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.

    cas1.setDocumentText("This is a test document in the initial view");
    AnnotationFS anAnnot1 = cas1.createAnnotation(cas1.getAnnotationType(), 0, 4);
    cas1.getIndexRepository().addFS(anAnnot1);
    AnnotationFS anAnnot2 = cas1.createAnnotation(cas1.getAnnotationType(), 5, 10);
    cas1.getIndexRepository().addFS(anAnnot2);
    FSIndex tIndex = cas1.getAnnotationIndex();
    assertTrue(tIndex.size() == 3); //doc annot plus  annots
    
    //serialize complete  
    XmiSerializationSharedData sharedData = new XmiSerializationSharedData();
    String xml = this.serialize(cas1, sharedData);
    int maxOutgoingXmiId = sharedData.getMaxXmiId();
    //deserialize into cas2
    XmiSerializationSharedData sharedData2 = new XmiSerializationSharedData();      
    //XmiCasDeserializer.deserialize(new StringBufferInputStream(xml), cas2, true, sharedData2);
    this.deserialize(xml, cas2, sharedData2, true, -1);
    CasComparer.assertEquals(cas1, cas2);
    
    //create Marker, add/modify fs and serialize in delta xmi format.
    Marker marker = cas2.createMarker();
    FSIndex cas2tIndex = cas2.getAnnotationIndex();
    
    //create an annotation and add to index
    AnnotationFS cas2newAnnot = cas2.createAnnotation(cas2.getAnnotationType(), 6, 8);
    cas2.getIndexRepository().addFS(cas2newAnnot);
    assertTrue(cas2tIndex.size() == 4); // prev annots and this new one
    
    //modify an existing annotation
    Iterator<FeatureStructure> tIndexIter = cas2tIndex.iterator();
    AnnotationFS docAnnot = (AnnotationFS) tIndexIter.next(); //doc annot
    //delete from index
    AnnotationFS delAnnot = (AnnotationFS) tIndexIter.next(); //annot
    cas2.getIndexRepository().removeFS(delAnnot);
    assertTrue(cas2.getAnnotationIndex().size() == 3);

View Full Code Here

      this.deserialize(xml, cas2, sharedData2, true, -1);
      CasComparer.assertEquals(cas1, cas2);
      
      //create Marker, add/modify fs and serialize in delta xmi format.
      Marker marker = cas2.createMarker();
      FSIndex cas2tIndex = cas2.getAnnotationIndex();
      
      //create an annotation and add to index
      AnnotationFS cas2newAnnot = cas2.createAnnotation(cas2.getAnnotationType(), 6, 8);
      cas2.getIndexRepository().addFS(cas2newAnnot);
      assertTrue(cas2tIndex.size() == 4); // prev annots and this new one
      
      //modify language feature
      Iterator<FeatureStructure> tIndexIter = cas2tIndex.iterator();
      AnnotationFS docAnnot = (AnnotationFS) tIndexIter.next();
      Feature languageF = cas2.getDocumentAnnotation().getType().getFeatureByBaseName(CAS.FEATURE_BASE_NAME_LANGUAGE);
      docAnnot.setStringValue(languageF, "en");
     
      // serialize cas2 in delta format

View Full Code Here

        this.deserialize(xml, cas2, sharedData2, true, -1);
        CasComparer.assertEquals(cas1, cas2);
        
        //create Marker, add/modify fs and serialize in delta xmi format.
        Marker marker = cas2.createMarker();
        FSIndex cas2tIndex = cas2.getAnnotationIndex();
        
        // serialize cas2 in delta format 
        String deltaxml1 = serialize(cas2, sharedData2, marker);
        //System.out.println(deltaxml1);

View Full Code Here

      cas1.setDocumentText("This is a test document in the initial view");
      AnnotationFS anAnnot1 = cas1.createAnnotation(cas1.getAnnotationType(), 0, 4);
      cas1.getIndexRepository().addFS(anAnnot1);
      AnnotationFS anAnnot2 = cas1.createAnnotation(cas1.getAnnotationType(), 5, 10);
      cas1.getIndexRepository().addFS(anAnnot2);
      FSIndex tIndex = cas1.getAnnotationIndex();
      assertTrue(tIndex.size() == 3); //doc annot plus 2 annots
      
      //serialize complete  
      XmiSerializationSharedData sharedData = new XmiSerializationSharedData();
      String xml = serialize(cas1, sharedData);
      int maxOutgoingXmiId = sharedData.getMaxXmiId();
      
      //deserialize into cas2
      XmiSerializationSharedData sharedData2 = new XmiSerializationSharedData();      
      this.deserialize(xml, cas2, sharedData2, true, -1);
      CasComparer.assertEquals(cas1, cas2);
      
      //create Marker, add/modify fs and serialize in delta xmi format.
      Marker marker = cas2.createMarker();
      FSIndex cas2tIndex = cas2.getAnnotationIndex();
      
      //create an annotation and add to index
      AnnotationFS cas2newAnnot = cas2.createAnnotation(cas2.getAnnotationType(), 6, 8);
      cas2.getIndexRepository().addFS(cas2newAnnot);
      assertTrue(cas2tIndex.size() == 4); // prev annots and this new one
      
      //modify language feature
      Iterator<FeatureStructure> tIndexIter = cas2tIndex.iterator();
      AnnotationFS docAnnot = (AnnotationFS) tIndexIter.next();
      
      //delete annotation from index    
      AnnotationFS delAnnot = (AnnotationFS) tIndexIter.next(); //annot
      cas2.getIndexRepository().removeFS(delAnnot);

View Full Code Here

      cas1.getIndexRepository().addFS(anAnnot2);
      AnnotationFS anAnnot3 = cas1.createAnnotation(cas1.getAnnotationType(), 8, 13);
      cas1.getIndexRepository().addFS(anAnnot3);
      AnnotationFS anAnnot4 = cas1.createAnnotation(cas1.getAnnotationType(), 15, 30);
      cas1.getIndexRepository().addFS(anAnnot4);
      FSIndex tIndex = cas1.getAnnotationIndex();
      assertTrue(tIndex.size() == 5); //doc annot plus 4 annots
      
      FeatureStructure entityFS = cas1.createFS(entityType);
      cas1.getIndexRepository().addFS(entityFS);
      
      StringArrayFS strArrayFS = cas1.createStringArrayFS(5);
      strArrayFS.set(0, "class1");
      entityFS.setFeatureValue(classesFeat, strArrayFS);
      
      //create listFS and set the link feature
      FeatureStructure emptyNode = cas1.createFS(emptyFsListType);
      FeatureStructure secondNode = cas1.createFS(nonEmptyFsListType);
      secondNode.setFeatureValue(headFeat, anAnnot2);
      secondNode.setFeatureValue(tailFeat, emptyNode);
      FeatureStructure firstNode = cas1.createFS(nonEmptyFsListType);
      firstNode.setFeatureValue(headFeat, anAnnot1);
      firstNode.setFeatureValue(tailFeat, secondNode);
      entityFS.setFeatureValue(linksFeat, firstNode);
      
      // create a view w/o setting document text
      CAS view1 = cas1.createView("View1");
      
      // create another view 
      CAS preexistingView = cas1.createView("preexistingView");
      String preexistingViewText = "John Smith blah blah blah";
      preexistingView.setDocumentText(preexistingViewText);
      AnnotationFS person1Annot = createPersonAnnot(preexistingView, 0, 10);
      person1Annot.setStringValue(componentIdFeat, "deltacas1");
      AnnotationFS person2Annot = createPersonAnnot(preexistingView, 0, 5);
      AnnotationFS orgAnnot = preexistingView.createAnnotation(orgType, 16, 24);
      preexistingView.addFsToIndexes(orgAnnot);
      
      AnnotationFS ownerAnnot = preexistingView.createAnnotation(ownerType, 0, 24);
      preexistingView.addFsToIndexes(ownerAnnot);
      FeatureStructure relArgs = cas1.createFS(relArgsType);
      relArgs.setFeatureValue(domainFeat, person1Annot);
      ownerAnnot.setFeatureValue(argsFeat, relArgs);
      
      //serialize complete  
      XmiSerializationSharedData sharedData = new XmiSerializationSharedData();
      String xml = serialize(cas1, sharedData);
      int maxOutgoingXmiId = sharedData.getMaxXmiId();
      //System.out.println("CAS1 " + xml);
      //System.out.println("MaxOutgoingXmiId " + maxOutgoingXmiId);
   
      //deserialize into cas2
      XmiSerializationSharedData sharedData2 = new XmiSerializationSharedData();      
      this.deserialize(xml, cas2, sharedData2, true, -1);
      CasComparer.assertEquals(cas1, cas2);
 
      //=======================================================================
      //create Marker, add/modify fs and serialize in delta xmi format.
      Marker marker = cas2.createMarker();
      FSIndex cas2tIndex = cas2.getAnnotationIndex();
      CAS cas2preexistingView = cas2.getView("preexistingView");
      FSIndex cas2personIndex = cas2preexistingView.getAnnotationIndex(personType);
      FSIndex cas2orgIndex = cas2preexistingView.getAnnotationIndex(orgType);
      FSIndex cas2ownerIndex = cas2preexistingView.getAnnotationIndex(ownerType);
      
      // create an annotation and add to index
      AnnotationFS cas2anAnnot5 = cas2.createAnnotation(cas2.getAnnotationType(), 6, 8);
      cas2.getIndexRepository().addFS(cas2anAnnot5);
      assertTrue(cas2tIndex.size() == 6); // prev annots and this new one
     
      // set document text of View1
      CAS cas2view1 = cas2.getView("View1");
      cas2view1.setDocumentText("This is the View1 document.");
      //create an annotation in View1
      AnnotationFS cas2view1Annot = cas2view1.createAnnotation(cas2.getAnnotationType(), 1, 5);
      cas2view1.getIndexRepository().addFS(cas2view1Annot);
      FSIndex cas2view1Index = cas2view1.getAnnotationIndex();
      assertTrue(cas2view1Index.size() == 2); //document annot and this annot
      
      //modify an existing annotation
      Iterator<FeatureStructure> tIndexIter = cas2tIndex.iterator();
      AnnotationFS docAnnot = (AnnotationFS) tIndexIter.next(); //doc annot
      AnnotationFS modAnnot1 = (AnnotationFS) tIndexIter.next();

View Full Code Here

        cas1.getIndexRepository().addFS(anAnnot2);
        AnnotationFS anAnnot3 = cas1.createAnnotation(cas1.getAnnotationType(), 8, 13);
        cas1.getIndexRepository().addFS(anAnnot3);
        AnnotationFS anAnnot4 = cas1.createAnnotation(cas1.getAnnotationType(), 15, 30);
        cas1.getIndexRepository().addFS(anAnnot4);
        FSIndex tIndex = cas1.getAnnotationIndex();
        assertTrue(tIndex.size() == 5); //doc annot plus 4 annots
        
        FeatureStructure entityFS = cas1.createFS(entityType);
        cas1.getIndexRepository().addFS(entityFS);
        
        StringArrayFS strArrayFS = cas1.createStringArrayFS(5);
        strArrayFS.set(0, "class1");
        entityFS.setFeatureValue(classesFeat, strArrayFS);
        
        //create listFS and set the link feature
        FeatureStructure emptyNode = cas1.createFS(emptyFsListType);
        FeatureStructure secondNode = cas1.createFS(nonEmptyFsListType);
        secondNode.setFeatureValue(headFeat, anAnnot2);
        secondNode.setFeatureValue(tailFeat, emptyNode);
        FeatureStructure firstNode = cas1.createFS(nonEmptyFsListType);
        firstNode.setFeatureValue(headFeat, anAnnot1);
        firstNode.setFeatureValue(tailFeat, secondNode);
        entityFS.setFeatureValue(linksFeat, firstNode);
        
        // create a view w/o setting document text
        CAS view1 = cas1.createView("View1");
         
        //serialize complete  
        XmiSerializationSharedData sharedData = new XmiSerializationSharedData();
        String xml = serialize(cas1, sharedData);
        int maxOutgoingXmiId = sharedData.getMaxXmiId();
        //System.out.println("CAS1 " + xml);
        //System.out.println("MaxOutgoingXmiId " + maxOutgoingXmiId);
     
        //deserialize into cas2
        XmiSerializationSharedData sharedData2 = new XmiSerializationSharedData();      
        this.deserialize(xml, cas2, sharedData2, true, -1);
        CasComparer.assertEquals(cas1, cas2);
   
        //=======================================================================
        //create Marker, add/modify fs and serialize in delta xmi format.
        Marker marker = cas2.createMarker();
        FSIndex cas2tIndex = cas2.getAnnotationIndex();
        
        // create an annotation and add to index
        AnnotationFS cas2anAnnot5 = cas2.createAnnotation(cas2.getAnnotationType(), 6, 8);
        cas2.getIndexRepository().addFS(cas2anAnnot5);
        assertTrue(cas2tIndex.size() == 6); // prev annots and this new one
        // create an annotation and add to index
        AnnotationFS cas2anAnnot6 = cas2.createAnnotation(cas2.getAnnotationType(), 6, 8);
        cas2.getIndexRepository().addFS(cas2anAnnot6);
        assertTrue(cas2tIndex.size() == 7); // prev annots and twonew one
        
        //add to FSList 
        Iterator<FeatureStructure> iter = cas2.getIndexRepository().getIndex("testEntityIndex").iterator();
        FeatureStructure cas2EntityFS = iter.next();
        FeatureStructure cas2linksFS = cas2EntityFS.getFeatureValue(linksFeat);

View Full Code Here

      Assert.assertEquals("EnumType", et.getName());
      Assert.assertEquals(et, f2.getRange());


      // indexes
      FSIndexRepository irep = cas.getIndexRepository();
      FSIndex ind = irep.getIndex("Index1");
      Assert.assertNotNull(ind);
      Assert.assertEquals("Type1", ind.getType().getName());
      Assert.assertEquals(FSIndex.SORTED_INDEX, ind.getIndexingStrategy());


      FeatureStructure fs1 = cas.createFS(t1);
      fs1.setIntValue(f1, 0);
      FeatureStructure fs2 = cas.createFS(t1);
      fs2.setIntValue(f1, 1);
      Assert.assertTrue(ind.compare(fs1, fs2) < 0);


      FSIndex ind2 = irep.getIndex("Index2");
      Assert.assertNotNull(ind2);
      Assert.assertEquals("Type2", ind2.getType().getName());
      Assert.assertEquals(FSIndex.SET_INDEX, ind2.getIndexingStrategy());


      FeatureStructure fs3 = cas.createFS(t2);
      fs3.setStringValue(f2, "One");
      FeatureStructure fs4 = cas.createFS(t2);
      fs4.setStringValue(f2, "Two");
      Assert.assertTrue(ind2.compare(fs3, fs4) > 0);


      FSIndex ind3 = irep.getIndex("Index3");
      Assert.assertNotNull(ind3);
      Assert.assertEquals("uima.tcas.Annotation", ind3.getType().getName());
      Assert.assertEquals(FSIndex.SORTED_INDEX, ind3.getIndexingStrategy());


      AnnotationFS fs5 = cas.createAnnotation(t1, 0, 0);
      AnnotationFS fs6 = cas.createAnnotation(t2, 0, 0);
      AnnotationFS fs7 = cas.createAnnotation(t1, 0, 0);
      Assert.assertTrue(ind3.compare(fs5, fs6) < 0);
      Assert.assertTrue(ind3.compare(fs6, fs7) > 0);


      // only way to check if allowed values is correct is to try to set an
      // invalid value?
      CASRuntimeException ex = null;
      try {

View Full Code Here


      // Test that the annotations are in separate index spaces, and that Sofas are indexed
      JFSIndexRepository indexes = jcas.getJFSIndexRepository();
      // FSIndex sofaIndex = indexes.getIndex(CAS.SOFA_INDEX_NAME);
      indexes = engJcas.getJFSIndexRepository();
      FSIndex engIndex = indexes.getAnnotationIndex(Annotation.type);
      indexes = gerJcas.getJFSIndexRepository();
      FSIndex gerIndex = indexes.getAnnotationIndex(Annotation.type);
      indexes = frJcas.getJFSIndexRepository();
      FSIndex frIndex = indexes.getAnnotationIndex(Annotation.type);
      FSIterator sofaIter = jcas.getSofaIterator();
      int numSofas = 0;
      while (sofaIter.isValid()) {
        numSofas++;
        sofaIter.moveToNext();
      }
      // 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();
      Annotation engAnnot = (Annotation) engIt.get();
      Annotation gerAnnot = (Annotation) gerIt.get();
      Annotation frAnnot = (Annotation) frIt.get();
      assertTrue((CAS.TYPE_NAME_DOCUMENT_ANNOTATION).equals(engAnnot.getType().getName()));
      assertTrue((CAS.TYPE_NAME_DOCUMENT_ANNOTATION).equals(gerAnnot.getType().getName()));

View Full Code Here

      }
      return;
    }
    // Attempt to find a non-set index first.
    // If none found, then use the an arbitrary set index if any.
    FSIndex setIndex = null;
    final Iterator<String> iter = getLabels();
    while (iter.hasNext()) {
      final String label = iter.next();
      final FSIndex index = getIndex(label);
      // Ignore auto-indexes at this stage, they're handled above.
      if (index.getIndexingStrategy() == FSIndex.DEFAULT_BAG_INDEX) {
        continue;
      }
      if (this.typeSystem.subsumes(index.getType(), type)) {
        if (index.getIndexingStrategy() != FSIndex.SET_INDEX) {
          iteratorList.add(getIndex(label, type).iterator());
          // Done, found non-set index.
          return;
        }
        setIndex = getIndex(label, type);

View Full Code Here

      }
      return;
    }
    // Attempt to find a non-set index first.
    // If none found, then use the an arbitrary set index if any.
    FSIndex setIndex = null;
    final Iterator<String> iter = getLabels();
    while (iter.hasNext()) {
      final String label = iter.next();
      final FSIndex index = getIndex(label);
      // Ignore auto-indexes at this stage, they're handled above.
      if (index.getIndexingStrategy() == FSIndex.DEFAULT_BAG_INDEX) {
        continue;
      }
      if (this.typeSystem.subsumes(index.getType(), type)) {
        if (index.getIndexingStrategy() != FSIndex.SET_INDEX) {
          iteratorList.add(getIndex(label, type).iterator());
          // Done, found non-set index.
          return;
        }
        setIndex = getIndex(label, type);

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.