Examples of ILexicalData

Examples of org.carrot2.text.linguistic.ILexicalData

109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
    }
    return solrStopWords.get(fieldName);
  }

  public ILexicalData getLexicalData(LanguageCode languageCode) {
    final ILexicalData carrot2LexicalData = carrot2LexicalDataFactory
        .getLexicalData(languageCode);

    return new ILexicalData() {
      public boolean isStopLabel(CharSequence word) {
        // Nothing in Solr maps to the concept of a stop label,
        // so return Carrot2's default here.
        return carrot2LexicalData.isStopLabel(word);
      }

      public boolean isCommonWord(MutableCharArray word) {
        // Loop over the fields involved in clustering first
        for (String fieldName : fieldNames) {
          for (CharArraySet stopWords : getSolrStopWordsForField(fieldName)) {
            if (stopWords.contains(word)) {
              return true;
            }
          }
        }
        // Check default Carrot2 stop words too
        return carrot2LexicalData.isCommonWord(word);
      }
    };
  }
View Full Code Here

Examples of org.carrot2.text.linguistic.ILexicalData

67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
      return;
    }

    // Test with Maltese so that the English clustering performed in other tests
    // is not affected by the test stopwords and stoplabels.
    ILexicalData lexicalData = preprocessing.lexicalDataFactory
        .getLexicalData(LanguageCode.MALTESE);

    for (String word : wordsToCheck.split(",")) {
      if (!lexicalData.isCommonWord(new MutableCharArray(word))
          && !lexicalData.isStopLabel(word)) {
        clusters.add(new Cluster(word));
      }
    }
  }
View Full Code Here

Examples of org.carrot2.text.linguistic.ILexicalData

134
135
136
137
138
139
140
141
142
143
144
        {
            // Here we always return the same language model, regardless of the requested
            // language. In your implementation you may want to return different models
            // based on the language, if needed.
            System.out.println("lexical data");
            return new ILexicalData()
            {
                @Override
                public boolean isStopLabel(CharSequence formattedLabel)
                {
                    return formattedLabel.length() <= 4;
View Full Code Here

Examples of org.carrot2.text.linguistic.ILexicalData

40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
        final char [][] wordImages = context.allWords.image;
        final short [] types = context.allWords.type;

        final MutableCharArray mutableCharArray = new MutableCharArray("");
        char [] buffer = new char [128];
        final ILexicalData lexData = context.language.getLexicalData();

        for (int i = 0; i < wordImages.length; i++)
        {
            final char [] word = wordImages[i];
            if (buffer.length < word.length) buffer = new char [word.length];

            CharArrayUtils.toLowerCase(word, buffer);
            mutableCharArray.reset(buffer, 0, word.length);
            if (lexData.isCommonWord(mutableCharArray))
            {
                types[i] |= ITokenizer.TF_COMMON_WORD;
            }
        }
    }
View Full Code Here

Examples of org.carrot2.text.linguistic.ILexicalData

559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
                return -Float.compare(c1.score, c2.score);
            }
        });

        j = 0;
        ILexicalData lexicalData = context.language.getLexicalData();
        for (int max = candidates.size(), i = 0; i < max && j < maxBaseClusters; i++)
        {
            ClusterCandidate cc = candidates.get(i);
            // Build the candidate cluster's label for filtering. This may be costly so
            // we only do this for base clusters which are promoted to merging phase.
            assert cc.phrases.size() == 1;
            if (!lexicalData.isStopLabel(buildLabel(cc.phrases.get(0))))
            {
                candidates.set(j++, cc);
            }
        }
View Full Code Here

Examples of org.carrot2.text.linguistic.ILexicalData

20
21
22
23
24
25
26
27
28
29
30
public final class TestLexicalDataFactory implements ILexicalDataFactory
{
    @Override
    public ILexicalData getLexicalData(LanguageCode language)
    {
        return new ILexicalData()
        {
            public boolean isCommonWord(MutableCharArray word)
            {
                return word.toString().contains("stop");
            }
View Full Code Here

Examples of org.carrot2.text.linguistic.ILexicalData

51
52
53
54
55
56
57
58
59
60
61
    }

    @Override
    public ILexicalData getLexicalData(LanguageCode language)
    {
        return new ILexicalData()
        {
            public boolean isCommonWord(MutableCharArray word)
            {
                return word.toString().contains("stop");
            }
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.