Package org.apache.lucene.analysis

Examples of org.apache.lucene.analysis.KeywordMarkerFilter

221
222
223
224
225
226
227
228
    CharArraySet set = new CharArraySet(Version.LUCENE_31, 1, true);
    set.add("строеве");
    MockTokenizer tokenStream = new MockTokenizer(new StringReader("строевете строеве"), MockTokenizer.WHITESPACE, false);

    BulgarianStemFilter filter = new BulgarianStemFilter(
        new KeywordMarkerFilter(tokenStream, set));
    assertTokenStreamContents(filter, new String[] { "строй", "строеве" });
  }
View Full Code Here
46
47
48
49
50
51
52
53
54
  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
58
59
60
61
62
63
64
65
66
67
    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
154
155
156
157
158
159
160
161
162
  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
165
166
167
168
169
170
171
172
173
    CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true);
    set.add("Brasília");
    CharArraySet set1 = new CharArraySet(TEST_VERSION_CURRENT, 1, true);
    set1.add("Brasilia");
    BrazilianStemFilter filter = new BrazilianStemFilter(
        new KeywordMarkerFilter(new LowerCaseTokenizer(TEST_VERSION_CURRENT, new StringReader(
            "Brasília Brasilia")), set), set1);
    assertTokenStreamContents(filter, new String[] { "brasília", "brasilia" });
  }
View Full Code Here
140
141
142
143
144
145
146
147
148
      result = new ElisionFilter(matchVersion, result, DEFAULT_ARTICLES);
    }
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new KeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new CatalanStemmer());
    return new TokenStreamComponents(source, result);
  }
View Full Code Here
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
      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
122
123
124
125
126
127
128
129
  public void testWithKeywordAttribute() throws IOException {
    CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true);
    set.add("ساهدهات");
    ArabicLetterTokenizer tokenStream  = new ArabicLetterTokenizer(TEST_VERSION_CURRENT, new StringReader("ساهدهات"));

    ArabicStemFilter filter = new ArabicStemFilter(new KeywordMarkerFilter(tokenStream, set));
    assertTokenStreamContents(filter, new String[]{"ساهدهات"});
  }
View Full Code Here
280
281
282
283
284
285
286
287
288
  }
 
  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
TOP

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

  • com.github.pmerienne.trident.ml.preprocessing.EnglishTokenizer$EnglishSpecialAnalyzer
  • com.mozilla.grouperfish.lucene.analysis.en.EnglishAnalyzer
  • com.mozilla.grouperfish.lucene.analysis.en.NGramEnglishAnalyzer
  • com.mozilla.grouperfish.transforms.coclustering.lucene.analysis.en.EnglishAnalyzer
  • com.mozilla.grouperfish.transforms.coclustering.lucene.analysis.en.NGramEnglishAnalyzer
  • 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
    • 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.