Package org.apache.lucene.analysis

Examples of org.apache.lucene.analysis.KeywordTokenizer

54
55
56
57
58
59
60
61
62
63
64
 
  public void testEmptyTerm() throws IOException {
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new KeywordTokenizer(reader);
        return new TokenStreamComponents(tokenizer, new SwedishLightStemFilter(tokenizer));
      }
    };
    checkOneTermReuse(a, "", "");
  }
View Full Code Here
47
48
49
50
51
52
53
54
55
56
57
 
  public void testEmptyTerm() throws IOException {
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new KeywordTokenizer(reader);
        return new TokenStreamComponents(tokenizer, new IrishLowerCaseFilter(tokenizer));
      }
    };
    checkOneTermReuse(a, "", "");
  }
View Full Code Here
136
137
138
139
140
141
142
143
144
145
146
 
  public void testEmptyTerm() throws IOException {
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new KeywordTokenizer(reader);
        return new TokenStreamComponents(tokenizer, new IndonesianStemFilter(tokenizer));
      }
    };
    checkOneTermReuse(a, "", "");
  }
View Full Code Here
55
56
57
58
59
60
61
62
63
64
65
 
  public void testEmptyTerm() throws IOException {
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new KeywordTokenizer(reader);
        return new TokenStreamComponents(tokenizer, new NorwegianMinimalStemFilter(tokenizer));
      }
    };
    checkOneTermReuse(a, "", "");
  }
View Full Code Here
68
69
70
71
72
73
74
75
76
77
78
 
  public void testEmptyTerm() throws IOException {
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new KeywordTokenizer(reader);
        return new TokenStreamComponents(tokenizer, new PersianNormalizationFilter(tokenizer));
      }
    };
    checkOneTermReuse(a, "", "");
  }
View Full Code Here
55
56
57
58
59
60
61
62
63
64
65
 
  public void testEmptyTerm() throws IOException {
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new KeywordTokenizer(reader);
        return new TokenStreamComponents(tokenizer, new NorwegianLightStemFilter(tokenizer));
      }
    };
    checkOneTermReuse(a, "", "");
  }
View Full Code Here
68
69
70
71
72
73
74
75
76
77
78
 
  public void testEmptyTerm() throws IOException {
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new KeywordTokenizer(reader);
        return new TokenStreamComponents(tokenizer, new FrenchMinimalStemFilter(tokenizer));
      }
    };
    checkOneTermReuse(a, "", "");
  }
View Full Code Here
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
    final String[] dict = { "a", "e", "i", "o", "u", "y", "bc", "def" };
    Analyzer a = new ReusableAnalyzerBase() {

      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new KeywordTokenizer(reader);
        return new TokenStreamComponents(tokenizer, new DictionaryCompoundWordTokenFilter(TEST_VERSION_CURRENT, tokenizer, dict));
      }
    };
    checkOneTermReuse(a, "", "");
   
    InputSource is = new InputSource(getClass().getResource("da_UTF8.xml").toExternalForm());
    final HyphenationTree hyphenator = HyphenationCompoundWordTokenFilter.getHyphenationTree(is);
    Analyzer b = new ReusableAnalyzerBase() {

      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new KeywordTokenizer(reader);
        TokenFilter filter = new HyphenationCompoundWordTokenFilter(TEST_VERSION_CURRENT, tokenizer, hyphenator);
        return new TokenStreamComponents(tokenizer, filter);
      }
    };
    checkOneTermReuse(b, "", "");
View Full Code Here
168
169
170
171
172
173
174
175
176
177
178
 
  public void testEmptyTerm() throws IOException {
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new KeywordTokenizer(reader);
        return new TokenStreamComponents(tokenizer, new FrenchLightStemFilter(tokenizer));
      }
    };
    checkOneTermReuse(a, "", "");
  }
View Full Code Here
69
70
71
72
73
74
75
76
77
78
79
 
  public void testEmptyTerm() throws IOException {
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new KeywordTokenizer(reader);
        return new TokenStreamComponents(tokenizer, new CJKWidthFilter(tokenizer));
      }
    };
    checkOneTermReuse(a, "", "");
  }
View Full Code Here
TOP

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

  • it.unibz.instasearch.indexing.QueryAnalyzer
  • org.apache.lucene.analysis.ar.TestArabicNormalizationFilter
  • org.apache.lucene.analysis.ar.TestArabicStemFilter
  • org.apache.lucene.analysis.bg.TestBulgarianStemmer
  • org.apache.lucene.analysis.br.TestBrazilianStemmer
  • org.apache.lucene.analysis.cjk.TestCJKAnalyzer
  • org.apache.lucene.analysis.cjk.TestCJKWidthFilter
  • org.apache.lucene.analysis.cn.smart.TestSmartChineseAnalyzer
  • org.apache.lucene.analysis.compound.TestCompoundWordTokenFilter
  • org.apache.lucene.analysis.cz.TestCzechStemmer
    • 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.