Package org.apache.lucene.analysis.miscellaneous

Examples of org.apache.lucene.analysis.miscellaneous.KeywordMarkerFilter

60
61
62
63
64
65
66
67
68
69
70
    final CharArraySet exclusionSet = new CharArraySet(TEST_VERSION_CURRENT, asSet("sängerinnen"), false);
    Analyzer a = new Analyzer() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer source = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
        TokenStream sink = new KeywordMarkerFilter(source, exclusionSet);
        return new TokenStreamComponents(source, new GermanMinimalStemFilter(sink));
      }
    };
    checkOneTerm(a, "sängerinnen", "sängerinnen");
  }
View Full Code Here
37
38
39
40
41
42
43
44
45
 
  public void testWithKeywordAttribute() throws IOException {
    CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true);
    set.add("fischen");
    GermanStemFilter filter = new GermanStemFilter(
        new KeywordMarkerFilter(new LowerCaseTokenizer(TEST_VERSION_CURRENT, new StringReader(
            "Fischen Trinken")), set));
    assertTokenStreamContents(filter, new String[] { "fischen", "trink" });
  }
View Full Code Here
66
67
68
69
70
71
72
73
74
75
76
    final CharArraySet exclusionSet = new CharArraySet(TEST_VERSION_CURRENT, asSet("sängerinnen"), false);
    Analyzer a = new Analyzer() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer source = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
        TokenStream sink = new KeywordMarkerFilter(source, exclusionSet);
        return new TokenStreamComponents(source, new GermanStemFilter(sink));
      }
    };
    checkOneTerm(a, "sängerinnen", "sängerinnen");
  }
View Full Code Here
279
280
281
282
283
284
285
286
287
  }
 
  public void testWithKeywordAttribute() throws IOException {
    CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true);
    set.add("hole");
    CzechStemFilter filter = new CzechStemFilter(new KeywordMarkerFilter(
        new MockTokenizer(new StringReader("hole desek"), MockTokenizer.WHITESPACE, false), set));
    assertTokenStreamContents(filter, new String[] { "hole", "desk" });
  }
View Full Code Here
129
130
131
132
133
134
135
136
    Tokenizer source = new StandardTokenizer(matchVersion, reader);
    TokenStream result = new LowerCaseFilter(matchVersion, source);
    result = new StandardFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(excltable != null && !excltable.isEmpty())
      result = new KeywordMarkerFilter(result, excltable);
    return new TokenStreamComponents(source, new BrazilianStemFilter(result));
  }
View Full Code Here
74
75
76
77
78
79
80
81
82
83
84
    final CharArraySet exclusionSet = new CharArraySet(TEST_VERSION_CURRENT, asSet("quilométricas"), false);
    Analyzer a = new Analyzer() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer source = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
        TokenStream sink = new KeywordMarkerFilter(source, exclusionSet);
        return new TokenStreamComponents(source, new PortugueseStemFilter(sink));
      }
    };
    checkOneTerm(a, "quilométricas", "quilométricas");
  }
View Full Code Here
101
102
103
104
105
106
107
108
109
110
111
    final CharArraySet exclusionSet = new CharArraySet(TEST_VERSION_CURRENT, asSet("quilométricas"), false);
    Analyzer a = new Analyzer() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer source = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
        TokenStream sink = new KeywordMarkerFilter(source, exclusionSet);
        return new TokenStreamComponents(source, new PortugueseLightStemFilter(sink));
      }
    };
    checkOneTerm(a, "quilométricas", "quilométricas");
  }
View Full Code Here
47
48
49
50
51
52
53
54
55
56
57
    final CharArraySet exclusionSet = new CharArraySet(TEST_VERSION_CURRENT, asSet("あり"), false);
    Analyzer a = new Analyzer() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer source = new JapaneseTokenizer(reader, null, true, JapaneseTokenizer.DEFAULT_MODE);
        TokenStream sink = new KeywordMarkerFilter(source, exclusionSet);
        return new TokenStreamComponents(source, new JapaneseBaseFormFilter(sink));
      }
    };
    assertAnalyzesTo(a, "それはまだ実験段階にあります",
        new String[] { "それ", "は", "まだ", "実験", "段階", "に", "あり", "ます"  }
View Full Code Here
53
54
55
56
57
58
59
60
61
62
63
    final CharArraySet exclusionSet = new CharArraySet(TEST_VERSION_CURRENT, asSet("edeltäjistään"), false);
    Analyzer a = new Analyzer() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer source = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
        TokenStream sink = new KeywordMarkerFilter(source, exclusionSet);
        return new TokenStreamComponents(source, new FinnishLightStemFilter(sink));
      }
    };
    checkOneTerm(a, "edeltäjistään", "edeltäjistään");
  }
View Full Code Here
55
56
57
58
59
60
61
62
 
  public void testWithKeywordAttribute() throws IOException {
    CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true);
    set.add("yourselves");
    Tokenizer tokenizer = new MockTokenizer(new StringReader("yourselves yours"), MockTokenizer.WHITESPACE, false);
    TokenStream filter = new PorterStemFilter(new KeywordMarkerFilter(tokenizer, set));  
    assertTokenStreamContents(filter, new String[] {"yourselves", "your"});
  }
View Full Code Here
TOP

Related Classes of org.apache.lucene.analysis.miscellaneous.KeywordMarkerFilter

  • org.apache.lucene.analysis.ar.ArabicAnalyzer
  • org.apache.lucene.analysis.ar.TestArabicStemFilter
  • org.apache.lucene.analysis.bg.BulgarianAnalyzer
  • org.apache.lucene.analysis.bg.TestBulgarianStemmer
  • org.apache.lucene.analysis.br.BrazilianAnalyzer
  • org.apache.lucene.analysis.br.TestBrazilianStemmer
  • org.apache.lucene.analysis.ca.CatalanAnalyzer
  • org.apache.lucene.analysis.cz.CzechAnalyzer
  • org.apache.lucene.analysis.cz.TestCzechStemmer
  • org.apache.lucene.analysis.da.DanishAnalyzer
    • 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.