Examples of org.apache.uima.cas.FSIndex

org.apache.uima.cas.FSIndex
Feature structure index access interface.
Notice that each feature structure index uses its own ordering relation that will usually be different from index to index. In particular, equality with respect to the index ordering will in general not imply object identity for the feature structures.
We currently support three different kinds of indexes: sorted, set and bag indexes. The default index is a sorted index. In a sorted index, all FSs that are committed are entered, even if they are duplicates of already existing FSs. The index is sorted in the sense that iterators will output FSs in sorted order according to the comparator for that index. The order of FSs that are equal wrt the comparator is arbitrary but fixed. That is, if you iterate over the same index several times, you will see the same relative order of FSs every time. We also guarantee that reverse iterators will produce exactly the reverse sequence of forward iteration.
A set index will contain no duplicates of the same type, where a duplicate is defined by the indexing comparator. That is, if you commit two feature structures of the same type that are equal wrt the indexing comparator, only the first one will be entered into the index. Note that you can still have duplicates wrt the indexing order if they are of a different type. A set index is not guaranteed to be sorted.
A bag index finally simply stores everything, without any guaranteed order. Our current implementation works such that for any two FSs of the same type, they will be returned in the order in which they are committed (FIFO style). Note that any operation like find() or FSIterator.moveTo() will not produce useful results on bag indexes, since bag indexes do not honor comparators. Only use a bag index if you want very fast adding and will have to iterate over the whole index anyway.

      logger.logError(PARAM_DATA_BLOCK_FS + " '"
          + spanFeatureStructureName
          + "' specified, but does not exist: ");
      throw new AnnotatorInitializationException();
    }
    FSIndex dbIndex = tcas.getAnnotationIndex(spanFeatureStructureType);
    FSIterator spanIterator = dbIndex.iterator();
    while (spanIterator.hasNext()) {
      AnnotationFS enclosingSpanAnnotation = (AnnotationFS) spanIterator
          .next();
      String enclosingRegionSpan = enclosingSpanAnnotation
          .getCoveredText();

View Full Code Here

      setJCas(tcas.getJCas()); // this is needed to get around an issue
      // where UIMA crashes if no JCas is
      // referenced
      // 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);

View Full Code Here


      // create an annotation and add to index of both views
      AnnotationFS anAnnot = cas.createAnnotation(cas.getAnnotationType(), 0, 5);
      cas.getIndexRepository().addFS(anAnnot);
      cas2.getIndexRepository().addFS(anAnnot);
      FSIndex tIndex = cas.getAnnotationIndex();
      FSIndex t2Index = cas2.getAnnotationIndex();
      assertTrue(tIndex.size() == 2); // document annot and this one
      assertTrue(t2Index.size() == 2); // ditto


      // serialize
      StringWriter sw = new StringWriter();
      XMLSerializer xmlSer = new XMLSerializer(sw, false);
      XmiCasSerializer xmiSer = new XmiCasSerializer(cas.getTypeSystem());
      xmiSer.serialize(cas, xmlSer.getContentHandler());
      String xml = sw.getBuffer().toString();


      // deserialize into another CAS (repeat twice to check it still works after reset)
      CAS newCas = CasCreationUtils.createCas(typeSystem, new TypePriorities_impl(),
              new FsIndexDescription[0]);
      for (int i = 0; i < 2; i++) {
        XmiCasDeserializer newDeser = new XmiCasDeserializer(newCas.getTypeSystem());
        ContentHandler newDeserHandler = newDeser.getXmiCasHandler(newCas);
        SAXParserFactory fact = SAXParserFactory.newInstance();
        SAXParser parser = fact.newSAXParser();
        XMLReader xmlReader = parser.getXMLReader();
        xmlReader.setContentHandler(newDeserHandler);
        xmlReader.parse(new InputSource(new StringReader(xml)));


        // check sofas
        assertEquals("This is a test", newCas.getDocumentText());
        CAS newCas2 = newCas.getView("OtherSofa");
        assertEquals("This is only a test", newCas2.getDocumentText());


        // check that annotation is still indexed in both views
        assertTrue(tIndex.size() == 2); // document annot and this one
        assertTrue(t2Index.size() == 2); // ditto


        newCas.reset();
      }
    } catch (Exception e) {
      JUnitExtension.handleException(e);

View Full Code Here

      assertTrue(cas2.getAnnotationIndex(orgType).size() == 0);
      assertTrue(cas.getAnnotationIndex(orgType).size() > 0);


      // but that some types are still there
      Type personType = cas2.getTypeSystem().getType("org.apache.uima.testTypeSystem.Person");
      FSIndex personIndex = cas2.getAnnotationIndex(personType);
      assertTrue(personIndex.size() > 0);


      // check that mentionType has been filtered out (set to null)
      FeatureStructure somePlace = personIndex.iterator().get();
      Feature mentionTypeFeat = personType.getFeatureByBaseName("mentionType");
      assertNotNull(mentionTypeFeat);
      assertNull(somePlace.getStringValue(mentionTypeFeat));
    } catch (Exception e) {
      JUnitExtension.handleException(e);

View Full Code Here

      int numSofas = 0;
      while (sofaIter.isValid()) {
        numSofas++;
        sofaIter.moveToNext();
      }
      FSIndex engIndex = engTcas.getAnnotationIndex();
      FSIndex gerIndex = gerTcas.getAnnotationIndex();
      FSIndex frIndex = frTcas.getAnnotationIndex();
      // assertTrue(sofaIndex.size() == 3); // 3 sofas
      assertTrue(numSofas == 3);
      assertTrue(engIndex.size() == 5); // 4 annots plus
      // documentAnnotation
      assertTrue(gerIndex.size() == 5); // 4 annots plus
      // documentAnnotation
      assertTrue(frIndex.size() == 5); // 4 annots plus
      // documentAnnotation


      // Test that the annotations are of the correct types
      FSIterator engIt = engIndex.iterator();
      FSIterator gerIt = gerIndex.iterator();
      FSIterator frIt = frIndex.iterator();
      AnnotationFS engAnnot = (AnnotationFS) engIt.get();
      AnnotationFS gerAnnot = (AnnotationFS) gerIt.get();
      AnnotationFS frAnnot = (AnnotationFS) frIt.get();
      assertTrue(docAnnotationType.getName().equals(engAnnot.getType().getName()));
      assertTrue(docAnnotationType.getName().equals(gerAnnot.getType().getName()));

View Full Code Here

      setJCas(tcas.getJCas()); // this is needed to get around an issue
      // where UIMA crashes if no JCas is
      // referenced
      // 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);

View Full Code Here

          new Object[] { FsVariables.VALUE_FEATURE_NAME });
    }
  }


  public boolean checkCas(CAS cas) {
    FSIndex variableIndex = cas.getIndexRepository().getIndex(FsVariables.INDEX_NAME);
    if (variableIndex == null) {
      return false;
    }
    TypeSystem ts = cas.getTypeSystem();
    Type type = ts.getType(FsVariables.TYPE_NAME);

View Full Code Here

  /**
   * @see JCasAnnotator_ImplBase#process(JCas)
   */
  public void process(JCas aJCas) {
    // get annotation indexes
    FSIndex roomNumberIndex = aJCas.getAnnotationIndex(RoomNumber.type);
    FSIndex dateIndex = aJCas.getAnnotationIndex(DateAnnot.type);
    FSIndex timeIndex = aJCas.getAnnotationIndex(TimeAnnot.type);


    // store end position of last meeting we identified, to prevent multiple
    // annotations over same span
    int lastMeetingEnd = -1;


    // iterate over all combinations
    Iterator roomNumberIter = roomNumberIndex.iterator();
    while (roomNumberIter.hasNext()) {
      RoomNumber room = (RoomNumber) roomNumberIter.next();


      Iterator dateIter = dateIndex.iterator();
      while (dateIter.hasNext()) {
        DateAnnot date = (DateAnnot) dateIter.next();


        Iterator time1Iter = timeIndex.iterator();
        while (time1Iter.hasNext()) {
          TimeAnnot time1 = (TimeAnnot) time1Iter.next();


          Iterator time2Iter = timeIndex.iterator();
          while (time2Iter.hasNext()) {
            TimeAnnot time2 = (TimeAnnot) time2Iter.next();


            // times must be different annotations
            if (time1 != time2) {

View Full Code Here

    // later go back and add these to the CAS indexes. We need to do this
    // because it's not allowed to add to an index that you're currently
    // iterating over.
    List uimaMeetings = new ArrayList();


    FSIndex meetingIndex = aJCas.getAnnotationIndex(Meeting.type);
    FSIterator iter = meetingIndex.iterator();
    while (iter.isValid()) {
      Meeting meeting = (Meeting) iter.get();
      // get span of text within 50 chars on either side of meeting
      // (window size should probably be a config. param)
      int begin = meeting.getBegin() - 50;

View Full Code Here

    // call a CAS Analysis Engine that "translates" the English document
    // and puts the translation into a German Sofa
    seAnnotator.process(cas);


    // get annotation iterator for the English CAS view
    FSIndex anIndex = englishView.getAnnotationIndex();
    FSIterator anIter = anIndex.iterator();


    // and print out all annotations found
    System.out.println("---Printing all annotations for English Sofa---");
    while (anIter.isValid()) {
      AnnotationFS annot = (AnnotationFS) anIter.get();
      System.out.println(" " + annot.getType().getName() + ": " + annot.getCoveredText());
      anIter.moveToNext();
    }


    // now try to get the CAS view for the German Sofa
    System.out.println();
    CAS germanView = cas.getView("GermanDocument");


    // and annotator iterator for the German CAS View
    anIndex = germanView.getAnnotationIndex();
    anIter = anIndex.iterator();
    Type cross = germanView.getTypeSystem().getType("sofa.test.CrossAnnotation");
    Feature other = cross.getFeatureByBaseName("otherAnnotation");


    // print out all annotations for the German Sofa
    System.out.println("---Printing all annotations for German Sofa---");

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.apache.uima.cas.FSIndex

edu.pitt.dbmi.nlp.noble.uima.NobleCoderUimaAnnotator

edu.pitt.dbmi.nobletools.uima.NobleCoderUimaAnnotator

opennlp.uima.doccat.DocumentCategorizerTrainer

org.apache.ctakes.utils.test.TestUtil

org.apache.uima.analysis_engine.impl.AnalysisEngine_implTest

org.apache.uima.cas.impl.CASImpl

org.apache.uima.cas.impl.CASMgrSerializer

org.apache.uima.cas.impl.FSIndexRepositoryImpl

org.apache.uima.cas.impl.XCASDeserializerTest

org.apache.uima.cas.impl.XmiCasDeserializerTest

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.