Examples with LiteralFactory org.apache.clerezza.rdf.core.LiteralFactory used on opensource projects

Example 16 with LiteralFactory

use of org.apache.clerezza.rdf.core.LiteralFactory in project stanbol by apache.

the class MetaGraphManager method updateCreateEntry.

public void updateCreateEntry(OWLOntologyID publicKey) {
    if (publicKey == null || publicKey.isAnonymous())
        throw new IllegalArgumentException("An anonymous ontology cannot be mapped. A non-anonymous ontology ID must be forged in these cases.");
    Triple tType, tHasOiri = null, tHasViri = null;
    org.semanticweb.owlapi.model.IRI ontologyIRI = publicKey.getOntologyIRI(), versionIri = publicKey.getVersionIRI();
    IRI entry = buildResource(publicKey);
    tType = new TripleImpl(entry, RDF.type, ENTRY_URIREF);
    LiteralFactory lf = LiteralFactory.getInstance();
    tHasOiri = new TripleImpl(entry, HAS_ONTOLOGY_IRI_URIREF, lf.createTypedLiteral(new IRI(ontologyIRI.toString())));
    if (versionIri != null)
        tHasViri = new TripleImpl(entry, HAS_VERSION_IRI_URIREF, lf.createTypedLiteral(new IRI(versionIri.toString())));
    synchronized (graph) {
        graph.add(tType);
        if (tHasViri != null)
            graph.add(tHasViri);
        graph.add(tHasOiri);
    }
}

Example 17 with LiteralFactory

use of org.apache.clerezza.rdf.core.LiteralFactory in project stanbol by apache.

the class RestfulNlpAnalysisEngine 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 {
    // validate that the service is active
    checkRESTfulNlpAnalysisService();
    // get/create the AnalysedText
    final AnalysedText at = NlpEngineHelper.initAnalysedText(this, analysedTextFactory, ci);
    final Blob blob = at.getBlob();
    // send the text to the server
    final String language = getLanguage(this, ci, true);
    final HttpPost request = new HttpPost(analysisServiceUrl);
    request.addHeader(HttpHeaders.CONTENT_LANGUAGE, language);
    request.setEntity(new InputStreamEntity(blob.getStream(), blob.getContentLength(), ContentType.create(blob.getMimeType(), blob.getParameter().get("charset"))));
    // execute the request
    try {
        AccessController.doPrivileged(new PrivilegedExceptionAction<AnalysedText>() {

            public AnalysedText run() throws ClientProtocolException, IOException {
                return httpClient.execute(request, new AnalysisResponseHandler(at));
            }
        });
    } catch (PrivilegedActionException pae) {
        Exception e = pae.getException();
        if (e instanceof ClientProtocolException) {
            // force re-initialisation upon error
            setRESTfulNlpAnalysisServiceUnavailable();
            throw new EngineException(this, ci, "Exception while executing Request " + "on RESTful NLP Analysis Service at " + analysisServiceUrl, e);
        } else if (e instanceof IOException) {
            // force re-initialisation upon error
            setRESTfulNlpAnalysisServiceUnavailable();
            throw new EngineException(this, ci, "Exception while executing Request " + "on RESTful NLP Analysis Service at " + analysisServiceUrl, e);
        } else {
            throw RuntimeException.class.cast(e);
        }
    }
    if (writeTextAnnotations) {
        // if enabled fise:TextAnnotations are created for Named Entities and Sentiments
        double positiveSent = 0.0;
        int positiveCount = 0;
        double negativeSent = 0.0;
        int negativeCount = 0;
        int sentimentCount = 0;
        Iterator<Span> spans = at.getEnclosed(EnumSet.of(SpanTypeEnum.Sentence, SpanTypeEnum.Chunk));
        Sentence context = null;
        Graph metadata = ci.getMetadata();
        Language lang = new Language(language);
        LiteralFactory lf = LiteralFactory.getInstance();
        ci.getLock().writeLock().lock();
        try {
            // write TextAnnotations for Named Entities
            while (spans.hasNext()) {
                Span span = spans.next();
                switch(span.getType()) {
                    case Sentence:
                        context = (Sentence) span;
                    // FALLThrough intended!!
                    default:
                        Value<NerTag> nerAnno = span.getAnnotation(NER_ANNOTATION);
                        if (nerAnno != null) {
                            IRI ta = EnhancementEngineHelper.createTextEnhancement(ci, this);
                            // add span related data
                            metadata.add(new TripleImpl(ta, ENHANCER_SELECTED_TEXT, new PlainLiteralImpl(span.getSpan(), lang)));
                            metadata.add(new TripleImpl(ta, ENHANCER_START, lf.createTypedLiteral(span.getStart())));
                            metadata.add(new TripleImpl(ta, ENHANCER_END, lf.createTypedLiteral(span.getEnd())));
                            metadata.add(new TripleImpl(ta, ENHANCER_SELECTION_CONTEXT, new PlainLiteralImpl(context == null ? getDefaultSelectionContext(at.getSpan(), span.getSpan(), span.getStart()) : context.getSpan(), lang)));
                            // add the NER type
                            if (nerAnno.value().getType() != null) {
                                metadata.add(new TripleImpl(ta, DC_TYPE, nerAnno.value().getType()));
                            }
                            if (nerAnno.probability() >= 0) {
                                metadata.add(new TripleImpl(ta, ENHANCER_CONFIDENCE, lf.createTypedLiteral(nerAnno.probability())));
                            }
                        }
                        Value<Double> sentimentAnnotation = span.getAnnotation(SENTIMENT_ANNOTATION);
                        if (sentimentAnnotation != null) {
                            // this span has a sentiment assigned
                            Double sentiment = sentimentAnnotation.value();
                            // Create a fise:TextAnnotation for the sentiment
                            IRI ta = EnhancementEngineHelper.createTextEnhancement(ci, this);
                            metadata.add(new TripleImpl(ta, ENHANCER_START, lf.createTypedLiteral(span.getStart())));
                            metadata.add(new TripleImpl(ta, ENHANCER_END, lf.createTypedLiteral(span.getEnd())));
                            metadata.add(new TripleImpl(ta, SENTIMENT_PROPERTY, lf.createTypedLiteral(sentiment)));
                            // add the generic dc:type used for all Sentiment annotation
                            metadata.add(new TripleImpl(ta, DC_TYPE, SENTIMENT_TYPE));
                            // determine the specific dc:type for the sentiment annotation
                            IRI ssoType = NIFHelper.SPAN_TYPE_TO_SSO_TYPE.get(span.getType());
                            if (ssoType != null) {
                                metadata.add(new TripleImpl(ta, DC_TYPE, ssoType));
                            }
                            // keep statistics for the overall sentiment for the Document
                            sentimentCount++;
                            if (sentiment > 0) {
                                positiveSent += sentiment;
                                positiveCount++;
                            } else if (sentiment < 0) {
                                negativeSent += sentiment;
                                negativeCount++;
                            }
                        }
                        break;
                }
            }
            // Add the annotation for the overall sentiment of the document
            if (sentimentCount > 0) {
                IRI ta = EnhancementEngineHelper.createTextEnhancement(ci, this);
                // calculate the average sentiment for a document
                // TODO: Think on a better way to calculate a general sentiment value for a document.
                metadata.add(new TripleImpl(ta, SENTIMENT_PROPERTY, lf.createTypedLiteral((positiveSent + negativeSent) / sentimentCount)));
                if (positiveCount > 0) {
                    // average positive sentiment calculation for the document
                    metadata.add(new TripleImpl(ta, POSITIVE_SENTIMENT_PROPERTY, lf.createTypedLiteral(positiveSent / positiveCount)));
                }
                if (negativeCount > 0) {
                    // average negative sentiment calculation for the document
                    metadata.add(new TripleImpl(ta, NEGATIVE_SENTIMENT_PROPERTY, lf.createTypedLiteral(negativeSent / negativeCount)));
                }
                metadata.add(new TripleImpl(ta, DC_TYPE, SENTIMENT_TYPE));
                metadata.add(new TripleImpl(ta, DC_TYPE, DOCUMENT_SENTIMENT_TYPE));
            }
        // no sentiment annotation present ... nothing to do
        } finally {
            ci.getLock().writeLock().unlock();
        }
    }
// else do not write fise:TextAnnotations
}

Example 18 with LiteralFactory

use of org.apache.clerezza.rdf.core.LiteralFactory in project stanbol by apache.

the class OntologyMappings method addMediaResourceOntologyMappings.

public static void addMediaResourceOntologyMappings(OntologyMappings mappings) {
    mappings.addMappings(new PropertyMapping(ma + "hasContributor", DublinCore.CONTRIBUTOR.getName(), XMPDM.ARTIST.getName(), XMPDM.COMPOSER.getName()));
    mappings.addMapping(new ResourceMapping(ma + "hasLocation", new TypeMapping(ma + "Location"), new PropertyMapping(ma + "locationName", DublinCore.COVERAGE.getName())));
    mappings.addMappings(new PropertyMapping(ma + "hasCreator", DublinCore.CREATOR.getName(), MSOffice.AUTHOR, "initial-creator"));
    mappings.addMappings(new PropertyMapping(ma + "description", DublinCore.DESCRIPTION.getName()));
    mappings.addMappings(new PropertyMapping(ma + "hasFormat", DublinCore.FORMAT.getName(), HttpHeaders.CONTENT_TYPE));
    /*
         * Excerpt of the MA recommendation:
         *   The identifier of a media resource is represented in RDF by the URI 
         *   of the node representing that media resource. If a resource is 
         *   identified by several URI, owl:sameAs should be used.
         */
    mappings.addMappings(new PropertyMapping(OWL.sameAs, RDFS.Resource, DublinCore.IDENTIFIER.getName()));
    mappings.addMappings(new PropertyMapping(ma + "hasLanguage", DublinCore.LANGUAGE.getName(), HttpHeaders.CONTENT_LANGUAGE));
    mappings.addMappings(new PropertyMapping(ma + "editDate", XSD.dateTime, DublinCore.MODIFIED.getName(), MSOffice.LAST_SAVED.getName()));
    mappings.addMappings(new PropertyMapping(ma + "hasPublisher", DublinCore.PUBLISHER.getName()));
    mappings.addMappings(new PropertyMapping(ma + "hasRelatedResource", DublinCore.RELATION.getName()));
    mappings.addMappings(new PropertyMapping(ma + "copyright", RDFS.Resource, // DC:rights and cc:license
    DublinCore.RIGHTS.getName(), CreativeCommons.LICENSE_LOCATION, CreativeCommons.LICENSE_URL, XMPDM.COPYRIGHT.getName()));
    mappings.addMappings(new PropertyMapping(ma + "isMemberOf", DublinCore.SOURCE.getName()));
    mappings.addMappings(new PropertyMapping(ma + "hasKeyword", DublinCore.SUBJECT.getName(), MSOffice.KEYWORDS));
    mappings.addMappings(new PropertyMapping(ma + "title", DublinCore.TITLE.getName(), XMPDM.SCENE.getName(), XMPDM.TAPE_NAME.getName(), XMPDM.SHOT_NAME.getName()));
    mappings.addMapping(new PropertyMapping(ma + "alternativeTitle", XMPDM.ALT_TAPE_NAME.getName()));
    mappings.addMapping(new PropertyMapping(ma + "mainOriginalTitle", XMPDM.ALBUM.getName()));
    mappings.addMappings(new PropertyMapping(ma + "hasGenre", DublinCore.TYPE.getName(), XMPDM.GENRE.getName()));
    mappings.addMappings(new PropertyMapping(ma + "creationDate", XSD.dateTime, DublinCore.DATE.getName(), MSOffice.CREATION_DATE.getName(), "created"));
    mappings.addMapping(new PropertyMapping(ma + "description", DublinCore.DESCRIPTION.getName(), MSOffice.COMMENTS));
    mappings.addMappings(new PropertyMapping(ma + "hasContributor", MSOffice.LAST_AUTHOR, MSOffice.AUTHOR, XMPDM.ENGINEER.getName()));
    // other properties -> Media Ontology
    mappings.addMappings(new PropertyMapping(ma + "hasCreator", "producer", "initial-creator"));
    // EXIF -> Media Ontology
    mappings.addMappings(new PropertyMapping(ma + "frameHeight", XSD.int_, TIFF.IMAGE_LENGTH.getName()));
    mappings.addMappings(new PropertyMapping(ma + "frameWidth", XSD.int_, TIFF.IMAGE_WIDTH.getName()));
    mappings.addMappings(new PropertyMapping(ma + "creationDate", XSD.dateTime, TIFF.ORIGINAL_DATE.getName(), XMPDM.SHOT_DATE.getName()));
    // XMP -> Media Ontology
    // here we need to split up the metadata for the audio and video
    mappings.addMapping(new PropertyMapping(ma + "releaseDate", XSD.dateTime, XMPDM.RELEASE_DATE.getName()));
    mappings.addMapping(new ResourceMapping(ma + "hasTrack", new Mapping[] {/* no required */
    }, new Mapping[] { // optional
    new PropertyMapping(ma + "hasFormat", XSD.string, XMPDM.AUDIO_CHANNEL_TYPE.getName()), new PropertyMapping(ma + "hasCompression", XSD.string, XMPDM.AUDIO_COMPRESSOR.getName()), new PropertyMapping(ma + "editDate", XMPDM.AUDIO_MOD_DATE.getName()), new PropertyMapping(ma + "samplingRate", XSD.int_, XMPDM.AUDIO_SAMPLE_RATE.getName()) }, new Mapping[] { new TypeMapping(ma + "MediaFragment"), new TypeMapping(ma + "Track"), new TypeMapping(ma + "AudioTrack") }));
    mappings.addMapping(new ResourceMapping(ma + "hasTrack", new Mapping[] {/* no required */
    }, new Mapping[] { // optional
    new PropertyMapping(ma + "hasCompression", XSD.string, XMPDM.VIDEO_COMPRESSOR.getName()), new PropertyMapping(ma + "editDate", XMPDM.VIDEO_MOD_DATE.getName()), new PropertyMapping(ma + "frameRate", XSD.double_, XMPDM.VIDEO_FRAME_RATE.getName()) }, new Mapping[] { // additioanl
    new TypeMapping(ma + "MediaFragment"), new TypeMapping(ma + "Track"), new TypeMapping(ma + "VideoTrack"), new PropertyMapping(ma + "frameHeight", XSD.int_, TIFF.IMAGE_LENGTH.getName()), new PropertyMapping(ma + "frameWidth", XSD.int_, TIFF.IMAGE_WIDTH.getName()) }));
    mappings.addMapping(new PropertyMapping(ma + "numberOfTracks", XSD.int_, XMPDM.TRACK_NUMBER.getName()));
    mappings.addMapping(new PropertyMapping(ma + "averageBitRate", XSD.double_, new // we need to convert from MByte/min to kByte/sec
    Mapping.Converter() {

        @Override
        public RDFTerm convert(RDFTerm value) {
            if (value instanceof Literal && XSD.double_.equals(((Literal) value).getDataType())) {
                LiteralFactory lf = LiteralFactory.getInstance();
                double mm = lf.createObject(Double.class, (Literal) value);
                return lf.createTypedLiteral(Double.valueOf(mm * 1024 / 60));
            } else {
                // do not convert
                return value;
            }
        }
    }, XMPDM.FILE_DATA_RATE.getName()));
    // GEO -> Media RDFTerm Ontology
    mappings.addMapping(new ResourceMapping(ma + "hasLocation", new Mapping[] { // required
    new PropertyMapping(ma + "locationLatitude", XSD.double_, Geographic.LATITUDE.getName()), new PropertyMapping(ma + "locationLongitude", XSD.double_, Geographic.LONGITUDE.getName()) }, new Mapping[] { // optional
    new PropertyMapping(ma + "locationAltitude", XSD.double_, Geographic.ALTITUDE.getName()) }, new Mapping[] { // additional
    new TypeMapping(ma + "Location") }));
}

Example 19 with LiteralFactory

use of org.apache.clerezza.rdf.core.LiteralFactory in project stanbol by apache.

the class NamedEntityTaggingEngine method computeEnhancements.

public void computeEnhancements(ContentItem ci) throws EngineException {
    final Site site;
    if (referencedSiteID != null) {
        // lookup the referenced site
        site = siteManager.getSite(referencedSiteID);
        // ensure that it is present
        if (site == null) {
            String msg = String.format("Unable to enhance %s because Referenced Site %s is currently not active!", ci.getUri().getUnicodeString(), referencedSiteID);
            log.warn(msg);
            // throw new EngineException(msg);
            return;
        }
        // and that it supports offline mode if required
        if (isOfflineMode() && !site.supportsLocalMode()) {
            log.warn("Unable to enhance ci {} because OfflineMode is not supported by ReferencedSite {}.", ci.getUri().getUnicodeString(), site.getId());
            return;
        }
    } else {
        // null indicates to use the Entityhub to lookup Entities
        site = null;
    }
    Graph graph = ci.getMetadata();
    LiteralFactory literalFactory = LiteralFactory.getInstance();
    // Retrieve the existing text annotations (requires read lock)
    Map<NamedEntity, List<IRI>> textAnnotations = new HashMap<NamedEntity, List<IRI>>();
    // the language extracted for the parsed content or NULL if not
    // available
    String contentLangauge;
    ci.getLock().readLock().lock();
    try {
        contentLangauge = EnhancementEngineHelper.getLanguage(ci);
        for (Iterator<Triple> it = graph.filter(null, RDF_TYPE, TechnicalClasses.ENHANCER_TEXTANNOTATION); it.hasNext(); ) {
            IRI uri = (IRI) it.next().getSubject();
            if (graph.filter(uri, Properties.DC_RELATION, null).hasNext()) {
                // skip
                continue;
            }
            NamedEntity namedEntity = NamedEntity.createFromTextAnnotation(graph, uri);
            if (namedEntity != null) {
                // This is a first occurrence, collect any subsumed
                // annotations
                List<IRI> subsumed = new ArrayList<IRI>();
                for (Iterator<Triple> it2 = graph.filter(null, Properties.DC_RELATION, uri); it2.hasNext(); ) {
                    subsumed.add((IRI) it2.next().getSubject());
                }
                textAnnotations.put(namedEntity, subsumed);
            }
        }
    } finally {
        ci.getLock().readLock().unlock();
    }
    // search the suggestions
    Map<NamedEntity, List<Suggestion>> suggestions = new HashMap<NamedEntity, List<Suggestion>>(textAnnotations.size());
    for (Entry<NamedEntity, List<IRI>> entry : textAnnotations.entrySet()) {
        try {
            List<Suggestion> entitySuggestions = computeEntityRecommentations(site, entry.getKey(), entry.getValue(), contentLangauge);
            if (entitySuggestions != null && !entitySuggestions.isEmpty()) {
                suggestions.put(entry.getKey(), entitySuggestions);
            }
        } catch (EntityhubException e) {
            throw new EngineException(this, ci, e);
        }
    }
    // now write the results (requires write lock)
    ci.getLock().writeLock().lock();
    try {
        RdfValueFactory factory = RdfValueFactory.getInstance();
        Map<String, Representation> entityData = new HashMap<String, Representation>();
        for (Entry<NamedEntity, List<Suggestion>> entitySuggestions : suggestions.entrySet()) {
            List<IRI> subsumed = textAnnotations.get(entitySuggestions.getKey());
            List<BlankNodeOrIRI> annotationsToRelate = new ArrayList<BlankNodeOrIRI>(subsumed);
            annotationsToRelate.add(entitySuggestions.getKey().getEntity());
            for (Suggestion suggestion : entitySuggestions.getValue()) {
                log.debug("Add Suggestion {} for {}", suggestion.getEntity().getId(), entitySuggestions.getKey());
                EnhancementRDFUtils.writeEntityAnnotation(this, literalFactory, graph, ci.getUri(), annotationsToRelate, suggestion, nameField, // header)?!
                contentLangauge == null ? DEFAULT_LANGUAGE : contentLangauge);
                if (dereferenceEntities) {
                    entityData.put(suggestion.getEntity().getId(), suggestion.getEntity().getRepresentation());
                }
            }
        }
        // Representations to add! If false entityData will be empty
        for (Representation rep : entityData.values()) {
            graph.addAll(factory.toRdfRepresentation(rep).getRdfGraph());
        }
    } finally {
        ci.getLock().writeLock().unlock();
    }
}

Example 20 with LiteralFactory

use of org.apache.clerezza.rdf.core.LiteralFactory in project stanbol by apache.

the class DBPSpotlightDisambiguateEnhancementTest method initTest.

@Before
public void initTest() throws IOException {
    // create the contentItem for testing
    ci = ciFactory.createContentItem(new StringSource(TEST_TEXT));
    assertNotNull(ci);
    textContentPart = ContentItemHelper.getBlob(ci, Collections.singleton("text/plain"));
    assertNotNull(textContentPart);
    // add the language of the text
    ci.getMetadata().add(new TripleImpl(ci.getUri(), Properties.DC_LANGUAGE, new PlainLiteralImpl("en")));
    assertEquals("en", EnhancementEngineHelper.getLanguage(ci));
    LiteralFactory lf = LiteralFactory.getInstance();
    // we need also to create a fise:TextAnnotation to test disambiguation
    String selected = "Angela Merkel";
    Language en = new Language("en");
    IRI textAnnotation = EnhancementEngineHelper.createTextEnhancement(ci, new DBPSpotlightSpotEnhancementEngine());
    Graph model = ci.getMetadata();
    model.add(new TripleImpl(textAnnotation, Properties.ENHANCER_SELECTED_TEXT, new PlainLiteralImpl(selected, en)));
    model.add(new TripleImpl(textAnnotation, Properties.ENHANCER_SELECTION_CONTEXT, new PlainLiteralImpl(TEST_TEXT, en)));
    model.add(new TripleImpl(textAnnotation, Properties.ENHANCER_START, lf.createTypedLiteral(TEST_TEXT.indexOf(selected))));
    model.add(new TripleImpl(textAnnotation, Properties.ENHANCER_END, lf.createTypedLiteral(TEST_TEXT.indexOf(selected) + selected.length())));
    model.add(new TripleImpl(textAnnotation, Properties.DC_TYPE, OntologicalClasses.DBPEDIA_PERSON));
    // validate that the created TextAnnotation is valid (test the test ...)
    EnhancementStructureHelper.validateAllTextAnnotations(model, TEST_TEXT, null);
}