FeatureMap features = gateDoc.getFeatures(); String originalContent = (String) features.get(GateConstants.ORIGINAL_DOCUMENT_CONTENT_FEATURE_NAME); int length = originalContent.length(); TextualDocumentFormat tdf = new TextualDocumentFormat(); try { tdf.annotateParagraphs(gateDoc,0, length,null); } catch (DocumentFormatException e) { e.printStackTrace(); } AnnotationSet paragraphs = gateDoc.getAnnotations().get("paragraph"); Iterator it = paragraphs.iterator(); Annotation currAnnot; SortedAnnotationList sortedParagraphs = new SortedAnnotationList(); while (it.hasNext()) { currAnnot = (Annotation) it.next(); sortedParagraphs.addSortedExclusive(currAnnot); } // while StringBuffer editableContent = new StringBuffer(originalContent); System.out.println("Number of Paragraphs - "+paragraphs.size()); for(Annotation paragraph:paragraphs){ long start = paragraph.getStartNode().getOffset().longValue(); long end = paragraph.getEndNode().getOffset().longValue(); String paraText=editableContent.substring((int) start, (int) end); System.out.println(paraText); }
@Override protected Annotation[] getAnnotsToProcess(GATEDocument gateDocument) throws IndexException { Document document = gateDocument.getDocument(); Annotation[] semanticAnnots; AnnotationSet semAnnSet = (indexConfig.getSemanticAnnotationSetName() == null || indexConfig.getSemanticAnnotationSetName().length() == 0) ? document.getAnnotations() : document.getAnnotations(indexConfig.getSemanticAnnotationSetName()); if(semAnnSet.size() > 0){ AnnotationSet semAnns = null; synchronized(semAnnSet) { semAnns = semAnnSet.get(annotationHelpers.keySet()); } semanticAnnots = semAnns.toArray(new Annotation[semAnns.size()]); Arrays.sort(semanticAnnots, offsetComparator); } else { semanticAnnots = new Annotation[0]; } return semanticAnnots; }
if(sentencesAS != null && sentencesAS.size() > 0 && tokensAS != null && tokensAS.size() > 0){ long startTime = System.currentTimeMillis(); fireStatusChanged("POS tagging " + document.getName()); Annotation currentToken = tokensIter.next(); int sentIndex = 0; int sentCnt = sentencesAS.size(); while(sentencesIter.hasNext()){ Annotation currentSentence = sentencesIter.next();
if(annotsToTransfer == null || annotsToTransfer.size() == 0) return;
this.textSentences = new Sentence[sentenceAnnotations.size()]; Annotation[] sentenceArray = sentenceAnnotations.toArray(new Annotation[sentenceAnnotations.size()]); Arrays.sort(sentenceArray,ANNOTATION_OFFSET_COMPARATOR); this.quotedText = new Quote[sentQuotes.size()]; Annotation[] quotesArray = sentQuotes.toArray(new Annotation[sentQuotes.size()]); Arrays.sort(quotesArray,ANNOTATION_OFFSET_COMPARATOR); this.pleonasticIt = new Annotation[plaonasticSet.size()]; Annotation[] quotesArray = plaonasticSet.toArray(new Annotation[plaonasticSet.size()]); Arrays.sort(quotesArray,ANNOTATION_OFFSET_COMPARATOR);
.getStartNode().getOffset(), anaphor.getEndNode().getOffset()); if(existing.size() > 0) {
document.getAnnotations(outputASName); AnnotationSet annotations = outputAS.get(outputAnnotationType); if(annotations == null || annotations.size() == 0) {
int tokenSize = tokens.size(); int tokensProcessed = 0; int lastReport = 0;
if(tokens == null || tokens.size() < 1) { if(failOnMissingInputAnnotations) {