private void logChunks(AnalysedText at){ Iterator<Span> it = at.getEnclosed(EnumSet.of(SpanTypeEnum.Sentence, SpanTypeEnum.Chunk)); while(it.hasNext()){ Span span = it.next(); if(span.getType() == SpanTypeEnum.Chunk){ log.trace(" > {} {}",span,span.getSpan()); } else { log.trace(" > {}",span); } for(Value<PhraseTag> value : span.getAnnotations(PHRASE_ANNOTATION)){ log.trace(" - {}",value); } } }
String currentTokenString = currentToken.getSpan().toLowerCase(); String previousTokenString = previousToken.getSpan().toLowerCase(); concatTokens = new StringBuilder(); concatTokens.append(previousTokenString); String nextTokenString = nextToken.getSpan().toLowerCase(); concatTokens = new StringBuilder(); concatTokens.append(currentTokenString);
&& langDeterminerSet.contains(token.getSpan().toLowerCase())) { hasGoodDeterminer = true;
String nounPhraseText = nounPhrase.getChunk().getSpan().toLowerCase(); int classStart = 0; int classEnd = 0;
/** * Gets an Entity from the configured {@link Site} based on the NER text and type. * * @param ner * @param language * @return * @throws EngineException */ private Entity lookupEntity(Span ner, String language) throws EngineException { Site site = getReferencedSite(); FieldQueryFactory queryFactory = site == null ? entityHub.getQueryFactory() : site.getQueryFactory(); FieldQuery query = queryFactory.createFieldQuery(); Constraint labelConstraint; String namedEntityLabel = ner.getSpan(); labelConstraint = new TextConstraint(namedEntityLabel, false, language, null); query.setConstraint(RDFS_LABEL.getUnicodeString(), labelConstraint); query.setConstraint(RDF_TYPE.getUnicodeString(), new ReferenceConstraint(ner.getAnnotation(NlpAnnotations.NER_ANNOTATION).value().getType() .getUnicodeString())); query.setLimit(1); QueryResultList<Entity> results = site == null ? // if site is NULL entityHub.findEntities(query) : // use the Entityhub site.findEntities(query); // else the referenced site if (results.isEmpty()) return null; // We set the limit to 1 so if it found anything it should contain just 1 entry return results.iterator().next(); }
new PlainLiteralImpl(span.getSpan(), lang))); metadata.add(new TripleImpl(ta, ENHANCER_START, lf.createTypedLiteral(span.getStart()))); metadata.add(new TripleImpl(ta, ENHANCER_SELECTION_CONTEXT, new PlainLiteralImpl(context == null ? getDefaultSelectionContext(at.getSpan(), span.getSpan(), span.getStart()) : context.getSpan(), lang)));
graph.add(new TripleImpl(segment, RDF_TYPE, StringOntology.OffsetBasedString.getUri())); graph.add(new TripleImpl(segment, StringOntology.anchorOf.getUri(), new PlainLiteralImpl(span.getSpan(),language))); graph.add(new TripleImpl(segment, StringOntology.beginIndex.getUri(), lf.createTypedLiteral(span.getStart())));
graph.add(new TripleImpl(segment, RDF_TYPE, StringOntology.OffsetBasedString.getUri())); graph.add(new TripleImpl(segment, StringOntology.anchorOf.getUri(), new PlainLiteralImpl(span.getSpan(),language))); graph.add(new TripleImpl(segment, StringOntology.beginIndex.getUri(), lf.createTypedLiteral(span.getStart())));