Package org.apache.lucene.analysis

Examples of org.apache.lucene.analysis.KeywordMarkerFilter

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
182
183
184
185
186
187
188
189
190
    // the order here is important: the stopword list is not normalized!
    result = new StopFilter( matchVersion, result, stopwords);
    // TODO maybe we should make ArabicNormalization filter also KeywordAttribute aware?!
    result = new ArabicNormalizationFilter(result);
    if(!stemExclusionSet.isEmpty()) {
      result = new KeywordMarkerFilter(result, stemExclusionSet);
    }
    return new TokenStreamComponents(source, new ArabicStemFilter(result));
  }
View Full Code Here
126
127
128
129
130
131
132
133
134
    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 KeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new RomanianStemmer());
    return new TokenStreamComponents(source, result);
  }
View Full Code Here
217
218
219
220
221
222
223
224
    set.add("строеве");
    WhitespaceTokenizer tokenStream = new WhitespaceTokenizer(TEST_VERSION_CURRENT,
        new StringReader("строевете строеве"));

    BulgarianStemFilter filter = new BulgarianStemFilter(
        new KeywordMarkerFilter(tokenStream, set));
    assertTokenStreamContents(filter, new String[] { "строй", "строеве" });
  }
View Full Code Here
122
123
124
125
126
127
128
129
130
    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 KeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new DanishStemmer());
    return new TokenStreamComponents(source, result);
  }
View Full Code Here
122
123
124
125
126
127
128
129
130
    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 KeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new ItalianStemmer());
    return new TokenStreamComponents(source, result);
  }
View Full Code Here
134
135
136
137
138
139
140
141
142
    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 KeywordMarkerFilter(result, stemExclusionSet);
    result = new BulgarianStemFilter(result);
    return new TokenStreamComponents(source, result);
  }
View Full Code Here
121
122
123
124
125
126
127
128
129
    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 KeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new ArmenianStemmer());
    return new TokenStreamComponents(source, result);
  }
View Full Code Here
122
123
124
125
126
127
128
129
130
    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 KeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new SpanishStemmer());
    return new TokenStreamComponents(source, result);
  }
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.