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.

  public void testGetTypeSystem() {
    assertTrue(this.cas.getTypeSystem() != null);
  }
  
  public void testGetAnnotationIndex() {
    AnnotationIndex index = this.cas.getAnnotationIndex();
    assertNotNull(index);
    assertTrue(index.iterator() != null);
    boolean caughtException = false;
    try {
      this.cas.getAnnotationIndex(this.cas.getTypeSystem().getType(CAS.TYPE_NAME_TOP));
    } catch (CASRuntimeException e) {
      caughtException = true;

View Full Code Here


    logger.info(" process(JCas)");
        List<ConllDependencyNode> nodes = new ArrayList<ConllDependencyNode>();
        List<BaseToken> tokens          = new ArrayList<BaseToken>();


        AnnotationIndex nodeIndex = jCas.getAnnotationIndex(ConllDependencyNode.type);
        AnnotationIndex tokenIndex = jCas.getAnnotationIndex(BaseToken.type);
        FSIterator sentences = jCas.getAnnotationIndex(Sentence.type).iterator();


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


            FSIterator tokenIterator = tokenIndex.subiterator(sentence);
            while (tokenIterator.hasNext()) {
                tokens.add((BaseToken) tokenIterator.next());
            }
            //logger.info(" new sentence: ");
            FSIterator nodeIterator = nodeIndex.subiterator(sentence);

View Full Code Here




  /** Returns the first ConllDependencyNode in the CAS w/ same begin and end as the given Annotation **/  
  public static ConllDependencyNode getDependencyNode(JCas jCas, Annotation annot) {


    AnnotationIndex nodeIndex = jCas.getAnnotationIndex(ConllDependencyNode.type);
      FSIterator nodeIterator = nodeIndex.iterator();
      while (nodeIterator.hasNext()) {
          ConllDependencyNode node = (ConllDependencyNode) nodeIterator.next();
          if (equalCoverage(annot,node)) {
            return node;
          }

View Full Code Here

  }
  
  /** Returns the ConllDependencyNodes in the CAS w/ subsumed begins and ends **/  
  public static List<ConllDependencyNode> getDependencyNodes(JCas jCas, Annotation annot) {
    ArrayList<ConllDependencyNode> output = new ArrayList<ConllDependencyNode>();
    AnnotationIndex nodeIndex = jCas.getAnnotationIndex(ConllDependencyNode.type);
      FSIterator nodeIterator = nodeIndex.iterator();
      while (nodeIterator.hasNext()) {
          ConllDependencyNode node = (ConllDependencyNode) nodeIterator.next();
          if (doesSubsume(annot,node)) {
            output.add(node);
          }

View Full Code Here


    logger.info(" process(JCas)");
        List<ConllDependencyNode> nodes = new ArrayList<ConllDependencyNode>();
        List<BaseToken> tokens          = new ArrayList<BaseToken>();


        AnnotationIndex nodeIndex = jCas.getAnnotationIndex(ConllDependencyNode.type);
        AnnotationIndex tokenIndex = jCas.getAnnotationIndex(BaseToken.type);
        FSIterator sentences = jCas.getAnnotationIndex(Sentence.type).iterator();


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


            tokens.clear();
            nodes.clear();


            FSIterator tokenIterator = tokenIndex.subiterator(sentence);
            while (tokenIterator.hasNext()) {
                tokens.add((BaseToken) tokenIterator.next());
            }


            FSIterator nodeIterator = nodeIndex.subiterator(sentence);

View Full Code Here

  public void process(JCas aJCas) throws AnalysisEngineProcessException {


    ArrayList<TokenAnnotation> tokenList = new ArrayList<TokenAnnotation>();
    ArrayList<String> wordList = new ArrayList<String>();


    AnnotationIndex sentenceIndex = aJCas.getAnnotationIndex(SentenceAnnotation.type);
    AnnotationIndex tokenIndex = aJCas.getAnnotationIndex(TokenAnnotation.type);


    // iterate over Sentences
    FSIterator sentenceIterator = sentenceIndex.iterator();


    while (sentenceIterator.hasNext()) {
      SentenceAnnotation sentence = (SentenceAnnotation) sentenceIterator.next();


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


      FSIterator tokenIterator = tokenIndex.subiterator(sentence);
      while (tokenIterator.hasNext()) {
        TokenAnnotation token = (TokenAnnotation) tokenIterator.next();


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

View Full Code Here

    */
   @Override
   public void process( final JCas jcas ) throws AnalysisEngineProcessException {
      _logger.info( "Starting processing" );
      final JFSIndexRepository indexes = jcas.getJFSIndexRepository();
      final AnnotationIndex annotationIndex = indexes.getAnnotationIndex( _lookupWindowType );
      if ( annotationIndex == null ) {  // I don't trust AnnotationIndex.size(), so don't check
         return;
      }
      final Map<RareWordDictionary,Collection<SpannedRareWordTerm>> dictionaryTermsMap
            = new HashMap<RareWordDictionary, Collection<SpannedRareWordTerm>>();
      final Iterator windowIterator = annotationIndex.iterator();
      try {
         while ( windowIterator.hasNext() ) {
            final Annotation window = (Annotation) windowIterator.next();
            if ( isWindowOk( window ) ) {
               processWindow( jcas, window, dictionaryTermsMap );

View Full Code Here

      try {
        jcas = aCAS.getJCas();
      } catch (CASException e) {
        throw new AnalysisEngineProcessException(e);
      }
      AnnotationIndex aIndx = jcas.getAnnotationIndex(SourceDocumentInformation.type);
      FSIterator aIter = aIndx.iterator();
      if (!aIter.isValid()) {
        String msg = name + " didn't find a SourceDocumentInformation annotation";
        System.out.println(msg);
        throw new AnalysisEngineProcessException(new Exception(msg));
      }

View Full Code Here

      // logger.setupDocument (getJCas ());


      FSIndex dbIndex = tcas.getAnnotationIndex(spanFeatureStructureType);
      FSIterator spanIterator = dbIndex.iterator();


      AnnotationIndex tokenIndex = (AnnotationIndex) tcas.getAnnotationIndex(tokenType);


      while (spanIterator.hasNext()) {
        ArrayList<AnnotationFS> tokens = new ArrayList<AnnotationFS>(2048);


        Annotation spanAnnotation = (Annotation) spanIterator.next();


        FSIterator tokenIter = tokenIndex.subiterator(spanAnnotation);


        // System.err.println ("Tokens:");


        // get all tokens for the specified block
        while (tokenIter.hasNext()) {

View Full Code Here


    ArrayList<Annotation> tokenList = new ArrayList<Annotation>();


    ArrayList<String> wordList = new ArrayList<String>();


    AnnotationIndex sentenceIndex = workingView.getAnnotationIndex(getType(workingView, this.theSentenceTypeName));
    AnnotationIndex tokenIndex = workingView.getAnnotationIndex(getType(workingView, this.theTokenTypeName));
    // iterate over Sentences
    FSIterator sentenceIterator = sentenceIndex.iterator();


    while (sentenceIterator.hasNext()) {
      Annotation sentence = (Annotation) sentenceIterator.next();


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


      FSIterator tokenIterator = tokenIndex.subiterator(sentence);
      while (tokenIterator.hasNext()) {
        TokenAnnotation token = (TokenAnnotation) tokenIterator.next();


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

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.