use of org.apache.stanbol.enhancer.servicesapi.EngineException 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);
}
use of org.apache.stanbol.enhancer.servicesapi.EngineException in project stanbol by apache.
the class CeliNamedEntityExtractionEnhancementEngineTest 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)));
nerEngine.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(nerEngine.getClass().getName()));
int textAnnoNum = validateAllTextAnnotations(ci.getMetadata(), txt, expectedValues);
log.info(textAnnoNum + " TextAnnotations found ...");
int entityAnnoNum = EnhancementStructureHelper.validateAllEntityAnnotations(ci.getMetadata(), expectedValues);
log.info(entityAnnoNum + " EntityAnnotations found ...");
} catch (EngineException e) {
RemoteServiceHelper.checkServiceUnavailable(e);
}
}
use of org.apache.stanbol.enhancer.servicesapi.EngineException 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);
}
}
use of org.apache.stanbol.enhancer.servicesapi.EngineException in project stanbol by apache.
the class DBPSpotlightDisambiguateEnhancementEngine method doPostRequest.
/**
* Sends a POST request to the DBpediaSpotlight url.
*
* @param text
* a <code>String</code> with the text to be analyzed
* @param xmlTextAnnotations
* @param textAnnotations
* @param contentItemUri the URI of the {@link ContentItem} (only
* used for logging in case of an error)
* @return a <code>String</code> with the server response
* @throws EngineException
* if the request cannot be sent
*/
protected Collection<Annotation> doPostRequest(String text, String xmlTextAnnotations, IRI contentItemUri) throws EngineException {
HttpURLConnection connection = null;
BufferedWriter wr = null;
try {
connection = (HttpURLConnection) spotlightUrl.openConnection();
connection.setRequestMethod("POST");
connection.setRequestProperty("Content-Type", "application/x-www-form-urlencoded");
connection.setRequestProperty("Accept", "text/xml");
// set ConnectionTimeout (if configured)
if (connectionTimeout > 0) {
connection.setConnectTimeout(connectionTimeout * 1000);
connection.setReadTimeout(connectionTimeout * 1000);
}
connection.setUseCaches(false);
connection.setDoInput(true);
connection.setDoOutput(true);
// Send request
wr = new BufferedWriter(new OutputStreamWriter(connection.getOutputStream(), UTF8));
} catch (IOException e) {
IOUtils.closeQuietly(wr);
throw new EngineException("Unable to open connection to " + spotlightUrl, e);
}
try {
wr.write("spotter=SpotXmlParser&");
if (spotlightDisambiguator != null && !spotlightDisambiguator.isEmpty()) {
wr.write("disambiguator=");
wr.write(URLEncoder.encode(spotlightDisambiguator, "UTF-8"));
wr.write('&');
}
if (spotlightTypesRestriction != null && !spotlightTypesRestriction.isEmpty()) {
wr.write("types=");
wr.write(URLEncoder.encode(spotlightTypesRestriction, "UTF-8"));
wr.write('&');
}
if (spotlightSupport != null && !spotlightSupport.isEmpty()) {
wr.write("support=");
wr.write(URLEncoder.encode(spotlightSupport, "UTF-8"));
wr.write('&');
}
if (spotlightConfidence != null && !spotlightConfidence.isEmpty()) {
wr.write("confidence=");
wr.write(URLEncoder.encode(spotlightConfidence, "UTF-8"));
wr.write('&');
}
if (spotlightSparql != null && !spotlightSparql.isEmpty() && spotlightTypesRestriction == null) {
wr.write("sparql=");
wr.write(URLEncoder.encode(spotlightSparql, "UTF-8"));
wr.write('&');
}
wr.write("text=");
wr.write(URLEncoder.encode(xmlTextAnnotations, "UTF-8"));
} catch (UnsupportedEncodingException e) {
throw new IllegalStateException("The platform does not support encoding " + UTF8.name(), e);
} catch (IOException e) {
throw new EngineException("Unable to write 'plain/text' content " + "for ContentItem " + contentItemUri + " to " + spotlightUrl, e);
} finally {
IOUtils.closeQuietly(wr);
}
InputStream is = null;
Document xmlDoc;
try {
// Get Response
is = connection.getInputStream();
xmlDoc = loadXMLFromInputStream(is);
} catch (IOException e) {
throw new EngineException("Unable to spot Entities with" + "Dbpedia Spotlight Annotate RESTful Serice running at " + spotlightUrl, e);
} catch (SAXException e) {
throw new EngineException("Unable to parse Response from " + "Dbpedia Spotlight Annotate RESTful Serice running at " + spotlightUrl, e);
} finally {
IOUtils.closeQuietly(is);
}
return Annotation.parseAnnotations(xmlDoc);
}
use of org.apache.stanbol.enhancer.servicesapi.EngineException 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);
}
}
Aggregations