Package org.apache.ctakes.typesystem.type.syntax

Examples of org.apache.ctakes.typesystem.type.syntax.WordToken

1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
//        }
       
        String oldSystemTokenClass = oldSystemToken.getClass().getName();
        if (oldSystemTokenClass.equals(WordToken.class.getName()))
        {
          newGoldToken = new WordToken(goldView, oldSystemToken.getBegin(), oldSystemToken.getEnd());
        } else if (oldSystemTokenClass.equals(ContractionToken.class.getName()))
        {
          newGoldToken = new ContractionToken(goldView, oldSystemToken.getBegin(), oldSystemToken.getEnd());
        } else if (oldSystemTokenClass.equals(NewlineToken.class.getName()))
        {
View Full Code Here
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
   * @return
   */
 
  private boolean isAdjacentWithStopWords(JCas jcas, Annotation prevAnn, Annotation currAnn)
  {
    WordToken prevWta = getLastToken(prevAnn);
    WordToken currWta = getFirstToken(currAnn);
   
    if(prevWta == null || currWta == null)
      return false;
   
    if(prevWta.getTokenNumber() == (currWta.getTokenNumber() - 1))
      return true;
   
    List<WordToken> containedWTAs = getContainedWordTokens(jcas, prevWta, currWta);
    for(int i=0; i<containedWTAs.size(); i++)
    {
      WordToken tempWta = containedWTAs.get(i);
      if(stopWords.contains(tempWta.getCoveredText()))
          continue;
      else
        return false;
    }
   
View Full Code Here
501
502
503
504
505
506
507
508
509
510
511
512
    JFSIndexRepository indexes = jcas.getJFSIndexRepository();
    Iterator<?> annotItr = indexes.getAnnotationIndex(WordToken.type).iterator();

    while (annotItr.hasNext())
    {
      WordToken wta = (WordToken)annotItr.next();
      if(wta.getBegin() >= prevWta.getEnd() && wta.getEnd() <= currWta.getBegin())
        list.add(wta);
    }
   
    return list;
  }
View Full Code Here
539
540
541
542
543
544
545
546
547
548
549
    return l;
  }
 
  private WordToken getFirstToken(Annotation ann)
  {
    WordToken wta = null;
   
    if(ann instanceof PADLocation)
    {
      FSArray fsa = (((PADLocation)ann).getRelatedTokens());
     
View Full Code Here
567
568
569
570
571
572
573
574
575
576
577
    return wta;
  }

  private WordToken getLastToken(Annotation ann)
  {
    WordToken wta = null;

    if(ann instanceof PADLocation)
    {
      FSArray fsa = (((PADLocation)ann).getRelatedTokens());
     
View Full Code Here
91
92
93
94
95
96
97
98
99
100
101
102
        .iterator();
    List<String> unigrams = new ArrayList<String>();
    List bigrams = new ArrayList();

    while (wordTokenItr.hasNext()) {
      WordToken token = (WordToken) wordTokenItr.next();
      String tok = token.getCoveredText();

      if (tok == null)
        continue;
      if (!caseSensitive)
        tok = tok.toLowerCase();
View Full Code Here
203
204
205
206
207
208
209
210
211
212
213
   * @param obj
   * @return
   */
  private BaseToken adaptToBaseToken(org.apache.ctakes.typesystem.type.syntax.BaseToken obj) throws Exception {
    if (obj instanceof WordToken) {
      WordToken wta = (WordToken) obj;
      return new WordTokenAdapter(wta);
    } else if (obj instanceof NumToken) {
      NumToken nta = (NumToken) obj;
      if (nta.getNumType() == TokenizerAnnotator.TOKEN_NUM_TYPE_INTEGER) {
        return new IntegerTokenAdapter(nta);
View Full Code Here
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
          sent.setSentenceNumber(sentNum);
        }
        sentNum++;
        sent.addToIndexes();
        for (int j=0; j < tokenArrays[i].length; j++) {
          WordToken tok = new WordToken(jcas);
          LineAndTokenPosition word = new LineAndTokenPosition();
          word.setLine(i+1);
          word.setTokenOffset(j);
          LineTokenToCharacterOffsetConverter.BeginAndEndCharacterOffsetPair tPos = converter.convert(word);
          if (tPos == null) {
            tok.setBegin(0);
            tok.setEnd(1);
          } else {
            tok.setBegin(tPos.getBegin());
            tok.setEnd(tPos.getEnd() + 1);
          }
          tok.setTokenNumber(tokNum);
          tokNum++; 
          tok.addToIndexes();
        }
      }
      logger.info("before assertions");
      for (Annotation a : assertions) {
        logger.info("  begin assertion");
View Full Code Here
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
      throws AnalysisEngineProcessException {
    JFSIndexRepository indexes = jcas.getJFSIndexRepository();
    Iterator wordItr = indexes.getAnnotationIndex(WordToken.type)
        .iterator();
    while (wordItr.hasNext()) {
      WordToken wordAnnotation = (WordToken) wordItr.next();
      if (wordAnnotation.getBegin() >= rangeBegin
          && wordAnnotation.getEnd() <= rangeEnd) {
        String word = text.substring(wordAnnotation.getBegin(),
            wordAnnotation.getEnd());

        // if the original word was misspelled, use the spell correction
        String suggestion = wordAnnotation.getSuggestion();

        if ((suggestion != null) && (suggestion.length() > 0)) {
          word = suggestion;
        }
View Full Code Here
470
471
472
473
474
475
476
477
478
479
480
  }

  private BaseToken adaptToBaseToken(org.apache.ctakes.typesystem.type.syntax.BaseToken bta)
      throws Exception {
    if (bta instanceof WordToken) {
      WordToken wta = (WordToken) bta;
      return new WordTokenAdapter(wta);
    } else if (bta instanceof NumToken) {
      NumToken nta = (NumToken) bta;
      if (nta.getNumType() == TokenizerAnnotator.TOKEN_NUM_TYPE_INTEGER) {
        return new IntegerTokenAdapter(nta);
View Full Code Here
TOP

Related Classes of org.apache.ctakes.typesystem.type.syntax.WordToken

  • org.apache.ctakes.assertion.eval.AssertionEvalBasedOnModifier$ReferenceSupportingAnnotationsSystemToGoldCopier
  • org.apache.ctakes.assertion.eval.AssertionEvaluation$ReferenceSupportingAnnotationsSystemToGoldCopier
  • org.apache.ctakes.assertion.medfacts.Converti2b2AnnotationsToCTAKES
  • org.apache.ctakes.clinicalpipeline.ae.ExtractionPrepAnnotator
  • org.apache.ctakes.contexttokenizer.ae.ContextDependentTokenizerAnnotator
  • org.apache.ctakes.core.ae.TokenConverter
  • org.apache.ctakes.core.cc.NormalizedFilesInDirectoryCasConsumer
  • org.apache.ctakes.core.cc.TokenFreqCasConsumer
  • org.apache.ctakes.core.nlp.tokenizer.TokenizerPTB
  • org.apache.ctakes.coreference.ae.MipacqMarkableCreator
    • 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.