/** * @deprecated Use a {@link SentenceDetectorFactory} to extend * SentenceDetector functionality. */ public SentenceDetectorME(SentenceModel model, Factory factory) { this.model = model.getMaxentModel(); // if the model has custom EOS characters set, use this to get the context // generator and the EOS scanner; otherwise use language-specific defaults char[] customEOSCharacters = model.getEosCharacters(); if (customEOSCharacters == null) { cgen = factory.createSentenceContextGenerator(model.getLanguage(), getAbbreviations(model.getAbbreviations())); scanner = factory.createEndOfSentenceScanner(model.getLanguage()); } else { cgen = factory.createSentenceContextGenerator( getAbbreviations(model.getAbbreviations()), customEOSCharacters); scanner = factory.createEndOfSentenceScanner(customEOSCharacters); } useTokenEnd = model.useTokenEnd(); }
private SentenceDetector getSentenceDetector(String language) { try { SentenceModel model = openNLP.getSentenceModel(language); if(model != null) { log.debug("Sentence Detection Model {} for lanugage '{}' version: {}", new Object[]{model.getClass().getSimpleName(), model.getLanguage(), model.getVersion() != null ? model.getVersion() : "undefined"}); return new SentenceDetectorME(model); } } catch (Exception e) { } log.debug("Sentence Detection Model for Language '{}' not available.", language); return null; } private POSTagger getPOSTagger(String language) {
log.debug("Sentence Detection Model {} for lanugage '{}' version: {}", new Object[]{model.getClass().getSimpleName(), model.getLanguage(), model.getVersion() != null ? model.getVersion() : "undefined"}); return new SentenceDetectorME(model);
/** * @deprecated Use a {@link SentenceDetectorFactory} to extend * SentenceDetector functionality. */ public SentenceDetectorME(SentenceModel model, Factory factory) { this.model = model.getMaxentModel(); // if the model has custom EOS characters set, use this to get the context // generator and the EOS scanner; otherwise use language-specific defaults char[] customEOSCharacters = model.getEosCharacters(); if (customEOSCharacters == null) { cgen = factory.createSentenceContextGenerator(model.getLanguage(), getAbbreviations(model.getAbbreviations())); scanner = factory.createEndOfSentenceScanner(model.getLanguage()); } else { cgen = factory.createSentenceContextGenerator( getAbbreviations(model.getAbbreviations()), customEOSCharacters); scanner = factory.createEndOfSentenceScanner(customEOSCharacters); } useTokenEnd = model.useTokenEnd(); }
/** * @deprecated Use a {@link SentenceDetectorFactory} to extend * SentenceDetector functionality. */ public SentenceDetectorME(SentenceModel model, Factory factory) { this.model = model.getMaxentModel(); // if the model has custom EOS characters set, use this to get the context // generator and the EOS scanner; otherwise use language-specific defaults char[] customEOSCharacters = model.getEosCharacters(); if (customEOSCharacters == null) { cgen = factory.createSentenceContextGenerator(model.getLanguage(), getAbbreviations(model.getAbbreviations())); scanner = factory.createEndOfSentenceScanner(model.getLanguage()); } else { cgen = factory.createSentenceContextGenerator( getAbbreviations(model.getAbbreviations()), customEOSCharacters); scanner = factory.createEndOfSentenceScanner(customEOSCharacters); } useTokenEnd = model.useTokenEnd(); }
StandardCharsets.UTF_8)), factory, mlParams); Assert.assertEquals("eng", sentdetectModel.getLanguage());