Examples with ContentItem org.apache.stanbol.enhancer.servicesapi.ContentItem used on opensource projects

Example 31 with ContentItem

use of org.apache.stanbol.enhancer.servicesapi.ContentItem in project stanbol by apache.

the class CeliAnalyzedTextSentimentAnalysisEngineTest method testEngine.

@Test
public void testEngine() throws IOException, EngineException {
    ContentItem ci = ciFactory.createContentItem(new StringSource(text));
    Assert.assertNotNull(ci);
    AnalysedText at = atFactory.createAnalysedText(ci, ci.getBlob());
    Assert.assertNotNull(at);
    ci.getMetadata().add(new TripleImpl(ci.getUri(), DC_LANGUAGE, new PlainLiteralImpl("it")));
    Assert.assertEquals("it", EnhancementEngineHelper.getLanguage(ci));
    Assert.assertEquals("Can not enhance Test ContentItem", EnhancementEngine.ENHANCE_ASYNC, engine.canEnhance(ci));
    //compute the enhancements
    try {
        engine.computeEnhancements(ci);
    } catch (EngineException e) {
        RemoteServiceHelper.checkServiceUnavailable(e);
        //deactivate test
        return;
    }
    //now validate the enhancements
    int sentimentExpressionCnt = 0;
    for (Iterator<Token> tokens = at.getTokens(); tokens.hasNext(); ) {
        Token token = tokens.next();
        log.info("Token: {}", token);
        List<Value<Double>> sentimentExpressionsList = token.getAnnotations(NlpAnnotations.SENTIMENT_ANNOTATION);
        if (sentimentExpressionsList != null && sentimentExpressionsList.size() > 0)
            sentimentExpressionCnt++;
    }
    Assert.assertTrue("2 sentiment expressions should be recognized in: " + text, sentimentExpressionCnt == 2);
}

Example 32 with ContentItem

use of org.apache.stanbol.enhancer.servicesapi.ContentItem in project stanbol by apache.

the class CeliSentimentAnalysisEngineTest method testInput.

private void testInput(String txt, String lang) throws EngineException, IOException {
    ContentItem ci = wrapAsContentItem(txt);
    try {
        // add a simple triple to statically define the language of the test content
        ci.getMetadata().add(new TripleImpl(ci.getUri(), DC_LANGUAGE, new PlainLiteralImpl(lang)));
        sentimentAnalysisEngine.computeEnhancements(ci);
        TestUtils.logEnhancements(ci);
        HashMap<IRI, RDFTerm> expectedValues = new HashMap<IRI, RDFTerm>();
        expectedValues.put(Properties.ENHANCER_EXTRACTED_FROM, ci.getUri());
        expectedValues.put(Properties.DC_CREATOR, LiteralFactory.getInstance().createTypedLiteral(sentimentAnalysisEngine.getClass().getName()));
        expectedValues.put(DC_TYPE, CeliConstants.SENTIMENT_EXPRESSION);
        int textAnnoNum = validateAllTextAnnotations(ci.getMetadata(), txt, expectedValues);
        log.info(textAnnoNum + " TextAnnotations found ...");
        assertTrue("2 sentiment expressions should be recognized in: " + txt, textAnnoNum == 2);
        int entityAnnoNum = EnhancementStructureHelper.validateAllEntityAnnotations(ci.getMetadata(), expectedValues);
        assertTrue("0 entity annotations should be recognized in: " + txt, entityAnnoNum == 0);
    } catch (EngineException e) {
        RemoteServiceHelper.checkServiceUnavailable(e);
    }
}

Example 33 with ContentItem

use of org.apache.stanbol.enhancer.servicesapi.ContentItem in project stanbol by apache.

the class CeliClassificationEnhancementEngineTest method tesetEngine.

@Test
public void tesetEngine() throws Exception {
    ContentItem ci = wrapAsContentItem(TEXT);
    try {
        //add a simple triple to statically define the language of the test
        //content
        ci.getMetadata().add(new TripleImpl(ci.getUri(), DC_LANGUAGE, new PlainLiteralImpl("fr")));
        //unit test should not depend on each other (if possible)
        //CeliLanguageIdentifierEnhancementEngineTest.addEnanchements(ci);
        classificationEngine.computeEnhancements(ci);
        TestUtils.logEnhancements(ci);
        HashMap<IRI, RDFTerm> expectedValues = new HashMap<IRI, RDFTerm>();
        expectedValues.put(Properties.ENHANCER_EXTRACTED_FROM, ci.getUri());
        expectedValues.put(Properties.DC_CREATOR, LiteralFactory.getInstance().createTypedLiteral(classificationEngine.getClass().getName()));
        int textAnnoNum = EnhancementStructureHelper.validateAllTextAnnotations(ci.getMetadata(), TEXT, expectedValues);
        assertEquals("Only a single fise:TextAnnotation is expeted", 1, textAnnoNum);
        int numTopicAnnotations = validateAllTopicAnnotations(ci.getMetadata(), expectedValues);
        assertTrue("No TpocisAnnotations found", numTopicAnnotations > 0);
    } catch (EngineException e) {
        RemoteServiceHelper.checkServiceUnavailable(e);
        return;
    }
}

Example 34 with ContentItem

use of org.apache.stanbol.enhancer.servicesapi.ContentItem in project stanbol by apache.

the class CeliLanguageIdentifierEnhancementEngineTest method tesetEngine.

@Test
public void tesetEngine() throws Exception {
    ContentItem ci = wrapAsContentItem(TEXT);
    try {
        langIdentifier.computeEnhancements(ci);
        TestUtils.logEnhancements(ci);
        HashMap<IRI, RDFTerm> expectedValues = new HashMap<IRI, RDFTerm>();
        expectedValues.put(Properties.ENHANCER_EXTRACTED_FROM, ci.getUri());
        expectedValues.put(Properties.DC_CREATOR, LiteralFactory.getInstance().createTypedLiteral(langIdentifier.getClass().getName()));
        int numTextAnnotations = validateAllTextAnnotations(ci.getMetadata(), TEXT, expectedValues);
        assertEquals("A single TextAnnotation is expected by this Test", 1, numTextAnnotations);
        //even through this tests do not validate service quality but rather
        //the correct integration of the CELI service as EnhancementEngine
        //we expect the "fr" is detected for the parsed text
        assertEquals("The detected language for text '" + TEXT + "' MUST BE 'fr'", "fr", EnhancementEngineHelper.getLanguage(ci));
        int entityAnnoNum = validateAllEntityAnnotations(ci.getMetadata(), expectedValues);
        assertEquals("No EntityAnnotations are expected", 0, entityAnnoNum);
    } catch (EngineException e) {
        RemoteServiceHelper.checkServiceUnavailable(e);
    }
}

Example 35 with ContentItem

use of org.apache.stanbol.enhancer.servicesapi.ContentItem in project stanbol by apache.

the class CeliAnalyzedTextLemmatizerEngineTest method testEngineDe.

@Test
public void testEngineDe() throws IOException, EngineException {
    ContentItem ci = ciFactory.createContentItem(new StringSource(de_text));
    Assert.assertNotNull(ci);
    AnalysedText at = atFactory.createAnalysedText(ci, ci.getBlob());
    Assert.assertNotNull(at);
    ci.getMetadata().add(new TripleImpl(ci.getUri(), DC_LANGUAGE, new PlainLiteralImpl("de")));
    Assert.assertEquals("de", EnhancementEngineHelper.getLanguage(ci));
    //Add some Tokens with POS annotations to test the usage of
    //existing POS annotations by the lemmatizer
    Token verbrachten = at.addToken(de_verbStart, de_verbStart + de_verb.length());
    verbrachten.addAnnotation(POS_ANNOTATION, Value.value(new PosTag("V", LexicalCategory.Verb), de_verbProb));
    Token schonen = at.addToken(de_adjectiveStart, de_adjectiveStart + de_adjective.length());
    schonen.addAnnotation(POS_ANNOTATION, Value.value(new PosTag("ADJ", LexicalCategory.Adjective), de_adjectiveProb));
    Token urlaub = at.addToken(de_nounStart, de_nounStart + de_noun.length());
    urlaub.addAnnotation(POS_ANNOTATION, Value.value(new PosTag("NC", LexicalCategory.Noun), de_nounProb));
    Assert.assertEquals("Can not enhance Test ContentItem", EnhancementEngine.ENHANCE_ASYNC, engine.canEnhance(ci));
    //compute the enhancements
    try {
        engine.computeEnhancements(ci);
    } catch (EngineException e) {
        RemoteServiceHelper.checkServiceUnavailable(e);
        //deactivate test
        return;
    }
    //now validate the enhancements
    boolean foundVerb = false;
    boolean foundAdjective = false;
    boolean foundNoun = false;
    for (Iterator<Token> tokens = at.getTokens(); tokens.hasNext(); ) {
        Token token = tokens.next();
        log.info("Token: {}", token);
        List<Value<MorphoFeatures>> mfs = token.getAnnotations(NlpAnnotations.MORPHO_ANNOTATION);
        if (de_verb.equals(token.getSpan())) {
            foundVerb = !mfs.isEmpty();
            validateMorphFeatureProbability(mfs, LexicalCategory.Verb, de_verbProb);
        } else if (de_adjective.equals(token.getSpan())) {
            foundAdjective = !mfs.isEmpty();
            validateMorphFeatureProbability(mfs, LexicalCategory.Adjective, de_adjectiveProb);
        } else if (de_noun.equals(token.getSpan())) {
            foundNoun = !mfs.isEmpty();
            validateMorphFeatureProbability(mfs, LexicalCategory.Noun, de_nounProb);
        }
        for (Value<MorphoFeatures> mf : mfs) {
            log.info("  - {}", mf);
            Assert.assertNotNull(mf.value().getLemma());
        }
    }
    Assert.assertTrue("No MorphoFeatures found for '" + de_verb + "'!", foundVerb);
    Assert.assertTrue("No MorphoFeatures found for '" + de_adjective + "'!", foundAdjective);
    Assert.assertTrue("No MorphoFeatures found for '" + de_noun + "'!", foundNoun);
}