Examples of org.apache.uima.cas.text.AnnotationIndex

org.apache.uima.cas.text.AnnotationIndex
An annotation index provides additional iterator functionality that applies only to instances of uima.tcas.Annotation. You can obtain an AnnotationIndex by calling:
AnnotationIndex idx = (AnnotationIndex)cas.getAnnotationIndex();
(the typecast is necessary for historical reasons).

Note that the AnnotationIndex defines the following sort order between two annotations:
- Annotations are sorted in increasing order of their start offset. That is, for any annotations a and b, if a.start < b.start then a < b.
- Annotations whose start offsets are equal are next sorted by decreasing order of their end offsets. That is, if a.start = b.start and a.end > b.end, then a < b. This causes annotations with larger to be sorted before annotations with smaller spans, which produces an iteration order similar to a preorder tree traversal.
- Annotations whose start offsets are equal and whose end offsets are equal are sorted based on {@link org.apache.uima.resource.metadata.TypePriorities} (which is an element of the componentdescriptor). That is, if a.start = b.start, a.end = b.end, and the type of a is defined before the type of b in the type priorities, then a < b.
- If none of the above rules apply, then the ordering is arbitrary. This will occur if you have two annotations of the exact same type that also have the same span. It will also occur if you have not defined any type priority between two annotations that have the same span.
In the method descriptions below, the notation a < b, where a and b are annotations, should be taken to mean a comes before b in the index, according to the above rules.

   * @throws UnsupportedEncodingException
   */
  private void printPosTags(JCas cas) throws UnsupportedEncodingException, IOException {
    Writer writer = new BufferedWriter(new OutputStreamWriter(new FileOutputStream(
        "moby-tag-list.txt"), "utf-8"));
    AnnotationIndex tokenIndex = cas.getAnnotationIndex(TokenAnnotation.type);
    FSIterator tokIt = tokenIndex.iterator();
    TokenAnnotation token = null;
    for (tokIt.moveToFirst(); tokIt.isValid(); tokIt.moveToNext()) {
      token = (TokenAnnotation) tokIt.get();
      writer.write(token.getPosTag());
      writer.write('\n');

View Full Code Here

      ++annotCount;
      this.cas.getIndexRepository().addFS(this.cas.createAnnotation(this.sentenceType, i, i + 10));
    }


    int count;
    AnnotationIndex annotIndex = this.cas.getAnnotationIndex();
    FSIterator it = annotIndex.iterator(true);
    count = 0;
    while (it.isValid()) {
      ++count;
      it.moveToNext();
    }
    assertTrue(annotCount == count);
    // System.out.println("Size of ambiguous iterator: " + count);
    it = annotIndex.iterator(false);
    count = 0;
    while (it.isValid()) {
      ++count;
      it.moveToNext();
    }
    assertTrue(count == 1);
    // System.out.println("Size of unambiguous iterator: " + count);
    AnnotationFS bigAnnot = this.cas.createAnnotation(this.sentenceType, 10, 41);
    it = annotIndex.subiterator(bigAnnot, true, true);
    count = 0;
    while (it.isValid()) {
      ++count;
      // AnnotationFS a = (AnnotationFS) it.get();
      // System.out.println("Annotation from " + a.getBegin() + " to " + a.getEnd());
      it.moveToNext();
    }
    assertTrue(count == 32);
    count = 0;
    for (it.moveToLast(); it.isValid(); it.moveToPrevious()) {
      ++count;
    }
    assertTrue(count == 32);
    // System.out.println("Size of subiterator(true, true): " + count);
    it = annotIndex.subiterator(bigAnnot, false, true);
    count = 0;
    while (it.isValid()) {
      ++count;
      // AnnotationFS a = (AnnotationFS) it.get();
      // System.out.println("Annotation from " + a.getBegin() + " to " + a.getEnd());
      it.moveToNext();
    }
    assertTrue(count == 3);
    // System.out.println("Size of subiterator(false, true): " + count);
    count = 0;
    for (it.moveToLast(); it.isValid(); it.moveToPrevious()) {
      ++count;
    }
    assertTrue(count == 3);
    it = annotIndex.subiterator(bigAnnot, true, false);
    count = 0;
    while (it.isValid()) {
      ++count;
      // AnnotationFS a = (AnnotationFS) it.get();
      // System.out.println("Annotation from " + a.getBegin() + " to " + a.getEnd());
      it.moveToNext();
    }
    assertTrue(count == 39);
    // System.out.println("Size of subiterator(true, false): " + count);
    count = 0;
    for (it.moveToLast(); it.isValid(); it.moveToPrevious()) {
      ++count;
    }
    assertTrue(count == 39);
    it = annotIndex.subiterator(bigAnnot, false, false);
    count = 0;
    while (it.isValid()) {
      ++count;
      // AnnotationFS a = (AnnotationFS) it.get();
      // System.out.println("Annotation from " + a.getBegin() + " to " + a.getEnd());
      it.moveToNext();
    }
    assertTrue(count == 4);
    // System.out.println("Size of subiterator(false, false): " + count);
    count = 0;
    for (it.moveToLast(); it.isValid(); it.moveToPrevious()) {
      ++count;
    }
    assertTrue(count == 4);
    AnnotationFS sent = (AnnotationFS) this.cas.getAnnotationIndex(this.sentenceType).iterator().get();
    it = annotIndex.subiterator(sent, false, true);
    count = 0;
    while (it.isValid()) {
      ++count;
      // AnnotationFS a = (AnnotationFS) it.get();
      // System.out.println("Annotation from " + a.getBegin() + " to " + a.getEnd());

View Full Code Here

      
        iv_logger.info("process(JCas)");


      JFSIndexRepository indexes = jcas.getJFSIndexRepository();
      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>();
        while (btaItr.hasNext()) {

View Full Code Here


    ArrayList wordList = new ArrayList();
    StringBuffer sentenceBuffer = new StringBuffer();
    offsetMap.clear();


    AnnotationIndex sentenceIndex = aJCas.getAnnotationIndex(Sentence.type);
    AnnotationIndex tokenIndex = aJCas.getAnnotationIndex(Token.type);


    // iterate over Sentences
    FSIterator sentenceIterator = sentenceIndex.iterator();
    while (sentenceIterator.hasNext()) {
      Sentence sentence = (Sentence) sentenceIterator.next();


      wordList.clear();
      sentenceBuffer.setLength(0);


      int mapIdx = 0;


      // iterate over Tokens
      FSIterator tokenIterator = tokenIndex.subiterator(sentence);
      while (tokenIterator.hasNext()) {
        Token token = (Token) tokenIterator.next();


        String word = escapeToken(token.getCoveredText());

View Full Code Here

   * 
   * @see JCasAnnotator_ImplBase#process(JCas)
   */
  public void process(JCas aJCas) throws AnalysisEngineProcessException {


    AnnotationIndex sentenceIndex = aJCas.getAnnotationIndex(Sentence.type);


    // iterate over Sentences
    FSIterator sentenceIterator = sentenceIndex.iterator();
    while (sentenceIterator.hasNext()) {
      Sentence sentence = (Sentence) sentenceIterator.next();


      String text = sentence.getCoveredText();
      Span[] tokenSpans = tokenizer.tokenizePos(text);

View Full Code Here


    ArrayList tokenList = new ArrayList();
    ArrayList wordList = new ArrayList();
    List finderTags;


    AnnotationIndex sentenceIndex = aJCas.getAnnotationIndex(Sentence.type);
    AnnotationIndex tokenIndex = aJCas.getAnnotationIndex(Token.type);


    // iterate over Sentences
    FSIterator sentenceIterator = sentenceIndex.iterator();
    while (sentenceIterator.hasNext()) {
      Sentence sentence = (Sentence) sentenceIterator.next();


      tokenList.clear();
      wordList.clear();


      // iterate over Tokens
      FSIterator tokenIterator = tokenIndex.subiterator(sentence);
      while (tokenIterator.hasNext()) {
        Token token = (Token) tokenIterator.next();


        tokenList.add(token);
        wordList.add(token.getCoveredText());

View Full Code Here

  public void process(JCas aJCas) throws AnalysisEngineProcessException {


    ArrayList tokenList = new ArrayList();
    ArrayList wordList = new ArrayList();


    AnnotationIndex sentenceIndex = aJCas.getAnnotationIndex(Sentence.type);
    AnnotationIndex tokenIndex = aJCas.getAnnotationIndex(Token.type);


    // iterate over Sentences
    FSIterator sentenceIterator = sentenceIndex.iterator();
    while (sentenceIterator.hasNext()) {
      Sentence sentence = (Sentence) sentenceIterator.next();


      tokenList.clear();
      wordList.clear();


      // iterate over Tokens
      FSIterator tokenIterator = tokenIndex.subiterator(sentence);
      while (tokenIterator.hasNext()) {
        Token token = (Token) tokenIterator.next();


        tokenList.add(token);
        wordList.add(token.getCoveredText());

View Full Code Here

      assertTrue(false);
    }
    jcas.setDocumentText(text);
    try {
      this.ae.process(jcas);
      AnnotationIndex tokenIndex = jcas.getAnnotationIndex(jcas.getCasType(Token.type));
      AnnotationFS sentence = (AnnotationFS) jcas.getAnnotationIndex(jcas.getCasType(Sentence.type)).iterator().next();
      FSIterator tokenIterator = tokenIndex.subiterator(sentence);
      AnnotationFS token = (AnnotationFS) tokenIndex.iterator().next();
      tokenIterator.moveTo(token); //throws ClassCastException    
    } catch (AnalysisEngineProcessException e) {
      e.printStackTrace();
      assertTrue(false);
    } catch (ClassCastException e) {

View Full Code Here

    logger.info("process(JCas)");


    List<BaseToken> tokens = new ArrayList<BaseToken>();
    List<String> words = new ArrayList<String>();


    AnnotationIndex baseTokenIndex = jCas.getAnnotationIndex(BaseToken.type);


    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());
      }

View Full Code Here

      ++annotCount;
      this.cas.getIndexRepository().addFS(this.cas.createAnnotation(this.sentenceType, i, i + 10));
    }


    int count;
    AnnotationIndex annotIndex = this.cas.getAnnotationIndex();
    FSIterator it = annotIndex.iterator(true);
    count = 0;
    while (it.isValid()) {
      ++count;
      it.moveToNext();
    }
    assertTrue(annotCount == count);
    // System.out.println("Size of ambiguous iterator: " + count);
    it = annotIndex.iterator(false);
    count = 0;
    while (it.isValid()) {
      ++count;
      it.moveToNext();
    }
    assertTrue(count == 1);
    // System.out.println("Size of unambiguous iterator: " + count);
    AnnotationFS bigAnnot = this.cas.createAnnotation(this.sentenceType, 10, 41);
    it = annotIndex.subiterator(bigAnnot, true, true);
    count = 0;
    while (it.isValid()) {
      ++count;
      // AnnotationFS a = (AnnotationFS) it.get();
      // System.out.println("Annotation from " + a.getBegin() + " to " + a.getEnd());
      it.moveToNext();
    }
    assertTrue(count == 32);
    count = 0;
    for (it.moveToLast(); it.isValid(); it.moveToPrevious()) {
      ++count;
    }
    assertTrue(count == 32);
    // System.out.println("Size of subiterator(true, true): " + count);
    it = annotIndex.subiterator(bigAnnot, false, true);
    count = 0;
    while (it.isValid()) {
      ++count;
      // AnnotationFS a = (AnnotationFS) it.get();
      // System.out.println("Annotation from " + a.getBegin() + " to " + a.getEnd());
      it.moveToNext();
    }
    assertTrue(count == 3);
    // System.out.println("Size of subiterator(false, true): " + count);
    count = 0;
    for (it.moveToLast(); it.isValid(); it.moveToPrevious()) {
      ++count;
    }
    assertTrue(count == 3);
    it = annotIndex.subiterator(bigAnnot, true, false);
    count = 0;
    while (it.isValid()) {
      ++count;
      // AnnotationFS a = (AnnotationFS) it.get();
      // System.out.println("Annotation from " + a.getBegin() + " to " + a.getEnd());
      it.moveToNext();
    }
    assertTrue(count == 39);
    // System.out.println("Size of subiterator(true, false): " + count);
    count = 0;
    for (it.moveToLast(); it.isValid(); it.moveToPrevious()) {
      ++count;
    }
    assertTrue(count == 39);
    it = annotIndex.subiterator(bigAnnot, false, false);
    count = 0;
    while (it.isValid()) {
      ++count;
      // AnnotationFS a = (AnnotationFS) it.get();
      // System.out.println("Annotation from " + a.getBegin() + " to " + a.getEnd());
      it.moveToNext();
    }
    assertTrue(count == 4);
    // System.out.println("Size of subiterator(false, false): " + count);
    count = 0;
    for (it.moveToLast(); it.isValid(); it.moveToPrevious()) {
      ++count;
    }
    assertTrue(count == 4);
    AnnotationFS sent = (AnnotationFS) this.cas.getAnnotationIndex(this.sentenceType).iterator().get();
    it = annotIndex.subiterator(sent, false, true);
    count = 0;
    while (it.isValid()) {
      ++count;
      // AnnotationFS a = (AnnotationFS) it.get();
      // System.out.println("Annotation from " + a.getBegin() + " to " + a.getEnd());

View Full Code Here

0 1 2 3

TOP

Related Classes of org.apache.uima.cas.text.AnnotationIndex

org.apache.ctakes.chunker.ae.Chunker

org.apache.ctakes.contexttokenizer.ae.ContextDependentTokenizerAnnotator

org.apache.ctakes.dependency.parser.ae.LemAssigner

org.apache.ctakes.dependency.parser.ae.PosAssigner

org.apache.ctakes.dependency.parser.DependencyNodeWriter

org.apache.ctakes.dependency.parser.util.DependencyUtility

org.apache.ctakes.dictionary.lookup2.ae.AbstractJCasTermAnnotator

org.apache.ctakes.postagger.POSTagger

org.apache.ctakes.ytex.uima.annotators.NegexAnnotator

org.apache.uima.ae.noop.CheckTextAnnotator

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.