Examples of WordTokenizer

Examples of com.dci.intellij.dbn.common.util.WordTokenizer

50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
    public MySqlArgumentsResultSet(ResultSet resultSet) throws SQLException {
        List<Argument> argumentList = new ArrayList<Argument>();
        while (resultSet.next()) {
            String argumentsString = resultSet.getString("ARGUMENTS");
            WordTokenizer wordTokenizer = new WordTokenizer(argumentsString);

            String methodName = resultSet.getString("METHOD_NAME");
            String methodType = resultSet.getString("METHOD_TYPE");
            boolean betweenBrackets = false;
            boolean typePostfixSet = false;
            int argumentPosition = methodType.equals("FUNCTION") ? 0 : 1;

            Argument argument = null;

            for (String token : wordTokenizer.getTokens()) {
                if (argument == null) {
                    typePostfixSet = false;
                    argument = new Argument();
                    argument.methodName = methodName;
                    argument.methodType = methodType;
View Full Code Here

Examples of edu.harvard.wcfia.yoshikoder.document.tokenizer.WordTokenizer

266
267
268
269
270
271
272
273
     * Tokenizes the document using a WordTokenizer.  This is not the final version.
     *
     */
    protected void tokenize() throws IOException {
        String txt = getText();
        WordTokenizer tok = new WordTokenizer(getLocale());
        tokenSpans = tok.getTokenSpans(txt);
    }
View Full Code Here

Examples of net.yacy.document.WordTokenizer

288
289
290
291
292
293
294
295
296
297
298
                    // Search word highlighting
                    for (final StringBuilder s: sentences) {
                        sentence = s.toString();
                        Enumeration<String> tokens = null;
                        tokens = new WordTokenizer(new ByteArrayInputStream(UTF8.getBytes(sentence)), LibraryProvider.dymLib);
                        while (tokens.hasMoreElements()) {
                            token = tokens.nextElement();
                            if (token.length() > 0) {
                                prop.put("viewMode_words_" + i + "_nr", i + 1);
                                prop.put("viewMode_words_" + i + "_word", token);
View Full Code Here

Examples of net.yacy.document.WordTokenizer

98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
      final int bufferSize = document.dc_title().length() + document.dc_description().length() + document.dc_subject(' ').length() + 32;
      final StringBuilder buffer = new StringBuilder(bufferSize);
      buffer.append(document.dc_title());
      buffer.append(document.dc_description());
      buffer.append(document.dc_subject(' '));
      final Enumeration<String> tokens = new WordTokenizer(new ByteArrayInputStream(UTF8.getBytes(buffer.toString())), LibraryProvider.dymLib);

      int count = 0;

      // loop through potential tag and rank them
      while(tokens.hasMoreElements()) {
        count = 0;
        token = tokens.nextElement();

        /*
        pair.delete(0, pair.indexOf(SPACE)+1);
        if(pair.length() > 1)
          pair.append(SPACE);
View Full Code Here

Examples of net.yacy.document.WordTokenizer

288
289
290
291
292
293
294
295
296
297
298
                    // Search word highlighting
                    for (final StringBuilder s: sentences) {
                        sentence = s.toString();
                        Enumeration<StringBuilder> tokens = null;
                        tokens = new WordTokenizer(new ByteArrayInputStream(UTF8.getBytes(sentence)), LibraryProvider.dymLib);
                        while (tokens.hasMoreElements()) {
                            token = tokens.nextElement();
                            if (token.length() > 0) {
                                prop.put("viewMode_words_" + i + "_nr", i + 1);
                                prop.put("viewMode_words_" + i + "_word", token);
View Full Code Here

Examples of net.yacy.document.WordTokenizer

93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
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
      final StringBuilder buffer = new StringBuilder(bufferSize);
      final StringBuilder pwords = new StringBuilder(1000);
      buffer.append(document.dc_title().toLowerCase());
      buffer.append(document.dc_description().toLowerCase());
      buffer.append(document.dc_subject(' ').toLowerCase());
      final Enumeration<StringBuilder> tokens = new WordTokenizer(new ByteArrayInputStream(UTF8.getBytes(buffer.toString())), LibraryProvider.dymLib);
      int score = 0;
     
      // get phrases
      final TreeMap<String, YMarkTag> phrases = getPhrases(document, 2);
      phrases.putAll(getPhrases(document, 3));
      final Iterator<String> iter = phrases.keySet().iterator();
      while(iter.hasNext()) {
        score = 10;
        final String phrase = iter.next();             
        if(phrases.get(phrase).size() > 3 && phrases.get(phrase).size() < 10) {
          score = phrases.get(phrase).size() * phrase.split(" ").length * 20;
        }
        if(isDigitSpace(phrase)) {
          score = 10;
        }
        if(phrases.get(phrase).size() > 2 && buffer.indexOf(phrase) > 1) {         
          score = score * 10;
        }
        if (tags.containsKey(phrase)) {
          score = score * 20;
        }
        topwords.add(new YMarkTag(phrase, score));
        pwords.append(phrase);
        pwords.append(' ');
      }
     
      // loop through potential tag and rank them
      while(tokens.hasMoreElements()) {       
        score = 0;
        token = tokens.nextElement();
       
        // check if the token appears in the text
        if (words.containsKey(token.toString())) {         
          final Word word = words.get(token.toString());
          // token appears in text and matches an existing bookmark tag
View Full Code Here

Examples of net.yacy.document.WordTokenizer

168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
  } 
 
  private static TreeMap<String, YMarkTag> getPhrases(final Document document, final int size) {
    final TreeMap<String, YMarkTag> phrases = new TreeMap<String, YMarkTag>();
    final StringBuilder phrase = new StringBuilder(128);
    final Enumeration<StringBuilder> tokens = new WordTokenizer(document.getText(), LibraryProvider.dymLib);
    StringBuilder token;
    int count = 0;
   
    // loop through text
    while(tokens.hasMoreElements()) {       

      token = tokens.nextElement();     
      if(stopwords.contains(token.toString()) || isDigitSpace(token.toString()))
        continue;     
     
      // if we have a full phrase, delete the first token
      count++;
View Full Code Here

Examples of org.apache.lucene.analysis.cn.smart.WordTokenizer

85
86
87
88
89
90
91
92
93
94
95
    wordSegment = new WordSegmenter();
  }

  public TokenStream tokenStream(String fieldName, Reader reader) {
    TokenStream result = new SentenceTokenizer(reader);
    result = new WordTokenizer(result, wordSegment);
    // result = new LowerCaseFilter(result);
    // 不再需要LowerCaseFilter，因为SegTokenFilter已经将所有英文字符转换成小写
    // stem太严格了, This is not bug, this feature:)
    result = new PorterStemFilter(result);
    if (stopWords != null) {
View Full Code Here

Examples of org.languagetool.tokenizers.WordTokenizer

36
37
38
39
40
41
42
43
44
45
  private DemoDisambiguator disamb2;
 
  @Override
  public void setUp() {
    tagger = new EnglishTagger();
    tokenizer = new WordTokenizer();
    sentenceTokenizer = new SentenceTokenizer();
    disambiguator = new EnglishRuleDisambiguator();
    disamb2 = new DemoDisambiguator();
  }
View Full Code Here

Examples of org.languagetool.tokenizers.WordTokenizer

31
32
33
34
35
36
37
  private WordTokenizer tokenizer;
     
  @Override
  public void setUp() {
    tagger = new DutchTagger();
    tokenizer = new WordTokenizer();
  }
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.