Package org.carrot2.text.linguistic

Examples of org.carrot2.text.linguistic.IStemmer

56
57
58
59
60
61
62
63
    /**
     * Creates a {@link SpriteBuilder} with the provided parameters and log.
     */
    public SpriteBuilder(SmartSpritesParameters parameters, MessageLog messageLog)
    {
        this(parameters, messageLog, new FileSystemResourceHandler(
            parameters.getDocumentRootDir(), parameters.getCssFileEncoding(), messageLog));
    }
View Full Code Here
56
57
58
59
60
61
62
63
    /**
     * Creates a {@link SpriteBuilder} with the provided parameters and log.
     */
    public SpriteBuilder(SmartSpritesParameters parameters, MessageLog messageLog)
    {
        this(parameters, messageLog, new FileSystemResourceHandler(
            parameters.getDocumentRootDir(), parameters.getCssFileEncoding(), messageLog));
    }
View Full Code Here
18
19
20
21
22
23
24
25
    @Before
    public void prepare()
    {
        spriteDirectiveOccurrenceCollector = new SpriteDirectiveOccurrenceCollector(
            messageLog, new FileSystemResourceHandler(null,
                SmartSpritesParameters.DEFAULT_CSS_FILE_ENCODING, messageLog));
    }
View Full Code Here
56
57
58
59
60
61
62
63
       */
    case ARABIC:
      // Intentional fall-through.

    default:
      return new ExtendedWhitespaceTokenizer();
    }
  }
View Full Code Here
84
85
86
87
88
89
90
91
    static ITokenizer createTokenizer() {
      try {
        return new ChineseTokenizer();
      } catch (Throwable e) {
        return new ExtendedWhitespaceTokenizer();
      }
    }
View Full Code Here
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
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
97
98
99
100
101
102
103
104
105
106
107
        {
            // 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("stemmer");
            return new IStemmer()
            {
                public CharSequence stem(CharSequence word)
                {
                    // Some contrived stemming algorithm
                    return word.length() > 3 ? word.subSequence(0, word.length() - 2)
View Full Code Here
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
    /**
     * Performs stemming and saves the results to the <code>context</code>.
     */
    public void stem(PreprocessingContext context)
    {
        final IStemmer stemmer = context.language.getStemmer();

        final char [][] wordImages = context.allWords.image;
        final char [][] stemImages = new char [wordImages.length] [];

        final MutableCharArray mutableCharArray = new MutableCharArray(CharArrayUtils.EMPTY_ARRAY);
        char [] buffer = new char [128];

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

            final boolean different = CharArrayUtils.toLowerCase(word, buffer);

            mutableCharArray.reset(buffer, 0, word.length);
            final CharSequence stemmed = stemmer.stem(mutableCharArray);
            if (stemmed != null)
            {
                mutableCharArray.reset(stemmed);
                stemImages[i] = context.intern(mutableCharArray);
            }
View Full Code Here
19
20
21
22
23
24
25
26
27
28
29
public final class TestStemmerFactory implements IStemmerFactory
{
    @Override
    public IStemmer getStemmer(LanguageCode language)
    {
        return new IStemmer()
        {
            public CharSequence stem(CharSequence word)
            {
                if (word.length() > 2)
                {
View Full Code Here
TOP

Related Classes of org.carrot2.text.linguistic.IStemmer

  • com.carrotsearch.hppc.BitSet
  • com.carrotsearch.hppc.IntArrayList
  • com.carrotsearch.hppc.IntIntOpenHashMap
  • com.carrotsearch.hppc.IntStack
  • com.tamingtext.carrot2.Carrot2ExampleTest
  • org.apache.http.message.BasicNameValuePair
  • org.apache.lucene.search.IndexSearcher
  • org.apache.mahout.math.matrix.DoubleMatrix2D
  • org.carrot2.clustering.kmeans.BisectingKMeansClusteringAlgorithm
  • org.carrot2.clustering.kmeans.BisectingKMeansClusteringAlgorithmTest
    • 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.