Uploaded image for project: 'UIMA'
  1. UIMA
  2. UIMA-3357

CONTAINS fails when running script as AE in a pipeline with a new CAS

    Details

    • Type: Bug
    • Status: Closed
    • Priority: Minor
    • Resolution: Fixed
    • Affects Version/s: 2.0.1ruta, 2.1.0ruta
    • Fix Version/s: 2.2.0ruta
    • Component/s: Ruta, uimaFIT
    • Labels:
      None

      Description

      When running my Ruta script as an analysis engine in a pipeline, it does not work correctly when creating a new CAS and processing the pipeline a second time with the new CAS.
      While reusing the old cas with "cas.reset()" is working, creating a new CAS results in failing rules including "CONTAINS" in the ruta script.

      The ruta script used in the example:

      mystic.ruta
      PACKAGE de.tudarmstadt.algo.vpino.ruta;
      DECLARE test;
      Document{CONTAINS(CW)->MARK(test)};
      

      The following Java class can reproduce the error. It creates four xmi files. The last xmi file is missing the annotations created with rules including "CONTAINS".

      MysticPipe.java
      package org.uimafit.pipeline;
      
      import java.io.File;
      import java.io.FileOutputStream;
      import java.io.IOException;
      import java.io.OutputStream;
      import java.util.ArrayList;
      import java.util.List;
      
      import org.apache.uima.UIMAFramework;
      import org.apache.uima.analysis_engine.AnalysisEngine;
      import org.apache.uima.analysis_engine.AnalysisEngineDescription;
      import org.apache.uima.analysis_engine.AnalysisEngineProcessException;
      import org.apache.uima.cas.CAS;
      import org.apache.uima.cas.impl.XmiCasSerializer;
      import org.apache.uima.fit.factory.AnalysisEngineFactory;
      import org.apache.uima.fit.pipeline.SimplePipeline;
      import org.apache.uima.resource.ResourceInitializationException;
      import org.apache.uima.resource.metadata.ResourceMetaData;
      import org.apache.uima.util.CasCreationUtils;
      import org.apache.uima.util.InvalidXMLException;
      import org.apache.uima.util.XMLInputSource;
      import org.apache.uima.util.XMLSerializer;
      import org.xml.sax.SAXException;
      
      public class MysticPipe {
      
      	public static void main(String[] args) throws Exception {
      		working("This is a test.", initPipeline());
      		failing("This is a test.", initPipeline());
      	}
      
      	private static AnalysisEngine initPipeline() throws ResourceInitializationException, IOException, InvalidXMLException {
      		File specFile = new File("./descriptor/de/tudarmstadt/algo/vpino/ruta/mysticEngine.xml");
      		XMLInputSource in = new XMLInputSource(specFile);
      		AnalysisEngineDescription ruta = (AnalysisEngineDescription) UIMAFramework.getXMLParser().parseResourceSpecifier(in);
      		return AnalysisEngineFactory.createEngine(ruta);
      	}
      
      	private static void working(String input, AnalysisEngine theEngine) throws ResourceInitializationException, AnalysisEngineProcessException, IOException,
      	        SAXException {
      		final List<ResourceMetaData> metaData = new ArrayList<ResourceMetaData>();
      		metaData.add(theEngine.getMetaData());
      		final CAS cas = CasCreationUtils.createCas(metaData);
      		System.out.println("create a new cas...");
      		cas.setDocumentLanguage("de");
      		cas.setDocumentText(input);
      		SimplePipeline.runPipeline(cas, theEngine);
      		writeXmiFile(cas, "works_test1");//CHECK
      		//THE DIFFERENCE
      		cas.reset();
      		//END DIFFERENCE
      		System.out.println("create a new cas...");
      		cas.setDocumentLanguage("de");
      		cas.setDocumentText(input);
      		SimplePipeline.runPipeline(cas, theEngine);
      		writeXmiFile(cas, "works_test2");//CHECK
      	}
      
      	private static void failing(String input, AnalysisEngine theEngine) throws ResourceInitializationException, AnalysisEngineProcessException, IOException,
      	        SAXException {
      		final List<ResourceMetaData> metaData = new ArrayList<ResourceMetaData>();
      		metaData.add(theEngine.getMetaData());
      		final CAS cas = CasCreationUtils.createCas(metaData);
      		System.out.println("create a new cas...");
      		cas.setDocumentLanguage("de");
      		cas.setDocumentText(input);
      		SimplePipeline.runPipeline(cas, theEngine);
      		writeXmiFile(cas, "works_test3"); // CHECK
      		//THE DIFFERENCE
      		final CAS cas2 = CasCreationUtils.createCas(metaData);
      		//END DIFFERENCE
      		System.out.println("create a new cas...");
      		cas2.setDocumentLanguage("de");
      		cas2.setDocumentText(input);
      		SimplePipeline.runPipeline(cas2, theEngine);
      		writeXmiFile(cas2, "fail_test4"); //FAIL
      		return;
      	}
      	
      	public static void writeXmiFile(CAS aCas, String Fname) throws IOException, SAXException {
      		File outFile = new File("output", Fname + ".xmi");
      		OutputStream out = null;
      
      		try {
      			// out = new StringOutputStream();
      			out = new FileOutputStream(outFile);
      			XmiCasSerializer ser = new XmiCasSerializer(aCas.getTypeSystem());
      			XMLSerializer xmlSer = new XMLSerializer(out, false);
      			ser.serialize(aCas, xmlSer.getContentHandler());
      		} finally {
      			if (out != null) {
      				out.close();
      			}
      		}
      	}
      }
      

        Attachments

          Activity

            People

            • Assignee:
              pkluegl Peter Klügl
              Reporter:
              maeurerdaniel Daniel Maeurer
            • Votes:
              0 Vote for this issue
              Watchers:
              2 Start watching this issue

              Dates

              • Created:
                Updated:
                Resolved: