Examples of org.apache.uima.collection.CollectionProcessingEngine

org.apache.uima.collection.CollectionProcessingEngine
A CollectionProcessingEngine (CPE) processes a collection of artifacts (for text analysis applications, this will be a collection of documents) and produces collection-level results.
A CPE consists of a {@link org.apache.uima.collection.CollectionReader}, zero or more {@link org.apache.uima.analysis_engine.AnalysisEngine}s and zero or more {@link org.apache.uima.collection.CasConsumer}s. The Collection Reader is responsible for reading artifacts from a collection and setting up the CAS. The AnalysisEngines analyze each CAS and the results are passed on to the CAS Consumers. CAS Consumers perform analysis over multiple CASes and generally produce collection-level results in some application-specific data structure.
Processing is started by calling the {@link #process()} method. Processing can be controlled viathe {@link #pause()}, {@link #resume()}, and {@link #stop()} methods.
Listeners can register with the CPE by calling the {@link #addStatusCallbackListener(StatusCallbackListener)} method. These listeners receive statuscallbacks during the processing. At any time, performance and progress reports are available from the {@link #getPerformanceReport()} and {@link #getProgress()} methods.
A CPE implementation may choose to implement parallelization of the processing, but this is not a requirement of the architecture.
Note that a CPE only supports processing one collection at a time. Attempting to start a new processing job while a previous processing job is running will result in an exception. Processing multiple collections simultaneously is done by instantiating and configuring multiple instances of the CPE.
A CollectionProcessingEngine instance can be obtained by calling {@link org.apache.uima.UIMAFramework#produceCollectionProcessingEngine(CpeDescription)}.

   * @return CollectionProcessingEngine - initialized cpe
   */
  private CollectionProcessingEngine setupCpm(int documentCount, String exceptionName,
          int exceptionSequence, String functionName) {
    CpeDescription cpeDesc = null;
    CollectionProcessingEngine cpe = null;


    try {
      String colReaderBase = JUnitExtension.getFile(
              "CpmTests" + FS + "ErrorTestCollectionReader.xml").getAbsolutePath();
      String taeBase = JUnitExtension.getFile("CpmTests" + FS + "ErrorTestAnnotator.xml")

View Full Code Here

      params.put(Resource.PARAM_PERFORMANCE_TUNING_SETTINGS, newProps);


      CpeDescription cpeDesc = UIMAFramework.getXMLParser().parseCpeDescription(
    new XMLInputSource(JUnitExtension
        .getFile("CollectionProcessingEngineImplTest/performanceTuningSettingsTestCpe.xml")));
      CollectionProcessingEngine cpe = UIMAFramework.produceCollectionProcessingEngine(cpeDesc,
    params);
      cpe.process();
      // Need to give CPE time to do its work. The following should work, but
      // doesn't
      // while (cpe.isProcessing())
      // {
      // Thread.sleep(1000);

View Full Code Here

      ResourceManager rm = UIMAFramework.newDefaultResourceManager();
      rm.setDataPath(TEST_DATAPATH);
      CpeDescription cpeDesc = UIMAFramework.getXMLParser().parseCpeDescription(
    new XMLInputSource(JUnitExtension
        .getFile("CollectionProcessingEngineImplTest/externalResourceTestCpe.xml")));
      CollectionProcessingEngine cpe = UIMAFramework.produceCollectionProcessingEngine(cpeDesc, rm,
    null);
      CollectionReader colRdr = (CollectionReader) cpe.getCollectionReader();
      assertNotNull(colRdr.getUimaContext().getResourceObject("TestFileResource"));
      CasInitializer casIni = colRdr.getCasInitializer();
      assertNotNull(casIni.getUimaContext().getResourceObject("TestFileLanguageResource",
    new String[] { "en" }));
      AnalysisEngine ae = (AnalysisEngine) cpe.getCasProcessors()[0];
      assertNotNull(ae.getUimaContext().getResourceObject("TestResourceObject"));
      assertNotNull(ae.getUimaContext().getResourceObject("TestLanguageResourceObject",
    new String[] { "en" }));
    } catch (Exception e) {
      JUnitExtension.handleException(e);

View Full Code Here

  
  public void testCasMultiplierTypeSystem() throws Throwable {
    CpeDescription cpeDesc = UIMAFramework.getXMLParser()
            .parseCpeDescription(new XMLInputSource(
                    JUnitExtension.getFile("CollectionProcessingEngineImplTest/cpeWithWrappedCasMultiplier.xml")));
    CollectionProcessingEngine cpe = UIMAFramework.produceCollectionProcessingEngine(cpeDesc);
    // create and register a status callback listener
    TestStatusCallbackListener listener = new TestStatusCallbackListener();
    cpe.addStatusCallbackListener(listener);


    // run CPM
    cpe.process();


    // wait until CPM has finished
    while (!listener.isFinished()) {
      Thread.sleep(5);
    }

View Full Code Here

  public void testCpmStopSingleThread() throws Exception {
    int documentCount = 100000; // hopefully enough that we won't finish before we abort
    int threadCount = 1;


    // setup CPM to process 100 documents
    CollectionProcessingEngine cpe = setupCpm(documentCount, threadCount, false);


    // create and register a status callback listener
    TestStatusCallbackListener listener = new TestStatusCallbackListener();
    cpe.addStatusCallbackListener(listener);


    // run CPM
    cpe.process();


    // sleep a bit
    Thread.sleep(1000);


    // stop CPM
    cpe.stop();


    // wait until CPM has aborted
    while (!listener.isAborted()) {
      Thread.sleep(5);
    }

View Full Code Here

  public void testCpmStopMultipleThreads() throws Exception {
    int documentCount = 100000; // hopefully enough that we won't finish before we abort
    int threadCount = 5;


    // setup CPM to process 100 documents
    CollectionProcessingEngine cpe = setupCpm(documentCount, threadCount, false);


    // create and register a status callback listener
    TestStatusCallbackListener listener = new TestStatusCallbackListener();
    cpe.addStatusCallbackListener(listener);


    // run CPM
    cpe.process();


    // sleep a bit
    Thread.sleep(1000);


    // stop CPM
    cpe.stop();


    // wait until CPM has aborted
    while (!listener.isAborted()) {
      Thread.sleep(5);
    }

View Full Code Here

  public void testCpmStopSlowAnnotator() throws Exception {
    int documentCount = 1000; // hopefully enough that we won't finish before we abort
    int threadCount = 1;


    // setup CPM to process 100 documents
    final CollectionProcessingEngine cpe = setupCpm(documentCount, threadCount, true);


    // register status callback listener
    final TestStatusCallbackListener listener = new TestStatusCallbackListener();
    cpe.addStatusCallbackListener(listener);


    // run CPM
    cpe.process();


    // sleep a bit
    Thread.sleep(1000);


    // stop CPM
    cpe.stop();


    // wait until CPM has aborted
    while (!listener.isAborted()) {
      Thread.sleep(5);
    }

View Full Code Here

  public void testCpmStopImmediate() throws Exception {
    int documentCount = 100000; // hopefully enough that we won't finish before we abort
    int threadCount = 1;


    // setup CPM to process 100 documents
    CollectionProcessingEngine cpe = setupCpm(documentCount, threadCount, false);


    // create and register a status callback listener
    TestStatusCallbackListener listener = new TestStatusCallbackListener();
    cpe.addStatusCallbackListener(listener);


    // run CPM
    cpe.process();


    // stop CPM immediately
    cpe.stop();


    // wait until CPM has aborted
    while (!listener.isAborted()) {
      Thread.sleep(5);
    }

View Full Code Here

   * @return CollectionProcessingEngine - initialized cpe
   */
  private CollectionProcessingEngine setupCpm(int documentCount, int threadCount,
          boolean useSlowAnnotator) throws Exception {
    CpeDescription cpeDesc = null;
    CollectionProcessingEngine cpe = null;


    String colReaderBase = JUnitExtension.getFile("CpmTests" + separator
            + "ErrorTestCollectionReader.xml").getAbsolutePath();
    String taeBase = JUnitExtension.getFile("CpmTests" + separator + "ErrorTestAnnotator.xml").getAbsolutePath();
    String casConsumerBase = JUnitExtension.getFile("CpmTests" + separator

View Full Code Here

    // process 100 documents and multiple threads
    int documentCount = 100;
    int threadCount = 5;


    // setup CPM to process 100 documents
    CollectionProcessingEngine cpe = setupCpm(documentCount, threadCount);


    // create and register a status callback listener
    TestStatusCallbackListener listener = new TestStatusCallbackListener() {
      TypeSystem sts = null;
      public void entityProcessComplete(CAS aCas, EntityProcessStatus aStatus) {
        super.entityProcessComplete(aCas, aStatus);
        if (sts == null) {
          sts = aCas.getTypeSystem();
        } else {
          Assert.assertTrue(sts == aCas.getTypeSystem());
        }
      }      
    };
    cpe.addStatusCallbackListener(listener);


    // run CPM
    cpe.process();


    // wait until CPM has finished
    while (!listener.isFinished()) {
      Thread.sleep(5);
    }

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.apache.uima.collection.CollectionProcessingEngine

org.apache.ctakes.core.cpe.CmdLineCpeRunner

org.apache.ctakes.regression.test.RegressionPipelineTest

org.apache.uima.collection.impl.CollectionProcessingEngine_implTest

org.apache.uima.collection.impl.cpm.CasPoolTest

org.apache.uima.collection.impl.cpm.CpeImportTest

org.apache.uima.collection.impl.cpm.CpmAE_ErrorTest

org.apache.uima.collection.impl.cpm.CpmAE_ErrorTests

org.apache.uima.collection.impl.cpm.CpmCasConsumer_ErrorTest

org.apache.uima.collection.impl.cpm.CpmCasConsumer_ErrorTests

org.apache.uima.collection.impl.cpm.CpmCollectionReader_ErrorTest

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.