Examples with PlainLiteralImpl org.apache.clerezza.commons.rdf.impl.utils.PlainLiteralImpl used on opensource projects

Example 31 with PlainLiteralImpl

use of org.apache.clerezza.commons.rdf.impl.utils.PlainLiteralImpl in project stanbol by apache.

the class Mapping method toResource.

/**
     * Converts the parsed value based on the mapping information to an RDF
     * {@link RDFTerm}. Optionally supports also validation if the parsed
     * value is valid for the {@link Mapping#ontType ontology type} specified by
     * the parsed mapping.
     * @param value the value
     * @param mapping the mapping
     * @param validate 
     * @return the {@link RDFTerm} or <code>null</code> if the parsed value is
     * <code>null</code> or {@link String#isEmpty() empty}.
     * @throws IllegalArgumentException if the parsed {@link Mapping} is 
     * <code>null</code>
     */
protected RDFTerm toResource(String value, boolean validate) {
    //used for date validation
    Metadata dummy = null;
    if (value == null || value.isEmpty()) {
        //ignore null and empty values
        return null;
    }
    RDFTerm object;
    if (ontType == null) {
        object = new PlainLiteralImpl(value);
    } else if (ontType == RDFS.Resource) {
        try {
            if (validate) {
                new URI(value);
            }
            object = new IRI(value);
        } catch (URISyntaxException e) {
            log.warn("Unable to create Reference for value {} (not a valid URI)" + " -> create a literal instead", value);
            object = new PlainLiteralImpl(value);
        }
    } else {
        //typed literal
        Class<?> clazz = Mapping.ONT_TYPE_MAP.get(ontType);
        if (clazz.equals(Date.class)) {
            //parseDate(..) method
            if (dummy == null) {
                dummy = new Metadata();
            }
            //any Property with the Date type could be used here
            dummy.add(DATE.getName(), value);
            //access parseDate(..)
            Date date = dummy.getDate(DublinCore.DATE);
            if (date != null) {
                //now use the Clerezza Literal factory
                object = lf.createTypedLiteral(date);
            } else {
                //fall back to xsd:string
                object = new TypedLiteralImpl(value, XSD.string);
            }
        } else {
            object = new TypedLiteralImpl(value, ontType);
        }
        if (validate && clazz != null && !clazz.equals(Date.class)) {
            //we need not to validate dates
            try {
                lf.createObject(clazz, (Literal) object);
            } catch (NoConvertorException e) {
                log.info("Unable to validate typed literals of type {} because" + "there is no converter for Class {} registered with Clerezza", ontType, clazz);
            } catch (InvalidLiteralTypeException e) {
                log.info("The value '{}' is not valid for dataType {}!" + "create literal with type 'xsd:string' instead", value, ontType);
                object = new TypedLiteralImpl(value, XSD.string);
            }
        }
    //else no validation needed
    }
    if (converter != null) {
        object = converter.convert(object);
    }
    return object;
}

Example 32 with PlainLiteralImpl

use of org.apache.clerezza.commons.rdf.impl.utils.PlainLiteralImpl in project stanbol by apache.

the class RestfulLangidentEngine method computeEnhancements.

/**
     * Compute enhancements for supplied ContentItem. The results of the process
     * are expected to be stored in the metadata of the content item.
     * <p/>
     * The client (usually an {@link org.apache.stanbol.enhancer.servicesapi.EnhancementJobManager}) should take care of
     * persistent storage of the enhanced {@link org.apache.stanbol.enhancer.servicesapi.ContentItem}.
     * <p/>
     * This method creates a new POSContentPart using {@link org.apache.stanbol.enhancer.engines.pos.api.POSTaggerHelper#createContentPart} from a text/plain part and
     * stores it as a new part in the content item. The metadata is not changed.
     *
     * @throws org.apache.stanbol.enhancer.servicesapi.EngineException
     *          if the underlying process failed to work as
     *          expected
     */
@Override
public void computeEnhancements(final ContentItem ci) throws EngineException {
    //get the plain text Blob
    Map.Entry<IRI, Blob> textBlob = getPlainText(this, ci, false);
    Blob blob = textBlob.getValue();
    //send the text to the server
    final HttpPost request = new HttpPost(serviceUrl);
    request.setEntity(new InputStreamEntity(blob.getStream(), blob.getContentLength(), ContentType.create(blob.getMimeType(), blob.getParameter().get("charset"))));
    //execute the request
    List<LangSuggestion> detected;
    try {
        detected = AccessController.doPrivileged(new PrivilegedExceptionAction<List<LangSuggestion>>() {

            public List<LangSuggestion> run() throws ClientProtocolException, IOException {
                return httpClient.execute(request, new LangIdentResponseHandler(ci, objectMapper));
            }
        });
    } catch (PrivilegedActionException pae) {
        Exception e = pae.getException();
        if (e instanceof ClientProtocolException) {
            throw new EngineException(this, ci, "Exception while executing Request " + "on RESTful Language Identification Service at " + serviceUrl, e);
        } else if (e instanceof IOException) {
            throw new EngineException(this, ci, "Exception while executing Request " + "on RESTful Language Identification Service at " + serviceUrl, e);
        } else {
            throw RuntimeException.class.cast(e);
        }
    }
    Graph metadata = ci.getMetadata();
    log.debug("Detected Languages for ContentItem {} and Blob {}");
    ci.getLock().writeLock().lock();
    try {
        //write TextAnnotations for the detected languages
        for (LangSuggestion suggestion : detected) {
            // add a hypothesis
            log.debug(" > {}@{}", suggestion.getLanguage(), suggestion.hasProbability() ? suggestion.getProbability() : "-,--");
            IRI textEnhancement = EnhancementEngineHelper.createTextEnhancement(ci, this);
            metadata.add(new TripleImpl(textEnhancement, DC_LANGUAGE, new PlainLiteralImpl(suggestion.getLanguage())));
            metadata.add(new TripleImpl(textEnhancement, DC_TYPE, DCTERMS_LINGUISTIC_SYSTEM));
            if (suggestion.hasProbability()) {
                metadata.add(new TripleImpl(textEnhancement, ENHANCER_CONFIDENCE, literalFactory.createTypedLiteral(suggestion.getProbability())));
            }
        }
    } finally {
        ci.getLock().writeLock().unlock();
    }
}

Example 33 with PlainLiteralImpl

use of org.apache.clerezza.commons.rdf.impl.utils.PlainLiteralImpl 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 34 with PlainLiteralImpl

use of org.apache.clerezza.commons.rdf.impl.utils.PlainLiteralImpl 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 35 with PlainLiteralImpl

use of org.apache.clerezza.commons.rdf.impl.utils.PlainLiteralImpl in project stanbol by apache.

the class CeliSentimentAnalysisEngine method computeEnhancements.

@Override
public void computeEnhancements(ContentItem ci) throws EngineException {
    Entry<IRI, Blob> contentPart = ContentItemHelper.getBlob(ci, SUPPORTED_MIMTYPES);
    if (contentPart == null) {
        throw new IllegalStateException("No ContentPart with Mimetype '" + TEXT_PLAIN_MIMETYPE + "' found for ContentItem " + ci.getUri() + ": This is also checked in the canEnhance method! -> This " + "indicated an Bug in the implementation of the " + "EnhancementJobManager!");
    }
    String text = "";
    try {
        text = ContentItemHelper.getText(contentPart.getValue());
    } catch (IOException e) {
        throw new InvalidContentException(this, ci, e);
    }
    if (text.trim().length() == 0) {
        log.info("No text contained in ContentPart {" + contentPart.getKey() + "} of ContentItem {" + ci.getUri() + "}");
        return;
    }
    String language = EnhancementEngineHelper.getLanguage(ci);
    if (language == null) {
        throw new IllegalStateException("Unable to extract Language for " + "ContentItem " + ci.getUri() + ": This is also checked in the canEnhance " + "method! -> This indicated an Bug in the implementation of the " + "EnhancementJobManager!");
    }
    //used for the palin literals in TextAnnotations
    Language lang = new Language(language);
    try {
        List<SentimentExpression> lista = this.client.extractSentimentExpressions(text, language);
        LiteralFactory literalFactory = LiteralFactory.getInstance();
        Graph g = ci.getMetadata();
        for (SentimentExpression se : lista) {
            try {
                IRI textAnnotation = EnhancementEngineHelper.createTextEnhancement(ci, this);
                //add selected text as PlainLiteral in the language extracted from the text
                g.add(new TripleImpl(textAnnotation, ENHANCER_SELECTED_TEXT, new PlainLiteralImpl(se.getSnippetStr(), lang)));
                g.add(new TripleImpl(textAnnotation, DC_TYPE, CeliConstants.SENTIMENT_EXPRESSION));
                if (se.getStartSnippet() != null && se.getEndSnippet() != null) {
                    g.add(new TripleImpl(textAnnotation, ENHANCER_START, literalFactory.createTypedLiteral(se.getStartSnippet().intValue())));
                    g.add(new TripleImpl(textAnnotation, ENHANCER_END, literalFactory.createTypedLiteral(se.getEndSnippet().intValue())));
                    g.add(new TripleImpl(textAnnotation, ENHANCER_SELECTION_CONTEXT, new PlainLiteralImpl(getSelectionContext(text, se.getSnippetStr(), se.getStartSnippet()), lang)));
                    g.add(new TripleImpl(textAnnotation, CeliConstants.HAS_SENTIMENT_EXPRESSION_POLARITY, literalFactory.createTypedLiteral(se.getSentimentPolarityAsDoubleValue())));
                }
            } catch (NoConvertorException e) {
                log.error(e.getMessage(), e);
            }
        }
    } catch (IOException e) {
        throw new EngineException("Error while calling the CELI Sentiment Analysis service (configured URL: " + serviceURL + ")!", e);
    } catch (SOAPException e) {
        throw new EngineException("Error wile encoding/decoding the request/response to the CELI Sentiment Analysis service!", e);
    }
}