Package org.apache.lucene.analysis.compound

Examples of org.apache.lucene.analysis.compound.DictionaryCompoundWordTokenFilter

43
44
45
46
47
48
49
50
    @Inject public DictionaryCompoundWordTokenFilterFactory(Index index, @IndexSettings Settings indexSettings, Environment env, @Assisted String name, @Assisted Settings settings) {
        super(index, indexSettings, env, name, settings);
    }

    @Override public TokenStream create(TokenStream tokenStream) {
        return new DictionaryCompoundWordTokenFilter(version, tokenStream, wordList,
                minWordSize, minSubwordSize, maxSubwordSize, onlyLongestMatch);
    }
View Full Code Here
65
66
67
68
69
70
71
72
73
      throw new RuntimeException( e );
    }
  }

  public DictionaryCompoundWordTokenFilter create(TokenStream input) {
    return new DictionaryCompoundWordTokenFilter(
        input, dictionary, minWordSize, minSubwordSize, maxSubwordSize, onlyLongestMatch
    );
  }
View Full Code Here
108
109
110
111
112
113
114
115
116
117
118
  public void testDumbCompoundWordsSE() throws Exception {
    String[] dict = { "Bil", "Dörr", "Motor", "Tak", "Borr", "Slag", "Hammar",
        "Pelar", "Glas", "Ögon", "Fodral", "Bas", "Fiol", "Makare", "Gesäll",
        "Sko", "Vind", "Rute", "Torkare", "Blad" };

    DictionaryCompoundWordTokenFilter tf = new DictionaryCompoundWordTokenFilter(
        new WhitespaceTokenizer(
            new StringReader(
                "Bildörr Bilmotor Biltak Slagborr Hammarborr Pelarborr Glasögonfodral Basfiolsfodral Basfiolsfodralmakaregesäll Skomakare Vindrutetorkare Vindrutetorkarblad abba")),
        dict);
View Full Code Here
137
138
139
140
141
142
143
144
145
146
147
  public void testDumbCompoundWordsSELongestMatch() throws Exception {
    String[] dict = { "Bil", "Dörr", "Motor", "Tak", "Borr", "Slag", "Hammar",
        "Pelar", "Glas", "Ögon", "Fodral", "Bas", "Fiols", "Makare", "Gesäll",
        "Sko", "Vind", "Rute", "Torkare", "Blad", "Fiolsfodral" };

    DictionaryCompoundWordTokenFilter tf = new DictionaryCompoundWordTokenFilter(
        new WhitespaceTokenizer(new StringReader("Basfiolsfodralmakaregesäll")),
        dict, CompoundWordTokenFilterBase.DEFAULT_MIN_WORD_SIZE,
        CompoundWordTokenFilterBase.DEFAULT_MIN_SUBWORD_SIZE,
        CompoundWordTokenFilterBase.DEFAULT_MAX_SUBWORD_SIZE, true);
View Full Code Here
47
48
49
50
51
52
53
54
55
56
57
    }

    @Override
    public TokenStream create(TokenStream tokenStream) {
        if (version.onOrAfter(Version.LUCENE_4_4_0)) {
            return new DictionaryCompoundWordTokenFilter(tokenStream, wordList, minWordSize,
                                                         minSubwordSize, maxSubwordSize, onlyLongestMatch);
        } else {
            return new Lucene43DictionaryCompoundWordTokenFilter(tokenStream, wordList, minWordSize,
                                                                 minSubwordSize, maxSubwordSize, onlyLongestMatch);
        }
View Full Code Here
TOP

Related Classes of org.apache.lucene.analysis.compound.DictionaryCompoundWordTokenFilter

  • org.apache.lucene.analysis.compound.TestCompoundWordTokenFilter
  • org.apache.lucene.analysis.Token
  • org.apache.solr.analysis.DictionaryCompoundWordTokenFilterFactory
  • org.elasticsearch.index.analysis.compound.DictionaryCompoundWordTokenFilterFactory
    • 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.