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.


      // 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

      enqueueIndexed();
      enqueueFeaturesOfIndexed();
      iElementCount += indexedFSs.size();
      iElementCount += queue.size();


      FSIndex sofaIndex = cas.getBaseCAS().indexRepository.getIndex(CAS.SOFA_INDEX_NAME);
      iElementCount += (sofaIndex.size() + 1); // one View element per sofa, plus 1 for base


      workAttrs.clear();
      computeNamespaceDeclarationAttrs(workAttrs);
      workAttrs.addAttribute(XMI_NS_URI, XMI_VERSION_LOCAL_NAME, XMI_VERSION_QNAME, "CDATA",
              XMI_VERSION_VALUE);

View Full Code Here

      this.indexNames[i] = label;
    }
    // Create a vector of the indexes, and build the name-to-index map.
    this.nameToIndexMap = new int[numNames];
    Vector indexVector = new Vector();
    FSIndex index;
    int pos;
    for (int i = 0; i < numNames; i++) {
      index = ir.getIndex(this.indexNames[i]);
      pos = indexVector.indexOf(index);
      if (pos < 0) {

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


      r2.addToIndexes();
      r1.addToIndexes();


      JFSIndexRepository jfsi = jcas.getJFSIndexRepository();
      FSIndex fsi1 = jfsi.getIndex("all", Root.type);
      FSIterator fsit1 = fsi1.iterator();
      assertTrue(fsit1.isValid());
      assertTrue(r2 == fsit1.get());
      fsit1.moveToNext();
      assertTrue(fsit1.isValid());
      assertTrue(r1 == fsit1.get());

View Full Code Here

      a1.addToIndexes();
      FeatureStructure f1 = localCas.createFS(subTok);
      localCas.getIndexRepository().addFS(f1);


      JFSIndexRepository ir = jcas.getJFSIndexRepository();
      FSIndex index = ir.getAnnotationIndex();
      FSIterator it = index.iterator();


      try {


        while (it.isValid()) {
          assertTrue(it.get() instanceof Annotation);

View Full Code Here

    Serialization.deserializeCASComplete(cs, realCasMgr);
    cas = ((CASImpl) realCasMgr).getCurrentView();
    casMgr = (CASMgr) cas;


    // System.out.println("After serialization\n");
    FSIndex index = cas.getAnnotationIndex();
    assertTrue(index != null);
    assertTrue(index.getIndexingStrategy() == FSIndex.SORTED_INDEX);
    // System.out.println("Size of ordered index: " + index.size());
    assertTrue(index.size() == ordSize);


    index = cas.getIndexRepository().getIndex(ANNOT_BAG_INDEX);
    assertTrue(index != null);
    assertTrue(index.getIndexingStrategy() == FSIndex.BAG_INDEX);
    // System.out.println("Size of bag index: " + index.size());
    assertTrue(index.size() == bagSize);


    index = cas.getIndexRepository().getIndex(ANNOT_SET_INDEX);
    assertTrue(index != null);
    assertTrue(index.getIndexingStrategy() == FSIndex.SET_INDEX);
    // System.out.println("Size of set index: " + index.size());
    // System.out.println("Should be: " + setSize);
    assertTrue(index.size() == setSize);


  }

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);
    XCASSerializer xcasSer = new XCASSerializer(cas.getTypeSystem());
    xcasSer.serialize(cas, xmlSer.getContentHandler(), true);
    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(), indexes);
    for (int i = 0; i < 2; i++) {
      XCASDeserializer newDeser = new XCASDeserializer(newCas.getTypeSystem());
      ContentHandler newDeserHandler = newDeser.getXCASHandler(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();
    }
  }

View Full Code Here

    FSIndexRepository indexRepository = cas.getIndexRepository();
    // assert(indexRepository != null);
    Iterator labelIt = indexRepository.getLabels();
    assertTrue(labelIt != null);
    // Get the standard index for tokens.
    FSIndex tokenIndex = cas.getAnnotationIndex(tokenType);
    // assert(tokenIndex != null);
    // Get an iterator over tokens.
    FSIterator it = tokenIndex.iterator();
    // assert(it != null);
    // Now create sentences. We do this as follows: a sentence starts where
    // the first token after an EOS starts, and ends with an EOS.
    long time = System.currentTimeMillis();
    int endOfSentenceCounter = 0;

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.