[UIMA-3141] Binary CAS format 6 + type filtering fails to deserialize document annotation correctly

• Type: Bug
• Status: Open
• Priority: Major
• Resolution: Unresolved
• Affects Version/s: 2.4.1SDK
• Component/s: Core Java Framework
• Assignee: Marshall Schor
• Reporter: Richard Eckart de Castilho
• Created: 02/Aug/13 19:45
• Updated: 03/Jun/21 06:57

Description

When a custom document annotation type is used, the language is not properly restored after deserializing from CAS format 6.

Expected: deserialized CAS has language "latin"

Actual: deserialized CAS has language "x-unspecified"

If the line sourceCas.addFsToIndexes(ma); is commented out, the code works.

import static org.junit.Assert.assertEquals;
import static org.junit.Assert.assertTrue;

import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.InputStream;
import java.io.OutputStream;

import org.apache.commons.io.IOUtils;
import org.apache.uima.cas.CAS;
import org.apache.uima.cas.impl.Serialization;
import org.apache.uima.cas.text.AnnotationFS;
import org.apache.uima.resource.metadata.TypeSystemDescription;
import org.apache.uima.resource.metadata.impl.TypeSystemDescription_impl;
import org.apache.uima.util.CasCreationUtils;
import org.junit.Rule;
import org.junit.Test;
import org.junit.rules.TemporaryFolder;

public class MinimalTest
{
    @Rule
    public TemporaryFolder testFolder = new TemporaryFolder();

    @Test
    public void test()
        throws Exception
    {
        TypeSystemDescription sourceTsd = new TypeSystemDescription_impl();
        sourceTsd.addType("DocMeta", "", CAS.TYPE_NAME_DOCUMENT_ANNOTATION);
        TypeSystemDescription targetTsd = new TypeSystemDescription_impl();

        CAS sourceCas = CasCreationUtils.createCas(sourceTsd, null, null);
        AnnotationFS ma = sourceCas.createAnnotation(sourceCas.getTypeSystem().getType("DocMeta"),
                0, 0);
        sourceCas.addFsToIndexes(ma);
        sourceCas.setDocumentLanguage("latin");
        sourceCas.setDocumentText("test");

        File file = testFolder.newFile("test.bin");

        OutputStream os = new FileOutputStream(file);
        Serialization.serializeWithCompression(sourceCas, os, sourceCas.getTypeSystem());
        IOUtils.closeQuietly(os);

        assertTrue(new File(testFolder.getRoot(), "test.bin").exists());

        CAS targetCas = CasCreationUtils.createCas(targetTsd, null, null);
        InputStream is = new FileInputStream(file);
        Serialization.deserializeCAS(targetCas, is, sourceCas.getTypeSystem(), null);
        IOUtils.closeQuietly(is);

        assertEquals("latin", targetCas.getDocumentLanguage());
        assertEquals("test", targetCas.getDocumentText());
    }
}