Package org.carrot2.text.analysis

Examples of org.carrot2.text.analysis.ITokenizer

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
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
        documentIndices = new IntArrayList();
        fieldIndices = new ByteArrayList();

        final Iterator<Document> docIterator = documents.iterator();
        int documentIndex = 0;
        final ITokenizer ts = context.language.getTokenizer();
        final MutableCharArray wrapper = new MutableCharArray(CharArrayUtils.EMPTY_ARRAY);

        while (docIterator.hasNext())
        {
            final Document doc = docIterator.next();

            boolean hadTokens = false;
            for (int i = 0; i < fieldNames.length; i++)
            {
                final byte fieldIndex = (byte) i;
                final String fieldName = fieldNames[i];
                final String fieldValue = doc.getField(fieldName);

                if (!StringUtils.isEmpty(fieldValue))
                {
                    try
                    {
                        short tokenType;

                        ts.reset(new StringReader(fieldValue));
                        if ((tokenType = ts.nextToken()) != ITokenizer.TT_EOF)
                        {
                            if (hadTokens) addFieldSeparator(documentIndex);
                            do
                            {
                                ts.setTermBuffer(wrapper);
                                add(documentIndex, fieldIndex, context.intern(wrapper), tokenType);
                            } while ( (tokenType = ts.nextToken()) != ITokenizer.TT_EOF);
                            hadTokens = true;
                        }
                    }
                    catch (IOException e)
                    {
View Full Code Here
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
     */
    protected void assertEqualTokens(String testString, TokenImage [] expectedTokens)
    {
        try
        {
            final ITokenizer tokenStream = createTokenStream();
            tokenStream.reset(new StringReader(testString));

            final ArrayList<TokenImage> tokens = new ArrayList<TokenImage>();
            short token;
            MutableCharArray buffer = new MutableCharArray();
            while ((token = tokenStream.nextToken()) >= 0)
            {
                tokenStream.setTermBuffer(buffer);
                tokens.add(new TokenImage(buffer.toString(), token));
            }

            for (int i = 0; i < tokens.size(); i++) {
            }       
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
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
     * one <code>language</code>.
     */
    private void cluster(LanguageCode language)
    {
        // Preprocessing of documents
        final PreprocessingContext context = preprocessingPipeline.preprocess(documents,
            query, language);

        // Further processing only if there are words to process
        clusters = Lists.newArrayList();
        if (context.hasLabels())
        {
            // Term-document matrix building and reduction
            final VectorSpaceModelContext vsmContext = new VectorSpaceModelContext(
                context);
            final ReducedVectorSpaceModelContext reducedVsmContext = new ReducedVectorSpaceModelContext(
View Full Code Here
TOP

Related Classes of org.carrot2.text.analysis.ITokenizer

  • com.carrotsearch.hppc.BitSet
  • com.carrotsearch.hppc.IntArrayList
  • com.carrotsearch.hppc.IntIntOpenHashMap
  • 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
  • org.carrot2.clustering.lingo.ClusterBuilder
    • 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.