Package net.yacy.document

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
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
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
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
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
TOP

Related Classes of net.yacy.document.WordTokenizer

  • de.anomic.data.ymark.YMarkAutoTagger
  • ViewFile
  • java.io.ByteArrayInputStream
    • 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.