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)}.

      int exceptionSequence = 4; // the sequence in which errors are produced
      boolean manuallyAborted = false; // flag, if we shut down the cpm by hand.
      ManageOutputDevice.setAllSystemOutputToNirvana();


      // setup CPM
      CollectionProcessingEngine cpe = setupCpm(documentCount,
            "NullPointerException", exceptionSequence, "hasNext");


      // Create and register a Status Callback Listener
      TestStatusCallbackListener listener = new CollectionReaderStatusCallbackListener(
            cpe);
      cpe.addStatusCallbackListener(listener);


      cpe.process();


      // wait until cpm has finished
      Date d = new Date();
      long time = d.getTime() + 1000 * TIMEOUT;
      while (!listener.isFinished() && !listener.isAborted()) {
         Thread.sleep(5);
         d = new Date();
         // timeout mechanism
         if (time < d.getTime()) {
            manuallyAborted = true;
            cpe.stop();
            // wait until CPM has aborted
            while (!listener.isAborted()) {
               Thread.sleep(5);
            }
         }

View Full Code Here

      // thrown
      ManageOutputDevice.setAllSystemOutputToNirvana();


      try {
         // setup CPM
         CollectionProcessingEngine cpe = setupCpm(documentCount,
               "ResourceInitializationException", exceptionSequence,
               "initialize");


         // Create and register a Status Callback Listener
         listener = new CollectionReaderStatusCallbackListener(cpe);
         cpe.addStatusCallbackListener(listener);


         cpe.process();


         // wait until cpm has finished


         while (!listener.isFinished() && !listener.isAborted()) {
            Thread.sleep(5);

View Full Code Here

      ManageOutputDevice.setAllSystemOutputToNirvana();
      TestStatusCallbackListener listener = null;


      try {
         // setup CPM
         CollectionProcessingEngine cpe = setupCpm(documentCount,
               "NullPointerException", exceptionSequence, "initialize");


         // Create and register a Status Callback Listener
         listener = new CollectionReaderStatusCallbackListener(cpe);
         cpe.addStatusCallbackListener(listener);


         cpe.process();


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

View Full Code Here

      // which the
      // statusinformation are made avaiable


      try {
         // setup CPM
         CollectionProcessingEngine cpe = setupCpm(documentCount,
               "OutOfMemoryError", exceptionSequence, "initialize");


         // Create and register a Status Callback Listener
         listener = new CollectionReaderStatusCallbackListener(cpe);
         cpe.addStatusCallbackListener(listener);


         cpe.process();


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

View Full Code Here

      int documentCount = 20; // number of documents processed
      int exceptionSequence = 3; // the sequence in which errors are produced
      ManageOutputDevice.setAllSystemOutputToNirvana();


      // setup CPM
      CollectionProcessingEngine cpe = setupCpm(documentCount, "IOException",
            exceptionSequence, "getProgress");


      // Create and register a Status Callback Listener
      TestStatusCallbackListener listener = new CollectionReaderStatusCallbackListener(
            cpe);
      cpe.addStatusCallbackListener(listener);


      cpe.process();


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

View Full Code Here

      int documentCount = 20; // number of documents processed
      int exceptionSequence = 3; // the sequence in which errors are produced
      ManageOutputDevice.setAllSystemOutputToNirvana();


      // setup CPM
      CollectionProcessingEngine cpe = setupCpm(documentCount,
            "OutOfMemoryError", exceptionSequence, "getProgress");


      // Create and register a Status Callback Listener
      CollectionReaderStatusCallbackListener listener = new CollectionReaderStatusCallbackListener(
            cpe);
      cpe.addStatusCallbackListener(listener);


      cpe.process();


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

View Full Code Here

  public void testInitSingleThreadCPMMode() throws Exception {
    int documentCount = 10000000;
    int threadCount = 1;


    // setup CPM to process 1 documents
    CollectionProcessingEngine cpe = setupCpm(documentCount, threadCount, false, true);


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


    // run CPM
    cpe.process();


    // wait for initialized call from the CPM
    while (!listener.isInitialized()) {
      Thread.sleep(10);
    }
    System.out.println("SingleThreadCPMMode Initialize was called: " + listener.isInitialized());


    // Let the CPM process some docs, before calling stop
    Thread.sleep(300);


    // stop CPM
    cpe.stop();


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

View Full Code Here

  public void testInitMultiThreadCPMMode() throws Exception {
    int documentCount = 10000000; // hopefully enough that we won't finish before we abort
    int threadCount = 1;


    // setup CPM to process 1 documents
    CollectionProcessingEngine cpe = setupCpm(documentCount, threadCount, false, false);


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


    // run CPM
    cpe.process();


    while (!listener.isInitialized()) {
      Thread.sleep(10);
    }
    System.out.println("MultiThreadCPMMode Initialize was called: " + listener.isInitialized());


    // Let the CPM process some docs, before calling stop
    Thread.sleep(300);


    // stop CPM
    cpe.stop();


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

View Full Code Here

  public void testInitMultiThreadCPM() throws Exception {
    int documentCount = 10000000;
    int threadCount = 3;


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


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


    // run CPM
    cpe.process();


    while (!listener.isInitialized()) {
      Thread.sleep(10);
    }
    System.out.println("testInitMultiThreadCPM()-Initialize was called: "
            + listener.isInitialized());
    // Let the CPM process some docs, before calling stop
    Thread.sleep(300);


    // stop CPM
    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, boolean singleThreaded) throws Exception {
    CpeDescription cpeDesc = null;
    CollectionProcessingEngine cpe = null;


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

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.