/** * @generated * @param jcas JCas to which this Feature Structure belongs * @param begin offset to the begin spot in the SofA * @param end offset to the end spot in the SofA */ public WordLemma(JCas jcas, int begin, int end) { super(jcas); setBegin(begin); setEnd(end); readObject(); }
@Test public void testAddsLemmaToExistingLemmas() throws UIMAException, ResourceInitializationException { jCas.setDocumentText("Is this working?"); final WordToken s = new WordToken(jCas); s.setBegin(jCas.getDocumentText().indexOf("working")); s.setEnd(s.getBegin() + "working".length()); s.setPartOfSpeech("VERB"); s.setLemmas(new FSArray(jCas, 1)); final WordLemma existingLemma = new WordLemma(jCas); existingLemma.setPartOfSpeech("existing"); existingLemma.setLemmaForm("existing"); s.setLemmas(0, existingLemma); s.addToIndexes(); processJCas("wordnet", wordnetErd); final List<WordToken> out = new ArrayList<>(JCasUtil.select(jCas, WordToken.class)); assertEquals(existingLemma, out.get(0).getLemmas(0)); assertEquals("work", out.get(0).getLemmas(1).getLemmaForm()); } }
private WordToken createWordToken(Sentence sentence, int i) { WordToken wordToken = new WordToken(jCas); wordToken.setBegin(sentence.startOffsets()[i]); wordToken.setEnd(sentence.endOffsets()[i]); Option<String[]> tags = sentence.tags(); if (tags.isDefined()) { wordToken.setPartOfSpeech(tags.get()[i]); } Option<String[]> lemmas = sentence.lemmas(); if (lemmas.isDefined() && !MISSING_VALUE.equals(lemmas.get()[i])) { wordToken.setLemmas(new FSArray(jCas, 1)); WordLemma lemma = new WordLemma(jCas); lemma.setLemmaForm(lemmas.get()[i]); if (tags.isDefined()) { lemma.setPartOfSpeech(tags.get()[i]); } lemma.addToIndexes(); wordToken.setLemmas(0, lemma); } else { wordToken.setLemmas(new FSArray(jCas, 0)); } wordToken.addToIndexes(); return wordToken; }
jumps.setEnd(8 + "jumps".length()); jumps.setPartOfSpeech("VB"); final WordLemma jumpLemma = new WordLemma(jCas); jumpLemma.setLemmaForm("jump"); jumps.setLemmas(new FSArray(jCas, 1)); jumps.setLemmas(0, jumpLemma);
private String getLemma(final WordToken token) { final FSArray array = token.getLemmas(); if (array == null || array.size() == 0) { return token.getCoveredText().toLowerCase(); } else { return ((WordLemma) array.get(0)).getLemmaForm(); } }
/** * @generated * @param jcas JCas to which this Feature Structure belongs */ public WordLemma(JCas jcas) { super(jcas); readObject(); }
private WordToken createWordToken(Sentence sentence, int i) { WordToken wordToken = new WordToken(jCas); wordToken.setBegin(sentence.startOffsets()[i]); wordToken.setEnd(sentence.endOffsets()[i]); Option<String[]> tags = sentence.tags(); if (tags.isDefined()) { wordToken.setPartOfSpeech(tags.get()[i]); } Option<String[]> lemmas = sentence.lemmas(); if (lemmas.isDefined() && !MISSING_VALUE.equals(lemmas.get()[i])) { wordToken.setLemmas(new FSArray(jCas, 1)); WordLemma lemma = new WordLemma(jCas); lemma.setLemmaForm(lemmas.get()[i]); if (tags.isDefined()) { lemma.setPartOfSpeech(tags.get()[i]); } lemma.addToIndexes(); wordToken.setLemmas(0, lemma); } else { wordToken.setLemmas(new FSArray(jCas, 0)); } wordToken.addToIndexes(); return wordToken; }
private String getLemma(final WordToken token) { final FSArray array = token.getLemmas(); if (array == null || array.size() == 0) { return token.getCoveredText().toLowerCase(); } else { return ((WordLemma) array.get(0)).getLemmaForm(); } }
/** * Internal - constructor used by generator * * @generated * @param addr low level Feature Structure reference * @param type the type of this Feature Structure */ public WordLemma(int addr, TOP_Type type) { super(addr, type); readObject(); }
/** * Save words. * * @param pattern the pattern * @return the DB object */ private List<Object> saveWords(final Pattern pattern) { final List<Object> list = new ArrayList<>(); for (int i = 0; i < pattern.getWords().size(); i++) { final WordToken w = pattern.getWords(i); final Document o = new Document().append("text", w.getCoveredText()).append("pos", w.getPartOfSpeech()); if (w.getLemmas() != null && w.getLemmas().size() >= 1) { o.put("lemma", w.getLemmas(0).getLemmaForm()); } list.add(o); } return list; }
/** * @generated * @param jcas JCas to which this Feature Structure belongs * @param begin offset to the begin spot in the SofA * @param end offset to the end spot in the SofA */ public WordLemma(JCas jcas, int begin, int end) { super(jcas); setBegin(begin); setEnd(end); readObject(); }
/** * @generated * @param jcas JCas to which this Feature Structure belongs */ public WordLemma(JCas jcas) { super(jcas); readObject(); }
@Test public void testAddsLemma() throws UIMAException, ResourceInitializationException { jCas.setDocumentText("Is this working?"); final WordToken t = new WordToken(jCas); t.setBegin(jCas.getDocumentText().indexOf("working")); t.setEnd(t.getBegin() + "working".length()); t.setPartOfSpeech("VERB"); t.addToIndexes(); processJCas("wordnet", wordnetErd); final List<WordToken> out = new ArrayList<>(JCasUtil.select(jCas, WordToken.class)); assertEquals("work", out.get(0).getLemmas(0).getLemmaForm()); }
/** * Internal - constructor used by generator * * @generated * @param addr low level Feature Structure reference * @param type the type of this Feature Structure */ public WordLemma(int addr, TOP_Type type) { super(addr, type); readObject(); }