[UIMA-4049] The curious case of the zombie annotation

• Type: Bug
• Status: Closed
• Priority: Major
• Resolution: Done
• Fix Version/s: 2.7.0SDK
• Component/s: Core Java Framework
• Assignee: Marshall Schor
• Reporter: Richard Eckart de Castilho
• Created: 09/Oct/14 16:13
• Updated: 21/Nov/14 06:47
• Resolved: 20/Nov/14 21:00

Description

When annotations are removed from indexes, sometimes they come back... the following test case shows how an annotation is removed but still present when iterating over the index later.

    @Test
    public void testForZombies() throws Exception
    {
        // No zombie here
        int[] offsets1 = { 0, 4, 5, 11, 12, 21, 22, 25, 26, 29, 30, 35, 36, 40, 41, 50, 51, 60, 61,
                64, 64, 65 };
        testForZombies("Dies flößte Friedrich II. für seine neue Eroberung Besorgnis ein.", offsets1);
        
        // Zombie hiding in here
        int[] offsets2 = { 0, 3, 4, 7, 8, 13, 14, 18, 19, 22, 23, 33, 34, 35 };
        testForZombies("Ich bin Franz III. von Hammerfels !", offsets2);
    }

    public void testForZombies(String aText, int[] aOffsets) throws Exception
    {
        // Init some dictionaries we ues
        Set<String> names = new HashSet<String>();
        names.add("Friedrich");
        names.add("Franz");

        Set<String> suffix = new HashSet<String>();
        suffix.add("II.");
        suffix.add("III.");

        // Set up type system
        TypeSystemDescription tsd = new TypeSystemDescription_impl();
        tsd.addType("Token", "", CAS.TYPE_NAME_ANNOTATION);
        
        // Create CAS
        CAS jcas = CasCreationUtils.createCas(tsd, null, null);
        jcas.setDocumentText(aText);
        
        Type tokenType = jcas.getTypeSystem().getType("Token");
        Feature beginFeature = tokenType.getFeatureByBaseName("begin");
        
        // Create tokens in CAS
        for (int i = 0; i < aOffsets.length; i += 2) {
            jcas.addFsToIndexes(jcas.createAnnotation(tokenType, aOffsets[i], aOffsets[i+1]));
        }
        
        // List the tokens in the CAS
        for (AnnotationFS token : jcas.getAnnotationIndex(tokenType)) {
            System.out.printf("Starting with %s%n", token.getCoveredText());
        }

        // Merge some tokens, in particular "Franz" "III." -> "Franz III." and "Friedrich" "II."
        // into "Friedrich II."
        AnnotationFS previous = null;
        List<AnnotationFS> toDelete = new ArrayList<>();
        for (AnnotationFS token : jcas.getAnnotationIndex(tokenType)) {
            if (previous != null && names.contains(previous.getCoveredText())
                    && suffix.contains(token.getCoveredText())) {
                token.setIntValue(beginFeature, previous.getBegin());
                toDelete.add(previous);
            }
            previous = token;
        }

        // Remove the no longer necessary tokens ("Friedrich" and "Franz"), since we expanded the
        // following tokens "III." and "II." to include their text
        Set<String> removedWords = new HashSet<String>();
        for (AnnotationFS token : toDelete) {
            System.out.printf("Removing %s%n", token.getCoveredText());
            removedWords.add(token.getCoveredText());
            jcas.removeFsFromIndexes(token);
        }

        // Check if the tokens that we wanted to remove are really gone
        for (AnnotationFS token : jcas.getAnnotationIndex(tokenType)) {
            System.out.printf("Remaining %s%n", token.getCoveredText());
            if (removedWords.contains(token.getCoveredText())) {
               org.junit.Assert.fail("I saw a zombie!!!");
            }
        }
    }

Issue Links

• is related to: UIMA-4059 Checking for incorrect key modifications