Package org.apache.lucene.analysis.core

Examples of org.apache.lucene.analysis.core.LowerCaseFilter
50
51
52
53
54
55
56
57
58
59
60
            @Override
            protected Analyzer.TokenStreamComponents createComponents(String fieldName, Reader reader) {
                StandardTokenizer source = new StandardTokenizer(Version.LUCENE_45, reader);

                TokenStream filter = new ASCIIFoldingFilter(new LemmagenFilter(
                        new LowerCaseFilter(TEST_VERSION_CURRENT,
                                new StandardFilter(TEST_VERSION_CURRENT, source)), "mlteast-sk", TEST_VERSION_CURRENT));
                return new Analyzer.TokenStreamComponents(source, filter);
            }
        };
    }
View Full Code Here
94
95
96
97
98
99
100
101
102
103
104
   
    Analyzer analyzer = new Analyzer() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = factory == null ? new WhitespaceTokenizer(Version.LUCENE_CURRENT, reader) : factory.create(reader);
        TokenStream stream = ignoreCase ? new LowerCaseFilter(Version.LUCENE_CURRENT, tokenizer) : tokenizer;
        return new TokenStreamComponents(tokenizer, stream);
      }
    };

    try {
View Full Code Here
91
92
93
94
95
96
97
98
99
100
101
      Reader reader) {
    if (matchVersion.onOrAfter(Version.LUCENE_36)) {
      final Tokenizer source = new StandardTokenizer(matchVersion, reader);
      // run the widthfilter first before bigramming, it sometimes combines characters.
      TokenStream result = new CJKWidthFilter(source);
      result = new LowerCaseFilter(matchVersion, result);
      result = new CJKBigramFilter(result);
      return new TokenStreamComponents(source, new StopFilter(matchVersion, result, stopwords));
    } else {
      final Tokenizer source = new CJKTokenizer(reader);
      return new TokenStreamComponents(source, new StopFilter(matchVersion, source, stopwords));
View Full Code Here
46
47
48
49
50
51
52
    }
  }

  @Override
  public LowerCaseFilter create(TokenStream input) {
    return new LowerCaseFilter(luceneMatchVersion,input);
  }
View Full Code Here
118
119
120
121
122
123
124
125
126
127
128
  @Override
  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 LatvianStemFilter(result);
    return new TokenStreamComponents(source, result);
View Full Code Here
76
77
78
79
80
81
82
83
84
85
86
      result = new EnglishPossessiveFilter(result);
    // Use a special lowercase filter for turkish, the stemmer expects it.
    if (matchVersion.onOrAfter(Version.LUCENE_31) && name.equals("Turkish"))
      result = new TurkishLowerCaseFilter(result);
    else
      result = new LowerCaseFilter(matchVersion, result);
    if (stopSet != null)
      result = new StopFilter(matchVersion,
                              result, stopSet);
    result = new SnowballFilter(result, name);
    return new TokenStreamComponents(tokenizer, result);
View Full Code Here
119
120
121
122
123
124
125
126
127
128
129
   */
  @Override
  public 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 BulgarianStemFilter(result);
    return new TokenStreamComponents(source, result);
View Full Code Here
120
121
122
123
124
125
126
127
128
129
130
  @Override
  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 SwedishStemmer());
    return new TokenStreamComponents(source, result);
View Full Code Here
172
173
174
175
176
177
178
179
180
181
182
  @Override
  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_36)) {
      result = new GermanNormalizationFilter(result);
      result = new GermanLightStemFilter(result);
View Full Code Here
117
118
119
120
121
122
123
124
125
126
127
  @Override
  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);
    }
    return new TokenStreamComponents(source, new IndonesianStemFilter(result));
View Full Code Here
TOP

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

  • com.code972.elasticsearch.analysis.HebrewExactAnalyzer
  • com.foundationdb.server.service.text.SelectiveCaseAnalyzer
  • com.googlecode.lucene.PorterAnalyzer
  • com.livingsocial.hive.udf.Tokenize$MyAnalyzer
  • de.arago.lucene.util.LowCaseAnalyzer
  • gov.nysenate.openleg.lucene.OpenLegislationAnalyzer
  • org.apache.blur.analysis.NoStopWordStandardAnalyzer
  • org.apache.jackrabbit.oak.plugins.index.lucene.OakAnalyzer
  • 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.