Package org.apache.ctakes.typesystem.type.textspan

Examples of org.apache.ctakes.typesystem.type.textspan.Sentence

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
    FSIterator sentences = jCas.getAnnotationIndex(Sentence.type)
        .iterator();

    while (sentences.hasNext()) {
      Sentence sentence = (Sentence) sentences.next();

      tokens.clear();
      words.clear();

      FSIterator tokenIterator = baseTokenIndex.subiterator(sentence);
      while (tokenIterator.hasNext()) {
        BaseToken token = (BaseToken) tokenIterator.next();
        tokens.add(token);
        words.add(token.getCoveredText());
      }

      List<?> wordTagList = null; // List of BaseToken's
      if (words.size() > 0) {
        wordTagList = tagger.tag(words);
      }
      // else {
      // logger.info("sentence has no words = '" +
      // sentence.getCoveredText()
      // + "' at (" +sentence.getBegin() + "," + sentence.getEnd() + ")");
      // }

      try {
        for (int i = 0; i < tokens.size(); i++) {
          BaseToken token = (BaseToken) tokens.get(i);
          String posTag = (String) wordTagList.get(i);
          token.setPartOfSpeech(posTag);
        }
      } catch (IndexOutOfBoundsException e) {
        throw new AnalysisEngineProcessException(
            "sentence being tagged is: '"
                + sentence.getCoveredText() + "'", null, e);
      }
    }
  }
View Full Code Here
116
117
118
119
120
121
122
123
124
125
126
127
128
          baseToken.addToIndexes();

          documentText.append(word + " ");
          wordStart = wordEnd + 1;
        }
        Sentence sentence = new Sentence(jCas, 0, wordEnd);
        sentence.setSentenceNumber(0);
        sentence.addToIndexes();
        jCas.setDocumentText(documentText.toString());
      }
    } catch (CASException ce) {
      throw new CollectionException(ce);
    }
View Full Code Here
81
82
83
84
85
86
87
88
89
90
91
92
    // iterate over sentences
    FSIterator iterator = jcas.getAnnotationIndex(Sentence.type).iterator();
    Parse parse = null;
   
    while(iterator.hasNext()){
      Sentence sentAnnot = (Sentence) iterator.next();
      if(sentAnnot.getCoveredText().length() == 0){
        continue;
      }
      FSArray termArray = TreeUtils.getTerminals(jcas, sentAnnot);
      Parse inputTokens = TreeUtils.ctakesTokensToOpennlpTokens(sentAnnot, termArray);
      String sentStr = TreeUtils.getSentence(termArray);
View Full Code Here
112
113
114
115
116
117
118
119
120
121
122
      Iterator<?> sentItr = indexes.getAnnotationIndex(Sentence.type).iterator();
      AnnotationIndex baseTokenIndex = jcas.getJFSIndexRepository().getAnnotationIndex(
          org.apache.ctakes.typesystem.type.syntax.BaseToken.type);
     
      while (sentItr.hasNext()) {
        Sentence sentAnnot = (Sentence) sentItr.next();
        FSIterator btaItr = baseTokenIndex.subiterator(sentAnnot);

        // adapt JCas objects into objects expected by the Finite state
        // machines
        List<BaseToken> baseTokenList = new ArrayList<BaseToken>();
View Full Code Here
332
333
334
335
336
337
338
339
340
341
342
//          cuePhraseInWindowExtractor.extract(jCas, entityOrEventMention);
          //cuePhraseInWindowExtractor.extractWithin(jCas, entityMention, firstCoveringSentence);
//      List<Sentence> sents = new ArrayList<Sentence>(coveringSents.get(entityOrEventMention));
      List<Sentence> sents = new ArrayList<Sentence>(JCasUtil.selectCovering(jCas, Sentence.class, entityOrEventMention.getBegin(), entityOrEventMention.getEnd()));
      if(sents.size() > 0){
        Sentence sentence = sents.get(0);
        List<AssertionCuePhraseAnnotation> cues = JCasUtil.selectCovered(AssertionCuePhraseAnnotation.class, sentence);
        int closest = Integer.MAX_VALUE;
        AssertionCuePhraseAnnotation closestCue = null;
        for(AssertionCuePhraseAnnotation cue : cues){
          List<BaseToken> tokens = JCasUtil.selectBetween(BaseToken.class, cue, entityOrEventMention);
View Full Code Here
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
      String [][] tokenArrays = p.getTokenArrays();
      jcas.setSofaDataString(contents, "");
      int sentNum = 0;
      int tokNum = 0;
      for (int i=0; i < tokenArrays.length; i++) {
        Sentence sent = new Sentence(jcas);
        LineAndTokenPosition sentStart = new LineAndTokenPosition();
        sentStart.setLine(i+1);
        sentStart.setTokenOffset(0);
        LineAndTokenPosition sentEnd = new LineAndTokenPosition();
        sentEnd.setLine(i+1);
        sentEnd.setTokenOffset(tokenArrays[i].length-1);
        LineTokenToCharacterOffsetConverter.BeginAndEndCharacterOffsetPair sStart = converter.convert(sentStart);
        LineTokenToCharacterOffsetConverter.BeginAndEndCharacterOffsetPair sEnd = converter.convert(sentEnd);
        if ((sStart == null) || (sEnd == null)) {
          sent.setBegin(0);
          sent.setEnd(0);
          sent.setSentenceNumber(sentNum);
        } else {
          sent.setBegin(sStart.getBegin()); // get begin of first token
          sent.setEnd(sEnd.getEnd() + 1); // get end of last token
          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);
View Full Code Here
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
      {
        logger.info("no covering sentences found!!! continuing with next entity/event...");
        continue;
      }
      logger.info(String.format("covering sentence count: %d", coveringSentences.size()));
      Sentence firstCoveringSentence = coveringSentences.iterator().next();
     
      logger.info(String.format(
          "first covering sentence: [%d-%d] \"%s\" (%s)",
          firstCoveringSentence.getBegin(), firstCoveringSentence.getEnd(),
          firstCoveringSentence.getCoveredText(),
          firstCoveringSentence.getClass().getName()));
     
      List<Feature> cuePhraseFeatures =
          //cuePhraseInSentenceExtractor.extract(jcas, firstCoveringSentence);
          cuePhraseInWindowExtractor.extractWithin(jcas, current, firstCoveringSentence);
          //cuePhraseInWindowNamingExtractor.extract(jcas, current);
View Full Code Here
67
68
69
70
71
72
73
74
75
76
77
  public List<Feature> extract(JCas view, Annotation mention)
      throws CleartkExtractorException {
    ArrayList<Feature> feats = new ArrayList<Feature>();
    List<Sentence> sents = JCasUtil.selectCovering(view, Sentence.class, mention.getBegin(), mention.getEnd());
    if(sents.size() == 0) return feats;
    Sentence sent = sents.get(0);
    List<BaseToken> tokens = JCasUtil.selectCovered(BaseToken.class, sent);
    int startIndex = -1;
    int endIndex = -1;
   
    for(int i = 0; i < tokens.size(); i++){
View Full Code Here
61
62
63
64
65
66
67
68
69
70
71
    beginTreeMap = new TreeMap<Integer, Sentence>();
   
    AnnotationIndex<Annotation> annotationIndex = jcas.getAnnotationIndex(Sentence.type);
    for (Annotation current : annotationIndex)
    {
      Sentence currentSentence = (Sentence)current;
     
      int begin = currentSentence.getBegin();
      beginTreeMap.put(begin, currentSentence);
    }
  }
View Full Code Here
91
92
93
94
95
96
97
98
99
    Integer floorKey = beginTreeMap.floorKey(characterOffset);
    if (floorKey == null)
    {
      return null;
    }
    Sentence floorEntry = beginTreeMap.get(floorKey);
   
    return floorEntry;
  }
View Full Code Here
TOP

Related Classes of org.apache.ctakes.typesystem.type.textspan.Sentence

  • org.apache.ctakes.assertion.attributes.generic.GenericAttributeClassifier
  • org.apache.ctakes.assertion.attributes.history.HistoryAttributeClassifier
  • org.apache.ctakes.assertion.attributes.subject.SubjectAttributeClassifier
  • org.apache.ctakes.assertion.eval.AssertionEvalBasedOnModifier$ReferenceSupportingAnnotationsSystemToGoldCopier
  • org.apache.ctakes.assertion.eval.AssertionEvaluation
  • org.apache.ctakes.assertion.eval.AssertionEvaluation$ReferenceSupportingAnnotationsSystemToGoldCopier
  • org.apache.ctakes.assertion.medfacts.cleartk.AssertionCleartkAnalysisEngine
  • org.apache.ctakes.assertion.medfacts.cleartk.extractors.AssertionDependencyTreeExtractor
  • org.apache.ctakes.assertion.medfacts.cleartk.extractors.ContextWordWindowExtractor
  • org.apache.ctakes.assertion.medfacts.cleartk.extractors.CueWordTest
    • 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.