Package org.apache.lucene.analysis

Examples of org.apache.lucene.analysis.CharArraySet$CharArraySetIterator

230
231
232
233
234
235
236
      this.enablePositionIncrements = enablePositionIncrements;
    }
    @Override
    public TokenStream tokenStream(String fieldName, Reader reader) {
      TokenStream ts = a.tokenStream(fieldName,reader);
      return new StopFilter(enablePositionIncrements, ts, new CharArraySet(Collections.singleton("stop"), true));
    }
View Full Code Here
232
233
234
235
236
237
238
    }
    @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
107
108
109
110
111
112
113
114
115
116
117
118
          new String[] { "знан", "эт", "хран", "тайн" });
    }
   
   
    public void testWithStemExclusionSet() throws Exception {
      CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true);
      set.add("представление");
      Analyzer a = new RussianAnalyzer(TEST_VERSION_CURRENT, RussianAnalyzer.getDefaultStopSet() , set);
      assertAnalyzesToReuse(a, "Вместе с тем о силе электромагнитной энергии имели представление еще",
          new String[] { "вмест", "сил", "электромагнитн", "энерг", "имел", "представление" });
    
    }
View Full Code Here
36
37
38
39
40
41
42
43
44
45
  }
 
  public void testExclusionTableBWCompat() throws IOException {
    GermanStemFilter filter = new GermanStemFilter(new LowerCaseTokenizer(TEST_VERSION_CURRENT,
        new StringReader("Fischen Trinken")));
    CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true);
    set.add("fischen");
    filter.setExclusionSet(set);
    assertTokenStreamContents(filter, new String[] { "fischen", "trink" });
  }
View Full Code Here
43
44
45
46
47
48
49
50
51
52
53
54
    filter.setExclusionSet(set);
    assertTokenStreamContents(filter, new String[] { "fischen", "trink" });
  }

  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
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
            "Fischen Trinken")), set));
    assertTokenStreamContents(filter, new String[] { "fischen", "trink" });
  }

  public void testWithKeywordAttributeAndExclusionTable() throws IOException {
    CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true);
    set.add("fischen");
    CharArraySet set1 = new CharArraySet(TEST_VERSION_CURRENT, 1, true);
    set1.add("trinken");
    set1.add("fischen");
    GermanStemFilter filter = new GermanStemFilter(
        new KeywordMarkerFilter(new LowerCaseTokenizer(TEST_VERSION_CURRENT, new StringReader(
            "Fischen Trinken")), set));
    filter.setExclusionSet(set1);
    assertTokenStreamContents(filter, new String[] { "fischen", "trinken" });
View Full Code Here
68
69
70
71
72
73
74
75
76
77
   
    assertAnalyzesTo(a, "градове", new String[] {"град"});
  }
 
  public void testWithStemExclusionSet() throws IOException {
    CharArraySet set = new CharArraySet(Version.LUCENE_31, 1, true);
    set.add("строеве");
    Analyzer a = new BulgarianAnalyzer(TEST_VERSION_CURRENT, CharArraySet.EMPTY_SET, set);
    assertAnalyzesTo(a, "строевете строеве", new String[] { "строй", "строеве" });
  }
View Full Code Here
211
212
213
214
215
216
217
218
219
220
221
222
    assertAnalyzesTo(a, "строя", new String[] {"стр"});
    assertAnalyzesTo(a, "строят", new String[] {"стр"});
  }

  public void testWithKeywordAttribute() throws IOException {
    CharArraySet set = new CharArraySet(Version.LUCENE_31, 1, true);
    set.add("строеве");
    WhitespaceTokenizer tokenStream = new WhitespaceTokenizer(TEST_VERSION_CURRENT,
        new StringReader("строевете строеве"));

    BulgarianStemFilter filter = new BulgarianStemFilter(
        new KeywordMarkerFilter(tokenStream, set));
View Full Code Here
139
140
141
142
143
144
145
146
147
148
149
    a.setStemExclusionTable(new String[] { "quintessência" });
    checkReuse(a, "quintessência", "quintessência"); // excluded words will be completely unchanged.
  }
 
  public void testStemExclusionTableBWCompat() throws IOException {
    CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true);
    set.add("Brasília");
    BrazilianStemFilter filter = new BrazilianStemFilter(
        new LowerCaseTokenizer(TEST_VERSION_CURRENT, new StringReader("Brasília Brasilia")), set);
    assertTokenStreamContents(filter, new String[] { "brasília", "brasil" });
  }
View Full Code Here
147
148
149
150
151
152
153
154
155
156
157
158
        new LowerCaseTokenizer(TEST_VERSION_CURRENT, new StringReader("Brasília Brasilia")), set);
    assertTokenStreamContents(filter, new String[] { "brasília", "brasil" });
  }

  public void testWithKeywordAttribute() throws IOException {
    CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true);
    set.add("Brasília");
    BrazilianStemFilter filter = new BrazilianStemFilter(
        new KeywordMarkerFilter(new LowerCaseTokenizer(TEST_VERSION_CURRENT, new StringReader(
            "Brasília Brasilia")), set));
    assertTokenStreamContents(filter, new String[] { "brasília", "brasil" });
  }
View Full Code Here
TOP

Related Classes of org.apache.lucene.analysis.CharArraySet$CharArraySetIterator

  • com.github.le11.nls.lucene.TypeAwareStopFilter
  • com.github.le11.nls.solr.TypeAwareStopFilterFactory
  • de.jetwick.solrplugin.TWordDelimiterFilterFactory
  • edu.wiki.index.WikipediaAnalyzer
  • org.apache.lucene.analysis.ar.TestArabicAnalyzer
  • org.apache.lucene.analysis.ar.TestArabicStemFilter
  • org.apache.lucene.analysis.bg.TestBulgarianAnalyzer
  • org.apache.lucene.analysis.bg.TestBulgarianStemmer
  • org.apache.lucene.analysis.br.TestBrazilianStemmer
  • org.apache.lucene.analysis.ca.TestCatalanAnalyzer
    • 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.