Package org.apache.lucene.analysis.miscellaneous

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

143
144
145
146
147
148
149
150
151
    // 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
68
69
70
71
72
73
74
75
76
77
78
    final CharArraySet exclusionSet = new CharArraySet(TEST_VERSION_CURRENT, asSet("コーヒー"), 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 JapaneseKatakanaStemFilter(sink));
      }
    };
    checkOneTerm(a, "コーヒー", "コーヒー");
  }
View Full Code Here
120
121
122
123
124
125
126
127
128
    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);
    }
    return new TokenStreamComponents(source, new IndonesianStemFilter(result));
  }
View Full Code Here
124
125
126
127
128
129
130
131
132
    final Tokenizer source = new StandardTokenizer(matchVersion, reader);
    TokenStream result = new StandardFilter(matchVersion, source);
    result = new TurkishLowerCaseFilter(result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new KeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new TurkishStemmer());
    return new TokenStreamComponents(source, result);
  }
View Full Code Here
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
      if (matchVersion.onOrAfter(Version.LUCENE_31)) {
        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 org.tartarus.snowball.ext.RussianStemmer());
        return new TokenStreamComponents(source, result);
      } else {
        final Tokenizer source = new RussianLetterTokenizer(matchVersion, reader);
        TokenStream result = new LowerCaseFilter(matchVersion, source);
        result = new StopFilter(matchVersion, result, stopwords);
        if (!stemExclusionSet.isEmpty()) result = new KeywordMarkerFilter(
          result, stemExclusionSet);
        result = new SnowballFilter(result, new org.tartarus.snowball.ext.RussianStemmer());
        return new TokenStreamComponents(source, result);
      }
    }
View Full Code Here
120
121
122
123
124
125
126
127
128
    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 LatvianStemFilter(result);
    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 BulgarianStemFilter(result);
    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 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 FinnishStemmer());
    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 SwedishStemmer());
    return new TokenStreamComponents(source, result);
  }
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.