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

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

79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
    tokenBeginEndTreeSet = new TreeSet<Integer>();
   
    AnnotationIndex<Annotation> annotationIndex = jcas.getAnnotationIndex(BaseToken.type);
    for (Annotation current : annotationIndex)
    {
      BaseToken bt = (BaseToken)current;
      // filter out NewlineToken
      if (!(bt instanceof NewlineToken)) {
        int begin = bt.getBegin();
        int end = bt.getEnd();
          tokenBeginEndTreeSet.add(begin);
          tokenBeginEndTreeSet.add(end);
      }
    }
  }
View Full Code Here
96
97
98
99
100
101
102
103
104
105
106
      sentenceToTokenNumberMap = new HashMap<Sentence, List<BaseToken>>();
      for (Sentence s : beginTreeMap.values()) {
              FSIterator<Annotation> tokensInSentenceIterator = jcas
                              .getAnnotationIndex(BaseToken.type).subiterator(s);
              List<BaseToken> btList = new ArrayList<BaseToken>();
              BaseToken bt = null;
              while ((bt = this.getNextNonEOLToken(tokensInSentenceIterator)) != null) {
                      btList.add(bt);
              }
              sentenceToTokenNumberMap.put(s, btList);
      }
View Full Code Here
192
193
194
195
196
197
198
199
200
201
202
   
   
    FSIterator<Annotation> beginTokenInSentenceIterator = constraintConstructorFindContainedBy
            .createFilteredIterator(characterOffset, characterOffset,
                            baseTokenType);
  BaseToken beginToken = this
              .getNextNonEOLToken(beginTokenInSentenceIterator);
  int beginTokenWordNumber = this.sentenceToTokenNumberMap.get(sentence)
              .indexOf(beginToken);
  LineAndTokenPosition b = new LineAndTokenPosition();
  b.setLine(lineNumber);
View Full Code Here
206
207
208
209
210
211
212
213
214
215
216
  }
 
  public BaseToken getNextNonEOLToken(
          FSIterator<Annotation> tokensInSentenceIterator) {
    while (tokensInSentenceIterator.hasNext()) {
            BaseToken bt = (BaseToken) tokensInSentenceIterator.next();
            if (!(bt instanceof NewlineToken)) {
                    return bt;
            }
    }
    return null;
View Full Code Here
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
      // beginTokenInSentenceIterator.next();
      // BaseToken beginToken = (BaseToken) beginTokenAnnotation;
      // int beginTokenNumber = beginToken.getTokenNumber();
      // int beginTokenWordNumber = beginTokenNumber
      // - firstTokenInSentenceNumber;
      BaseToken beginToken = this
                      .getNextNonEOLToken(beginTokenInSentenceIterator);
      int beginTokenWordNumber = this.sentenceToTokenNumberMap.get(sentence)
                      .indexOf(beginToken);

      beginTokenInSentenceIterator.moveToLast();
      if (!beginTokenInSentenceIterator.hasNext()) {
              throw new RuntimeException("First token in sentence not found!!");
      }
      Annotation endTokenAnnotation = beginTokenInSentenceIterator.next();
      BaseToken endToken = (BaseToken) endTokenAnnotation;
      // int endTokenNumber = endToken.getTokenNumber();
      // int endTokenWordNumber = endTokenNumber - firstTokenInSentenceNumber;
      int endTokenWordNumber = this.sentenceToTokenNumberMap.get(sentence)
                      .indexOf(endToken);
View Full Code Here
151
152
153
154
155
156
157
158
159
160
161
162
163
        try {
          componentView = jCas.getView(component.getSimpleName());
          CasCopier casCopy = new CasCopier(jCas.getCas(), componentView.getCas());
          org.apache.uima.cas.Feature sofaFeature = jCas.getTypeSystem().getFeatureByFullName(CAS.FEATURE_FULL_NAME_SOFA);
          for(BaseToken token: tokens){
            BaseToken fs = (BaseToken) casCopy.copyFs(token);
            fs.setFeatureValue(sofaFeature, componentView.getSofa());
            fs.addToIndexes(componentView);
          }
          List<BaseToken> viewTokens = JCasUtil.selectCovered(componentView, BaseToken.class, sentence.getBegin(), sentence.getEnd());
          List<TimeMention> times = JCasUtil.selectCovered(componentView, TimeMention.class, sentence);
          componentOutcomes.add(this.timeChunking.createOutcomes(componentView, viewTokens, times));
        } catch (CASException e) {
View Full Code Here
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
269
270
271
272
273
274
275
276
277
278
279
 
  public static FSArray getTerminals(JCas jcas, Sentence sent){
    ArrayList<BaseToken> wordList = new ArrayList<BaseToken>();
    FSIterator<Annotation> iterator = jcas.getAnnotationIndex(BaseToken.type).subiterator(sent);
    while(iterator.hasNext()){
      BaseToken w = (BaseToken)iterator.next();
      if(w instanceof NewlineToken) continue;
      wordList.add(w);
    }
   
    FSArray terms = new FSArray(jcas, wordList.size());
    for(int i = 0; i < wordList.size(); i++){
      BaseToken w = wordList.get(i);
      TerminalTreebankNode ttn = new TerminalTreebankNode(jcas, w.getBegin(), w.getEnd());
      ttn.setChildren(null);
      ttn.setIndex(i);
      ttn.setTokenIndex(i);
      ttn.setLeaf(true);
      ttn.setNodeTags(null);
      if(w instanceof PunctuationToken){
        String tokStr = w.getCoveredText();
        if(tokStr.equals("(") || tokStr.equals("[")){
          ttn.setNodeValue("-LRB-");
        }else if(tokStr.equals(")") || tokStr.equals("]")){
          ttn.setNodeValue("-RRB-");
        }else if(tokStr.equals("{")){
          ttn.setNodeValue("-LCB-");
        }else if(tokStr.equals("}")){
          ttn.setNodeValue("-RCB-");
        }else{
          ttn.setNodeValue(w.getCoveredText());
        }
      }else{
        ttn.setNodeValue(w.getCoveredText());
      }
//      ttn.addToIndexes();
      terms.set(i, ttn);
    }
   
View Full Code Here
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
  @SuppressWarnings("null")
  @Override
  public void process(JCas jCas) throws AnalysisEngineProcessException {
    ArrayList<BaseToken> tokens = new ArrayList<BaseToken>(JCasUtil.select(jCas, BaseToken.class));
    String lastKey = null;
    BaseToken lastToken = null;
    for(int i = 0; i < tokens.size(); i++){
      BaseToken token = tokens.get(i);
     
      String key = token.getCoveredText().toLowerCase();
      if(cueWords.containsKey(key)){
        addCuePhrase(jCas, key, token.getBegin(), token.getEnd());
      }
     
      if(i > 0){
        String twoKey = lastKey + " " + key;
        if(cueWords.containsKey(twoKey)){
          addCuePhrase(jCas, twoKey, lastToken.getBegin(), token.getEnd());
        }
      }
     
      lastToken = token;
      lastKey = key;
View Full Code Here
143
144
145
146
147
148
149
150
151
152
153
154
      // create the Tokens and add them to the Sentence
      for (int i = 0; i < tree.getTerminals().size(); i++) {
        TreebankNode leaf = tree.getTerminals(i);
        if (leaf.getBegin() != leaf.getEnd()) {
          BaseToken token = new BaseToken(jcas, leaf.getBegin(), leaf.getEnd());
          token.setPartOfSpeech(leaf.getNodeType());
          token.addToIndexes();
        }
      }
    }
  }
View Full Code Here
230
231
232
233
234
235
236
237
238
239
240
    Multimap<BaseToken, Feature> endOfEntityFeatures = HashMultimap.create();
    for (IdentifiedAnnotation entity : JCasUtil.select(jCas, IdentifiedAnnotation.class)) {
      if (!entity.getClass().equals(EventMention.class)) {
        List<BaseToken> tokens = JCasUtil.selectCovered(jCas, BaseToken.class, entity);
        if (tokens.size() > 0){
          BaseToken lastToken = tokens.get(tokens.size() - 1);
            String value = String.format("%s_%s", entity.getClass().getSimpleName(), entity.getTypeID());
            endOfEntityFeatures.put(lastToken, new Feature("EndOf", value));
        }      
      }
    }
View Full Code Here
TOP

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

  • org.apache.ctakes.assertion.eval.AssertionEvalBasedOnModifier$ReferenceSupportingAnnotationsSystemToGoldCopier
  • org.apache.ctakes.assertion.eval.AssertionEvaluation$ReferenceSupportingAnnotationsSystemToGoldCopier
  • org.apache.ctakes.assertion.medfacts.cleartk.AlternateCuePhraseAnnotator
  • org.apache.ctakes.assertion.medfacts.cleartk.extractors.SRLFeatureExtractor
  • org.apache.ctakes.assertion.medfacts.i2b2.api.CharacterOffsetToLineTokenConverterCtakesImpl
  • org.apache.ctakes.assertion.medfacts.i2b2.api.SingleDocumentProcessorCtakes
  • org.apache.ctakes.chunker.ae.Chunker
  • org.apache.ctakes.clinicalpipeline.ae.ExtractionPrepAnnotator
  • org.apache.ctakes.constituency.parser.MaxentParserWrapper
  • org.apache.ctakes.constituency.parser.util.TreeUtils
    • 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.