
      TokenStream result = new StandardFilter(matchVersion, source);
      result = new LowerCaseFilter(matchVersion, result);
      result = new StopFilter(matchVersion, result, stoptable);
      if (!excltable.isEmpty())
        result = new KeywordMarkerFilter(result, excltable);
      if (!stemdict.isEmpty())
        result = new StemmerOverrideFilter(matchVersion, result, stemdict);
      result = new SnowballFilter(result, new org.tartarus.snowball.ext.DutchStemmer());
      return new TokenStreamComponents(source, result);
    } else {
      final Tokenizer source = new StandardTokenizer(matchVersion, aReader);
      TokenStream result = new StandardFilter(matchVersion, source);
      result = new StopFilter(matchVersion, result, stoptable);
      if (!excltable.isEmpty())
        result = new KeywordMarkerFilter(result, excltable);
      result = new DutchStemFilter(result, stemdict);
      return new TokenStreamComponents(source, result);
    }
View Full Code Here
140
141
142
143
144
145
146
147
148
149
    StandardTokenizer tokenStream = new StandardTokenizer(reader, replaceInvalidAcronym);
    tokenStream.setMaxTokenLength(maxTokenLength);
    TokenStream result = new StandardFilter(tokenStream);

    result = new LowerCaseFilter(result);
    result = new StopFilter(result, TERRIER_STOP_WORDS);
    result = new PorterStemFilter(result);

    return result;
  }
View Full Code Here
TOP

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

  • BugAnalyzer.PorterStemAnalyzer
  • com.gentics.cr.lucene.analysis.CustomPatternAnalyzer
  • com.gentics.cr.lucene.autocomplete.AutocompleteAnalyzer
  • com.github.pmerienne.trident.ml.preprocessing.EnglishTokenizer$EnglishSpecialAnalyzer
  • com.infoclinika.mssharing.search.NoStopWordsAnalyzer
  • com.mozilla.grouperfish.lucene.analysis.en.EnglishAnalyzer
  • com.mozilla.grouperfish.transforms.coclustering.lucene.analysis.en.EnglishAnalyzer
  • edu.wiki.index.WikipediaAnalyzer
  • ivory.core.tokenize.LuceneArabicAnalyzer
  • ivory.core.tokenize.LuceneSpanishAnalyzer
    • 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.