Package edu.harvard.wcfia.yoshikoder.document.tokenizer

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

117
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
157
158
159
160
161
162
163
164
165
        // TODO remove redundant code here!
       
        // FIRST DOC
        YKDocument doc1 = (YKDocument)docs.get(0);
        // tokenize the document
        TokenizationCache tcache = yoshikoder.getTokenizationCache();
        TokenList tl1 = tcache.getTokenList(doc1);
        if (tl1 == null)
          tl1 = TokenizationService.getTokenizationService().tokenize(doc1);
       
        // for _all_ categories
        EntryFrequencyMap efm1 = new EntryFrequencyMap(dict.getDictionaryRoot(), tl1);
        List lkeys = efm1.getSortedCategoryEntries();
        Node[] keys = (Node[])lkeys.toArray(new Node[lkeys.size()]);
        int[] counts = new int[keys.length+1];
        for (int ii=0; ii<keys.length; ii++) {
          Integer cnt = (Integer) efm1.getEntryCount(keys[ii]);
          counts[ii] = cnt.intValue();
        }
        // add N
        counts[keys.length] = efm1.getTokenTotal();

        HSSFWorkbook wb = new HSSFWorkbook();
        HSSFRow row;
        HSSFCell cell;

        HSSFSheet sheet = wb.createSheet("Category frequencies");

        // header
        row = sheet.createRow((short)0);
        for (int c=0; c<keys.length; c++){
          cell = row.createCell((short)(c+1));
          cell.setEncoding(HSSFCell.ENCODING_UTF_16);
          String nodepath = efm1.getEntryPath(keys[c]);
          cell.setCellValue(nodepath);
        }
        cell = row.createCell((short)(keys.length+1));
        cell.setEncoding(HSSFCell.ENCODING_UTF_16);
        cell.setCellValue("Total");

        int rownum = 1;
        for (Iterator iter = docs.iterator(); iter.hasNext();) {
          YKDocument d = (YKDocument) iter.next();
          TokenList tl2 = tcache.getTokenList(d);
          if (tl2 == null)
            tl2 = TokenizationService.getTokenizationService().tokenize(d);
          Concordance conc = dict.getConcordance(tl2, catnode, wsize);
         
          // note _all_categories counted (implicitly around catnode matches)
View Full Code Here
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
    tworker = new TaskWorker(yoshikoder){
      protected void doWork() throws Exception {
        // FIRST DOC
        YKDocument doc1 = (YKDocument)docs.get(0);
        // tokenize the document
        TokenizationCache tcache = yoshikoder.getTokenizationCache();
        TokenList tl1 = tcache.getTokenList(doc1);
        if (tl1 == null)
          tl1 = TokenizationService.getTokenizationService().tokenize(doc1);

        // compute the dictionary counts
        EntryFrequencyMap efm1 = new EntryFrequencyMap(dict.getDictionaryRoot(), tl1);
        List lkeys = efm1.getSortedCategoryEntries();
        Node[] keys = (Node[])lkeys.toArray(new Node[lkeys.size()]);
        int[] counts = new int[keys.length+1];
        for (int ii=0; ii<keys.length; ii++) {
          Integer cnt = (Integer) efm1.getEntryCount(keys[ii]);
          counts[ii] = cnt.intValue();
        }
        // add N
        counts[keys.length] = efm1.getTokenTotal();

        for (int ii = 0; ii < keys.length; ii++) {
          String nodepath = efm1.getEntryPath(keys[ii]);

          writer.write(",");
          writer.write(FileUtil.escapeForCsv(nodepath));
        }
        writer.write(",Total\n");

        // and the rest
        for (Iterator iter = docs.iterator(); iter.hasNext();) {
          YKDocument d = (YKDocument) iter.next();
          TokenList tl2 = tcache.getTokenList(d);
          if (tl2 == null)
            tl2 = TokenizationService.getTokenizationService().tokenize(d);
          Concordance conc = dict.getConcordance(tl2, catnode, wsize);
         
          counts = getDocumentStats(d.getTitle(), conc, keys, dict.getDictionaryRoot());
View Full Code Here
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
        super(yk, MakeConcordanceAction.class.getName());       
    }
   
    protected Map<YKDocument,Concordance> makeMultipleDocumentConcordance(YKDocument[] docs, Node n, int wsize) throws TokenizationException, IOException {
      //Concordance con = new ConcordanceImpl(wsize);
      TokenizationCache tcache = yoshikoder.getTokenizationCache();
      TokenizationService service = TokenizationService.getTokenizationService();
      Map<YKDocument,Concordance> map = new HashMap<YKDocument,Concordance>();
      for (YKDocument doc : docs) {
        TokenList tl = tcache.getTokenList(doc);
        if (tl == null){
          tl = service.tokenize(doc);
          tcache.putTokenList(doc, tl);
        }
        Concordance c = yoshikoder.getDictionary().getConcordance(tl, n, wsize);
        map.put(doc, c);
      }
      return map;
View Full Code Here
77
78
79
80
81
82
83
84
85
86
87
88
  }

  protected int[] getDocumentStats(YKDocument doc, Node[] keys, CategoryNode catnode) throws IOException, TokenizationException {
       
    // tokenize the document
    TokenizationCache tcache = yoshikoder.getTokenizationCache();
        TokenList tl1 = tcache.getTokenList(doc);
        if (tl1 == null)
            tl1 = TokenizationService.getTokenizationService().tokenize(doc);
       
        // compute the dictionary counts
        EntryFrequencyMap efm1 = new EntryFrequencyMap(catnode, tl1);
View Full Code Here
107
108
109
110
111
112
113
114
115
116
117
118
    tworker = new TaskWorker(yoshikoder){
            protected void doWork() throws Exception {
              // FIRST DOC
              YKDocument doc1 = (YKDocument)docs.get(0);
              // tokenize the document
            TokenizationCache tcache = yoshikoder.getTokenizationCache();
            TokenList tl1 = tcache.getTokenList(doc1);
                if (tl1 == null)
                  tl1 = TokenizationService.getTokenizationService().tokenize(doc1);
                 YKDictionary dict = yoshikoder.getDictionary();
               
                 // compute the dictionary counts
View Full Code Here
213
214
215
216
217
218
219
220
221
222
223
224
    tworker = new TaskWorker(yoshikoder){
            protected void doWork() throws Exception {
              // FIRST DOC
              YKDocument doc1 = (YKDocument)docs.get(0);
              // tokenize the document
            TokenizationCache tcache = yoshikoder.getTokenizationCache();
            TokenList tl1 = tcache.getTokenList(doc1);
                if (tl1 == null)
                  tl1 = TokenizationService.getTokenizationService().tokenize(doc1);
                 YKDictionary dict = yoshikoder.getDictionary();
               
                 // compute the dictionary counts
View Full Code Here
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
  }

  // first pass to get vocab
  protected List<String> getVocab(List<YKDocument> docs) throws IOException, TokenizationException {
    Set<String> vocab = new HashSet<String>();
    TokenizationCache tcache = yoshikoder.getTokenizationCache();
    for (YKDocument doc : docs) {
      TokenList tl = tcache.getTokenList(doc);
      if (tl == null){
        tl = TokenizationService.getTokenizationService().tokenize(doc);
        tcache.putTokenList(doc, tl);
      }
      WordFrequencyMap map = new WordFrequencyMap(tl);
      vocab.addAll(map.getVocabularyList());
    }
    List<String> list = new ArrayList<String>();
View Full Code Here
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
    // write header
    for (String word : vocab)
      writer.write("," + FileUtil.escapeForCsv(word));
    writer.write(",Total\n");
   
    TokenizationCache tcache = yoshikoder.getTokenizationCache();
    for (YKDocument doc : docs) {
      TokenList tl = tcache.getTokenList(doc);
      if (tl == null){
        tl = TokenizationService.getTokenizationService().tokenize(doc);
        tcache.putTokenList(doc, tl);
      }
      WordFrequencyMap map = new WordFrequencyMap(tl);
      writer.write( FileUtil.escapeForCsv(doc.getTitle()) );
      for (String vocabWord: vocab) {
        Integer count = map.getWordCount(vocabWord);
View Full Code Here
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
        cell = row.createCell((short)(vocab.size()+1));
        cell.setEncoding(HSSFCell.ENCODING_UTF_16);
        cell.setCellValue("Total");
   
        int rowNumber = 1;
    TokenizationCache tcache = yoshikoder.getTokenizationCache();
    for (YKDocument doc : docs) {
      TokenList tl = tcache.getTokenList(doc);
      if (tl == null){
        tl = TokenizationService.getTokenizationService().tokenize(doc);
        tcache.putTokenList(doc, tl);
      }
      WordFrequencyMap map = new WordFrequencyMap(tl);
     
      row = sheet.createRow((short)rowNumber);
      cell = row.createCell((short)0);
View Full Code Here
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
                protected void doWork() throws Exception {
                    DocumentList dl = new DocumentListImpl();
                    dl.add(doc1);
                    dl.add(doc2);

                    TokenizationCache tcache = yoshikoder.getTokenizationCache();
                    TokenList tl1 = tcache.getTokenList(doc1);
                    TokenList tl2 = tcache.getTokenList(doc2);
                    if (tl1 == null){
                        tl1 = TokenizationService.getTokenizationService().tokenize(doc1);
                        tcache.putTokenList(doc1, tl1);
                    }
                    if (tl2 == null){
                        tl2 = TokenizationService.getTokenizationService().tokenize(doc2);
                        tcache.putTokenList(doc2, tl2);
                    }
                   
                    //YKDictionary dict = yoshikoder.getDictionary();
                    EntryFrequencyMap efm1 = new EntryFrequencyMap(catnode, tl1);
                    EntryFrequencyMap efm2 = new EntryFrequencyMap(catnode, tl2);
View Full Code Here
TOP

Related Classes of edu.harvard.wcfia.yoshikoder.document.tokenizer.TokenizationCache

  • edu.harvard.wcfia.yoshikoder.AddHighlightsAction
  • edu.harvard.wcfia.yoshikoder.DictionaryRRDocumentComparisonAction
  • edu.harvard.wcfia.yoshikoder.MakeConcordanceAction
  • edu.harvard.wcfia.yoshikoder.MultipleConcordanceFrequencyReportAction
  • edu.harvard.wcfia.yoshikoder.SingleDocumentDictionaryReportAction
  • edu.harvard.wcfia.yoshikoder.SingleDocumentWordFrequencyReportAction
  • edu.harvard.wcfia.yoshikoder.ui.DocumentPanel
  • edu.harvard.wcfia.yoshikoder.UnifiedDictionaryFrequencyReportAction
  • edu.harvard.wcfia.yoshikoder.UnifiedWordFrequencyReportAction
    • 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.