/** * @param aView * @return */ private String getLemmasAsStringSequence(JCas aView) { String result=""; // get all Lemmas Collection<Lemma> lemmas = JCasUtil.select(aView, Lemma.class); for(Lemma cur : lemmas ) { result += cur.getValue() + " "; } return result; }
Lemma outLemma = new Lemma(aJCas, outToken.getBegin(), outToken.getEnd()); outLemma.setValue(lemma.get(i)); outLemma.addToIndexes(); outToken.setLemma(outLemma);
String indexEntry = lemma.getValue().toLowerCase(); if (!lemmaIndex.containsKey(indexEntry)) lemmaIndex.put(indexEntry, new LinkedList<Lemma>()); if (lemmaIndex.containsKey(entry[0].toLowerCase())) { for (Lemma lemma : lemmaIndex.get(entry[0].toLowerCase())) { int begin = lemma.getBegin(); int end = lemma.getEnd(); Lemma nextLemma; for (int i = 1; i < entry.length; i++) { nextLemma = JCasUtil.selectFollowing(Lemma.class, lemma, 1).get(0); if (nextLemma.getValue().equalsIgnoreCase(entry[i].toLowerCase())) { end = nextLemma.getEnd(); } else { end = -1;
types.add(lemma.getValue().toLowerCase()); tokens.add(lemma.getCoveredText().toLowerCase()); System.out.println("Couldn't add token: " + lemma.getCoveredText());
tokenAnnot.setEnd(end); tokenAnnot.addToIndexes(); Lemma lemmaAnnot = new Lemma(jcas1); lemmaAnnot.setBegin(begin); lemmaAnnot.setEnd(end); lemmaAnnot.setValue(thisTok.toLowerCase()); // not really lemma. just lc(token). just as an example. lemmaAnnot.addToIndexes();
for (Lemma lemma : JCasUtil.selectCovered(getJCas(), Lemma.class, token.getBegin(), token.getEnd())) { if (lemma.getBegin() == token.getBegin() && lemma.getEnd() == token.getEnd()) { if (lemma.getValue().equals(this.lemma)) { duplicate = true; break; Lemma lemma = new Lemma(getJCas(), token.getBegin(), token.getEnd()); lemma.setValue(this.lemma); lemma.addToIndexes(); token.setLemma(lemma); token.addToIndexes();
lemmata.add(token.getLemma().getValue()); lemmata.add(lemma.getValue()); toRemove.add(lemma); if (!lemmata.isEmpty()) { if (lemma == null) { lemma = new Lemma(aJCas); lemma.setValue(StringUtils.join(lemmata, " ")); lemma.removeFromIndexes(); lemma.setBegin(token.getBegin()); lemma.setEnd(token.getEnd()); lemma.addToIndexes();
Lemma lemma = new Lemma(jcas, token.getBegin(), token.getEnd()); lemma.setValue(lemmaString); lemma.addToIndexes(); oldLemma.removeFromIndexes();
@Override public void token(Token aToken, String aPos, String aLemma) { synchronized (cas) { // Add the Part of Speech if (writePos && aPos != null) { Type posTag = posMappingProvider.getTagType(aPos); POS posAnno = (POS) cas.createAnnotation(posTag, aToken.getBegin(), aToken.getEnd()); posAnno.setPosValue(aPos.intern()); POSUtils.assignCoarseValue(posAnno); aToken.setPos(posAnno); pos[count.get()] = posAnno; } // Add the lemma if (writeLemma && aLemma != null) { Lemma lemmaAnno = new Lemma(aJCas, aToken.getBegin(), aToken.getEnd()); lemmaAnno.setValue(aLemma.intern()); aToken.setLemma(lemmaAnno); lemma[count.get()] = lemmaAnno; } count.getAndIncrement(); } } });
private Annotation getAnnotationObject(JCas aJCas, String viewName, String type, Integer[] index) throws Exception{ if (type.matches(txpAnn.token)) return new Token(aJCas.getView(viewName)); if (type.matches(txpAnn.lemma)) return new Lemma(aJCas.getView(viewName)); if (type.matches(txpAnn.pos)) return getAnnotationObject(aJCas, viewName, txpAnn.getAnnotation(type).get(index), POS.class); if (type.matches(txpAnn.sentence)) return new Sentence(aJCas.getView(viewName)); if (type.matches(txpAnn.ne)) return getAnnotationObject(aJCas, viewName, txpAnn.getNEtype(index), NamedEntity.class); return new Annotation(aJCas.getView(viewName)); }
lemma[i].addToIndexes();
a.setEnd(position[1]); if (type.matches(txpAnn.lemma)) { ((Lemma) a).setValue(annotation.get(position)); } else { if (type.matches(txpAnn.ne)) {
private void addAlignmentLinkT2H(JCas aJCas, LexicalRule<?> rule, Lemma[] tLemmasToBeMatched, Lemma[] hSideTarget) throws AlignmentComponentException logger.debug("addAlignmentLinkT2H: got request of adding links for rule { " + rule.getLLemma() + " => " + rule.getRLemma() + " } on H-SOFA " + hSideTarget[0].getBegin() + " <-> " + hSideTarget[hSideTarget.length -1].getEnd()); int toBegin = hSideTarget[0].getBegin(); int toEnd = hSideTarget[hSideTarget.length - 1].getEnd(); int fromBegin = tLemmasToBeMatched[matchLoc].getBegin(); int fromEnd = tLemmasToBeMatched[matchLoc + ruleLeft.length -1].getEnd();
boolean duplicate = false; for (Lemma lemma : JCasUtil.selectCovered(getJCas(), Lemma.class, token.getBegin(), token.getEnd())) { if (lemma.getBegin() == token.getBegin() && lemma.getEnd() == token.getEnd()) { if (lemma.getValue().equals(this.lemma)) { duplicate = true; break; Lemma lemma = new Lemma(getJCas(), token.getBegin(), token.getEnd()); lemma.setValue(this.lemma); lemma.addToIndexes(); token.setLemma(lemma); token.addToIndexes();
private void convertLemma(JCas aJCas, TextCorpus aCorpusData, Map<String, Token> aTokens) { if (aCorpusData.getLemmasLayer() == null) { return; } for (int i = 0; i < aCorpusData.getLemmasLayer().size(); i++) { eu.clarin.weblicht.wlfxb.tc.api.Token[] lemmaTokens = aCorpusData.getLemmasLayer() .getTokens(aCorpusData.getLemmasLayer().getLemma(i)); String value = aCorpusData.getLemmasLayer().getLemma(i).getString(); Lemma outLemma = new Lemma(aJCas); outLemma.setBegin(aTokens.get(lemmaTokens[0].getID()).getBegin()); outLemma.setEnd(aTokens.get(lemmaTokens[0].getID()).getEnd()); outLemma.setValue(value); outLemma.addToIndexes(); // Set the lemma to the token aTokens.get(lemmaTokens[0].getID()).setLemma(outLemma); } }
types.add(lemma.getValue().toLowerCase()); tokens.add(lemma.getCoveredText().toLowerCase()); System.out.println("Couldn't add token: " + lemma.getCoveredText());
@Override public void process(JCas aJCas) throws AnalysisEngineProcessException { for (Lemma lemma : select(aJCas, Lemma.class)) { Token t = selectSingleAt(aJCas, Token.class, lemma.getBegin(), lemma.getEnd()); assert t.getLemma() == lemma; } for (Stem stem : select(aJCas, Stem.class)) { Token t = selectSingleAt(aJCas, Token.class, stem.getBegin(), stem.getEnd()); assert t.getStem() == stem; } for (MorphologicalFeatures morph : select(aJCas, MorphologicalFeatures.class)) { Token t = selectSingleAt(aJCas, Token.class, morph.getBegin(), morph.getEnd()); assert t.getMorph() == morph; } for (POS pos : select(aJCas, POS.class)) { Token t = selectSingleAt(aJCas, Token.class, pos.getBegin(), pos.getEnd()); assert t.getPos() == pos; } for (Dependency dep : select(aJCas, Dependency.class)) { assert dep.getBegin() == dep.getDependent().getBegin(); assert dep.getEnd() == dep.getDependent().getEnd(); } } }
Lemma outLemma = new Lemma(aJCas, outToken.getBegin(), outToken.getEnd()); outLemma.setValue(lemma.get(i)); outLemma.addToIndexes(); outToken.setLemma(outLemma);